N: Kees Cook
E: kees@outflux.net
-W: http://outflux.net/
-P: 1024D/17063E6D 9FA3 C49C 23C9 D1BC 2E30 1975 1FFF 4BA9 1706 3E6D
-D: Minor updates to SCSI types, added /proc/pid/maps protection
+E: kees@ubuntu.com
+E: keescook@chromium.org
+W: http://outflux.net/blog/
+P: 4096R/DC6DC026 A5C3 F68F 229D D60F 723E 6E13 8972 F4DF DC6D C026
+D: Various security things, bug fixes, and documentation.
S: (ask for current address)
+S: Portland, Oregon
S: USA
N: Robin Cornelius
when a discarded area is read the discard_zeroes_data
parameter will be set to one. Otherwise it will be 0 and
the result of reading a discarded area is undefined.
-What: /sys/block/<disk>/alias
-Date: Aug 2011
-Contact: Nao Nishijima <nao.nishijima.xt@hitachi.com>
-Description:
- A raw device name of a disk does not always point a same disk
- each boot-up time. Therefore, users have to use persistent
- device names, which udev creates when the kernel finds a disk,
- instead of raw device name. However, kernel doesn't show those
- persistent names on its messages (e.g. dmesg).
- This file can store an alias of the disk and it would be
- appeared in kernel messages if it is set. A disk can have an
- alias which length is up to 255bytes. Users can use alphabets,
- numbers, "-" and "_" in alias name. This file is writeonce.
$ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_create
-rollback_snap
-
- Rolls back data to the specified snapshot. This goes over the entire
- list of rados blocks and sends a rollback command to each.
-
- $ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_rollback
-
snap_*
A directory per each snapshot
</para>
<itemizedlist>
+<listitem><para>
+<varname>const char *name</varname>: Optional. Set this to help identify
+the memory region, it will show up in the corresponding sysfs node.
+</para></listitem>
+
<listitem><para>
<varname>int memtype</varname>: Required if the mapping is used. Set this to
<varname>UIO_MEM_PHYS</varname> if you you have physical memory on your
</itemizedlist>
<para>
-Please do not touch the <varname>kobj</varname> element of
+Please do not touch the <varname>map</varname> element of
<varname>struct uio_mem</varname>! It is used by the UIO framework
to set up sysfs files for this mapping. Simply leave it alone.
</para>
"SCSI support" in your kernel configuration to be able to use SCSI
tape drives with your Smart Array 5xxx controller.
-Additionally, note that the driver will not engage the SCSI core at init
-time. The driver must be directed to dynamically engage the SCSI core via
-the /proc filesystem entry which the "block" side of the driver creates as
-/proc/driver/cciss/cciss* at runtime. This is because at driver init time,
-the SCSI core may not yet be initialized (because the driver is a block
-driver) and attempting to register it with the SCSI core in such a case
-would cause a hang. This is best done via an initialization script
-(typically in /etc/init.d, but could vary depending on distribution).
+Additionally, note that the driver will engage the SCSI core at init
+time if any tape drives or medium changers are detected. The driver may
+also be directed to dynamically engage the SCSI core via the /proc filesystem
+entry which the "block" side of the driver creates as
+/proc/driver/cciss/cciss* at runtime. This is best done via a script.
+
For example:
for x in /proc/driver/cciss/cciss[0-9]*
- oom-killer disable knob and oom-notifier
- Root cgroup has no limit controls.
- Kernel memory and Hugepages are not under control yet. We just manage
- pages on LRU. To add more controls, we have to take care of performance.
+ Kernel memory support is work in progress, and the current version provides
+ basically functionality. (See Section 2.7)
Brief summary of control files.
memory.oom_control # set/show oom controls.
memory.numa_stat # show the number of memory usage per numa node
+ memory.kmem.tcp.limit_in_bytes # set/show hard limit for tcp buf memory
+ memory.kmem.tcp.usage_in_bytes # show current tcp buf memory allocation
+
1. History
The memory controller has a long history. A request for comments for the memory
per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
zone->lru_lock, it has no lock of its own.
+2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+
+With the Kernel memory extension, the Memory Controller is able to limit
+the amount of kernel memory used by the system. Kernel memory is fundamentally
+different than user memory, since it can't be swapped out, which makes it
+possible to DoS the system by consuming too much of this precious resource.
+
+Kernel memory limits are not imposed for the root cgroup. Usage for the root
+cgroup may or may not be accounted.
+
+Currently no soft limit is implemented for kernel memory. It is future work
+to trigger slab reclaim when those limits are reached.
+
+2.7.1 Current Kernel Memory resources accounted
+
+* sockets memory pressure: some sockets protocols have memory pressure
+thresholds. The Memory Controller allows them to be controlled individually
+per cgroup, instead of globally.
+
+* tcp memory pressure: sockets memory pressure for the tcp protocol.
+
3. User Interface
0. Configuration
--- /dev/null
+Network priority cgroup
+-------------------------
+
+The Network priority cgroup provides an interface to allow an administrator to
+dynamically set the priority of network traffic generated by various
+applications
+
+Nominally, an application would set the priority of its traffic via the
+SO_PRIORITY socket option. This however, is not always possible because:
+
+1) The application may not have been coded to set this value
+2) The priority of application traffic is often a site-specific administrative
+ decision rather than an application defined one.
+
+This cgroup allows an administrator to assign a process to a group which defines
+the priority of egress traffic on a given interface. Network priority groups can
+be created by first mounting the cgroup filesystem.
+
+# mount -t cgroup -onet_prio none /sys/fs/cgroup/net_prio
+
+With the above step, the initial group acting as the parent accounting group
+becomes visible at '/sys/fs/cgroup/net_prio'. This group includes all tasks in
+the system. '/sys/fs/cgroup/net_prio/tasks' lists the tasks in this cgroup.
+
+Each net_prio cgroup contains two files that are subsystem specific
+
+net_prio.prioidx
+This file is read-only, and is simply informative. It contains a unique integer
+value that the kernel uses as an internal representation of this cgroup.
+
+net_prio.ifpriomap
+This file contains a map of the priorities assigned to traffic originating from
+processes in this group and egressing the system on various interfaces. It
+contains a list of tuples in the form <ifname priority>. Contents of this file
+can be modified by echoing a string into the file using the same tuple format.
+for example:
+
+echo "eth0 5" > /sys/fs/cgroups/net_prio/iscsi/net_prio.ifpriomap
+
+This command would force any traffic originating from processes belonging to the
+iscsi net_prio cgroup and egressing on interface eth0 to have the priority of
+said traffic set to the value 5. The parent accounting group also has a
+writeable 'net_prio.ifpriomap' file that can be used to set a system default
+priority.
+
+Priorities are set immediately prior to queueing a frame to the device
+queueing discipline (qdisc) so priorities will be assigned prior to the hardware
+queue selection being made.
+
+One usage for the net_prio cgroup is with mqprio qdisc allowing application
+traffic to be steered to hardware/driver based traffic classes. These mappings
+can then be managed by administrators or other networking protocols such as
+DCBX.
--- /dev/null
+* Calxeda Highbank 10Gb XGMAC Ethernet
+
+Required properties:
+- compatible : Should be "calxeda,hb-xgmac"
+- reg : Address and length of the register set for the device
+- interrupts : Should contain 3 xgmac interrupts. The 1st is main interrupt.
+ The 2nd is pwr mgt interrupt. The 3rd is low power state interrupt.
+
+Example:
+
+ethernet@fff50000 {
+ compatible = "calxeda,hb-xgmac";
+ reg = <0xfff50000 0x1000>;
+ interrupts = <0 77 4 0 78 4 0 79 4>;
+};
--- /dev/null
+Memory mapped Bosch CC770 and Intel AN82527 CAN controller
+
+Note: The CC770 is a CAN controller from Bosch, which is 100%
+compatible with the old AN82527 from Intel, but with "bugs" being fixed.
+
+Required properties:
+
+- compatible : should be "bosch,cc770" for the CC770 and "intc,82527"
+ for the AN82527.
+
+- reg : should specify the chip select, address offset and size required
+ to map the registers of the controller. The size is usually 0x80.
+
+- interrupts : property with a value describing the interrupt source
+ (number and sensitivity) required for the controller.
+
+Optional properties:
+
+- bosch,external-clock-frequency : frequency of the external oscillator
+ clock in Hz. Note that the internal clock frequency used by the
+ controller is half of that value. If not specified, a default
+ value of 16000000 (16 MHz) is used.
+
+- bosch,clock-out-frequency : slock frequency in Hz on the CLKOUT pin.
+ If not specified or if the specified value is 0, the CLKOUT pin
+ will be disabled.
+
+- bosch,slew-rate : slew rate of the CLKOUT signal. If not specified,
+ a resonable value will be calculated.
+
+- bosch,disconnect-rx0-input : see data sheet.
+
+- bosch,disconnect-rx1-input : see data sheet.
+
+- bosch,disconnect-tx1-output : see data sheet.
+
+- bosch,polarity-dominant : see data sheet.
+
+- bosch,divide-memory-clock : see data sheet.
+
+- bosch,iso-low-speed-mux : see data sheet.
+
+For further information, please have a look to the CC770 or AN82527.
+
+Examples:
+
+can@3,100 {
+ compatible = "bosch,cc770";
+ reg = <3 0x100 0x80>;
+ interrupts = <2 0>;
+ interrupt-parent = <&mpic>;
+ bosch,external-clock-frequency = <16000000>;
+};
ramtron Ramtron International
samsung Samsung Semiconductor
schindler Schindler
+sil Silicon Image
simtek
sirf SiRF Technology, Inc.
stericsson ST-Ericsson
Userspace tools for creating and manipulating Btrfs file systems are
available from the git repository at the following location:
- http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git
- git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git
+ http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs.git
These include the following tools:
The I2C protocol knows about two kinds of device addresses: normal 7 bit
addresses, and an extended set of 10 bit addresses. The sets of addresses
do not intersect: the 7 bit address 0x10 is not the same as the 10 bit
-address 0x10 (though a single device could respond to both of them). You
-select a 10 bit address by adding an extra byte after the address
-byte:
- S Addr7 Rd/Wr ....
-becomes
- S 11110 Addr10 Rd/Wr
-S is the start bit, Rd/Wr the read/write bit, and if you count the number
-of bits, you will see the there are 8 after the S bit for 7 bit addresses,
-and 16 after the S bit for 10 bit addresses.
+address 0x10 (though a single device could respond to both of them).
-WARNING! The current 10 bit address support is EXPERIMENTAL. There are
-several places in the code that will cause SEVERE PROBLEMS with 10 bit
-addresses, even though there is some basic handling and hooks. Also,
-almost no supported adapter handles the 10 bit addresses correctly.
+I2C messages to and from 10-bit address devices have a different format.
+See the I2C specification for the details.
-As soon as a real 10 bit address device is spotted 'in the wild', we
-can and will add proper support. Right now, 10 bit address devices
-are defined by the I2C protocol, but we have never seen a single device
-which supports them.
+The current 10 bit address support is minimal. It should work, however
+you can expect some problems along the way:
+* Not all bus drivers support 10-bit addresses. Some don't because the
+ hardware doesn't support them (SMBus doesn't require 10-bit address
+ support for example), some don't because nobody bothered adding the
+ code (or it's there but not working properly.) Software implementation
+ (i2c-algo-bit) is known to work.
+* Some optional features do not support 10-bit addresses. This is the
+ case of automatic detection and instantiation of devices by their,
+ drivers, for example.
+* Many user-space packages (for example i2c-tools) lack support for
+ 10-bit addresses.
+
+Note that 10-bit address devices are still pretty rare, so the limitations
+listed above could stay for a long time, maybe even forever if nobody
+needs them to be fixed.
CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler.
- 1: only for 32-bit processes
- 2: only for 64-bit processes
+ 32: only for 32-bit processes
+ 64: only for 64-bit processes
on: enable for both 32- and 64-bit processes
off: disable for both 32- and 64-bit processes
- amd_iommu= [HW,X86-84]
+ amd_iommu= [HW,X86-64]
Pass parameters to the AMD IOMMU driver in the system.
Possible values are:
fullflush - enable flushing of IO/TLB entries when
- The Linux Near Field Communication (NFS) subsystem.
olympic.txt
- IBM PCI Pit/Pit-Phy/Olympic Token Ring driver info.
+openvswitch.txt
+ - Open vSwitch developer documentation.
operstates.txt
- Overview of network interface operational states.
packet_mmap.txt
0 - All debug output disabled
1 - Enable messages related to routing / flooding / broadcasting
-2 - Enable route or tt entry added / changed / deleted
-3 - Enable all messages
+2 - Enable messages related to route added / changed / deleted
+4 - Enable messages related to translation table operations
+7 - Enable all messages
The debug output can be changed at runtime using the file
/sys/class/net/bat0/mesh/log_level. e.g.
# echo 2 > /sys/class/net/bat0/mesh/log_level
-will enable debug messages for when routes or TTs change.
+will enable debug messages for when routes change.
BATCTL
The parameters are as follows:
+active_slave
+
+ Specifies the new active slave for modes that support it
+ (active-backup, balance-alb and balance-tlb). Possible values
+ are the name of any currently enslaved interface, or an empty
+ string. If a name is given, the slave and its link must be up in order
+ to be selected as the new active slave. If an empty string is
+ specified, the current active slave is cleared, and a new active
+ slave is selected automatically.
+
+ Note that this is only available through the sysfs interface. No module
+ parameter by this name exists.
+
+ The normal value of this option is the name of the currently
+ active slave, or the empty string if there is no active slave or
+ the current mode does not use an active slave.
+
ad_select
Specifies the 802.3ad aggregation selection logic to use. The
See header include/net/mac802154.h and several drivers in drivers/ieee802154/.
+6LoWPAN Linux implementation
+============================
+
+The IEEE 802.15.4 standard specifies an MTU of 128 bytes, yielding about 80
+octets of actual MAC payload once security is turned on, on a wireless link
+with a link throughput of 250 kbps or less. The 6LoWPAN adaptation format
+[RFC4944] was specified to carry IPv6 datagrams over such constrained links,
+taking into account limited bandwidth, memory, or energy resources that are
+expected in applications such as wireless Sensor Networks. [RFC4944] defines
+a Mesh Addressing header to support sub-IP forwarding, a Fragmentation header
+to support the IPv6 minimum MTU requirement [RFC2460], and stateless header
+compression for IPv6 datagrams (LOWPAN_HC1 and LOWPAN_HC2) to reduce the
+relatively large IPv6 and UDP headers down to (in the best case) several bytes.
+
+In Semptember 2011 the standard update was published - [RFC6282].
+It deprecates HC1 and HC2 compression and defines IPHC encoding format which is
+used in this Linux implementation.
+
+All the code related to 6lowpan you may find in files: net/ieee802154/6lowpan.*
+
+To setup 6lowpan interface you need (busybox release > 1.17.0):
+1. Add IEEE802.15.4 interface and initialize PANid;
+2. Add 6lowpan interface by command like:
+ # ip link add link wpan0 name lowpan0 type lowpan
+3. Set MAC (if needs):
+ # ip link set lowpan0 address de:ad:be:ef:ca:fe:ba:be
+4. Bring up 'lowpan0' interface
metric = 0;
} else
metric = ifr.ifr_metric;
+ printf("The result of SIOCGIFMETRIC is %d\n", metric);
strcpy(ifr.ifr_name, ifname);
if (ioctl(skfd, SIOCGIFMTU, &ifr) < 0)
mtu = 0;
else
mtu = ifr.ifr_mtu;
+ printf("The result of SIOCGIFMTU is %d\n", mtu);
strcpy(ifr.ifr_name, ifname);
if (ioctl(skfd, SIOCGIFDSTADDR, &ifr) < 0) {
default FALSE
min_pmtu - INTEGER
- default 562 - minimum discovered Path MTU
+ default 552 - minimum discovered Path MTU
route/max_size - INTEGER
Maximum number of routes allowed in the kernel. Increase
when using large numbers of interfaces and when communicating
with large numbers of directly-connected peers.
+neigh/default/unres_qlen_bytes - INTEGER
+ The maximum number of bytes which may be used by packets
+ queued for each unresolved address by other network layers.
+ (added in linux 3.3)
+
+neigh/default/unres_qlen - INTEGER
+ The maximum number of packets which may be queued for each
+ unresolved address by other network layers.
+ (deprecated in linux 3.3) : use unres_qlen_bytes instead.
+
mtu_expires - INTEGER
Time, in seconds, that cached PMTU information is kept.
connections. The algorithm "reno" is always available, but
additional choices may be available based on kernel configuration.
Default is set as part of kernel configuration.
+ For passive connections, the listener congestion control choice
+ is inherited.
+ [see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
tcp_cookie_size - INTEGER
Default size of TCP Cookie Transactions (TCPCT) option, that may be
Default: 0 (off)
tcp_max_syn_backlog - INTEGER
- Maximal number of remembered connection requests, which are
- still did not receive an acknowledgment from connecting client.
- Default value is 1024 for systems with more than 128Mb of memory,
- and 128 for low memory machines. If server suffers of overload,
- try to increase this number.
+ Maximal number of remembered connection requests, which have not
+ received an acknowledgment from connecting client.
+ The minimal value is 128 for low memory machines, and it will
+ increase in proportion to the memory of machine.
+ If server suffers from overload, try increasing this number.
tcp_max_tw_buckets - INTEGER
Maximal number of timewait sockets held by system simultaneously.
--- /dev/null
+Open vSwitch datapath developer documentation
+=============================================
+
+The Open vSwitch kernel module allows flexible userspace control over
+flow-level packet processing on selected network devices. It can be
+used to implement a plain Ethernet switch, network device bonding,
+VLAN processing, network access control, flow-based network control,
+and so on.
+
+The kernel module implements multiple "datapaths" (analogous to
+bridges), each of which can have multiple "vports" (analogous to ports
+within a bridge). Each datapath also has associated with it a "flow
+table" that userspace populates with "flows" that map from keys based
+on packet headers and metadata to sets of actions. The most common
+action forwards the packet to another vport; other actions are also
+implemented.
+
+When a packet arrives on a vport, the kernel module processes it by
+extracting its flow key and looking it up in the flow table. If there
+is a matching flow, it executes the associated actions. If there is
+no match, it queues the packet to userspace for processing (as part of
+its processing, userspace will likely set up a flow to handle further
+packets of the same type entirely in-kernel).
+
+
+Flow key compatibility
+----------------------
+
+Network protocols evolve over time. New protocols become important
+and existing protocols lose their prominence. For the Open vSwitch
+kernel module to remain relevant, it must be possible for newer
+versions to parse additional protocols as part of the flow key. It
+might even be desirable, someday, to drop support for parsing
+protocols that have become obsolete. Therefore, the Netlink interface
+to Open vSwitch is designed to allow carefully written userspace
+applications to work with any version of the flow key, past or future.
+
+To support this forward and backward compatibility, whenever the
+kernel module passes a packet to userspace, it also passes along the
+flow key that it parsed from the packet. Userspace then extracts its
+own notion of a flow key from the packet and compares it against the
+kernel-provided version:
+
+ - If userspace's notion of the flow key for the packet matches the
+ kernel's, then nothing special is necessary.
+
+ - If the kernel's flow key includes more fields than the userspace
+ version of the flow key, for example if the kernel decoded IPv6
+ headers but userspace stopped at the Ethernet type (because it
+ does not understand IPv6), then again nothing special is
+ necessary. Userspace can still set up a flow in the usual way,
+ as long as it uses the kernel-provided flow key to do it.
+
+ - If the userspace flow key includes more fields than the
+ kernel's, for example if userspace decoded an IPv6 header but
+ the kernel stopped at the Ethernet type, then userspace can
+ forward the packet manually, without setting up a flow in the
+ kernel. This case is bad for performance because every packet
+ that the kernel considers part of the flow must go to userspace,
+ but the forwarding behavior is correct. (If userspace can
+ determine that the values of the extra fields would not affect
+ forwarding behavior, then it could set up a flow anyway.)
+
+How flow keys evolve over time is important to making this work, so
+the following sections go into detail.
+
+
+Flow key format
+---------------
+
+A flow key is passed over a Netlink socket as a sequence of Netlink
+attributes. Some attributes represent packet metadata, defined as any
+information about a packet that cannot be extracted from the packet
+itself, e.g. the vport on which the packet was received. Most
+attributes, however, are extracted from headers within the packet,
+e.g. source and destination addresses from Ethernet, IP, or TCP
+headers.
+
+The <linux/openvswitch.h> header file defines the exact format of the
+flow key attributes. For informal explanatory purposes here, we write
+them as comma-separated strings, with parentheses indicating arguments
+and nesting. For example, the following could represent a flow key
+corresponding to a TCP packet that arrived on vport 1:
+
+ in_port(1), eth(src=e0:91:f5:21:d0:b2, dst=00:02:e3:0f:80:a4),
+ eth_type(0x0800), ipv4(src=172.16.0.20, dst=172.18.0.52, proto=17, tos=0,
+ frag=no), tcp(src=49163, dst=80)
+
+Often we ellipsize arguments not important to the discussion, e.g.:
+
+ in_port(1), eth(...), eth_type(0x0800), ipv4(...), tcp(...)
+
+
+Basic rule for evolving flow keys
+---------------------------------
+
+Some care is needed to really maintain forward and backward
+compatibility for applications that follow the rules listed under
+"Flow key compatibility" above.
+
+The basic rule is obvious:
+
+ ------------------------------------------------------------------
+ New network protocol support must only supplement existing flow
+ key attributes. It must not change the meaning of already defined
+ flow key attributes.
+ ------------------------------------------------------------------
+
+This rule does have less-obvious consequences so it is worth working
+through a few examples. Suppose, for example, that the kernel module
+did not already implement VLAN parsing. Instead, it just interpreted
+the 802.1Q TPID (0x8100) as the Ethertype then stopped parsing the
+packet. The flow key for any packet with an 802.1Q header would look
+essentially like this, ignoring metadata:
+
+ eth(...), eth_type(0x8100)
+
+Naively, to add VLAN support, it makes sense to add a new "vlan" flow
+key attribute to contain the VLAN tag, then continue to decode the
+encapsulated headers beyond the VLAN tag using the existing field
+definitions. With this change, an TCP packet in VLAN 10 would have a
+flow key much like this:
+
+ eth(...), vlan(vid=10, pcp=0), eth_type(0x0800), ip(proto=6, ...), tcp(...)
+
+But this change would negatively affect a userspace application that
+has not been updated to understand the new "vlan" flow key attribute.
+The application could, following the flow compatibility rules above,
+ignore the "vlan" attribute that it does not understand and therefore
+assume that the flow contained IP packets. This is a bad assumption
+(the flow only contains IP packets if one parses and skips over the
+802.1Q header) and it could cause the application's behavior to change
+across kernel versions even though it follows the compatibility rules.
+
+The solution is to use a set of nested attributes. This is, for
+example, why 802.1Q support uses nested attributes. A TCP packet in
+VLAN 10 is actually expressed as:
+
+ eth(...), eth_type(0x8100), vlan(vid=10, pcp=0), encap(eth_type(0x0800),
+ ip(proto=6, ...), tcp(...)))
+
+Notice how the "eth_type", "ip", and "tcp" flow key attributes are
+nested inside the "encap" attribute. Thus, an application that does
+not understand the "vlan" key will not see either of those attributes
+and therefore will not misinterpret them. (Also, the outer eth_type
+is still 0x8100, not changed to 0x0800.)
+
+Handling malformed packets
+--------------------------
+
+Don't drop packets in the kernel for malformed protocol headers, bad
+checksums, etc. This would prevent userspace from implementing a
+simple Ethernet switch that forwards every packet.
+
+Instead, in such a case, include an attribute with "empty" content.
+It doesn't matter if the empty content could be valid protocol values,
+as long as those values are rarely seen in practice, because userspace
+can always forward all packets with those values to userspace and
+handle them individually.
+
+For example, consider a packet that contains an IP header that
+indicates protocol 6 for TCP, but which is truncated just after the IP
+header, so that the TCP header is missing. The flow key for this
+packet would include a tcp attribute with all-zero src and dst, like
+this:
+
+ eth(...), eth_type(0x0800), ip(proto=6, ...), tcp(src=0, dst=0)
+
+As another example, consider a packet with an Ethernet type of 0x8100,
+indicating that a VLAN TCI should follow, but which is truncated just
+after the Ethernet type. The flow key for this packet would include
+an all-zero-bits vlan and an empty encap attribute, like this:
+
+ eth(...), eth_type(0x8100), vlan(0), encap()
+
+Unlike a TCP packet with source and destination ports 0, an
+all-zero-bits VLAN TCI is not that rare, so the CFI bit (aka
+VLAN_TAG_PRESENT inside the kernel) is ordinarily set in a vlan
+attribute expressly to allow this situation to be distinguished.
+Thus, the flow key in this second example unambiguously indicates a
+missing or malformed VLAN TCI.
+
+Other rules
+-----------
+
+The other rules for flow keys are much less subtle:
+
+ - Duplicate attributes are not allowed at a given nesting level.
+
+ - Ordering of attributes is not significant.
+
+ - When the kernel sends a given flow key to userspace, it always
+ composes it the same way. This allows userspace to hash and
+ compare entire flow keys that it may not be able to fully
+ interpret.
/* fill sockaddr_ll struct to prepare binding */
my_addr.sll_family = AF_PACKET;
- my_addr.sll_protocol = ETH_P_ALL;
+ my_addr.sll_protocol = htons(ETH_P_ALL);
my_addr.sll_ifindex = s_ifr.ifr_ifindex;
/* bind socket to eth0 */
CPU's backlog when a packet in this flow was last enqueued. Each backlog
queue has a head counter that is incremented on dequeue. A tail counter
is computed as head counter + queue length. In other words, the counter
-in rps_dev_flow_table[i] records the last element in flow i that has
+in rps_dev_flow[i] records the last element in flow i that has
been enqueued onto the currently designated CPU for flow i (of course,
entry i is actually selected by hash and multiple flows may hash to the
same entry i).
- The current CPU's queue head counter >= the recorded tail counter
value in rps_dev_flow[i]
-- The current CPU is unset (equal to NR_CPUS)
+- The current CPU is unset (equal to RPS_NO_CPU)
- The current CPU is offline
After this check, the packet is sent to the (possibly updated) current
==== RFS Configuration
-RFS is only available if the kconfig symbol CONFIG_RFS is enabled (on
+RFS is only available if the kconfig symbol CONFIG_RPS is enabled (on
by default for SMP). The functionality remains disabled until explicitly
configured. The number of entries in the global flow table is set through:
would normally be configured to the same value as rps_sock_flow_entries.
For a multi-queue device, the rps_flow_cnt for each queue might be
configured as rps_sock_flow_entries / N, where N is the number of
-queues. So for instance, if rps_flow_entries is set to 32768 and there
+queues. So for instance, if rps_sock_flow_entries is set to 32768 and there
are 16 configured receive queues, rps_flow_cnt for each queue might be
configured as 2048.
Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
-(Synopsys IP blocks); it has been fully tested on STLinux platforms.
+(Synopsys IP blocks).
Currently this network device driver is for all STM embedded MAC/GMAC
-(i.e. 7xxx/5xxx SoCs) and it's known working on other platforms i.e. ARM SPEAr.
+(i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XLINX XC2V3000
+FF1152AMT0221 D1215994A VIRTEX FPGA board.
-DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100
-Universal version 4.0 have been used for developing the first code
-implementation.
+DWC Ether MAC 10/100/1000 Universal version 3.60a (and older) and DWC Ether MAC 10/100
+Universal version 4.0 have been used for developing this driver.
+
+This driver supports both the platform bus and PCI.
Please, for more information also visit: www.stlinux.com
6) TODO:
o XGMAC is not supported.
- o Review the timer optimisation code to use an embedded device that will be
- available in new chip generations.
+ o Add the EEE - Energy Efficient Ethernet
+ o Add the PTP - precision time protocol
--- /dev/null
+Team devices are driven from userspace via libteam library which is here:
+ https://github.com/jpirko/libteam
Subsystem-Level Methods
-----------------------
The core methods to suspend and resume devices reside in struct dev_pm_ops
-pointed to by the pm member of struct bus_type, struct device_type and
-struct class. They are mostly of interest to the people writing infrastructure
-for buses, like PCI or USB, or device type and device class drivers.
+pointed to by the ops member of struct dev_pm_domain, or by the pm member of
+struct bus_type, struct device_type and struct class. They are mostly of
+interest to the people writing infrastructure for platforms and buses, like PCI
+or USB, or device type and device class drivers.
Bus drivers implement these methods as appropriate for the hardware and the
drivers using it; PCI works differently from USB, and so on. Not many people
/sys/devices/.../power/wakeup files
-----------------------------------
-All devices in the driver model have two flags to control handling of wakeup
-events (hardware signals that can force the device and/or system out of a low
-power state). These flags are initialized by bus or device driver code using
+All device objects in the driver model contain fields that control the handling
+of system wakeup events (hardware signals that can force the system out of a
+sleep state). These fields are initialized by bus or device driver code using
device_set_wakeup_capable() and device_set_wakeup_enable(), defined in
include/linux/pm_wakeup.h.
-The "can_wakeup" flag just records whether the device (and its driver) can
+The "power.can_wakeup" flag just records whether the device (and its driver) can
physically support wakeup events. The device_set_wakeup_capable() routine
-affects this flag. The "should_wakeup" flag controls whether the device should
-try to use its wakeup mechanism. device_set_wakeup_enable() affects this flag;
-for the most part drivers should not change its value. The initial value of
-should_wakeup is supposed to be false for the majority of devices; the major
-exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-(wake-on-LAN) feature has been set up with ethtool. It should also default
-to true for devices that don't generate wakeup requests on their own but merely
-forward wakeup requests from one bus to another (like PCI bridges).
+affects this flag. The "power.wakeup" field is a pointer to an object of type
+struct wakeup_source used for controlling whether or not the device should use
+its system wakeup mechanism and for notifying the PM core of system wakeup
+events signaled by the device. This object is only present for wakeup-capable
+devices (i.e. devices whose "can_wakeup" flags are set) and is created (or
+removed) by device_set_wakeup_capable().
Whether or not a device is capable of issuing wakeup events is a hardware
matter, and the kernel is responsible for keeping track of it. By contrast,
whether or not a wakeup-capable device should issue wakeup events is a policy
decision, and it is managed by user space through a sysfs attribute: the
-power/wakeup file. User space can write the strings "enabled" or "disabled" to
-set or clear the "should_wakeup" flag, respectively. This file is only present
-for wakeup-capable devices (i.e. devices whose "can_wakeup" flags are set)
-and is created (or removed) by device_set_wakeup_capable(). Reads from the
-file will return the corresponding string.
-
-The device_may_wakeup() routine returns true only if both flags are set.
+"power/wakeup" file. User space can write the strings "enabled" or "disabled"
+to it to indicate whether or not, respectively, the device is supposed to signal
+system wakeup. This file is only present if the "power.wakeup" object exists
+for the given device and is created (or removed) along with that object, by
+device_set_wakeup_capable(). Reads from the file will return the corresponding
+string.
+
+The "power/wakeup" file is supposed to contain the "disabled" string initially
+for the majority of devices; the major exceptions are power buttons, keyboards,
+and Ethernet adapters whose WoL (wake-on-LAN) feature has been set up with
+ethtool. It should also default to "enabled" for devices that don't generate
+wakeup requests on their own but merely forward wakeup requests from one bus to
+another (like PCI Express ports).
+
+The device_may_wakeup() routine returns true only if the "power.wakeup" object
+exists and the corresponding "power/wakeup" file contains the string "enabled".
This information is used by subsystems, like the PCI bus type code, to see
whether or not to enable the devices' wakeup mechanisms. If device wakeup
mechanisms are enabled or disabled directly by drivers, they also should use
device_may_wakeup() to decide what to do during a system sleep transition.
-However for runtime power management, wakeup events should be enabled whenever
-the device and driver both support them, regardless of the should_wakeup flag.
-
+Device drivers, however, are not supposed to call device_set_wakeup_enable()
+directly in any case.
+
+It ought to be noted that system wakeup is conceptually different from "remote
+wakeup" used by runtime power management, although it may be supported by the
+same physical mechanism. Remote wakeup is a feature allowing devices in
+low-power states to trigger specific interrupts to signal conditions in which
+they should be put into the full-power state. Those interrupts may or may not
+be used to signal system wakeup events, depending on the hardware design. On
+some systems it is impossible to trigger them from system sleep states. In any
+case, remote wakeup should always be enabled for runtime power management for
+all devices and drivers that support it.
/sys/devices/.../power/control files
------------------------------------
support all these callbacks and not all drivers use all the callbacks. The
various phases always run after tasks have been frozen and before they are
unfrozen. Furthermore, the *_noirq phases run at a time when IRQ handlers have
-been disabled (except for those marked with the IRQ_WAKEUP flag).
-
-All phases use bus, type, or class callbacks (that is, methods defined in
-dev->bus->pm, dev->type->pm, or dev->class->pm). These callbacks are mutually
-exclusive, so if the device type provides a struct dev_pm_ops object pointed to
-by its pm field (i.e. both dev->type and dev->type->pm are defined), the
-callbacks included in that object (i.e. dev->type->pm) will be used. Otherwise,
-if the class provides a struct dev_pm_ops object pointed to by its pm field
-(i.e. both dev->class and dev->class->pm are defined), the PM core will use the
-callbacks from that object (i.e. dev->class->pm). Finally, if the pm fields of
-both the device type and class objects are NULL (or those objects do not exist),
-the callbacks provided by the bus (that is, the callbacks from dev->bus->pm)
-will be used (this allows device types to override callbacks provided by bus
-types or classes if necessary).
+been disabled (except for those marked with the IRQF_NO_SUSPEND flag).
+
+All phases use PM domain, bus, type, or class callbacks (that is, methods
+defined in dev->pm_domain->ops, dev->bus->pm, dev->type->pm, or dev->class->pm).
+These callbacks are regarded by the PM core as mutually exclusive. Moreover,
+PM domain callbacks always take precedence over bus, type and class callbacks,
+while type callbacks take precedence over bus and class callbacks, and class
+callbacks take precedence over bus callbacks. To be precise, the following
+rules are used to determine which callback to execute in the given phase:
+
+ 1. If dev->pm_domain is present, the PM core will attempt to execute the
+ callback included in dev->pm_domain->ops. If that callback is not
+ present, no action will be carried out for the given device.
+
+ 2. Otherwise, if both dev->type and dev->type->pm are present, the callback
+ included in dev->type->pm will be executed.
+
+ 3. Otherwise, if both dev->class and dev->class->pm are present, the
+ callback included in dev->class->pm will be executed.
+
+ 4. Otherwise, if both dev->bus and dev->bus->pm are present, the callback
+ included in dev->bus->pm will be executed.
+
+This allows PM domains and device types to override callbacks provided by bus
+types or device classes if necessary.
These callbacks may in turn invoke device- or driver-specific methods stored in
dev->driver->pm, but they don't have to.
After the prepare callback method returns, no new children may be
registered below the device. The method may also prepare the device or
- driver in some way for the upcoming system power transition (for
- example, by allocating additional memory required for this purpose), but
- it should not put the device into a low-power state.
+ driver in some way for the upcoming system power transition, but it
+ should not put the device into a low-power state.
2. The suspend methods should quiesce the device to stop it from performing
I/O. They also may save the device registers and put it into the
};
The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
-are executed by the PM core for either the power domain, or the device type
-(if the device power domain's struct dev_pm_ops does not exist), or the class
-(if the device power domain's and type's struct dev_pm_ops object does not
-exist), or the bus type (if the device power domain's, type's and class'
-struct dev_pm_ops objects do not exist) of the given device, so the priority
-order of callbacks from high to low is that power domain callbacks, device
-type callbacks, class callbacks and bus type callbacks, and the high priority
-one will take precedence over low priority one. The bus type, device type and
-class callbacks are referred to as subsystem-level callbacks in what follows,
-and generally speaking, the power domain callbacks are used for representing
-power domains within a SoC.
+are executed by the PM core for the device's subsystem that may be either of
+the following:
+
+ 1. PM domain of the device, if the device's PM domain object, dev->pm_domain,
+ is present.
+
+ 2. Device type of the device, if both dev->type and dev->type->pm are present.
+
+ 3. Device class of the device, if both dev->class and dev->class->pm are
+ present.
+
+ 4. Bus type of the device, if both dev->bus and dev->bus->pm are present.
+
+The PM core always checks which callback to use in the order given above, so the
+priority order of callbacks from high to low is: PM domain, device type, class
+and bus type. Moreover, the high-priority one will always take precedence over
+a low-priority one. The PM domain, bus type, device type and class callbacks
+are referred to as subsystem-level callbacks in what follows.
By default, the callbacks are always invoked in process context with interrupts
enabled. However, subsystems can use the pm_runtime_irq_safe() helper function
-to tell the PM core that a device's ->runtime_suspend() and ->runtime_resume()
-callbacks should be invoked in atomic context with interrupts disabled.
-This implies that these callback routines must not block or sleep, but it also
-means that the synchronous helper functions listed at the end of Section 4 can
-be used within an interrupt handler or in an atomic context.
+to tell the PM core that their ->runtime_suspend(), ->runtime_resume() and
+->runtime_idle() callbacks may be invoked in atomic context with interrupts
+disabled for a given device. This implies that the callback routines in
+question must not block or sleep, but it also means that the synchronous helper
+functions listed at the end of Section 4 may be used for that device within an
+interrupt handler or generally in an atomic context.
The subsystem-level suspend callback is _entirely_ _responsible_ for handling
the suspend of the device as appropriate, which may, but need not include
struct serial_rs485 rs485conf;
- /* Set RS485 mode: */
+ /* Enable RS485 mode: */
rs485conf.flags |= SER_RS485_ENABLED;
+ /* Set logical level for RTS pin equal to 1 when sending: */
+ rs485conf.flags |= SER_RS485_RTS_ON_SEND;
+ /* or, set logical level for RTS pin equal to 0 when sending: */
+ rs485conf.flags &= ~(SER_RS485_RTS_ON_SEND);
+
+ /* Set logical level for RTS pin equal to 1 after sending: */
+ rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
+ /* or, set logical level for RTS pin equal to 0 after sending: */
+ rs485conf.flags &= ~(SER_RS485_RTS_AFTER_SEND);
+
/* Set rts delay before send, if needed: */
- rs485conf.flags |= SER_RS485_RTS_BEFORE_SEND;
rs485conf.delay_rts_before_send = ...;
/* Set rts delay after send, if needed: */
- rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
rs485conf.delay_rts_after_send = ...;
/* Set this flag if you want to receive data even whilst sending data */
~~~~~~~~~~~~~~~~
The latest development codes for HD-audio are found on sound git tree:
-- git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6.git
+- git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
The master branch or for-next branches can be used as the main
development branches in general while the HD-audio specific patches
install(-modules). See INSTALL in the package. The snapshot tarballs
are found at:
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/snapshot/
+- ftp://ftp.suse.com/pub/people/tiwai/snapshot/
Sending a Bug Report
The hda-verb program is found in the ftp directory:
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/misc/
+- ftp://ftp.suse.com/pub/people/tiwai/misc/
Also a git repository is available:
The package is found in:
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/misc/
+- ftp://ftp.suse.com/pub/people/tiwai/misc/
A git repository is available:
The machine DAI configuration glues all the codec and CPU DAIs together. It can
also be used to set up the DAI system clock and for any machine related DAI
initialisation e.g. the machine audio map can be connected to the codec audio
-map, unconnected codec pins can be set as such. Please see corgi.c, spitz.c
-for examples.
+map, unconnected codec pins can be set as such.
struct snd_soc_dai_link is used to set up each DAI in your machine. e.g.
The machine driver can optionally extend the codec power map and to become an
audio power map of the audio subsystem. This allows for automatic power up/down
of speaker/HP amplifiers, etc. Codec pins can be connected to the machines jack
-sockets in the machine init function. See soc/pxa/spitz.c and dapm.txt for
-details.
+sockets in the machine init function.
Machine Controls
[SourceDisksFiles]
[SourceDisksNames]
[DeviceList]
-%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02
+%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02, USB\VID_1D6B&PID_0106&MI_00
[DeviceList.NTamd64]
-%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02
+%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02, USB\VID_1D6B&PID_0106&MI_00
;------------------------------------------------------------------------------
eax, ebx, ecx, edx: the values returned by the cpuid instruction for
this function/index combination
+The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
+as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
+support. Instead it is reported via
+
+ ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
+
+if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
+feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
+
4.47 KVM_PPC_GET_PVINFO
Capability: KVM_CAP_PPC_GET_PVINFO
/* Depends on KVM_CAP_IOMMU */
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
+The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
+isolation of the device. Usages not specifying this flag are deprecated.
+
+Only PCI header type 0 devices with PCI BAR resources are supported by
+device assignment. The user requesting this ioctl must have read/write
+access to the PCI sysfs resource files associated with the device.
+
4.49 KVM_DEASSIGN_PCI_DEVICE
Capability: KVM_CAP_DEVICE_DEASSIGNMENT
L: iommu@lists.linux-foundation.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu.git
S: Supported
-F: arch/x86/kernel/amd_iommu*.c
-F: arch/x86/include/asm/amd_iommu*.h
+F: drivers/iommu/amd_iommu*.[ch]
+F: include/linux/amd-iommu.h
AMD MICROCODE UPDATE SUPPORT
M: Andreas Herrmann <andreas.herrmann3@amd.com>
S: Maintained
T: git git://git.pengutronix.de/git/imx/linux-2.6.git
F: arch/arm/mach-mx*/
+F: arch/arm/mach-imx/
F: arch/arm/plat-mxc/
ARM/FREESCALE IMX51
T: git git://git.linaro.org/people/shawnguo/linux-2.6.git
F: arch/arm/mach-imx/*imx6*
+ARM/FREESCALE MXS ARM ARCHITECTURE
+M: Shawn Guo <shawn.guo@linaro.org>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+T: git git://git.linaro.org/people/shawnguo/linux-2.6.git
+F: arch/arm/mach-mxs/
+
ARM/GLOMATION GESBC9312SX MACHINE SUPPORT
M: Lennert Buytenhek <kernel@wantstofly.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
M: Ben Dooks <ben-linux@fluff.org>
M: Kukjin Kim <kgene.kim@samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
W: http://www.fluff.org/ben/linux/
S: Maintained
F: arch/arm/plat-samsung/
F: arch/arm/plat-s3c24xx/
F: arch/arm/plat-s5p/
+F: arch/arm/mach-s3c24*/
+F: arch/arm/mach-s3c64xx/
F: drivers/*/*s3c2410*
F: drivers/*/*/*s3c2410*
-
-ARM/S3C2410 ARM ARCHITECTURE
-M: Ben Dooks <ben-linux@fluff.org>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.fluff.org/ben/linux/
-S: Maintained
-F: arch/arm/mach-s3c2410/
-
-ARM/S3C244x ARM ARCHITECTURE
-M: Ben Dooks <ben-linux@fluff.org>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.fluff.org/ben/linux/
-S: Maintained
-F: arch/arm/mach-s3c2440/
-F: arch/arm/mach-s3c2443/
-
-ARM/S3C64xx ARM ARCHITECTURE
-M: Ben Dooks <ben-linux@fluff.org>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://www.fluff.org/ben/linux/
-S: Maintained
-F: arch/arm/mach-s3c64xx/
+F: drivers/spi/spi-s3c*
+F: sound/soc/samsung/*
ARM/S5P EXYNOS ARM ARCHITECTURES
M: Kukjin Kim <kgene.kim@samsung.com>
CAN NETWORK LAYER
M: Oliver Hartkopp <socketcan@hartkopp.net>
-M: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
-M: Urs Thuermann <urs.thuermann@volkswagen.de>
L: linux-can@vger.kernel.org
-L: netdev@vger.kernel.org
-W: http://developer.berlios.de/projects/socketcan/
+W: http://gitorious.org/linux-can
+T: git git://gitorious.org/linux-can/linux-can-next.git
S: Maintained
F: net/can/
F: include/linux/can.h
CAN NETWORK DRIVERS
M: Wolfgang Grandegger <wg@grandegger.com>
+M: Marc Kleine-Budde <mkl@pengutronix.de>
L: linux-can@vger.kernel.org
-L: netdev@vger.kernel.org
-W: http://developer.berlios.de/projects/socketcan/
+W: http://gitorious.org/linux-can
+T: git git://gitorious.org/linux-can/linux-can-next.git
S: Maintained
F: drivers/net/can/
F: include/linux/can/dev.h
F: net/wireless/*
X: net/wireless/wext*
+CHAR and MISC DRIVERS
+M: Arnd Bergmann <arnd@arndb.de>
+M: Greg Kroah-Hartman <greg@kroah.com>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
+S: Maintained
+F: drivers/char/*
+F: drivers/misc/*
+
CHECKPATCH
M: Andy Whitcroft <apw@canonical.com>
S: Supported
F: drivers/connector/
CONTROL GROUPS (CGROUPS)
-M: Paul Menage <paul@paulmenage.org>
+M: Tejun Heo <tj@kernel.org>
M: Li Zefan <lizf@cn.fujitsu.com>
L: containers@lists.linux-foundation.org
+L: cgroups@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
S: Maintained
F: include/linux/cgroup*
F: kernel/cgroup*
F: drivers/net/ethernet/i825xx/eexpress.*
ETHERNET BRIDGE
-M: Stephen Hemminger <shemminger@linux-foundation.org>
+M: Stephen Hemminger <shemminger@vyatta.com>
L: bridge@lists.linux-foundation.org
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net:Bridge
M: Stefan Richter <stefanr@s5r6.in-berlin.de>
L: linux1394-devel@lists.sourceforge.net
W: http://ieee1394.wiki.kernel.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394.git
S: Maintained
F: drivers/firewire/
F: include/linux/firewire*.h
HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS
M: Thomas Gleixner <tglx@linutronix.de>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
S: Maintained
F: Documentation/timers/
F: kernel/hrtimer.c
IRQ SUBSYSTEM
M: Thomas Gleixner <tglx@linutronix.de>
S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
F: kernel/irq/
ISAPNP
F: include/linux/jbd2.h
JSM Neo PCI based serial card
-M: Breno Leitao <leitao@linux.vnet.ibm.com>
+M: Lucas Tavares <lucaskt@linux.vnet.ibm.com>
L: linux-serial@vger.kernel.org
S: Maintained
F: drivers/tty/serial/jsm/
LOCKDEP AND LOCKSTAT
M: Peter Zijlstra <peterz@infradead.org>
M: Ingo Molnar <mingo@redhat.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-lockdep.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
S: Maintained
F: Documentation/lockdep*.txt
F: Documentation/lockstat.txt
S: Maintained
F: Documentation/dvb/
F: Documentation/video4linux/
+F: Documentation/DocBook/media/
F: drivers/media/
+F: drivers/staging/media/
F: include/media/
F: include/linux/dvb/
F: include/linux/videodev*.h
F: mm/
MEMORY RESOURCE CONTROLLER
+M: Johannes Weiner <hannes@cmpxchg.org>
+M: Michal Hocko <mhocko@suse.cz>
M: Balbir Singh <bsingharora@gmail.com>
-M: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
M: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+L: cgroups@vger.kernel.org
L: linux-mm@kvack.org
S: Maintained
F: mm/memcontrol.c
M: Ralf Baechle <ralf@linux-mips.org>
L: linux-mips@linux-mips.org
W: http://www.linux-mips.org/
-T: git git://git.linux-mips.org/pub/scm/linux.git
+T: git git://git.linux-mips.org/pub/scm/ralf/linux.git
Q: http://patchwork.linux-mips.org/project/linux-mips/list/
S: Supported
F: Documentation/mips/
F: drivers/infiniband/hw/nes/
NETEM NETWORK EMULATOR
-M: Stephen Hemminger <shemminger@linux-foundation.org>
+M: Stephen Hemminger <shemminger@vyatta.com>
L: netem@lists.linux-foundation.org
S: Maintained
F: net/sched/sch_netem.c
T: git git://openrisc.net/~jonas/linux
F: arch/openrisc
+OPENVSWITCH
+M: Jesse Gross <jesse@nicira.com>
+L: dev@openvswitch.org
+W: http://openvswitch.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch.git
+S: Maintained
+F: net/openvswitch/
+
OPL4 DRIVER
M: Clemens Ladisch <clemens@ladisch.de>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
F: include/linux/ppdev.h
PARAVIRT_OPS INTERFACE
-M: Jeremy Fitzhardinge <jeremy@xensource.com>
+M: Jeremy Fitzhardinge <jeremy@goop.org>
M: Chris Wright <chrisw@sous-sol.org>
M: Alok Kataria <akataria@vmware.com>
M: Rusty Russell <rusty@rustcorp.com.au>
M: Paul Mackerras <paulus@samba.org>
M: Ingo Molnar <mingo@elte.hu>
M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
S: Supported
F: kernel/events/*
F: include/linux/perf_event.h
POSIX CLOCKS and TIMERS
M: Thomas Gleixner <tglx@linutronix.de>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
S: Supported
F: fs/timerfd.c
F: include/linux/timer*
F: drivers/scsi/qla4xxx/
QLOGIC QLA3XXX NETWORK DRIVER
+M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
M: Ron Mercer <ron.mercer@qlogic.com>
M: linux-driver@qlogic.com
L: netdev@vger.kernel.org
F: include/media/*7146*
SAMSUNG AUDIO (ASoC) DRIVERS
-M: Jassi Brar <jassisinghbrar@gmail.com>
M: Sangbeom Kim <sbkim73@samsung.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Supported
TIMEKEEPING, NTP
M: John Stultz <johnstul@us.ibm.com>
M: Thomas Gleixner <tglx@linutronix.de>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
S: Supported
F: include/linux/clocksource.h
F: include/linux/time.h
SCHEDULER
M: Ingo Molnar <mingo@elte.hu>
M: Peter Zijlstra <peterz@infradead.org>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
S: Maintained
F: kernel/sched*
F: include/linux/sched.h
SFC NETWORK DRIVER
M: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
-M: Steve Hodgson <shodgson@solarflare.com>
M: Ben Hutchings <bhutchings@solarflare.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/usb/misc/sisusbvga/
SKGE, SKY2 10/100/1000 GIGABIT ETHERNET DRIVERS
-M: Stephen Hemminger <shemminger@linux-foundation.org>
+M: Stephen Hemminger <shemminger@vyatta.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/marvell/sk*
S: Maintained
F: net/ipv4/tcp_lp.c
+TEAM DRIVER
+M: Jiri Pirko <jpirko@redhat.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/team/
+F: include/linux/if_team.h
+
TEGRA SUPPORT
M: Colin Cross <ccross@android.com>
M: Olof Johansson <olof@lixom.net>
M: Steven Rostedt <rostedt@goodmis.org>
M: Frederic Weisbecker <fweisbec@gmail.com>
M: Ingo Molnar <mingo@redhat.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
S: Maintained
F: Documentation/trace/ftrace.txt
F: arch/*/*/*/ftrace.h
M: Ingo Molnar <mingo@redhat.com>
M: "H. Peter Anvin" <hpa@zytor.com>
M: x86@kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
S: Maintained
F: Documentation/x86/
F: arch/x86/
F: arch/x86/kernel/cpu/mcheck/*
XEN HYPERVISOR INTERFACE
-M: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+M: Jeremy Fitzhardinge <jeremy@goop.org>
L: xen-devel@lists.xensource.com (moderated for non-subscribers)
L: virtualization@lists.linux-foundation.org
S: Supported
XFS FILESYSTEM
P: Silicon Graphics Inc
-M: Alex Elder <aelder@sgi.com>
+M: Ben Myers <bpm@sgi.com>
+M: Alex Elder <elder@kernel.org>
M: xfs-masters@oss.sgi.com
L: xfs@oss.sgi.com
W: http://oss.sgi.com/projects/xfs
VERSION = 3
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
NAME = Saber-toothed Squirrel
# *DOCUMENTATION*
be avoided when possible.
config PHYS_OFFSET
- hex "Physical address of main memory"
+ hex "Physical address of main memory" if MMU
depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+ default DRAM_BASE if !MMU
help
Please provide the physical address corresponding to the
location of main memory in your system.
capabilities of the processor.
config PL310_ERRATA_588369
- bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
+ bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
depends on CACHE_L2X0
help
The PL310 L2 cache controller implements three types of Clean &
config ARM_ERRATA_720789
bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
- depends on CPU_V7 && SMP
+ depends on CPU_V7
help
This option enables the workaround for the 720789 Cortex-A9 (prior to
r2p0) erratum. A faulty ASID can be sent to the other CPUs for the
entries regardless of the ASID.
config PL310_ERRATA_727915
- bool "Background Clean & Invalidate by Way operation can cause data corruption"
+ bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
depends on CACHE_L2X0
help
PL310 implements the Clean & Invalidate by Way L2 cache maintenance
config ARM_ERRATA_751472
bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation"
- depends on CPU_V7 && SMP
+ depends on CPU_V7
help
This option enables the workaround for the 751472 Cortex-A9 (prior
to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the
operation is received by a CPU before the ICIALLUIS has completed,
potentially leading to corrupted entries in the cache or TLB.
-config ARM_ERRATA_753970
- bool "ARM errata: cache sync operation may be faulty"
+config PL310_ERRATA_753970
+ bool "PL310 errata: cache sync operation may be faulty"
depends on CACHE_PL310
help
This option enables the workaround for the 753970 PL310 (r3p0) erratum.
relevant cache maintenance functions and sets a specific bit
in the diagnostic control register of the SCU.
+config PL310_ERRATA_769419
+ bool "PL310 errata: no automatic Store Buffer drain"
+ depends on CACHE_L2X0
+ help
+ On revisions of the PL310 prior to r3p2, the Store Buffer does
+ not automatically drain. This can cause normal, non-cacheable
+ writes to be retained when the memory system is idle, leading
+ to suboptimal I/O performance for drivers using coherent DMA.
+ This option adds a write barrier to the cpu_idle loop so that,
+ on systems with an outer cache, the store buffer is drained
+ explicitly.
+
endmenu
source "arch/arm/common/Kconfig"
$(obj)/dtbs: $(addprefix $(obj)/, $(dtb-y))
+clean-files := *.dtb
+
quiet_cmd_uimage = UIMAGE $@
cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A arm -O linux -T kernel \
-C none -a $(LOADADDR) -e $(STARTADDR) \
sizeof(u32));
BUG_ON(!gic->saved_ppi_conf);
- cpu_pm_register_notifier(&gic_notifier_block);
+ if (gic == &gic_data[0])
+ cpu_pm_register_notifier(&gic_notifier_block);
}
#else
static void __init gic_pm_init(struct gic_chip_data *gic)
* For primary GICs, skip over SGIs.
* For secondary GICs, skip over PPIs, too.
*/
+ domain->hwirq_base = 32;
if (gic_nr == 0) {
gic_cpu_base_addr = cpu_base;
- domain->hwirq_base = 16;
- if (irq_start > 0)
- irq_start = (irq_start & ~31) + 16;
- } else
- domain->hwirq_base = 32;
+
+ if ((irq_start & 31) > 0) {
+ domain->hwirq_base = 16;
+ if (irq_start != -1)
+ irq_start = (irq_start & ~31) + 16;
+ }
+ }
/*
* Find out how many interrupts are supported.
*/
#define MCODE_BUFF_PER_REQ 256
-/*
- * Mark a _pl330_req as free.
- * We do it by writing DMAEND as the first instruction
- * because no valid request is going to have DMAEND as
- * its first instruction to execute.
- */
-#define MARK_FREE(req) do { \
- _emit_END(0, (req)->mc_cpu); \
- (req)->mc_len = 0; \
- } while (0)
-
/* If the _pl330_req is available to the client */
#define IS_FREE(req) (*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
struct pl330_dmac *dmac;
/* Only two at a time */
struct _pl330_req req[2];
- /* Index of the last submitted request */
+ /* Index of the last enqueued request */
unsigned lstenq;
+ /* Index of the last submitted request or -1 if the DMA is stopped */
+ int req_running;
};
enum pl330_dmac_state {
writel(0, regs + DBGCMD);
}
+/*
+ * Mark a _pl330_req as free.
+ * We do it by writing DMAEND as the first instruction
+ * because no valid request is going to have DMAEND as
+ * its first instruction to execute.
+ */
+static void mark_free(struct pl330_thread *thrd, int idx)
+{
+ struct _pl330_req *req = &thrd->req[idx];
+
+ _emit_END(0, req->mc_cpu);
+ req->mc_len = 0;
+
+ thrd->req_running = -1;
+}
+
static inline u32 _state(struct pl330_thread *thrd)
{
void __iomem *regs = thrd->dmac->pinfo->base;
}
}
-/* If the request 'req' of thread 'thrd' is currently active */
-static inline bool _req_active(struct pl330_thread *thrd,
- struct _pl330_req *req)
-{
- void __iomem *regs = thrd->dmac->pinfo->base;
- u32 buf = req->mc_bus, pc = readl(regs + CPC(thrd->id));
-
- if (IS_FREE(req))
- return false;
-
- return (pc >= buf && pc <= buf + req->mc_len) ? true : false;
-}
-
-/* Returns 0 if the thread is inactive, ID of active req + 1 otherwise */
-static inline unsigned _thrd_active(struct pl330_thread *thrd)
-{
- if (_req_active(thrd, &thrd->req[0]))
- return 1; /* First req active */
-
- if (_req_active(thrd, &thrd->req[1]))
- return 2; /* Second req active */
-
- return 0;
-}
-
static void _stop(struct pl330_thread *thrd)
{
void __iomem *regs = thrd->dmac->pinfo->base;
struct _arg_GO go;
unsigned ns;
u8 insn[6] = {0, 0, 0, 0, 0, 0};
+ int idx;
/* Return if already ACTIVE */
if (_state(thrd) != PL330_STATE_STOPPED)
return true;
- if (!IS_FREE(&thrd->req[1 - thrd->lstenq]))
- req = &thrd->req[1 - thrd->lstenq];
- else if (!IS_FREE(&thrd->req[thrd->lstenq]))
- req = &thrd->req[thrd->lstenq];
- else
- req = NULL;
+ idx = 1 - thrd->lstenq;
+ if (!IS_FREE(&thrd->req[idx]))
+ req = &thrd->req[idx];
+ else {
+ idx = thrd->lstenq;
+ if (!IS_FREE(&thrd->req[idx]))
+ req = &thrd->req[idx];
+ else
+ req = NULL;
+ }
/* Return if no request */
if (!req || !req->r)
/* Only manager can execute GO */
_execute_DBGINSN(thrd, insn, true);
+ thrd->req_running = idx;
+
return true;
}
ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
- ccr |= (rqc->dcctl << CC_SRCCCTRL_SHFT);
- ccr |= (rqc->scctl << CC_DSTCCTRL_SHFT);
+ ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
+ ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
ccr |= (rqc->swap << CC_SWAP_SHFT);
thrd->req[0].r = NULL;
thrd->req[1].r = NULL;
- MARK_FREE(&thrd->req[0]);
- MARK_FREE(&thrd->req[1]);
+ mark_free(thrd, 0);
+ mark_free(thrd, 1);
/* Clear the reset flag */
pl330->dmac_tbd.reset_chan &= ~(1 << i);
thrd = &pl330->channels[id];
- active = _thrd_active(thrd);
- if (!active) /* Aborted */
+ active = thrd->req_running;
+ if (active == -1) /* Aborted */
continue;
- active -= 1;
-
rqdone = &thrd->req[active];
- MARK_FREE(rqdone);
+ mark_free(thrd, active);
/* Get going again ASAP */
_start(thrd);
struct pl330_thread *thrd = ch_id;
struct pl330_dmac *pl330;
unsigned long flags;
- int ret = 0, active;
+ int ret = 0, active = thrd->req_running;
if (!thrd || thrd->free || thrd->dmac->state == DYING)
return -EINVAL;
thrd->req[0].r = NULL;
thrd->req[1].r = NULL;
- MARK_FREE(&thrd->req[0]);
- MARK_FREE(&thrd->req[1]);
+ mark_free(thrd, 0);
+ mark_free(thrd, 1);
break;
case PL330_OP_ABORT:
- active = _thrd_active(thrd);
-
/* Make sure the channel is stopped */
_stop(thrd);
/* ABORT is only for the active req */
- if (!active)
+ if (active == -1)
break;
- active--;
-
thrd->req[active].r = NULL;
- MARK_FREE(&thrd->req[active]);
+ mark_free(thrd, active);
/* Start the next */
case PL330_OP_START:
- if (!_thrd_active(thrd) && !_start(thrd))
+ if ((active == -1) && !_start(thrd))
ret = -EIO;
break;
else
pstatus->faulting = false;
- active = _thrd_active(thrd);
+ active = thrd->req_running;
- if (!active) {
+ if (active == -1) {
/* Indicate that the thread is not running */
pstatus->top_req = NULL;
pstatus->wait_req = NULL;
} else {
- active--;
pstatus->top_req = thrd->req[active].r;
pstatus->wait_req = !IS_FREE(&thrd->req[1 - active])
? thrd->req[1 - active].r : NULL;
return -1;
}
+static bool _chan_ns(const struct pl330_info *pi, int i)
+{
+ return pi->pcfg.irq_ns & (1 << i);
+}
+
/* Upon success, returns IdentityToken for the
* allocated channel, NULL otherwise.
*/
for (i = 0; i < chans; i++) {
thrd = &pl330->channels[i];
- if (thrd->free) {
+ if ((thrd->free) && (!_manager_ns(thrd) ||
+ _chan_ns(pi, i))) {
thrd->ev = _alloc_event(thrd);
if (thrd->ev >= 0) {
thrd->free = false;
thrd->lstenq = 1;
thrd->req[0].r = NULL;
- MARK_FREE(&thrd->req[0]);
+ mark_free(thrd, 0);
thrd->req[1].r = NULL;
- MARK_FREE(&thrd->req[1]);
+ mark_free(thrd, 1);
break;
}
}
thrd->req[0].mc_bus = pl330->mcode_bus
+ (thrd->id * pi->mcbufsz);
thrd->req[0].r = NULL;
- MARK_FREE(&thrd->req[0]);
+ mark_free(thrd, 0);
thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
+ pi->mcbufsz / 2;
thrd->req[1].mc_bus = thrd->req[0].mc_bus
+ pi->mcbufsz / 2;
thrd->req[1].r = NULL;
- MARK_FREE(&thrd->req[1]);
+ mark_free(thrd, 1);
}
static int dmac_alloc_threads(struct pl330_dmac *pl330)
# CONFIG_IPV6 is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_CHAR=y
CONFIG_MTD_BLOCK=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_MULTI_LUN=y
CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
CONFIG_MII=y
CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_FB=y
CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_CLUT224 is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_AT91SAM9=y
CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
CONFIG_JFFS2_FS=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
CONFIG_BRIDGE=m
CONFIG_VLAN_8021Q=m
CONFIG_BT=m
-CONFIG_BT_L2CAP=m
-CONFIG_BT_SCO=m
-CONFIG_BT_RFCOMM=m
-CONFIG_BT_RFCOMM_TTY=y
-CONFIG_BT_BNEP=m
-CONFIG_BT_BNEP_MC_FILTER=y
-CONFIG_BT_BNEP_PROTO_FILTER=y
-CONFIG_BT_HIDP=m
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_AFS_PARTS=y
CONFIG_MTD_CHAR=y
CONFIG_BLK_DEV_NBD=y
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_TCLIB=y
-CONFIG_EEPROM_LEGACY=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=m
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_NETDEVICES=y
CONFIG_TUN=m
+CONFIG_ARM_AT91_ETHER=y
CONFIG_PHYLIB=y
CONFIG_DAVICOM_PHY=y
CONFIG_SMSC_PHY=y
CONFIG_MICREL_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_ARM_AT91_ETHER=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=y
+CONFIG_SLIP=m
+CONFIG_SLIP_COMPRESSED=y
+CONFIG_SLIP_SMART=y
+CONFIG_SLIP_MODE_SLIP6=y
CONFIG_USB_CATC=m
CONFIG_USB_KAWETH=m
CONFIG_USB_PEGASUS=m
CONFIG_USB_ALI_M5632=y
CONFIG_USB_AN2720=y
CONFIG_USB_EPSON2888=y
-CONFIG_PPP=y
-CONFIG_PPP_MULTILINK=y
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_ASYNC=y
-CONFIG_PPP_DEFLATE=y
-CONFIG_PPP_BSDCOMP=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_SLIP=m
-CONFIG_SLIP_COMPRESSED=y
-CONFIG_SLIP_SMART=y
-CONFIG_SLIP_MODE_SLIP6=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=640
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_LEGACY_PTY_COUNT=32
CONFIG_SERIAL_ATMEL=y
CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=32
CONFIG_HW_RANDOM=y
CONFIG_I2C=y
CONFIG_I2C_CHARDEV=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
CONFIG_NFSD=y
-CONFIG_SMB_FS=m
CONFIG_CIFS=m
CONFIG_PARTITION_ADVANCED=y
CONFIG_MAC_PARTITION=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
# CONFIG_FTRACE is not set
CONFIG_CRYPTO_PCBC=y
CONFIG_CRYPTO_SHA1=y
# CONFIG_IOSCHED_CFQ is not set
CONFIG_ARCH_AT91=y
CONFIG_ARCH_AT91SAM9260=y
+CONFIG_ARCH_AT91SAM9260_SAM9XE=y
CONFIG_MACH_AT91SAM9260EK=y
+CONFIG_MACH_CAM60=y
+CONFIG_MACH_SAM9_L9260=y
+CONFIG_MACH_AFEB9260=y
+CONFIG_MACH_USB_A9260=y
+CONFIG_MACH_QIL_A9260=y
+CONFIG_MACH_CPU9260=y
+CONFIG_MACH_FLEXIBITY=y
+CONFIG_MACH_SNAPPER_9260=y
+CONFIG_MACH_AT91SAM_DT=y
CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
# CONFIG_ARM_THUMB is not set
CONFIG_ZBOOT_ROM_TEXT=0x0
CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
CONFIG_FPE_NWFPE=y
CONFIG_NET=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_MULTI_LUN=y
CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
CONFIG_MII=y
CONFIG_MACB=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_AT91SAM9X_WATCHDOG=y
-# CONFIG_VGA_CONSOLE is not set
# CONFIG_USB_HID is not set
CONFIG_USB=y
CONFIG_USB_DEVICEFS=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_AT91SAM9=y
CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
CONFIG_CRAMFS=y
CONFIG_ARCH_AT91SAM9G20=y
CONFIG_MACH_AT91SAM9G20EK=y
CONFIG_MACH_AT91SAM9G20EK_2MMC=y
+CONFIG_MACH_CPU9G20=y
+CONFIG_MACH_ACMENETUSFOXG20=y
+CONFIG_MACH_PORTUXG20=y
+CONFIG_MACH_STAMP9G20=y
+CONFIG_MACH_PCONTROL_G20=y
+CONFIG_MACH_GSIA18S=y
+CONFIG_MACH_USB_A9G20=y
+CONFIG_MACH_SNAPPER_9260=y
+CONFIG_MACH_AT91SAM_DT=y
CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
# CONFIG_ARM_THUMB is not set
CONFIG_AEABI=y
CONFIG_LEDS_CPU=y
CONFIG_ZBOOT_ROM_TEXT=0x0
CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
# CONFIG_IPV6 is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_CHAR=y
CONFIG_MTD_BLOCK=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_MULTI_LUN=y
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
CONFIG_MII=y
CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=320
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=240
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
+CONFIG_LEGACY_PTY_COUNT=16
CONFIG_SERIAL_ATMEL=y
CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=16
CONFIG_HW_RANDOM=y
CONFIG_SPI=y
CONFIG_SPI_ATMEL=y
CONFIG_SPI_SPIDEV=y
# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
CONFIG_SOUND=y
CONFIG_SND=y
CONFIG_SND_SEQUENCER=y
CONFIG_SND_PCM_OSS=y
CONFIG_SND_SEQUENCER_OSS=y
# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=y
CONFIG_USB=y
CONFIG_USB_DEVICEFS=y
# CONFIG_USB_DEVICE_CLASS is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_AT91SAM9=y
CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
CONFIG_ARCH_AT91=y
CONFIG_ARCH_AT91SAM9G45=y
CONFIG_MACH_AT91SAM9M10G45EK=y
+CONFIG_MACH_AT91SAM_DT=y
CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
CONFIG_AT91_SLOW_CLOCK=y
CONFIG_AEABI=y
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_NETDEVICES=y
CONFIG_MII=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_NET_ETHERNET=y
CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_DAVICOM_PHY=y
CONFIG_LIBERTAS_THINFIRM=m
CONFIG_LIBERTAS_THINFIRM_USB=m
CONFIG_AT76C50X_USB=m
CONFIG_SPI=y
CONFIG_SPI_ATMEL=y
# CONFIG_HWMON is not set
-# CONFIG_MFD_SUPPORT is not set
CONFIG_FB=y
CONFIG_FB_ATMEL=y
CONFIG_FB_UDL=m
CONFIG_UNIX=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_CHAR=y
CONFIG_MTD_BLOCK=y
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=4
CONFIG_BLK_DEV_RAM_SIZE=24576
-CONFIG_ATMEL_SSC=y
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_MULTI_LUN=y
CONFIG_AT91SAM9X_WATCHDOG=y
CONFIG_FB=y
CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
CONFIG_MMC=y
CONFIG_MMC_AT91=m
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_AT91SAM9=y
CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
# CONFIG_USB_DEVICE_CLASS is not set
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
CONFIG_USB_ETH=m
# CONFIG_USB_ETH_RNDIS is not set
CONFIG_MMC=y
# CONFIG_USB_DEVICE_CLASS is not set
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
CONFIG_USB_ETH=m
# CONFIG_USB_ETH_RNDIS is not set
CONFIG_MMC=y
CONFIG_ARCH_IMX_V4_V5=y
CONFIG_ARCH_MX1ADS=y
CONFIG_MACH_SCB9328=y
+CONFIG_MACH_APF9328=y
CONFIG_MACH_MX21ADS=y
CONFIG_MACH_MX25_3DS=y
-CONFIG_MACH_EUKREA_CPUIMX25=y
+CONFIG_MACH_EUKREA_CPUIMX25SD=y
CONFIG_MACH_MX27ADS=y
CONFIG_MACH_PCM038=y
CONFIG_MACH_CPUIMX27=y
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_PHYSMAP=y
CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_MXC=y
CONFIG_MTD_UBI=y
CONFIG_MISC_DEVICES=y
CONFIG_EEPROM_AT24=y
CONFIG_EEPROM_AT25=y
CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_SMC91X=y
CONFIG_DM9000=y
+CONFIG_SMC91X=y
CONFIG_SMC911X=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_SMSC_PHY=y
# CONFIG_INPUT_MOUSEDEV is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
CONFIG_I2C_IMX=y
CONFIG_SPI=y
CONFIG_SPI_IMX=y
+CONFIG_SPI_SPIDEV=y
CONFIG_W1=y
CONFIG_W1_MASTER_MXC=y
CONFIG_W1_SLAVE_THERM=y
CONFIG_MMC_MXC=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
CONFIG_LEDS_MC13783=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_GADGET=y
CONFIG_USB_GADGET_VBUS_DRAW=500
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
CONFIG_USB_ETH=m
# CONFIG_USB_ETH_RNDIS is not set
CONFIG_USB_GADGETFS=m
CONFIG_MACH_NOKIA770=y
CONFIG_MACH_AMS_DELTA=y
CONFIG_MACH_OMAP_GENERIC=y
-CONFIG_OMAP_CLOCKS_SET_BY_BOOTLOADER=y
-CONFIG_OMAP_ARM_216MHZ=y
-CONFIG_OMAP_ARM_195MHZ=y
-CONFIG_OMAP_ARM_192MHZ=y
CONFIG_OMAP_ARM_182MHZ=y
-CONFIG_OMAP_ARM_168MHZ=y
-# CONFIG_OMAP_ARM_60MHZ is not set
# CONFIG_ARM_THUMB is not set
CONFIG_PCCARD=y
CONFIG_OMAP_CF=y
CONFIG_ARCH_U300=y
CONFIG_MACH_U300=y
CONFIG_MACH_U300_BS335=y
-CONFIG_MACH_U300_DUAL_RAM=y
-CONFIG_U300_DEBUG=y
CONFIG_MACH_U300_SPIDUMMY=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_CMDLINE="root=/dev/ram0 rw rootfstype=rootfs console=ttyAMA0,115200n8 lpj=515072"
CONFIG_CPU_IDLE=y
CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
# CONFIG_SUSPEND is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_MISC_DEVICES is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSMC=y
# CONFIG_INPUT_MOUSEDEV is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_KEYBOARD_ATKBD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
+CONFIG_LEGACY_PTY_COUNT=16
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=16
# CONFIG_HW_RANDOM is not set
CONFIG_I2C=y
# CONFIG_HWMON is not set
# CONFIG_HID_SUPPORT is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_MMC=y
+CONFIG_MMC_CLKGATE=y
CONFIG_MMC_ARMMMCI=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_NLS_ISO8859_1=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_TIMER_STATS=y
# CONFIG_DEBUG_PREEMPT is not set
CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
# CONFIG_CRC32 is not set
CONFIG_ARCH_U8500=y
CONFIG_UX500_SOC_DB5500=y
CONFIG_UX500_SOC_DB8500=y
-CONFIG_MACH_U8500=y
+CONFIG_MACH_HREFV60=y
CONFIG_MACH_SNOWBALL=y
CONFIG_MACH_U5500=y
CONFIG_NO_HZ=y
CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
CONFIG_VFP=y
CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_AB8500_PWM=y
CONFIG_SENSORS_BH1780=y
CONFIG_NETDEVICES=y
-CONFIG_SMSC_PHY=y
-CONFIG_NET_ETHERNET=y
CONFIG_SMSC911X=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_SMSC_PHY=y
# CONFIG_WLAN is not set
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_EVDEV=y
CONFIG_SPI_PL022=y
CONFIG_GPIO_STMPE=y
CONFIG_GPIO_TC3589X=y
-# CONFIG_HWMON is not set
CONFIG_MFD_STMPE=y
CONFIG_MFD_TC3589X=y
+CONFIG_AB5500_CORE=y
CONFIG_AB8500_CORE=y
CONFIG_REGULATOR_AB8500=y
# CONFIG_HID_SUPPORT is not set
-CONFIG_USB_MUSB_HDRC=y
-CONFIG_USB_GADGET_MUSB_HDRC=y
-CONFIG_MUSB_PIO_ONLY=y
CONFIG_USB_GADGET=y
CONFIG_AB8500_USB=y
CONFIG_MMC=y
CONFIG_STE_DMA40=y
CONFIG_STAGING=y
CONFIG_TOUCHSCREEN_SYNAPTICS_I2C_RMI4=y
+CONFIG_HSEM_U8500=y
CONFIG_EXT2_FS=y
CONFIG_EXT2_FS_XATTR=y
CONFIG_EXT2_FS_POSIX_ACL=y
CONFIG_USB_SERIAL_GENERIC=y
CONFIG_USB_SERIAL_MCT_U232=m
CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
CONFIG_USB_ETH=m
CONFIG_USB_GADGETFS=m
CONFIG_USB_FILE_STORAGE=m
#ifndef __ASM_ARM_HARDWARE_L2X0_H
#define __ASM_ARM_HARDWARE_L2X0_H
+#include <linux/errno.h>
+
#define L2X0_CACHE_ID 0x000
#define L2X0_CACHE_TYPE 0x004
#define L2X0_CTRL 0x100
struct tag;
struct meminfo;
struct sys_timer;
+struct pt_regs;
struct machine_desc {
unsigned int nr; /* architecture number */
extern void
release_pmu(enum arm_pmu_type type);
-/**
- * init_pmu() - Initialise the PMU.
- *
- * Initialise the system ready for PMU enabling. This should typically set the
- * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do
- * the actual hardware initialisation.
- */
-extern int
-init_pmu(enum arm_pmu_type type);
-
#else /* CONFIG_CPU_HAS_PMU */
#include <linux/err.h>
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+const struct cpumask *cpu_coregroup_mask(int cpu);
#else
#define __NR_syncfs (__NR_SYSCALL_BASE+373)
#define __NR_sendmmsg (__NR_SYSCALL_BASE+374)
#define __NR_setns (__NR_SYSCALL_BASE+375)
+#define __NR_process_vm_readv (__NR_SYSCALL_BASE+376)
+#define __NR_process_vm_writev (__NR_SYSCALL_BASE+377)
/*
* The following SWIs are ARM private.
};
struct unwind_idx {
- unsigned long addr;
+ unsigned long addr_offset;
unsigned long insn;
};
struct unwind_table {
struct list_head list;
- struct unwind_idx *start;
- struct unwind_idx *stop;
+ const struct unwind_idx *start;
+ const struct unwind_idx *origin;
+ const struct unwind_idx *stop;
unsigned long begin_addr;
unsigned long end_addr;
};
extern void unwind_table_del(struct unwind_table *tab);
extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk);
-#ifdef CONFIG_ARM_UNWIND
-extern int __init unwind_init(void);
-#else
-static inline int __init unwind_init(void)
-{
- return 0;
-}
-#endif
-
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_ARM_UNWIND
CALL(sys_syncfs)
CALL(sys_sendmmsg)
/* 375 */ CALL(sys_setns)
+ CALL(sys_process_vm_readv)
+ CALL(sys_process_vm_writev)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
.popsection
.pushsection __ex_table,"a"
.long 1b, 4b
-#if __LINUX_ARM_ARCH__ >= 7
+#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
.long 2b, 4b
.long 3b, 4b
#endif
* r13 = *virtual* address to jump to upon completion
*/
__enable_mmu:
-#ifdef CONFIG_ALIGNMENT_TRAP
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
orr r0, r0, #CR_A
#else
bic r0, r0, #CR_A
static const union decode_item arm_cccc_0001_____1001_table[] = {
/* Synchronization primitives */
+#if __LINUX_ARM_ARCH__ < 6
+ /* Deprecated on ARMv6 and may be UNDEFINED on v7 */
/* SMP/SWPB cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */
DECODE_EMULATEX (0x0fb000f0, 0x01000090, emulate_rd12rn16rm0_rwflags_nopc,
REGS(NOPC, NOPC, 0, 0, NOPC)),
-
+#endif
/* LDREX/STREX{,D,B,H} cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */
/* And unallocated instructions... */
DECODE_END
TEST_GROUP("Synchronization primitives")
- /*
- * Use hard coded constants for SWP instructions to avoid warnings
- * about deprecated instructions.
- */
- TEST_RP( ".word 0xe108e097 @ swp lr, r",7,VAL2,", [r",8,0,"]")
- TEST_R( ".word 0x610d0091 @ swpvs r0, r",1,VAL1,", [sp]")
- TEST_RP( ".word 0xe10cd09e @ swp sp, r",14,VAL2,", [r",12,13*4,"]")
+#if __LINUX_ARM_ARCH__ < 6
+ TEST_RP("swp lr, r",7,VAL2,", [r",8,0,"]")
+ TEST_R( "swpvs r0, r",1,VAL1,", [sp]")
+ TEST_RP("swp sp, r",14,VAL2,", [r",12,13*4,"]")
+#else
+ TEST_UNSUPPORTED(".word 0xe108e097 @ swp lr, r7, [r8]")
+ TEST_UNSUPPORTED(".word 0x610d0091 @ swpvs r0, r1, [sp]")
+ TEST_UNSUPPORTED(".word 0xe10cd09e @ swp sp, r14 [r12]")
+#endif
TEST_UNSUPPORTED(".word 0xe102f091 @ swp pc, r1, [r2]")
TEST_UNSUPPORTED(".word 0xe102009f @ swp r0, pc, [r2]")
TEST_UNSUPPORTED(".word 0xe10f0091 @ swp r0, r1, [pc]")
- TEST_RP( ".word 0xe148e097 @ swpb lr, r",7,VAL2,", [r",8,0,"]")
- TEST_R( ".word 0x614d0091 @ swpvsb r0, r",1,VAL1,", [sp]")
+#if __LINUX_ARM_ARCH__ < 6
+ TEST_RP("swpb lr, r",7,VAL2,", [r",8,0,"]")
+ TEST_R( "swpvsb r0, r",1,VAL1,", [sp]")
+#else
+ TEST_UNSUPPORTED(".word 0xe148e097 @ swpb lr, r7, [r8]")
+ TEST_UNSUPPORTED(".word 0x614d0091 @ swpvsb r0, r1, [sp]")
+#endif
TEST_UNSUPPORTED(".word 0xe142f091 @ swpb pc, r1, [r2]")
TEST_UNSUPPORTED(".word 0xe1100090") /* Unallocated space */
TEST_RPR( "strccd r",8, VAL2,", [r",13,0, ", r",12,48,"]")
TEST_RPR( "strd r",4, VAL1,", [r",2, 24,", r",3, 48,"]!")
TEST_RPR( "strcsd r",12,VAL2,", [r",11,48,", -r",10,24,"]!")
- TEST_RPR( "strd r",2, VAL1,", [r",3, 24,"], r",4,48,"")
+ TEST_RPR( "strd r",2, VAL1,", [r",5, 24,"], r",4,48,"")
TEST_RPR( "strd r",10,VAL2,", [r",9, 48,"], -r",7,24,"")
TEST_UNSUPPORTED(".word 0xe1afc0fa @ strd r12, [pc, r10]!")
DONT_TEST_IN_ITBLOCK(
TEST_BF_R( "cbnz r",0,0, ", 2f")
TEST_BF_R( "cbz r",2,-1,", 2f")
- TEST_BF_RX( "cbnz r",4,1, ", 2f",0x20)
- TEST_BF_RX( "cbz r",7,0, ", 2f",0x40)
+ TEST_BF_RX( "cbnz r",4,1, ", 2f", SPACE_0x20)
+ TEST_BF_RX( "cbz r",7,0, ", 2f", SPACE_0x40)
)
TEST_R("sxth r0, r",7, HH1,"")
TEST_R("sxth r7, r",0, HH2,"")
TESTCASE_START(code) \
TEST_ARG_PTR(13, offset) \
TEST_ARG_END("") \
- TEST_BRANCH_F(code,0) \
+ TEST_BRANCH_F(code) \
TESTCASE_END
TEST("push {r0}")
TEST_BF( "b 2f")
TEST_BB( "b 2b")
- TEST_BF_X("b 2f", 0x400)
- TEST_BB_X("b 2b", 0x400)
+ TEST_BF_X("b 2f", SPACE_0x400)
+ TEST_BB_X("b 2b", SPACE_0x400)
TEST_GROUP("Testing instructions in IT blocks")
TEST_BB("bne.w 2b")
TEST_BF("bgt.w 2f")
TEST_BB("blt.w 2b")
- TEST_BF_X("bpl.w 2f",0x1000)
+ TEST_BF_X("bpl.w 2f", SPACE_0x1000)
)
TEST_UNSUPPORTED("msr cpsr, r0")
TEST_BF( "b.w 2f")
TEST_BB( "b.w 2b")
- TEST_BF_X("b.w 2f", 0x1000)
+ TEST_BF_X("b.w 2f", SPACE_0x1000)
TEST_BF( "bl.w 2f")
TEST_BB( "bl.w 2b")
- TEST_BB_X("bl.w 2b", 0x1000)
+ TEST_BB_X("bl.w 2b", SPACE_0x1000)
TEST_X( "blx __dummy_arm_subroutine",
".arm \n\t"
"1: "instruction" \n\t" \
" nop \n\t"
-#define TEST_BRANCH_F(instruction, xtra_dist) \
+#define TEST_BRANCH_F(instruction) \
TEST_INSTRUCTION(instruction) \
- ".if "#xtra_dist" \n\t" \
" b 99f \n\t" \
- ".space "#xtra_dist" \n\t" \
- ".endif \n\t" \
+ "2: nop \n\t"
+
+#define TEST_BRANCH_B(instruction) \
+ " b 50f \n\t" \
+ " b 99f \n\t" \
+ "2: nop \n\t" \
+ " b 99f \n\t" \
+ TEST_INSTRUCTION(instruction)
+
+#define TEST_BRANCH_FX(instruction, codex) \
+ TEST_INSTRUCTION(instruction) \
+ " b 99f \n\t" \
+ codex" \n\t" \
" b 99f \n\t" \
"2: nop \n\t"
-#define TEST_BRANCH_B(instruction, xtra_dist) \
+#define TEST_BRANCH_BX(instruction, codex) \
" b 50f \n\t" \
" b 99f \n\t" \
"2: nop \n\t" \
" b 99f \n\t" \
- ".if "#xtra_dist" \n\t" \
- ".space "#xtra_dist" \n\t" \
- ".endif \n\t" \
+ codex" \n\t" \
TEST_INSTRUCTION(instruction)
#define TESTCASE_END \
TESTCASE_START(code1 #reg1 code2) \
TEST_ARG_PTR(reg1, val1) \
TEST_ARG_END("") \
- TEST_BRANCH_F(code1 #reg1 code2, 0) \
+ TEST_BRANCH_F(code1 #reg1 code2) \
TESTCASE_END
-#define TEST_BF_X(code, xtra_dist) \
+#define TEST_BF(code) \
TESTCASE_START(code) \
TEST_ARG_END("") \
- TEST_BRANCH_F(code, xtra_dist) \
+ TEST_BRANCH_F(code) \
TESTCASE_END
-#define TEST_BB_X(code, xtra_dist) \
+#define TEST_BB(code) \
TESTCASE_START(code) \
TEST_ARG_END("") \
- TEST_BRANCH_B(code, xtra_dist) \
+ TEST_BRANCH_B(code) \
TESTCASE_END
-#define TEST_BF_RX(code1, reg, val, code2, xtra_dist) \
- TESTCASE_START(code1 #reg code2) \
- TEST_ARG_REG(reg, val) \
- TEST_ARG_END("") \
- TEST_BRANCH_F(code1 #reg code2, xtra_dist) \
+#define TEST_BF_R(code1, reg, val, code2) \
+ TESTCASE_START(code1 #reg code2) \
+ TEST_ARG_REG(reg, val) \
+ TEST_ARG_END("") \
+ TEST_BRANCH_F(code1 #reg code2) \
TESTCASE_END
-#define TEST_BB_RX(code1, reg, val, code2, xtra_dist) \
- TESTCASE_START(code1 #reg code2) \
- TEST_ARG_REG(reg, val) \
- TEST_ARG_END("") \
- TEST_BRANCH_B(code1 #reg code2, xtra_dist) \
+#define TEST_BB_R(code1, reg, val, code2) \
+ TESTCASE_START(code1 #reg code2) \
+ TEST_ARG_REG(reg, val) \
+ TEST_ARG_END("") \
+ TEST_BRANCH_B(code1 #reg code2) \
TESTCASE_END
-#define TEST_BF(code) TEST_BF_X(code, 0)
-#define TEST_BB(code) TEST_BB_X(code, 0)
-
-#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0)
-#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0)
-
#define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3) \
TESTCASE_START(code1 #reg1 code2 #reg2 code3) \
TEST_ARG_REG(reg1, val1) \
TEST_ARG_REG(reg2, val2) \
TEST_ARG_END("") \
- TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0) \
+ TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3) \
+ TESTCASE_END
+
+#define TEST_BF_X(code, codex) \
+ TESTCASE_START(code) \
+ TEST_ARG_END("") \
+ TEST_BRANCH_FX(code, codex) \
+ TESTCASE_END
+
+#define TEST_BB_X(code, codex) \
+ TESTCASE_START(code) \
+ TEST_ARG_END("") \
+ TEST_BRANCH_BX(code, codex) \
+ TESTCASE_END
+
+#define TEST_BF_RX(code1, reg, val, code2, codex) \
+ TESTCASE_START(code1 #reg code2) \
+ TEST_ARG_REG(reg, val) \
+ TEST_ARG_END("") \
+ TEST_BRANCH_FX(code1 #reg code2, codex) \
TESTCASE_END
#define TEST_X(code, codex) \
TESTCASE_END
+/*
+ * Macros for defining space directives spread over multiple lines.
+ * These are required so the compiler guesses better the length of inline asm
+ * code and will spill the literal pool early enough to avoid generating PC
+ * relative loads with out of range offsets.
+ */
+#define TWICE(x) x x
+#define SPACE_0x8 TWICE(".space 4\n\t")
+#define SPACE_0x10 TWICE(SPACE_0x8)
+#define SPACE_0x20 TWICE(SPACE_0x10)
+#define SPACE_0x40 TWICE(SPACE_0x20)
+#define SPACE_0x80 TWICE(SPACE_0x40)
+#define SPACE_0x100 TWICE(SPACE_0x80)
+#define SPACE_0x200 TWICE(SPACE_0x100)
+#define SPACE_0x400 TWICE(SPACE_0x200)
+#define SPACE_0x800 TWICE(SPACE_0x400)
+#define SPACE_0x1000 TWICE(SPACE_0x800)
+
+
/* Various values used in test cases... */
#define N(val) (val ^ 0xffffffff)
#define VAL1 0x12345678
int machine_kexec_prepare(struct kimage *image)
{
- unsigned long page_list;
- void *reboot_code_buffer;
- page_list = image->head & PAGE_MASK;
-
- reboot_code_buffer = page_address(image->control_code_page);
-
- /* Prepare parameters for reboot_code_buffer*/
- kexec_start_address = image->start;
- kexec_indirection_page = page_list;
- kexec_mach_type = machine_arch_type;
- kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
-
- /* copy our kernel relocation code to the control code page */
- memcpy(reboot_code_buffer,
- relocate_new_kernel, relocate_new_kernel_size);
-
- flush_icache_range((unsigned long) reboot_code_buffer,
- (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
return 0;
}
void machine_kexec(struct kimage *image)
{
+ unsigned long page_list;
unsigned long reboot_code_buffer_phys;
void *reboot_code_buffer;
+
+ page_list = image->head & PAGE_MASK;
+
/* we need both effective and real address here */
reboot_code_buffer_phys =
page_to_pfn(image->control_code_page) << PAGE_SHIFT;
reboot_code_buffer = page_address(image->control_code_page);
+ /* Prepare parameters for reboot_code_buffer*/
+ kexec_start_address = image->start;
+ kexec_indirection_page = page_list;
+ kexec_mach_type = machine_arch_type;
+ kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
+
+ /* copy our kernel relocation code to the control code page */
+ memcpy(reboot_code_buffer,
+ relocate_new_kernel, relocate_new_kernel_size);
+
+
+ flush_icache_range((unsigned long) reboot_code_buffer,
+ (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
printk(KERN_INFO "Bye!\n");
if (kexec_reinit)
{
struct perf_event *sibling, *leader = event->group_leader;
struct pmu_hw_events fake_pmu;
+ DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
- memset(&fake_pmu, 0, sizeof(fake_pmu));
+ /*
+ * Initialise the fake PMU. We only need to populate the
+ * used_mask for the purposes of validation.
+ */
+ memset(fake_used_mask, 0, sizeof(fake_used_mask));
+ fake_pmu.used_mask = fake_used_mask;
if (!validate_event(&fake_pmu, leader))
- return -ENOSPC;
+ return -EINVAL;
list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
if (!validate_event(&fake_pmu, sibling))
- return -ENOSPC;
+ return -EINVAL;
}
if (!validate_event(&fake_pmu, event))
- return -ENOSPC;
+ return -EINVAL;
return 0;
}
int i, err, irq, irqs;
struct platform_device *pmu_device = armpmu->plat_device;
+ if (!pmu_device)
+ return -ENODEV;
+
err = reserve_pmu(armpmu->type);
if (err) {
pr_warning("unable to reserve pmu\n");
static int __devinit armpmu_device_probe(struct platform_device *pdev)
{
+ if (!cpu_pmu)
+ return -ENODEV;
+
cpu_pmu->plat_device = pdev;
return 0;
}
{
clear_bit_unlock(type, pmu_lock);
}
+EXPORT_SYMBOL_GPL(release_pmu);
#endif
local_irq_disable();
+#ifdef CONFIG_PL310_ERRATA_769419
+ wmb();
+#endif
if (hlt_counter) {
local_irq_enable();
cpu_relax();
cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
proc_arch[cpu_architecture()], cr_alignment);
- sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
- sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
+ snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
+ list->arch_name, ENDIANNESS);
+ snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
+ list->elf_name, ENDIANNESS);
elf_hwcap = list->elf_hwcap;
#ifndef CONFIG_ARM_THUMB
elf_hwcap &= ~HWCAP_THUMB;
{
struct machine_desc *mdesc;
- unwind_init();
-
setup_processor();
mdesc = setup_machine_fdt(__atags_pointer);
if (!mdesc)
machine_desc = mdesc;
machine_name = mdesc->name;
+#ifdef CONFIG_ZONE_DMA
+ if (mdesc->dma_zone_size) {
+ extern unsigned long arm_dma_zone_size;
+ arm_dma_zone_size = mdesc->dma_zone_size;
+ }
+#endif
if (mdesc->soft_reboot)
reboot_setup("s");
tcm_init();
-#ifdef CONFIG_ZONE_DMA
- if (mdesc->dma_zone_size) {
- extern unsigned long arm_dma_zone_size;
- arm_dma_zone_size = mdesc->dma_zone_size;
- }
-#endif
#ifdef CONFIG_MULTI_IRQ_HANDLER
handle_arch_irq = mdesc->handle_irq;
#endif
struct cputopo_arm cpu_topology[NR_CPUS];
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_topology[cpu].core_sibling;
}
struct unwind_ctrl_block {
unsigned long vrs[16]; /* virtual register set */
- unsigned long *insn; /* pointer to the current instructions word */
+ const unsigned long *insn; /* pointer to the current instructions word */
int entries; /* number of entries left to interpret */
int byte; /* current byte number in the instructions word */
};
PC = 15
};
-extern struct unwind_idx __start_unwind_idx[];
-extern struct unwind_idx __stop_unwind_idx[];
+extern const struct unwind_idx __start_unwind_idx[];
+static const struct unwind_idx *__origin_unwind_idx;
+extern const struct unwind_idx __stop_unwind_idx[];
static DEFINE_SPINLOCK(unwind_lock);
static LIST_HEAD(unwind_tables);
})
/*
- * Binary search in the unwind index. The entries entries are
+ * Binary search in the unwind index. The entries are
* guaranteed to be sorted in ascending order by the linker.
+ *
+ * start = first entry
+ * origin = first entry with positive offset (or stop if there is no such entry)
+ * stop - 1 = last entry
*/
-static struct unwind_idx *search_index(unsigned long addr,
- struct unwind_idx *first,
- struct unwind_idx *last)
+static const struct unwind_idx *search_index(unsigned long addr,
+ const struct unwind_idx *start,
+ const struct unwind_idx *origin,
+ const struct unwind_idx *stop)
{
- pr_debug("%s(%08lx, %p, %p)\n", __func__, addr, first, last);
+ unsigned long addr_prel31;
+
+ pr_debug("%s(%08lx, %p, %p, %p)\n",
+ __func__, addr, start, origin, stop);
+
+ /*
+ * only search in the section with the matching sign. This way the
+ * prel31 numbers can be compared as unsigned longs.
+ */
+ if (addr < (unsigned long)start)
+ /* negative offsets: [start; origin) */
+ stop = origin;
+ else
+ /* positive offsets: [origin; stop) */
+ start = origin;
+
+ /* prel31 for address relavive to start */
+ addr_prel31 = (addr - (unsigned long)start) & 0x7fffffff;
- if (addr < first->addr) {
+ while (start < stop - 1) {
+ const struct unwind_idx *mid = start + ((stop - start) >> 1);
+
+ /*
+ * As addr_prel31 is relative to start an offset is needed to
+ * make it relative to mid.
+ */
+ if (addr_prel31 - ((unsigned long)mid - (unsigned long)start) <
+ mid->addr_offset)
+ stop = mid;
+ else {
+ /* keep addr_prel31 relative to start */
+ addr_prel31 -= ((unsigned long)mid -
+ (unsigned long)start);
+ start = mid;
+ }
+ }
+
+ if (likely(start->addr_offset <= addr_prel31))
+ return start;
+ else {
pr_warning("unwind: Unknown symbol address %08lx\n", addr);
return NULL;
- } else if (addr >= last->addr)
- return last;
+ }
+}
- while (first < last - 1) {
- struct unwind_idx *mid = first + ((last - first + 1) >> 1);
+static const struct unwind_idx *unwind_find_origin(
+ const struct unwind_idx *start, const struct unwind_idx *stop)
+{
+ pr_debug("%s(%p, %p)\n", __func__, start, stop);
+ while (start < stop) {
+ const struct unwind_idx *mid = start + ((stop - start) >> 1);
- if (addr < mid->addr)
- last = mid;
+ if (mid->addr_offset >= 0x40000000)
+ /* negative offset */
+ start = mid + 1;
else
- first = mid;
+ /* positive offset */
+ stop = mid;
}
-
- return first;
+ pr_debug("%s -> %p\n", __func__, stop);
+ return stop;
}
-static struct unwind_idx *unwind_find_idx(unsigned long addr)
+static const struct unwind_idx *unwind_find_idx(unsigned long addr)
{
- struct unwind_idx *idx = NULL;
+ const struct unwind_idx *idx = NULL;
unsigned long flags;
pr_debug("%s(%08lx)\n", __func__, addr);
- if (core_kernel_text(addr))
+ if (core_kernel_text(addr)) {
+ if (unlikely(!__origin_unwind_idx))
+ __origin_unwind_idx =
+ unwind_find_origin(__start_unwind_idx,
+ __stop_unwind_idx);
+
/* main unwind table */
idx = search_index(addr, __start_unwind_idx,
- __stop_unwind_idx - 1);
- else {
+ __origin_unwind_idx,
+ __stop_unwind_idx);
+ } else {
/* module unwind tables */
struct unwind_table *table;
if (addr >= table->begin_addr &&
addr < table->end_addr) {
idx = search_index(addr, table->start,
- table->stop - 1);
+ table->origin,
+ table->stop);
/* Move-to-front to exploit common traces */
list_move(&table->list, &unwind_tables);
break;
int unwind_frame(struct stackframe *frame)
{
unsigned long high, low;
- struct unwind_idx *idx;
+ const struct unwind_idx *idx;
struct unwind_ctrl_block ctrl;
/* only go to a higher address on the stack */
unsigned long text_size)
{
unsigned long flags;
- struct unwind_idx *idx;
struct unwind_table *tab = kmalloc(sizeof(*tab), GFP_KERNEL);
pr_debug("%s(%08lx, %08lx, %08lx, %08lx)\n", __func__, start, size,
if (!tab)
return tab;
- tab->start = (struct unwind_idx *)start;
- tab->stop = (struct unwind_idx *)(start + size);
+ tab->start = (const struct unwind_idx *)start;
+ tab->stop = (const struct unwind_idx *)(start + size);
+ tab->origin = unwind_find_origin(tab->start, tab->stop);
tab->begin_addr = text_addr;
tab->end_addr = text_addr + text_size;
- /* Convert the symbol addresses to absolute values */
- for (idx = tab->start; idx < tab->stop; idx++)
- idx->addr = prel31_to_addr(&idx->addr);
-
spin_lock_irqsave(&unwind_lock, flags);
list_add_tail(&tab->list, &unwind_tables);
spin_unlock_irqrestore(&unwind_lock, flags);
kfree(tab);
}
-
-int __init unwind_init(void)
-{
- struct unwind_idx *idx;
-
- /* Convert the symbol addresses to absolute values */
- for (idx = __start_unwind_idx; idx < __stop_unwind_idx; idx++)
- idx->addr = prel31_to_addr(&idx->addr);
-
- pr_debug("unwind: ARM stack unwinding initialised\n");
-
- return 0;
-}
+#include <asm/unwind.h>
+
#if __LINUX_ARM_ARCH__ >= 6
- .macro bitop, instr
+ .macro bitop, name, instr
+ENTRY( \name )
+UNWIND( .fnstart )
ands ip, r1, #3
strneb r1, [ip] @ assert word-aligned
mov r2, #1
cmp r0, #0
bne 1b
bx lr
+UNWIND( .fnend )
+ENDPROC(\name )
.endm
- .macro testop, instr, store
+ .macro testop, name, instr, store
+ENTRY( \name )
+UNWIND( .fnstart )
ands ip, r1, #3
strneb r1, [ip] @ assert word-aligned
mov r2, #1
cmp r0, #0
movne r0, #1
2: bx lr
+UNWIND( .fnend )
+ENDPROC(\name )
.endm
#else
- .macro bitop, instr
+ .macro bitop, name, instr
+ENTRY( \name )
+UNWIND( .fnstart )
ands ip, r1, #3
strneb r1, [ip] @ assert word-aligned
and r2, r0, #31
str r2, [r1, r0, lsl #2]
restore_irqs ip
mov pc, lr
+UNWIND( .fnend )
+ENDPROC(\name )
.endm
/**
* Note: we can trivially conditionalise the store instruction
* to avoid dirtying the data cache.
*/
- .macro testop, instr, store
+ .macro testop, name, instr, store
+ENTRY( \name )
+UNWIND( .fnstart )
ands ip, r1, #3
strneb r1, [ip] @ assert word-aligned
and r3, r0, #31
moveq r0, #0
restore_irqs ip
mov pc, lr
+UNWIND( .fnend )
+ENDPROC(\name )
.endm
#endif
#include "bitops.h"
.text
-ENTRY(_change_bit)
- bitop eor
-ENDPROC(_change_bit)
+bitop _change_bit, eor
#include "bitops.h"
.text
-ENTRY(_clear_bit)
- bitop bic
-ENDPROC(_clear_bit)
+bitop _clear_bit, bic
#include "bitops.h"
.text
-ENTRY(_set_bit)
- bitop orr
-ENDPROC(_set_bit)
+bitop _set_bit, orr
#include "bitops.h"
.text
-ENTRY(_test_and_change_bit)
- testop eor, str
-ENDPROC(_test_and_change_bit)
+testop _test_and_change_bit, eor, str
#include "bitops.h"
.text
-ENTRY(_test_and_clear_bit)
- testop bicne, strne
-ENDPROC(_test_and_clear_bit)
+testop _test_and_clear_bit, bicne, strne
#include "bitops.h"
.text
-ENTRY(_test_and_set_bit)
- testop orreq, streq
-ENDPROC(_test_and_set_bit)
+testop _test_and_set_bit, orreq, streq
* USB Device (Gadget)
* -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
static struct at91_udc_data udc_data;
static struct resource udc_resources[] = {
CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
- CLKDEV_CON_DEV_ID("t3_clk", "atmel_tcb.1", &tc3_clk),
- CLKDEV_CON_DEV_ID("t4_clk", "atmel_tcb.1", &tc4_clk),
- CLKDEV_CON_DEV_ID("t5_clk", "atmel_tcb.1", &tc5_clk),
+ CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
+ CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
+ CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc_clk),
/* more usart lookup table for DT entries */
CLKDEV_CON_DEV_ID("usart", "fffff200.serial", &mck),
* USB Device (Gadget)
* -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
static struct at91_udc_data udc_data;
static struct resource udc_resources[] = {
* USB Device (Gadget)
* -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
static struct at91_udc_data udc_data;
static struct resource udc_resources[] = {
* USB Device (Gadget)
* -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
static struct at91_udc_data udc_data;
static struct resource udc_resources[] = {
#define BOARD_HAVE_NAND_16BIT (1 << 31)
static inline int board_have_nand_16bit(void)
{
- return system_rev & BOARD_HAVE_NAND_16BIT;
+ return (system_rev & BOARD_HAVE_NAND_16BIT) ? 1 : 0;
}
#endif /* __ARCH_SYSTEM_REV_H__ */
*/
bcmring_clocksource_init();
- sp804_clockevents_register(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
+ sp804_clockevents_init(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
}
struct sys_timer bcmring_timer = {
#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/atomic.h>
+#include <linux/sched.h>
#include <mach/dma.h>
/* I don't quite understand why dc4 fails when this is set to 1 and DMA is enabled */
.num_serializer = ARRAY_SIZE(da850_iis_serializer_direction),
.tdm_slots = 2,
.serial_dir = da850_iis_serializer_direction,
- .asp_chan_q = EVENTQ_1,
+ .asp_chan_q = EVENTQ_0,
.version = MCASP_VERSION_2,
.txnumevt = 1,
.rxnumevt = 1,
/* UBL (a few copies) plus U-Boot */
.name = "bootloader",
.offset = 0,
- .size = 28 * NAND_BLOCK_SIZE,
+ .size = 30 * NAND_BLOCK_SIZE,
.mask_flags = MTD_WRITEABLE, /* force read-only */
}, {
/* U-Boot environment */
int val;
u32 value;
- if (!vpif_vsclkdis_reg || !cpld_client)
+ if (!vpif_vidclkctl_reg || !cpld_client)
return -ENXIO;
val = i2c_smbus_read_byte(cpld_client);
return val;
spin_lock_irqsave(&vpif_reg_lock, flags);
- value = __raw_readl(vpif_vsclkdis_reg);
+ value = __raw_readl(vpif_vidclkctl_reg);
if (mux_mode) {
val &= VPIF_INPUT_TWO_CHANNEL;
value |= VIDCH1CLK;
val |= VPIF_INPUT_ONE_CHANNEL;
value &= ~VIDCH1CLK;
}
- __raw_writel(value, vpif_vsclkdis_reg);
+ __raw_writel(value, vpif_vidclkctl_reg);
spin_unlock_irqrestore(&vpif_reg_lock, flags);
err = i2c_smbus_write_byte(cpld_client, val);
.name = "dsp",
.parent = &pll1_sysclk1,
.lpsc = DM646X_LPSC_C64X_CPU,
- .flags = PSC_DSP,
.usecount = 1, /* REVISIT how to disable? */
};
#define PTCMD 0x120
#define PTSTAT 0x128
#define PDSTAT 0x200
-#define PDCTL1 0x304
+#define PDCTL 0x300
#define MDSTAT 0x800
#define MDCTL 0xA00
#define PSC_STATE_ENABLE 3
#define MDSTAT_STATE_MASK 0x3f
+#define PDSTAT_STATE_MASK 0x1f
#define MDCTL_FORCE BIT(31)
+#define PDCTL_NEXT BIT(1)
+#define PDCTL_EPCGOOD BIT(8)
#ifndef __ASSEMBLER__
void davinci_psc_config(unsigned int domain, unsigned int ctlr,
unsigned int id, bool enable, u32 flags)
{
- u32 epcpr, ptcmd, ptstat, pdstat, pdctl1, mdstat, mdctl;
+ u32 epcpr, ptcmd, ptstat, pdstat, pdctl, mdstat, mdctl;
void __iomem *psc_base;
struct davinci_soc_info *soc_info = &davinci_soc_info;
u32 next_state = PSC_STATE_ENABLE;
mdctl |= MDCTL_FORCE;
__raw_writel(mdctl, psc_base + MDCTL + 4 * id);
- pdstat = __raw_readl(psc_base + PDSTAT);
- if ((pdstat & 0x00000001) == 0) {
- pdctl1 = __raw_readl(psc_base + PDCTL1);
- pdctl1 |= 0x1;
- __raw_writel(pdctl1, psc_base + PDCTL1);
+ pdstat = __raw_readl(psc_base + PDSTAT + 4 * domain);
+ if ((pdstat & PDSTAT_STATE_MASK) == 0) {
+ pdctl = __raw_readl(psc_base + PDCTL + 4 * domain);
+ pdctl |= PDCTL_NEXT;
+ __raw_writel(pdctl, psc_base + PDCTL + 4 * domain);
ptcmd = 1 << domain;
__raw_writel(ptcmd, psc_base + PTCMD);
epcpr = __raw_readl(psc_base + EPCPR);
} while ((((epcpr >> domain) & 1) == 0));
- pdctl1 = __raw_readl(psc_base + PDCTL1);
- pdctl1 |= 0x100;
- __raw_writel(pdctl1, psc_base + PDCTL1);
+ pdctl = __raw_readl(psc_base + PDCTL + 4 * domain);
+ pdctl |= PDCTL_EPCGOOD;
+ __raw_writel(pdctl, psc_base + PDCTL + 4 * domain);
} else {
ptcmd = 1 << domain;
__raw_writel(ptcmd, psc_base + PTCMD);
.pfn = __phys_to_pfn(EXYNOS4_PA_DMC0),
.length = SZ_4K,
.type = MT_DEVICE,
- }, {
- .virtual = (unsigned long)S5P_VA_SROMC,
- .pfn = __phys_to_pfn(EXYNOS4_PA_SROMC),
- .length = SZ_4K,
- .type = MT_DEVICE,
}, {
.virtual = (unsigned long)S3C_VA_USB_HSPHY,
.pfn = __phys_to_pfn(EXYNOS4_PA_HSPHY),
#include <linux/init.h>
#include <linux/cpuidle.h>
#include <linux/io.h>
+#include <linux/export.h>
+#include <linux/time.h>
#include <asm/proc-fns.h>
char name[10];
};
-static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
-
static void exynos4_mct_write(unsigned int value, void *addr)
{
void __iomem *stat_addr;
}
#ifdef CONFIG_LOCAL_TIMERS
+
+static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
+
/* Clock event handling */
static void exynos4_mct_tick_stop(struct mct_clock_event_device *mevt)
{
void local_timer_stop(struct clock_event_device *evt)
{
+ unsigned int cpu = smp_processor_id();
evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
if (mct_int_type == MCT_INT_SPI)
- disable_irq(evt->irq);
+ if (cpu == 0)
+ remove_irq(evt->irq, &mct_tick0_event_irq);
+ else
+ remove_irq(evt->irq, &mct_tick1_event_irq);
else
disable_percpu_irq(IRQ_MCT_LOCALTIMER);
}
clk_rate = clk_get_rate(mct_clk);
+#ifdef CONFIG_LOCAL_TIMERS
if (mct_int_type == MCT_INT_PPI) {
int err;
WARN(err, "MCT: can't request IRQ %d (%d)\n",
IRQ_MCT_LOCALTIMER, err);
}
+#endif /* CONFIG_LOCAL_TIMERS */
}
static void __init exynos4_timer_init(void)
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/of_address.h>
+#include <linux/smp.h>
#include <asm/cacheflush.h>
#include <asm/unified.h>
void highbank_set_cpu_jump(int cpu, void *jump_addr)
{
+#ifdef CONFIG_SMP
+ cpu = cpu_logical_map(cpu);
+#endif
writel(BSYM(virt_to_phys(jump_addr)), HB_JUMP_TABLE_VIRT(cpu));
__cpuc_flush_dcache_area(HB_JUMP_TABLE_VIRT(cpu), 16);
outer_clean_range(HB_JUMP_TABLE_PHYS(cpu),
config HAVE_IMX_SRC
bool
-#
-# ARCH_MX31 and ARCH_MX35 are left for compatibility
-# Some usages assume that having one of them implies not having (e.g.) ARCH_MX2.
-# To easily distinguish good and reviewed from unreviewed usages new (and IMHO
-# more sensible) names are used: SOC_IMX31 and SOC_IMX35
config ARCH_MX1
bool
config MACH_MX27
bool
-config ARCH_MX31
- bool
-
-config ARCH_MX35
- bool
-
config SOC_IMX1
bool
select ARCH_MX1
select CPU_V6
select IMX_HAVE_PLATFORM_MXC_RNGA
select ARCH_MXC_AUDMUX_V2
- select ARCH_MX31
select MXC_AVIC
select SMP_ON_UP if SMP
select ARCH_MXC_IOMUX_V3
select ARCH_MXC_AUDMUX_V2
select HAVE_EPIT
- select ARCH_MX35
select MXC_AVIC
select SMP_ON_UP if SMP
select IMX_HAVE_PLATFORM_MXC_NAND
select IMX_HAVE_PLATFORM_SDHCI_ESDHC_IMX
-config MACH_EUKREA_CPUIMX25
+config MACH_EUKREA_CPUIMX25SD
bool "Support Eukrea CPUIMX25 Platform"
select SOC_IMX25
select IMX_HAVE_PLATFORM_FLEXCAN
choice
prompt "Baseboard"
- depends on MACH_EUKREA_CPUIMX25
+ depends on MACH_EUKREA_CPUIMX25SD
default MACH_EUKREA_MBIMXSD25_BASEBOARD
config MACH_EUKREA_MBIMXSD25_BASEBOARD
Include support for MX35PDK platform. This includes specific
configurations for the board and its peripherals.
-config MACH_EUKREA_CPUIMX35
+config MACH_EUKREA_CPUIMX35SD
bool "Support Eukrea CPUIMX35 Platform"
select SOC_IMX35
select IMX_HAVE_PLATFORM_FLEXCAN
choice
prompt "Baseboard"
- depends on MACH_EUKREA_CPUIMX35
+ depends on MACH_EUKREA_CPUIMX35SD
default MACH_EUKREA_MBIMXSD35_BASEBOARD
config MACH_EUKREA_MBIMXSD35_BASEBOARD
# i.MX25 based machines
obj-$(CONFIG_MACH_MX25_3DS) += mach-mx25_3ds.o
-obj-$(CONFIG_MACH_EUKREA_CPUIMX25) += mach-eukrea_cpuimx25.o
+obj-$(CONFIG_MACH_EUKREA_CPUIMX25SD) += mach-eukrea_cpuimx25.o
obj-$(CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD) += eukrea_mbimxsd25-baseboard.o
# i.MX27 based machines
# i.MX35 based machines
obj-$(CONFIG_MACH_PCM043) += mach-pcm043.o
obj-$(CONFIG_MACH_MX35_3DS) += mach-mx35_3ds.o
-obj-$(CONFIG_MACH_EUKREA_CPUIMX35) += mach-cpuimx35.o
+obj-$(CONFIG_MACH_EUKREA_CPUIMX35SD) += mach-cpuimx35.o
obj-$(CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD) += eukrea_mbimxsd35-baseboard.o
obj-$(CONFIG_MACH_VPR200) += mach-vpr200.o
int __init mx35_clocks_init()
{
- unsigned int cgr2 = 3 << 26, cgr3 = 0;
+ unsigned int cgr2 = 3 << 26;
#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC)
cgr2 |= 3 << 16;
__raw_writel((3 << 18), CCM_BASE + CCM_CGR0);
__raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16),
CCM_BASE + CCM_CGR1);
+ __raw_writel(cgr2, CCM_BASE + CCM_CGR2);
+ __raw_writel(0, CCM_BASE + CCM_CGR3);
+
+ clk_enable(&iim_clk);
+ imx_print_silicon_rev("i.MX35", mx35_revision());
+ clk_disable(&iim_clk);
/*
* Check if we came up in internal boot mode. If yes, we need some
*/
if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) {
/* Additionally turn on UART1, SCC, and IIM clocks */
- cgr2 |= 3 << 16 | 3 << 4;
- cgr3 |= 3 << 2;
+ clk_enable(&iim_clk);
+ clk_enable(&uart1_clk);
+ clk_enable(&scc_clk);
}
- __raw_writel(cgr2, CCM_BASE + CCM_CGR2);
- __raw_writel(cgr3, CCM_BASE + CCM_CGR3);
-
- clk_enable(&iim_clk);
- imx_print_silicon_rev("i.MX35", mx35_revision());
- clk_disable(&iim_clk);
-
#ifdef CONFIG_MXC_USE_EPIT
epit_timer_init(&epit1_clk,
MX35_IO_ADDRESS(MX35_EPIT1_BASE_ADDR), MX35_INT_EPIT1);
imx_map_entry(MX6Q, ANATOP, MT_DEVICE),
};
+void __init imx6q_clock_map_io(void)
+{
+ iotable_init(imx6q_clock_desc, ARRAY_SIZE(imx6q_clock_desc));
+}
+
int __init mx6q_clocks_init(void)
{
struct device_node *np;
void __iomem *base;
int i, irq;
- iotable_init(imx6q_clock_desc, ARRAY_SIZE(imx6q_clock_desc));
-
/* retrieve the freqency of fixed clocks from device tree */
for_each_compatible_node(np, NULL, "fixed-clock") {
u32 rate;
.bitrate = 100000,
};
+#define TSC2007_IRQGPIO IMX_GPIO_NR(3, 2)
+static int tsc2007_get_pendown_state(void)
+{
+ return !gpio_get_value(TSC2007_IRQGPIO);
+}
+
static struct tsc2007_platform_data tsc2007_info = {
.model = 2007,
.x_plate_ohms = 180,
+ .get_pendown_state = tsc2007_get_pendown_state,
};
-#define TSC2007_IRQGPIO IMX_GPIO_NR(3, 2)
static struct i2c_board_info eukrea_cpuimx35_i2c_devices[] = {
{
I2C_BOARD_INFO("pcf8563", 0x51),
{
imx_lluart_map_io();
imx_scu_map_io();
+ imx6q_clock_map_io();
}
-static void __init imx6q_gpio_add_irq_domain(struct device_node *np,
+static int __init imx6q_gpio_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
- static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
- 32 * 7; /* imx6q gets 7 gpio ports */
+ static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
+ gpio_irq_base -= 32;
irq_domain_add_simple(np, gpio_irq_base);
- gpio_irq_base += 32;
+
+ return 0;
}
static const struct of_device_id imx6q_irq_match[] __initconst = {
static void imx3_idle(void)
{
unsigned long reg = 0;
- __asm__ __volatile__(
- /* disable I and D cache */
- "mrc p15, 0, %0, c1, c0, 0\n"
- "bic %0, %0, #0x00001000\n"
- "bic %0, %0, #0x00000004\n"
- "mcr p15, 0, %0, c1, c0, 0\n"
- /* invalidate I cache */
- "mov %0, #0\n"
- "mcr p15, 0, %0, c7, c5, 0\n"
- /* clear and invalidate D cache */
- "mov %0, #0\n"
- "mcr p15, 0, %0, c7, c14, 0\n"
- /* WFI */
- "mov %0, #0\n"
- "mcr p15, 0, %0, c7, c0, 4\n"
- "nop\n" "nop\n" "nop\n" "nop\n"
- "nop\n" "nop\n" "nop\n"
- /* enable I and D cache */
- "mrc p15, 0, %0, c1, c0, 0\n"
- "orr %0, %0, #0x00001000\n"
- "orr %0, %0, #0x00000004\n"
- "mcr p15, 0, %0, c1, c0, 0\n"
- : "=r" (reg));
+
+ if (!need_resched())
+ __asm__ __volatile__(
+ /* disable I and D cache */
+ "mrc p15, 0, %0, c1, c0, 0\n"
+ "bic %0, %0, #0x00001000\n"
+ "bic %0, %0, #0x00000004\n"
+ "mcr p15, 0, %0, c1, c0, 0\n"
+ /* invalidate I cache */
+ "mov %0, #0\n"
+ "mcr p15, 0, %0, c7, c5, 0\n"
+ /* clear and invalidate D cache */
+ "mov %0, #0\n"
+ "mcr p15, 0, %0, c7, c14, 0\n"
+ /* WFI */
+ "mov %0, #0\n"
+ "mcr p15, 0, %0, c7, c0, 4\n"
+ "nop\n" "nop\n" "nop\n" "nop\n"
+ "nop\n" "nop\n" "nop\n"
+ /* enable I and D cache */
+ "mrc p15, 0, %0, c1, c0, 0\n"
+ "orr %0, %0, #0x00001000\n"
+ "orr %0, %0, #0x00000004\n"
+ "mcr p15, 0, %0, c1, c0, 0\n"
+ : "=r" (reg));
+ local_irq_enable();
}
static void __iomem *imx3_ioremap(unsigned long phys_addr, size_t size,
l2x0_init(l2x0_base, 0x00030024, 0x00000000);
}
+#ifdef CONFIG_SOC_IMX31
static struct map_desc mx31_io_desc[] __initdata = {
imx_map_entry(MX31, X_MEMC, MT_DEVICE),
imx_map_entry(MX31, AVIC, MT_DEVICE_NONSHARED),
iotable_init(mx31_io_desc, ARRAY_SIZE(mx31_io_desc));
}
-static struct map_desc mx35_io_desc[] __initdata = {
- imx_map_entry(MX35, X_MEMC, MT_DEVICE),
- imx_map_entry(MX35, AVIC, MT_DEVICE_NONSHARED),
- imx_map_entry(MX35, AIPS1, MT_DEVICE_NONSHARED),
- imx_map_entry(MX35, AIPS2, MT_DEVICE_NONSHARED),
- imx_map_entry(MX35, SPBA0, MT_DEVICE_NONSHARED),
-};
-
-void __init mx35_map_io(void)
-{
- iotable_init(mx35_io_desc, ARRAY_SIZE(mx35_io_desc));
-}
-
void __init imx31_init_early(void)
{
mxc_set_cpu_type(MXC_CPU_MX31);
mxc_arch_reset_init(MX31_IO_ADDRESS(MX31_WDOG_BASE_ADDR));
- imx_idle = imx3_idle;
- imx_ioremap = imx3_ioremap;
-}
-
-void __init imx35_init_early(void)
-{
- mxc_set_cpu_type(MXC_CPU_MX35);
- mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
- mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
- imx_idle = imx3_idle;
+ pm_idle = imx3_idle;
imx_ioremap = imx3_ioremap;
}
mxc_init_irq(MX31_IO_ADDRESS(MX31_AVIC_BASE_ADDR));
}
-void __init mx35_init_irq(void)
-{
- mxc_init_irq(MX35_IO_ADDRESS(MX35_AVIC_BASE_ADDR));
-}
-
static struct sdma_script_start_addrs imx31_to1_sdma_script __initdata = {
.per_2_per_addr = 1677,
};
imx_add_imx_sdma("imx31-sdma", MX31_SDMA_BASE_ADDR, MX31_INT_SDMA, &imx31_sdma_pdata);
}
+#endif /* ifdef CONFIG_SOC_IMX31 */
+
+#ifdef CONFIG_SOC_IMX35
+static struct map_desc mx35_io_desc[] __initdata = {
+ imx_map_entry(MX35, X_MEMC, MT_DEVICE),
+ imx_map_entry(MX35, AVIC, MT_DEVICE_NONSHARED),
+ imx_map_entry(MX35, AIPS1, MT_DEVICE_NONSHARED),
+ imx_map_entry(MX35, AIPS2, MT_DEVICE_NONSHARED),
+ imx_map_entry(MX35, SPBA0, MT_DEVICE_NONSHARED),
+};
+
+void __init mx35_map_io(void)
+{
+ iotable_init(mx35_io_desc, ARRAY_SIZE(mx35_io_desc));
+}
+
+void __init imx35_init_early(void)
+{
+ mxc_set_cpu_type(MXC_CPU_MX35);
+ mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
+ mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
+ pm_idle = imx3_idle;
+ imx_ioremap = imx3_ioremap;
+}
+
+void __init mx35_init_irq(void)
+{
+ mxc_init_irq(MX35_IO_ADDRESS(MX35_AVIC_BASE_ADDR));
+}
static struct sdma_script_start_addrs imx35_to1_sdma_script __initdata = {
.ap_2_ap_addr = 642,
imx_add_imx_sdma("imx35-sdma", MX35_SDMA_BASE_ADDR, MX35_INT_SDMA, &imx35_sdma_pdata);
}
+#endif /* ifdef CONFIG_SOC_IMX35 */
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/smp.h>
#include <asm/unified.h>
#define SRC_SCR 0x000
static void __iomem *src_base;
+#ifndef CONFIG_SMP
+#define cpu_logical_map(cpu) 0
+#endif
+
void imx_enable_cpu(int cpu, bool enable)
{
u32 mask, val;
+ cpu = cpu_logical_map(cpu);
mask = 1 << (BP_SRC_SCR_CORE1_ENABLE + cpu - 1);
val = readl_relaxed(src_base + SRC_SCR);
val = enable ? val | mask : val & ~mask;
void imx_set_cpu_jump(int cpu, void *jump_addr)
{
+ cpu = cpu_logical_map(cpu);
writel_relaxed(BSYM(virt_to_phys(jump_addr)),
src_base + SRC_GPR1 + cpu * 8);
}
/* on-chip devices */
pxa168_add_uart(3);
- pxa168_add_ssp(0);
+ pxa168_add_ssp(1);
pxa168_add_twsi(0, NULL, ARRAY_AND_SIZE(gplugd_i2c_board_info));
pxa168_add_eth(&gplugd_eth_platform_data);
#define GPIO_REGS_VIRT (APB_VIRT_BASE + 0x19000)
#define BANK_OFF(n) (((n) < 3) ? (n) << 2 : 0x100 + (((n) - 3) << 2))
-#define GPIO_REG(x) (GPIO_REGS_VIRT + (x))
+#define GPIO_REG(x) (*(volatile u32 *)(GPIO_REGS_VIRT + (x)))
#define NR_BUILTIN_GPIO IRQ_GPIO_NUM
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/bootmem.h>
+#include <linux/module.h>
#include <mach/irqs.h>
#include <mach/iommu.h>
{
iomux_v3_cfg_t usbh1stp = MX51_PAD_USBH1_STP__USBH1_STP;
iomux_v3_cfg_t power_key = NEW_PAD_CTRL(MX51_PAD_EIM_A27__GPIO2_21,
- PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH | PAD_CTL_PUS_100K_UP);
+ PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH);
imx51_soc_init();
gpio_set_value(MX53_EVK_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_evk_fec_pdata = {
+static const struct fec_platform_data mx53_evk_fec_pdata __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
gpio_set_value(LOCO_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_loco_fec_data = {
+static const struct fec_platform_data mx53_loco_fec_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
gpio_set_value(SMD_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_smd_fec_data = {
+static const struct fec_platform_data mx53_smd_fec_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
#include <linux/init.h>
#include <linux/module.h>
#include <mach/hardware.h>
-#include <asm/io.h>
+#include <linux/io.h>
static int mx5_cpu_rev = -1;
if (!cpu_is_mx51())
return 0;
- if (mx51_revision() < IMX_CHIP_REVISION_3_0 && (elf_hwcap & HWCAP_NEON)) {
+ if (mx51_revision() < IMX_CHIP_REVISION_3_0 &&
+ (elf_hwcap & HWCAP_NEON)) {
elf_hwcap &= ~HWCAP_NEON;
pr_info("Turning off NEON support, detected broken NEON implementation\n");
}
{ /* sentinel */ }
};
-static void __init imx51_tzic_add_irq_domain(struct device_node *np,
+static int __init imx51_tzic_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
irq_domain_add_simple(np, 0);
+ return 0;
}
-static void __init imx51_gpio_add_irq_domain(struct device_node *np,
+static int __init imx51_gpio_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
- static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
- 32 * 4; /* imx51 gets 4 gpio ports */
+ static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
+ gpio_irq_base -= 32;
irq_domain_add_simple(np, gpio_irq_base);
- gpio_irq_base += 32;
+
+ return 0;
}
static const struct of_device_id imx51_irq_match[] __initconst = {
{ /* sentinel */ }
};
-static void __init imx53_tzic_add_irq_domain(struct device_node *np,
+static int __init imx53_tzic_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
irq_domain_add_simple(np, 0);
+ return 0;
}
-static void __init imx53_gpio_add_irq_domain(struct device_node *np,
+static int __init imx53_gpio_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
- static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
- 32 * 7; /* imx53 gets 7 gpio ports */
+ static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
+ gpio_irq_base -= 32;
irq_domain_add_simple(np, gpio_irq_base);
- gpio_irq_base += 32;
+
+ return 0;
}
static const struct of_device_id imx53_irq_match[] __initconst = {
static void imx5_idle(void)
{
- mx5_cpu_lp_set(WAIT_UNCLOCKED_POWER_OFF);
+ if (!need_resched())
+ mx5_cpu_lp_set(WAIT_UNCLOCKED_POWER_OFF);
+ local_irq_enable();
}
/*
mxc_set_cpu_type(MXC_CPU_MX51);
mxc_iomux_v3_init(MX51_IO_ADDRESS(MX51_IOMUXC_BASE_ADDR));
mxc_arch_reset_init(MX51_IO_ADDRESS(MX51_WDOG1_BASE_ADDR));
- imx_idle = imx5_idle;
+ pm_idle = imx5_idle;
}
void __init imx53_init_early(void)
reg = __raw_readl(CLKCTRL_BASE_ADDR + HW_CLKCTRL_##dr); \
reg &= ~BM_CLKCTRL_##dr##_DIV; \
reg |= div << BP_CLKCTRL_##dr##_DIV; \
- if (reg | (1 << clk->enable_shift)) { \
+ if (reg & (1 << clk->enable_shift)) { \
pr_err("%s: clock is gated\n", __func__); \
return -EINVAL; \
} \
#define MX28_INT_CAN1 9
#define MX28_INT_LRADC_TOUCH 10
#define MX28_INT_HSADC 13
-#define MX28_INT_IRADC_THRESH0 14
-#define MX28_INT_IRADC_THRESH1 15
+#define MX28_INT_LRADC_THRESH0 14
+#define MX28_INT_LRADC_THRESH1 15
#define MX28_INT_LRADC_CH0 16
#define MX28_INT_LRADC_CH1 17
#define MX28_INT_LRADC_CH2 18
*/
#define cpu_is_mx23() ( \
machine_is_mx23evk() || \
+ machine_is_stmp378x() || \
0)
#define cpu_is_mx28() ( \
machine_is_mx28evk() || \
MACHINE_START(M28EVK, "DENX M28 EVK")
.map_io = mx28_map_io,
.init_irq = mx28_init_irq,
- .init_machine = m28evk_init,
.timer = &m28evk_timer,
+ .init_machine = m28evk_init,
MACHINE_END
MACHINE_START(STMP378X, "STMP378X")
.map_io = mx23_map_io,
.init_irq = mx23_init_irq,
- .init_machine = stmp378x_dvb_init,
.timer = &stmp378x_dvb_timer,
+ .init_machine = stmp378x_dvb_init,
MACHINE_END
MX28_PAD_ENET0_CRS__ENET1_RX_EN,
};
-static struct fec_platform_data tx28_fec0_data = {
+static const struct fec_platform_data tx28_fec0_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
-static struct fec_platform_data tx28_fec1_data = {
+static const struct fec_platform_data tx28_fec1_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
comment "OMAP CPU Speed"
depends on ARCH_OMAP1
-config OMAP_CLOCKS_SET_BY_BOOTLOADER
- bool "OMAP clocks set by bootloader"
- depends on ARCH_OMAP1
- help
- Enable this option to prevent the kernel from overriding the clock
- frequencies programmed by bootloader for MPU, DSP, MMUs, TC,
- internal LCD controller and MPU peripherals.
-
config OMAP_ARM_216MHZ
bool "OMAP ARM 216 MHz CPU (1710 only)"
depends on ARCH_OMAP1 && ARCH_OMAP16XX
omap_cfg_reg(J19_1610_CAM_D6);
omap_cfg_reg(J18_1610_CAM_D7);
- iotable_init(ams_delta_io_desc, ARRAY_SIZE(ams_delta_io_desc));
-
omap_board_config = ams_delta_config;
omap_board_config_size = ARRAY_SIZE(ams_delta_config);
omap_serial_init();
}
arch_initcall(ams_delta_modem_init);
+static void __init ams_delta_map_io(void)
+{
+ omap15xx_map_io();
+ iotable_init(ams_delta_io_desc, ARRAY_SIZE(ams_delta_io_desc));
+}
+
MACHINE_START(AMS_DELTA, "Amstrad E3 (Delta)")
/* Maintainer: Jonathan McDowell <noodles@earth.li> */
.atag_offset = 0x100,
- .map_io = omap15xx_map_io,
+ .map_io = ams_delta_map_io,
.init_early = omap1_init_early,
.reserve = omap_reserve,
.init_irq = omap1_init_irq,
#include <plat/clock.h>
-extern int __init omap1_clk_init(void);
+int omap1_clk_init(void);
+void omap1_clk_late_init(void);
extern int omap1_clk_enable(struct clk *clk);
extern void omap1_clk_disable(struct clk *clk);
extern long omap1_clk_round_rate(struct clk *clk, unsigned long rate);
#include <linux/kernel.h>
#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
#include <linux/io.h>
#include <asm/mach-types.h> /* for machine_is_* */
.clk_disable_unused = omap1_clk_disable_unused,
};
+static void __init omap1_show_rates(void)
+{
+ pr_notice("Clocking rate (xtal/DPLL1/MPU): "
+ "%ld.%01ld/%ld.%01ld/%ld.%01ld MHz\n",
+ ck_ref.rate / 1000000, (ck_ref.rate / 100000) % 10,
+ ck_dpll1.rate / 1000000, (ck_dpll1.rate / 100000) % 10,
+ arm_ck.rate / 1000000, (arm_ck.rate / 100000) % 10);
+}
+
int __init omap1_clk_init(void)
{
struct omap_clk *c;
/* We want to be in syncronous scalable mode */
omap_writew(0x1000, ARM_SYSST);
-#ifdef CONFIG_OMAP_CLOCKS_SET_BY_BOOTLOADER
- /* Use values set by bootloader. Determine PLL rate and recalculate
- * dependent clocks as if kernel had changed PLL or divisors.
+
+ /*
+ * Initially use the values set by bootloader. Determine PLL rate and
+ * recalculate dependent clocks as if kernel had changed PLL or
+ * divisors. See also omap1_clk_late_init() that can reprogram dpll1
+ * after the SRAM is initialized.
*/
{
unsigned pll_ctl_val = omap_readw(DPLL_CTL);
}
}
}
-#else
- /* Find the highest supported frequency and enable it */
- if (omap1_select_table_rate(&virtual_ck_mpu, ~0)) {
- printk(KERN_ERR "System frequencies not set. Check your config.\n");
- /* Guess sane values (60MHz) */
- omap_writew(0x2290, DPLL_CTL);
- omap_writew(cpu_is_omap7xx() ? 0x3005 : 0x1005, ARM_CKCTL);
- ck_dpll1.rate = 60000000;
- }
-#endif
propagate_rate(&ck_dpll1);
/* Cache rates for clocks connected to ck_ref (not dpll1) */
propagate_rate(&ck_ref);
- printk(KERN_INFO "Clocking rate (xtal/DPLL1/MPU): "
- "%ld.%01ld/%ld.%01ld/%ld.%01ld MHz\n",
- ck_ref.rate / 1000000, (ck_ref.rate / 100000) % 10,
- ck_dpll1.rate / 1000000, (ck_dpll1.rate / 100000) % 10,
- arm_ck.rate / 1000000, (arm_ck.rate / 100000) % 10);
-
+ omap1_show_rates();
if (machine_is_omap_perseus2() || machine_is_omap_fsample()) {
/* Select slicer output as OMAP input clock */
omap_writew(omap_readw(OMAP7XX_PCC_UPLD_CTRL) & ~0x1,
return 0;
}
+
+#define OMAP1_DPLL1_SANE_VALUE 60000000
+
+void __init omap1_clk_late_init(void)
+{
+ unsigned long rate = ck_dpll1.rate;
+
+ if (rate >= OMAP1_DPLL1_SANE_VALUE)
+ return;
+
+ /* System booting at unusable rate, force reprogramming of DPLL1 */
+ ck_dpll1_p->rate = 0;
+
+ /* Find the highest supported frequency and enable it */
+ if (omap1_select_table_rate(&virtual_ck_mpu, ~0)) {
+ pr_err("System frequencies not set, using default. Check your config.\n");
+ omap_writew(0x2290, DPLL_CTL);
+ omap_writew(cpu_is_omap7xx() ? 0x2005 : 0x0005, ARM_CKCTL);
+ ck_dpll1.rate = OMAP1_DPLL1_SANE_VALUE;
+ }
+ propagate_rate(&ck_dpll1);
+ omap1_show_rates();
+ loops_per_jiffy = cpufreq_scale(loops_per_jiffy, rate, ck_dpll1.rate);
+}
#include <plat/omap7xx.h>
#include <plat/mcbsp.h>
+#include "clock.h"
+
/*-------------------------------------------------------------------------*/
#if defined(CONFIG_RTC_DRV_OMAP) || defined(CONFIG_RTC_DRV_OMAP_MODULE)
return -ENODEV;
omap_sram_init();
+ omap1_clk_late_init();
/* please keep these calls, and their implementations above,
* in alphabetical order so they're easier to sort through.
config OMAP3_EMU
bool "OMAP3 debugging peripherals"
depends on ARCH_OMAP3
+ select ARM_AMBA
select OC_ETM
help
Say Y here to enable debugging hardware of omap3
# Common support
obj-y := id.o io.o control.o mux.o devices.o serial.o gpmc.o timer.o pm.o \
- common.o gpio.o dma.o wd_timer.o
+ common.o gpio.o dma.o wd_timer.o display.o
omap-2-3-common = irq.o sdrc.o
hwmod-common = omap_hwmod.o \
obj-y += $(smsc911x-m) $(smsc911x-y)
obj-$(CONFIG_ARCH_OMAP4) += hwspinlock.o
-disp-$(CONFIG_OMAP2_DSS) := display.o
-obj-y += $(disp-m) $(disp-y)
-
obj-y += common-board-devices.o twl-common.o
static void __init rx51_charger_init(void)
{
WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO,
- GPIOF_OUT_INIT_LOW, "isp1704_reset"));
+ GPIOF_OUT_INIT_HIGH, "isp1704_reset"));
platform_device_register(&rx51_charger_device);
}
#include <linux/sched.h>
#include <linux/cpuidle.h>
+#include <linux/export.h>
#include <plat/prcm.h>
#include <plat/irqs.h>
#include <plat/omap_hwmod.h>
#include <plat/omap_device.h>
#include <plat/omap-pm.h>
+#include <plat/common.h>
#include "control.h"
+#include "display.h"
+
+#define DISPC_CONTROL 0x0040
+#define DISPC_CONTROL2 0x0238
+#define DISPC_IRQSTATUS 0x0018
+
+#define DSS_SYSCONFIG 0x10
+#define DSS_SYSSTATUS 0x14
+#define DSS_CONTROL 0x40
+#define DSS_SDI_CONTROL 0x44
+#define DSS_PLL_CONTROL 0x48
+
+#define LCD_EN_MASK (0x1 << 0)
+#define DIGIT_EN_MASK (0x1 << 1)
+
+#define FRAMEDONE_IRQ_SHIFT 0
+#define EVSYNC_EVEN_IRQ_SHIFT 2
+#define EVSYNC_ODD_IRQ_SHIFT 3
+#define FRAMEDONE2_IRQ_SHIFT 22
+#define FRAMEDONETV_IRQ_SHIFT 24
+
+/*
+ * FRAMEDONE_IRQ_TIMEOUT: how long (in milliseconds) to wait during DISPC
+ * reset before deciding that something has gone wrong
+ */
+#define FRAMEDONE_IRQ_TIMEOUT 100
static struct platform_device omap_display_device = {
.name = "omapdss",
return r;
}
+
+static void dispc_disable_outputs(void)
+{
+ u32 v, irq_mask = 0;
+ bool lcd_en, digit_en, lcd2_en = false;
+ int i;
+ struct omap_dss_dispc_dev_attr *da;
+ struct omap_hwmod *oh;
+
+ oh = omap_hwmod_lookup("dss_dispc");
+ if (!oh) {
+ WARN(1, "display: could not disable outputs during reset - could not find dss_dispc hwmod\n");
+ return;
+ }
+
+ if (!oh->dev_attr) {
+ pr_err("display: could not disable outputs during reset due to missing dev_attr\n");
+ return;
+ }
+
+ da = (struct omap_dss_dispc_dev_attr *)oh->dev_attr;
+
+ /* store value of LCDENABLE and DIGITENABLE bits */
+ v = omap_hwmod_read(oh, DISPC_CONTROL);
+ lcd_en = v & LCD_EN_MASK;
+ digit_en = v & DIGIT_EN_MASK;
+
+ /* store value of LCDENABLE for LCD2 */
+ if (da->manager_count > 2) {
+ v = omap_hwmod_read(oh, DISPC_CONTROL2);
+ lcd2_en = v & LCD_EN_MASK;
+ }
+
+ if (!(lcd_en | digit_en | lcd2_en))
+ return; /* no managers currently enabled */
+
+ /*
+ * If any manager was enabled, we need to disable it before
+ * DSS clocks are disabled or DISPC module is reset
+ */
+ if (lcd_en)
+ irq_mask |= 1 << FRAMEDONE_IRQ_SHIFT;
+
+ if (digit_en) {
+ if (da->has_framedonetv_irq) {
+ irq_mask |= 1 << FRAMEDONETV_IRQ_SHIFT;
+ } else {
+ irq_mask |= 1 << EVSYNC_EVEN_IRQ_SHIFT |
+ 1 << EVSYNC_ODD_IRQ_SHIFT;
+ }
+ }
+
+ if (lcd2_en)
+ irq_mask |= 1 << FRAMEDONE2_IRQ_SHIFT;
+
+ /*
+ * clear any previous FRAMEDONE, FRAMEDONETV,
+ * EVSYNC_EVEN/ODD or FRAMEDONE2 interrupts
+ */
+ omap_hwmod_write(irq_mask, oh, DISPC_IRQSTATUS);
+
+ /* disable LCD and TV managers */
+ v = omap_hwmod_read(oh, DISPC_CONTROL);
+ v &= ~(LCD_EN_MASK | DIGIT_EN_MASK);
+ omap_hwmod_write(v, oh, DISPC_CONTROL);
+
+ /* disable LCD2 manager */
+ if (da->manager_count > 2) {
+ v = omap_hwmod_read(oh, DISPC_CONTROL2);
+ v &= ~LCD_EN_MASK;
+ omap_hwmod_write(v, oh, DISPC_CONTROL2);
+ }
+
+ i = 0;
+ while ((omap_hwmod_read(oh, DISPC_IRQSTATUS) & irq_mask) !=
+ irq_mask) {
+ i++;
+ if (i > FRAMEDONE_IRQ_TIMEOUT) {
+ pr_err("didn't get FRAMEDONE1/2 or TV interrupt\n");
+ break;
+ }
+ mdelay(1);
+ }
+}
+
+#define MAX_MODULE_SOFTRESET_WAIT 10000
+int omap_dss_reset(struct omap_hwmod *oh)
+{
+ struct omap_hwmod_opt_clk *oc;
+ int c = 0;
+ int i, r;
+
+ if (!(oh->class->sysc->sysc_flags & SYSS_HAS_RESET_STATUS)) {
+ pr_err("dss_core: hwmod data doesn't contain reset data\n");
+ return -EINVAL;
+ }
+
+ for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+ if (oc->_clk)
+ clk_enable(oc->_clk);
+
+ dispc_disable_outputs();
+
+ /* clear SDI registers */
+ if (cpu_is_omap3430()) {
+ omap_hwmod_write(0x0, oh, DSS_SDI_CONTROL);
+ omap_hwmod_write(0x0, oh, DSS_PLL_CONTROL);
+ }
+
+ /*
+ * clear DSS_CONTROL register to switch DSS clock sources to
+ * PRCM clock, if any
+ */
+ omap_hwmod_write(0x0, oh, DSS_CONTROL);
+
+ omap_test_timeout((omap_hwmod_read(oh, oh->class->sysc->syss_offs)
+ & SYSS_RESETDONE_MASK),
+ MAX_MODULE_SOFTRESET_WAIT, c);
+
+ if (c == MAX_MODULE_SOFTRESET_WAIT)
+ pr_warning("dss_core: waiting for reset to finish failed\n");
+ else
+ pr_debug("dss_core: softreset done\n");
+
+ for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+ if (oc->_clk)
+ clk_disable(oc->_clk);
+
+ r = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
+
+ return r;
+}
--- /dev/null
+/*
+ * display.h - OMAP2+ integration-specific DSS header
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_DISPLAY_H
+#define __ARCH_ARM_MACH_OMAP2_DISPLAY_H
+
+#include <linux/kernel.h>
+
+struct omap_dss_dispc_dev_attr {
+ u8 manager_count;
+ bool has_framedonetv_irq;
+};
+
+#endif
pdata->reg_size = 4;
pdata->has_ccr = true;
}
+ pdata->set_clk_src = omap2_mcbsp_set_clk_src;
+ if (id == 1)
+ pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
if (oh->class->rev == MCBSP_CONFIG_TYPE3) {
if (id == 2)
name, oh->name);
return PTR_ERR(pdev);
}
- pdata->set_clk_src = omap2_mcbsp_set_clk_src;
- if (id == 1)
- pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
omap_mcbsp_count++;
return 0;
}
ohii = &oh->mpu_irqs[i++];
} while (ohii->irq != -1);
- return i;
+ return i-1;
}
/**
ohdi = &oh->sdma_reqs[i++];
} while (ohdi->dma_req != -1);
- return i;
+ return i-1;
}
/**
mem = &os->addr[i++];
} while (mem->pa_start != mem->pa_end);
- return i;
+ return i-1;
}
/**
};
static struct omap_hwmod_opt_clk dss_opt_clks[] = {
+ /*
+ * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+ * driver does not use these clocks.
+ */
{ .role = "tv_clk", .clk = "dss_54m_fck" },
{ .role = "sys_clk", .clk = "dss2_fck" },
};
.slaves_cnt = ARRAY_SIZE(omap2420_dss_slaves),
.masters = omap2420_dss_masters,
.masters_cnt = ARRAY_SIZE(omap2420_dss_masters),
- .flags = HWMOD_NO_IDLEST,
+ .flags = HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
};
/* l4_core -> dss_dispc */
.slaves = omap2420_dss_dispc_slaves,
.slaves_cnt = ARRAY_SIZE(omap2420_dss_dispc_slaves),
.flags = HWMOD_NO_IDLEST,
+ .dev_attr = &omap2_3_dss_dispc_dev_attr
};
/* l4_core -> dss_rfbi */
&omap2420_l4_core__dss_rfbi,
};
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+ { .role = "ick", .clk = "dss_ick" },
+};
+
static struct omap_hwmod omap2420_dss_rfbi_hwmod = {
.name = "dss_rfbi",
.class = &omap2_rfbi_hwmod_class,
.module_offs = CORE_MOD,
},
},
+ .opt_clks = dss_rfbi_opt_clks,
+ .opt_clks_cnt = ARRAY_SIZE(dss_rfbi_opt_clks),
.slaves = omap2420_dss_rfbi_slaves,
.slaves_cnt = ARRAY_SIZE(omap2420_dss_rfbi_slaves),
.flags = HWMOD_NO_IDLEST,
static struct omap_hwmod_ocp_if omap2420_l4_core__dss_venc = {
.master = &omap2420_l4_core_hwmod,
.slave = &omap2420_dss_venc_hwmod,
- .clk = "dss_54m_fck",
+ .clk = "dss_ick",
.addr = omap2_dss_venc_addrs,
.fw = {
.omap2 = {
static struct omap_hwmod omap2420_dss_venc_hwmod = {
.name = "dss_venc",
.class = &omap2_venc_hwmod_class,
- .main_clk = "dss1_fck",
+ .main_clk = "dss_54m_fck",
.prcm = {
.omap2 = {
.prcm_reg_id = 1,
};
static struct omap_hwmod_opt_clk dss_opt_clks[] = {
+ /*
+ * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+ * driver does not use these clocks.
+ */
{ .role = "tv_clk", .clk = "dss_54m_fck" },
{ .role = "sys_clk", .clk = "dss2_fck" },
};
.slaves_cnt = ARRAY_SIZE(omap2430_dss_slaves),
.masters = omap2430_dss_masters,
.masters_cnt = ARRAY_SIZE(omap2430_dss_masters),
- .flags = HWMOD_NO_IDLEST,
+ .flags = HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
};
/* l4_core -> dss_dispc */
.slaves = omap2430_dss_dispc_slaves,
.slaves_cnt = ARRAY_SIZE(omap2430_dss_dispc_slaves),
.flags = HWMOD_NO_IDLEST,
+ .dev_attr = &omap2_3_dss_dispc_dev_attr
};
/* l4_core -> dss_rfbi */
&omap2430_l4_core__dss_rfbi,
};
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+ { .role = "ick", .clk = "dss_ick" },
+};
+
static struct omap_hwmod omap2430_dss_rfbi_hwmod = {
.name = "dss_rfbi",
.class = &omap2_rfbi_hwmod_class,
.module_offs = CORE_MOD,
},
},
+ .opt_clks = dss_rfbi_opt_clks,
+ .opt_clks_cnt = ARRAY_SIZE(dss_rfbi_opt_clks),
.slaves = omap2430_dss_rfbi_slaves,
.slaves_cnt = ARRAY_SIZE(omap2430_dss_rfbi_slaves),
.flags = HWMOD_NO_IDLEST,
static struct omap_hwmod_ocp_if omap2430_l4_core__dss_venc = {
.master = &omap2430_l4_core_hwmod,
.slave = &omap2430_dss_venc_hwmod,
- .clk = "dss_54m_fck",
+ .clk = "dss_ick",
.addr = omap2_dss_venc_addrs,
.flags = OCPIF_SWSUP_IDLE,
.user = OCP_USER_MPU | OCP_USER_SDMA,
static struct omap_hwmod omap2430_dss_venc_hwmod = {
.name = "dss_venc",
.class = &omap2_venc_hwmod_class,
- .main_clk = "dss1_fck",
+ .main_clk = "dss_54m_fck",
.prcm = {
.omap2 = {
.prcm_reg_id = 1,
#include <plat/omap_hwmod.h>
#include <plat/serial.h>
#include <plat/dma.h>
+#include <plat/common.h>
#include <mach/irqs.h>
.rev_offs = 0x0000,
.sysc_offs = 0x0010,
.syss_offs = 0x0014,
- .sysc_flags = (SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE),
+ .sysc_flags = (SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE |
+ SYSS_HAS_RESET_STATUS),
.sysc_fields = &omap_hwmod_sysc_type1,
};
struct omap_hwmod_class omap2_dss_hwmod_class = {
.name = "dss",
.sysc = &omap2_dss_sysc,
+ .reset = omap_dss_reset,
};
/*
};
static struct omap_hwmod_opt_clk dss_opt_clks[] = {
- { .role = "tv_clk", .clk = "dss_tv_fck" },
- { .role = "video_clk", .clk = "dss_96m_fck" },
+ /*
+ * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+ * driver does not use these clocks.
+ */
{ .role = "sys_clk", .clk = "dss2_alwon_fck" },
+ { .role = "tv_clk", .clk = "dss_tv_fck" },
+ /* required only on OMAP3430 */
+ { .role = "tv_dac_clk", .clk = "dss_96m_fck" },
};
static struct omap_hwmod omap3430es1_dss_core_hwmod = {
.slaves_cnt = ARRAY_SIZE(omap3430es1_dss_slaves),
.masters = omap3xxx_dss_masters,
.masters_cnt = ARRAY_SIZE(omap3xxx_dss_masters),
- .flags = HWMOD_NO_IDLEST,
+ .flags = HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
};
static struct omap_hwmod omap3xxx_dss_core_hwmod = {
.name = "dss_core",
+ .flags = HWMOD_CONTROL_OPT_CLKS_IN_RESET,
.class = &omap2_dss_hwmod_class,
.main_clk = "dss1_alwon_fck", /* instead of dss_fck */
.sdma_reqs = omap3xxx_dss_sdma_chs,
.slaves = omap3xxx_dss_dispc_slaves,
.slaves_cnt = ARRAY_SIZE(omap3xxx_dss_dispc_slaves),
.flags = HWMOD_NO_IDLEST,
+ .dev_attr = &omap2_3_dss_dispc_dev_attr
};
/*
static struct omap_hwmod_ocp_if omap3xxx_l4_core__dss_dsi1 = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap3xxx_dss_dsi1_hwmod,
+ .clk = "dss_ick",
.addr = omap3xxx_dss_dsi1_addrs,
.fw = {
.omap2 = {
&omap3xxx_l4_core__dss_dsi1,
};
+static struct omap_hwmod_opt_clk dss_dsi1_opt_clks[] = {
+ { .role = "sys_clk", .clk = "dss2_alwon_fck" },
+};
+
static struct omap_hwmod omap3xxx_dss_dsi1_hwmod = {
.name = "dss_dsi1",
.class = &omap3xxx_dsi_hwmod_class,
.module_offs = OMAP3430_DSS_MOD,
},
},
+ .opt_clks = dss_dsi1_opt_clks,
+ .opt_clks_cnt = ARRAY_SIZE(dss_dsi1_opt_clks),
.slaves = omap3xxx_dss_dsi1_slaves,
.slaves_cnt = ARRAY_SIZE(omap3xxx_dss_dsi1_slaves),
.flags = HWMOD_NO_IDLEST,
&omap3xxx_l4_core__dss_rfbi,
};
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+ { .role = "ick", .clk = "dss_ick" },
+};
+
static struct omap_hwmod omap3xxx_dss_rfbi_hwmod = {
.name = "dss_rfbi",
.class = &omap2_rfbi_hwmod_class,
.module_offs = OMAP3430_DSS_MOD,
},
},
+ .opt_clks = dss_rfbi_opt_clks,
+ .opt_clks_cnt = ARRAY_SIZE(dss_rfbi_opt_clks),
.slaves = omap3xxx_dss_rfbi_slaves,
.slaves_cnt = ARRAY_SIZE(omap3xxx_dss_rfbi_slaves),
.flags = HWMOD_NO_IDLEST,
static struct omap_hwmod_ocp_if omap3xxx_l4_core__dss_venc = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap3xxx_dss_venc_hwmod,
- .clk = "dss_tv_fck",
+ .clk = "dss_ick",
.addr = omap2_dss_venc_addrs,
.fw = {
.omap2 = {
&omap3xxx_l4_core__dss_venc,
};
+static struct omap_hwmod_opt_clk dss_venc_opt_clks[] = {
+ /* required only on OMAP3430 */
+ { .role = "tv_dac_clk", .clk = "dss_96m_fck" },
+};
+
static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
.name = "dss_venc",
.class = &omap2_venc_hwmod_class,
- .main_clk = "dss1_alwon_fck",
+ .main_clk = "dss_tv_fck",
.prcm = {
.omap2 = {
.prcm_reg_id = 1,
.module_offs = OMAP3430_DSS_MOD,
},
},
+ .opt_clks = dss_venc_opt_clks,
+ .opt_clks_cnt = ARRAY_SIZE(dss_venc_opt_clks),
.slaves = omap3xxx_dss_venc_slaves,
.slaves_cnt = ARRAY_SIZE(omap3xxx_dss_venc_slaves),
.flags = HWMOD_NO_IDLEST,
/* 3430ES1-only hwmods */
static __initdata struct omap_hwmod *omap3430es1_hwmods[] = {
- &omap3xxx_iva_hwmod,
&omap3430es1_dss_core_hwmod,
- &omap3xxx_mailbox_hwmod,
NULL
};
/* 3430ES2+-only hwmods */
static __initdata struct omap_hwmod *omap3430es2plus_hwmods[] = {
- &omap3xxx_iva_hwmod,
&omap3xxx_dss_core_hwmod,
&omap3xxx_usbhsotg_hwmod,
- &omap3xxx_mailbox_hwmod,
NULL
};
#include <plat/mmc.h>
#include <plat/i2c.h>
#include <plat/dmtimer.h>
+#include <plat/common.h>
#include "omap_hwmod_common_data.h"
static struct omap_hwmod_class omap44xx_dss_hwmod_class = {
.name = "dss",
.sysc = &omap44xx_dss_sysc,
+ .reset = omap_dss_reset,
};
/* dss */
static struct omap_hwmod_opt_clk dss_opt_clks[] = {
{ .role = "sys_clk", .clk = "dss_sys_clk" },
{ .role = "tv_clk", .clk = "dss_tv_clk" },
- { .role = "dss_clk", .clk = "dss_dss_clk" },
- { .role = "video_clk", .clk = "dss_48mhz_clk" },
+ { .role = "hdmi_clk", .clk = "dss_48mhz_clk" },
};
static struct omap_hwmod omap44xx_dss_hwmod = {
.name = "dss_core",
+ .flags = HWMOD_CONTROL_OPT_CLKS_IN_RESET,
.class = &omap44xx_dss_hwmod_class,
.clkdm_name = "l3_dss_clkdm",
.main_clk = "dss_dss_clk",
{ }
};
+static struct omap_dss_dispc_dev_attr omap44xx_dss_dispc_dev_attr = {
+ .manager_count = 3,
+ .has_framedonetv_irq = 1
+};
+
/* l4_per -> dss_dispc */
static struct omap_hwmod_ocp_if omap44xx_l4_per__dss_dispc = {
.master = &omap44xx_l4_per_hwmod,
&omap44xx_l4_per__dss_dispc,
};
-static struct omap_hwmod_opt_clk dss_dispc_opt_clks[] = {
- { .role = "sys_clk", .clk = "dss_sys_clk" },
- { .role = "tv_clk", .clk = "dss_tv_clk" },
- { .role = "hdmi_clk", .clk = "dss_48mhz_clk" },
-};
-
static struct omap_hwmod omap44xx_dss_dispc_hwmod = {
.name = "dss_dispc",
.class = &omap44xx_dispc_hwmod_class,
.context_offs = OMAP4_RM_DSS_DSS_CONTEXT_OFFSET,
},
},
- .opt_clks = dss_dispc_opt_clks,
- .opt_clks_cnt = ARRAY_SIZE(dss_dispc_opt_clks),
.slaves = omap44xx_dss_dispc_slaves,
.slaves_cnt = ARRAY_SIZE(omap44xx_dss_dispc_slaves),
+ .dev_attr = &omap44xx_dss_dispc_dev_attr
};
/*
.clkdm_name = "l3_dss_clkdm",
.mpu_irqs = omap44xx_dss_hdmi_irqs,
.sdma_reqs = omap44xx_dss_hdmi_sdma_reqs,
- .main_clk = "dss_dss_clk",
+ .main_clk = "dss_48mhz_clk",
.prcm = {
.omap4 = {
.clkctrl_offs = OMAP4_CM_DSS_DSS_CLKCTRL_OFFSET,
.name = "dss_venc",
.class = &omap44xx_venc_hwmod_class,
.clkdm_name = "l3_dss_clkdm",
- .main_clk = "dss_dss_clk",
+ .main_clk = "dss_tv_clk",
.prcm = {
.omap4 = {
.clkctrl_offs = OMAP4_CM_DSS_DSS_CLKCTRL_OFFSET,
.srst_shift = SYSC_TYPE2_SOFTRESET_SHIFT,
};
+struct omap_dss_dispc_dev_attr omap2_3_dss_dispc_dev_attr = {
+ .manager_count = 2,
+ .has_framedonetv_irq = 0
+};
#include <plat/omap_hwmod.h>
+#include "display.h"
+
/* Common address space across OMAP2xxx */
extern struct omap_hwmod_addr_space omap2xxx_uart1_addr_space[];
extern struct omap_hwmod_addr_space omap2xxx_uart2_addr_space[];
extern struct omap_hwmod_class omap2xxx_mailbox_hwmod_class;
extern struct omap_hwmod_class omap2xxx_mcspi_class;
+extern struct omap_dss_dispc_dev_attr omap2_3_dss_dispc_dev_attr;
+
#endif
static const struct of_device_id l3_noc_match[] = {
{.compatible = "ti,omap4-l3-noc", },
{},
-}
+};
MODULE_DEVICE_TABLE(of, l3_noc_match);
#else
#define l3_noc_match NULL
#include "powerdomain.h"
#include "clockdomain.h"
#include "pm.h"
+#include "twl-common.h"
static struct omap_device_pm_latency *pm_lats;
static int __init omap2_common_pm_late_init(void)
{
- /* Init the OMAP TWL parameters */
- omap3_twl_init();
- omap4_twl_init();
-
/* Init the voltage layer */
+ omap_pmic_late_init();
omap_voltage_late_init();
/* Initialize the voltages */
sr_write_reg(sr_info, ERRCONFIG_V1, status);
} else if (sr_info->ip_type == SR_TYPE_V2) {
/* Read the status bits */
- sr_read_reg(sr_info, IRQSTATUS);
+ status = sr_read_reg(sr_info, IRQSTATUS);
/* Clear them by writing back */
sr_write_reg(sr_info, IRQSTATUS, status);
#include <plat/usb.h>
#include "twl-common.h"
+#include "pm.h"
static struct i2c_board_info __initdata pmic_i2c_board_info = {
.addr = 0x48,
omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
}
+void __init omap_pmic_late_init(void)
+{
+ /* Init the OMAP TWL parameters (if PMIC has been registerd) */
+ if (!pmic_i2c_board_info.irq)
+ return;
+
+ omap3_twl_init();
+ omap4_twl_init();
+}
+
#if defined(CONFIG_ARCH_OMAP3)
static struct twl4030_usb_data omap3_usb_pdata = {
.usb_mode = T2_USB_MODE_ULPI,
#ifndef __OMAP_PMIC_COMMON__
#define __OMAP_PMIC_COMMON__
+#include <plat/irqs.h>
+
#define TWL_COMMON_PDATA_USB (1 << 0)
#define TWL_COMMON_PDATA_BCI (1 << 1)
#define TWL_COMMON_PDATA_MADC (1 << 2)
void omap_pmic_init(int bus, u32 clkrate, const char *pmic_type, int pmic_irq,
struct twl4030_platform_data *pmic_data);
+void omap_pmic_late_init(void);
static inline void omap2_pmic_init(const char *pmic_type,
struct twl4030_platform_data *pmic_data)
#include <linux/kernel.h>
#include <linux/suspend.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/init.h>
#include <linux/kernel.h>
+#include <asm/sizes.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
#include <linux/of.h>
/******************************************************************************
* USB Gadget
******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
static void balloon3_udc_command(int cmd)
{
if (cmd == PXA2XX_UDC_CMD_CONNECT)
static inline void __init colibri_pxa320_init_eth(void) {}
#endif /* CONFIG_AX88796 */
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
static struct gpio_vbus_mach_info colibri_pxa320_gpio_vbus_info = {
.gpio_vbus = mfp_to_gpio(MFP_PIN_GPIO96),
.gpio_pullup = -1,
}
#endif
-#ifdef CONFIG_USB_GADGET_PXA25X
+#ifdef CONFIG_USB_PXA25X
static struct gpio_vbus_mach_info gumstix_udc_info = {
.gpio_vbus = GPIO_GUMSTIX_USB_GPIOn,
.gpio_pullup = GPIO_GUMSTIX_USB_GPIOx,
#define palm27x_lcd_init(power, mode) do {} while (0)
#endif
-#if defined(CONFIG_USB_GADGET_PXA27X) || \
- defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X) || \
+ defined(CONFIG_USB_PXA27X_MODULE)
extern void __init palm27x_udc_init(int vbus, int pullup,
int vbus_inverted);
#else
/******************************************************************************
* USB Gadget
******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X) || \
- defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X) || \
+ defined(CONFIG_USB_PXA27X_MODULE)
static struct gpio_vbus_mach_info palm27x_udc_info = {
.gpio_vbus_inverted = 1,
};
/******************************************************************************
* UDC
******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA25X)||defined(CONFIG_USB_GADGET_PXA25X_MODULE)
+#if defined(CONFIG_USB_PXA25X)||defined(CONFIG_USB_PXA25X_MODULE)
static struct gpio_vbus_mach_info palmtc_udc_info = {
.gpio_vbus = GPIO_NR_PALMTC_USB_DETECT_N,
.gpio_vbus_inverted = 1,
/******************************************************************************
* USB Gadget
******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
static struct gpio_vbus_mach_info vpac270_gpio_vbus_info = {
.gpio_vbus = GPIO41_VPAC270_UDC_DETECT,
.gpio_pullup = -1,
#include <linux/kernel.h>
#include <linux/string.h>
+#include <linux/export.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
#include <linux/gpio.h>
* published by the Free Software Foundation.
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/i2c.h>
s3c64xx_init_irq(~0 & ~(0xf << 5), ~0);
}
-struct sysdev_class s3c6400_sysclass = {
+static struct sysdev_class s3c6400_sysclass = {
.name = "s3c6400-core",
};
#include <plat/fb.h>
#include <plat/gpio-cfg.h>
-extern void s3c64xx_fb_gpio_setup_24bpp(void)
+void s3c64xx_fb_gpio_setup_24bpp(void)
{
s3c_gpio_cfgrange_nopull(S3C64XX_GPI(0), 16, S3C_GPIO_SFN(2));
s3c_gpio_cfgrange_nopull(S3C64XX_GPJ(0), 12, S3C_GPIO_SFN(2));
static struct platform_pwm_backlight_data smdkv210_bl_data = {
.pwm_id = 3,
+ .pwm_period_ns = 1000,
};
static void __init smdkv210_map_io(void)
-ifeq ($(CONFIG_ARCH_SA1100),y)
- zreladdr-$(CONFIG_SA1111) += 0xc0208000
+ifeq ($(CONFIG_SA1111),y)
+ zreladdr-y += 0xc0208000
else
zreladdr-y += 0xc0008000
endif
MACHINE_START(AG5EVM, "ag5evm")
.map_io = ag5evm_map_io,
+ .nr_irqs = NR_IRQS_LEGACY,
.init_irq = sh73a0_init_irq,
.handle_irq = shmobile_handle_irq_gic,
.init_machine = ag5evm_init,
#include <linux/input/sh_keysc.h>
#include <linux/gpio_keys.h>
#include <linux/leds.h>
+#include <linux/platform_data/leds-renesas-tpu.h>
#include <linux/mmc/host.h>
#include <linux/mmc/sh_mmcif.h>
#include <linux/mfd/tmio.h>
.flags = IORESOURCE_MEM,
},
[1] = {
- .start = gic_spi(33), /* PINTA2 @ PORT144 */
+ .start = SH73A0_PINT0_IRQ(2), /* PINTA2 */
.flags = IORESOURCE_IRQ,
},
};
#define GPIO_LED(n, g) { .name = n, .gpio = g }
static struct gpio_led gpio_leds[] = {
- GPIO_LED("V2513", GPIO_PORT153), /* PORT153 [TPU1T02] -> V2513 */
- GPIO_LED("V2514", GPIO_PORT199), /* PORT199 [TPU4TO1] -> V2514 */
- GPIO_LED("V2515", GPIO_PORT197), /* PORT197 [TPU2TO1] -> V2515 */
- GPIO_LED("KEYLED", GPIO_PORT163), /* PORT163 [TPU3TO0] -> KEYLED */
GPIO_LED("G", GPIO_PORT20), /* PORT20 [GPO0] -> LED7 -> "G" */
GPIO_LED("H", GPIO_PORT21), /* PORT21 [GPO1] -> LED8 -> "H" */
GPIO_LED("J", GPIO_PORT22), /* PORT22 [GPO2] -> LED9 -> "J" */
},
};
+/* TPU LED */
+static struct led_renesas_tpu_config led_renesas_tpu12_pdata = {
+ .name = "V2513",
+ .pin_gpio_fn = GPIO_FN_TPU1TO2,
+ .pin_gpio = GPIO_PORT153,
+ .channel_offset = 0x90,
+ .timer_bit = 2,
+ .max_brightness = 1000,
+};
+
+static struct resource tpu12_resources[] = {
+ [0] = {
+ .name = "TPU12",
+ .start = 0xe6610090,
+ .end = 0xe66100b5,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct platform_device leds_tpu12_device = {
+ .name = "leds-renesas-tpu",
+ .id = 12,
+ .dev = {
+ .platform_data = &led_renesas_tpu12_pdata,
+ },
+ .num_resources = ARRAY_SIZE(tpu12_resources),
+ .resource = tpu12_resources,
+};
+
+static struct led_renesas_tpu_config led_renesas_tpu41_pdata = {
+ .name = "V2514",
+ .pin_gpio_fn = GPIO_FN_TPU4TO1,
+ .pin_gpio = GPIO_PORT199,
+ .channel_offset = 0x50,
+ .timer_bit = 1,
+ .max_brightness = 1000,
+};
+
+static struct resource tpu41_resources[] = {
+ [0] = {
+ .name = "TPU41",
+ .start = 0xe6640050,
+ .end = 0xe6640075,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct platform_device leds_tpu41_device = {
+ .name = "leds-renesas-tpu",
+ .id = 41,
+ .dev = {
+ .platform_data = &led_renesas_tpu41_pdata,
+ },
+ .num_resources = ARRAY_SIZE(tpu41_resources),
+ .resource = tpu41_resources,
+};
+
+static struct led_renesas_tpu_config led_renesas_tpu21_pdata = {
+ .name = "V2515",
+ .pin_gpio_fn = GPIO_FN_TPU2TO1,
+ .pin_gpio = GPIO_PORT197,
+ .channel_offset = 0x50,
+ .timer_bit = 1,
+ .max_brightness = 1000,
+};
+
+static struct resource tpu21_resources[] = {
+ [0] = {
+ .name = "TPU21",
+ .start = 0xe6620050,
+ .end = 0xe6620075,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct platform_device leds_tpu21_device = {
+ .name = "leds-renesas-tpu",
+ .id = 21,
+ .dev = {
+ .platform_data = &led_renesas_tpu21_pdata,
+ },
+ .num_resources = ARRAY_SIZE(tpu21_resources),
+ .resource = tpu21_resources,
+};
+
+static struct led_renesas_tpu_config led_renesas_tpu30_pdata = {
+ .name = "KEYLED",
+ .pin_gpio_fn = GPIO_FN_TPU3TO0,
+ .pin_gpio = GPIO_PORT163,
+ .channel_offset = 0x10,
+ .timer_bit = 0,
+ .max_brightness = 1000,
+};
+
+static struct resource tpu30_resources[] = {
+ [0] = {
+ .name = "TPU30",
+ .start = 0xe6630010,
+ .end = 0xe6630035,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct platform_device leds_tpu30_device = {
+ .name = "leds-renesas-tpu",
+ .id = 30,
+ .dev = {
+ .platform_data = &led_renesas_tpu30_pdata,
+ },
+ .num_resources = ARRAY_SIZE(tpu30_resources),
+ .resource = tpu30_resources,
+};
+
/* MMCIF */
static struct resource mmcif_resources[] = {
[0] = {
&keysc_device,
&gpio_keys_device,
&gpio_leds_device,
+ &leds_tpu12_device,
+ &leds_tpu41_device,
+ &leds_tpu21_device,
+ &leds_tpu30_device,
&mmcif_device,
&sdhi0_device,
&sdhi1_device,
shmobile_setup_console();
}
-#define PINTER0A 0xe69000a0
-#define PINTCR0A 0xe69000b0
-
-void __init kota2_init_irq(void)
-{
- sh73a0_init_irq();
-
- /* setup PINT: enable PINTA2 as active low */
- __raw_writel(1 << 29, PINTER0A);
- __raw_writew(2 << 10, PINTCR0A);
-}
-
static void __init kota2_init(void)
{
sh73a0_pinmux_init();
MACHINE_START(KOTA2, "kota2")
.map_io = kota2_map_io,
- .init_irq = kota2_init_irq,
+ .nr_irqs = NR_IRQS_LEGACY,
+ .init_irq = sh73a0_init_irq,
.handle_irq = shmobile_handle_irq_gic,
.init_machine = kota2_init,
.timer = &kota2_timer,
.ops = &main_clk_ops,
};
+/* Divide Main clock by two */
+static struct clk main_div2_clk = {
+ .ops = &div2_clk_ops,
+ .parent = &main_clk,
+};
+
/* PLL0, PLL1, PLL2, PLL3 */
static unsigned long pll_recalc(struct clk *clk)
{
&extal1_div2_clk,
&extal2_div2_clk,
&main_clk,
+ &main_div2_clk,
&pll0_clk,
&pll1_clk,
&pll2_clk,
[DIV6_VCK1] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR1, 0),
[DIV6_VCK2] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR2, 0),
[DIV6_VCK3] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR3, 0),
- [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, 0),
+ [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, CLK_ENABLE_ON_INIT),
[DIV6_FLCTL] = SH_CLK_DIV6(&pll1_div2_clk, FLCKCR, 0),
[DIV6_SDHI0] = SH_CLK_DIV6(&pll1_div2_clk, SD0CKCR, 0),
[DIV6_SDHI1] = SH_CLK_DIV6(&pll1_div2_clk, SD1CKCR, 0),
MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
MSTP331, MSTP329, MSTP325, MSTP323, MSTP318,
MSTP314, MSTP313, MSTP312, MSTP311,
+ MSTP303, MSTP302, MSTP301, MSTP300,
MSTP411, MSTP410, MSTP403,
MSTP_NR };
[MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
[MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
[MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */
+ [MSTP303] = MSTP(&main_div2_clk, SMSTPCR3, 3, 0), /* TPU1 */
+ [MSTP302] = MSTP(&main_div2_clk, SMSTPCR3, 2, 0), /* TPU2 */
+ [MSTP301] = MSTP(&main_div2_clk, SMSTPCR3, 1, 0), /* TPU3 */
+ [MSTP300] = MSTP(&main_div2_clk, SMSTPCR3, 0, 0), /* TPU4 */
[MSTP411] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 11, 0), /* IIC3 */
[MSTP410] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 10, 0), /* IIC4 */
[MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */
CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */
+ CLKDEV_DEV_ID("leds-renesas-tpu.12", &mstp_clks[MSTP303]), /* TPU1 */
+ CLKDEV_DEV_ID("leds-renesas-tpu.21", &mstp_clks[MSTP302]), /* TPU2 */
+ CLKDEV_DEV_ID("leds-renesas-tpu.30", &mstp_clks[MSTP301]), /* TPU3 */
+ CLKDEV_DEV_ID("leds-renesas-tpu.41", &mstp_clks[MSTP300]), /* TPU4 */
CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */
CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */
CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/bitrev.h>
+#include <linux/console.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/tlbflush.h>
return 0;
}
-static int pd_power_up(struct generic_pm_domain *genpd)
+static int __pd_power_up(struct sh7372_pm_domain *sh7372_pd, bool do_resume)
{
- struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd);
unsigned int mask = 1 << sh7372_pd->bit_shift;
unsigned int retry_count;
int ret = 0;
for (retry_count = 2 * PSTR_RETRIES; retry_count; retry_count--) {
if (!(__raw_readl(SWUCR) & mask))
- goto out;
+ break;
if (retry_count > PSTR_RETRIES)
udelay(PSTR_DELAY_US);
else
cpu_relax();
}
- if (__raw_readl(SWUCR) & mask)
+ if (!retry_count)
ret = -EIO;
if (!sh7372_pd->no_debug)
mask, __raw_readl(PSTR));
out:
- if (ret == 0 && sh7372_pd->resume)
+ if (ret == 0 && sh7372_pd->resume && do_resume)
sh7372_pd->resume();
return ret;
}
+static int pd_power_up(struct generic_pm_domain *genpd)
+{
+ return __pd_power_up(to_sh7372_pd(genpd), true);
+}
+
static void sh7372_a4r_suspend(void)
{
sh7372_intcs_suspend();
genpd->active_wakeup = pd_active_wakeup;
genpd->power_off = pd_power_down;
genpd->power_on = pd_power_up;
- genpd->power_on(&sh7372_pd->genpd);
+ __pd_power_up(sh7372_pd, false);
}
void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
.no_debug = true,
};
+static void sh7372_a3sp_init(void)
+{
+ /* serial consoles make use of SCIF hardware located in A3SP,
+ * keep such power domain on if "no_console_suspend" is set.
+ */
+ sh7372_a3sp.stay_on = !console_suspend_enabled;
+}
+
struct sh7372_pm_domain sh7372_a3sg = {
.bit_shift = 13,
};
-#endif /* CONFIG_PM */
+#else /* !CONFIG_PM */
+
+static inline void sh7372_a3sp_init(void) {}
+
+#endif /* !CONFIG_PM */
#if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
static int sh7372_do_idle_core_standby(unsigned long unused)
/* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */
__raw_writel(0, PDNSEL);
+ sh7372_a3sp_init();
+
sh7372_suspend_init();
sh7372_cpuidle_init();
}
/* LCD controller*/
-static struct nuc900fb_display __initdata nuc900_lcd_info[] = {
+static struct nuc900fb_display nuc900_lcd_info[] = {
/* Giantplus Technology GPM1040A0 320x240 Color TFT LCD */
[0] = {
.type = LCM_DCCS_VA_SRC_RGB565,
},
};
-static struct nuc900fb_mach_info nuc900_fb_info __initdata = {
+static struct nuc900fb_mach_info nuc900_fb_info = {
#if defined(CONFIG_GPM1040A0_320X240)
.displays = &nuc900_lcd_info[0],
#else
extern void mfp_set_groupf(struct device *dev);
extern void mfp_set_groupc(struct device *dev);
extern void mfp_set_groupi(struct device *dev);
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
+extern void mfp_set_groupd(struct device *dev, const char *subname);
#endif /* __ASM_ARCH_MFP_H */
#ifndef __ASM_ARCH_SPI_H
#define __ASM_ARCH_SPI_H
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
struct nuc900_spi_info {
unsigned int num_cs;
#define REG_MFSEL (W90X900_VA_GCR + 0xC)
#define GPSELF (0x01 << 1)
-
#define GPSELC (0x03 << 2)
-#define ENKPI (0x02 << 2)
-#define ENNAND (0x01 << 2)
+#define GPSELD (0x0f << 4)
#define GPSELEI0 (0x01 << 26)
#define GPSELEI1 (0x01 << 27)
#define GPIOG0TO1 (0x03 << 14)
#define GPIOG2TO3 (0x03 << 16)
#define GPIOG22TO23 (0x03 << 22)
+#define GPIOG18TO20 (0x07 << 18)
#define ENSPI (0x0a << 14)
#define ENI2C0 (0x01 << 14)
#define ENI2C1 (0x01 << 16)
#define ENAC97 (0x02 << 22)
+#define ENSD1 (0x02 << 18)
+#define ENSD0 (0x0a << 4)
+#define ENKPI (0x02 << 2)
+#define ENNAND (0x01 << 2)
static DEFINE_MUTEX(mfp_mutex);
}
EXPORT_SYMBOL(mfp_set_groupi);
-void mfp_set_groupg(struct device *dev)
+void mfp_set_groupg(struct device *dev, const char *subname)
{
unsigned long mfpen;
const char *dev_id;
- BUG_ON(!dev);
+ BUG_ON((!dev) && (!subname));
mutex_lock(&mfp_mutex);
- dev_id = dev_name(dev);
+ if (subname != NULL)
+ dev_id = subname;
+ else
+ dev_id = dev_name(dev);
mfpen = __raw_readl(REG_MFSEL);
} else if (strcmp(dev_id, "nuc900-audio") == 0) {
mfpen &= ~(GPIOG22TO23);
mfpen |= ENAC97;/*enable AC97*/
+ } else if (strcmp(dev_id, "nuc900-mmc-port1") == 0) {
+ mfpen &= ~(GPIOG18TO20);
+ mfpen |= (ENSD1 | 0x01);/*enable sd1*/
} else {
mfpen &= ~(GPIOG0TO1 | GPIOG2TO3);/*GPIOG[3:0]*/
}
}
EXPORT_SYMBOL(mfp_set_groupg);
+void mfp_set_groupd(struct device *dev, const char *subname)
+{
+ unsigned long mfpen;
+ const char *dev_id;
+
+ BUG_ON((!dev) && (!subname));
+
+ mutex_lock(&mfp_mutex);
+
+ if (subname != NULL)
+ dev_id = subname;
+ else
+ dev_id = dev_name(dev);
+
+ mfpen = __raw_readl(REG_MFSEL);
+
+ if (strcmp(dev_id, "nuc900-mmc-port0") == 0) {
+ mfpen &= ~GPSELD;/*enable sd0*/
+ mfpen |= ENSD0;
+ } else
+ mfpen &= (~GPSELD);
+
+ __raw_writel(mfpen, REG_MFSEL);
+
+ mutex_unlock(&mfp_mutex);
+}
+EXPORT_SYMBOL(mfp_set_groupd);
{
void __iomem *base = l2x0_base;
-#ifdef CONFIG_ARM_ERRATA_753970
+#ifdef CONFIG_PL310_ERRATA_753970
/* write to an unmmapped register */
writel_relaxed(0, base + L2X0_DUMMY_REG);
#else
pte_t *pte;
int i = 0;
unsigned long base = consistent_base;
- unsigned long num_ptes = (CONSISTENT_END - base) >> PGDIR_SHIFT;
+ unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
if (!consistent_pte) {
struct page *page;
void *addr;
+ /*
+ * Following is a work-around (a.k.a. hack) to prevent pages
+ * with __GFP_COMP being passed to split_page() which cannot
+ * handle them. The real problem is that this flag probably
+ * should be 0 on ARM as it is not supported on this
+ * platform; see CONFIG_HUGETLBFS.
+ */
+ gfp &= ~(__GFP_COMP);
+
*handle = ~0;
size = PAGE_ALIGN(size);
#include <linux/io.h>
#include <linux/personality.h>
#include <linux/random.h>
-#include <asm/cputype.h>
-#include <asm/system.h>
+#include <asm/cachetype.h>
#define COLOUR_ALIGN(addr,pgoff) \
((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long start_addr;
-#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
- unsigned int cache_type;
- int do_align = 0, aliasing = 0;
+ int do_align = 0;
+ int aliasing = cache_is_vipt_aliasing();
/*
* We only need to do colour alignment if either the I or D
- * caches alias. This is indicated by bits 9 and 21 of the
- * cache type register.
+ * caches alias.
*/
- cache_type = read_cpuid_cachetype();
- if (cache_type != read_cpuid_id()) {
- aliasing = (cache_type | cache_type >> 12) & (1 << 11);
- if (aliasing)
- do_align = filp || flags & MAP_SHARED;
- }
-#else
-#define do_align 0
-#define aliasing 0
-#endif
+ if (aliasing)
+ do_align = filp || (flags & MAP_SHARED);
/*
* We enforce the MAP_FIXED case.
orreq r10, r10, #1 << 6 @ set bit #6
mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register
#endif
-#ifdef CONFIG_ARM_ERRATA_751472
- cmp r6, #0x30 @ present prior to r3p0
+#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP)
+ ALT_SMP(cmp r6, #0x30) @ present prior to r3p0
+ ALT_UP_B(1f)
mrclt p15, 0, r10, c15, c0, 1 @ read diagnostic register
orrlt r10, r10, #1 << 11 @ set bit #11
mcrlt p15, 0, r10, c15, c0, 1 @ write diagnostic register
+1:
#endif
3: mov r10, #0
return oprofile_perf_init(ops);
}
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
{
oprofile_perf_exit();
}
* the CPU clock speed on the fly.
*/
+#include <linux/module.h>
#include <linux/cpufreq.h>
#include <linux/clk.h>
#include <linux/err.h>
return ret;
}
-static int __init mxc_cpufreq_init(struct cpufreq_policy *policy)
+static int mxc_cpufreq_init(struct cpufreq_policy *policy)
{
int ret;
int i;
};
extern void mx5_cpu_lp_set(enum mxc_cpu_pwr_mode mode);
-extern void (*imx_idle)(void);
extern void imx_print_silicon_rev(const char *cpu, int srev);
void avic_handle_irq(struct pt_regs *);
extern void imx53_smd_common_init(void);
extern int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode);
extern void imx6q_pm_init(void);
+extern void imx6q_clock_map_io(void);
#endif
#define IMX_CHIP_REVISION_3_3 0x33
#define IMX_CHIP_REVISION_UNKNOWN 0xff
-#define IMX_CHIP_REVISION_1_0_STRING "1.0"
-#define IMX_CHIP_REVISION_1_1_STRING "1.1"
-#define IMX_CHIP_REVISION_1_2_STRING "1.2"
-#define IMX_CHIP_REVISION_1_3_STRING "1.3"
-#define IMX_CHIP_REVISION_2_0_STRING "2.0"
-#define IMX_CHIP_REVISION_2_1_STRING "2.1"
-#define IMX_CHIP_REVISION_2_2_STRING "2.2"
-#define IMX_CHIP_REVISION_2_3_STRING "2.3"
-#define IMX_CHIP_REVISION_3_0_STRING "3.0"
-#define IMX_CHIP_REVISION_3_1_STRING "3.1"
-#define IMX_CHIP_REVISION_3_2_STRING "3.2"
-#define IMX_CHIP_REVISION_3_3_STRING "3.3"
-#define IMX_CHIP_REVISION_UNKNOWN_STRING "unknown"
-
#ifndef __ASSEMBLY__
extern unsigned int __mxc_cpu_type;
#endif
#ifndef __ASM_ARCH_MXC_SYSTEM_H__
#define __ASM_ARCH_MXC_SYSTEM_H__
-extern void (*imx_idle)(void);
-
static inline void arch_idle(void)
{
- if (imx_idle != NULL)
- (imx_idle)();
- else
- cpu_do_idle();
+ cpu_do_idle();
}
void arch_reset(char mode, const char *cmd);
case MACH_TYPE_PCM043:
case MACH_TYPE_LILLY1131:
case MACH_TYPE_VPR200:
+ case MACH_TYPE_EUKREA_CPUIMX35SD:
uart_base = MX3X_UART1_BASE_ADDR;
break;
case MACH_TYPE_MAGX_ZN5:
#define MX3_PWMSAR 0x0C /* PWM Sample Register */
#define MX3_PWMPR 0x10 /* PWM Period Register */
#define MX3_PWMCR_PRESCALER(x) (((x - 1) & 0xFFF) << 4)
+#define MX3_PWMCR_DOZEEN (1 << 24)
+#define MX3_PWMCR_WAITEN (1 << 23)
+#define MX3_PWMCR_DBGEN (1 << 22)
#define MX3_PWMCR_CLKSRC_IPG_HIGH (2 << 16)
#define MX3_PWMCR_CLKSRC_IPG (1 << 16)
#define MX3_PWMCR_EN (1 << 0)
do_div(c, period_ns);
duty_cycles = c;
+ /*
+ * according to imx pwm RM, the real period value should be
+ * PERIOD value in PWMPR plus 2.
+ */
+ if (period_cycles > 2)
+ period_cycles -= 2;
+ else
+ period_cycles = 0;
+
writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR);
writel(period_cycles, pwm->mmio_base + MX3_PWMPR);
- cr = MX3_PWMCR_PRESCALER(prescale) | MX3_PWMCR_EN;
+ cr = MX3_PWMCR_PRESCALER(prescale) |
+ MX3_PWMCR_DOZEEN | MX3_PWMCR_WAITEN |
+ MX3_PWMCR_DBGEN | MX3_PWMCR_EN;
if (cpu_is_mx25())
cr |= MX3_PWMCR_CLKSRC_IPG;
#include <linux/io.h>
#include <linux/err.h>
#include <linux/delay.h>
+#include <linux/module.h>
#include <mach/hardware.h>
#include <mach/common.h>
#include <asm/system.h>
#include <asm/mach-types.h>
-void (*imx_idle)(void) = NULL;
void __iomem *(*imx_ioremap)(unsigned long, size_t, unsigned int) = NULL;
+EXPORT_SYMBOL_GPL(imx_ioremap);
static void __iomem *wdog_base;
u8 auto_recal_bit;
u8 recal_en_bit;
u8 recal_st_bit;
- u8 flags;
# endif
+ u8 flags;
};
#endif
#include <linux/delay.h>
#include <plat/i2c.h>
+#include <plat/omap_hwmod.h>
struct sys_timer;
void ti816x_init_early(void);
void omap4430_init_early(void);
+extern int omap_dss_reset(struct omap_hwmod *);
+
void omap_sram_init(void);
/*
struct orion_gpio_chip *ochip;
struct irq_chip_generic *gc;
struct irq_chip_type *ct;
+ char gc_label[16];
if (orion_gpio_chip_count == ARRAY_SIZE(orion_gpio_chips))
return;
+ snprintf(gc_label, sizeof(gc_label), "orion_gpio%d",
+ orion_gpio_chip_count);
+
ochip = orion_gpio_chips + orion_gpio_chip_count;
- ochip->chip.label = "orion_gpio";
+ ochip->chip.label = kstrdup(gc_label, GFP_KERNEL);
ochip->chip.request = orion_gpio_request;
ochip->chip.direction_input = orion_gpio_direction_input;
ochip->chip.get = orion_gpio_get;
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/ioport.h>
#include <linux/cpufreq.h>
#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
+#include <linux/export.h>
#include <asm/pgtable.h>
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/pwm_backlight.h>
-#include <linux/slab.h>
#include <plat/devs.h>
#include <plat/gpio-cfg.h>
extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void);
extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void);
-extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
- struct s3c_cpufreq_config *cfg,
- union s3c_iobank *iob);
-
-extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
- struct s3c_cpufreq_config *cfg,
- union s3c_iobank *iob);
-
#ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUGFS
#define s3c_cpufreq_debugfs_call(x) x
#else
extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg);
#ifdef CONFIG_S3C2410_IOTIMING
+extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
+ struct s3c_cpufreq_config *cfg,
+ union s3c_iobank *iob);
+
extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg,
struct s3c_iotimings *iot);
extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
struct s3c_iotimings *iot);
#else
+#define s3c2410_iotiming_debugfs NULL
#define s3c2410_iotiming_calc NULL
#define s3c2410_iotiming_get NULL
#define s3c2410_iotiming_set NULL
/* S3C2412 compatible routines */
-extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
- struct s3c_iotimings *timings);
+#ifdef CONFIG_S3C2412_IOTIMING
+extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
+ struct s3c_cpufreq_config *cfg,
+ union s3c_iobank *iob);
extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
struct s3c_iotimings *timings);
extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg,
struct s3c_iotimings *iot);
+#else
+#define s3c2412_iotiming_debugfs NULL
+#define s3c2412_iotiming_calc NULL
+#define s3c2412_iotiming_get NULL
+#define s3c2412_iotiming_set NULL
+#endif /* CONFIG_S3C2412_IOTIMING */
#ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUG
#define s3c_freq_dbg(x...) printk(KERN_INFO x)
#ifndef __PLAT_GPIO_CFG_H
#define __PLAT_GPIO_CFG_H __FILE__
+#include<linux/types.h>
+
typedef unsigned int __bitwise__ samsung_gpio_pull_t;
typedef unsigned int __bitwise__ s5p_gpio_drvstr_t;
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/platform_device.h>
#include <linux/err.h>
#include <linux/pm_runtime.h>
* the Free Software Foundation; either version 2 of the License.
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
thales_adc MACH_THALES_ADC THALES_ADC 3492
ubisys_p9d_evp MACH_UBISYS_P9D_EVP UBISYS_P9D_EVP 3493
atdgp318 MACH_ATDGP318 ATDGP318 3494
+m28evk MACH_M28EVK M28EVK 3613
smdk4212 MACH_SMDK4212 SMDK4212 3638
smdk4412 MACH_SMDK4412 SMDK4412 3765
config ETRAX_ETHERNET
bool "Ethernet support"
depends on ETRAX_ARCH_V10
- select NET_ETHERNET
+ select ETHERNET
select NET_CORE
select MII
help
config ETRAX_ETHERNET
bool "Ethernet support"
depends on ETRAX_ARCH_V32
- select NET_ETHERNET
+ select ETHERNET
select NET_CORE
select MII
help
*/
#define cputime_to_usecs(__ct) ((__ct) / NSEC_PER_USEC)
#define usecs_to_cputime(__usecs) ((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs) usecs_to_cputime(__usecs)
/*
* Convert cputime <-> seconds
#define __NR_clock_adjtime 342
#define __NR_syncfs 343
#define __NR_setns 344
+#define __NR_process_vm_readv 345
+#define __NR_process_vm_writev 346
#ifdef __KERNEL__
-#define NR_syscalls 345
+#define NR_syscalls 347
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
.long sys_clock_adjtime
.long sys_syncfs
.long sys_setns
+ .long sys_process_vm_readv /* 345 */
+ .long sys_process_vm_writev
+++ /dev/null
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_NAMEI_H
-#define _ASM_MICROBLAZE_NAMEI_H
-
-#ifdef __KERNEL__
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-#define __emul_prefix() NULL
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_MICROBLAZE_NAMEI_H */
static struct map_info flash_map;
static struct mtd_info *mymtd;
-static int nr_parts;
-static struct mtd_partition *parts;
static const char *part_probe_types[] = {
"cmdlinepart",
#ifdef CONFIG_MTD_REDBOOT_PARTS
mymtd = do_map_probe("cfi_probe", &flash_map);
if (mymtd) {
mymtd->owner = THIS_MODULE;
-
- nr_parts = parse_mtd_partitions(mymtd,
- part_probe_types,
- &parts, 0);
- mtd_device_register(mymtd, parts, nr_parts);
+ mtd_device_parse_register(mymtd, part_probe_types,
+ 0, NULL, 0);
} else {
pr_err("Failed to register MTD device for flash\n");
}
* the other bits alone.
*/
cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffff);
- if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED,
- "SMP-IPI", mailbox_interrupt)) {
+ if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt,
+ IRQF_PERCPU | IRQF_NO_THREAD, "SMP-IPI",
+ mailbox_interrupt)) {
panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n");
}
}
/* arg[0] is "g", the rest is boot parameters */
for (i = 1; i < argc; i++) {
- if (strlen(arcs_cmdline) + strlen(arg[i] + 1)
+ if (strlen(arcs_cmdline) + strlen(arg[i]) + 1
>= sizeof(arcs_cmdline))
break;
strcat(arcs_cmdline, arg[i]);
* Ethernet interface
*/
struct mace_ethernet {
- volatile unsigned long mac_ctrl;
+ volatile u64 mac_ctrl;
volatile unsigned long int_stat;
volatile unsigned long dma_ctrl;
volatile unsigned long timer;
return -EINVAL;
}
+#define gpio_get_value_cansleep gpio_get_value
+
static inline void gpio_set_value(unsigned gpio, int value)
{
switch (bcm47xx_bus_type) {
}
}
+#define gpio_set_value_cansleep gpio_set_value
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+ return 0;
+}
+
+static inline int gpio_is_valid(unsigned gpio)
+{
+ return gpio < (BCM47XX_EXTIF_GPIO_LINES + BCM47XX_CHIPCO_GPIO_LINES);
+}
+
+
static inline int gpio_direction_input(unsigned gpio)
{
switch (bcm47xx_bus_type) {
}
-/* cansleep wrappers */
-#include <asm-generic/gpio.h>
-
#endif /* __BCM47XX_GPIO_H */
#define __NR_syncfs (__NR_Linux + 342)
#define __NR_sendmmsg (__NR_Linux + 343)
#define __NR_setns (__NR_Linux + 344)
+#define __NR_process_vm_readv (__NR_Linux + 345)
+#define __NR_process_vm_writev (__NR_Linux + 346)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 344
+#define __NR_Linux_syscalls 346
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 344
+#define __NR_O32_Linux_syscalls 346
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_syncfs (__NR_Linux + 301)
#define __NR_sendmmsg (__NR_Linux + 302)
#define __NR_setns (__NR_Linux + 303)
+#define __NR_process_vm_readv (__NR_Linux + 304)
+#define __NR_process_vm_writev (__NR_Linux + 305)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 303
+#define __NR_Linux_syscalls 305
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 303
+#define __NR_64_Linux_syscalls 305
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_syncfs (__NR_Linux + 306)
#define __NR_sendmmsg (__NR_Linux + 307)
#define __NR_setns (__NR_Linux + 308)
+#define __NR_process_vm_readv (__NR_Linux + 309)
+#define __NR_process_vm_writev (__NR_Linux + 310)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 308
+#define __NR_Linux_syscalls 310
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 308
+#define __NR_N32_Linux_syscalls 310
#ifdef __KERNEL__
/*
* Compare interrupt can be routed and latched outside the core,
- * so a single execution hazard barrier may not be enough to give
- * it time to clear as seen in the Cause register. 4 time the
- * pipeline depth seems reasonably conservative, and empirically
- * works better in configurations with high CPU/bus clock ratios.
+ * so wait up to worst case number of cycle counter ticks for timer interrupt
+ * changes to propagate to the cause register.
*/
-
-#define compare_change_hazard() \
- do { \
- irq_disable_hazard(); \
- irq_disable_hazard(); \
- irq_disable_hazard(); \
- irq_disable_hazard(); \
- } while (0)
+#define COMPARE_INT_SEEN_TICKS 50
int c0_compare_int_usable(void)
{
* IP7 already pending? Try to clear it by acking the timer.
*/
if (c0_compare_int_pending()) {
- write_c0_compare(read_c0_count());
- compare_change_hazard();
+ cnt = read_c0_count();
+ write_c0_compare(cnt);
+ back_to_back_c0_hazard();
+ while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+ if (!c0_compare_int_pending())
+ break;
if (c0_compare_int_pending())
return 0;
}
cnt = read_c0_count();
cnt += delta;
write_c0_compare(cnt);
- compare_change_hazard();
+ back_to_back_c0_hazard();
if ((int)(read_c0_count() - cnt) < 0)
break;
/* increase delta if the timer was already expired */
while ((int)(read_c0_count() - cnt) <= 0)
; /* Wait for expiry */
- compare_change_hazard();
+ while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+ if (c0_compare_int_pending())
+ break;
if (!c0_compare_int_pending())
return 0;
-
- write_c0_compare(read_c0_count());
- compare_change_hazard();
+ cnt = read_c0_count();
+ write_c0_compare(cnt);
+ back_to_back_c0_hazard();
+ while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+ if (!c0_compare_int_pending())
+ break;
if (c0_compare_int_pending())
return 0;
* for more details.
*/
+#include <linux/module.h>
#include <linux/cpufreq.h>
#include <linux/platform_device.h>
if (!atomic_inc_not_zero(&active_events)) {
if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
atomic_dec(&active_events);
- return -ENOSPC;
+ return -EINVAL;
}
mutex_lock(&pmu_reserve_mutex);
memset(&fake_cpuc, 0, sizeof(fake_cpuc));
if (!validate_event(&fake_cpuc, leader))
- return -ENOSPC;
+ return -EINVAL;
list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
if (!validate_event(&fake_cpuc, sibling))
- return -ENOSPC;
+ return -EINVAL;
}
if (!validate_event(&fake_cpuc, event))
- return -ENOSPC;
+ return -EINVAL;
return 0;
}
sys sys_syncfs 1
sys sys_sendmmsg 4
sys sys_setns 2
+ sys sys_process_vm_readv 6 /* 4345 */
+ sys sys_process_vm_writev 6
.endm
/* We pre-compute the number of _instruction_ bytes needed to
PTR sys_syncfs
PTR sys_sendmmsg
PTR sys_setns
+ PTR sys_process_vm_readv
+ PTR sys_process_vm_writev /* 5305 */
.size sys_call_table,.-sys_call_table
PTR sys_syncfs
PTR compat_sys_sendmmsg
PTR sys_setns
+ PTR compat_sys_process_vm_readv
+ PTR compat_sys_process_vm_writev /* 6310 */
.size sysn32_call_table,.-sysn32_call_table
PTR sys_syncfs
PTR compat_sys_sendmmsg
PTR sys_setns
+ PTR compat_sys_process_vm_readv /* 4345 */
+ PTR compat_sys_process_vm_writev
.size sys_call_table,.-sys_call_table
}
#endif /* CONFIG_MIPS_MT_SMTC */
- cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
+ if (!cpu_data[cpu].asid_cache)
+ cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
* Copyright (C) 2010 John Crispin <blogic@openwrt.org>
*/
#include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/types.h>
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kernel.h>
* Copyright (C) 2010 John Crispin <blogic@openwrt.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/clk.h>
#include <asm/bootinfo.h>
#include <asm/time.h>
*/
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/io.h>
#include <linux/ioport.h>
#include <asm/bootinfo.h>
*/
#include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/clk.h>
*/
#include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/clk.h>
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/mtd/physmap.h>
#include <linux/platform_device.h>
#include <linux/io.h>
#include <linux/dma-mapping.h>
+#include <linux/export.h>
#include <lantiq_soc.h>
#include <xway_dma.h>
*/
#include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/platform_device.h>
#include <linux/gpio.h>
#include <linux/ioport.h>
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/platform_device.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/platform_device.h>
#include <linux/mutex.h>
* Copyright (C) 2010 John Crispin <blogic@openwrt.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/clk.h>
#include <asm/bootinfo.h>
#include <asm/time.h>
* Copyright (C) 2010 John Crispin <blogic@openwrt.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/clk.h>
#include <asm/bootinfo.h>
#include <asm/time.h>
#include <linux/io.h>
#include <linux/ioport.h>
#include <linux/pm.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/reboot.h>
#include <lantiq_soc.h>
+++ /dev/null
-/*
- *
- * BRIEF MODULE DESCRIPTION
- *
- * Author: source@mvista.com
- *
- * This program is free software; you can distribute it and/or modify it
- * under the terms of the GNU General Public License (Version 2) as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-
-#include <pci.h>
-#include <glb.h>
-#include <nand.h>
-
-static struct resource pci_io_resource = {
- .start = PNX8550_PCIIO + 0x1000, /* reserve regacy I/O space */
- .end = PNX8550_PCIIO + PNX8550_PCIIO_SIZE,
- .name = "pci IO space",
- .flags = IORESOURCE_IO
-};
-
-static struct resource pci_mem_resource = {
- .start = PNX8550_PCIMEM,
- .end = PNX8550_PCIMEM + PNX8550_PCIMEM_SIZE - 1,
- .name = "pci memory space",
- .flags = IORESOURCE_MEM
-};
-
-extern struct pci_ops pnx8550_pci_ops;
-
-static struct pci_controller pnx8550_controller = {
- .pci_ops = &pnx8550_pci_ops,
- .io_map_base = PNX8550_PORT_BASE,
- .io_resource = &pci_io_resource,
- .mem_resource = &pci_mem_resource,
-};
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-static inline unsigned long get_system_mem_size(void)
-{
- /* Read IP2031_RANK0_ADDR_LO */
- unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
- /* Read IP2031_RANK1_ADDR_HI */
- unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
- return dram_r1_hi - dram_r0_lo + 1;
-}
-
-static int __init pnx8550_pci_setup(void)
-{
- int pci_mem_code;
- int mem_size = get_system_mem_size() >> 20;
-
- /* Clear the Global 2 Register, PCI Inta Output Enable Registers
- Bit 1:Enable DAC Powerdown
- -> 0:DACs are enabled and are working normally
- 1:DACs are powerdown
- Bit 0:Enable of PCI inta output
- -> 0 = Disable PCI inta output
- 1 = Enable PCI inta output
- */
- PNX8550_GLB2_ENAB_INTA_O = 0;
-
- /* Calc the PCI mem size code */
- if (mem_size >= 128)
- pci_mem_code = SIZE_128M;
- else if (mem_size >= 64)
- pci_mem_code = SIZE_64M;
- else if (mem_size >= 32)
- pci_mem_code = SIZE_32M;
- else
- pci_mem_code = SIZE_16M;
-
- /* Set PCI_XIO registers */
- outl(pci_mem_resource.start, PCI_BASE | PCI_BASE1_LO);
- outl(pci_mem_resource.end + 1, PCI_BASE | PCI_BASE1_HI);
- outl(pci_io_resource.start, PCI_BASE | PCI_BASE2_LO);
- outl(pci_io_resource.end, PCI_BASE | PCI_BASE2_HI);
-
- /* Send memory transaction via PCI_BASE2 */
- outl(0x00000001, PCI_BASE | PCI_IO);
-
- /* Unlock the setup register */
- outl(0xca, PCI_BASE | PCI_UNLOCKREG);
-
- /*
- * BAR0 of PNX8550 (pci base 10) must be zero in order for ide
- * to work, and in order for bus_to_baddr to work without any
- * hacks.
- */
- outl(0x00000000, PCI_BASE | PCI_BASE10);
-
- /*
- *These two bars are set by default or the boot code.
- * However, it's safer to set them here so we're not boot
- * code dependent.
- */
- outl(0x1be00000, PCI_BASE | PCI_BASE14); /* PNX MMIO */
- outl(PNX8550_NAND_BASE_ADDR, PCI_BASE | PCI_BASE18); /* XIO */
-
- outl(PCI_EN_TA |
- PCI_EN_PCI2MMI |
- PCI_EN_XIO |
- PCI_SETUP_BASE18_SIZE(SIZE_32M) |
- PCI_SETUP_BASE18_EN |
- PCI_SETUP_BASE14_EN |
- PCI_SETUP_BASE10_PREF |
- PCI_SETUP_BASE10_SIZE(pci_mem_code) |
- PCI_SETUP_CFGMANAGE_EN |
- PCI_SETUP_PCIARB_EN,
- PCI_BASE |
- PCI_SETUP); /* PCI_SETUP */
- outl(0x00000000, PCI_BASE | PCI_CTRL); /* PCI_CONTROL */
-
- register_pci_controller(&pnx8550_controller);
-
- return 0;
-}
-
-arch_initcall(pnx8550_pci_setup);
+++ /dev/null
-/*
- *
- * 2.6 port, Embedded Alley Solutions, Inc
- *
- * Based on Per Hallsmark, per.hallsmark@mvista.com
- *
- * This program is free software; you can distribute it and/or modify it
- * under the terms of the GNU General Public License (Version 2) as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/irq.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/serial_pnx8xxx.h>
-#include <linux/pm.h>
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
-#include <asm/time.h>
-
-#include <glb.h>
-#include <int.h>
-#include <pci.h>
-#include <uart.h>
-#include <nand.h>
-
-extern void __init board_setup(void);
-extern void pnx8550_machine_restart(char *);
-extern void pnx8550_machine_halt(void);
-extern void pnx8550_machine_power_off(void);
-extern struct resource ioport_resource;
-extern struct resource iomem_resource;
-extern char *prom_getcmdline(void);
-
-struct resource standard_io_resources[] = {
- {
- .start = 0x00,
- .end = 0x1f,
- .name = "dma1",
- .flags = IORESOURCE_BUSY
- }, {
- .start = 0x40,
- .end = 0x5f,
- .name = "timer",
- .flags = IORESOURCE_BUSY
- }, {
- .start = 0x80,
- .end = 0x8f,
- .name = "dma page reg",
- .flags = IORESOURCE_BUSY
- }, {
- .start = 0xc0,
- .end = 0xdf,
- .name = "dma2",
- .flags = IORESOURCE_BUSY
- },
-};
-
-#define STANDARD_IO_RESOURCES ARRAY_SIZE(standard_io_resources)
-
-extern struct resource pci_io_resource;
-extern struct resource pci_mem_resource;
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-unsigned long get_system_mem_size(void)
-{
- /* Read IP2031_RANK0_ADDR_LO */
- unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
- /* Read IP2031_RANK1_ADDR_HI */
- unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
- return dram_r1_hi - dram_r0_lo + 1;
-}
-
-int pnx8550_console_port = -1;
-
-void __init plat_mem_setup(void)
-{
- int i;
- char* argptr;
-
- board_setup(); /* board specific setup */
-
- _machine_restart = pnx8550_machine_restart;
- _machine_halt = pnx8550_machine_halt;
- pm_power_off = pnx8550_machine_power_off;
-
- /* Clear the Global 2 Register, PCI Inta Output Enable Registers
- Bit 1:Enable DAC Powerdown
- -> 0:DACs are enabled and are working normally
- 1:DACs are powerdown
- Bit 0:Enable of PCI inta output
- -> 0 = Disable PCI inta output
- 1 = Enable PCI inta output
- */
- PNX8550_GLB2_ENAB_INTA_O = 0;
-
- /* IO/MEM resources. */
- set_io_port_base(PNX8550_PORT_BASE);
- ioport_resource.start = 0;
- ioport_resource.end = ~0;
- iomem_resource.start = 0;
- iomem_resource.end = ~0;
-
- /* Request I/O space for devices on this board */
- for (i = 0; i < STANDARD_IO_RESOURCES; i++)
- request_resource(&ioport_resource, standard_io_resources + i);
-
- /* Place the Mode Control bit for GPIO pin 16 in primary function */
- /* Pin 16 is used by UART1, UA1_TX */
- outl((PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_16_BIT) |
- (PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_17_BIT),
- PNX8550_GPIO_MC1);
-
- argptr = prom_getcmdline();
- if ((argptr = strstr(argptr, "console=ttyS")) != NULL) {
- argptr += strlen("console=ttyS");
- pnx8550_console_port = *argptr == '0' ? 0 : 1;
-
- /* We must initialize the UART (console) before early printk */
- /* Set LCR to 8-bit and BAUD to 38400 (no 5) */
- ip3106_lcr(UART_BASE, pnx8550_console_port) =
- PNX8XXX_UART_LCR_8BIT;
- ip3106_baud(UART_BASE, pnx8550_console_port) = 5;
- }
-}
* Support for all devices (greater than 16) added by David Gathright.
*/
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
+#include <linux/export.h>
#include <linux/platform_device.h>
#include <asm/pci.h>
/* Get the boot parameters */
for (i = 1; i < argc; i++) {
- if (strlen(arcs_cmdline) + strlen(arg[i] + 1) >=
+ if (strlen(arcs_cmdline) + strlen(arg[i]) + 1 >=
sizeof(arcs_cmdline))
break;
config KEXEC
bool "kexec system call (EXPERIMENTAL)"
- depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !47x)) && EXPERIMENTAL
+ depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !PPC_47x)) && EXPERIMENTAL
help
kexec is a system call that implements the ability to shutdown your
current kernel, and to start another kernel. It is like a reboot
echo 'disable kernel modules' ; \
false ; \
fi
- @if ! /bin/echo dssall | $(AS) -many -o $(TOUT) >/dev/null 2>&1 ; then \
- echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build ' ; \
- echo 'correctly with old versions of binutils.' ; \
- echo '*** Please upgrade your binutils to 2.12.1 or newer' ; \
- false ; \
- fi
CLEAN_FILES += $(TOUT)
interrupt-parent = <&mpic>;
interrupts = <16 2>;
interrupt-map-mask = <0xf800 0 0 7>;
+ /* IRQ[0:3] are pulled up on board, set to active-low */
interrupt-map = <
/* IDSEL 0x0 */
0000 0 0 1 &mpic 0 1
interrupt-parent = <&mpic>;
interrupts = <16 2>;
interrupt-map-mask = <0xf800 0 0 7>;
+ /*
+ * IRQ[4:6] only for PCIe, set to active-high,
+ * IRQ[7] is pulled up on board, set to active-low
+ */
interrupt-map = <
/* IDSEL 0x0 */
- 0000 0 0 1 &mpic 4 1
- 0000 0 0 2 &mpic 5 1
- 0000 0 0 3 &mpic 6 1
+ 0000 0 0 1 &mpic 4 2
+ 0000 0 0 2 &mpic 5 2
+ 0000 0 0 3 &mpic 6 2
0000 0 0 4 &mpic 7 1
>;
ranges = <0x2000000 0x0 0xa0000000
interrupt-parent = <&mpic>;
interrupts = <16 2>;
interrupt-map-mask = <0xf800 0 0 7>;
+ /*
+ * IRQ[8:10] are pulled up on board, set to active-low
+ * IRQ[11] only for PCIe, set to active-high,
+ */
interrupt-map = <
/* IDSEL 0x0 */
0000 0 0 1 &mpic 8 1
0000 0 0 2 &mpic 9 1
0000 0 0 3 &mpic 10 1
- 0000 0 0 4 &mpic 11 1
+ 0000 0 0 4 &mpic 11 2
>;
ranges = <0x2000000 0x0 0x80000000
0x2000000 0x0 0x80000000
ranges = <
0 0x0 0xfc000000 0x04000000 // NOR FLASH bank 1
1 0x0 0xf8000000 0x08000000 // NOR FLASH bank 0
- 2 0x0 0xa3000000 0x00008000 // CAN (2 x i82527)
+ 2 0x0 0xa3000000 0x00008000 // CAN (2 x CC770)
3 0x0 0xa3010000 0x00008000 // NAND FLASH
>;
};
/* Note: CAN support needs be enabled in U-Boot */
- can0@2,0 {
- compatible = "intel,82527"; // Bosch CC770
+ can@2,0 {
+ compatible = "bosch,cc770"; // Bosch CC770
reg = <2 0x0 0x100>;
interrupts = <4 1>;
interrupt-parent = <&mpic>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
+ bosch,clock-out-frequency = <16000000>;
};
- can1@2,100 {
- compatible = "intel,82527"; // Bosch CC770
+ can@2,100 {
+ compatible = "bosch,cc770"; // Bosch CC770
reg = <2 0x100 0x100>;
interrupts = <4 1>;
interrupt-parent = <&mpic>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
};
/* Note: NAND support needs to be enabled in U-Boot */
ranges = <
0 0x0 0xfc000000 0x04000000 // NOR FLASH bank 1
1 0x0 0xf8000000 0x08000000 // NOR FLASH bank 0
- 2 0x0 0xe3000000 0x00008000 // CAN (2 x i82527)
+ 2 0x0 0xe3000000 0x00008000 // CAN (2 x CC770)
3 0x0 0xe3010000 0x00008000 // NAND FLASH
>;
};
/* Note: CAN support needs be enabled in U-Boot */
- can0@2,0 {
- compatible = "intel,82527"; // Bosch CC770
+ can@2,0 {
+ compatible = "bosch,cc770"; // Bosch CC770
reg = <2 0x0 0x100>;
interrupts = <4 1>;
interrupt-parent = <&mpic>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
+ bosch,clock-out-frequency = <16000000>;
};
- can1@2,100 {
- compatible = "intel,82527"; // Bosch CC770
+ can@2,100 {
+ compatible = "bosch,cc770"; // Bosch CC770
reg = <2 0x100 0x100>;
interrupts = <4 1>;
interrupt-parent = <&mpic>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
};
/* Note: NAND support needs to be enabled in U-Boot */
ranges = <
0x0 0x0 0x40000000 0x800000
+ 0x3 0x0 0xc0000000 0x200
>;
flash@0,0 {
bank-width = <4>;
device-width = <2>;
};
+
+ /* Note: CAN support needs be enabled in U-Boot */
+ can@3,0 {
+ compatible = "intc,82527";
+ reg = <3 0x0 0x80>;
+ interrupts = <8 1>;
+ interrupt-parent = <&PIC>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
+ bosch,clock-out-frequency = <16000000>;
+ };
+
+ can@3,100 {
+ compatible = "intc,82527";
+ reg = <3 0x100 0x80>;
+ interrupts = <8 1>;
+ interrupt-parent = <&PIC>;
+ bosch,external-clock-frequency = <16000000>;
+ bosch,disconnect-rx1-input;
+ bosch,disconnect-tx1-output;
+ bosch,iso-low-speed-mux;
+ };
};
soc@fff00000 {
CONFIG_MTD_JEDECPROBE=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_NAND=m
+CONFIG_MTD_NAND_NDFC=m
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_GLUEBI=m
CONFIG_PROC_DEVICETREE=y
int t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%2 # atomic_add_return\n\
add %0,%1,%0\n"
PPC405_ERR77(0,%2)
" stwcx. %0,0,%2 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (a), "r" (&v->counter)
: "cc", "memory");
int t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%2 # atomic_sub_return\n\
subf %0,%1,%0\n"
PPC405_ERR77(0,%2)
" stwcx. %0,0,%2 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (a), "r" (&v->counter)
: "cc", "memory");
int t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%1 # atomic_inc_return\n\
addic %0,%0,1\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (&v->counter)
: "cc", "xer", "memory");
int t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%1 # atomic_dec_return\n\
addic %0,%0,-1\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (&v->counter)
: "cc", "xer", "memory");
int t;
__asm__ __volatile__ (
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%1 # __atomic_add_unless\n\
cmpw 0,%0,%3 \n\
beq- 2f \n\
PPC405_ERR77(0,%2)
" stwcx. %0,0,%1 \n\
bne- 1b \n"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
" subf %0,%2,%0 \n\
2:"
: "=&r" (t)
int t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %0,0,%1 # atomic_dec_if_positive\n\
cmpwi %0,1\n\
addi %0,%0,-1\n\
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
"\n\
2:" : "=&b" (t)
: "r" (&v->counter)
long t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%2 # atomic64_add_return\n\
add %0,%1,%0\n\
stdcx. %0,0,%2 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (a), "r" (&v->counter)
: "cc", "memory");
long t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%2 # atomic64_sub_return\n\
subf %0,%1,%0\n\
stdcx. %0,0,%2 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (a), "r" (&v->counter)
: "cc", "memory");
long t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%1 # atomic64_inc_return\n\
addic %0,%0,1\n\
stdcx. %0,0,%1 \n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (&v->counter)
: "cc", "xer", "memory");
long t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%1 # atomic64_dec_return\n\
addic %0,%0,-1\n\
stdcx. %0,0,%1\n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
: "=&r" (t)
: "r" (&v->counter)
: "cc", "xer", "memory");
long t;
__asm__ __volatile__(
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%1 # atomic64_dec_if_positive\n\
addic. %0,%0,-1\n\
blt- 2f\n\
stdcx. %0,0,%1\n\
bne- 1b"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
"\n\
2:" : "=&r" (t)
: "r" (&v->counter)
long t;
__asm__ __volatile__ (
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: ldarx %0,0,%1 # __atomic_add_unless\n\
cmpd 0,%0,%3 \n\
beq- 2f \n\
add %0,%2,%0 \n"
" stdcx. %0,0,%1 \n\
bne- 1b \n"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
" subf %0,%2,%0 \n\
2:"
: "=&r" (t)
return (old & mask); \
}
-DEFINE_TESTOP(test_and_set_bits, or, PPC_RELEASE_BARRIER,
- PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
+ PPC_ATOMIC_EXIT_BARRIER, 0)
DEFINE_TESTOP(test_and_set_bits_lock, or, "",
PPC_ACQUIRE_BARRIER, 1)
-DEFINE_TESTOP(test_and_clear_bits, andc, PPC_RELEASE_BARRIER,
- PPC_ACQUIRE_BARRIER, 0)
-DEFINE_TESTOP(test_and_change_bits, xor, PPC_RELEASE_BARRIER,
- PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
+ PPC_ATOMIC_EXIT_BARRIER, 0)
+DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
+ PPC_ATOMIC_EXIT_BARRIER, 0)
static __inline__ int test_and_set_bit(unsigned long nr,
volatile unsigned long *addr)
return ct;
}
+#define usecs_to_cputime64(us) usecs_to_cputime(us)
+
/*
* Convert cputime <-> seconds
*/
#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
__asm__ __volatile ( \
- PPC_RELEASE_BARRIER \
+ PPC_ATOMIC_ENTRY_BARRIER \
"1: lwarx %0,0,%2\n" \
insn \
PPC405_ERR77(0, %2) \
"2: stwcx. %1,0,%2\n" \
"bne- 1b\n" \
+ PPC_ATOMIC_EXIT_BARRIER \
"li %1,0\n" \
"3: .section .fixup,\"ax\"\n" \
"4: li %1,%3\n" \
return -EFAULT;
__asm__ __volatile__ (
- PPC_RELEASE_BARRIER
+ PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\
cmpw 0,%1,%4\n\
bne- 3f\n"
PPC405_ERR77(0,%3)
"2: stwcx. %5,0,%3\n\
bne- 1b\n"
- PPC_ACQUIRE_BARRIER
+ PPC_ATOMIC_EXIT_BARRIER
"3: .section .fixup,\"ax\"\n\
4: li %0,%6\n\
b 3b\n\
#define KVM_SREGS_E_UPDATE_DEC (1 << 2)
#define KVM_SREGS_E_UPDATE_DBSR (1 << 3)
-/*
- * Book3S special bits to indicate contents in the struct by maintaining
- * backwards compatibility with older structs. If adding a new field,
- * please make sure to add a flag for that new field */
-#define KVM_SREGS_S_HIOR (1 << 0)
-
/*
* In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
* previous KVM_GET_REGS.
__u64 ibat[8];
__u64 dbat[8];
} ppc32;
- __u64 flags; /* KVM_SREGS_S_ */
- __u64 hior;
} s;
struct {
union {
#endif
int context_id[SID_CONTEXTS];
- bool hior_sregs; /* HIOR is set by SREGS, not PVR */
-
struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
}
#endif
-static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
- unsigned long pte_index)
-{
- unsigned long rb, va_low;
-
- rb = (v & ~0x7fUL) << 16; /* AVA field */
- va_low = pte_index >> 3;
- if (v & HPTE_V_SECONDARY)
- va_low = ~va_low;
- /* xor vsid from AVA */
- if (!(v & HPTE_V_1TB_SEG))
- va_low ^= v >> 12;
- else
- va_low ^= v >> 24;
- va_low &= 0x7ff;
- if (v & HPTE_V_LARGE) {
- rb |= 1; /* L field */
- if (cpu_has_feature(CPU_FTR_ARCH_206) &&
- (r & 0xff000)) {
- /* non-16MB large page, must be 64k */
- /* (masks depend on page size) */
- rb |= 0x1000; /* page encoding in LP field */
- rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
- rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */
- }
- } else {
- /* 4kB page */
- rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */
- }
- rb |= (v >> 54) & 0x300; /* B field */
- return rb;
-}
-
/* Magic register values loaded into r3 and r4 before the 'sc' assembly
* instruction for the OSI hypercalls */
#define OSI_SC_MAGIC_R3 0x113724FA
#define SPAPR_TCE_SHIFT 12
+static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
+ unsigned long pte_index)
+{
+ unsigned long rb, va_low;
+
+ rb = (v & ~0x7fUL) << 16; /* AVA field */
+ va_low = pte_index >> 3;
+ if (v & HPTE_V_SECONDARY)
+ va_low = ~va_low;
+ /* xor vsid from AVA */
+ if (!(v & HPTE_V_1TB_SEG))
+ va_low ^= v >> 12;
+ else
+ va_low ^= v >> 24;
+ va_low &= 0x7ff;
+ if (v & HPTE_V_LARGE) {
+ rb |= 1; /* L field */
+ if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+ (r & 0xff000)) {
+ /* non-16MB large page, must be 64k */
+ /* (masks depend on page size) */
+ rb |= 0x1000; /* page encoding in LP field */
+ rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
+ rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */
+ }
+ } else {
+ /* 4kB page */
+ rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */
+ }
+ rb |= (v >> 54) & 0x300; /* B field */
+ return rb;
+}
+
#endif /* __ASM_KVM_BOOK3S_64_H__ */
#define MSR_ MSR_ME | MSR_CE
#define MSR_KERNEL MSR_ | MSR_64BIT
-#define MSR_USER32 MSR_ | MSR_PR | MSR_EE | MSR_DE
+#define MSR_USER32 MSR_ | MSR_PR | MSR_EE
#define MSR_USER64 MSR_USER32 | MSR_64BIT
#elif defined (CONFIG_40x)
#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
#ifdef __powerpc64__
-extern char _end[];
+extern char __end_interrupts[];
static inline int in_kernel_text(unsigned long addr)
{
extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
void *fixup_end);
+extern void do_final_fixups(void);
static inline void eieio(void)
{
START_LWSYNC_SECTION(97); \
isync; \
MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
-#define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
-#define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n"
+#define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
+#define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n"
#else
#define PPC_ACQUIRE_BARRIER
#define PPC_RELEASE_BARRIER
+#define PPC_ATOMIC_ENTRY_BARRIER
+#define PPC_ATOMIC_EXIT_BARRIER
#endif
#endif /* __KERNEL__ */
stw r9,8(r1)
stw r11,12(r1)
stw r3,ORIG_GPR3(r1)
+ /*
+ * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
+ * If from user mode there is only one stack frame on the stack, and
+ * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
+ * stack frame to make trace_hardirqs_off happy.
+ */
+ andi. r12,r12,MSR_PR
+ beq 11f
+ stwu r1,-16(r1)
+ bl trace_hardirqs_off
+ addi r1,r1,16
+ b 12f
+
+11:
bl trace_hardirqs_off
+12:
lwz r0,GPR0(r1)
lwz r3,ORIG_GPR3(r1)
lwz r4,GPR4(r1)
#include <linux/jump_label.h>
#include <asm/code-patching.h>
+#ifdef HAVE_JUMP_LABEL
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
else
patch_instruction(addr, PPC_INST_NOP);
}
+#endif
/* On relocatable kernels interrupts handlers and our code
can be in different regions, so we don't patch them */
- extern u32 __end_interrupts;
if ((ulong)inst < (ulong)&__end_interrupts)
return;
#endif
mr r5, r31
li r0, 0
-#elif defined(CONFIG_44x) && !defined(CONFIG_47x)
+#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x)
/*
* Code for setting up 1:1 mapping for PPC440x for KEXEC
new_thread = &new->thread;
old_thread = ¤t->thread;
-#if defined(CONFIG_PPC_BOOK3E_64)
- /* XXX Current Book3E code doesn't deal with kernel side DBCR0,
- * we always hold the user values, so we set it now.
- *
- * However, we ensure the kernel MSR:DE is appropriately cleared too
- * to avoid spurrious single step exceptions in the kernel.
- *
- * This will have to change to merge with the ppc32 code at some point,
- * but I don't like much what ppc32 is doing today so there's some
- * thinking needed there
- */
- if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) {
- u32 dbcr0;
-
- mtmsr(mfmsr() & ~MSR_DE);
- isync();
- dbcr0 = mfspr(SPRN_DBCR0);
- dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0;
- mtspr(SPRN_DBCR0, dbcr0);
- }
-#endif /* CONFIG_PPC64_BOOK3E */
-
#ifdef CONFIG_PPC64
/*
* Collect processor utilization data per process
if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
printk("CFAR: "REG"\n", regs->orig_gpr3);
if (trap == 0x300 || trap == 0x600)
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
#else
printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr);
return;
base = alloc_down(size, PAGE_SIZE, 0);
- if (base == 0) {
- prom_printf("RTAS allocation failed !\n");
- return;
- }
+ if (base == 0)
+ prom_panic("Could not allocate memory for RTAS\n");
rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
if (!IHANDLE_VALID(rtas_inst)) {
PTRRELOC(&__start___lwsync_fixup),
PTRRELOC(&__stop___lwsync_fixup));
+ do_final_fixups();
+
return KERNELBASE + offset;
}
&__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
do_lwsync_fixups(cur_cpu_spec->cpu_features,
&__start___lwsync_fixup, &__stop___lwsync_fixup);
+ do_final_fixups();
/*
* Unflatten the device-tree passed by prom_init or kexec
compat_sigset_t cset;
switch (_NSIG_WORDS) {
- case 4: cset.sig[5] = set->sig[3] & 0xffffffffull;
+ case 4: cset.sig[6] = set->sig[3] & 0xffffffffull;
cset.sig[7] = set->sig[3] >> 32;
case 3: cset.sig[4] = set->sig[2] & 0xffffffffull;
cset.sig[5] = set->sig[2] >> 32;
if (user_mode(regs)) {
current->thread.dbcr0 &= ~DBCR0_IC;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0,
current->thread.dbcr1))
regs->msr |= MSR_DE;
else
/* Make sure the IDM bit is off */
current->thread.dbcr0 &= ~DBCR0_IDM;
-#endif
}
_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
#include <asm/processor.h>
#include <asm/cputhreads.h>
#include <asm/page.h>
+#include <asm/hvcall.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
tpaca->kvm_hstate.napping = 0;
vcpu->cpu = vc->pcpu;
smp_wmb();
-#ifdef CONFIG_PPC_ICP_NATIVE
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
if (vcpu->arch.ptid) {
tpaca->cpu_start = 0x80;
wmb();
#ifdef CONFIG_PPC_BOOK3S_64
if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
kvmppc_mmu_book3s_64_init(vcpu);
- if (!to_book3s(vcpu)->hior_sregs)
- to_book3s(vcpu)->hior = 0xfff00000;
+ to_book3s(vcpu)->hior = 0xfff00000;
to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
vcpu->arch.cpu_type = KVM_CPU_3S_64;
} else
#endif
{
kvmppc_mmu_book3s_32_init(vcpu);
- if (!to_book3s(vcpu)->hior_sregs)
- to_book3s(vcpu)->hior = 0;
+ to_book3s(vcpu)->hior = 0;
to_book3s(vcpu)->msr_mask = 0xffffffffULL;
vcpu->arch.cpu_type = KVM_CPU_3S_32;
}
ulong cmd = kvmppc_get_gpr(vcpu, 3);
int i;
+#ifdef CONFIG_KVM_BOOK3S_64_PR
if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
r = RESUME_GUEST;
break;
}
+#endif
run->papr_hcall.nr = cmd;
for (i = 0; i < 9; ++i) {
}
}
- if (sregs->u.s.flags & KVM_SREGS_S_HIOR)
- sregs->u.s.hior = to_book3s(vcpu)->hior;
-
return 0;
}
/* Flush the MMU after messing with the segments */
kvmppc_mmu_pte_flush(vcpu, 0, 0);
- if (sregs->u.s.flags & KVM_SREGS_S_HIOR) {
- to_book3s(vcpu)->hior_sregs = true;
- to_book3s(vcpu)->hior = sregs->u.s.hior;
- }
-
return 0;
}
#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <asm/reg.h>
#include <asm/cputable.h>
case KVM_CAP_PPC_BOOKE_SREGS:
#else
case KVM_CAP_PPC_SEGSTATE:
- case KVM_CAP_PPC_HIOR:
case KVM_CAP_PPC_PAPR:
#endif
case KVM_CAP_PPC_UNSET_IRQ:
#include <linux/init.h>
#include <asm/cputable.h>
#include <asm/code-patching.h>
+#include <asm/page.h>
+#include <asm/sections.h>
struct fixup_entry {
}
}
+void do_final_fixups(void)
+{
+#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
+ int *src, *dest;
+ unsigned long length;
+
+ if (PHYSICAL_START == 0)
+ return;
+
+ src = (int *)(KERNELBASE + PHYSICAL_START);
+ dest = (int *)KERNELBASE;
+ length = (__end_interrupts - _stext) / sizeof(int);
+
+ while (length--) {
+ patch_instruction(dest, *src);
+ src++;
+ dest++;
+ }
+#endif
+}
+
#ifdef CONFIG_FTR_FIXUP_SELFTEST
#define check(x) \
#include <linux/of_fdt.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
+#include <linux/moduleparam.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
select PPC_E500MC
select PHYS_64BIT
select SWIOTLB
- select MPC8xxx_GPIO
+ select GPIO_MPC8XXX
select HAS_RAPIDIO
select PPC_EPAPR_HV_PIC
help
.power_save = e500_idle,
};
-machine_device_initcall(p3060_qds, declare_of_platform_devices);
+machine_device_initcall(p3060_qds, corenet_ds_publish_devices);
#ifdef CONFIG_SWIOTLB
machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier);
config MCU_MPC8349EMITX
bool "MPC8349E-mITX MCU driver"
- depends on I2C && PPC_83xx
+ depends on I2C=y && PPC_83xx
select GENERIC_GPIO
select ARCH_REQUIRE_GPIOLIB
help
struct ps3_bmp bmp __attribute__ ((aligned (PS3_BMP_MINALIGN)));
u64 ppe_id;
u64 thread_id;
+ unsigned long ipi_mask;
};
static DEFINE_PER_CPU(struct ps3_private, ps3_private);
static void ps3_chip_eoi(struct irq_data *d)
{
const struct ps3_private *pd = irq_data_get_irq_chip_data(d);
- lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
+
+ /* non-IPIs are EOIed here. */
+
+ if (!test_bit(63 - d->irq, &pd->ipi_mask))
+ lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
}
/**
cpu, virq, pd->bmp.ipi_debug_brk_mask);
}
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq)
+{
+ struct ps3_private *pd = &per_cpu(ps3_private, cpu);
+
+ set_bit(63 - virq, &pd->ipi_mask);
+
+ DBG("%s:%d: cpu %u, virq %u, ipi_mask %lxh\n", __func__, __LINE__,
+ cpu, virq, pd->ipi_mask);
+}
+
static unsigned int ps3_get_irq(void)
{
struct ps3_private *pd = &__get_cpu_var(ps3_private);
BUG();
}
#endif
+
+ /* IPIs are EOIed here. */
+
+ if (test_bit(63 - plug, &pd->ipi_mask))
+ lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, plug);
+
return plug;
}
void ps3_init_IRQ(void);
void ps3_shutdown_IRQ(int cpu);
void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq);
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq);
/* smp */
static int ps3_smp_probe(void)
{
- return 2;
-}
+ int cpu;
-static void __init ps3_smp_setup_cpu(int cpu)
-{
- int result;
- unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
- int i;
+ for (cpu = 0; cpu < 2; cpu++) {
+ int result;
+ unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
+ int i;
- DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
+ DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
- /*
- * Check assumptions on ps3_ipi_virqs[] indexing. If this
- * check fails, then a different mapping of PPC_MSG_
- * to index needs to be setup.
- */
+ /*
+ * Check assumptions on ps3_ipi_virqs[] indexing. If this
+ * check fails, then a different mapping of PPC_MSG_
+ * to index needs to be setup.
+ */
- BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION != 0);
- BUILD_BUG_ON(PPC_MSG_RESCHEDULE != 1);
- BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
- BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3);
+ BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION != 0);
+ BUILD_BUG_ON(PPC_MSG_RESCHEDULE != 1);
+ BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
+ BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3);
- for (i = 0; i < MSG_COUNT; i++) {
- result = ps3_event_receive_port_setup(cpu, &virqs[i]);
+ for (i = 0; i < MSG_COUNT; i++) {
+ result = ps3_event_receive_port_setup(cpu, &virqs[i]);
- if (result)
- continue;
+ if (result)
+ continue;
- DBG("%s:%d: (%d, %d) => virq %u\n",
- __func__, __LINE__, cpu, i, virqs[i]);
+ DBG("%s:%d: (%d, %d) => virq %u\n",
+ __func__, __LINE__, cpu, i, virqs[i]);
- result = smp_request_message_ipi(virqs[i], i);
+ result = smp_request_message_ipi(virqs[i], i);
- if (result)
- virqs[i] = NO_IRQ;
- }
+ if (result)
+ virqs[i] = NO_IRQ;
+ else
+ ps3_register_ipi_irq(cpu, virqs[i]);
+ }
- ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
+ ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
- DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+ DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+ }
+
+ return 2;
}
void ps3_smp_cleanup_cpu(int cpu)
.probe = ps3_smp_probe,
.message_pass = ps3_smp_message_pass,
.kick_cpu = smp_generic_kick_cpu,
- .setup_cpu = ps3_smp_setup_cpu,
};
void smp_init_ps3(void)
if (!ehv_pic->irqhost) {
of_node_put(np);
+ kfree(ehv_pic);
return;
}
err:
iounmap(fsl_lbc_ctrl_dev->regs);
kfree(fsl_lbc_ctrl_dev);
+ fsl_lbc_ctrl_dev = NULL;
return ret;
}
/* Errata QE_General4, which affects some MPC832x and MPC836x SOCs, says
that the BRG divisor must be even if you're not using divide-by-16
mode. */
- if (!div16 && (divisor & 1))
+ if (!div16 && (divisor & 1) && (divisor > 3))
divisor++;
tempval = ((divisor - 1) << QE_BRGC_DIVISOR_SHIFT) |
config CRASH_DUMP
bool "kernel crash dumps"
depends on 64BIT
+ select KEXEC
help
Generate crash dump after being started by kexec.
Crash dump kernels are loaded in the main kernel with kexec-tools
if (facility_mask & CRYPT_S390_MSA && !test_facility(17))
return 0;
- if (facility_mask & CRYPT_S390_MSA3 && !test_facility(76))
+
+ if (facility_mask & CRYPT_S390_MSA3 &&
+ (!test_facility(2) || !test_facility(76)))
return 0;
- if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77))
+ if (facility_mask & CRYPT_S390_MSA4 &&
+ (!test_facility(2) || !test_facility(77)))
return 0;
switch (func & CRYPT_S390_OP_MASK) {
return (cputime_t) m * 4096;
}
+#define usecs_to_cputime64(m) usecs_to_cputime(m)
+
/*
* Convert cputime to milliseconds and back.
*/
#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
-#define CPUSTAT_HOST 0x80000000
+#define CPUSTAT_STOPPED 0x80000000
#define CPUSTAT_WAIT 0x10000000
#define CPUSTAT_ECALL_PEND 0x08000000
#define CPUSTAT_STOP_INT 0x04000000
u32 instruction_stfl;
u32 instruction_tprot;
u32 instruction_sigp_sense;
+ u32 instruction_sigp_sense_running;
u32 instruction_sigp_external_call;
u32 instruction_sigp_emergency;
u32 instruction_sigp_stop;
unsigned long address, bits;
unsigned char skey;
+ if (!pte_present(*ptep))
+ return pgste;
address = pte_val(*ptep) & PAGE_MASK;
skey = page_get_storage_key(address);
bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
/* Clear page changed & referenced bit in the storage key */
- if (bits) {
- skey ^= bits;
- page_set_storage_key(address, skey, 1);
- }
+ if (bits & _PAGE_CHANGED)
+ page_set_storage_key(address, skey ^ bits, 1);
+ else if (bits)
+ page_reset_referenced(address);
/* Transfer page changed & referenced bit to guest bits in pgste */
pgste_val(pgste) |= bits << 48; /* RCP_GR_BIT & RCP_GC_BIT */
/* Get host changed & referenced bits from pgste */
#ifdef CONFIG_PGSTE
int young;
+ if (!pte_present(*ptep))
+ return pgste;
young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
/* Transfer page referenced bit to pte software bit (host view) */
if (young || (pgste_val(pgste) & RCP_HR_BIT))
}
-static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
+static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
{
#ifdef CONFIG_PGSTE
unsigned long address;
unsigned long okey, nkey;
- address = pte_val(*ptep) & PAGE_MASK;
+ if (!pte_present(entry))
+ return;
+ address = pte_val(entry) & PAGE_MASK;
okey = nkey = page_get_storage_key(address);
nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
/* Set page access key and fetch protection bit from pgste */
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste_set_pte(ptep, pgste);
+ pgste_set_pte(ptep, pgste, entry);
*ptep = entry;
pgste_set_unlock(ptep, pgste);
} else
#define MACHINE_FLAG_LPAR (1UL << 12)
#define MACHINE_FLAG_SPP (1UL << 13)
#define MACHINE_FLAG_TOPOLOGY (1UL << 14)
+#define MACHINE_FLAG_STCKF (1UL << 15)
#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
#define MACHINE_HAS_PFMF (0)
#define MACHINE_HAS_SPP (0)
#define MACHINE_HAS_TOPOLOGY (0)
+#define MACHINE_HAS_STCKF (0)
#else /* __s390x__ */
#define MACHINE_HAS_IEEE (1)
#define MACHINE_HAS_CSP (1)
#define MACHINE_HAS_PFMF (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
#define MACHINE_HAS_SPP (S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
#define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
+#define MACHINE_HAS_STCKF (S390_lowcore.machine_flags & MACHINE_FLAG_STCKF)
#endif /* __s390x__ */
#define ZFCPDUMP_HSA_SIZE (32UL<<20)
{
unsigned long long clk;
- if (test_facility(25))
+ if (MACHINE_HAS_STCKF)
asm volatile(".insn s,0xb27c0000,%0" : "=Q" (clk) : : "cc");
else
clk = get_clock();
#define __NR_clock_adjtime 337
#define __NR_syncfs 338
#define __NR_setns 339
-#define NR_syscalls 340
+#define __NR_process_vm_readv 340
+#define __NR_process_vm_writev 341
+#define NR_syscalls 342
/*
* There are some system calls that are not present on 64 bit, some
lgfr %r2,%r2 # int
lgfr %r3,%r3 # int
jg sys_setns
+
+ENTRY(compat_sys_process_vm_readv_wrapper)
+ lgfr %r2,%r2 # compat_pid_t
+ llgtr %r3,%r3 # struct compat_iovec __user *
+ llgfr %r4,%r4 # unsigned long
+ llgtr %r5,%r5 # struct compat_iovec __user *
+ llgfr %r6,%r6 # unsigned long
+ llgf %r0,164(%r15) # unsigned long
+ stg %r0,160(%r15)
+ jg sys_process_vm_readv
+
+ENTRY(compat_sys_process_vm_writev_wrapper)
+ lgfr %r2,%r2 # compat_pid_t
+ llgtr %r3,%r3 # struct compat_iovec __user *
+ llgfr %r4,%r4 # unsigned long
+ llgtr %r5,%r5 # struct compat_iovec __user *
+ llgfr %r6,%r6 # unsigned long
+ llgf %r0,164(%r15) # unsigned long
+ stg %r0,160(%r15)
+ jg sys_process_vm_writev
S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
if (test_facility(40))
S390_lowcore.machine_flags |= MACHINE_FLAG_SPP;
+ if (test_facility(25))
+ S390_lowcore.machine_flags |= MACHINE_FLAG_STCKF;
#endif
}
((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
/* Invalid psw mask. */
return -EINVAL;
- if (addr == (addr_t) &dummy->regs.psw.addr)
- /*
- * The debugger changed the instruction address,
- * reset system call restart, see signal.c:do_signal
- */
- task_thread_info(child)->system_call = 0;
-
*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
/* Transfer 31 bit amode bit to psw mask. */
regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
(__u64)(tmp & PSW32_ADDR_AMODE);
- /*
- * The debugger changed the instruction address,
- * reset system call restart, see signal.c:do_signal
- */
- task_thread_info(child)->system_call = 0;
} else {
/* gpr 0-15 */
*(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp;
return 0;
}
+static int s390_last_break_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ return 0;
+}
+
#endif
static int s390_system_call_get(struct task_struct *target,
.size = sizeof(long),
.align = sizeof(long),
.get = s390_last_break_get,
+ .set = s390_last_break_set,
},
#endif
[REGSET_SYSTEM_CALL] = {
return 0;
}
+static int s390_compat_last_break_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ return 0;
+}
+
static const struct user_regset s390_compat_regsets[] = {
[REGSET_GENERAL] = {
.core_note_type = NT_PRSTATUS,
.size = sizeof(long),
.align = sizeof(long),
.get = s390_compat_last_break_get,
+ .set = s390_compat_last_break_set,
},
[REGSET_SYSTEM_CALL] = {
.core_note_type = NT_S390_SYSTEM_CALL,
if (ipl_info.type != IPL_TYPE_FCP_DUMP)
return;
+ if (OLDMEM_BASE)
+ return;
if (console_devno != -1)
sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x",
ipl_info.data.fcp.dev_id.devno, console_devno);
#ifdef CONFIG_ZFCPDUMP
- if (ipl_info.type == IPL_TYPE_FCP_DUMP) {
+ if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) {
memory_end = ZFCPDUMP_HSA_SIZE;
memory_end_set = 1;
}
*msg = "first memory chunk must be at least crashkernel size";
return 0;
}
- if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE))
+ if (OLDMEM_BASE && crash_size == OLDMEM_SIZE)
return OLDMEM_BASE;
for (i = MEMORY_CHUNKS - 1; i >= 0; i--) {
regs->svc_code >> 16);
break;
}
- /* No longer in a system call */
- clear_thread_flag(TIF_SYSCALL);
}
+ /* No longer in a system call */
+ clear_thread_flag(TIF_SYSCALL);
if ((is_compat_task() ?
handle_signal32(signr, &ka, &info, oldset, regs) :
}
/* No handlers present - check for system call restart */
+ clear_thread_flag(TIF_SYSCALL);
if (current_thread_info()->system_call) {
regs->svc_code = current_thread_info()->system_call;
switch (regs->gprs[2]) {
regs->gprs[2] = regs->orig_gpr2;
set_thread_flag(TIF_SYSCALL);
break;
- default:
- clear_thread_flag(TIF_SYSCALL);
- break;
}
}
SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
return mask;
}
-static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
- struct mask_info *book, struct mask_info *core)
+static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
+ struct mask_info *book,
+ struct mask_info *core,
+ int z10)
{
unsigned int cpu;
cpu_book_id[lcpu] = book->id;
#endif
cpumask_set_cpu(lcpu, &core->mask);
- cpu_core_id[lcpu] = core->id;
+ if (z10) {
+ cpu_core_id[lcpu] = rcpu;
+ core = core->next;
+ } else {
+ cpu_core_id[lcpu] = core->id;
+ }
smp_cpu_polarization[lcpu] = tl_cpu->pp;
}
}
+ return core;
}
static void clear_masks(void)
{
#ifdef CONFIG_SCHED_BOOK
struct mask_info *book = &book_info;
+ struct cpuid cpu_id;
#else
struct mask_info *book = NULL;
#endif
struct mask_info *core = &core_info;
union topology_entry *tle, *end;
+ int z10 = 0;
-
+#ifdef CONFIG_SCHED_BOOK
+ get_cpu_id(&cpu_id);
+ z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098;
+#endif
spin_lock_irq(&topology_lock);
clear_masks();
tle = info->tle;
end = (union topology_entry *)((unsigned long)info + info->length);
while (tle < end) {
+#ifdef CONFIG_SCHED_BOOK
+ if (z10) {
+ switch (tle->nl) {
+ case 1:
+ book = book->next;
+ book->id = tle->container.id;
+ break;
+ case 0:
+ core = add_cpus_to_mask(&tle->cpu, book, core, z10);
+ break;
+ default:
+ clear_masks();
+ goto out;
+ }
+ tle = next_tle(tle);
+ continue;
+ }
+#endif
switch (tle->nl) {
#ifdef CONFIG_SCHED_BOOK
case 2:
core->id = tle->container.id;
break;
case 0:
- add_cpus_to_mask(&tle->cpu, book, core);
+ add_cpus_to_mask(&tle->cpu, book, core, z10);
break;
default:
clear_masks();
for (i = 0; i < TOPOLOGY_NR_MAG; i++)
printk(" %d", info->mag[i]);
printk(" / %d\n", info->mnest);
- alloc_masks(info, &core_info, 2);
+ alloc_masks(info, &core_info, 1);
#ifdef CONFIG_SCHED_BOOK
- alloc_masks(info, &book_info, 3);
+ alloc_masks(info, &book_info, 2);
#endif
}
NOTES :text :note
+ .dummy : { *(.dummy) } :data
+
RODATA
#ifdef CONFIG_SHARED_KERNEL
return -EOPNOTSUPP;
}
- atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
int rc = 0;
vcpu->stat.exit_stop_request++;
- atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
spin_lock_bh(&vcpu->arch.local_int.lock);
if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
}
if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+ atomic_set_mask(CPUSTAT_STOPPED,
+ &vcpu->arch.sie_block->cpuflags);
vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
rc = -EOPNOTSUPP;
offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
if (rc == -EFAULT)
exception = 1;
+ atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
break;
case KVM_S390_PROGRAM_INT:
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+ { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
switch (ext) {
case KVM_CAP_S390_PSW:
case KVM_CAP_S390_GMAP:
+ case KVM_CAP_SYNC_MMU:
r = 1;
break;
default:
restore_fp_regs(&vcpu->arch.guest_fpregs);
restore_access_regs(vcpu->arch.guest_acrs);
gmap_enable(vcpu->arch.gmap);
+ atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
save_fp_regs(&vcpu->arch.guest_fpregs);
save_access_regs(vcpu->arch.guest_acrs);
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
- atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
+ atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
+ CPUSTAT_SM |
+ CPUSTAT_STOPPED);
vcpu->arch.sie_block->ecb = 6;
vcpu->arch.sie_block->eca = 0xC1002001U;
vcpu->arch.sie_block->fac = (int) (long) facilities;
{
int rc = 0;
- if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+ if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
rc = -EBUSY;
else {
vcpu->run->psw_mask = psw.mask;
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
- atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
struct vm_area_struct *vma;
+ unsigned long user_address;
vcpu->stat.instruction_tprot++;
return -EOPNOTSUPP;
+ /* we must resolve the address without holding the mmap semaphore.
+ * This is ok since the userspace hypervisor is not supposed to change
+ * the mapping while the guest queries the memory. Otherwise the guest
+ * might crash or get wrong info anyway. */
+ user_address = (unsigned long) __guestaddr_to_user(vcpu, address1);
+
down_read(¤t->mm->mmap_sem);
- vma = find_vma(current->mm,
- (unsigned long) __guestaddr_to_user(vcpu, address1));
+ vma = find_vma(current->mm, user_address);
if (!vma) {
up_read(¤t->mm->mmap_sem);
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
#define SIGP_SET_PREFIX 0x0d
#define SIGP_STORE_STATUS_ADDR 0x0e
#define SIGP_SET_ARCH 0x12
+#define SIGP_SENSE_RUNNING 0x15
/* cpu status bits */
#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL
+#define SIGP_STAT_NOT_RUNNING 0x00000400UL
#define SIGP_STAT_INCORRECT_STATE 0x00000200UL
#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL
spin_lock(&fi->lock);
if (fi->local_int[cpu_addr] == NULL)
rc = 3; /* not operational */
- else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
- & CPUSTAT_RUNNING) {
+ else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+ & CPUSTAT_STOPPED)) {
*reg &= 0xffffffff00000000UL;
rc = 1; /* status stored */
} else {
spin_lock_bh(&li->lock);
/* cpu must be in stopped state */
- if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+ if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
rc = 1; /* incorrect state */
*reg &= SIGP_STAT_INCORRECT_STATE;
kfree(inti);
return rc;
}
+static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
+ unsigned long *reg)
+{
+ int rc;
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ spin_lock(&fi->lock);
+ if (fi->local_int[cpu_addr] == NULL)
+ rc = 3; /* not operational */
+ else {
+ if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+ & CPUSTAT_RUNNING) {
+ /* running */
+ rc = 1;
+ } else {
+ /* not running */
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STAT_NOT_RUNNING;
+ rc = 0;
+ }
+ }
+ spin_unlock(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
+ rc);
+
+ return rc;
+}
+
int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
{
int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
&vcpu->arch.guest_gprs[r1]);
break;
+ case SIGP_SENSE_RUNNING:
+ vcpu->stat.instruction_sigp_sense_running++;
+ rc = __sigp_sense_running(vcpu, cpu_addr,
+ &vcpu->arch.guest_gprs[r1]);
+ break;
case SIGP_RESTART:
vcpu->stat.instruction_sigp_restart++;
/* user space must know about restart */
} else {
/* Completion interrupt was faster than initial
* interrupt. Set pfault_wait to -1 so the initial
- * interrupt doesn't put the task to sleep. */
- tsk->thread.pfault_wait = -1;
+ * interrupt doesn't put the task to sleep.
+ * If the task is not running, ignore the completion
+ * interrupt since it must be a leftover of a PFAULT
+ * CANCEL operation which didn't remove all pending
+ * completion interrupts. */
+ if (tsk->state == TASK_RUNNING)
+ tsk->thread.pfault_wait = -1;
}
put_task_struct(tsk);
} else {
return -EINVAL;
retval = oprofilefs_ulong_from_user(&val, buf, count);
- if (retval)
+ if (retval <= 0)
return retval;
if (oprofile_started)
#define GBECONT 0xffc10100
#define GBECONT_RMII1 BIT(17)
#define GBECONT_RMII0 BIT(16)
-static void sh7757_eth_set_mdio_gate(unsigned long addr)
+static void sh7757_eth_set_mdio_gate(void *addr)
{
- if ((addr & 0x00000fff) < 0x0800)
+ if (((unsigned long)addr & 0x00000fff) < 0x0800)
writel(readl(GBECONT) | GBECONT_RMII0, GBECONT);
else
writel(readl(GBECONT) | GBECONT_RMII1, GBECONT);
},
};
-static void sh7757_eth_giga_set_mdio_gate(unsigned long addr)
+static void sh7757_eth_giga_set_mdio_gate(void *addr)
{
- if ((addr & 0x00000fff) < 0x0800) {
+ if (((unsigned long)addr & 0x00000fff) < 0x0800) {
gpio_set_value(GPIO_PTT4, 1);
writel(readl(GBECONT) & ~GBECONT_RMII0, GBECONT);
} else {
};
static struct sh_mmcif_dma sh7757lcr_mmcif_dma = {
- .chan_priv_tx = SHDMA_SLAVE_MMCIF_TX,
- .chan_priv_rx = SHDMA_SLAVE_MMCIF_RX,
+ .chan_priv_tx = {
+ .slave_id = SHDMA_SLAVE_MMCIF_TX,
+ },
+ .chan_priv_rx = {
+ .slave_id = SHDMA_SLAVE_MMCIF_RX,
+ }
};
static struct sh_mmcif_plat_data sh_mmcif_plat = {
return oprofile_perf_init(ops);
}
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
{
oprofile_perf_exit();
kfree(sh_pmu_op_name);
ops->backtrace = sh_backtrace;
return -ENODEV;
}
-void __exit oprofile_arch_exit(void) {}
+void oprofile_arch_exit(void) {}
#endif /* CONFIG_HW_PERF_EVENTS */
#define kern_addr_valid(addr) \
(test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
-extern int io_remap_pfn_range(struct vm_area_struct *vma,
- unsigned long from, unsigned long pfn,
- unsigned long size, pgprot_t prot);
-
/*
* For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
* its high 4 bits. These macros/functions put it there or get it from there.
#define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4))
#define GET_PFN(pfn) (pfn & 0x0fffffffUL)
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+ unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long long offset, space, phys_base;
+
+ offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
+ space = GET_IOSPACE(pfn);
+ phys_base = offset | (space << 32ULL);
+
+ return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
({ \
extern int page_in_phys_avail(unsigned long paddr);
-extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn,
- unsigned long size, pgprot_t prot);
-
/*
* For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
* its high 4 bits. These macros/functions put it there or get it from there.
#define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4))
#define GET_PFN(pfn) (pfn & 0x0fffffffffffffffUL)
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+ unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+ int space = GET_IOSPACE(pfn);
+ unsigned long phys_base;
+
+ phys_base = offset | (((unsigned long) space) << 32UL);
+
+ return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
#include <asm-generic/pgtable.h>
/* We provide our own get_unmapped_area to cope with VA holes and
dp->rcv_buf_len = 4096;
- dp->ds_states = kzalloc(sizeof(ds_states_template),
- GFP_KERNEL);
+ dp->ds_states = kmemdup(ds_states_template,
+ sizeof(ds_states_template), GFP_KERNEL);
if (!dp->ds_states)
goto out_free_rcv_buf;
- memcpy(dp->ds_states, ds_states_template,
- sizeof(ds_states_template));
dp->num_ds_states = ARRAY_SIZE(ds_states_template);
for (i = 0; i < dp->num_ds_states; i++)
extern void fpload(unsigned long *fpregs, unsigned long *fsr);
#else /* CONFIG_SPARC32 */
+
+#include <asm/trap_block.h>
+
struct popc_3insn_patch_entry {
unsigned int addr;
unsigned int insns[3];
__popc_6insn_patch_end;
extern void __init per_cpu_patch(void);
+extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+ struct sun4v_1insn_patch_entry *);
+extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+ struct sun4v_2insn_patch_entry *);
extern void __init sun4v_patch(void);
extern void __init boot_cpu_id_too_large(int cpu);
extern unsigned int dcache_parity_tl1_occurred;
#include <asm/processor.h>
#include <asm/spitfire.h>
+#include "entry.h"
+
#ifdef CONFIG_SPARC64
#include <linux/jump_label.h>
}
#ifdef CONFIG_SPARC64
+static void do_patch_sections(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs)
+{
+ const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL;
+ char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+ if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name))
+ sun4v_1insn = s;
+ if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name))
+ sun4v_2insn = s;
+ }
+
+ if (sun4v_1insn && tlb_type == hypervisor) {
+ void *p = (void *) sun4v_1insn->sh_addr;
+ sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size);
+ }
+ if (sun4v_2insn && tlb_type == hypervisor) {
+ void *p = (void *) sun4v_2insn->sh_addr;
+ sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size);
+ }
+}
+
int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
/* make jump label nops */
jump_label_apply_nops(me);
+ do_patch_sections(hdr, sechdrs);
+
/* Cheetah's I-cache is fully coherent. */
if (tlb_type == spitfire) {
unsigned long va;
if (!irq)
return -ENOMEM;
- if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
- return -EINVAL;
if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID))
return -EINVAL;
+ if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
+ return -EINVAL;
return irq;
}
void *new_val;
int err;
- new_val = kmalloc(len, GFP_KERNEL);
+ new_val = kmemdup(val, len, GFP_KERNEL);
if (!new_val)
return -ENOMEM;
- memcpy(new_val, val, len);
-
err = -ENODEV;
mutex_lock(&of_set_property_mutex);
}
}
-void __init sun4v_patch(void)
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start,
+ struct sun4v_1insn_patch_entry *end)
{
- extern void sun4v_hvapi_init(void);
- struct sun4v_1insn_patch_entry *p1;
- struct sun4v_2insn_patch_entry *p2;
-
- if (tlb_type != hypervisor)
- return;
+ while (start < end) {
+ unsigned long addr = start->addr;
- p1 = &__sun4v_1insn_patch;
- while (p1 < &__sun4v_1insn_patch_end) {
- unsigned long addr = p1->addr;
-
- *(unsigned int *) (addr + 0) = p1->insn;
+ *(unsigned int *) (addr + 0) = start->insn;
wmb();
__asm__ __volatile__("flush %0" : : "r" (addr + 0));
- p1++;
+ start++;
}
+}
- p2 = &__sun4v_2insn_patch;
- while (p2 < &__sun4v_2insn_patch_end) {
- unsigned long addr = p2->addr;
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+ struct sun4v_2insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
- *(unsigned int *) (addr + 0) = p2->insns[0];
+ *(unsigned int *) (addr + 0) = start->insns[0];
wmb();
__asm__ __volatile__("flush %0" : : "r" (addr + 0));
- *(unsigned int *) (addr + 4) = p2->insns[1];
+ *(unsigned int *) (addr + 4) = start->insns[1];
wmb();
__asm__ __volatile__("flush %0" : : "r" (addr + 4));
- p2++;
+ start++;
}
+}
+
+void __init sun4v_patch(void)
+{
+ extern void sun4v_hvapi_init(void);
+
+ if (tlb_type != hypervisor)
+ return;
+
+ sun4v_patch_1insn_range(&__sun4v_1insn_patch,
+ &__sun4v_1insn_patch_end);
+
+ sun4v_patch_2insn_range(&__sun4v_2insn_patch,
+ &__sun4v_2insn_patch_end);
sun4v_hvapi_init();
}
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*/
-void do_signal32(sigset_t *oldset, struct pt_regs * regs,
- int restart_syscall, unsigned long orig_i0)
+void do_signal32(sigset_t *oldset, struct pt_regs * regs)
{
struct k_sigaction ka;
+ unsigned long orig_i0;
+ int restart_syscall;
siginfo_t info;
int signr;
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
- /* If the debugger messes with the program counter, it clears
- * the "in syscall" bit, directing us to not perform a syscall
- * restart.
- */
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ orig_i0 = 0;
+ if (pt_regs_is_syscall(regs) &&
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
if (signr > 0) {
if (restart_syscall)
siginfo_t info;
int signr;
+ /* It's a lot of work and synchronization to add a new ptrace
+ * register for GDB to save and restore in order to get
+ * orig_i0 correct for syscall restarts when debugging.
+ *
+ * Although it should be the case that most of the global
+ * registers are volatile across a system call, glibc already
+ * depends upon that fact that we preserve them. So we can't
+ * just use any global register to save away the orig_i0 value.
+ *
+ * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+ * preserved across a system call trap by various pieces of
+ * code in glibc.
+ *
+ * %g7 is used as the "thread register". %g6 is not used in
+ * any fixed manner. %g6 is used as a scratch register and
+ * a compiler temporary, but it's value is never used across
+ * a system call. Therefore %g6 is usable for orig_i0 storage.
+ */
if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C))
- restart_syscall = 1;
- else
- restart_syscall = 0;
+ regs->u_regs[UREG_G6] = orig_i0;
if (test_thread_flag(TIF_RESTORE_SIGMASK))
oldset = ¤t->saved_sigmask;
* the software "in syscall" bit, directing us to not perform
* a syscall restart.
*/
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
+
if (signr > 0) {
if (restart_syscall)
siginfo_t info;
int signr;
+ /* It's a lot of work and synchronization to add a new ptrace
+ * register for GDB to save and restore in order to get
+ * orig_i0 correct for syscall restarts when debugging.
+ *
+ * Although it should be the case that most of the global
+ * registers are volatile across a system call, glibc already
+ * depends upon that fact that we preserve them. So we can't
+ * just use any global register to save away the orig_i0 value.
+ *
+ * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+ * preserved across a system call trap by various pieces of
+ * code in glibc.
+ *
+ * %g7 is used as the "thread register". %g6 is not used in
+ * any fixed manner. %g6 is used as a scratch register and
+ * a compiler temporary, but it's value is never used across
+ * a system call. Therefore %g6 is usable for orig_i0 storage.
+ */
if (pt_regs_is_syscall(regs) &&
- (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
- restart_syscall = 1;
- } else
- restart_syscall = 0;
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY)))
+ regs->u_regs[UREG_G6] = orig_i0;
if (current_thread_info()->status & TS_RESTORE_SIGMASK)
oldset = ¤t->saved_sigmask;
#ifdef CONFIG_COMPAT
if (test_thread_flag(TIF_32BIT)) {
- extern void do_signal32(sigset_t *, struct pt_regs *,
- int restart_syscall,
- unsigned long orig_i0);
- do_signal32(oldset, regs, restart_syscall, orig_i0);
+ extern void do_signal32(sigset_t *, struct pt_regs *);
+ do_signal32(oldset, regs);
return;
}
#endif
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
- /* If the debugger messes with the program counter, it clears
- * the software "in syscall" bit, directing us to not perform
- * a syscall restart.
- */
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ if (pt_regs_is_syscall(regs) &&
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
if (signr > 0) {
if (restart_syscall)
#include <linux/types.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
+#include <linux/errno.h>
#include <asm/sigcontext.h>
#include <asm/fpumacro.h>
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
obj-$(CONFIG_SPARC32) += loadmmu.o
-obj-y += generic_$(BITS).o
obj-$(CONFIG_SPARC32) += extable.o btfixup.o srmmu.o iommu.o io-unit.o
obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o
obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
case 'i': /* INT */
if ((insn & 0xc1c00000) == 0x01000000) /* %HI */
set_addr(addr, q[1], fmangled, (insn & 0xffc00000) | (p[1] >> 10));
- else if ((insn & 0x80002000) == 0x80002000 &&
- (insn & 0x01800000) != 0x01800000) /* %LO */
+ else if ((insn & 0x80002000) == 0x80002000) /* %LO */
set_addr(addr, q[1], fmangled, (insn & 0xffffe000) | (p[1] & 0x3ff));
else {
prom_printf(insn_i, p, addr, insn);
+++ /dev/null
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- * MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-#include <linux/export.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
- address += PAGE_SIZE;
- offset += PAGE_SIZE;
- pte++;
- } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- offset -= address;
- do {
- pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
- if (!pte)
- return -ENOMEM;
- io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = vma->vm_mm;
- int space = GET_IOSPACE(pfn);
- unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-
- /* See comment in mm/memory.c remap_pfn_range */
- vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- vma->vm_pgoff = (offset >> PAGE_SHIFT) |
- ((unsigned long)space << 28UL);
-
- offset -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(vma, beg, end);
-
- while (from < end) {
- pmd_t *pmd = pmd_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- }
-
- flush_tlb_range(vma, beg, end);
- return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
+++ /dev/null
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- * MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/export.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
- unsigned long address,
- unsigned long size,
- unsigned long offset, pgprot_t prot,
- int space)
-{
- unsigned long end;
-
- /* clear hack bit that was used as a write_combine side-effect flag */
- offset &= ~0x1UL;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- pte_t entry;
- unsigned long curend = address + PAGE_SIZE;
-
- entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
- if (!(address & 0xffff)) {
- if (PAGE_SIZE < (4 * 1024 * 1024) &&
- !(address & 0x3fffff) &&
- !(offset & 0x3ffffe) &&
- end >= address + 0x400000) {
- entry = mk_pte_io(offset, prot, space,
- 4 * 1024 * 1024);
- curend = address + 0x400000;
- offset += 0x400000;
- } else if (PAGE_SIZE < (512 * 1024) &&
- !(address & 0x7ffff) &&
- !(offset & 0x7fffe) &&
- end >= address + 0x80000) {
- entry = mk_pte_io(offset, prot, space,
- 512 * 1024 * 1024);
- curend = address + 0x80000;
- offset += 0x80000;
- } else if (PAGE_SIZE < (64 * 1024) &&
- !(offset & 0xfffe) &&
- end >= address + 0x10000) {
- entry = mk_pte_io(offset, prot, space,
- 64 * 1024);
- curend = address + 0x10000;
- offset += 0x10000;
- } else
- offset += PAGE_SIZE;
- } else
- offset += PAGE_SIZE;
-
- if (pte_write(entry))
- entry = pte_mkdirty(entry);
- do {
- BUG_ON(!pte_none(*pte));
- set_pte_at(mm, address, pte, entry);
- address += PAGE_SIZE;
- pte_val(entry) += PAGE_SIZE;
- pte++;
- } while (address < curend);
- } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- offset -= address;
- do {
- pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
- if (!pte)
- return -ENOMEM;
- io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
- pte_unmap(pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return 0;
-}
-
-static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PUD_MASK;
- end = address + size;
- if (end > PUD_SIZE)
- end = PUD_SIZE;
- offset -= address;
- do {
- pmd_t *pmd = pmd_alloc(mm, pud, address);
- if (!pud)
- return -ENOMEM;
- io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space);
- address = (address + PUD_SIZE) & PUD_MASK;
- pud++;
- } while (address < end);
- return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = vma->vm_mm;
- int space = GET_IOSPACE(pfn);
- unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
- unsigned long phys_base;
-
- phys_base = offset | (((unsigned long) space) << 32UL);
-
- /* See comment in mm/memory.c remap_pfn_range */
- vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- vma->vm_pgoff = phys_base >> PAGE_SHIFT;
-
- offset -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(vma, beg, end);
-
- while (from < end) {
- pud_t *pud = pud_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pud)
- break;
- error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- }
-
- flush_tlb_range(vma, beg, end);
- return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
*/
void tile_irq_activate(unsigned int irq, int tile_irq_type);
-/*
- * For onboard, non-PCI (e.g. TILE_IRQ_PERCPU) devices, drivers know
- * how to use enable/disable_percpu_irq() to manage interrupts on each
- * core. We can't use the generic enable/disable_irq() because they
- * use a single reference count per irq, rather than per cpu per irq.
- */
-void enable_percpu_irq(unsigned int irq);
-void disable_percpu_irq(unsigned int irq);
-
-
void setup_irq_regs(void);
#endif /* _ASM_TILE_IRQ_H */
* Remove an irq from the disabled mask. If we're in an interrupt
* context, defer enabling the HW interrupt until we leave.
*/
-void enable_percpu_irq(unsigned int irq)
+static void tile_irq_chip_enable(struct irq_data *d)
{
- get_cpu_var(irq_disable_mask) &= ~(1UL << irq);
+ get_cpu_var(irq_disable_mask) &= ~(1UL << d->irq);
if (__get_cpu_var(irq_depth) == 0)
- unmask_irqs(1UL << irq);
+ unmask_irqs(1UL << d->irq);
put_cpu_var(irq_disable_mask);
}
-EXPORT_SYMBOL(enable_percpu_irq);
/*
* Add an irq to the disabled mask. We disable the HW interrupt
* in an interrupt context, the return path is careful to avoid
* unmasking a newly disabled interrupt.
*/
-void disable_percpu_irq(unsigned int irq)
+static void tile_irq_chip_disable(struct irq_data *d)
{
- get_cpu_var(irq_disable_mask) |= (1UL << irq);
- mask_irqs(1UL << irq);
+ get_cpu_var(irq_disable_mask) |= (1UL << d->irq);
+ mask_irqs(1UL << d->irq);
put_cpu_var(irq_disable_mask);
}
-EXPORT_SYMBOL(disable_percpu_irq);
/* Mask an interrupt. */
static void tile_irq_chip_mask(struct irq_data *d)
static struct irq_chip tile_irq_chip = {
.name = "tile_irq_chip",
+ .irq_enable = tile_irq_chip_enable,
+ .irq_disable = tile_irq_chip_disable,
.irq_ack = tile_irq_chip_ack,
.irq_eoi = tile_irq_chip_eoi,
.irq_mask = tile_irq_chip_mask,
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/vmalloc.h>
+#include <linux/export.h>
#include <asm/tlbflush.h>
#include <asm/homecache.h>
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/uaccess.h>
+#include <linux/export.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/smp.h>
+#include <linux/stat.h>
#include <hv/hypervisor.h>
/* Return a string queried from the hypervisor, truncated to page size. */
EXPORT_SYMBOL(current_text_addr);
EXPORT_SYMBOL(dump_stack);
+/* arch/tile/kernel/head.S */
+EXPORT_SYMBOL(empty_zero_page);
+
/* arch/tile/lib/, various memcpy files */
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(__copy_to_user_inatomic);
VM_BUG_ON(!virt_addr_valid((void *)addr));
page = virt_to_page((void *)addr);
if (put_page_testzero(page)) {
- int pages = (1 << order);
homecache_change_page_home(page, order, initial_page_home());
- while (pages--)
- __free_page(page++);
+ if (order == 0) {
+ free_hot_cold_page(page, 0);
+ } else {
+ init_page_count(page);
+ __free_pages(page, order);
+ }
}
}
config I2C_BATTERY_BQ27200
tristate "I2C Battery BQ27200 Support"
- select PUV3_I2C
+ select I2C_PUV3
select POWER_SUPPLY
select BATTERY_BQ27x00
config I2C_EEPROM_AT24
tristate "I2C EEPROMs AT24 support"
- select PUV3_I2C
+ select I2C_PUV3
select MISC_DEVICES
select EEPROM_AT24
Say Y here if you want the debug print routines to direct their
output to the UniCore On-Chip-Debugger channel using CP #1.
-config DEBUG_OCD_BREAKPOINT
- bool "Breakpoint support via On-Chip-Debugger"
- depends on DEBUG_OCD
-
-config DEBUG_UART
- int "Kernel low-level debugging messages via serial port"
- depends on DEBUG_LL
- range 0 1
- default "0"
- help
- Choice for UART for kernel low-level using PKUnity UARTS,
- should be between zero and one. The port must have been
- initialised by the boot-loader before use.
-
endmenu
# Copyright (C) 2001~2010 GUAN Xue-tao
#
-EXTRA_CFLAGS := -fpic -fno-builtin
-EXTRA_AFLAGS := -Wa,-march=all
+ccflags-y := -fpic -fno-builtin
+asflags-y := -Wa,-march=all
OBJS := misc.o
#ifndef __UNICORE_BITOPS_H__
#define __UNICORE_BITOPS_H__
-#define find_next_bit __uc32_find_next_bit
-#define find_next_zero_bit __uc32_find_next_zero_bit
-
-#define find_first_bit __uc32_find_first_bit
-#define find_first_zero_bit __uc32_find_first_zero_bit
-
#define _ASM_GENERIC_BITOPS_FLS_H_
#define _ASM_GENERIC_BITOPS___FLS_H_
#define _ASM_GENERIC_BITOPS_FFS_H_
#include <asm-generic/bitops.h>
+/* following definitions: to avoid using codes in lib/find_*.c */
+#define find_next_bit find_next_bit
+#define find_next_zero_bit find_next_zero_bit
+#define find_first_bit find_first_bit
+#define find_first_zero_bit find_first_zero_bit
+
#endif /* __UNICORE_BITOPS_H__ */
#define start_thread(regs, pc, sp) \
({ \
unsigned long *stack = (unsigned long *)sp; \
- set_fs(USER_DS); \
memset(regs->uregs, 0, sizeof(regs->uregs)); \
regs->UCreg_asr = USER_MODE; \
regs->UCreg_pc = pc & ~1; /* pc */ \
#include "ksyms.h"
-EXPORT_SYMBOL(__uc32_find_next_zero_bit);
-EXPORT_SYMBOL(__uc32_find_next_bit);
+EXPORT_SYMBOL(find_next_zero_bit);
+EXPORT_SYMBOL(find_next_bit);
EXPORT_SYMBOL(__backtrace);
* Purpose : Find a 'zero' bit
* Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
*/
-__uc32_find_first_zero_bit:
+ENTRY(find_first_zero_bit)
cxor.a r1, #0
beq 3f
mov r2, #0
bub 1b
3: mov r0, r1 @ no free bits
mov pc, lr
+ENDPROC(find_first_zero_bit)
/*
* Purpose : Find next 'zero' bit
* Prototype: int find_next_zero_bit
* (void *addr, unsigned int maxbit, int offset)
*/
-ENTRY(__uc32_find_next_zero_bit)
+ENTRY(find_next_zero_bit)
cxor.a r1, #0
beq 3b
and.a ip, r2, #7
or r2, r2, #7 @ if zero, then no bits here
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
-ENDPROC(__uc32_find_next_zero_bit)
+ENDPROC(find_next_zero_bit)
/*
* Purpose : Find a 'one' bit
* Prototype: int find_first_bit
* (const unsigned long *addr, unsigned int maxbit);
*/
-__uc32_find_first_bit:
+ENTRY(find_first_bit)
cxor.a r1, #0
beq 3f
mov r2, #0
bub 1b
3: mov r0, r1 @ no free bits
mov pc, lr
+ENDPROC(find_first_bit)
/*
* Purpose : Find next 'one' bit
* Prototype: int find_next_zero_bit
* (void *addr, unsigned int maxbit, int offset)
*/
-ENTRY(__uc32_find_next_bit)
+ENTRY(find_next_bit)
cxor.a r1, #0
beq 3b
and.a ip, r2, #7
or r2, r2, #7 @ if zero, then no bits here
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
-ENDPROC(__uc32_find_next_bit)
+ENDPROC(find_next_bit)
/*
* One or more bits in the LSB of r3 are assumed to be set.
This option compiles in support for the CE4100 SOC for settop
boxes and media devices.
-config X86_INTEL_MID
+config X86_WANT_INTEL_MID
bool "Intel MID platform support"
depends on X86_32
depends on X86_EXTENDED_PLATFORM
systems which do not have the PCI legacy interfaces (Moorestown,
Medfield). If you are building for a PC class system say N here.
-if X86_INTEL_MID
+if X86_WANT_INTEL_MID
+
+config X86_INTEL_MID
+ bool
config X86_MRST
bool "Moorestown MID platform"
select SPI
select INTEL_SCU_IPC
select X86_PLATFORM_DEVICES
+ select X86_INTEL_MID
---help---
Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
Internet Device(MID) platform. Moorestown consists of two chips:
extern int local_apic_timer_c2_ok;
extern int disable_apic;
+extern unsigned int lapic_timer_frequency;
#ifdef CONFIG_SMP
extern void __inquire_remote_apic(int apicid);
#include <linux/notifier.h>
-#define IPCMSG_VRTC 0xFA /* Set vRTC device */
-
-/* Command id associated with message IPCMSG_VRTC */
-#define IPC_CMD_VRTC_SETTIME 1 /* Set time */
-#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */
+#define IPCMSG_WARM_RESET 0xF0
+#define IPCMSG_COLD_RESET 0xF1
+#define IPCMSG_SOFT_RESET 0xF2
+#define IPCMSG_COLD_BOOT 0xF3
+
+#define IPCMSG_VRTC 0xFA /* Set vRTC device */
+ /* Command id associated with message IPCMSG_VRTC */
+ #define IPC_CMD_VRTC_SETTIME 1 /* Set time */
+ #define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */
/* Read single register */
int intel_scu_ipc_ioread8(u16 addr, u8 *data);
#define NMI_REASON_CLEAR_IOCHK 0x08
#define NMI_REASON_CLEAR_MASK 0x0f
-static inline unsigned char get_nmi_reason(void)
+static inline unsigned char default_get_nmi_reason(void)
{
return inb(NMI_REASON_PORT);
}
void mce_notify_process(void);
DECLARE_PER_CPU(struct mce, injectm);
-extern struct file_operations mce_chrdev_ops;
+
+extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
+ const char __user *ubuf,
+ size_t usize, loff_t *off));
/*
* Exception handler
};
extern enum mrst_cpu_type __mrst_cpu_chip;
+
+#ifdef CONFIG_X86_INTEL_MID
+
static inline enum mrst_cpu_type mrst_identify_cpu(void)
{
return __mrst_cpu_chip;
}
+#else /* !CONFIG_X86_INTEL_MID */
+
+#define mrst_identify_cpu() (0)
+
+#endif /* !CONFIG_X86_INTEL_MID */
+
enum mrst_timer_options {
MRST_TIMER_DEFAULT,
MRST_TIMER_APBT_ONLY,
extern enum mrst_timer_options mrst_timer_options;
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU 83200
+#define PENWELL_FSB_FREQ_100SKU 99840
+
#define SFI_MTMR_MAX_NUM 8
#define SFI_MRTC_MAX 8
return native_write_msr_safe(msr, low, high);
}
-/* rdmsr with exception handling */
+/*
+ * rdmsr with exception handling.
+ *
+ * Please note that the exception handling works only after we've
+ * switched to the "smart" #GP handler in trap_init() which knows about
+ * exception tables - using this macro earlier than that causes machine
+ * hangs on boxes which do not implement the @msr in the first argument.
+ */
#define rdmsr_safe(msr, p1, p2) \
({ \
int __err; \
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
void default_idle(void);
+bool set_pm_idle_to_default(void);
void stop_this_cpu(void *dummy);
* (mathieu.desnoyers@polymtl.ca)
*
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ *
+ * In:
+ *
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * Although we may still have enough bits to store the value of ns,
+ * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
+ * leading to an incorrect result.
+ *
+ * To avoid this, we can decompose 'cycles' into quotient and remainder
+ * of division by SC. Then,
+ *
+ * ns = (quot * SC + rem) * cyc2ns_scale / SC
+ * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
+ *
+ * - sqazi@google.com
*/
DECLARE_PER_CPU(unsigned long, cyc2ns);
static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
{
+ unsigned long long quot;
+ unsigned long long rem;
int cpu = smp_processor_id();
unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
- ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+ quot = (cyc >> CYC2NS_SCALE_FACTOR);
+ rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
+ ns += quot * per_cpu(cyc2ns, cpu) +
+ ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
return ns;
}
#define UV1_HUB_PART_NUMBER 0x88a5
#define UV2_HUB_PART_NUMBER 0x8eb8
+#define UV2_HUB_PART_NUMBER_X 0x1111
/* Compat: if this #define is present, UV headers support UV2 */
#define UV2_HUB_IS_SUPPORTED 1
/**
* struct x86_platform_ops - platform specific runtime functions
* @calibrate_tsc: calibrate TSC
+ * @wallclock_init: init the wallclock device
* @get_wallclock: get time from HW clock like RTC etc.
* @set_wallclock: set time back to HW clock
* @is_untracked_pat_range exclude from PAT logic
*/
struct x86_platform_ops {
unsigned long (*calibrate_tsc)(void);
+ void (*wallclock_init)(void);
unsigned long (*get_wallclock)(void);
int (*set_wallclock)(unsigned long nowtime);
void (*iommu_shutdown)(void);
bool (*is_untracked_pat_range)(u64 start, u64 end);
void (*nmi_init)(void);
+ unsigned char (*get_nmi_reason)(void);
int (*i8042_detect)(void);
};
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
- __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+ __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
}
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
-static unsigned int calibration_result;
+unsigned int lapic_timer_frequency = 0;
static void apic_pm_activate(void);
switch (mode) {
case CLOCK_EVT_MODE_PERIODIC:
case CLOCK_EVT_MODE_ONESHOT:
- __setup_APIC_LVTT(calibration_result,
+ __setup_APIC_LVTT(lapic_timer_frequency,
mode != CLOCK_EVT_MODE_PERIODIC, 1);
break;
case CLOCK_EVT_MODE_UNUSED:
long delta, deltatsc;
int pm_referenced = 0;
+ /**
+ * check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. if so, we just fill
+ * in the clockevent structure and return.
+ */
+
+ if (lapic_timer_frequency) {
+ apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
+ lapic_timer_frequency);
+ lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ TICK_NSEC, lapic_clockevent.shift);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+ return 0;
+ }
+
local_irq_disable();
/* Replace the global interrupt handler */
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
- calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
- calibration_result);
+ lapic_timer_frequency);
if (cpu_has_tsc) {
apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
"%u.%04u MHz.\n",
- calibration_result / (1000000 / HZ),
- calibration_result % (1000000 / HZ));
+ lapic_timer_frequency / (1000000 / HZ),
+ lapic_timer_frequency % (1000000 / HZ));
/*
* Do a sanity check on the APIC calibration result
*/
- if (calibration_result < (1000000 / HZ)) {
+ if (lapic_timer_frequency < (1000000 / HZ)) {
local_irq_enable();
pr_warning("APIC frequency too slow, disabling apic timer\n");
return -1;
struct irq_cfg *cfg;
int count, node, i;
- if (!legacy_pic->nr_legacy_irqs) {
- nr_irqs_gsi = 0;
+ if (!legacy_pic->nr_legacy_irqs)
io_apic_irqs = ~0UL;
- }
for (i = 0; i < nr_ioapics; i++) {
ioapics[i].saved_registers =
int ioapic_idx;
struct irq_cfg *cfg;
unsigned int irq;
+ struct irq_chip *chip;
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
for_each_active_irq(irq) {
struct irq_pin_list *entry;
+ chip = irq_get_chip(irq);
+ if (chip != &ioapic_chip)
+ continue;
+
cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+ if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X)
+ uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
uv_hub_info->hub_revision = uv_min_hub_revision_id;
pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
{
- u32 dummy;
-
early_init_amd_mc(c);
/*
set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
}
#endif
-
- rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
}
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
+ u32 dummy;
+
#ifdef CONFIG_SMP
unsigned long long value;
checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
}
}
+
+ rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
}
#ifdef CONFIG_X86_32
if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
return -ENOMEM;
printk(KERN_INFO "Machine check injector initialized\n");
- mce_chrdev_ops.write = mce_write;
+ register_mce_write_callback(mce_write);
register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
"mce_notify");
return 0;
}
}
-/* Modified in mce-inject.c, so not static or const */
-struct file_operations mce_chrdev_ops = {
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+ const char __user *ubuf,
+ size_t usize, loff_t *off))
+{
+ mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off)
+{
+ if (mce_write)
+ return mce_write(filp, ubuf, usize, off);
+ else
+ return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
.open = mce_chrdev_open,
.release = mce_chrdev_release,
.read = mce_chrdev_read,
+ .write = mce_chrdev_write,
.poll = mce_chrdev_poll,
.unlocked_ioctl = mce_chrdev_ioctl,
.llseek = no_llseek,
};
-EXPORT_SYMBOL_GPL(mce_chrdev_ops);
static struct miscdevice mce_chrdev_device = {
MISC_MCELOG_MINOR,
if (tmp != mask_lo) {
printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
+ add_taint(TAINT_FIRMWARE_WORKAROUND);
mask_lo = tmp;
}
}
/* Disable MTRRs, and set the default type to uncached */
mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
+ wbinvd();
}
static void post_set(void) __releases(set_atomicity_lock)
return -EOPNOTSUPP;
}
- /*
- * Do not allow config1 (extended registers) to propagate,
- * there's no sane user-space generalization yet:
- */
if (attr->type == PERF_TYPE_RAW)
- return 0;
+ return x86_pmu_extra_regs(event->attr.config, event);
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, event);
x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
}
}
- return num ? -ENOSPC : 0;
+ return num ? -EINVAL : 0;
}
/*
if (is_x86_event(leader)) {
if (n >= max_count)
- return -ENOSPC;
+ return -EINVAL;
cpuc->event_list[n] = leader;
n++;
}
continue;
if (n >= max_count)
- return -ENOSPC;
+ return -EINVAL;
cpuc->event_list[n] = event;
n++;
c = x86_pmu.get_event_constraints(fake_cpuc, event);
if (!c || !c->weight)
- ret = -ENOSPC;
+ ret = -EINVAL;
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(fake_cpuc, event);
{
struct perf_event *leader = event->group_leader;
struct cpu_hw_events *fake_cpuc;
- int ret = -ENOSPC, n;
+ int ret = -EINVAL, n;
fake_cpuc = allocate_fake_cpuc();
if (IS_ERR(fake_cpuc))
goto out;
}
- pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
- pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+ pr_info("IBS: LVT offset %d assigned\n", offset);
return 0;
out:
static __init int amd_ibs_init(void)
{
u32 caps;
- int ret;
+ int ret = -EINVAL;
caps = __get_ibs_caps();
if (!caps)
return -ENODEV; /* ibs not supported by the cpu */
- if (!ibs_eilvt_valid()) {
- ret = force_ibs_eilvt_setup();
- if (ret) {
- pr_err("Failed to setup IBS, %d\n", ret);
- return ret;
- }
- }
+ /*
+ * Force LVT offset assignment for family 10h: The offsets are
+ * not assigned by the BIOS for this family, so the OS is
+ * responsible for doing it. If the OS assignment fails, fall
+ * back to BIOS settings and try to setup this.
+ */
+ if (boot_cpu_data.x86 == 0x10)
+ force_ibs_eilvt_setup();
+
+ if (!ibs_eilvt_valid())
+ goto out;
get_online_cpus();
ibs_caps = caps;
smp_call_function(setup_APIC_ibs, NULL, 1);
put_online_cpus();
- return perf_event_ibs_init();
+ ret = perf_event_ibs_init();
+out:
+ if (ret)
+ pr_err("Failed to setup IBS, %d\n", ret);
+ return ret;
}
/* Since we need the pci subsystem to init ibs we can't do this earlier: */
*/
c = &unconstrained;
} else if (intel_try_alt_er(event, orig_idx)) {
- raw_spin_unlock(&era->lock);
+ raw_spin_unlock_irqrestore(&era->lock, flags);
goto again;
}
raw_spin_unlock_irqrestore(&era->lock, flags);
x86_pmu.pebs_constraints = NULL;
}
+static void intel_sandybridge_quirks(void)
+{
+ printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+ x86_pmu.pebs = 0;
+ x86_pmu.pebs_constraints = NULL;
+}
+
__init int intel_pmu_init(void)
{
union cpuid10_edx edx;
break;
case 42: /* SandyBridge */
+ x86_pmu.quirks = intel_sandybridge_quirks;
case 45: /* SandyBridge, "Romely-EP" */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
unsigned long from = cpuc->lbr_entries[0].from;
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
+ int is_64bit = 0;
/*
* We don't need to fixup if the PEBS assist is fault like
} else
kaddr = (void *)to;
- kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+ is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+ insn_init(&insn, kaddr, is_64bit);
insn_get_length(&insn);
to += insn.length;
} while (to < ip);
}
done:
- return num ? -ENOSPC : 0;
+ return num ? -EINVAL : 0;
}
static __initconst const struct x86_pmu p4_pmu = {
for (i = 0; i < code_len; i++, ip++) {
if (ip < (u8 *)PAGE_OFFSET ||
probe_kernel_address(ip, c)) {
- printk(" Bad EIP value.");
+ printk(KERN_CONT " Bad EIP value.");
break;
}
if (ip == (u8 *)regs->ip)
- printk("<%02x> ", c);
+ printk(KERN_CONT "<%02x> ", c);
else
- printk("%02x ", c);
+ printk(KERN_CONT "%02x ", c);
}
}
- printk("\n");
+ printk(KERN_CONT "\n");
}
int is_valid_bugaddr(unsigned long ip)
for (i = 0; i < code_len; i++, ip++) {
if (ip < (u8 *)PAGE_OFFSET ||
probe_kernel_address(ip, c)) {
- printk(" Bad RIP value.");
+ printk(KERN_CONT " Bad RIP value.");
break;
}
if (ip == (u8 *)regs->ip)
- printk("<%02x> ", c);
+ printk(KERN_CONT "<%02x> ", c);
else
- printk("%02x ", c);
+ printk(KERN_CONT "%02x ", c);
}
}
- printk("\n");
+ printk(KERN_CONT "\n");
}
int is_valid_bugaddr(unsigned long ip)
}
EXPORT_SYMBOL_GPL(hpet_rtc_timer_init);
+static void hpet_disable_rtc_channel(void)
+{
+ unsigned long cfg;
+ cfg = hpet_readl(HPET_T1_CFG);
+ cfg &= ~HPET_TN_ENABLE;
+ hpet_writel(cfg, HPET_T1_CFG);
+}
+
/*
* The functions below are called from rtc driver.
* Return 0 if HPET is not being used.
return 0;
hpet_rtc_flags &= ~bit_mask;
+ if (unlikely(!hpet_rtc_flags))
+ hpet_disable_rtc_channel();
+
return 1;
}
EXPORT_SYMBOL_GPL(hpet_mask_rtc_irq_bit);
static void hpet_rtc_timer_reinit(void)
{
- unsigned int cfg, delta;
+ unsigned int delta;
int lost_ints = -1;
- if (unlikely(!hpet_rtc_flags)) {
- cfg = hpet_readl(HPET_T1_CFG);
- cfg &= ~HPET_TN_ENABLE;
- hpet_writel(cfg, HPET_T1_CFG);
- return;
- }
+ if (unlikely(!hpet_rtc_flags))
+ hpet_disable_rtc_channel();
if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
delta = hpet_default_delta;
#ifdef CONFIG_DEBUG_STACKOVERFLOW
u64 curbase = (u64)task_stack_page(current);
+ if (user_mode_vm(regs))
+ return;
+
WARN_ONCE(regs->sp >= curbase &&
regs->sp <= curbase + THREAD_SIZE &&
regs->sp < curbase + sizeof(struct thread_info) +
struct pvclock_vcpu_time_info *src;
cycle_t ret;
- src = &get_cpu_var(hv_clock);
+ preempt_disable_notrace();
+ src = &__get_cpu_var(hv_clock);
ret = pvclock_clocksource_read(src);
- put_cpu_var(hv_clock);
+ preempt_enable_notrace();
return ret;
}
return 0;
}
-static void microcode_dev_exit(void)
+static void __exit microcode_dev_exit(void)
{
misc_deregister(µcode_dev);
}
microcode_pdev = platform_device_register_simple("microcode", -1,
NULL, 0);
- if (IS_ERR(microcode_pdev)) {
- microcode_dev_exit();
+ if (IS_ERR(microcode_pdev))
return PTR_ERR(microcode_pdev);
- }
get_online_cpus();
mutex_lock(µcode_mutex);
mutex_unlock(µcode_mutex);
put_online_cpus();
- if (error) {
- platform_device_unregister(microcode_pdev);
- return error;
- }
+ if (error)
+ goto out_pdev;
error = microcode_dev_init();
if (error)
- return error;
+ goto out_sysdev_driver;
register_syscore_ops(&mc_syscore_ops);
register_hotcpu_notifier(&mc_cpu_notifier);
" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
return 0;
+
+out_sysdev_driver:
+ get_online_cpus();
+ mutex_lock(µcode_mutex);
+
+ sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+
+ mutex_unlock(µcode_mutex);
+ put_online_cpus();
+
+out_pdev:
+ platform_device_unregister(microcode_pdev);
+ return error;
+
}
module_init(microcode_init);
}
#endif
+ set_bit(m->busid, mp_bus_not_pci);
if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) {
- set_bit(m->busid, mp_bus_not_pci);
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
#endif
#include <asm/traps.h>
#include <asm/mach_traps.h>
#include <asm/nmi.h>
+#include <asm/x86_init.h>
#define NMI_MAX_NAMELEN 16
struct nmiaction {
/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
raw_spin_lock(&nmi_reason_lock);
- reason = get_nmi_reason();
+ reason = x86_platform.get_nmi_reason();
if (reason & NMI_REASON_MASK) {
if (reason & NMI_REASON_SERR)
EXPORT_SYMBOL(default_idle);
#endif
+bool set_pm_idle_to_default(void)
+{
+ bool ret = !!pm_idle;
+
+ pm_idle = default_idle;
+
+ return ret;
+}
void stop_this_cpu(void *dummy)
{
local_irq_disable();
quirk_amd_nb_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F0,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F1,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F2,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4,
+ quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
+ quirk_amd_nb_node);
+
#endif
*/
/*
- * Some machines require the "reboot=b" commandline option,
+ * Some machines require the "reboot=b" or "reboot=k" commandline options,
* this quirk makes that automatic.
*/
static int __init set_bios_reboot(const struct dmi_system_id *d)
return 0;
}
+static int __init set_kbd_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_KBD) {
+ reboot_type = BOOT_KBD;
+ printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident);
+ }
+ return 0;
+}
+
static struct dmi_system_id __initdata reboot_dmi_table[] = {
{ /* Handle problems with rebooting on Dell E520's */
.callback = set_bios_reboot,
},
},
{ /* Handle reboot issue on Acer Aspire one */
- .callback = set_bios_reboot,
+ .callback = set_kbd_reboot,
.ident = "Acer Aspire One A110",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
},
},
+ { /* Handle problems with rebooting on the OptiPlex 990. */
+ .callback = set_pci_reboot,
+ .ident = "Dell OptiPlex 990",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+ },
+ },
{ }
};
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
#include <asm/time.h>
+#include <asm/mrst.h>
#ifdef CONFIG_X86_32
/*
if (of_have_populated_dt())
return 0;
+ /* Intel MID platforms don't have ioport rtc */
+ if (mrst_identify_cpu())
+ return -ENODEV;
+
platform_device_register(&rtc_device);
dev_info(&rtc_device.dev,
"registered platform RTC device (no PNP device found)\n");
x86_init.timers.wallclock_init();
+ x86_platform.wallclock_init();
+
mcheck_init();
arch_init_ideal_nops();
#include <asm/pat.h>
#include <asm/tsc.h>
#include <asm/iommu.h>
+#include <asm/mach_traps.h>
void __cpuinit x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
void __init x86_init_pgd_noop(pgd_t *unused) { }
int __init iommu_init_noop(void) { return 0; }
void iommu_shutdown_noop(void) { }
+void wallclock_init_noop(void) { }
/*
* The platform setup functions are preset with the default functions
struct x86_platform_ops x86_platform = {
.calibrate_tsc = native_calibrate_tsc,
+ .wallclock_init = wallclock_init_noop,
.get_wallclock = mach_get_cmos_time,
.set_wallclock = mach_set_rtc_mmss,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,
+ .get_nmi_reason = default_get_nmi_reason,
.i8042_detect = default_i8042_detect
};
return HRTIMER_NORESTART;
}
-static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
{
+ struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
struct kvm_timer *pt = &ps->pit_timer;
s64 interval;
+ if (!irqchip_in_kernel(kvm))
+ return;
+
interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
pr_debug("create pit timer, interval is %llu nsec\n", interval);
/* FIXME: enhance mode 4 precision */
case 4:
if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
- create_pit_timer(ps, val, 0);
+ create_pit_timer(kvm, val, 0);
}
break;
case 2:
case 3:
if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
- create_pit_timer(ps, val, 1);
+ create_pit_timer(kvm, val, 1);
}
break;
default:
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>
+#include <asm/perf_event.h>
#include "trace.h"
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
-#define NR_AUTOLOAD_MSRS 1
+#define NR_AUTOLOAD_MSRS 8
#define VMCS02_POOL_SIZE 1
struct vmcs {
static unsigned long *vmx_msr_bitmap_longmode;
static bool cpu_has_load_ia32_efer;
+static bool cpu_has_load_perf_global_ctrl;
static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);
vmcs_write32(EXCEPTION_BITMAP, eb);
}
+static void clear_atomic_switch_msr_special(unsigned long entry,
+ unsigned long exit)
+{
+ vmcs_clear_bits(VM_ENTRY_CONTROLS, entry);
+ vmcs_clear_bits(VM_EXIT_CONTROLS, exit);
+}
+
static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
{
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
- if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
- vmcs_clear_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
- vmcs_clear_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
- return;
+ switch (msr) {
+ case MSR_EFER:
+ if (cpu_has_load_ia32_efer) {
+ clear_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+ VM_EXIT_LOAD_IA32_EFER);
+ return;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ if (cpu_has_load_perf_global_ctrl) {
+ clear_atomic_switch_msr_special(
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+ return;
+ }
+ break;
}
for (i = 0; i < m->nr; ++i)
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
}
+static void add_atomic_switch_msr_special(unsigned long entry,
+ unsigned long exit, unsigned long guest_val_vmcs,
+ unsigned long host_val_vmcs, u64 guest_val, u64 host_val)
+{
+ vmcs_write64(guest_val_vmcs, guest_val);
+ vmcs_write64(host_val_vmcs, host_val);
+ vmcs_set_bits(VM_ENTRY_CONTROLS, entry);
+ vmcs_set_bits(VM_EXIT_CONTROLS, exit);
+}
+
static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
u64 guest_val, u64 host_val)
{
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
- if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
- vmcs_write64(GUEST_IA32_EFER, guest_val);
- vmcs_write64(HOST_IA32_EFER, host_val);
- vmcs_set_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
- vmcs_set_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
- return;
+ switch (msr) {
+ case MSR_EFER:
+ if (cpu_has_load_ia32_efer) {
+ add_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+ VM_EXIT_LOAD_IA32_EFER,
+ GUEST_IA32_EFER,
+ HOST_IA32_EFER,
+ guest_val, host_val);
+ return;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ if (cpu_has_load_perf_global_ctrl) {
+ add_atomic_switch_msr_special(
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
+ GUEST_IA32_PERF_GLOBAL_CTRL,
+ HOST_IA32_PERF_GLOBAL_CTRL,
+ guest_val, host_val);
+ return;
+ }
+ break;
}
for (i = 0; i < m->nr; ++i)
if (m->guest[i].index == msr)
break;
- if (i == m->nr) {
+ if (i == NR_AUTOLOAD_MSRS) {
+ printk_once(KERN_WARNING"Not enough mst switch entries. "
+ "Can't add msr %x\n", msr);
+ return;
+ } else if (i == m->nr) {
++m->nr;
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
VM_EXIT_LOAD_IA32_EFER);
+ cpu_has_load_perf_global_ctrl =
+ allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
+ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+
+ /*
+ * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
+ * but due to arrata below it can't be used. Workaround is to use
+ * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
+ *
+ * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
+ *
+ * AAK155 (model 26)
+ * AAP115 (model 30)
+ * AAT100 (model 37)
+ * BC86,AAY89,BD102 (model 44)
+ * BA97 (model 46)
+ *
+ */
+ if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) {
+ switch (boot_cpu_data.x86_model) {
+ case 26:
+ case 30:
+ case 37:
+ case 44:
+ case 46:
+ cpu_has_load_perf_global_ctrl = false;
+ printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+ "does not work properly. Using workaround\n");
+ break;
+ default:
+ break;
+ }
+ }
+
return 0;
}
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
+static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
+{
+ int i, nr_msrs;
+ struct perf_guest_switch_msr *msrs;
+
+ msrs = perf_guest_get_msrs(&nr_msrs);
+
+ if (!msrs)
+ return;
+
+ for (i = 0; i < nr_msrs; i++)
+ if (msrs[i].host == msrs[i].guest)
+ clear_atomic_switch_msr(vmx, msrs[i].msr);
+ else
+ add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
+ msrs[i].host);
+}
+
#ifdef CONFIG_X86_64
#define R "r"
#define Q "q"
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ atomic_switch_perf_msrs(vmx);
+
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
{
struct kvm_cpuid_entry2 *best;
struct kvm_lapic *apic = vcpu->arch.apic;
- u32 timer_mode_mask;
best = kvm_find_cpuid_entry(vcpu, 1, 0);
if (!best)
best->ecx |= bit(X86_FEATURE_OSXSAVE);
}
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
- best->function == 0x1) {
- best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER);
- timer_mode_mask = 3 << 17;
- } else
- timer_mode_mask = 1 << 17;
-
- if (apic)
- apic->lapic_timer.timer_mode_mask = timer_mode_mask;
+ if (apic) {
+ if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
+ apic->lapic_timer.timer_mode_mask = 3 << 17;
+ else
+ apic->lapic_timer.timer_mode_mask = 1 << 17;
+ }
}
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
case KVM_CAP_TSC_CONTROL:
r = kvm_has_tsc_control;
break;
+ case KVM_CAP_TSC_DEADLINE_TIMER:
+ r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
+ break;
default:
r = 0;
break;
do {
VM_BUG_ON(compound_head(page) != head);
pages[*nr] = page;
+ if (PageTail(page))
+ get_huge_page_tail(page);
(*nr)++;
page++;
refs++;
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
BUG_ON(!pte_none(*(kmap_pte-idx)));
set_pte(kmap_pte-idx, mk_pte(page, prot));
+ arch_flush_lazy_mmu_mode();
return (void *)vaddr;
}
*/
kpte_clear_flush(kmap_pte-idx, vaddr);
kmap_atomic_idx_pop();
+ arch_flush_lazy_mmu_mode();
}
#ifdef CONFIG_DEBUG_HIGHMEM
else {
break;
}
if (filter[i].jt != 0) {
- if (filter[i].jf)
- t_offset += is_near(f_offset) ? 2 : 6;
+ if (filter[i].jf && f_offset)
+ t_offset += is_near(f_offset) ? 2 : 5;
EMIT_COND_JMP(t_op, t_offset);
if (filter[i].jf)
EMIT_JMP(f_offset);
extern void op_nmi_exit(void);
extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
+static int nmi_timer;
int __init oprofile_arch_init(struct oprofile_operations *ops)
{
#ifdef CONFIG_X86_LOCAL_APIC
ret = op_nmi_init(ops);
#endif
+ nmi_timer = (ret != 0);
#ifdef CONFIG_X86_IO_APIC
- if (ret < 0)
+ if (nmi_timer)
ret = op_nmi_timer_init(ops);
#endif
ops->backtrace = x86_backtrace;
void oprofile_arch_exit(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
- op_nmi_exit();
+ if (!nmi_timer)
+ op_nmi_exit();
#endif
}
*/
static unsigned long efi_rt_eflags;
-static pgd_t efi_bak_pg_dir_pointer[2];
void efi_call_phys_prelog(void)
{
- unsigned long cr4;
- unsigned long temp;
struct desc_ptr gdt_descr;
local_irq_save(efi_rt_eflags);
- /*
- * If I don't have PAE, I should just duplicate two entries in page
- * directory. If I have PAE, I just need to duplicate one entry in
- * page directory.
- */
- cr4 = read_cr4_safe();
-
- if (cr4 & X86_CR4_PAE) {
- efi_bak_pg_dir_pointer[0].pgd =
- swapper_pg_dir[pgd_index(0)].pgd;
- swapper_pg_dir[0].pgd =
- swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
- } else {
- efi_bak_pg_dir_pointer[0].pgd =
- swapper_pg_dir[pgd_index(0)].pgd;
- efi_bak_pg_dir_pointer[1].pgd =
- swapper_pg_dir[pgd_index(0x400000)].pgd;
- swapper_pg_dir[pgd_index(0)].pgd =
- swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
- temp = PAGE_OFFSET + 0x400000;
- swapper_pg_dir[pgd_index(0x400000)].pgd =
- swapper_pg_dir[pgd_index(temp)].pgd;
- }
-
- /*
- * After the lock is released, the original page table is restored.
- */
+ load_cr3(initial_page_table);
__flush_tlb_all();
gdt_descr.address = __pa(get_cpu_gdt_table(0));
void efi_call_phys_epilog(void)
{
- unsigned long cr4;
struct desc_ptr gdt_descr;
gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
- cr4 = read_cr4_safe();
-
- if (cr4 & X86_CR4_PAE) {
- swapper_pg_dir[pgd_index(0)].pgd =
- efi_bak_pg_dir_pointer[0].pgd;
- } else {
- swapper_pg_dir[pgd_index(0)].pgd =
- efi_bak_pg_dir_pointer[0].pgd;
- swapper_pg_dir[pgd_index(0x400000)].pgd =
- efi_bak_pg_dir_pointer[1].pgd;
- }
-
- /*
- * After the lock is released, the original page table is restored.
- */
+ load_cr3(swapper_pg_dir);
__flush_tlb_all();
local_irq_restore(efi_rt_eflags);
EXPORT_SYMBOL_GPL(sfi_mrtc_array);
int sfi_mrtc_num;
+static void mrst_power_off(void)
+{
+ if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+ intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 1);
+}
+
+static void mrst_reboot(void)
+{
+ if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+ intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
+ else
+ intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+}
+
/* parse all the mtimer info to a static mtimer array */
static int __init sfi_parse_mtmr(struct sfi_table_header *table)
{
static unsigned long __init mrst_calibrate_tsc(void)
{
unsigned long flags, fast_calibrate;
-
- local_irq_save(flags);
- fast_calibrate = apbt_quick_calibrate();
- local_irq_restore(flags);
-
+ if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) {
+ u32 lo, hi, ratio, fsb;
+
+ rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+ pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+ ratio = (hi >> 8) & 0x1f;
+ pr_debug("ratio is %d\n", ratio);
+ if (!ratio) {
+ pr_err("read a zero ratio, should be incorrect!\n");
+ pr_err("force tsc ratio to 16 ...\n");
+ ratio = 16;
+ }
+ rdmsr(MSR_FSB_FREQ, lo, hi);
+ if ((lo & 0x7) == 0x7)
+ fsb = PENWELL_FSB_FREQ_83SKU;
+ else
+ fsb = PENWELL_FSB_FREQ_100SKU;
+ fast_calibrate = ratio * fsb;
+ pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+ lapic_timer_frequency = fsb * 1000 / HZ;
+ /* mark tsc clocksource as reliable */
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+ } else {
+ local_irq_save(flags);
+ fast_calibrate = apbt_quick_calibrate();
+ local_irq_restore(flags);
+ }
+
if (fast_calibrate)
return fast_calibrate;
return 0;
}
-/* Reboot and power off are handled by the SCU on a MID device */
-static void mrst_power_off(void)
-{
- intel_scu_ipc_simple_command(0xf1, 1);
-}
-
-static void mrst_reboot(void)
+/*
+ * Moorestown does not have external NMI source nor port 0x61 to report
+ * NMI status. The possible NMI sources are from pmu as a result of NMI
+ * watchdog or lock debug. Reading io port 0x61 results in 0xff which
+ * misled NMI handler.
+ */
+static unsigned char mrst_get_nmi_reason(void)
{
- intel_scu_ipc_simple_command(0xf1, 0);
+ return 0;
}
/*
x86_platform.calibrate_tsc = mrst_calibrate_tsc;
x86_platform.i8042_detect = mrst_i8042_detect;
x86_init.timers.wallclock_init = mrst_rtc_init;
+ x86_platform.get_nmi_reason = mrst_get_nmi_reason;
+
x86_init.pci.init = pci_mrst_init;
x86_init.pci.fixup_irqs = x86_init_noop;
return max7315;
}
+static void *tca6416_platform_data(void *info)
+{
+ static struct pca953x_platform_data tca6416;
+ struct i2c_board_info *i2c_info = info;
+ int gpio_base, intr;
+ char base_pin_name[SFI_NAME_LEN + 1];
+ char intr_pin_name[SFI_NAME_LEN + 1];
+
+ strcpy(i2c_info->type, "tca6416");
+ strcpy(base_pin_name, "tca6416_base");
+ strcpy(intr_pin_name, "tca6416_int");
+
+ gpio_base = get_gpio_by_name(base_pin_name);
+ intr = get_gpio_by_name(intr_pin_name);
+
+ if (gpio_base == -1)
+ return NULL;
+ tca6416.gpio_base = gpio_base;
+ if (intr != -1) {
+ i2c_info->irq = intr + MRST_IRQ_OFFSET;
+ tca6416.irq_base = gpio_base + MRST_IRQ_OFFSET;
+ } else {
+ i2c_info->irq = -1;
+ tca6416.irq_base = -1;
+ }
+ return &tca6416;
+}
+
+static void *mpu3050_platform_data(void *info)
+{
+ struct i2c_board_info *i2c_info = info;
+ int intr = get_gpio_by_name("mpu3050_int");
+
+ if (intr == -1)
+ return NULL;
+
+ i2c_info->irq = intr + MRST_IRQ_OFFSET;
+ return NULL;
+}
+
static void __init *emc1403_platform_data(void *info)
{
static short intr2nd_pdata;
static const struct devs_id __initconst device_ids[] = {
{"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data},
{"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+ {"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data},
{"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
{"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
{"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+ {"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data},
{"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
{"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
{"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+ {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data},
/* MSIC subdevices */
{"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data},
#endif
#define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_SP)
#define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP)
#define ARCH_IS_STACKGROW(address) \
int cpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
- per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ xen_vcpu_setup(cpu);
if (xen_have_vector_callback)
xen_init_lock_cpu(cpu);
break;
xen_hvm_smp_init();
register_cpu_notifier(&xen_hvm_cpu_notifier);
xen_unplug_emulated_devices();
- have_vcpu_info_placement = 0;
x86_init.irqs.intr_init = xen_init_IRQ;
xen_hvm_init_time_ops();
xen_hvm_init_mmu_ops();
if (shared == NULL) {
struct vm_struct *area =
- alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+ alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
BUG_ON(area == NULL);
shared = area->addr;
*__shared = shared;
domid_t domid = DOMID_SELF;
int ret;
- ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
- if (ret > 0)
- max_pages = ret;
+ /*
+ * For the initial domain we use the maximum reservation as
+ * the maximum page.
+ *
+ * For guest domains the current maximum reservation reflects
+ * the current maximum rather than the static maximum. In this
+ * case the e820 map provided to us will cover the static
+ * maximum region.
+ */
+ if (xen_initial_domain()) {
+ ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+ if (ret > 0)
+ max_pages = ret;
+ }
+
return min(max_pages, MAX_DOMAIN_PAGES);
}
#endif
disable_cpuidle();
boot_option_idle_override = IDLE_HALT;
-
+ WARN_ON(set_pm_idle_to_default());
fiddle_vdso();
}
if (drain_all)
blk_throtl_drain(q);
- __blk_run_queue(q);
+ /*
+ * This function might be called on a queue which failed
+ * driver init after queue creation. Some drivers
+ * (e.g. fd) get unhappy in such cases. Kick queue iff
+ * dispatch queue has something on it.
+ */
+ if (!list_empty(&q->queue_head))
+ __blk_run_queue(q);
if (drain_all)
nr_rqs = q->rq.count[0] + q->rq.count[1];
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
q->backing_dev_info.name = "block";
+ q->node = node_id;
err = bdi_init(&q->backing_dev_info);
if (err) {
if (!uninit_q)
return NULL;
- q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
+ q = blk_init_allocated_queue(uninit_q, rfn, lock);
if (!q)
blk_cleanup_queue(uninit_q);
struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
-{
- return blk_init_allocated_queue_node(q, rfn, lock, -1);
-}
-EXPORT_SYMBOL(blk_init_allocated_queue);
-
-struct request_queue *
-blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
- spinlock_t *lock, int node_id)
{
if (!q)
return NULL;
- q->node = node_id;
if (blk_init_free_list(q))
return NULL;
return NULL;
}
-EXPORT_SYMBOL(blk_init_allocated_queue_node);
+EXPORT_SYMBOL(blk_init_allocated_queue);
int blk_get_queue(struct request_queue *q)
{
*/
if (list_empty(&plug->list))
trace_block_plug(q);
- else if (!plug->should_sort) {
- struct request *__rq;
+ else {
+ if (!plug->should_sort) {
+ struct request *__rq;
- __rq = list_entry_rq(plug->list.prev);
- if (__rq->q != q)
- plug->should_sort = 1;
+ __rq = list_entry_rq(plug->list.prev);
+ if (__rq->q != q)
+ plug->should_sort = 1;
+ }
+ if (request_count >= BLK_MAX_REQUEST_COUNT) {
+ blk_flush_plug_list(plug, false);
+ trace_block_plug(q);
+ }
}
- if (request_count >= BLK_MAX_REQUEST_COUNT)
- blk_flush_plug_list(plug, false);
list_add_tail(&req->queuelist, &plug->list);
drive_stat_acct(req, 1);
} else {
if (!iov[i].iov_len)
return -EINVAL;
- if (uaddr & queue_dma_alignment(q)) {
+ /*
+ * Keep going so we check length of all segments
+ */
+ if (uaddr & queue_dma_alignment(q))
unaligned = 1;
- break;
- }
}
if (unaligned || (q->dma_pad_mask & len) || map_data)
if (IS_ERR(bio))
return PTR_ERR(bio);
- if (rq_data_dir(rq) == WRITE)
+ if (!reading)
bio->bi_rw |= REQ_WRITE;
if (do_copy)
void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
- int tag = rq->tag;
+ unsigned tag = rq->tag; /* negative tags invalid */
- BUG_ON(tag == -1);
-
- if (unlikely(tag >= bqt->max_depth)) {
- /*
- * This can happen after tag depth has been reduced.
- * But tag shouldn't be larger than real_max_depth.
- */
- WARN_ON(tag >= bqt->real_max_depth);
- return;
- }
+ BUG_ON(tag >= bqt->real_max_depth);
list_del_init(&rq->queuelist);
rq->cmd_flags &= ~REQ_QUEUED;
struct request *next)
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
+ struct cfq_data *cfqd = q->elevator->elevator_data;
+
/*
* reposition in fifo if next is older than rq
*/
cfq_remove_request(next);
cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg,
rq_data_dir(next), rq_is_sync(next));
+
+ cfqq = RQ_CFQQ(next);
+ /*
+ * all requests of this queue are merged to other queues, delete it
+ * from the service tree. If it's the active_queue,
+ * cfq_dispatch_requests() will choose to expire it or do idle
+ */
+ if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list) &&
+ cfqq != cfqd->active_queue)
+ cfq_del_cfqq_rr(cfqd, cfqq);
}
static int cfq_allow_merge(struct request_queue *q, struct request *rq,
}
}
- if (ret)
+ if (ret && ret != -EEXIST)
printk(KERN_ERR "cfq: cic link failed!\n");
return ret;
{
struct io_context *ioc = NULL;
struct cfq_io_context *cic;
+ int ret;
might_sleep_if(gfp_mask & __GFP_WAIT);
if (!ioc)
return NULL;
+retry:
cic = cfq_cic_lookup(cfqd, ioc);
if (cic)
goto out;
if (cic == NULL)
goto err;
- if (cfq_cic_link(cfqd, ioc, cic, gfp_mask))
+ ret = cfq_cic_link(cfqd, ioc, cic, gfp_mask);
+ if (ret == -EEXIST) {
+ /* someone has linked cic to ioc already */
+ cfq_cic_free(cic);
+ goto retry;
+ } else if (ret)
goto err_free;
out:
if (blkio_alloc_blkg_stats(&cfqg->blkg)) {
kfree(cfqg);
+
+ spin_lock(&cic_index_lock);
+ ida_remove(&cic_index_ida, cfqd->cic_index);
+ spin_unlock(&cic_index_lock);
+
kfree(cfqd);
return NULL;
}
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
-#include <linux/ctype.h>
#include "blk.h"
subsys_initcall(genhd_device_init);
-static ssize_t alias_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gendisk *disk = dev_to_disk(dev);
- ssize_t ret = 0;
-
- if (disk->alias)
- ret = snprintf(buf, ALIAS_LEN, "%s\n", disk->alias);
- return ret;
-}
-
-static ssize_t alias_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gendisk *disk = dev_to_disk(dev);
- char *alias;
- char *envp[] = { NULL, NULL };
- unsigned char c;
- int i;
- ssize_t ret = count;
-
- if (!count)
- return -EINVAL;
-
- if (count >= ALIAS_LEN) {
- printk(KERN_ERR "alias: alias is too long\n");
- return -EINVAL;
- }
-
- /* Validation check */
- for (i = 0; i < count; i++) {
- c = buf[i];
- if (i == count - 1 && c == '\n')
- break;
- if (!isalnum(c) && c != '_' && c != '-') {
- printk(KERN_ERR "alias: invalid alias\n");
- return -EINVAL;
- }
- }
-
- if (disk->alias) {
- printk(KERN_INFO "alias: %s is already assigned (%s)\n",
- disk->disk_name, disk->alias);
- return -EINVAL;
- }
-
- alias = kasprintf(GFP_KERNEL, "%s", buf);
- if (!alias)
- return -ENOMEM;
-
- if (alias[count - 1] == '\n')
- alias[count - 1] = '\0';
-
- envp[0] = kasprintf(GFP_KERNEL, "ALIAS=%s", alias);
- if (!envp[0]) {
- kfree(alias);
- return -ENOMEM;
- }
-
- disk->alias = alias;
- printk(KERN_INFO "alias: assigned %s to %s\n", alias, disk->disk_name);
-
- kobject_uevent_env(&dev->kobj, KOBJ_ADD, envp);
-
- kfree(envp[0]);
- return ret;
-}
-
static ssize_t disk_range_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
}
-static DEVICE_ATTR(alias, S_IRUGO|S_IWUSR, alias_show, alias_store);
static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
#endif
static struct attribute *disk_attrs[] = {
- &dev_attr_alias.attr,
&dev_attr_range.attr,
&dev_attr_ext_range.attr,
&dev_attr_removable.attr,
static int erst_open_pstore(struct pstore_info *psi);
static int erst_close_pstore(struct pstore_info *psi);
static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
- struct timespec *time, struct pstore_info *psi);
+ struct timespec *time, char **buf,
+ struct pstore_info *psi);
static int erst_writer(enum pstore_type_id type, u64 *id, unsigned int part,
size_t size, struct pstore_info *psi);
static int erst_clearer(enum pstore_type_id type, u64 id,
}
static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
- struct timespec *time, struct pstore_info *psi)
+ struct timespec *time, char **buf,
+ struct pstore_info *psi)
{
int rc;
ssize_t len = 0;
u64 record_id;
- struct cper_pstore_record *rcd = (struct cper_pstore_record *)
- (erst_info.buf - sizeof(*rcd));
+ struct cper_pstore_record *rcd;
+ size_t rcd_len = sizeof(*rcd) + erst_info.bufsize;
if (erst_disable)
return -ENODEV;
+ rcd = kmalloc(rcd_len, GFP_KERNEL);
+ if (!rcd) {
+ rc = -ENOMEM;
+ goto out;
+ }
skip:
rc = erst_get_record_id_next(&reader_pos, &record_id);
if (rc)
/* no more record */
if (record_id == APEI_ERST_INVALID_RECORD_ID) {
- rc = -1;
+ rc = -EINVAL;
goto out;
}
- len = erst_read(record_id, &rcd->hdr, sizeof(*rcd) +
- erst_info.bufsize);
+ len = erst_read(record_id, &rcd->hdr, rcd_len);
/* The record may be cleared by others, try read next record */
if (len == -ENOENT)
goto skip;
- else if (len < 0) {
- rc = -1;
+ else if (len < sizeof(*rcd)) {
+ rc = -EIO;
goto out;
}
if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0)
goto skip;
+ *buf = kmalloc(len, GFP_KERNEL);
+ if (*buf == NULL) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ memcpy(*buf, rcd->data, len - sizeof(*rcd));
*id = record_id;
if (uuid_le_cmp(rcd->sec_hdr.section_type,
CPER_SECTION_TYPE_DMESG) == 0)
time->tv_nsec = 0;
out:
+ kfree(rcd);
return (rc < 0) ? rc : (len - sizeof(*rcd));
}
config PATA_OF_PLATFORM
tristate "OpenFirmware platform device PATA support"
- depends on PATA_PLATFORM && OF
+ depends on PATA_PLATFORM && OF && OF_IRQ
help
This option enables support for generic directly connected ATA
devices commonly found on embedded systems with OpenFirmware
struct device *dev = &pdev->dev;
struct ahci_platform_data *pdata = dev_get_platdata(dev);
const struct platform_device_id *id = platform_get_device_id(pdev);
- struct ata_port_info pi = ahci_port_info[id->driver_data];
+ struct ata_port_info pi = ahci_port_info[id ? id->driver_data : 0];
const struct ata_port_info *ppi[] = { &pi, NULL };
struct ahci_host_priv *hpriv;
struct ata_host *host;
if (rc)
goto out;
+#ifdef CONFIG_ATA_BMDMA
if (bmdma)
/* prepare and activate BMDMA host */
rc = ata_pci_bmdma_prepare_host(pdev, ppi, &host);
else
+#endif
/* prepare and activate SFF host */
rc = ata_pci_sff_prepare_host(pdev, ppi, &host);
if (rc)
host->private_data = host_priv;
host->flags |= hflags;
+#ifdef CONFIG_ATA_BMDMA
if (bmdma) {
pci_set_master(pdev);
rc = ata_pci_sff_activate_host(host, ata_bmdma_interrupt, sht);
} else
+#endif
rc = ata_pci_sff_activate_host(host, ata_sff_interrupt, sht);
out:
if (rc == 0)
if (ia_vcc == NULL)
{
atomic_inc(&vcc->stats->rx_err);
+ atm_return(vcc, skb->truesize);
dev_kfree_skb_any(skb);
- atm_return(vcc, atm_guess_pdu2truesize(len));
goto INCR_DLE;
}
// get real pkt length pwang_test
atomic_inc(&vcc->stats->rx_err);
IF_ERR(printk("rx_dle_intr: Bad AAL5 trailer %d (skb len %d)",
length, skb->len);)
+ atm_return(vcc, skb->truesize);
dev_kfree_skb_any(skb);
- atm_return(vcc, atm_guess_pdu2truesize(len));
goto INCR_DLE;
}
skb_trim(skb, length);
#include <linux/kallsyms.h>
#include <linux/mutex.h>
#include <linux/async.h>
+#include <linux/pm_runtime.h>
#include "base.h"
#include "power/power.h"
list_del_init(&dev->kobj.entry);
spin_unlock(&devices_kset->list_lock);
+ /* Don't allow any more runtime suspends */
+ pm_runtime_get_noresume(dev);
+ pm_runtime_barrier(dev);
+
if (dev->bus && dev->bus->shutdown) {
dev_dbg(dev, "shutdown\n");
dev->bus->shutdown(dev);
nid, K(node_page_state(nid, NR_WRITEBACK)),
nid, K(node_page_state(nid, NR_FILE_PAGES)),
nid, K(node_page_state(nid, NR_FILE_MAPPED)),
- nid, K(node_page_state(nid, NR_ANON_PAGES)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ nid, K(node_page_state(nid, NR_ANON_PAGES)
+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR
+ HPAGE_PMD_NR),
+#else
+ nid, K(node_page_state(nid, NR_ANON_PAGES)),
#endif
- ),
nid, K(node_page_state(nid, NR_SHMEM)),
nid, node_page_state(nid, NR_KERNEL_STACK) *
THREAD_SIZE / 1024,
nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
- nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
, nid,
K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR)
+ HPAGE_PMD_NR));
+#else
+ nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
#endif
- );
n += hugetlb_report_node_meminfo(nid, buf + n);
return n;
}
list_for_each_entry_reverse(ce, &psd->clock_list, node) {
if (ce->status < PCE_STATUS_ERROR) {
- clk_disable(ce->clk);
+ if (ce->status == PCE_STATUS_ENABLED)
+ clk_disable(ce->clk);
ce->status = PCE_STATUS_ACQUIRED;
}
}
End:
if (!error) {
dev->power.is_suspended = true;
- if (dev->power.wakeup_path && dev->parent)
+ if (dev->power.wakeup_path
+ && dev->parent && !dev->parent->power.ignore_children)
dev->parent->power.wakeup_path = true;
}
if (!dev || !req) /*guard against callers passing in null */
return -EINVAL;
- if (dev_pm_qos_request_active(req)) {
- WARN(1, KERN_ERR "dev_pm_qos_add_request() called for already "
- "added request\n");
+ if (WARN(dev_pm_qos_request_active(req),
+ "%s() called for already added request\n", __func__))
return -EINVAL;
- }
req->dev = dev;
if (!req) /*guard against callers passing in null */
return -EINVAL;
- if (!dev_pm_qos_request_active(req)) {
- WARN(1, KERN_ERR "dev_pm_qos_update_request() called for "
- "unknown object\n");
+ if (WARN(!dev_pm_qos_request_active(req),
+ "%s() called for unknown object\n", __func__))
return -EINVAL;
- }
mutex_lock(&dev_pm_qos_mtx);
if (!req) /*guard against callers passing in null */
return -EINVAL;
- if (!dev_pm_qos_request_active(req)) {
- WARN(1, KERN_ERR "dev_pm_qos_remove_request() called for "
- "unknown object\n");
+ if (WARN(!dev_pm_qos_request_active(req),
+ "%s() called for unknown object\n", __func__))
return -EINVAL;
- }
mutex_lock(&dev_pm_qos_mtx);
#include <linux/interrupt.h>
#include <linux/types.h>
#include <linux/pci.h>
+#include <linux/pci-aspm.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/delay.h>
c->Request.Timeout = 0;
c->Request.CDB[0] = BMIC_WRITE;
c->Request.CDB[6] = BMIC_CACHE_FLUSH;
+ c->Request.CDB[7] = (size >> 8) & 0xFF;
+ c->Request.CDB[8] = size & 0xFF;
break;
case TEST_UNIT_READY:
c->Request.CDBLen = 6;
dev_warn(&h->pdev->dev, "controller appears to be disabled\n");
return -ENODEV;
}
+
+ pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
+ PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
+
err = pci_enable_device(h->pdev);
if (err) {
dev_warn(&h->pdev->dev, "Unable to Enable PCI device\n");
{
if (h->msix_vector || h->msi_vector) {
if (!request_irq(h->intr[h->intr_mode], msixhandler,
- IRQF_DISABLED, h->devname, h))
+ 0, h->devname, h))
return 0;
dev_err(&h->pdev->dev, "Unable to get msi irq %d"
" for %s\n", h->intr[h->intr_mode],
}
if (!request_irq(h->intr[h->intr_mode], intxhandler,
- IRQF_DISABLED, h->devname, h))
+ IRQF_SHARED, h->devname, h))
return 0;
dev_err(&h->pdev->dev, "Unable to get irq %d for %s\n",
h->intr[h->intr_mode], h->devname);
h->cciss_max_sectors = 8192;
rebuild_lun_table(h, 1, 0);
+ cciss_engage_scsi(h);
h->busy_initializing = 0;
return 1;
/* If no tape support, then these become defined out of existence */
#define cciss_scsi_setup(cntl_num)
+#define cciss_engage_scsi(h)
#endif /* CONFIG_CISS_SCSI_TAPE */
&xor_funcs
};
-static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
- loff_t size, offset, loopsize;
+ loff_t size, loopsize;
/* Compute loopsize in bytes */
size = i_size_read(file->f_mapping->host);
- offset = lo->lo_offset;
loopsize = size - offset;
- if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
- loopsize = lo->lo_sizelimit;
+ /* offset is beyond i_size, wierd but possible */
+ if (loopsize < 0)
+ return 0;
+ if (sizelimit > 0 && sizelimit < loopsize)
+ loopsize = sizelimit;
/*
* Unfortunately, if we want to do I/O on the device,
* the number of 512-byte sectors has to fit into a sector_t.
return loopsize >> 9;
}
+static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+{
+ return get_size(lo->lo_offset, lo->lo_sizelimit, file);
+}
+
static int
-figure_loop_size(struct loop_device *lo)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
{
- loff_t size = get_loop_size(lo, lo->lo_backing_file);
+ loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
sector_t x = (sector_t)size;
if (unlikely((loff_t)x != size))
return -EFBIG;
-
+ if (lo->lo_offset != offset)
+ lo->lo_offset = offset;
+ if (lo->lo_sizelimit != sizelimit)
+ lo->lo_sizelimit = sizelimit;
set_capacity(lo->lo_disk, x);
- return 0;
+ return 0;
}
static inline int
if (retval < 0)
return retval;
-
+ if (retval != bvec->bv_len)
+ return -EIO;
return 0;
}
/*
* We use punch hole to reclaim the free space used by the
- * image a.k.a. discard. However we do support discard if
+ * image a.k.a. discard. However we do not support discard if
* encryption is enabled, because it may give an attacker
* useful information.
*/
}
q->limits.discard_granularity = inode->i_sb->s_blocksize;
- q->limits.discard_alignment = inode->i_sb->s_blocksize;
+ q->limits.discard_alignment = 0;
q->limits.max_discard_sectors = UINT_MAX >> 9;
q->limits.discard_zeroes_data = 1;
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
if (lo->lo_offset != info->lo_offset ||
lo->lo_sizelimit != info->lo_sizelimit) {
- lo->lo_offset = info->lo_offset;
- lo->lo_sizelimit = info->lo_sizelimit;
- if (figure_loop_size(lo))
+ if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
return -EFBIG;
}
loop_config_discard(lo);
err = -ENXIO;
if (unlikely(lo->lo_state != Lo_bound))
goto out;
- err = figure_loop_size(lo);
+ err = figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
if (unlikely(err))
goto out;
sec = get_capacity(lo->lo_disk);
goto out_unlocked;
break;
case LOOP_SET_STATUS:
- err = loop_set_status_old(lo, (struct loop_info __user *) arg);
+ err = -EPERM;
+ if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+ err = loop_set_status_old(lo,
+ (struct loop_info __user *)arg);
break;
case LOOP_GET_STATUS:
err = loop_get_status_old(lo, (struct loop_info __user *) arg);
break;
case LOOP_SET_STATUS64:
- err = loop_set_status64(lo, (struct loop_info64 __user *) arg);
+ err = -EPERM;
+ if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+ err = loop_set_status64(lo,
+ (struct loop_info64 __user *) arg);
break;
case LOOP_GET_STATUS64:
err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
if (dev->status & 0x10)
return -ETIME;
+ memset(&hdr, 0, sizeof(hdr));
hdr.magic = PG_MAGIC;
hdr.dlen = dev->dlen;
copy = 0;
static int __rbd_init_snaps_header(struct rbd_device *rbd_dev);
static void rbd_dev_release(struct device *dev);
-static ssize_t rbd_snap_rollback(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t size);
static ssize_t rbd_snap_add(struct device *dev,
struct device_attribute *attr,
const char *buf,
u32 snap_count = le32_to_cpu(ondisk->snap_count);
int ret = -ENOMEM;
+ if (memcmp(ondisk, RBD_HEADER_TEXT, sizeof(RBD_HEADER_TEXT))) {
+ return -ENXIO;
+ }
+
init_rwsem(&header->snap_rwsem);
header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
return ret;
}
-/*
- * Request sync osd rollback
- */
-static int rbd_req_sync_rollback_obj(struct rbd_device *dev,
- u64 snapid,
- const char *obj)
-{
- struct ceph_osd_req_op *ops;
- int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_ROLLBACK, 0);
- if (ret < 0)
- return ret;
-
- ops[0].snap.snapid = snapid;
-
- ret = rbd_req_sync_op(dev, NULL,
- CEPH_NOSNAP,
- 0,
- CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
- ops,
- 1, obj, 0, 0, NULL, NULL, NULL);
-
- rbd_destroy_ops(ops);
-
- return ret;
-}
-
/*
* Request sync osd read
*/
goto out_dh;
rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
- if (rc < 0)
+ if (rc < 0) {
+ if (rc == -ENXIO) {
+ pr_warning("unrecognized header format"
+ " for image %s", rbd_dev->obj);
+ }
goto out_dh;
+ }
if (snap_count != header->total_snaps) {
snap_count = header->total_snaps;
static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
static DEVICE_ATTR(create_snap, S_IWUSR, NULL, rbd_snap_add);
-static DEVICE_ATTR(rollback_snap, S_IWUSR, NULL, rbd_snap_rollback);
static struct attribute *rbd_attrs[] = {
&dev_attr_size.attr,
&dev_attr_current_snap.attr,
&dev_attr_refresh.attr,
&dev_attr_create_snap.attr,
- &dev_attr_rollback_snap.attr,
NULL
};
return ret;
}
-static ssize_t rbd_snap_rollback(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct rbd_device *rbd_dev = dev_to_rbd(dev);
- int ret;
- u64 snapid;
- u64 cur_ofs;
- char *seg_name = NULL;
- char *snap_name = kmalloc(count + 1, GFP_KERNEL);
- ret = -ENOMEM;
- if (!snap_name)
- return ret;
-
- /* parse snaps add command */
- snprintf(snap_name, count, "%s", buf);
- seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
- if (!seg_name)
- goto done;
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- ret = snap_by_name(&rbd_dev->header, snap_name, &snapid, NULL);
- if (ret < 0)
- goto done_unlock;
-
- dout("snapid=%lld\n", snapid);
-
- cur_ofs = 0;
- while (cur_ofs < rbd_dev->header.image_size) {
- cur_ofs += rbd_get_segment(&rbd_dev->header,
- rbd_dev->obj,
- cur_ofs, (u64)-1,
- seg_name, NULL);
- dout("seg_name=%s\n", seg_name);
-
- ret = rbd_req_sync_rollback_obj(rbd_dev, snapid, seg_name);
- if (ret < 0)
- pr_warning("could not roll back obj %s err=%d\n",
- seg_name, ret);
- }
-
- ret = __rbd_update_snaps(rbd_dev);
- if (ret < 0)
- goto done_unlock;
-
- ret = count;
-
-done_unlock:
- mutex_unlock(&ctl_mutex);
-done:
- kfree(seg_name);
- kfree(snap_name);
-
- return ret;
-}
-
static struct bus_attribute rbd_bus_attrs[] = {
__ATTR(add, S_IWUSR, NULL, rbd_add),
__ATTR(remove, S_IWUSR, NULL, rbd_remove),
* handle GCR disks
*/
+#undef DEBUG
+
#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <asm/machdep.h>
#include <asm/pmac_feature.h>
-static DEFINE_MUTEX(swim3_mutex);
-static struct request_queue *swim3_queue;
-static struct gendisk *disks[2];
-static struct request *fd_req;
-
#define MAX_FLOPPIES 2
+static DEFINE_MUTEX(swim3_mutex);
+static struct gendisk *disks[MAX_FLOPPIES];
+
enum swim_state {
idle,
locating,
struct floppy_state {
enum swim_state state;
- spinlock_t lock;
struct swim3 __iomem *swim3; /* hardware registers */
struct dbdma_regs __iomem *dma; /* DMA controller registers */
int swim3_intr; /* interrupt number for SWIM3 */
int wanted;
struct macio_dev *mdev;
char dbdma_cmd_space[5 * sizeof(struct dbdma_cmd)];
+ int index;
+ struct request *cur_req;
};
+#define swim3_err(fmt, arg...) dev_err(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#define swim3_warn(fmt, arg...) dev_warn(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#define swim3_info(fmt, arg...) dev_info(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+
+#ifdef DEBUG
+#define swim3_dbg(fmt, arg...) dev_dbg(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#else
+#define swim3_dbg(fmt, arg...) do { } while(0)
+#endif
+
static struct floppy_state floppy_states[MAX_FLOPPIES];
static int floppy_count = 0;
static DEFINE_SPINLOCK(swim3_lock);
0, 0, 0, 0, 0, 0
};
-static void swim3_select(struct floppy_state *fs, int sel);
-static void swim3_action(struct floppy_state *fs, int action);
-static int swim3_readbit(struct floppy_state *fs, int bit);
-static void do_fd_request(struct request_queue * q);
-static void start_request(struct floppy_state *fs);
-static void set_timeout(struct floppy_state *fs, int nticks,
- void (*proc)(unsigned long));
-static void scan_track(struct floppy_state *fs);
static void seek_track(struct floppy_state *fs, int n);
static void init_dma(struct dbdma_cmd *cp, int cmd, void *buf, int count);
-static void setup_transfer(struct floppy_state *fs);
static void act(struct floppy_state *fs);
static void scan_timeout(unsigned long data);
static void seek_timeout(unsigned long data);
unsigned int clearing);
static int floppy_revalidate(struct gendisk *disk);
-static bool swim3_end_request(int err, unsigned int nr_bytes)
+static bool swim3_end_request(struct floppy_state *fs, int err, unsigned int nr_bytes)
{
- if (__blk_end_request(fd_req, err, nr_bytes))
- return true;
+ struct request *req = fs->cur_req;
+ int rc;
- fd_req = NULL;
- return false;
-}
+ swim3_dbg(" end request, err=%d nr_bytes=%d, cur_req=%p\n",
+ err, nr_bytes, req);
-static bool swim3_end_request_cur(int err)
-{
- return swim3_end_request(err, blk_rq_cur_bytes(fd_req));
+ if (err)
+ nr_bytes = blk_rq_cur_bytes(req);
+ rc = __blk_end_request(req, err, nr_bytes);
+ if (rc)
+ return true;
+ fs->cur_req = NULL;
+ return false;
}
static void swim3_select(struct floppy_state *fs, int sel)
return (stat & DATA) == 0;
}
-static void do_fd_request(struct request_queue * q)
-{
- int i;
-
- for(i=0; i<floppy_count; i++) {
- struct floppy_state *fs = &floppy_states[i];
- if (fs->mdev->media_bay &&
- check_media_bay(fs->mdev->media_bay) != MB_FD)
- continue;
- start_request(fs);
- }
-}
-
static void start_request(struct floppy_state *fs)
{
struct request *req;
unsigned long x;
+ swim3_dbg("start request, initial state=%d\n", fs->state);
+
if (fs->state == idle && fs->wanted) {
fs->state = available;
wake_up(&fs->wait);
return;
}
while (fs->state == idle) {
- if (!fd_req) {
- fd_req = blk_fetch_request(swim3_queue);
- if (!fd_req)
+ swim3_dbg("start request, idle loop, cur_req=%p\n", fs->cur_req);
+ if (!fs->cur_req) {
+ fs->cur_req = blk_fetch_request(disks[fs->index]->queue);
+ swim3_dbg(" fetched request %p\n", fs->cur_req);
+ if (!fs->cur_req)
break;
}
- req = fd_req;
-#if 0
- printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
- req->rq_disk->disk_name, req->cmd,
- (long)blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
- printk(" errors=%d current_nr_sectors=%u\n",
- req->errors, blk_rq_cur_sectors(req));
+ req = fs->cur_req;
+
+ if (fs->mdev->media_bay &&
+ check_media_bay(fs->mdev->media_bay) != MB_FD) {
+ swim3_dbg("%s", " media bay absent, dropping req\n");
+ swim3_end_request(fs, -ENODEV, 0);
+ continue;
+ }
+
+#if 0 /* This is really too verbose */
+ swim3_dbg("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
+ req->rq_disk->disk_name, req->cmd,
+ (long)blk_rq_pos(req), blk_rq_sectors(req),
+ req->buffer);
+ swim3_dbg(" errors=%d current_nr_sectors=%u\n",
+ req->errors, blk_rq_cur_sectors(req));
#endif
if (blk_rq_pos(req) >= fs->total_secs) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg(" pos out of bounds (%ld, max is %ld)\n",
+ (long)blk_rq_pos(req), (long)fs->total_secs);
+ swim3_end_request(fs, -EIO, 0);
continue;
}
if (fs->ejected) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg("%s", " disk ejected\n");
+ swim3_end_request(fs, -EIO, 0);
continue;
}
if (fs->write_prot < 0)
fs->write_prot = swim3_readbit(fs, WRITE_PROT);
if (fs->write_prot) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg("%s", " try to write, disk write protected\n");
+ swim3_end_request(fs, -EIO, 0);
continue;
}
}
x = ((long)blk_rq_pos(req)) % fs->secpercyl;
fs->head = x / fs->secpertrack;
fs->req_sector = x % fs->secpertrack + 1;
- fd_req = req;
fs->state = do_transfer;
fs->retries = 0;
}
}
+static void do_fd_request(struct request_queue * q)
+{
+ start_request(q->queuedata);
+}
+
static void set_timeout(struct floppy_state *fs, int nticks,
void (*proc)(unsigned long))
{
- unsigned long flags;
-
- spin_lock_irqsave(&fs->lock, flags);
if (fs->timeout_pending)
del_timer(&fs->timeout);
fs->timeout.expires = jiffies + nticks;
fs->timeout.data = (unsigned long) fs;
add_timer(&fs->timeout);
fs->timeout_pending = 1;
- spin_unlock_irqrestore(&fs->lock, flags);
}
static inline void scan_track(struct floppy_state *fs)
struct swim3 __iomem *sw = fs->swim3;
struct dbdma_cmd *cp = fs->dma_cmd;
struct dbdma_regs __iomem *dr = fs->dma;
+ struct request *req = fs->cur_req;
- if (blk_rq_cur_sectors(fd_req) <= 0) {
- printk(KERN_ERR "swim3: transfer 0 sectors?\n");
+ if (blk_rq_cur_sectors(req) <= 0) {
+ swim3_warn("%s", "Transfer 0 sectors ?\n");
return;
}
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
n = 1;
else {
n = fs->secpertrack - fs->req_sector + 1;
- if (n > blk_rq_cur_sectors(fd_req))
- n = blk_rq_cur_sectors(fd_req);
+ if (n > blk_rq_cur_sectors(req))
+ n = blk_rq_cur_sectors(req);
}
+
+ swim3_dbg(" setup xfer at sect %d (of %d) head %d for %d\n",
+ fs->req_sector, fs->secpertrack, fs->head, n);
+
fs->scount = n;
swim3_select(fs, fs->head? READ_DATA_1: READ_DATA_0);
out_8(&sw->sector, fs->req_sector);
out_8(&sw->nsect, n);
out_8(&sw->gap3, 0);
out_le32(&dr->cmdptr, virt_to_bus(cp));
- if (rq_data_dir(fd_req) == WRITE) {
+ if (rq_data_dir(req) == WRITE) {
/* Set up 3 dma commands: write preamble, data, postamble */
init_dma(cp, OUTPUT_MORE, write_preamble, sizeof(write_preamble));
++cp;
- init_dma(cp, OUTPUT_MORE, fd_req->buffer, 512);
+ init_dma(cp, OUTPUT_MORE, req->buffer, 512);
++cp;
init_dma(cp, OUTPUT_LAST, write_postamble, sizeof(write_postamble));
} else {
- init_dma(cp, INPUT_LAST, fd_req->buffer, n * 512);
+ init_dma(cp, INPUT_LAST, req->buffer, n * 512);
}
++cp;
out_le16(&cp->command, DBDMA_STOP);
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
in_8(&sw->error);
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
out_8(&sw->control_bis, WRITE_SECTORS);
in_8(&sw->intr);
out_le32(&dr->control, (RUN << 16) | RUN);
static void act(struct floppy_state *fs)
{
for (;;) {
+ swim3_dbg(" act loop, state=%d, req_cyl=%d, cur_cyl=%d\n",
+ fs->state, fs->req_cyl, fs->cur_cyl);
+
switch (fs->state) {
case idle:
return; /* XXX shouldn't get here */
case locating:
if (swim3_readbit(fs, TRACK_ZERO)) {
+ swim3_dbg("%s", " locate track 0\n");
fs->cur_cyl = 0;
if (fs->req_cyl == 0)
fs->state = do_transfer;
break;
}
if (fs->req_cyl == fs->cur_cyl) {
- printk("whoops, seeking 0\n");
+ swim3_warn("%s", "Whoops, seeking 0\n");
fs->state = do_transfer;
break;
}
case do_transfer:
if (fs->cur_cyl != fs->req_cyl) {
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_err("Wrong cylinder in transfer, want: %d got %d\n",
+ fs->req_cyl, fs->cur_cyl);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
return;
}
return;
default:
- printk(KERN_ERR"swim3: unknown state %d\n", fs->state);
+ swim3_err("Unknown state %d\n", fs->state);
return;
}
}
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+
+ swim3_dbg("* scan timeout, state=%d\n", fs->state);
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
out_8(&sw->select, RELAX);
out_8(&sw->intr_enable, 0);
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
} else {
fs->state = jogging;
act(fs);
}
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void seek_timeout(unsigned long data)
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+
+ swim3_dbg("* seek timeout, state=%d\n", fs->state);
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_8(&sw->control_bic, DO_SEEK);
out_8(&sw->select, RELAX);
out_8(&sw->intr_enable, 0);
- printk(KERN_ERR "swim3: seek timeout\n");
- swim3_end_request_cur(-EIO);
+ swim3_err("%s", "Seek timeout\n");
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void settle_timeout(unsigned long data)
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+
+ swim3_dbg("* settle timeout, state=%d\n", fs->state);
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
if (swim3_readbit(fs, SEEK_COMPLETE)) {
out_8(&sw->select, RELAX);
fs->state = locating;
act(fs);
- return;
+ goto unlock;
}
out_8(&sw->select, RELAX);
if (fs->settle_time < 2*HZ) {
++fs->settle_time;
set_timeout(fs, 1, settle_timeout);
- return;
+ goto unlock;
}
- printk(KERN_ERR "swim3: seek settle timeout\n");
- swim3_end_request_cur(-EIO);
+ swim3_err("%s", "Seek settle timeout\n");
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ unlock:
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void xfer_timeout(unsigned long data)
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
struct dbdma_regs __iomem *dr = fs->dma;
+ unsigned long flags;
int n;
+ swim3_dbg("* xfer timeout, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_le32(&dr->control, RUN << 16);
/* We must wait a bit for dbdma to stop */
out_8(&sw->intr_enable, 0);
out_8(&sw->control_bic, WRITE_SECTORS | DO_ACTION);
out_8(&sw->select, RELAX);
- printk(KERN_ERR "swim3: timeout %sing sector %ld\n",
- (rq_data_dir(fd_req)==WRITE? "writ": "read"),
- (long)blk_rq_pos(fd_req));
- swim3_end_request_cur(-EIO);
+ swim3_err("Timeout %sing sector %ld\n",
+ (rq_data_dir(fs->cur_req)==WRITE? "writ": "read"),
+ (long)blk_rq_pos(fs->cur_req));
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static irqreturn_t swim3_interrupt(int irq, void *dev_id)
int stat, resid;
struct dbdma_regs __iomem *dr;
struct dbdma_cmd *cp;
+ unsigned long flags;
+ struct request *req = fs->cur_req;
+
+ swim3_dbg("* interrupt, state=%d\n", fs->state);
+ spin_lock_irqsave(&swim3_lock, flags);
intr = in_8(&sw->intr);
err = (intr & ERROR_INTR)? in_8(&sw->error): 0;
if ((intr & ERROR_INTR) && fs->state != do_transfer)
- printk(KERN_ERR "swim3_interrupt, state=%d, dir=%x, intr=%x, err=%x\n",
- fs->state, rq_data_dir(fd_req), intr, err);
+ swim3_err("Non-transfer error interrupt: state=%d, dir=%x, intr=%x, err=%x\n",
+ fs->state, rq_data_dir(req), intr, err);
switch (fs->state) {
case locating:
if (intr & SEEN_SECTOR) {
del_timer(&fs->timeout);
fs->timeout_pending = 0;
if (sw->ctrack == 0xff) {
- printk(KERN_ERR "swim3: seen sector but cyl=ff?\n");
+ swim3_err("%s", "Seen sector but cyl=ff?\n");
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
} else {
fs->cur_cyl = sw->ctrack;
fs->cur_sector = sw->csect;
if (fs->expect_cyl != -1 && fs->expect_cyl != fs->cur_cyl)
- printk(KERN_ERR "swim3: expected cyl %d, got %d\n",
- fs->expect_cyl, fs->cur_cyl);
+ swim3_err("Expected cyl %d, got %d\n",
+ fs->expect_cyl, fs->cur_cyl);
fs->state = do_transfer;
act(fs);
}
fs->timeout_pending = 0;
dr = fs->dma;
cp = fs->dma_cmd;
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
++cp;
/*
* Check that the main data transfer has finished.
if (intr & ERROR_INTR) {
n = fs->scount - 1 - resid / 512;
if (n > 0) {
- blk_update_request(fd_req, 0, n << 9);
+ blk_update_request(req, 0, n << 9);
fs->req_sector += n;
}
if (fs->retries < 5) {
++fs->retries;
act(fs);
} else {
- printk("swim3: error %sing block %ld (err=%x)\n",
- rq_data_dir(fd_req) == WRITE? "writ": "read",
- (long)blk_rq_pos(fd_req), err);
- swim3_end_request_cur(-EIO);
+ swim3_err("Error %sing block %ld (err=%x)\n",
+ rq_data_dir(req) == WRITE? "writ": "read",
+ (long)blk_rq_pos(req), err);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
}
} else {
if ((stat & ACTIVE) == 0 || resid != 0) {
/* musta been an error */
- printk(KERN_ERR "swim3: fd dma: stat=%x resid=%d\n", stat, resid);
- printk(KERN_ERR " state=%d, dir=%x, intr=%x, err=%x\n",
- fs->state, rq_data_dir(fd_req), intr, err);
- swim3_end_request_cur(-EIO);
+ swim3_err("fd dma error: stat=%x resid=%d\n", stat, resid);
+ swim3_err(" state=%d, dir=%x, intr=%x, err=%x\n",
+ fs->state, rq_data_dir(req), intr, err);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
break;
}
- if (swim3_end_request(0, fs->scount << 9)) {
+ fs->retries = 0;
+ if (swim3_end_request(fs, 0, fs->scount << 9)) {
fs->req_sector += fs->scount;
if (fs->req_sector > fs->secpertrack) {
fs->req_sector -= fs->secpertrack;
start_request(fs);
break;
default:
- printk(KERN_ERR "swim3: don't know what to do in state %d\n", fs->state);
+ swim3_err("Don't know what to do in state %d\n", fs->state);
}
+ spin_unlock_irqrestore(&swim3_lock, flags);
return IRQ_HANDLED;
}
}
*/
+/* Called under the mutex to grab exclusive access to a drive */
static int grab_drive(struct floppy_state *fs, enum swim_state state,
int interruptible)
{
unsigned long flags;
- spin_lock_irqsave(&fs->lock, flags);
- if (fs->state != idle) {
+ swim3_dbg("%s", "-> grab drive\n");
+
+ spin_lock_irqsave(&swim3_lock, flags);
+ if (fs->state != idle && fs->state != available) {
++fs->wanted;
while (fs->state != available) {
+ spin_unlock_irqrestore(&swim3_lock, flags);
if (interruptible && signal_pending(current)) {
--fs->wanted;
- spin_unlock_irqrestore(&fs->lock, flags);
return -EINTR;
}
interruptible_sleep_on(&fs->wait);
+ spin_lock_irqsave(&swim3_lock, flags);
}
--fs->wanted;
}
fs->state = state;
- spin_unlock_irqrestore(&fs->lock, flags);
+ spin_unlock_irqrestore(&swim3_lock, flags);
+
return 0;
}
{
unsigned long flags;
- spin_lock_irqsave(&fs->lock, flags);
+ swim3_dbg("%s", "-> release drive\n");
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->state = idle;
start_request(fs);
- spin_unlock_irqrestore(&fs->lock, flags);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static int fd_eject(struct floppy_state *fs)
{
struct floppy_state *fs = disk->private_data;
struct swim3 __iomem *sw = fs->swim3;
+
mutex_lock(&swim3_mutex);
if (fs->ref_count > 0 && --fs->ref_count == 0) {
swim3_action(fs, MOTOR_OFF);
.revalidate_disk= floppy_revalidate,
};
+static void swim3_mb_event(struct macio_dev* mdev, int mb_state)
+{
+ struct floppy_state *fs = macio_get_drvdata(mdev);
+ struct swim3 __iomem *sw = fs->swim3;
+
+ if (!fs)
+ return;
+ if (mb_state != MB_FD)
+ return;
+
+ /* Clear state */
+ out_8(&sw->intr_enable, 0);
+ in_8(&sw->intr);
+ in_8(&sw->error);
+}
+
static int swim3_add_device(struct macio_dev *mdev, int index)
{
struct device_node *swim = mdev->ofdev.dev.of_node;
struct floppy_state *fs = &floppy_states[index];
int rc = -EBUSY;
+ /* Do this first for message macros */
+ memset(fs, 0, sizeof(*fs));
+ fs->mdev = mdev;
+ fs->index = index;
+
/* Check & Request resources */
if (macio_resource_count(mdev) < 2) {
- printk(KERN_WARNING "ifd%d: no address for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "No address in device-tree\n");
return -ENXIO;
}
- if (macio_irq_count(mdev) < 2) {
- printk(KERN_WARNING "fd%d: no intrs for device %s\n",
- index, swim->full_name);
+ if (macio_irq_count(mdev) < 1) {
+ swim3_err("%s", "No interrupt in device-tree\n");
+ return -ENXIO;
}
if (macio_request_resource(mdev, 0, "swim3 (mmio)")) {
- printk(KERN_ERR "fd%d: can't request mmio resource for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Can't request mmio resource\n");
return -EBUSY;
}
if (macio_request_resource(mdev, 1, "swim3 (dma)")) {
- printk(KERN_ERR "fd%d: can't request dma resource for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Can't request dma resource\n");
macio_release_resource(mdev, 0);
return -EBUSY;
}
if (mdev->media_bay == NULL)
pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 1);
- memset(fs, 0, sizeof(*fs));
- spin_lock_init(&fs->lock);
fs->state = idle;
fs->swim3 = (struct swim3 __iomem *)
ioremap(macio_resource_start(mdev, 0), 0x200);
if (fs->swim3 == NULL) {
- printk("fd%d: couldn't map registers for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Couldn't map mmio registers\n");
rc = -ENOMEM;
goto out_release;
}
fs->dma = (struct dbdma_regs __iomem *)
ioremap(macio_resource_start(mdev, 1), 0x200);
if (fs->dma == NULL) {
- printk("fd%d: couldn't map DMA for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Couldn't map dma registers\n");
iounmap(fs->swim3);
rc = -ENOMEM;
goto out_release;
fs->secpercyl = 36;
fs->secpertrack = 18;
fs->total_secs = 2880;
- fs->mdev = mdev;
init_waitqueue_head(&fs->wait);
fs->dma_cmd = (struct dbdma_cmd *) DBDMA_ALIGN(fs->dbdma_cmd_space);
memset(fs->dma_cmd, 0, 2 * sizeof(struct dbdma_cmd));
st_le16(&fs->dma_cmd[1].command, DBDMA_STOP);
+ if (mdev->media_bay == NULL || check_media_bay(mdev->media_bay) == MB_FD)
+ swim3_mb_event(mdev, MB_FD);
+
if (request_irq(fs->swim3_intr, swim3_interrupt, 0, "SWIM3", fs)) {
- printk(KERN_ERR "fd%d: couldn't request irq %d for %s\n",
- index, fs->swim3_intr, swim->full_name);
+ swim3_err("%s", "Couldn't request interrupt\n");
pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 0);
goto out_unmap;
return -EBUSY;
}
-/*
- if (request_irq(fs->dma_intr, fd_dma_interrupt, 0, "SWIM3-dma", fs)) {
- printk(KERN_ERR "Couldn't get irq %d for SWIM3 DMA",
- fs->dma_intr);
- return -EBUSY;
- }
-*/
init_timer(&fs->timeout);
- printk(KERN_INFO "fd%d: SWIM3 floppy controller %s\n", floppy_count,
+ swim3_info("SWIM3 floppy controller %s\n",
mdev->media_bay ? "in media bay" : "");
return 0;
static int __devinit swim3_attach(struct macio_dev *mdev, const struct of_device_id *match)
{
- int i, rc;
struct gendisk *disk;
+ int index, rc;
+
+ index = floppy_count++;
+ if (index >= MAX_FLOPPIES)
+ return -ENXIO;
/* Add the drive */
- rc = swim3_add_device(mdev, floppy_count);
+ rc = swim3_add_device(mdev, index);
if (rc)
return rc;
+ /* Now register that disk. Same comment about failure handling */
+ disk = disks[index] = alloc_disk(1);
+ if (disk == NULL)
+ return -ENOMEM;
+ disk->queue = blk_init_queue(do_fd_request, &swim3_lock);
+ if (disk->queue == NULL) {
+ put_disk(disk);
+ return -ENOMEM;
+ }
+ disk->queue->queuedata = &floppy_states[index];
- /* Now create the queue if not there yet */
- if (swim3_queue == NULL) {
+ if (index == 0) {
/* If we failed, there isn't much we can do as the driver is still
* too dumb to remove the device, just bail out
*/
if (register_blkdev(FLOPPY_MAJOR, "fd"))
return 0;
- swim3_queue = blk_init_queue(do_fd_request, &swim3_lock);
- if (swim3_queue == NULL) {
- unregister_blkdev(FLOPPY_MAJOR, "fd");
- return 0;
- }
}
- /* Now register that disk. Same comment about failure handling */
- i = floppy_count++;
- disk = disks[i] = alloc_disk(1);
- if (disk == NULL)
- return 0;
-
disk->major = FLOPPY_MAJOR;
- disk->first_minor = i;
+ disk->first_minor = index;
disk->fops = &floppy_fops;
- disk->private_data = &floppy_states[i];
- disk->queue = swim3_queue;
+ disk->private_data = &floppy_states[index];
disk->flags |= GENHD_FL_REMOVABLE;
- sprintf(disk->disk_name, "fd%d", i);
+ sprintf(disk->disk_name, "fd%d", index);
set_capacity(disk, 2880);
add_disk(disk);
.of_match_table = swim3_match,
},
.probe = swim3_attach,
+#ifdef CONFIG_PMAC_MEDIABAY
+ .mediabay_event = swim3_mb_event,
+#endif
#if 0
.suspend = swim3_suspend,
.resume = swim3_resume,
#define IPMI_WDOG_SET_TIMER 0x24
#define IPMI_WDOG_GET_TIMER 0x25
+#define IPMI_WDOG_TIMER_NOT_INIT_RESP 0x80
+
/* These are here until the real ones get into the watchdog.h interface. */
#ifndef WDIOC_GETTIMEOUT
#define WDIOC_GETTIMEOUT _IOW(WATCHDOG_IOCTL_BASE, 20, int)
struct kernel_ipmi_msg msg;
int rv;
struct ipmi_system_interface_addr addr;
+ int timeout_retries = 0;
if (ipmi_ignore_heartbeat)
return 0;
mutex_lock(&heartbeat_lock);
+restart:
atomic_set(&heartbeat_tofree, 2);
/*
/* Wait for the heartbeat to be sent. */
wait_for_completion(&heartbeat_wait);
- if (heartbeat_recv_msg.msg.data[0] != 0) {
+ if (heartbeat_recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP) {
+ timeout_retries++;
+ if (timeout_retries > 3) {
+ printk(KERN_ERR PFX ": Unable to restore the IPMI"
+ " watchdog's settings, giving up.\n");
+ rv = -EIO;
+ goto out_unlock;
+ }
+
+ /*
+ * The timer was not initialized, that means the BMC was
+ * probably reset and lost the watchdog information. Attempt
+ * to restore the timer's info. Note that we still hold
+ * the heartbeat lock, to keep a heartbeat from happening
+ * in this process, so must say no heartbeat to avoid a
+ * deadlock on this mutex.
+ */
+ rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+ if (rv) {
+ printk(KERN_ERR PFX ": Unable to send the command to"
+ " set the watchdog's settings, giving up.\n");
+ goto out_unlock;
+ }
+
+ /* We might need a new heartbeat, so do it now */
+ goto restart;
+ } else if (heartbeat_recv_msg.msg.data[0] != 0) {
/*
* Got an error in the heartbeat response. It was already
* reported in ipmi_wdog_msg_handler, but we should return
rv = -EINVAL;
}
+out_unlock:
mutex_unlock(&heartbeat_lock);
return rv;
static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg,
void *handler_data)
{
- if (msg->msg.data[0] != 0) {
+ if (msg->msg.cmd == IPMI_WDOG_RESET_TIMER &&
+ msg->msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)
+ printk(KERN_INFO PFX "response: The IPMI controller appears"
+ " to have been reset, will attempt to reinitialize"
+ " the watchdog timer\n");
+ else if (msg->msg.data[0] != 0)
printk(KERN_ERR PFX "response: Error %x on cmd %x\n",
msg->msg.data[0],
msg->msg.cmd);
- }
ipmi_free_recv_msg(msg);
}
if (!arch_get_random_long(&v))
break;
- memcpy(buf, &v, chunk);
+ memcpy(p, &v, chunk);
p += chunk;
nbytes -= chunk;
}
else
op.config |= CFG_MID_FRAG;
- writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
- writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
- writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
- writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
- writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+ if (first_block) {
+ writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
+ writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
+ writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
+ writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
+ writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+ }
}
memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config));
-config ARCH_HAS_DEVFREQ
- bool
- depends on ARCH_HAS_OPP
- help
- Denotes that the architecture supports DEVFREQ. If the architecture
- supports multiple OPP entries per device and the frequency of the
- devices with OPPs may be altered dynamically, the architecture
- supports DEVFREQ.
-
menuconfig PM_DEVFREQ
bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
- depends on PM_OPP && ARCH_HAS_DEVFREQ
help
- With OPP support, a device may have a list of frequencies and
- voltages available. DEVFREQ, a generic DVFS framework can be
- registered for a device with OPP support in order to let the
- governor provided to DEVFREQ choose an operating frequency
- based on the OPP's list and the policy given with DEVFREQ.
+ A device may have a list of frequencies and voltages available.
+ devfreq, a generic DVFS framework can be registered for a device
+ in order to let the governor provided to devfreq choose an
+ operating frequency based on the device driver's policy.
- Each device may have its own governor and policy. DEVFREQ can
+ Each device may have its own governor and policy. Devfreq can
reevaluate the device state periodically and/or based on the
- OPP list changes (each frequency/voltage pair in OPP may be
- disabled or enabled).
+ notification to "nb", a notifier block, of devfreq.
- Like some CPUs with CPUFREQ, a device may have multiple clocks.
+ Like some CPUs with CPUfreq, a device may have multiple clocks.
However, because the clock frequencies of a single device are
- determined by the single device's state, an instance of DEVFREQ
+ determined by the single device's state, an instance of devfreq
is attached to a single device and returns a "representative"
- clock frequency from the OPP of the device, which is also attached
- to a device by 1-to-1. The device registering DEVFREQ takes the
- responsiblity to "interpret" the frequency listed in OPP and
+ clock frequency of the device, which is also attached
+ to a device by 1-to-1. The device registering devfreq takes the
+ responsiblity to "interpret" the representative frequency and
to set its every clock accordingly with the "target" callback
- given to DEVFREQ.
+ given to devfreq.
+
+ When OPP is used with the devfreq device, it is recommended to
+ register devfreq's nb to the OPP's notifier head. If OPP is
+ used with the devfreq device, you may use OPP helper
+ functions defined in devfreq.h.
if PM_DEVFREQ
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/stat.h>
#include <linux/opp.h>
#include <linux/devfreq.h>
#include <linux/workqueue.h>
*/
int devfreq_remove_device(struct devfreq *devfreq)
{
+ bool central_polling;
+
if (!devfreq)
return -EINVAL;
- if (!devfreq->governor->no_central_polling) {
+ central_polling = !devfreq->governor->no_central_polling;
+
+ if (central_polling) {
mutex_lock(&devfreq_list_lock);
while (wait_remove_device == devfreq) {
mutex_unlock(&devfreq_list_lock);
mutex_lock(&devfreq->lock);
_remove_devfreq(devfreq, false); /* it unlocks devfreq->lock */
- if (!devfreq->governor->no_central_polling)
+ if (central_polling)
mutex_unlock(&devfreq_list_lock);
return 0;
config MX3_IPU
bool "MX3x Image Processing Unit support"
- depends on ARCH_MX3
+ depends on SOC_IMX31 ||Â SOC_IMX35
select DMA_ENGINE
default y
help
config IMX_SDMA
tristate "i.MX SDMA support"
- depends on ARCH_MX25 || ARCH_MX3 || ARCH_MX5
+ depends on ARCH_MX25 || SOC_IMX31 ||Â SOC_IMX35 || ARCH_MX5
select DMA_ENGINE
help
Support the i.MX SDMA engine. This engine is integrated into
{ .compatible = "fsl,p1020-memory-controller", },
{ .compatible = "fsl,p1021-memory-controller", },
{ .compatible = "fsl,p2020-memory-controller", },
- { .compatible = "fsl,p4080-memory-controller", },
+ { .compatible = "fsl,qoriq-memory-controller", },
{},
};
MODULE_DEVICE_TABLE(of, mpc85xx_mc_err_of_match);
}
/**
- * dmi_name_in_vendors - Check if string is anywhere in the DMI vendor information.
+ * dmi_name_in_vendors - Check if string is in the DMI system or board vendor name
* @str: Case sensitive Name
*/
int dmi_name_in_vendors(const char *str)
{
- static int fields[] = { DMI_BIOS_VENDOR, DMI_BIOS_VERSION, DMI_SYS_VENDOR,
- DMI_PRODUCT_NAME, DMI_PRODUCT_VERSION, DMI_BOARD_VENDOR,
- DMI_BOARD_NAME, DMI_BOARD_VERSION, DMI_NONE };
+ static int fields[] = { DMI_SYS_VENDOR, DMI_BOARD_VENDOR, DMI_NONE };
int i;
for (i = 0; fields[i] != DMI_NONE; i++) {
int f = fields[i];
}
static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
- struct timespec *timespec, struct pstore_info *psi)
+ struct timespec *timespec,
+ char **buf, struct pstore_info *psi)
{
efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
struct efivars *efivars = psi->data;
timespec->tv_nsec = 0;
get_var_data_locked(efivars, &efivars->walk_entry->var);
size = efivars->walk_entry->var.DataSize;
- memcpy(psi->buf, efivars->walk_entry->var.Data, size);
+ *buf = kmalloc(size, GFP_KERNEL);
+ if (*buf == NULL)
+ return -ENOMEM;
+ memcpy(*buf, efivars->walk_entry->var.Data,
+ size);
efivars->walk_entry = list_entry(efivars->walk_entry->list.next,
struct efivar_entry, list);
return size;
}
static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
- struct timespec *time, struct pstore_info *psi)
+ struct timespec *timespec,
+ char **buf, struct pstore_info *psi)
{
return -1;
}
ibft_cleanup();
}
+#ifdef CONFIG_ACPI
+static const struct {
+ char *sign;
+} ibft_signs[] = {
+ /*
+ * One spec says "IBFT", the other says "iBFT". We have to check
+ * for both.
+ */
+ { ACPI_SIG_IBFT },
+ { "iBFT" },
+};
+
+static void __init acpi_find_ibft_region(void)
+{
+ int i;
+ struct acpi_table_header *table = NULL;
+
+ if (acpi_disabled)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(ibft_signs) && !ibft_addr; i++) {
+ acpi_get_table(ibft_signs[i].sign, 0, &table);
+ ibft_addr = (struct acpi_table_ibft *)table;
+ }
+}
+#else
+static void __init acpi_find_ibft_region(void)
+{
+}
+#endif
+
/*
* ibft_init() - creates sysfs tree entries for the iBFT data.
*/
{
int rc = 0;
+ /*
+ As on UEFI systems the setup_arch()/find_ibft_region()
+ is called before ACPI tables are parsed and it only does
+ legacy finding.
+ */
+ if (!ibft_addr)
+ acpi_find_ibft_region();
+
if (ibft_addr) {
- printk(KERN_INFO "iBFT detected at 0x%llx.\n",
- (u64)isa_virt_to_bus(ibft_addr));
+ pr_info("iBFT detected.\n");
rc = ibft_check_device();
if (rc)
static const struct {
char *sign;
} ibft_signs[] = {
-#ifdef CONFIG_ACPI
- /*
- * One spec says "IBFT", the other says "iBFT". We have to check
- * for both.
- */
- { ACPI_SIG_IBFT },
-#endif
{ "iBFT" },
{ "BIFT" }, /* Broadcom iSCSI Offload */
};
#define VGA_MEM 0xA0000 /* VGA buffer */
#define VGA_SIZE 0x20000 /* 128kB */
-#ifdef CONFIG_ACPI
-static int __init acpi_find_ibft(struct acpi_table_header *header)
-{
- ibft_addr = (struct acpi_table_ibft *)header;
- return 0;
-}
-#endif /* CONFIG_ACPI */
-
static int __init find_ibft_in_mem(void)
{
unsigned long pos;
* the table cannot be valid. */
if (pos + len <= (IBFT_END-1)) {
ibft_addr = (struct acpi_table_ibft *)virt;
+ pr_info("iBFT found at 0x%lx.\n", pos);
goto done;
}
}
*/
unsigned long __init find_ibft_region(unsigned long *sizep)
{
-#ifdef CONFIG_ACPI
- int i;
-#endif
ibft_addr = NULL;
-#ifdef CONFIG_ACPI
- for (i = 0; i < ARRAY_SIZE(ibft_signs) && !ibft_addr; i++)
- acpi_table_parse(ibft_signs[i].sign, acpi_find_ibft);
-#endif /* CONFIG_ACPI */
-
/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
* only use ACPI for this */
- if (!ibft_addr && !efi_enabled)
+ if (!efi_enabled)
find_ibft_in_mem();
if (ibft_addr) {
#include <linux/module.h>
#include <linux/sigma.h>
-/* Return: 0==OK, <0==error, =1 ==no more actions */
+static size_t sigma_action_size(struct sigma_action *sa)
+{
+ size_t payload = 0;
+
+ switch (sa->instr) {
+ case SIGMA_ACTION_WRITEXBYTES:
+ case SIGMA_ACTION_WRITESINGLE:
+ case SIGMA_ACTION_WRITESAFELOAD:
+ payload = sigma_action_len(sa);
+ break;
+ default:
+ break;
+ }
+
+ payload = ALIGN(payload, 2);
+
+ return payload + sizeof(struct sigma_action);
+}
+
+/*
+ * Returns a negative error value in case of an error, 0 if processing of
+ * the firmware should be stopped after this action, 1 otherwise.
+ */
static int
-process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw)
+process_sigma_action(struct i2c_client *client, struct sigma_action *sa)
{
- struct sigma_action *sa = (void *)(ssfw->fw->data + ssfw->pos);
size_t len = sigma_action_len(sa);
- int ret = 0;
+ int ret;
pr_debug("%s: instr:%i addr:%#x len:%zu\n", __func__,
sa->instr, sa->addr, len);
case SIGMA_ACTION_WRITEXBYTES:
case SIGMA_ACTION_WRITESINGLE:
case SIGMA_ACTION_WRITESAFELOAD:
- if (ssfw->fw->size < ssfw->pos + len)
- return -EINVAL;
ret = i2c_master_send(client, (void *)&sa->addr, len);
if (ret < 0)
return -EINVAL;
break;
-
case SIGMA_ACTION_DELAY:
- ret = 0;
udelay(len);
len = 0;
break;
-
case SIGMA_ACTION_END:
- return 1;
-
+ return 0;
default:
return -EINVAL;
}
- /* when arrive here ret=0 or sent data */
- ssfw->pos += sigma_action_size(sa, len);
- return ssfw->pos == ssfw->fw->size;
+ return 1;
}
static int
process_sigma_actions(struct i2c_client *client, struct sigma_firmware *ssfw)
{
- pr_debug("%s: processing %p\n", __func__, ssfw);
+ struct sigma_action *sa;
+ size_t size;
+ int ret;
+
+ while (ssfw->pos + sizeof(*sa) <= ssfw->fw->size) {
+ sa = (struct sigma_action *)(ssfw->fw->data + ssfw->pos);
+
+ size = sigma_action_size(sa);
+ ssfw->pos += size;
+ if (ssfw->pos > ssfw->fw->size || size == 0)
+ break;
+
+ ret = process_sigma_action(client, sa);
- while (1) {
- int ret = process_sigma_action(client, ssfw);
pr_debug("%s: action returned %i\n", __func__, ret);
- if (ret == 1)
- return 0;
- else if (ret)
+
+ if (ret <= 0)
return ret;
}
+
+ if (ssfw->pos != ssfw->fw->size)
+ return -EINVAL;
+
+ return 0;
}
int process_sigma_firmware(struct i2c_client *client, const char *name)
/* then verify the header */
ret = -EINVAL;
- if (fw->size < sizeof(*ssfw_head))
+
+ /*
+ * Reject too small or unreasonable large files. The upper limit has been
+ * chosen a bit arbitrarily, but it should be enough for all practical
+ * purposes and having the limit makes it easier to avoid integer
+ * overflows later in the loading process.
+ */
+ if (fw->size < sizeof(*ssfw_head) || fw->size >= 0x4000000)
goto done;
ssfw_head = (void *)fw->data;
if (memcmp(ssfw_head->magic, SIGMA_MAGIC, ARRAY_SIZE(ssfw_head->magic)))
goto done;
- crc = crc32(0, fw->data, fw->size);
+ crc = crc32(0, fw->data + sizeof(*ssfw_head),
+ fw->size - sizeof(*ssfw_head));
pr_debug("%s: crc=%x\n", __func__, crc);
- if (crc != ssfw_head->crc)
+ if (crc != le32_to_cpu(ssfw_head->crc))
goto done;
ssfw.pos = sizeof(*ssfw_head);
obj-$(CONFIG_GPIO_EP93XX) += gpio-ep93xx.o
obj-$(CONFIG_GPIO_IT8761E) += gpio-it8761e.o
obj-$(CONFIG_GPIO_JANZ_TTL) += gpio-janz-ttl.o
-obj-$(CONFIG_MACH_KS8695) += gpio-ks8695.o
+obj-$(CONFIG_ARCH_KS8695) += gpio-ks8695.o
obj-$(CONFIG_GPIO_LANGWELL) += gpio-langwell.o
obj-$(CONFIG_ARCH_LPC32XX) += gpio-lpc32xx.o
obj-$(CONFIG_GPIO_MAX730X) += gpio-max730x.o
#include <linux/mfd/da9052/da9052.h>
#include <linux/mfd/da9052/reg.h>
#include <linux/mfd/da9052/pdata.h>
-#include <linux/mfd/da9052/gpio.h>
#define DA9052_INPUT 1
#define DA9052_OUTPUT_OPENDRAIN 2
#define DA9052_GPIO_MASK_UPPER_NIBBLE 0xF0
#define DA9052_GPIO_MASK_LOWER_NIBBLE 0x0F
#define DA9052_GPIO_NIBBLE_SHIFT 4
+#define DA9052_IRQ_GPI0 16
+#define DA9052_GPIO_ODD_SHIFT 7
+#define DA9052_GPIO_EVEN_SHIFT 3
struct da9052_gpio {
struct da9052 *da9052;
static void da9052_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
{
struct da9052_gpio *gpio = to_da9052_gpio(gc);
- unsigned char register_value = 0;
int ret;
if (da9052_gpio_port_odd(offset)) {
- if (value) {
- register_value = DA9052_GPIO_ODD_PORT_MODE;
ret = da9052_reg_update(gpio->da9052, (offset >> 1) +
DA9052_GPIO_0_1_REG,
DA9052_GPIO_ODD_PORT_MODE,
- register_value);
+ value << DA9052_GPIO_ODD_SHIFT);
if (ret != 0)
dev_err(gpio->da9052->dev,
"Failed to updated gpio odd reg,%d",
ret);
- }
} else {
- if (value) {
- register_value = DA9052_GPIO_EVEN_PORT_MODE;
ret = da9052_reg_update(gpio->da9052, (offset >> 1) +
DA9052_GPIO_0_1_REG,
DA9052_GPIO_EVEN_PORT_MODE,
- register_value);
+ value << DA9052_GPIO_EVEN_SHIFT);
if (ret != 0)
dev_err(gpio->da9052->dev,
"Failed to updated gpio even reg,%d",
ret);
- }
}
}
.direction_input = da9052_gpio_direction_input,
.direction_output = da9052_gpio_direction_output,
.to_irq = da9052_gpio_to_irq,
- .can_sleep = 1;
- .ngpio = 16;
- .base = -1;
+ .can_sleep = 1,
+ .ngpio = 16,
+ .base = -1,
};
static int __devinit da9052_gpio_probe(struct platform_device *pdev)
&chip->reg->regs[chip->ch].imask);
}
+static void ioh_irq_disable(struct irq_data *d)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct ioh_gpio *chip = gc->private;
+ unsigned long flags;
+ u32 ien;
+
+ spin_lock_irqsave(&chip->spinlock, flags);
+ ien = ioread32(&chip->reg->regs[chip->ch].ien);
+ ien &= ~(1 << (d->irq - chip->irq_base));
+ iowrite32(ien, &chip->reg->regs[chip->ch].ien);
+ spin_unlock_irqrestore(&chip->spinlock, flags);
+}
+
+static void ioh_irq_enable(struct irq_data *d)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct ioh_gpio *chip = gc->private;
+ unsigned long flags;
+ u32 ien;
+
+ spin_lock_irqsave(&chip->spinlock, flags);
+ ien = ioread32(&chip->reg->regs[chip->ch].ien);
+ ien |= 1 << (d->irq - chip->irq_base);
+ iowrite32(ien, &chip->reg->regs[chip->ch].ien);
+ spin_unlock_irqrestore(&chip->spinlock, flags);
+}
+
static irqreturn_t ioh_gpio_handler(int irq, void *dev_id)
{
struct ioh_gpio *chip = dev_id;
int i, j;
int ret = IRQ_NONE;
- for (i = 0; i < 8; i++) {
+ for (i = 0; i < 8; i++, chip++) {
reg_val = ioread32(&chip->reg->regs[i].istatus);
for (j = 0; j < num_ports[i]; j++) {
if (reg_val & BIT(j)) {
ct->chip.irq_mask = ioh_irq_mask;
ct->chip.irq_unmask = ioh_irq_unmask;
ct->chip.irq_set_type = ioh_irq_type;
+ ct->chip.irq_disable = ioh_irq_disable;
+ ct->chip.irq_enable = ioh_irq_enable;
irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
IRQ_NOREQUEST | IRQ_NOPROBE, 0);
return 0;
}
+static int mpc5121_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
+{
+ /* GPIO 28..31 are input only on MPC5121 */
+ if (gpio >= 28)
+ return -EINVAL;
+
+ return mpc8xxx_gpio_dir_out(gc, gpio, val);
+}
+
static int mpc8xxx_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
{
struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
mm_gc->save_regs = mpc8xxx_gpio_save_regs;
gc->ngpio = MPC8XXX_GPIO_PINS;
gc->direction_input = mpc8xxx_gpio_dir_in;
- gc->direction_output = mpc8xxx_gpio_dir_out;
- if (of_device_is_compatible(np, "fsl,mpc8572-gpio"))
- gc->get = mpc8572_gpio_get;
- else
- gc->get = mpc8xxx_gpio_get;
+ gc->direction_output = of_device_is_compatible(np, "fsl,mpc5121-gpio") ?
+ mpc5121_gpio_dir_out : mpc8xxx_gpio_dir_out;
+ gc->get = of_device_is_compatible(np, "fsl,mpc8572-gpio") ?
+ mpc8572_gpio_get : mpc8xxx_gpio_get;
gc->set = mpc8xxx_gpio_set;
gc->to_irq = mpc8xxx_gpio_to_irq;
* Translate OpenFirmware node properties into platform_data
* WARNING: This is DEPRECATED and will be removed eventually!
*/
-void
+static void
pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert)
{
struct device_node *node;
*invert = *val;
}
#else
-void
+static void
pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert)
{
*gpio_base = -1;
int ret, irq, i;
static DECLARE_BITMAP(init_irq, NR_IRQS);
- pdata = dev->dev.platform_data;
- if (pdata == NULL)
- return -ENODEV;
-
chip = kzalloc(sizeof(*chip), GFP_KERNEL);
if (chip == NULL)
return -ENOMEM;
}
if (num_clips && clips_ptr) {
+ if (num_clips < 0 || num_clips > DRM_MODE_FB_DIRTY_MAX_CLIPS) {
+ ret = -EINVAL;
+ goto out_err1;
+ }
clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
if (!clips) {
ret = -ENOMEM;
EXPORT_SYMBOL(drm_crtc_helper_set_mode);
+static int
+drm_crtc_helper_disable(struct drm_crtc *crtc)
+{
+ struct drm_device *dev = crtc->dev;
+ struct drm_connector *connector;
+ struct drm_encoder *encoder;
+
+ /* Decouple all encoders and their attached connectors from this crtc */
+ list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+ if (encoder->crtc != crtc)
+ continue;
+
+ list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ if (connector->encoder != encoder)
+ continue;
+
+ connector->encoder = NULL;
+ }
+ }
+
+ drm_helper_disable_unused_functions(dev);
+ return 0;
+}
+
/**
* drm_crtc_helper_set_config - set a new config from userspace
* @crtc: CRTC to setup
(int)set->num_connectors, set->x, set->y);
} else {
DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id);
- set->mode = NULL;
- set->num_connectors = 0;
+ return drm_crtc_helper_disable(set->crtc);
}
dev = set->crtc->dev;
/* Prevent vblank irq processing while disabling vblank irqs,
* so no updates of timestamps or count can happen after we've
* disabled. Needed to prevent races in case of delayed irq's.
- * Disable preemption, so vblank_time_lock is held as short as
- * possible, even under a kernel with PREEMPT_RT patches.
*/
- preempt_disable();
spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
dev->driver->disable_vblank(dev, crtc);
clear_vblank_timestamps(dev, crtc);
spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
- preempt_enable();
}
static void vblank_disable_fn(unsigned long arg)
spin_lock_irqsave(&dev->vbl_lock, irqflags);
/* Going from 0->1 means we have to enable interrupts again */
if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
- /* Disable preemption while holding vblank_time_lock. Do
- * it explicitely to guard against PREEMPT_RT kernel.
- */
- preempt_disable();
spin_lock_irqsave(&dev->vblank_time_lock, irqflags2);
if (!dev->vblank_enabled[crtc]) {
/* Enable vblank irqs under vblank_time_lock protection.
}
}
spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2);
- preempt_enable();
} else {
if (!dev->vblank_enabled[crtc]) {
atomic_dec(&dev->vblank_refcount[crtc]);
#include "drm.h"
#include "exynos_drm_drv.h"
+#include "exynos_drm_gem.h"
#include "exynos_drm_buf.h"
-static DEFINE_MUTEX(exynos_drm_buf_lock);
-
static int lowlevel_buffer_allocate(struct drm_device *dev,
- struct exynos_drm_buf_entry *entry)
+ struct exynos_drm_gem_buf *buffer)
{
DRM_DEBUG_KMS("%s\n", __FILE__);
- entry->vaddr = dma_alloc_writecombine(dev->dev, entry->size,
- (dma_addr_t *)&entry->paddr, GFP_KERNEL);
- if (!entry->paddr) {
+ buffer->kvaddr = dma_alloc_writecombine(dev->dev, buffer->size,
+ &buffer->dma_addr, GFP_KERNEL);
+ if (!buffer->kvaddr) {
DRM_ERROR("failed to allocate buffer.\n");
return -ENOMEM;
}
- DRM_DEBUG_KMS("allocated : vaddr(0x%x), paddr(0x%x), size(0x%x)\n",
- (unsigned int)entry->vaddr, entry->paddr, entry->size);
+ DRM_DEBUG_KMS("vaddr(0x%lx), dma_addr(0x%lx), size(0x%lx)\n",
+ (unsigned long)buffer->kvaddr,
+ (unsigned long)buffer->dma_addr,
+ buffer->size);
return 0;
}
static void lowlevel_buffer_deallocate(struct drm_device *dev,
- struct exynos_drm_buf_entry *entry)
+ struct exynos_drm_gem_buf *buffer)
{
DRM_DEBUG_KMS("%s.\n", __FILE__);
- if (entry->paddr && entry->vaddr && entry->size)
- dma_free_writecombine(dev->dev, entry->size, entry->vaddr,
- entry->paddr);
+ if (buffer->dma_addr && buffer->size)
+ dma_free_writecombine(dev->dev, buffer->size, buffer->kvaddr,
+ (dma_addr_t)buffer->dma_addr);
else
- DRM_DEBUG_KMS("entry data is null.\n");
+ DRM_DEBUG_KMS("buffer data are invalid.\n");
}
-struct exynos_drm_buf_entry *exynos_drm_buf_create(struct drm_device *dev,
+struct exynos_drm_gem_buf *exynos_drm_buf_create(struct drm_device *dev,
unsigned int size)
{
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
DRM_DEBUG_KMS("%s.\n", __FILE__);
+ DRM_DEBUG_KMS("desired size = 0x%x\n", size);
- entry = kzalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry) {
- DRM_ERROR("failed to allocate exynos_drm_buf_entry.\n");
+ buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+ if (!buffer) {
+ DRM_ERROR("failed to allocate exynos_drm_gem_buf.\n");
return ERR_PTR(-ENOMEM);
}
- entry->size = size;
+ buffer->size = size;
/*
* allocate memory region with size and set the memory information
- * to vaddr and paddr of a entry object.
+ * to vaddr and dma_addr of a buffer object.
*/
- if (lowlevel_buffer_allocate(dev, entry) < 0) {
- kfree(entry);
- entry = NULL;
+ if (lowlevel_buffer_allocate(dev, buffer) < 0) {
+ kfree(buffer);
+ buffer = NULL;
return ERR_PTR(-ENOMEM);
}
- return entry;
+ return buffer;
}
void exynos_drm_buf_destroy(struct drm_device *dev,
- struct exynos_drm_buf_entry *entry)
+ struct exynos_drm_gem_buf *buffer)
{
DRM_DEBUG_KMS("%s.\n", __FILE__);
- if (!entry) {
- DRM_DEBUG_KMS("entry is null.\n");
+ if (!buffer) {
+ DRM_DEBUG_KMS("buffer is null.\n");
return;
}
- lowlevel_buffer_deallocate(dev, entry);
+ lowlevel_buffer_deallocate(dev, buffer);
- kfree(entry);
- entry = NULL;
+ kfree(buffer);
+ buffer = NULL;
}
MODULE_AUTHOR("Inki Dae <inki.dae@samsung.com>");
#ifndef _EXYNOS_DRM_BUF_H_
#define _EXYNOS_DRM_BUF_H_
-/*
- * exynos drm buffer entry structure.
- *
- * @paddr: physical address of allocated memory.
- * @vaddr: kernel virtual address of allocated memory.
- * @size: size of allocated memory.
- */
-struct exynos_drm_buf_entry {
- dma_addr_t paddr;
- void __iomem *vaddr;
- unsigned int size;
-};
-
/* allocate physical memory. */
-struct exynos_drm_buf_entry *exynos_drm_buf_create(struct drm_device *dev,
+struct exynos_drm_gem_buf *exynos_drm_buf_create(struct drm_device *dev,
unsigned int size);
-/* get physical memory information of a drm framebuffer. */
-struct exynos_drm_buf_entry *exynos_drm_fb_get_buf(struct drm_framebuffer *fb);
+/* get memory information of a drm framebuffer. */
+struct exynos_drm_gem_buf *exynos_drm_fb_get_buf(struct drm_framebuffer *fb);
/* remove allocated physical memory. */
void exynos_drm_buf_destroy(struct drm_device *dev,
- struct exynos_drm_buf_entry *entry);
+ struct exynos_drm_gem_buf *buffer);
#endif
struct exynos_drm_connector {
struct drm_connector drm_connector;
+ uint32_t encoder_id;
+ struct exynos_drm_manager *manager;
};
/* convert exynos_video_timings to drm_display_mode */
DRM_DEBUG_KMS("%s\n", __FILE__);
mode->clock = timing->pixclock / 1000;
+ mode->vrefresh = timing->refresh;
mode->hdisplay = timing->xres;
mode->hsync_start = mode->hdisplay + timing->left_margin;
mode->vsync_start = mode->vdisplay + timing->upper_margin;
mode->vsync_end = mode->vsync_start + timing->vsync_len;
mode->vtotal = mode->vsync_end + timing->lower_margin;
+
+ if (timing->vmode & FB_VMODE_INTERLACED)
+ mode->flags |= DRM_MODE_FLAG_INTERLACE;
+
+ if (timing->vmode & FB_VMODE_DOUBLE)
+ mode->flags |= DRM_MODE_FLAG_DBLSCAN;
}
/* convert drm_display_mode to exynos_video_timings */
memset(timing, 0, sizeof(*timing));
timing->pixclock = mode->clock * 1000;
- timing->refresh = mode->vrefresh;
+ timing->refresh = drm_mode_vrefresh(mode);
timing->xres = mode->hdisplay;
timing->left_margin = mode->hsync_start - mode->hdisplay;
static int exynos_drm_connector_get_modes(struct drm_connector *connector)
{
- struct exynos_drm_manager *manager =
- exynos_drm_get_manager(connector->encoder);
- struct exynos_drm_display *display = manager->display;
+ struct exynos_drm_connector *exynos_connector =
+ to_exynos_connector(connector);
+ struct exynos_drm_manager *manager = exynos_connector->manager;
+ struct exynos_drm_display_ops *display_ops = manager->display_ops;
unsigned int count;
DRM_DEBUG_KMS("%s\n", __FILE__);
- if (!display) {
- DRM_DEBUG_KMS("display is null.\n");
+ if (!display_ops) {
+ DRM_DEBUG_KMS("display_ops is null.\n");
return 0;
}
* P.S. in case of lcd panel, count is always 1 if success
* because lcd panel has only one mode.
*/
- if (display->get_edid) {
+ if (display_ops->get_edid) {
int ret;
void *edid;
return 0;
}
- ret = display->get_edid(manager->dev, connector,
+ ret = display_ops->get_edid(manager->dev, connector,
edid, MAX_EDID);
if (ret < 0) {
DRM_ERROR("failed to get edid data.\n");
struct drm_display_mode *mode = drm_mode_create(connector->dev);
struct fb_videomode *timing;
- if (display->get_timing)
- timing = display->get_timing(manager->dev);
+ if (display_ops->get_timing)
+ timing = display_ops->get_timing(manager->dev);
else {
drm_mode_destroy(connector->dev, mode);
return 0;
static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
{
- struct exynos_drm_manager *manager =
- exynos_drm_get_manager(connector->encoder);
- struct exynos_drm_display *display = manager->display;
+ struct exynos_drm_connector *exynos_connector =
+ to_exynos_connector(connector);
+ struct exynos_drm_manager *manager = exynos_connector->manager;
+ struct exynos_drm_display_ops *display_ops = manager->display_ops;
struct fb_videomode timing;
int ret = MODE_BAD;
convert_to_video_timing(&timing, mode);
- if (display && display->check_timing)
- if (!display->check_timing(manager->dev, (void *)&timing))
+ if (display_ops && display_ops->check_timing)
+ if (!display_ops->check_timing(manager->dev, (void *)&timing))
ret = MODE_OK;
return ret;
struct drm_encoder *exynos_drm_best_encoder(struct drm_connector *connector)
{
+ struct drm_device *dev = connector->dev;
+ struct exynos_drm_connector *exynos_connector =
+ to_exynos_connector(connector);
+ struct drm_mode_object *obj;
+ struct drm_encoder *encoder;
+
DRM_DEBUG_KMS("%s\n", __FILE__);
- return connector->encoder;
+ obj = drm_mode_object_find(dev, exynos_connector->encoder_id,
+ DRM_MODE_OBJECT_ENCODER);
+ if (!obj) {
+ DRM_DEBUG_KMS("Unknown ENCODER ID %d\n",
+ exynos_connector->encoder_id);
+ return NULL;
+ }
+
+ encoder = obj_to_encoder(obj);
+
+ return encoder;
}
static struct drm_connector_helper_funcs exynos_connector_helper_funcs = {
static enum drm_connector_status
exynos_drm_connector_detect(struct drm_connector *connector, bool force)
{
- struct exynos_drm_manager *manager =
- exynos_drm_get_manager(connector->encoder);
- struct exynos_drm_display *display = manager->display;
+ struct exynos_drm_connector *exynos_connector =
+ to_exynos_connector(connector);
+ struct exynos_drm_manager *manager = exynos_connector->manager;
+ struct exynos_drm_display_ops *display_ops =
+ manager->display_ops;
enum drm_connector_status status = connector_status_disconnected;
DRM_DEBUG_KMS("%s\n", __FILE__);
- if (display && display->is_connected) {
- if (display->is_connected(manager->dev))
+ if (display_ops && display_ops->is_connected) {
+ if (display_ops->is_connected(manager->dev))
status = connector_status_connected;
else
status = connector_status_disconnected;
connector = &exynos_connector->drm_connector;
- switch (manager->display->type) {
+ switch (manager->display_ops->type) {
case EXYNOS_DISPLAY_TYPE_HDMI:
type = DRM_MODE_CONNECTOR_HDMIA;
+ connector->interlace_allowed = true;
+ connector->polled = DRM_CONNECTOR_POLL_HPD;
break;
default:
type = DRM_MODE_CONNECTOR_Unknown;
if (err)
goto err_connector;
+ exynos_connector->encoder_id = encoder->base.id;
+ exynos_connector->manager = manager;
connector->encoder = encoder;
+
err = drm_mode_connector_attach_encoder(connector, encoder);
if (err) {
DRM_ERROR("failed to attach a connector to a encoder\n");
#include "drmP.h"
#include "drm_crtc_helper.h"
+#include "exynos_drm_crtc.h"
#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
#include "exynos_drm_encoder.h"
+#include "exynos_drm_gem.h"
#include "exynos_drm_buf.h"
#define to_exynos_crtc(x) container_of(x, struct exynos_drm_crtc,\
drm_crtc)
-/*
- * Exynos specific crtc postion structure.
- *
- * @fb_x: offset x on a framebuffer to be displyed
- * - the unit is screen coordinates.
- * @fb_y: offset y on a framebuffer to be displayed
- * - the unit is screen coordinates.
- * @crtc_x: offset x on hardware screen.
- * @crtc_y: offset y on hardware screen.
- * @crtc_w: width of hardware screen.
- * @crtc_h: height of hardware screen.
- */
-struct exynos_drm_crtc_pos {
- unsigned int fb_x;
- unsigned int fb_y;
- unsigned int crtc_x;
- unsigned int crtc_y;
- unsigned int crtc_w;
- unsigned int crtc_h;
-};
-
/*
* Exynos specific crtc structure.
*
exynos_drm_fn_encoder(crtc, overlay,
exynos_drm_encoder_crtc_mode_set);
- exynos_drm_fn_encoder(crtc, NULL, exynos_drm_encoder_crtc_commit);
+ exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+ exynos_drm_encoder_crtc_commit);
}
-static int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
- struct drm_framebuffer *fb,
- struct drm_display_mode *mode,
- struct exynos_drm_crtc_pos *pos)
+int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
+ struct drm_framebuffer *fb,
+ struct drm_display_mode *mode,
+ struct exynos_drm_crtc_pos *pos)
{
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
unsigned int actual_w;
unsigned int actual_h;
- entry = exynos_drm_fb_get_buf(fb);
- if (!entry) {
- DRM_LOG_KMS("entry is null.\n");
+ buffer = exynos_drm_fb_get_buf(fb);
+ if (!buffer) {
+ DRM_LOG_KMS("buffer is null.\n");
return -EFAULT;
}
- overlay->paddr = entry->paddr;
- overlay->vaddr = entry->vaddr;
+ overlay->dma_addr = buffer->dma_addr;
+ overlay->vaddr = buffer->kvaddr;
- DRM_DEBUG_KMS("vaddr = 0x%lx, paddr = 0x%lx\n",
+ DRM_DEBUG_KMS("vaddr = 0x%lx, dma_addr = 0x%lx\n",
(unsigned long)overlay->vaddr,
- (unsigned long)overlay->paddr);
+ (unsigned long)overlay->dma_addr);
actual_w = min((mode->hdisplay - pos->crtc_x), pos->crtc_w);
actual_h = min((mode->vdisplay - pos->crtc_y), pos->crtc_h);
static void exynos_drm_crtc_dpms(struct drm_crtc *crtc, int mode)
{
- DRM_DEBUG_KMS("%s\n", __FILE__);
+ struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
- /* TODO */
+ DRM_DEBUG_KMS("crtc[%d] mode[%d]\n", crtc->base.id, mode);
+
+ switch (mode) {
+ case DRM_MODE_DPMS_ON:
+ exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+ exynos_drm_encoder_crtc_commit);
+ break;
+ case DRM_MODE_DPMS_STANDBY:
+ case DRM_MODE_DPMS_SUSPEND:
+ case DRM_MODE_DPMS_OFF:
+ /* TODO */
+ exynos_drm_fn_encoder(crtc, NULL,
+ exynos_drm_encoder_crtc_disable);
+ break;
+ default:
+ DRM_DEBUG_KMS("unspecified mode %d\n", mode);
+ break;
+ }
}
static void exynos_drm_crtc_prepare(struct drm_crtc *crtc)
static void exynos_drm_crtc_commit(struct drm_crtc *crtc)
{
+ struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+
DRM_DEBUG_KMS("%s\n", __FILE__);
- /* drm framework doesn't check NULL. */
+ exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+ exynos_drm_encoder_crtc_commit);
}
static bool
int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int crtc);
void exynos_drm_crtc_disable_vblank(struct drm_device *dev, int crtc);
+/*
+ * Exynos specific crtc postion structure.
+ *
+ * @fb_x: offset x on a framebuffer to be displyed
+ * - the unit is screen coordinates.
+ * @fb_y: offset y on a framebuffer to be displayed
+ * - the unit is screen coordinates.
+ * @crtc_x: offset x on hardware screen.
+ * @crtc_y: offset y on hardware screen.
+ * @crtc_w: width of hardware screen.
+ * @crtc_h: height of hardware screen.
+ */
+struct exynos_drm_crtc_pos {
+ unsigned int fb_x;
+ unsigned int fb_y;
+ unsigned int crtc_x;
+ unsigned int crtc_y;
+ unsigned int crtc_w;
+ unsigned int crtc_h;
+};
+
+int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
+ struct drm_framebuffer *fb,
+ struct drm_display_mode *mode,
+ struct exynos_drm_crtc_pos *pos);
#endif
#include "drmP.h"
#include "drm.h"
+#include "drm_crtc_helper.h"
#include <drm/exynos_drm.h>
drm_mode_config_init(dev);
+ /* init kms poll for handling hpd */
+ drm_kms_helper_poll_init(dev);
+
exynos_drm_mode_config_init(dev);
/*
exynos_drm_fbdev_fini(dev);
exynos_drm_device_unregister(dev);
drm_vblank_cleanup(dev);
+ drm_kms_helper_poll_fini(dev);
drm_mode_config_cleanup(dev);
kfree(dev->dev_private);
#ifndef _EXYNOS_DRM_DRV_H_
#define _EXYNOS_DRM_DRV_H_
+#include <linux/module.h>
#include "drm.h"
#define MAX_CRTC 2
* @scan_flag: interlace or progressive way.
* (it could be DRM_MODE_FLAG_*)
* @bpp: pixel size.(in bit)
- * @paddr: bus(accessed by dma) physical memory address to this overlay
- * and this is physically continuous.
+ * @dma_addr: bus(accessed by dma) address to the memory region allocated
+ * for a overlay.
* @vaddr: virtual memory addresss to this overlay.
* @default_win: a window to be enabled.
* @color_key: color key on or off.
unsigned int scan_flag;
unsigned int bpp;
unsigned int pitch;
- dma_addr_t paddr;
+ dma_addr_t dma_addr;
void __iomem *vaddr;
bool default_win;
* @check_timing: check if timing is valid or not.
* @power_on: display device on or off.
*/
-struct exynos_drm_display {
+struct exynos_drm_display_ops {
enum exynos_drm_output_type type;
bool (*is_connected)(struct device *dev);
int (*get_edid)(struct device *dev, struct drm_connector *connector,
* @mode_set: convert drm_display_mode to hw specific display mode and
* would be called by encoder->mode_set().
* @commit: set current hw specific display mode to hw.
+ * @disable: disable hardware specific display mode.
* @enable_vblank: specific driver callback for enabling vblank interrupt.
* @disable_vblank: specific driver callback for disabling vblank interrupt.
*/
struct exynos_drm_manager_ops {
void (*mode_set)(struct device *subdrv_dev, void *mode);
void (*commit)(struct device *subdrv_dev);
+ void (*disable)(struct device *subdrv_dev);
int (*enable_vblank)(struct device *subdrv_dev);
void (*disable_vblank)(struct device *subdrv_dev);
};
int pipe;
struct exynos_drm_manager_ops *ops;
struct exynos_drm_overlay_ops *overlay_ops;
- struct exynos_drm_display *display;
+ struct exynos_drm_display_ops *display_ops;
};
/*
struct drm_device *dev = encoder->dev;
struct drm_connector *connector;
struct exynos_drm_manager *manager = exynos_drm_get_manager(encoder);
+ struct exynos_drm_manager_ops *manager_ops = manager->ops;
DRM_DEBUG_KMS("%s, encoder dpms: %d\n", __FILE__, mode);
+ switch (mode) {
+ case DRM_MODE_DPMS_ON:
+ if (manager_ops && manager_ops->commit)
+ manager_ops->commit(manager->dev);
+ break;
+ case DRM_MODE_DPMS_STANDBY:
+ case DRM_MODE_DPMS_SUSPEND:
+ case DRM_MODE_DPMS_OFF:
+ /* TODO */
+ if (manager_ops && manager_ops->disable)
+ manager_ops->disable(manager->dev);
+ break;
+ default:
+ DRM_ERROR("unspecified mode %d\n", mode);
+ break;
+ }
+
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
if (connector->encoder == encoder) {
- struct exynos_drm_display *display = manager->display;
+ struct exynos_drm_display_ops *display_ops =
+ manager->display_ops;
- if (display && display->power_on)
- display->power_on(manager->dev, mode);
+ DRM_DEBUG_KMS("connector[%d] dpms[%d]\n",
+ connector->base.id, mode);
+ if (display_ops && display_ops->power_on)
+ display_ops->power_on(manager->dev, mode);
}
}
}
{
struct exynos_drm_manager *manager = exynos_drm_get_manager(encoder);
struct exynos_drm_manager_ops *manager_ops = manager->ops;
- struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
DRM_DEBUG_KMS("%s\n", __FILE__);
if (manager_ops && manager_ops->commit)
manager_ops->commit(manager->dev);
-
- if (overlay_ops && overlay_ops->commit)
- overlay_ops->commit(manager->dev);
}
static struct drm_crtc *
{
struct drm_device *dev = crtc->dev;
struct drm_encoder *encoder;
+ struct exynos_drm_private *private = dev->dev_private;
+ struct exynos_drm_manager *manager;
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
- if (encoder->crtc != crtc)
- continue;
+ /*
+ * if crtc is detached from encoder, check pipe,
+ * otherwise check crtc attached to encoder
+ */
+ if (!encoder->crtc) {
+ manager = to_exynos_encoder(encoder)->manager;
+ if (manager->pipe < 0 ||
+ private->crtc[manager->pipe] != crtc)
+ continue;
+ } else {
+ if (encoder->crtc != crtc)
+ continue;
+ }
fn(encoder, data);
}
struct exynos_drm_manager *manager =
to_exynos_encoder(encoder)->manager;
struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+ int crtc = *(int *)data;
+
+ DRM_DEBUG_KMS("%s\n", __FILE__);
+
+ /*
+ * when crtc is detached from encoder, this pipe is used
+ * to select manager operation
+ */
+ manager->pipe = crtc;
- overlay_ops->commit(manager->dev);
+ if (overlay_ops && overlay_ops->commit)
+ overlay_ops->commit(manager->dev);
}
void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data)
struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
struct exynos_drm_overlay *overlay = data;
- overlay_ops->mode_set(manager->dev, overlay);
+ if (overlay_ops && overlay_ops->mode_set)
+ overlay_ops->mode_set(manager->dev, overlay);
+}
+
+void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data)
+{
+ struct exynos_drm_manager *manager =
+ to_exynos_encoder(encoder)->manager;
+ struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+
+ DRM_DEBUG_KMS("\n");
+
+ if (overlay_ops && overlay_ops->disable)
+ overlay_ops->disable(manager->dev);
+
+ /*
+ * crtc is already detached from encoder and last
+ * function for detaching is properly done, so
+ * clear pipe from manager to prevent repeated call
+ */
+ if (!encoder->crtc)
+ manager->pipe = -1;
}
MODULE_AUTHOR("Inki Dae <inki.dae@samsung.com>");
void exynos_drm_disable_vblank(struct drm_encoder *encoder, void *data);
void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data);
void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data);
#endif
#include "drmP.h"
#include "drm_crtc.h"
#include "drm_crtc_helper.h"
+#include "drm_fb_helper.h"
+#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
#include "exynos_drm_buf.h"
#include "exynos_drm_gem.h"
*
* @fb: drm framebuffer obejct.
* @exynos_gem_obj: exynos specific gem object containing a gem object.
- * @entry: pointer to exynos drm buffer entry object.
- * - containing only the information to physically continuous memory
- * region allocated at default framebuffer creation.
+ * @buffer: pointer to exynos_drm_gem_buffer object.
+ * - contain the memory information to memory region allocated
+ * at default framebuffer creation.
*/
struct exynos_drm_fb {
struct drm_framebuffer fb;
struct exynos_drm_gem_obj *exynos_gem_obj;
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
};
static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
* default framebuffer has no gem object so
* a buffer of the default framebuffer should be released at here.
*/
- if (!exynos_fb->exynos_gem_obj && exynos_fb->entry)
- exynos_drm_buf_destroy(fb->dev, exynos_fb->entry);
+ if (!exynos_fb->exynos_gem_obj && exynos_fb->buffer)
+ exynos_drm_buf_destroy(fb->dev, exynos_fb->buffer);
kfree(exynos_fb);
exynos_fb = NULL;
*/
if (!mode_cmd->handle) {
if (!file_priv) {
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
/*
* in case that file_priv is NULL, it allocates
* only buffer and this buffer would be used
* for default framebuffer.
*/
- entry = exynos_drm_buf_create(dev, size);
- if (IS_ERR(entry)) {
- ret = PTR_ERR(entry);
+ buffer = exynos_drm_buf_create(dev, size);
+ if (IS_ERR(buffer)) {
+ ret = PTR_ERR(buffer);
goto err_buffer;
}
- exynos_fb->entry = entry;
+ exynos_fb->buffer = buffer;
- DRM_LOG_KMS("default fb: paddr = 0x%lx, size = 0x%x\n",
- (unsigned long)entry->paddr, size);
+ DRM_LOG_KMS("default: dma_addr = 0x%lx, size = 0x%x\n",
+ (unsigned long)buffer->dma_addr, size);
goto out;
} else {
- exynos_gem_obj = exynos_drm_gem_create(file_priv, dev,
- size,
- &mode_cmd->handle);
+ exynos_gem_obj = exynos_drm_gem_create(dev, file_priv,
+ &mode_cmd->handle,
+ size);
if (IS_ERR(exynos_gem_obj)) {
ret = PTR_ERR(exynos_gem_obj);
goto err_buffer;
* so that default framebuffer has no its own gem object,
* only its own buffer object.
*/
- exynos_fb->entry = exynos_gem_obj->entry;
+ exynos_fb->buffer = exynos_gem_obj->buffer;
- DRM_LOG_KMS("paddr = 0x%lx, size = 0x%x, gem object = 0x%x\n",
- (unsigned long)exynos_fb->entry->paddr, size,
+ DRM_LOG_KMS("dma_addr = 0x%lx, size = 0x%x, gem object = 0x%x\n",
+ (unsigned long)exynos_fb->buffer->dma_addr, size,
(unsigned int)&exynos_gem_obj->base);
out:
return exynos_drm_fb_init(file_priv, dev, mode_cmd);
}
-struct exynos_drm_buf_entry *exynos_drm_fb_get_buf(struct drm_framebuffer *fb)
+struct exynos_drm_gem_buf *exynos_drm_fb_get_buf(struct drm_framebuffer *fb)
{
struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
DRM_DEBUG_KMS("%s\n", __FILE__);
- entry = exynos_fb->entry;
- if (!entry)
+ buffer = exynos_fb->buffer;
+ if (!buffer)
return NULL;
- DRM_DEBUG_KMS("vaddr = 0x%lx, paddr = 0x%lx\n",
- (unsigned long)entry->vaddr,
- (unsigned long)entry->paddr);
+ DRM_DEBUG_KMS("vaddr = 0x%lx, dma_addr = 0x%lx\n",
+ (unsigned long)buffer->kvaddr,
+ (unsigned long)buffer->dma_addr);
- return entry;
+ return buffer;
+}
+
+static void exynos_drm_output_poll_changed(struct drm_device *dev)
+{
+ struct exynos_drm_private *private = dev->dev_private;
+ struct drm_fb_helper *fb_helper = private->fb_helper;
+
+ if (fb_helper)
+ drm_fb_helper_hotplug_event(fb_helper);
}
static struct drm_mode_config_funcs exynos_drm_mode_config_funcs = {
.fb_create = exynos_drm_fb_create,
+ .output_poll_changed = exynos_drm_output_poll_changed,
};
void exynos_drm_mode_config_init(struct drm_device *dev)
#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
+#include "exynos_drm_gem.h"
#include "exynos_drm_buf.h"
#define MAX_CONNECTOR 4
};
static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
- struct drm_framebuffer *fb,
- unsigned int fb_width,
- unsigned int fb_height)
+ struct drm_framebuffer *fb)
{
struct fb_info *fbi = helper->fbdev;
struct drm_device *dev = helper->dev;
struct exynos_drm_fbdev *exynos_fb = to_exynos_fbdev(helper);
- struct exynos_drm_buf_entry *entry;
- unsigned int size = fb_width * fb_height * (fb->bits_per_pixel >> 3);
+ struct exynos_drm_gem_buf *buffer;
+ unsigned int size = fb->width * fb->height * (fb->bits_per_pixel >> 3);
unsigned long offset;
DRM_DEBUG_KMS("%s\n", __FILE__);
exynos_fb->fb = fb;
drm_fb_helper_fill_fix(fbi, fb->pitch, fb->depth);
- drm_fb_helper_fill_var(fbi, helper, fb_width, fb_height);
+ drm_fb_helper_fill_var(fbi, helper, fb->width, fb->height);
- entry = exynos_drm_fb_get_buf(fb);
- if (!entry) {
- DRM_LOG_KMS("entry is null.\n");
+ buffer = exynos_drm_fb_get_buf(fb);
+ if (!buffer) {
+ DRM_LOG_KMS("buffer is null.\n");
return -EFAULT;
}
offset = fbi->var.xoffset * (fb->bits_per_pixel >> 3);
offset += fbi->var.yoffset * fb->pitch;
- dev->mode_config.fb_base = entry->paddr;
- fbi->screen_base = entry->vaddr + offset;
- fbi->fix.smem_start = entry->paddr + offset;
+ dev->mode_config.fb_base = (resource_size_t)buffer->dma_addr;
+ fbi->screen_base = buffer->kvaddr + offset;
+ fbi->fix.smem_start = (unsigned long)(buffer->dma_addr + offset);
fbi->screen_size = size;
fbi->fix.smem_len = size;
goto out;
}
- ret = exynos_drm_fbdev_update(helper, helper->fb, sizes->fb_width,
- sizes->fb_height);
+ ret = exynos_drm_fbdev_update(helper, helper->fb);
if (ret < 0)
fb_dealloc_cmap(&fbi->cmap);
}
helper->fb = exynos_fbdev->fb;
- return exynos_drm_fbdev_update(helper, helper->fb, sizes->fb_width,
- sizes->fb_height);
+ return exynos_drm_fbdev_update(helper, helper->fb);
}
static int exynos_drm_fbdev_probe(struct drm_fb_helper *helper,
fb_helper = private->fb_helper;
if (fb_helper) {
+ struct list_head temp_list;
+
+ INIT_LIST_HEAD(&temp_list);
+
+ /*
+ * fb_helper is reintialized but kernel fb is reused
+ * so kernel_fb_list need to be backuped and restored
+ */
+ if (!list_empty(&fb_helper->kernel_fb_list))
+ list_replace_init(&fb_helper->kernel_fb_list,
+ &temp_list);
+
drm_fb_helper_fini(fb_helper);
ret = drm_fb_helper_init(dev, fb_helper,
return ret;
}
+ if (!list_empty(&temp_list))
+ list_replace(&temp_list, &fb_helper->kernel_fb_list);
+
ret = drm_fb_helper_single_add_all_connectors(fb_helper);
if (ret < 0) {
DRM_ERROR("failed to add fb helper to connectors\n");
unsigned int fb_width;
unsigned int fb_height;
unsigned int bpp;
- dma_addr_t paddr;
+ dma_addr_t dma_addr;
void __iomem *vaddr;
unsigned int buf_offsize;
unsigned int line_size; /* bytes */
return 0;
}
-static struct exynos_drm_display fimd_display = {
+static struct exynos_drm_display_ops fimd_display_ops = {
.type = EXYNOS_DISPLAY_TYPE_LCD,
.is_connected = fimd_display_is_connected,
.get_timing = fimd_get_timing,
writel(val, ctx->regs + VIDCON0);
}
+static void fimd_disable(struct device *dev)
+{
+ struct fimd_context *ctx = get_fimd_context(dev);
+ struct exynos_drm_subdrv *subdrv = &ctx->subdrv;
+ struct drm_device *drm_dev = subdrv->drm_dev;
+ struct exynos_drm_manager *manager = &subdrv->manager;
+ u32 val;
+
+ DRM_DEBUG_KMS("%s\n", __FILE__);
+
+ /* fimd dma off */
+ val = readl(ctx->regs + VIDCON0);
+ val &= ~(VIDCON0_ENVID | VIDCON0_ENVID_F);
+ writel(val, ctx->regs + VIDCON0);
+
+ /*
+ * if vblank is enabled status with dma off then
+ * it disables vsync interrupt.
+ */
+ if (drm_dev->vblank_enabled[manager->pipe] &&
+ atomic_read(&drm_dev->vblank_refcount[manager->pipe])) {
+ drm_vblank_put(drm_dev, manager->pipe);
+
+ /*
+ * if vblank_disable_allowed is 0 then disable
+ * vsync interrupt right now else the vsync interrupt
+ * would be disabled by drm timer once a current process
+ * gives up ownershop of vblank event.
+ */
+ if (!drm_dev->vblank_disable_allowed)
+ drm_vblank_off(drm_dev, manager->pipe);
+ }
+}
+
static int fimd_enable_vblank(struct device *dev)
{
struct fimd_context *ctx = get_fimd_context(dev);
static struct exynos_drm_manager_ops fimd_manager_ops = {
.commit = fimd_commit,
+ .disable = fimd_disable,
.enable_vblank = fimd_enable_vblank,
.disable_vblank = fimd_disable_vblank,
};
win_data->ovl_height = overlay->crtc_height;
win_data->fb_width = overlay->fb_width;
win_data->fb_height = overlay->fb_height;
- win_data->paddr = overlay->paddr + offset;
+ win_data->dma_addr = overlay->dma_addr + offset;
win_data->vaddr = overlay->vaddr + offset;
win_data->bpp = overlay->bpp;
win_data->buf_offsize = (overlay->fb_width - overlay->crtc_width) *
DRM_DEBUG_KMS("ovl_width = %d, ovl_height = %d\n",
win_data->ovl_width, win_data->ovl_height);
DRM_DEBUG_KMS("paddr = 0x%lx, vaddr = 0x%lx\n",
- (unsigned long)win_data->paddr,
+ (unsigned long)win_data->dma_addr,
(unsigned long)win_data->vaddr);
DRM_DEBUG_KMS("fb_width = %d, crtc_width = %d\n",
overlay->fb_width, overlay->crtc_width);
writel(val, ctx->regs + SHADOWCON);
/* buffer start address */
- val = win_data->paddr;
+ val = (unsigned long)win_data->dma_addr;
writel(val, ctx->regs + VIDWx_BUF_START(win, 0));
/* buffer end address */
size = win_data->fb_width * win_data->ovl_height * (win_data->bpp >> 3);
- val = win_data->paddr + size;
+ val = (unsigned long)(win_data->dma_addr + size);
writel(val, ctx->regs + VIDWx_BUF_END(win, 0));
DRM_DEBUG_KMS("start addr = 0x%lx, end addr = 0x%lx, size = 0x%lx\n",
- (unsigned long)win_data->paddr, val, size);
+ (unsigned long)win_data->dma_addr, val, size);
DRM_DEBUG_KMS("ovl_width = %d, ovl_height = %d\n",
win_data->ovl_width, win_data->ovl_height);
static void fimd_win_disable(struct device *dev)
{
struct fimd_context *ctx = get_fimd_context(dev);
- struct fimd_win_data *win_data;
int win = ctx->default_win;
u32 val;
if (win < 0 || win > WINDOWS_NR)
return;
- win_data = &ctx->win_data[win];
-
/* protect windows */
val = readl(ctx->regs + SHADOWCON);
val |= SHADOWCON_WINx_PROTECT(win);
/* VSYNC interrupt */
writel(VIDINTCON1_INT_FRAME, ctx->regs + VIDINTCON1);
+ /*
+ * in case that vblank_disable_allowed is 1, it could induce
+ * the problem that manager->pipe could be -1 because with
+ * disable callback, vsync interrupt isn't disabled and at this moment,
+ * vsync interrupt could occur. the vsync interrupt would be disabled
+ * by timer handler later.
+ */
+ if (manager->pipe == -1)
+ return IRQ_HANDLED;
+
drm_handle_vblank(drm_dev, manager->pipe);
fimd_finish_pageflip(drm_dev, manager->pipe);
*/
drm_dev->irq_enabled = 1;
- /*
- * with vblank_disable_allowed = 1, vblank interrupt will be disabled
- * by drm timer once a current process gives up ownership of
- * vblank event.(drm_vblank_put function was called)
- */
- drm_dev->vblank_disable_allowed = 1;
-
return 0;
}
subdrv->manager.pipe = -1;
subdrv->manager.ops = &fimd_manager_ops;
subdrv->manager.overlay_ops = &fimd_overlay_ops;
- subdrv->manager.display = &fimd_display;
+ subdrv->manager.display_ops = &fimd_display_ops;
subdrv->manager.dev = dev;
platform_set_drvdata(pdev, ctx);
return (unsigned int)obj->map_list.hash.key << PAGE_SHIFT;
}
-struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv,
- struct drm_device *dev, unsigned int size,
- unsigned int *handle)
+static struct exynos_drm_gem_obj
+ *exynos_drm_gem_init(struct drm_device *drm_dev,
+ struct drm_file *file_priv, unsigned int *handle,
+ unsigned int size)
{
struct exynos_drm_gem_obj *exynos_gem_obj;
- struct exynos_drm_buf_entry *entry;
struct drm_gem_object *obj;
int ret;
- DRM_DEBUG_KMS("%s\n", __FILE__);
-
- size = roundup(size, PAGE_SIZE);
-
exynos_gem_obj = kzalloc(sizeof(*exynos_gem_obj), GFP_KERNEL);
if (!exynos_gem_obj) {
DRM_ERROR("failed to allocate exynos gem object.\n");
return ERR_PTR(-ENOMEM);
}
- /* allocate the new buffer object and memory region. */
- entry = exynos_drm_buf_create(dev, size);
- if (!entry) {
- kfree(exynos_gem_obj);
- return ERR_PTR(-ENOMEM);
- }
-
- exynos_gem_obj->entry = entry;
-
obj = &exynos_gem_obj->base;
- ret = drm_gem_object_init(dev, obj, size);
+ ret = drm_gem_object_init(drm_dev, obj, size);
if (ret < 0) {
- DRM_ERROR("failed to initailize gem object.\n");
- goto err_obj_init;
+ DRM_ERROR("failed to initialize gem object.\n");
+ ret = -EINVAL;
+ goto err_object_init;
}
DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp);
err_create_mmap_offset:
drm_gem_object_release(obj);
-err_obj_init:
- exynos_drm_buf_destroy(dev, exynos_gem_obj->entry);
-
+err_object_init:
kfree(exynos_gem_obj);
return ERR_PTR(ret);
}
+struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev,
+ struct drm_file *file_priv,
+ unsigned int *handle, unsigned long size)
+{
+
+ struct exynos_drm_gem_obj *exynos_gem_obj = NULL;
+ struct exynos_drm_gem_buf *buffer;
+
+ size = roundup(size, PAGE_SIZE);
+
+ DRM_DEBUG_KMS("%s: size = 0x%lx\n", __FILE__, size);
+
+ buffer = exynos_drm_buf_create(dev, size);
+ if (IS_ERR(buffer)) {
+ return ERR_CAST(buffer);
+ }
+
+ exynos_gem_obj = exynos_drm_gem_init(dev, file_priv, handle, size);
+ if (IS_ERR(exynos_gem_obj)) {
+ exynos_drm_buf_destroy(dev, buffer);
+ return exynos_gem_obj;
+ }
+
+ exynos_gem_obj->buffer = buffer;
+
+ return exynos_gem_obj;
+}
+
int exynos_drm_gem_create_ioctl(struct drm_device *dev, void *data,
- struct drm_file *file_priv)
+ struct drm_file *file_priv)
{
struct drm_exynos_gem_create *args = data;
- struct exynos_drm_gem_obj *exynos_gem_obj;
+ struct exynos_drm_gem_obj *exynos_gem_obj = NULL;
- DRM_DEBUG_KMS("%s : size = 0x%x\n", __FILE__, args->size);
+ DRM_DEBUG_KMS("%s\n", __FILE__);
- exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size,
- &args->handle);
+ exynos_gem_obj = exynos_drm_gem_create(dev, file_priv,
+ &args->handle, args->size);
if (IS_ERR(exynos_gem_obj))
return PTR_ERR(exynos_gem_obj);
{
struct drm_gem_object *obj = filp->private_data;
struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj);
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
unsigned long pfn, vm_size;
DRM_DEBUG_KMS("%s\n", __FILE__);
vm_size = vma->vm_end - vma->vm_start;
/*
- * a entry contains information to physically continuous memory
+ * a buffer contains information to physically continuous memory
* allocated by user request or at framebuffer creation.
*/
- entry = exynos_gem_obj->entry;
+ buffer = exynos_gem_obj->buffer;
/* check if user-requested size is valid. */
- if (vm_size > entry->size)
+ if (vm_size > buffer->size)
return -EINVAL;
/*
* get page frame number to physical memory to be mapped
* to user space.
*/
- pfn = exynos_gem_obj->entry->paddr >> PAGE_SHIFT;
+ pfn = ((unsigned long)exynos_gem_obj->buffer->dma_addr) >> PAGE_SHIFT;
DRM_DEBUG_KMS("pfn = 0x%lx\n", pfn);
exynos_gem_obj = to_exynos_gem_obj(gem_obj);
- exynos_drm_buf_destroy(gem_obj->dev, exynos_gem_obj->entry);
+ exynos_drm_buf_destroy(gem_obj->dev, exynos_gem_obj->buffer);
kfree(exynos_gem_obj);
}
args->pitch = args->width * args->bpp >> 3;
args->size = args->pitch * args->height;
- exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size,
- &args->handle);
+ exynos_gem_obj = exynos_drm_gem_create(dev, file_priv, &args->handle,
+ args->size);
if (IS_ERR(exynos_gem_obj))
return PTR_ERR(exynos_gem_obj);
mutex_lock(&dev->struct_mutex);
- pfn = (exynos_gem_obj->entry->paddr >> PAGE_SHIFT) + page_offset;
+ pfn = (((unsigned long)exynos_gem_obj->buffer->dma_addr) >>
+ PAGE_SHIFT) + page_offset;
ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn);
#define to_exynos_gem_obj(x) container_of(x,\
struct exynos_drm_gem_obj, base)
+/*
+ * exynos drm gem buffer structure.
+ *
+ * @kvaddr: kernel virtual address to allocated memory region.
+ * @dma_addr: bus address(accessed by dma) to allocated memory region.
+ * - this address could be physical address without IOMMU and
+ * device address with IOMMU.
+ * @size: size of allocated memory region.
+ */
+struct exynos_drm_gem_buf {
+ void __iomem *kvaddr;
+ dma_addr_t dma_addr;
+ unsigned long size;
+};
+
/*
* exynos drm buffer structure.
*
* @base: a gem object.
* - a new handle to this gem object would be created
* by drm_gem_handle_create().
- * @entry: pointer to exynos drm buffer entry object.
- * - containing the information to physically
+ * @buffer: a pointer to exynos_drm_gem_buffer object.
+ * - contain the information to memory region allocated
+ * by user request or at framebuffer creation.
* continuous memory region allocated by user request
* or at framebuffer creation.
*
*/
struct exynos_drm_gem_obj {
struct drm_gem_object base;
- struct exynos_drm_buf_entry *entry;
+ struct exynos_drm_gem_buf *buffer;
};
/* create a new buffer and get a new gem handle. */
-struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv,
- struct drm_device *dev, unsigned int size,
- unsigned int *handle);
+struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev,
+ struct drm_file *file_priv,
+ unsigned int *handle, unsigned long size);
/*
* request gem object creation and buffer allocation as the size
const struct intel_device_info *info = INTEL_INFO(dev);
seq_printf(m, "gen: %d\n", info->gen);
+ seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev));
#define B(x) seq_printf(m, #x ": %s\n", yesno(info->x))
B(is_mobile);
B(is_i85x);
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
struct intel_ring_buffer *ring;
+ int ret;
ring = &dev_priv->ring[(uintptr_t)node->info_ent->data];
if (ring->size == 0)
return 0;
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
+
seq_printf(m, "Ring %s:\n", ring->name);
seq_printf(m, " Head : %08x\n", I915_READ_HEAD(ring) & HEAD_ADDR);
seq_printf(m, " Tail : %08x\n", I915_READ_TAIL(ring) & TAIL_ADDR);
seq_printf(m, " Control : %08x\n", I915_READ_CTL(ring));
seq_printf(m, " Start : %08x\n", I915_READ_START(ring));
+ mutex_unlock(&dev->struct_mutex);
+
return 0;
}
struct drm_info_node *node = (struct drm_info_node *) m->private;
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
- u16 crstanddelay = I915_READ16(CRSTANDVID);
+ u16 crstanddelay;
+ int ret;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
+
+ crstanddelay = I915_READ16(CRSTANDVID);
+
+ mutex_unlock(&dev->struct_mutex);
seq_printf(m, "w/ctx: %d, w/o ctx: %d\n", (crstanddelay >> 8) & 0x3f, (crstanddelay & 0x3f));
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
u32 delayfreq;
- int i;
+ int ret, i;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
for (i = 0; i < 16; i++) {
delayfreq = I915_READ(PXVFREQ_BASE + i * 4);
(delayfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT);
}
+ mutex_unlock(&dev->struct_mutex);
+
return 0;
}
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
u32 inttoext;
- int i;
+ int ret, i;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
for (i = 1; i <= 32; i++) {
inttoext = I915_READ(INTTOEXT_BASE_ILK + i * 4);
seq_printf(m, "INTTOEXT%02d: 0x%08x\n", i, inttoext);
}
+ mutex_unlock(&dev->struct_mutex);
+
return 0;
}
struct drm_info_node *node = (struct drm_info_node *) m->private;
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
- u32 rgvmodectl = I915_READ(MEMMODECTL);
- u32 rstdbyctl = I915_READ(RSTDBYCTL);
- u16 crstandvid = I915_READ16(CRSTANDVID);
+ u32 rgvmodectl, rstdbyctl;
+ u16 crstandvid;
+ int ret;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
+
+ rgvmodectl = I915_READ(MEMMODECTL);
+ rstdbyctl = I915_READ(RSTDBYCTL);
+ crstandvid = I915_READ16(CRSTANDVID);
+
+ mutex_unlock(&dev->struct_mutex);
seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ?
"yes" : "no");
struct drm_info_node *node = (struct drm_info_node *) m->private;
struct drm_device *dev = node->minor->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
+ int ret;
+
+ ret = mutex_lock_interruptible(&dev->struct_mutex);
+ if (ret)
+ return ret;
seq_printf(m, "GFXEC: %ld\n", (unsigned long)I915_READ(0x112f4));
+ mutex_unlock(&dev->struct_mutex);
+
return 0;
}
diff1 = now - dev_priv->last_time1;
+ /* Prevent division-by-zero if we are asking too fast.
+ * Also, we don't get interesting results if we are polling
+ * faster than once in 10ms, so just return the saved value
+ * in such cases.
+ */
+ if (diff1 <= 10)
+ return dev_priv->chipset_power;
+
count1 = I915_READ(DMIEC);
count2 = I915_READ(DDREC);
count3 = I915_READ(CSIEC);
dev_priv->last_count1 = total_count;
dev_priv->last_time1 = now;
+ dev_priv->chipset_power = ret;
+
return ret;
}
MODULE_PARM_DESC(powersave,
"Enable powersavings, fbc, downclocking, etc. (default: true)");
-unsigned int i915_semaphores __read_mostly = 0;
+int i915_semaphores __read_mostly = -1;
module_param_named(semaphores, i915_semaphores, int, 0600);
MODULE_PARM_DESC(semaphores,
- "Use semaphores for inter-ring sync (default: false)");
+ "Use semaphores for inter-ring sync (default: -1 (use per-chip defaults))");
-unsigned int i915_enable_rc6 __read_mostly = 0;
+int i915_enable_rc6 __read_mostly = -1;
module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
MODULE_PARM_DESC(i915_enable_rc6,
- "Enable power-saving render C-state 6 (default: true)");
+ "Enable power-saving render C-state 6 (default: -1 (use per-chip default)");
-unsigned int i915_enable_fbc __read_mostly = -1;
+int i915_enable_fbc __read_mostly = -1;
module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
MODULE_PARM_DESC(i915_enable_fbc,
"Enable frame buffer compression for power savings "
"Use panel (LVDS/eDP) downclocking for power savings "
"(default: false)");
-unsigned int i915_panel_use_ssc __read_mostly = -1;
+int i915_panel_use_ssc __read_mostly = -1;
module_param_named(lvds_use_ssc, i915_panel_use_ssc, int, 0600);
MODULE_PARM_DESC(lvds_use_ssc,
"Use Spread Spectrum Clock with panels [LVDS/eDP] "
extern int intel_agp_enabled;
#define INTEL_VGA_DEVICE(id, info) { \
- .class = PCI_CLASS_DISPLAY_VGA << 8, \
+ .class = PCI_BASE_CLASS_DISPLAY << 16, \
.class_mask = 0xff0000, \
.vendor = 0x8086, \
.device = id, \
}
}
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
{
int count;
udelay(10);
}
+void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+{
+ int count;
+
+ count = 0;
+ while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1))
+ udelay(10);
+
+ I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 1);
+ POSTING_READ(FORCEWAKE_MT);
+
+ count = 0;
+ while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1) == 0)
+ udelay(10);
+}
+
/*
* Generally this is called implicitly by the register read function. However,
* if some sequence requires the GT to not power down then this function should
/* Forcewake is atomic in case we get in here without the lock */
if (atomic_add_return(1, &dev_priv->forcewake_count) == 1)
- __gen6_gt_force_wake_get(dev_priv);
+ dev_priv->display.force_wake_get(dev_priv);
}
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
{
I915_WRITE_NOTRACE(FORCEWAKE, 0);
POSTING_READ(FORCEWAKE);
}
+void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+{
+ I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 0);
+ POSTING_READ(FORCEWAKE_MT);
+}
+
/*
* see gen6_gt_force_wake_get()
*/
WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
if (atomic_dec_and_test(&dev_priv->forcewake_count))
- __gen6_gt_force_wake_put(dev_priv);
+ dev_priv->display.force_wake_put(dev_priv);
}
void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
(((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE))
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE) && \
+ ((reg) != ECOBUS))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
struct opregion_acpi;
struct opregion_swsci;
struct opregion_asle;
+struct drm_i915_private;
struct intel_opregion {
struct opregion_header *header;
struct _drm_i915_sarea *sarea_priv;
};
#define I915_FENCE_REG_NONE -1
+#define I915_MAX_NUM_FENCES 16
+/* 16 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 5
struct drm_i915_fence_reg {
struct list_head lru_list;
u32 instdone1;
u32 seqno;
u64 bbaddr;
- u64 fence[16];
+ u64 fence[I915_MAX_NUM_FENCES];
struct timeval time;
struct drm_i915_error_object {
int page_count;
u32 gtt_offset;
u32 read_domains;
u32 write_domain;
- s32 fence_reg:5;
+ s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
s32 pinned:2;
u32 tiling:2;
u32 dirty:1;
struct drm_i915_gem_object *obj);
int (*update_plane)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
int x, int y);
+ void (*force_wake_get)(struct drm_i915_private *dev_priv);
+ void (*force_wake_put)(struct drm_i915_private *dev_priv);
/* clock updates for mode set */
/* cursor updates */
/* render clock increase/decrease */
struct notifier_block lid_notifier;
int crt_ddc_pin;
- struct drm_i915_fence_reg fence_regs[16]; /* assume 965 */
+ struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */
int num_fence_regs; /* 8 on pre-965, 16 otherwise */
u8 saveAR[21];
u8 saveDACMASK;
u8 saveCR[37];
- uint64_t saveFENCE[16];
+ uint64_t saveFENCE[I915_MAX_NUM_FENCES];
u32 saveCURACNTR;
u32 saveCURAPOS;
u32 saveCURABASE;
u64 last_count1;
unsigned long last_time1;
+ unsigned long chipset_power;
u64 last_count2;
struct timespec last_time2;
unsigned long gfx_power;
* Fence register bits (if any) for this object. Will be set
* as needed when mapped into the GTT.
* Protected by dev->struct_mutex.
- *
- * Size: 4 bits for 16 fences + sign (for FENCE_REG_NONE)
*/
- signed int fence_reg:5;
+ signed int fence_reg:I915_MAX_NUM_FENCE_BITS;
/**
* Advice: are the backing pages purgeable?
extern unsigned int i915_fbpercrtc __always_unused;
extern int i915_panel_ignore_lid __read_mostly;
extern unsigned int i915_powersave __read_mostly;
-extern unsigned int i915_semaphores __read_mostly;
+extern int i915_semaphores __read_mostly;
extern unsigned int i915_lvds_downclock __read_mostly;
-extern unsigned int i915_panel_use_ssc __read_mostly;
+extern int i915_panel_use_ssc __read_mostly;
extern int i915_vbt_sdvo_panel_type __read_mostly;
-extern unsigned int i915_enable_rc6 __read_mostly;
-extern unsigned int i915_enable_fbc __read_mostly;
+extern int i915_enable_rc6 __read_mostly;
+extern int i915_enable_fbc __read_mostly;
extern bool i915_enable_hangcheck __read_mostly;
extern int i915_suspend(struct drm_device *dev, pm_message_t state);
extern void intel_detect_pch(struct drm_device *dev);
extern int intel_trans_dp_port_sel(struct drm_crtc *crtc);
+extern void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv);
+
/* overlay */
#ifdef CONFIG_DEBUG_FS
extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
(((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE))
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE) && \
+ ((reg) != ECOBUS))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg);
struct drm_i915_private *dev_priv = dev->dev_private;
int i;
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
struct drm_i915_gem_object *obj = reg->obj;
* so emit a request to do so.
*/
request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request)
+ if (request) {
ret = i915_add_request(obj->ring, NULL, request);
- else
+ if (ret)
+ kfree(request);
+ } else
ret = -ENOMEM;
}
obj->base.write_domain = I915_GEM_DOMAIN_CPU;
obj->base.read_domains = I915_GEM_DOMAIN_CPU;
- if (IS_GEN6(dev)) {
+ if (IS_GEN6(dev) || IS_GEN7(dev)) {
/* On Gen6, we can have the GPU use the LLC (the CPU
* cache) for about a 10% performance improvement
* compared to uncached. Graphics requests other than
INIT_LIST_HEAD(&dev_priv->mm.gtt_list);
for (i = 0; i < I915_NUM_RINGS; i++)
init_ring_lists(&dev_priv->ring[i]);
- for (i = 0; i < 16; i++)
+ for (i = 0; i < I915_MAX_NUM_FENCES; i++)
INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list);
INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
i915_gem_retire_work_handler);
#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_drv.h"
+#include <linux/dma_remapping.h>
struct change_domains {
uint32_t invalidate_domains;
return 0;
}
+static bool
+intel_enable_semaphores(struct drm_device *dev)
+{
+ if (INTEL_INFO(dev)->gen < 6)
+ return 0;
+
+ if (i915_semaphores >= 0)
+ return i915_semaphores;
+
+ /* Disable semaphores on SNB */
+ if (INTEL_INFO(dev)->gen == 6)
+ return 0;
+
+ return 1;
+}
+
static int
i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj,
struct intel_ring_buffer *to)
return 0;
/* XXX gpu semaphores are implicated in various hard hangs on SNB */
- if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores)
+ if (!intel_enable_semaphores(obj->base.dev))
return i915_gem_object_wait_rendering(obj);
idx = intel_ring_sync_index(from, to);
/* Fences */
switch (INTEL_INFO(dev)->gen) {
+ case 7:
case 6:
for (i = 0; i < 16; i++)
error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
*/
#define PP_READY (1 << 30)
#define PP_SEQUENCE_NONE (0 << 28)
-#define PP_SEQUENCE_ON (1 << 28)
-#define PP_SEQUENCE_OFF (2 << 28)
-#define PP_SEQUENCE_MASK 0x30000000
+#define PP_SEQUENCE_POWER_UP (1 << 28)
+#define PP_SEQUENCE_POWER_DOWN (2 << 28)
+#define PP_SEQUENCE_MASK (3 << 28)
+#define PP_SEQUENCE_SHIFT 28
#define PP_CYCLE_DELAY_ACTIVE (1 << 27)
-#define PP_SEQUENCE_STATE_ON_IDLE (1 << 3)
#define PP_SEQUENCE_STATE_MASK 0x0000000f
+#define PP_SEQUENCE_STATE_OFF_IDLE (0x0 << 0)
+#define PP_SEQUENCE_STATE_OFF_S0_1 (0x1 << 0)
+#define PP_SEQUENCE_STATE_OFF_S0_2 (0x2 << 0)
+#define PP_SEQUENCE_STATE_OFF_S0_3 (0x3 << 0)
+#define PP_SEQUENCE_STATE_ON_IDLE (0x8 << 0)
+#define PP_SEQUENCE_STATE_ON_S1_0 (0x9 << 0)
+#define PP_SEQUENCE_STATE_ON_S1_2 (0xa << 0)
+#define PP_SEQUENCE_STATE_ON_S1_3 (0xb << 0)
+#define PP_SEQUENCE_STATE_RESET (0xf << 0)
#define PP_CONTROL 0x61204
#define POWER_TARGET_ON (1 << 0)
#define PP_ON_DELAYS 0x61208
/* or SDVOB */
#define HDMIB 0xe1140
#define PORT_ENABLE (1 << 31)
-#define TRANSCODER_A (0)
-#define TRANSCODER_B (1 << 30)
-#define TRANSCODER(pipe) ((pipe) << 30)
-#define TRANSCODER_MASK (1 << 30)
+#define TRANSCODER(pipe) ((pipe) << 30)
+#define TRANSCODER_CPT(pipe) ((pipe) << 29)
+#define TRANSCODER_MASK (1 << 30)
+#define TRANSCODER_MASK_CPT (3 << 29)
#define COLOR_FORMAT_8bpc (0)
#define COLOR_FORMAT_12bpc (3 << 26)
#define SDVOB_HOTPLUG_ENABLE (1 << 23)
#define EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B (0x38<<22)
#define EDP_LINK_TRAIN_VOL_EMP_MASK_SNB (0x3f<<22)
+/* IVB */
+#define EDP_LINK_TRAIN_400MV_0DB_IVB (0x24 <<22)
+#define EDP_LINK_TRAIN_400MV_3_5DB_IVB (0x2a <<22)
+#define EDP_LINK_TRAIN_400MV_6DB_IVB (0x2f <<22)
+#define EDP_LINK_TRAIN_600MV_0DB_IVB (0x30 <<22)
+#define EDP_LINK_TRAIN_600MV_3_5DB_IVB (0x36 <<22)
+#define EDP_LINK_TRAIN_800MV_0DB_IVB (0x38 <<22)
+#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x33 <<22)
+
+/* legacy values */
+#define EDP_LINK_TRAIN_500MV_0DB_IVB (0x00 <<22)
+#define EDP_LINK_TRAIN_1000MV_0DB_IVB (0x20 <<22)
+#define EDP_LINK_TRAIN_500MV_3_5DB_IVB (0x02 <<22)
+#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB (0x22 <<22)
+#define EDP_LINK_TRAIN_1000MV_6DB_IVB (0x23 <<22)
+
+#define EDP_LINK_TRAIN_VOL_EMP_MASK_IVB (0x3f<<22)
+
#define FORCEWAKE 0xA18C
#define FORCEWAKE_ACK 0x130090
+#define FORCEWAKE_MT 0xa188 /* multi-threaded */
+#define FORCEWAKE_MT_ACK 0x130040
+#define ECOBUS 0xa180
+#define FORCEWAKE_MT_ENABLE (1<<5)
#define GT_FIFO_FREE_ENTRIES 0x120008
#define GT_FIFO_NUM_RESERVED_ENTRIES 20
+#define GEN6_UCGCTL2 0x9404
+# define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE (1 << 12)
+# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE (1 << 11)
+
#define GEN6_RPNSWREQ 0xA008
#define GEN6_TURBO_DISABLE (1<<31)
#define GEN6_FREQUENCY(x) ((x)<<25)
/* Fences */
switch (INTEL_INFO(dev)->gen) {
+ case 7:
case 6:
for (i = 0; i < 16; i++)
dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
/* Fences */
switch (INTEL_INFO(dev)->gen) {
+ case 7:
case 6:
for (i = 0; i < 16; i++)
I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]);
#include "i915_drv.h"
#include "i915_trace.h"
#include "drm_dp_helper.h"
-
#include "drm_crtc_helper.h"
+#include <linux/dma_remapping.h>
#define HAS_eDP (intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))
/* For PCH DP, enable TRANS_DP_CTL */
if (HAS_PCH_CPT(dev) &&
- intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) {
+ (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
+ intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) {
u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) >> 5;
reg = TRANS_DP_CTL(pipe);
temp = I915_READ(reg);
/**
* intel_choose_pipe_bpp_dither - figure out what color depth the pipe should send
* @crtc: CRTC structure
+ * @mode: requested mode
*
* A pipe may be connected to one or more outputs. Based on the depth of the
* attached framebuffer, choose a good color depth to use on the pipe.
* HDMI supports only 8bpc or 12bpc, so clamp to 8bpc with dither for 10bpc
* Displays may support a restricted set as well, check EDID and clamp as
* appropriate.
+ * DP may want to dither down to 6bpc to fit larger modes
*
* RETURNS:
* Dithering requirement (i.e. false if display bpc and pipe bpc match,
* true if they don't match).
*/
static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
- unsigned int *pipe_bpp)
+ unsigned int *pipe_bpp,
+ struct drm_display_mode *mode)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
lvds_bpc = 6;
if (lvds_bpc < display_bpc) {
- DRM_DEBUG_DRIVER("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
+ DRM_DEBUG_KMS("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
display_bpc = lvds_bpc;
}
continue;
unsigned int edp_bpc = dev_priv->edp.bpp / 3;
if (edp_bpc < display_bpc) {
- DRM_DEBUG_DRIVER("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
+ DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
display_bpc = edp_bpc;
}
continue;
/* Don't use an invalid EDID bpc value */
if (connector->display_info.bpc &&
connector->display_info.bpc < display_bpc) {
- DRM_DEBUG_DRIVER("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
+ DRM_DEBUG_KMS("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
display_bpc = connector->display_info.bpc;
}
}
*/
if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
if (display_bpc > 8 && display_bpc < 12) {
- DRM_DEBUG_DRIVER("forcing bpc to 12 for HDMI\n");
+ DRM_DEBUG_KMS("forcing bpc to 12 for HDMI\n");
display_bpc = 12;
} else {
- DRM_DEBUG_DRIVER("forcing bpc to 8 for HDMI\n");
+ DRM_DEBUG_KMS("forcing bpc to 8 for HDMI\n");
display_bpc = 8;
}
}
}
+ if (mode->private_flags & INTEL_MODE_DP_FORCE_6BPC) {
+ DRM_DEBUG_KMS("Dithering DP to 6bpc\n");
+ display_bpc = 6;
+ }
+
/*
* We could just drive the pipe at the highest bpc all the time and
* enable dithering as needed, but that costs bandwidth. So choose
display_bpc = min(display_bpc, bpc);
- DRM_DEBUG_DRIVER("setting pipe bpc to %d (max display bpc %d)\n",
- bpc, display_bpc);
+ DRM_DEBUG_KMS("setting pipe bpc to %d (max display bpc %d)\n",
+ bpc, display_bpc);
*pipe_bpp = display_bpc * 3;
pipeconf &= ~PIPECONF_DOUBLE_WIDE;
}
+ /* default to 8bpc */
+ pipeconf &= ~(PIPECONF_BPP_MASK | PIPECONF_DITHER_EN);
+ if (is_dp) {
+ if (mode->private_flags & INTEL_MODE_DP_FORCE_6BPC) {
+ pipeconf |= PIPECONF_BPP_6 |
+ PIPECONF_DITHER_EN |
+ PIPECONF_DITHER_TYPE_SP;
+ }
+ }
+
dpll |= DPLL_VCO_ENABLE;
DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe == 0 ? 'A' : 'B');
/* determine panel color depth */
temp = I915_READ(PIPECONF(pipe));
temp &= ~PIPE_BPC_MASK;
- dither = intel_choose_pipe_bpp_dither(crtc, &pipe_bpp);
+ dither = intel_choose_pipe_bpp_dither(crtc, &pipe_bpp, mode);
switch (pipe_bpp) {
case 18:
temp |= PIPE_6BPC;
pipeconf &= ~PIPECONF_DITHER_TYPE_MASK;
if ((is_lvds && dev_priv->lvds_dither) || dither) {
pipeconf |= PIPECONF_DITHER_EN;
- pipeconf |= PIPECONF_DITHER_TYPE_ST1;
+ pipeconf |= PIPECONF_DITHER_TYPE_SP;
}
if (is_dp || intel_encoder_is_pch_edp(&has_edp_encoder->base)) {
intel_dp_set_m_n(crtc, mode, adjusted_mode);
work->old_fb_obj = intel_fb->obj;
INIT_WORK(&work->work, intel_unpin_work_fn);
+ ret = drm_vblank_get(dev, intel_crtc->pipe);
+ if (ret)
+ goto free_work;
+
/* We borrow the event spin lock for protecting unpin_work */
spin_lock_irqsave(&dev->event_lock, flags);
if (intel_crtc->unpin_work) {
spin_unlock_irqrestore(&dev->event_lock, flags);
kfree(work);
+ drm_vblank_put(dev, intel_crtc->pipe);
DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
return -EBUSY;
crtc->fb = fb;
- ret = drm_vblank_get(dev, intel_crtc->pipe);
- if (ret)
- goto cleanup_objs;
-
work->pending_flip_obj = obj;
work->enable_stall_check = true;
cleanup_pending:
atomic_sub(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip);
-cleanup_objs:
drm_gem_object_unreference(&work->old_fb_obj->base);
drm_gem_object_unreference(&obj->base);
mutex_unlock(&dev->struct_mutex);
intel_crtc->unpin_work = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
+ drm_vblank_put(dev, intel_crtc->pipe);
+free_work:
kfree(work);
return ret;
dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
}
+static bool intel_enable_rc6(struct drm_device *dev)
+{
+ /*
+ * Respect the kernel parameter if it is set
+ */
+ if (i915_enable_rc6 >= 0)
+ return i915_enable_rc6;
+
+ /*
+ * Disable RC6 on Ironlake
+ */
+ if (INTEL_INFO(dev)->gen == 5)
+ return 0;
+
+ /*
+ * Disable rc6 on Sandybridge
+ */
+ if (INTEL_INFO(dev)->gen == 6) {
+ DRM_DEBUG_DRIVER("Sandybridge: RC6 disabled\n");
+ return 0;
+ }
+ DRM_DEBUG_DRIVER("RC6 enabled\n");
+ return 1;
+}
+
void gen6_enable_rps(struct drm_i915_private *dev_priv)
{
u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
I915_WRITE(GEN6_RC6p_THRESHOLD, 100000);
I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
- if (i915_enable_rc6)
+ if (intel_enable_rc6(dev_priv->dev))
rc6_mask = GEN6_RC_CTL_RC6p_ENABLE |
GEN6_RC_CTL_RC6_ENABLE;
I915_WRITE(WM2_LP_ILK, 0);
I915_WRITE(WM1_LP_ILK, 0);
+ /* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
+ * gating disable must be set. Failure to set it results in
+ * flickering pixels due to Z write ordering failures after
+ * some amount of runtime in the Mesa "fire" demo, and Unigine
+ * Sanctuary and Tropics, and apparently anything else with
+ * alpha test or pixel discard.
+ *
+ * According to the spec, bit 11 (RCCUNIT) must also be set,
+ * but we didn't debug actual testcases to find it out.
+ */
+ I915_WRITE(GEN6_UCGCTL2,
+ GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+ GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
/*
* According to the spec the following bits should be
* set in order to enable memory self-refresh and fbc:
/* rc6 disabled by default due to repeated reports of hanging during
* boot and resume.
*/
- if (!i915_enable_rc6)
+ if (!intel_enable_rc6(dev))
return;
mutex_lock(&dev->struct_mutex);
/* For FIFO watermark updates */
if (HAS_PCH_SPLIT(dev)) {
+ dev_priv->display.force_wake_get = __gen6_gt_force_wake_get;
+ dev_priv->display.force_wake_put = __gen6_gt_force_wake_put;
+
+ /* IVB configs may use multi-threaded forcewake */
+ if (IS_IVYBRIDGE(dev)) {
+ u32 ecobus;
+
+ mutex_lock(&dev->struct_mutex);
+ __gen6_gt_force_wake_mt_get(dev_priv);
+ ecobus = I915_READ(ECOBUS);
+ __gen6_gt_force_wake_mt_put(dev_priv);
+ mutex_unlock(&dev->struct_mutex);
+
+ if (ecobus & FORCEWAKE_MT_ENABLE) {
+ DRM_DEBUG_KMS("Using MT version of forcewake\n");
+ dev_priv->display.force_wake_get =
+ __gen6_gt_force_wake_mt_get;
+ dev_priv->display.force_wake_put =
+ __gen6_gt_force_wake_mt_put;
+ }
+ }
+
if (HAS_PCH_IBX(dev))
dev_priv->display.init_pch_clock_gating = ibx_init_clock_gating;
else if (HAS_PCH_CPT(dev))
struct i2c_algo_dp_aux_data algo;
bool is_pch_edp;
uint8_t train_set[4];
- uint8_t link_status[DP_LINK_STATUS_SIZE];
int panel_power_up_delay;
int panel_power_down_delay;
int panel_power_cycle_delay;
struct drm_display_mode *panel_fixed_mode; /* for eDP */
struct delayed_work panel_vdd_work;
bool want_panel_vdd;
- unsigned long panel_off_jiffies;
};
/**
static int
intel_dp_max_lane_count(struct intel_dp *intel_dp)
{
- int max_lane_count = 4;
-
- if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11) {
- max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
- switch (max_lane_count) {
- case 1: case 2: case 4:
- break;
- default:
- max_lane_count = 4;
- }
+ int max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
+ switch (max_lane_count) {
+ case 1: case 2: case 4:
+ break;
+ default:
+ max_lane_count = 4;
}
return max_lane_count;
}
*/
static int
-intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock)
+intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock, int check_bpp)
{
struct drm_crtc *crtc = intel_dp->base.base.crtc;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
int bpp = 24;
- if (intel_crtc)
+ if (check_bpp)
+ bpp = check_bpp;
+ else if (intel_crtc)
bpp = intel_crtc->bpp;
return (pixel_clock * bpp + 9) / 10;
struct intel_dp *intel_dp = intel_attached_dp(connector);
int max_link_clock = intel_dp_link_clock(intel_dp_max_link_bw(intel_dp));
int max_lanes = intel_dp_max_lane_count(intel_dp);
+ int max_rate, mode_rate;
if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
if (mode->hdisplay > intel_dp->panel_fixed_mode->hdisplay)
return MODE_PANEL;
}
- if (intel_dp_link_required(intel_dp, mode->clock)
- > intel_dp_max_data_rate(max_link_clock, max_lanes))
- return MODE_CLOCK_HIGH;
+ mode_rate = intel_dp_link_required(intel_dp, mode->clock, 0);
+ max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
+
+ if (mode_rate > max_rate) {
+ mode_rate = intel_dp_link_required(intel_dp,
+ mode->clock, 18);
+ if (mode_rate > max_rate)
+ return MODE_CLOCK_HIGH;
+ else
+ mode->private_flags |= INTEL_MODE_DP_FORCE_6BPC;
+ }
if (mode->clock < 10000)
return MODE_CLOCK_LOW;
* clock divider.
*/
if (is_cpu_edp(intel_dp)) {
- if (IS_GEN6(dev))
- aux_clock_divider = 200; /* SNB eDP input clock at 400Mhz */
+ if (IS_GEN6(dev) || IS_GEN7(dev))
+ aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */
else
aux_clock_divider = 225; /* eDP input clock at 450Mhz */
} else if (HAS_PCH_SPLIT(dev))
int lane_count, clock;
int max_lane_count = intel_dp_max_lane_count(intel_dp);
int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
+ int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 0;
static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
for (clock = 0; clock <= max_clock; clock++) {
int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count);
- if (intel_dp_link_required(intel_dp, mode->clock)
+ if (intel_dp_link_required(intel_dp, mode->clock, bpp)
<= link_avail) {
intel_dp->link_bw = bws[clock];
intel_dp->lane_count = lane_count;
continue;
intel_dp = enc_to_intel_dp(encoder);
- if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT) {
+ if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+ intel_dp->base.type == INTEL_OUTPUT_EDP)
+ {
lane_count = intel_dp->lane_count;
break;
- } else if (is_edp(intel_dp)) {
- lane_count = dev_priv->edp.lanes;
- break;
}
}
struct drm_display_mode *adjusted_mode)
{
struct drm_device *dev = encoder->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
struct drm_crtc *crtc = intel_dp->base.base.crtc;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
ironlake_edp_pll_off(encoder);
}
- intel_dp->DP = DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
- intel_dp->DP |= intel_dp->color_range;
+ /*
+ * There are four kinds of DP registers:
+ *
+ * IBX PCH
+ * SNB CPU
+ * IVB CPU
+ * CPT PCH
+ *
+ * IBX PCH and CPU are the same for almost everything,
+ * except that the CPU DP PLL is configured in this
+ * register
+ *
+ * CPT PCH is quite different, having many bits moved
+ * to the TRANS_DP_CTL register instead. That
+ * configuration happens (oddly) in ironlake_pch_enable
+ */
+
+ /* Preserve the BIOS-computed detected bit. This is
+ * supposed to be read-only.
+ */
+ intel_dp->DP = I915_READ(intel_dp->output_reg) & DP_DETECTED;
+ intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
- if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
- intel_dp->DP |= DP_SYNC_HS_HIGH;
- if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
- intel_dp->DP |= DP_SYNC_VS_HIGH;
+ /* Handle DP bits in common between all three register formats */
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
- intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
- else
- intel_dp->DP |= DP_LINK_TRAIN_OFF;
+ intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
switch (intel_dp->lane_count) {
case 1:
intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
intel_write_eld(encoder, adjusted_mode);
}
-
memset(intel_dp->link_configuration, 0, DP_LINK_CONFIGURATION_SIZE);
intel_dp->link_configuration[0] = intel_dp->link_bw;
intel_dp->link_configuration[1] = intel_dp->lane_count;
intel_dp->link_configuration[8] = DP_SET_ANSI_8B10B;
-
/*
* Check for DPCD version > 1.1 and enhanced framing support
*/
if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
(intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP)) {
intel_dp->link_configuration[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
- intel_dp->DP |= DP_ENHANCED_FRAMING;
}
- /* CPT DP's pipe select is decided in TRANS_DP_CTL */
- if (intel_crtc->pipe == 1 && !HAS_PCH_CPT(dev))
- intel_dp->DP |= DP_PIPEB_SELECT;
+ /* Split out the IBX/CPU vs CPT settings */
+
+ if (is_cpu_edp(intel_dp) && IS_GEN7(dev)) {
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+ intel_dp->DP |= DP_SYNC_HS_HIGH;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+ intel_dp->DP |= DP_SYNC_VS_HIGH;
+ intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
+
+ if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
+ intel_dp->DP |= DP_ENHANCED_FRAMING;
+
+ intel_dp->DP |= intel_crtc->pipe << 29;
- if (is_cpu_edp(intel_dp)) {
/* don't miss out required setting for eDP */
intel_dp->DP |= DP_PLL_ENABLE;
if (adjusted_mode->clock < 200000)
intel_dp->DP |= DP_PLL_FREQ_160MHZ;
else
intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+ } else if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+ intel_dp->DP |= intel_dp->color_range;
+
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+ intel_dp->DP |= DP_SYNC_HS_HIGH;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+ intel_dp->DP |= DP_SYNC_VS_HIGH;
+ intel_dp->DP |= DP_LINK_TRAIN_OFF;
+
+ if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
+ intel_dp->DP |= DP_ENHANCED_FRAMING;
+
+ if (intel_crtc->pipe == 1)
+ intel_dp->DP |= DP_PIPEB_SELECT;
+
+ if (is_cpu_edp(intel_dp)) {
+ /* don't miss out required setting for eDP */
+ intel_dp->DP |= DP_PLL_ENABLE;
+ if (adjusted_mode->clock < 200000)
+ intel_dp->DP |= DP_PLL_FREQ_160MHZ;
+ else
+ intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+ }
+ } else {
+ intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
}
}
-static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+#define IDLE_ON_MASK (PP_ON | 0 | PP_SEQUENCE_MASK | 0 | PP_SEQUENCE_STATE_MASK)
+#define IDLE_ON_VALUE (PP_ON | 0 | PP_SEQUENCE_NONE | 0 | PP_SEQUENCE_STATE_ON_IDLE)
+
+#define IDLE_OFF_MASK (PP_ON | 0 | PP_SEQUENCE_MASK | 0 | PP_SEQUENCE_STATE_MASK)
+#define IDLE_OFF_VALUE (0 | 0 | PP_SEQUENCE_NONE | 0 | PP_SEQUENCE_STATE_OFF_IDLE)
+
+#define IDLE_CYCLE_MASK (PP_ON | 0 | PP_SEQUENCE_MASK | PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK)
+#define IDLE_CYCLE_VALUE (0 | 0 | PP_SEQUENCE_NONE | 0 | PP_SEQUENCE_STATE_OFF_IDLE)
+
+static void ironlake_wait_panel_status(struct intel_dp *intel_dp,
+ u32 mask,
+ u32 value)
{
- unsigned long off_time;
- unsigned long delay;
+ struct drm_device *dev = intel_dp->base.base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
- DRM_DEBUG_KMS("Wait for panel power off time\n");
+ DRM_DEBUG_KMS("mask %08x value %08x status %08x control %08x\n",
+ mask, value,
+ I915_READ(PCH_PP_STATUS),
+ I915_READ(PCH_PP_CONTROL));
- if (ironlake_edp_have_panel_power(intel_dp) ||
- ironlake_edp_have_panel_vdd(intel_dp))
- {
- DRM_DEBUG_KMS("Panel still on, no delay needed\n");
- return;
+ if (_wait_for((I915_READ(PCH_PP_STATUS) & mask) == value, 5000, 10)) {
+ DRM_ERROR("Panel status timeout: status %08x control %08x\n",
+ I915_READ(PCH_PP_STATUS),
+ I915_READ(PCH_PP_CONTROL));
}
+}
- off_time = intel_dp->panel_off_jiffies + msecs_to_jiffies(intel_dp->panel_power_down_delay);
- if (time_after(jiffies, off_time)) {
- DRM_DEBUG_KMS("Time already passed");
- return;
- }
- delay = jiffies_to_msecs(off_time - jiffies);
- if (delay > intel_dp->panel_power_down_delay)
- delay = intel_dp->panel_power_down_delay;
- DRM_DEBUG_KMS("Waiting an additional %ld ms\n", delay);
- msleep(delay);
+static void ironlake_wait_panel_on(struct intel_dp *intel_dp)
+{
+ DRM_DEBUG_KMS("Wait for panel power on\n");
+ ironlake_wait_panel_status(intel_dp, IDLE_ON_MASK, IDLE_ON_VALUE);
+}
+
+static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+{
+ DRM_DEBUG_KMS("Wait for panel power off time\n");
+ ironlake_wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE);
+}
+
+static void ironlake_wait_panel_power_cycle(struct intel_dp *intel_dp)
+{
+ DRM_DEBUG_KMS("Wait for panel power cycle\n");
+ ironlake_wait_panel_status(intel_dp, IDLE_CYCLE_MASK, IDLE_CYCLE_VALUE);
+}
+
+
+/* Read the current pp_control value, unlocking the register if it
+ * is locked
+ */
+
+static u32 ironlake_get_pp_control(struct drm_i915_private *dev_priv)
+{
+ u32 control = I915_READ(PCH_PP_CONTROL);
+
+ control &= ~PANEL_UNLOCK_MASK;
+ control |= PANEL_UNLOCK_REGS;
+ return control;
}
static void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
"eDP VDD already requested on\n");
intel_dp->want_panel_vdd = true;
+
if (ironlake_edp_have_panel_vdd(intel_dp)) {
DRM_DEBUG_KMS("eDP VDD already on\n");
return;
}
- ironlake_wait_panel_off(intel_dp);
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
+ if (!ironlake_edp_have_panel_power(intel_dp))
+ ironlake_wait_panel_power_cycle(intel_dp);
+
+ pp = ironlake_get_pp_control(dev_priv);
pp |= EDP_FORCE_VDD;
I915_WRITE(PCH_PP_CONTROL, pp);
POSTING_READ(PCH_PP_CONTROL);
u32 pp;
if (!intel_dp->want_panel_vdd && ironlake_edp_have_panel_vdd(intel_dp)) {
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
+ pp = ironlake_get_pp_control(dev_priv);
pp &= ~EDP_FORCE_VDD;
I915_WRITE(PCH_PP_CONTROL, pp);
POSTING_READ(PCH_PP_CONTROL);
/* Make sure sequencer is idle before allowing subsequent activity */
DRM_DEBUG_KMS("PCH_PP_STATUS: 0x%08x PCH_PP_CONTROL: 0x%08x\n",
I915_READ(PCH_PP_STATUS), I915_READ(PCH_PP_CONTROL));
- intel_dp->panel_off_jiffies = jiffies;
+
+ msleep(intel_dp->panel_power_down_delay);
}
}
struct intel_dp, panel_vdd_work);
struct drm_device *dev = intel_dp->base.base.dev;
- mutex_lock(&dev->struct_mutex);
+ mutex_lock(&dev->mode_config.mutex);
ironlake_panel_vdd_off_sync(intel_dp);
- mutex_unlock(&dev->struct_mutex);
+ mutex_unlock(&dev->mode_config.mutex);
}
static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
DRM_DEBUG_KMS("Turn eDP VDD off %d\n", intel_dp->want_panel_vdd);
WARN(!intel_dp->want_panel_vdd, "eDP VDD not forced on");
-
+
intel_dp->want_panel_vdd = false;
if (sync) {
}
}
-/* Returns true if the panel was already on when called */
static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
{
struct drm_device *dev = intel_dp->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 pp, idle_on_mask = PP_ON | PP_SEQUENCE_STATE_ON_IDLE;
+ u32 pp;
if (!is_edp(intel_dp))
return;
- if (ironlake_edp_have_panel_power(intel_dp))
+
+ DRM_DEBUG_KMS("Turn eDP power on\n");
+
+ if (ironlake_edp_have_panel_power(intel_dp)) {
+ DRM_DEBUG_KMS("eDP power already on\n");
return;
+ }
- ironlake_wait_panel_off(intel_dp);
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
+ ironlake_wait_panel_power_cycle(intel_dp);
+ pp = ironlake_get_pp_control(dev_priv);
if (IS_GEN5(dev)) {
/* ILK workaround: disable reset around power sequence */
pp &= ~PANEL_POWER_RESET;
}
pp |= POWER_TARGET_ON;
+ if (!IS_GEN5(dev))
+ pp |= PANEL_POWER_RESET;
+
I915_WRITE(PCH_PP_CONTROL, pp);
POSTING_READ(PCH_PP_CONTROL);
- if (wait_for((I915_READ(PCH_PP_STATUS) & idle_on_mask) == idle_on_mask,
- 5000))
- DRM_ERROR("panel on wait timed out: 0x%08x\n",
- I915_READ(PCH_PP_STATUS));
+ ironlake_wait_panel_on(intel_dp);
if (IS_GEN5(dev)) {
pp |= PANEL_POWER_RESET; /* restore panel reset bit */
}
}
-static void ironlake_edp_panel_off(struct drm_encoder *encoder)
+static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
{
- struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
- struct drm_device *dev = encoder->dev;
+ struct drm_device *dev = intel_dp->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 pp, idle_off_mask = PP_ON | PP_SEQUENCE_MASK |
- PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK;
+ u32 pp;
if (!is_edp(intel_dp))
return;
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
- if (IS_GEN5(dev)) {
- /* ILK workaround: disable reset around power sequence */
- pp &= ~PANEL_POWER_RESET;
- I915_WRITE(PCH_PP_CONTROL, pp);
- POSTING_READ(PCH_PP_CONTROL);
- }
+ DRM_DEBUG_KMS("Turn eDP power off\n");
- intel_dp->panel_off_jiffies = jiffies;
+ WARN(intel_dp->want_panel_vdd, "Cannot turn power off while VDD is on\n");
- if (IS_GEN5(dev)) {
- pp &= ~POWER_TARGET_ON;
- I915_WRITE(PCH_PP_CONTROL, pp);
- POSTING_READ(PCH_PP_CONTROL);
- pp &= ~POWER_TARGET_ON;
- I915_WRITE(PCH_PP_CONTROL, pp);
- POSTING_READ(PCH_PP_CONTROL);
- msleep(intel_dp->panel_power_cycle_delay);
-
- if (wait_for((I915_READ(PCH_PP_STATUS) & idle_off_mask) == 0, 5000))
- DRM_ERROR("panel off wait timed out: 0x%08x\n",
- I915_READ(PCH_PP_STATUS));
+ pp = ironlake_get_pp_control(dev_priv);
+ pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+ I915_WRITE(PCH_PP_CONTROL, pp);
+ POSTING_READ(PCH_PP_CONTROL);
- pp |= PANEL_POWER_RESET; /* restore panel reset bit */
- I915_WRITE(PCH_PP_CONTROL, pp);
- POSTING_READ(PCH_PP_CONTROL);
- }
+ ironlake_wait_panel_off(intel_dp);
}
static void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
* allowing it to appear.
*/
msleep(intel_dp->backlight_on_delay);
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
+ pp = ironlake_get_pp_control(dev_priv);
pp |= EDP_BLC_ENABLE;
I915_WRITE(PCH_PP_CONTROL, pp);
POSTING_READ(PCH_PP_CONTROL);
return;
DRM_DEBUG_KMS("\n");
- pp = I915_READ(PCH_PP_CONTROL);
- pp &= ~PANEL_UNLOCK_MASK;
- pp |= PANEL_UNLOCK_REGS;
+ pp = ironlake_get_pp_control(dev_priv);
pp &= ~EDP_BLC_ENABLE;
I915_WRITE(PCH_PP_CONTROL, pp);
POSTING_READ(PCH_PP_CONTROL);
{
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ ironlake_edp_backlight_off(intel_dp);
+ ironlake_edp_panel_off(intel_dp);
+
/* Wake up the sink first */
ironlake_edp_panel_vdd_on(intel_dp);
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+ intel_dp_link_down(intel_dp);
ironlake_edp_panel_vdd_off(intel_dp, false);
/* Make sure the panel is off before trying to
* change the mode
*/
- ironlake_edp_backlight_off(intel_dp);
- intel_dp_link_down(intel_dp);
- ironlake_edp_panel_off(encoder);
}
static void intel_dp_commit(struct drm_encoder *encoder)
intel_dp_start_link_train(intel_dp);
ironlake_edp_panel_on(intel_dp);
ironlake_edp_panel_vdd_off(intel_dp, true);
-
intel_dp_complete_link_train(intel_dp);
ironlake_edp_backlight_on(intel_dp);
uint32_t dp_reg = I915_READ(intel_dp->output_reg);
if (mode != DRM_MODE_DPMS_ON) {
+ ironlake_edp_backlight_off(intel_dp);
+ ironlake_edp_panel_off(intel_dp);
+
ironlake_edp_panel_vdd_on(intel_dp);
- if (is_edp(intel_dp))
- ironlake_edp_backlight_off(intel_dp);
intel_dp_sink_dpms(intel_dp, mode);
intel_dp_link_down(intel_dp);
- ironlake_edp_panel_off(encoder);
- if (is_edp(intel_dp) && !is_pch_edp(intel_dp))
- ironlake_edp_pll_off(encoder);
ironlake_edp_panel_vdd_off(intel_dp, false);
+
+ if (is_cpu_edp(intel_dp))
+ ironlake_edp_pll_off(encoder);
} else {
+ if (is_cpu_edp(intel_dp))
+ ironlake_edp_pll_on(encoder);
+
ironlake_edp_panel_vdd_on(intel_dp);
intel_dp_sink_dpms(intel_dp, mode);
if (!(dp_reg & DP_PORT_EN)) {
ironlake_edp_panel_on(intel_dp);
ironlake_edp_panel_vdd_off(intel_dp, true);
intel_dp_complete_link_train(intel_dp);
- ironlake_edp_backlight_on(intel_dp);
} else
ironlake_edp_panel_vdd_off(intel_dp, false);
ironlake_edp_backlight_on(intel_dp);
* link status information
*/
static bool
-intel_dp_get_link_status(struct intel_dp *intel_dp)
+intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
{
return intel_dp_aux_native_read_retry(intel_dp,
DP_LANE0_1_STATUS,
- intel_dp->link_status,
+ link_status,
DP_LINK_STATUS_SIZE);
}
}
static uint8_t
-intel_get_adjust_request_voltage(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_voltage(uint8_t adjust_request[2],
int lane)
{
- int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
int s = ((lane & 1) ?
DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
- uint8_t l = intel_dp_link_status(link_status, i);
+ uint8_t l = adjust_request[lane>>1];
return ((l >> s) & 3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
}
static uint8_t
-intel_get_adjust_request_pre_emphasis(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_pre_emphasis(uint8_t adjust_request[2],
int lane)
{
- int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
int s = ((lane & 1) ?
DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
- uint8_t l = intel_dp_link_status(link_status, i);
+ uint8_t l = adjust_request[lane>>1];
return ((l >> s) & 3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
}
* These are source-specific values; current Intel hardware supports
* a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
*/
-#define I830_DP_VOLTAGE_MAX DP_TRAIN_VOLTAGE_SWING_800
static uint8_t
-intel_dp_pre_emphasis_max(uint8_t voltage_swing)
+intel_dp_voltage_max(struct intel_dp *intel_dp)
{
- switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
- case DP_TRAIN_VOLTAGE_SWING_400:
- return DP_TRAIN_PRE_EMPHASIS_6;
- case DP_TRAIN_VOLTAGE_SWING_600:
- return DP_TRAIN_PRE_EMPHASIS_6;
- case DP_TRAIN_VOLTAGE_SWING_800:
- return DP_TRAIN_PRE_EMPHASIS_3_5;
- case DP_TRAIN_VOLTAGE_SWING_1200:
- default:
- return DP_TRAIN_PRE_EMPHASIS_0;
+ struct drm_device *dev = intel_dp->base.base.dev;
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp))
+ return DP_TRAIN_VOLTAGE_SWING_800;
+ else if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ return DP_TRAIN_VOLTAGE_SWING_1200;
+ else
+ return DP_TRAIN_VOLTAGE_SWING_800;
+}
+
+static uint8_t
+intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
+{
+ struct drm_device *dev = intel_dp->base.base.dev;
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+ case DP_TRAIN_VOLTAGE_SWING_400:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_600:
+ case DP_TRAIN_VOLTAGE_SWING_800:
+ return DP_TRAIN_PRE_EMPHASIS_3_5;
+ default:
+ return DP_TRAIN_PRE_EMPHASIS_0;
+ }
+ } else {
+ switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+ case DP_TRAIN_VOLTAGE_SWING_400:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_600:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_800:
+ return DP_TRAIN_PRE_EMPHASIS_3_5;
+ case DP_TRAIN_VOLTAGE_SWING_1200:
+ default:
+ return DP_TRAIN_PRE_EMPHASIS_0;
+ }
}
}
static void
-intel_get_adjust_train(struct intel_dp *intel_dp)
+intel_get_adjust_train(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
{
uint8_t v = 0;
uint8_t p = 0;
int lane;
+ uint8_t *adjust_request = link_status + (DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS);
+ uint8_t voltage_max;
+ uint8_t preemph_max;
for (lane = 0; lane < intel_dp->lane_count; lane++) {
- uint8_t this_v = intel_get_adjust_request_voltage(intel_dp->link_status, lane);
- uint8_t this_p = intel_get_adjust_request_pre_emphasis(intel_dp->link_status, lane);
+ uint8_t this_v = intel_get_adjust_request_voltage(adjust_request, lane);
+ uint8_t this_p = intel_get_adjust_request_pre_emphasis(adjust_request, lane);
if (this_v > v)
v = this_v;
p = this_p;
}
- if (v >= I830_DP_VOLTAGE_MAX)
- v = I830_DP_VOLTAGE_MAX | DP_TRAIN_MAX_SWING_REACHED;
+ voltage_max = intel_dp_voltage_max(intel_dp);
+ if (v >= voltage_max)
+ v = voltage_max | DP_TRAIN_MAX_SWING_REACHED;
- if (p >= intel_dp_pre_emphasis_max(v))
- p = intel_dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
+ preemph_max = intel_dp_pre_emphasis_max(intel_dp, v);
+ if (p >= preemph_max)
+ p = preemph_max | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
for (lane = 0; lane < 4; lane++)
intel_dp->train_set[lane] = v | p;
}
static uint32_t
-intel_dp_signal_levels(uint8_t train_set, int lane_count)
+intel_dp_signal_levels(uint8_t train_set)
{
uint32_t signal_levels = 0;
}
}
+/* Gen7's DP voltage swing and pre-emphasis control */
+static uint32_t
+intel_gen7_edp_signal_levels(uint8_t train_set)
+{
+ int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
+ DP_TRAIN_PRE_EMPHASIS_MASK);
+ switch (signal_levels) {
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_400MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_400MV_3_5DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
+ return EDP_LINK_TRAIN_400MV_6DB_IVB;
+
+ case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_600MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_600MV_3_5DB_IVB;
+
+ case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_800MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_800MV_3_5DB_IVB;
+
+ default:
+ DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
+ "0x%x\n", signal_levels);
+ return EDP_LINK_TRAIN_500MV_0DB_IVB;
+ }
+}
+
static uint8_t
intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
int lane)
{
- int i = DP_LANE0_1_STATUS + (lane >> 1);
int s = (lane & 1) * 4;
- uint8_t l = intel_dp_link_status(link_status, i);
+ uint8_t l = link_status[lane>>1];
return (l >> s) & 0xf;
}
DP_LANE_CHANNEL_EQ_DONE|\
DP_LANE_SYMBOL_LOCKED)
static bool
-intel_channel_eq_ok(struct intel_dp *intel_dp)
+intel_channel_eq_ok(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
{
uint8_t lane_align;
uint8_t lane_status;
int lane;
- lane_align = intel_dp_link_status(intel_dp->link_status,
+ lane_align = intel_dp_link_status(link_status,
DP_LANE_ALIGN_STATUS_UPDATED);
if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
return false;
for (lane = 0; lane < intel_dp->lane_count; lane++) {
- lane_status = intel_get_lane_status(intel_dp->link_status, lane);
+ lane_status = intel_get_lane_status(link_status, lane);
if ((lane_status & CHANNEL_EQ_BITS) != CHANNEL_EQ_BITS)
return false;
}
ret = intel_dp_aux_native_write(intel_dp,
DP_TRAINING_LANE0_SET,
- intel_dp->train_set, 4);
- if (ret != 4)
+ intel_dp->train_set,
+ intel_dp->lane_count);
+ if (ret != intel_dp->lane_count)
return false;
return true;
int i;
uint8_t voltage;
bool clock_recovery = false;
- int tries;
+ int voltage_tries, loop_tries;
u32 reg;
uint32_t DP = intel_dp->DP;
DP_LINK_CONFIGURATION_SIZE);
DP |= DP_PORT_EN;
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
DP &= ~DP_LINK_TRAIN_MASK_CPT;
else
DP &= ~DP_LINK_TRAIN_MASK;
memset(intel_dp->train_set, 0, 4);
voltage = 0xff;
- tries = 0;
+ voltage_tries = 0;
+ loop_tries = 0;
clock_recovery = false;
for (;;) {
/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
+ uint8_t link_status[DP_LINK_STATUS_SIZE];
uint32_t signal_levels;
- if (IS_GEN6(dev) && is_edp(intel_dp)) {
+
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ signal_levels = intel_gen7_edp_signal_levels(intel_dp->train_set[0]);
+ DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_IVB) | signal_levels;
+ } else if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
} else {
- signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+ signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
+ DRM_DEBUG_KMS("training pattern 1 signal levels %08x\n", signal_levels);
DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_PAT_1_CPT;
else
reg = DP | DP_LINK_TRAIN_PAT_1;
/* Set training pattern 1 */
udelay(100);
- if (!intel_dp_get_link_status(intel_dp))
+ if (!intel_dp_get_link_status(intel_dp, link_status)) {
+ DRM_ERROR("failed to get link status\n");
break;
+ }
- if (intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+ if (intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+ DRM_DEBUG_KMS("clock recovery OK\n");
clock_recovery = true;
break;
}
for (i = 0; i < intel_dp->lane_count; i++)
if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
break;
- if (i == intel_dp->lane_count)
- break;
+ if (i == intel_dp->lane_count) {
+ ++loop_tries;
+ if (loop_tries == 5) {
+ DRM_DEBUG_KMS("too many full retries, give up\n");
+ break;
+ }
+ memset(intel_dp->train_set, 0, 4);
+ voltage_tries = 0;
+ continue;
+ }
/* Check to see if we've tried the same voltage 5 times */
if ((intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK) == voltage) {
- ++tries;
- if (tries == 5)
+ ++voltage_tries;
+ if (voltage_tries == 5) {
+ DRM_DEBUG_KMS("too many voltage retries, give up\n");
break;
+ }
} else
- tries = 0;
+ voltage_tries = 0;
voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK;
/* Compute new intel_dp->train_set as requested by target */
- intel_get_adjust_train(intel_dp);
+ intel_get_adjust_train(intel_dp, link_status);
}
intel_dp->DP = DP;
for (;;) {
/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
uint32_t signal_levels;
+ uint8_t link_status[DP_LINK_STATUS_SIZE];
if (cr_tries > 5) {
DRM_ERROR("failed to train DP, aborting\n");
break;
}
- if (IS_GEN6(dev) && is_edp(intel_dp)) {
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ signal_levels = intel_gen7_edp_signal_levels(intel_dp->train_set[0]);
+ DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_IVB) | signal_levels;
+ } else if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
} else {
- signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+ signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_PAT_2_CPT;
else
reg = DP | DP_LINK_TRAIN_PAT_2;
break;
udelay(400);
- if (!intel_dp_get_link_status(intel_dp))
+ if (!intel_dp_get_link_status(intel_dp, link_status))
break;
/* Make sure clock is still ok */
- if (!intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+ if (!intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
intel_dp_start_link_train(intel_dp);
cr_tries++;
continue;
}
- if (intel_channel_eq_ok(intel_dp)) {
+ if (intel_channel_eq_ok(intel_dp, link_status)) {
channel_eq = true;
break;
}
}
/* Compute new intel_dp->train_set as requested by target */
- intel_get_adjust_train(intel_dp);
+ intel_get_adjust_train(intel_dp, link_status);
++tries;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_OFF_CPT;
else
reg = DP | DP_LINK_TRAIN_OFF;
udelay(100);
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp)) {
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp))) {
DP &= ~DP_LINK_TRAIN_MASK_CPT;
I915_WRITE(intel_dp->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE_CPT);
} else {
msleep(17);
- if (is_edp(intel_dp))
- DP |= DP_LINK_TRAIN_OFF;
+ if (is_edp(intel_dp)) {
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
+ DP |= DP_LINK_TRAIN_OFF_CPT;
+ else
+ DP |= DP_LINK_TRAIN_OFF;
+ }
if (!HAS_PCH_CPT(dev) &&
I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
intel_dp_check_link_status(struct intel_dp *intel_dp)
{
u8 sink_irq_vector;
+ u8 link_status[DP_LINK_STATUS_SIZE];
if (intel_dp->dpms_mode != DRM_MODE_DPMS_ON)
return;
return;
/* Try to read receiver status if the link appears to be up */
- if (!intel_dp_get_link_status(intel_dp)) {
+ if (!intel_dp_get_link_status(intel_dp, link_status)) {
intel_dp_link_down(intel_dp);
return;
}
DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
}
- if (!intel_channel_eq_ok(intel_dp)) {
+ if (!intel_channel_eq_ok(intel_dp, link_status)) {
DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
drm_get_encoder_name(&intel_dp->base.base));
intel_dp_start_link_train(intel_dp);
continue;
intel_dp = enc_to_intel_dp(encoder);
- if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT)
+ if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+ intel_dp->base.type == INTEL_OUTPUT_EDP)
return intel_dp->output_reg;
}
cur.t8 = (pp_on & PANEL_LIGHT_ON_DELAY_MASK) >>
PANEL_LIGHT_ON_DELAY_SHIFT;
-
+
cur.t9 = (pp_off & PANEL_LIGHT_OFF_DELAY_MASK) >>
PANEL_LIGHT_OFF_DELAY_SHIFT;
DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
- intel_dp->panel_off_jiffies = jiffies - intel_dp->panel_power_down_delay;
-
ironlake_edp_panel_vdd_on(intel_dp);
ret = intel_dp_get_dpcd(intel_dp);
ironlake_edp_panel_vdd_off(intel_dp, false);
+
if (ret) {
if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11)
dev_priv->no_aux_handshake =
/* drm_display_mode->private_flags */
#define INTEL_MODE_PIXEL_MULTIPLIER_SHIFT (0x0)
#define INTEL_MODE_PIXEL_MULTIPLIER_MASK (0xf << INTEL_MODE_PIXEL_MULTIPLIER_SHIFT)
+#define INTEL_MODE_DP_FORCE_6BPC (0x10)
static inline void
intel_mode_set_pixel_multiplier(struct drm_display_mode *mode,
DMI_MATCH(DMI_PRODUCT_NAME, "EB1007"),
},
},
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Asus AT5NM10T-I",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "AT5NM10T-I"),
+ },
+ },
{ } /* terminating entry */
};
if (HAS_PCH_SPLIT(dev)) {
max >>= 16;
} else {
- if (IS_PINEVIEW(dev)) {
+ if (INTEL_INFO(dev)->gen < 4)
max >>= 17;
- } else {
+ else
max >>= 16;
- if (INTEL_INFO(dev)->gen < 4)
- max &= ~1;
- }
if (is_backlight_combination_mode(dev))
max *= 0xff;
val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
} else {
val = I915_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
- if (IS_PINEVIEW(dev))
+ if (INTEL_INFO(dev)->gen < 4)
val >>= 1;
if (is_backlight_combination_mode(dev)) {
u8 lbpc;
- val &= ~1;
pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc);
val *= lbpc;
}
}
tmp = I915_READ(BLC_PWM_CTL);
- if (IS_PINEVIEW(dev)) {
- tmp &= ~(BACKLIGHT_DUTY_CYCLE_MASK - 1);
+ if (INTEL_INFO(dev)->gen < 4)
level <<= 1;
- } else
- tmp &= ~BACKLIGHT_DUTY_CYCLE_MASK;
+ tmp &= ~BACKLIGHT_DUTY_CYCLE_MASK;
I915_WRITE(BLC_PWM_CTL, tmp | level);
}
static int intel_panel_get_brightness(struct backlight_device *bd)
{
struct drm_device *dev = bl_get_data(bd);
- return intel_panel_get_backlight(dev);
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ return dev_priv->backlight_level;
}
static const struct backlight_ops intel_panel_bl_ops = {
#define IS_TMDS(c) (c->output_flag & SDVO_TMDS_MASK)
#define IS_LVDS(c) (c->output_flag & SDVO_LVDS_MASK)
#define IS_TV_OR_LVDS(c) (c->output_flag & (SDVO_TV_MASK | SDVO_LVDS_MASK))
+#define IS_DIGITAL(c) (c->output_flag & (SDVO_TMDS_MASK | SDVO_LVDS_MASK))
static const char *tv_format_names[] = {
}
sdvox |= (9 << 19) | SDVO_BORDER_ENABLE;
}
- if (intel_crtc->pipe == 1)
- sdvox |= SDVO_PIPE_B_SELECT;
+
+ if (INTEL_PCH_TYPE(dev) >= PCH_CPT)
+ sdvox |= TRANSCODER_CPT(intel_crtc->pipe);
+ else
+ sdvox |= TRANSCODER(intel_crtc->pipe);
+
if (intel_sdvo->has_hdmi_audio)
sdvox |= SDVO_AUDIO_ENABLE;
return status;
}
+static bool
+intel_sdvo_connector_matches_edid(struct intel_sdvo_connector *sdvo,
+ struct edid *edid)
+{
+ bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL);
+ bool connector_is_digital = !!IS_DIGITAL(sdvo);
+
+ DRM_DEBUG_KMS("connector_is_digital? %d, monitor_is_digital? %d\n",
+ connector_is_digital, monitor_is_digital);
+ return connector_is_digital == monitor_is_digital;
+}
+
static enum drm_connector_status
intel_sdvo_detect(struct drm_connector *connector, bool force)
{
if (edid == NULL)
edid = intel_sdvo_get_analog_edid(connector);
if (edid != NULL) {
- if (edid->input & DRM_EDID_INPUT_DIGITAL)
- ret = connector_status_disconnected;
- else
+ if (intel_sdvo_connector_matches_edid(intel_sdvo_connector,
+ edid))
ret = connector_status_connected;
+ else
+ ret = connector_status_disconnected;
+
connector->display_info.raw_edid = NULL;
kfree(edid);
} else
edid = intel_sdvo_get_analog_edid(connector);
if (edid != NULL) {
- struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
- bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL);
- bool connector_is_digital = !!IS_TMDS(intel_sdvo_connector);
-
- if (connector_is_digital == monitor_is_digital) {
+ if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector),
+ edid)) {
drm_mode_connector_update_edid_property(connector, edid);
drm_add_edid_modes(connector, edid);
}
spin_unlock_irqrestore(&dev->event_lock, flags);
return 0;
}
+
+int
+nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
+ struct drm_mode_create_dumb *args)
+{
+ struct nouveau_bo *bo;
+ int ret;
+
+ args->pitch = roundup(args->width * (args->bpp / 8), 256);
+ args->size = args->pitch * args->height;
+ args->size = roundup(args->size, PAGE_SIZE);
+
+ ret = nouveau_gem_new(dev, args->size, 0, TTM_PL_FLAG_VRAM, 0, 0, &bo);
+ if (ret)
+ return ret;
+
+ ret = drm_gem_handle_create(file_priv, bo->gem, &args->handle);
+ drm_gem_object_unreference_unlocked(bo->gem);
+ return ret;
+}
+
+int
+nouveau_display_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
+ uint32_t handle)
+{
+ return drm_gem_handle_delete(file_priv, handle);
+}
+
+int
+nouveau_display_dumb_map_offset(struct drm_file *file_priv,
+ struct drm_device *dev,
+ uint32_t handle, uint64_t *poffset)
+{
+ struct drm_gem_object *gem;
+
+ gem = drm_gem_object_lookup(dev, file_priv, handle);
+ if (gem) {
+ struct nouveau_bo *bo = gem->driver_private;
+ *poffset = bo->bo.addr_space_offset;
+ drm_gem_object_unreference_unlocked(gem);
+ return 0;
+ }
+
+ return -ENOENT;
+}
.gem_open_object = nouveau_gem_object_open,
.gem_close_object = nouveau_gem_object_close,
+ .dumb_create = nouveau_display_dumb_create,
+ .dumb_map_offset = nouveau_display_dumb_map_offset,
+ .dumb_destroy = nouveau_display_dumb_destroy,
+
.name = DRIVER_NAME,
.desc = DRIVER_DESC,
#ifdef GIT_REVISION
struct drm_pending_vblank_event *event);
int nouveau_finish_page_flip(struct nouveau_channel *,
struct nouveau_page_flip_state *);
+int nouveau_display_dumb_create(struct drm_file *, struct drm_device *,
+ struct drm_mode_create_dumb *args);
+int nouveau_display_dumb_map_offset(struct drm_file *, struct drm_device *,
+ uint32_t handle, uint64_t *offset);
+int nouveau_display_dumb_destroy(struct drm_file *, struct drm_device *,
+ uint32_t handle);
/* nv10_gpio.c */
int nv10_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag);
return ret;
}
- ret = drm_mm_init(&chan->ramin_heap, base, size);
+ ret = drm_mm_init(&chan->ramin_heap, base, size - base);
if (ret) {
NV_ERROR(dev, "Error creating PRAMIN heap: %d\n", ret);
nouveau_gpuobj_ref(NULL, &chan->ramin);
pci_unmap_page(dev->pdev, nvbe->pages[nvbe->nr_pages],
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
}
+ nvbe->unmap_pages = false;
}
+
+ nvbe->pages = NULL;
}
static void
struct drm_nouveau_private *dev_priv = dev->dev_private;
struct nv50_display *disp = nv50_display(dev);
u32 unk30 = nv_rd32(dev, 0x610030), mc;
- int i, crtc, or, type = OUTPUT_ANY;
+ int i, crtc, or = 0, type = OUTPUT_ANY;
NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30);
disp->irq.dcb = NULL;
struct nv50_display *disp = nv50_display(dev);
u32 unk30 = nv_rd32(dev, 0x610030), tmp, pclk, script, mc = 0;
struct dcb_entry *dcb;
- int i, crtc, or, type = OUTPUT_ANY;
+ int i, crtc, or = 0, type = OUTPUT_ANY;
NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30);
dcb = disp->irq.dcb;
u8 tpnr[GPC_MAX];
int i, gpc, tpc;
+ nv_wr32(dev, TP_UNIT(0, 0, 0x5c), 1); /* affects TFB offset queries */
+
/*
* TP ROP UNKVAL(magic_not_rop_nr)
* 450: 4/0/0/0 2 3
continue;
if (nv_partner != nv_encoder &&
- nv_partner->dcb->or == nv_encoder->or) {
+ nv_partner->dcb->or == nv_encoder->dcb->or) {
if (nv_partner->last_dpms == DRM_MODE_DPMS_ON)
return;
break;
return -EINVAL;
}
- if (tiling_flags & RADEON_TILING_MACRO)
+ if (tiling_flags & RADEON_TILING_MACRO) {
+ if (rdev->family >= CHIP_CAYMAN)
+ tmp = rdev->config.cayman.tile_config;
+ else
+ tmp = rdev->config.evergreen.tile_config;
+
+ switch ((tmp & 0xf0) >> 4) {
+ case 0: /* 4 banks */
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
+ break;
+ case 1: /* 8 banks */
+ default:
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
+ break;
+ case 2: /* 16 banks */
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
+ break;
+ }
+
+ switch ((tmp & 0xf000) >> 12) {
+ case 0: /* 1KB rows */
+ default:
+ fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_1KB);
+ break;
+ case 1: /* 2KB rows */
+ fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_2KB);
+ break;
+ case 2: /* 4KB rows */
+ fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_4KB);
+ break;
+ }
+
fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1);
- else if (tiling_flags & RADEON_TILING_MICRO)
+ } else if (tiling_flags & RADEON_TILING_MICRO)
fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1);
switch (radeon_crtc->crtc_id) {
{
struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
u32 tmp = RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset);
+ int i;
/* Lock the graphics update lock */
tmp |= EVERGREEN_GRPH_UPDATE_LOCK;
(u32)crtc_base);
/* Wait for update_pending to go high. */
- while (!(RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING)
+ break;
+ udelay(1);
+ }
DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
/* Unlock the lock, so double-buffering can take place inside vblank */
rdev->accel_working = false;
}
}
+
+ /* Don't start up if the MC ucode is missing on BTC parts.
+ * The default clocks and voltages before the MC ucode
+ * is loaded are not suffient for advanced operations.
+ */
+ if (ASIC_IS_DCE5(rdev)) {
+ if (!rdev->mc_fw && !(rdev->flags & RADEON_IS_IGP)) {
+ DRM_ERROR("radeon: MC ucode required for NI+.\n");
+ return -EINVAL;
+ }
+ }
+
return 0;
}
u32 group_size;
u32 nbanks;
u32 npipes;
+ u32 row_size;
/* value we track */
u32 nsamples;
u32 cb_color_base_last[12];
struct radeon_bo *db_s_write_bo;
};
+static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
+{
+ if (tiling_flags & RADEON_TILING_MACRO)
+ return ARRAY_2D_TILED_THIN1;
+ else if (tiling_flags & RADEON_TILING_MICRO)
+ return ARRAY_1D_TILED_THIN1;
+ else
+ return ARRAY_LINEAR_GENERAL;
+}
+
+static u32 evergreen_cs_get_num_banks(u32 nbanks)
+{
+ switch (nbanks) {
+ case 2:
+ return ADDR_SURF_2_BANK;
+ case 4:
+ return ADDR_SURF_4_BANK;
+ case 8:
+ default:
+ return ADDR_SURF_8_BANK;
+ case 16:
+ return ADDR_SURF_16_BANK;
+ }
+}
+
+static u32 evergreen_cs_get_tile_split(u32 row_size)
+{
+ switch (row_size) {
+ case 1:
+ default:
+ return ADDR_SURF_TILE_SPLIT_1KB;
+ case 2:
+ return ADDR_SURF_TILE_SPLIT_2KB;
+ case 4:
+ return ADDR_SURF_TILE_SPLIT_4KB;
+ }
+}
+
static void evergreen_cs_track_init(struct evergreen_cs_track *track)
{
int i;
}
break;
case DB_Z_INFO:
- r = evergreen_cs_packet_next_reloc(p, &reloc);
- if (r) {
- dev_warn(p->dev, "bad SET_CONTEXT_REG "
- "0x%04X\n", reg);
- return -EINVAL;
- }
track->db_z_info = radeon_get_ib_value(p, idx);
- ib[idx] &= ~Z_ARRAY_MODE(0xf);
- track->db_z_info &= ~Z_ARRAY_MODE(0xf);
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else {
- ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ r = evergreen_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ dev_warn(p->dev, "bad SET_CONTEXT_REG "
+ "0x%04X\n", reg);
+ return -EINVAL;
+ }
+ ib[idx] &= ~Z_ARRAY_MODE(0xf);
+ track->db_z_info &= ~Z_ARRAY_MODE(0xf);
+ ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ ib[idx] |= DB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+ }
}
break;
case DB_STENCIL_INFO:
case CB_COLOR5_INFO:
case CB_COLOR6_INFO:
case CB_COLOR7_INFO:
- r = evergreen_cs_packet_next_reloc(p, &reloc);
- if (r) {
- dev_warn(p->dev, "bad SET_CONTEXT_REG "
- "0x%04X\n", reg);
- return -EINVAL;
- }
tmp = (reg - CB_COLOR0_INFO) / 0x3c;
track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ r = evergreen_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ dev_warn(p->dev, "bad SET_CONTEXT_REG "
+ "0x%04X\n", reg);
+ return -EINVAL;
+ }
+ ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
}
break;
case CB_COLOR8_INFO:
case CB_COLOR9_INFO:
case CB_COLOR10_INFO:
case CB_COLOR11_INFO:
- r = evergreen_cs_packet_next_reloc(p, &reloc);
- if (r) {
- dev_warn(p->dev, "bad SET_CONTEXT_REG "
- "0x%04X\n", reg);
- return -EINVAL;
- }
tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- } else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
- ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
- track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ r = evergreen_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ dev_warn(p->dev, "bad SET_CONTEXT_REG "
+ "0x%04X\n", reg);
+ return -EINVAL;
+ }
+ ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
}
break;
case CB_COLOR0_PITCH:
case CB_COLOR9_ATTRIB:
case CB_COLOR10_ATTRIB:
case CB_COLOR11_ATTRIB:
+ r = evergreen_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ dev_warn(p->dev, "bad SET_CONTEXT_REG "
+ "0x%04X\n", reg);
+ return -EINVAL;
+ }
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ ib[idx] |= CB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+ }
break;
case CB_COLOR0_DIM:
case CB_COLOR1_DIM:
return -EINVAL;
}
ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ ib[idx+1+(i*8)+1] |=
+ TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx+1+(i*8)+6] |=
+ TEX_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+ ib[idx+1+(i*8)+7] |=
+ TEX_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ }
+ }
texture = reloc->robj;
/* tex mip base */
r = evergreen_cs_packet_next_reloc(p, &reloc);
{
struct radeon_cs_packet pkt;
struct evergreen_cs_track *track;
+ u32 tmp;
int r;
if (p->track == NULL) {
if (track == NULL)
return -ENOMEM;
evergreen_cs_track_init(track);
- track->npipes = p->rdev->config.evergreen.tiling_npipes;
- track->nbanks = p->rdev->config.evergreen.tiling_nbanks;
- track->group_size = p->rdev->config.evergreen.tiling_group_size;
+ if (p->rdev->family >= CHIP_CAYMAN)
+ tmp = p->rdev->config.cayman.tile_config;
+ else
+ tmp = p->rdev->config.evergreen.tile_config;
+
+ switch (tmp & 0xf) {
+ case 0:
+ track->npipes = 1;
+ break;
+ case 1:
+ default:
+ track->npipes = 2;
+ break;
+ case 2:
+ track->npipes = 4;
+ break;
+ case 3:
+ track->npipes = 8;
+ break;
+ }
+
+ switch ((tmp & 0xf0) >> 4) {
+ case 0:
+ track->nbanks = 4;
+ break;
+ case 1:
+ default:
+ track->nbanks = 8;
+ break;
+ case 2:
+ track->nbanks = 16;
+ break;
+ }
+
+ switch ((tmp & 0xf00) >> 8) {
+ case 0:
+ track->group_size = 256;
+ break;
+ case 1:
+ default:
+ track->group_size = 512;
+ break;
+ }
+
+ switch ((tmp & 0xf000) >> 12) {
+ case 0:
+ track->row_size = 1;
+ break;
+ case 1:
+ default:
+ track->row_size = 2;
+ break;
+ case 2:
+ track->row_size = 4;
+ break;
+ }
+
p->track = track;
}
do {
# define EVERGREEN_GRPH_DEPTH_8BPP 0
# define EVERGREEN_GRPH_DEPTH_16BPP 1
# define EVERGREEN_GRPH_DEPTH_32BPP 2
+# define EVERGREEN_GRPH_NUM_BANKS(x) (((x) & 0x3) << 2)
+# define EVERGREEN_ADDR_SURF_2_BANK 0
+# define EVERGREEN_ADDR_SURF_4_BANK 1
+# define EVERGREEN_ADDR_SURF_8_BANK 2
+# define EVERGREEN_ADDR_SURF_16_BANK 3
+# define EVERGREEN_GRPH_Z(x) (((x) & 0x3) << 4)
+# define EVERGREEN_GRPH_BANK_WIDTH(x) (((x) & 0x3) << 6)
+# define EVERGREEN_ADDR_SURF_BANK_WIDTH_1 0
+# define EVERGREEN_ADDR_SURF_BANK_WIDTH_2 1
+# define EVERGREEN_ADDR_SURF_BANK_WIDTH_4 2
+# define EVERGREEN_ADDR_SURF_BANK_WIDTH_8 3
# define EVERGREEN_GRPH_FORMAT(x) (((x) & 0x7) << 8)
/* 8 BPP */
# define EVERGREEN_GRPH_FORMAT_INDEXED 0
# define EVERGREEN_GRPH_FORMAT_8B_BGRA1010102 5
# define EVERGREEN_GRPH_FORMAT_RGB111110 6
# define EVERGREEN_GRPH_FORMAT_BGR101111 7
+# define EVERGREEN_GRPH_BANK_HEIGHT(x) (((x) & 0x3) << 11)
+# define EVERGREEN_ADDR_SURF_BANK_HEIGHT_1 0
+# define EVERGREEN_ADDR_SURF_BANK_HEIGHT_2 1
+# define EVERGREEN_ADDR_SURF_BANK_HEIGHT_4 2
+# define EVERGREEN_ADDR_SURF_BANK_HEIGHT_8 3
+# define EVERGREEN_GRPH_TILE_SPLIT(x) (((x) & 0x7) << 13)
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_64B 0
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_128B 1
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_256B 2
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_512B 3
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_1KB 4
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_2KB 5
+# define EVERGREEN_ADDR_SURF_TILE_SPLIT_4KB 6
+# define EVERGREEN_GRPH_MACRO_TILE_ASPECT(x) (((x) & 0x3) << 18)
+# define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_1 0
+# define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_2 1
+# define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_4 2
+# define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_8 3
# define EVERGREEN_GRPH_ARRAY_MODE(x) (((x) & 0x7) << 20)
# define EVERGREEN_GRPH_ARRAY_LINEAR_GENERAL 0
# define EVERGREEN_GRPH_ARRAY_LINEAR_ALIGNED 1
#define DB_HTILE_DATA_BASE 0x28014
#define DB_Z_INFO 0x28040
# define Z_ARRAY_MODE(x) ((x) << 4)
+# define DB_TILE_SPLIT(x) (((x) & 0x7) << 8)
+# define DB_NUM_BANKS(x) (((x) & 0x3) << 12)
+# define DB_BANK_WIDTH(x) (((x) & 0x3) << 16)
+# define DB_BANK_HEIGHT(x) (((x) & 0x3) << 20)
#define DB_STENCIL_INFO 0x28044
#define DB_Z_READ_BASE 0x28048
#define DB_STENCIL_READ_BASE 0x2804c
# define CB_SF_EXPORT_FULL 0
# define CB_SF_EXPORT_NORM 1
#define CB_COLOR0_ATTRIB 0x28c74
+# define CB_TILE_SPLIT(x) (((x) & 0x7) << 5)
+# define ADDR_SURF_TILE_SPLIT_64B 0
+# define ADDR_SURF_TILE_SPLIT_128B 1
+# define ADDR_SURF_TILE_SPLIT_256B 2
+# define ADDR_SURF_TILE_SPLIT_512B 3
+# define ADDR_SURF_TILE_SPLIT_1KB 4
+# define ADDR_SURF_TILE_SPLIT_2KB 5
+# define ADDR_SURF_TILE_SPLIT_4KB 6
+# define CB_NUM_BANKS(x) (((x) & 0x3) << 10)
+# define ADDR_SURF_2_BANK 0
+# define ADDR_SURF_4_BANK 1
+# define ADDR_SURF_8_BANK 2
+# define ADDR_SURF_16_BANK 3
+# define CB_BANK_WIDTH(x) (((x) & 0x3) << 13)
+# define ADDR_SURF_BANK_WIDTH_1 0
+# define ADDR_SURF_BANK_WIDTH_2 1
+# define ADDR_SURF_BANK_WIDTH_4 2
+# define ADDR_SURF_BANK_WIDTH_8 3
+# define CB_BANK_HEIGHT(x) (((x) & 0x3) << 16)
+# define ADDR_SURF_BANK_HEIGHT_1 0
+# define ADDR_SURF_BANK_HEIGHT_2 1
+# define ADDR_SURF_BANK_HEIGHT_4 2
+# define ADDR_SURF_BANK_HEIGHT_8 3
#define CB_COLOR0_DIM 0x28c78
/* only CB0-7 blocks have these regs */
#define CB_COLOR0_CMASK 0x28c7c
# define SQ_SEL_1 5
#define SQ_TEX_RESOURCE_WORD5_0 0x30014
#define SQ_TEX_RESOURCE_WORD6_0 0x30018
+# define TEX_TILE_SPLIT(x) (((x) & 0x7) << 29)
#define SQ_TEX_RESOURCE_WORD7_0 0x3001c
+# define TEX_BANK_WIDTH(x) (((x) & 0x3) << 8)
+# define TEX_BANK_HEIGHT(x) (((x) & 0x3) << 10)
+# define TEX_NUM_BANKS(x) (((x) & 0x3) << 16)
#define SQ_VTX_CONSTANT_WORD0_0 0x30000
#define SQ_VTX_CONSTANT_WORD1_0 0x30004
{
struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
+ int i;
/* Lock the graphics update lock */
/* update the scanout addresses */
WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
/* Wait for update_pending to go high. */
- while (!(RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET)
+ break;
+ udelay(1);
+ }
DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
/* Unlock the lock, so double-buffering can take place inside vblank */
return r;
}
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- tile_flags |= R300_TXO_MACRO_TILE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- tile_flags |= R300_TXO_MICRO_TILE;
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
- tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
-
- tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
- tmp |= tile_flags;
- ib[idx] = tmp;
+ if (p->keep_tiling_flags) {
+ ib[idx] = (idx_value & 31) | /* keep the 1st 5 bits */
+ ((idx_value & ~31) + (u32)reloc->lobj.gpu_offset);
+ } else {
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= R300_TXO_MACRO_TILE;
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ tile_flags |= R300_TXO_MICRO_TILE;
+ else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+ tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
+
+ tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
+ tmp |= tile_flags;
+ ib[idx] = tmp;
+ }
track->textures[i].robj = reloc->robj;
track->tex_dirty = true;
break;
/* RB3D_COLORPITCH1 */
/* RB3D_COLORPITCH2 */
/* RB3D_COLORPITCH3 */
- r = r100_cs_packet_next_reloc(p, &reloc);
- if (r) {
- DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
- idx, reg);
- r100_cs_dump_packet(p, pkt);
- return r;
- }
+ if (!p->keep_tiling_flags) {
+ r = r100_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+ idx, reg);
+ r100_cs_dump_packet(p, pkt);
+ return r;
+ }
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- tile_flags |= R300_COLOR_TILE_ENABLE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- tile_flags |= R300_COLOR_MICROTILE_ENABLE;
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
- tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= R300_COLOR_TILE_ENABLE;
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ tile_flags |= R300_COLOR_MICROTILE_ENABLE;
+ else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+ tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
- tmp = idx_value & ~(0x7 << 16);
- tmp |= tile_flags;
- ib[idx] = tmp;
+ tmp = idx_value & ~(0x7 << 16);
+ tmp |= tile_flags;
+ ib[idx] = tmp;
+ }
i = (reg - 0x4E38) >> 2;
track->cb[i].pitch = idx_value & 0x3FFE;
switch (((idx_value >> 21) & 0xF)) {
break;
case 0x4F24:
/* ZB_DEPTHPITCH */
- r = r100_cs_packet_next_reloc(p, &reloc);
- if (r) {
- DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
- idx, reg);
- r100_cs_dump_packet(p, pkt);
- return r;
- }
-
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- tile_flags |= R300_DEPTHMACROTILE_ENABLE;
- if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- tile_flags |= R300_DEPTHMICROTILE_TILED;
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
- tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
+ if (!p->keep_tiling_flags) {
+ r = r100_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+ idx, reg);
+ r100_cs_dump_packet(p, pkt);
+ return r;
+ }
- tmp = idx_value & ~(0x7 << 16);
- tmp |= tile_flags;
- ib[idx] = tmp;
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ tile_flags |= R300_DEPTHMACROTILE_ENABLE;
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ tile_flags |= R300_DEPTHMICROTILE_TILED;
+ else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+ tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
+ tmp = idx_value & ~(0x7 << 16);
+ tmp |= tile_flags;
+ ib[idx] = tmp;
+ }
track->zb.pitch = idx_value & 0x3FFC;
track->zb_dirty = true;
break;
track->db_depth_control = radeon_get_ib_value(p, idx);
break;
case R_028010_DB_DEPTH_INFO:
- if (r600_cs_packet_next_is_pkt3_nop(p)) {
+ if (!p->keep_tiling_flags &&
+ r600_cs_packet_next_is_pkt3_nop(p)) {
r = r600_cs_packet_next_reloc(p, &reloc);
if (r) {
dev_warn(p->dev, "bad SET_CONTEXT_REG "
case R_0280B4_CB_COLOR5_INFO:
case R_0280B8_CB_COLOR6_INFO:
case R_0280BC_CB_COLOR7_INFO:
- if (r600_cs_packet_next_is_pkt3_nop(p)) {
+ if (!p->keep_tiling_flags &&
+ r600_cs_packet_next_is_pkt3_nop(p)) {
r = r600_cs_packet_next_reloc(p, &reloc);
if (r) {
dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
mip_offset <<= 8;
word0 = radeon_get_ib_value(p, idx + 0);
- if (tiling_flags & RADEON_TILING_MACRO)
- word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
- else if (tiling_flags & RADEON_TILING_MICRO)
- word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ if (tiling_flags & RADEON_TILING_MACRO)
+ word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+ else if (tiling_flags & RADEON_TILING_MICRO)
+ word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+ }
word1 = radeon_get_ib_value(p, idx + 1);
w0 = G_038000_TEX_WIDTH(word0) + 1;
h0 = G_038004_TEX_HEIGHT(word1) + 1;
return -EINVAL;
}
base_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
- if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
- ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
- else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
- ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+ if (!p->keep_tiling_flags) {
+ if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+ ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+ else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+ ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+ }
texture = reloc->robj;
/* tex mip base */
r = r600_cs_packet_next_reloc(p, &reloc);
struct radeon_ib *ib;
void *track;
unsigned family;
- int parser_error;
+ int parser_error;
+ bool keep_tiling_flags;
};
extern int radeon_cs_update_pages(struct radeon_cs_parser *p, int pg_idx);
/* Fail only if calling the method fails and ATIF is supported */
if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
- printk(KERN_DEBUG "failed to evaluate ATIF got %s\n", acpi_format_exception(status));
+ DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
+ acpi_format_exception(status));
kfree(buffer.pointer);
return 1;
}
acpi_handle handle;
int ret;
- /* No need to proceed if we're sure that ATIF is not supported */
- if (!ASIC_IS_AVIVO(rdev) || !rdev->bios)
- return 0;
-
/* Get the device handle */
handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+ /* No need to proceed if we're sure that ATIF is not supported */
+ if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
+ return 0;
+
/* Call the ATIF method */
ret = radeon_atif_call(handle);
if (ret)
struct _ATOM_SUPPORTED_DEVICES_INFO_2d1 info_2d1;
};
+static void radeon_lookup_i2c_gpio_quirks(struct radeon_device *rdev,
+ ATOM_GPIO_I2C_ASSIGMENT *gpio,
+ u8 index)
+{
+ /* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
+ if ((rdev->family == CHIP_R420) ||
+ (rdev->family == CHIP_R423) ||
+ (rdev->family == CHIP_RV410)) {
+ if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
+ gpio->ucClkMaskShift = 0x19;
+ gpio->ucDataMaskShift = 0x18;
+ }
+ }
+
+ /* some evergreen boards have bad data for this entry */
+ if (ASIC_IS_DCE4(rdev)) {
+ if ((index == 7) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
+ (gpio->sucI2cId.ucAccess == 0)) {
+ gpio->sucI2cId.ucAccess = 0x97;
+ gpio->ucDataMaskShift = 8;
+ gpio->ucDataEnShift = 8;
+ gpio->ucDataY_Shift = 8;
+ gpio->ucDataA_Shift = 8;
+ }
+ }
+
+ /* some DCE3 boards have bad data for this entry */
+ if (ASIC_IS_DCE3(rdev)) {
+ if ((index == 4) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
+ (gpio->sucI2cId.ucAccess == 0x94))
+ gpio->sucI2cId.ucAccess = 0x14;
+ }
+}
+
+static struct radeon_i2c_bus_rec radeon_get_bus_rec_for_i2c_gpio(ATOM_GPIO_I2C_ASSIGMENT *gpio)
+{
+ struct radeon_i2c_bus_rec i2c;
+
+ memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
+
+ i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
+ i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
+ i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
+ i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
+ i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
+ i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
+ i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
+ i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
+ i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
+ i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
+ i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
+ i2c.en_data_mask = (1 << gpio->ucDataEnShift);
+ i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
+ i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
+ i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
+ i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
+
+ if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
+ i2c.hw_capable = true;
+ else
+ i2c.hw_capable = false;
+
+ if (gpio->sucI2cId.ucAccess == 0xa0)
+ i2c.mm_i2c = true;
+ else
+ i2c.mm_i2c = false;
+
+ i2c.i2c_id = gpio->sucI2cId.ucAccess;
+
+ if (i2c.mask_clk_reg)
+ i2c.valid = true;
+ else
+ i2c.valid = false;
+
+ return i2c;
+}
+
static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rdev,
uint8_t id)
{
for (i = 0; i < num_indices; i++) {
gpio = &i2c_info->asGPIO_Info[i];
- /* some evergreen boards have bad data for this entry */
- if (ASIC_IS_DCE4(rdev)) {
- if ((i == 7) &&
- (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
- (gpio->sucI2cId.ucAccess == 0)) {
- gpio->sucI2cId.ucAccess = 0x97;
- gpio->ucDataMaskShift = 8;
- gpio->ucDataEnShift = 8;
- gpio->ucDataY_Shift = 8;
- gpio->ucDataA_Shift = 8;
- }
- }
-
- /* some DCE3 boards have bad data for this entry */
- if (ASIC_IS_DCE3(rdev)) {
- if ((i == 4) &&
- (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
- (gpio->sucI2cId.ucAccess == 0x94))
- gpio->sucI2cId.ucAccess = 0x14;
- }
+ radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
if (gpio->sucI2cId.ucAccess == id) {
- i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
- i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
- i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
- i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
- i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
- i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
- i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
- i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
- i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
- i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
- i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
- i2c.en_data_mask = (1 << gpio->ucDataEnShift);
- i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
- i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
- i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
- i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
- if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
- i2c.hw_capable = true;
- else
- i2c.hw_capable = false;
-
- if (gpio->sucI2cId.ucAccess == 0xa0)
- i2c.mm_i2c = true;
- else
- i2c.mm_i2c = false;
-
- i2c.i2c_id = gpio->sucI2cId.ucAccess;
-
- if (i2c.mask_clk_reg)
- i2c.valid = true;
+ i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
break;
}
}
int i, num_indices;
char stmp[32];
- memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
-
if (atom_parse_data_header(ctx, index, &size, NULL, NULL, &data_offset)) {
i2c_info = (struct _ATOM_GPIO_I2C_INFO *)(ctx->bios + data_offset);
for (i = 0; i < num_indices; i++) {
gpio = &i2c_info->asGPIO_Info[i];
- i2c.valid = false;
-
- /* some evergreen boards have bad data for this entry */
- if (ASIC_IS_DCE4(rdev)) {
- if ((i == 7) &&
- (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
- (gpio->sucI2cId.ucAccess == 0)) {
- gpio->sucI2cId.ucAccess = 0x97;
- gpio->ucDataMaskShift = 8;
- gpio->ucDataEnShift = 8;
- gpio->ucDataY_Shift = 8;
- gpio->ucDataA_Shift = 8;
- }
- }
-
- /* some DCE3 boards have bad data for this entry */
- if (ASIC_IS_DCE3(rdev)) {
- if ((i == 4) &&
- (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
- (gpio->sucI2cId.ucAccess == 0x94))
- gpio->sucI2cId.ucAccess = 0x14;
- }
-
- i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
- i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
- i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
- i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
- i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
- i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
- i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
- i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
- i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
- i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
- i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
- i2c.en_data_mask = (1 << gpio->ucDataEnShift);
- i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
- i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
- i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
- i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
- if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
- i2c.hw_capable = true;
- else
- i2c.hw_capable = false;
- if (gpio->sucI2cId.ucAccess == 0xa0)
- i2c.mm_i2c = true;
- else
- i2c.mm_i2c = false;
+ radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
- i2c.i2c_id = gpio->sucI2cId.ucAccess;
+ i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
- if (i2c.mask_clk_reg) {
- i2c.valid = true;
+ if (i2c.valid) {
sprintf(stmp, "0x%x", i2c.i2c_id);
rdev->i2c_bus[i] = radeon_i2c_create(rdev->ddev, &i2c, stmp);
}
return state_index;
/* last mode is usually default, array is low to high */
for (i = 0; i < num_modes; i++) {
+ rdev->pm.power_state[state_index].clock_info =
+ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
+ if (!rdev->pm.power_state[state_index].clock_info)
+ return state_index;
+ rdev->pm.power_state[state_index].num_clock_modes = 1;
rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
switch (frev) {
case 1:
- rdev->pm.power_state[state_index].clock_info =
- kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
- if (!rdev->pm.power_state[state_index].clock_info)
- return state_index;
- rdev->pm.power_state[state_index].num_clock_modes = 1;
rdev->pm.power_state[state_index].clock_info[0].mclk =
le16_to_cpu(power_info->info.asPowerPlayInfo[i].usMemoryClock);
rdev->pm.power_state[state_index].clock_info[0].sclk =
state_index++;
break;
case 2:
- rdev->pm.power_state[state_index].clock_info =
- kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
- if (!rdev->pm.power_state[state_index].clock_info)
- return state_index;
- rdev->pm.power_state[state_index].num_clock_modes = 1;
rdev->pm.power_state[state_index].clock_info[0].mclk =
le32_to_cpu(power_info->info_2.asPowerPlayInfo[i].ulMemoryClock);
rdev->pm.power_state[state_index].clock_info[0].sclk =
state_index++;
break;
case 3:
- rdev->pm.power_state[state_index].clock_info =
- kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
- if (!rdev->pm.power_state[state_index].clock_info)
- return state_index;
- rdev->pm.power_state[state_index].num_clock_modes = 1;
rdev->pm.power_state[state_index].clock_info[0].mclk =
le32_to_cpu(power_info->info_3.asPowerPlayInfo[i].ulMemoryClock);
rdev->pm.power_state[state_index].clock_info[0].sclk =
rdev->pm.current_power_state_index = rdev->pm.default_power_state_index;
rdev->pm.current_clock_mode_index = 0;
- rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
+ if (rdev->pm.default_power_state_index >= 0)
+ rdev->pm.current_vddc =
+ rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
+ else
+ rdev->pm.current_vddc = 0;
}
void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable)
{
struct drm_radeon_cs *cs = data;
uint64_t *chunk_array_ptr;
- unsigned size, i;
+ unsigned size, i, flags = 0;
if (!cs->num_chunks) {
return 0;
if (p->chunks[i].length_dw == 0)
return -EINVAL;
}
+ if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS &&
+ !p->chunks[i].length_dw) {
+ return -EINVAL;
+ }
p->chunks[i].length_dw = user_chunk.length_dw;
p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
p->chunks[i].user_ptr, size)) {
return -EFAULT;
}
+ if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
+ flags = p->chunks[i].kdata[0];
+ }
} else {
p->chunks[i].kpage[0] = kmalloc(PAGE_SIZE, GFP_KERNEL);
p->chunks[i].kpage[1] = kmalloc(PAGE_SIZE, GFP_KERNEL);
p->chunks[p->chunk_ib_idx].length_dw);
return -EINVAL;
}
+
+ p->keep_tiling_flags = (flags & RADEON_CS_KEEP_TILING_FLAGS) != 0;
return 0;
}
* 2.9.0 - r600 tiling (s3tc,rgtc) working, SET_PREDICATION packet 3 on r600 + eg, backend query
* 2.10.0 - fusion 2D tiling
* 2.11.0 - backend map, initial compute support for the CS checker
+ * 2.12.0 - RADEON_CS_KEEP_TILING_FLAGS
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 11
+#define KMS_DRIVER_MINOR 12
#define KMS_DRIVER_PATCHLEVEL 0
int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
int radeon_driver_unload_kms(struct drm_device *dev);
switch (radeon_encoder->encoder_id) {
case ENCODER_OBJECT_ID_TRAVIS:
case ENCODER_OBJECT_ID_NUTMEG:
- return true;
+ return radeon_encoder->encoder_id;
default:
- return false;
+ return ENCODER_OBJECT_ID_NONE;
}
}
-
- return false;
+ return ENCODER_OBJECT_ID_NONE;
}
void radeon_panel_mode_fixup(struct drm_encoder *encoder,
{
struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+ int i;
/* Lock the graphics update lock */
tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
(u32)crtc_base);
/* Wait for update_pending to go high. */
- while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+ break;
+ udelay(1);
+ }
DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
/* Unlock the lock, so double-buffering can take place inside vblank */
{
struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+ int i;
/* Lock the graphics update lock */
tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
(u32)crtc_base);
/* Wait for update_pending to go high. */
- while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+ break;
+ udelay(1);
+ }
DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
/* Unlock the lock, so double-buffering can take place inside vblank */
return ret;
spin_lock(&glob->lru_lock);
+
+ if (unlikely(list_empty(&bo->ddestroy))) {
+ spin_unlock(&glob->lru_lock);
+ return 0;
+ }
+
ret = ttm_bo_reserve_locked(bo, interruptible,
no_wait_reserve, false, 0);
- if (unlikely(ret != 0) || list_empty(&bo->ddestroy)) {
+ if (unlikely(ret != 0)) {
spin_unlock(&glob->lru_lock);
return ret;
}
struct ttm_object_file *tfile,
int id,
struct vmw_resource **p_res);
+extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
+ struct ttm_object_file *tfile,
+ uint32_t handle,
+ struct vmw_surface **out_surf,
+ struct vmw_dma_buffer **out_buf);
extern void vmw_surface_res_free(struct vmw_resource *res);
extern int vmw_surface_init(struct vmw_private *dev_priv,
struct vmw_surface *srf,
{
__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
uint32_t fifo_min, hwversion;
+ const struct vmw_fifo_state *fifo = &dev_priv->fifo;
if (!(dev_priv->capabilities & SVGA_CAP_EXTENDED_FIFO))
return false;
if (fifo_min <= SVGA_FIFO_3D_HWVERSION * sizeof(unsigned int))
return false;
- hwversion = ioread32(fifo_mem + SVGA_FIFO_3D_HWVERSION);
+ hwversion = ioread32(fifo_mem +
+ ((fifo->capabilities &
+ SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ?
+ SVGA_FIFO_3D_HWVERSION_REVISED :
+ SVGA_FIFO_3D_HWVERSION));
+
if (hwversion == 0)
return false;
case DRM_VMW_PARAM_FIFO_HW_VERSION:
{
__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
-
- param->value = ioread32(fifo_mem + SVGA_FIFO_3D_HWVERSION);
+ const struct vmw_fifo_state *fifo = &dev_priv->fifo;
+
+ param->value =
+ ioread32(fifo_mem +
+ ((fifo->capabilities &
+ SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ?
+ SVGA_FIFO_3D_HWVERSION_REVISED :
+ SVGA_FIFO_3D_HWVERSION));
break;
}
default:
goto out_clips;
}
- clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
+ clips = kcalloc(num_clips, sizeof(*clips), GFP_KERNEL);
if (clips == NULL) {
DRM_ERROR("Failed to allocate clip rect list.\n");
ret = -ENOMEM;
ret = -EINVAL;
goto out_no_fb;
}
-
vfb = vmw_framebuffer_to_vfb(obj_to_fb(obj));
- if (!vfb->dmabuf) {
- DRM_ERROR("Framebuffer not dmabuf backed.\n");
- ret = -EINVAL;
- goto out_no_fb;
- }
ret = ttm_read_lock(&vmaster->lock, true);
if (unlikely(ret != 0))
goto out_clips;
}
- clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
+ clips = kcalloc(num_clips, sizeof(*clips), GFP_KERNEL);
if (clips == NULL) {
DRM_ERROR("Failed to allocate clip rect list.\n");
ret = -ENOMEM;
/* Might need a hrtimer here? */
#define VMWGFX_PRESENT_RATE ((HZ / 60 > 0) ? HZ / 60 : 1)
+
+struct vmw_clip_rect {
+ int x1, x2, y1, y2;
+};
+
+/**
+ * Clip @num_rects number of @rects against @clip storing the
+ * results in @out_rects and the number of passed rects in @out_num.
+ */
+void vmw_clip_cliprects(struct drm_clip_rect *rects,
+ int num_rects,
+ struct vmw_clip_rect clip,
+ SVGASignedRect *out_rects,
+ int *out_num)
+{
+ int i, k;
+
+ for (i = 0, k = 0; i < num_rects; i++) {
+ int x1 = max_t(int, clip.x1, rects[i].x1);
+ int y1 = max_t(int, clip.y1, rects[i].y1);
+ int x2 = min_t(int, clip.x2, rects[i].x2);
+ int y2 = min_t(int, clip.y2, rects[i].y2);
+
+ if (x1 >= x2)
+ continue;
+ if (y1 >= y2)
+ continue;
+
+ out_rects[k].left = x1;
+ out_rects[k].top = y1;
+ out_rects[k].right = x2;
+ out_rects[k].bottom = y2;
+ k++;
+ }
+
+ *out_num = k;
+}
+
void vmw_display_unit_cleanup(struct vmw_display_unit *du)
{
if (du->cursor_surface)
return 0;
}
+int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
+ struct vmw_dma_buffer *dmabuf,
+ u32 width, u32 height,
+ u32 hotspotX, u32 hotspotY)
+{
+ struct ttm_bo_kmap_obj map;
+ unsigned long kmap_offset;
+ unsigned long kmap_num;
+ void *virtual;
+ bool dummy;
+ int ret;
+
+ kmap_offset = 0;
+ kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ ret = ttm_bo_reserve(&dmabuf->base, true, false, false, 0);
+ if (unlikely(ret != 0)) {
+ DRM_ERROR("reserve failed\n");
+ return -EINVAL;
+ }
+
+ ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map);
+ if (unlikely(ret != 0))
+ goto err_unreserve;
+
+ virtual = ttm_kmap_obj_virtual(&map, &dummy);
+ ret = vmw_cursor_update_image(dev_priv, virtual, width, height,
+ hotspotX, hotspotY);
+
+ ttm_bo_kunmap(&map);
+err_unreserve:
+ ttm_bo_unreserve(&dmabuf->base);
+
+ return ret;
+}
+
+
void vmw_cursor_update_position(struct vmw_private *dev_priv,
bool show, int x, int y)
{
return -EINVAL;
if (handle) {
- ret = vmw_user_surface_lookup_handle(dev_priv, tfile,
- handle, &surface);
- if (!ret) {
- if (!surface->snooper.image) {
- DRM_ERROR("surface not suitable for cursor\n");
- vmw_surface_unreference(&surface);
- return -EINVAL;
- }
- } else {
- ret = vmw_user_dmabuf_lookup(tfile,
- handle, &dmabuf);
- if (ret) {
- DRM_ERROR("failed to find surface or dmabuf: %i\n", ret);
- return -EINVAL;
- }
+ ret = vmw_user_lookup_handle(dev_priv, tfile,
+ handle, &surface, &dmabuf);
+ if (ret) {
+ DRM_ERROR("failed to find surface or dmabuf: %i\n", ret);
+ return -EINVAL;
}
}
+ /* need to do this before taking down old image */
+ if (surface && !surface->snooper.image) {
+ DRM_ERROR("surface not suitable for cursor\n");
+ vmw_surface_unreference(&surface);
+ return -EINVAL;
+ }
+
/* takedown old cursor */
if (du->cursor_surface) {
du->cursor_surface->snooper.crtc = NULL;
vmw_cursor_update_image(dev_priv, surface->snooper.image,
64, 64, du->hotspot_x, du->hotspot_y);
} else if (dmabuf) {
- struct ttm_bo_kmap_obj map;
- unsigned long kmap_offset;
- unsigned long kmap_num;
- void *virtual;
- bool dummy;
-
/* vmw_user_surface_lookup takes one reference */
du->cursor_dmabuf = dmabuf;
- kmap_offset = 0;
- kmap_num = (64*64*4) >> PAGE_SHIFT;
-
- ret = ttm_bo_reserve(&dmabuf->base, true, false, false, 0);
- if (unlikely(ret != 0)) {
- DRM_ERROR("reserve failed\n");
- return -EINVAL;
- }
-
- ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map);
- if (unlikely(ret != 0))
- goto err_unreserve;
-
- virtual = ttm_kmap_obj_virtual(&map, &dummy);
- vmw_cursor_update_image(dev_priv, virtual, 64, 64,
- du->hotspot_x, du->hotspot_y);
-
- ttm_bo_kunmap(&map);
-err_unreserve:
- ttm_bo_unreserve(&dmabuf->base);
-
+ ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, width, height,
+ du->hotspot_x, du->hotspot_y);
} else {
vmw_cursor_update_position(dev_priv, false, 0, 0);
return 0;
struct drm_clip_rect *clips,
unsigned num_clips, int inc)
{
- struct drm_clip_rect *clips_ptr;
struct vmw_display_unit *units[VMWGFX_NUM_DISPLAY_UNITS];
+ struct drm_clip_rect *clips_ptr;
+ struct drm_clip_rect *tmp;
struct drm_crtc *crtc;
size_t fifo_size;
int i, num_units;
} *cmd;
SVGASignedRect *blits;
-
num_units = 0;
list_for_each_entry(crtc, &dev_priv->dev->mode_config.crtc_list,
head) {
BUG_ON(!clips || !num_clips);
+ tmp = kzalloc(sizeof(*tmp) * num_clips, GFP_KERNEL);
+ if (unlikely(tmp == NULL)) {
+ DRM_ERROR("Temporary cliprect memory alloc failed.\n");
+ return -ENOMEM;
+ }
+
fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num_clips;
cmd = kzalloc(fifo_size, GFP_KERNEL);
if (unlikely(cmd == NULL)) {
DRM_ERROR("Temporary fifo memory alloc failed.\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_free_tmp;
}
+ /* setup blits pointer */
+ blits = (SVGASignedRect *)&cmd[1];
+
+ /* initial clip region */
left = clips->x1;
right = clips->x2;
top = clips->y1;
cmd->body.srcRect.bottom = bottom;
clips_ptr = clips;
- blits = (SVGASignedRect *)&cmd[1];
for (i = 0; i < num_clips; i++, clips_ptr += inc) {
- blits[i].left = clips_ptr->x1 - left;
- blits[i].right = clips_ptr->x2 - left;
- blits[i].top = clips_ptr->y1 - top;
- blits[i].bottom = clips_ptr->y2 - top;
+ tmp[i].x1 = clips_ptr->x1 - left;
+ tmp[i].x2 = clips_ptr->x2 - left;
+ tmp[i].y1 = clips_ptr->y1 - top;
+ tmp[i].y2 = clips_ptr->y2 - top;
}
/* do per unit writing, reuse fifo for each */
for (i = 0; i < num_units; i++) {
struct vmw_display_unit *unit = units[i];
- int clip_x1 = left - unit->crtc.x;
- int clip_y1 = top - unit->crtc.y;
- int clip_x2 = right - unit->crtc.x;
- int clip_y2 = bottom - unit->crtc.y;
+ struct vmw_clip_rect clip;
+ int num;
+
+ clip.x1 = left - unit->crtc.x;
+ clip.y1 = top - unit->crtc.y;
+ clip.x2 = right - unit->crtc.x;
+ clip.y2 = bottom - unit->crtc.y;
/* skip any crtcs that misses the clip region */
- if (clip_x1 >= unit->crtc.mode.hdisplay ||
- clip_y1 >= unit->crtc.mode.vdisplay ||
- clip_x2 <= 0 || clip_y2 <= 0)
+ if (clip.x1 >= unit->crtc.mode.hdisplay ||
+ clip.y1 >= unit->crtc.mode.vdisplay ||
+ clip.x2 <= 0 || clip.y2 <= 0)
continue;
+ /*
+ * In order for the clip rects to be correctly scaled
+ * the src and dest rects needs to be the same size.
+ */
+ cmd->body.destRect.left = clip.x1;
+ cmd->body.destRect.right = clip.x2;
+ cmd->body.destRect.top = clip.y1;
+ cmd->body.destRect.bottom = clip.y2;
+
+ /* create a clip rect of the crtc in dest coords */
+ clip.x2 = unit->crtc.mode.hdisplay - clip.x1;
+ clip.y2 = unit->crtc.mode.vdisplay - clip.y1;
+ clip.x1 = 0 - clip.x1;
+ clip.y1 = 0 - clip.y1;
+
/* need to reset sid as it is changed by execbuf */
cmd->body.srcImage.sid = cpu_to_le32(framebuffer->user_handle);
-
cmd->body.destScreenId = unit->unit;
- /*
- * The blit command is a lot more resilient then the
- * readback command when it comes to clip rects. So its
- * okay to go out of bounds.
- */
+ /* clip and write blits to cmd stream */
+ vmw_clip_cliprects(tmp, num_clips, clip, blits, &num);
- cmd->body.destRect.left = clip_x1;
- cmd->body.destRect.right = clip_x2;
- cmd->body.destRect.top = clip_y1;
- cmd->body.destRect.bottom = clip_y2;
+ /* if no cliprects hit skip this */
+ if (num == 0)
+ continue;
+ /* recalculate package length */
+ fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num;
+ cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header));
ret = vmw_execbuf_process(file_priv, dev_priv, NULL, cmd,
fifo_size, 0, NULL);
break;
}
+
kfree(cmd);
+out_free_tmp:
+ kfree(tmp);
return ret;
}
* Sanity checks.
*/
+ /* Surface must be marked as a scanout. */
+ if (unlikely(!surface->scanout))
+ return -EINVAL;
+
if (unlikely(surface->mip_levels[0] != 1 ||
surface->num_sizes != 1 ||
surface->sizes[0].width < mode_cmd->width ||
int clip_y1 = clips_ptr->y1 - unit->crtc.y;
int clip_x2 = clips_ptr->x2 - unit->crtc.x;
int clip_y2 = clips_ptr->y2 - unit->crtc.y;
+ int move_x, move_y;
/* skip any crtcs that misses the clip region */
if (clip_x1 >= unit->crtc.mode.hdisplay ||
clip_x2 <= 0 || clip_y2 <= 0)
continue;
+ /* clip size to crtc size */
+ clip_x2 = min_t(int, clip_x2, unit->crtc.mode.hdisplay);
+ clip_y2 = min_t(int, clip_y2, unit->crtc.mode.vdisplay);
+
+ /* translate both src and dest to bring clip into screen */
+ move_x = min_t(int, clip_x1, 0);
+ move_y = min_t(int, clip_y1, 0);
+
+ /* actual translate done here */
blits[hit_num].header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN;
blits[hit_num].body.destScreenId = unit->unit;
- blits[hit_num].body.srcOrigin.x = clips_ptr->x1;
- blits[hit_num].body.srcOrigin.y = clips_ptr->y1;
- blits[hit_num].body.destRect.left = clip_x1;
- blits[hit_num].body.destRect.top = clip_y1;
+ blits[hit_num].body.srcOrigin.x = clips_ptr->x1 - move_x;
+ blits[hit_num].body.srcOrigin.y = clips_ptr->y1 - move_y;
+ blits[hit_num].body.destRect.left = clip_x1 - move_x;
+ blits[hit_num].body.destRect.top = clip_y1 - move_y;
blits[hit_num].body.destRect.right = clip_x2;
blits[hit_num].body.destRect.bottom = clip_y2;
hit_num++;
struct vmw_surface *surface = NULL;
struct vmw_dma_buffer *bo = NULL;
struct ttm_base_object *user_obj;
- u64 required_size;
int ret;
/**
* requested framebuffer.
*/
- required_size = mode_cmd->pitch * mode_cmd->height;
- if (unlikely(required_size > (u64) dev_priv->vram_size)) {
+ if (!vmw_kms_validate_mode_vram(dev_priv,
+ mode_cmd->pitch,
+ mode_cmd->height)) {
DRM_ERROR("VRAM size is too small for requested mode.\n");
return ERR_PTR(-ENOMEM);
}
return ERR_PTR(-ENOENT);
}
- /**
- * End conditioned code.
- */
-
- ret = vmw_user_surface_lookup_handle(dev_priv, tfile,
- mode_cmd->handle, &surface);
+ /* returns either a dmabuf or surface */
+ ret = vmw_user_lookup_handle(dev_priv, tfile,
+ mode_cmd->handle,
+ &surface, &bo);
if (ret)
- goto try_dmabuf;
-
- if (!surface->scanout)
- goto err_not_scanout;
-
- ret = vmw_kms_new_framebuffer_surface(dev_priv, file_priv, surface,
- &vfb, mode_cmd);
-
- /* vmw_user_surface_lookup takes one ref so does new_fb */
- vmw_surface_unreference(&surface);
-
- if (ret) {
- DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret);
- ttm_base_object_unref(&user_obj);
- return ERR_PTR(ret);
- } else
- vfb->user_obj = user_obj;
- return &vfb->base;
-
-try_dmabuf:
- DRM_INFO("%s: trying buffer\n", __func__);
-
- ret = vmw_user_dmabuf_lookup(tfile, mode_cmd->handle, &bo);
- if (ret) {
- DRM_ERROR("failed to find buffer: %i\n", ret);
- return ERR_PTR(-ENOENT);
- }
-
- ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, bo, &vfb,
- mode_cmd);
+ goto err_out;
+
+ /* Create the new framebuffer depending one what we got back */
+ if (bo)
+ ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, bo, &vfb,
+ mode_cmd);
+ else if (surface)
+ ret = vmw_kms_new_framebuffer_surface(dev_priv, file_priv,
+ surface, &vfb, mode_cmd);
+ else
+ BUG();
- /* vmw_user_dmabuf_lookup takes one ref so does new_fb */
- vmw_dmabuf_unreference(&bo);
+err_out:
+ /* vmw_user_lookup_handle takes one ref so does new_fb */
+ if (bo)
+ vmw_dmabuf_unreference(&bo);
+ if (surface)
+ vmw_surface_unreference(&surface);
if (ret) {
DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret);
vfb->user_obj = user_obj;
return &vfb->base;
-
-err_not_scanout:
- DRM_ERROR("surface not marked as scanout\n");
- /* vmw_user_surface_lookup takes one ref */
- vmw_surface_unreference(&surface);
- ttm_base_object_unref(&user_obj);
-
- return ERR_PTR(-EINVAL);
}
static struct drm_mode_config_funcs vmw_kms_funcs = {
uint32_t num_clips)
{
struct vmw_display_unit *units[VMWGFX_NUM_DISPLAY_UNITS];
+ struct drm_clip_rect *tmp;
struct drm_crtc *crtc;
size_t fifo_size;
int i, k, num_units;
int ret = 0; /* silence warning */
+ int left, right, top, bottom;
struct {
SVGA3dCmdHeader header;
BUG_ON(surface == NULL);
BUG_ON(!clips || !num_clips);
+ tmp = kzalloc(sizeof(*tmp) * num_clips, GFP_KERNEL);
+ if (unlikely(tmp == NULL)) {
+ DRM_ERROR("Temporary cliprect memory alloc failed.\n");
+ return -ENOMEM;
+ }
+
fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num_clips;
cmd = kmalloc(fifo_size, GFP_KERNEL);
if (unlikely(cmd == NULL)) {
DRM_ERROR("Failed to allocate temporary fifo memory.\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_free_tmp;
+ }
+
+ left = clips->x;
+ right = clips->x + clips->w;
+ top = clips->y;
+ bottom = clips->y + clips->h;
+
+ for (i = 1; i < num_clips; i++) {
+ left = min_t(int, left, (int)clips[i].x);
+ right = max_t(int, right, (int)clips[i].x + clips[i].w);
+ top = min_t(int, top, (int)clips[i].y);
+ bottom = max_t(int, bottom, (int)clips[i].y + clips[i].h);
}
/* only need to do this once */
memset(cmd, 0, fifo_size);
cmd->header.id = cpu_to_le32(SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN);
- cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header));
-
- cmd->body.srcRect.left = 0;
- cmd->body.srcRect.right = surface->sizes[0].width;
- cmd->body.srcRect.top = 0;
- cmd->body.srcRect.bottom = surface->sizes[0].height;
blits = (SVGASignedRect *)&cmd[1];
+
+ cmd->body.srcRect.left = left;
+ cmd->body.srcRect.right = right;
+ cmd->body.srcRect.top = top;
+ cmd->body.srcRect.bottom = bottom;
+
for (i = 0; i < num_clips; i++) {
- blits[i].left = clips[i].x;
- blits[i].right = clips[i].x + clips[i].w;
- blits[i].top = clips[i].y;
- blits[i].bottom = clips[i].y + clips[i].h;
+ tmp[i].x1 = clips[i].x - left;
+ tmp[i].x2 = clips[i].x + clips[i].w - left;
+ tmp[i].y1 = clips[i].y - top;
+ tmp[i].y2 = clips[i].y + clips[i].h - top;
}
for (k = 0; k < num_units; k++) {
struct vmw_display_unit *unit = units[k];
- int clip_x1 = destX - unit->crtc.x;
- int clip_y1 = destY - unit->crtc.y;
- int clip_x2 = clip_x1 + surface->sizes[0].width;
- int clip_y2 = clip_y1 + surface->sizes[0].height;
+ struct vmw_clip_rect clip;
+ int num;
+
+ clip.x1 = left + destX - unit->crtc.x;
+ clip.y1 = top + destY - unit->crtc.y;
+ clip.x2 = right + destX - unit->crtc.x;
+ clip.y2 = bottom + destY - unit->crtc.y;
/* skip any crtcs that misses the clip region */
- if (clip_x1 >= unit->crtc.mode.hdisplay ||
- clip_y1 >= unit->crtc.mode.vdisplay ||
- clip_x2 <= 0 || clip_y2 <= 0)
+ if (clip.x1 >= unit->crtc.mode.hdisplay ||
+ clip.y1 >= unit->crtc.mode.vdisplay ||
+ clip.x2 <= 0 || clip.y2 <= 0)
continue;
+ /*
+ * In order for the clip rects to be correctly scaled
+ * the src and dest rects needs to be the same size.
+ */
+ cmd->body.destRect.left = clip.x1;
+ cmd->body.destRect.right = clip.x2;
+ cmd->body.destRect.top = clip.y1;
+ cmd->body.destRect.bottom = clip.y2;
+
+ /* create a clip rect of the crtc in dest coords */
+ clip.x2 = unit->crtc.mode.hdisplay - clip.x1;
+ clip.y2 = unit->crtc.mode.vdisplay - clip.y1;
+ clip.x1 = 0 - clip.x1;
+ clip.y1 = 0 - clip.y1;
+
/* need to reset sid as it is changed by execbuf */
cmd->body.srcImage.sid = sid;
-
cmd->body.destScreenId = unit->unit;
- /*
- * The blit command is a lot more resilient then the
- * readback command when it comes to clip rects. So its
- * okay to go out of bounds.
- */
+ /* clip and write blits to cmd stream */
+ vmw_clip_cliprects(tmp, num_clips, clip, blits, &num);
- cmd->body.destRect.left = clip_x1;
- cmd->body.destRect.right = clip_x2;
- cmd->body.destRect.top = clip_y1;
- cmd->body.destRect.bottom = clip_y2;
+ /* if no cliprects hit skip this */
+ if (num == 0)
+ continue;
+ /* recalculate package length */
+ fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num;
+ cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header));
ret = vmw_execbuf_process(file_priv, dev_priv, NULL, cmd,
fifo_size, 0, NULL);
}
kfree(cmd);
+out_free_tmp:
+ kfree(tmp);
return ret;
}
}
rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect);
- rects = kzalloc(rects_size, GFP_KERNEL);
+ rects = kcalloc(arg->num_outputs, sizeof(struct drm_vmw_rect),
+ GFP_KERNEL);
if (unlikely(!rects)) {
ret = -ENOMEM;
goto out_unlock;
}
for (i = 0; i < arg->num_outputs; ++i) {
- if (rects->x < 0 ||
- rects->y < 0 ||
- rects->x + rects->w > mode_config->max_width ||
- rects->y + rects->h > mode_config->max_height) {
+ if (rects[i].x < 0 ||
+ rects[i].y < 0 ||
+ rects[i].x + rects[i].w > mode_config->max_width ||
+ rects[i].y + rects[i].h > mode_config->max_height) {
DRM_ERROR("Invalid GUI layout.\n");
ret = -EINVAL;
goto out_free;
int vmw_cursor_update_image(struct vmw_private *dev_priv,
u32 *image, u32 width, u32 height,
u32 hotspotX, u32 hotspotY);
+int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
+ struct vmw_dma_buffer *dmabuf,
+ u32 width, u32 height,
+ u32 hotspotX, u32 hotspotY);
void vmw_cursor_update_position(struct vmw_private *dev_priv,
bool show, int x, int y);
+
/**
* Base class display unit.
*
{
struct vmw_legacy_display *lds = dev_priv->ldu_priv;
struct vmw_legacy_display_unit *entry;
+ struct vmw_display_unit *du = NULL;
struct drm_framebuffer *fb = NULL;
struct drm_crtc *crtc = NULL;
- int i = 0;
+ int i = 0, ret;
/* If there is no display topology the host just assumes
* that the guest will set the same layout as the host.
lds->last_num_active = lds->num_active;
+
+ /* Find the first du with a cursor. */
+ list_for_each_entry(entry, &lds->active, active) {
+ du = &entry->base;
+
+ if (!du->cursor_dmabuf)
+ continue;
+
+ ret = vmw_cursor_update_dmabuf(dev_priv,
+ du->cursor_dmabuf,
+ 64, 64,
+ du->hotspot_x,
+ du->hotspot_y);
+ if (ret == 0)
+ break;
+
+ DRM_ERROR("Could not update cursor image\n");
+ }
+
return 0;
}
write_unlock(lock);
}
+/**
+ * Helper function that looks either a surface or dmabuf.
+ *
+ * The pointer this pointed at by out_surf and out_buf needs to be null.
+ */
+int vmw_user_lookup_handle(struct vmw_private *dev_priv,
+ struct ttm_object_file *tfile,
+ uint32_t handle,
+ struct vmw_surface **out_surf,
+ struct vmw_dma_buffer **out_buf)
+{
+ int ret;
+
+ BUG_ON(*out_surf || *out_buf);
+
+ ret = vmw_user_surface_lookup_handle(dev_priv, tfile, handle, out_surf);
+ if (!ret)
+ return 0;
+
+ ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf);
+ return ret;
+}
+
int vmw_user_surface_lookup_handle(struct vmw_private *dev_priv,
struct ttm_object_file *tfile,
while (new_bus) {
new_bridge = new_bus->self;
- if (new_bridge) {
- /* go through list of devices already registered */
- list_for_each_entry(same_bridge_vgadev, &vga_list, list) {
- bus = same_bridge_vgadev->pdev->bus;
- bridge = bus->self;
-
- /* see if the share a bridge with this device */
- if (new_bridge == bridge) {
- /* if their direct parent bridge is the same
- as any bridge of this device then it can't be used
- for that device */
- same_bridge_vgadev->bridge_has_one_vga = false;
- }
+ /* go through list of devices already registered */
+ list_for_each_entry(same_bridge_vgadev, &vga_list, list) {
+ bus = same_bridge_vgadev->pdev->bus;
+ bridge = bus->self;
+
+ /* see if the share a bridge with this device */
+ if (new_bridge == bridge) {
+ /* if their direct parent bridge is the same
+ as any bridge of this device then it can't be used
+ for that device */
+ same_bridge_vgadev->bridge_has_one_vga = false;
+ }
- /* now iterate the previous devices bridge hierarchy */
- /* if the new devices parent bridge is in the other devices
- hierarchy then we can't use it to control this device */
- while (bus) {
- bridge = bus->self;
- if (bridge) {
- if (bridge == vgadev->pdev->bus->self)
- vgadev->bridge_has_one_vga = false;
- }
- bus = bus->parent;
+ /* now iterate the previous devices bridge hierarchy */
+ /* if the new devices parent bridge is in the other devices
+ hierarchy then we can't use it to control this device */
+ while (bus) {
+ bridge = bus->self;
+ if (bridge) {
+ if (bridge == vgadev->pdev->bus->self)
+ vgadev->bridge_has_one_vga = false;
}
+ bus = bus->parent;
}
}
new_bus = new_bus->parent;
uc = &priv->cards[i];
}
- if (!uc)
- return -EINVAL;
+ if (!uc) {
+ ret_val = -EINVAL;
+ goto done;
+ }
- if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0)
- return -EINVAL;
+ if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0) {
+ ret_val = -EINVAL;
+ goto done;
+ }
- if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0)
- return -EINVAL;
+ if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0) {
+ ret_val = -EINVAL;
+ goto done;
+ }
vga_put(pdev, io_state);
{ HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0001) },
{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0002) },
- { HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0003) },
{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0004) },
{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_4_PHIDGETSERVO_30) },
{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_1_PHIDGETSERVO_30) },
#define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR 0x0002
#define USB_VENDOR_ID_GENERAL_TOUCH 0x0dfc
-#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0001
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0003
#define USB_VENDOR_ID_GLAB 0x06c2
#define USB_DEVICE_ID_4_PHIDGETSERVO_30 0x0038
config SENSORS_EXYNOS4_TMU
tristate "Temperature sensor on Samsung EXYNOS4"
- depends on EXYNOS4_DEV_TMU
+ depends on ARCH_EXYNOS4
help
If you say yes here you get support for TMU (Thermal Managment
Unit) on SAMSUNG EXYNOS4 series of SoC.
static struct spi_driver ad7314_driver = {
.driver = {
.name = "ad7314",
- .bus = &spi_bus_type,
.owner = THIS_MODULE,
},
.probe = ad7314_probe,
static struct spi_driver ads7871_driver = {
.driver = {
.name = DEVICE_NAME,
- .bus = &spi_bus_type,
.owner = THIS_MODULE,
},
.resume = exynos4_tmu_resume,
};
-static int __init exynos4_tmu_driver_init(void)
-{
- return platform_driver_register(&exynos4_tmu_driver);
-}
-module_init(exynos4_tmu_driver_init);
-
-static void __exit exynos4_tmu_driver_exit(void)
-{
- platform_driver_unregister(&exynos4_tmu_driver);
-}
-module_exit(exynos4_tmu_driver_exit);
+module_platform_driver(exynos4_tmu_driver);
MODULE_DESCRIPTION("EXYNOS4 TMU Driver");
MODULE_AUTHOR("Donggeun Kim <dg77.kim@samsung.com>");
},
};
-static int __init gpio_fan_init(void)
-{
- return platform_driver_register(&gpio_fan_driver);
-}
-
-static void __exit gpio_fan_exit(void)
-{
- platform_driver_unregister(&gpio_fan_driver);
-}
-
-module_init(gpio_fan_init);
-module_exit(gpio_fan_exit);
+module_platform_driver(gpio_fan_driver);
MODULE_AUTHOR("Simon Guinot <sguinot@lacie.com>");
MODULE_DESCRIPTION("GPIO FAN driver");
{
struct jz4740_hwmon *hwmon = dev_get_drvdata(dev);
struct completion *completion = &hwmon->read_completion;
- unsigned long t;
+ long t;
unsigned long val;
int ret;
return 0;
}
-struct platform_driver jz4740_hwmon_driver = {
+static struct platform_driver jz4740_hwmon_driver = {
.probe = jz4740_hwmon_probe,
.remove = __devexit_p(jz4740_hwmon_remove),
.driver = {
},
};
-static int __init jz4740_hwmon_init(void)
-{
- return platform_driver_register(&jz4740_hwmon_driver);
-}
-module_init(jz4740_hwmon_init);
-
-static void __exit jz4740_hwmon_exit(void)
-{
- platform_driver_unregister(&jz4740_hwmon_driver);
-}
-module_exit(jz4740_hwmon_exit);
+module_platform_driver(jz4740_hwmon_driver);
MODULE_DESCRIPTION("JZ4740 SoC HWMON driver");
MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
.id_table = ntc_thermistor_id,
};
-static int __init ntc_thermistor_init(void)
-{
- return platform_driver_register(&ntc_thermistor_driver);
-}
-
-module_init(ntc_thermistor_init);
-
-static void __exit ntc_thermistor_cleanup(void)
-{
- platform_driver_unregister(&ntc_thermistor_driver);
-}
-
-module_exit(ntc_thermistor_cleanup);
+module_platform_driver(ntc_thermistor_driver);
MODULE_DESCRIPTION("NTC Thermistor Driver");
MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
.remove = __devexit_p(s3c_hwmon_remove),
};
-static int __init s3c_hwmon_init(void)
-{
- return platform_driver_register(&s3c_hwmon_driver);
-}
-
-static void __exit s3c_hwmon_exit(void)
-{
- platform_driver_unregister(&s3c_hwmon_driver);
-}
-
-module_init(s3c_hwmon_init);
-module_exit(s3c_hwmon_exit);
+module_platform_driver(s3c_hwmon_driver);
MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
MODULE_DESCRIPTION("S3C ADC HWMon driver");
.remove = sch5627_remove,
};
-static int __init sch5627_init(void)
-{
- return platform_driver_register(&sch5627_driver);
-}
-
-static void __exit sch5627_exit(void)
-{
- platform_driver_unregister(&sch5627_driver);
-}
+module_platform_driver(sch5627_driver);
MODULE_DESCRIPTION("SMSC SCH5627 Hardware Monitoring Driver");
MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
MODULE_LICENSE("GPL");
-
-module_init(sch5627_init);
-module_exit(sch5627_exit);
.remove = sch5636_remove,
};
-static int __init sch5636_init(void)
-{
- return platform_driver_register(&sch5636_driver);
-}
-
-static void __exit sch5636_exit(void)
-{
- platform_driver_unregister(&sch5636_driver);
-}
+module_platform_driver(sch5636_driver);
MODULE_DESCRIPTION("SMSC SCH5636 Hardware Monitoring Driver");
MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
MODULE_LICENSE("GPL");
-
-module_init(sch5636_init);
-module_exit(sch5636_exit);
},
};
-static int __init twl4030_madc_hwmon_init(void)
-{
- return platform_driver_register(&twl4030_madc_hwmon_driver);
-}
-
-module_init(twl4030_madc_hwmon_init);
-
-static void __exit twl4030_madc_hwmon_exit(void)
-{
- platform_driver_unregister(&twl4030_madc_hwmon_driver);
-}
-
-module_exit(twl4030_madc_hwmon_exit);
+module_platform_driver(twl4030_madc_hwmon_driver);
MODULE_DESCRIPTION("TWL4030 ADC Hwmon driver");
MODULE_LICENSE("GPL");
.remove = __devexit_p(env_remove),
};
-static int __init env_init(void)
-{
- return platform_driver_register(&env_driver);
-}
-
-static void __exit env_exit(void)
-{
- platform_driver_unregister(&env_driver);
-}
-
-module_init(env_init);
-module_exit(env_exit);
+module_platform_driver(env_driver);
},
};
-static int __init wm831x_hwmon_init(void)
-{
- return platform_driver_register(&wm831x_hwmon_driver);
-}
-module_init(wm831x_hwmon_init);
-
-static void __exit wm831x_hwmon_exit(void)
-{
- platform_driver_unregister(&wm831x_hwmon_driver);
-}
-module_exit(wm831x_hwmon_exit);
+module_platform_driver(wm831x_hwmon_driver);
MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
MODULE_DESCRIPTION("WM831x Hardware Monitoring");
},
};
-static int __init wm8350_hwmon_init(void)
-{
- return platform_driver_register(&wm8350_hwmon_driver);
-}
-module_init(wm8350_hwmon_init);
-
-static void __exit wm8350_hwmon_exit(void)
-{
- platform_driver_unregister(&wm8350_hwmon_driver);
-}
-module_exit(wm8350_hwmon_exit);
+module_platform_driver(wm8350_hwmon_driver);
MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
MODULE_DESCRIPTION("WM8350 Hardware Monitoring");
if (flags & I2C_M_TEN) {
/* a ten bit address */
- addr = 0xf0 | ((msg->addr >> 7) & 0x03);
+ addr = 0xf0 | ((msg->addr >> 7) & 0x06);
bit_dbg(2, &i2c_adap->dev, "addr0: %d\n", addr);
/* try extended address code...*/
ret = try_address(i2c_adap, addr, retries);
return -ENXIO;
}
/* the remaining 8 bit address */
- ret = i2c_outb(i2c_adap, msg->addr & 0x7f);
+ ret = i2c_outb(i2c_adap, msg->addr & 0xff);
if ((ret != 1) && !nak_ok) {
/* the chip did not ack / xmission error occurred */
dev_err(&i2c_adap->dev, "died at 2nd address code\n");
/* Set the number of I2C channel instance */
adap_info->ch_num = id->driver_data;
+ ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
+ KBUILD_MODNAME, adap_info);
+ if (ret) {
+ pch_pci_err(pdev, "request_irq FAILED\n");
+ goto err_request_irq;
+ }
+
for (i = 0; i < adap_info->ch_num; i++) {
pch_adap = &adap_info->pch_data[i].pch_adapter;
adap_info->pch_i2c_suspended = false;
pch_adap->dev.parent = &pdev->dev;
+ pch_i2c_init(&adap_info->pch_data[i]);
ret = i2c_add_adapter(pch_adap);
if (ret) {
pch_pci_err(pdev, "i2c_add_adapter[ch:%d] FAILED\n", i);
- goto err_i2c_add_adapter;
+ goto err_add_adapter;
}
-
- pch_i2c_init(&adap_info->pch_data[i]);
- }
- ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
- KBUILD_MODNAME, adap_info);
- if (ret) {
- pch_pci_err(pdev, "request_irq FAILED\n");
- goto err_i2c_add_adapter;
}
pci_set_drvdata(pdev, adap_info);
pch_pci_dbg(pdev, "returns %d.\n", ret);
return 0;
-err_i2c_add_adapter:
+err_add_adapter:
for (j = 0; j < i; j++)
i2c_del_adapter(&adap_info->pch_data[j].pch_adapter);
+ free_irq(pdev->irq, adap_info);
+err_request_irq:
pci_iounmap(pdev, base_addr);
err_pci_iomap:
pci_release_regions(pdev);
i2c->adap.algo_data = i2c;
i2c->adap.dev.parent = &pdev->dev;
- mfp_set_groupg(&pdev->dev);
+ mfp_set_groupg(&pdev->dev, NULL);
clk_get_rate(i2c->clk);
* size. This is to ensure that we can handle the status on int
* call back latencies.
*/
- if (dev->rev >= OMAP_I2C_REV_ON_3530_4430) {
- dev->fifo_size = 0;
+
+ dev->fifo_size = (dev->fifo_size / 2);
+
+ if (dev->rev >= OMAP_I2C_REV_ON_3530_4430)
dev->b_hw = 0; /* Disable hardware fixes */
- } else {
- dev->fifo_size = (dev->fifo_size / 2);
+ else
dev->b_hw = 1; /* Enable hardware fixes */
- }
+
/* calculate wakeup latency constraint for MPU */
if (dev->set_mpu_wkup_lat != NULL)
dev->latency = (1000000 * dev->fifo_size) /
/* first, try busy waiting briefly */
do {
+ cpu_relax();
iicstat = readl(i2c->regs + S3C2410_IICSTAT);
} while ((iicstat & S3C2410_IICSTAT_START) && --spins);
#else
static int s3c24xx_i2c_parse_dt_gpio(struct s3c24xx_i2c *i2c)
{
- return -EINVAL;
+ return 0;
}
static void s3c24xx_i2c_dt_gpio_free(struct s3c24xx_i2c *i2c)
client->dev.type = &i2c_client_type;
client->dev.of_node = info->of_node;
+ /* For 10-bit clients, add an arbitrary offset to avoid collisions */
dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
- client->addr);
+ client->addr | ((client->flags & I2C_CLIENT_TEN)
+ ? 0xa000 : 0));
status = device_register(&client->dev);
if (status)
goto out_err;
return 0;
}
-int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
+static int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
void *data)
{
struct device *dev = data;
/*
* Copyright (C) 1998-2000 Andreas S. Krebs (akrebs@altavista.net), Maintainer
* Copyright (C) 1998-2002 Andre Hedrick <andre@linux-ide.org>, Integrator
- * Copyright (C) 2007-2010 Bartlomiej Zolnierkiewicz
+ * Copyright (C) 2007-2011 Bartlomiej Zolnierkiewicz
*
* CYPRESS CY82C693 chipset IDE controller
*
u8 time_16, time_8;
/* select primary or secondary channel */
- if (hwif->index > 0) { /* drive is on the secondary channel */
+ if (drive->dn > 1) { /* drive is on the secondary channel */
dev = pci_get_slot(dev->bus, dev->devfn+1);
if (!dev) {
printk(KERN_ERR "%s: tune_drive: "
pci_write_config_byte(dev, CY82_IDE_SLAVE_IOW, time_16);
pci_write_config_byte(dev, CY82_IDE_SLAVE_8BIT, time_8);
}
- if (hwif->index > 0)
+ if (drive->dn > 1)
pci_dev_put(dev);
}
if (ec->dma != NO_DMA && !request_dma(ec->dma, DRV_NAME)) {
d.init_dma = icside_dma_init;
d.port_ops = &icside_v6_port_ops;
+ } else
d.dma_ops = NULL;
- }
ret = ide_host_register(host, &d, hws);
if (ret)
.udma_mask = udma, \
}
-#define DECLARE_ICH_DEV(udma) \
+#define DECLARE_ICH_DEV(mwdma, udma) \
{ \
.name = DRV_NAME, \
.init_chipset = init_chipset_ich, \
.port_ops = &ich_port_ops, \
.pio_mask = ATA_PIO4, \
.swdma_mask = ATA_SWDMA2_ONLY, \
- .mwdma_mask = ATA_MWDMA12_ONLY, \
+ .mwdma_mask = mwdma, \
.udma_mask = udma, \
}
/* 2: PIIX4 */
DECLARE_PIIX_DEV(ATA_UDMA2),
/* 3: ICH0 */
- DECLARE_ICH_DEV(ATA_UDMA2),
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA2),
/* 4: ICH */
- DECLARE_ICH_DEV(ATA_UDMA4),
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA4),
/* 5: PIIX4 */
DECLARE_PIIX_DEV(ATA_UDMA4),
- /* 6: ICH[2-7]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
- DECLARE_ICH_DEV(ATA_UDMA5),
+ /* 6: ICH[2-6]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA5),
+ /* 7: ICH7/7-R, no MWDMA1 */
+ DECLARE_ICH_DEV(ATA_MWDMA2_ONLY, ATA_UDMA5),
};
/**
#endif
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB_2), 6 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH6_19), 6 },
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21), 6 },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21), 7 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_82801DB_1), 6 },
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18), 6 },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18), 7 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH8_6), 6 },
{ 0, },
};
};
MODULE_DEVICE_TABLE(pci, triflex_pci_tbl);
+#ifdef CONFIG_PM
+static int triflex_ide_pci_suspend(struct pci_dev *dev, pm_message_t state)
+{
+ /*
+ * We must not disable or powerdown the device.
+ * APM bios refuses to suspend if IDE is not accessible.
+ */
+ pci_save_state(dev);
+ return 0;
+}
+#else
+#define triflex_ide_pci_suspend NULL
+#endif
+
static struct pci_driver triflex_pci_driver = {
.name = "TRIFLEX_IDE",
.id_table = triflex_pci_tbl,
.probe = triflex_init_one,
.remove = ide_pci_remove,
- .suspend = ide_pci_suspend,
+ .suspend = triflex_ide_pci_suspend,
.resume = ide_pci_resume,
};
{
dev->addr_len = IEEE802154_ADDR_LEN;
memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
- dev->features = NETIF_F_NO_CSUM;
+ dev->features = NETIF_F_HW_CSUM;
dev->needed_tailroom = 2; /* FCS */
dev->mtu = 127;
dev->tx_queue_len = 10;
mutex_unlock(&lock);
}
+static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *addr)
+{
+ struct neighbour *n;
+ int ret;
+
+ rcu_read_lock();
+ n = dst_get_neighbour_noref(dst);
+ if (!n || !(n->nud_state & NUD_VALID)) {
+ if (n)
+ neigh_event_send(n, NULL);
+ ret = -ENODATA;
+ } else {
+ ret = rdma_copy_addr(addr, dst->dev, n->ha);
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
static int addr4_resolve(struct sockaddr_in *src_in,
struct sockaddr_in *dst_in,
struct rdma_dev_addr *addr)
__be32 src_ip = src_in->sin_addr.s_addr;
__be32 dst_ip = dst_in->sin_addr.s_addr;
struct rtable *rt;
- struct neighbour *neigh;
struct flowi4 fl4;
int ret;
goto put;
}
- neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev);
- if (!neigh || !(neigh->nud_state & NUD_VALID)) {
- neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
- ret = -ENODATA;
- if (neigh)
- goto release;
- goto put;
- }
-
- ret = rdma_copy_addr(addr, neigh->dev, neigh->ha);
-release:
- neigh_release(neigh);
+ ret = dst_fetch_ha(&rt->dst, addr);
put:
ip_rt_put(rt);
out:
struct rdma_dev_addr *addr)
{
struct flowi6 fl6;
- struct neighbour *neigh;
struct dst_entry *dst;
int ret;
memset(&fl6, 0, sizeof fl6);
- ipv6_addr_copy(&fl6.daddr, &dst_in->sin6_addr);
- ipv6_addr_copy(&fl6.saddr, &src_in->sin6_addr);
+ fl6.daddr = dst_in->sin6_addr;
+ fl6.saddr = src_in->sin6_addr;
fl6.flowi6_oif = addr->bound_dev_if;
dst = ip6_route_output(&init_net, NULL, &fl6);
goto put;
src_in->sin6_family = AF_INET6;
- ipv6_addr_copy(&src_in->sin6_addr, &fl6.saddr);
+ src_in->sin6_addr = fl6.saddr;
}
if (dst->dev->flags & IFF_LOOPBACK) {
goto put;
}
- neigh = dst_get_neighbour(dst);
- if (!neigh || !(neigh->nud_state & NUD_VALID)) {
- if (neigh)
- neigh_event_send(neigh, NULL);
- ret = -ENODATA;
- goto put;
- }
-
- ret = rdma_copy_addr(addr, dst->dev, neigh->ha);
+ ret = dst_fetch_ha(dst, addr);
put:
dst_release(dst);
return ret;
if (cma_zero_addr(src)) {
dst = (struct sockaddr *) &id_priv->id.route.addr.dst_addr;
if ((src->sa_family = dst->sa_family) == AF_INET) {
- ((struct sockaddr_in *) src)->sin_addr.s_addr =
- ((struct sockaddr_in *) dst)->sin_addr.s_addr;
+ ((struct sockaddr_in *)src)->sin_addr =
+ ((struct sockaddr_in *)dst)->sin_addr;
} else {
- ipv6_addr_copy(&((struct sockaddr_in6 *) src)->sin6_addr,
- &((struct sockaddr_in6 *) dst)->sin6_addr);
+ ((struct sockaddr_in6 *)src)->sin6_addr =
+ ((struct sockaddr_in6 *)dst)->sin6_addr;
}
}
req.private_data_len = sizeof(struct cma_hdr) +
conn_param->private_data_len;
+ if (req.private_data_len < conn_param->private_data_len)
+ return -EINVAL;
+
req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
if (!req.private_data)
return -ENOMEM;
memset(&req, 0, sizeof req);
offset = cma_user_data_offset(id_priv->id.ps);
req.private_data_len = offset + conn_param->private_data_len;
+ if (req.private_data_len < conn_param->private_data_len)
+ return -EINVAL;
+
private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
if (!private_data)
return -ENOMEM;
struct iwch_ep *child_ep, *parent_ep = ctx;
struct cpl_pass_accept_req *req = cplhdr(skb);
unsigned int hwtid = GET_TID(req);
- struct neighbour *neigh;
struct dst_entry *dst;
struct l2t_entry *l2t;
struct rtable *rt;
goto reject;
}
dst = &rt->dst;
- neigh = dst_get_neighbour(dst);
- l2t = t3_l2t_get(tdev, neigh, neigh->dev);
+ l2t = t3_l2t_get(tdev, dst, NULL);
if (!l2t) {
printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
__func__);
int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
{
struct iwch_dev *h = to_iwch_dev(cm_id->device);
- struct neighbour *neigh;
struct iwch_ep *ep;
struct rtable *rt;
int err = 0;
goto fail3;
}
ep->dst = &rt->dst;
-
- neigh = dst_get_neighbour(ep->dst);
-
- /* get a l2t entry */
- ep->l2t = t3_l2t_get(ep->com.tdev, neigh, neigh->dev);
+ ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL);
if (!ep->l2t) {
printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
err = -ENOMEM;
(mpa_rev_to_use == 2 ? MPA_ENHANCED_RDMA_CONN : 0);
mpa->private_data_size = htons(ep->plen);
mpa->revision = mpa_rev_to_use;
- if (mpa_rev_to_use == 1)
+ if (mpa_rev_to_use == 1) {
ep->tried_with_mpa_v1 = 1;
+ ep->retry_with_mpa_v1 = 0;
+ }
if (mpa_rev_to_use == 2) {
mpa->private_data_size +=
return;
}
+static int import_ep(struct c4iw_ep *ep, __be32 peer_ip, struct dst_entry *dst,
+ struct c4iw_dev *cdev, bool clear_mpa_v1)
+{
+ struct neighbour *n;
+ int err, step;
+
+ rcu_read_lock();
+ n = dst_get_neighbour_noref(dst);
+ err = -ENODEV;
+ if (!n)
+ goto out;
+ err = -ENOMEM;
+ if (n->dev->flags & IFF_LOOPBACK) {
+ struct net_device *pdev;
+
+ pdev = ip_dev_find(&init_net, peer_ip);
+ ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
+ n, pdev, 0);
+ if (!ep->l2t)
+ goto out;
+ ep->mtu = pdev->mtu;
+ ep->tx_chan = cxgb4_port_chan(pdev);
+ ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
+ step = cdev->rdev.lldi.ntxq /
+ cdev->rdev.lldi.nchan;
+ ep->txq_idx = cxgb4_port_idx(pdev) * step;
+ step = cdev->rdev.lldi.nrxq /
+ cdev->rdev.lldi.nchan;
+ ep->ctrlq_idx = cxgb4_port_idx(pdev);
+ ep->rss_qid = cdev->rdev.lldi.rxq_ids[
+ cxgb4_port_idx(pdev) * step];
+ dev_put(pdev);
+ } else {
+ ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
+ n, n->dev, 0);
+ if (!ep->l2t)
+ goto out;
+ ep->mtu = dst_mtu(ep->dst);
+ ep->tx_chan = cxgb4_port_chan(n->dev);
+ ep->smac_idx = (cxgb4_port_viid(n->dev) & 0x7F) << 1;
+ step = cdev->rdev.lldi.ntxq /
+ cdev->rdev.lldi.nchan;
+ ep->txq_idx = cxgb4_port_idx(n->dev) * step;
+ ep->ctrlq_idx = cxgb4_port_idx(n->dev);
+ step = cdev->rdev.lldi.nrxq /
+ cdev->rdev.lldi.nchan;
+ ep->rss_qid = cdev->rdev.lldi.rxq_ids[
+ cxgb4_port_idx(n->dev) * step];
+
+ if (clear_mpa_v1) {
+ ep->retry_with_mpa_v1 = 0;
+ ep->tried_with_mpa_v1 = 0;
+ }
+ }
+ err = 0;
+out:
+ rcu_read_unlock();
+
+ return err;
+}
+
static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *child_ep, *parent_ep;
unsigned int stid = GET_POPEN_TID(ntohl(req->tos_stid));
struct tid_info *t = dev->rdev.lldi.tids;
unsigned int hwtid = GET_TID(req);
- struct neighbour *neigh;
struct dst_entry *dst;
- struct l2t_entry *l2t;
struct rtable *rt;
__be32 local_ip, peer_ip;
__be16 local_port, peer_port;
- struct net_device *pdev;
- u32 tx_chan, smac_idx;
- u16 rss_qid;
- u32 mtu;
- int step;
- int txq_idx, ctrlq_idx;
+ int err;
parent_ep = lookup_stid(t, stid);
PDBG("%s parent ep %p tid %u\n", __func__, parent_ep, hwtid);
goto reject;
}
dst = &rt->dst;
- neigh = dst_get_neighbour(dst);
- if (neigh->dev->flags & IFF_LOOPBACK) {
- pdev = ip_dev_find(&init_net, peer_ip);
- BUG_ON(!pdev);
- l2t = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, pdev, 0);
- mtu = pdev->mtu;
- tx_chan = cxgb4_port_chan(pdev);
- smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
- step = dev->rdev.lldi.ntxq / dev->rdev.lldi.nchan;
- txq_idx = cxgb4_port_idx(pdev) * step;
- ctrlq_idx = cxgb4_port_idx(pdev);
- step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
- rss_qid = dev->rdev.lldi.rxq_ids[cxgb4_port_idx(pdev) * step];
- dev_put(pdev);
- } else {
- l2t = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, neigh->dev, 0);
- mtu = dst_mtu(dst);
- tx_chan = cxgb4_port_chan(neigh->dev);
- smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
- step = dev->rdev.lldi.ntxq / dev->rdev.lldi.nchan;
- txq_idx = cxgb4_port_idx(neigh->dev) * step;
- ctrlq_idx = cxgb4_port_idx(neigh->dev);
- step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
- rss_qid = dev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(neigh->dev) * step];
- }
- if (!l2t) {
- printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
+
+ child_ep = alloc_ep(sizeof(*child_ep), GFP_KERNEL);
+ if (!child_ep) {
+ printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
__func__);
dst_release(dst);
goto reject;
}
- child_ep = alloc_ep(sizeof(*child_ep), GFP_KERNEL);
- if (!child_ep) {
- printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
+ err = import_ep(child_ep, peer_ip, dst, dev, false);
+ if (err) {
+ printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
__func__);
- cxgb4_l2t_release(l2t);
dst_release(dst);
+ kfree(child_ep);
goto reject;
}
+
state_set(&child_ep->com, CONNECTING);
child_ep->com.dev = dev;
child_ep->com.cm_id = NULL;
c4iw_get_ep(&parent_ep->com);
child_ep->parent_ep = parent_ep;
child_ep->tos = GET_POPEN_TOS(ntohl(req->tos_stid));
- child_ep->l2t = l2t;
child_ep->dst = dst;
child_ep->hwtid = hwtid;
- child_ep->tx_chan = tx_chan;
- child_ep->smac_idx = smac_idx;
- child_ep->rss_qid = rss_qid;
- child_ep->mtu = mtu;
- child_ep->txq_idx = txq_idx;
- child_ep->ctrlq_idx = ctrlq_idx;
PDBG("%s tx_chan %u smac_idx %u rss_qid %u\n", __func__,
- tx_chan, smac_idx, rss_qid);
+ child_ep->tx_chan, child_ep->smac_idx, child_ep->rss_qid);
init_timer(&child_ep->timer);
cxgb4_insert_tid(t, child_ep, hwtid);
static int c4iw_reconnect(struct c4iw_ep *ep)
{
- int err = 0;
struct rtable *rt;
- struct net_device *pdev;
- struct neighbour *neigh;
- int step;
+ int err = 0;
PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
init_timer(&ep->timer);
}
ep->dst = &rt->dst;
- neigh = dst_get_neighbour(ep->dst);
-
- /* get a l2t entry */
- if (neigh->dev->flags & IFF_LOOPBACK) {
- PDBG("%s LOOPBACK\n", __func__);
- pdev = ip_dev_find(&init_net,
- ep->com.cm_id->remote_addr.sin_addr.s_addr);
- ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
- neigh, pdev, 0);
- ep->mtu = pdev->mtu;
- ep->tx_chan = cxgb4_port_chan(pdev);
- ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
- step = ep->com.dev->rdev.lldi.ntxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->txq_idx = cxgb4_port_idx(pdev) * step;
- step = ep->com.dev->rdev.lldi.nrxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->ctrlq_idx = cxgb4_port_idx(pdev);
- ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(pdev) * step];
- dev_put(pdev);
- } else {
- ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
- neigh, neigh->dev, 0);
- ep->mtu = dst_mtu(ep->dst);
- ep->tx_chan = cxgb4_port_chan(neigh->dev);
- ep->smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
- step = ep->com.dev->rdev.lldi.ntxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->txq_idx = cxgb4_port_idx(neigh->dev) * step;
- ep->ctrlq_idx = cxgb4_port_idx(neigh->dev);
- step = ep->com.dev->rdev.lldi.nrxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(neigh->dev) * step];
- }
- if (!ep->l2t) {
+ err = import_ep(ep, ep->com.cm_id->remote_addr.sin_addr.s_addr,
+ ep->dst, ep->com.dev, false);
+ if (err) {
printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
- err = -ENOMEM;
goto fail4;
}
int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
{
- int err = 0;
struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
struct c4iw_ep *ep;
struct rtable *rt;
- struct net_device *pdev;
- struct neighbour *neigh;
- int step;
+ int err = 0;
if ((conn_param->ord > c4iw_max_read_depth) ||
(conn_param->ird > c4iw_max_read_depth)) {
}
ep->dst = &rt->dst;
- neigh = dst_get_neighbour(ep->dst);
-
- /* get a l2t entry */
- if (neigh->dev->flags & IFF_LOOPBACK) {
- PDBG("%s LOOPBACK\n", __func__);
- pdev = ip_dev_find(&init_net,
- cm_id->remote_addr.sin_addr.s_addr);
- ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
- neigh, pdev, 0);
- ep->mtu = pdev->mtu;
- ep->tx_chan = cxgb4_port_chan(pdev);
- ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
- step = ep->com.dev->rdev.lldi.ntxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->txq_idx = cxgb4_port_idx(pdev) * step;
- step = ep->com.dev->rdev.lldi.nrxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->ctrlq_idx = cxgb4_port_idx(pdev);
- ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(pdev) * step];
- dev_put(pdev);
- } else {
- ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
- neigh, neigh->dev, 0);
- ep->mtu = dst_mtu(ep->dst);
- ep->tx_chan = cxgb4_port_chan(neigh->dev);
- ep->smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
- step = ep->com.dev->rdev.lldi.ntxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->txq_idx = cxgb4_port_idx(neigh->dev) * step;
- ep->ctrlq_idx = cxgb4_port_idx(neigh->dev);
- step = ep->com.dev->rdev.lldi.nrxq /
- ep->com.dev->rdev.lldi.nchan;
- ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(neigh->dev) * step];
- ep->retry_with_mpa_v1 = 0;
- ep->tried_with_mpa_v1 = 0;
- }
- if (!ep->l2t) {
+ err = import_ep(ep, cm_id->remote_addr.sin_addr.s_addr,
+ ep->dst, ep->com.dev, true);
+ if (err) {
printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
- err = -ENOMEM;
goto fail4;
}
while (ptr != cq->sw_pidx) {
cqe = &cq->sw_queue[ptr];
if (RQ_TYPE(cqe) && (CQE_OPCODE(cqe) != FW_RI_READ_RESP) &&
- (CQE_QPID(cqe) == wq->rq.qid) && cqe_completes_wr(cqe, wq))
+ (CQE_QPID(cqe) == wq->sq.qid) && cqe_completes_wr(cqe, wq))
(*count)++;
if (++ptr == cq->size)
ptr = 0;
err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma,
in_modifier, op_modifier,
- MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+ MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+ MLX4_CMD_NATIVE);
if (!err)
memcpy(response_mad, outmailbox->buf, 256);
return IB_MAD_RESULT_FAILURE;
err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0,
- MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C);
+ MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
+ MLX4_CMD_WRAPPED);
if (err)
err = IB_MAD_RESULT_FAILURE;
else {
{
struct mlx4_dev *dev = to_mdev(device)->dev;
- return dev->caps.port_mask & (1 << (port_num - 1)) ?
+ return dev->caps.port_mask[port_num] == MLX4_PORT_TYPE_IB ?
IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
}
memset(mailbox->buf, 0, 256);
memcpy(mailbox->buf, props->node_desc, 64);
mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
- MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox);
}
err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
mlx4_free_cmd_mailbox(dev->dev, mailbox);
return err;
memcpy(gids, gw->gids, sizeof gw->gids);
err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
- 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B);
+ 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
if (err)
printk(KERN_WARNING "set port command failed\n");
else {
printk_once(KERN_INFO "%s", mlx4_ib_version);
+ if (mlx4_is_mfunc(dev)) {
+ printk(KERN_WARNING "IB not yet supported in SRIOV\n");
+ return NULL;
+ }
+
mlx4_foreach_ib_transport_port(i, dev)
num_ports++;
err_counter:
for (; i; --i)
- mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]);
+ if (ibdev->counters[i - 1] != -1)
+ mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]);
err_map:
iounmap(ibdev->uar_map);
}
iounmap(ibdev->uar_map);
for (p = 0; p < ibdev->num_ports; ++p)
- mlx4_counter_free(ibdev->dev, ibdev->counters[p]);
+ if (ibdev->counters[p] != -1)
+ mlx4_counter_free(ibdev->dev, ibdev->counters[p]);
mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB)
mlx4_CLOSE_PORT(dev, p);
else
netdev = nesvnic->netdev;
- neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, netdev);
+ rcu_read_lock();
+ neigh = dst_get_neighbour_noref(&rt->dst);
if (neigh) {
if (neigh->nud_state & NUD_VALID) {
nes_debug(NES_DBG_CM, "Neighbor MAC address for 0x%08X"
if (!memcmp(nesadapter->arp_table[arpindex].mac_addr,
neigh->ha, ETH_ALEN)) {
/* Mac address same as in nes_arp_table */
- neigh_release(neigh);
ip_rt_put(rt);
return rc;
}
dst_ip, NES_ARP_ADD);
rc = nes_arp_table(nesvnic->nesdev, dst_ip, NULL,
NES_ARP_RESOLVE);
+ } else {
+ neigh_event_send(neigh, NULL);
}
- neigh_release(neigh);
}
-
- if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID)))
- neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
-
+ rcu_read_unlock();
ip_rt_put(rt);
return rc;
}
.set_pauseparam = nes_netdev_set_pauseparam,
};
-static void nes_vlan_mode(struct net_device *netdev, struct nes_device *nesdev, u32 features)
+static void nes_vlan_mode(struct net_device *netdev, struct nes_device *nesdev, netdev_features_t features)
{
struct nes_adapter *nesadapter = nesdev->nesadapter;
u32 u32temp;
spin_unlock_irqrestore(&nesadapter->phy_lock, flags);
}
-static u32 nes_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t nes_fix_features(struct net_device *netdev, netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int nes_set_features(struct net_device *netdev, u32 features)
+static int nes_set_features(struct net_device *netdev, netdev_features_t features)
{
struct nes_vnic *nesvnic = netdev_priv(netdev);
struct nes_device *nesdev = nesvnic->nesdev;
strlcpy(rcd->comm, current->comm, sizeof(rcd->comm));
ctxt_fp(fp) = rcd;
qib_stats.sps_ctxts++;
- dd->freectxts++;
+ dd->freectxts--;
ret = 0;
goto bail;
if (dd->pageshadow)
unlock_expected_tids(rcd);
qib_stats.sps_ctxts--;
- dd->freectxts--;
+ dd->freectxts++;
}
mutex_unlock(&qib_mutex);
SYM_LSB(IBCCtrlA_0, MaxPktLen);
ppd->cpspec->ibcctrl_a = ibc; /* without linkcmd or linkinitcmd! */
- /* initially come up waiting for TS1, without sending anything. */
- val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
- QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
-
- ppd->cpspec->ibcctrl_a = val;
/*
* Reset the PCS interface to the serdes (and also ibc, which is still
* in reset from above). Writes new value of ibcctrl_a as last step.
*/
qib_7322_mini_pcs_reset(ppd);
- qib_write_kreg(dd, kr_scratch, 0ULL);
- /* clear the linkinit cmds */
- ppd->cpspec->ibcctrl_a &= ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
if (!ppd->cpspec->ibcctrl_b) {
unsigned lse = ppd->link_speed_enabled;
ppd->cpspec->ibcctrl_a |= SYM_MASK(IBCCtrlA_0, IBLinkEn);
set_vls(ppd);
+ /* initially come up DISABLED, without sending anything. */
+ val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
+ QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
+ qib_write_kreg_port(ppd, krp_ibcctrl_a, val);
+ qib_write_kreg(dd, kr_scratch, 0ULL);
+ /* clear the linkinit cmds */
+ ppd->cpspec->ibcctrl_a = val & ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
+
/* be paranoid against later code motion, etc. */
spin_lock_irqsave(&dd->cspec->rcvmod_lock, flags);
ppd->p_rcvctrl |= SYM_MASK(RcvCtrl_0, RcvIBPortEnable);
off */
if (ppd->dd->flags & QIB_HAS_QSFP) {
qd->t_insert = get_jiffies_64();
- schedule_work(&qd->work);
+ queue_work(ib_wq, &qd->work);
}
spin_lock_irqsave(&ppd->sdma_lock, flags);
if (__qib_sdma_running(ppd))
udelay(20); /* Generous RST dwell */
dd->f_gpio_mod(dd, mask, mask, mask);
- /* Spec says module can take up to two seconds! */
- mask = QSFP_GPIO_MOD_PRS_N;
- if (qd->ppd->hw_pidx)
- mask <<= QSFP_GPIO_PORT2_SHIFT;
-
- /* Do not try to wait here. Better to let event handle it */
- if (!qib_qsfp_mod_present(qd->ppd))
- goto bail;
- /* We see a module, but it may be unwise to look yet. Just schedule */
- qd->t_insert = get_jiffies_64();
- queue_work(ib_wq, &qd->work);
-bail:
return;
}
struct ib_pd *pd, struct ib_ah_attr *attr)
{
struct ipoib_ah *ah;
+ struct ib_ah *vah;
ah = kmalloc(sizeof *ah, GFP_KERNEL);
if (!ah)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ah->dev = dev;
ah->last_send = 0;
kref_init(&ah->ref);
- ah->ah = ib_create_ah(pd, attr);
- if (IS_ERR(ah->ah)) {
+ vah = ib_create_ah(pd, attr);
+ if (IS_ERR(vah)) {
kfree(ah);
- ah = NULL;
- } else
+ ah = (struct ipoib_ah *)vah;
+ } else {
+ ah->ah = vah;
ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
+ }
return ah;
}
return 0;
}
-static u32 ipoib_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
spin_lock_irqsave(&priv->lock, flags);
- if (ah) {
+ if (!IS_ERR_OR_NULL(ah)) {
path->pathrec = *pathrec;
old_ah = path->ah;
return 0;
}
-static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
+/* called with rcu_read_lock */
+static void neigh_add_path(struct sk_buff *skb, struct neighbour *n, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
struct ipoib_neigh *neigh;
- struct neighbour *n;
unsigned long flags;
- n = dst_get_neighbour(skb_dst(skb));
neigh = ipoib_neigh_alloc(n, skb->dev);
if (!neigh) {
++dev->stats.tx_dropped;
spin_unlock_irqrestore(&priv->lock, flags);
}
-static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
+/* called with rcu_read_lock */
+static void ipoib_path_lookup(struct sk_buff *skb, struct neighbour *n, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(skb->dev);
- struct dst_entry *dst = skb_dst(skb);
- struct neighbour *n;
/* Look up path record for unicasts */
- n = dst_get_neighbour(dst);
if (n->ha[4] != 0xff) {
- neigh_add_path(skb, dev);
+ neigh_add_path(skb, n, dev);
return;
}
struct neighbour *n = NULL;
unsigned long flags;
- if (likely(skb_dst(skb)))
- n = dst_get_neighbour(skb_dst(skb));
-
+ rcu_read_lock();
+ if (likely(skb_dst(skb))) {
+ n = dst_get_neighbour_noref(skb_dst(skb));
+ if (!n) {
+ ++dev->stats.tx_dropped;
+ dev_kfree_skb_any(skb);
+ goto unlock;
+ }
+ }
if (likely(n)) {
if (unlikely(!*to_ipoib_neigh(n))) {
- ipoib_path_lookup(skb, dev);
- return NETDEV_TX_OK;
+ ipoib_path_lookup(skb, n, dev);
+ goto unlock;
}
neigh = *to_ipoib_neigh(n);
list_del(&neigh->list);
ipoib_neigh_free(dev, neigh);
spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_path_lookup(skb, dev);
- return NETDEV_TX_OK;
+ ipoib_path_lookup(skb, n, dev);
+ goto unlock;
}
if (ipoib_cm_get(neigh)) {
if (ipoib_cm_up(neigh)) {
ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
- return NETDEV_TX_OK;
+ goto unlock;
}
} else if (neigh->ah) {
ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(n->ha));
- return NETDEV_TX_OK;
+ goto unlock;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
phdr->hwaddr + 4);
dev_kfree_skb_any(skb);
++dev->stats.tx_dropped;
- return NETDEV_TX_OK;
+ goto unlock;
}
unicast_arp_send(skb, dev, phdr);
}
}
-
+unlock:
+ rcu_read_unlock();
return NETDEV_TX_OK;
}
dst = skb_dst(skb);
n = NULL;
if (dst)
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref_raw(dst);
if ((!dst || !n) && daddr) {
struct ipoib_pseudoheader *phdr =
(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu;
+ priv->dev->neigh_priv_len = sizeof(struct ipoib_neigh);
+
result = ib_query_pkey(hca, port, 0, &priv->pkey);
if (result) {
printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
av.grh.dgid = mcast->mcmember.mgid;
ah = ipoib_create_ah(dev, priv->pd, &av);
- if (!ah) {
- ipoib_warn(priv, "ib_address_create failed\n");
+ if (IS_ERR(ah)) {
+ ipoib_warn(priv, "ib_address_create failed %ld\n",
+ -PTR_ERR(ah));
+ /* use original error */
+ return PTR_ERR(ah);
} else {
spin_lock_irq(&priv->lock);
mcast->ah = ah;
skb->dev = dev;
if (dst)
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref_raw(dst);
if (!dst || !n) {
/* put pseudoheader back on for next time */
skb_push(skb, sizeof (struct ipoib_pseudoheader));
if (mcast && mcast->ah) {
struct dst_entry *dst = skb_dst(skb);
struct neighbour *n = NULL;
+
+ rcu_read_lock();
if (dst)
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
if (n && !*to_ipoib_neigh(n)) {
struct ipoib_neigh *neigh = ipoib_neigh_alloc(n,
skb->dev);
list_add_tail(&neigh->list, &mcast->neigh_list);
}
}
-
+ rcu_read_unlock();
spin_unlock_irqrestore(&priv->lock, flags);
ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
return;
static irqreturn_t cma3000_thread_irq(int irq, void *dev_id)
{
struct cma3000_accl_data *data = dev_id;
- int datax, datay, dataz;
- u8 ctrl, mode, range, intr_status;
+ int datax, datay, dataz, intr_status;
+ u8 ctrl, mode, range;
intr_status = CMA3000_READ(data, CMA3000_INTSTATUS, "interrupt status");
if (intr_status < 0)
*/
static int elantech_set_properties(struct elantech_data *etd)
{
+ /* This represents the version of IC body. */
int ver = (etd->fw_version & 0x0f0000) >> 16;
+ /* Early version of Elan touchpads doesn't obey the rule. */
if (etd->fw_version < 0x020030 || etd->fw_version == 0x020600)
etd->hw_version = 1;
- else if (etd->fw_version < 0x150600)
- etd->hw_version = 2;
- else if (ver == 5)
- etd->hw_version = 3;
- else if (ver == 6)
- etd->hw_version = 4;
- else
- return -1;
+ else {
+ switch (ver) {
+ case 2:
+ case 4:
+ etd->hw_version = 2;
+ break;
+ case 5:
+ etd->hw_version = 3;
+ break;
+ case 6:
+ etd->hw_version = 4;
+ break;
+ default:
+ return -1;
+ }
+ }
/*
* Turn on packet checking by default.
* Finger Sensing Pad PS/2 mouse driver.
*
* Copyright (C) 2005-2007 Asia Vital Components Co., Ltd.
- * Copyright (C) 2005-2010 Tai-hwa Liang, Sentelic Corporation.
+ * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
ps2_sendbyte(ps2dev, v, FSP_CMD_TIMEOUT2);
if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0)
- return -1;
+ goto out;
if ((v = fsp_test_invert_cmd(reg_val)) != reg_val) {
/* inversion is required */
ps2_sendbyte(ps2dev, 0x88, FSP_CMD_TIMEOUT2);
if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0)
- return -1;
+ goto out;
if ((v = fsp_test_invert_cmd(reg_val)) != reg_val) {
ps2_sendbyte(ps2dev, 0x47, FSP_CMD_TIMEOUT2);
};
int val;
- if (fsp_reg_read(psmouse, FSP_REG_TMOD_STATUS1, &val) == -1)
+ if (fsp_reg_read(psmouse, FSP_REG_TMOD_STATUS, &val) == -1)
return -EIO;
*btn = buttons[(val & 0x30) >> 4];
* Finger Sensing Pad PS/2 mouse driver.
*
* Copyright (C) 2005-2007 Asia Vital Components Co., Ltd.
- * Copyright (C) 2005-2009 Tai-hwa Liang, Sentelic Corporation.
+ * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
/* Finger-sensing Pad control registers */
#define FSP_REG_SYSCTL1 0x10
#define FSP_BIT_EN_REG_CLK BIT(5)
+#define FSP_REG_TMOD_STATUS 0x20
#define FSP_REG_OPC_QDOWN 0x31
#define FSP_BIT_EN_OPC_TAG BIT(7)
#define FSP_REG_OPTZ_XLO 0x34
*/
#include <linux/module.h>
+#include <linux/delay.h>
#include <linux/dmi.h>
#include <linux/input/mt.h>
#include <linux/serio.h>
do {
psmouse_reset(psmouse);
+ if (retry) {
+ /*
+ * On some boxes, right after resuming, the touchpad
+ * needs some time to finish initializing (I assume
+ * it needs time to calibrate) and start responding
+ * to Synaptics-specific queries, so let's wait a
+ * bit.
+ */
+ ssleep(1);
+ }
error = synaptics_detect(psmouse, 0);
} while (error && ++retry < 3);
#include <linux/irq.h>
#include <linux/serio.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <asm/mach-types.h>
#include <plat/board-ams-delta.h>
DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
},
},
+ {
+ /* Newer HP Pavilion dv4 models */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+ },
+ },
{ }
};
DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
},
},
+ {
+ /* Newer HP Pavilion dv4 models */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+ },
+ },
{ }
};
static const struct wacom_features wacom_features_0xE6 =
{ "Wacom ISDv4 E6", WACOM_PKGLEN_TPC2FG, 27760, 15694, 255,
0, TABLETPC2FG, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0xEC =
+ { "Wacom ISDv4 EC", WACOM_PKGLEN_GRAPHIRE, 25710, 14500, 255,
+ 0, TABLETPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
static const struct wacom_features wacom_features_0x47 =
{ "Wacom Intuos2 6x8", WACOM_PKGLEN_INTUOS, 20320, 16240, 1023,
31, INTUOS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
{ USB_DEVICE_WACOM(0xE2) },
{ USB_DEVICE_WACOM(0xE3) },
{ USB_DEVICE_WACOM(0xE6) },
+ { USB_DEVICE_WACOM(0xEC) },
{ USB_DEVICE_WACOM(0x47) },
{ USB_DEVICE_LENOVO(0x6004) },
{ }
int dmar_disabled = 1;
#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+int intel_iommu_enabled = 0;
+EXPORT_SYMBOL_GPL(intel_iommu_enabled);
+
static int dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;
return 0;
}
-int dmar_parse_rmrr_atsr_dev(void)
+int __init dmar_parse_rmrr_atsr_dev(void)
{
struct dmar_rmrr_unit *rmrr, *rmrr_n;
struct dmar_atsr_unit *atsr, *atsr_n;
bus_register_notifier(&pci_bus_type, &device_nb);
+ intel_iommu_enabled = 1;
+
return 0;
}
return ir_supported;
}
-int ir_dev_scope_init(void)
+int __init ir_dev_scope_init(void)
{
if (!intr_remapping_enabled)
return 0;
if (bus == NULL || bus->iommu_ops == NULL)
return NULL;
- domain = kmalloc(sizeof(*domain), GFP_KERNEL);
+ domain = kzalloc(sizeof(*domain), GFP_KERNEL);
if (!domain)
return NULL;
case IIOCDOCFINT:
if (!divert_if.drv_to_name(dioctl.cf_ctrl.drvid))
return (-EINVAL); /* invalid driver */
+ if (strnlen(dioctl.cf_ctrl.msn, sizeof(dioctl.cf_ctrl.msn)) ==
+ sizeof(dioctl.cf_ctrl.msn))
+ return -EINVAL;
+ if (strnlen(dioctl.cf_ctrl.fwd_nr, sizeof(dioctl.cf_ctrl.fwd_nr)) ==
+ sizeof(dioctl.cf_ctrl.fwd_nr))
+ return -EINVAL;
if ((i = cf_command(dioctl.cf_ctrl.drvid,
(cmd == IIOCDOCFACT) ? 1 : (cmd == IIOCDOCFDIS) ? 0 : 2,
dioctl.cf_ctrl.cfproc,
{
isdn_if *iif;
- pr_info("ISDN4Linux interface\n");
-
iif = kmalloc(sizeof *iif, GFP_KERNEL);
if (!iif) {
pr_err("out of memory\n");
*/
void gigaset_isdn_regdrv(void)
{
+ pr_info("ISDN4Linux interface\n");
/* nothing to do */
}
char *c,
*e;
+ if (strnlen(cfg->drvid, sizeof(cfg->drvid)) ==
+ sizeof(cfg->drvid))
+ return -EINVAL;
drvidx = -1;
chidx = -1;
strcpy(drvid, cfg->drvid);
del_timer_sync(&led_cdev->blink_timer);
if (led_cdev->blink_set &&
- !led_cdev->blink_set(led_cdev, delay_on, delay_off)) {
- led_cdev->blink_delay_on = *delay_on;
- led_cdev->blink_delay_off = *delay_off;
+ !led_cdev->blink_set(led_cdev, delay_on, delay_off))
return;
- }
/* blink with 1 Hz as default if nothing specified */
if (!*delay_on && !*delay_off)
return PTR_ERR(vqs[i]);
}
+static const char *lg_bus_name(struct virtio_device *vdev)
+{
+ return "";
+}
+
/* The ops structure which hooks everything together. */
static struct virtio_config_ops lguest_config_ops = {
.get_features = lg_get_features,
.reset = lg_reset,
.find_vqs = lg_find_vqs,
.del_vqs = lg_del_vqs,
+ .bus_name = lg_bus_name,
};
/*
*/
int i;
+ spin_lock_irq(&bitmap->lock);
for (i = 0; i < bitmap->file_pages; i++)
set_page_attr(bitmap, bitmap->filemap[i],
BITMAP_PAGE_NEEDWRITE);
bitmap->allclean = 0;
+ spin_unlock_irq(&bitmap->lock);
}
static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
atomic_read(&bitmap->behind_writes),
bitmap->mddev->bitmap_info.max_write_behind);
}
- if (bitmap->mddev->degraded)
- /* Never clear bits or update events_cleared when degraded */
- success = 0;
while (sectors) {
sector_t blocks;
return;
}
- if (success &&
+ if (success && !bitmap->mddev->degraded &&
bitmap->events_cleared < bitmap->mddev->events) {
bitmap->events_cleared = bitmap->mddev->events;
bitmap->need_sync = 1;
for (chunk = s; chunk <= e; chunk++) {
sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
bitmap_set_memory_bits(bitmap, sec, 1);
+ spin_lock_irq(&bitmap->lock);
bitmap_file_set_bit(bitmap, sec);
+ spin_unlock_irq(&bitmap->lock);
if (sec < bitmap->mddev->recovery_cp)
/* We are asserting that the array is dirty,
* so move the recovery_cp address back so
return -EINVAL;
rdev->raid_disk = rdev->saved_raid_disk;
+ rdev->saved_raid_disk = -1;
newconf = linear_conf(mddev,mddev->raid_disks+1);
mddev->ctime == 0 && !mddev->hold_active) {
/* Array is not configured at all, and not held active,
* so destroy it */
- list_del(&mddev->all_mddevs);
+ list_del_init(&mddev->all_mddevs);
bs = mddev->bio_set;
mddev->bio_set = NULL;
if (mddev->gendisk) {
sep = ",";
}
if (test_bit(Blocked, &rdev->flags) ||
- rdev->badblocks.unacked_exist) {
+ (rdev->badblocks.unacked_exist
+ && !test_bit(Faulty, &rdev->flags))) {
len += sprintf(page+len, "%sblocked", sep);
sep = ",";
}
if (err)
return err;
else {
+ if (mddev->hold_active == UNTIL_IOCTL)
+ mddev->hold_active = 0;
sysfs_notify_dirent_safe(mddev->sysfs_state);
return len;
}
if (!entry->show)
return -EIO;
+ spin_lock(&all_mddevs_lock);
+ if (list_empty(&mddev->all_mddevs)) {
+ spin_unlock(&all_mddevs_lock);
+ return -EBUSY;
+ }
+ mddev_get(mddev);
+ spin_unlock(&all_mddevs_lock);
+
rv = mddev_lock(mddev);
if (!rv) {
rv = entry->show(mddev, page);
mddev_unlock(mddev);
}
+ mddev_put(mddev);
return rv;
}
return -EIO;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
+ spin_lock(&all_mddevs_lock);
+ if (list_empty(&mddev->all_mddevs)) {
+ spin_unlock(&all_mddevs_lock);
+ return -EBUSY;
+ }
+ mddev_get(mddev);
+ spin_unlock(&all_mddevs_lock);
rv = mddev_lock(mddev);
- if (mddev->hold_active == UNTIL_IOCTL)
- mddev->hold_active = 0;
if (!rv) {
rv = entry->store(mddev, page, length);
mddev_unlock(mddev);
}
+ mddev_put(mddev);
return rv;
}
spares++;
md_new_event(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- } else
- break;
+ }
}
}
}
s + rdev->data_offset, sectors, acknowledged);
if (rv) {
/* Make sure they get written out promptly */
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
md_wakeup_thread(rdev->mddev->thread);
}
if (dev->written)
s->written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = NULL;
if (rdev) {
is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
&first_bad, &bad_sectors);
}
} else if (test_bit(In_sync, &rdev->flags))
set_bit(R5_Insync, &dev->flags);
- else if (!test_bit(Faulty, &rdev->flags)) {
+ else if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
/* in sync if before recovery_offset */
- if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
- set_bit(R5_Insync, &dev->flags);
- }
- if (test_bit(R5_WriteError, &dev->flags)) {
+ set_bit(R5_Insync, &dev->flags);
+ else if (test_bit(R5_UPTODATE, &dev->flags) &&
+ test_bit(R5_Expanded, &dev->flags))
+ /* If we've reshaped into here, we assume it is Insync.
+ * We will shortly update recovery_offset to make
+ * it official.
+ */
+ set_bit(R5_Insync, &dev->flags);
+
+ if (rdev && test_bit(R5_WriteError, &dev->flags)) {
clear_bit(R5_Insync, &dev->flags);
if (!test_bit(Faulty, &rdev->flags)) {
s->handle_bad_blocks = 1;
} else
clear_bit(R5_WriteError, &dev->flags);
}
- if (test_bit(R5_MadeGood, &dev->flags)) {
+ if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
if (!test_bit(Faulty, &rdev->flags)) {
s->handle_bad_blocks = 1;
atomic_inc(&rdev->nr_pending);
static int mxl5007t_read_reg(struct mxl5007t_state *state, u8 reg, u8 *val)
{
+ u8 buf[2] = { 0xfb, reg };
struct i2c_msg msg[] = {
{ .addr = state->i2c_props.addr, .flags = 0,
- .buf = ®, .len = 1 },
+ .buf = buf, .len = 2 },
{ .addr = state->i2c_props.addr, .flags = I2C_M_RD,
.buf = val, .len = 1 },
};
switch (params->u.ofdm.bandwidth) {
case BANDWIDTH_6_MHZ:
LP_Fc = 0;
- LO_Frac = params->frequency + 4000000;
+ LO_Frac = params->frequency + 3000000;
break;
case BANDWIDTH_7_MHZ:
LP_Fc = 1;
dma_addr_t inbuf_dma;
dma_addr_t outbuf_dma;
- unsigned char old_data[2]; /* Detect duplicate events */
+ unsigned char old_data; /* Detect duplicate events */
unsigned long old_jiffies;
unsigned long acc_jiffies; /* handle acceleration */
unsigned long first_jiffies;
/* Translation table from hardware messages to input events. */
static const struct {
short kind;
- unsigned char data1, data2;
+ unsigned char data;
int type;
unsigned int code;
int value;
} ati_remote_tbl[] = {
/* Directional control pad axes */
- {KIND_ACCEL, 0x35, 0x70, EV_REL, REL_X, -1}, /* left */
- {KIND_ACCEL, 0x36, 0x71, EV_REL, REL_X, 1}, /* right */
- {KIND_ACCEL, 0x37, 0x72, EV_REL, REL_Y, -1}, /* up */
- {KIND_ACCEL, 0x38, 0x73, EV_REL, REL_Y, 1}, /* down */
+ {KIND_ACCEL, 0x70, EV_REL, REL_X, -1}, /* left */
+ {KIND_ACCEL, 0x71, EV_REL, REL_X, 1}, /* right */
+ {KIND_ACCEL, 0x72, EV_REL, REL_Y, -1}, /* up */
+ {KIND_ACCEL, 0x73, EV_REL, REL_Y, 1}, /* down */
/* Directional control pad diagonals */
- {KIND_LU, 0x39, 0x74, EV_REL, 0, 0}, /* left up */
- {KIND_RU, 0x3a, 0x75, EV_REL, 0, 0}, /* right up */
- {KIND_LD, 0x3c, 0x77, EV_REL, 0, 0}, /* left down */
- {KIND_RD, 0x3b, 0x76, EV_REL, 0, 0}, /* right down */
+ {KIND_LU, 0x74, EV_REL, 0, 0}, /* left up */
+ {KIND_RU, 0x75, EV_REL, 0, 0}, /* right up */
+ {KIND_LD, 0x77, EV_REL, 0, 0}, /* left down */
+ {KIND_RD, 0x76, EV_REL, 0, 0}, /* right down */
/* "Mouse button" buttons */
- {KIND_LITERAL, 0x3d, 0x78, EV_KEY, BTN_LEFT, 1}, /* left btn down */
- {KIND_LITERAL, 0x3e, 0x79, EV_KEY, BTN_LEFT, 0}, /* left btn up */
- {KIND_LITERAL, 0x41, 0x7c, EV_KEY, BTN_RIGHT, 1},/* right btn down */
- {KIND_LITERAL, 0x42, 0x7d, EV_KEY, BTN_RIGHT, 0},/* right btn up */
+ {KIND_LITERAL, 0x78, EV_KEY, BTN_LEFT, 1}, /* left btn down */
+ {KIND_LITERAL, 0x79, EV_KEY, BTN_LEFT, 0}, /* left btn up */
+ {KIND_LITERAL, 0x7c, EV_KEY, BTN_RIGHT, 1},/* right btn down */
+ {KIND_LITERAL, 0x7d, EV_KEY, BTN_RIGHT, 0},/* right btn up */
/* Artificial "doubleclick" events are generated by the hardware.
* They are mapped to the "side" and "extra" mouse buttons here. */
- {KIND_FILTERED, 0x3f, 0x7a, EV_KEY, BTN_SIDE, 1}, /* left dblclick */
- {KIND_FILTERED, 0x43, 0x7e, EV_KEY, BTN_EXTRA, 1},/* right dblclick */
+ {KIND_FILTERED, 0x7a, EV_KEY, BTN_SIDE, 1}, /* left dblclick */
+ {KIND_FILTERED, 0x7e, EV_KEY, BTN_EXTRA, 1},/* right dblclick */
/* Non-mouse events are handled by rc-core */
- {KIND_END, 0x00, 0x00, EV_MAX + 1, 0, 0}
+ {KIND_END, 0x00, EV_MAX + 1, 0, 0}
};
/* Local function prototypes */
return retval;
}
-/*
- * ati_remote_event_lookup
- */
-static int ati_remote_event_lookup(int rem, unsigned char d1, unsigned char d2)
-{
- int i;
-
- for (i = 0; ati_remote_tbl[i].kind != KIND_END; i++) {
- /*
- * Decide if the table entry matches the remote input.
- */
- if (ati_remote_tbl[i].data1 == d1 &&
- ati_remote_tbl[i].data2 == d2)
- return i;
-
- }
- return -1;
-}
-
/*
* ati_remote_compute_accel
*
int index = -1;
int acc;
int remote_num;
- unsigned char scancode[2];
+ unsigned char scancode;
+ int i;
+
+ /*
+ * data[0] = 0x14
+ * data[1] = data[2] + data[3] + 0xd5 (a checksum byte)
+ * data[2] = the key code (with toggle bit in MSB with some models)
+ * data[3] = channel << 4 (the low 4 bits must be zero)
+ */
/* Deal with strange looking inputs */
if ( (urb->actual_length != 4) || (data[0] != 0x14) ||
return;
}
+ if (data[1] != ((data[2] + data[3] + 0xd5) & 0xff)) {
+ dbginfo(&ati_remote->interface->dev,
+ "wrong checksum in input: %02x %02x %02x %02x\n",
+ data[0], data[1], data[2], data[3]);
+ return;
+ }
+
/* Mask unwanted remote channels. */
/* note: remote_num is 0-based, channel 1 on remote == 0 here */
remote_num = (data[3] >> 4) & 0x0f;
return;
}
- scancode[0] = (((data[1] - ((remote_num + 1) << 4)) & 0xf0) | (data[1] & 0x0f));
-
/*
- * Some devices (e.g. SnapStream Firefly) use 8080 as toggle code,
- * so we have to clear them. The first bit is a bit tricky as the
- * "non-toggled" state depends on remote_num, so we xor it with the
- * second bit which is only used for toggle.
+ * MSB is a toggle code, though only used by some devices
+ * (e.g. SnapStream Firefly)
*/
- scancode[0] ^= (data[2] & 0x80);
-
- scancode[1] = data[2] & ~0x80;
+ scancode = data[2] & 0x7f;
- /* Look up event code index in mouse translation table. */
- index = ati_remote_event_lookup(remote_num, scancode[0], scancode[1]);
+ /* Look up event code index in the mouse translation table. */
+ for (i = 0; ati_remote_tbl[i].kind != KIND_END; i++) {
+ if (scancode == ati_remote_tbl[i].data) {
+ index = i;
+ break;
+ }
+ }
if (index >= 0) {
dbginfo(&ati_remote->interface->dev,
- "channel 0x%02x; mouse data %02x,%02x; index %d; keycode %d\n",
- remote_num, data[1], data[2], index, ati_remote_tbl[index].code);
+ "channel 0x%02x; mouse data %02x; index %d; keycode %d\n",
+ remote_num, data[2], index, ati_remote_tbl[index].code);
if (!dev)
return; /* no mouse device */
} else
dbginfo(&ati_remote->interface->dev,
- "channel 0x%02x; key data %02x,%02x, scancode %02x,%02x\n",
- remote_num, data[1], data[2], scancode[0], scancode[1]);
+ "channel 0x%02x; key data %02x, scancode %02x\n",
+ remote_num, data[2], scancode);
if (index >= 0 && ati_remote_tbl[index].kind == KIND_LITERAL) {
unsigned long now = jiffies;
/* Filter duplicate events which happen "too close" together. */
- if (ati_remote->old_data[0] == data[1] &&
- ati_remote->old_data[1] == data[2] &&
+ if (ati_remote->old_data == data[2] &&
time_before(now, ati_remote->old_jiffies +
msecs_to_jiffies(repeat_filter))) {
ati_remote->repeat_count++;
ati_remote->first_jiffies = now;
}
- ati_remote->old_data[0] = data[1];
- ati_remote->old_data[1] = data[2];
+ ati_remote->old_data = data[2];
ati_remote->old_jiffies = now;
/* Ensure we skip at least the 4 first duplicate events (generated
if (index < 0) {
/* Not a mouse event, hand it to rc-core. */
- u32 rc_code = (scancode[0] << 8) | scancode[1];
/*
* We don't use the rc-core repeat handling yet as
* it would cause ghost repeats which would be a
* regression for this driver.
*/
- rc_keydown_notimeout(ati_remote->rdev, rc_code,
+ rc_keydown_notimeout(ati_remote->rdev, scancode,
data[2]);
rc_keyup(ati_remote->rdev);
return;
input_sync(dev);
ati_remote->old_jiffies = jiffies;
- ati_remote->old_data[0] = data[1];
- ati_remote->old_data[1] = data[2];
+ ati_remote->old_data = data[2];
}
}
#include <media/rc-map.h>
static struct rc_map_table ati_x10[] = {
- { 0xd20d, KEY_1 },
- { 0xd30e, KEY_2 },
- { 0xd40f, KEY_3 },
- { 0xd510, KEY_4 },
- { 0xd611, KEY_5 },
- { 0xd712, KEY_6 },
- { 0xd813, KEY_7 },
- { 0xd914, KEY_8 },
- { 0xda15, KEY_9 },
- { 0xdc17, KEY_0 },
- { 0xc500, KEY_A },
- { 0xc601, KEY_B },
- { 0xde19, KEY_C },
- { 0xe01b, KEY_D },
- { 0xe621, KEY_E },
- { 0xe823, KEY_F },
+ { 0x0d, KEY_1 },
+ { 0x0e, KEY_2 },
+ { 0x0f, KEY_3 },
+ { 0x10, KEY_4 },
+ { 0x11, KEY_5 },
+ { 0x12, KEY_6 },
+ { 0x13, KEY_7 },
+ { 0x14, KEY_8 },
+ { 0x15, KEY_9 },
+ { 0x17, KEY_0 },
+ { 0x00, KEY_A },
+ { 0x01, KEY_B },
+ { 0x19, KEY_C },
+ { 0x1b, KEY_D },
+ { 0x21, KEY_E },
+ { 0x23, KEY_F },
- { 0xdd18, KEY_KPENTER }, /* "check" */
- { 0xdb16, KEY_MENU }, /* "menu" */
- { 0xc702, KEY_POWER }, /* Power */
- { 0xc803, KEY_TV }, /* TV */
- { 0xc904, KEY_DVD }, /* DVD */
- { 0xca05, KEY_WWW }, /* WEB */
- { 0xcb06, KEY_BOOKMARKS }, /* "book" */
- { 0xcc07, KEY_EDIT }, /* "hand" */
- { 0xe11c, KEY_COFFEE }, /* "timer" */
- { 0xe520, KEY_FRONT }, /* "max" */
- { 0xe21d, KEY_LEFT }, /* left */
- { 0xe41f, KEY_RIGHT }, /* right */
- { 0xe722, KEY_DOWN }, /* down */
- { 0xdf1a, KEY_UP }, /* up */
- { 0xe31e, KEY_OK }, /* "OK" */
- { 0xce09, KEY_VOLUMEDOWN }, /* VOL + */
- { 0xcd08, KEY_VOLUMEUP }, /* VOL - */
- { 0xcf0a, KEY_MUTE }, /* MUTE */
- { 0xd00b, KEY_CHANNELUP }, /* CH + */
- { 0xd10c, KEY_CHANNELDOWN },/* CH - */
- { 0xec27, KEY_RECORD }, /* ( o) red */
- { 0xea25, KEY_PLAY }, /* ( >) */
- { 0xe924, KEY_REWIND }, /* (<<) */
- { 0xeb26, KEY_FORWARD }, /* (>>) */
- { 0xed28, KEY_STOP }, /* ([]) */
- { 0xee29, KEY_PAUSE }, /* ('') */
- { 0xf02b, KEY_PREVIOUS }, /* (<-) */
- { 0xef2a, KEY_NEXT }, /* (>+) */
- { 0xf22d, KEY_INFO }, /* PLAYING */
- { 0xf32e, KEY_HOME }, /* TOP */
- { 0xf42f, KEY_END }, /* END */
- { 0xf530, KEY_SELECT }, /* SELECT */
+ { 0x18, KEY_KPENTER }, /* "check" */
+ { 0x16, KEY_MENU }, /* "menu" */
+ { 0x02, KEY_POWER }, /* Power */
+ { 0x03, KEY_TV }, /* TV */
+ { 0x04, KEY_DVD }, /* DVD */
+ { 0x05, KEY_WWW }, /* WEB */
+ { 0x06, KEY_BOOKMARKS }, /* "book" */
+ { 0x07, KEY_EDIT }, /* "hand" */
+ { 0x1c, KEY_COFFEE }, /* "timer" */
+ { 0x20, KEY_FRONT }, /* "max" */
+ { 0x1d, KEY_LEFT }, /* left */
+ { 0x1f, KEY_RIGHT }, /* right */
+ { 0x22, KEY_DOWN }, /* down */
+ { 0x1a, KEY_UP }, /* up */
+ { 0x1e, KEY_OK }, /* "OK" */
+ { 0x09, KEY_VOLUMEDOWN }, /* VOL + */
+ { 0x08, KEY_VOLUMEUP }, /* VOL - */
+ { 0x0a, KEY_MUTE }, /* MUTE */
+ { 0x0b, KEY_CHANNELUP }, /* CH + */
+ { 0x0c, KEY_CHANNELDOWN },/* CH - */
+ { 0x27, KEY_RECORD }, /* ( o) red */
+ { 0x25, KEY_PLAY }, /* ( >) */
+ { 0x24, KEY_REWIND }, /* (<<) */
+ { 0x26, KEY_FORWARD }, /* (>>) */
+ { 0x28, KEY_STOP }, /* ([]) */
+ { 0x29, KEY_PAUSE }, /* ('') */
+ { 0x2b, KEY_PREVIOUS }, /* (<-) */
+ { 0x2a, KEY_NEXT }, /* (>+) */
+ { 0x2d, KEY_INFO }, /* PLAYING */
+ { 0x2e, KEY_HOME }, /* TOP */
+ { 0x2f, KEY_END }, /* END */
+ { 0x30, KEY_SELECT }, /* SELECT */
};
static struct rc_map_list ati_x10_map = {
#include <media/rc-map.h>
static struct rc_map_table medion_x10[] = {
- { 0xf12c, KEY_TV }, /* TV */
- { 0xf22d, KEY_VCR }, /* VCR */
- { 0xc904, KEY_DVD }, /* DVD */
- { 0xcb06, KEY_AUDIO }, /* MUSIC */
-
- { 0xf32e, KEY_RADIO }, /* RADIO */
- { 0xca05, KEY_DIRECTORY }, /* PHOTO */
- { 0xf42f, KEY_INFO }, /* TV-PREVIEW */
- { 0xf530, KEY_LIST }, /* CHANNEL-LST */
-
- { 0xe01b, KEY_SETUP }, /* SETUP */
- { 0xf631, KEY_VIDEO }, /* VIDEO DESKTOP */
-
- { 0xcd08, KEY_VOLUMEDOWN }, /* VOL - */
- { 0xce09, KEY_VOLUMEUP }, /* VOL + */
- { 0xd00b, KEY_CHANNELUP }, /* CHAN + */
- { 0xd10c, KEY_CHANNELDOWN }, /* CHAN - */
- { 0xc500, KEY_MUTE }, /* MUTE */
-
- { 0xf732, KEY_RED }, /* red */
- { 0xf833, KEY_GREEN }, /* green */
- { 0xf934, KEY_YELLOW }, /* yellow */
- { 0xfa35, KEY_BLUE }, /* blue */
- { 0xdb16, KEY_TEXT }, /* TXT */
-
- { 0xd20d, KEY_1 },
- { 0xd30e, KEY_2 },
- { 0xd40f, KEY_3 },
- { 0xd510, KEY_4 },
- { 0xd611, KEY_5 },
- { 0xd712, KEY_6 },
- { 0xd813, KEY_7 },
- { 0xd914, KEY_8 },
- { 0xda15, KEY_9 },
- { 0xdc17, KEY_0 },
- { 0xe11c, KEY_SEARCH }, /* TV/RAD, CH SRC */
- { 0xe520, KEY_DELETE }, /* DELETE */
-
- { 0xfb36, KEY_KEYBOARD }, /* RENAME */
- { 0xdd18, KEY_SCREEN }, /* SNAPSHOT */
-
- { 0xdf1a, KEY_UP }, /* up */
- { 0xe722, KEY_DOWN }, /* down */
- { 0xe21d, KEY_LEFT }, /* left */
- { 0xe41f, KEY_RIGHT }, /* right */
- { 0xe31e, KEY_OK }, /* OK */
-
- { 0xfc37, KEY_SELECT }, /* ACQUIRE IMAGE */
- { 0xfd38, KEY_EDIT }, /* EDIT IMAGE */
-
- { 0xe924, KEY_REWIND }, /* rewind (<<) */
- { 0xea25, KEY_PLAY }, /* play ( >) */
- { 0xeb26, KEY_FORWARD }, /* forward (>>) */
- { 0xec27, KEY_RECORD }, /* record ( o) */
- { 0xed28, KEY_STOP }, /* stop ([]) */
- { 0xee29, KEY_PAUSE }, /* pause ('') */
-
- { 0xe621, KEY_PREVIOUS }, /* prev */
- { 0xfe39, KEY_SWITCHVIDEOMODE }, /* F SCR */
- { 0xe823, KEY_NEXT }, /* next */
- { 0xde19, KEY_MENU }, /* MENU */
- { 0xff3a, KEY_LANGUAGE }, /* AUDIO */
-
- { 0xc702, KEY_POWER }, /* POWER */
+ { 0x2c, KEY_TV }, /* TV */
+ { 0x2d, KEY_VCR }, /* VCR */
+ { 0x04, KEY_DVD }, /* DVD */
+ { 0x06, KEY_AUDIO }, /* MUSIC */
+
+ { 0x2e, KEY_RADIO }, /* RADIO */
+ { 0x05, KEY_DIRECTORY }, /* PHOTO */
+ { 0x2f, KEY_INFO }, /* TV-PREVIEW */
+ { 0x30, KEY_LIST }, /* CHANNEL-LST */
+
+ { 0x1b, KEY_SETUP }, /* SETUP */
+ { 0x31, KEY_VIDEO }, /* VIDEO DESKTOP */
+
+ { 0x08, KEY_VOLUMEDOWN }, /* VOL - */
+ { 0x09, KEY_VOLUMEUP }, /* VOL + */
+ { 0x0b, KEY_CHANNELUP }, /* CHAN + */
+ { 0x0c, KEY_CHANNELDOWN }, /* CHAN - */
+ { 0x00, KEY_MUTE }, /* MUTE */
+
+ { 0x32, KEY_RED }, /* red */
+ { 0x33, KEY_GREEN }, /* green */
+ { 0x34, KEY_YELLOW }, /* yellow */
+ { 0x35, KEY_BLUE }, /* blue */
+ { 0x16, KEY_TEXT }, /* TXT */
+
+ { 0x0d, KEY_1 },
+ { 0x0e, KEY_2 },
+ { 0x0f, KEY_3 },
+ { 0x10, KEY_4 },
+ { 0x11, KEY_5 },
+ { 0x12, KEY_6 },
+ { 0x13, KEY_7 },
+ { 0x14, KEY_8 },
+ { 0x15, KEY_9 },
+ { 0x17, KEY_0 },
+ { 0x1c, KEY_SEARCH }, /* TV/RAD, CH SRC */
+ { 0x20, KEY_DELETE }, /* DELETE */
+
+ { 0x36, KEY_KEYBOARD }, /* RENAME */
+ { 0x18, KEY_SCREEN }, /* SNAPSHOT */
+
+ { 0x1a, KEY_UP }, /* up */
+ { 0x22, KEY_DOWN }, /* down */
+ { 0x1d, KEY_LEFT }, /* left */
+ { 0x1f, KEY_RIGHT }, /* right */
+ { 0x1e, KEY_OK }, /* OK */
+
+ { 0x37, KEY_SELECT }, /* ACQUIRE IMAGE */
+ { 0x38, KEY_EDIT }, /* EDIT IMAGE */
+
+ { 0x24, KEY_REWIND }, /* rewind (<<) */
+ { 0x25, KEY_PLAY }, /* play ( >) */
+ { 0x26, KEY_FORWARD }, /* forward (>>) */
+ { 0x27, KEY_RECORD }, /* record ( o) */
+ { 0x28, KEY_STOP }, /* stop ([]) */
+ { 0x29, KEY_PAUSE }, /* pause ('') */
+
+ { 0x21, KEY_PREVIOUS }, /* prev */
+ { 0x39, KEY_SWITCHVIDEOMODE }, /* F SCR */
+ { 0x23, KEY_NEXT }, /* next */
+ { 0x19, KEY_MENU }, /* MENU */
+ { 0x3a, KEY_LANGUAGE }, /* AUDIO */
+
+ { 0x02, KEY_POWER }, /* POWER */
};
static struct rc_map_list medion_x10_map = {
#include <media/rc-map.h>
static struct rc_map_table snapstream_firefly[] = {
- { 0xf12c, KEY_ZOOM }, /* Maximize */
- { 0xc702, KEY_CLOSE },
-
- { 0xd20d, KEY_1 },
- { 0xd30e, KEY_2 },
- { 0xd40f, KEY_3 },
- { 0xd510, KEY_4 },
- { 0xd611, KEY_5 },
- { 0xd712, KEY_6 },
- { 0xd813, KEY_7 },
- { 0xd914, KEY_8 },
- { 0xda15, KEY_9 },
- { 0xdc17, KEY_0 },
- { 0xdb16, KEY_BACK },
- { 0xdd18, KEY_KPENTER }, /* ent */
-
- { 0xce09, KEY_VOLUMEUP },
- { 0xcd08, KEY_VOLUMEDOWN },
- { 0xcf0a, KEY_MUTE },
- { 0xd00b, KEY_CHANNELUP },
- { 0xd10c, KEY_CHANNELDOWN },
- { 0xc500, KEY_VENDOR }, /* firefly */
-
- { 0xf32e, KEY_INFO },
- { 0xf42f, KEY_OPTION },
-
- { 0xe21d, KEY_LEFT },
- { 0xe41f, KEY_RIGHT },
- { 0xe722, KEY_DOWN },
- { 0xdf1a, KEY_UP },
- { 0xe31e, KEY_OK },
-
- { 0xe11c, KEY_MENU },
- { 0xe520, KEY_EXIT },
-
- { 0xec27, KEY_RECORD },
- { 0xea25, KEY_PLAY },
- { 0xed28, KEY_STOP },
- { 0xe924, KEY_REWIND },
- { 0xeb26, KEY_FORWARD },
- { 0xee29, KEY_PAUSE },
- { 0xf02b, KEY_PREVIOUS },
- { 0xef2a, KEY_NEXT },
-
- { 0xcb06, KEY_AUDIO }, /* Music */
- { 0xca05, KEY_IMAGES }, /* Photos */
- { 0xc904, KEY_DVD },
- { 0xc803, KEY_TV },
- { 0xcc07, KEY_VIDEO },
-
- { 0xc601, KEY_HELP },
- { 0xf22d, KEY_MODE }, /* Mouse */
-
- { 0xde19, KEY_A },
- { 0xe01b, KEY_B },
- { 0xe621, KEY_C },
- { 0xe823, KEY_D },
+ { 0x2c, KEY_ZOOM }, /* Maximize */
+ { 0x02, KEY_CLOSE },
+
+ { 0x0d, KEY_1 },
+ { 0x0e, KEY_2 },
+ { 0x0f, KEY_3 },
+ { 0x10, KEY_4 },
+ { 0x11, KEY_5 },
+ { 0x12, KEY_6 },
+ { 0x13, KEY_7 },
+ { 0x14, KEY_8 },
+ { 0x15, KEY_9 },
+ { 0x17, KEY_0 },
+ { 0x16, KEY_BACK },
+ { 0x18, KEY_KPENTER }, /* ent */
+
+ { 0x09, KEY_VOLUMEUP },
+ { 0x08, KEY_VOLUMEDOWN },
+ { 0x0a, KEY_MUTE },
+ { 0x0b, KEY_CHANNELUP },
+ { 0x0c, KEY_CHANNELDOWN },
+ { 0x00, KEY_VENDOR }, /* firefly */
+
+ { 0x2e, KEY_INFO },
+ { 0x2f, KEY_OPTION },
+
+ { 0x1d, KEY_LEFT },
+ { 0x1f, KEY_RIGHT },
+ { 0x22, KEY_DOWN },
+ { 0x1a, KEY_UP },
+ { 0x1e, KEY_OK },
+
+ { 0x1c, KEY_MENU },
+ { 0x20, KEY_EXIT },
+
+ { 0x27, KEY_RECORD },
+ { 0x25, KEY_PLAY },
+ { 0x28, KEY_STOP },
+ { 0x24, KEY_REWIND },
+ { 0x26, KEY_FORWARD },
+ { 0x29, KEY_PAUSE },
+ { 0x2b, KEY_PREVIOUS },
+ { 0x2a, KEY_NEXT },
+
+ { 0x06, KEY_AUDIO }, /* Music */
+ { 0x05, KEY_IMAGES }, /* Photos */
+ { 0x04, KEY_DVD },
+ { 0x03, KEY_TV },
+ { 0x07, KEY_VIDEO },
+
+ { 0x01, KEY_HELP },
+ { 0x2d, KEY_MODE }, /* Mouse */
+
+ { 0x19, KEY_A },
+ { 0x1b, KEY_B },
+ { 0x21, KEY_C },
+ { 0x23, KEY_D },
};
static struct rc_map_list snapstream_firefly_map = {
switch (tv.model) {
case 72000: /* WinTV-HVR950q (Retail, IR, ATSC/QAM */
case 72001: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */
+ case 72101: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */
+ case 72201: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */
case 72211: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */
case 72221: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */
case 72231: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */
case 72241: /* WinTV-HVR950q (OEM, No IR, ATSC/QAM and analog video */
case 72251: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */
+ case 72261: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */
case 72301: /* WinTV-HVR850 (Retail, IR, ATSC and analog video */
case 72500: /* WinTV-HVR950q (OEM, No IR, ATSC/QAM */
break;
.driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q_MXL },
{ USB_DEVICE(0x2040, 0x8200),
.driver_info = AU0828_BOARD_HAUPPAUGE_WOODBURY },
+ { USB_DEVICE(0x2040, 0x7260),
+ .driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q },
+ { USB_DEVICE(0x2040, 0x7213),
+ .driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q },
{ },
};
gspca_dev->usb_err = 0;
/* do the specific subdriver stuff before endpoint selection */
- gspca_dev->alt = 0;
+ intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface);
+ gspca_dev->alt = gspca_dev->cam.bulk ? intf->num_altsetting : 0;
if (gspca_dev->sd_desc->isoc_init) {
ret = gspca_dev->sd_desc->isoc_init(gspca_dev);
if (ret < 0)
goto unlock;
}
- intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface);
xfer = gspca_dev->cam.bulk ? USB_ENDPOINT_XFER_BULK
: USB_ENDPOINT_XFER_ISOC;
ret = -EIO;
goto out;
}
- alt = ep_tb[--alt_idx].alt;
+ gspca_dev->alt = ep_tb[--alt_idx].alt;
}
}
out:
* @pad: media pad
* @ffmt: current fmt according to resolution type
* @res_type: current resolution type
- * @code: current code
* @irq_waitq: waitqueue for the capture
* @work_irq: workqueue for the IRQ
* @flags: state variable for the interrupt handler
struct media_pad pad;
struct v4l2_mbus_framefmt ffmt[M5MOLS_RESTYPE_MAX];
int res_type;
- enum v4l2_mbus_pixelcode code;
wait_queue_head_t irq_waitq;
struct work_struct work_irq;
unsigned long flags;
int ret = -EINVAL;
u8 reg;
- if (mode < REG_PARAMETER && mode > REG_CAPTURE)
+ if (mode < REG_PARAMETER || mode > REG_CAPTURE)
return ret;
ret = m5mols_read_u8(sd, SYSTEM_SYSMODE, ®);
struct m5mols_info *info = to_m5mols(sd);
struct v4l2_mbus_framefmt *format;
- if (fmt->pad != 0)
- return -EINVAL;
-
format = __find_format(info, fh, fmt->which, info->res_type);
if (!format)
return -EINVAL;
u32 resolution = 0;
int ret;
- if (fmt->pad != 0)
- return -EINVAL;
-
ret = __find_resolution(sd, format, &type, &resolution);
if (ret < 0)
return ret;
if (!sfmt)
return 0;
- *sfmt = m5mols_default_ffmt[type];
- sfmt->width = format->width;
- sfmt->height = format->height;
+
+ format->code = m5mols_default_ffmt[type].code;
+ format->colorspace = V4L2_COLORSPACE_JPEG;
+ format->field = V4L2_FIELD_NONE;
if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
+ *sfmt = *format;
info->resolution = resolution;
- info->code = format->code;
info->res_type = type;
}
static int m5mols_s_stream(struct v4l2_subdev *sd, int enable)
{
struct m5mols_info *info = to_m5mols(sd);
+ u32 code = info->ffmt[info->res_type].code;
if (enable) {
int ret = -EINVAL;
- if (is_code(info->code, M5MOLS_RESTYPE_MONITOR))
+ if (is_code(code, M5MOLS_RESTYPE_MONITOR))
ret = m5mols_start_monitor(info);
- if (is_code(info->code, M5MOLS_RESTYPE_CAPTURE))
+ if (is_code(code, M5MOLS_RESTYPE_CAPTURE))
ret = m5mols_start_capture(info);
return ret;
mt9m111->rect.height = MT9M111_MAX_HEIGHT;
mt9m111->fmt = &mt9m111_colour_fmts[0];
mt9m111->lastpage = -1;
+ mutex_init(&mt9m111->power_lock);
ret = mt9m111_video_probe(client);
if (ret) {
v4l2_i2c_subdev_init(&priv->subdev, client, &mt9t112_subdev_ops);
ret = mt9t112_camera_probe(client);
- if (ret)
+ if (ret) {
kfree(priv);
+ return ret;
+ }
/* Cannot fail: using the default supported pixel code */
mt9t112_set_params(priv, &rect, V4L2_MBUS_FMT_UYVY8_2X8);
#include <linux/irq.h>
#include <linux/videodev2.h>
#include <linux/dma-mapping.h>
+#include <linux/slab.h>
#include <media/videobuf-dma-contig.h>
#include <media/v4l2-device.h>
vid_dev->num_displays = 0;
for_each_dss_dev(dssdev) {
omap_dss_get_device(dssdev);
+
+ if (!dssdev->driver) {
+ dev_warn(&pdev->dev, "no driver for display: %s\n",
+ dssdev->name);
+ omap_dss_put_device(dssdev);
+ continue;
+ }
+
vid_dev->displays[vid_dev->num_displays++] = dssdev;
}
#include <linux/clk.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
unsigned long flags;
struct sgdma_state *sg_state;
- if ((sglen < 0) || ((sglen > 0) & !sglist))
+ if ((sglen < 0) || ((sglen > 0) && !sglist))
return -EINVAL;
spin_lock_irqsave(&sgdma->lock, flags);
{
struct isp_pipeline *pipe =
to_isp_pipeline(&ccdc->video_out.video.entity);
- struct video_device *vdev = &ccdc->subdev.devnode;
+ struct video_device *vdev = ccdc->subdev.devnode;
struct v4l2_event event;
memset(&event, 0, sizeof(event));
static void isp_stat_queue_event(struct ispstat *stat, int err)
{
- struct video_device *vdev = &stat->subdev.devnode;
+ struct video_device *vdev = stat->subdev.devnode;
struct v4l2_event event;
struct omap3isp_stat_event_status *status = (void *)event.u.data;
#include <asm/cacheflush.h>
#include <linux/clk.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/scatterlist.h>
#include <linux/sched.h>
static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
{
struct i2c_client *client = v4l2_get_subdevdata(sd);
- struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id;
+ struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd);
struct soc_camera_sense *sense = icd->sense;
struct ov6650 *priv = to_ov6650(client);
bool half_scale = !is_unscaled_ok(mf->width, mf->height, &priv->rect);
vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
}
set_bit(ST_CAPT_SUSPENDED, &fimc->state);
+
+ fimc_hw_reset(fimc);
+ cap->buf_index = 0;
+
spin_unlock_irqrestore(&fimc->slock, flags);
if (streaming)
struct fimc_dev *fimc = ctx->fimc_dev;
int ret;
- if (test_bit(ST_CAPT_APPLY_CFG, &fimc->state))
+ if (!test_bit(ST_CAPT_APPLY_CFG, &fimc->state))
return 0;
spin_lock(&ctx->slock);
fimc_hw_set_rotation(ctx);
fimc_prepare_dma_offset(ctx, &ctx->d_frame);
fimc_hw_set_out_dma(ctx);
- set_bit(ST_CAPT_APPLY_CFG, &fimc->state);
+ clear_bit(ST_CAPT_APPLY_CFG, &fimc->state);
}
spin_unlock(&ctx->slock);
return ret;
int min_bufs;
int ret;
- fimc_hw_reset(fimc);
vid_cap->frame_count = 0;
ret = fimc_init_capture(fimc);
max_w = rotation ? pl->out_rot_en_w : pl->out_rot_dis_w;
min_w = ctx->state & FIMC_DST_CROP ? dst->width : var->min_out_pixsize;
min_h = ctx->state & FIMC_DST_CROP ? dst->height : var->min_out_pixsize;
- if (fimc->id == 1 && var->pix_hoff)
+ if (var->min_vsize_align == 1 && !rotation)
align_h = fimc_fmt_is_rgb(ffmt->color) ? 0 : 1;
depth = fimc_get_format_depth(ffmt);
mutex_lock(&fimc->lock);
set_frame_bounds(ff, mf->width, mf->height);
+ fimc->vid_cap.mf = *mf;
ff->fmt = ffmt;
/* Reset the crop rectangle if required. */
media_entity_cleanup(&sd->entity);
v4l2_device_unregister_subdev(sd);
kfree(sd);
- sd = NULL;
+ fimc->vid_cap.subdev = NULL;
}
/* Set default format at the sensor and host interface */
static struct fimc_fmt fimc_formats[] = {
{
.name = "RGB565",
- .fourcc = V4L2_PIX_FMT_RGB565X,
+ .fourcc = V4L2_PIX_FMT_RGB565,
.depth = { 16 },
.color = S5P_FIMC_RGB565,
.memplanes = 1,
mod_x = 6; /* 64 x 32 pixels tile */
mod_y = 5;
} else {
- if (fimc->id == 1 && variant->pix_hoff)
+ if (variant->min_vsize_align == 1)
mod_y = fimc_fmt_is_rgb(fmt->color) ? 0 : 1;
else
- mod_y = mod_x;
+ mod_y = ffs(variant->min_vsize_align) - 1;
}
- dbg("mod_x: %d, mod_y: %d, max_w: %d", mod_x, mod_y, max_w);
v4l_bound_align_image(&pix->width, 16, max_w, mod_x,
&pix->height, 8, variant->pix_limit->scaler_dis_w, mod_y, 0);
fimc->variant->min_inp_pixsize : fimc->variant->min_out_pixsize;
/* Get pixel alignment constraints. */
- if (fimc->id == 1 && fimc->variant->pix_hoff)
+ if (fimc->variant->min_vsize_align == 1)
halign = fimc_fmt_is_rgb(f->fmt->color) ? 0 : 1;
else
- halign = ffs(min_size) - 1;
+ halign = ffs(fimc->variant->min_vsize_align) - 1;
for (i = 0; i < f->fmt->colplanes; i++)
depth += f->fmt->depth[i];
pdata = pdev->dev.platform_data;
fimc->pdata = pdata;
- set_bit(ST_LPM, &fimc->state);
init_waitqueue_head(&fimc->irq_queue);
spin_lock_init(&fimc->slock);
/* Enable clocks and perform basic initalization */
clk_enable(fimc->clock[CLK_GATE]);
fimc_hw_reset(fimc);
- if (fimc->variant->out_buf_count > 4)
- fimc_hw_set_dma_seq(fimc, 0xF);
/* Resume the capture or mem-to-mem device */
if (fimc_capture_busy(fimc))
return 0;
}
fimc_hw_reset(fimc);
- if (fimc->variant->out_buf_count > 4)
- fimc_hw_set_dma_seq(fimc, 0xF);
spin_unlock_irqrestore(&fimc->slock, flags);
if (fimc_capture_busy(fimc))
struct fimc_dev *fimc = platform_get_drvdata(pdev);
pm_runtime_disable(&pdev->dev);
- fimc_runtime_suspend(&pdev->dev);
pm_runtime_set_suspended(&pdev->dev);
vb2_dma_contig_cleanup_ctx(fimc->alloc_ctx);
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 8,
+ .min_vsize_align = 16,
.out_buf_count = 4,
.pix_limit = &s5p_pix_limit[0],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 8,
+ .min_vsize_align = 16,
.out_buf_count = 4,
.pix_limit = &s5p_pix_limit[1],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 8,
+ .min_vsize_align = 16,
.out_buf_count = 4,
.pix_limit = &s5p_pix_limit[1],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 1,
+ .min_vsize_align = 1,
.out_buf_count = 4,
.pix_limit = &s5p_pix_limit[2],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 8,
+ .min_vsize_align = 16,
.out_buf_count = 4,
.pix_limit = &s5p_pix_limit[2],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 2,
+ .min_vsize_align = 1,
.out_buf_count = 32,
.pix_limit = &s5p_pix_limit[1],
};
.min_inp_pixsize = 16,
.min_out_pixsize = 16,
.hor_offs_align = 2,
+ .min_vsize_align = 1,
.out_buf_count = 32,
.pix_limit = &s5p_pix_limit[3],
};
* @min_inp_pixsize: minimum input pixel size
* @min_out_pixsize: minimum output pixel size
* @hor_offs_align: horizontal pixel offset aligment
+ * @min_vsize_align: minimum vertical pixel size alignment
* @out_buf_count: the number of buffers in output DMA sequence
*/
struct samsung_fimc_variant {
u16 min_inp_pixsize;
u16 min_out_pixsize;
u16 hor_offs_align;
+ u16 min_vsize_align;
u16 out_buf_count;
};
sd = v4l2_i2c_new_subdev_board(&fmd->v4l2_dev, adapter,
s_info->pdata->board_info, NULL);
if (IS_ERR_OR_NULL(sd)) {
+ i2c_put_adapter(adapter);
v4l2_err(&fmd->v4l2_dev, "Failed to acquire subdev\n");
return NULL;
}
static void fimc_md_unregister_sensor(struct v4l2_subdev *sd)
{
struct i2c_client *client = v4l2_get_subdevdata(sd);
+ struct i2c_adapter *adapter;
if (!client)
return;
v4l2_device_unregister_subdev(sd);
+ adapter = client->adapter;
i2c_unregister_device(client);
- i2c_put_adapter(client->adapter);
+ if (adapter)
+ i2c_put_adapter(adapter);
}
static int fimc_md_register_sensor_entities(struct fimc_md *fmd)
static int fimc_md_register_video_nodes(struct fimc_md *fmd)
{
+ struct video_device *vdev;
int i, ret = 0;
for (i = 0; i < FIMC_MAX_DEVS && !ret; i++) {
if (!fmd->fimc[i])
continue;
- if (fmd->fimc[i]->m2m.vfd)
- ret = video_register_device(fmd->fimc[i]->m2m.vfd,
- VFL_TYPE_GRABBER, -1);
- if (ret)
- break;
- if (fmd->fimc[i]->vid_cap.vfd)
- ret = video_register_device(fmd->fimc[i]->vid_cap.vfd,
- VFL_TYPE_GRABBER, -1);
+ vdev = fmd->fimc[i]->m2m.vfd;
+ if (vdev) {
+ ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+ if (ret)
+ break;
+ v4l2_info(&fmd->v4l2_dev, "Registered %s as /dev/%s\n",
+ vdev->name, video_device_node_name(vdev));
+ }
+
+ vdev = fmd->fimc[i]->vid_cap.vfd;
+ if (vdev == NULL)
+ continue;
+ ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+ v4l2_info(&fmd->v4l2_dev, "Registered %s as /dev/%s\n",
+ vdev->name, video_device_node_name(vdev));
}
return ret;
if (WARN(csis == NULL,
"MIPI-CSI interface specified "
"but s5p-csis module is not loaded!\n"))
- continue;
+ return -EINVAL;
ret = media_entity_create_link(&sensor->entity, 0,
&csis->entity, CSIS_PAD_SINK,
struct fimc_md *fmd;
int ret;
- if (WARN(!pdev->dev.platform_data, "Platform data not specified!\n"))
- return -EINVAL;
-
fmd = kzalloc(sizeof(struct fimc_md), GFP_KERNEL);
if (!fmd)
return -ENOMEM;
if (ret)
goto err3;
- ret = fimc_md_register_sensor_entities(fmd);
- if (ret)
- goto err3;
+ if (pdev->dev.platform_data) {
+ ret = fimc_md_register_sensor_entities(fmd);
+ if (ret)
+ goto err3;
+ }
ret = fimc_md_create_links(fmd);
if (ret)
goto err3;
cfg = readl(dev->regs + S5P_CIGCTRL);
cfg &= ~S5P_CIGCTRL_SWRST;
writel(cfg, dev->regs + S5P_CIGCTRL);
+
+ if (dev->variant->out_buf_count > 4)
+ fimc_hw_set_dma_seq(dev, 0xF);
}
static u32 fimc_hw_get_in_flip(struct fimc_ctx *ctx)
struct fimc_scaler *sc = &ctx->scaler;
struct fimc_frame *src_frame = &ctx->s_frame;
struct fimc_frame *dst_frame = &ctx->d_frame;
- u32 cfg = 0;
+
+ u32 cfg = readl(dev->regs + S5P_CISCCTRL);
+
+ cfg &= ~(S5P_CISCCTRL_CSCR2Y_WIDE | S5P_CISCCTRL_CSCY2R_WIDE |
+ S5P_CISCCTRL_SCALEUP_H | S5P_CISCCTRL_SCALEUP_V |
+ S5P_CISCCTRL_SCALERBYPASS | S5P_CISCCTRL_ONE2ONE |
+ S5P_CISCCTRL_INRGB_FMT_MASK | S5P_CISCCTRL_OUTRGB_FMT_MASK |
+ S5P_CISCCTRL_INTERLACE | S5P_CISCCTRL_RGB_EXT);
if (!(ctx->flags & FIMC_COLOR_RANGE_NARROW))
cfg |= (S5P_CISCCTRL_CSCR2Y_WIDE | S5P_CISCCTRL_CSCY2R_WIDE);
fimc_hw_set_scaler(ctx);
cfg = readl(dev->regs + S5P_CISCCTRL);
+ cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK);
if (variant->has_mainscaler_ext) {
- cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK);
cfg |= S5P_CISCCTRL_MHRATIO_EXT(sc->main_hratio);
cfg |= S5P_CISCCTRL_MVRATIO_EXT(sc->main_vratio);
writel(cfg, dev->regs + S5P_CISCCTRL);
cfg |= S5P_CIEXTEN_MVRATIO_EXT(sc->main_vratio);
writel(cfg, dev->regs + S5P_CIEXTEN);
} else {
- cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK);
cfg |= S5P_CISCCTRL_MHRATIO(sc->main_hratio);
cfg |= S5P_CISCCTRL_MVRATIO(sc->main_vratio);
writel(cfg, dev->regs + S5P_CISCCTRL);
.num_planes = 1,
},
{
- .name = "H264 Encoded Stream",
+ .name = "H263 Encoded Stream",
.fourcc = V4L2_PIX_FMT_H263,
.codec_mode = S5P_FIMV_CODEC_H263_ENC,
.type = MFC_FMT_ENC,
#include <media/v4l2-ioctl.h>
#include <linux/videodev2.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/version.h>
#include <linux/timer.h>
#include <media/videobuf2-dma-contig.h>
ret = sh_mobile_ceu_soft_reset(pcdev);
csi2_sd = find_csi2(pcdev);
- if (csi2_sd)
- csi2_sd->grp_id = (long)icd;
+ if (csi2_sd) {
+ csi2_sd->grp_id = soc_camera_grp_id(icd);
+ v4l2_set_subdev_hostdata(csi2_sd, icd);
+ }
ret = v4l2_subdev_call(csi2_sd, core, s_power, 1);
if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV) {
{
if (pcdev->csi2_pdev) {
struct v4l2_subdev *csi2_sd = find_csi2(pcdev);
- if (csi2_sd && csi2_sd->grp_id == (u32)icd)
+ if (csi2_sd && csi2_sd->grp_id == soc_camera_grp_id(icd))
return csi2_sd;
}
/* Try 2560x1920, 1280x960, 640x480, 320x240 */
mf.width = 2560 >> shift;
mf.height = 1920 >> shift;
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video,
- s_mbus_fmt, &mf);
+ ret = v4l2_device_call_until_err(sd->v4l2_dev,
+ soc_camera_grp_id(icd), video,
+ s_mbus_fmt, &mf);
if (ret < 0)
return ret;
shift++;
bool ceu_1to1;
int ret;
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video,
+ ret = v4l2_device_call_until_err(sd->v4l2_dev,
+ soc_camera_grp_id(icd), video,
s_mbus_fmt, mf);
if (ret < 0)
return ret;
tmp_h = min(2 * tmp_h, max_height);
mf->width = tmp_w;
mf->height = tmp_h;
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video,
- s_mbus_fmt, mf);
+ ret = v4l2_device_call_until_err(sd->v4l2_dev,
+ soc_camera_grp_id(icd), video,
+ s_mbus_fmt, mf);
dev_geo(dev, "Camera scaled to %ux%u\n",
mf->width, mf->height);
if (ret < 0) {
}
if (interm_width < icd->user_width || interm_height < icd->user_height) {
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (int)icd, video,
- s_mbus_fmt, &mf);
+ ret = v4l2_device_call_until_err(sd->v4l2_dev,
+ soc_camera_grp_id(icd), video,
+ s_mbus_fmt, &mf);
if (ret < 0)
return ret;
mf.code = xlate->code;
mf.colorspace = pix->colorspace;
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, try_mbus_fmt, &mf);
+ ret = v4l2_device_call_until_err(sd->v4l2_dev, soc_camera_grp_id(icd),
+ video, try_mbus_fmt, &mf);
if (ret < 0)
return ret;
*/
mf.width = 2560;
mf.height = 1920;
- ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video,
- try_mbus_fmt, &mf);
+ ret = v4l2_device_call_until_err(sd->v4l2_dev,
+ soc_camera_grp_id(icd), video,
+ try_mbus_fmt, &mf);
if (ret < 0) {
/* Shouldn't actually happen... */
dev_err(icd->parent,
const struct v4l2_mbus_config *cfg)
{
struct sh_csi2 *priv = container_of(sd, struct sh_csi2, subdev);
- struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id;
+ struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd);
struct v4l2_subdev *client_sd = soc_camera_to_subdev(icd);
struct v4l2_mbus_config client_cfg = {.type = V4L2_MBUS_CSI2,
.flags = priv->mipi_flags};
static int sh_csi2_client_connect(struct sh_csi2 *priv)
{
struct sh_csi2_pdata *pdata = priv->pdev->dev.platform_data;
- struct soc_camera_device *icd = (struct soc_camera_device *)priv->subdev.grp_id;
+ struct soc_camera_device *icd = v4l2_get_subdev_hostdata(&priv->subdev);
struct v4l2_subdev *client_sd = soc_camera_to_subdev(icd);
struct device *dev = v4l2_get_subdevdata(&priv->subdev);
struct v4l2_mbus_config cfg;
}
sd = soc_camera_to_subdev(icd);
- sd->grp_id = (long)icd;
+ sd->grp_id = soc_camera_grp_id(icd);
+ v4l2_set_subdev_hostdata(sd, icd);
if (v4l2_ctrl_add_handler(&icd->ctrl_handler, sd->ctrl_handler))
goto ectrl;
* Debugfs support for the AB5500 MFD driver
*/
-#include <linux/export.h>
+#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/mfd/ab5500/ab5500.h>
static struct resource __devinitdata ab8500_chargalg_resources[] = {};
+#ifdef CONFIG_DEBUG_FS
static struct resource __devinitdata ab8500_debug_resources[] = {
{
.name = "IRQ_FIRST",
.flags = IORESOURCE_IRQ,
},
};
+#endif
static struct resource __devinitdata ab8500_usb_resources[] = {
{
ret = __adp5520_read(chip->client, reg, ®_val);
- if (!ret && ((reg_val & bit_mask) == 0)) {
+ if (!ret && ((reg_val & bit_mask) != bit_mask)) {
reg_val |= bit_mask;
ret = __adp5520_write(chip->client, reg, reg_val);
}
if (ret)
goto out;
- if ((reg_val & bit_mask) == 0) {
+ if ((reg_val & bit_mask) != bit_mask) {
reg_val |= bit_mask;
ret = __da903x_write(chip->client, reg, reg_val);
}
struct da903x_chip *chip = i2c_get_clientdata(client);
da903x_remove_subdevs(chip);
+ free_irq(client->irq, chip);
kfree(chip);
return 0;
}
*/
#include <linux/err.h>
+#include <linux/io.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
if (ret)
goto out;
- if ((reg_val & bit_mask) == 0) {
+ if ((reg_val & bit_mask) != bit_mask) {
reg_val |= bit_mask;
ret = __tps6586x_write(to_i2c_client(dev), reg, reg_val);
}
goto out;
}
- data &= mask;
+ data &= ~mask;
err = tps65910_i2c_write(tps65910, reg, 1, &data);
if (err)
dev_err(tps65910->dev, "write to reg %x failed\n", reg);
pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
return -EPERM;
}
- sid = twl_map[mod_no].sid;
- twl = &twl_modules[sid];
-
if (unlikely(!inuse)) {
- pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid);
+ pr_err("%s: not initialized\n", DRIVER_NAME);
return -EPERM;
}
+ sid = twl_map[mod_no].sid;
+ twl = &twl_modules[sid];
+
mutex_lock(&twl->xfer_lock);
/*
* [MSG1]: fill the register address data
pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
return -EPERM;
}
- sid = twl_map[mod_no].sid;
- twl = &twl_modules[sid];
-
if (unlikely(!inuse)) {
- pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid);
+ pr_err("%s: not initialized\n", DRIVER_NAME);
return -EPERM;
}
+ sid = twl_map[mod_no].sid;
+ twl = &twl_modules[sid];
+
mutex_lock(&twl->xfer_lock);
/* [MSG1] fill the register address data */
msg = &twl->xfer_msg[0];
u32 edge_change;
struct mutex irq_lock;
+ char *irq_name;
};
/*----------------------------------------------------------------------*/
* Generic handler for SIH interrupts ... we "know" this is called
* in task context, with IRQs enabled.
*/
-static void handle_twl4030_sih(unsigned irq, struct irq_desc *desc)
+static irqreturn_t handle_twl4030_sih(int irq, void *data)
{
struct sih_agent *agent = irq_get_handler_data(irq);
const struct sih *sih = agent->sih;
pr_err("twl4030: %s SIH, read ISR error %d\n",
sih->name, isr);
/* REVISIT: recover; eventually mask it all, etc */
- return;
+ return IRQ_HANDLED;
}
while (isr) {
pr_err("twl4030: %s SIH, invalid ISR bit %d\n",
sih->name, irq);
}
+ return IRQ_HANDLED;
}
static unsigned twl4030_irq_next;
activate_irq(irq);
}
- status = irq_base;
twl4030_irq_next += i;
/* replace generic PIH handler (handle_simple_irq) */
irq = sih_mod + twl4030_irq_base;
irq_set_handler_data(irq, agent);
- irq_set_chained_handler(irq, handle_twl4030_sih);
+ agent->irq_name = kasprintf(GFP_KERNEL, "twl4030_%s", sih->name);
+ status = request_threaded_irq(irq, NULL, handle_twl4030_sih, 0,
+ agent->irq_name ?: sih->name, NULL);
pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", sih->name,
irq, irq_base, twl4030_irq_next - 1);
- return status;
+ return status < 0 ? status : irq_base;
}
/* FIXME need a call to reverse twl4030_sih_setup() ... */
}
/* install an irq handler to demultiplex the TWL4030 interrupt */
- status = request_threaded_irq(irq_num, NULL, handle_twl4030_pih, 0,
- "TWL4030-PIH", NULL);
+ status = request_threaded_irq(irq_num, NULL, handle_twl4030_pih,
+ IRQF_ONESHOT,
+ "TWL4030-PIH", NULL);
if (status < 0) {
pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status);
goto fail_rqirq;
switch (wm8994->type) {
case WM8958:
+ case WM1811:
ret = wm8994_reg_read(wm8994, WM8958_MIC_DETECT_1);
if (ret < 0) {
dev_err(dev, "Failed to read power status: %d\n", ret);
module will be called bmp085.
config PCH_PHUB
- tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) PHUB"
+ tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) PHUB"
depends on PCI
help
This driver is for PCH(Platform controller Hub) PHUB(Packet Hub) of
processor. The Topcliff has MAC address and Option ROM data in SROM.
This driver can access MAC address and Option ROM data in SROM.
- This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
- Output Hub), ML7213 and ML7223.
- ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
- for MP(Media Phone) use.
- ML7213/ML7223 is companion chip for Intel Atom E6xx series.
- ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+ This driver also can be used for LAPIS Semiconductor's IOH,
+ ML7213/ML7223/ML7831.
+ ML7213 which is for IVI(In-Vehicle Infotainment) use.
+ ML7223 IOH is for MP(Media Phone) use.
+ ML7831 IOH is for general purpose use.
+ ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+ ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
To compile this driver as a module, choose M here: the module will
be called pch_phub.
AD5293_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT, BRDAC0, 10, 27),
AD7376_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT,
BRDAC0, 7, 28),
- AD8400_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT,
+ AD8400_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_16BIT,
BRDAC0, 8, 29),
AD8402_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_16BIT,
BRDAC0 | BRDAC1, 8, 30),
/* CTL-CPLD Version Register */
#define CTL_CPLD_VERSION 0x2000
-static int fpga_of_probe(struct platform_device *op,
- const struct of_device_id *match)
+static int fpga_of_probe(struct platform_device *op)
{
struct device_node *of_node = op->dev.of_node;
struct device *this_device;
{},
};
-static struct of_platform_driver fpga_of_driver = {
+static struct platform_driver fpga_of_driver = {
.probe = fpga_of_probe,
.remove = fpga_of_remove,
.driver = {
static int __init fpga_init(void)
{
led_trigger_register_simple("fpga", &ledtrig_fpga);
- return of_register_platform_driver(&fpga_of_driver);
+ return platform_driver_register(&fpga_of_driver);
}
static void __exit fpga_exit(void)
{
- of_unregister_platform_driver(&fpga_of_driver);
+ platform_driver_unregister(&fpga_of_driver);
led_trigger_unregister_simple(ledtrig_fpga);
}
return true;
}
-static int data_of_probe(struct platform_device *op,
- const struct of_device_id *match)
+static int data_of_probe(struct platform_device *op)
{
struct device_node *of_node = op->dev.of_node;
struct device *this_device;
{},
};
-static struct of_platform_driver data_of_driver = {
+static struct platform_driver data_of_driver = {
.probe = data_of_probe,
.remove = data_of_remove,
.driver = {
static int __init data_init(void)
{
- return of_register_platform_driver(&data_of_driver);
+ return platform_driver_register(&data_of_driver);
}
static void __exit data_exit(void)
{
- of_unregister_platform_driver(&data_of_driver);
+ platform_driver_unregister(&data_of_driver);
}
MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
config EEPROM_DIGSY_MTC_CFG
bool "DigsyMTC display configuration EEPROMs device"
- depends on PPC_MPC5200_GPIO && GPIOLIB && SPI_GPIO
+ depends on GPIO_MPC5200 && SPI_GPIO
help
This option enables access to display configuration EEPROMs
on digsy_mtc board. You have to additionally select Microwire
eeprom->reg_data_out = 0;
eeprom->reg_data_clock = 0;
eeprom->reg_chip_select = 1;
+ eeprom->drive_data = 1;
eeprom->register_write(eeprom);
/*
*/
eeprom->reg_data_in = 0;
eeprom->reg_data_out = 0;
+ eeprom->drive_data = 1;
/*
* Start writing all bits.
*/
eeprom->reg_data_in = 0;
eeprom->reg_data_out = 0;
+ eeprom->drive_data = 0;
/*
* Start reading all bits.
}
EXPORT_SYMBOL_GPL(eeprom_93cx6_multiread);
+/**
+ * eeprom_93cx6_wren - set the write enable state
+ * @eeprom: Pointer to eeprom structure
+ * @enable: true to enable writes, otherwise disable writes
+ *
+ * Set the EEPROM write enable state to either allow or deny
+ * writes depending on the @enable value.
+ */
+void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable)
+{
+ u16 command;
+
+ /* start the command */
+ eeprom_93cx6_startup(eeprom);
+
+ /* create command to enable/disable */
+
+ command = enable ? PCI_EEPROM_EWEN_OPCODE : PCI_EEPROM_EWDS_OPCODE;
+ command <<= (eeprom->width - 2);
+
+ eeprom_93cx6_write_bits(eeprom, command,
+ PCI_EEPROM_WIDTH_OPCODE + eeprom->width);
+
+ eeprom_93cx6_cleanup(eeprom);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_wren);
+
+/**
+ * eeprom_93cx6_write - write data to the EEPROM
+ * @eeprom: Pointer to eeprom structure
+ * @addr: Address to write data to.
+ * @data: The data to write to address @addr.
+ *
+ * Write the @data to the specified @addr in the EEPROM and
+ * waiting for the device to finish writing.
+ *
+ * Note, since we do not expect large number of write operations
+ * we delay in between parts of the operation to avoid using excessive
+ * amounts of CPU time busy waiting.
+ */
+void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom, u8 addr, u16 data)
+{
+ int timeout = 100;
+ u16 command;
+
+ /* start the command */
+ eeprom_93cx6_startup(eeprom);
+
+ command = PCI_EEPROM_WRITE_OPCODE << eeprom->width;
+ command |= addr;
+
+ /* send write command */
+ eeprom_93cx6_write_bits(eeprom, command,
+ PCI_EEPROM_WIDTH_OPCODE + eeprom->width);
+
+ /* send data */
+ eeprom_93cx6_write_bits(eeprom, data, 16);
+
+ /* get ready to check for busy */
+ eeprom->drive_data = 0;
+ eeprom->reg_chip_select = 1;
+ eeprom->register_write(eeprom);
+
+ /* wait at-least 250ns to get DO to be the busy signal */
+ usleep_range(1000, 2000);
+
+ /* wait for DO to go high to signify finish */
+
+ while (true) {
+ eeprom->register_read(eeprom);
+
+ if (eeprom->reg_data_out)
+ break;
+
+ usleep_range(1000, 2000);
+
+ if (--timeout <= 0) {
+ printk(KERN_ERR "%s: timeout\n", __func__);
+ break;
+ }
+ }
+
+ eeprom_93cx6_cleanup(eeprom);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_write);
/*
- * Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ * Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
#define PCH_PHUB_ROM_START_ADDR_EG20T 0x80 /* ROM data area start address offset
(Intel EG20T PCH)*/
#define PCH_PHUB_ROM_START_ADDR_ML7213 0x400 /* ROM data area start address
- offset(OKI SEMICONDUCTOR ML7213)
+ offset(LAPIS Semicon ML7213)
*/
#define PCH_PHUB_ROM_START_ADDR_ML7223 0x400 /* ROM data area start address
- offset(OKI SEMICONDUCTOR ML7223)
+ offset(LAPIS Semicon ML7223)
*/
/* MAX number of INT_REDUCE_CONTROL registers */
#define PCI_DEVICE_ID_ROHM_ML7223_mPHUB 0x8012 /* for Bus-m */
#define PCI_DEVICE_ID_ROHM_ML7223_nPHUB 0x8002 /* for Bus-n */
+/* Macros for ML7831 */
+#define PCI_DEVICE_ID_ROHM_ML7831_PHUB 0x8801
+
/* SROM ACCESS Macro */
#define PCH_WORD_ADDR_MASK (~((1 << 2) - 1))
* @pch_mac_start_address: MAC address area start address
* @pch_opt_rom_start_address: Option ROM start address
* @ioh_type: Save IOH type
+ * @pdev: pointer to pci device struct
*/
struct pch_phub_reg {
u32 phub_id_reg;
u32 pch_mac_start_address;
u32 pch_opt_rom_start_address;
int ioh_type;
+ struct pci_dev *pdev;
};
/* SROM SPEC for MAC address assignment offset */
int retval;
int i;
- if (chip->ioh_type == 1) /* EG20T */
+ if ((chip->ioh_type == 1) || (chip->ioh_type == 5)) /* EG20T or ML7831*/
retval = pch_phub_gbe_serial_rom_conf(chip);
else /* ML7223 */
retval = pch_phub_gbe_serial_rom_conf_mp(chip);
unsigned int orom_size;
int ret;
int err;
+ ssize_t rom_size;
struct pch_phub_reg *chip =
dev_get_drvdata(container_of(kobj, struct device, kobj));
}
/* Get Rom signature */
+ chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+ if (!chip->pch_phub_extrom_base_address)
+ goto exrom_map_err;
+
pch_phub_read_serial_rom(chip, chip->pch_opt_rom_start_address,
(unsigned char *)&rom_signature);
rom_signature &= 0xff;
goto return_err;
}
return_ok:
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
mutex_unlock(&pch_phub_mutex);
return addr_offset;
return_err:
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
+exrom_map_err:
mutex_unlock(&pch_phub_mutex);
return_err_nomutex:
return err;
int err;
unsigned int addr_offset;
int ret;
+ ssize_t rom_size;
struct pch_phub_reg *chip =
dev_get_drvdata(container_of(kobj, struct device, kobj));
goto return_ok;
}
+ chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+ if (!chip->pch_phub_extrom_base_address) {
+ err = -ENOMEM;
+ goto exrom_map_err;
+ }
+
for (addr_offset = 0; addr_offset < count; addr_offset++) {
if (PCH_PHUB_OROM_SIZE < off + addr_offset)
goto return_ok;
}
return_ok:
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
mutex_unlock(&pch_phub_mutex);
return addr_offset;
return_err:
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
+
+exrom_map_err:
mutex_unlock(&pch_phub_mutex);
return err;
}
{
u8 mac[8];
struct pch_phub_reg *chip = dev_get_drvdata(dev);
+ ssize_t rom_size;
+
+ chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+ if (!chip->pch_phub_extrom_base_address)
+ return -ENOMEM;
pch_phub_read_gbe_mac_addr(chip, mac);
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
return sprintf(buf, "%pM\n", mac);
}
const char *buf, size_t count)
{
u8 mac[6];
+ ssize_t rom_size;
struct pch_phub_reg *chip = dev_get_drvdata(dev);
if (count != 18)
(u32 *)&mac[0], (u32 *)&mac[1], (u32 *)&mac[2], (u32 *)&mac[3],
(u32 *)&mac[4], (u32 *)&mac[5]);
+ chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+ if (!chip->pch_phub_extrom_base_address)
+ return -ENOMEM;
+
pch_phub_write_gbe_mac_addr(chip, mac);
+ pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
return count;
}
int retval;
int ret;
- ssize_t rom_size;
struct pch_phub_reg *chip;
chip = kzalloc(sizeof(struct pch_phub_reg), GFP_KERNEL);
"in pch_phub_base_address variable is %p\n", __func__,
chip->pch_phub_base_address);
- if (id->driver_data != 3) {
- chip->pch_phub_extrom_base_address =\
- pci_map_rom(pdev, &rom_size);
- if (chip->pch_phub_extrom_base_address == 0) {
- dev_err(&pdev->dev, "%s: pci_map_rom FAILED", __func__);
- ret = -ENOMEM;
- goto err_pci_map;
- }
- dev_dbg(&pdev->dev, "%s : "
- "pci_map_rom SUCCESS and value in "
- "pch_phub_extrom_base_address variable is %p\n",
- __func__, chip->pch_phub_extrom_base_address);
- }
+ chip->pdev = pdev; /* Save pci device struct */
if (id->driver_data == 1) { /* EG20T PCH */
const char *board_name;
chip->pch_opt_rom_start_address =\
PCH_PHUB_ROM_START_ADDR_ML7223;
chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_ML7223;
+ } else if (id->driver_data == 5) { /* ML7831 */
+ retval = sysfs_create_file(&pdev->dev.kobj,
+ &dev_attr_pch_mac.attr);
+ if (retval)
+ goto err_sysfs_create;
+
+ retval = sysfs_create_bin_file(&pdev->dev.kobj, &pch_bin_attr);
+ if (retval)
+ goto exit_bin_attr;
+
+ /* set the prefech value */
+ iowrite32(0x000affaa, chip->pch_phub_base_address + 0x14);
+ /* set the interrupt delay value */
+ iowrite32(0x25, chip->pch_phub_base_address + 0x44);
+ chip->pch_opt_rom_start_address = PCH_PHUB_ROM_START_ADDR_EG20T;
+ chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_EG20T;
}
chip->ioh_type = id->driver_data;
sysfs_remove_file(&pdev->dev.kobj, &dev_attr_pch_mac.attr);
err_sysfs_create:
- pci_unmap_rom(pdev, chip->pch_phub_extrom_base_address);
-err_pci_map:
pci_iounmap(pdev, chip->pch_phub_base_address);
err_pci_iomap:
pci_release_regions(pdev);
sysfs_remove_file(&pdev->dev.kobj, &dev_attr_pch_mac.attr);
sysfs_remove_bin_file(&pdev->dev.kobj, &pch_bin_attr);
- pci_unmap_rom(pdev, chip->pch_phub_extrom_base_address);
pci_iounmap(pdev, chip->pch_phub_base_address);
pci_release_regions(pdev);
pci_disable_device(pdev);
{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7213_PHUB), 2, },
{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_mPHUB), 3, },
{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_nPHUB), 4, },
+ { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7831_PHUB), 5, },
{ }
};
MODULE_DEVICE_TABLE(pci, pch_phub_pcidev_id);
module_init(pch_phub_pci_init);
module_exit(pch_phub_pci_exit);
-MODULE_DESCRIPTION("Intel EG20T PCH/OKI SEMICONDUCTOR IOH(ML7213/ML7223) PHUB");
+MODULE_DESCRIPTION("Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7223) PHUB");
MODULE_LICENSE("GPL");
* report an error if the data is not retrievable and the
* packet will be dropped.
*/
- xpnet_device->features = NETIF_F_NO_CSUM;
+ xpnet_device->features = NETIF_F_HW_CSUM;
result = register_netdev(xpnet_device);
if (result != 0) {
}
module_exit(spear_pcie_gadget_exit);
-MODULE_ALIAS("pcie-gadget-spear");
+MODULE_ALIAS("platform:pcie-gadget-spear");
MODULE_AUTHOR("Pratyush Anand");
MODULE_LICENSE("GPL");
MMC_QUIRK_BLK_NO_CMD23),
MMC_FIXUP("MMC32G", 0x11, CID_OEMID_ANY, add_quirk_mmc,
MMC_QUIRK_BLK_NO_CMD23),
+
+ /*
+ * Some Micron MMC cards needs longer data read timeout than
+ * indicated in CSD.
+ */
+ MMC_FIXUP(CID_NAME_ANY, 0x13, 0x200, add_quirk_mmc,
+ MMC_QUIRK_LONG_READ_TIME),
+
END_FIXUP
};
data->timeout_clks = 0;
}
}
+
+ /*
+ * Some cards require longer data read timeout than indicated in CSD.
+ * Address this by setting the read timeout to a "reasonably high"
+ * value. For the cards tested, 300ms has proven enough. If necessary,
+ * this value can be increased if other problematic cards require this.
+ */
+ if (mmc_card_long_read_time(card) && data->flags & MMC_DATA_READ) {
+ data->timeout_ns = 300000000;
+ data->timeout_clks = 0;
+ }
+
/*
* Some cards need very high timeouts if driven in SPI mode.
* The worst observed timeout was 900ms after writing a
mmc_host_clk_release(host);
}
+static void mmc_poweroff_notify(struct mmc_host *host)
+{
+ struct mmc_card *card;
+ unsigned int timeout;
+ unsigned int notify_type = EXT_CSD_NO_POWER_NOTIFICATION;
+ int err = 0;
+
+ card = host->card;
+
+ /*
+ * Send power notify command only if card
+ * is mmc and notify state is powered ON
+ */
+ if (card && mmc_card_mmc(card) &&
+ (card->poweroff_notify_state == MMC_POWERED_ON)) {
+
+ if (host->power_notify_type == MMC_HOST_PW_NOTIFY_SHORT) {
+ notify_type = EXT_CSD_POWER_OFF_SHORT;
+ timeout = card->ext_csd.generic_cmd6_time;
+ card->poweroff_notify_state = MMC_POWEROFF_SHORT;
+ } else {
+ notify_type = EXT_CSD_POWER_OFF_LONG;
+ timeout = card->ext_csd.power_off_longtime;
+ card->poweroff_notify_state = MMC_POWEROFF_LONG;
+ }
+
+ err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+ EXT_CSD_POWER_OFF_NOTIFICATION,
+ notify_type, timeout);
+
+ if (err && err != -EBADMSG)
+ pr_err("Device failed to respond within %d poweroff "
+ "time. Forcefully powering down the device\n",
+ timeout);
+
+ /* Set the card state to no notification after the poweroff */
+ card->poweroff_notify_state = MMC_NO_POWER_NOTIFICATION;
+ }
+}
+
/*
* Apply power to the MMC stack. This is a two-stage process.
* First, we enable power to the card without the clock running.
void mmc_power_off(struct mmc_host *host)
{
- struct mmc_card *card;
- unsigned int notify_type;
- unsigned int timeout;
- int err;
-
mmc_host_clk_hold(host);
- card = host->card;
host->ios.clock = 0;
host->ios.vdd = 0;
- if (card && mmc_card_mmc(card) &&
- (card->poweroff_notify_state == MMC_POWERED_ON)) {
-
- if (host->power_notify_type == MMC_HOST_PW_NOTIFY_SHORT) {
- notify_type = EXT_CSD_POWER_OFF_SHORT;
- timeout = card->ext_csd.generic_cmd6_time;
- card->poweroff_notify_state = MMC_POWEROFF_SHORT;
- } else {
- notify_type = EXT_CSD_POWER_OFF_LONG;
- timeout = card->ext_csd.power_off_longtime;
- card->poweroff_notify_state = MMC_POWEROFF_LONG;
- }
-
- err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
- EXT_CSD_POWER_OFF_NOTIFICATION,
- notify_type, timeout);
-
- if (err && err != -EBADMSG)
- pr_err("Device failed to respond within %d poweroff "
- "time. Forcefully powering down the device\n",
- timeout);
-
- /* Set the card state to no notification after the poweroff */
- card->poweroff_notify_state = MMC_NO_POWER_NOTIFICATION;
- }
+ mmc_poweroff_notify(host);
/*
* Reset ocr mask to be the highest possible voltage supported for
mmc_bus_get(host);
- if (host->bus_ops && !host->bus_dead && host->bus_ops->awake)
+ if (host->bus_ops && !host->bus_dead && host->bus_ops->sleep)
err = host->bus_ops->sleep(host);
mmc_bus_put(host);
* pre-claim the host.
*/
if (mmc_try_claim_host(host)) {
- if (host->bus_ops->suspend)
+ if (host->bus_ops->suspend) {
+ /*
+ * For eMMC 4.5 device send notify command
+ * before sleep, because in sleep state eMMC 4.5
+ * devices respond to only RESET and AWAKE cmd
+ */
+ mmc_poweroff_notify(host);
err = host->bus_ops->suspend(host);
+ }
+ mmc_do_release_host(host);
+
if (err == -ENOSYS || !host->bus_ops->resume) {
/*
* We simply "remove" the card in this case.
host->pm_flags = 0;
err = 0;
}
- mmc_do_release_host(host);
} else {
err = -EBUSY;
}
host->max_blk_size = 512;
host->max_blk_count = PAGE_CACHE_SIZE / 512;
- /*
- * Enable runtime power management by default. This flag was added due
- * to runtime power management causing disruption for some users, but
- * the power on/off code has been improved since then.
- *
- * We'll enable this flag by default as an experiment, and if no
- * problems are reported, we will follow up later and remove the flag
- * altogether.
- */
- host->caps = MMC_CAP_POWER_OFF_CARD;
-
return host;
free:
* set the notification byte in the ext_csd register of device
*/
if ((host->caps2 & MMC_CAP2_POWEROFF_NOTIFY) &&
- (card->poweroff_notify_state == MMC_NO_POWER_NOTIFICATION)) {
+ (card->ext_csd.rev >= 6)) {
err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
EXT_CSD_POWER_OFF_NOTIFICATION,
EXT_CSD_POWER_ON,
card->ext_csd.generic_cmd6_time);
if (err && err != -EBADMSG)
goto free_card;
- }
- if (!err)
- card->poweroff_notify_state = MMC_POWERED_ON;
+ /*
+ * The err can be -EBADMSG or 0,
+ * so check for success and update the flag
+ */
+ if (!err)
+ card->poweroff_notify_state = MMC_POWERED_ON;
+ }
/*
* Activate high speed (if supported)
unsigned int status)
{
/* First check for errors */
- if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_TXUNDERRUN|MCI_RXOVERRUN)) {
+ if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
+ MCI_TXUNDERRUN|MCI_RXOVERRUN)) {
u32 remain, success;
/* Terminate the DMA transfer */
}
if (!cmd->data || cmd->error) {
- if (host->data)
+ if (host->data) {
+ /* Terminate the DMA transfer */
+ if (dma_inprogress(host))
+ mmci_dma_data_error(host);
mmci_stop_data(host);
+ }
mmci_request_end(host, cmd->mrq);
} else if (!(cmd->data->flags & MMC_DATA_READ)) {
mmci_start_data(host, cmd->data);
dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status);
data = host->data;
- if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_TXUNDERRUN|
- MCI_RXOVERRUN|MCI_DATAEND|MCI_DATABLOCKEND) && data)
+ if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
+ MCI_TXUNDERRUN|MCI_RXOVERRUN|MCI_DATAEND|
+ MCI_DATABLOCKEND) && data)
mmci_data_irq(host, data, status);
cmd = host->cmd;
"failed to config DMA channel. Falling back to PIO\n");
dma_release_channel(host->dma);
host->do_dma = 0;
+ host->dma = NULL;
}
}
host->data->sg_len,
omap_hsmmc_get_dma_dir(host, host->data));
omap_free_dma(dma_ch);
+ host->data->host_cookie = 0;
}
host->data = NULL;
}
struct mmc_data *data = mrq->data;
if (host->use_dma) {
- dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
- omap_hsmmc_get_dma_dir(host, data));
+ if (data->host_cookie)
+ dma_unmap_sg(mmc_dev(host->mmc), data->sg,
+ data->sg_len,
+ omap_hsmmc_get_dma_dir(host, data));
data->host_cookie = 0;
}
}
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/mmc/host.h>
+#include <linux/module.h>
#include <mach/cns3xxx.h>
#include "sdhci-pltfm.h"
.driver = {
.name = "sdhci-cns3xxx",
.owner = THIS_MODULE,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_cns3xxx_probe,
.remove = __devexit_p(sdhci_cns3xxx_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_cns3xxx_init(void)
.driver = {
.name = "sdhci-dove",
.owner = THIS_MODULE,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_dove_probe,
.remove = __devexit_p(sdhci_dove_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_dove_init(void)
.name = "sdhci-esdhc-imx",
.owner = THIS_MODULE,
.of_match_table = imx_esdhc_dt_ids,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.id_table = imx_esdhc_devtype,
.probe = sdhci_esdhc_imx_probe,
.remove = __devexit_p(sdhci_esdhc_imx_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_esdhc_imx_init(void)
.name = "sdhci-esdhc",
.owner = THIS_MODULE,
.of_match_table = sdhci_esdhc_of_match,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_esdhc_probe,
.remove = __devexit_p(sdhci_esdhc_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_esdhc_init(void)
.name = "sdhci-hlwd",
.owner = THIS_MODULE,
.of_match_table = sdhci_hlwd_of_match,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_hlwd_probe,
.remove = __devexit_p(sdhci_hlwd_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_hlwd_init(void)
int (*probe_slot) (struct sdhci_pci_slot *);
void (*remove_slot) (struct sdhci_pci_slot *, int);
- int (*suspend) (struct sdhci_pci_chip *,
- pm_message_t);
+ int (*suspend) (struct sdhci_pci_chip *);
int (*resume) (struct sdhci_pci_chip *);
};
jmicron_enable_mmc(slot->host, 0);
}
-static int jmicron_suspend(struct sdhci_pci_chip *chip, pm_message_t state)
+static int jmicron_suspend(struct sdhci_pci_chip *chip)
{
int i;
#ifdef CONFIG_PM
-static int sdhci_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+static int sdhci_pci_suspend(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct sdhci_pci_chip *chip;
struct sdhci_pci_slot *slot;
mmc_pm_flag_t slot_pm_flags;
if (!slot)
continue;
- ret = sdhci_suspend_host(slot->host, state);
+ ret = sdhci_suspend_host(slot->host);
if (ret) {
for (i--; i >= 0; i--)
}
if (chip->fixes && chip->fixes->suspend) {
- ret = chip->fixes->suspend(chip, state);
+ ret = chip->fixes->suspend(chip);
if (ret) {
for (i = chip->num_slots - 1; i >= 0; i--)
sdhci_resume_host(chip->slots[i]->host);
}
pci_set_power_state(pdev, PCI_D3hot);
} else {
- pci_enable_wake(pdev, pci_choose_state(pdev, state), 0);
+ pci_enable_wake(pdev, PCI_D3hot, 0);
pci_disable_device(pdev);
- pci_set_power_state(pdev, pci_choose_state(pdev, state));
+ pci_set_power_state(pdev, PCI_D3hot);
}
return 0;
}
-static int sdhci_pci_resume(struct pci_dev *pdev)
+static int sdhci_pci_resume(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct sdhci_pci_chip *chip;
struct sdhci_pci_slot *slot;
int i, ret;
struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
struct sdhci_pci_chip *chip;
struct sdhci_pci_slot *slot;
- pm_message_t state = { .event = PM_EVENT_SUSPEND };
int i, ret;
chip = pci_get_drvdata(pdev);
}
if (chip->fixes && chip->fixes->suspend) {
- ret = chip->fixes->suspend(chip, state);
+ ret = chip->fixes->suspend(chip);
if (ret) {
for (i = chip->num_slots - 1; i >= 0; i--)
sdhci_runtime_resume_host(chip->slots[i]->host);
#endif
static const struct dev_pm_ops sdhci_pci_pm_ops = {
+ .suspend = sdhci_pci_suspend,
+ .resume = sdhci_pci_resume,
.runtime_suspend = sdhci_pci_runtime_suspend,
.runtime_resume = sdhci_pci_runtime_resume,
.runtime_idle = sdhci_pci_runtime_idle,
.id_table = pci_ids,
.probe = sdhci_pci_probe,
.remove = __devexit_p(sdhci_pci_remove),
- .suspend = sdhci_pci_suspend,
- .resume = sdhci_pci_resume,
.driver = {
.pm = &sdhci_pci_pm_ops
},
EXPORT_SYMBOL_GPL(sdhci_pltfm_unregister);
#ifdef CONFIG_PM
-int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state)
+static int sdhci_pltfm_suspend(struct device *dev)
{
- struct sdhci_host *host = platform_get_drvdata(dev);
+ struct sdhci_host *host = dev_get_drvdata(dev);
- return sdhci_suspend_host(host, state);
+ return sdhci_suspend_host(host);
}
-EXPORT_SYMBOL_GPL(sdhci_pltfm_suspend);
-int sdhci_pltfm_resume(struct platform_device *dev)
+static int sdhci_pltfm_resume(struct device *dev)
{
- struct sdhci_host *host = platform_get_drvdata(dev);
+ struct sdhci_host *host = dev_get_drvdata(dev);
return sdhci_resume_host(host);
}
-EXPORT_SYMBOL_GPL(sdhci_pltfm_resume);
+
+const struct dev_pm_ops sdhci_pltfm_pmops = {
+ .suspend = sdhci_pltfm_suspend,
+ .resume = sdhci_pltfm_resume,
+};
+EXPORT_SYMBOL_GPL(sdhci_pltfm_pmops);
#endif /* CONFIG_PM */
static int __init sdhci_pltfm_drv_init(void)
extern int sdhci_pltfm_unregister(struct platform_device *pdev);
#ifdef CONFIG_PM
-extern int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state);
-extern int sdhci_pltfm_resume(struct platform_device *dev);
+extern const struct dev_pm_ops sdhci_pltfm_pmops;
+#define SDHCI_PLTFM_PMOPS (&sdhci_pltfm_pmops)
+#else
+#define SDHCI_PLTFM_PMOPS NULL
#endif
#endif /* _DRIVERS_MMC_SDHCI_PLTFM_H */
.driver = {
.name = "sdhci-pxav2",
.owner = THIS_MODULE,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_pxav2_probe,
.remove = __devexit_p(sdhci_pxav2_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_pxav2_init(void)
{
.driver = {
.name = "sdhci-pxav3",
.owner = THIS_MODULE,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_pxav3_probe,
.remove = __devexit_p(sdhci_pxav3_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_pxav3_init(void)
{
#ifdef CONFIG_PM
-static int sdhci_s3c_suspend(struct platform_device *dev, pm_message_t pm)
+static int sdhci_s3c_suspend(struct device *dev)
{
- struct sdhci_host *host = platform_get_drvdata(dev);
+ struct sdhci_host *host = dev_get_drvdata(dev);
- return sdhci_suspend_host(host, pm);
+ return sdhci_suspend_host(host);
}
-static int sdhci_s3c_resume(struct platform_device *dev)
+static int sdhci_s3c_resume(struct device *dev)
{
- struct sdhci_host *host = platform_get_drvdata(dev);
+ struct sdhci_host *host = dev_get_drvdata(dev);
return sdhci_resume_host(host);
}
+static const struct dev_pm_ops sdhci_s3c_pmops = {
+ .suspend = sdhci_s3c_suspend,
+ .resume = sdhci_s3c_resume,
+};
+
+#define SDHCI_S3C_PMOPS (&sdhci_s3c_pmops)
+
#else
-#define sdhci_s3c_suspend NULL
-#define sdhci_s3c_resume NULL
+#define SDHCI_S3C_PMOPS NULL
#endif
static struct platform_driver sdhci_s3c_driver = {
.probe = sdhci_s3c_probe,
.remove = __devexit_p(sdhci_s3c_remove),
- .suspend = sdhci_s3c_suspend,
- .resume = sdhci_s3c_resume,
.driver = {
.owner = THIS_MODULE,
.name = "s3c-sdhci",
+ .pm = SDHCI_S3C_PMOPS,
},
};
.name = "sdhci-tegra",
.owner = THIS_MODULE,
.of_match_table = sdhci_tegra_dt_match,
+ .pm = SDHCI_PLTFM_PMOPS,
},
.probe = sdhci_tegra_probe,
.remove = __devexit_p(sdhci_tegra_remove),
-#ifdef CONFIG_PM
- .suspend = sdhci_pltfm_suspend,
- .resume = sdhci_pltfm_resume,
-#endif
};
static int __init sdhci_tegra_init(void)
#ifdef CONFIG_PM
-int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state)
+int sdhci_suspend_host(struct sdhci_host *host)
{
int ret;
extern void sdhci_remove_host(struct sdhci_host *host, int dead);
#ifdef CONFIG_PM
-extern int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state);
+extern int sdhci_suspend_host(struct sdhci_host *host);
extern int sdhci_resume_host(struct sdhci_host *host);
extern void sdhci_enable_irq_wakeups(struct sdhci_host *host);
#endif
if (host->power) {
pm_runtime_put(&host->pd->dev);
host->power = false;
- if (p->down_pwr)
+ if (p->down_pwr && ios->power_mode == MMC_POWER_OFF)
p->down_pwr(host->pd);
}
host->state = STATE_IDLE;
/* start bus clock */
tmio_mmc_clk_start(host);
} else if (ios->power_mode != MMC_POWER_UP) {
- if (host->set_pwr)
+ if (host->set_pwr && ios->power_mode == MMC_POWER_OFF)
host->set_pwr(host->pdev, 0);
if ((pdata->flags & TMIO_MMC_HAS_COLD_CD) &&
pdata->power) {
static int firmware_rom_wait_states = 0x1C;
#endif
-module_param(firmware_rom_wait_states, bool, 0644);
+module_param(firmware_rom_wait_states, int, 0644);
MODULE_PARM_DESC(firmware_rom_wait_states,
"ROM wait states byte=RRRIIEEE (Reserved Internal External)");
if (!err)
dev_info(&pdev->dev, "registered mtd device\n");
- /* add the whole device. */
- err = mtd_device_register(info->mtd, NULL, 0);
- if (err)
- dev_err(&pdev->dev, "failed to register the entire device\n");
+ if (pdata->nr_partitions) {
+ /* add the whole device. */
+ err = mtd_device_register(info->mtd, NULL, 0);
+ if (err) {
+ dev_err(&pdev->dev,
+ "failed to register the entire device\n");
+ }
+ }
return err;
}
info->mtd->owner = THIS_MODULE;
- mtd_device_parse_register(info->mtd, probes, 0, NULL, 0);
+ mtd_device_parse_register(info->mtd, probes, 0, flash->parts, flash->nr_parts);
platform_set_drvdata(pdev, info);
return 0;
#include <linux/clk.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
#include <linux/mtd/gpmi-nand.h>
#include <linux/mtd/partitions.h>
-
#include "gpmi-nand.h"
/* add our owner bbt descriptor */
if (!flash_np)
return -ENODEV;
- ppdata->of_node = flash_np;
+ ppdata.of_node = flash_np;
ndfc->mtd.name = kasprintf(GFP_KERNEL, "%s.%s",
dev_name(&ndfc->ofdev->dev), flash_np->name);
if (!ndfc->mtd.name) {
'ifb1' etc.
Look at the iproute2 documentation directory for usage etc
+source "drivers/net/team/Kconfig"
+
config MACVLAN
tristate "MAC-VLAN support (EXPERIMENTAL)"
depends on EXPERIMENTAL
source "drivers/net/caif/Kconfig"
+source "drivers/net/dsa/Kconfig"
+
source "drivers/net/ethernet/Kconfig"
source "drivers/net/fddi/Kconfig"
+source "drivers/net/hippi/Kconfig"
+
config NET_SB1000
tristate "General Instruments Surfboard 1000"
depends on PNP
obj-$(CONFIG_NETCONSOLE) += netconsole.o
obj-$(CONFIG_PHYLIB) += phy/
obj-$(CONFIG_RIONET) += rionet.o
+obj-$(CONFIG_NET_TEAM) += team/
obj-$(CONFIG_TUN) += tun.o
obj-$(CONFIG_VETH) += veth.o
obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
obj-$(CONFIG_CAIF) += caif/
obj-$(CONFIG_CAN) += can/
obj-$(CONFIG_ETRAX_ETHERNET) += cris/
+obj-$(CONFIG_NET_DSA) += dsa/
obj-$(CONFIG_ETHERNET) += ethernet/
obj-$(CONFIG_FDDI) += fddi/
obj-$(CONFIG_HIPPI) += hippi/
menuconfig ARCNET
depends on NETDEVICES && (ISA || PCI || PCMCIA)
- bool "ARCnet support"
+ tristate "ARCnet support"
---help---
If you have a network card of this type, say Y and check out the
(arguably) beautiful poetry in
+++ /dev/null
-/*
- * Copyright(c) 2008 Hewlett-Packard Development Company, L.P.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called LICENSE.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/types.h>
-#include <linux/if_vlan.h>
-#include <net/ipv6.h>
-#include <net/ndisc.h>
-#include <net/addrconf.h>
-#include <net/netns/generic.h>
-#include "bonding.h"
-
-/*
- * Assign bond->master_ipv6 to the next IPv6 address in the list, or
- * zero it out if there are none.
- */
-static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr)
-{
- struct inet6_dev *idev;
-
- if (!dev)
- return;
-
- idev = in6_dev_get(dev);
- if (!idev)
- return;
-
- read_lock_bh(&idev->lock);
- if (!list_empty(&idev->addr_list)) {
- struct inet6_ifaddr *ifa
- = list_first_entry(&idev->addr_list,
- struct inet6_ifaddr, if_list);
- ipv6_addr_copy(addr, &ifa->addr);
- } else
- ipv6_addr_set(addr, 0, 0, 0, 0);
-
- read_unlock_bh(&idev->lock);
-
- in6_dev_put(idev);
-}
-
-static void bond_na_send(struct net_device *slave_dev,
- struct in6_addr *daddr,
- int router,
- unsigned short vlan_id)
-{
- struct in6_addr mcaddr;
- struct icmp6hdr icmp6h = {
- .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
- };
- struct sk_buff *skb;
-
- icmp6h.icmp6_router = router;
- icmp6h.icmp6_solicited = 0;
- icmp6h.icmp6_override = 1;
-
- addrconf_addr_solict_mult(daddr, &mcaddr);
-
- pr_debug("ipv6 na on slave %s: dest %pI6, src %pI6\n",
- slave_dev->name, &mcaddr, daddr);
-
- skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr,
- ND_OPT_TARGET_LL_ADDR);
-
- if (!skb) {
- pr_err("NA packet allocation failed\n");
- return;
- }
-
- if (vlan_id) {
- /* The Ethernet header is not present yet, so it is
- * too early to insert a VLAN tag. Force use of an
- * out-of-line tag here and let dev_hard_start_xmit()
- * insert it if the slave hardware can't.
- */
- skb = __vlan_hwaccel_put_tag(skb, vlan_id);
- if (!skb) {
- pr_err("failed to insert VLAN tag\n");
- return;
- }
- }
-
- ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h);
-}
-
-/*
- * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on
- * the bonding master. This will help the switch learn our address
- * if in active-backup mode.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-void bond_send_unsolicited_na(struct bonding *bond)
-{
- struct slave *slave = bond->curr_active_slave;
- struct vlan_entry *vlan;
- struct inet6_dev *idev;
- int is_router;
-
- pr_debug("%s: bond %s slave %s\n", bond->dev->name,
- __func__, slave ? slave->dev->name : "NULL");
-
- if (!slave || !bond->send_unsol_na ||
- test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
- return;
-
- bond->send_unsol_na--;
-
- idev = in6_dev_get(bond->dev);
- if (!idev)
- return;
-
- is_router = !!idev->cnf.forwarding;
-
- in6_dev_put(idev);
-
- if (!ipv6_addr_any(&bond->master_ipv6))
- bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0);
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- if (!ipv6_addr_any(&vlan->vlan_ipv6)) {
- bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router,
- vlan->vlan_id);
- }
- }
-}
-
-/*
- * bond_inet6addr_event: handle inet6addr notifier chain events.
- *
- * We keep track of device IPv6 addresses primarily to use as source
- * addresses in NS probes.
- *
- * We track one IPv6 for the main device (if it has one).
- */
-static int bond_inet6addr_event(struct notifier_block *this,
- unsigned long event,
- void *ptr)
-{
- struct inet6_ifaddr *ifa = ptr;
- struct net_device *vlan_dev, *event_dev = ifa->idev->dev;
- struct bonding *bond;
- struct vlan_entry *vlan;
- struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id);
-
- list_for_each_entry(bond, &bn->dev_list, bond_list) {
- if (bond->dev == event_dev) {
- switch (event) {
- case NETDEV_UP:
- if (ipv6_addr_any(&bond->master_ipv6))
- ipv6_addr_copy(&bond->master_ipv6,
- &ifa->addr);
- return NOTIFY_OK;
- case NETDEV_DOWN:
- if (ipv6_addr_equal(&bond->master_ipv6,
- &ifa->addr))
- bond_glean_dev_ipv6(bond->dev,
- &bond->master_ipv6);
- return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
- }
- }
-
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
- rcu_read_lock();
- vlan_dev = __vlan_find_dev_deep(bond->dev,
- vlan->vlan_id);
- rcu_read_unlock();
- if (vlan_dev == event_dev) {
- switch (event) {
- case NETDEV_UP:
- if (ipv6_addr_any(&vlan->vlan_ipv6))
- ipv6_addr_copy(&vlan->vlan_ipv6,
- &ifa->addr);
- return NOTIFY_OK;
- case NETDEV_DOWN:
- if (ipv6_addr_equal(&vlan->vlan_ipv6,
- &ifa->addr))
- bond_glean_dev_ipv6(vlan_dev,
- &vlan->vlan_ipv6);
- return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
- }
- }
- }
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block bond_inet6addr_notifier = {
- .notifier_call = bond_inet6addr_event,
-};
-
-void bond_register_ipv6_notifier(void)
-{
- register_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
-void bond_unregister_ipv6_notifier(void)
-{
- unregister_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
* @bond_dev: bonding net device that got called
* @vid: vlan id being added
*/
-static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
+static int bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
{
struct bonding *bond = netdev_priv(bond_dev);
- struct slave *slave;
+ struct slave *slave, *stop_at;
int i, res;
bond_for_each_slave(bond, slave, i) {
- struct net_device *slave_dev = slave->dev;
- const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
- if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
- slave_ops->ndo_vlan_rx_add_vid) {
- slave_ops->ndo_vlan_rx_add_vid(slave_dev, vid);
- }
+ res = vlan_vid_add(slave->dev, vid);
+ if (res)
+ goto unwind;
}
res = bond_add_vlan(bond, vid);
if (res) {
pr_err("%s: Error: Failed to add vlan id %d\n",
bond_dev->name, vid);
+ return res;
}
+
+ return 0;
+
+unwind:
+ /* unwind from head to the slave that failed */
+ stop_at = slave;
+ bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at)
+ vlan_vid_del(slave->dev, vid);
+
+ return res;
}
/**
* @bond_dev: bonding net device that got called
* @vid: vlan id being removed
*/
-static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
+static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
int i, res;
- bond_for_each_slave(bond, slave, i) {
- struct net_device *slave_dev = slave->dev;
- const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
- if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
- slave_ops->ndo_vlan_rx_kill_vid) {
- slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid);
- }
- }
+ bond_for_each_slave(bond, slave, i)
+ vlan_vid_del(slave->dev, vid);
res = bond_del_vlan(bond, vid);
if (res) {
pr_err("%s: Error: Failed to remove vlan id %d\n",
bond_dev->name, vid);
+ return res;
}
+
+ return 0;
}
static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
{
struct vlan_entry *vlan;
- const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
- if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
- !(slave_ops->ndo_vlan_rx_add_vid))
- return;
+ int res;
- list_for_each_entry(vlan, &bond->vlan_list, vlan_list)
- slave_ops->ndo_vlan_rx_add_vid(slave_dev, vlan->vlan_id);
+ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
+ res = vlan_vid_add(slave_dev, vlan->vlan_id);
+ if (res)
+ pr_warning("%s: Failed to add vlan id %d to device %s\n",
+ bond->dev->name, vlan->vlan_id,
+ slave_dev->name);
+ }
}
static void bond_del_vlans_from_slave(struct bonding *bond,
struct net_device *slave_dev)
{
- const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct vlan_entry *vlan;
- if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
- !(slave_ops->ndo_vlan_rx_kill_vid))
- return;
-
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
if (!vlan->vlan_id)
continue;
- slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
+ vlan_vid_del(slave_dev, vlan->vlan_id);
}
}
return 0;
}
-static u32 bond_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t bond_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct slave *slave;
struct bonding *bond = netdev_priv(dev);
- u32 mask;
+ netdev_features_t mask;
int i;
read_lock(&bond->lock);
{
struct slave *slave;
struct net_device *bond_dev = bond->dev;
- u32 vlan_features = BOND_VLAN_FEATURES;
+ netdev_features_t vlan_features = BOND_VLAN_FEATURES;
unsigned short max_hard_header_len = ETH_HLEN;
int i;
"but new slave device does not support netpoll.\n",
bond_dev->name);
res = -EBUSY;
- goto err_close;
+ goto err_detach;
}
}
#endif
res = bond_create_slave_symlinks(bond_dev, slave_dev);
if (res)
- goto err_close;
+ goto err_detach;
res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
new_slave);
err_dest_symlinks:
bond_destroy_slave_symlinks(bond_dev, slave_dev);
+err_detach:
+ write_lock_bh(&bond->lock);
+ bond_detach_slave(bond, new_slave);
+ write_unlock_bh(&bond->lock);
+
err_close:
dev_close(slave_dev);
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr addr;
- u32 old_features = bond_dev->features;
+ netdev_features_t old_features = bond_dev->features;
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
}
}
-static __be32 bond_glean_dev_ip(struct net_device *dev)
-{
- struct in_device *idev;
- struct in_ifaddr *ifa;
- __be32 addr = 0;
-
- if (!dev)
- return 0;
-
- rcu_read_lock();
- idev = __in_dev_get_rcu(dev);
- if (!idev)
- goto out;
-
- ifa = idev->ifa_list;
- if (!ifa)
- goto out;
-
- addr = ifa->ifa_local;
-out:
- rcu_read_unlock();
- return addr;
-}
-
static int bond_has_this_ip(struct bonding *bond, __be32 ip)
{
struct vlan_entry *vlan;
struct bonding *bond;
struct vlan_entry *vlan;
+ /* we only care about primary address */
+ if(ifa->ifa_flags & IFA_F_SECONDARY)
+ return NOTIFY_DONE;
+
list_for_each_entry(bond, &bn->dev_list, bond_list) {
if (bond->dev == event_dev) {
switch (event) {
bond->master_ip = ifa->ifa_local;
return NOTIFY_OK;
case NETDEV_DOWN:
- bond->master_ip = bond_glean_dev_ip(bond->dev);
+ bond->master_ip = 0;
return NOTIFY_OK;
default:
return NOTIFY_DONE;
vlan->vlan_ip = ifa->ifa_local;
return NOTIFY_OK;
case NETDEV_DOWN:
- vlan->vlan_ip =
- bond_glean_dev_ip(vlan_dev);
+ vlan->vlan_ip = 0;
return NOTIFY_OK;
default:
return NOTIFY_DONE;
NETIF_F_HW_VLAN_RX |
NETIF_F_HW_VLAN_FILTER;
- bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM);
+ bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM);
bond_dev->features |= bond_dev->hw_features;
}
goto out;
}
+ if (bond->slave_cnt > 0) {
+ pr_err("unable to update mode of %s because it has slaves.\n",
+ bond->dev->name);
+ ret = -EPERM;
+ goto out;
+ }
+
new_value = bond_parse_parm(buf, bond_mode_tbl);
if (new_value < 0) {
pr_err("%s: Ignoring invalid mode value %.*s.\n",
dev_dbg(&cfhsi->ndev->dev, "%s.\n",
__func__);
-
- ret = cfhsi->dev->cfhsi_wake_up(cfhsi->dev);
- if (ret) {
- dev_warn(&cfhsi->ndev->dev,
- "%s: can't wake up HSI interface: %d.\n",
- __func__, ret);
- return ret;
- }
-
do {
ret = cfhsi->dev->cfhsi_fifo_occupancy(cfhsi->dev,
&fifo_occupancy);
}
} while (1);
- cfhsi->dev->cfhsi_wake_down(cfhsi->dev);
-
return ret;
}
/* Create HSI frame. */
len = cfhsi_tx_frm(desc, cfhsi);
- BUG_ON(!len);
+ WARN_ON(!len);
/* Set up new transfer. */
res = cfhsi->dev->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->dev);
/*This list is protected by the rtnl lock. */
static LIST_HEAD(ser_list);
-static int ser_loop;
+static bool ser_loop;
module_param(ser_loop, bool, S_IRUGO);
MODULE_PARM_DESC(ser_loop, "Run in simulated loopback mode.");
-static int ser_use_stx = 1;
+static bool ser_use_stx = true;
module_param(ser_use_stx, bool, S_IRUGO);
MODULE_PARM_DESC(ser_use_stx, "STX enabled or not.");
-static int ser_use_fcs = 1;
+static bool ser_use_fcs = true;
module_param(ser_use_fcs, bool, S_IRUGO);
MODULE_PARM_DESC(ser_use_fcs, "FCS enabled or not.");
skb_pull(skb, tty_wr);
if (skb->len == 0) {
struct sk_buff *tmp = skb_dequeue(&ser->head);
- BUG_ON(tmp != skb);
+ WARN_ON(tmp != skb);
if (in_interrupt())
dev_kfree_skb_irq(skb);
else
ser = tty->disc_data;
BUG_ON(ser == NULL);
- BUG_ON(ser->tty != tty);
+ WARN_ON(ser->tty != tty);
handle_tx(ser);
}
if ((avail_emptybuff > HIGH_WATERMARK) &&
(!pshm_drv->tx_empty_available)) {
pshm_drv->tx_empty_available = 1;
+ spin_unlock_irqrestore(&pshm_drv->lock, flags);
pshm_drv->cfdev.flowctrl
(pshm_drv->pshm_dev->pshm_netdev,
CAIF_FLOW_ON);
- spin_unlock_irqrestore(&pshm_drv->lock, flags);
/* Schedule the work queue. if required */
if (!work_pending(&pshm_drv->shm_tx_work))
list_entry(pshm_drv->rx_full_list.next, struct buf_list,
list);
list_del_init(&pbuf->list);
+ spin_unlock_irqrestore(&pshm_drv->lock, flags);
/* Retrieve pointer to start of the packet descriptor area. */
pck_desc = (struct shm_pck_desc *) pbuf->desc_vptr;
/* Get a suitable CAIF packet and copy in data. */
skb = netdev_alloc_skb(pshm_drv->pshm_dev->pshm_netdev,
frm_pck_len + 1);
- BUG_ON(skb == NULL);
+
+ if (skb == NULL) {
+ pr_info("OOM: Try next frame in descriptor\n");
+ break;
+ }
p = skb_put(skb, frm_pck_len);
memcpy(p, pbuf->desc_vptr + frm_pck_ofs, frm_pck_len);
pck_desc++;
}
+ spin_lock_irqsave(&pshm_drv->lock, flags);
list_add_tail(&pbuf->list, &pshm_drv->rx_pend_list);
spin_unlock_irqrestore(&pshm_drv->lock, flags);
if (skb == NULL)
goto send_msg;
-
/* Check the available no. of buffers in the empty list */
list_for_each(pos, &pshm_drv->tx_empty_list)
avail_emptybuff++;
pshm_drv->tx_empty_available) {
/* Update blocking condition. */
pshm_drv->tx_empty_available = 0;
+ spin_unlock_irqrestore(&pshm_drv->lock, flags);
pshm_drv->cfdev.flowctrl
(pshm_drv->pshm_dev->pshm_netdev,
CAIF_FLOW_OFF);
+ spin_lock_irqsave(&pshm_drv->lock, flags);
}
/*
* We simply return back to the caller if we do not have space
}
skb = skb_dequeue(&pshm_drv->sk_qhead);
+ if (skb == NULL)
+ break;
/* Copy in CAIF frame. */
skb_copy_bits(skb, 0, pbuf->desc_vptr +
pbuf->frm_ofs + SHM_HDR_LEN +
pshm_drv->pshm_dev->pshm_netdev->stats.tx_packets++;
pshm_drv->pshm_dev->pshm_netdev->stats.tx_bytes +=
frmlen;
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
/* Fill in the shared memory packet descriptor area. */
pck_desc = (struct shm_pck_desc *) (pbuf->desc_vptr);
static int shm_netdev_tx(struct sk_buff *skb, struct net_device *shm_netdev)
{
struct shmdrv_layer *pshm_drv;
- unsigned long flags = 0;
pshm_drv = netdev_priv(shm_netdev);
- spin_lock_irqsave(&pshm_drv->lock, flags);
-
skb_queue_tail(&pshm_drv->sk_qhead, skb);
- spin_unlock_irqrestore(&pshm_drv->lock, flags);
-
/* Schedule Tx work queue. for deferred processing of skbs*/
if (!work_pending(&pshm_drv->shm_tx_work))
queue_work(pshm_drv->pshm_tx_workqueue, &pshm_drv->shm_tx_work);
pshm_drv->shm_rx_addr = pshm_dev->shm_base_addr +
(NR_TX_BUF * TX_BUF_SZ);
+ spin_lock_init(&pshm_drv->lock);
INIT_LIST_HEAD(&pshm_drv->tx_empty_list);
INIT_LIST_HEAD(&pshm_drv->tx_pend_list);
INIT_LIST_HEAD(&pshm_drv->tx_full_list);
tx_buf->frm_ofs = SHM_CAIF_FRM_OFS;
if (pshm_dev->shm_loopback)
- tx_buf->desc_vptr = (char *)tx_buf->phy_addr;
+ tx_buf->desc_vptr = (unsigned char *)tx_buf->phy_addr;
else
tx_buf->desc_vptr =
ioremap(tx_buf->phy_addr, TX_BUF_SZ);
rx_buf->len = RX_BUF_SZ;
if (pshm_dev->shm_loopback)
- rx_buf->desc_vptr = (char *)rx_buf->phy_addr;
+ rx_buf->desc_vptr = (unsigned char *)rx_buf->phy_addr;
else
rx_buf->desc_vptr =
ioremap(rx_buf->phy_addr, RX_BUF_SZ);
/* Returns the number of padding bytes for alignment. */
#define PAD_POW2(x, pow) ((((x)&((pow)-1))==0) ? 0 : (((pow)-((x)&((pow)-1)))))
-static int spi_loop;
+static bool spi_loop;
module_param(spi_loop, bool, S_IRUGO);
MODULE_PARM_DESC(spi_loop, "SPI running in loopback mode.");
"Tx data (Len: %d):\n", cfspi->tx_cpck_len);
len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
- cfspi->xfer.va_tx,
+ cfspi->xfer.va_tx[0],
(cfspi->tx_cpck_len + SPI_CMD_SZ), 100);
len += snprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
netif_stop_queue(dev);
return 0;
}
-static const struct net_device_ops cfspi_ops = {
- .ndo_open = cfspi_open,
- .ndo_stop = cfspi_close,
- .ndo_start_xmit = cfspi_xmit
-};
-static void cfspi_setup(struct net_device *dev)
+static int cfspi_init(struct net_device *dev)
{
+ int res = 0;
struct cfspi *cfspi = netdev_priv(dev);
- dev->features = 0;
- dev->netdev_ops = &cfspi_ops;
- dev->type = ARPHRD_CAIF;
- dev->flags = IFF_NOARP | IFF_POINTOPOINT;
- dev->tx_queue_len = 0;
- dev->mtu = SPI_MAX_PAYLOAD_SIZE;
- dev->destructor = free_netdev;
- skb_queue_head_init(&cfspi->qhead);
- skb_queue_head_init(&cfspi->chead);
- cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
- cfspi->cfdev.use_frag = false;
- cfspi->cfdev.use_stx = false;
- cfspi->cfdev.use_fcs = false;
- cfspi->ndev = dev;
-}
-
-int cfspi_spi_probe(struct platform_device *pdev)
-{
- struct cfspi *cfspi = NULL;
- struct net_device *ndev;
- struct cfspi_dev *dev;
- int res;
- dev = (struct cfspi_dev *)pdev->dev.platform_data;
-
- ndev = alloc_netdev(sizeof(struct cfspi),
- "cfspi%d", cfspi_setup);
- if (!ndev)
- return -ENOMEM;
-
- cfspi = netdev_priv(ndev);
- netif_stop_queue(ndev);
- cfspi->ndev = ndev;
- cfspi->pdev = pdev;
/* Set flow info. */
cfspi->flow_off_sent = 0;
cfspi->slave_talked = false;
}
- /* Assign the SPI device. */
- cfspi->dev = dev;
- /* Assign the device ifc to this SPI interface. */
- dev->ifc = &cfspi->ifc;
-
/* Allocate DMA buffers. */
- cfspi->xfer.va_tx = dma_alloc(&cfspi->xfer.pa_tx);
- if (!cfspi->xfer.va_tx) {
+ cfspi->xfer.va_tx[0] = dma_alloc(&cfspi->xfer.pa_tx[0]);
+ if (!cfspi->xfer.va_tx[0]) {
res = -ENODEV;
- goto err_dma_alloc_tx;
+ goto err_dma_alloc_tx_0;
}
cfspi->xfer.va_rx = dma_alloc(&cfspi->xfer.pa_rx);
/* Schedule the work queue. */
queue_work(cfspi->wq, &cfspi->work);
+ return 0;
+
+ err_create_wq:
+ dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
+ err_dma_alloc_rx:
+ dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
+ err_dma_alloc_tx_0:
+ return res;
+}
+
+static void cfspi_uninit(struct net_device *dev)
+{
+ struct cfspi *cfspi = netdev_priv(dev);
+
+ /* Remove from list. */
+ spin_lock(&cfspi_list_lock);
+ list_del(&cfspi->list);
+ spin_unlock(&cfspi_list_lock);
+
+ cfspi->ndev = NULL;
+ /* Free DMA buffers. */
+ dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
+ dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
+ set_bit(SPI_TERMINATE, &cfspi->state);
+ wake_up_interruptible(&cfspi->wait);
+ destroy_workqueue(cfspi->wq);
+ /* Destroy debugfs directory and files. */
+ dev_debugfs_rem(cfspi);
+ return;
+}
+
+static const struct net_device_ops cfspi_ops = {
+ .ndo_open = cfspi_open,
+ .ndo_stop = cfspi_close,
+ .ndo_init = cfspi_init,
+ .ndo_uninit = cfspi_uninit,
+ .ndo_start_xmit = cfspi_xmit
+};
+
+static void cfspi_setup(struct net_device *dev)
+{
+ struct cfspi *cfspi = netdev_priv(dev);
+ dev->features = 0;
+ dev->netdev_ops = &cfspi_ops;
+ dev->type = ARPHRD_CAIF;
+ dev->flags = IFF_NOARP | IFF_POINTOPOINT;
+ dev->tx_queue_len = 0;
+ dev->mtu = SPI_MAX_PAYLOAD_SIZE;
+ dev->destructor = free_netdev;
+ skb_queue_head_init(&cfspi->qhead);
+ skb_queue_head_init(&cfspi->chead);
+ cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
+ cfspi->cfdev.use_frag = false;
+ cfspi->cfdev.use_stx = false;
+ cfspi->cfdev.use_fcs = false;
+ cfspi->ndev = dev;
+}
+
+int cfspi_spi_probe(struct platform_device *pdev)
+{
+ struct cfspi *cfspi = NULL;
+ struct net_device *ndev;
+ struct cfspi_dev *dev;
+ int res;
+ dev = (struct cfspi_dev *)pdev->dev.platform_data;
+
+ ndev = alloc_netdev(sizeof(struct cfspi),
+ "cfspi%d", cfspi_setup);
+ if (!dev)
+ return -ENODEV;
+
+ cfspi = netdev_priv(ndev);
+ netif_stop_queue(ndev);
+ cfspi->ndev = ndev;
+ cfspi->pdev = pdev;
+
+ /* Assign the SPI device. */
+ cfspi->dev = dev;
+ /* Assign the device ifc to this SPI interface. */
+ dev->ifc = &cfspi->ifc;
+
/* Register network device. */
res = register_netdev(ndev);
if (res) {
return res;
err_net_reg:
- dev_debugfs_rem(cfspi);
- set_bit(SPI_TERMINATE, &cfspi->state);
- wake_up_interruptible(&cfspi->wait);
- destroy_workqueue(cfspi->wq);
- err_create_wq:
- dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
- err_dma_alloc_rx:
- dma_free(cfspi->xfer.va_tx, cfspi->xfer.pa_tx);
- err_dma_alloc_tx:
free_netdev(ndev);
return res;
int cfspi_spi_remove(struct platform_device *pdev)
{
- struct list_head *list_node;
- struct list_head *n;
- struct cfspi *cfspi = NULL;
- struct cfspi_dev *dev;
-
- dev = (struct cfspi_dev *)pdev->dev.platform_data;
- spin_lock(&cfspi_list_lock);
- list_for_each_safe(list_node, n, &cfspi_list) {
- cfspi = list_entry(list_node, struct cfspi, list);
- /* Find the corresponding device. */
- if (cfspi->dev == dev) {
- /* Remove from list. */
- list_del(list_node);
- /* Free DMA buffers. */
- dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
- dma_free(cfspi->xfer.va_tx, cfspi->xfer.pa_tx);
- set_bit(SPI_TERMINATE, &cfspi->state);
- wake_up_interruptible(&cfspi->wait);
- destroy_workqueue(cfspi->wq);
- /* Destroy debugfs directory and files. */
- dev_debugfs_rem(cfspi);
- unregister_netdev(cfspi->ndev);
- spin_unlock(&cfspi_list_lock);
- return 0;
- }
- }
- spin_unlock(&cfspi_list_lock);
- return -ENODEV;
+ /* Everything is done in cfspi_uninit(). */
+ return 0;
}
static void __exit cfspi_exit_module(void)
list_for_each_safe(list_node, n, &cfspi_list) {
cfspi = list_entry(list_node, struct cfspi, list);
- platform_device_unregister(cfspi->pdev);
+ unregister_netdev(cfspi->ndev);
}
/* Destroy sysfs files. */
source "drivers/net/can/c_can/Kconfig"
+source "drivers/net/can/cc770/Kconfig"
+
source "drivers/net/can/usb/Kconfig"
source "drivers/net/can/softing/Kconfig"
obj-$(CONFIG_CAN_SJA1000) += sja1000/
obj-$(CONFIG_CAN_MSCAN) += mscan/
obj-$(CONFIG_CAN_C_CAN) += c_can/
+obj-$(CONFIG_CAN_CC770) += cc770/
obj-$(CONFIG_CAN_AT91) += at91_can.o
obj-$(CONFIG_CAN_TI_HECC) += ti_hecc.o
obj-$(CONFIG_CAN_MCP251X) += mcp251x.o
.id_table = at91_can_id_table,
};
-static int __init at91_can_module_init(void)
-{
- return platform_driver_register(&at91_can_driver);
-}
-
-static void __exit at91_can_module_exit(void)
-{
- platform_driver_unregister(&at91_can_driver);
-}
-
-module_init(at91_can_module_init);
-module_exit(at91_can_module_exit);
+module_platform_driver(at91_can_driver);
MODULE_AUTHOR("Marc Kleine-Budde <mkl@pengutronix.de>");
MODULE_LICENSE("GPL v2");
},
};
-static int __init bfin_can_init(void)
-{
- return platform_driver_register(&bfin_can_driver);
-}
-module_init(bfin_can_init);
-
-static void __exit bfin_can_exit(void)
-{
- platform_driver_unregister(&bfin_can_driver);
-}
-module_exit(bfin_can_exit);
+module_platform_driver(bfin_can_driver);
MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>");
MODULE_LICENSE("GPL");
.remove = __devexit_p(c_can_plat_remove),
};
-static int __init c_can_plat_init(void)
-{
- return platform_driver_register(&c_can_plat_driver);
-}
-module_init(c_can_plat_init);
-
-static void __exit c_can_plat_exit(void)
-{
- platform_driver_unregister(&c_can_plat_driver);
-}
-module_exit(c_can_plat_exit);
+module_platform_driver(c_can_plat_driver);
MODULE_AUTHOR("Bhupesh Sharma <bhupesh.sharma@st.com>");
MODULE_LICENSE("GPL v2");
--- /dev/null
+menuconfig CAN_CC770
+ tristate "Bosch CC770 and Intel AN82527 devices"
+ depends on CAN_DEV && HAS_IOMEM
+
+if CAN_CC770
+
+config CAN_CC770_ISA
+ tristate "ISA Bus based legacy CC770 driver"
+ ---help---
+ This driver adds legacy support for CC770 and AN82527 chips
+ connected to the ISA bus using I/O port, memory mapped or
+ indirect access.
+
+config CAN_CC770_PLATFORM
+ tristate "Generic Platform Bus based CC770 driver"
+ ---help---
+ This driver adds support for the CC770 and AN82527 chips
+ connected to the "platform bus" (Linux abstraction for directly
+ to the processor attached devices).
+
+endif
--- /dev/null
+#
+# Makefile for the Bosch CC770 CAN controller drivers.
+#
+
+obj-$(CONFIG_CAN_CC770) += cc770.o
+obj-$(CONFIG_CAN_CC770_ISA) += cc770_isa.o
+obj-$(CONFIG_CAN_CC770_PLATFORM) += cc770_platform.o
+
+ccflags-$(CONFIG_CAN_DEBUG_DEVICES) := -DDEBUG
--- /dev/null
+/*
+ * Core driver for the CC770 and AN82527 CAN controllers
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/skbuff.h>
+#include <linux/delay.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION(KBUILD_MODNAME "CAN netdevice driver");
+
+/*
+ * The CC770 is a CAN controller from Bosch, which is 100% compatible
+ * with the AN82527 from Intel, but with "bugs" being fixed and some
+ * additional functionality, mainly:
+ *
+ * 1. RX and TX error counters are readable.
+ * 2. Support of silent (listen-only) mode.
+ * 3. Message object 15 can receive all types of frames, also RTR and EFF.
+ *
+ * Details are available from Bosch's "CC770_Product_Info_2007-01.pdf",
+ * which explains in detail the compatibility between the CC770 and the
+ * 82527. This driver use the additional functionality 3. on real CC770
+ * devices. Unfortunately, the CC770 does still not store the message
+ * identifier of received remote transmission request frames and
+ * therefore it's set to 0.
+ *
+ * The message objects 1..14 can be used for TX and RX while the message
+ * objects 15 is optimized for RX. It has a shadow register for reliable
+ * data receiption under heavy bus load. Therefore it makes sense to use
+ * this message object for the needed use case. The frame type (EFF/SFF)
+ * for the message object 15 can be defined via kernel module parameter
+ * "msgobj15_eff". If not equal 0, it will receive 29-bit EFF frames,
+ * otherwise 11 bit SFF messages.
+ */
+static int msgobj15_eff;
+module_param(msgobj15_eff, int, S_IRUGO);
+MODULE_PARM_DESC(msgobj15_eff, "Extended 29-bit frames for message object 15 "
+ "(default: 11-bit standard frames)");
+
+static int i82527_compat;
+module_param(i82527_compat, int, S_IRUGO);
+MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 comptibility mode "
+ "without using additional functions");
+
+/*
+ * This driver uses the last 5 message objects 11..15. The definitions
+ * and structure below allows to configure and assign them to the real
+ * message object.
+ */
+static unsigned char cc770_obj_flags[CC770_OBJ_MAX] = {
+ [CC770_OBJ_RX0] = CC770_OBJ_FLAG_RX,
+ [CC770_OBJ_RX1] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_EFF,
+ [CC770_OBJ_RX_RTR0] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_RTR,
+ [CC770_OBJ_RX_RTR1] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_RTR |
+ CC770_OBJ_FLAG_EFF,
+ [CC770_OBJ_TX] = 0,
+};
+
+static struct can_bittiming_const cc770_bittiming_const = {
+ .name = KBUILD_MODNAME,
+ .tseg1_min = 1,
+ .tseg1_max = 16,
+ .tseg2_min = 1,
+ .tseg2_max = 8,
+ .sjw_max = 4,
+ .brp_min = 1,
+ .brp_max = 64,
+ .brp_inc = 1,
+};
+
+static inline int intid2obj(unsigned int intid)
+{
+ if (intid == 2)
+ return 0;
+ else
+ return MSGOBJ_LAST + 2 - intid;
+}
+
+static void enable_all_objs(const struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ u8 msgcfg;
+ unsigned char obj_flags;
+ unsigned int o, mo;
+
+ for (o = 0; o < ARRAY_SIZE(priv->obj_flags); o++) {
+ obj_flags = priv->obj_flags[o];
+ mo = obj2msgobj(o);
+
+ if (obj_flags & CC770_OBJ_FLAG_RX) {
+ /*
+ * We don't need extra objects for RTR and EFF if
+ * the additional CC770 functions are enabled.
+ */
+ if (priv->control_normal_mode & CTRL_EAF) {
+ if (o > 0)
+ continue;
+ netdev_dbg(dev, "Message object %d for "
+ "RX data, RTR, SFF and EFF\n", mo);
+ } else {
+ netdev_dbg(dev,
+ "Message object %d for RX %s %s\n",
+ mo, obj_flags & CC770_OBJ_FLAG_RTR ?
+ "RTR" : "data",
+ obj_flags & CC770_OBJ_FLAG_EFF ?
+ "EFF" : "SFF");
+ }
+
+ if (obj_flags & CC770_OBJ_FLAG_EFF)
+ msgcfg = MSGCFG_XTD;
+ else
+ msgcfg = 0;
+ if (obj_flags & CC770_OBJ_FLAG_RTR)
+ msgcfg |= MSGCFG_DIR;
+
+ cc770_write_reg(priv, msgobj[mo].config, msgcfg);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_SET | TXIE_RES |
+ RXIE_SET | INTPND_RES);
+
+ if (obj_flags & CC770_OBJ_FLAG_RTR)
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | CPUUPD_SET |
+ TXRQST_RES | RMTPND_RES);
+ else
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | MSGLST_RES |
+ TXRQST_RES | RMTPND_RES);
+ } else {
+ netdev_dbg(dev, "Message object %d for "
+ "TX data, RTR, SFF and EFF\n", mo);
+
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ RMTPND_RES | TXRQST_RES |
+ CPUUPD_RES | NEWDAT_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_RES | TXIE_RES |
+ RXIE_RES | INTPND_RES);
+ }
+ }
+}
+
+static void disable_all_objs(const struct cc770_priv *priv)
+{
+ int o, mo;
+
+ for (o = 0; o < ARRAY_SIZE(priv->obj_flags); o++) {
+ mo = obj2msgobj(o);
+
+ if (priv->obj_flags[o] & CC770_OBJ_FLAG_RX) {
+ if (o > 0 && priv->control_normal_mode & CTRL_EAF)
+ continue;
+
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | MSGLST_RES |
+ TXRQST_RES | RMTPND_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_RES | TXIE_RES |
+ RXIE_RES | INTPND_RES);
+ } else {
+ /* Clear message object for send */
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ RMTPND_RES | TXRQST_RES |
+ CPUUPD_RES | NEWDAT_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_RES | TXIE_RES |
+ RXIE_RES | INTPND_RES);
+ }
+ }
+}
+
+static void set_reset_mode(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+
+ /* Enable configuration and puts chip in bus-off, disable interrupts */
+ cc770_write_reg(priv, control, CTRL_CCE | CTRL_INI);
+
+ priv->can.state = CAN_STATE_STOPPED;
+
+ /* Clear interrupts */
+ cc770_read_reg(priv, interrupt);
+
+ /* Clear status register */
+ cc770_write_reg(priv, status, 0);
+
+ /* Disable all used message objects */
+ disable_all_objs(priv);
+}
+
+static void set_normal_mode(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+
+ /* Clear interrupts */
+ cc770_read_reg(priv, interrupt);
+
+ /* Clear status register and pre-set last error code */
+ cc770_write_reg(priv, status, STAT_LEC_MASK);
+
+ /* Enable all used message objects*/
+ enable_all_objs(dev);
+
+ /*
+ * Clear bus-off, interrupts only for errors,
+ * not for status change
+ */
+ cc770_write_reg(priv, control, priv->control_normal_mode);
+
+ priv->can.state = CAN_STATE_ERROR_ACTIVE;
+}
+
+static void chipset_init(struct cc770_priv *priv)
+{
+ int mo, id, data;
+
+ /* Enable configuration and put chip in bus-off, disable interrupts */
+ cc770_write_reg(priv, control, (CTRL_CCE | CTRL_INI));
+
+ /* Set CLKOUT divider and slew rates */
+ cc770_write_reg(priv, clkout, priv->clkout);
+
+ /* Configure CPU interface / CLKOUT enable */
+ cc770_write_reg(priv, cpu_interface, priv->cpu_interface);
+
+ /* Set bus configuration */
+ cc770_write_reg(priv, bus_config, priv->bus_config);
+
+ /* Clear interrupts */
+ cc770_read_reg(priv, interrupt);
+
+ /* Clear status register */
+ cc770_write_reg(priv, status, 0);
+
+ /* Clear and invalidate message objects */
+ for (mo = MSGOBJ_FIRST; mo <= MSGOBJ_LAST; mo++) {
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ INTPND_UNC | RXIE_RES |
+ TXIE_RES | MSGVAL_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ INTPND_RES | RXIE_RES |
+ TXIE_RES | MSGVAL_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | MSGLST_RES |
+ TXRQST_RES | RMTPND_RES);
+ for (data = 0; data < 8; data++)
+ cc770_write_reg(priv, msgobj[mo].data[data], 0);
+ for (id = 0; id < 4; id++)
+ cc770_write_reg(priv, msgobj[mo].id[id], 0);
+ cc770_write_reg(priv, msgobj[mo].config, 0);
+ }
+
+ /* Set all global ID masks to "don't care" */
+ cc770_write_reg(priv, global_mask_std[0], 0);
+ cc770_write_reg(priv, global_mask_std[1], 0);
+ cc770_write_reg(priv, global_mask_ext[0], 0);
+ cc770_write_reg(priv, global_mask_ext[1], 0);
+ cc770_write_reg(priv, global_mask_ext[2], 0);
+ cc770_write_reg(priv, global_mask_ext[3], 0);
+
+}
+
+static int cc770_probe_chip(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+
+ /* Enable configuration, put chip in bus-off, disable ints */
+ cc770_write_reg(priv, control, CTRL_CCE | CTRL_EAF | CTRL_INI);
+ /* Configure cpu interface / CLKOUT disable */
+ cc770_write_reg(priv, cpu_interface, priv->cpu_interface);
+
+ /*
+ * Check if hardware reset is still inactive or maybe there
+ * is no chip in this address space
+ */
+ if (cc770_read_reg(priv, cpu_interface) & CPUIF_RST) {
+ netdev_info(dev, "probing @0x%p failed (reset)\n",
+ priv->reg_base);
+ return -ENODEV;
+ }
+
+ /* Write and read back test pattern (some arbitrary values) */
+ cc770_write_reg(priv, msgobj[1].data[1], 0x25);
+ cc770_write_reg(priv, msgobj[2].data[3], 0x52);
+ cc770_write_reg(priv, msgobj[10].data[6], 0xc3);
+ if ((cc770_read_reg(priv, msgobj[1].data[1]) != 0x25) ||
+ (cc770_read_reg(priv, msgobj[2].data[3]) != 0x52) ||
+ (cc770_read_reg(priv, msgobj[10].data[6]) != 0xc3)) {
+ netdev_info(dev, "probing @0x%p failed (pattern)\n",
+ priv->reg_base);
+ return -ENODEV;
+ }
+
+ /* Check if this chip is a CC770 supporting additional functions */
+ if (cc770_read_reg(priv, control) & CTRL_EAF)
+ priv->control_normal_mode |= CTRL_EAF;
+
+ return 0;
+}
+
+static void cc770_start(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+
+ /* leave reset mode */
+ if (priv->can.state != CAN_STATE_STOPPED)
+ set_reset_mode(dev);
+
+ /* leave reset mode */
+ set_normal_mode(dev);
+}
+
+static int cc770_set_mode(struct net_device *dev, enum can_mode mode)
+{
+ switch (mode) {
+ case CAN_MODE_START:
+ cc770_start(dev);
+ netif_wake_queue(dev);
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int cc770_set_bittiming(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct can_bittiming *bt = &priv->can.bittiming;
+ u8 btr0, btr1;
+
+ btr0 = ((bt->brp - 1) & 0x3f) | (((bt->sjw - 1) & 0x3) << 6);
+ btr1 = ((bt->prop_seg + bt->phase_seg1 - 1) & 0xf) |
+ (((bt->phase_seg2 - 1) & 0x7) << 4);
+ if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+ btr1 |= 0x80;
+
+ netdev_info(dev, "setting BTR0=0x%02x BTR1=0x%02x\n", btr0, btr1);
+
+ cc770_write_reg(priv, bit_timing_0, btr0);
+ cc770_write_reg(priv, bit_timing_1, btr1);
+
+ return 0;
+}
+
+static int cc770_get_berr_counter(const struct net_device *dev,
+ struct can_berr_counter *bec)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+
+ bec->txerr = cc770_read_reg(priv, tx_error_counter);
+ bec->rxerr = cc770_read_reg(priv, rx_error_counter);
+
+ return 0;
+}
+
+static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ struct can_frame *cf = (struct can_frame *)skb->data;
+ unsigned int mo = obj2msgobj(CC770_OBJ_TX);
+ u8 dlc, rtr;
+ u32 id;
+ int i;
+
+ if (can_dropped_invalid_skb(dev, skb))
+ return NETDEV_TX_OK;
+
+ if ((cc770_read_reg(priv,
+ msgobj[mo].ctrl1) & TXRQST_UNC) == TXRQST_SET) {
+ netdev_err(dev, "TX register is still occupied!\n");
+ return NETDEV_TX_BUSY;
+ }
+
+ netif_stop_queue(dev);
+
+ dlc = cf->can_dlc;
+ id = cf->can_id;
+ if (cf->can_id & CAN_RTR_FLAG)
+ rtr = 0;
+ else
+ rtr = MSGCFG_DIR;
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ RMTPND_RES | TXRQST_RES | CPUUPD_SET | NEWDAT_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_SET | TXIE_SET | RXIE_RES | INTPND_RES);
+ if (id & CAN_EFF_FLAG) {
+ id &= CAN_EFF_MASK;
+ cc770_write_reg(priv, msgobj[mo].config,
+ (dlc << 4) | rtr | MSGCFG_XTD);
+ cc770_write_reg(priv, msgobj[mo].id[3], id << 3);
+ cc770_write_reg(priv, msgobj[mo].id[2], id >> 5);
+ cc770_write_reg(priv, msgobj[mo].id[1], id >> 13);
+ cc770_write_reg(priv, msgobj[mo].id[0], id >> 21);
+ } else {
+ id &= CAN_SFF_MASK;
+ cc770_write_reg(priv, msgobj[mo].config, (dlc << 4) | rtr);
+ cc770_write_reg(priv, msgobj[mo].id[0], id >> 3);
+ cc770_write_reg(priv, msgobj[mo].id[1], id << 5);
+ }
+
+ for (i = 0; i < dlc; i++)
+ cc770_write_reg(priv, msgobj[mo].data[i], cf->data[i]);
+
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ RMTPND_RES | TXRQST_SET | CPUUPD_RES | NEWDAT_UNC);
+
+ stats->tx_bytes += dlc;
+
+ can_put_echo_skb(skb, dev, 0);
+
+ /*
+ * HM: We had some cases of repeated IRQs so make sure the
+ * INT is acknowledged I know it's already further up, but
+ * doing again fixed the issue
+ */
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES);
+
+ return NETDEV_TX_OK;
+}
+
+static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ struct can_frame *cf;
+ struct sk_buff *skb;
+ u8 config;
+ u32 id;
+ int i;
+
+ skb = alloc_can_skb(dev, &cf);
+ if (!skb)
+ return;
+
+ config = cc770_read_reg(priv, msgobj[mo].config);
+
+ if (ctrl1 & RMTPND_SET) {
+ /*
+ * Unfortunately, the chip does not store the real message
+ * identifier of the received remote transmission request
+ * frame. Therefore we set it to 0.
+ */
+ cf->can_id = CAN_RTR_FLAG;
+ if (config & MSGCFG_XTD)
+ cf->can_id |= CAN_EFF_FLAG;
+ cf->can_dlc = 0;
+ } else {
+ if (config & MSGCFG_XTD) {
+ id = cc770_read_reg(priv, msgobj[mo].id[3]);
+ id |= cc770_read_reg(priv, msgobj[mo].id[2]) << 8;
+ id |= cc770_read_reg(priv, msgobj[mo].id[1]) << 16;
+ id |= cc770_read_reg(priv, msgobj[mo].id[0]) << 24;
+ id >>= 3;
+ id |= CAN_EFF_FLAG;
+ } else {
+ id = cc770_read_reg(priv, msgobj[mo].id[1]);
+ id |= cc770_read_reg(priv, msgobj[mo].id[0]) << 8;
+ id >>= 5;
+ }
+
+ cf->can_id = id;
+ cf->can_dlc = get_can_dlc((config & 0xf0) >> 4);
+ for (i = 0; i < cf->can_dlc; i++)
+ cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
+ }
+ netif_rx(skb);
+
+ stats->rx_packets++;
+ stats->rx_bytes += cf->can_dlc;
+}
+
+static int cc770_err(struct net_device *dev, u8 status)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ struct can_frame *cf;
+ struct sk_buff *skb;
+ u8 lec;
+
+ netdev_dbg(dev, "status interrupt (%#x)\n", status);
+
+ skb = alloc_can_err_skb(dev, &cf);
+ if (!skb)
+ return -ENOMEM;
+
+ /* Use extended functions of the CC770 */
+ if (priv->control_normal_mode & CTRL_EAF) {
+ cf->data[6] = cc770_read_reg(priv, tx_error_counter);
+ cf->data[7] = cc770_read_reg(priv, rx_error_counter);
+ }
+
+ if (status & STAT_BOFF) {
+ /* Disable interrupts */
+ cc770_write_reg(priv, control, CTRL_INI);
+ cf->can_id |= CAN_ERR_BUSOFF;
+ priv->can.state = CAN_STATE_BUS_OFF;
+ can_bus_off(dev);
+ } else if (status & STAT_WARN) {
+ cf->can_id |= CAN_ERR_CRTL;
+ /* Only the CC770 does show error passive */
+ if (cf->data[7] > 127) {
+ cf->data[1] = CAN_ERR_CRTL_RX_PASSIVE |
+ CAN_ERR_CRTL_TX_PASSIVE;
+ priv->can.state = CAN_STATE_ERROR_PASSIVE;
+ priv->can.can_stats.error_passive++;
+ } else {
+ cf->data[1] = CAN_ERR_CRTL_RX_WARNING |
+ CAN_ERR_CRTL_TX_WARNING;
+ priv->can.state = CAN_STATE_ERROR_WARNING;
+ priv->can.can_stats.error_warning++;
+ }
+ } else {
+ /* Back to error avtive */
+ cf->can_id |= CAN_ERR_PROT;
+ cf->data[2] = CAN_ERR_PROT_ACTIVE;
+ priv->can.state = CAN_STATE_ERROR_ACTIVE;
+ }
+
+ lec = status & STAT_LEC_MASK;
+ if (lec < 7 && lec > 0) {
+ if (lec == STAT_LEC_ACK) {
+ cf->can_id |= CAN_ERR_ACK;
+ } else {
+ cf->can_id |= CAN_ERR_PROT;
+ switch (lec) {
+ case STAT_LEC_STUFF:
+ cf->data[2] |= CAN_ERR_PROT_STUFF;
+ break;
+ case STAT_LEC_FORM:
+ cf->data[2] |= CAN_ERR_PROT_FORM;
+ break;
+ case STAT_LEC_BIT1:
+ cf->data[2] |= CAN_ERR_PROT_BIT1;
+ break;
+ case STAT_LEC_BIT0:
+ cf->data[2] |= CAN_ERR_PROT_BIT0;
+ break;
+ case STAT_LEC_CRC:
+ cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+ break;
+ }
+ }
+ }
+
+ netif_rx(skb);
+
+ stats->rx_packets++;
+ stats->rx_bytes += cf->can_dlc;
+
+ return 0;
+}
+
+static int cc770_status_interrupt(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ u8 status;
+
+ status = cc770_read_reg(priv, status);
+ /* Reset the status register including RXOK and TXOK */
+ cc770_write_reg(priv, status, STAT_LEC_MASK);
+
+ if (status & (STAT_WARN | STAT_BOFF) ||
+ (status & STAT_LEC_MASK) != STAT_LEC_MASK) {
+ cc770_err(dev, status);
+ return status & STAT_BOFF;
+ }
+
+ return 0;
+}
+
+static void cc770_rx_interrupt(struct net_device *dev, unsigned int o)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ unsigned int mo = obj2msgobj(o);
+ u8 ctrl1;
+ int n = CC770_MAX_MSG;
+
+ while (n--) {
+ ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1);
+
+ if (!(ctrl1 & NEWDAT_SET)) {
+ /* Check for RTR if additional functions are enabled */
+ if (priv->control_normal_mode & CTRL_EAF) {
+ if (!(cc770_read_reg(priv, msgobj[mo].ctrl0) &
+ INTPND_SET))
+ break;
+ } else {
+ break;
+ }
+ }
+
+ if (ctrl1 & MSGLST_SET) {
+ stats->rx_over_errors++;
+ stats->rx_errors++;
+ }
+ if (mo < MSGOBJ_LAST)
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | MSGLST_RES |
+ TXRQST_UNC | RMTPND_UNC);
+ cc770_rx(dev, mo, ctrl1);
+
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_SET | TXIE_RES |
+ RXIE_SET | INTPND_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | MSGLST_RES |
+ TXRQST_RES | RMTPND_RES);
+ }
+}
+
+static void cc770_rtr_interrupt(struct net_device *dev, unsigned int o)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ unsigned int mo = obj2msgobj(o);
+ u8 ctrl0, ctrl1;
+ int n = CC770_MAX_MSG;
+
+ while (n--) {
+ ctrl0 = cc770_read_reg(priv, msgobj[mo].ctrl0);
+ if (!(ctrl0 & INTPND_SET))
+ break;
+
+ ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1);
+ cc770_rx(dev, mo, ctrl1);
+
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_SET | TXIE_RES |
+ RXIE_SET | INTPND_RES);
+ cc770_write_reg(priv, msgobj[mo].ctrl1,
+ NEWDAT_RES | CPUUPD_SET |
+ TXRQST_RES | RMTPND_RES);
+ }
+}
+
+static void cc770_tx_interrupt(struct net_device *dev, unsigned int o)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ unsigned int mo = obj2msgobj(o);
+
+ /* Nothing more to send, switch off interrupts */
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_RES | TXIE_RES | RXIE_RES | INTPND_RES);
+ /*
+ * We had some cases of repeated IRQ so make sure the
+ * INT is acknowledged
+ */
+ cc770_write_reg(priv, msgobj[mo].ctrl0,
+ MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES);
+
+ stats->tx_packets++;
+ can_get_echo_skb(dev, 0);
+ netif_wake_queue(dev);
+}
+
+irqreturn_t cc770_interrupt(int irq, void *dev_id)
+{
+ struct net_device *dev = (struct net_device *)dev_id;
+ struct cc770_priv *priv = netdev_priv(dev);
+ u8 intid;
+ int o, n = 0;
+
+ /* Shared interrupts and IRQ off? */
+ if (priv->can.state == CAN_STATE_STOPPED)
+ return IRQ_NONE;
+
+ if (priv->pre_irq)
+ priv->pre_irq(priv);
+
+ while (n < CC770_MAX_IRQ) {
+ /* Read the highest pending interrupt request */
+ intid = cc770_read_reg(priv, interrupt);
+ if (!intid)
+ break;
+ n++;
+
+ if (intid == 1) {
+ /* Exit in case of bus-off */
+ if (cc770_status_interrupt(dev))
+ break;
+ } else {
+ o = intid2obj(intid);
+
+ if (o >= CC770_OBJ_MAX) {
+ netdev_err(dev, "Unexpected interrupt id %d\n",
+ intid);
+ continue;
+ }
+
+ if (priv->obj_flags[o] & CC770_OBJ_FLAG_RTR)
+ cc770_rtr_interrupt(dev, o);
+ else if (priv->obj_flags[o] & CC770_OBJ_FLAG_RX)
+ cc770_rx_interrupt(dev, o);
+ else
+ cc770_tx_interrupt(dev, o);
+ }
+ }
+
+ if (priv->post_irq)
+ priv->post_irq(priv);
+
+ if (n >= CC770_MAX_IRQ)
+ netdev_dbg(dev, "%d messages handled in ISR", n);
+
+ return (n) ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int cc770_open(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ int err;
+
+ /* set chip into reset mode */
+ set_reset_mode(dev);
+
+ /* common open */
+ err = open_candev(dev);
+ if (err)
+ return err;
+
+ err = request_irq(dev->irq, &cc770_interrupt, priv->irq_flags,
+ dev->name, dev);
+ if (err) {
+ close_candev(dev);
+ return -EAGAIN;
+ }
+
+ /* init and start chip */
+ cc770_start(dev);
+
+ netif_start_queue(dev);
+
+ return 0;
+}
+
+static int cc770_close(struct net_device *dev)
+{
+ netif_stop_queue(dev);
+ set_reset_mode(dev);
+
+ free_irq(dev->irq, dev);
+ close_candev(dev);
+
+ return 0;
+}
+
+struct net_device *alloc_cc770dev(int sizeof_priv)
+{
+ struct net_device *dev;
+ struct cc770_priv *priv;
+
+ dev = alloc_candev(sizeof(struct cc770_priv) + sizeof_priv,
+ CC770_ECHO_SKB_MAX);
+ if (!dev)
+ return NULL;
+
+ priv = netdev_priv(dev);
+
+ priv->dev = dev;
+ priv->can.bittiming_const = &cc770_bittiming_const;
+ priv->can.do_set_bittiming = cc770_set_bittiming;
+ priv->can.do_set_mode = cc770_set_mode;
+ priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
+
+ memcpy(priv->obj_flags, cc770_obj_flags, sizeof(cc770_obj_flags));
+
+ if (sizeof_priv)
+ priv->priv = (void *)priv + sizeof(struct cc770_priv);
+
+ return dev;
+}
+EXPORT_SYMBOL_GPL(alloc_cc770dev);
+
+void free_cc770dev(struct net_device *dev)
+{
+ free_candev(dev);
+}
+EXPORT_SYMBOL_GPL(free_cc770dev);
+
+static const struct net_device_ops cc770_netdev_ops = {
+ .ndo_open = cc770_open,
+ .ndo_stop = cc770_close,
+ .ndo_start_xmit = cc770_start_xmit,
+};
+
+int register_cc770dev(struct net_device *dev)
+{
+ struct cc770_priv *priv = netdev_priv(dev);
+ int err;
+
+ err = cc770_probe_chip(dev);
+ if (err)
+ return err;
+
+ dev->netdev_ops = &cc770_netdev_ops;
+
+ dev->flags |= IFF_ECHO; /* we support local echo */
+
+ /* Should we use additional functions? */
+ if (!i82527_compat && priv->control_normal_mode & CTRL_EAF) {
+ priv->can.do_get_berr_counter = cc770_get_berr_counter;
+ priv->control_normal_mode = CTRL_IE | CTRL_EAF | CTRL_EIE;
+ netdev_dbg(dev, "i82527 mode with additional functions\n");
+ } else {
+ priv->control_normal_mode = CTRL_IE | CTRL_EIE;
+ netdev_dbg(dev, "strict i82527 compatibility mode\n");
+ }
+
+ chipset_init(priv);
+ set_reset_mode(dev);
+
+ return register_candev(dev);
+}
+EXPORT_SYMBOL_GPL(register_cc770dev);
+
+void unregister_cc770dev(struct net_device *dev)
+{
+ set_reset_mode(dev);
+ unregister_candev(dev);
+}
+EXPORT_SYMBOL_GPL(unregister_cc770dev);
+
+static __init int cc770_init(void)
+{
+ if (msgobj15_eff) {
+ cc770_obj_flags[CC770_OBJ_RX0] |= CC770_OBJ_FLAG_EFF;
+ cc770_obj_flags[CC770_OBJ_RX1] &= ~CC770_OBJ_FLAG_EFF;
+ }
+
+ pr_info("CAN netdevice driver\n");
+
+ return 0;
+}
+module_init(cc770_init);
+
+static __exit void cc770_exit(void)
+{
+ pr_info("driver removed\n");
+}
+module_exit(cc770_exit);
--- /dev/null
+/*
+ * Core driver for the CC770 and AN82527 CAN controllers
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef CC770_DEV_H
+#define CC770_DEV_H
+
+#include <linux/can/dev.h>
+
+struct cc770_msgobj {
+ u8 ctrl0;
+ u8 ctrl1;
+ u8 id[4];
+ u8 config;
+ u8 data[8];
+ u8 dontuse; /* padding */
+} __packed;
+
+struct cc770_regs {
+ union {
+ struct cc770_msgobj msgobj[16]; /* Message object 1..15 */
+ struct {
+ u8 control; /* Control Register */
+ u8 status; /* Status Register */
+ u8 cpu_interface; /* CPU Interface Register */
+ u8 dontuse1;
+ u8 high_speed_read[2]; /* High Speed Read */
+ u8 global_mask_std[2]; /* Standard Global Mask */
+ u8 global_mask_ext[4]; /* Extended Global Mask */
+ u8 msg15_mask[4]; /* Message 15 Mask */
+ u8 dontuse2[15];
+ u8 clkout; /* Clock Out Register */
+ u8 dontuse3[15];
+ u8 bus_config; /* Bus Configuration Register */
+ u8 dontuse4[15];
+ u8 bit_timing_0; /* Bit Timing Register byte 0 */
+ u8 dontuse5[15];
+ u8 bit_timing_1; /* Bit Timing Register byte 1 */
+ u8 dontuse6[15];
+ u8 interrupt; /* Interrupt Register */
+ u8 dontuse7[15];
+ u8 rx_error_counter; /* Receive Error Counter */
+ u8 dontuse8[15];
+ u8 tx_error_counter; /* Transmit Error Counter */
+ u8 dontuse9[31];
+ u8 p1_conf;
+ u8 dontuse10[15];
+ u8 p2_conf;
+ u8 dontuse11[15];
+ u8 p1_in;
+ u8 dontuse12[15];
+ u8 p2_in;
+ u8 dontuse13[15];
+ u8 p1_out;
+ u8 dontuse14[15];
+ u8 p2_out;
+ u8 dontuse15[15];
+ u8 serial_reset_addr;
+ };
+ };
+} __packed;
+
+/* Control Register (0x00) */
+#define CTRL_INI 0x01 /* Initialization */
+#define CTRL_IE 0x02 /* Interrupt Enable */
+#define CTRL_SIE 0x04 /* Status Interrupt Enable */
+#define CTRL_EIE 0x08 /* Error Interrupt Enable */
+#define CTRL_EAF 0x20 /* Enable additional functions */
+#define CTRL_CCE 0x40 /* Change Configuration Enable */
+
+/* Status Register (0x01) */
+#define STAT_LEC_STUFF 0x01 /* Stuff error */
+#define STAT_LEC_FORM 0x02 /* Form error */
+#define STAT_LEC_ACK 0x03 /* Acknowledgement error */
+#define STAT_LEC_BIT1 0x04 /* Bit1 error */
+#define STAT_LEC_BIT0 0x05 /* Bit0 error */
+#define STAT_LEC_CRC 0x06 /* CRC error */
+#define STAT_LEC_MASK 0x07 /* Last Error Code mask */
+#define STAT_TXOK 0x08 /* Transmit Message Successfully */
+#define STAT_RXOK 0x10 /* Receive Message Successfully */
+#define STAT_WAKE 0x20 /* Wake Up Status */
+#define STAT_WARN 0x40 /* Warning Status */
+#define STAT_BOFF 0x80 /* Bus Off Status */
+
+/*
+ * CPU Interface Register (0x02)
+ * Clock Out Register (0x1f)
+ * Bus Configuration Register (0x2f)
+ *
+ * see include/linux/can/platform/cc770.h
+ */
+
+/* Message Control Register 0 (Base Address + 0x0) */
+#define INTPND_RES 0x01 /* No Interrupt pending */
+#define INTPND_SET 0x02 /* Interrupt pending */
+#define INTPND_UNC 0x03
+#define RXIE_RES 0x04 /* Receive Interrupt Disable */
+#define RXIE_SET 0x08 /* Receive Interrupt Enable */
+#define RXIE_UNC 0x0c
+#define TXIE_RES 0x10 /* Transmit Interrupt Disable */
+#define TXIE_SET 0x20 /* Transmit Interrupt Enable */
+#define TXIE_UNC 0x30
+#define MSGVAL_RES 0x40 /* Message Invalid */
+#define MSGVAL_SET 0x80 /* Message Valid */
+#define MSGVAL_UNC 0xc0
+
+/* Message Control Register 1 (Base Address + 0x01) */
+#define NEWDAT_RES 0x01 /* No New Data */
+#define NEWDAT_SET 0x02 /* New Data */
+#define NEWDAT_UNC 0x03
+#define MSGLST_RES 0x04 /* No Message Lost */
+#define MSGLST_SET 0x08 /* Message Lost */
+#define MSGLST_UNC 0x0c
+#define CPUUPD_RES 0x04 /* No CPU Updating */
+#define CPUUPD_SET 0x08 /* CPU Updating */
+#define CPUUPD_UNC 0x0c
+#define TXRQST_RES 0x10 /* No Transmission Request */
+#define TXRQST_SET 0x20 /* Transmission Request */
+#define TXRQST_UNC 0x30
+#define RMTPND_RES 0x40 /* No Remote Request Pending */
+#define RMTPND_SET 0x80 /* Remote Request Pending */
+#define RMTPND_UNC 0xc0
+
+/* Message Configuration Register (Base Address + 0x06) */
+#define MSGCFG_XTD 0x04 /* Extended Identifier */
+#define MSGCFG_DIR 0x08 /* Direction is Transmit */
+
+#define MSGOBJ_FIRST 1
+#define MSGOBJ_LAST 15
+
+#define CC770_IO_SIZE 0x100
+#define CC770_MAX_IRQ 20 /* max. number of interrupts handled in ISR */
+#define CC770_MAX_MSG 4 /* max. number of messages handled in ISR */
+
+#define CC770_ECHO_SKB_MAX 1
+
+#define cc770_read_reg(priv, member) \
+ priv->read_reg(priv, offsetof(struct cc770_regs, member))
+
+#define cc770_write_reg(priv, member, value) \
+ priv->write_reg(priv, offsetof(struct cc770_regs, member), value)
+
+/*
+ * Message objects and flags used by this driver
+ */
+#define CC770_OBJ_FLAG_RX 0x01
+#define CC770_OBJ_FLAG_RTR 0x02
+#define CC770_OBJ_FLAG_EFF 0x04
+
+enum {
+ CC770_OBJ_RX0 = 0, /* for receiving normal messages */
+ CC770_OBJ_RX1, /* for receiving normal messages */
+ CC770_OBJ_RX_RTR0, /* for receiving remote transmission requests */
+ CC770_OBJ_RX_RTR1, /* for receiving remote transmission requests */
+ CC770_OBJ_TX, /* for sending messages */
+ CC770_OBJ_MAX
+};
+
+#define obj2msgobj(o) (MSGOBJ_LAST - (o)) /* message object 11..15 */
+
+/*
+ * CC770 private data structure
+ */
+struct cc770_priv {
+ struct can_priv can; /* must be the first member */
+ struct sk_buff *echo_skb;
+
+ /* the lower-layer is responsible for appropriate locking */
+ u8 (*read_reg)(const struct cc770_priv *priv, int reg);
+ void (*write_reg)(const struct cc770_priv *priv, int reg, u8 val);
+ void (*pre_irq)(const struct cc770_priv *priv);
+ void (*post_irq)(const struct cc770_priv *priv);
+
+ void *priv; /* for board-specific data */
+ struct net_device *dev;
+
+ void __iomem *reg_base; /* ioremap'ed address to registers */
+ unsigned long irq_flags; /* for request_irq() */
+
+ unsigned char obj_flags[CC770_OBJ_MAX];
+ u8 control_normal_mode; /* Control register for normal mode */
+ u8 cpu_interface; /* CPU interface register */
+ u8 clkout; /* Clock out register */
+ u8 bus_config; /* Bus conffiguration register */
+};
+
+struct net_device *alloc_cc770dev(int sizeof_priv);
+void free_cc770dev(struct net_device *dev);
+int register_cc770dev(struct net_device *dev);
+void unregister_cc770dev(struct net_device *dev);
+
+#endif /* CC770_DEV_H */
--- /dev/null
+/*
+ * Driver for CC770 and AN82527 CAN controllers on the legacy ISA bus
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Bosch CC770 and Intel AN82527 CAN controllers on the ISA or PC-104 bus.
+ * The I/O port or memory address and the IRQ number must be specified via
+ * module parameters:
+ *
+ * insmod cc770_isa.ko port=0x310,0x380 irq=7,11
+ *
+ * for ISA devices using I/O ports or:
+ *
+ * insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11
+ *
+ * for memory mapped ISA devices.
+ *
+ * Indirect access via address and data port is supported as well:
+ *
+ * insmod cc770_isa.ko port=0x310,0x380 indirect=1 irq=7,11
+ *
+ * Furthermore, the following mode parameter can be defined:
+ *
+ * clk: External oscillator clock frequency (default=16000000 [16 MHz])
+ * cir: CPU interface register (default=0x40 [DSC])
+ * bcr: Bus configuration register (default=0x40 [CBY])
+ * cor: Clockout register (default=0x00)
+ *
+ * Note: for clk, cir, bcr and cor, the first argument re-defines the
+ * default for all other devices, e.g.:
+ *
+ * insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11 clk=24000000
+ *
+ * is equivalent to
+ *
+ * insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11 clk=24000000,24000000
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+#define MAXDEV 8
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_DESCRIPTION("Socket-CAN driver for CC770 on the ISA bus");
+MODULE_LICENSE("GPL v2");
+
+#define CLK_DEFAULT 16000000 /* 16 MHz */
+#define COR_DEFAULT 0x00
+#define BCR_DEFAULT BUSCFG_CBY
+
+static unsigned long port[MAXDEV];
+static unsigned long mem[MAXDEV];
+static int __devinitdata irq[MAXDEV];
+static int __devinitdata clk[MAXDEV];
+static u8 __devinitdata cir[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static u8 __devinitdata cor[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static u8 __devinitdata bcr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static int __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
+
+module_param_array(port, ulong, NULL, S_IRUGO);
+MODULE_PARM_DESC(port, "I/O port number");
+
+module_param_array(mem, ulong, NULL, S_IRUGO);
+MODULE_PARM_DESC(mem, "I/O memory address");
+
+module_param_array(indirect, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
+
+module_param_array(irq, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(irq, "IRQ number");
+
+module_param_array(clk, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(clk, "External oscillator clock frequency "
+ "(default=16000000 [16 MHz])");
+
+module_param_array(cir, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(cir, "CPU interface register (default=0x40 [DSC])");
+
+module_param_array(cor, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(cor, "Clockout register (default=0x00)");
+
+module_param_array(bcr, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(bcr, "Bus configuration register (default=0x40 [CBY])");
+
+#define CC770_IOSIZE 0x20
+#define CC770_IOSIZE_INDIRECT 0x02
+
+static struct platform_device *cc770_isa_devs[MAXDEV];
+
+static u8 cc770_isa_mem_read_reg(const struct cc770_priv *priv, int reg)
+{
+ return readb(priv->reg_base + reg);
+}
+
+static void cc770_isa_mem_write_reg(const struct cc770_priv *priv,
+ int reg, u8 val)
+{
+ writeb(val, priv->reg_base + reg);
+}
+
+static u8 cc770_isa_port_read_reg(const struct cc770_priv *priv, int reg)
+{
+ return inb((unsigned long)priv->reg_base + reg);
+}
+
+static void cc770_isa_port_write_reg(const struct cc770_priv *priv,
+ int reg, u8 val)
+{
+ outb(val, (unsigned long)priv->reg_base + reg);
+}
+
+static u8 cc770_isa_port_read_reg_indirect(const struct cc770_priv *priv,
+ int reg)
+{
+ unsigned long base = (unsigned long)priv->reg_base;
+
+ outb(reg, base);
+ return inb(base + 1);
+}
+
+static void cc770_isa_port_write_reg_indirect(const struct cc770_priv *priv,
+ int reg, u8 val)
+{
+ unsigned long base = (unsigned long)priv->reg_base;
+
+ outb(reg, base);
+ outb(val, base + 1);
+}
+
+static int __devinit cc770_isa_probe(struct platform_device *pdev)
+{
+ struct net_device *dev;
+ struct cc770_priv *priv;
+ void __iomem *base = NULL;
+ int iosize = CC770_IOSIZE;
+ int idx = pdev->id;
+ int err;
+ u32 clktmp;
+
+ dev_dbg(&pdev->dev, "probing idx=%d: port=%#lx, mem=%#lx, irq=%d\n",
+ idx, port[idx], mem[idx], irq[idx]);
+ if (mem[idx]) {
+ if (!request_mem_region(mem[idx], iosize, KBUILD_MODNAME)) {
+ err = -EBUSY;
+ goto exit;
+ }
+ base = ioremap_nocache(mem[idx], iosize);
+ if (!base) {
+ err = -ENOMEM;
+ goto exit_release;
+ }
+ } else {
+ if (indirect[idx] > 0 ||
+ (indirect[idx] == -1 && indirect[0] > 0))
+ iosize = CC770_IOSIZE_INDIRECT;
+ if (!request_region(port[idx], iosize, KBUILD_MODNAME)) {
+ err = -EBUSY;
+ goto exit;
+ }
+ }
+
+ dev = alloc_cc770dev(0);
+ if (!dev) {
+ err = -ENOMEM;
+ goto exit_unmap;
+ }
+ priv = netdev_priv(dev);
+
+ dev->irq = irq[idx];
+ priv->irq_flags = IRQF_SHARED;
+ if (mem[idx]) {
+ priv->reg_base = base;
+ dev->base_addr = mem[idx];
+ priv->read_reg = cc770_isa_mem_read_reg;
+ priv->write_reg = cc770_isa_mem_write_reg;
+ } else {
+ priv->reg_base = (void __iomem *)port[idx];
+ dev->base_addr = port[idx];
+
+ if (iosize == CC770_IOSIZE_INDIRECT) {
+ priv->read_reg = cc770_isa_port_read_reg_indirect;
+ priv->write_reg = cc770_isa_port_write_reg_indirect;
+ } else {
+ priv->read_reg = cc770_isa_port_read_reg;
+ priv->write_reg = cc770_isa_port_write_reg;
+ }
+ }
+
+ if (clk[idx])
+ clktmp = clk[idx];
+ else if (clk[0])
+ clktmp = clk[0];
+ else
+ clktmp = CLK_DEFAULT;
+ priv->can.clock.freq = clktmp;
+
+ if (cir[idx] != 0xff) {
+ priv->cpu_interface = cir[idx];
+ } else if (cir[0] != 0xff) {
+ priv->cpu_interface = cir[0];
+ } else {
+ /* The system clock may not exceed 10 MHz */
+ if (clktmp > 10000000) {
+ priv->cpu_interface |= CPUIF_DSC;
+ clktmp /= 2;
+ }
+ /* The memory clock may not exceed 8 MHz */
+ if (clktmp > 8000000)
+ priv->cpu_interface |= CPUIF_DMC;
+ }
+
+ if (priv->cpu_interface & CPUIF_DSC)
+ priv->can.clock.freq /= 2;
+
+ if (bcr[idx] != 0xff)
+ priv->bus_config = bcr[idx];
+ else if (bcr[0] != 0xff)
+ priv->bus_config = bcr[0];
+ else
+ priv->bus_config = BCR_DEFAULT;
+
+ if (cor[idx] != 0xff)
+ priv->clkout = cor[idx];
+ else if (cor[0] != 0xff)
+ priv->clkout = cor[0];
+ else
+ priv->clkout = COR_DEFAULT;
+
+ dev_set_drvdata(&pdev->dev, dev);
+ SET_NETDEV_DEV(dev, &pdev->dev);
+
+ err = register_cc770dev(dev);
+ if (err) {
+ dev_err(&pdev->dev,
+ "couldn't register device (err=%d)\n", err);
+ goto exit_unmap;
+ }
+
+ dev_info(&pdev->dev, "device registered (reg_base=0x%p, irq=%d)\n",
+ priv->reg_base, dev->irq);
+ return 0;
+
+ exit_unmap:
+ if (mem[idx])
+ iounmap(base);
+ exit_release:
+ if (mem[idx])
+ release_mem_region(mem[idx], iosize);
+ else
+ release_region(port[idx], iosize);
+ exit:
+ return err;
+}
+
+static int __devexit cc770_isa_remove(struct platform_device *pdev)
+{
+ struct net_device *dev = dev_get_drvdata(&pdev->dev);
+ struct cc770_priv *priv = netdev_priv(dev);
+ int idx = pdev->id;
+
+ unregister_cc770dev(dev);
+ dev_set_drvdata(&pdev->dev, NULL);
+
+ if (mem[idx]) {
+ iounmap(priv->reg_base);
+ release_mem_region(mem[idx], CC770_IOSIZE);
+ } else {
+ if (priv->read_reg == cc770_isa_port_read_reg_indirect)
+ release_region(port[idx], CC770_IOSIZE_INDIRECT);
+ else
+ release_region(port[idx], CC770_IOSIZE);
+ }
+ free_cc770dev(dev);
+
+ return 0;
+}
+
+static struct platform_driver cc770_isa_driver = {
+ .probe = cc770_isa_probe,
+ .remove = __devexit_p(cc770_isa_remove),
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init cc770_isa_init(void)
+{
+ int idx, err;
+
+ for (idx = 0; idx < ARRAY_SIZE(cc770_isa_devs); idx++) {
+ if ((port[idx] || mem[idx]) && irq[idx]) {
+ cc770_isa_devs[idx] =
+ platform_device_alloc(KBUILD_MODNAME, idx);
+ if (!cc770_isa_devs[idx]) {
+ err = -ENOMEM;
+ goto exit_free_devices;
+ }
+ err = platform_device_add(cc770_isa_devs[idx]);
+ if (err) {
+ platform_device_put(cc770_isa_devs[idx]);
+ goto exit_free_devices;
+ }
+ pr_debug("platform device %d: port=%#lx, mem=%#lx, "
+ "irq=%d\n",
+ idx, port[idx], mem[idx], irq[idx]);
+ } else if (idx == 0 || port[idx] || mem[idx]) {
+ pr_err("insufficient parameters supplied\n");
+ err = -EINVAL;
+ goto exit_free_devices;
+ }
+ }
+
+ err = platform_driver_register(&cc770_isa_driver);
+ if (err)
+ goto exit_free_devices;
+
+ pr_info("driver for max. %d devices registered\n", MAXDEV);
+
+ return 0;
+
+exit_free_devices:
+ while (--idx >= 0) {
+ if (cc770_isa_devs[idx])
+ platform_device_unregister(cc770_isa_devs[idx]);
+ }
+
+ return err;
+}
+module_init(cc770_isa_init);
+
+static void __exit cc770_isa_exit(void)
+{
+ int idx;
+
+ platform_driver_unregister(&cc770_isa_driver);
+ for (idx = 0; idx < ARRAY_SIZE(cc770_isa_devs); idx++) {
+ if (cc770_isa_devs[idx])
+ platform_device_unregister(cc770_isa_devs[idx]);
+ }
+}
+module_exit(cc770_isa_exit);
--- /dev/null
+/*
+ * Driver for CC770 and AN82527 CAN controllers on the platform bus
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * If platform data are used you should have similar definitions
+ * in your board-specific code:
+ *
+ * static struct cc770_platform_data myboard_cc770_pdata = {
+ * .osc_freq = 16000000,
+ * .cir = 0x41,
+ * .cor = 0x20,
+ * .bcr = 0x40,
+ * };
+ *
+ * Please see include/linux/can/platform/cc770.h for description of
+ * above fields.
+ *
+ * If the device tree is used, you need a CAN node definition in your
+ * DTS file similar to:
+ *
+ * can@3,100 {
+ * compatible = "bosch,cc770";
+ * reg = <3 0x100 0x80>;
+ * interrupts = <2 0>;
+ * interrupt-parent = <&mpic>;
+ * bosch,external-clock-frequency = <16000000>;
+ * };
+ *
+ * See "Documentation/devicetree/bindings/net/can/cc770.txt" for further
+ * information.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+#define DRV_NAME "cc770_platform"
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_DESCRIPTION("Socket-CAN driver for CC770 on the platform bus");
+MODULE_LICENSE("GPL v2");
+
+#define CC770_PLATFORM_CAN_CLOCK 16000000
+
+static u8 cc770_platform_read_reg(const struct cc770_priv *priv, int reg)
+{
+ return ioread8(priv->reg_base + reg);
+}
+
+static void cc770_platform_write_reg(const struct cc770_priv *priv, int reg,
+ u8 val)
+{
+ iowrite8(val, priv->reg_base + reg);
+}
+
+static int __devinit cc770_get_of_node_data(struct platform_device *pdev,
+ struct cc770_priv *priv)
+{
+ struct device_node *np = pdev->dev.of_node;
+ const u32 *prop;
+ int prop_size;
+ u32 clkext;
+
+ prop = of_get_property(np, "bosch,external-clock-frequency",
+ &prop_size);
+ if (prop && (prop_size == sizeof(u32)))
+ clkext = *prop;
+ else
+ clkext = CC770_PLATFORM_CAN_CLOCK; /* default */
+ priv->can.clock.freq = clkext;
+
+ /* The system clock may not exceed 10 MHz */
+ if (priv->can.clock.freq > 10000000) {
+ priv->cpu_interface |= CPUIF_DSC;
+ priv->can.clock.freq /= 2;
+ }
+
+ /* The memory clock may not exceed 8 MHz */
+ if (priv->can.clock.freq > 8000000)
+ priv->cpu_interface |= CPUIF_DMC;
+
+ if (of_get_property(np, "bosch,divide-memory-clock", NULL))
+ priv->cpu_interface |= CPUIF_DMC;
+ if (of_get_property(np, "bosch,iso-low-speed-mux", NULL))
+ priv->cpu_interface |= CPUIF_MUX;
+
+ if (!of_get_property(np, "bosch,no-comperator-bypass", NULL))
+ priv->bus_config |= BUSCFG_CBY;
+ if (of_get_property(np, "bosch,disconnect-rx0-input", NULL))
+ priv->bus_config |= BUSCFG_DR0;
+ if (of_get_property(np, "bosch,disconnect-rx1-input", NULL))
+ priv->bus_config |= BUSCFG_DR1;
+ if (of_get_property(np, "bosch,disconnect-tx1-output", NULL))
+ priv->bus_config |= BUSCFG_DT1;
+ if (of_get_property(np, "bosch,polarity-dominant", NULL))
+ priv->bus_config |= BUSCFG_POL;
+
+ prop = of_get_property(np, "bosch,clock-out-frequency", &prop_size);
+ if (prop && (prop_size == sizeof(u32)) && *prop > 0) {
+ u32 cdv = clkext / *prop;
+ int slew;
+
+ if (cdv > 0 && cdv < 16) {
+ priv->cpu_interface |= CPUIF_CEN;
+ priv->clkout |= (cdv - 1) & CLKOUT_CD_MASK;
+
+ prop = of_get_property(np, "bosch,slew-rate",
+ &prop_size);
+ if (prop && (prop_size == sizeof(u32))) {
+ slew = *prop;
+ } else {
+ /* Determine default slew rate */
+ slew = (CLKOUT_SL_MASK >>
+ CLKOUT_SL_SHIFT) -
+ ((cdv * clkext - 1) / 8000000);
+ if (slew < 0)
+ slew = 0;
+ }
+ priv->clkout |= (slew << CLKOUT_SL_SHIFT) &
+ CLKOUT_SL_MASK;
+ } else {
+ dev_dbg(&pdev->dev, "invalid clock-out-frequency\n");
+ }
+ }
+
+ return 0;
+}
+
+static int __devinit cc770_get_platform_data(struct platform_device *pdev,
+ struct cc770_priv *priv)
+{
+
+ struct cc770_platform_data *pdata = pdev->dev.platform_data;
+
+ priv->can.clock.freq = pdata->osc_freq;
+ if (priv->cpu_interface | CPUIF_DSC)
+ priv->can.clock.freq /= 2;
+ priv->clkout = pdata->cor;
+ priv->bus_config = pdata->bcr;
+ priv->cpu_interface = pdata->cir;
+
+ return 0;
+}
+
+static int __devinit cc770_platform_probe(struct platform_device *pdev)
+{
+ struct net_device *dev;
+ struct cc770_priv *priv;
+ struct resource *mem;
+ resource_size_t mem_size;
+ void __iomem *base;
+ int err, irq;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ irq = platform_get_irq(pdev, 0);
+ if (!mem || irq <= 0)
+ return -ENODEV;
+
+ mem_size = resource_size(mem);
+ if (!request_mem_region(mem->start, mem_size, pdev->name))
+ return -EBUSY;
+
+ base = ioremap(mem->start, mem_size);
+ if (!base) {
+ err = -ENOMEM;
+ goto exit_release_mem;
+ }
+
+ dev = alloc_cc770dev(0);
+ if (!dev) {
+ err = -ENOMEM;
+ goto exit_unmap_mem;
+ }
+
+ dev->irq = irq;
+ priv = netdev_priv(dev);
+ priv->read_reg = cc770_platform_read_reg;
+ priv->write_reg = cc770_platform_write_reg;
+ priv->irq_flags = IRQF_SHARED;
+ priv->reg_base = base;
+
+ if (pdev->dev.of_node)
+ err = cc770_get_of_node_data(pdev, priv);
+ else if (pdev->dev.platform_data)
+ err = cc770_get_platform_data(pdev, priv);
+ else
+ err = -ENODEV;
+ if (err)
+ goto exit_free_cc770;
+
+ dev_dbg(&pdev->dev,
+ "reg_base=0x%p irq=%d clock=%d cpu_interface=0x%02x "
+ "bus_config=0x%02x clkout=0x%02x\n",
+ priv->reg_base, dev->irq, priv->can.clock.freq,
+ priv->cpu_interface, priv->bus_config, priv->clkout);
+
+ dev_set_drvdata(&pdev->dev, dev);
+ SET_NETDEV_DEV(dev, &pdev->dev);
+
+ err = register_cc770dev(dev);
+ if (err) {
+ dev_err(&pdev->dev,
+ "couldn't register CC700 device (err=%d)\n", err);
+ goto exit_free_cc770;
+ }
+
+ return 0;
+
+exit_free_cc770:
+ free_cc770dev(dev);
+exit_unmap_mem:
+ iounmap(base);
+exit_release_mem:
+ release_mem_region(mem->start, mem_size);
+
+ return err;
+}
+
+static int __devexit cc770_platform_remove(struct platform_device *pdev)
+{
+ struct net_device *dev = dev_get_drvdata(&pdev->dev);
+ struct cc770_priv *priv = netdev_priv(dev);
+ struct resource *mem;
+
+ unregister_cc770dev(dev);
+ iounmap(priv->reg_base);
+ free_cc770dev(dev);
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ release_mem_region(mem->start, resource_size(mem));
+
+ return 0;
+}
+
+static struct of_device_id __devinitdata cc770_platform_table[] = {
+ {.compatible = "bosch,cc770"}, /* CC770 from Bosch */
+ {.compatible = "intc,82527"}, /* AN82527 from Intel CP */
+ {},
+};
+
+static struct platform_driver cc770_platform_driver = {
+ .driver = {
+ .name = DRV_NAME,
+ .owner = THIS_MODULE,
+ .of_match_table = cc770_platform_table,
+ },
+ .probe = cc770_platform_probe,
+ .remove = __devexit_p(cc770_platform_remove),
+};
+
+module_platform_driver(cc770_platform_driver);
/* New-style flags. */
dev->flags = IFF_NOARP;
- dev->features = NETIF_F_NO_CSUM;
+ dev->features = NETIF_F_HW_CSUM;
}
struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
.remove = __devexit_p(flexcan_remove),
};
-static int __init flexcan_init(void)
-{
- pr_info("%s netdevice driver\n", DRV_NAME);
- return platform_driver_register(&flexcan_driver);
-}
-
-static void __exit flexcan_exit(void)
-{
- platform_driver_unregister(&flexcan_driver);
- pr_info("%s: driver removed\n", DRV_NAME);
-}
-
-module_init(flexcan_init);
-module_exit(flexcan_exit);
+module_platform_driver(flexcan_driver);
MODULE_AUTHOR("Sascha Hauer <kernel@pengutronix.de>, "
"Marc Kleine-Budde <kernel@pengutronix.de>");
.remove = __devexit_p(ican3_remove),
};
-static int __init ican3_init(void)
-{
- return platform_driver_register(&ican3_driver);
-}
-
-static void __exit ican3_exit(void)
-{
- platform_driver_unregister(&ican3_driver);
-}
+module_platform_driver(ican3_driver);
MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
MODULE_DESCRIPTION("Janz MODULbus VMOD-ICAN3 Driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:janz-ican3");
-
-module_init(ican3_init);
-module_exit(ican3_exit);
#endif
};
-static int __init mpc5xxx_can_init(void)
-{
- return platform_driver_register(&mpc5xxx_can_driver);
-}
-module_init(mpc5xxx_can_init);
-
-static void __exit mpc5xxx_can_exit(void)
-{
- platform_driver_unregister(&mpc5xxx_can_driver);
-};
-module_exit(mpc5xxx_can_exit);
+module_platform_driver(mpc5xxx_can_driver);
MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
MODULE_DESCRIPTION("Freescale MPC5xxx CAN driver");
priv->open_time = jiffies;
- clrbits8(®s->canctl1, MSCAN_LISTEN);
+ if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+ setbits8(®s->canctl1, MSCAN_LISTEN);
+ else
+ clrbits8(®s->canctl1, MSCAN_LISTEN);
ret = mscan_start(dev);
if (ret)
priv->can.bittiming_const = &mscan_bittiming_const;
priv->can.do_set_bittiming = mscan_do_set_bittiming;
priv->can.do_set_mode = mscan_do_set_mode;
- priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
+ priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+ CAN_CTRLMODE_LISTENONLY;
for (i = 0; i < TX_QUEUE_SIZE; i++) {
priv->tx_queue[i].id = i;
config CAN_SJA1000_ISA
tristate "ISA Bus based legacy SJA1000 driver"
- depends on ISA
---help---
This driver adds legacy support for SJA1000 chips connected to
the ISA bus using I/O port, memory mapped or indirect access.
*/
#include <linux/kernel.h>
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/isa.h>
+#include <linux/platform_device.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/delay.h>
static unsigned long mem[MAXDEV];
static int __devinitdata irq[MAXDEV];
static int __devinitdata clk[MAXDEV];
-static char __devinitdata cdr[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
-static char __devinitdata ocr[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
-static char __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
+static unsigned char __devinitdata cdr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static unsigned char __devinitdata ocr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static int __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
module_param_array(port, ulong, NULL, S_IRUGO);
MODULE_PARM_DESC(port, "I/O port number");
module_param_array(mem, ulong, NULL, S_IRUGO);
MODULE_PARM_DESC(mem, "I/O memory address");
-module_param_array(indirect, byte, NULL, S_IRUGO);
+module_param_array(indirect, int, NULL, S_IRUGO);
MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
module_param_array(irq, int, NULL, S_IRUGO);
#define SJA1000_IOSIZE 0x20
#define SJA1000_IOSIZE_INDIRECT 0x02
+static struct platform_device *sja1000_isa_devs[MAXDEV];
+
static u8 sja1000_isa_mem_read_reg(const struct sja1000_priv *priv, int reg)
{
return readb(priv->reg_base + reg);
outb(val, base + 1);
}
-static int __devinit sja1000_isa_match(struct device *pdev, unsigned int idx)
-{
- if (port[idx] || mem[idx]) {
- if (irq[idx])
- return 1;
- } else if (idx)
- return 0;
-
- dev_err(pdev, "insufficient parameters supplied\n");
- return 0;
-}
-
-static int __devinit sja1000_isa_probe(struct device *pdev, unsigned int idx)
+static int __devinit sja1000_isa_probe(struct platform_device *pdev)
{
struct net_device *dev;
struct sja1000_priv *priv;
void __iomem *base = NULL;
int iosize = SJA1000_IOSIZE;
+ int idx = pdev->id;
int err;
+ dev_dbg(&pdev->dev, "probing idx=%d: port=%#lx, mem=%#lx, irq=%d\n",
+ idx, port[idx], mem[idx], irq[idx]);
+
if (mem[idx]) {
if (!request_mem_region(mem[idx], iosize, DRV_NAME)) {
err = -EBUSY;
else
priv->can.clock.freq = CLK_DEFAULT / 2;
- if (ocr[idx] != -1)
- priv->ocr = ocr[idx] & 0xff;
- else if (ocr[0] != -1)
- priv->ocr = ocr[0] & 0xff;
+ if (ocr[idx] != 0xff)
+ priv->ocr = ocr[idx];
+ else if (ocr[0] != 0xff)
+ priv->ocr = ocr[0];
else
priv->ocr = OCR_DEFAULT;
- if (cdr[idx] != -1)
- priv->cdr = cdr[idx] & 0xff;
- else if (cdr[0] != -1)
- priv->cdr = cdr[0] & 0xff;
+ if (cdr[idx] != 0xff)
+ priv->cdr = cdr[idx];
+ else if (cdr[0] != 0xff)
+ priv->cdr = cdr[0];
else
priv->cdr = CDR_DEFAULT;
- dev_set_drvdata(pdev, dev);
- SET_NETDEV_DEV(dev, pdev);
+ dev_set_drvdata(&pdev->dev, dev);
+ SET_NETDEV_DEV(dev, &pdev->dev);
err = register_sja1000dev(dev);
if (err) {
- dev_err(pdev, "registering %s failed (err=%d)\n",
+ dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
DRV_NAME, err);
goto exit_unmap;
}
- dev_info(pdev, "%s device registered (reg_base=0x%p, irq=%d)\n",
+ dev_info(&pdev->dev, "%s device registered (reg_base=0x%p, irq=%d)\n",
DRV_NAME, priv->reg_base, dev->irq);
return 0;
return err;
}
-static int __devexit sja1000_isa_remove(struct device *pdev, unsigned int idx)
+static int __devexit sja1000_isa_remove(struct platform_device *pdev)
{
- struct net_device *dev = dev_get_drvdata(pdev);
+ struct net_device *dev = dev_get_drvdata(&pdev->dev);
struct sja1000_priv *priv = netdev_priv(dev);
+ int idx = pdev->id;
unregister_sja1000dev(dev);
- dev_set_drvdata(pdev, NULL);
+ dev_set_drvdata(&pdev->dev, NULL);
if (mem[idx]) {
iounmap(priv->reg_base);
return 0;
}
-static struct isa_driver sja1000_isa_driver = {
- .match = sja1000_isa_match,
+static struct platform_driver sja1000_isa_driver = {
.probe = sja1000_isa_probe,
.remove = __devexit_p(sja1000_isa_remove),
.driver = {
.name = DRV_NAME,
+ .owner = THIS_MODULE,
},
};
static int __init sja1000_isa_init(void)
{
- int err = isa_register_driver(&sja1000_isa_driver, MAXDEV);
+ int idx, err;
+
+ for (idx = 0; idx < MAXDEV; idx++) {
+ if ((port[idx] || mem[idx]) && irq[idx]) {
+ sja1000_isa_devs[idx] =
+ platform_device_alloc(DRV_NAME, idx);
+ if (!sja1000_isa_devs[idx]) {
+ err = -ENOMEM;
+ goto exit_free_devices;
+ }
+ err = platform_device_add(sja1000_isa_devs[idx]);
+ if (err) {
+ platform_device_put(sja1000_isa_devs[idx]);
+ goto exit_free_devices;
+ }
+ pr_debug("%s: platform device %d: port=%#lx, mem=%#lx, "
+ "irq=%d\n",
+ DRV_NAME, idx, port[idx], mem[idx], irq[idx]);
+ } else if (idx == 0 || port[idx] || mem[idx]) {
+ pr_err("%s: insufficient parameters supplied\n",
+ DRV_NAME);
+ err = -EINVAL;
+ goto exit_free_devices;
+ }
+ }
+
+ err = platform_driver_register(&sja1000_isa_driver);
+ if (err)
+ goto exit_free_devices;
+
+ pr_info("Legacy %s driver for max. %d devices registered\n",
+ DRV_NAME, MAXDEV);
+
+ return 0;
+
+exit_free_devices:
+ while (--idx >= 0) {
+ if (sja1000_isa_devs[idx])
+ platform_device_unregister(sja1000_isa_devs[idx]);
+ }
- if (!err)
- printk(KERN_INFO
- "Legacy %s driver for max. %d devices registered\n",
- DRV_NAME, MAXDEV);
return err;
}
static void __exit sja1000_isa_exit(void)
{
- isa_unregister_driver(&sja1000_isa_driver);
+ int idx;
+
+ platform_driver_unregister(&sja1000_isa_driver);
+ for (idx = 0; idx < MAXDEV; idx++) {
+ if (sja1000_isa_devs[idx])
+ platform_device_unregister(sja1000_isa_devs[idx]);
+ }
}
module_init(sja1000_isa_init);
.remove = __devexit_p(sja1000_ofp_remove),
};
-static int __init sja1000_ofp_init(void)
-{
- return platform_driver_register(&sja1000_ofp_driver);
-}
-module_init(sja1000_ofp_init);
-
-static void __exit sja1000_ofp_exit(void)
-{
- return platform_driver_unregister(&sja1000_ofp_driver);
-};
-module_exit(sja1000_ofp_exit);
+module_platform_driver(sja1000_ofp_driver);
},
};
-static int __init sp_init(void)
-{
- return platform_driver_register(&sp_driver);
-}
-
-static void __exit sp_exit(void)
-{
- platform_driver_unregister(&sp_driver);
-}
-
-module_init(sp_init);
-module_exit(sp_exit);
+module_platform_driver(sp_driver);
/* New-style flags. */
dev->flags = IFF_NOARP;
- dev->features = NETIF_F_NO_CSUM;
+ dev->features = NETIF_F_HW_CSUM;
}
/******************************************
.remove = __devexit_p(softing_pdev_remove),
};
-MODULE_ALIAS("platform:softing");
-
-static int __init softing_start(void)
-{
- return platform_driver_register(&softing_driver);
-}
-
-static void __exit softing_stop(void)
-{
- platform_driver_unregister(&softing_driver);
-}
-
-module_init(softing_start);
-module_exit(softing_stop);
+module_platform_driver(softing_driver);
+MODULE_ALIAS("platform:softing");
MODULE_DESCRIPTION("Softing DPRAM CAN driver");
MODULE_AUTHOR("Kurt Van Dijck <kurt.van.dijck@eia.be>");
MODULE_LICENSE("GPL v2");
.resume = ti_hecc_resume,
};
-static int __init ti_hecc_init_driver(void)
-{
- printk(KERN_INFO DRV_DESC "\n");
- return platform_driver_register(&ti_hecc_driver);
-}
-
-static void __exit ti_hecc_exit_driver(void)
-{
- printk(KERN_INFO DRV_DESC " unloaded\n");
- platform_driver_unregister(&ti_hecc_driver);
-}
-
-module_exit(ti_hecc_exit_driver);
-module_init(ti_hecc_init_driver);
+module_platform_driver(ti_hecc_driver);
MODULE_AUTHOR("Anant Gole <anantgole@ti.com>");
MODULE_LICENSE("GPL v2");
* See Documentation/networking/can.txt for details.
*/
-static int echo; /* echo testing. Default: 0 (Off) */
+static bool echo; /* echo testing. Default: 0 (Off) */
module_param(echo, bool, S_IRUGO);
MODULE_PARM_DESC(echo, "Echo sent frames (for testing). Default: 0 (Off)");
--- /dev/null
+menu "Distributed Switch Architecture drivers"
+ depends on NET_DSA
+
+config NET_DSA_MV88E6XXX
+ tristate
+ default n
+
+config NET_DSA_MV88E6060
+ tristate "Marvell 88E6060 ethernet switch chip support"
+ select NET_DSA_TAG_TRAILER
+ ---help---
+ This enables support for the Marvell 88E6060 ethernet switch
+ chip.
+
+config NET_DSA_MV88E6XXX_NEED_PPU
+ bool
+ default n
+
+config NET_DSA_MV88E6131
+ tristate "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support"
+ select NET_DSA_MV88E6XXX
+ select NET_DSA_MV88E6XXX_NEED_PPU
+ select NET_DSA_TAG_DSA
+ ---help---
+ This enables support for the Marvell 88E6085/6095/6095F/6131
+ ethernet switch chips.
+
+config NET_DSA_MV88E6123_61_65
+ tristate "Marvell 88E6123/6161/6165 ethernet switch chip support"
+ select NET_DSA_MV88E6XXX
+ select NET_DSA_TAG_EDSA
+ ---help---
+ This enables support for the Marvell 88E6123/6161/6165
+ ethernet switch chips.
+
+endmenu
--- /dev/null
+obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
+obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx_drv.o
+mv88e6xxx_drv-y += mv88e6xxx.o
+ifdef CONFIG_NET_DSA_MV88E6123_61_65
+mv88e6xxx_drv-y += mv88e6123_61_65.o
+endif
+ifdef CONFIG_NET_DSA_MV88E6131
+mv88e6xxx_drv-y += mv88e6131.o
+endif
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
#define REG_PORT(p) (8 + (p))
#define REG_GLOBAL 0x0f
unregister_switch_driver(&mv88e6060_switch_driver);
}
module_exit(mv88e6060_cleanup);
+
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
+MODULE_DESCRIPTION("Driver for Marvell 88E6060 ethernet switch chip");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mv88e6060");
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
#include "mv88e6xxx.h"
static char *mv88e6123_61_65_probe(struct mii_bus *bus, int sw_addr)
return ARRAY_SIZE(mv88e6123_61_65_hw_stats);
}
-static struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
+struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
.tag_protocol = cpu_to_be16(ETH_P_EDSA),
.priv_size = sizeof(struct mv88e6xxx_priv_state),
.probe = mv88e6123_61_65_probe,
.get_sset_count = mv88e6123_61_65_get_sset_count,
};
-static int __init mv88e6123_61_65_init(void)
-{
- register_switch_driver(&mv88e6123_61_65_switch_driver);
- return 0;
-}
-module_init(mv88e6123_61_65_init);
-
-static void __exit mv88e6123_61_65_cleanup(void)
-{
- unregister_switch_driver(&mv88e6123_61_65_switch_driver);
-}
-module_exit(mv88e6123_61_65_cleanup);
+MODULE_ALIAS("platform:mv88e6123");
+MODULE_ALIAS("platform:mv88e6161");
+MODULE_ALIAS("platform:mv88e6165");
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
#include "mv88e6xxx.h"
/*
return ARRAY_SIZE(mv88e6131_hw_stats);
}
-static struct dsa_switch_driver mv88e6131_switch_driver = {
+struct dsa_switch_driver mv88e6131_switch_driver = {
.tag_protocol = cpu_to_be16(ETH_P_DSA),
.priv_size = sizeof(struct mv88e6xxx_priv_state),
.probe = mv88e6131_probe,
.get_sset_count = mv88e6131_get_sset_count,
};
-static int __init mv88e6131_init(void)
-{
- register_switch_driver(&mv88e6131_switch_driver);
- return 0;
-}
-module_init(mv88e6131_init);
-
-static void __exit mv88e6131_cleanup(void)
-{
- unregister_switch_driver(&mv88e6131_switch_driver);
-}
-module_exit(mv88e6131_cleanup);
+MODULE_ALIAS("platform:mv88e6085");
+MODULE_ALIAS("platform:mv88e6095");
+MODULE_ALIAS("platform:mv88e6095f");
+MODULE_ALIAS("platform:mv88e6131");
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
#include "mv88e6xxx.h"
/*
mutex_unlock(&ps->stats_mutex);
}
+
+static int __init mv88e6xxx_init(void)
+{
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131)
+ register_switch_driver(&mv88e6131_switch_driver);
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
+ register_switch_driver(&mv88e6123_61_65_switch_driver);
+#endif
+ return 0;
+}
+module_init(mv88e6xxx_init);
+
+static void __exit mv88e6xxx_cleanup(void)
+{
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
+ unregister_switch_driver(&mv88e6123_61_65_switch_driver);
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131)
+ unregister_switch_driver(&mv88e6131_switch_driver);
+#endif
+}
+module_exit(mv88e6xxx_cleanup);
+
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
+MODULE_DESCRIPTION("Driver for Marvell 88E6XXX ethernet switch chips");
+MODULE_LICENSE("GPL");
int nr_stats, struct mv88e6xxx_hw_stat *stats,
int port, uint64_t *data);
+extern struct dsa_switch_driver mv88e6131_switch_driver;
+extern struct dsa_switch_driver mv88e6123_61_65_switch_driver;
+
#define REG_READ(addr, reg) \
({ \
int __ret; \
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_TSO;
- dev->features |= NETIF_F_NO_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
+ dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
random_ether_addr(dev->dev_addr);
}
static void netdev_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "PCMCIA 0x%lx", dev->base_addr);
}
static const struct ethtool_ops netdev_ethtool_ops = {
{
struct vortex_private *vp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
if (VORTEX_PCI(vp)) {
- strcpy(info->bus_info, pci_name(VORTEX_PCI(vp)));
+ strlcpy(info->bus_info, pci_name(VORTEX_PCI(vp)),
+ sizeof(info->bus_info));
} else {
if (VORTEX_EISA(vp))
- strcpy(info->bus_info, dev_name(vp->gendev));
+ strlcpy(info->bus_info, dev_name(vp->gendev),
+ sizeof(info->bus_info));
else
- sprintf(info->bus_info, "EISA 0x%lx %d",
- dev->base_addr, dev->irq);
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "EISA 0x%lx %d", dev->base_addr, dev->irq);
}
}
smp_rmb();
if(tp->card_state == Sleeping) {
- strcpy(info->fw_version, "Sleep image");
+ strlcpy(info->fw_version, "Sleep image",
+ sizeof(info->fw_version));
} else {
INIT_COMMAND_WITH_RESPONSE(&xp_cmd, TYPHOON_CMD_READ_VERSIONS);
if(typhoon_issue_command(tp, 1, &xp_cmd, 3, xp_resp) < 0) {
- strcpy(info->fw_version, "Unknown runtime");
+ strlcpy(info->fw_version, "Unknown runtime",
+ sizeof(info->fw_version));
} else {
u32 sleep_ver = le32_to_cpu(xp_resp[0].parm2);
- snprintf(info->fw_version, 32, "%02x.%03x.%03x",
- sleep_ver >> 24, (sleep_ver >> 12) & 0xfff,
- sleep_ver & 0xfff);
+ snprintf(info->fw_version, sizeof(info->fw_version),
+ "%02x.%03x.%03x", sleep_ver >> 24,
+ (sleep_ver >> 12) & 0xfff, sleep_ver & 0xfff);
}
}
- strcpy(info->driver, KBUILD_MODNAME);
- strcpy(info->bus_info, pci_name(pci_dev));
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
}
static int
#define TX_PAGES 12 /* Two Tx slots */
-#define ETHER_ADDR_LEN 6
-
/* The 8390 specific per-packet-header format. */
struct e8390_pkt_hdr {
unsigned char status; /* status */
i = request_irq(dev->irq, apne_interrupt, IRQF_SHARED, DRV_NAME, dev);
if (i) return i;
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = SA_prom[i];
printk(" %pM\n", dev->dev_addr);
if (ax->plat->flags & AXFLG_MAC_FROMDEV) {
ei_outb(E8390_NODMA + E8390_PAGE1 + E8390_STOP,
ei_local->mem + E8390_CMD); /* 0x61 */
- for (i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] =
ei_inb(ioaddr + EN1_PHYS_SHIFT(i));
}
if ((ax->plat->flags & AXFLG_MAC_FROMPLATFORM) &&
ax->plat->mac_addr)
- memcpy(dev->dev_addr, ax->plat->mac_addr,
- ETHER_ADDR_LEN);
+ memcpy(dev->dev_addr, ax->plat->mac_addr, ETH_ALEN);
ax_reset_8390(dev);
.resume = ax_resume,
};
-static int __init axdrv_init(void)
-{
- return platform_driver_register(&axdrv);
-}
-
-static void __exit axdrv_exit(void)
-{
- platform_driver_unregister(&axdrv);
-}
-
-module_init(axdrv_init);
-module_exit(axdrv_exit);
+module_platform_driver(axdrv);
MODULE_DESCRIPTION("AX88796 10/100 Ethernet platform driver");
MODULE_AUTHOR("Ben Dooks, <ben@simtec.co.uk>");
goto out;
}
- for (i = 0; i < ETHER_ADDR_LEN ; i++)
+ for (i = 0; i < ETH_ALEN ; i++)
dev->dev_addr[i] = inb(ioaddr + ES_SA_PROM + i);
/* Check the Racal vendor ID as well. */
/* Retrieve and checksum the station address. */
outw(MAC_Page, ioaddr + HP_PAGING);
- for(i = 0; i < ETHER_ADDR_LEN; i++) {
+ for(i = 0; i < ETH_ALEN; i++) {
unsigned char inval = inb(ioaddr + 8 + i);
dev->dev_addr[i] = inval;
checksum += inval;
printk("%s: %s (ID %02x) at %#3x,", dev->name, name, board_id, ioaddr);
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for(i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = inb(ioaddr + i);
printk(" %pM", dev->dev_addr);
if (!dev)
return -ENOMEM;
- for(j = 0; j < ETHER_ADDR_LEN; j++)
+ for (j = 0; j < ETH_ALEN; j++)
dev->dev_addr[j] = *((u8 *)(board + HYDRA_ADDRPROM + 2*j));
/* We must set the 8390 for word mode. */
|| inb(ioaddr + LNE390_SA_PROM + 1) != LNE390_ADDR1
|| inb(ioaddr + LNE390_SA_PROM + 2) != LNE390_ADDR2 ) {
printk("lne390.c: card not found");
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
printk(" %02x", inb(ioaddr + LNE390_SA_PROM + i));
printk(" (invalid prefix).\n");
return -ENODEV;
}
#endif
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = inb(ioaddr + LNE390_SA_PROM + i);
printk("lne390.c: LNE390%X in EISA slot %d, address %pM.\n",
0xa+revision, ioaddr/0x1000, dev->dev_addr);
dev->base_addr = ioaddr;
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = SA_prom[i];
printk(" %pM\n", dev->dev_addr);
#ifdef CONFIG_PLAT_MAPPI
outb_p(E8390_NODMA + E8390_PAGE1 + E8390_STOP,
ioaddr + E8390_CMD); /* 0x61 */
- for (i = 0 ; i < ETHER_ADDR_LEN ; i++) {
+ for (i = 0; i < ETH_ALEN; i++) {
dev->dev_addr[i] = SA_prom[i]
= inb_p(ioaddr + EN1_PHYS_SHIFT(i));
}
#else
- for(i = 0; i < ETHER_ADDR_LEN; i++) {
+ for (i = 0; i < ETH_ALEN; i++) {
dev->dev_addr[i] = SA_prom[i];
}
#endif
dev->base_addr = base_addr;
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = SA_prom[i];
printk(" %pM\n", dev->dev_addr);
struct ei_device *ei = netdev_priv(dev);
struct pci_dev *pci_dev = (struct pci_dev *) ei->priv;
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
}
static const struct ethtool_ops ne2k_pci_ethtool_ops = {
#endif
port_index = inb(ioaddr + NE3210_CFG2) >> 6;
- for(i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = inb(ioaddr + NE3210_SA_PROM + i);
printk("ne3210.c: NE3210 in EISA slot %d, media: %s, addr: %pM.\n",
edev->slot, ifmap[port_index], dev->dev_addr);
#ifdef CONFIG_SH_STANDARD_BIOS
sh_bios_get_node_addr (stnic_eadr);
#endif
- for (i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = stnic_eadr[i];
/* Set the base address to point to the NIC, not the "real" base! */
if (i)
return i;
- for (i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = SA_prom[i];
pr_debug("Found ethernet address: %pM\n", dev->dev_addr);
source "drivers/net/ethernet/adi/Kconfig"
source "drivers/net/ethernet/broadcom/Kconfig"
source "drivers/net/ethernet/brocade/Kconfig"
+source "drivers/net/ethernet/calxeda/Kconfig"
source "drivers/net/ethernet/chelsio/Kconfig"
source "drivers/net/ethernet/cirrus/Kconfig"
source "drivers/net/ethernet/cisco/Kconfig"
obj-$(CONFIG_NET_BFIN) += adi/
obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
+obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
#ifdef VLAN_SUPPORT
-static void netdev_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int netdev_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct netdev_private *np = netdev_priv(dev);
set_bit(vid, np->active_vlans);
set_rx_mode(dev);
spin_unlock(&np->lock);
+
+ return 0;
}
-static void netdev_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int netdev_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct netdev_private *np = netdev_priv(dev);
clear_bit(vid, np->active_vlans);
set_rx_mode(dev);
spin_unlock(&np->lock);
+
+ return 0;
}
#endif /* VLAN_SUPPORT */
static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct netdev_private *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
.remove = __devexit_p(greth_of_remove),
};
-static int __init greth_init(void)
-{
- return platform_driver_register(&greth_of_driver);
-}
-
-static void __exit greth_cleanup(void)
-{
- platform_driver_unregister(&greth_of_driver);
-}
-
-module_init(greth_init);
-module_exit(greth_cleanup);
+module_platform_driver(greth_of_driver);
MODULE_AUTHOR("Aeroflex Gaisler AB.");
MODULE_DESCRIPTION("Aeroflex Gaisler Ethernet MAC driver");
writel( VAL0 | APAD_XMT | REX_RTRY, mmio + CMD2 );
/* Setting the MAC address to the device */
- for(i = 0; i < ETH_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
writeb( dev->dev_addr[i], mmio + PADR + i );
/* Enable interrupt coalesce */
{
struct amd8111e_priv *lp = netdev_priv(dev);
struct pci_dev *pci_dev = lp->pci_dev;
- strcpy (info->driver, MODULE_NAME);
- strcpy (info->version, MODULE_VERS);
- sprintf(info->fw_version,"%u",chip_version);
- strcpy (info->bus_info, pci_name(pci_dev));
+ strlcpy(info->driver, MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, MODULE_VERS, sizeof(info->version));
+ snprintf(info->fw_version, sizeof(info->fw_version),
+ "%u", chip_version);
+ strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
}
static int amd8111e_get_regs_len(struct net_device *dev)
memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
spin_lock_irq(&lp->lock);
/* Setting the MAC address to the device */
- for(i = 0; i < ETH_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
writeb( dev->dev_addr[i], lp->mmio + PADR + i );
spin_unlock_irq(&lp->lock);
}
/* Initializing MAC address */
- for(i = 0; i < ETH_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = readb(lp->mmio + PADR + i);
/* Setting user defined parametrs */
#define PKT_BUFF_SZ 1536
#define MIN_PKT_LEN 60
-#define ETH_ADDR_LEN 6
#define AMD8111E_TX_TIMEOUT (3 * HZ)/* 3 sec */
#define SOFT_TIMER_FREQ 0xBEBC /* 0.5 sec */
static int card_idx;
static int speed_duplex[MAX_UNITS] = { 0, };
-static int coalesce[MAX_UNITS] = {1,1,1,1,1,1,1,1};
-static int dynamic_ipg[MAX_UNITS] = {0,0,0,0,0,0,0,0};
+static bool coalesce[MAX_UNITS] = { [ 0 ... MAX_UNITS-1] = true };
+static bool dynamic_ipg[MAX_UNITS] = { [ 0 ... MAX_UNITS-1] = false };
static unsigned int chip_version;
#endif /* _AMD8111E_H */
.owner = THIS_MODULE,
},
};
-MODULE_ALIAS("platform:au1000-eth");
-
-
-static int __init au1000_init_module(void)
-{
- return platform_driver_register(&au1000_eth_driver);
-}
-static void __exit au1000_exit_module(void)
-{
- platform_driver_unregister(&au1000_eth_driver);
-}
+module_platform_driver(au1000_eth_driver);
-module_init(au1000_init_module);
-module_exit(au1000_exit_module);
+MODULE_ALIAS("platform:au1000-eth");
Defines
---------------------------------------------------------------------------- */
-#define ETHER_ADDR_LEN ETH_ALEN
- /* 6 bytes in an Ethernet Address */
#define MACE_LADRF_LEN 8
/* 8 bytes in Logical Address Filter */
}
}
/* Set PADR register */
- for (i = 0; i < ETHER_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
mace_write(lp, ioaddr, MACE_PADR, enet_addr[i]);
/* MAC Configuration Control Register should be written last */
/* Read the ethernet address from the CIS. */
len = pcmcia_get_tuple(link, 0x80, &buf);
- if (!buf || len < ETHER_ADDR_LEN) {
+ if (!buf || len < ETH_ALEN) {
kfree(buf);
goto failed;
}
- memcpy(dev->dev_addr, buf, ETHER_ADDR_LEN);
+ memcpy(dev->dev_addr, buf, ETH_ALEN);
kfree(buf);
/* Verify configuration by reading the MACE ID. */
static void netdev_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "PCMCIA 0x%lx", dev->base_addr);
}
static const struct ethtool_ops netdev_ethtool_ops = {
static void set_multicast_list(struct net_device *dev)
{
mace_private *lp = netdev_priv(dev);
- int adr[ETHER_ADDR_LEN] = {0}; /* Ethernet address */
+ int adr[ETH_ALEN] = {0}; /* Ethernet address */
struct netdev_hw_addr *ha;
#ifdef PCMCIA_DEBUG
/* Calculate multicast logical address filter */
memset(lp->multicast_ladrf, 0, MACE_LADRF_LEN);
netdev_for_each_mc_addr(ha, dev) {
- memcpy(adr, ha->addr, ETHER_ADDR_LEN);
+ memcpy(adr, ha->addr, ETH_ALEN);
BuildLAF(lp->multicast_ladrf, adr);
}
}
{
struct pcnet32_private *lp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
if (lp->pci_dev)
- strcpy(info->bus_info, pci_name(lp->pci_dev));
+ strlcpy(info->bus_info, pci_name(lp->pci_dev),
+ sizeof(info->bus_info));
else
- sprintf(info->bus_info, "VLB 0x%lx", dev->base_addr);
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "VLB 0x%lx", dev->base_addr);
}
static u32 pcnet32_get_link(struct net_device *dev)
.remove = __devexit_p(sunlance_sbus_remove),
};
-
-/* Find all the lance cards on the system and initialize them */
-static int __init sparc_lance_init(void)
-{
- return platform_driver_register(&sunlance_sbus_driver);
-}
-
-static void __exit sparc_lance_exit(void)
-{
- platform_driver_unregister(&sunlance_sbus_driver);
-}
-
-module_init(sparc_lance_init);
-module_exit(sparc_lance_exit);
+module_platform_driver(sunlance_sbus_driver);
strlcpy(drvinfo->driver, atl1c_driver_name, sizeof(drvinfo->driver));
strlcpy(drvinfo->version, atl1c_driver_version,
sizeof(drvinfo->version));
- strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
sizeof(drvinfo->bus_info));
drvinfo->n_stats = 0;
}
}
-static void __atl1c_vlan_mode(u32 features, u32 *mac_ctrl_data)
+static void __atl1c_vlan_mode(netdev_features_t features, u32 *mac_ctrl_data)
{
if (features & NETIF_F_HW_VLAN_RX) {
/* enable VLAN tag insert/strip */
}
}
-static void atl1c_vlan_mode(struct net_device *netdev, u32 features)
+static void atl1c_vlan_mode(struct net_device *netdev,
+ netdev_features_t features)
{
struct atl1c_adapter *adapter = netdev_priv(netdev);
struct pci_dev *pdev = adapter->pdev;
roundup(mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN, 8) : AT_RX_BUF_SIZE;
}
-static u32 atl1c_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl1c_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int atl1c_set_features(struct net_device *netdev, u32 features)
+static int atl1c_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
atl1c_vlan_mode(netdev, features);
{
struct atl1e_adapter *adapter = netdev_priv(netdev);
- strncpy(drvinfo->driver, atl1e_driver_name, 32);
- strncpy(drvinfo->version, atl1e_driver_version, 32);
- strncpy(drvinfo->fw_version, "L1e", 32);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->driver, atl1e_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, atl1e_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = 0;
drvinfo->testinfo_len = 0;
drvinfo->regdump_len = atl1e_get_regs_len(netdev);
}
}
-static void __atl1e_vlan_mode(u32 features, u32 *mac_ctrl_data)
+static void __atl1e_vlan_mode(netdev_features_t features, u32 *mac_ctrl_data)
{
if (features & NETIF_F_HW_VLAN_RX) {
/* enable VLAN tag insert/strip */
}
}
-static void atl1e_vlan_mode(struct net_device *netdev, u32 features)
+static void atl1e_vlan_mode(struct net_device *netdev,
+ netdev_features_t features)
{
struct atl1e_adapter *adapter = netdev_priv(netdev);
u32 mac_ctrl_data = 0;
return 0;
}
-static u32 atl1e_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl1e_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int atl1e_set_features(struct net_device *netdev, u32 features)
+static int atl1e_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
atl1e_vlan_mode(netdev, features);
strlcpy(drvinfo->driver, ATLX_DRIVER_NAME, sizeof(drvinfo->driver));
strlcpy(drvinfo->version, ATLX_DRIVER_VERSION,
sizeof(drvinfo->version));
- strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
sizeof(drvinfo->bus_info));
drvinfo->eedump_len = ATL1_EEDUMP_LEN;
synchronize_irq(adapter->pdev->irq);
}
-static void __atl2_vlan_mode(u32 features, u32 *ctrl)
+static void __atl2_vlan_mode(netdev_features_t features, u32 *ctrl)
{
if (features & NETIF_F_HW_VLAN_RX) {
/* enable VLAN tag insert/strip */
}
}
-static void atl2_vlan_mode(struct net_device *netdev, u32 features)
+static void atl2_vlan_mode(struct net_device *netdev,
+ netdev_features_t features)
{
struct atl2_adapter *adapter = netdev_priv(netdev);
u32 ctrl;
atl2_vlan_mode(adapter->netdev, adapter->netdev->features);
}
-static u32 atl2_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl2_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int atl2_set_features(struct net_device *netdev, u32 features)
+static int atl2_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
atl2_vlan_mode(netdev, features);
{
struct atl2_adapter *adapter = netdev_priv(netdev);
- strncpy(drvinfo->driver, atl2_driver_name, 32);
- strncpy(drvinfo->version, atl2_driver_version, 32);
- strncpy(drvinfo->fw_version, "L2", 32);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->driver, atl2_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, atl2_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, "L2", sizeof(drvinfo->fw_version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = 0;
drvinfo->testinfo_len = 0;
drvinfo->regdump_len = atl2_get_regs_len(netdev);
spin_unlock_irqrestore(&adapter->lock, flags);
}
-static void __atlx_vlan_mode(u32 features, u32 *ctrl)
+static void __atlx_vlan_mode(netdev_features_t features, u32 *ctrl)
{
if (features & NETIF_F_HW_VLAN_RX) {
/* enable VLAN tag insert/strip */
}
}
-static void atlx_vlan_mode(struct net_device *netdev, u32 features)
+static void atlx_vlan_mode(struct net_device *netdev,
+ netdev_features_t features)
{
struct atlx_adapter *adapter = netdev_priv(netdev);
unsigned long flags;
atlx_vlan_mode(adapter->netdev, adapter->netdev->features);
}
-static u32 atlx_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atlx_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int atlx_set_features(struct net_device *netdev, u32 features)
+static int atlx_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
atlx_vlan_mode(netdev, features);
skb->len,
DMA_TO_DEVICE);
rp->skb = NULL;
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
}
bp->tx_cons = cons;
#include "bnx2_fw.h"
#define DRV_MODULE_NAME "bnx2"
-#define DRV_MODULE_VERSION "2.1.11"
-#define DRV_MODULE_RELDATE "July 20, 2011"
-#define FW_MIPS_FILE_06 "bnx2/bnx2-mips-06-6.2.1.fw"
+#define DRV_MODULE_VERSION "2.2.1"
+#define DRV_MODULE_RELDATE "Dec 18, 2011"
+#define FW_MIPS_FILE_06 "bnx2/bnx2-mips-06-6.2.3.fw"
#define FW_RV2P_FILE_06 "bnx2/bnx2-rv2p-06-6.0.15.fw"
-#define FW_MIPS_FILE_09 "bnx2/bnx2-mips-09-6.2.1a.fw"
+#define FW_MIPS_FILE_09 "bnx2/bnx2-mips-09-6.2.1b.fw"
#define FW_RV2P_FILE_09_Ax "bnx2/bnx2-rv2p-09ax-6.0.17.fw"
#define FW_RV2P_FILE_09 "bnx2/bnx2-rv2p-09-6.0.17.fw"
mutex_lock(&bp->cnic_lock);
cp->drv_state = 0;
bnapi->cnic_present = 0;
- rcu_assign_pointer(bp->cnic_ops, NULL);
+ RCU_INIT_POINTER(bp->cnic_ops, NULL);
mutex_unlock(&bp->cnic_lock);
synchronize_rcu();
return 0;
if (bp->autoneg & AUTONEG_SPEED) {
u32 adv_reg, adv1000_reg;
- u32 new_adv_reg = 0;
- u32 new_adv1000_reg = 0;
+ u32 new_adv = 0;
+ u32 new_adv1000 = 0;
bnx2_read_phy(bp, bp->mii_adv, &adv_reg);
adv_reg &= (PHY_ALL_10_100_SPEED | ADVERTISE_PAUSE_CAP |
bnx2_read_phy(bp, MII_CTRL1000, &adv1000_reg);
adv1000_reg &= PHY_ALL_1000_SPEED;
- if (bp->advertising & ADVERTISED_10baseT_Half)
- new_adv_reg |= ADVERTISE_10HALF;
- if (bp->advertising & ADVERTISED_10baseT_Full)
- new_adv_reg |= ADVERTISE_10FULL;
- if (bp->advertising & ADVERTISED_100baseT_Half)
- new_adv_reg |= ADVERTISE_100HALF;
- if (bp->advertising & ADVERTISED_100baseT_Full)
- new_adv_reg |= ADVERTISE_100FULL;
- if (bp->advertising & ADVERTISED_1000baseT_Full)
- new_adv1000_reg |= ADVERTISE_1000FULL;
+ new_adv = ethtool_adv_to_mii_adv_t(bp->advertising);
+ new_adv |= ADVERTISE_CSMA;
+ new_adv |= bnx2_phy_get_pause_adv(bp);
- new_adv_reg |= ADVERTISE_CSMA;
+ new_adv1000 |= ethtool_adv_to_mii_ctrl1000_t(bp->advertising);
- new_adv_reg |= bnx2_phy_get_pause_adv(bp);
-
- if ((adv1000_reg != new_adv1000_reg) ||
- (adv_reg != new_adv_reg) ||
+ if ((adv1000_reg != new_adv1000) ||
+ (adv_reg != new_adv) ||
((bmcr & BMCR_ANENABLE) == 0)) {
- bnx2_write_phy(bp, bp->mii_adv, new_adv_reg);
- bnx2_write_phy(bp, MII_CTRL1000, new_adv1000_reg);
+ bnx2_write_phy(bp, bp->mii_adv, new_adv);
+ bnx2_write_phy(bp, MII_CTRL1000, new_adv1000);
bnx2_write_phy(bp, bp->mii_bmcr, BMCR_ANRESTART |
BMCR_ANENABLE);
}
}
static inline int
-bnx2_alloc_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gfp_t gfp)
+bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gfp_t gfp)
{
- struct sk_buff *skb;
+ u8 *data;
struct sw_bd *rx_buf = &rxr->rx_buf_ring[index];
dma_addr_t mapping;
struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(index)][RX_IDX(index)];
- unsigned long align;
- skb = __netdev_alloc_skb(bp->dev, bp->rx_buf_size, gfp);
- if (skb == NULL) {
+ data = kmalloc(bp->rx_buf_size, gfp);
+ if (!data)
return -ENOMEM;
- }
- if (unlikely((align = (unsigned long) skb->data & (BNX2_RX_ALIGN - 1))))
- skb_reserve(skb, BNX2_RX_ALIGN - align);
-
- mapping = dma_map_single(&bp->pdev->dev, skb->data, bp->rx_buf_use_size,
+ mapping = dma_map_single(&bp->pdev->dev,
+ get_l2_fhdr(data),
+ bp->rx_buf_use_size,
PCI_DMA_FROMDEVICE);
if (dma_mapping_error(&bp->pdev->dev, mapping)) {
- dev_kfree_skb(skb);
+ kfree(data);
return -EIO;
}
- rx_buf->skb = skb;
- rx_buf->desc = (struct l2_fhdr *) skb->data;
+ rx_buf->data = data;
dma_unmap_addr_set(rx_buf, mapping, mapping);
rxbd->rx_bd_haddr_hi = (u64) mapping >> 32;
struct bnx2_tx_ring_info *txr = &bnapi->tx_ring;
u16 hw_cons, sw_cons, sw_ring_cons;
int tx_pkt = 0, index;
+ unsigned int tx_bytes = 0;
struct netdev_queue *txq;
index = (bnapi - bp->bnx2_napi);
sw_cons = NEXT_TX_BD(sw_cons);
+ tx_bytes += skb->len;
dev_kfree_skb(skb);
tx_pkt++;
if (tx_pkt == budget)
hw_cons = bnx2_get_hw_tx_cons(bnapi);
}
+ netdev_tx_completed_queue(txq, tx_pkt, tx_bytes);
txr->hw_tx_cons = hw_cons;
txr->tx_cons = sw_cons;
}
static inline void
-bnx2_reuse_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
- struct sk_buff *skb, u16 cons, u16 prod)
+bnx2_reuse_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
+ u8 *data, u16 cons, u16 prod)
{
struct sw_bd *cons_rx_buf, *prod_rx_buf;
struct rx_bd *cons_bd, *prod_bd;
rxr->rx_prod_bseq += bp->rx_buf_use_size;
- prod_rx_buf->skb = skb;
- prod_rx_buf->desc = (struct l2_fhdr *) skb->data;
+ prod_rx_buf->data = data;
if (cons == prod)
return;
prod_bd->rx_bd_haddr_lo = cons_bd->rx_bd_haddr_lo;
}
-static int
-bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, struct sk_buff *skb,
+static struct sk_buff *
+bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u8 *data,
unsigned int len, unsigned int hdr_len, dma_addr_t dma_addr,
u32 ring_idx)
{
int err;
u16 prod = ring_idx & 0xffff;
+ struct sk_buff *skb;
- err = bnx2_alloc_rx_skb(bp, rxr, prod, GFP_ATOMIC);
+ err = bnx2_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
if (unlikely(err)) {
- bnx2_reuse_rx_skb(bp, rxr, skb, (u16) (ring_idx >> 16), prod);
+ bnx2_reuse_rx_data(bp, rxr, data, (u16) (ring_idx >> 16), prod);
+error:
if (hdr_len) {
unsigned int raw_len = len + 4;
int pages = PAGE_ALIGN(raw_len - hdr_len) >> PAGE_SHIFT;
bnx2_reuse_rx_skb_pages(bp, rxr, NULL, pages);
}
- return err;
+ return NULL;
}
- skb_reserve(skb, BNX2_RX_OFFSET);
dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
PCI_DMA_FROMDEVICE);
-
+ skb = build_skb(data);
+ if (!skb) {
+ kfree(data);
+ goto error;
+ }
+ skb_reserve(skb, ((u8 *)get_l2_fhdr(data) - data) + BNX2_RX_OFFSET);
if (hdr_len == 0) {
skb_put(skb, len);
- return 0;
+ return skb;
} else {
unsigned int i, frag_len, frag_size, pages;
struct sw_pg *rx_pg;
skb_frag_size_sub(frag, tail);
skb->data_len -= tail;
}
- return 0;
+ return skb;
}
rx_pg = &rxr->rx_pg_ring[pg_cons];
rxr->rx_pg_prod = pg_prod;
bnx2_reuse_rx_skb_pages(bp, rxr, skb,
pages - i);
- return err;
+ return NULL;
}
dma_unmap_page(&bp->pdev->dev, mapping_old,
rxr->rx_pg_prod = pg_prod;
rxr->rx_pg_cons = pg_cons;
}
- return 0;
+ return skb;
}
static inline u16
struct sw_bd *rx_buf, *next_rx_buf;
struct sk_buff *skb;
dma_addr_t dma_addr;
+ u8 *data;
sw_ring_cons = RX_RING_IDX(sw_cons);
sw_ring_prod = RX_RING_IDX(sw_prod);
rx_buf = &rxr->rx_buf_ring[sw_ring_cons];
- skb = rx_buf->skb;
- prefetchw(skb);
-
- next_rx_buf =
- &rxr->rx_buf_ring[RX_RING_IDX(NEXT_RX_BD(sw_cons))];
- prefetch(next_rx_buf->desc);
+ data = rx_buf->data;
+ rx_buf->data = NULL;
- rx_buf->skb = NULL;
+ rx_hdr = get_l2_fhdr(data);
+ prefetch(rx_hdr);
dma_addr = dma_unmap_addr(rx_buf, mapping);
BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH,
PCI_DMA_FROMDEVICE);
- rx_hdr = rx_buf->desc;
+ next_rx_buf =
+ &rxr->rx_buf_ring[RX_RING_IDX(NEXT_RX_BD(sw_cons))];
+ prefetch(get_l2_fhdr(next_rx_buf->data));
+
len = rx_hdr->l2_fhdr_pkt_len;
status = rx_hdr->l2_fhdr_status;
L2_FHDR_ERRORS_TOO_SHORT |
L2_FHDR_ERRORS_GIANT_FRAME))) {
- bnx2_reuse_rx_skb(bp, rxr, skb, sw_ring_cons,
+ bnx2_reuse_rx_data(bp, rxr, data, sw_ring_cons,
sw_ring_prod);
if (pg_ring_used) {
int pages;
len -= 4;
if (len <= bp->rx_copy_thresh) {
- struct sk_buff *new_skb;
-
- new_skb = netdev_alloc_skb(bp->dev, len + 6);
- if (new_skb == NULL) {
- bnx2_reuse_rx_skb(bp, rxr, skb, sw_ring_cons,
+ skb = netdev_alloc_skb(bp->dev, len + 6);
+ if (skb == NULL) {
+ bnx2_reuse_rx_data(bp, rxr, data, sw_ring_cons,
sw_ring_prod);
goto next_rx;
}
/* aligned copy */
- skb_copy_from_linear_data_offset(skb,
- BNX2_RX_OFFSET - 6,
- new_skb->data, len + 6);
- skb_reserve(new_skb, 6);
- skb_put(new_skb, len);
+ memcpy(skb->data,
+ (u8 *)rx_hdr + BNX2_RX_OFFSET - 6,
+ len + 6);
+ skb_reserve(skb, 6);
+ skb_put(skb, len);
- bnx2_reuse_rx_skb(bp, rxr, skb,
+ bnx2_reuse_rx_data(bp, rxr, data,
sw_ring_cons, sw_ring_prod);
- skb = new_skb;
- } else if (unlikely(bnx2_rx_skb(bp, rxr, skb, len, hdr_len,
- dma_addr, (sw_ring_cons << 16) | sw_ring_prod)))
- goto next_rx;
-
+ } else {
+ skb = bnx2_rx_skb(bp, rxr, data, len, hdr_len, dma_addr,
+ (sw_ring_cons << 16) | sw_ring_prod);
+ if (!skb)
+ goto next_rx;
+ }
if ((status & L2_FHDR_STATUS_L2_VLAN_TAG) &&
!(bp->rx_mode & BNX2_EMAC_RX_MODE_KEEP_VLAN_TAG))
__vlan_hwaccel_put_tag(skb, rx_hdr->l2_fhdr_vlan_tag);
ring_prod = prod = rxr->rx_prod;
for (i = 0; i < bp->rx_ring_size; i++) {
- if (bnx2_alloc_rx_skb(bp, rxr, ring_prod, GFP_KERNEL) < 0) {
+ if (bnx2_alloc_rx_data(bp, rxr, ring_prod, GFP_KERNEL) < 0) {
netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d skbs only\n",
ring_num, i, bp->rx_ring_size);
break;
rx_size = bp->dev->mtu + ETH_HLEN + BNX2_RX_OFFSET + 8;
rx_space = SKB_DATA_ALIGN(rx_size + BNX2_RX_ALIGN) + NET_SKB_PAD +
- sizeof(struct skb_shared_info);
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
bp->rx_copy_thresh = BNX2_RX_COPY_THRESH;
bp->rx_pg_ring_size = 0;
}
bp->rx_buf_use_size = rx_size;
- /* hw alignment */
- bp->rx_buf_size = bp->rx_buf_use_size + BNX2_RX_ALIGN;
+ /* hw alignment + build_skb() overhead*/
+ bp->rx_buf_size = SKB_DATA_ALIGN(bp->rx_buf_use_size + BNX2_RX_ALIGN) +
+ NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
bp->rx_jumbo_thresh = rx_size - BNX2_RX_OFFSET;
bp->rx_ring_size = size;
bp->rx_max_ring = bnx2_find_max_ring(size, MAX_RX_RINGS);
}
dev_kfree_skb(skb);
}
+ netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
}
}
for (j = 0; j < bp->rx_max_ring_idx; j++) {
struct sw_bd *rx_buf = &rxr->rx_buf_ring[j];
- struct sk_buff *skb = rx_buf->skb;
+ u8 *data = rx_buf->data;
- if (skb == NULL)
+ if (data == NULL)
continue;
dma_unmap_single(&bp->pdev->dev,
bp->rx_buf_use_size,
PCI_DMA_FROMDEVICE);
- rx_buf->skb = NULL;
+ rx_buf->data = NULL;
- dev_kfree_skb(skb);
+ kfree(data);
}
for (j = 0; j < bp->rx_max_pg_ring_idx; j++)
bnx2_free_rx_page(bp, rxr, j);
bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
{
unsigned int pkt_size, num_pkts, i;
- struct sk_buff *skb, *rx_skb;
+ struct sk_buff *skb;
+ u8 *data;
unsigned char *packet;
u16 rx_start_idx, rx_idx;
dma_addr_t map;
}
rx_buf = &rxr->rx_buf_ring[rx_start_idx];
- rx_skb = rx_buf->skb;
+ data = rx_buf->data;
- rx_hdr = rx_buf->desc;
- skb_reserve(rx_skb, BNX2_RX_OFFSET);
+ rx_hdr = get_l2_fhdr(data);
+ data = (u8 *)rx_hdr + BNX2_RX_OFFSET;
dma_sync_single_for_cpu(&bp->pdev->dev,
dma_unmap_addr(rx_buf, mapping),
- bp->rx_buf_size, PCI_DMA_FROMDEVICE);
+ bp->rx_buf_use_size, PCI_DMA_FROMDEVICE);
if (rx_hdr->l2_fhdr_status &
(L2_FHDR_ERRORS_BAD_CRC |
}
for (i = 14; i < pkt_size; i++) {
- if (*(rx_skb->data + i) != (unsigned char) (i & 0xff)) {
+ if (*(data + i) != (unsigned char) (i & 0xff)) {
goto loopback_test_done;
}
}
}
txbd->tx_bd_vlan_tag_flags |= TX_BD_FLAGS_END;
+ netdev_tx_sent_queue(txq, skb->len);
+
prod = NEXT_TX_BD(prod);
txr->tx_prod_bseq += skb->len;
{
struct bnx2 *bp = netdev_priv(dev);
- strcpy(info->driver, DRV_MODULE_NAME);
- strcpy(info->version, DRV_MODULE_VERSION);
- strcpy(info->bus_info, pci_name(bp->pdev));
- strcpy(info->fw_version, bp->fw_version);
+ strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
+ strlcpy(info->fw_version, bp->fw_version, sizeof(info->fw_version));
}
#define BNX2_REGDUMP_LEN (32 * 1024)
return 0;
}
-static u32
-bnx2_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t
+bnx2_fix_features(struct net_device *dev, netdev_features_t features)
{
struct bnx2 *bp = netdev_priv(dev);
}
static int
-bnx2_set_features(struct net_device *dev, u32 features)
+bnx2_set_features(struct net_device *dev, netdev_features_t features)
{
struct bnx2 *bp = netdev_priv(dev);
#define MB_TX_CID_ADDR MB_GET_CID_ADDR(TX_CID)
#define MB_RX_CID_ADDR MB_GET_CID_ADDR(RX_CID)
+/*
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
+ */
struct sw_bd {
- struct sk_buff *skb;
- struct l2_fhdr *desc;
+ u8 *data;
DEFINE_DMA_UNMAP_ADDR(mapping);
};
+/* Its faster to compute this from data than storing it in sw_bd
+ * (less cache misses)
+ */
+static inline struct l2_fhdr *get_l2_fhdr(u8 *data)
+{
+ return (struct l2_fhdr *)(PTR_ALIGN(data, BNX2_RX_ALIGN) + NET_SKB_PAD);
+}
+
+
struct sw_pg {
struct page *page;
DEFINE_DMA_UNMAP_ADDR(mapping);
* (you will need to reboot afterwards) */
/* #define BNX2X_STOP_ON_ERROR */
-#define DRV_MODULE_VERSION "1.70.30-0"
-#define DRV_MODULE_RELDATE "2011/10/25"
+#define DRV_MODULE_VERSION "1.70.35-0"
+#define DRV_MODULE_RELDATE "2011/11/10"
#define BNX2X_BC_VER 0x040200
#if defined(CONFIG_DCB)
#define FCOE_TXQ_IDX(bp) (MAX_ETH_TXQ_IDX(bp))
/* fast path */
+/*
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
+ */
struct sw_rx_bd {
- struct sk_buff *skb;
+ u8 *data;
DEFINE_DMA_UNMAP_ADDR(mapping);
};
/* Number of u64 elements in SGE mask array */
-#define RX_SGE_MASK_LEN ((NUM_RX_SGE_PAGES * RX_SGE_CNT) / \
- BIT_VEC64_ELEM_SZ)
+#define RX_SGE_MASK_LEN (NUM_RX_SGE / BIT_VEC64_ELEM_SZ)
#define RX_SGE_MASK_LEN_MASK (RX_SGE_MASK_LEN - 1)
#define NEXT_SGE_MASK_ELEM(el) (((el) + 1) & RX_SGE_MASK_LEN_MASK)
struct bnx2x_agg_info {
/*
- * First aggregation buffer is an skb, the following - are pages.
- * We will preallocate the skbs for each aggregation when
+ * First aggregation buffer is a data buffer, the following - are pages.
+ * We will preallocate the data buffer for each aggregation when
* we open the interface and will replace the BD at the consumer
* with this one when we receive the TPA_START CQE in order to
* keep the Rx BD ring consistent.
u16 parsing_flags;
u16 vlan_tag;
u16 len_on_bd;
+ u32 rxhash;
};
#define Q_STATS_OFFSET32(stat_name) \
__le16 fp_hc_idx;
u8 index; /* number in fp array */
+ u8 rx_queue; /* index for skb_record */
u8 cl_id; /* eth client id */
u8 cl_qzone_id;
u8 fw_sb_id; /* status block number in FW */
#define CHIP_PORT_MODE_NONE 0x2
#define CHIP_MODE(bp) (bp->common.chip_port_mode)
#define CHIP_MODE_IS_4_PORT(bp) (CHIP_MODE(bp) == CHIP_4_PORT_MODE)
+
+ u32 boot_mode;
};
/* IGU MSIX STATISTICS on 57712: 64 for VFs; 4 for PFs; 4 for Attentions */
u32 wb_comp;
u32 wb_data[4];
+
+ union drv_info_to_mcp drv_info_to_mcp;
};
#define bnx2x_sp(bp, var) (&bp->slowpath->var)
enum {
BNX2X_PORT_QUERY_IDX,
BNX2X_PF_QUERY_IDX,
+ BNX2X_FCOE_QUERY_IDX,
BNX2X_FIRST_QUEUE_QUERY_IDX,
};
struct bnx2x_fw_stats_req {
struct stats_query_header hdr;
- struct stats_query_entry query[STATS_QUERY_CMD_COUNT];
+ struct stats_query_entry query[FP_SB_MAX_E1x+
+ BNX2X_FIRST_QUEUE_QUERY_IDX];
};
struct bnx2x_fw_stats_data {
struct stats_counter storm_counters;
struct per_port_stats port;
struct per_pf_stats pf;
+ struct fcoe_statistics_params fcoe;
struct per_queue_stats queue_stats[1];
};
enum {
BNX2X_SP_RTNL_SETUP_TC,
BNX2X_SP_RTNL_TX_TIMEOUT,
+ BNX2X_SP_RTNL_FAN_FAILURE,
};
#define ETH_MAX_JUMBO_PACKET_SIZE 9600
/* Max supported alignment is 256 (8 shift) */
-#define BNX2X_RX_ALIGN_SHIFT ((L1_CACHE_SHIFT < 8) ? \
- L1_CACHE_SHIFT : 8)
- /* FW use 2 Cache lines Alignment for start packet and size */
-#define BNX2X_FW_RX_ALIGN (2 << BNX2X_RX_ALIGN_SHIFT)
+#define BNX2X_RX_ALIGN_SHIFT min(8, L1_CACHE_SHIFT)
+
+ /* FW uses 2 Cache lines Alignment for start packet and size
+ *
+ * We assume skb_build() uses sizeof(struct skb_shared_info) bytes
+ * at the end of skb->data, to avoid wasting a full cache line.
+ * This reduces memory use (skb->truesize).
+ */
+#define BNX2X_FW_RX_ALIGN_START (1UL << BNX2X_RX_ALIGN_SHIFT)
+
+#define BNX2X_FW_RX_ALIGN_END \
+ max(1UL << BNX2X_RX_ALIGN_SHIFT, \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
#define BNX2X_PXP_DRAM_ALIGN (BNX2X_RX_ALIGN_SHIFT - 5)
struct host_sp_status_block *def_status_blk;
#define NO_ISCSI_OOO_FLAG (1 << 13)
#define NO_ISCSI_FLAG (1 << 14)
#define NO_FCOE_FLAG (1 << 15)
+#define BC_SUPPORTS_PFC_STATS (1 << 17)
#define NO_ISCSI(bp) ((bp)->flags & NO_ISCSI_FLAG)
#define NO_ISCSI_OOO(bp) ((bp)->flags & NO_ISCSI_OOO_FLAG)
#define HW_PRTY_ASSERT_SET_4 (AEU_INPUTS_ATTN_BITS_PGLUE_PARITY_ERROR | \
AEU_INPUTS_ATTN_BITS_ATC_PARITY_ERROR)
-#define RSS_FLAGS(bp) \
- (TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV4_CAPABILITY | \
- TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV4_TCP_CAPABILITY | \
- TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV6_CAPABILITY | \
- TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV6_TCP_CAPABILITY | \
- (bp->multi_mode << \
- TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_MODE_SHIFT))
#define MULTI_MASK 0x7f
#define BNX2X_VPD_LEN 128
#define VENDOR_ID_LEN 4
+int bnx2x_close(struct net_device *dev);
+
/* Congestion management fairness mode */
#define CMNG_FNS_NONE 0
#define CMNG_FNS_MINMAX 1
void bnx2x_set_ethtool_ops(struct net_device *netdev);
void bnx2x_notify_link_changed(struct bnx2x *bp);
+
+
+#define BNX2X_MF_PROTOCOL(bp) \
+ ((bp)->mf_config[BP_VN(bp)] & FUNC_MF_CFG_PROTOCOL_MASK)
+
+#ifdef BCM_CNIC
+#define BNX2X_IS_MF_PROTOCOL_ISCSI(bp) \
+ (BNX2X_MF_PROTOCOL(bp) == FUNC_MF_CFG_PROTOCOL_ISCSI)
+
+#define IS_MF_ISCSI_SD(bp) (IS_MF_SD(bp) && BNX2X_IS_MF_PROTOCOL_ISCSI(bp))
+#endif
+
#endif /* bnx2x.h */
* @to: destination FP index
*
* Makes sure the contents of the bp->fp[to].napi is kept
- * intact.
+ * intact. This is done by first copying the napi struct from
+ * the target to the source, and then mem copying the entire
+ * source onto the target
*/
static inline void bnx2x_move_fp(struct bnx2x *bp, int from, int to)
{
struct bnx2x_fastpath *from_fp = &bp->fp[from];
struct bnx2x_fastpath *to_fp = &bp->fp[to];
- struct napi_struct orig_napi = to_fp->napi;
+
+ /* Copy the NAPI object as it has been already initialized */
+ from_fp->napi = to_fp->napi;
+
/* Move bnx2x_fastpath contents */
memcpy(to_fp, from_fp, sizeof(*to_fp));
to_fp->index = to;
-
- /* Restore the NAPI object as it has been already initialized */
- to_fp->napi = orig_napi;
}
int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */
* return idx of last bd freed
*/
static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
- u16 idx)
+ u16 idx, unsigned int *pkts_compl,
+ unsigned int *bytes_compl)
{
struct sw_tx_bd *tx_buf = &txdata->tx_buf_ring[idx];
struct eth_tx_start_bd *tx_start_bd;
/* release skb */
WARN_ON(!skb);
+ if (skb) {
+ (*pkts_compl)++;
+ (*bytes_compl) += skb->len;
+ }
dev_kfree_skb_any(skb);
tx_buf->first_bd = 0;
tx_buf->skb = NULL;
{
struct netdev_queue *txq;
u16 hw_cons, sw_cons, bd_cons = txdata->tx_bd_cons;
+ unsigned int pkts_compl = 0, bytes_compl = 0;
#ifdef BNX2X_STOP_ON_ERROR
if (unlikely(bp->panic))
" pkt_cons %u\n",
txdata->txq_index, hw_cons, sw_cons, pkt_cons);
- bd_cons = bnx2x_free_tx_pkt(bp, txdata, pkt_cons);
+ bd_cons = bnx2x_free_tx_pkt(bp, txdata, pkt_cons,
+ &pkts_compl, &bytes_compl);
+
sw_cons++;
}
+ netdev_tx_completed_queue(txq, pkts_compl, bytes_compl);
+
txdata->tx_pkt_cons = sw_cons;
txdata->tx_bd_cons = bd_cons;
fp->last_max_sge, fp->rx_sge_prod);
}
+/* Set Toeplitz hash value in the skb using the value from the
+ * CQE (calculated by HW).
+ */
+static u32 bnx2x_get_rxhash(const struct bnx2x *bp,
+ const struct eth_fast_path_rx_cqe *cqe)
+{
+ /* Set Toeplitz hash from CQE */
+ if ((bp->dev->features & NETIF_F_RXHASH) &&
+ (cqe->status_flags & ETH_FAST_PATH_RX_CQE_RSS_HASH_FLG))
+ return le32_to_cpu(cqe->rss_hash_result);
+ return 0;
+}
+
static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
- struct sk_buff *skb, u16 cons, u16 prod,
+ u16 cons, u16 prod,
struct eth_fast_path_rx_cqe *cqe)
{
struct bnx2x *bp = fp->bp;
if (tpa_info->tpa_state != BNX2X_TPA_STOP)
BNX2X_ERR("start of bin not in stop [%d]\n", queue);
- /* Try to map an empty skb from the aggregation info */
+ /* Try to map an empty data buffer from the aggregation info */
mapping = dma_map_single(&bp->pdev->dev,
- first_buf->skb->data,
+ first_buf->data + NET_SKB_PAD,
fp->rx_buf_size, DMA_FROM_DEVICE);
/*
* ...if it fails - move the skb from the consumer to the producer
if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
/* Move the BD from the consumer to the producer */
- bnx2x_reuse_rx_skb(fp, cons, prod);
+ bnx2x_reuse_rx_data(fp, cons, prod);
tpa_info->tpa_state = BNX2X_TPA_ERROR;
return;
}
- /* move empty skb from pool to prod */
- prod_rx_buf->skb = first_buf->skb;
+ /* move empty data from pool to prod */
+ prod_rx_buf->data = first_buf->data;
dma_unmap_addr_set(prod_rx_buf, mapping, mapping);
- /* point prod_bd to new skb */
+ /* point prod_bd to new data */
prod_bd->addr_hi = cpu_to_le32(U64_HI(mapping));
prod_bd->addr_lo = cpu_to_le32(U64_LO(mapping));
tpa_info->tpa_state = BNX2X_TPA_START;
tpa_info->len_on_bd = le16_to_cpu(cqe->len_on_bd);
tpa_info->placement_offset = cqe->placement_offset;
+ tpa_info->rxhash = bnx2x_get_rxhash(bp, cqe);
#ifdef BNX2X_STOP_ON_ERROR
fp->tpa_queue_used |= (1 << queue);
{
struct bnx2x_agg_info *tpa_info = &fp->tpa_info[queue];
struct sw_rx_bd *rx_buf = &tpa_info->first_buf;
- u8 pad = tpa_info->placement_offset;
+ u32 pad = tpa_info->placement_offset;
u16 len = tpa_info->len_on_bd;
- struct sk_buff *skb = rx_buf->skb;
+ struct sk_buff *skb = NULL;
+ u8 *data = rx_buf->data;
/* alloc new skb */
- struct sk_buff *new_skb;
+ u8 *new_data;
u8 old_tpa_state = tpa_info->tpa_state;
tpa_info->tpa_state = BNX2X_TPA_STOP;
if (old_tpa_state == BNX2X_TPA_ERROR)
goto drop;
- /* Try to allocate the new skb */
- new_skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size);
+ /* Try to allocate the new data */
+ new_data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
/* Unmap skb in the pool anyway, as we are going to change
pool entry status to BNX2X_TPA_STOP even if new skb allocation
fails. */
dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping),
fp->rx_buf_size, DMA_FROM_DEVICE);
+ if (likely(new_data))
+ skb = build_skb(data);
- if (likely(new_skb)) {
- prefetch(skb);
- prefetch(((char *)(skb)) + L1_CACHE_BYTES);
+ if (likely(skb)) {
#ifdef BNX2X_STOP_ON_ERROR
if (pad + len > fp->rx_buf_size) {
}
#endif
- skb_reserve(skb, pad);
+ skb_reserve(skb, pad + NET_SKB_PAD);
skb_put(skb, len);
+ skb->rxhash = tpa_info->rxhash;
skb->protocol = eth_type_trans(skb, bp->dev);
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- /* put new skb in bin */
- rx_buf->skb = new_skb;
+ /* put new data in bin */
+ rx_buf->data = new_data;
return;
}
fp->eth_q_stats.rx_skb_alloc_failed++;
}
-/* Set Toeplitz hash value in the skb using the value from the
- * CQE (calculated by HW).
- */
-static inline void bnx2x_set_skb_rxhash(struct bnx2x *bp, union eth_rx_cqe *cqe,
- struct sk_buff *skb)
-{
- /* Set Toeplitz hash from CQE */
- if ((bp->dev->features & NETIF_F_RXHASH) &&
- (cqe->fast_path_cqe.status_flags &
- ETH_FAST_PATH_RX_CQE_RSS_HASH_FLG))
- skb->rxhash =
- le32_to_cpu(cqe->fast_path_cqe.rss_hash_result);
-}
int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
{
u8 cqe_fp_flags;
enum eth_rx_cqe_type cqe_fp_type;
u16 len, pad;
+ u8 *data;
#ifdef BNX2X_STOP_ON_ERROR
if (unlikely(bp->panic))
bd_prod = RX_BD(bd_prod);
bd_cons = RX_BD(bd_cons);
- /* Prefetch the page containing the BD descriptor
- at producer's index. It will be needed when new skb is
- allocated */
- prefetch((void *)(PAGE_ALIGN((unsigned long)
- (&fp->rx_desc_ring[bd_prod])) -
- PAGE_SIZE + 1));
-
cqe = &fp->rx_comp_ring[comp_ring_cons];
cqe_fp = &cqe->fast_path_cqe;
cqe_fp_flags = cqe_fp->type_error_flags;
if (unlikely(CQE_TYPE_SLOW(cqe_fp_type))) {
bnx2x_sp_event(fp, cqe);
goto next_cqe;
+ }
+ rx_buf = &fp->rx_buf_ring[bd_cons];
+ data = rx_buf->data;
- /* this is an rx packet */
- } else {
- rx_buf = &fp->rx_buf_ring[bd_cons];
- skb = rx_buf->skb;
- prefetch(skb);
-
- if (!CQE_TYPE_FAST(cqe_fp_type)) {
+ if (!CQE_TYPE_FAST(cqe_fp_type)) {
#ifdef BNX2X_STOP_ON_ERROR
- /* sanity check */
- if (fp->disable_tpa &&
- (CQE_TYPE_START(cqe_fp_type) ||
- CQE_TYPE_STOP(cqe_fp_type)))
- BNX2X_ERR("START/STOP packet while "
- "disable_tpa type %x\n",
- CQE_TYPE(cqe_fp_type));
+ /* sanity check */
+ if (fp->disable_tpa &&
+ (CQE_TYPE_START(cqe_fp_type) ||
+ CQE_TYPE_STOP(cqe_fp_type)))
+ BNX2X_ERR("START/STOP packet while "
+ "disable_tpa type %x\n",
+ CQE_TYPE(cqe_fp_type));
#endif
- if (CQE_TYPE_START(cqe_fp_type)) {
- u16 queue = cqe_fp->queue_index;
- DP(NETIF_MSG_RX_STATUS,
- "calling tpa_start on queue %d\n",
- queue);
+ if (CQE_TYPE_START(cqe_fp_type)) {
+ u16 queue = cqe_fp->queue_index;
+ DP(NETIF_MSG_RX_STATUS,
+ "calling tpa_start on queue %d\n",
+ queue);
- bnx2x_tpa_start(fp, queue, skb,
- bd_cons, bd_prod,
- cqe_fp);
-
- /* Set Toeplitz hash for LRO skb */
- bnx2x_set_skb_rxhash(bp, cqe, skb);
-
- goto next_rx;
-
- } else {
- u16 queue =
- cqe->end_agg_cqe.queue_index;
- DP(NETIF_MSG_RX_STATUS,
- "calling tpa_stop on queue %d\n",
- queue);
-
- bnx2x_tpa_stop(bp, fp, queue,
- &cqe->end_agg_cqe,
- comp_ring_cons);
+ bnx2x_tpa_start(fp, queue,
+ bd_cons, bd_prod,
+ cqe_fp);
+ goto next_rx;
+ } else {
+ u16 queue =
+ cqe->end_agg_cqe.queue_index;
+ DP(NETIF_MSG_RX_STATUS,
+ "calling tpa_stop on queue %d\n",
+ queue);
+
+ bnx2x_tpa_stop(bp, fp, queue,
+ &cqe->end_agg_cqe,
+ comp_ring_cons);
#ifdef BNX2X_STOP_ON_ERROR
- if (bp->panic)
- return 0;
+ if (bp->panic)
+ return 0;
#endif
- bnx2x_update_sge_prod(fp, cqe_fp);
- goto next_cqe;
- }
+ bnx2x_update_sge_prod(fp, cqe_fp);
+ goto next_cqe;
}
- /* non TPA */
- len = le16_to_cpu(cqe_fp->pkt_len);
- pad = cqe_fp->placement_offset;
- dma_sync_single_for_cpu(&bp->pdev->dev,
+ }
+ /* non TPA */
+ len = le16_to_cpu(cqe_fp->pkt_len);
+ pad = cqe_fp->placement_offset;
+ dma_sync_single_for_cpu(&bp->pdev->dev,
dma_unmap_addr(rx_buf, mapping),
- pad + RX_COPY_THRESH,
- DMA_FROM_DEVICE);
- prefetch(((char *)(skb)) + L1_CACHE_BYTES);
+ pad + RX_COPY_THRESH,
+ DMA_FROM_DEVICE);
+ pad += NET_SKB_PAD;
+ prefetch(data + pad); /* speedup eth_type_trans() */
+ /* is this an error packet? */
+ if (unlikely(cqe_fp_flags & ETH_RX_ERROR_FALGS)) {
+ DP(NETIF_MSG_RX_ERR,
+ "ERROR flags %x rx packet %u\n",
+ cqe_fp_flags, sw_comp_cons);
+ fp->eth_q_stats.rx_err_discard_pkt++;
+ goto reuse_rx;
+ }
- /* is this an error packet? */
- if (unlikely(cqe_fp_flags & ETH_RX_ERROR_FALGS)) {
+ /* Since we don't have a jumbo ring
+ * copy small packets if mtu > 1500
+ */
+ if ((bp->dev->mtu > ETH_MAX_PACKET_SIZE) &&
+ (len <= RX_COPY_THRESH)) {
+ skb = netdev_alloc_skb_ip_align(bp->dev, len);
+ if (skb == NULL) {
DP(NETIF_MSG_RX_ERR,
- "ERROR flags %x rx packet %u\n",
- cqe_fp_flags, sw_comp_cons);
- fp->eth_q_stats.rx_err_discard_pkt++;
+ "ERROR packet dropped because of alloc failure\n");
+ fp->eth_q_stats.rx_skb_alloc_failed++;
goto reuse_rx;
}
-
- /* Since we don't have a jumbo ring
- * copy small packets if mtu > 1500
- */
- if ((bp->dev->mtu > ETH_MAX_PACKET_SIZE) &&
- (len <= RX_COPY_THRESH)) {
- struct sk_buff *new_skb;
-
- new_skb = netdev_alloc_skb(bp->dev, len + pad);
- if (new_skb == NULL) {
- DP(NETIF_MSG_RX_ERR,
- "ERROR packet dropped "
- "because of alloc failure\n");
- fp->eth_q_stats.rx_skb_alloc_failed++;
- goto reuse_rx;
- }
-
- /* aligned copy */
- skb_copy_from_linear_data_offset(skb, pad,
- new_skb->data + pad, len);
- skb_reserve(new_skb, pad);
- skb_put(new_skb, len);
-
- bnx2x_reuse_rx_skb(fp, bd_cons, bd_prod);
-
- skb = new_skb;
-
- } else
- if (likely(bnx2x_alloc_rx_skb(bp, fp, bd_prod) == 0)) {
+ memcpy(skb->data, data + pad, len);
+ bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
+ } else {
+ if (likely(bnx2x_alloc_rx_data(bp, fp, bd_prod) == 0)) {
dma_unmap_single(&bp->pdev->dev,
- dma_unmap_addr(rx_buf, mapping),
+ dma_unmap_addr(rx_buf, mapping),
fp->rx_buf_size,
DMA_FROM_DEVICE);
+ skb = build_skb(data);
+ if (unlikely(!skb)) {
+ kfree(data);
+ fp->eth_q_stats.rx_skb_alloc_failed++;
+ goto next_rx;
+ }
skb_reserve(skb, pad);
- skb_put(skb, len);
-
} else {
DP(NETIF_MSG_RX_ERR,
"ERROR packet dropped because "
"of alloc failure\n");
fp->eth_q_stats.rx_skb_alloc_failed++;
reuse_rx:
- bnx2x_reuse_rx_skb(fp, bd_cons, bd_prod);
+ bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
goto next_rx;
}
+ }
- skb->protocol = eth_type_trans(skb, bp->dev);
+ skb_put(skb, len);
+ skb->protocol = eth_type_trans(skb, bp->dev);
- /* Set Toeplitz hash for a none-LRO skb */
- bnx2x_set_skb_rxhash(bp, cqe, skb);
+ /* Set Toeplitz hash for a none-LRO skb */
+ skb->rxhash = bnx2x_get_rxhash(bp, cqe_fp);
- skb_checksum_none_assert(skb);
+ skb_checksum_none_assert(skb);
- if (bp->dev->features & NETIF_F_RXCSUM) {
+ if (bp->dev->features & NETIF_F_RXCSUM) {
- if (likely(BNX2X_RX_CSUM_OK(cqe)))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- fp->eth_q_stats.hw_csum_err++;
- }
+ if (likely(BNX2X_RX_CSUM_OK(cqe)))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ else
+ fp->eth_q_stats.hw_csum_err++;
}
- skb_record_rx_queue(skb, fp->index);
+ skb_record_rx_queue(skb, fp->rx_queue);
if (le16_to_cpu(cqe_fp->pars_flags.flags) &
PARSING_FLAGS_VLAN)
next_rx:
- rx_buf->skb = NULL;
+ rx_buf->data = NULL;
bd_cons = NEXT_RX_IDX(bd_cons);
bd_prod = NEXT_RX_IDX(bd_prod);
struct sw_rx_bd *first_buf =
&tpa_info->first_buf;
- first_buf->skb = netdev_alloc_skb(bp->dev,
- fp->rx_buf_size);
- if (!first_buf->skb) {
+ first_buf->data = kmalloc(fp->rx_buf_size + NET_SKB_PAD,
+ GFP_ATOMIC);
+ if (!first_buf->data) {
BNX2X_ERR("Failed to allocate TPA "
"skb pool for queue[%d] - "
"disabling TPA on this "
struct bnx2x_fastpath *fp = &bp->fp[i];
for_each_cos_in_tx_queue(fp, cos) {
struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+ unsigned pkts_compl = 0, bytes_compl = 0;
- u16 bd_cons = txdata->tx_bd_cons;
u16 sw_prod = txdata->tx_pkt_prod;
u16 sw_cons = txdata->tx_pkt_cons;
while (sw_cons != sw_prod) {
- bd_cons = bnx2x_free_tx_pkt(bp, txdata,
- TX_BD(sw_cons));
+ bnx2x_free_tx_pkt(bp, txdata, TX_BD(sw_cons),
+ &pkts_compl, &bytes_compl);
sw_cons++;
}
+ netdev_tx_reset_queue(
+ netdev_get_tx_queue(bp->dev, txdata->txq_index));
}
}
}
for (i = 0; i < NUM_RX_BD; i++) {
struct sw_rx_bd *rx_buf = &fp->rx_buf_ring[i];
- struct sk_buff *skb = rx_buf->skb;
+ u8 *data = rx_buf->data;
- if (skb == NULL)
+ if (data == NULL)
continue;
dma_unmap_single(&bp->pdev->dev,
dma_unmap_addr(rx_buf, mapping),
fp->rx_buf_size, DMA_FROM_DEVICE);
- rx_buf->skb = NULL;
- dev_kfree_skb(skb);
+ rx_buf->data = NULL;
+ kfree(data);
}
}
break;
}
+#ifdef BCM_CNIC
+ /* override in ISCSI SD mod */
+ if (IS_MF_ISCSI_SD(bp))
+ bp->num_queues = 1;
+#endif
/* Add special queues */
bp->num_queues += NON_ETH_CONTEXT_USE;
}
for_each_queue(bp, i) {
struct bnx2x_fastpath *fp = &bp->fp[i];
+ u32 mtu;
/* Always use a mini-jumbo MTU for the FCoE L2 ring */
if (IS_FCOE_IDX(i))
* IP_HEADER_ALIGNMENT_PADDING to prevent a buffer
* overrun attack.
*/
- fp->rx_buf_size =
- BNX2X_FCOE_MINI_JUMBO_MTU + ETH_OVREHEAD +
- BNX2X_FW_RX_ALIGN + IP_HEADER_ALIGNMENT_PADDING;
+ mtu = BNX2X_FCOE_MINI_JUMBO_MTU;
else
- fp->rx_buf_size =
- bp->dev->mtu + ETH_OVREHEAD +
- BNX2X_FW_RX_ALIGN + IP_HEADER_ALIGNMENT_PADDING;
+ mtu = bp->dev->mtu;
+ fp->rx_buf_size = BNX2X_FW_RX_ALIGN_START +
+ IP_HEADER_ALIGNMENT_PADDING +
+ ETH_OVREHEAD +
+ mtu +
+ BNX2X_FW_RX_ALIGN_END;
+ /* Note : rx_buf_size doesnt take into account NET_SKB_PAD */
}
}
if (bp->multi_mode != ETH_RSS_MODE_DISABLED) {
for (i = 0; i < sizeof(ind_table); i++)
ind_table[i] =
- bp->fp->cl_id + (i % num_eth_queues);
+ bp->fp->cl_id +
+ ethtool_rxfh_indir_default(i, num_eth_queues);
}
/*
break;
}
- if (!bp->port.pmf)
+ if (bp->port.pmf)
+ bnx2x_update_drv_flags(bp, DRV_FLAGS_DCB_CONFIGURED, 0);
+ else
bnx2x__link_status_update(bp);
/* start the timer */
mod_timer(&bp->timer, jiffies + bp->current_interval);
#ifdef BCM_CNIC
+ /* re-read iscsi info */
+ bnx2x_get_iscsi_info(bp);
bnx2x_setup_cnic_irq_info(bp);
if (bp->state == BNX2X_STATE_OPEN)
bnx2x_cnic_notify(bp, CNIC_CTL_START_CMD);
mapping = skb_frag_dma_map(&bp->pdev->dev, frag, 0,
skb_frag_size(frag), DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
+ unsigned int pkts_compl = 0, bytes_compl = 0;
DP(NETIF_MSG_TX_QUEUED, "Unable to map page - "
"dropping packet...\n");
*/
first_bd->nbd = cpu_to_le16(nbd);
bnx2x_free_tx_pkt(bp, txdata,
- TX_BD(txdata->tx_pkt_prod));
+ TX_BD(txdata->tx_pkt_prod),
+ &pkts_compl, &bytes_compl);
return NETDEV_TX_OK;
}
pbd_e2->parsing_data);
DP(NETIF_MSG_TX_QUEUED, "doorbell: nbd %d bd %u\n", nbd, bd_prod);
+ netdev_tx_sent_queue(txq, skb->len);
+
txdata->tx_pkt_prod++;
/*
* Make sure that the BD data is updated before updating the producer
struct bnx2x *bp = netdev_priv(dev);
int rc = 0;
- if (!is_valid_ether_addr((u8 *)(addr->sa_data)))
+ if (!bnx2x_is_valid_ether_addr(bp, addr->sa_data))
return -EINVAL;
+#ifdef BCM_CNIC
+ if (IS_MF_ISCSI_SD(bp) && !is_zero_ether_addr(addr->sa_data))
+ return -EINVAL;
+#endif
+
if (netif_running(dev)) {
rc = bnx2x_set_eth_mac(bp, false);
if (rc)
u8 cos;
int rx_ring_size = 0;
- /* if rx_ring_size specified - use it */
+#ifdef BCM_CNIC
+ if (IS_MF_ISCSI_SD(bp)) {
+ rx_ring_size = MIN_RX_SIZE_NONTPA;
+ bp->rx_ring_size = rx_ring_size;
+ } else
+#endif
if (!bp->rx_ring_size) {
rx_ring_size = MAX_RX_AVAIL/BNX2X_NUM_RX_QUEUES(bp);
MIN_RX_SIZE_TPA, rx_ring_size);
bp->rx_ring_size = rx_ring_size;
- } else
+ } else /* if rx_ring_size specified - use it */
rx_ring_size = bp->rx_ring_size;
/* Common */
msix_table_size = bp->igu_sb_cnt + 1;
/* fp array: RSS plus CNIC related L2 queues */
- fp = kzalloc((BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE) *
+ fp = kcalloc(BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE,
sizeof(*fp), GFP_KERNEL);
if (!fp)
goto alloc_err;
bp->fp = fp;
/* msix table */
- tbl = kzalloc(msix_table_size * sizeof(*tbl), GFP_KERNEL);
+ tbl = kcalloc(msix_table_size, sizeof(*tbl), GFP_KERNEL);
if (!tbl)
goto alloc_err;
bp->msix_table = tbl;
return bnx2x_reload_if_running(dev);
}
-u32 bnx2x_fix_features(struct net_device *dev, u32 features)
+netdev_features_t bnx2x_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct bnx2x *bp = netdev_priv(dev);
return features;
}
-int bnx2x_set_features(struct net_device *dev, u32 features)
+int bnx2x_set_features(struct net_device *dev, netdev_features_t features)
{
struct bnx2x *bp = netdev_priv(dev);
u32 flags = bp->flags;
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include "bnx2x.h"
*/
int bnx2x_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type);
#endif
-u32 bnx2x_fix_features(struct net_device *dev, u32 features);
-int bnx2x_set_features(struct net_device *dev, u32 features);
+netdev_features_t bnx2x_fix_features(struct net_device *dev,
+ netdev_features_t features);
+int bnx2x_set_features(struct net_device *dev, netdev_features_t features);
/**
* bnx2x_tx_timeout - tx timeout netdev callback
static inline void bnx2x_init_sge_ring_bit_mask(struct bnx2x_fastpath *fp)
{
/* Set the mask to all 1-s: it's faster to compare to 0 than to 0xf-s */
- memset(fp->sge_mask, 0xff,
- (NUM_RX_SGE >> BIT_VEC64_ELEM_SHIFT)*sizeof(u64));
+ memset(fp->sge_mask, 0xff, sizeof(fp->sge_mask));
/* Clear the two last indices in the page to 1:
these are the indices that correspond to the "next" element,
return 0;
}
-static inline int bnx2x_alloc_rx_skb(struct bnx2x *bp,
- struct bnx2x_fastpath *fp, u16 index)
+static inline int bnx2x_alloc_rx_data(struct bnx2x *bp,
+ struct bnx2x_fastpath *fp, u16 index)
{
- struct sk_buff *skb;
+ u8 *data;
struct sw_rx_bd *rx_buf = &fp->rx_buf_ring[index];
struct eth_rx_bd *rx_bd = &fp->rx_desc_ring[index];
dma_addr_t mapping;
- skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size);
- if (unlikely(skb == NULL))
+ data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
+ if (unlikely(data == NULL))
return -ENOMEM;
- mapping = dma_map_single(&bp->pdev->dev, skb->data, fp->rx_buf_size,
+ mapping = dma_map_single(&bp->pdev->dev, data + NET_SKB_PAD,
+ fp->rx_buf_size,
DMA_FROM_DEVICE);
if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
- dev_kfree_skb_any(skb);
+ kfree(data);
return -ENOMEM;
}
- rx_buf->skb = skb;
+ rx_buf->data = data;
dma_unmap_addr_set(rx_buf, mapping, mapping);
rx_bd->addr_hi = cpu_to_le32(U64_HI(mapping));
return 0;
}
-/* note that we are not allocating a new skb,
+/* note that we are not allocating a new buffer,
* we are just moving one from cons to prod
* we are not creating a new mapping,
* so there is no need to check for dma_mapping_error().
*/
-static inline void bnx2x_reuse_rx_skb(struct bnx2x_fastpath *fp,
+static inline void bnx2x_reuse_rx_data(struct bnx2x_fastpath *fp,
u16 cons, u16 prod)
{
struct sw_rx_bd *cons_rx_buf = &fp->rx_buf_ring[cons];
dma_unmap_addr_set(prod_rx_buf, mapping,
dma_unmap_addr(cons_rx_buf, mapping));
- prod_rx_buf->skb = cons_rx_buf->skb;
+ prod_rx_buf->data = cons_rx_buf->data;
*prod_bd = *cons_bd;
}
for (i = 0; i < last; i++) {
struct bnx2x_agg_info *tpa_info = &fp->tpa_info[i];
struct sw_rx_bd *first_buf = &tpa_info->first_buf;
- struct sk_buff *skb = first_buf->skb;
+ u8 *data = first_buf->data;
- if (skb == NULL) {
+ if (data == NULL) {
DP(NETIF_MSG_IFDOWN, "tpa bin %d empty on free\n", i);
continue;
}
dma_unmap_single(&bp->pdev->dev,
dma_unmap_addr(first_buf, mapping),
fp->rx_buf_size, DMA_FROM_DEVICE);
- dev_kfree_skb(skb);
- first_buf->skb = NULL;
+ kfree(data);
+ first_buf->data = NULL;
}
}
* fp->eth_q_stats.rx_skb_alloc_failed = 0
*/
for (i = 0; i < rx_ring_size; i++) {
- if (bnx2x_alloc_rx_skb(bp, fp, ring_prod) < 0) {
+ if (bnx2x_alloc_rx_data(bp, fp, ring_prod) < 0) {
fp->eth_q_stats.rx_skb_alloc_failed++;
continue;
}
struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
unsigned long q_type = 0;
+ bnx2x_fcoe(bp, rx_queue) = BNX2X_NUM_ETH_QUEUES(bp);
bnx2x_fcoe(bp, cl_id) = bnx2x_cnic_eth_cl_id(bp,
BNX2X_FCOE_ETH_CL_ID_IDX);
/** Current BNX2X_FCOE_ETH_CID deffinition implies not more than
return max_cfg;
}
+/**
+ * bnx2x_get_iscsi_info - update iSCSI params according to licensing info.
+ *
+ * @bp: driver handle
+ *
+ */
+void bnx2x_get_iscsi_info(struct bnx2x *bp);
+
+/* returns func by VN for current port */
+static inline int func_by_vn(struct bnx2x *bp, int vn)
+{
+ return 2 * vn + BP_PORT(bp);
+}
+
+/**
+ * bnx2x_link_sync_notify - send notification to other functions.
+ *
+ * @bp: driver handle
+ *
+ */
+static inline void bnx2x_link_sync_notify(struct bnx2x *bp)
+{
+ int func;
+ int vn;
+
+ /* Set the attention towards other drivers on the same port */
+ for (vn = VN_0; vn < BP_MAX_VN_NUM(bp); vn++) {
+ if (vn == BP_VN(bp))
+ continue;
+
+ func = func_by_vn(bp, vn);
+ REG_WR(bp, MISC_REG_AEU_GENERAL_ATTN_0 +
+ (LINK_SYNC_ATTENTION_BIT_FUNC_0 + func)*4, 1);
+ }
+}
+
+/**
+ * bnx2x_update_drv_flags - update flags in shmem
+ *
+ * @bp: driver handle
+ * @flags: flags to update
+ * @set: set or clear
+ *
+ */
+static inline void bnx2x_update_drv_flags(struct bnx2x *bp, u32 flags, u32 set)
+{
+ if (SHMEM2_HAS(bp, drv_flags)) {
+ u32 drv_flags;
+ bnx2x_acquire_hw_lock(bp, HW_LOCK_DRV_FLAGS);
+ drv_flags = SHMEM2_RD(bp, drv_flags);
+
+ if (set)
+ SET_FLAGS(drv_flags, flags);
+ else
+ RESET_FLAGS(drv_flags, flags);
+
+ SHMEM2_WR(bp, drv_flags, drv_flags);
+ DP(NETIF_MSG_HW, "drv_flags 0x%08x\n", drv_flags);
+ bnx2x_release_hw_lock(bp, HW_LOCK_DRV_FLAGS);
+ }
+}
+
+static inline bool bnx2x_is_valid_ether_addr(struct bnx2x *bp, u8 *addr)
+{
+ if (is_valid_ether_addr(addr))
+ return true;
+#ifdef BCM_CNIC
+ if (is_zero_ether_addr(addr) && IS_MF_ISCSI_SD(bp))
+ return true;
+#endif
+ return false;
+}
+
#endif /* BNX2X_CMN_H */
}
#endif
-static inline void bnx2x_update_drv_flags(struct bnx2x *bp, u32 flags, u32 set)
-{
- if (SHMEM2_HAS(bp, drv_flags)) {
- u32 drv_flags;
- bnx2x_acquire_hw_lock(bp, HW_LOCK_DRV_FLAGS);
- drv_flags = SHMEM2_RD(bp, drv_flags);
-
- if (set)
- SET_FLAGS(drv_flags, flags);
- else
- RESET_FLAGS(drv_flags, flags);
-
- SHMEM2_WR(bp, drv_flags, drv_flags);
- DP(NETIF_MSG_HW, "drv_flags 0x%08x\n", drv_flags);
- bnx2x_release_hw_lock(bp, HW_LOCK_DRV_FLAGS);
- }
-}
-
static inline void bnx2x_dcbx_update_tc_mapping(struct bnx2x *bp)
{
u8 prio, cos;
/* mark DCBX result for PMF migration */
bnx2x_update_drv_flags(bp, DRV_FLAGS_DCB_CONFIGURED, 1);
#ifdef BCM_DCBNL
- /**
+ /*
* Add new app tlvs to dcbnl
*/
bnx2x_dcbnl_update_applist(bp, false);
#endif
- bnx2x_dcbx_stop_hw_tx(bp);
-
- /* reconfigure the netdevice with the results of the new
+ /*
+ * reconfigure the netdevice with the results of the new
* dcbx negotiation.
*/
bnx2x_dcbx_update_tc_mapping(bp);
+ /*
+ * allow other funtions to update their netdevices
+ * accordingly
+ */
+ if (IS_MF(bp))
+ bnx2x_link_sync_notify(bp);
+
+ bnx2x_dcbx_stop_hw_tx(bp);
+
return;
}
case BNX2X_DCBX_STATE_TX_PAUSED:
bnx2x_dcbx_update_ets_params(bp);
bnx2x_dcbx_resume_hw_tx(bp);
+
return;
case BNX2X_DCBX_STATE_TX_RELEASED:
DP(NETIF_MSG_LINK, "BNX2X_DCBX_STATE_TX_RELEASED\n");
/*For IEEE admin_recommendation_bw_precentage
*For IEEE admin_recommendation_ets_pg */
af->pfc.pri_en_bitmap = (u8)dp->admin_pfc_bitmap;
- for (i = 0; i < 4; i++) {
+ for (i = 0; i < DCBX_CONFIG_MAX_APP_PROTOCOL; i++) {
if (dp->admin_priority_app_table[i].valid) {
struct bnx2x_admin_priority_app_table *table =
dp->admin_priority_app_table;
void bnx2x_dcbx_set_state(struct bnx2x *bp, bool dcb_on, u32 dcbx_enabled)
{
- if (!CHIP_IS_E1x(bp) && !CHIP_IS_E3(bp)) {
+ if (!CHIP_IS_E1x(bp)) {
bp->dcb_state = dcb_on;
bp->dcbx_enabled = dcbx_enabled;
} else {
void bnx2x_dcbx_pmf_update(struct bnx2x *bp)
{
/* if we need to syncronize DCBX result from prev PMF
- * read it from shmem and update bp accordingly
+ * read it from shmem and update bp and netdev accordingly
*/
if (SHMEM2_HAS(bp, drv_flags) &&
GET_FLAGS(SHMEM2_RD(bp, drv_flags), DRV_FLAGS_DCB_CONFIGURED)) {
bp->dcbx_error);
bnx2x_get_dcbx_drv_param(bp, &bp->dcbx_local_feat,
bp->dcbx_error);
+#ifdef BCM_DCBNL
+ /*
+ * Add new app tlvs to dcbnl
+ */
+ bnx2x_dcbnl_update_applist(bp, false);
+ /*
+ * Send a notification for the new negotiated parameters
+ */
+ dcbnl_cee_notify(bp->dev, RTM_GETDCB, DCB_CMD_CEE_GET, 0, 0);
+#endif
+ /*
+ * reconfigure the netdevice with the results of the new
+ * dcbx negotiation.
+ */
+ bnx2x_dcbx_update_tc_mapping(bp);
+
}
}
int i, ff;
/* iterate over the app entries looking for idtype and idval */
- for (i = 0, ff = -1; i < 4; i++) {
+ for (i = 0, ff = -1; i < DCBX_CONFIG_MAX_APP_PROTOCOL; i++) {
struct bnx2x_admin_priority_app_table *app_ent =
&bp->dcbx_config_params.admin_priority_app_table[i];
if (bnx2x_admin_app_is_equal(app_ent, idtype, idval))
if (ff < 0 && !app_ent->valid)
ff = i;
}
- if (i < 4)
+ if (i < DCBX_CONFIG_MAX_APP_PROTOCOL)
/* if found overwrite up */
bp->dcbx_config_params.
admin_priority_app_table[i].priority = up;
u32 app_id;
};
+#define DCBX_CONFIG_MAX_APP_PROTOCOL 4
struct bnx2x_config_dcbx_params {
u32 overwrite_settings;
u32 admin_dcbx_version;
u32 admin_recommendation_bw_precentage[8];
u32 admin_recommendation_ets_pg[8];
u32 admin_pfc_bitmap;
- struct bnx2x_admin_priority_app_table admin_priority_app_table[4];
+ struct bnx2x_admin_priority_app_table
+ admin_priority_app_table[DCBX_CONFIG_MAX_APP_PROTOCOL];
u32 admin_default_priority;
};
4, STATS_FLAGS_PORT, "rx_filtered_packets" },
{ STATS_OFFSET32(mf_tag_discard),
4, STATS_FLAGS_PORT, "rx_mf_tag_discard" },
+ { STATS_OFFSET32(pfc_frames_received_hi),
+ 8, STATS_FLAGS_PORT, "pfc_frames_received" },
+ { STATS_OFFSET32(pfc_frames_sent_hi),
+ 8, STATS_FLAGS_PORT, "pfc_frames_sent" },
{ STATS_OFFSET32(brb_drop_hi),
8, STATS_FLAGS_PORT, "rx_brb_discard" },
{ STATS_OFFSET32(brb_truncate_hi),
DP(NETIF_MSG_LINK, "Unsupported port type\n");
return -EINVAL;
}
- /* Save new config in case command complete successuly */
+ /* Save new config in case command complete successully */
new_multi_phy_config = bp->link_params.multi_phy_config;
/* Get the new cfg_idx */
cfg_idx = bnx2x_get_link_cfg_idx(bp);
struct bnx2x *bp = netdev_priv(dev);
u8 phy_fw_ver[PHY_FW_VER_LEN];
- strcpy(info->driver, DRV_MODULE_NAME);
- strcpy(info->version, DRV_MODULE_VERSION);
+ strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
phy_fw_ver[0] = '\0';
if (bp->port.pmf) {
bnx2x_release_phy_lock(bp);
}
- strncpy(info->fw_version, bp->fw_ver, 32);
+ strlcpy(info->fw_version, bp->fw_ver, sizeof(info->fw_version));
snprintf(info->fw_version + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
"bc %d.%d.%d%s%s",
(bp->common.bc_ver & 0xff0000) >> 16,
(bp->common.bc_ver & 0xff00) >> 8,
(bp->common.bc_ver & 0xff),
((phy_fw_ver[0] != '\0') ? " phy " : ""), phy_fw_ver);
- strcpy(info->bus_info, pci_name(bp->pdev));
+ strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
info->n_stats = BNX2X_NUM_STATS;
info->testinfo_len = BNX2X_NUM_TESTS;
info->eedump_len = bp->common.flash_size;
struct sw_rx_bd *rx_buf;
u16 len;
int rc = -ENODEV;
+ u8 *data;
+ struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txdata->txq_index);
/* check the loopback mode */
switch (loopback_mode) {
return -EINVAL;
break;
case BNX2X_MAC_LOOPBACK:
- bp->link_params.loopback_mode = CHIP_IS_E3(bp) ?
- LOOPBACK_XMAC : LOOPBACK_BMAC;
+ if (CHIP_IS_E3(bp)) {
+ int cfg_idx = bnx2x_get_link_cfg_idx(bp);
+ if (bp->port.supported[cfg_idx] &
+ (SUPPORTED_10000baseT_Full |
+ SUPPORTED_20000baseMLD2_Full |
+ SUPPORTED_20000baseKR2_Full))
+ bp->link_params.loopback_mode = LOOPBACK_XMAC;
+ else
+ bp->link_params.loopback_mode = LOOPBACK_UMAC;
+ } else
+ bp->link_params.loopback_mode = LOOPBACK_BMAC;
+
bnx2x_phy_init(&bp->link_params, &bp->link_vars);
break;
default:
tx_start_idx = le16_to_cpu(*txdata->tx_cons_sb);
rx_start_idx = le16_to_cpu(*fp_rx->rx_cons_sb);
+ netdev_tx_sent_queue(txq, skb->len);
+
pkt_prod = txdata->tx_pkt_prod++;
tx_buf = &txdata->tx_buf_ring[TX_BD(pkt_prod)];
tx_buf->first_bd = txdata->tx_bd_prod;
dma_sync_single_for_cpu(&bp->pdev->dev,
dma_unmap_addr(rx_buf, mapping),
fp_rx->rx_buf_size, DMA_FROM_DEVICE);
- skb = rx_buf->skb;
- skb_reserve(skb, cqe->fast_path_cqe.placement_offset);
+ data = rx_buf->data + NET_SKB_PAD + cqe->fast_path_cqe.placement_offset;
for (i = ETH_HLEN; i < pkt_size; i++)
- if (*(skb->data + i) != (unsigned char) (i & 0xff))
+ if (*(data + i) != (unsigned char) (i & 0xff))
goto test_loopback_rx_exit;
rc = 0;
}
}
-static int bnx2x_get_rxfh_indir(struct net_device *dev,
- struct ethtool_rxfh_indir *indir)
+static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
+{
+ struct bnx2x *bp = netdev_priv(dev);
+
+ return (bp->multi_mode == ETH_RSS_MODE_DISABLED ?
+ 0 : T_ETH_INDIRECTION_TABLE_SIZE);
+}
+
+static int bnx2x_get_rxfh_indir(struct net_device *dev, u32 *indir)
{
struct bnx2x *bp = netdev_priv(dev);
- size_t copy_size =
- min_t(size_t, indir->size, T_ETH_INDIRECTION_TABLE_SIZE);
u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
size_t i;
- if (bp->multi_mode == ETH_RSS_MODE_DISABLED)
- return -EOPNOTSUPP;
-
/* Get the current configuration of the RSS indirection table */
bnx2x_get_rss_ind_table(&bp->rss_conf_obj, ind_table);
* align the returned table to the Client ID of the leading RSS
* queue.
*/
- for (i = 0; i < copy_size; i++)
- indir->ring_index[i] = ind_table[i] - bp->fp->cl_id;
-
- indir->size = T_ETH_INDIRECTION_TABLE_SIZE;
+ for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++)
+ indir[i] = ind_table[i] - bp->fp->cl_id;
return 0;
}
-static int bnx2x_set_rxfh_indir(struct net_device *dev,
- const struct ethtool_rxfh_indir *indir)
+static int bnx2x_set_rxfh_indir(struct net_device *dev, const u32 *indir)
{
struct bnx2x *bp = netdev_priv(dev);
size_t i;
u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
- u32 num_eth_queues = BNX2X_NUM_ETH_QUEUES(bp);
-
- if (bp->multi_mode == ETH_RSS_MODE_DISABLED)
- return -EOPNOTSUPP;
-
- /* validate the size */
- if (indir->size != T_ETH_INDIRECTION_TABLE_SIZE)
- return -EINVAL;
for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
- /* validate the indices */
- if (indir->ring_index[i] >= num_eth_queues)
- return -EINVAL;
/*
* The same as in bnx2x_get_rxfh_indir: we can't use a memcpy()
* as an internal storage of an indirection table is a u8 array
* align the received table to the Client ID of the leading RSS
* queue
*/
- ind_table[i] = indir->ring_index[i] + bp->fp->cl_id;
+ ind_table[i] = indir[i] + bp->fp->cl_id;
}
return bnx2x_config_rss_pf(bp, ind_table, false);
.set_phys_id = bnx2x_set_phys_id,
.get_ethtool_stats = bnx2x_get_ethtool_stats,
.get_rxnfc = bnx2x_get_rxnfc,
+ .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size,
.get_rxfh_indir = bnx2x_get_rxfh_indir,
.set_rxfh_indir = bnx2x_set_rxfh_indir,
};
#define DRV_MSG_CODE_VRFY_SPECIFIC_PHY_OPT_MDL 0xa1000000
#define REQ_BC_VER_4_VRFY_SPECIFIC_PHY_OPT_MDL 0x00050234
#define REQ_BC_VER_4_SFP_TX_DISABLE_SUPPORTED 0x00070014
+ #define REQ_BC_VER_4_PFC_STATS_SUPPORTED 0x00070201
#define DRV_MSG_CODE_DCBX_ADMIN_PMF_MSG 0xb0000000
#define DRV_MSG_CODE_DCBX_PMF_DRV_OK 0xb2000000
#define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000
+ #define DRV_MSG_CODE_DRV_INFO_ACK 0xd8000000
+ #define DRV_MSG_CODE_DRV_INFO_NACK 0xd9000000
#define DRV_MSG_CODE_SET_MF_BW 0xe0000000
#define REQ_BC_VER_4_SET_MF_BW 0x00060202
#define FW_MSG_CODE_VRFY_OPT_MDL_INVLD_IMG 0xa0200000
#define FW_MSG_CODE_VRFY_OPT_MDL_UNAPPROVED 0xa0300000
#define FW_MSG_CODE_VF_DISABLED_DONE 0xb0000000
+ #define FW_MSG_CODE_DRV_INFO_ACK 0xd8100000
+ #define FW_MSG_CODE_DRV_INFO_NACK 0xd9100000
#define FW_MSG_CODE_SET_MF_BW_SENT 0xe0000000
#define FW_MSG_CODE_SET_MF_BW_DONE 0xe1000000
#define DRV_STATUS_DCBX_EVENT_MASK 0x000f0000
#define DRV_STATUS_DCBX_NEGOTIATION_RESULTS 0x00010000
+ #define DRV_STATUS_DRV_INFO_REQ 0x04000000
u32 virt_mac_upper;
#define VIRT_MAC_SIGN_MASK 0xffff0000
u32 extended_dev_info_shared_addr;
u32 ncsi_oem_data_addr;
- u32 ocsd_host_addr;
- u32 ocbb_host_addr;
- u32 ocsd_req_update_interval;
+ u32 ocsd_host_addr; /* initialized by option ROM */
+ u32 ocbb_host_addr; /* initialized by option ROM */
+ u32 ocsd_req_update_interval; /* initialized by option ROM */
+ u32 temperature_in_half_celsius;
+ u32 glob_struct_in_host;
+
+ u32 dcbx_neg_res_ext_offset;
+#define SHMEM_DCBX_NEG_RES_EXT_NONE 0x00000000
+
+ u32 drv_capabilities_flag[E2_FUNC_MAX];
+#define DRV_FLAGS_CAPABILITIES_LOADED_SUPPORTED 0x00000001
+#define DRV_FLAGS_CAPABILITIES_LOADED_L2 0x00000002
+#define DRV_FLAGS_CAPABILITIES_LOADED_FCOE 0x00000004
+#define DRV_FLAGS_CAPABILITIES_LOADED_ISCSI 0x00000008
+
+ u32 extended_dev_info_shared_cfg_size;
+
+ u32 dcbx_en[PORT_MAX];
+
+ /* The offset points to the multi threaded meta structure */
+ u32 multi_thread_data_offset;
+
+ /* address of DMAable host address holding values from the drivers */
+ u32 drv_info_host_addr_lo;
+ u32 drv_info_host_addr_hi;
+
+ /* general values written by the MFW (such as current version) */
+ u32 drv_info_control;
+#define DRV_INFO_CONTROL_VER_MASK 0x000000ff
+#define DRV_INFO_CONTROL_VER_SHIFT 0
+#define DRV_INFO_CONTROL_OP_CODE_MASK 0x0000ff00
+#define DRV_INFO_CONTROL_OP_CODE_SHIFT 8
};
#define MAC_STX_IDX_MAX 2
struct host_port_stats {
- u32 host_port_stats_start;
+ u32 host_port_stats_counter;
struct mac_stx mac_stx[MAC_STX_IDX_MAX];
u32 brb_drop_hi;
u32 brb_drop_lo;
- u32 host_port_stats_end;
+ u32 not_used; /* obsolete */
+ u32 pfc_frames_tx_hi;
+ u32 pfc_frames_tx_lo;
+ u32 pfc_frames_rx_hi;
+ u32 pfc_frames_rx_lo;
};
/* VIC definitions */
#define VICSTATST_UIF_INDEX 2
+/* current drv_info version */
+#define DRV_INFO_CUR_VER 1
+
+/* drv_info op codes supported */
+enum drv_info_opcode {
+ ETH_STATS_OPCODE,
+ FCOE_STATS_OPCODE,
+ ISCSI_STATS_OPCODE
+};
+
+#define ETH_STAT_INFO_VERSION_LEN 12
+/* Per PCI Function Ethernet Statistics required from the driver */
+struct eth_stats_info {
+ /* Function's Driver Version. padded to 12 */
+ u8 version[ETH_STAT_INFO_VERSION_LEN];
+ /* Locally Admin Addr. BigEndian EIU48. Actual size is 6 bytes */
+ u8 mac_local[8];
+ u8 mac_add1[8]; /* Additional Programmed MAC Addr 1. */
+ u8 mac_add2[8]; /* Additional Programmed MAC Addr 2. */
+ u32 mtu_size; /* MTU Size. Note : Negotiated MTU */
+ u32 feature_flags; /* Feature_Flags. */
+#define FEATURE_ETH_CHKSUM_OFFLOAD_MASK 0x01
+#define FEATURE_ETH_LSO_MASK 0x02
+#define FEATURE_ETH_BOOTMODE_MASK 0x1C
+#define FEATURE_ETH_BOOTMODE_SHIFT 2
+#define FEATURE_ETH_BOOTMODE_NONE (0x0 << 2)
+#define FEATURE_ETH_BOOTMODE_PXE (0x1 << 2)
+#define FEATURE_ETH_BOOTMODE_ISCSI (0x2 << 2)
+#define FEATURE_ETH_BOOTMODE_FCOE (0x3 << 2)
+#define FEATURE_ETH_TOE_MASK 0x20
+ u32 lso_max_size; /* LSO MaxOffloadSize. */
+ u32 lso_min_seg_cnt; /* LSO MinSegmentCount. */
+ /* Num Offloaded Connections TCP_IPv4. */
+ u32 ipv4_ofld_cnt;
+ /* Num Offloaded Connections TCP_IPv6. */
+ u32 ipv6_ofld_cnt;
+ u32 promiscuous_mode; /* Promiscuous Mode. non-zero true */
+ u32 txq_size; /* TX Descriptors Queue Size */
+ u32 rxq_size; /* RX Descriptors Queue Size */
+ /* TX Descriptor Queue Avg Depth. % Avg Queue Depth since last poll */
+ u32 txq_avg_depth;
+ /* RX Descriptors Queue Avg Depth. % Avg Queue Depth since last poll */
+ u32 rxq_avg_depth;
+ /* IOV_Offload. 0=none; 1=MultiQueue, 2=VEB 3= VEPA*/
+ u32 iov_offload;
+ /* Number of NetQueue/VMQ Config'd. */
+ u32 netq_cnt;
+ u32 vf_cnt; /* Num VF assigned to this PF. */
+};
+
+/* Per PCI Function FCOE Statistics required from the driver */
+struct fcoe_stats_info {
+ u8 version[12]; /* Function's Driver Version. */
+ u8 mac_local[8]; /* Locally Admin Addr. */
+ u8 mac_add1[8]; /* Additional Programmed MAC Addr 1. */
+ u8 mac_add2[8]; /* Additional Programmed MAC Addr 2. */
+ /* QoS Priority (per 802.1p). 0-7255 */
+ u32 qos_priority;
+ u32 txq_size; /* FCoE TX Descriptors Queue Size. */
+ u32 rxq_size; /* FCoE RX Descriptors Queue Size. */
+ /* FCoE TX Descriptor Queue Avg Depth. */
+ u32 txq_avg_depth;
+ /* FCoE RX Descriptors Queue Avg Depth. */
+ u32 rxq_avg_depth;
+ u32 rx_frames_lo; /* FCoE RX Frames received. */
+ u32 rx_frames_hi; /* FCoE RX Frames received. */
+ u32 rx_bytes_lo; /* FCoE RX Bytes received. */
+ u32 rx_bytes_hi; /* FCoE RX Bytes received. */
+ u32 tx_frames_lo; /* FCoE TX Frames sent. */
+ u32 tx_frames_hi; /* FCoE TX Frames sent. */
+ u32 tx_bytes_lo; /* FCoE TX Bytes sent. */
+ u32 tx_bytes_hi; /* FCoE TX Bytes sent. */
+};
+
+/* Per PCI Function iSCSI Statistics required from the driver*/
+struct iscsi_stats_info {
+ u8 version[12]; /* Function's Driver Version. */
+ u8 mac_local[8]; /* Locally Admin iSCSI MAC Addr. */
+ u8 mac_add1[8]; /* Additional Programmed MAC Addr 1. */
+ /* QoS Priority (per 802.1p). 0-7255 */
+ u32 qos_priority;
+ u8 initiator_name[64]; /* iSCSI Boot Initiator Node name. */
+ u8 ww_port_name[64]; /* iSCSI World wide port name */
+ u8 boot_target_name[64];/* iSCSI Boot Target Name. */
+ u8 boot_target_ip[16]; /* iSCSI Boot Target IP. */
+ u32 boot_target_portal; /* iSCSI Boot Target Portal. */
+ u8 boot_init_ip[16]; /* iSCSI Boot Initiator IP Address. */
+ u32 max_frame_size; /* Max Frame Size. bytes */
+ u32 txq_size; /* PDU TX Descriptors Queue Size. */
+ u32 rxq_size; /* PDU RX Descriptors Queue Size. */
+ u32 txq_avg_depth; /* PDU TX Descriptor Queue Avg Depth. */
+ u32 rxq_avg_depth; /* PDU RX Descriptors Queue Avg Depth. */
+ u32 rx_pdus_lo; /* iSCSI PDUs received. */
+ u32 rx_pdus_hi; /* iSCSI PDUs received. */
+ u32 rx_bytes_lo; /* iSCSI RX Bytes received. */
+ u32 rx_bytes_hi; /* iSCSI RX Bytes received. */
+ u32 tx_pdus_lo; /* iSCSI PDUs sent. */
+ u32 tx_pdus_hi; /* iSCSI PDUs sent. */
+ u32 tx_bytes_lo; /* iSCSI PDU TX Bytes sent. */
+ u32 tx_bytes_hi; /* iSCSI PDU TX Bytes sent. */
+ u32 pcp_prior_map_tbl; /* C-PCP to S-PCP Priority MapTable.
+ * 9 nibbles, the position of each nibble
+ * represents the C-PCP value, the value
+ * of the nibble = S-PCP value.
+ */
+};
+
+union drv_info_to_mcp {
+ struct eth_stats_info ether_stat;
+ struct fcoe_stats_info fcoe_stat;
+ struct iscsi_stats_info iscsi_stat;
+};
#define BCM_5710_FW_MAJOR_VERSION 7
#define BCM_5710_FW_MINOR_VERSION 0
#define BCM_5710_FW_REVISION_VERSION 29
/*
- * cfc delete event data
+ * FCoE RX statistics parameters section#0
*/
+struct fcoe_rx_stat_params_section0 {
+ __le32 fcoe_rx_pkt_cnt;
+ __le32 fcoe_rx_byte_cnt;
+};
+
+
+/*
+ * FCoE RX statistics parameters section#1
+ */
+struct fcoe_rx_stat_params_section1 {
+ __le32 fcoe_ver_cnt;
+ __le32 fcoe_rx_drop_pkt_cnt;
+};
+
+
+/*
+ * FCoE RX statistics parameters section#2
+ */
+struct fcoe_rx_stat_params_section2 {
+ __le32 fc_crc_cnt;
+ __le32 eofa_del_cnt;
+ __le32 miss_frame_cnt;
+ __le32 seq_timeout_cnt;
+ __le32 drop_seq_cnt;
+ __le32 fcoe_rx_drop_pkt_cnt;
+ __le32 fcp_rx_pkt_cnt;
+ __le32 reserved0;
+};
+
+
+/*
+ * FCoE TX statistics parameters
+ */
+struct fcoe_tx_stat_params {
+ __le32 fcoe_tx_pkt_cnt;
+ __le32 fcoe_tx_byte_cnt;
+ __le32 fcp_tx_pkt_cnt;
+ __le32 reserved0;
+};
+
+/*
+ * FCoE statistics parameters
+ */
+struct fcoe_statistics_params {
+ struct fcoe_tx_stat_params tx_stat;
+ struct fcoe_rx_stat_params_section0 rx_stat0;
+ struct fcoe_rx_stat_params_section1 rx_stat1;
+ struct fcoe_rx_stat_params_section2 rx_stat2;
+};
+
+
+/*
+ * cfc delete event data
+*/
struct cfc_del_event_data {
u32 cid;
u32 reserved0;
#include "bnx2x.h"
#include "bnx2x_cmn.h"
-
/********************************************************/
#define ETH_HLEN 14
/* L2 header size + 2*VLANs (8 bytes) + LLC SNAP (8 bytes) */
#define EDC_MODE_LIMITING 0x0044
#define EDC_MODE_PASSIVE_DAC 0x0055
+/* BRB default for class 0 E2 */
+#define DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR 170
+#define DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR 250
+#define DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR 10
+#define DEFAULT0_E2_BRB_MAC_FULL_XON_THR 50
/* BRB thresholds for E2*/
#define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE 170
#define PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE 50
#define PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE 250
+/* BRB default for class 0 E3A0 */
+#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR 290
+#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR 410
+#define DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR 10
+#define DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR 50
+
/* BRB thresholds for E3A0 */
#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE 290
#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE 0
#define PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE 50
#define PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE 410
+/* BRB default for E3B0 */
+#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR 330
+#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR 490
+#define DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR 15
+#define DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR 55
/* BRB thresholds for E3B0 2 port mode*/
#define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE 1025
#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE 50
#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE 384
-
/* only for E3B0*/
#define PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR 304
#define PFC_E3B0_4P_BRB_FULL_LB_XON_THR 384
-#define PFC_E3B0_4P_LB_GUART 120
+#define PFC_E3B0_4P_LB_GUART 120
#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART 120
-#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST 80
+#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST 80
#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART 80
-#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST 120
+#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST 120
+
+/* Pause defines*/
+#define DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR 330
+#define DEFAULT_E3B0_BRB_FULL_LB_XON_THR 490
+#define DEFAULT_E3B0_LB_GUART 40
+
+#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART 40
+#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST 0
+
+#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART 40
+#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST 0
+/* ETS defines*/
#define DCBX_INVALID_COS (0xFF)
#define ETS_BW_LIMIT_CREDIT_UPPER_BOUND (0x5000)
u32 min_w_val = 0;
/* Calculate min_w_val.*/
if (vars->link_up) {
- if (SPEED_20000 == vars->line_speed)
+ if (vars->line_speed == SPEED_20000)
min_w_val = ETS_E3B0_NIG_MIN_W_VAL_20GBPS;
else
min_w_val = ETS_E3B0_NIG_MIN_W_VAL_UP_TO_10GBPS;
REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_CREDIT_UPPER_BOUND_5 :
NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_5, credit_upper_bound);
- if (0 == port) {
+ if (!port) {
REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_6,
credit_upper_bound);
REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_7,
NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4, 0x0);
REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_5 :
NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5, 0x0);
- if (0 == port) {
+ if (!port) {
REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_6, 0x0);
REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_7, 0x0);
REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_8, 0x0);
* In 2 port mode port0 has COS0-5 that can be used for WFQ.In 4
* port mode port1 has COS0-2 that can be used for WFQ.
*/
- if (0 == port) {
+ if (!port) {
base_upper_bound = PBF_REG_COS0_UPPER_BOUND_P0;
max_cos = DCBX_E3B0_MAX_NUM_COS_PORT0;
} else {
* In 2 port mode port0 has COS0-5 that can be used for WFQ.
* In 4 port mode port1 has COS0-2 that can be used for WFQ.
*/
- if (0 == port) {
+ if (!port) {
base_weight = PBF_REG_COS0_WEIGHT_P0;
max_cos = DCBX_E3B0_MAX_NUM_COS_PORT0;
} else {
******************************************************************************/
static int bnx2x_ets_e3b0_get_total_bw(
const struct link_params *params,
- const struct bnx2x_ets_params *ets_params,
+ struct bnx2x_ets_params *ets_params,
u16 *total_bw)
{
struct bnx2x *bp = params->bp;
u8 cos_idx = 0;
+ u8 is_bw_cos_exist = 0;
*total_bw = 0 ;
+
/* Calculate total BW requested */
for (cos_idx = 0; cos_idx < ets_params->num_of_cos; cos_idx++) {
- if (bnx2x_cos_state_bw == ets_params->cos[cos_idx].state) {
+ if (ets_params->cos[cos_idx].state == bnx2x_cos_state_bw) {
+ is_bw_cos_exist = 1;
+ if (!ets_params->cos[cos_idx].params.bw_params.bw) {
+ DP(NETIF_MSG_LINK, "bnx2x_ets_E3B0_config BW"
+ "was set to 0\n");
+ /*
+ * This is to prevent a state when ramrods
+ * can't be sent
+ */
+ ets_params->cos[cos_idx].params.bw_params.bw
+ = 1;
+ }
*total_bw +=
ets_params->cos[cos_idx].params.bw_params.bw;
}
}
/* Check total BW is valid */
- if ((100 != *total_bw) || (0 == *total_bw)) {
- if (0 == *total_bw) {
+ if ((is_bw_cos_exist == 1) && (*total_bw != 100)) {
+ if (*total_bw == 0) {
DP(NETIF_MSG_LINK,
- "bnx2x_ets_E3B0_config toatl BW shouldn't be 0\n");
+ "bnx2x_ets_E3B0_config total BW shouldn't be 0\n");
return -EINVAL;
}
DP(NETIF_MSG_LINK,
- "bnx2x_ets_E3B0_config toatl BW should be 100\n");
- /**
- * We can handle a case whre the BW isn't 100 this can happen
- * if the TC are joined.
- */
+ "bnx2x_ets_E3B0_config total BW should be 100\n");
+ /*
+ * We can handle a case whre the BW isn't 100 this can happen
+ * if the TC are joined.
+ */
}
return 0;
}
const u8 max_num_of_cos = (port) ? DCBX_E3B0_MAX_NUM_COS_PORT1 :
DCBX_E3B0_MAX_NUM_COS_PORT0;
- if (DCBX_INVALID_COS != sp_pri_to_cos[pri]) {
+ if (sp_pri_to_cos[pri] != DCBX_INVALID_COS) {
DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
"parameter There can't be two COS's with "
"the same strict pri\n");
if (pri > max_num_of_cos) {
DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
- "parameter Illegal strict priority\n");
+ "parameter Illegal strict priority\n");
return -EINVAL;
}
/* Set all the strict priority first */
for (i = 0; i < max_num_of_cos; i++) {
- if (DCBX_INVALID_COS != sp_pri_to_cos[i]) {
- if (DCBX_MAX_NUM_COS <= sp_pri_to_cos[i]) {
+ if (sp_pri_to_cos[i] != DCBX_INVALID_COS) {
+ if (sp_pri_to_cos[i] >= DCBX_MAX_NUM_COS) {
DP(NETIF_MSG_LINK,
"bnx2x_ets_e3b0_sp_set_pri_cli_reg "
"invalid cos entry\n");
sp_pri_to_cos[i], pri_set);
pri_bitmask = 1 << sp_pri_to_cos[i];
/* COS is used remove it from bitmap.*/
- if (0 == (pri_bitmask & cos_bit_to_set)) {
+ if (!(pri_bitmask & cos_bit_to_set)) {
DP(NETIF_MSG_LINK,
"bnx2x_ets_e3b0_sp_set_pri_cli_reg "
"invalid There can't be two COS's with"
******************************************************************************/
int bnx2x_ets_e3b0_config(const struct link_params *params,
const struct link_vars *vars,
- const struct bnx2x_ets_params *ets_params)
+ struct bnx2x_ets_params *ets_params)
{
struct bnx2x *bp = params->bp;
int bnx2x_status = 0;
/* Prepare BW parameters*/
bnx2x_status = bnx2x_ets_e3b0_get_total_bw(params, ets_params,
&total_bw);
- if (0 != bnx2x_status) {
+ if (bnx2x_status) {
DP(NETIF_MSG_LINK,
"bnx2x_ets_E3B0_config get_total_bw failed\n");
return -EINVAL;
}
- /**
- * Upper bound is set according to current link speed (min_w_val
- * should be the same for upper bound and COS credit val).
+ /*
+ * Upper bound is set according to current link speed (min_w_val
+ * should be the same for upper bound and COS credit val).
*/
bnx2x_ets_e3b0_set_credit_upper_bound_nig(params, min_w_val_nig);
bnx2x_ets_e3b0_set_credit_upper_bound_pbf(params, min_w_val_pbf);
for (cos_entry = 0; cos_entry < ets_params->num_of_cos; cos_entry++) {
if (bnx2x_cos_state_bw == ets_params->cos[cos_entry].state) {
cos_bw_bitmap |= (1 << cos_entry);
- /**
+ /*
* The function also sets the BW in HW(not the mappin
* yet)
*/
"bnx2x_ets_e3b0_config cos state not valid\n");
return -EINVAL;
}
- if (0 != bnx2x_status) {
+ if (bnx2x_status) {
DP(NETIF_MSG_LINK,
"bnx2x_ets_e3b0_config set cos bw failed\n");
return bnx2x_status;
bnx2x_status = bnx2x_ets_e3b0_sp_set_pri_cli_reg(params,
sp_pri_to_cos);
- if (0 != bnx2x_status) {
+ if (bnx2x_status) {
DP(NETIF_MSG_LINK,
"bnx2x_ets_E3B0_config set_pri_cli_reg failed\n");
return bnx2x_status;
cos_sp_bitmap,
cos_bw_bitmap);
- if (0 != bnx2x_status) {
+ if (bnx2x_status) {
DP(NETIF_MSG_LINK, "bnx2x_ets_E3B0_config SP failed\n");
return bnx2x_status;
}
DP(NETIF_MSG_LINK, "ETS enabled BW limit configuration\n");
- if ((0 == total_bw) ||
- (0 == cos0_bw) ||
- (0 == cos1_bw)) {
+ if ((!total_bw) ||
+ (!cos0_bw) ||
+ (!cos1_bw)) {
DP(NETIF_MSG_LINK, "Total BW can't be zero\n");
return;
}
* dbg0-010 dbg1-001 cos1-100 cos0-011 MCP-000
* dbg0-010 dbg1-001 cos0-011 cos1-100 MCP-000
*/
- val = (0 == strict_cos) ? 0x2318 : 0x22E0;
+ val = (!strict_cos) ? 0x2318 : 0x22E0;
REG_WR(bp, NIG_REG_P0_TX_ARB_PRIORITY_CLIENT, val);
return 0;
/******************************************************************/
/* PFC section */
/******************************************************************/
-
static void bnx2x_update_pfc_xmac(struct link_params *params,
struct link_vars *vars,
u8 is_lb)
if (!vars->link_up)
return;
- if (MAC_TYPE_EMAC == vars->mac_type) {
+ if (vars->mac_type == MAC_TYPE_EMAC) {
DP(NETIF_MSG_LINK, "About to read PFC stats from EMAC\n");
bnx2x_emac_get_pfc_stat(params, pfc_frames_sent,
pfc_frames_received);
udelay(40);
}
+static u8 bnx2x_is_4_port_mode(struct bnx2x *bp)
+{
+ u32 port4mode_ovwr_val;
+ /* Check 4-port override enabled */
+ port4mode_ovwr_val = REG_RD(bp, MISC_REG_PORT4MODE_EN_OVWR);
+ if (port4mode_ovwr_val & (1<<0)) {
+ /* Return 4-port mode override value */
+ return ((port4mode_ovwr_val & (1<<1)) == (1<<1));
+ }
+ /* Return 4-port mode from input pin */
+ return (u8)REG_RD(bp, MISC_REG_PORT4MODE_EN);
+}
static void bnx2x_emac_init(struct link_params *params,
struct link_vars *vars)
}
-static u8 bnx2x_is_4_port_mode(struct bnx2x *bp)
-{
- u32 port4mode_ovwr_val;
- /* Check 4-port override enabled */
- port4mode_ovwr_val = REG_RD(bp, MISC_REG_PORT4MODE_EN_OVWR);
- if (port4mode_ovwr_val & (1<<0)) {
- /* Return 4-port mode override value */
- return ((port4mode_ovwr_val & (1<<1)) == (1<<1));
- }
- /* Return 4-port mode from input pin */
- return (u8)REG_RD(bp, MISC_REG_PORT4MODE_EN);
-}
-
/* Define the XMAC mode */
static void bnx2x_xmac_init(struct link_params *params, u32 max_speed)
{
struct bnx2x *bp = params->bp;
u32 is_port4mode = bnx2x_is_4_port_mode(bp);
- /**
- * In 4-port mode, need to set the mode only once, so if XMAC is
- * already out of reset, it means the mode has already been set,
- * and it must not* reset the XMAC again, since it controls both
- * ports of the path
- **/
+ /*
+ * In 4-port mode, need to set the mode only once, so if XMAC is
+ * already out of reset, it means the mode has already been set,
+ * and it must not* reset the XMAC again, since it controls both
+ * ports of the path
+ */
if ((CHIP_NUM(bp) == CHIP_NUM_57840) &&
(REG_RD(bp, MISC_REG_RESET_REG_2) &
return 0;
}
+
static int bnx2x_emac_enable(struct link_params *params,
struct link_vars *vars, u8 lb)
{
REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2);
}
-
/* PFC BRB internal port configuration params */
struct bnx2x_pfc_brb_threshold_val {
u32 pause_xoff;
};
struct bnx2x_pfc_brb_e3b0_val {
+ u32 per_class_guaranty_mode;
+ u32 lb_guarantied_hyst;
u32 full_lb_xoff_th;
u32 full_lb_xon_threshold;
u32 lb_guarantied;
struct bnx2x_pfc_brb_th_val {
struct bnx2x_pfc_brb_threshold_val pauseable_th;
struct bnx2x_pfc_brb_threshold_val non_pauseable_th;
+ struct bnx2x_pfc_brb_threshold_val default_class0;
+ struct bnx2x_pfc_brb_threshold_val default_class1;
+
};
static int bnx2x_pfc_brb_get_config_params(
struct link_params *params,
{
struct bnx2x *bp = params->bp;
DP(NETIF_MSG_LINK, "Setting PFC BRB configuration\n");
+
+ config_val->default_class1.pause_xoff = 0;
+ config_val->default_class1.pause_xon = 0;
+ config_val->default_class1.full_xoff = 0;
+ config_val->default_class1.full_xon = 0;
+
if (CHIP_IS_E2(bp)) {
+ /* class0 defaults */
+ config_val->default_class0.pause_xoff =
+ DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR;
+ config_val->default_class0.pause_xon =
+ DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR;
+ config_val->default_class0.full_xoff =
+ DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR;
+ config_val->default_class0.full_xon =
+ DEFAULT0_E2_BRB_MAC_FULL_XON_THR;
+ /* pause able*/
config_val->pauseable_th.pause_xoff =
- PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+ PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
config_val->pauseable_th.pause_xon =
- PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE;
+ PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE;
config_val->pauseable_th.full_xoff =
- PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE;
+ PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE;
config_val->pauseable_th.full_xon =
- PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE;
+ PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE;
/* non pause able*/
config_val->non_pauseable_th.pause_xoff =
- PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+ PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.pause_xon =
- PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+ PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xoff =
- PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+ PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xon =
- PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+ PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE;
} else if (CHIP_IS_E3A0(bp)) {
+ /* class0 defaults */
+ config_val->default_class0.pause_xoff =
+ DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR;
+ config_val->default_class0.pause_xon =
+ DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR;
+ config_val->default_class0.full_xoff =
+ DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR;
+ config_val->default_class0.full_xon =
+ DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR;
+ /* pause able */
config_val->pauseable_th.pause_xoff =
- PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+ PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
config_val->pauseable_th.pause_xon =
- PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE;
+ PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE;
config_val->pauseable_th.full_xoff =
- PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE;
+ PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE;
config_val->pauseable_th.full_xon =
- PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE;
+ PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE;
/* non pause able*/
config_val->non_pauseable_th.pause_xoff =
- PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+ PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.pause_xon =
- PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+ PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xoff =
- PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+ PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xon =
- PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+ PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE;
} else if (CHIP_IS_E3B0(bp)) {
+ /* class0 defaults */
+ config_val->default_class0.pause_xoff =
+ DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR;
+ config_val->default_class0.pause_xon =
+ DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR;
+ config_val->default_class0.full_xoff =
+ DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR;
+ config_val->default_class0.full_xon =
+ DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR;
+
if (params->phy[INT_PHY].flags &
FLAGS_4_PORT_MODE) {
config_val->pauseable_th.pause_xoff =
- PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
config_val->pauseable_th.pause_xon =
- PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE;
config_val->pauseable_th.full_xoff =
- PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE;
config_val->pauseable_th.full_xon =
- PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE;
/* non pause able*/
config_val->non_pauseable_th.pause_xoff =
- PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.pause_xon =
- PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xoff =
- PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+ PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
config_val->non_pauseable_th.full_xon =
- PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
- } else {
- config_val->pauseable_th.pause_xoff =
- PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
- config_val->pauseable_th.pause_xon =
- PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE;
- config_val->pauseable_th.full_xoff =
- PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE;
- config_val->pauseable_th.full_xon =
- PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE;
- /* non pause able*/
- config_val->non_pauseable_th.pause_xoff =
- PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
- config_val->non_pauseable_th.pause_xon =
- PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
- config_val->non_pauseable_th.full_xoff =
- PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
- config_val->non_pauseable_th.full_xon =
- PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
- }
+ PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+ } else {
+ config_val->pauseable_th.pause_xoff =
+ PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+ config_val->pauseable_th.pause_xon =
+ PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE;
+ config_val->pauseable_th.full_xoff =
+ PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE;
+ config_val->pauseable_th.full_xon =
+ PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE;
+ /* non pause able*/
+ config_val->non_pauseable_th.pause_xoff =
+ PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+ config_val->non_pauseable_th.pause_xon =
+ PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+ config_val->non_pauseable_th.full_xoff =
+ PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+ config_val->non_pauseable_th.full_xon =
+ PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+ }
} else
return -EINVAL;
return 0;
}
-
-static void bnx2x_pfc_brb_get_e3b0_config_params(struct link_params *params,
- struct bnx2x_pfc_brb_e3b0_val
- *e3b0_val,
- u32 cos0_pauseable,
- u32 cos1_pauseable)
+static void bnx2x_pfc_brb_get_e3b0_config_params(
+ struct link_params *params,
+ struct bnx2x_pfc_brb_e3b0_val
+ *e3b0_val,
+ struct bnx2x_nig_brb_pfc_port_params *pfc_params,
+ const u8 pfc_enabled)
{
- if (params->phy[INT_PHY].flags & FLAGS_4_PORT_MODE) {
+ if (pfc_enabled && pfc_params) {
+ e3b0_val->per_class_guaranty_mode = 1;
+ e3b0_val->lb_guarantied_hyst = 80;
+
+ if (params->phy[INT_PHY].flags &
+ FLAGS_4_PORT_MODE) {
+ e3b0_val->full_lb_xoff_th =
+ PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR;
+ e3b0_val->full_lb_xon_threshold =
+ PFC_E3B0_4P_BRB_FULL_LB_XON_THR;
+ e3b0_val->lb_guarantied =
+ PFC_E3B0_4P_LB_GUART;
+ e3b0_val->mac_0_class_t_guarantied =
+ PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART;
+ e3b0_val->mac_0_class_t_guarantied_hyst =
+ PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST;
+ e3b0_val->mac_1_class_t_guarantied =
+ PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART;
+ e3b0_val->mac_1_class_t_guarantied_hyst =
+ PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST;
+ } else {
+ e3b0_val->full_lb_xoff_th =
+ PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR;
+ e3b0_val->full_lb_xon_threshold =
+ PFC_E3B0_2P_BRB_FULL_LB_XON_THR;
+ e3b0_val->mac_0_class_t_guarantied_hyst =
+ PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST;
+ e3b0_val->mac_1_class_t_guarantied =
+ PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART;
+ e3b0_val->mac_1_class_t_guarantied_hyst =
+ PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST;
+
+ if (pfc_params->cos0_pauseable !=
+ pfc_params->cos1_pauseable) {
+ /* nonpauseable= Lossy + pauseable = Lossless*/
+ e3b0_val->lb_guarantied =
+ PFC_E3B0_2P_MIX_PAUSE_LB_GUART;
+ e3b0_val->mac_0_class_t_guarantied =
+ PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART;
+ } else if (pfc_params->cos0_pauseable) {
+ /* Lossless +Lossless*/
+ e3b0_val->lb_guarantied =
+ PFC_E3B0_2P_PAUSE_LB_GUART;
+ e3b0_val->mac_0_class_t_guarantied =
+ PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART;
+ } else {
+ /* Lossy +Lossy*/
+ e3b0_val->lb_guarantied =
+ PFC_E3B0_2P_NON_PAUSE_LB_GUART;
+ e3b0_val->mac_0_class_t_guarantied =
+ PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART;
+ }
+ }
+ } else {
+ e3b0_val->per_class_guaranty_mode = 0;
+ e3b0_val->lb_guarantied_hyst = 0;
e3b0_val->full_lb_xoff_th =
- PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR;
+ DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR;
e3b0_val->full_lb_xon_threshold =
- PFC_E3B0_4P_BRB_FULL_LB_XON_THR;
+ DEFAULT_E3B0_BRB_FULL_LB_XON_THR;
e3b0_val->lb_guarantied =
- PFC_E3B0_4P_LB_GUART;
+ DEFAULT_E3B0_LB_GUART;
e3b0_val->mac_0_class_t_guarantied =
- PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART;
+ DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART;
e3b0_val->mac_0_class_t_guarantied_hyst =
- PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST;
+ DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST;
e3b0_val->mac_1_class_t_guarantied =
- PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART;
+ DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART;
e3b0_val->mac_1_class_t_guarantied_hyst =
- PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST;
- } else {
- e3b0_val->full_lb_xoff_th =
- PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR;
- e3b0_val->full_lb_xon_threshold =
- PFC_E3B0_2P_BRB_FULL_LB_XON_THR;
- e3b0_val->mac_0_class_t_guarantied_hyst =
- PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST;
- e3b0_val->mac_1_class_t_guarantied =
- PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART;
- e3b0_val->mac_1_class_t_guarantied_hyst =
- PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST;
-
- if (cos0_pauseable != cos1_pauseable) {
- /* nonpauseable= Lossy + pauseable = Lossless*/
- e3b0_val->lb_guarantied =
- PFC_E3B0_2P_MIX_PAUSE_LB_GUART;
- e3b0_val->mac_0_class_t_guarantied =
- PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART;
- } else if (cos0_pauseable) {
- /* Lossless +Lossless*/
- e3b0_val->lb_guarantied =
- PFC_E3B0_2P_PAUSE_LB_GUART;
- e3b0_val->mac_0_class_t_guarantied =
- PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART;
- } else {
- /* Lossy +Lossy*/
- e3b0_val->lb_guarantied =
- PFC_E3B0_2P_NON_PAUSE_LB_GUART;
- e3b0_val->mac_0_class_t_guarantied =
- PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART;
- }
+ DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST;
}
}
static int bnx2x_update_pfc_brb(struct link_params *params,
struct bnx2x *bp = params->bp;
struct bnx2x_pfc_brb_th_val config_val = { {0} };
struct bnx2x_pfc_brb_threshold_val *reg_th_config =
- &config_val.pauseable_th;
+ &config_val.pauseable_th;
struct bnx2x_pfc_brb_e3b0_val e3b0_val = {0};
- int set_pfc = params->feature_config_flags &
+ const int set_pfc = params->feature_config_flags &
FEATURE_CONFIG_PFC_ENABLED;
+ const u8 pfc_enabled = (set_pfc && pfc_params);
int bnx2x_status = 0;
u8 port = params->port;
/* default - pause configuration */
reg_th_config = &config_val.pauseable_th;
bnx2x_status = bnx2x_pfc_brb_get_config_params(params, &config_val);
- if (0 != bnx2x_status)
+ if (bnx2x_status)
return bnx2x_status;
- if (set_pfc && pfc_params)
+ if (pfc_enabled) {
/* First COS */
- if (!pfc_params->cos0_pauseable)
+ if (pfc_params->cos0_pauseable)
+ reg_th_config = &config_val.pauseable_th;
+ else
reg_th_config = &config_val.non_pauseable_th;
+ } else
+ reg_th_config = &config_val.default_class0;
/*
* The number of free blocks below which the pause signal to class 0
* of MAC #n is asserted. n=0,1
REG_WR(bp, (port) ? BRB1_REG_FULL_0_XON_THRESHOLD_1 :
BRB1_REG_FULL_0_XON_THRESHOLD_0 , reg_th_config->full_xon);
- if (set_pfc && pfc_params) {
+ if (pfc_enabled) {
/* Second COS */
if (pfc_params->cos1_pauseable)
reg_th_config = &config_val.pauseable_th;
else
reg_th_config = &config_val.non_pauseable_th;
+ } else
+ reg_th_config = &config_val.default_class1;
+ /*
+ * The number of free blocks below which the pause signal to
+ * class 1 of MAC #n is asserted. n=0,1
+ */
+ REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 :
+ BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0,
+ reg_th_config->pause_xoff);
+
+ /*
+ * The number of free blocks above which the pause signal to
+ * class 1 of MAC #n is de-asserted. n=0,1
+ */
+ REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 :
+ BRB1_REG_PAUSE_1_XON_THRESHOLD_0,
+ reg_th_config->pause_xon);
+ /*
+ * The number of free blocks below which the full signal to
+ * class 1 of MAC #n is asserted. n=0,1
+ */
+ REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 :
+ BRB1_REG_FULL_1_XOFF_THRESHOLD_0,
+ reg_th_config->full_xoff);
+ /*
+ * The number of free blocks above which the full signal to
+ * class 1 of MAC #n is de-asserted. n=0,1
+ */
+ REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 :
+ BRB1_REG_FULL_1_XON_THRESHOLD_0,
+ reg_th_config->full_xon);
+
+ if (CHIP_IS_E3B0(bp)) {
+ bnx2x_pfc_brb_get_e3b0_config_params(
+ params,
+ &e3b0_val,
+ pfc_params,
+ pfc_enabled);
+
+ REG_WR(bp, BRB1_REG_PER_CLASS_GUARANTY_MODE,
+ e3b0_val.per_class_guaranty_mode);
+
/*
- * The number of free blocks below which the pause signal to
- * class 1 of MAC #n is asserted. n=0,1
- **/
- REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 :
- BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0,
- reg_th_config->pause_xoff);
+ * The hysteresis on the guarantied buffer space for the Lb
+ * port before signaling XON.
+ */
+ REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST,
+ e3b0_val.lb_guarantied_hyst);
+
/*
- * The number of free blocks above which the pause signal to
- * class 1 of MAC #n is de-asserted. n=0,1
+ * The number of free blocks below which the full signal to the
+ * LB port is asserted.
*/
- REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 :
- BRB1_REG_PAUSE_1_XON_THRESHOLD_0,
- reg_th_config->pause_xon);
+ REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD,
+ e3b0_val.full_lb_xoff_th);
/*
- * The number of free blocks below which the full signal to
- * class 1 of MAC #n is asserted. n=0,1
+ * The number of free blocks above which the full signal to the
+ * LB port is de-asserted.
*/
- REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 :
- BRB1_REG_FULL_1_XOFF_THRESHOLD_0,
- reg_th_config->full_xoff);
+ REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD,
+ e3b0_val.full_lb_xon_threshold);
/*
- * The number of free blocks above which the full signal to
- * class 1 of MAC #n is de-asserted. n=0,1
+ * The number of blocks guarantied for the MAC #n port. n=0,1
*/
- REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 :
- BRB1_REG_FULL_1_XON_THRESHOLD_0,
- reg_th_config->full_xon);
+ /* The number of blocks guarantied for the LB port.*/
+ REG_WR(bp, BRB1_REG_LB_GUARANTIED,
+ e3b0_val.lb_guarantied);
- if (CHIP_IS_E3B0(bp)) {
- /*Should be done by init tool */
- /*
- * BRB_empty_for_dup = BRB1_REG_BRB_EMPTY_THRESHOLD
- * reset value
- * 944
- */
-
- /**
- * The hysteresis on the guarantied buffer space for the Lb port
- * before signaling XON.
- **/
- REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST, 80);
-
- bnx2x_pfc_brb_get_e3b0_config_params(
- params,
- &e3b0_val,
- pfc_params->cos0_pauseable,
- pfc_params->cos1_pauseable);
- /**
- * The number of free blocks below which the full signal to the
- * LB port is asserted.
- */
- REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD,
- e3b0_val.full_lb_xoff_th);
- /**
- * The number of free blocks above which the full signal to the
- * LB port is de-asserted.
- */
- REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD,
- e3b0_val.full_lb_xon_threshold);
- /**
- * The number of blocks guarantied for the MAC #n port. n=0,1
- */
-
- /*The number of blocks guarantied for the LB port.*/
- REG_WR(bp, BRB1_REG_LB_GUARANTIED,
- e3b0_val.lb_guarantied);
-
- /**
- * The number of blocks guarantied for the MAC #n port.
- */
- REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0,
- 2 * e3b0_val.mac_0_class_t_guarantied);
- REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1,
- 2 * e3b0_val.mac_1_class_t_guarantied);
- /**
- * The number of blocks guarantied for class #t in MAC0. t=0,1
- */
- REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED,
- e3b0_val.mac_0_class_t_guarantied);
- REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED,
- e3b0_val.mac_0_class_t_guarantied);
- /**
- * The hysteresis on the guarantied buffer space for class in
- * MAC0. t=0,1
- */
- REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST,
- e3b0_val.mac_0_class_t_guarantied_hyst);
- REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST,
- e3b0_val.mac_0_class_t_guarantied_hyst);
-
- /**
- * The number of blocks guarantied for class #t in MAC1.t=0,1
- */
- REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED,
- e3b0_val.mac_1_class_t_guarantied);
- REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED,
- e3b0_val.mac_1_class_t_guarantied);
- /**
- * The hysteresis on the guarantied buffer space for class #t
- * in MAC1. t=0,1
- */
- REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST,
- e3b0_val.mac_1_class_t_guarantied_hyst);
- REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST,
- e3b0_val.mac_1_class_t_guarantied_hyst);
-
- }
+ /*
+ * The number of blocks guarantied for the MAC #n port.
+ */
+ REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0,
+ 2 * e3b0_val.mac_0_class_t_guarantied);
+ REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1,
+ 2 * e3b0_val.mac_1_class_t_guarantied);
+ /*
+ * The number of blocks guarantied for class #t in MAC0. t=0,1
+ */
+ REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED,
+ e3b0_val.mac_0_class_t_guarantied);
+ REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED,
+ e3b0_val.mac_0_class_t_guarantied);
+ /*
+ * The hysteresis on the guarantied buffer space for class in
+ * MAC0. t=0,1
+ */
+ REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST,
+ e3b0_val.mac_0_class_t_guarantied_hyst);
+ REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST,
+ e3b0_val.mac_0_class_t_guarantied_hyst);
+ /*
+ * The number of blocks guarantied for class #t in MAC1.t=0,1
+ */
+ REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED,
+ e3b0_val.mac_1_class_t_guarantied);
+ REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED,
+ e3b0_val.mac_1_class_t_guarantied);
+ /*
+ * The hysteresis on the guarantied buffer space for class #t
+ * in MAC1. t=0,1
+ */
+ REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST,
+ e3b0_val.mac_1_class_t_guarantied_hyst);
+ REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST,
+ e3b0_val.mac_1_class_t_guarantied_hyst);
}
return bnx2x_status;
/* update BRB params */
bnx2x_status = bnx2x_update_pfc_brb(params, vars, pfc_params);
- if (0 != bnx2x_status)
+ if (bnx2x_status)
return bnx2x_status;
if (!vars->link_up)
bnx2x_emac_enable(params, vars, 0);
return bnx2x_status;
}
-
if (CHIP_IS_E2(bp))
bnx2x_update_pfc_bmac2(params, vars, bmac_loopback);
else
DP(NETIF_MSG_LINK, "write phy register failed\n");
netdev_err(bp->dev, "MDC/MDIO access timeout\n");
rc = -EFAULT;
-
} else {
/* data */
tmp = ((phy->addr << 21) | (devad << 16) | val |
EMAC_MDIO_STATUS_10MB);
return rc;
}
-
-
/******************************************************************/
/* BSC access functions from E3 */
/******************************************************************/
aer_val = 0x3800 + offset - 1;
else
aer_val = 0x3800 + offset;
- DP(NETIF_MSG_LINK, "Set AER to 0x%x\n", aer_val);
+
CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
MDIO_AER_BLOCK_AER_REG, aer_val);
static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy,
struct link_params *params,
- u8 fiber_mode)
+ u8 fiber_mode,
+ u8 always_autoneg)
{
struct bnx2x *bp = params->bp;
u16 val16, digctrl_kx1, digctrl_kx2;
- u8 lane;
-
- lane = bnx2x_get_warpcore_lane(phy, params);
/* Clear XFI clock comp in non-10G single lane mode. */
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
MDIO_WC_REG_RX66_CONTROL, val16 & ~(3<<13));
- if (phy->req_line_speed == SPEED_AUTO_NEG) {
+ if (always_autoneg || phy->req_line_speed == SPEED_AUTO_NEG) {
/* SGMII Autoneg */
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
} else {
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
- val16 &= 0xcfbf;
+ val16 &= 0xcebf;
switch (phy->req_line_speed) {
case SPEED_10:
break;
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
MDIO_WC_REG_DIGITAL5_MISC6, &val);
}
-
-
- /* Clear SFI/XFI link settings registers */
+/* Clear SFI/XFI link settings registers */
static void bnx2x_warpcore_clear_regs(struct bnx2x_phy *phy,
struct link_params *params,
u16 lane)
vars->phy_flags |= PHY_SGMII_FLAG;
DP(NETIF_MSG_LINK, "Setting SGMII mode\n");
bnx2x_warpcore_clear_regs(phy, params, lane);
- bnx2x_warpcore_set_sgmii_speed(phy, params, 0);
+ bnx2x_warpcore_set_sgmii_speed(phy, params, 0, 1);
} else {
switch (serdes_net_if) {
case PORT_HW_CFG_NET_SERDES_IF_KR:
}
bnx2x_warpcore_set_sgmii_speed(phy,
params,
- fiber_mode);
+ fiber_mode,
+ 0);
}
break;
bnx2x_warpcore_set_10G_XFI(phy, params, 0);
} else if (vars->line_speed == SPEED_1000) {
DP(NETIF_MSG_LINK, "Setting 1G Fiber\n");
- bnx2x_warpcore_set_sgmii_speed(phy, params, 1);
+ bnx2x_warpcore_set_sgmii_speed(
+ phy, params, 1, 0);
}
/* Issue Module detection */
if (bnx2x_is_sfp_module_plugged(phy, params))
/* Switch back to 4-copy registers */
bnx2x_set_aer_mmd(params, phy);
- /* Global loopback, not recommended. */
- bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
- bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_COMBO_IEEE0_MIICTRL, val16 |
- 0x4000);
} else {
/* 10G & 20G */
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
}
-void bnx2x_link_status_update(struct link_params *params,
- struct link_vars *vars)
+void bnx2x_sync_link(struct link_params *params,
+ struct link_vars *vars)
{
struct bnx2x *bp = params->bp;
u8 link_10g_plus;
- u8 port = params->port;
- u32 sync_offset, media_types;
- /* Update PHY configuration */
- set_phy_vars(params, vars);
-
- vars->link_status = REG_RD(bp, params->shmem_base +
- offsetof(struct shmem_region,
- port_mb[port].link_status));
-
- vars->link_up = (vars->link_status & LINK_STATUS_LINK_UP);
- vars->phy_flags = PHY_XGXS_FLAG;
if (vars->link_status & LINK_STATUS_PHYSICAL_LINK_FLAG)
vars->phy_flags |= PHY_PHYSICAL_LINK_FLAG;
-
+ vars->link_up = (vars->link_status & LINK_STATUS_LINK_UP);
if (vars->link_up) {
DP(NETIF_MSG_LINK, "phy link up\n");
if (vars->link_status & LINK_STATUS_PHYSICAL_LINK_FLAG)
vars->phy_flags |= PHY_HALF_OPEN_CONN_FLAG;
}
+}
+
+void bnx2x_link_status_update(struct link_params *params,
+ struct link_vars *vars)
+{
+ struct bnx2x *bp = params->bp;
+ u8 port = params->port;
+ u32 sync_offset, media_types;
+ /* Update PHY configuration */
+ set_phy_vars(params, vars);
+ vars->link_status = REG_RD(bp, params->shmem_base +
+ offsetof(struct shmem_region,
+ port_mb[port].link_status));
+
+ vars->phy_flags = PHY_XGXS_FLAG;
+ bnx2x_sync_link(params, vars);
/* Sync media type */
sync_offset = params->shmem_base +
offsetof(struct shmem_region,
vars->line_speed, vars->duplex, vars->flow_ctrl);
}
-
static void bnx2x_set_master_ln(struct link_params *params,
struct bnx2x_phy *phy)
{
* Each two bits represents a lane number:
* No swap is 0123 => 0x1b no need to enable the swap
*/
- u16 ser_lane, rx_lane_swap, tx_lane_swap;
+ u16 rx_lane_swap, tx_lane_swap;
- ser_lane = ((params->lane_config &
- PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >>
- PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT);
rx_lane_swap = ((params->lane_config &
PORT_HW_CFG_LANE_SWAP_CFG_RX_MASK) >>
PORT_HW_CFG_LANE_SWAP_CFG_RX_SHIFT);
struct link_params *params,
struct link_vars *vars)
{
-
struct bnx2x *bp = params->bp;
u16 gp_status, duplex = DUPLEX_HALF, link_up = 0, speed_mask;
struct link_params *params,
struct link_vars *vars)
{
-
struct bnx2x *bp = params->bp;
-
u8 lane;
u16 gp_status1, gp_speed, link_up, duplex = DUPLEX_FULL;
int rc = 0;
return rc;
}
-
/*****************************************************************************/
/* External Phy section */
/*****************************************************************************/
static void bnx2x_warpcore_hw_reset(struct bnx2x_phy *phy,
struct link_params *params)
{
+ struct bnx2x *bp = params->bp;
bnx2x_warpcore_power_module(params, phy, 0);
+ /* Put Warpcore in low power mode */
+ REG_WR(bp, MISC_REG_WC0_RESET, 0x0c0e);
+
+ /* Put LCPLL in low power mode */
+ REG_WR(bp, MISC_REG_LCPLL_E40_PWRDWN, 1);
+ REG_WR(bp, MISC_REG_LCPLL_E40_RESETB_ANA, 0);
+ REG_WR(bp, MISC_REG_LCPLL_E40_RESETB_DIG, 0);
}
static void bnx2x_power_sfp_module(struct link_params *params,
DP(NETIF_MSG_LINK,
"8727 Power fault has been detected on port %d\n",
oc_port);
- netdev_err(bp->dev, "Error: Power fault on Port %d has"
- " been detected and the power to "
- "that SFP+ module has been removed"
- " to prevent failure of the card."
- " Please remove the SFP+ module and"
- " restart the system to clear this"
- " error.\n",
+ netdev_err(bp->dev, "Error: Power fault on Port %d has "
+ "been detected and the power to "
+ "that SFP+ module has been removed "
+ "to prevent failure of the card. "
+ "Please remove the SFP+ module and "
+ "restart the system to clear this "
+ "error.\n",
oc_port);
/* Disable all RX_ALARMs except for mod_abs */
bnx2x_cl45_write(bp, phy,
static void bnx2x_848xx_set_led(struct bnx2x *bp,
struct bnx2x_phy *phy)
{
- u16 val;
+ u16 val, offset;
/* PHYC_CTL_LED_CTL */
bnx2x_cl45_read(bp, phy,
MDIO_PMA_REG_8481_LED3_BLINK,
0);
- bnx2x_cl45_read(bp, phy,
+ /* Configure the blink rate to ~15.9 Hz */
+ bnx2x_cl45_write(bp, phy,
MDIO_PMA_DEVAD,
- MDIO_PMA_REG_84823_CTL_LED_CTL_1, &val);
- val |= MDIO_PMA_REG_84823_LED3_STRETCH_EN; /* stretch_en for LED3*/
+ MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH,
+ MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ);
+
+ if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833)
+ offset = MDIO_PMA_REG_84833_CTL_LED_CTL_1;
+ else
+ offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1;
+ bnx2x_cl45_read(bp, phy,
+ MDIO_PMA_DEVAD, offset, &val);
+ val |= MDIO_PMA_REG_84823_LED3_STRETCH_EN; /* stretch_en for LED3*/
bnx2x_cl45_write(bp, phy,
- MDIO_PMA_DEVAD,
- MDIO_PMA_REG_84823_CTL_LED_CTL_1, val);
+ MDIO_PMA_DEVAD, offset, val);
/* 'Interrupt Mask' */
bnx2x_cl45_write(bp, phy,
struct link_vars *vars)
{
struct bnx2x *bp = params->bp;
- u16 autoneg_val, an_1000_val, an_10_100_val;
+ u16 autoneg_val, an_1000_val, an_10_100_val, an_10g_val;
u16 tmp_req_line_speed;
tmp_req_line_speed = phy->req_line_speed;
bnx2x_cl45_write(bp, phy,
MDIO_AN_DEVAD, MDIO_AN_REG_8481_AUX_CTRL,
(1<<15 | 1<<9 | 7<<0));
+ /* The PHY needs this set even for forced link. */
+ an_10_100_val |= (1<<8) | (1<<7);
DP(NETIF_MSG_LINK, "Setting 100M force\n");
}
if ((phy->req_line_speed == SPEED_10) &&
DP(NETIF_MSG_LINK, "Advertising 10G\n");
/* Restart autoneg for 10G*/
+ bnx2x_cl45_read(bp, phy,
+ MDIO_AN_DEVAD,
+ MDIO_AN_REG_8481_10GBASE_T_AN_CTRL,
+ &an_10g_val);
+ bnx2x_cl45_write(bp, phy,
+ MDIO_AN_DEVAD,
+ MDIO_AN_REG_8481_10GBASE_T_AN_CTRL,
+ an_10g_val | 0x1000);
bnx2x_cl45_write(bp, phy,
- MDIO_AN_DEVAD, MDIO_AN_REG_CTRL,
- 0x3200);
+ MDIO_AN_DEVAD, MDIO_AN_REG_CTRL,
+ 0x3200);
} else
bnx2x_cl45_write(bp, phy,
MDIO_AN_DEVAD,
return bnx2x_848xx_cmn_config_init(phy, params, vars);
}
-
-#define PHY84833_HDSHK_WAIT 300
-static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy,
+#define PHY84833_CMDHDLR_WAIT 300
+#define PHY84833_CMDHDLR_MAX_ARGS 5
+static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
struct link_params *params,
- struct link_vars *vars)
+ u16 fw_cmd,
+ u16 cmd_args[])
{
u32 idx;
- u32 pair_swap;
u16 val;
- u16 data;
struct bnx2x *bp = params->bp;
- /* Do pair swap */
-
- /* Check for configuration. */
- pair_swap = REG_RD(bp, params->shmem_base +
- offsetof(struct shmem_region,
- dev_info.port_hw_config[params->port].xgbt_phy_cfg)) &
- PORT_HW_CFG_RJ45_PAIR_SWAP_MASK;
-
- if (pair_swap == 0)
- return 0;
-
- data = (u16)pair_swap;
-
/* Write CMD_OPEN_OVERRIDE to STATUS reg */
bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2,
- PHY84833_CMD_OPEN_OVERRIDE);
- for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
+ MDIO_84833_CMD_HDLR_STATUS,
+ PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+ for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) {
bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
- if (val == PHY84833_CMD_OPEN_FOR_CMDS)
+ MDIO_84833_CMD_HDLR_STATUS, &val);
+ if (val == PHY84833_STATUS_CMD_OPEN_FOR_CMDS)
break;
msleep(1);
}
- if (idx >= PHY84833_HDSHK_WAIT) {
- DP(NETIF_MSG_LINK, "Pairswap: FW not ready.\n");
+ if (idx >= PHY84833_CMDHDLR_WAIT) {
+ DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n");
return -EINVAL;
}
+ /* Prepare argument(s) and issue command */
+ for (idx = 0; idx < PHY84833_CMDHDLR_MAX_ARGS; idx++) {
+ bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+ MDIO_84833_CMD_HDLR_DATA1 + idx,
+ cmd_args[idx]);
+ }
bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG4,
- data);
- /* Issue pair swap command */
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG0,
- PHY84833_DIAG_CMD_PAIR_SWAP_CHANGE);
- for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
+ MDIO_84833_CMD_HDLR_COMMAND, fw_cmd);
+ for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) {
bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
- if ((val == PHY84833_CMD_COMPLETE_PASS) ||
- (val == PHY84833_CMD_COMPLETE_ERROR))
+ MDIO_84833_CMD_HDLR_STATUS, &val);
+ if ((val == PHY84833_STATUS_CMD_COMPLETE_PASS) ||
+ (val == PHY84833_STATUS_CMD_COMPLETE_ERROR))
break;
msleep(1);
}
- if ((idx >= PHY84833_HDSHK_WAIT) ||
- (val == PHY84833_CMD_COMPLETE_ERROR)) {
- DP(NETIF_MSG_LINK, "Pairswap: override failed.\n");
+ if ((idx >= PHY84833_CMDHDLR_WAIT) ||
+ (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) {
+ DP(NETIF_MSG_LINK, "FW cmd failed.\n");
return -EINVAL;
}
+ /* Gather returning data */
+ for (idx = 0; idx < PHY84833_CMDHDLR_MAX_ARGS; idx++) {
+ bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
+ MDIO_84833_CMD_HDLR_DATA1 + idx,
+ &cmd_args[idx]);
+ }
bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2,
- PHY84833_CMD_CLEAR_COMPLETE);
- DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data);
+ MDIO_84833_CMD_HDLR_STATUS,
+ PHY84833_STATUS_CMD_CLEAR_COMPLETE);
return 0;
}
+static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy,
+ struct link_params *params,
+ struct link_vars *vars)
+{
+ u32 pair_swap;
+ u16 data[PHY84833_CMDHDLR_MAX_ARGS];
+ int status;
+ struct bnx2x *bp = params->bp;
+
+ /* Check for configuration. */
+ pair_swap = REG_RD(bp, params->shmem_base +
+ offsetof(struct shmem_region,
+ dev_info.port_hw_config[params->port].xgbt_phy_cfg)) &
+ PORT_HW_CFG_RJ45_PAIR_SWAP_MASK;
+
+ if (pair_swap == 0)
+ return 0;
+
+ /* Only the second argument is used for this command */
+ data[1] = (u16)pair_swap;
+
+ status = bnx2x_84833_cmd_hdlr(phy, params,
+ PHY84833_CMD_SET_PAIR_SWAP, data);
+ if (status == 0)
+ DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]);
+
+ return status;
+}
+
static u8 bnx2x_84833_get_reset_gpios(struct bnx2x *bp,
u32 shmem_base_path[],
u32 chip_id)
return 0;
}
-static int bnx2x_84833_common_init_phy(struct bnx2x *bp,
- u32 shmem_base_path[],
- u32 chip_id)
-{
- u8 reset_gpios;
-
- reset_gpios = bnx2x_84833_get_reset_gpios(bp, shmem_base_path, chip_id);
-
- bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_LOW);
- udelay(10);
- bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_HIGH);
- msleep(800);
- DP(NETIF_MSG_LINK, "84833 reset pulse on pin values 0x%x\n",
- reset_gpios);
-
- return 0;
-}
-
#define PHY84833_CONSTANT_LATENCY 1193
static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
struct link_params *params,
struct bnx2x *bp = params->bp;
u8 port, initialize = 1;
u16 val;
- u16 temp;
- u32 actual_phy_selection, cms_enable, idx;
+ u32 actual_phy_selection, cms_enable;
+ u16 cmd_args[PHY84833_CMDHDLR_MAX_ARGS];
int rc = 0;
msleep(1);
bnx2x_cl45_write(bp, phy,
MDIO_PMA_DEVAD,
MDIO_PMA_REG_CTRL, 0x8000);
+ }
+
+ bnx2x_wait_reset_complete(bp, phy, params);
+
+ /* Wait for GPHY to come out of reset */
+ msleep(50);
+ if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
/* Bring PHY out of super isolate mode */
bnx2x_cl45_read(bp, phy,
MDIO_CTL_DEVAD,
bnx2x_cl45_write(bp, phy,
MDIO_CTL_DEVAD,
MDIO_84833_TOP_CFG_XGPHY_STRAP1, val);
- }
-
- bnx2x_wait_reset_complete(bp, phy, params);
-
- /* Wait for GPHY to come out of reset */
- msleep(50);
-
- if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833)
bnx2x_84833_pair_swap_cfg(phy, params, vars);
-
- /*
- * BCM84823 requires that XGXS links up first @ 10G for normal behavior
- */
- temp = vars->line_speed;
- vars->line_speed = SPEED_10000;
- bnx2x_set_autoneg(¶ms->phy[INT_PHY], params, vars, 0);
- bnx2x_program_serdes(¶ms->phy[INT_PHY], params, vars);
- vars->line_speed = temp;
-
- /* Set dual-media configuration according to configuration */
+ } else {
+ /*
+ * BCM84823 requires that XGXS links up first @ 10G for normal
+ * behavior.
+ */
+ u16 temp;
+ temp = vars->line_speed;
+ vars->line_speed = SPEED_10000;
+ bnx2x_set_autoneg(¶ms->phy[INT_PHY], params, vars, 0);
+ bnx2x_program_serdes(¶ms->phy[INT_PHY], params, vars);
+ vars->line_speed = temp;
+ }
bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
MDIO_CTL_REG_84823_MEDIA, &val);
/* AutogrEEEn */
if (params->feature_config_flags &
- FEATURE_CONFIG_AUTOGREEEN_ENABLED) {
- /* Ensure that f/w is ready */
- for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
- bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
- if (val == PHY84833_CMD_OPEN_FOR_CMDS)
- break;
- usleep_range(1000, 1000);
- }
- if (idx >= PHY84833_HDSHK_WAIT) {
- DP(NETIF_MSG_LINK, "AutogrEEEn: FW not ready.\n");
- return -EINVAL;
- }
-
- /* Select EEE mode */
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG3,
- 0x2);
-
- /* Set Idle and Latency */
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG4,
- PHY84833_CONSTANT_LATENCY + 1);
-
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_DATA3_REG,
- PHY84833_CONSTANT_LATENCY + 1);
-
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_DATA4_REG,
- PHY84833_CONSTANT_LATENCY);
-
- /* Send EEE instruction to command register */
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG0,
- PHY84833_DIAG_CMD_SET_EEE_MODE);
-
- /* Ensure that the command has completed */
- for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
- bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
- if ((val == PHY84833_CMD_COMPLETE_PASS) ||
- (val == PHY84833_CMD_COMPLETE_ERROR))
- break;
- usleep_range(1000, 1000);
- }
- if ((idx >= PHY84833_HDSHK_WAIT) ||
- (val == PHY84833_CMD_COMPLETE_ERROR)) {
- DP(NETIF_MSG_LINK, "AutogrEEEn: command failed.\n");
- return -EINVAL;
- }
-
- /* Reset command handler */
- bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
- MDIO_84833_TOP_CFG_SCRATCH_REG2,
- PHY84833_CMD_CLEAR_COMPLETE);
- }
+ FEATURE_CONFIG_AUTOGREEEN_ENABLED)
+ cmd_args[0] = 0x2;
+ else
+ cmd_args[0] = 0x0;
+ cmd_args[1] = 0x0;
+ cmd_args[2] = PHY84833_CONSTANT_LATENCY + 1;
+ cmd_args[3] = PHY84833_CONSTANT_LATENCY;
+ rc = bnx2x_84833_cmd_hdlr(phy, params,
+ PHY84833_CMD_SET_EEE_MODE, cmd_args);
+ if (rc != 0)
+ DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n");
if (initialize)
rc = bnx2x_848xx_cmn_config_init(phy, params, vars);
else
DP(NETIF_MSG_LINK, "54618SE cfg init\n");
usleep_range(1000, 1000);
- /* This works with E3 only, no need to check the chip
- before determining the port. */
+ /*
+ * This works with E3 only, no need to check the chip
+ * before determining the port.
+ */
port = params->port;
cfg_pin = (REG_RD(bp, params->shmem_base +
return 0;
}
+
+static void bnx2x_5461x_set_link_led(struct bnx2x_phy *phy,
+ struct link_params *params, u8 mode)
+{
+ struct bnx2x *bp = params->bp;
+ u16 temp;
+
+ bnx2x_cl22_write(bp, phy,
+ MDIO_REG_GPHY_SHADOW,
+ MDIO_REG_GPHY_SHADOW_LED_SEL1);
+ bnx2x_cl22_read(bp, phy,
+ MDIO_REG_GPHY_SHADOW,
+ &temp);
+ temp &= 0xff00;
+
+ DP(NETIF_MSG_LINK, "54618x set link led (mode=%x)\n", mode);
+ switch (mode) {
+ case LED_MODE_FRONT_PANEL_OFF:
+ case LED_MODE_OFF:
+ temp |= 0x00ee;
+ break;
+ case LED_MODE_OPER:
+ temp |= 0x0001;
+ break;
+ case LED_MODE_ON:
+ temp |= 0x00ff;
+ break;
+ default:
+ break;
+ }
+ bnx2x_cl22_write(bp, phy,
+ MDIO_REG_GPHY_SHADOW,
+ MDIO_REG_GPHY_SHADOW_WR_ENA | temp);
+ return;
+}
+
+
static void bnx2x_54618se_link_reset(struct bnx2x_phy *phy,
struct link_params *params)
{
.config_loopback = (config_loopback_t)bnx2x_54618se_config_loopback,
.format_fw_ver = (format_fw_ver_t)NULL,
.hw_reset = (hw_reset_t)NULL,
- .set_link_led = (set_link_led_t)NULL,
+ .set_link_led = (set_link_led_t)bnx2x_5461x_set_link_led,
.phy_specific_func = (phy_specific_func_t)NULL
};
/*****************************************************************/
offsetof(struct shmem_region,
dev_info.port_feature_config[port].link_config)) &
PORT_FEATURE_CONNECTED_SWITCH_MASK);
- chip_id = REG_RD(bp, MISC_REG_CHIP_NUM) << 16;
+ chip_id = (REG_RD(bp, MISC_REG_CHIP_NUM) << 16) |
+ ((REG_RD(bp, MISC_REG_CHIP_REV) & 0xf) << 12);
+
DP(NETIF_MSG_LINK, ":chip_id = 0x%x\n", chip_id);
if (USES_WARPCORE(bp)) {
u32 serdes_net_if;
return -EINVAL;
default:
*phy = phy_null;
+ /* In case external PHY wasn't found */
+ if ((phy_type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT) &&
+ (phy_type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN))
+ return -EINVAL;
return 0;
}
int bnx2x_phy_probe(struct link_params *params)
{
- u8 phy_index, actual_phy_idx, link_cfg_idx;
+ u8 phy_index, actual_phy_idx;
u32 phy_config_swapped, sync_offset, media_types;
struct bnx2x *bp = params->bp;
struct bnx2x_phy *phy;
for (phy_index = INT_PHY; phy_index < MAX_PHYS;
phy_index++) {
- link_cfg_idx = LINK_CONFIG_IDX(phy_index);
actual_phy_idx = phy_index;
if (phy_config_swapped) {
if (phy_index == EXT_PHY1)
return 0;
}
+static int bnx2x_84833_common_init_phy(struct bnx2x *bp,
+ u32 shmem_base_path[],
+ u32 shmem2_base_path[],
+ u8 phy_index,
+ u32 chip_id)
+{
+ u8 reset_gpios;
+ struct bnx2x_phy phy;
+ u32 shmem_base, shmem2_base, cnt;
+ s8 port = 0;
+ u16 val;
+
+ reset_gpios = bnx2x_84833_get_reset_gpios(bp, shmem_base_path, chip_id);
+ bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_LOW);
+ udelay(10);
+ bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_HIGH);
+ DP(NETIF_MSG_LINK, "84833 reset pulse on pin values 0x%x\n",
+ reset_gpios);
+ for (port = PORT_MAX - 1; port >= PORT_0; port--) {
+ /* This PHY is for E2 and E3. */
+ shmem_base = shmem_base_path[port];
+ shmem2_base = shmem2_base_path[port];
+ /* Extract the ext phy address for the port */
+ if (bnx2x_populate_phy(bp, phy_index, shmem_base, shmem2_base,
+ 0, &phy) !=
+ 0) {
+ DP(NETIF_MSG_LINK, "populate_phy failed\n");
+ return -EINVAL;
+ }
+
+ /* Wait for FW completing its initialization. */
+ for (cnt = 0; cnt < 1000; cnt++) {
+ bnx2x_cl45_read(bp, &phy,
+ MDIO_PMA_DEVAD,
+ MDIO_PMA_REG_CTRL, &val);
+ if (!(val & (1<<15)))
+ break;
+ msleep(1);
+ }
+ if (cnt >= 1000)
+ DP(NETIF_MSG_LINK,
+ "84833 Cmn reset timeout (%d)\n", port);
+
+ /* Put the port in super isolate mode. */
+ bnx2x_cl45_read(bp, &phy,
+ MDIO_CTL_DEVAD,
+ MDIO_84833_TOP_CFG_XGPHY_STRAP1, &val);
+ val |= MDIO_84833_SUPER_ISOLATE;
+ bnx2x_cl45_write(bp, &phy,
+ MDIO_CTL_DEVAD,
+ MDIO_84833_TOP_CFG_XGPHY_STRAP1, val);
+ }
+
+ return 0;
+}
+
+
static int bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[],
u32 shmem2_base_path[], u8 phy_index,
u32 ext_phy_type, u32 chip_id)
* GPIO3's are linked, and so both need to be toggled
* to obtain required 2us pulse.
*/
- rc = bnx2x_84833_common_init_phy(bp, shmem_base_path, chip_id);
+ rc = bnx2x_84833_common_init_phy(bp, shmem_base_path,
+ shmem2_base_path,
+ phy_index, chip_id);
break;
case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_FAILURE:
rc = -EINVAL;
/* Configure the COS to ETS according to BW and SP settings.*/
int bnx2x_ets_e3b0_config(const struct link_params *params,
const struct link_vars *vars,
- const struct bnx2x_ets_params *ets_params);
+ struct bnx2x_ets_params *ets_params);
/* Read pfc statistic*/
void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars,
u32 pfc_frames_sent[2],
CMNG_FLAGS_PER_PORT_FAIRNESS_VN;
}
-/* returns func by VN for current port */
-static inline int func_by_vn(struct bnx2x *bp, int vn)
-{
- return 2 * vn + BP_PORT(bp);
-}
-
static void bnx2x_init_vn_minmax(struct bnx2x *bp, int vn)
{
struct rate_shaping_vars_per_vn m_rs_vn;
"rate shaping and fairness are disabled\n");
}
-static inline void bnx2x_link_sync_notify(struct bnx2x *bp)
-{
- int func;
- int vn;
-
- /* Set the attention towards other drivers on the same port */
- for (vn = VN_0; vn < BP_MAX_VN_NUM(bp); vn++) {
- if (vn == BP_VN(bp))
- continue;
-
- func = func_by_vn(bp, vn);
- REG_WR(bp, MISC_REG_AEU_GENERAL_ATTN_0 +
- (LINK_SYNC_ATTENTION_BIT_FUNC_0 + func)*4, 1);
- }
-}
-
/* This function is called upon link interrupt */
static void bnx2x_link_attn(struct bnx2x *bp)
{
if (bp->state != BNX2X_STATE_OPEN)
return;
+ /* read updated dcb configuration */
+ bnx2x_dcbx_pmf_update(bp);
+
bnx2x_link_status_update(&bp->link_params, &bp->link_vars);
if (bp->link_vars.link_up)
return rc;
}
-static u8 stat_counter_valid(struct bnx2x *bp, struct bnx2x_fastpath *fp)
-{
-#ifdef BCM_CNIC
- /* Statistics are not supported for CNIC Clients at the moment */
- if (IS_FCOE_FP(fp))
- return false;
-#endif
- return true;
-}
void bnx2x_func_init(struct bnx2x *bp, struct bnx2x_func_init_params *p)
{
* parent connection). The statistics are zeroed when the parent
* connection is initialized.
*/
- if (stat_counter_valid(bp, fp)) {
- __set_bit(BNX2X_Q_FLG_STATS, &flags);
- if (zero_stats)
- __set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);
- }
+
+ __set_bit(BNX2X_Q_FLG_STATS, &flags);
+ if (zero_stats)
+ __set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);
+
return flags;
}
/* This should be a maximum number of data bytes that may be
* placed on the BD (not including paddings).
*/
- rxq_init->buf_sz = fp->rx_buf_size - BNX2X_FW_RX_ALIGN -
- IP_HEADER_ALIGNMENT_PADDING;
+ rxq_init->buf_sz = fp->rx_buf_size - BNX2X_FW_RX_ALIGN_START -
+ BNX2X_FW_RX_ALIGN_END - IP_HEADER_ALIGNMENT_PADDING;
rxq_init->cl_qzone_id = fp->cl_qzone_id;
rxq_init->tpa_agg_sz = tpa_agg_size;
*/
}
+#define DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED 3
+
+static void bnx2x_drv_info_ether_stat(struct bnx2x *bp)
+{
+ struct eth_stats_info *ether_stat =
+ &bp->slowpath->drv_info_to_mcp.ether_stat;
+
+ /* leave last char as NULL */
+ memcpy(ether_stat->version, DRV_MODULE_VERSION,
+ ETH_STAT_INFO_VERSION_LEN - 1);
+
+ bp->fp[0].mac_obj.get_n_elements(bp, &bp->fp[0].mac_obj,
+ DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
+ ether_stat->mac_local);
+
+ ether_stat->mtu_size = bp->dev->mtu;
+
+ if (bp->dev->features & NETIF_F_RXCSUM)
+ ether_stat->feature_flags |= FEATURE_ETH_CHKSUM_OFFLOAD_MASK;
+ if (bp->dev->features & NETIF_F_TSO)
+ ether_stat->feature_flags |= FEATURE_ETH_LSO_MASK;
+ ether_stat->feature_flags |= bp->common.boot_mode;
+
+ ether_stat->promiscuous_mode = (bp->dev->flags & IFF_PROMISC) ? 1 : 0;
+
+ ether_stat->txq_size = bp->tx_ring_size;
+ ether_stat->rxq_size = bp->rx_ring_size;
+}
+
+static void bnx2x_drv_info_fcoe_stat(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+ struct bnx2x_dcbx_app_params *app = &bp->dcbx_port_params.app;
+ struct fcoe_stats_info *fcoe_stat =
+ &bp->slowpath->drv_info_to_mcp.fcoe_stat;
+
+ memcpy(fcoe_stat->mac_local, bp->fip_mac, ETH_ALEN);
+
+ fcoe_stat->qos_priority =
+ app->traffic_type_priority[LLFC_TRAFFIC_TYPE_FCOE];
+
+ /* insert FCoE stats from ramrod response */
+ if (!NO_FCOE(bp)) {
+ struct tstorm_per_queue_stats *fcoe_q_tstorm_stats =
+ &bp->fw_stats_data->queue_stats[FCOE_IDX].
+ tstorm_queue_statistics;
+
+ struct xstorm_per_queue_stats *fcoe_q_xstorm_stats =
+ &bp->fw_stats_data->queue_stats[FCOE_IDX].
+ xstorm_queue_statistics;
+
+ struct fcoe_statistics_params *fw_fcoe_stat =
+ &bp->fw_stats_data->fcoe;
+
+ ADD_64(fcoe_stat->rx_bytes_hi, 0, fcoe_stat->rx_bytes_lo,
+ fw_fcoe_stat->rx_stat0.fcoe_rx_byte_cnt);
+
+ ADD_64(fcoe_stat->rx_bytes_hi,
+ fcoe_q_tstorm_stats->rcv_ucast_bytes.hi,
+ fcoe_stat->rx_bytes_lo,
+ fcoe_q_tstorm_stats->rcv_ucast_bytes.lo);
+
+ ADD_64(fcoe_stat->rx_bytes_hi,
+ fcoe_q_tstorm_stats->rcv_bcast_bytes.hi,
+ fcoe_stat->rx_bytes_lo,
+ fcoe_q_tstorm_stats->rcv_bcast_bytes.lo);
+
+ ADD_64(fcoe_stat->rx_bytes_hi,
+ fcoe_q_tstorm_stats->rcv_mcast_bytes.hi,
+ fcoe_stat->rx_bytes_lo,
+ fcoe_q_tstorm_stats->rcv_mcast_bytes.lo);
+
+ ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+ fw_fcoe_stat->rx_stat0.fcoe_rx_pkt_cnt);
+
+ ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+ fcoe_q_tstorm_stats->rcv_ucast_pkts);
+
+ ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+ fcoe_q_tstorm_stats->rcv_bcast_pkts);
+
+ ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+ fcoe_q_tstorm_stats->rcv_mcast_pkts);
+
+ ADD_64(fcoe_stat->tx_bytes_hi, 0, fcoe_stat->tx_bytes_lo,
+ fw_fcoe_stat->tx_stat.fcoe_tx_byte_cnt);
+
+ ADD_64(fcoe_stat->tx_bytes_hi,
+ fcoe_q_xstorm_stats->ucast_bytes_sent.hi,
+ fcoe_stat->tx_bytes_lo,
+ fcoe_q_xstorm_stats->ucast_bytes_sent.lo);
+
+ ADD_64(fcoe_stat->tx_bytes_hi,
+ fcoe_q_xstorm_stats->bcast_bytes_sent.hi,
+ fcoe_stat->tx_bytes_lo,
+ fcoe_q_xstorm_stats->bcast_bytes_sent.lo);
+
+ ADD_64(fcoe_stat->tx_bytes_hi,
+ fcoe_q_xstorm_stats->mcast_bytes_sent.hi,
+ fcoe_stat->tx_bytes_lo,
+ fcoe_q_xstorm_stats->mcast_bytes_sent.lo);
+
+ ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+ fw_fcoe_stat->tx_stat.fcoe_tx_pkt_cnt);
+
+ ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+ fcoe_q_xstorm_stats->ucast_pkts_sent);
+
+ ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+ fcoe_q_xstorm_stats->bcast_pkts_sent);
+
+ ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+ fcoe_q_xstorm_stats->mcast_pkts_sent);
+ }
+
+ /* ask L5 driver to add data to the struct */
+ bnx2x_cnic_notify(bp, CNIC_CTL_FCOE_STATS_GET_CMD);
+#endif
+}
+
+static void bnx2x_drv_info_iscsi_stat(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+ struct bnx2x_dcbx_app_params *app = &bp->dcbx_port_params.app;
+ struct iscsi_stats_info *iscsi_stat =
+ &bp->slowpath->drv_info_to_mcp.iscsi_stat;
+
+ memcpy(iscsi_stat->mac_local, bp->cnic_eth_dev.iscsi_mac, ETH_ALEN);
+
+ iscsi_stat->qos_priority =
+ app->traffic_type_priority[LLFC_TRAFFIC_TYPE_ISCSI];
+
+ /* ask L5 driver to add data to the struct */
+ bnx2x_cnic_notify(bp, CNIC_CTL_ISCSI_STATS_GET_CMD);
+#endif
+}
+
/* called due to MCP event (on pmf):
* reread new bandwidth configuration
* configure FW
bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW_ACK, 0);
}
+static void bnx2x_handle_drv_info_req(struct bnx2x *bp)
+{
+ enum drv_info_opcode op_code;
+ u32 drv_info_ctl = SHMEM2_RD(bp, drv_info_control);
+
+ /* if drv_info version supported by MFW doesn't match - send NACK */
+ if ((drv_info_ctl & DRV_INFO_CONTROL_VER_MASK) != DRV_INFO_CUR_VER) {
+ bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_NACK, 0);
+ return;
+ }
+
+ op_code = (drv_info_ctl & DRV_INFO_CONTROL_OP_CODE_MASK) >>
+ DRV_INFO_CONTROL_OP_CODE_SHIFT;
+
+ memset(&bp->slowpath->drv_info_to_mcp, 0,
+ sizeof(union drv_info_to_mcp));
+
+ switch (op_code) {
+ case ETH_STATS_OPCODE:
+ bnx2x_drv_info_ether_stat(bp);
+ break;
+ case FCOE_STATS_OPCODE:
+ bnx2x_drv_info_fcoe_stat(bp);
+ break;
+ case ISCSI_STATS_OPCODE:
+ bnx2x_drv_info_iscsi_stat(bp);
+ break;
+ default:
+ /* if op code isn't supported - send NACK */
+ bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_NACK, 0);
+ return;
+ }
+
+ /* if we got drv_info attn from MFW then these fields are defined in
+ * shmem2 for sure
+ */
+ SHMEM2_WR(bp, drv_info_host_addr_lo,
+ U64_LO(bnx2x_sp_mapping(bp, drv_info_to_mcp)));
+ SHMEM2_WR(bp, drv_info_host_addr_hi,
+ U64_HI(bnx2x_sp_mapping(bp, drv_info_to_mcp)));
+
+ bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_ACK, 0);
+}
+
static void bnx2x_dcc_event(struct bnx2x *bp, u32 dcc_event)
{
DP(BNX2X_MSG_MCP, "dcc_event 0x%x\n", dcc_event);
netdev_err(bp->dev, "Fan Failure on Network Controller has caused"
" the driver to shutdown the card to prevent permanent"
" damage. Please contact OEM Support for assistance\n");
+
+ /*
+ * Scheudle device reset (unload)
+ * This is due to some boards consuming sufficient power when driver is
+ * up to overheat if fan fails.
+ */
+ smp_mb__before_clear_bit();
+ set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state);
+ smp_mb__after_clear_bit();
+ schedule_delayed_work(&bp->sp_rtnl_task, 0);
+
}
static inline void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
if (val & DRV_STATUS_SET_MF_BW)
bnx2x_set_mf_bw(bp);
+ if (val & DRV_STATUS_DRV_INFO_REQ)
+ bnx2x_handle_drv_info_req(bp);
if ((bp->port.pmf == 0) && (val & DRV_STATUS_PMF))
bnx2x_pmf_update(bp);
u8 cos;
unsigned long q_type = 0;
u32 cids[BNX2X_MULTI_TX_COS] = { 0 };
-
+ fp->rx_queue = fp_idx;
fp->cid = fp_idx;
fp->cl_id = bnx2x_fp_cl_id(fp);
fp->fw_sb_id = bnx2x_fp_fw_sb_id(fp);
static inline int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
{
int num_groups;
+ int is_fcoe_stats = NO_FCOE(bp) ? 0 : 1;
- /* number of eth_queues */
- u8 num_queue_stats = BNX2X_NUM_ETH_QUEUES(bp);
+ /* number of queues for statistics is number of eth queues + FCoE */
+ u8 num_queue_stats = BNX2X_NUM_ETH_QUEUES(bp) + is_fcoe_stats;
/* Total number of FW statistics requests =
- * 1 for port stats + 1 for PF stats + num_eth_queues */
- bp->fw_stats_num = 2 + num_queue_stats;
+ * 1 for port stats + 1 for PF stats + potential 1 for FCoE stats +
+ * num of queues
+ */
+ bp->fw_stats_num = 2 + is_fcoe_stats + num_queue_stats;
/* Request is built from stats_query_header and an array of
* STATS_QUERY_CMD_COUNT rules. The real number or requests is
* configured in the stats_query_header.
*/
- num_groups = (2 + num_queue_stats) / STATS_QUERY_CMD_COUNT +
- (((2 + num_queue_stats) % STATS_QUERY_CMD_COUNT) ? 1 : 0);
+ num_groups = ((bp->fw_stats_num) / STATS_QUERY_CMD_COUNT) +
+ (((bp->fw_stats_num) % STATS_QUERY_CMD_COUNT) ? 1 : 0);
bp->fw_stats_req_sz = sizeof(struct stats_query_header) +
num_groups * sizeof(struct stats_query_cmd_group);
*
* stats_counter holds per-STORM counters that are incremented
* when STORM has finished with the current request.
+ *
+ * memory for FCoE offloaded statistics are counted anyway,
+ * even if they will not be sent.
*/
bp->fw_stats_data_sz = sizeof(struct per_port_stats) +
sizeof(struct per_pf_stats) +
+ sizeof(struct fcoe_statistics_params) +
sizeof(struct per_queue_stats) * num_queue_stats +
sizeof(struct stats_counter);
{
unsigned long ramrod_flags = 0;
+#ifdef BCM_CNIC
+ if (is_zero_ether_addr(bp->dev->dev_addr) && IS_MF_ISCSI_SD(bp)) {
+ DP(NETIF_MSG_IFUP, "Ignoring Zero MAC for iSCSI SD mode\n");
+ return 0;
+ }
+#endif
+
DP(NETIF_MSG_IFUP, "Adding Eth MAC\n");
__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
if (test_and_clear_bit(BNX2X_SP_RTNL_SETUP_TC, &bp->sp_rtnl_state))
bnx2x_setup_tc(bp->dev, bp->dcbx_port_params.ets.num_of_cos);
+ /*
+ * in case of fan failure we need to reset id if the "stop on error"
+ * debug flag is set, since we trying to prevent permanent overheating
+ * damage
+ */
+ if (test_and_clear_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state)) {
+ DP(BNX2X_MSG_SP, "fan failure detected. Unloading driver\n");
+ netif_device_detach(bp->dev);
+ bnx2x_close(bp->dev);
+ }
+
sp_rtnl_exit:
rtnl_unlock();
}
static void __devinit bnx2x_get_common_hwinfo(struct bnx2x *bp)
{
- u32 val, val2, val3, val4, id;
+ u32 val, val2, val3, val4, id, boot_mode;
u16 pmc;
/* Get the chip revision id and number. */
bp->link_params.feature_config_flags |=
(val >= REQ_BC_VER_4_SFP_TX_DISABLE_SUPPORTED) ?
FEATURE_CONFIG_BC_SUPPORTS_SFP_TX_DISABLED : 0;
+ bp->flags |= (val >= REQ_BC_VER_4_PFC_STATS_SUPPORTED) ?
+ BC_SUPPORTS_PFC_STATS : 0;
+
+ boot_mode = SHMEM_RD(bp,
+ dev_info.port_feature_config[BP_PORT(bp)].mba_config) &
+ PORT_FEATURE_MBA_BOOT_AGENT_TYPE_MASK;
+ switch (boot_mode) {
+ case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_PXE:
+ bp->common.boot_mode = FEATURE_ETH_BOOTMODE_PXE;
+ break;
+ case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_ISCSIB:
+ bp->common.boot_mode = FEATURE_ETH_BOOTMODE_ISCSI;
+ break;
+ case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_FCOE_BOOT:
+ bp->common.boot_mode = FEATURE_ETH_BOOTMODE_FCOE;
+ break;
+ case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_NONE:
+ bp->common.boot_mode = FEATURE_ETH_BOOTMODE_NONE;
+ break;
+ }
pci_read_config_word(bp->pdev, bp->pm_cap + PCI_PM_PMC, &pmc);
bp->flags |= (pmc & PCI_PM_CAP_PME_D3cold) ? 0 : NO_WOL_FLAG;
bp->common.shmem2_base);
}
-#ifdef BCM_CNIC
-static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp)
+void bnx2x_get_iscsi_info(struct bnx2x *bp)
{
+#ifdef BCM_CNIC
int port = BP_PORT(bp);
- int func = BP_ABS_FUNC(bp);
u32 max_iscsi_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
drv_lic_key[port].max_iscsi_conn);
- u32 max_fcoe_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
- drv_lic_key[port].max_fcoe_conn);
- /* Get the number of maximum allowed iSCSI and FCoE connections */
+ /* Get the number of maximum allowed iSCSI connections */
bp->cnic_eth_dev.max_iscsi_conn =
(max_iscsi_conn & BNX2X_MAX_ISCSI_INIT_CONN_MASK) >>
BNX2X_MAX_ISCSI_INIT_CONN_SHIFT;
+ BNX2X_DEV_INFO("max_iscsi_conn 0x%x\n",
+ bp->cnic_eth_dev.max_iscsi_conn);
+
+ /*
+ * If maximum allowed number of connections is zero -
+ * disable the feature.
+ */
+ if (!bp->cnic_eth_dev.max_iscsi_conn)
+ bp->flags |= NO_ISCSI_FLAG;
+#else
+ bp->flags |= NO_ISCSI_FLAG;
+#endif
+}
+
+static void __devinit bnx2x_get_fcoe_info(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+ int port = BP_PORT(bp);
+ int func = BP_ABS_FUNC(bp);
+
+ u32 max_fcoe_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
+ drv_lic_key[port].max_fcoe_conn);
+
+ /* Get the number of maximum allowed FCoE connections */
bp->cnic_eth_dev.max_fcoe_conn =
(max_fcoe_conn & BNX2X_MAX_FCOE_INIT_CONN_MASK) >>
BNX2X_MAX_FCOE_INIT_CONN_SHIFT;
}
}
- BNX2X_DEV_INFO("max_iscsi_conn 0x%x max_fcoe_conn 0x%x\n",
- bp->cnic_eth_dev.max_iscsi_conn,
- bp->cnic_eth_dev.max_fcoe_conn);
+ BNX2X_DEV_INFO("max_fcoe_conn 0x%x\n", bp->cnic_eth_dev.max_fcoe_conn);
/*
* If maximum allowed number of connections is zero -
* disable the feature.
*/
- if (!bp->cnic_eth_dev.max_iscsi_conn)
- bp->flags |= NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG;
-
if (!bp->cnic_eth_dev.max_fcoe_conn)
bp->flags |= NO_FCOE_FLAG;
-}
+#else
+ bp->flags |= NO_FCOE_FLAG;
#endif
+}
+
+static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp)
+{
+ /*
+ * iSCSI may be dynamically disabled but reading
+ * info here we will decrease memory usage by driver
+ * if the feature is disabled for good
+ */
+ bnx2x_get_iscsi_info(bp);
+ bnx2x_get_fcoe_info(bp);
+}
static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp)
{
bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2);
#ifdef BCM_CNIC
- /* iSCSI and FCoE NPAR MACs: if there is no either iSCSI or
+ /*
+ * iSCSI and FCoE NPAR MACs: if there is no either iSCSI or
* FCoE MAC then the appropriate feature should be disabled.
*/
if (IS_MF_SI(bp)) {
val = MF_CFG_RD(bp, func_ext_config[func].
fcoe_mac_addr_lower);
bnx2x_set_mac_buf(fip_mac, val, val2);
- BNX2X_DEV_INFO("Read FCoE L2 MAC to %pM\n",
+ BNX2X_DEV_INFO("Read FCoE L2 MAC: %pM\n",
fip_mac);
} else
bp->flags |= NO_FCOE_FLAG;
+ } else { /* SD mode */
+ if (BNX2X_IS_MF_PROTOCOL_ISCSI(bp)) {
+ /* use primary mac as iscsi mac */
+ memcpy(iscsi_mac, bp->dev->dev_addr, ETH_ALEN);
+ /* Zero primary MAC configuration */
+ memset(bp->dev->dev_addr, 0, ETH_ALEN);
+
+ BNX2X_DEV_INFO("SD ISCSI MODE\n");
+ BNX2X_DEV_INFO("Read iSCSI MAC: %pM\n",
+ iscsi_mac);
+ }
}
#endif
} else {
}
#endif
- if (!is_valid_ether_addr(bp->dev->dev_addr))
+ if (!bnx2x_is_valid_ether_addr(bp, bp->dev->dev_addr))
dev_err(&bp->pdev->dev,
"bad Ethernet MAC address configuration: "
"%pM, change it manually before bringing up "
/* Get MAC addresses */
bnx2x_get_mac_hwinfo(bp);
-#ifdef BCM_CNIC
bnx2x_get_cnic_info(bp);
-#endif
/* Get current FW pulse sequence */
if (!BP_NOMCP(bp)) {
static void __devinit bnx2x_read_fwinfo(struct bnx2x *bp)
{
int cnt, i, block_end, rodi;
- char vpd_data[BNX2X_VPD_LEN+1];
+ char vpd_start[BNX2X_VPD_LEN+1];
char str_id_reg[VENDOR_ID_LEN+1];
char str_id_cap[VENDOR_ID_LEN+1];
+ char *vpd_data;
+ char *vpd_extended_data = NULL;
u8 len;
- cnt = pci_read_vpd(bp->pdev, 0, BNX2X_VPD_LEN, vpd_data);
+ cnt = pci_read_vpd(bp->pdev, 0, BNX2X_VPD_LEN, vpd_start);
memset(bp->fw_ver, 0, sizeof(bp->fw_ver));
if (cnt < BNX2X_VPD_LEN)
goto out_not_found;
- i = pci_vpd_find_tag(vpd_data, 0, BNX2X_VPD_LEN,
+ /* VPD RO tag should be first tag after identifier string, hence
+ * we should be able to find it in first BNX2X_VPD_LEN chars
+ */
+ i = pci_vpd_find_tag(vpd_start, 0, BNX2X_VPD_LEN,
PCI_VPD_LRDT_RO_DATA);
if (i < 0)
goto out_not_found;
-
block_end = i + PCI_VPD_LRDT_TAG_SIZE +
- pci_vpd_lrdt_size(&vpd_data[i]);
+ pci_vpd_lrdt_size(&vpd_start[i]);
i += PCI_VPD_LRDT_TAG_SIZE;
- if (block_end > BNX2X_VPD_LEN)
- goto out_not_found;
+ if (block_end > BNX2X_VPD_LEN) {
+ vpd_extended_data = kmalloc(block_end, GFP_KERNEL);
+ if (vpd_extended_data == NULL)
+ goto out_not_found;
+
+ /* read rest of vpd image into vpd_extended_data */
+ memcpy(vpd_extended_data, vpd_start, BNX2X_VPD_LEN);
+ cnt = pci_read_vpd(bp->pdev, BNX2X_VPD_LEN,
+ block_end - BNX2X_VPD_LEN,
+ vpd_extended_data + BNX2X_VPD_LEN);
+ if (cnt < (block_end - BNX2X_VPD_LEN))
+ goto out_not_found;
+ vpd_data = vpd_extended_data;
+ } else
+ vpd_data = vpd_start;
+
+ /* now vpd_data holds full vpd content in both cases */
rodi = pci_vpd_find_info_keyword(vpd_data, i, block_end,
PCI_VPD_RO_KEYWORD_MFR_ID);
bp->fw_ver[len] = ' ';
}
}
+ kfree(vpd_extended_data);
return;
}
out_not_found:
+ kfree(vpd_extended_data);
return;
}
bp->multi_mode = multi_mode;
+ bp->disable_tpa = disable_tpa;
+
+#ifdef BCM_CNIC
+ bp->disable_tpa |= IS_MF_ISCSI_SD(bp);
+#endif
+
/* Set TPA flags */
- if (disable_tpa) {
+ if (bp->disable_tpa) {
bp->flags &= ~TPA_ENABLE_FLAG;
bp->dev->features &= ~NETIF_F_LRO;
} else {
bp->flags |= TPA_ENABLE_FLAG;
bp->dev->features |= NETIF_F_LRO;
}
- bp->disable_tpa = disable_tpa;
if (CHIP_IS_E1(bp))
bp->dropless_fc = 0;
}
/* called with rtnl_lock */
-static int bnx2x_close(struct net_device *dev)
+int bnx2x_close(struct net_device *dev)
{
struct bnx2x *bp = netdev_priv(dev);
}
bp->rx_mode = rx_mode;
+#ifdef BCM_CNIC
+ /* handle ISCSI SD mode */
+ if (IS_MF_ISCSI_SD(bp))
+ bp->rx_mode = BNX2X_RX_MODE_NONE;
+#endif
/* Schedule the rx_mode command */
if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state)) {
}
#endif
+static int bnx2x_validate_addr(struct net_device *dev)
+{
+ struct bnx2x *bp = netdev_priv(dev);
+
+ if (!bnx2x_is_valid_ether_addr(bp, dev->dev_addr))
+ return -EADDRNOTAVAIL;
+ return 0;
+}
+
static const struct net_device_ops bnx2x_netdev_ops = {
.ndo_open = bnx2x_open,
.ndo_stop = bnx2x_close,
.ndo_select_queue = bnx2x_select_queue,
.ndo_set_rx_mode = bnx2x_set_rx_mode,
.ndo_set_mac_address = bnx2x_change_mac_addr,
- .ndo_validate_addr = eth_validate_addr,
+ .ndo_validate_addr = bnx2x_validate_addr,
.ndo_do_ioctl = bnx2x_ioctl,
.ndo_change_mtu = bnx2x_change_mtu,
.ndo_fix_features = bnx2x_fix_features,
int bnx2x_init_firmware(struct bnx2x *bp)
{
- const char *fw_file_name;
struct bnx2x_fw_file_hdr *fw_hdr;
int rc;
- if (CHIP_IS_E1(bp))
- fw_file_name = FW_FILE_NAME_E1;
- else if (CHIP_IS_E1H(bp))
- fw_file_name = FW_FILE_NAME_E1H;
- else if (!CHIP_IS_E1x(bp))
- fw_file_name = FW_FILE_NAME_E2;
- else {
- BNX2X_ERR("Unsupported chip revision\n");
- return -EINVAL;
- }
- BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
+ if (!bp->firmware) {
+ const char *fw_file_name;
- rc = request_firmware(&bp->firmware, fw_file_name, &bp->pdev->dev);
- if (rc) {
- BNX2X_ERR("Can't load firmware file %s\n", fw_file_name);
- goto request_firmware_exit;
- }
+ if (CHIP_IS_E1(bp))
+ fw_file_name = FW_FILE_NAME_E1;
+ else if (CHIP_IS_E1H(bp))
+ fw_file_name = FW_FILE_NAME_E1H;
+ else if (!CHIP_IS_E1x(bp))
+ fw_file_name = FW_FILE_NAME_E2;
+ else {
+ BNX2X_ERR("Unsupported chip revision\n");
+ return -EINVAL;
+ }
+ BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
- rc = bnx2x_check_firmware(bp);
- if (rc) {
- BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
- goto request_firmware_exit;
+ rc = request_firmware(&bp->firmware, fw_file_name,
+ &bp->pdev->dev);
+ if (rc) {
+ BNX2X_ERR("Can't load firmware file %s\n",
+ fw_file_name);
+ goto request_firmware_exit;
+ }
+
+ rc = bnx2x_check_firmware(bp);
+ if (rc) {
+ BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
+ goto request_firmware_exit;
+ }
}
fw_hdr = (struct bnx2x_fw_file_hdr *)bp->firmware->data;
kfree(bp->init_ops);
kfree(bp->init_data);
release_firmware(bp->firmware);
+ bp->firmware = NULL;
}
bp->qm_cid_count = bnx2x_set_qm_cid_count(bp);
#ifdef BCM_CNIC
- /* disable FCOE L2 queue for E1x and E3*/
- if (CHIP_IS_E1x(bp) || CHIP_IS_E3(bp))
+ /* disable FCOE L2 queue for E1x */
+ if (CHIP_IS_E1x(bp))
bp->flags |= NO_FCOE_FLAG;
#endif
if (bp->doorbells)
iounmap(bp->doorbells);
+ bnx2x_release_firmware(bp);
+
bnx2x_free_mem_bp(bp);
free_netdev(dev);
smp_mb__after_atomic_inc();
break;
}
+ case DRV_CTL_ULP_REGISTER_CMD: {
+ int ulp_type = ctl->data.ulp_type;
+
+ if (CHIP_IS_E3(bp)) {
+ int idx = BP_FW_MB_IDX(bp);
+ u32 cap;
+
+ cap = SHMEM2_RD(bp, drv_capabilities_flag[idx]);
+ if (ulp_type == CNIC_ULP_ISCSI)
+ cap |= DRV_FLAGS_CAPABILITIES_LOADED_ISCSI;
+ else if (ulp_type == CNIC_ULP_FCOE)
+ cap |= DRV_FLAGS_CAPABILITIES_LOADED_FCOE;
+ SHMEM2_WR(bp, drv_capabilities_flag[idx], cap);
+ }
+ break;
+ }
+ case DRV_CTL_ULP_UNREGISTER_CMD: {
+ int ulp_type = ctl->data.ulp_type;
+
+ if (CHIP_IS_E3(bp)) {
+ int idx = BP_FW_MB_IDX(bp);
+ u32 cap;
+
+ cap = SHMEM2_RD(bp, drv_capabilities_flag[idx]);
+ if (ulp_type == CNIC_ULP_ISCSI)
+ cap &= ~DRV_FLAGS_CAPABILITIES_LOADED_ISCSI;
+ else if (ulp_type == CNIC_ULP_FCOE)
+ cap &= ~DRV_FLAGS_CAPABILITIES_LOADED_FCOE;
+ SHMEM2_WR(bp, drv_capabilities_flag[idx], cap);
+ }
+ break;
+ }
default:
BNX2X_ERR("unknown command %x\n", ctl->cmd);
mutex_lock(&bp->cnic_mutex);
cp->drv_state = 0;
- rcu_assign_pointer(bp->cnic_ops, NULL);
+ RCU_INIT_POINTER(bp->cnic_ops, NULL);
mutex_unlock(&bp->cnic_mutex);
synchronize_rcu();
kfree(bp->cnic_kwq);
#define BRB1_REG_PAUSE_HIGH_THRESHOLD_1 0x6007c
/* [RW 10] Write client 0: Assert pause threshold. */
#define BRB1_REG_PAUSE_LOW_THRESHOLD_0 0x60068
-#define BRB1_REG_PAUSE_LOW_THRESHOLD_1 0x6006c
-/* [R 24] The number of full blocks occupied by port. */
+/* [RW 1] Indicates if to use per-class guaranty mode (new mode) or per-MAC
+ * guaranty mode (backwards-compatible mode). 0=per-MAC guaranty mode (BC
+ * mode). 1=per-class guaranty mode (new mode). */
+#define BRB1_REG_PER_CLASS_GUARANTY_MODE 0x60268
+/* [R 24] The number of full blocks occpied by port. */
#define BRB1_REG_PORT_NUM_OCC_BLOCKS_0 0x60094
/* [RW 1] Reset the design by software. */
#define BRB1_REG_SOFT_RESET 0x600dc
register bits. */
#define MISC_REG_LCPLL_CTRL_1 0xa2a4
#define MISC_REG_LCPLL_CTRL_REG_2 0xa2a8
+/* [RW 1] LCPLL power down. Global register. Active High. Reset on POR
+ * reset. */
+#define MISC_REG_LCPLL_E40_PWRDWN 0xaa74
+/* [RW 1] LCPLL VCO reset. Global register. Active Low Reset on POR reset. */
+#define MISC_REG_LCPLL_E40_RESETB_ANA 0xaa78
+/* [RW 1] LCPLL post-divider reset. Global register. Active Low Reset on POR
+ * reset. */
+#define MISC_REG_LCPLL_E40_RESETB_DIG 0xaa7c
/* [RW 4] Interrupt mask register #0 read/write */
#define MISC_REG_MISC_INT_MASK 0xa388
/* [RW 1] Parity mask register #0 read/write */
* is compared to the value on ctrl_md_devad. Drives output
* misc_xgxs0_phy_addr. Global register. */
#define MISC_REG_WC0_CTRL_PHY_ADDR 0xa9cc
+#define MISC_REG_WC0_RESET 0xac30
/* [RW 2] XMAC Core port mode. Indicates the number of ports on the system
side. This should be less than or equal to phy_port_mode; if some of the
ports are not used. This enables reduction of frequency on the core side.
#define MDIO_CTL_REG_84823_MEDIA_PRIORITY_COPPER 0x0000
#define MDIO_CTL_REG_84823_MEDIA_PRIORITY_FIBER 0x0100
#define MDIO_CTL_REG_84823_MEDIA_FIBER_1G 0x1000
-#define MDIO_CTL_REG_84823_USER_CTRL_REG 0x4005
-#define MDIO_CTL_REG_84823_USER_CTRL_CMS 0x0080
-
-#define MDIO_PMA_REG_84823_CTL_LED_CTL_1 0xa8e3
-#define MDIO_PMA_REG_84823_LED3_STRETCH_EN 0x0080
+#define MDIO_CTL_REG_84823_USER_CTRL_REG 0x4005
+#define MDIO_CTL_REG_84823_USER_CTRL_CMS 0x0080
+#define MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH 0xa82b
+#define MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ 0x2f
+#define MDIO_PMA_REG_84823_CTL_LED_CTL_1 0xa8e3
+#define MDIO_PMA_REG_84833_CTL_LED_CTL_1 0xa8ec
+#define MDIO_PMA_REG_84823_LED3_STRETCH_EN 0x0080
/* BCM84833 only */
#define MDIO_84833_TOP_CFG_XGPHY_STRAP1 0x401a
#define MDIO_84833_TOP_CFG_SCRATCH_REG2 0x4007
#define MDIO_84833_TOP_CFG_SCRATCH_REG3 0x4008
#define MDIO_84833_TOP_CFG_SCRATCH_REG4 0x4009
-#define MDIO_84833_TOP_CFG_DATA3_REG 0x4011
-#define MDIO_84833_TOP_CFG_DATA4_REG 0x4012
+#define MDIO_84833_TOP_CFG_SCRATCH_REG26 0x4037
+#define MDIO_84833_TOP_CFG_SCRATCH_REG27 0x4038
+#define MDIO_84833_TOP_CFG_SCRATCH_REG28 0x4039
+#define MDIO_84833_TOP_CFG_SCRATCH_REG29 0x403a
+#define MDIO_84833_TOP_CFG_SCRATCH_REG30 0x403b
+#define MDIO_84833_TOP_CFG_SCRATCH_REG31 0x403c
+#define MDIO_84833_CMD_HDLR_COMMAND MDIO_84833_TOP_CFG_SCRATCH_REG0
+#define MDIO_84833_CMD_HDLR_STATUS MDIO_84833_TOP_CFG_SCRATCH_REG26
+#define MDIO_84833_CMD_HDLR_DATA1 MDIO_84833_TOP_CFG_SCRATCH_REG27
+#define MDIO_84833_CMD_HDLR_DATA2 MDIO_84833_TOP_CFG_SCRATCH_REG28
+#define MDIO_84833_CMD_HDLR_DATA3 MDIO_84833_TOP_CFG_SCRATCH_REG29
+#define MDIO_84833_CMD_HDLR_DATA4 MDIO_84833_TOP_CFG_SCRATCH_REG30
+#define MDIO_84833_CMD_HDLR_DATA5 MDIO_84833_TOP_CFG_SCRATCH_REG31
/* Mailbox command set used by 84833. */
-#define PHY84833_DIAG_CMD_PAIR_SWAP_CHANGE 0x2
+#define PHY84833_CMD_SET_PAIR_SWAP 0x8001
+#define PHY84833_CMD_GET_EEE_MODE 0x8008
+#define PHY84833_CMD_SET_EEE_MODE 0x8009
/* Mailbox status set used by 84833. */
-#define PHY84833_CMD_RECEIVED 0x0001
-#define PHY84833_CMD_IN_PROGRESS 0x0002
-#define PHY84833_CMD_COMPLETE_PASS 0x0004
-#define PHY84833_CMD_COMPLETE_ERROR 0x0008
-#define PHY84833_CMD_OPEN_FOR_CMDS 0x0010
-#define PHY84833_CMD_SYSTEM_BOOT 0x0020
-#define PHY84833_CMD_NOT_OPEN_FOR_CMDS 0x0040
-#define PHY84833_CMD_CLEAR_COMPLETE 0x0080
-#define PHY84833_CMD_OPEN_OVERRIDE 0xa5a5
-
+#define PHY84833_STATUS_CMD_RECEIVED 0x0001
+#define PHY84833_STATUS_CMD_IN_PROGRESS 0x0002
+#define PHY84833_STATUS_CMD_COMPLETE_PASS 0x0004
+#define PHY84833_STATUS_CMD_COMPLETE_ERROR 0x0008
+#define PHY84833_STATUS_CMD_OPEN_FOR_CMDS 0x0010
+#define PHY84833_STATUS_CMD_SYSTEM_BOOT 0x0020
+#define PHY84833_STATUS_CMD_NOT_OPEN_FOR_CMDS 0x0040
+#define PHY84833_STATUS_CMD_CLEAR_COMPLETE 0x0080
+#define PHY84833_STATUS_CMD_OPEN_OVERRIDE 0xa5a5
-/* 84833 F/W Feature Commands */
-#define PHY84833_DIAG_CMD_GET_EEE_MODE 0x27
-#define PHY84833_DIAG_CMD_SET_EEE_MODE 0x28
/* Warpcore clause 45 addressing */
#define MDIO_WC_DEVAD 0x3
#define MDIO_REG_INTR_MASK 0x1b
#define MDIO_REG_INTR_MASK_LINK_STATUS (0x1 << 1)
#define MDIO_REG_GPHY_SHADOW 0x1c
+#define MDIO_REG_GPHY_SHADOW_LED_SEL1 (0x0d << 10)
#define MDIO_REG_GPHY_SHADOW_LED_SEL2 (0x0e << 10)
#define MDIO_REG_GPHY_SHADOW_WR_ENA (0x1 << 15)
#define MDIO_REG_GPHY_SHADOW_AUTO_DET_MED (0x1e << 10)
#define BNX2X_MAX_EMUL_MULTI 16
+#define MAC_LEADING_ZERO_CNT (ALIGN(ETH_ALEN, sizeof(u32)) - ETH_ALEN)
+
/**** Exe Queue interfaces ****/
/**
return true;
}
+static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
+ int n, u8 *buf)
+{
+ struct bnx2x_vlan_mac_registry_elem *pos;
+ u8 *next = buf;
+ int counter = 0;
+
+ /* traverse list */
+ list_for_each_entry(pos, &o->head, link) {
+ if (counter < n) {
+ /* place leading zeroes in buffer */
+ memset(next, 0, MAC_LEADING_ZERO_CNT);
+
+ /* place mac after leading zeroes*/
+ memcpy(next + MAC_LEADING_ZERO_CNT, pos->u.mac.mac,
+ ETH_ALEN);
+
+ /* calculate address of next element and
+ * advance counter
+ */
+ counter++;
+ next = buf + counter * ALIGN(ETH_ALEN, sizeof(u32));
+
+ DP(BNX2X_MSG_SP, "copied element number %d to address %p element was %pM\n",
+ counter, next, pos->u.mac.mac);
+ }
+ }
+ return counter * ETH_ALEN;
+}
+
/* check_add() callbacks */
static int bnx2x_check_mac_add(struct bnx2x_vlan_mac_obj *o,
union bnx2x_classification_ramrod_data *data)
mac_obj->check_move = bnx2x_check_move;
mac_obj->ramrod_cmd =
RAMROD_CMD_ID_ETH_CLASSIFICATION_RULES;
+ mac_obj->get_n_elements = bnx2x_get_n_elements;
/* Exe Queue */
bnx2x_exe_queue_init(bp,
if (!list_empty(&o->registry.exact_match.macs))
return 0;
- elem = kzalloc(sizeof(*elem)*len, GFP_ATOMIC);
+ elem = kcalloc(len, sizeof(*elem), GFP_ATOMIC);
if (!elem) {
BNX2X_ERR("Failed to allocate registry memory\n");
return -ENOMEM;
rc = drv->init_fw(bp);
if (rc) {
BNX2X_ERR("Error loading firmware\n");
- goto fw_init_err;
+ goto init_err;
}
/* Handle the beginning of COMMON_XXX pases separatelly... */
case FW_MSG_CODE_DRV_LOAD_COMMON_CHIP:
rc = bnx2x_func_init_cmn_chip(bp, drv);
if (rc)
- goto init_hw_err;
+ goto init_err;
break;
case FW_MSG_CODE_DRV_LOAD_COMMON:
rc = bnx2x_func_init_cmn(bp, drv);
if (rc)
- goto init_hw_err;
+ goto init_err;
break;
case FW_MSG_CODE_DRV_LOAD_PORT:
rc = bnx2x_func_init_port(bp, drv);
if (rc)
- goto init_hw_err;
+ goto init_err;
break;
case FW_MSG_CODE_DRV_LOAD_FUNCTION:
rc = bnx2x_func_init_func(bp, drv);
if (rc)
- goto init_hw_err;
+ goto init_err;
break;
default:
rc = -EINVAL;
}
-init_hw_err:
- drv->release_fw(bp);
-
-fw_init_err:
+init_err:
drv->gunzip_end(bp);
/* In case of success, complete the comand immediatelly: no ramrods
/* RAMROD command to be used */
int ramrod_cmd;
+ /* copy first n elements onto preallocated buffer
+ *
+ * @param n number of elements to get
+ * @param buf buffer preallocated by caller into which elements
+ * will be copied. Note elements are 4-byte aligned
+ * so buffer size must be able to accomodate the
+ * aligned elements.
+ *
+ * @return number of copied bytes
+ */
+ int (*get_n_elements)(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
+ int n, u8 *buf);
+
/**
* Checks if ADD-ramrod with the given params may be performed.
*
#endif
}
+static u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp)
+{
+ u16 res = sizeof(struct host_port_stats) >> 2;
+
+ /* if PFC stats are not supported by the MFW, don't DMA them */
+ if (!(bp->flags & BC_SUPPORTS_PFC_STATS))
+ res -= (sizeof(u32)*4) >> 2;
+
+ return res;
+}
+
/*
* Init service functions
*/
DMAE_LEN32_RD_MAX * 4);
dmae->dst_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats) +
DMAE_LEN32_RD_MAX * 4);
- dmae->len = (sizeof(struct host_port_stats) >> 2) - DMAE_LEN32_RD_MAX;
+ dmae->len = bnx2x_get_port_stats_dma_len(bp) - DMAE_LEN32_RD_MAX;
+
dmae->comp_addr_lo = U64_LO(bnx2x_sp_mapping(bp, stats_comp));
dmae->comp_addr_hi = U64_HI(bnx2x_sp_mapping(bp, stats_comp));
dmae->comp_val = DMAE_COMP_VAL;
dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
dmae->dst_addr_lo = bp->port.port_stx >> 2;
dmae->dst_addr_hi = 0;
- dmae->len = sizeof(struct host_port_stats) >> 2;
+ dmae->len = bnx2x_get_port_stats_dma_len(bp);
dmae->comp_addr_lo = dmae_reg_go_c[loader_idx] >> 2;
dmae->comp_addr_hi = 0;
dmae->comp_val = 1;
UPDATE_STAT64(tx_stat_gterr,
tx_stat_dot3statsinternalmactransmiterrors);
UPDATE_STAT64(tx_stat_gtufl, tx_stat_mac_ufl);
+
+ /* collect PFC stats */
+ DIFF_64(diff.hi, new->tx_stat_gtpp_hi,
+ pstats->pfc_frames_tx_hi,
+ diff.lo, new->tx_stat_gtpp_lo,
+ pstats->pfc_frames_tx_lo);
+ pstats->pfc_frames_tx_hi = new->tx_stat_gtpp_hi;
+ pstats->pfc_frames_tx_lo = new->tx_stat_gtpp_lo;
+ ADD_64(pstats->pfc_frames_tx_hi, diff.hi,
+ pstats->pfc_frames_tx_lo, diff.lo);
+
+ DIFF_64(diff.hi, new->rx_stat_grpp_hi,
+ pstats->pfc_frames_rx_hi,
+ diff.lo, new->rx_stat_grpp_lo,
+ pstats->pfc_frames_rx_lo);
+ pstats->pfc_frames_rx_hi = new->rx_stat_grpp_hi;
+ pstats->pfc_frames_rx_lo = new->rx_stat_grpp_lo;
+ ADD_64(pstats->pfc_frames_rx_hi, diff.hi,
+ pstats->pfc_frames_rx_lo, diff.lo);
}
estats->pause_frames_received_hi =
pstats->mac_stx[1].tx_stat_outxoffsent_hi;
estats->pause_frames_sent_lo =
pstats->mac_stx[1].tx_stat_outxoffsent_lo;
+
+ estats->pfc_frames_received_hi =
+ pstats->pfc_frames_rx_hi;
+ estats->pfc_frames_received_lo =
+ pstats->pfc_frames_rx_lo;
+ estats->pfc_frames_sent_hi =
+ pstats->pfc_frames_tx_hi;
+ estats->pfc_frames_sent_lo =
+ pstats->pfc_frames_tx_lo;
}
static void bnx2x_mstat_stats_update(struct bnx2x *bp)
ADD_STAT64(stats_tx.tx_gtxpf, tx_stat_outxoffsent);
ADD_STAT64(stats_tx.tx_gtxpf, tx_stat_flowcontroldone);
+ /* collect pfc stats */
+ ADD_64(pstats->pfc_frames_tx_hi, new->stats_tx.tx_gtxpp_hi,
+ pstats->pfc_frames_tx_lo, new->stats_tx.tx_gtxpp_lo);
+ ADD_64(pstats->pfc_frames_rx_hi, new->stats_rx.rx_grxpp_hi,
+ pstats->pfc_frames_rx_lo, new->stats_rx.rx_grxpp_lo);
ADD_STAT64(stats_tx.tx_gt64, tx_stat_etherstatspkts64octets);
ADD_STAT64(stats_tx.tx_gt127,
pstats->mac_stx[1].tx_stat_outxoffsent_hi;
estats->pause_frames_sent_lo =
pstats->mac_stx[1].tx_stat_outxoffsent_lo;
+
+ estats->pfc_frames_received_hi =
+ pstats->pfc_frames_rx_hi;
+ estats->pfc_frames_received_lo =
+ pstats->pfc_frames_rx_lo;
+ estats->pfc_frames_sent_hi =
+ pstats->pfc_frames_tx_hi;
+ estats->pfc_frames_sent_lo =
+ pstats->pfc_frames_tx_lo;
}
static void bnx2x_emac_stats_update(struct bnx2x *bp)
estats->brb_drop_hi = pstats->brb_drop_hi;
estats->brb_drop_lo = pstats->brb_drop_lo;
- pstats->host_port_stats_start = ++pstats->host_port_stats_end;
+ pstats->host_port_stats_counter++;
if (!BP_NOMCP(bp)) {
u32 nig_timer_max =
dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
dmae->dst_addr_lo = bp->port.port_stx >> 2;
dmae->dst_addr_hi = 0;
- dmae->len = sizeof(struct host_port_stats) >> 2;
+ dmae->len = bnx2x_get_port_stats_dma_len(bp);
if (bp->func_stx) {
dmae->comp_addr_lo = dmae_reg_go_c[loader_idx] >> 2;
dmae->comp_addr_hi = 0;
enum bnx2x_stats_state state;
if (unlikely(bp->panic))
return;
- bnx2x_stats_stm[bp->stats_state][event].action(bp);
+
spin_lock_bh(&bp->stats_lock);
state = bp->stats_state;
bp->stats_state = bnx2x_stats_stm[state][event].next_state;
spin_unlock_bh(&bp->stats_lock);
+ bnx2x_stats_stm[state][event].action(bp);
+
if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
state, event, bp->stats_state);
dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
dmae->dst_addr_lo = bp->port.port_stx >> 2;
dmae->dst_addr_hi = 0;
- dmae->len = sizeof(struct host_port_stats) >> 2;
+ dmae->len = bnx2x_get_port_stats_dma_len(bp);
dmae->comp_addr_lo = U64_LO(bnx2x_sp_mapping(bp, stats_comp));
dmae->comp_addr_hi = U64_HI(bnx2x_sp_mapping(bp, stats_comp));
dmae->comp_val = DMAE_COMP_VAL;
static inline void bnx2x_prep_fw_stats_req(struct bnx2x *bp)
{
int i;
+ int first_queue_query_index;
struct stats_query_header *stats_hdr = &bp->fw_stats_req->hdr;
dma_addr_t cur_data_offset;
cur_query_entry->address.hi = cpu_to_le32(U64_HI(cur_data_offset));
cur_query_entry->address.lo = cpu_to_le32(U64_LO(cur_data_offset));
+ /**** FCoE FW statistics data ****/
+ if (!NO_FCOE(bp)) {
+ cur_data_offset = bp->fw_stats_data_mapping +
+ offsetof(struct bnx2x_fw_stats_data, fcoe);
+
+ cur_query_entry =
+ &bp->fw_stats_req->query[BNX2X_FCOE_QUERY_IDX];
+
+ cur_query_entry->kind = STATS_TYPE_FCOE;
+ /* For FCoE query index is a DONT CARE */
+ cur_query_entry->index = BP_PORT(bp);
+ cur_query_entry->funcID = cpu_to_le16(BP_FUNC(bp));
+ cur_query_entry->address.hi =
+ cpu_to_le32(U64_HI(cur_data_offset));
+ cur_query_entry->address.lo =
+ cpu_to_le32(U64_LO(cur_data_offset));
+ }
+
/**** Clients' queries ****/
cur_data_offset = bp->fw_stats_data_mapping +
offsetof(struct bnx2x_fw_stats_data, queue_stats);
+ /* first queue query index depends whether FCoE offloaded request will
+ * be included in the ramrod
+ */
+ if (!NO_FCOE(bp))
+ first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX;
+ else
+ first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX - 1;
+
for_each_eth_queue(bp, i) {
cur_query_entry =
&bp->fw_stats_req->
- query[BNX2X_FIRST_QUEUE_QUERY_IDX + i];
+ query[first_queue_query_index + i];
cur_query_entry->kind = STATS_TYPE_QUEUE;
cur_query_entry->index = bnx2x_stats_id(&bp->fp[i]);
cur_data_offset += sizeof(struct per_queue_stats);
}
+
+ /* add FCoE queue query if needed */
+ if (!NO_FCOE(bp)) {
+ cur_query_entry =
+ &bp->fw_stats_req->
+ query[first_queue_query_index + i];
+
+ cur_query_entry->kind = STATS_TYPE_QUEUE;
+ cur_query_entry->index = bnx2x_stats_id(&bp->fp[FCOE_IDX]);
+ cur_query_entry->funcID = cpu_to_le16(BP_FUNC(bp));
+ cur_query_entry->address.hi =
+ cpu_to_le32(U64_HI(cur_data_offset));
+ cur_query_entry->address.lo =
+ cpu_to_le32(U64_LO(cur_data_offset));
+ }
}
void bnx2x_stats_init(struct bnx2x *bp)
u32 total_tpa_aggregated_frames_lo;
u32 total_tpa_bytes_hi;
u32 total_tpa_bytes_lo;
+
+ /* PFC */
+ u32 pfc_frames_received_hi;
+ u32 pfc_frames_received_lo;
+ u32 pfc_frames_sent_hi;
+ u32 pfc_frames_sent_lo;
};
return io->data;
}
+static void cnic_ulp_ctl(struct cnic_dev *dev, int ulp_type, bool reg)
+{
+ struct cnic_local *cp = dev->cnic_priv;
+ struct cnic_eth_dev *ethdev = cp->ethdev;
+ struct drv_ctl_info info;
+
+ if (reg)
+ info.cmd = DRV_CTL_ULP_REGISTER_CMD;
+ else
+ info.cmd = DRV_CTL_ULP_UNREGISTER_CMD;
+
+ info.data.ulp_type = ulp_type;
+ ethdev->drv_ctl(dev->netdev, &info);
+}
+
static int cnic_in_use(struct cnic_sock *csk)
{
return test_bit(SK_F_INUSE, &csk->flags);
}
read_unlock(&cnic_dev_lock);
- rcu_assign_pointer(cnic_ulp_tbl[ulp_type], NULL);
+ RCU_INIT_POINTER(cnic_ulp_tbl[ulp_type], NULL);
mutex_unlock(&cnic_lock);
synchronize_rcu();
mutex_unlock(&cnic_lock);
+ cnic_ulp_ctl(dev, ulp_type, true);
+
return 0;
}
}
mutex_lock(&cnic_lock);
if (rcu_dereference(cp->ulp_ops[ulp_type])) {
- rcu_assign_pointer(cp->ulp_ops[ulp_type], NULL);
+ RCU_INIT_POINTER(cp->ulp_ops[ulp_type], NULL);
cnic_put(dev);
} else {
pr_err("%s: device not registered to this ulp type %d\n",
if (test_bit(ULP_F_CALL_PENDING, &cp->ulp_flags[ulp_type]))
netdev_warn(dev->netdev, "Failed waiting for ULP up call to complete\n");
+ cnic_ulp_ctl(dev, ulp_type, false);
+
return 0;
}
EXPORT_SYMBOL(cnic_unregister_driver);
}
}
+static int cnic_copy_ulp_stats(struct cnic_dev *dev, int ulp_type)
+{
+ struct cnic_local *cp = dev->cnic_priv;
+ struct cnic_ulp_ops *ulp_ops;
+ int rc;
+
+ mutex_lock(&cnic_lock);
+ ulp_ops = cnic_ulp_tbl_prot(ulp_type);
+ if (ulp_ops && ulp_ops->cnic_get_stats)
+ rc = ulp_ops->cnic_get_stats(cp->ulp_handle[ulp_type]);
+ else
+ rc = -ENODEV;
+ mutex_unlock(&cnic_lock);
+ return rc;
+}
+
static int cnic_ctl(void *data, struct cnic_ctl_info *info)
{
struct cnic_dev *dev = data;
+ int ulp_type = CNIC_ULP_ISCSI;
switch (info->cmd) {
case CNIC_CTL_STOP_CMD:
}
break;
}
+ case CNIC_CTL_FCOE_STATS_GET_CMD:
+ ulp_type = CNIC_ULP_FCOE;
+ /* fall through */
+ case CNIC_CTL_ISCSI_STATS_GET_CMD:
+ cnic_hold(dev);
+ cnic_copy_ulp_stats(dev, ulp_type);
+ cnic_put(dev);
+ break;
+
default:
return -EINVAL;
}
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
- ipv6_addr_copy(&fl6.daddr, &dst_addr->sin6_addr);
+ fl6.daddr = dst_addr->sin6_addr;
if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
fl6.flowi6_oif = dst_addr->sin6_scope_id;
}
cnic_shutdown_rings(dev);
clear_bit(CNIC_F_CNIC_UP, &dev->flags);
- rcu_assign_pointer(cp->ulp_ops[CNIC_ULP_L4], NULL);
+ RCU_INIT_POINTER(cp->ulp_ops[CNIC_ULP_L4], NULL);
synchronize_rcu();
cnic_cm_shutdown(dev);
cp->stop_hw(dev);
cdev->pcidev = pdev;
cp->chip_id = ethdev->chip_id;
+ cdev->stats_addr = ethdev->addr_drv_info_to_mcp;
+
if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI))
cdev->max_iscsi_conn = ethdev->max_iscsi_conn;
if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) &&
#define CNIC_CTL_START_CMD 2
#define CNIC_CTL_COMPLETION_CMD 3
#define CNIC_CTL_STOP_ISCSI_CMD 4
+#define CNIC_CTL_FCOE_STATS_GET_CMD 5
+#define CNIC_CTL_ISCSI_STATS_GET_CMD 6
#define DRV_CTL_IO_WR_CMD 0x101
#define DRV_CTL_IO_RD_CMD 0x102
#define DRV_CTL_STOP_L2_CMD 0x107
#define DRV_CTL_RET_L2_SPQ_CREDIT_CMD 0x10c
#define DRV_CTL_ISCSI_STOPPED_CMD 0x10d
+#define DRV_CTL_ULP_REGISTER_CMD 0x10e
+#define DRV_CTL_ULP_UNREGISTER_CMD 0x10f
struct cnic_ctl_completion {
u32 cid;
struct drv_ctl_spq_credit credit;
struct drv_ctl_io io;
struct drv_ctl_l2_ring ring;
+ int ulp_type;
char bytes[MAX_DRV_CTL_DATA];
} data;
};
struct kwqe_16 *[], u32);
int (*drv_ctl)(struct net_device *, struct drv_ctl_info *);
unsigned long reserved1[2];
+ union drv_info_to_mcp *addr_drv_info_to_mcp;
};
struct cnic_sockaddr {
int max_fcoe_conn;
int max_rdma_conn;
+ union drv_info_to_mcp *stats_addr;
+
void *cnic_priv;
};
void (*cm_remote_abort)(struct cnic_sock *);
int (*iscsi_nl_send_msg)(void *ulp_ctx, u32 msg_type,
char *data, u16 data_size);
+ int (*cnic_get_stats)(void *ulp_ctx);
struct module *owner;
atomic_t ref_count;
};
#define SBMAC_MAX_TXDESCR 256
#define SBMAC_MAX_RXDESCR 256
-#define ETHER_ADDR_LEN 6
#define ENET_PACKET_SIZE 1518
/*#define ENET_PACKET_SIZE 9216 */
int sbm_pause; /* current pause setting */
int sbm_link; /* current link state */
- unsigned char sbm_hwaddr[ETHER_ADDR_LEN];
+ unsigned char sbm_hwaddr[ETH_ALEN];
struct sbmacdma sbm_txdma; /* only channel 0 for now */
struct sbmacdma sbm_rxdma;
},
};
-static int __init sbmac_init_module(void)
-{
- return platform_driver_register(&sbmac_driver);
-}
-
-static void __exit sbmac_cleanup_module(void)
-{
- platform_driver_unregister(&sbmac_driver);
-}
-
-module_init(sbmac_init_module);
-module_exit(sbmac_cleanup_module);
+module_platform_driver(sbmac_driver);
#define DRV_MODULE_NAME "tg3"
#define TG3_MAJ_NUM 3
-#define TG3_MIN_NUM 121
+#define TG3_MIN_NUM 122
#define DRV_MODULE_VERSION \
__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE "November 2, 2011"
+#define DRV_MODULE_RELDATE "December 7, 2011"
#define RESET_KIND_SHUTDOWN 0
#define RESET_KIND_INIT 1
(tg3_flag(tp, LRG_PROD_RING_CAP) ? \
TG3_RX_JMB_MAX_SIZE_5717 : TG3_RX_JMB_MAX_SIZE_5700)
#define TG3_DEF_RX_JUMBO_RING_PENDING 100
-#define TG3_RSS_INDIR_TBL_SIZE 128
/* Do not place this n-ring entries value into the tp struct itself,
* we really want to expose these constants to GCC so that modulo et
#if (NET_IP_ALIGN != 0)
#define TG3_RX_OFFSET(tp) ((tp)->rx_offset)
#else
-#define TG3_RX_OFFSET(tp) 0
+#define TG3_RX_OFFSET(tp) (NET_SKB_PAD)
#endif
/* minimum number of free TX descriptors required to wake up TX process */
#define TG3_TX_WAKEUP_THRESH(tnapi) ((tnapi)->tx_pending / 4)
-#define TG3_TX_BD_DMA_MAX 4096
+#define TG3_TX_BD_DMA_MAX_2K 2048
+#define TG3_TX_BD_DMA_MAX_4K 4096
#define TG3_RAW_IP_ALIGN 2
}
}
-static u16 tg3_advert_flowctrl_1000T(u8 flow_ctrl)
-{
- u16 miireg;
-
- if ((flow_ctrl & FLOW_CTRL_TX) && (flow_ctrl & FLOW_CTRL_RX))
- miireg = ADVERTISE_PAUSE_CAP;
- else if (flow_ctrl & FLOW_CTRL_TX)
- miireg = ADVERTISE_PAUSE_ASYM;
- else if (flow_ctrl & FLOW_CTRL_RX)
- miireg = ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
- else
- miireg = 0;
-
- return miireg;
-}
-
static u16 tg3_advert_flowctrl_1000X(u8 flow_ctrl)
{
u16 miireg;
{
u8 cap = 0;
- if (lcladv & ADVERTISE_1000XPAUSE) {
- if (lcladv & ADVERTISE_1000XPSE_ASYM) {
- if (rmtadv & LPA_1000XPAUSE)
- cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
- else if (rmtadv & LPA_1000XPAUSE_ASYM)
- cap = FLOW_CTRL_RX;
- } else {
- if (rmtadv & LPA_1000XPAUSE)
- cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
- }
- } else if (lcladv & ADVERTISE_1000XPSE_ASYM) {
- if ((rmtadv & LPA_1000XPAUSE) && (rmtadv & LPA_1000XPAUSE_ASYM))
+ if (lcladv & rmtadv & ADVERTISE_1000XPAUSE) {
+ cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
+ } else if (lcladv & rmtadv & ADVERTISE_1000XPSE_ASYM) {
+ if (lcladv & ADVERTISE_1000XPAUSE)
+ cap = FLOW_CTRL_RX;
+ if (rmtadv & ADVERTISE_1000XPAUSE)
cap = FLOW_CTRL_TX;
}
if (phydev->duplex == DUPLEX_HALF)
mac_mode |= MAC_MODE_HALF_DUPLEX;
else {
- lcl_adv = tg3_advert_flowctrl_1000T(
+ lcl_adv = mii_advertise_flowctrl(
tp->link_config.flowctrl);
if (phydev->pause)
if (tp->link_config.active_speed == SPEED_1000 &&
(GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) &&
+ tg3_flag(tp, 57765_CLASS)) &&
!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
val = MII_TG3_DSP_TAP26_ALNOKO |
MII_TG3_DSP_TAP26_RMRXSTO;
bool need_vaux = false;
/* The GPIOs do something completely different on 57765. */
- if (!tg3_flag(tp, IS_NIC) ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ if (!tg3_flag(tp, IS_NIC) || tg3_flag(tp, 57765_CLASS))
return;
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
u32 val, new_adv;
new_adv = ADVERTISE_CSMA;
- if (advertise & ADVERTISED_10baseT_Half)
- new_adv |= ADVERTISE_10HALF;
- if (advertise & ADVERTISED_10baseT_Full)
- new_adv |= ADVERTISE_10FULL;
- if (advertise & ADVERTISED_100baseT_Half)
- new_adv |= ADVERTISE_100HALF;
- if (advertise & ADVERTISED_100baseT_Full)
- new_adv |= ADVERTISE_100FULL;
-
- new_adv |= tg3_advert_flowctrl_1000T(flowctrl);
+ new_adv |= ethtool_adv_to_mii_adv_t(advertise) & ADVERTISE_ALL;
+ new_adv |= mii_advertise_flowctrl(flowctrl);
err = tg3_writephy(tp, MII_ADVERTISE, new_adv);
if (err)
goto done;
- if (tp->phy_flags & TG3_PHYFLG_10_100_ONLY)
- goto done;
-
- new_adv = 0;
- if (advertise & ADVERTISED_1000baseT_Half)
- new_adv |= ADVERTISE_1000HALF;
- if (advertise & ADVERTISED_1000baseT_Full)
- new_adv |= ADVERTISE_1000FULL;
+ if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
+ new_adv = ethtool_adv_to_mii_ctrl1000_t(advertise);
- if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0 ||
- tp->pci_chip_rev_id == CHIPREV_ID_5701_B0)
- new_adv |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER;
+ if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0 ||
+ tp->pci_chip_rev_id == CHIPREV_ID_5701_B0)
+ new_adv |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER;
- err = tg3_writephy(tp, MII_CTRL1000, new_adv);
- if (err)
- goto done;
+ err = tg3_writephy(tp, MII_CTRL1000, new_adv);
+ if (err)
+ goto done;
+ }
if (!(tp->phy_flags & TG3_PHYFLG_EEE_CAP))
goto done;
switch (GET_ASIC_REV(tp->pci_chip_rev_id)) {
case ASIC_REV_5717:
case ASIC_REV_57765:
+ case ASIC_REV_57766:
case ASIC_REV_5719:
/* If we advertised any eee advertisements above... */
if (val)
return err;
}
-static int tg3_copper_is_advertising_all(struct tg3 *tp, u32 mask)
+static bool tg3_phy_copper_an_config_ok(struct tg3 *tp, u32 *lcladv)
{
- u32 adv_reg, all_mask = 0;
+ u32 advmsk, tgtadv, advertising;
- if (mask & ADVERTISED_10baseT_Half)
- all_mask |= ADVERTISE_10HALF;
- if (mask & ADVERTISED_10baseT_Full)
- all_mask |= ADVERTISE_10FULL;
- if (mask & ADVERTISED_100baseT_Half)
- all_mask |= ADVERTISE_100HALF;
- if (mask & ADVERTISED_100baseT_Full)
- all_mask |= ADVERTISE_100FULL;
+ advertising = tp->link_config.advertising;
+ tgtadv = ethtool_adv_to_mii_adv_t(advertising) & ADVERTISE_ALL;
- if (tg3_readphy(tp, MII_ADVERTISE, &adv_reg))
- return 0;
+ advmsk = ADVERTISE_ALL;
+ if (tp->link_config.active_duplex == DUPLEX_FULL) {
+ tgtadv |= mii_advertise_flowctrl(tp->link_config.flowctrl);
+ advmsk |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
+ }
- if ((adv_reg & ADVERTISE_ALL) != all_mask)
- return 0;
+ if (tg3_readphy(tp, MII_ADVERTISE, lcladv))
+ return false;
+
+ if ((*lcladv & advmsk) != tgtadv)
+ return false;
if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
u32 tg3_ctrl;
- all_mask = 0;
- if (mask & ADVERTISED_1000baseT_Half)
- all_mask |= ADVERTISE_1000HALF;
- if (mask & ADVERTISED_1000baseT_Full)
- all_mask |= ADVERTISE_1000FULL;
+ tgtadv = ethtool_adv_to_mii_ctrl1000_t(advertising);
if (tg3_readphy(tp, MII_CTRL1000, &tg3_ctrl))
- return 0;
+ return false;
tg3_ctrl &= (ADVERTISE_1000HALF | ADVERTISE_1000FULL);
- if (tg3_ctrl != all_mask)
- return 0;
+ if (tg3_ctrl != tgtadv)
+ return false;
}
- return 1;
+ return true;
}
-static int tg3_adv_1000T_flowctrl_ok(struct tg3 *tp, u32 *lcladv, u32 *rmtadv)
+static bool tg3_phy_copper_fetch_rmtadv(struct tg3 *tp, u32 *rmtadv)
{
- u32 curadv, reqadv;
+ u32 lpeth = 0;
- if (tg3_readphy(tp, MII_ADVERTISE, lcladv))
- return 1;
-
- curadv = *lcladv & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM);
- reqadv = tg3_advert_flowctrl_1000T(tp->link_config.flowctrl);
+ if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
+ u32 val;
- if (tp->link_config.active_duplex == DUPLEX_FULL) {
- if (curadv != reqadv)
- return 0;
+ if (tg3_readphy(tp, MII_STAT1000, &val))
+ return false;
- if (tg3_flag(tp, PAUSE_AUTONEG))
- tg3_readphy(tp, MII_LPA, rmtadv);
- } else {
- /* Reprogram the advertisement register, even if it
- * does not affect the current link. If the link
- * gets renegotiated in the future, we can save an
- * additional renegotiation cycle by advertising
- * it correctly in the first place.
- */
- if (curadv != reqadv) {
- *lcladv &= ~(ADVERTISE_PAUSE_CAP |
- ADVERTISE_PAUSE_ASYM);
- tg3_writephy(tp, MII_ADVERTISE, *lcladv | reqadv);
- }
+ lpeth = mii_stat1000_to_ethtool_lpa_t(val);
}
- return 1;
+ if (tg3_readphy(tp, MII_LPA, rmtadv))
+ return false;
+
+ lpeth |= mii_lpa_to_ethtool_lpa_t(*rmtadv);
+ tp->link_config.rmt_adv = lpeth;
+
+ return true;
}
static int tg3_setup_copper_phy(struct tg3 *tp, int force_reset)
current_link_up = 0;
current_speed = SPEED_INVALID;
current_duplex = DUPLEX_INVALID;
+ tp->phy_flags &= ~TG3_PHYFLG_MDIX_STATE;
+ tp->link_config.rmt_adv = 0;
if (tp->phy_flags & TG3_PHYFLG_CAPACITIVE_COUPLING) {
err = tg3_phy_auxctl_read(tp,
if (tp->link_config.autoneg == AUTONEG_ENABLE) {
if ((bmcr & BMCR_ANENABLE) &&
- tg3_copper_is_advertising_all(tp,
- tp->link_config.advertising)) {
- if (tg3_adv_1000T_flowctrl_ok(tp, &lcl_adv,
- &rmt_adv))
- current_link_up = 1;
- }
+ tg3_phy_copper_an_config_ok(tp, &lcl_adv) &&
+ tg3_phy_copper_fetch_rmtadv(tp, &rmt_adv))
+ current_link_up = 1;
} else {
if (!(bmcr & BMCR_ANENABLE) &&
tp->link_config.speed == current_speed &&
}
if (current_link_up == 1 &&
- tp->link_config.active_duplex == DUPLEX_FULL)
+ tp->link_config.active_duplex == DUPLEX_FULL) {
+ u32 reg, bit;
+
+ if (tp->phy_flags & TG3_PHYFLG_IS_FET) {
+ reg = MII_TG3_FET_GEN_STAT;
+ bit = MII_TG3_FET_GEN_STAT_MDIXSTAT;
+ } else {
+ reg = MII_TG3_EXT_STAT;
+ bit = MII_TG3_EXT_STAT_MDIX;
+ }
+
+ if (!tg3_readphy(tp, reg, &val) && (val & bit))
+ tp->phy_flags |= TG3_PHYFLG_MDIX_STATE;
+
tg3_setup_flow_control(tp, lcl_adv, rmt_adv);
+ }
}
relink:
if (sg_dig_status & SG_DIG_PARTNER_ASYM_PAUSE)
remote_adv |= LPA_1000XPAUSE_ASYM;
+ tp->link_config.rmt_adv =
+ mii_adv_to_ethtool_adv_x(remote_adv);
+
tg3_setup_flow_control(tp, local_adv, remote_adv);
current_link_up = 1;
tp->serdes_counter = 0;
if (rxflags & MR_LP_ADV_ASYM_PAUSE)
remote_adv |= LPA_1000XPAUSE_ASYM;
+ tp->link_config.rmt_adv =
+ mii_adv_to_ethtool_adv_x(remote_adv);
+
tg3_setup_flow_control(tp, local_adv, remote_adv);
current_link_up = 1;
udelay(40);
current_link_up = 0;
+ tp->link_config.rmt_adv = 0;
mac_status = tr32(MAC_STATUS);
if (tg3_flag(tp, HW_AUTONEG))
current_link_up = 0;
current_speed = SPEED_INVALID;
current_duplex = DUPLEX_INVALID;
+ tp->link_config.rmt_adv = 0;
err |= tg3_readphy(tp, MII_BMSR, &bmsr);
err |= tg3_readphy(tp, MII_BMSR, &bmsr);
(tp->phy_flags & TG3_PHYFLG_PARALLEL_DETECT)) {
/* do nothing, just check for link up at the end */
} else if (tp->link_config.autoneg == AUTONEG_ENABLE) {
- u32 adv, new_adv;
+ u32 adv, newadv;
err |= tg3_readphy(tp, MII_ADVERTISE, &adv);
- new_adv = adv & ~(ADVERTISE_1000XFULL | ADVERTISE_1000XHALF |
- ADVERTISE_1000XPAUSE |
- ADVERTISE_1000XPSE_ASYM |
- ADVERTISE_SLCT);
+ newadv = adv & ~(ADVERTISE_1000XFULL | ADVERTISE_1000XHALF |
+ ADVERTISE_1000XPAUSE |
+ ADVERTISE_1000XPSE_ASYM |
+ ADVERTISE_SLCT);
- new_adv |= tg3_advert_flowctrl_1000X(tp->link_config.flowctrl);
+ newadv |= tg3_advert_flowctrl_1000X(tp->link_config.flowctrl);
+ newadv |= ethtool_adv_to_mii_adv_x(tp->link_config.advertising);
- if (tp->link_config.advertising & ADVERTISED_1000baseT_Half)
- new_adv |= ADVERTISE_1000XHALF;
- if (tp->link_config.advertising & ADVERTISED_1000baseT_Full)
- new_adv |= ADVERTISE_1000XFULL;
-
- if ((new_adv != adv) || !(bmcr & BMCR_ANENABLE)) {
- tg3_writephy(tp, MII_ADVERTISE, new_adv);
+ if ((newadv != adv) || !(bmcr & BMCR_ANENABLE)) {
+ tg3_writephy(tp, MII_ADVERTISE, newadv);
bmcr |= BMCR_ANENABLE | BMCR_ANRESTART;
tg3_writephy(tp, MII_BMCR, bmcr);
current_duplex = DUPLEX_FULL;
else
current_duplex = DUPLEX_HALF;
+
+ tp->link_config.rmt_adv =
+ mii_adv_to_ethtool_adv_x(remote_adv);
} else if (!tg3_flag(tp, 5780_CLASS)) {
/* Link is up via parallel detect */
} else {
u32 sw_idx = tnapi->tx_cons;
struct netdev_queue *txq;
int index = tnapi - tp->napi;
+ unsigned int pkts_compl = 0, bytes_compl = 0;
if (tg3_flag(tp, ENABLE_TSS))
index--;
sw_idx = NEXT_TX(sw_idx);
}
+ pkts_compl++;
+ bytes_compl += skb->len;
+
dev_kfree_skb(skb);
if (unlikely(tx_bug)) {
}
}
+ netdev_completed_queue(tp->dev, pkts_compl, bytes_compl);
+
tnapi->tx_cons = sw_idx;
/* Need to make the tx_cons update visible to tg3_start_xmit()
}
}
-static void tg3_rx_skb_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
+static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
{
- if (!ri->skb)
+ if (!ri->data)
return;
pci_unmap_single(tp->pdev, dma_unmap_addr(ri, mapping),
map_sz, PCI_DMA_FROMDEVICE);
- dev_kfree_skb_any(ri->skb);
- ri->skb = NULL;
+ kfree(ri->data);
+ ri->data = NULL;
}
/* Returns size of skb allocated or < 0 on error.
* buffers the cpu only reads the last cacheline of the RX descriptor
* (to fetch the error flags, vlan tag, checksum, and opaque cookie).
*/
-static int tg3_alloc_rx_skb(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
+static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
u32 opaque_key, u32 dest_idx_unmasked)
{
struct tg3_rx_buffer_desc *desc;
struct ring_info *map;
- struct sk_buff *skb;
+ u8 *data;
dma_addr_t mapping;
- int skb_size, dest_idx;
+ int skb_size, data_size, dest_idx;
switch (opaque_key) {
case RXD_OPAQUE_RING_STD:
dest_idx = dest_idx_unmasked & tp->rx_std_ring_mask;
desc = &tpr->rx_std[dest_idx];
map = &tpr->rx_std_buffers[dest_idx];
- skb_size = tp->rx_pkt_map_sz;
+ data_size = tp->rx_pkt_map_sz;
break;
case RXD_OPAQUE_RING_JUMBO:
dest_idx = dest_idx_unmasked & tp->rx_jmb_ring_mask;
desc = &tpr->rx_jmb[dest_idx].std;
map = &tpr->rx_jmb_buffers[dest_idx];
- skb_size = TG3_RX_JMB_MAP_SZ;
+ data_size = TG3_RX_JMB_MAP_SZ;
break;
default:
* Callers depend upon this behavior and assume that
* we leave everything unchanged if we fail.
*/
- skb = netdev_alloc_skb(tp->dev, skb_size + TG3_RX_OFFSET(tp));
- if (skb == NULL)
+ skb_size = SKB_DATA_ALIGN(data_size + TG3_RX_OFFSET(tp)) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ data = kmalloc(skb_size, GFP_ATOMIC);
+ if (!data)
return -ENOMEM;
- skb_reserve(skb, TG3_RX_OFFSET(tp));
-
- mapping = pci_map_single(tp->pdev, skb->data, skb_size,
+ mapping = pci_map_single(tp->pdev,
+ data + TG3_RX_OFFSET(tp),
+ data_size,
PCI_DMA_FROMDEVICE);
if (pci_dma_mapping_error(tp->pdev, mapping)) {
- dev_kfree_skb(skb);
+ kfree(data);
return -EIO;
}
- map->skb = skb;
+ map->data = data;
dma_unmap_addr_set(map, mapping, mapping);
desc->addr_hi = ((u64)mapping >> 32);
desc->addr_lo = ((u64)mapping & 0xffffffff);
- return skb_size;
+ return data_size;
}
/* We only need to move over in the address because the other
* members of the RX descriptor are invariant. See notes above
- * tg3_alloc_rx_skb for full details.
+ * tg3_alloc_rx_data for full details.
*/
static void tg3_recycle_rx(struct tg3_napi *tnapi,
struct tg3_rx_prodring_set *dpr,
return;
}
- dest_map->skb = src_map->skb;
+ dest_map->data = src_map->data;
dma_unmap_addr_set(dest_map, mapping,
dma_unmap_addr(src_map, mapping));
dest_desc->addr_hi = src_desc->addr_hi;
*/
smp_wmb();
- src_map->skb = NULL;
+ src_map->data = NULL;
}
/* The RX ring scheme is composed of multiple rings which post fresh
struct sk_buff *skb;
dma_addr_t dma_addr;
u32 opaque_key, desc_idx, *post_ptr;
+ u8 *data;
desc_idx = desc->opaque & RXD_OPAQUE_INDEX_MASK;
opaque_key = desc->opaque & RXD_OPAQUE_RING_MASK;
if (opaque_key == RXD_OPAQUE_RING_STD) {
ri = &tp->napi[0].prodring.rx_std_buffers[desc_idx];
dma_addr = dma_unmap_addr(ri, mapping);
- skb = ri->skb;
+ data = ri->data;
post_ptr = &std_prod_idx;
rx_std_posted++;
} else if (opaque_key == RXD_OPAQUE_RING_JUMBO) {
ri = &tp->napi[0].prodring.rx_jmb_buffers[desc_idx];
dma_addr = dma_unmap_addr(ri, mapping);
- skb = ri->skb;
+ data = ri->data;
post_ptr = &jmb_prod_idx;
} else
goto next_pkt_nopost;
goto next_pkt;
}
+ prefetch(data + TG3_RX_OFFSET(tp));
len = ((desc->idx_len & RXD_LEN_MASK) >> RXD_LEN_SHIFT) -
ETH_FCS_LEN;
if (len > TG3_RX_COPY_THRESH(tp)) {
int skb_size;
- skb_size = tg3_alloc_rx_skb(tp, tpr, opaque_key,
+ skb_size = tg3_alloc_rx_data(tp, tpr, opaque_key,
*post_ptr);
if (skb_size < 0)
goto drop_it;
pci_unmap_single(tp->pdev, dma_addr, skb_size,
PCI_DMA_FROMDEVICE);
- /* Ensure that the update to the skb happens
+ skb = build_skb(data);
+ if (!skb) {
+ kfree(data);
+ goto drop_it_no_recycle;
+ }
+ skb_reserve(skb, TG3_RX_OFFSET(tp));
+ /* Ensure that the update to the data happens
* after the usage of the old DMA mapping.
*/
smp_wmb();
- ri->skb = NULL;
+ ri->data = NULL;
- skb_put(skb, len);
} else {
- struct sk_buff *copy_skb;
-
tg3_recycle_rx(tnapi, tpr, opaque_key,
desc_idx, *post_ptr);
- copy_skb = netdev_alloc_skb(tp->dev, len +
- TG3_RAW_IP_ALIGN);
- if (copy_skb == NULL)
+ skb = netdev_alloc_skb(tp->dev,
+ len + TG3_RAW_IP_ALIGN);
+ if (skb == NULL)
goto drop_it_no_recycle;
- skb_reserve(copy_skb, TG3_RAW_IP_ALIGN);
- skb_put(copy_skb, len);
+ skb_reserve(skb, TG3_RAW_IP_ALIGN);
pci_dma_sync_single_for_cpu(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
- skb_copy_from_linear_data(skb, copy_skb->data, len);
+ memcpy(skb->data,
+ data + TG3_RX_OFFSET(tp),
+ len);
pci_dma_sync_single_for_device(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
-
- /* We'll reuse the original ring buffer. */
- skb = copy_skb;
}
+ skb_put(skb, len);
if ((tp->dev->features & NETIF_F_RXCSUM) &&
(desc->type_flags & RXD_FLAG_TCPUDP_CSUM) &&
(((desc->ip_tcp_csum & RXD_TCPCSUM_MASK)
di = dpr->rx_std_prod_idx;
for (i = di; i < di + cpycnt; i++) {
- if (dpr->rx_std_buffers[i].skb) {
+ if (dpr->rx_std_buffers[i].data) {
cpycnt = i - di;
err = -ENOSPC;
break;
di = dpr->rx_jmb_prod_idx;
for (i = di; i < di + cpycnt; i++) {
- if (dpr->rx_jmb_buffers[i].skb) {
+ if (dpr->rx_jmb_buffers[i].data) {
cpycnt = i - di;
err = -ENOSPC;
break;
bool hwbug = false;
if (tg3_flag(tp, SHORT_DMA_BUG) && len <= 8)
- hwbug = 1;
+ hwbug = true;
if (tg3_4g_overflow_test(map, len))
- hwbug = 1;
+ hwbug = true;
if (tg3_40bit_overflow_test(tp, map, len))
- hwbug = 1;
+ hwbug = true;
- if (tg3_flag(tp, 4K_FIFO_LIMIT)) {
+ if (tp->dma_limit) {
u32 prvidx = *entry;
u32 tmp_flag = flags & ~TXD_FLAG_END;
- while (len > TG3_TX_BD_DMA_MAX && *budget) {
- u32 frag_len = TG3_TX_BD_DMA_MAX;
- len -= TG3_TX_BD_DMA_MAX;
+ while (len > tp->dma_limit && *budget) {
+ u32 frag_len = tp->dma_limit;
+ len -= tp->dma_limit;
/* Avoid the 8byte DMA problem */
if (len <= 8) {
- len += TG3_TX_BD_DMA_MAX / 2;
- frag_len = TG3_TX_BD_DMA_MAX / 2;
+ len += tp->dma_limit / 2;
+ frag_len = tp->dma_limit / 2;
}
tnapi->tx_buffers[*entry].fragmented = true;
*budget -= 1;
*entry = NEXT_TX(*entry);
} else {
- hwbug = 1;
+ hwbug = true;
tnapi->tx_buffers[prvidx].fragmented = false;
}
}
}
skb_tx_timestamp(skb);
+ netdev_sent_queue(tp->dev, skb->len);
/* Packets are ready, update Tx producer idx local and on card. */
tw32_tx_mbox(tnapi->prodmbox, entry);
return 0;
}
-static void tg3_set_loopback(struct net_device *dev, u32 features)
+static void tg3_set_loopback(struct net_device *dev, netdev_features_t features)
{
struct tg3 *tp = netdev_priv(dev);
}
}
-static u32 tg3_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t tg3_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct tg3 *tp = netdev_priv(dev);
return features;
}
-static int tg3_set_features(struct net_device *dev, u32 features)
+static int tg3_set_features(struct net_device *dev, netdev_features_t features)
{
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if ((changed & NETIF_F_LOOPBACK) && netif_running(dev))
tg3_set_loopback(dev, features);
if (tpr != &tp->napi[0].prodring) {
for (i = tpr->rx_std_cons_idx; i != tpr->rx_std_prod_idx;
i = (i + 1) & tp->rx_std_ring_mask)
- tg3_rx_skb_free(tp, &tpr->rx_std_buffers[i],
+ tg3_rx_data_free(tp, &tpr->rx_std_buffers[i],
tp->rx_pkt_map_sz);
if (tg3_flag(tp, JUMBO_CAPABLE)) {
for (i = tpr->rx_jmb_cons_idx;
i != tpr->rx_jmb_prod_idx;
i = (i + 1) & tp->rx_jmb_ring_mask) {
- tg3_rx_skb_free(tp, &tpr->rx_jmb_buffers[i],
+ tg3_rx_data_free(tp, &tpr->rx_jmb_buffers[i],
TG3_RX_JMB_MAP_SZ);
}
}
}
for (i = 0; i <= tp->rx_std_ring_mask; i++)
- tg3_rx_skb_free(tp, &tpr->rx_std_buffers[i],
+ tg3_rx_data_free(tp, &tpr->rx_std_buffers[i],
tp->rx_pkt_map_sz);
if (tg3_flag(tp, JUMBO_CAPABLE) && !tg3_flag(tp, 5780_CLASS)) {
for (i = 0; i <= tp->rx_jmb_ring_mask; i++)
- tg3_rx_skb_free(tp, &tpr->rx_jmb_buffers[i],
+ tg3_rx_data_free(tp, &tpr->rx_jmb_buffers[i],
TG3_RX_JMB_MAP_SZ);
}
}
/* Now allocate fresh SKBs for each rx ring. */
for (i = 0; i < tp->rx_pending; i++) {
- if (tg3_alloc_rx_skb(tp, tpr, RXD_OPAQUE_RING_STD, i) < 0) {
+ if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_STD, i) < 0) {
netdev_warn(tp->dev,
"Using a smaller RX standard ring. Only "
"%d out of %d buffers were allocated "
}
for (i = 0; i < tp->rx_jumbo_pending; i++) {
- if (tg3_alloc_rx_skb(tp, tpr, RXD_OPAQUE_RING_JUMBO, i) < 0) {
+ if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_JUMBO, i) < 0) {
netdev_warn(tp->dev,
"Using a smaller RX jumbo ring. Only %d "
"out of %d buffers were allocated "
dev_kfree_skb_any(skb);
}
}
+ netdev_reset_queue(tp->dev);
}
/* Initialize tx/rx rings for packet processing.
if (tnapi->hw_status)
memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE);
}
- if (tp->hw_stats)
- memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
return err;
}
pci_write_config_word(tp->pdev, PCI_COMMAND, tp->pci_cmd);
- if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5785) {
- if (tg3_flag(tp, PCI_EXPRESS))
- pcie_set_readrq(tp->pdev, tp->pcie_readrq);
- else {
- pci_write_config_byte(tp->pdev, PCI_CACHE_LINE_SIZE,
- tp->pci_cacheline_sz);
- pci_write_config_byte(tp->pdev, PCI_LATENCY_TIMER,
- tp->pci_lat_timer);
- }
+ if (!tg3_flag(tp, PCI_EXPRESS)) {
+ pci_write_config_byte(tp->pdev, PCI_CACHE_LINE_SIZE,
+ tp->pci_cacheline_sz);
+ pci_write_config_byte(tp->pdev, PCI_LATENCY_TIMER,
+ tp->pci_lat_timer);
}
/* Make sure PCI-X relaxed ordering bit is clear. */
pci_pcie_cap(tp->pdev) + PCI_EXP_DEVCTL,
val16);
- pcie_set_readrq(tp->pdev, tp->pcie_readrq);
-
/* Clear error status */
pci_write_config_word(tp->pdev,
pci_pcie_cap(tp->pdev) + PCI_EXP_DEVSTA,
return 0;
}
+static struct rtnl_link_stats64 *tg3_get_stats64(struct net_device *,
+ struct rtnl_link_stats64 *);
+static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *,
+ struct tg3_ethtool_stats *);
+
/* tp->lock is held. */
static int tg3_halt(struct tg3 *tp, int kind, int silent)
{
tg3_write_sig_legacy(tp, kind);
tg3_write_sig_post_reset(tp, kind);
+ if (tp->hw_stats) {
+ /* Save the stats across chip resets... */
+ tg3_get_stats64(tp->dev, &tp->net_stats_prev),
+ tg3_get_estats(tp, &tp->estats_prev);
+
+ /* And make sure the next sample is new data */
+ memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+ }
+
if (err)
return err;
limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 16;
else if (tg3_flag(tp, 5717_PLUS))
limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 4;
- else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ else if (tg3_flag(tp, 57765_CLASS))
limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 2;
else
limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE;
else if (!tg3_flag(tp, 5705_PLUS))
limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 16;
else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ tg3_flag(tp, 57765_CLASS))
limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 4;
else
limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE;
if (!tg3_flag(tp, 5750_PLUS) ||
tg3_flag(tp, 5780_CLASS) ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5750 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5752)
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5752 ||
+ tg3_flag(tp, 57765_PLUS))
bdcache_maxcnt = TG3_SRAM_RX_STD_BDCACHE_SIZE_5700;
else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787)
if (!tg3_flag(tp, JUMBO_CAPABLE) || tg3_flag(tp, 5780_CLASS))
return;
- if (!tg3_flag(tp, 5705_PLUS))
- bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5700;
- else
- bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5717;
+ bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5700;
host_rep_thresh = max_t(u32, tp->rx_jumbo_pending / 8, 1);
tw32(JMB_REPLENISH_LWM, bdcache_maxcnt);
}
+static void tg3_rss_init_dflt_indir_tbl(struct tg3 *tp)
+{
+ int i;
+
+ for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
+ tp->rss_ind_tbl[i] =
+ ethtool_rxfh_indir_default(i, tp->irq_cnt - 1);
+}
+
+static void tg3_rss_check_indir_tbl(struct tg3 *tp)
+{
+ int i;
+
+ if (!tg3_flag(tp, SUPPORT_MSIX))
+ return;
+
+ if (tp->irq_cnt <= 2) {
+ memset(&tp->rss_ind_tbl[0], 0, sizeof(tp->rss_ind_tbl));
+ return;
+ }
+
+ /* Validate table against current IRQ count */
+ for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++) {
+ if (tp->rss_ind_tbl[i] >= tp->irq_cnt - 1)
+ break;
+ }
+
+ if (i != TG3_RSS_INDIR_TBL_SIZE)
+ tg3_rss_init_dflt_indir_tbl(tp);
+}
+
+static void tg3_rss_write_indir_tbl(struct tg3 *tp)
+{
+ int i = 0;
+ u32 reg = MAC_RSS_INDIR_TBL_0;
+
+ while (i < TG3_RSS_INDIR_TBL_SIZE) {
+ u32 val = tp->rss_ind_tbl[i];
+ i++;
+ for (; i % 8; i++) {
+ val <<= 4;
+ val |= tp->rss_ind_tbl[i];
+ }
+ tw32(reg, val);
+ reg += 4;
+ }
+}
+
/* tp->lock is held. */
static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
{
tw32(GRC_MODE, grc_mode);
}
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) {
+ if (tg3_flag(tp, 57765_CLASS)) {
if (tp->pci_chip_rev_id == CHIPREV_ID_57765_A0) {
u32 grc_mode = tr32(GRC_MODE);
~DMA_RWCTRL_DIS_CACHE_ALIGNMENT;
if (tp->pci_chip_rev_id == CHIPREV_ID_57765_A0)
val &= ~DMA_RWCTRL_CRDRDR_RDMA_MRRS_MSK;
- if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765 &&
+ if (!tg3_flag(tp, 57765_CLASS) &&
GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717)
val |= DMA_RWCTRL_TAGGED_STAT_WA;
tw32(TG3PCI_DMA_RW_CTRL, val | tp->dma_rwctrl);
tw32(RCVDBDI_JUMBO_BD + TG3_BDINFO_MAXLEN_FLAGS,
val | BDINFO_FLAGS_USE_EXT_RECV);
if (!tg3_flag(tp, USE_JUMBO_BDFLAG) ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ tg3_flag(tp, 57765_CLASS))
tw32(RCVDBDI_JUMBO_BD + TG3_BDINFO_NIC_ADDR,
NIC_SRAM_RX_JUMBO_BUFFER_DESC);
} else {
}
if (tg3_flag(tp, 57765_PLUS)) {
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
- val = TG3_RX_STD_MAX_SIZE_5700;
- else
- val = TG3_RX_STD_MAX_SIZE_5717;
+ val = TG3_RX_STD_RING_SIZE(tp);
val <<= BDINFO_FLAGS_MAXLEN_SHIFT;
val |= (TG3_RX_STD_DMA_SZ << 2);
} else
if (tg3_flag(tp, PCI_EXPRESS))
rdmac_mode |= RDMAC_MODE_FIFO_LONG_BURST;
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+ rdmac_mode |= RDMAC_MODE_JMB_2K_MMRR;
+
if (tg3_flag(tp, HW_TSO_1) ||
tg3_flag(tp, HW_TSO_2) ||
tg3_flag(tp, HW_TSO_3))
udelay(100);
if (tg3_flag(tp, ENABLE_RSS)) {
- int i = 0;
- u32 reg = MAC_RSS_INDIR_TBL_0;
-
- if (tp->irq_cnt == 2) {
- for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i += 8) {
- tw32(reg, 0x0);
- reg += 4;
- }
- } else {
- u32 val;
-
- while (i < TG3_RSS_INDIR_TBL_SIZE) {
- val = i % (tp->irq_cnt - 1);
- i++;
- for (; i % 8; i++) {
- val <<= 4;
- val |= (i % (tp->irq_cnt - 1));
- }
- tw32(reg, val);
- reg += 4;
- }
- }
+ tg3_rss_write_indir_tbl(tp);
/* Setup the "secret" hash key. */
tw32(MAC_RSS_HASH_KEY_0, 0x5f865437);
/* Prevent chip from dropping frames when flow control
* is enabled.
*/
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ if (tg3_flag(tp, 57765_CLASS))
val = 1;
else
val = 2;
spin_lock(&tp->lock);
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ tg3_flag(tp, 57765_CLASS))
tg3_chk_missed_msi(tp);
if (!tg3_flag(tp, TAGGED_STATUS)) {
*/
tg3_ints_init(tp);
+ tg3_rss_check_indir_tbl(tp);
+
/* The placement of this call is tied
* to the setup and use of Host TX descriptors.
*/
tg3_free_rings(tp);
} else {
if (tg3_flag(tp, TAGGED_STATUS) &&
- GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 &&
- GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765)
+ GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 &&
+ !tg3_flag(tp, 57765_CLASS))
tp->timer_offset = HZ;
else
tp->timer_offset = HZ / 10;
return err;
}
-static struct rtnl_link_stats64 *tg3_get_stats64(struct net_device *,
- struct rtnl_link_stats64 *);
-static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *);
-
static int tg3_close(struct net_device *dev)
{
int i;
tg3_ints_fini(tp);
- tg3_get_stats64(tp->dev, &tp->net_stats_prev);
-
- memcpy(&tp->estats_prev, tg3_get_estats(tp),
- sizeof(tp->estats_prev));
+ /* Clear stats across close / open calls */
+ memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
+ memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
tg3_napi_fini(tp);
estats->member = old_estats->member + \
get_stat64(&hw_stats->member)
-static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *tp)
+static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *tp,
+ struct tg3_ethtool_stats *estats)
{
- struct tg3_ethtool_stats *estats = &tp->estats;
struct tg3_ethtool_stats *old_estats = &tp->estats_prev;
struct tg3_hw_stats *hw_stats = tp->hw_stats;
cmd->advertising |= ADVERTISED_Asym_Pause;
}
}
- if (netif_running(dev)) {
+ if (netif_running(dev) && netif_carrier_ok(dev)) {
ethtool_cmd_speed_set(cmd, tp->link_config.active_speed);
cmd->duplex = tp->link_config.active_duplex;
+ cmd->lp_advertising = tp->link_config.rmt_adv;
+ if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES)) {
+ if (tp->phy_flags & TG3_PHYFLG_MDIX_STATE)
+ cmd->eth_tp_mdix = ETH_TP_MDI_X;
+ else
+ cmd->eth_tp_mdix = ETH_TP_MDI;
+ }
} else {
ethtool_cmd_speed_set(cmd, SPEED_INVALID);
cmd->duplex = DUPLEX_INVALID;
+ cmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
}
cmd->phy_address = tp->phy_addr;
cmd->transceiver = XCVR_INTERNAL;
{
struct tg3 *tp = netdev_priv(dev);
- strcpy(info->driver, DRV_MODULE_NAME);
- strcpy(info->version, DRV_MODULE_VERSION);
- strcpy(info->fw_version, tp->fw_ver);
- strcpy(info->bus_info, pci_name(tp->pdev));
+ strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+ strlcpy(info->fw_version, tp->fw_ver, sizeof(info->fw_version));
+ strlcpy(info->bus_info, pci_name(tp->pdev), sizeof(info->bus_info));
}
static void tg3_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
epause->autoneg = !!tg3_flag(tp, PAUSE_AUTONEG);
- if (tp->link_config.active_flowctrl & FLOW_CTRL_RX)
+ if (tp->link_config.flowctrl & FLOW_CTRL_RX)
epause->rx_pause = 1;
else
epause->rx_pause = 0;
- if (tp->link_config.active_flowctrl & FLOW_CTRL_TX)
+ if (tp->link_config.flowctrl & FLOW_CTRL_TX)
epause->tx_pause = 1;
else
epause->tx_pause = 0;
}
}
+static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
+ u32 *rules __always_unused)
+{
+ struct tg3 *tp = netdev_priv(dev);
+
+ if (!tg3_flag(tp, SUPPORT_MSIX))
+ return -EOPNOTSUPP;
+
+ switch (info->cmd) {
+ case ETHTOOL_GRXRINGS:
+ if (netif_running(tp->dev))
+ info->data = tp->irq_cnt;
+ else {
+ info->data = num_online_cpus();
+ if (info->data > TG3_IRQ_MAX_VECS_RSS)
+ info->data = TG3_IRQ_MAX_VECS_RSS;
+ }
+
+ /* The first interrupt vector only
+ * handles link interrupts.
+ */
+ info->data -= 1;
+ return 0;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
+{
+ u32 size = 0;
+ struct tg3 *tp = netdev_priv(dev);
+
+ if (tg3_flag(tp, SUPPORT_MSIX))
+ size = TG3_RSS_INDIR_TBL_SIZE;
+
+ return size;
+}
+
+static int tg3_get_rxfh_indir(struct net_device *dev, u32 *indir)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
+ indir[i] = tp->rss_ind_tbl[i];
+
+ return 0;
+}
+
+static int tg3_set_rxfh_indir(struct net_device *dev, const u32 *indir)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ size_t i;
+
+ for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
+ tp->rss_ind_tbl[i] = indir[i];
+
+ if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
+ return 0;
+
+ /* It is legal to write the indirection
+ * table while the device is running.
+ */
+ tg3_full_lock(tp, 0);
+ tg3_rss_write_indir_tbl(tp);
+ tg3_full_unlock(tp);
+
+ return 0;
+}
+
static void tg3_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
{
switch (stringset) {
struct ethtool_stats *estats, u64 *tmp_stats)
{
struct tg3 *tp = netdev_priv(dev);
- memcpy(tmp_stats, tg3_get_estats(tp), sizeof(tp->estats));
+
+ tg3_get_estats(tp, (struct tg3_ethtool_stats *)tmp_stats);
}
static __be32 *tg3_vpd_readblock(struct tg3 *tp, u32 *vpdlen)
if (tg3_flag(tp, 5717_PLUS))
mem_tbl = mem_tbl_5717;
- else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ else if (tg3_flag(tp, 57765_CLASS))
mem_tbl = mem_tbl_57765;
else if (tg3_flag(tp, 5755_PLUS))
mem_tbl = mem_tbl_5755;
u32 rx_start_idx, rx_idx, tx_idx, opaque_key;
u32 base_flags = 0, mss = 0, desc_idx, coal_now, data_off, val;
u32 budget;
- struct sk_buff *skb, *rx_skb;
- u8 *tx_data;
+ struct sk_buff *skb;
+ u8 *tx_data, *rx_data;
dma_addr_t map;
int num_pkts, tx_len, rx_len, i, err;
struct tg3_rx_buffer_desc *desc;
}
if (opaque_key == RXD_OPAQUE_RING_STD) {
- rx_skb = tpr->rx_std_buffers[desc_idx].skb;
+ rx_data = tpr->rx_std_buffers[desc_idx].data;
map = dma_unmap_addr(&tpr->rx_std_buffers[desc_idx],
mapping);
} else if (opaque_key == RXD_OPAQUE_RING_JUMBO) {
- rx_skb = tpr->rx_jmb_buffers[desc_idx].skb;
+ rx_data = tpr->rx_jmb_buffers[desc_idx].data;
map = dma_unmap_addr(&tpr->rx_jmb_buffers[desc_idx],
mapping);
} else
pci_dma_sync_single_for_cpu(tp->pdev, map, rx_len,
PCI_DMA_FROMDEVICE);
+ rx_data += TG3_RX_OFFSET(tp);
for (i = data_off; i < rx_len; i++, val++) {
- if (*(rx_skb->data + i) != (u8) (val & 0xff))
+ if (*(rx_data + i) != (u8) (val & 0xff))
goto out;
}
}
err = 0;
- /* tg3_free_rings will unmap and free the rx_skb */
+ /* tg3_free_rings will unmap and free the rx_data */
out:
return err;
}
.get_coalesce = tg3_get_coalesce,
.set_coalesce = tg3_set_coalesce,
.get_sset_count = tg3_get_sset_count,
+ .get_rxnfc = tg3_get_rxnfc,
+ .get_rxfh_indir_size = tg3_get_rxfh_indir_size,
+ .get_rxfh_indir = tg3_get_rxfh_indir,
+ .set_rxfh_indir = tg3_set_rxfh_indir,
};
static void __devinit tg3_get_eeprom_size(struct tg3 *tp)
else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
tg3_get_5906_nvram_info(tp);
else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ tg3_flag(tp, 57765_CLASS))
tg3_get_57780_nvram_info(tp);
else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719)
static void __devinit tg3_phy_init_link_config(struct tg3 *tp)
{
- u32 adv = ADVERTISED_Autoneg |
- ADVERTISED_Pause;
+ u32 adv = ADVERTISED_Autoneg;
if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY))
adv |= ADVERTISED_1000baseT_Half |
if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES) &&
!tg3_flag(tp, ENABLE_APE) &&
!tg3_flag(tp, ENABLE_ASF)) {
- u32 bmsr, mask;
+ u32 bmsr, dummy;
tg3_readphy(tp, MII_BMSR, &bmsr);
if (!tg3_readphy(tp, MII_BMSR, &bmsr) &&
tg3_phy_set_wirespeed(tp);
- mask = (ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
- ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
- ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full);
- if (!tg3_copper_is_advertising_all(tp, mask)) {
+ if (!tg3_phy_copper_an_config_ok(tp, &dummy)) {
tg3_phy_autoneg_cfg(tp, tp->link_config.advertising,
tp->link_config.flowctrl);
strcpy(tp->board_part_number, "BCM57795");
else
goto nomatch;
+ } else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766) {
+ if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57762)
+ strcpy(tp->board_part_number, "BCM57762");
+ else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57766)
+ strcpy(tp->board_part_number, "BCM57766");
+ else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57782)
+ strcpy(tp->board_part_number, "BCM57782");
+ else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57786)
+ strcpy(tp->board_part_number, "BCM57786");
+ else
+ goto nomatch;
} else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) {
strcpy(tp->board_part_number, "BCM95906");
} else {
tp->pdev->device == TG3PCI_DEVICE_TIGON3_57761 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_57765 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_57791 ||
- tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795)
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57762 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57766 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57782 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57786)
pci_read_config_dword(tp->pdev,
TG3PCI_GEN15_PRODID_ASICREV,
&prod_id_asic_rev);
tg3_flag_set(tp, 5717_PLUS);
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765 ||
- tg3_flag(tp, 5717_PLUS))
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+ tg3_flag_set(tp, 57765_CLASS);
+
+ if (tg3_flag(tp, 57765_CLASS) || tg3_flag(tp, 5717_PLUS))
tg3_flag_set(tp, 57765_PLUS);
/* Intentionally exclude ASIC_REV_5906 */
if (tg3_flag(tp, HW_TSO_1) ||
tg3_flag(tp, HW_TSO_2) ||
tg3_flag(tp, HW_TSO_3) ||
- (tp->fw_needed && !tg3_flag(tp, ENABLE_ASF)))
+ tp->fw_needed) {
+ /* For firmware TSO, assume ASF is disabled.
+ * We'll disable TSO later if we discover ASF
+ * is enabled in tg3_get_eeprom_hw_cfg().
+ */
tg3_flag_set(tp, TSO_CAPABLE);
- else {
+ } else {
tg3_flag_clear(tp, TSO_CAPABLE);
tg3_flag_clear(tp, TSO_BUG);
tp->fw_needed = NULL;
if (tg3_flag(tp, 57765_PLUS)) {
tg3_flag_set(tp, SUPPORT_MSIX);
tp->irq_max = TG3_IRQ_MAX_VECS;
+ tg3_rss_init_dflt_indir_tbl(tp);
}
}
tg3_flag_set(tp, SHORT_DMA_BUG);
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719)
- tg3_flag_set(tp, 4K_FIFO_LIMIT);
+ tp->dma_limit = TG3_TX_BD_DMA_MAX_4K;
+ else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+ tp->dma_limit = TG3_TX_BD_DMA_MAX_2K;
- if (tg3_flag(tp, 5717_PLUS))
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720)
tg3_flag_set(tp, LRG_PROD_RING_CAP);
if (tg3_flag(tp, 57765_PLUS) &&
tg3_flag_set(tp, PCI_EXPRESS);
- tp->pcie_readrq = 4096;
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720)
- tp->pcie_readrq = 2048;
-
- pcie_set_readrq(tp->pdev, tp->pcie_readrq);
+ if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0) {
+ int readrq = pcie_get_readrq(tp->pdev);
+ if (readrq > 2048)
+ pcie_set_readrq(tp->pdev, 2048);
+ }
pci_read_config_word(tp->pdev,
pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL,
*/
tg3_get_eeprom_hw_cfg(tp);
+ if (tp->fw_needed && tg3_flag(tp, ENABLE_ASF)) {
+ tg3_flag_clear(tp, TSO_CAPABLE);
+ tg3_flag_clear(tp, TSO_BUG);
+ tp->fw_needed = NULL;
+ }
+
if (tg3_flag(tp, ENABLE_APE)) {
/* Allow reads and writes to the
* APE register and memory space.
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+ tg3_flag(tp, 57765_CLASS))
tp->grc_local_ctrl |= GRC_LCLCTRL_GPIO_UART_SEL;
if (tp->pdev->device == PCI_DEVICE_ID_TIGON3_5761 ||
else
tg3_flag_clear(tp, POLL_SERDES);
- tp->rx_offset = NET_IP_ALIGN;
+ tp->rx_offset = NET_SKB_PAD + NET_IP_ALIGN;
tp->rx_copy_thresh = TG3_RX_COPY_THRESHOLD;
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5701 &&
tg3_flag(tp, PCIX_MODE)) {
- tp->rx_offset = 0;
+ tp->rx_offset = NET_SKB_PAD;
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
tp->rx_copy_thresh = ~(u16)0;
#endif
u32 sndmbx, rcvmbx, intmbx;
char str[40];
u64 dma_mask, persist_dma_mask;
- u32 features = 0;
+ netdev_features_t features = 0;
printk_once(KERN_INFO "%s\n", version);
#define TG3_RX_RET_MAX_SIZE_5705 512
#define TG3_RX_RET_MAX_SIZE_5717 4096
+#define TG3_RSS_INDIR_TBL_SIZE 128
+
/* First 256 bytes are a mirror of PCI config space. */
#define TG3PCI_VENDOR 0x00000000
#define TG3PCI_VENDOR_BROADCOM 0x14e4
#define TG3PCI_DEVICE_TIGON3_57795 0x16b6
#define TG3PCI_DEVICE_TIGON3_5719 0x1657
#define TG3PCI_DEVICE_TIGON3_5720 0x165f
+#define TG3PCI_DEVICE_TIGON3_57762 0x1682
+#define TG3PCI_DEVICE_TIGON3_57766 0x1686
+#define TG3PCI_DEVICE_TIGON3_57786 0x16b3
+#define TG3PCI_DEVICE_TIGON3_57782 0x16b7
/* 0x04 --> 0x2c unused */
#define TG3PCI_SUBVENDOR_ID_BROADCOM PCI_VENDOR_ID_BROADCOM
#define TG3PCI_SUBDEVICE_ID_BROADCOM_95700A6 0x1644
#define ASIC_REV_57765 0x57785
#define ASIC_REV_5719 0x5719
#define ASIC_REV_5720 0x5720
+#define ASIC_REV_57766 0x57766
#define GET_CHIP_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 8)
#define CHIPREV_5700_AX 0x70
#define CHIPREV_5700_BX 0x71
#define RDMAC_MODE_MBUF_SBD_CRPT_ENAB 0x00002000
#define RDMAC_MODE_FIFO_SIZE_128 0x00020000
#define RDMAC_MODE_FIFO_LONG_BURST 0x00030000
+#define RDMAC_MODE_JMB_2K_MMRR 0x00800000
#define RDMAC_MODE_MULT_DMA_RD_DIS 0x01000000
#define RDMAC_MODE_IPV4_LSO_EN 0x08000000
#define RDMAC_MODE_IPV6_LSO_EN 0x10000000
#define MII_TG3_EXT_CTRL_TBI 0x8000
#define MII_TG3_EXT_STAT 0x11 /* Extended status register */
+#define MII_TG3_EXT_STAT_MDIX 0x2000
#define MII_TG3_EXT_STAT_LPASS 0x0100
#define MII_TG3_RXR_COUNTERS 0x14 /* Local/Remote Receiver Counts */
#define MII_TG3_FET_PTEST_FRC_TX_LINK 0x1000
#define MII_TG3_FET_PTEST_FRC_TX_LOCK 0x0800
+#define MII_TG3_FET_GEN_STAT 0x1c
+#define MII_TG3_FET_GEN_STAT_MDIXSTAT 0x2000
+
#define MII_TG3_FET_TEST 0x1f
#define MII_TG3_FET_SHADOW_EN 0x0080
/* 'mapping' is superfluous as the chip does not write into
* the tx/rx post rings so we could just fetch it from there.
* But the cache behavior is better how we are doing it now.
+ *
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
*/
struct ring_info {
- struct sk_buff *skb;
+ u8 *data;
DEFINE_DMA_UNMAP_ADDR(mapping);
};
#define DUPLEX_INVALID 0xff
#define AUTONEG_INVALID 0xff
u16 active_speed;
+ u32 rmt_adv;
/* When we go in and out of low power mode we need
* to swap with this state.
TG3_FLAG_NVRAM_BUFFERED,
TG3_FLAG_SUPPORT_MSI,
TG3_FLAG_SUPPORT_MSIX,
+ TG3_FLAG_USING_MSI,
+ TG3_FLAG_USING_MSIX,
TG3_FLAG_PCIX_MODE,
TG3_FLAG_PCI_HIGH_SPEED,
TG3_FLAG_PCI_32BIT,
TG3_FLAG_CHIP_RESETTING,
TG3_FLAG_INIT_COMPLETE,
TG3_FLAG_TSO_BUG,
- TG3_FLAG_IS_5788,
TG3_FLAG_MAX_RXPEND_64,
TG3_FLAG_TSO_CAPABLE,
TG3_FLAG_PCI_EXPRESS, /* BCM5785 + pci_is_pcie() */
TG3_FLAG_IS_NIC,
TG3_FLAG_FLASH,
TG3_FLAG_HW_TSO_1,
- TG3_FLAG_5705_PLUS,
- TG3_FLAG_5750_PLUS,
+ TG3_FLAG_HW_TSO_2,
TG3_FLAG_HW_TSO_3,
- TG3_FLAG_USING_MSI,
- TG3_FLAG_USING_MSIX,
TG3_FLAG_ICH_WORKAROUND,
- TG3_FLAG_5780_CLASS,
- TG3_FLAG_HW_TSO_2,
TG3_FLAG_1SHOT_MSI,
TG3_FLAG_NO_FWARE_REPORTED,
TG3_FLAG_NO_NVRAM_ADDR_TRANS,
TG3_FLAG_RGMII_EXT_IBND_RX_EN,
TG3_FLAG_RGMII_EXT_IBND_TX_EN,
TG3_FLAG_CLKREQ_BUG,
- TG3_FLAG_5755_PLUS,
TG3_FLAG_NO_NVRAM,
TG3_FLAG_ENABLE_RSS,
TG3_FLAG_ENABLE_TSS,
TG3_FLAG_SHORT_DMA_BUG,
TG3_FLAG_USE_JUMBO_BDFLAG,
TG3_FLAG_L1PLLPD_EN,
- TG3_FLAG_57765_PLUS,
TG3_FLAG_APE_HAS_NCSI,
- TG3_FLAG_5717_PLUS,
TG3_FLAG_4K_FIFO_LIMIT,
TG3_FLAG_RESET_TASK_PENDING,
+ TG3_FLAG_5705_PLUS,
+ TG3_FLAG_IS_5788,
+ TG3_FLAG_5750_PLUS,
+ TG3_FLAG_5780_CLASS,
+ TG3_FLAG_5755_PLUS,
+ TG3_FLAG_57765_PLUS,
+ TG3_FLAG_57765_CLASS,
+ TG3_FLAG_5717_PLUS,
/* Add new flags before this comment and TG3_FLAG_NUMBER_OF_FLAGS */
TG3_FLAG_NUMBER_OF_FLAGS, /* Last entry in enum TG3_FLAGS */
/* begin "tx thread" cacheline section */
void (*write32_tx_mbox) (struct tg3 *, u32,
u32);
+ u32 dma_limit;
/* begin "rx thread" cacheline section */
struct tg3_napi napi[TG3_IRQ_MAX_VECS];
unsigned long rx_dropped;
unsigned long tx_dropped;
struct rtnl_link_stats64 net_stats_prev;
- struct tg3_ethtool_stats estats;
struct tg3_ethtool_stats estats_prev;
DECLARE_BITMAP(tg3_flags, TG3_FLAG_NUMBER_OF_FLAGS);
#define TG3_PHYFLG_SERDES_PREEMPHASIS 0x00010000
#define TG3_PHYFLG_PARALLEL_DETECT 0x00020000
#define TG3_PHYFLG_EEE_CAP 0x00040000
+#define TG3_PHYFLG_MDIX_STATE 0x00200000
u32 led_ctrl;
u32 phy_otp;
u32 setlpicnt;
+ u8 rss_ind_tbl[TG3_RSS_INDIR_TBL_SIZE];
#define TG3_BPN_SIZE 24
char board_part_number[TG3_BPN_SIZE];
obj-$(CONFIG_BNA) += bna.o
-bna-objs := bnad.o bnad_ethtool.o bna_enet.o bna_tx_rx.o
+bna-objs := bnad.o bnad_ethtool.o bnad_debugfs.o bna_enet.o bna_tx_rx.o
bna-objs += bfa_msgq.o bfa_ioc.o bfa_ioc_ct.o bfa_cee.o
bna-objs += cna_fwimg.o
(dma_kva + bfa_cee_attr_meminfo());
}
+/**
+ * bfa_cee_get_attr()
+ *
+ * @brief Send the request to the f/w to fetch CEE attributes.
+ *
+ * @param[in] Pointer to the CEE module data structure.
+ *
+ * @return Status
+ */
+enum bfa_status
+bfa_nw_cee_get_attr(struct bfa_cee *cee, struct bfa_cee_attr *attr,
+ bfa_cee_get_attr_cbfn_t cbfn, void *cbarg)
+{
+ struct bfi_cee_get_req *cmd;
+
+ BUG_ON(!((cee != NULL) && (cee->ioc != NULL)));
+ if (!bfa_nw_ioc_is_operational(cee->ioc))
+ return BFA_STATUS_IOC_FAILURE;
+
+ if (cee->get_attr_pending == true)
+ return BFA_STATUS_DEVBUSY;
+
+ cee->get_attr_pending = true;
+ cmd = (struct bfi_cee_get_req *) cee->get_cfg_mb.msg;
+ cee->attr = attr;
+ cee->cbfn.get_attr_cbfn = cbfn;
+ cee->cbfn.get_attr_cbarg = cbarg;
+ bfi_h2i_set(cmd->mh, BFI_MC_CEE, BFI_CEE_H2I_GET_CFG_REQ,
+ bfa_ioc_portid(cee->ioc));
+ bfa_dma_be_addr_set(cmd->dma_addr, cee->attr_dma.pa);
+ bfa_nw_ioc_mbox_queue(cee->ioc, &cee->get_cfg_mb, NULL, NULL);
+
+ return BFA_STATUS_OK;
+}
+
/**
* bfa_cee_isrs()
*
void bfa_nw_cee_mem_claim(struct bfa_cee *cee, u8 *dma_kva,
u64 dma_pa);
void bfa_nw_cee_attach(struct bfa_cee *cee, struct bfa_ioc *ioc, void *dev);
-
+enum bfa_status bfa_nw_cee_get_attr(struct bfa_cee *cee,
+ struct bfa_cee_attr *attr,
+ bfa_cee_get_attr_cbfn_t cbfn, void *cbarg);
#endif /* __BFA_CEE_H__ */
* All numerical fields are in big-endian format.
*/
struct bfa_mfg_block {
- u8 version; /*!< manufacturing block version */
- u8 mfg_sig[3]; /*!< characters 'M', 'F', 'G' */
- u16 mfgsize; /*!< mfg block size */
- u16 u16_chksum; /*!< old u16 checksum */
- char brcd_serialnum[STRSZ(BFA_MFG_SERIALNUM_SIZE)];
- char brcd_partnum[STRSZ(BFA_MFG_PARTNUM_SIZE)];
- u8 mfg_day; /*!< manufacturing day */
- u8 mfg_month; /*!< manufacturing month */
- u16 mfg_year; /*!< manufacturing year */
- u64 mfg_wwn; /*!< wwn base for this adapter */
- u8 num_wwn; /*!< number of wwns assigned */
- u8 mfg_speeds; /*!< speeds allowed for this adapter */
- u8 rsv[2];
- char supplier_id[STRSZ(BFA_MFG_SUPPLIER_ID_SIZE)];
- char supplier_partnum[STRSZ(BFA_MFG_SUPPLIER_PARTNUM_SIZE)];
- char
- supplier_serialnum[STRSZ(BFA_MFG_SUPPLIER_SERIALNUM_SIZE)];
- char
- supplier_revision[STRSZ(BFA_MFG_SUPPLIER_REVISION_SIZE)];
- mac_t mfg_mac; /*!< mac address */
- u8 num_mac; /*!< number of mac addresses */
- u8 rsv2;
- u32 card_type; /*!< card type */
- char cap_nic; /*!< capability nic */
- char cap_cna; /*!< capability cna */
- char cap_hba; /*!< capability hba */
- char cap_fc16g; /*!< capability fc 16g */
- char cap_sriov; /*!< capability sriov */
- char cap_mezz; /*!< capability mezz */
- u8 rsv3;
- u8 mfg_nports; /*!< number of ports */
- char media[8]; /*!< xfi/xaui */
- char initial_mode[8];/*!< initial mode: hba/cna/nic */
- u8 rsv4[84];
- u8 md5_chksum[BFA_MFG_CHKSUM_SIZE]; /*!< md5 checksum */
+ u8 version; /* manufacturing block version */
+ u8 mfg_sig[3]; /* characters 'M', 'F', 'G' */
+ u16 mfgsize; /* mfg block size */
+ u16 u16_chksum; /* old u16 checksum */
+ char brcd_serialnum[STRSZ(BFA_MFG_SERIALNUM_SIZE)];
+ char brcd_partnum[STRSZ(BFA_MFG_PARTNUM_SIZE)];
+ u8 mfg_day; /* manufacturing day */
+ u8 mfg_month; /* manufacturing month */
+ u16 mfg_year; /* manufacturing year */
+ u64 mfg_wwn; /* wwn base for this adapter */
+ u8 num_wwn; /* number of wwns assigned */
+ u8 mfg_speeds; /* speeds allowed for this adapter */
+ u8 rsv[2];
+ char supplier_id[STRSZ(BFA_MFG_SUPPLIER_ID_SIZE)];
+ char supplier_partnum[STRSZ(BFA_MFG_SUPPLIER_PARTNUM_SIZE)];
+ char supplier_serialnum[STRSZ(BFA_MFG_SUPPLIER_SERIALNUM_SIZE)];
+ char supplier_revision[STRSZ(BFA_MFG_SUPPLIER_REVISION_SIZE)];
+ mac_t mfg_mac; /* base mac address */
+ u8 num_mac; /* number of mac addresses */
+ u8 rsv2;
+ u32 card_type; /* card type */
+ char cap_nic; /* capability nic */
+ char cap_cna; /* capability cna */
+ char cap_hba; /* capability hba */
+ char cap_fc16g; /* capability fc 16g */
+ char cap_sriov; /* capability sriov */
+ char cap_mezz; /* capability mezz */
+ u8 rsv3;
+ u8 mfg_nports; /* number of ports */
+ char media[8]; /* xfi/xaui */
+ char initial_mode[8]; /* initial mode: hba/cna/nic */
+ u8 rsv4[84];
+ u8 md5_chksum[BFA_MFG_CHKSUM_SIZE]; /* md5 checksum */
};
#pragma pack()
BFA_MODE_NIC = 3
};
+/*
+ * Flash module specific
+ */
+#define BFA_FLASH_PART_ENTRY_SIZE 32 /* partition entry size */
+#define BFA_FLASH_PART_MAX 32 /* maximal # of partitions */
+#define BFA_TOTAL_FLASH_SIZE 0x400000
+#define BFA_FLASH_PART_MFG 7
+
+/*
+ * flash partition attributes
+ */
+struct bfa_flash_part_attr {
+ u32 part_type; /* partition type */
+ u32 part_instance; /* partition instance */
+ u32 part_off; /* partition offset */
+ u32 part_size; /* partition size */
+ u32 part_len; /* partition content length */
+ u32 part_status; /* partition status */
+ char rsv[BFA_FLASH_PART_ENTRY_SIZE - 24];
+};
+
+/*
+ * flash attributes
+ */
+struct bfa_flash_attr {
+ u32 status; /* flash overall status */
+ u32 npart; /* num of partitions */
+ struct bfa_flash_part_attr part[BFA_FLASH_PART_MAX];
+};
+
#endif /* __BFA_DEFS_H__ */
static void bfa_ioc_event_notify(struct bfa_ioc *, enum bfa_ioc_event);
static void bfa_ioc_disable_comp(struct bfa_ioc *ioc);
static void bfa_ioc_lpu_stop(struct bfa_ioc *ioc);
+static void bfa_nw_ioc_debug_save_ftrc(struct bfa_ioc *ioc);
static void bfa_ioc_fail_notify(struct bfa_ioc *ioc);
static void bfa_ioc_pf_enabled(struct bfa_ioc *ioc);
static void bfa_ioc_pf_disabled(struct bfa_ioc *ioc);
static void
bfa_iocpf_sm_initfail_sync_entry(struct bfa_iocpf *iocpf)
{
+ bfa_nw_ioc_debug_save_ftrc(iocpf->ioc);
bfa_ioc_hw_sem_get(iocpf->ioc);
}
bfa_q_deq(&mod->cmd_q, &cmd);
}
+/**
+ * Read data from SMEM to host through PCI memmap
+ *
+ * @param[in] ioc memory for IOC
+ * @param[in] tbuf app memory to store data from smem
+ * @param[in] soff smem offset
+ * @param[in] sz size of smem in bytes
+ */
+static int
+bfa_nw_ioc_smem_read(struct bfa_ioc *ioc, void *tbuf, u32 soff, u32 sz)
+{
+ u32 pgnum, loff, r32;
+ int i, len;
+ u32 *buf = tbuf;
+
+ pgnum = PSS_SMEM_PGNUM(ioc->ioc_regs.smem_pg0, soff);
+ loff = PSS_SMEM_PGOFF(soff);
+
+ /*
+ * Hold semaphore to serialize pll init and fwtrc.
+ */
+ if (bfa_nw_ioc_sem_get(ioc->ioc_regs.ioc_init_sem_reg) == 0)
+ return 1;
+
+ writel(pgnum, ioc->ioc_regs.host_page_num_fn);
+
+ len = sz/sizeof(u32);
+ for (i = 0; i < len; i++) {
+ r32 = swab32(readl((loff) + (ioc->ioc_regs.smem_page_start)));
+ buf[i] = be32_to_cpu(r32);
+ loff += sizeof(u32);
+
+ /**
+ * handle page offset wrap around
+ */
+ loff = PSS_SMEM_PGOFF(loff);
+ if (loff == 0) {
+ pgnum++;
+ writel(pgnum, ioc->ioc_regs.host_page_num_fn);
+ }
+ }
+
+ writel(PSS_SMEM_PGNUM(ioc->ioc_regs.smem_pg0, 0),
+ ioc->ioc_regs.host_page_num_fn);
+
+ /*
+ * release semaphore
+ */
+ readl(ioc->ioc_regs.ioc_init_sem_reg);
+ writel(1, ioc->ioc_regs.ioc_init_sem_reg);
+ return 0;
+}
+
+/**
+ * Retrieve saved firmware trace from a prior IOC failure.
+ */
+int
+bfa_nw_ioc_debug_fwtrc(struct bfa_ioc *ioc, void *trcdata, int *trclen)
+{
+ u32 loff = BFI_IOC_TRC_OFF + BNA_DBG_FWTRC_LEN * ioc->port_id;
+ int tlen, status = 0;
+
+ tlen = *trclen;
+ if (tlen > BNA_DBG_FWTRC_LEN)
+ tlen = BNA_DBG_FWTRC_LEN;
+
+ status = bfa_nw_ioc_smem_read(ioc, trcdata, loff, tlen);
+ *trclen = tlen;
+ return status;
+}
+
+/**
+ * Save firmware trace if configured.
+ */
+static void
+bfa_nw_ioc_debug_save_ftrc(struct bfa_ioc *ioc)
+{
+ int tlen;
+
+ if (ioc->dbg_fwsave_once) {
+ ioc->dbg_fwsave_once = 0;
+ if (ioc->dbg_fwsave_len) {
+ tlen = ioc->dbg_fwsave_len;
+ bfa_nw_ioc_debug_fwtrc(ioc, ioc->dbg_fwsave, &tlen);
+ }
+ }
+}
+
+/**
+ * Retrieve saved firmware trace from a prior IOC failure.
+ */
+int
+bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen)
+{
+ int tlen;
+
+ if (ioc->dbg_fwsave_len == 0)
+ return BFA_STATUS_ENOFSAVE;
+
+ tlen = *trclen;
+ if (tlen > ioc->dbg_fwsave_len)
+ tlen = ioc->dbg_fwsave_len;
+
+ memcpy(trcdata, ioc->dbg_fwsave, tlen);
+ *trclen = tlen;
+ return BFA_STATUS_OK;
+}
+
static void
bfa_ioc_fail_notify(struct bfa_ioc *ioc)
{
*/
ioc->cbfn->hbfail_cbfn(ioc->bfa);
bfa_ioc_event_notify(ioc, BFA_IOC_E_FAILED);
+ bfa_nw_ioc_debug_save_ftrc(ioc);
}
/**
bfa_fsm_send_event(ioc, IOC_E_DISABLE);
}
+/**
+ * Initialize memory for saving firmware trace.
+ */
+void
+bfa_nw_ioc_debug_memclaim(struct bfa_ioc *ioc, void *dbg_fwsave)
+{
+ ioc->dbg_fwsave = dbg_fwsave;
+ ioc->dbg_fwsave_len = ioc->iocpf.auto_recover ? BNA_DBG_FWTRC_LEN : 0;
+}
+
static u32
bfa_ioc_smem_pgnum(struct bfa_ioc *ioc, u32 fmaddr)
{
bfa_fsm_cmp_state(ioc, bfa_ioc_sm_disabled);
}
+/**
+ * return true if IOC is operational
+ */
+bool
+bfa_nw_ioc_is_operational(struct bfa_ioc *ioc)
+{
+ return bfa_fsm_cmp_state(ioc, bfa_ioc_sm_op);
+}
+
/**
* Add to IOC heartbeat failure notification queue. To be used by common
* modules such as cee, port, diag.
msecs_to_jiffies(BFA_IOC_POLL_TOV));
}
}
+
+/*
+ * Flash module specific
+ */
+
+/*
+ * FLASH DMA buffer should be big enough to hold both MFG block and
+ * asic block(64k) at the same time and also should be 2k aligned to
+ * avoid write segement to cross sector boundary.
+ */
+#define BFA_FLASH_SEG_SZ 2048
+#define BFA_FLASH_DMA_BUF_SZ \
+ roundup(0x010000 + sizeof(struct bfa_mfg_block), BFA_FLASH_SEG_SZ)
+
+static void
+bfa_flash_cb(struct bfa_flash *flash)
+{
+ flash->op_busy = 0;
+ if (flash->cbfn)
+ flash->cbfn(flash->cbarg, flash->status);
+}
+
+static void
+bfa_flash_notify(void *cbarg, enum bfa_ioc_event event)
+{
+ struct bfa_flash *flash = cbarg;
+
+ switch (event) {
+ case BFA_IOC_E_DISABLED:
+ case BFA_IOC_E_FAILED:
+ if (flash->op_busy) {
+ flash->status = BFA_STATUS_IOC_FAILURE;
+ flash->cbfn(flash->cbarg, flash->status);
+ flash->op_busy = 0;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * Send flash write request.
+ *
+ * @param[in] cbarg - callback argument
+ */
+static void
+bfa_flash_write_send(struct bfa_flash *flash)
+{
+ struct bfi_flash_write_req *msg =
+ (struct bfi_flash_write_req *) flash->mb.msg;
+ u32 len;
+
+ msg->type = be32_to_cpu(flash->type);
+ msg->instance = flash->instance;
+ msg->offset = be32_to_cpu(flash->addr_off + flash->offset);
+ len = (flash->residue < BFA_FLASH_DMA_BUF_SZ) ?
+ flash->residue : BFA_FLASH_DMA_BUF_SZ;
+ msg->length = be32_to_cpu(len);
+
+ /* indicate if it's the last msg of the whole write operation */
+ msg->last = (len == flash->residue) ? 1 : 0;
+
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_WRITE_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, len, flash->dbuf_pa);
+ memcpy(flash->dbuf_kva, flash->ubuf + flash->offset, len);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+
+ flash->residue -= len;
+ flash->offset += len;
+}
+
+/*
+ * Send flash read request.
+ *
+ * @param[in] cbarg - callback argument
+ */
+static void
+bfa_flash_read_send(void *cbarg)
+{
+ struct bfa_flash *flash = cbarg;
+ struct bfi_flash_read_req *msg =
+ (struct bfi_flash_read_req *) flash->mb.msg;
+ u32 len;
+
+ msg->type = be32_to_cpu(flash->type);
+ msg->instance = flash->instance;
+ msg->offset = be32_to_cpu(flash->addr_off + flash->offset);
+ len = (flash->residue < BFA_FLASH_DMA_BUF_SZ) ?
+ flash->residue : BFA_FLASH_DMA_BUF_SZ;
+ msg->length = be32_to_cpu(len);
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_READ_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, len, flash->dbuf_pa);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+}
+
+/*
+ * Process flash response messages upon receiving interrupts.
+ *
+ * @param[in] flasharg - flash structure
+ * @param[in] msg - message structure
+ */
+static void
+bfa_flash_intr(void *flasharg, struct bfi_mbmsg *msg)
+{
+ struct bfa_flash *flash = flasharg;
+ u32 status;
+
+ union {
+ struct bfi_flash_query_rsp *query;
+ struct bfi_flash_write_rsp *write;
+ struct bfi_flash_read_rsp *read;
+ struct bfi_mbmsg *msg;
+ } m;
+
+ m.msg = msg;
+
+ /* receiving response after ioc failure */
+ if (!flash->op_busy && msg->mh.msg_id != BFI_FLASH_I2H_EVENT)
+ return;
+
+ switch (msg->mh.msg_id) {
+ case BFI_FLASH_I2H_QUERY_RSP:
+ status = be32_to_cpu(m.query->status);
+ if (status == BFA_STATUS_OK) {
+ u32 i;
+ struct bfa_flash_attr *attr, *f;
+
+ attr = (struct bfa_flash_attr *) flash->ubuf;
+ f = (struct bfa_flash_attr *) flash->dbuf_kva;
+ attr->status = be32_to_cpu(f->status);
+ attr->npart = be32_to_cpu(f->npart);
+ for (i = 0; i < attr->npart; i++) {
+ attr->part[i].part_type =
+ be32_to_cpu(f->part[i].part_type);
+ attr->part[i].part_instance =
+ be32_to_cpu(f->part[i].part_instance);
+ attr->part[i].part_off =
+ be32_to_cpu(f->part[i].part_off);
+ attr->part[i].part_size =
+ be32_to_cpu(f->part[i].part_size);
+ attr->part[i].part_len =
+ be32_to_cpu(f->part[i].part_len);
+ attr->part[i].part_status =
+ be32_to_cpu(f->part[i].part_status);
+ }
+ }
+ flash->status = status;
+ bfa_flash_cb(flash);
+ break;
+ case BFI_FLASH_I2H_WRITE_RSP:
+ status = be32_to_cpu(m.write->status);
+ if (status != BFA_STATUS_OK || flash->residue == 0) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else
+ bfa_flash_write_send(flash);
+ break;
+ case BFI_FLASH_I2H_READ_RSP:
+ status = be32_to_cpu(m.read->status);
+ if (status != BFA_STATUS_OK) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else {
+ u32 len = be32_to_cpu(m.read->length);
+ memcpy(flash->ubuf + flash->offset,
+ flash->dbuf_kva, len);
+ flash->residue -= len;
+ flash->offset += len;
+ if (flash->residue == 0) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else
+ bfa_flash_read_send(flash);
+ }
+ break;
+ case BFI_FLASH_I2H_BOOT_VER_RSP:
+ case BFI_FLASH_I2H_EVENT:
+ break;
+ default:
+ WARN_ON(1);
+ }
+}
+
+/*
+ * Flash memory info API.
+ */
+u32
+bfa_nw_flash_meminfo(void)
+{
+ return roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+}
+
+/*
+ * Flash attach API.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] ioc - ioc structure
+ * @param[in] dev - device structure
+ */
+void
+bfa_nw_flash_attach(struct bfa_flash *flash, struct bfa_ioc *ioc, void *dev)
+{
+ flash->ioc = ioc;
+ flash->cbfn = NULL;
+ flash->cbarg = NULL;
+ flash->op_busy = 0;
+
+ bfa_nw_ioc_mbox_regisr(flash->ioc, BFI_MC_FLASH, bfa_flash_intr, flash);
+ bfa_q_qe_init(&flash->ioc_notify);
+ bfa_ioc_notify_init(&flash->ioc_notify, bfa_flash_notify, flash);
+ list_add_tail(&flash->ioc_notify.qe, &flash->ioc->notify_q);
+}
+
+/*
+ * Claim memory for flash
+ *
+ * @param[in] flash - flash structure
+ * @param[in] dm_kva - pointer to virtual memory address
+ * @param[in] dm_pa - physical memory address
+ */
+void
+bfa_nw_flash_memclaim(struct bfa_flash *flash, u8 *dm_kva, u64 dm_pa)
+{
+ flash->dbuf_kva = dm_kva;
+ flash->dbuf_pa = dm_pa;
+ memset(flash->dbuf_kva, 0, BFA_FLASH_DMA_BUF_SZ);
+ dm_kva += roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+ dm_pa += roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+}
+
+/*
+ * Get flash attribute.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] attr - flash attribute structure
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_get_attr(struct bfa_flash *flash, struct bfa_flash_attr *attr,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ struct bfi_flash_query_req *msg =
+ (struct bfi_flash_query_req *) flash->mb.msg;
+
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->ubuf = (u8 *) attr;
+
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_QUERY_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, sizeof(struct bfa_flash_attr), flash->dbuf_pa);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+
+ return BFA_STATUS_OK;
+}
+
+/*
+ * Update flash partition.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] type - flash partition type
+ * @param[in] instance - flash partition instance
+ * @param[in] buf - update data buffer
+ * @param[in] len - data buffer length
+ * @param[in] offset - offset relative to the partition starting address
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_update_part(struct bfa_flash *flash, u32 type, u8 instance,
+ void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ /*
+ * 'len' must be in word (4-byte) boundary
+ */
+ if (!len || (len & 0x03))
+ return BFA_STATUS_FLASH_BAD_LEN;
+
+ if (type == BFA_FLASH_PART_MFG)
+ return BFA_STATUS_EINVAL;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->type = type;
+ flash->instance = instance;
+ flash->residue = len;
+ flash->offset = 0;
+ flash->addr_off = offset;
+ flash->ubuf = buf;
+
+ bfa_flash_write_send(flash);
+
+ return BFA_STATUS_OK;
+}
+
+/*
+ * Read flash partition.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] type - flash partition type
+ * @param[in] instance - flash partition instance
+ * @param[in] buf - read data buffer
+ * @param[in] len - data buffer length
+ * @param[in] offset - offset relative to the partition starting address
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_read_part(struct bfa_flash *flash, u32 type, u8 instance,
+ void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ /*
+ * 'len' must be in word (4-byte) boundary
+ */
+ if (!len || (len & 0x03))
+ return BFA_STATUS_FLASH_BAD_LEN;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->type = type;
+ flash->instance = instance;
+ flash->residue = len;
+ flash->offset = 0;
+ flash->addr_off = offset;
+ flash->ubuf = buf;
+
+ bfa_flash_read_send(flash);
+
+ return BFA_STATUS_OK;
+}
#define BFA_IOC_HWSEM_TOV 500 /* msecs */
#define BFA_IOC_HB_TOV 500 /* msecs */
#define BFA_IOC_POLL_TOV 200 /* msecs */
+#define BNA_DBG_FWTRC_LEN (BFI_IOC_TRC_ENTS * BFI_IOC_TRC_ENT_SZ + \
+ BFI_IOC_TRC_HDR_SZ)
/**
* PCI device information required by IOC
dma_addr->a32.addr_hi = (u32) htonl(upper_32_bits(pa));
}
+#define bfa_alen_set(__alen, __len, __pa) \
+ __bfa_alen_set(__alen, __len, (u64)__pa)
+
+static inline void
+__bfa_alen_set(struct bfi_alen *alen, u32 len, u64 pa)
+{
+ alen->al_len = cpu_to_be32(len);
+ bfa_dma_be_addr_set(alen->al_addr, pa);
+}
+
struct bfa_ioc_regs {
void __iomem *hfn_mbox_cmd;
void __iomem *hfn_mbox;
void bfa_nw_ioc_error_isr(struct bfa_ioc *ioc);
bool bfa_nw_ioc_is_disabled(struct bfa_ioc *ioc);
+bool bfa_nw_ioc_is_operational(struct bfa_ioc *ioc);
void bfa_nw_ioc_get_attr(struct bfa_ioc *ioc, struct bfa_ioc_attr *ioc_attr);
void bfa_nw_ioc_notify_register(struct bfa_ioc *ioc,
struct bfa_ioc_notify *notify);
bool bfa_nw_ioc_fwver_cmp(struct bfa_ioc *ioc,
struct bfi_ioc_image_hdr *fwhdr);
mac_t bfa_nw_ioc_get_mac(struct bfa_ioc *ioc);
+void bfa_nw_ioc_debug_memclaim(struct bfa_ioc *ioc, void *dbg_fwsave);
+int bfa_nw_ioc_debug_fwtrc(struct bfa_ioc *ioc, void *trcdata, int *trclen);
+int bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen);
/*
* Timeout APIs
u32 *bfa_cb_image_get_chunk(enum bfi_asic_gen asic_gen, u32 off);
u32 bfa_cb_image_get_size(enum bfi_asic_gen asic_gen);
+/*
+ * Flash module specific
+ */
+typedef void (*bfa_cb_flash) (void *cbarg, enum bfa_status status);
+
+struct bfa_flash {
+ struct bfa_ioc *ioc; /* back pointer to ioc */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 op_busy; /* operation busy flag */
+ u32 residue; /* residual length */
+ u32 offset; /* offset */
+ enum bfa_status status; /* status */
+ u8 *dbuf_kva; /* dma buf virtual address */
+ u64 dbuf_pa; /* dma buf physical address */
+ bfa_cb_flash cbfn; /* user callback function */
+ void *cbarg; /* user callback arg */
+ u8 *ubuf; /* user supplied buffer */
+ u32 addr_off; /* partition address offset */
+ struct bfa_mbox_cmd mb; /* mailbox */
+ struct bfa_ioc_notify ioc_notify; /* ioc event notify */
+};
+
+enum bfa_status bfa_nw_flash_get_attr(struct bfa_flash *flash,
+ struct bfa_flash_attr *attr,
+ bfa_cb_flash cbfn, void *cbarg);
+enum bfa_status bfa_nw_flash_update_part(struct bfa_flash *flash,
+ u32 type, u8 instance, void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg);
+enum bfa_status bfa_nw_flash_read_part(struct bfa_flash *flash,
+ u32 type, u8 instance, void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg);
+u32 bfa_nw_flash_meminfo(void);
+void bfa_nw_flash_attach(struct bfa_flash *flash,
+ struct bfa_ioc *ioc, void *dev);
+void bfa_nw_flash_memclaim(struct bfa_flash *flash, u8 *dm_kva, u64 dm_pa);
+
#endif /* __BFA_IOC_H__ */
} a32;
};
+/**
+ * Generic DMA addr-len pair.
+ */
+struct bfi_alen {
+ union bfi_addr_u al_addr; /* DMA addr of buffer */
+ u32 al_len; /* length of buffer */
+};
+
/*
* Large Message structure - 128 Bytes size Msgs
*/
*/
#define BFI_IOC_TRC_OFF (0x4b00)
#define BFI_IOC_TRC_ENTS 256
+#define BFI_IOC_TRC_ENT_SZ 16
+#define BFI_IOC_TRC_HDR_SZ 32
#define BFI_IOC_FW_SIGNATURE (0xbfadbfad)
#define BFI_IOC_MD5SUM_SZ 4
u16 len;
};
+/*
+ * FLASH module specific
+ */
+enum bfi_flash_h2i_msgs {
+ BFI_FLASH_H2I_QUERY_REQ = 1,
+ BFI_FLASH_H2I_ERASE_REQ = 2,
+ BFI_FLASH_H2I_WRITE_REQ = 3,
+ BFI_FLASH_H2I_READ_REQ = 4,
+ BFI_FLASH_H2I_BOOT_VER_REQ = 5,
+};
+
+enum bfi_flash_i2h_msgs {
+ BFI_FLASH_I2H_QUERY_RSP = BFA_I2HM(1),
+ BFI_FLASH_I2H_ERASE_RSP = BFA_I2HM(2),
+ BFI_FLASH_I2H_WRITE_RSP = BFA_I2HM(3),
+ BFI_FLASH_I2H_READ_RSP = BFA_I2HM(4),
+ BFI_FLASH_I2H_BOOT_VER_RSP = BFA_I2HM(5),
+ BFI_FLASH_I2H_EVENT = BFA_I2HM(127),
+};
+
+/*
+ * Flash query request
+ */
+struct bfi_flash_query_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ struct bfi_alen alen;
+};
+
+/*
+ * Flash write request
+ */
+struct bfi_flash_write_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ struct bfi_alen alen;
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 last;
+ u8 rsv[2];
+ u32 offset;
+ u32 length;
+};
+
+/*
+ * Flash read request
+ */
+struct bfi_flash_read_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 offset;
+ u32 length;
+ struct bfi_alen alen;
+};
+
+/*
+ * Flash query response
+ */
+struct bfi_flash_query_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 status;
+};
+
+/*
+ * Flash read response
+ */
+struct bfi_flash_read_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 status;
+ u32 length;
+};
+
+/*
+ * Flash write response
+ */
+struct bfi_flash_write_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 status;
+ u32 length;
+};
+
#pragma pack()
#endif /* __BFI_H__ */
bfa_nw_ioc_mem_claim(&ioceth->ioc, kva, dma);
kva = res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.mdl[0].kva;
+ bfa_nw_ioc_debug_memclaim(&ioceth->ioc, kva);
/**
* Attach common modules (Diag, SFP, CEE, Port) and claim respective
kva += bfa_nw_cee_meminfo();
dma += bfa_nw_cee_meminfo();
+ bfa_nw_flash_attach(&bna->flash, &ioceth->ioc, bna);
+ bfa_nw_flash_memclaim(&bna->flash, kva, dma);
+ kva += bfa_nw_flash_meminfo();
+ dma += bfa_nw_flash_meminfo();
+
bfa_msgq_attach(&bna->msgq, &ioceth->ioc);
bfa_msgq_memclaim(&bna->msgq, kva, dma);
bfa_msgq_regisr(&bna->msgq, BFI_MC_ENET, bna_msgq_rsp_handler, bna);
res_info[BNA_RES_MEM_T_COM].res_u.mem_info.num = 1;
res_info[BNA_RES_MEM_T_COM].res_u.mem_info.len = ALIGN(
(bfa_nw_cee_meminfo() +
- bfa_msgq_meminfo()), PAGE_SIZE);
+ bfa_nw_flash_meminfo() +
+ bfa_msgq_meminfo()), PAGE_SIZE);
/* DMA memory for retrieving IOC attributes */
res_info[BNA_RES_MEM_T_ATTR].res_type = BNA_RES_T_MEM;
/* Virtual memory for retreiving fw_trc */
res_info[BNA_RES_MEM_T_FWTRC].res_type = BNA_RES_T_MEM;
res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.mem_type = BNA_MEM_T_KVA;
- res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.num = 0;
- res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.len = 0;
+ res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.num = 1;
+ res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.len = BNA_DBG_FWTRC_LEN;
/* DMA memory for retreiving stats */
res_info[BNA_RES_MEM_T_STATS].res_type = BNA_RES_T_MEM;
struct bna_ioceth ioceth;
struct bfa_cee cee;
+ struct bfa_flash flash;
struct bfa_msgq msgq;
struct bna_ethport ethport;
module_param(bnad_ioc_auto_recover, uint, 0444);
MODULE_PARM_DESC(bnad_ioc_auto_recover, "Enable / Disable auto recovery");
+static uint bna_debugfs_enable = 1;
+module_param(bna_debugfs_enable, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(bna_debugfs_enable, "Enables debugfs feature, default=1,"
+ " Range[false:0|true:1]");
+
/*
* Global variables
*/
u32 bnad_rxqs_per_cq = 2;
-
+u32 bna_id;
+struct mutex bnad_list_mutex;
+LIST_HEAD(bnad_list);
static const u8 bnad_bcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
/*
#define BNAD_TXRX_SYNC_MDELAY 250 /* 250 msecs */
+static void
+bnad_add_to_list(struct bnad *bnad)
+{
+ mutex_lock(&bnad_list_mutex);
+ list_add_tail(&bnad->list_entry, &bnad_list);
+ bnad->id = bna_id++;
+ mutex_unlock(&bnad_list_mutex);
+}
+
+static void
+bnad_remove_from_list(struct bnad *bnad)
+{
+ mutex_lock(&bnad_list_mutex);
+ list_del(&bnad->list_entry);
+ mutex_unlock(&bnad_list_mutex);
+}
+
/*
* Reinitialize completions in CQ, once Rx is taken down
*/
bnad_cb_ethport_link_status(struct bnad *bnad,
enum bna_link_status link_status)
{
- bool link_up = 0;
+ bool link_up = false;
link_up = (link_status == BNA_LINK_UP) || (link_status == BNA_CEE_UP);
complete(&bnad->bnad_completions.mtu_comp);
}
+void
+bnad_cb_completion(void *arg, enum bfa_status status)
+{
+ struct bnad_iocmd_comp *iocmd_comp =
+ (struct bnad_iocmd_comp *)arg;
+
+ iocmd_comp->comp_status = (u32) status;
+ complete(&iocmd_comp->comp);
+}
+
/* Resource allocation, free functions */
static void
return err;
}
-static void
+static int
bnad_vlan_rx_add_vid(struct net_device *netdev,
unsigned short vid)
{
unsigned long flags;
if (!bnad->rx_info[0].rx)
- return;
+ return 0;
mutex_lock(&bnad->conf_mutex);
spin_unlock_irqrestore(&bnad->bna_lock, flags);
mutex_unlock(&bnad->conf_mutex);
+
+ return 0;
}
-static void
+static int
bnad_vlan_rx_kill_vid(struct net_device *netdev,
unsigned short vid)
{
unsigned long flags;
if (!bnad->rx_info[0].rx)
- return;
+ return 0;
mutex_lock(&bnad->conf_mutex);
spin_unlock_irqrestore(&bnad->bna_lock, flags);
mutex_unlock(&bnad->conf_mutex);
+
+ return 0;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
{
spin_lock_init(&bnad->bna_lock);
mutex_init(&bnad->conf_mutex);
+ mutex_init(&bnad_list_mutex);
}
static void
bnad_lock_uninit(struct bnad *bnad)
{
mutex_destroy(&bnad->conf_mutex);
+ mutex_destroy(&bnad_list_mutex);
}
/* PCI Initialization */
goto disable_device;
if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
!dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
- *using_dac = 1;
+ *using_dac = true;
} else {
err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
if (err) {
if (err)
goto release_regions;
}
- *using_dac = 0;
+ *using_dac = false;
}
pci_set_master(pdev);
return 0;
return err;
}
bnad = netdev_priv(netdev);
-
bnad_lock_init(bnad);
+ bnad_add_to_list(bnad);
mutex_lock(&bnad->conf_mutex);
/*
/* Set link to down state */
netif_carrier_off(netdev);
+ /* Setup the debugfs node for this bfad */
+ if (bna_debugfs_enable)
+ bnad_debugfs_init(bnad);
+
/* Get resource requirement form bna */
spin_lock_irqsave(&bnad->bna_lock, flags);
bna_res_req(&bnad->res_info[0]);
res_free:
bnad_res_free(bnad, &bnad->res_info[0], BNA_RES_T_MAX);
drv_uninit:
+ /* Remove the debugfs node for this bnad */
+ kfree(bnad->regdata);
+ bnad_debugfs_uninit(bnad);
bnad_uninit(bnad);
pci_uninit:
bnad_pci_uninit(pdev);
unlock_mutex:
mutex_unlock(&bnad->conf_mutex);
+ bnad_remove_from_list(bnad);
bnad_lock_uninit(bnad);
free_netdev(netdev);
return err;
bnad_disable_msix(bnad);
bnad_pci_uninit(pdev);
mutex_unlock(&bnad->conf_mutex);
+ bnad_remove_from_list(bnad);
bnad_lock_uninit(bnad);
+ /* Remove the debugfs node for this bnad */
+ kfree(bnad->regdata);
+ bnad_debugfs_uninit(bnad);
bnad_uninit(bnad);
free_netdev(netdev);
}
BNAD_LS_UP = 1
};
+struct bnad_iocmd_comp {
+ struct bnad *bnad;
+ struct completion comp;
+ int comp_status;
+};
+
struct bnad_completion {
struct completion ioc_comp;
struct completion ucast_comp;
struct bnad {
struct net_device *netdev;
+ u32 id;
+ struct list_head list_entry;
/* Data path */
struct bnad_tx_info tx_info[BNAD_MAX_TX];
char adapter_name[BNAD_NAME_LEN];
char port_name[BNAD_NAME_LEN];
char mbox_irq_name[BNAD_NAME_LEN];
+
+ /* debugfs specific data */
+ char *regdata;
+ u32 reglen;
+ struct dentry *bnad_dentry_files[5];
+ struct dentry *port_debugfs_root;
+};
+
+struct bnad_drvinfo {
+ struct bfa_ioc_attr ioc_attr;
+ struct bfa_cee_attr cee_attr;
+ struct bfa_flash_attr flash_attr;
+ u32 cee_status;
+ u32 flash_status;
};
/*
extern int bnad_enable_default_bcast(struct bnad *bnad);
extern void bnad_restore_vlans(struct bnad *bnad, u32 rx_id);
extern void bnad_set_ethtool_ops(struct net_device *netdev);
+extern void bnad_cb_completion(void *arg, enum bfa_status status);
/* Configuration & setup */
extern void bnad_tx_coalescing_timeo_set(struct bnad *bnad);
extern void bnad_netdev_hwstats_fill(struct bnad *bnad,
struct rtnl_link_stats64 *stats);
+/* Debugfs */
+void bnad_debugfs_init(struct bnad *bnad);
+void bnad_debugfs_uninit(struct bnad *bnad);
+
/**
* MACROS
*/
--- /dev/null
+/*
+ * Linux network driver for Brocade Converged Network Adapter.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License (GPL) Version 2 as
+ * published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+/*
+ * Copyright (c) 2005-2011 Brocade Communications Systems, Inc.
+ * All rights reserved
+ * www.brocade.com
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include "bnad.h"
+
+/*
+ * BNA debufs interface
+ *
+ * To access the interface, debugfs file system should be mounted
+ * if not already mounted using:
+ * mount -t debugfs none /sys/kernel/debug
+ *
+ * BNA Hierarchy:
+ * - bna/pci_dev:<pci_name>
+ * where the pci_name corresponds to the one under /sys/bus/pci/drivers/bna
+ *
+ * Debugging service available per pci_dev:
+ * fwtrc: To collect current firmware trace.
+ * fwsave: To collect last saved fw trace as a result of firmware crash.
+ * regwr: To write one word to chip register
+ * regrd: To read one or more words from chip register.
+ */
+
+struct bnad_debug_info {
+ char *debug_buffer;
+ void *i_private;
+ int buffer_len;
+};
+
+static int
+bnad_debugfs_open_fwtrc(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *fw_debug;
+ unsigned long flags;
+ int rc;
+
+ fw_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!fw_debug)
+ return -ENOMEM;
+
+ fw_debug->buffer_len = BNA_DBG_FWTRC_LEN;
+
+ fw_debug->debug_buffer = kzalloc(fw_debug->buffer_len, GFP_KERNEL);
+ if (!fw_debug->debug_buffer) {
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to allocate fwtrc buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ rc = bfa_nw_ioc_debug_fwtrc(&bnad->bna.ioceth.ioc,
+ fw_debug->debug_buffer,
+ &fw_debug->buffer_len);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ if (rc != BFA_STATUS_OK) {
+ kfree(fw_debug->debug_buffer);
+ fw_debug->debug_buffer = NULL;
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bnad %s: Failed to collect fwtrc\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = fw_debug;
+
+ return 0;
+}
+
+static int
+bnad_debugfs_open_fwsave(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *fw_debug;
+ unsigned long flags;
+ int rc;
+
+ fw_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!fw_debug)
+ return -ENOMEM;
+
+ fw_debug->buffer_len = BNA_DBG_FWTRC_LEN;
+
+ fw_debug->debug_buffer = kzalloc(fw_debug->buffer_len, GFP_KERNEL);
+ if (!fw_debug->debug_buffer) {
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to allocate fwsave buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ rc = bfa_nw_ioc_debug_fwsave(&bnad->bna.ioceth.ioc,
+ fw_debug->debug_buffer,
+ &fw_debug->buffer_len);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ if (rc != BFA_STATUS_OK && rc != BFA_STATUS_ENOFSAVE) {
+ kfree(fw_debug->debug_buffer);
+ fw_debug->debug_buffer = NULL;
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to collect fwsave\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = fw_debug;
+
+ return 0;
+}
+
+static int
+bnad_debugfs_open_reg(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *reg_debug;
+
+ reg_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!reg_debug)
+ return -ENOMEM;
+
+ reg_debug->i_private = inode->i_private;
+
+ file->private_data = reg_debug;
+
+ return 0;
+}
+
+static int
+bnad_get_debug_drvinfo(struct bnad *bnad, void *buffer, u32 len)
+{
+ struct bnad_drvinfo *drvinfo = (struct bnad_drvinfo *) buffer;
+ struct bnad_iocmd_comp fcomp;
+ unsigned long flags = 0;
+ int ret = BFA_STATUS_FAILED;
+
+ /* Get IOC info */
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ bfa_nw_ioc_get_attr(&bnad->bna.ioceth.ioc, &drvinfo->ioc_attr);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ /* Retrieve CEE related info */
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_cee_get_attr(&bnad->bna.cee, &drvinfo->cee_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto out;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ drvinfo->cee_status = fcomp.comp_status;
+
+ /* Retrieve flash partition info */
+ fcomp.comp_status = 0;
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_get_attr(&bnad->bna.flash, &drvinfo->flash_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto out;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ drvinfo->flash_status = fcomp.comp_status;
+out:
+ return ret;
+}
+
+static int
+bnad_debugfs_open_drvinfo(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *drv_info;
+ int rc;
+
+ drv_info = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!drv_info)
+ return -ENOMEM;
+
+ drv_info->buffer_len = sizeof(struct bnad_drvinfo);
+
+ drv_info->debug_buffer = kzalloc(drv_info->buffer_len, GFP_KERNEL);
+ if (!drv_info->debug_buffer) {
+ kfree(drv_info);
+ drv_info = NULL;
+ pr_warn("bna %s: Failed to allocate drv info buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ mutex_lock(&bnad->conf_mutex);
+ rc = bnad_get_debug_drvinfo(bnad, drv_info->debug_buffer,
+ drv_info->buffer_len);
+ mutex_unlock(&bnad->conf_mutex);
+ if (rc != BFA_STATUS_OK) {
+ kfree(drv_info->debug_buffer);
+ drv_info->debug_buffer = NULL;
+ kfree(drv_info);
+ drv_info = NULL;
+ pr_warn("bna %s: Failed to collect drvinfo\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = drv_info;
+
+ return 0;
+}
+
+/* Changes the current file position */
+static loff_t
+bnad_debugfs_lseek(struct file *file, loff_t offset, int orig)
+{
+ loff_t pos = file->f_pos;
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return -EINVAL;
+
+ switch (orig) {
+ case 0:
+ file->f_pos = offset;
+ break;
+ case 1:
+ file->f_pos += offset;
+ break;
+ case 2:
+ file->f_pos = debug->buffer_len - offset;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (file->f_pos < 0 || file->f_pos > debug->buffer_len) {
+ file->f_pos = pos;
+ return -EINVAL;
+ }
+
+ return file->f_pos;
+}
+
+static ssize_t
+bnad_debugfs_read(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *pos)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug || !debug->debug_buffer)
+ return 0;
+
+ return simple_read_from_buffer(buf, nbytes, pos,
+ debug->debug_buffer, debug->buffer_len);
+}
+
+#define BFA_REG_CT_ADDRSZ (0x40000)
+#define BFA_REG_CB_ADDRSZ (0x20000)
+#define BFA_REG_ADDRSZ(__ioc) \
+ ((u32)(bfa_asic_id_ctc(bfa_ioc_devid(__ioc)) ? \
+ BFA_REG_CT_ADDRSZ : BFA_REG_CB_ADDRSZ))
+#define BFA_REG_ADDRMSK(__ioc) (BFA_REG_ADDRSZ(__ioc) - 1)
+
+/*
+ * Function to check if the register offset passed is valid.
+ */
+static int
+bna_reg_offset_check(struct bfa_ioc *ioc, u32 offset, u32 len)
+{
+ u8 area;
+
+ /* check [16:15] */
+ area = (offset >> 15) & 0x7;
+ if (area == 0) {
+ /* PCIe core register */
+ if ((offset + (len<<2)) > 0x8000) /* 8k dwords or 32KB */
+ return BFA_STATUS_EINVAL;
+ } else if (area == 0x1) {
+ /* CB 32 KB memory page */
+ if ((offset + (len<<2)) > 0x10000) /* 8k dwords or 32KB */
+ return BFA_STATUS_EINVAL;
+ } else {
+ /* CB register space 64KB */
+ if ((offset + (len<<2)) > BFA_REG_ADDRMSK(ioc))
+ return BFA_STATUS_EINVAL;
+ }
+ return BFA_STATUS_OK;
+}
+
+static ssize_t
+bnad_debugfs_read_regrd(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *pos)
+{
+ struct bnad_debug_info *regrd_debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)regrd_debug->i_private;
+ ssize_t rc;
+
+ if (!bnad->regdata)
+ return 0;
+
+ rc = simple_read_from_buffer(buf, nbytes, pos,
+ bnad->regdata, bnad->reglen);
+
+ if ((*pos + nbytes) >= bnad->reglen) {
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+ }
+
+ return rc;
+}
+
+static ssize_t
+bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct bnad_debug_info *regrd_debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)regrd_debug->i_private;
+ struct bfa_ioc *ioc = &bnad->bna.ioceth.ioc;
+ int addr, len, rc, i;
+ u32 *regbuf;
+ void __iomem *rb, *reg_addr;
+ unsigned long flags;
+ void *kern_buf;
+
+ /* Allocate memory to store the user space buf */
+ kern_buf = kzalloc(nbytes, GFP_KERNEL);
+ if (!kern_buf) {
+ pr_warn("bna %s: Failed to allocate user buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ if (copy_from_user(kern_buf, (void __user *)buf, nbytes)) {
+ kfree(kern_buf);
+ return -ENOMEM;
+ }
+
+ rc = sscanf(kern_buf, "%x:%x", &addr, &len);
+ if (rc < 2) {
+ pr_warn("bna %s: Failed to read user buffer\n",
+ pci_name(bnad->pcidev));
+ kfree(kern_buf);
+ return -EINVAL;
+ }
+
+ kfree(kern_buf);
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+
+ bnad->regdata = kzalloc(len << 2, GFP_KERNEL);
+ if (!bnad->regdata) {
+ pr_warn("bna %s: Failed to allocate regrd buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ bnad->reglen = len << 2;
+ rb = bfa_ioc_bar0(ioc);
+ addr &= BFA_REG_ADDRMSK(ioc);
+
+ /* offset and len sanity check */
+ rc = bna_reg_offset_check(ioc, addr, len);
+ if (rc) {
+ pr_warn("bna %s: Failed reg offset check\n",
+ pci_name(bnad->pcidev));
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+ return -EINVAL;
+ }
+
+ reg_addr = rb + addr;
+ regbuf = (u32 *)bnad->regdata;
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ for (i = 0; i < len; i++) {
+ *regbuf = readl(reg_addr);
+ regbuf++;
+ reg_addr += sizeof(u32);
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ return nbytes;
+}
+
+static ssize_t
+bnad_debugfs_write_regwr(struct file *file, const char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct bnad_debug_info *debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)debug->i_private;
+ struct bfa_ioc *ioc = &bnad->bna.ioceth.ioc;
+ int addr, val, rc;
+ void __iomem *reg_addr;
+ unsigned long flags;
+ void *kern_buf;
+
+ /* Allocate memory to store the user space buf */
+ kern_buf = kzalloc(nbytes, GFP_KERNEL);
+ if (!kern_buf) {
+ pr_warn("bna %s: Failed to allocate user buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ if (copy_from_user(kern_buf, (void __user *)buf, nbytes)) {
+ kfree(kern_buf);
+ return -ENOMEM;
+ }
+
+ rc = sscanf(kern_buf, "%x:%x", &addr, &val);
+ if (rc < 2) {
+ pr_warn("bna %s: Failed to read user buffer\n",
+ pci_name(bnad->pcidev));
+ kfree(kern_buf);
+ return -EINVAL;
+ }
+ kfree(kern_buf);
+
+ addr &= BFA_REG_ADDRMSK(ioc); /* offset only 17 bit and word align */
+
+ /* offset and len sanity check */
+ rc = bna_reg_offset_check(ioc, addr, 1);
+ if (rc) {
+ pr_warn("bna %s: Failed reg offset check\n",
+ pci_name(bnad->pcidev));
+ return -EINVAL;
+ }
+
+ reg_addr = (bfa_ioc_bar0(ioc)) + addr;
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ writel(val, reg_addr);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ return nbytes;
+}
+
+static int
+bnad_debugfs_release(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return 0;
+
+ file->private_data = NULL;
+ kfree(debug);
+ return 0;
+}
+
+static int
+bnad_debugfs_buffer_release(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return 0;
+
+ kfree(debug->debug_buffer);
+
+ file->private_data = NULL;
+ kfree(debug);
+ debug = NULL;
+ return 0;
+}
+
+static const struct file_operations bnad_debugfs_op_fwtrc = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_fwtrc,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+static const struct file_operations bnad_debugfs_op_fwsave = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_fwsave,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+static const struct file_operations bnad_debugfs_op_regrd = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_reg,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read_regrd,
+ .write = bnad_debugfs_write_regrd,
+ .release = bnad_debugfs_release,
+};
+
+static const struct file_operations bnad_debugfs_op_regwr = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_reg,
+ .llseek = bnad_debugfs_lseek,
+ .write = bnad_debugfs_write_regwr,
+ .release = bnad_debugfs_release,
+};
+
+static const struct file_operations bnad_debugfs_op_drvinfo = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_drvinfo,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+struct bnad_debugfs_entry {
+ const char *name;
+ mode_t mode;
+ const struct file_operations *fops;
+};
+
+static const struct bnad_debugfs_entry bnad_debugfs_files[] = {
+ { "fwtrc", S_IFREG|S_IRUGO, &bnad_debugfs_op_fwtrc, },
+ { "fwsave", S_IFREG|S_IRUGO, &bnad_debugfs_op_fwsave, },
+ { "regrd", S_IFREG|S_IRUGO|S_IWUSR, &bnad_debugfs_op_regrd, },
+ { "regwr", S_IFREG|S_IWUSR, &bnad_debugfs_op_regwr, },
+ { "drvinfo", S_IFREG|S_IRUGO, &bnad_debugfs_op_drvinfo, },
+};
+
+static struct dentry *bna_debugfs_root;
+static atomic_t bna_debugfs_port_count;
+
+/* Initialize debugfs interface for BNA */
+void
+bnad_debugfs_init(struct bnad *bnad)
+{
+ const struct bnad_debugfs_entry *file;
+ char name[64];
+ int i;
+
+ /* Setup the BNA debugfs root directory*/
+ if (!bna_debugfs_root) {
+ bna_debugfs_root = debugfs_create_dir("bna", NULL);
+ atomic_set(&bna_debugfs_port_count, 0);
+ if (!bna_debugfs_root) {
+ pr_warn("BNA: debugfs root dir creation failed\n");
+ return;
+ }
+ }
+
+ /* Setup the pci_dev debugfs directory for the port */
+ snprintf(name, sizeof(name), "pci_dev:%s", pci_name(bnad->pcidev));
+ if (!bnad->port_debugfs_root) {
+ bnad->port_debugfs_root =
+ debugfs_create_dir(name, bna_debugfs_root);
+ if (!bnad->port_debugfs_root) {
+ pr_warn("bna pci_dev %s: root dir creation failed\n",
+ pci_name(bnad->pcidev));
+ return;
+ }
+
+ atomic_inc(&bna_debugfs_port_count);
+
+ for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) {
+ file = &bnad_debugfs_files[i];
+ bnad->bnad_dentry_files[i] =
+ debugfs_create_file(file->name,
+ file->mode,
+ bnad->port_debugfs_root,
+ bnad,
+ file->fops);
+ if (!bnad->bnad_dentry_files[i]) {
+ pr_warn(
+ "BNA pci_dev:%s: create %s entry failed\n",
+ pci_name(bnad->pcidev), file->name);
+ return;
+ }
+ }
+ }
+}
+
+/* Uninitialize debugfs interface for BNA */
+void
+bnad_debugfs_uninit(struct bnad *bnad)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) {
+ if (bnad->bnad_dentry_files[i]) {
+ debugfs_remove(bnad->bnad_dentry_files[i]);
+ bnad->bnad_dentry_files[i] = NULL;
+ }
+ }
+
+ /* Remove the pci_dev debugfs directory for the port */
+ if (bnad->port_debugfs_root) {
+ debugfs_remove(bnad->port_debugfs_root);
+ bnad->port_debugfs_root = NULL;
+ atomic_dec(&bna_debugfs_port_count);
+ }
+
+ /* Remove the BNA debugfs root directory */
+ if (atomic_read(&bna_debugfs_port_count) == 0) {
+ debugfs_remove(bna_debugfs_root);
+ bna_debugfs_root = NULL;
+ }
+}
struct bfa_ioc_attr *ioc_attr;
unsigned long flags;
- strcpy(drvinfo->driver, BNAD_NAME);
- strcpy(drvinfo->version, BNAD_VERSION);
+ strlcpy(drvinfo->driver, BNAD_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, BNAD_VERSION, sizeof(drvinfo->version));
ioc_attr = kzalloc(sizeof(*ioc_attr), GFP_KERNEL);
if (ioc_attr) {
bfa_nw_ioc_get_attr(&bnad->bna.ioceth.ioc, ioc_attr);
spin_unlock_irqrestore(&bnad->bna_lock, flags);
- strncpy(drvinfo->fw_version, ioc_attr->adapter_attr.fw_ver,
- sizeof(drvinfo->fw_version) - 1);
+ strlcpy(drvinfo->fw_version, ioc_attr->adapter_attr.fw_ver,
+ sizeof(drvinfo->fw_version));
kfree(ioc_attr);
}
- strncpy(drvinfo->bus_info, pci_name(bnad->pcidev), ETHTOOL_BUSINFO_LEN);
+ strlcpy(drvinfo->bus_info, pci_name(bnad->pcidev),
+ sizeof(drvinfo->bus_info));
}
static void
}
}
+static u32
+bnad_get_flash_partition_by_offset(struct bnad *bnad, u32 offset,
+ u32 *base_offset)
+{
+ struct bfa_flash_attr *flash_attr;
+ struct bnad_iocmd_comp fcomp;
+ u32 i, flash_part = 0, ret;
+ unsigned long flags = 0;
+
+ flash_attr = kzalloc(sizeof(struct bfa_flash_attr), GFP_KERNEL);
+ if (!flash_attr)
+ return -ENOMEM;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_get_attr(&bnad->bna.flash, flash_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ kfree(flash_attr);
+ goto out_err;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+
+ /* Check for the flash type & base offset value */
+ if (ret == BFA_STATUS_OK) {
+ for (i = 0; i < flash_attr->npart; i++) {
+ if (offset >= flash_attr->part[i].part_off &&
+ offset < (flash_attr->part[i].part_off +
+ flash_attr->part[i].part_size)) {
+ flash_part = flash_attr->part[i].part_type;
+ *base_offset = flash_attr->part[i].part_off;
+ break;
+ }
+ }
+ }
+ kfree(flash_attr);
+ return flash_part;
+out_err:
+ return -EINVAL;
+}
+
+static int
+bnad_get_eeprom_len(struct net_device *netdev)
+{
+ return BFA_TOTAL_FLASH_SIZE;
+}
+
+static int
+bnad_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+ u8 *bytes)
+{
+ struct bnad *bnad = netdev_priv(netdev);
+ struct bnad_iocmd_comp fcomp;
+ u32 flash_part = 0, base_offset = 0;
+ unsigned long flags = 0;
+ int ret = 0;
+
+ /* Check if the flash read request is valid */
+ if (eeprom->magic != (bnad->pcidev->vendor |
+ (bnad->pcidev->device << 16)))
+ return -EFAULT;
+
+ /* Query the flash partition based on the offset */
+ flash_part = bnad_get_flash_partition_by_offset(bnad,
+ eeprom->offset, &base_offset);
+ if (flash_part <= 0)
+ return -EFAULT;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_read_part(&bnad->bna.flash, flash_part,
+ bnad->id, bytes, eeprom->len,
+ eeprom->offset - base_offset,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto done;
+ }
+
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+done:
+ return ret;
+}
+
+static int
+bnad_set_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+ u8 *bytes)
+{
+ struct bnad *bnad = netdev_priv(netdev);
+ struct bnad_iocmd_comp fcomp;
+ u32 flash_part = 0, base_offset = 0;
+ unsigned long flags = 0;
+ int ret = 0;
+
+ /* Check if the flash update request is valid */
+ if (eeprom->magic != (bnad->pcidev->vendor |
+ (bnad->pcidev->device << 16)))
+ return -EINVAL;
+
+ /* Query the flash partition based on the offset */
+ flash_part = bnad_get_flash_partition_by_offset(bnad,
+ eeprom->offset, &base_offset);
+ if (flash_part <= 0)
+ return -EFAULT;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_update_part(&bnad->bna.flash, flash_part,
+ bnad->id, bytes, eeprom->len,
+ eeprom->offset - base_offset,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto done;
+ }
+
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+done:
+ return ret;
+}
+
static struct ethtool_ops bnad_ethtool_ops = {
.get_settings = bnad_get_settings,
.set_settings = bnad_set_settings,
.set_pauseparam = bnad_set_pauseparam,
.get_strings = bnad_get_strings,
.get_ethtool_stats = bnad_get_ethtool_stats,
- .get_sset_count = bnad_get_sset_count
+ .get_sset_count = bnad_get_sset_count,
+ .get_eeprom_len = bnad_get_eeprom_len,
+ .get_eeprom = bnad_get_eeprom,
+ .set_eeprom = bnad_set_eeprom,
};
void
#pragma pack(1)
-#define MAC_ADDRLEN (6)
-typedef struct mac { u8 mac[MAC_ADDRLEN]; } mac_t;
+typedef struct mac { u8 mac[ETH_ALEN]; } mac_t;
#pragma pack()
config NET_ATMEL
bool "Atmel devices"
+ default y
depends on HAVE_NET_MACB || (ARM && ARCH_AT91RM9200)
---help---
If you have a network (Ethernet) card belonging to this class, say Y.
--- /dev/null
+config NET_CALXEDA_XGMAC
+ tristate "Calxeda 1G/10G XGMAC Ethernet driver"
+ depends on HAS_IOMEM
+ select CRC32
+ help
+ This is the driver for the XGMAC Ethernet IP block found on Calxeda
+ Highbank platforms.
--- /dev/null
+obj-$(CONFIG_NET_CALXEDA_XGMAC) += xgmac.o
--- /dev/null
+/*
+ * Copyright 2010-2011 Calxeda, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/circ_buf.h>
+#include <linux/interrupt.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <linux/ethtool.h>
+#include <linux/if.h>
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+
+/* XGMAC Register definitions */
+#define XGMAC_CONTROL 0x00000000 /* MAC Configuration */
+#define XGMAC_FRAME_FILTER 0x00000004 /* MAC Frame Filter */
+#define XGMAC_FLOW_CTRL 0x00000018 /* MAC Flow Control */
+#define XGMAC_VLAN_TAG 0x0000001C /* VLAN Tags */
+#define XGMAC_VERSION 0x00000020 /* Version */
+#define XGMAC_VLAN_INCL 0x00000024 /* VLAN tag for tx frames */
+#define XGMAC_LPI_CTRL 0x00000028 /* LPI Control and Status */
+#define XGMAC_LPI_TIMER 0x0000002C /* LPI Timers Control */
+#define XGMAC_TX_PACE 0x00000030 /* Transmit Pace and Stretch */
+#define XGMAC_VLAN_HASH 0x00000034 /* VLAN Hash Table */
+#define XGMAC_DEBUG 0x00000038 /* Debug */
+#define XGMAC_INT_STAT 0x0000003C /* Interrupt and Control */
+#define XGMAC_ADDR_HIGH(reg) (0x00000040 + ((reg) * 8))
+#define XGMAC_ADDR_LOW(reg) (0x00000044 + ((reg) * 8))
+#define XGMAC_HASH(n) (0x00000300 + (n) * 4) /* HASH table regs */
+#define XGMAC_NUM_HASH 16
+#define XGMAC_OMR 0x00000400
+#define XGMAC_REMOTE_WAKE 0x00000700 /* Remote Wake-Up Frm Filter */
+#define XGMAC_PMT 0x00000704 /* PMT Control and Status */
+#define XGMAC_MMC_CTRL 0x00000800 /* XGMAC MMC Control */
+#define XGMAC_MMC_INTR_RX 0x00000804 /* Recieve Interrupt */
+#define XGMAC_MMC_INTR_TX 0x00000808 /* Transmit Interrupt */
+#define XGMAC_MMC_INTR_MASK_RX 0x0000080c /* Recieve Interrupt Mask */
+#define XGMAC_MMC_INTR_MASK_TX 0x00000810 /* Transmit Interrupt Mask */
+
+/* Hardware TX Statistics Counters */
+#define XGMAC_MMC_TXOCTET_GB_LO 0x00000814
+#define XGMAC_MMC_TXOCTET_GB_HI 0x00000818
+#define XGMAC_MMC_TXFRAME_GB_LO 0x0000081C
+#define XGMAC_MMC_TXFRAME_GB_HI 0x00000820
+#define XGMAC_MMC_TXBCFRAME_G 0x00000824
+#define XGMAC_MMC_TXMCFRAME_G 0x0000082C
+#define XGMAC_MMC_TXUCFRAME_GB 0x00000864
+#define XGMAC_MMC_TXMCFRAME_GB 0x0000086C
+#define XGMAC_MMC_TXBCFRAME_GB 0x00000874
+#define XGMAC_MMC_TXUNDERFLOW 0x0000087C
+#define XGMAC_MMC_TXOCTET_G_LO 0x00000884
+#define XGMAC_MMC_TXOCTET_G_HI 0x00000888
+#define XGMAC_MMC_TXFRAME_G_LO 0x0000088C
+#define XGMAC_MMC_TXFRAME_G_HI 0x00000890
+#define XGMAC_MMC_TXPAUSEFRAME 0x00000894
+#define XGMAC_MMC_TXVLANFRAME 0x0000089C
+
+/* Hardware RX Statistics Counters */
+#define XGMAC_MMC_RXFRAME_GB_LO 0x00000900
+#define XGMAC_MMC_RXFRAME_GB_HI 0x00000904
+#define XGMAC_MMC_RXOCTET_GB_LO 0x00000908
+#define XGMAC_MMC_RXOCTET_GB_HI 0x0000090C
+#define XGMAC_MMC_RXOCTET_G_LO 0x00000910
+#define XGMAC_MMC_RXOCTET_G_HI 0x00000914
+#define XGMAC_MMC_RXBCFRAME_G 0x00000918
+#define XGMAC_MMC_RXMCFRAME_G 0x00000920
+#define XGMAC_MMC_RXCRCERR 0x00000928
+#define XGMAC_MMC_RXRUNT 0x00000930
+#define XGMAC_MMC_RXJABBER 0x00000934
+#define XGMAC_MMC_RXUCFRAME_G 0x00000970
+#define XGMAC_MMC_RXLENGTHERR 0x00000978
+#define XGMAC_MMC_RXPAUSEFRAME 0x00000988
+#define XGMAC_MMC_RXOVERFLOW 0x00000990
+#define XGMAC_MMC_RXVLANFRAME 0x00000998
+#define XGMAC_MMC_RXWATCHDOG 0x000009a0
+
+/* DMA Control and Status Registers */
+#define XGMAC_DMA_BUS_MODE 0x00000f00 /* Bus Mode */
+#define XGMAC_DMA_TX_POLL 0x00000f04 /* Transmit Poll Demand */
+#define XGMAC_DMA_RX_POLL 0x00000f08 /* Received Poll Demand */
+#define XGMAC_DMA_RX_BASE_ADDR 0x00000f0c /* Receive List Base */
+#define XGMAC_DMA_TX_BASE_ADDR 0x00000f10 /* Transmit List Base */
+#define XGMAC_DMA_STATUS 0x00000f14 /* Status Register */
+#define XGMAC_DMA_CONTROL 0x00000f18 /* Ctrl (Operational Mode) */
+#define XGMAC_DMA_INTR_ENA 0x00000f1c /* Interrupt Enable */
+#define XGMAC_DMA_MISS_FRAME_CTR 0x00000f20 /* Missed Frame Counter */
+#define XGMAC_DMA_RI_WDOG_TIMER 0x00000f24 /* RX Intr Watchdog Timer */
+#define XGMAC_DMA_AXI_BUS 0x00000f28 /* AXI Bus Mode */
+#define XGMAC_DMA_AXI_STATUS 0x00000f2C /* AXI Status */
+#define XGMAC_DMA_HW_FEATURE 0x00000f58 /* Enabled Hardware Features */
+
+#define XGMAC_ADDR_AE 0x80000000
+#define XGMAC_MAX_FILTER_ADDR 31
+
+/* PMT Control and Status */
+#define XGMAC_PMT_POINTER_RESET 0x80000000
+#define XGMAC_PMT_GLBL_UNICAST 0x00000200
+#define XGMAC_PMT_WAKEUP_RX_FRM 0x00000040
+#define XGMAC_PMT_MAGIC_PKT 0x00000020
+#define XGMAC_PMT_WAKEUP_FRM_EN 0x00000004
+#define XGMAC_PMT_MAGIC_PKT_EN 0x00000002
+#define XGMAC_PMT_POWERDOWN 0x00000001
+
+#define XGMAC_CONTROL_SPD 0x40000000 /* Speed control */
+#define XGMAC_CONTROL_SPD_MASK 0x60000000
+#define XGMAC_CONTROL_SPD_1G 0x60000000
+#define XGMAC_CONTROL_SPD_2_5G 0x40000000
+#define XGMAC_CONTROL_SPD_10G 0x00000000
+#define XGMAC_CONTROL_SARC 0x10000000 /* Source Addr Insert/Replace */
+#define XGMAC_CONTROL_SARK_MASK 0x18000000
+#define XGMAC_CONTROL_CAR 0x04000000 /* CRC Addition/Replacement */
+#define XGMAC_CONTROL_CAR_MASK 0x06000000
+#define XGMAC_CONTROL_DP 0x01000000 /* Disable Padding */
+#define XGMAC_CONTROL_WD 0x00800000 /* Disable Watchdog on rx */
+#define XGMAC_CONTROL_JD 0x00400000 /* Jabber disable */
+#define XGMAC_CONTROL_JE 0x00100000 /* Jumbo frame */
+#define XGMAC_CONTROL_LM 0x00001000 /* Loop-back mode */
+#define XGMAC_CONTROL_IPC 0x00000400 /* Checksum Offload */
+#define XGMAC_CONTROL_ACS 0x00000080 /* Automatic Pad/FCS Strip */
+#define XGMAC_CONTROL_DDIC 0x00000010 /* Disable Deficit Idle Count */
+#define XGMAC_CONTROL_TE 0x00000008 /* Transmitter Enable */
+#define XGMAC_CONTROL_RE 0x00000004 /* Receiver Enable */
+
+/* XGMAC Frame Filter defines */
+#define XGMAC_FRAME_FILTER_PR 0x00000001 /* Promiscuous Mode */
+#define XGMAC_FRAME_FILTER_HUC 0x00000002 /* Hash Unicast */
+#define XGMAC_FRAME_FILTER_HMC 0x00000004 /* Hash Multicast */
+#define XGMAC_FRAME_FILTER_DAIF 0x00000008 /* DA Inverse Filtering */
+#define XGMAC_FRAME_FILTER_PM 0x00000010 /* Pass all multicast */
+#define XGMAC_FRAME_FILTER_DBF 0x00000020 /* Disable Broadcast frames */
+#define XGMAC_FRAME_FILTER_SAIF 0x00000100 /* Inverse Filtering */
+#define XGMAC_FRAME_FILTER_SAF 0x00000200 /* Source Address Filter */
+#define XGMAC_FRAME_FILTER_HPF 0x00000400 /* Hash or perfect Filter */
+#define XGMAC_FRAME_FILTER_VHF 0x00000800 /* VLAN Hash Filter */
+#define XGMAC_FRAME_FILTER_VPF 0x00001000 /* VLAN Perfect Filter */
+#define XGMAC_FRAME_FILTER_RA 0x80000000 /* Receive all mode */
+
+/* XGMAC FLOW CTRL defines */
+#define XGMAC_FLOW_CTRL_PT_MASK 0xffff0000 /* Pause Time Mask */
+#define XGMAC_FLOW_CTRL_PT_SHIFT 16
+#define XGMAC_FLOW_CTRL_DZQP 0x00000080 /* Disable Zero-Quanta Phase */
+#define XGMAC_FLOW_CTRL_PLT 0x00000020 /* Pause Low Threshhold */
+#define XGMAC_FLOW_CTRL_PLT_MASK 0x00000030 /* PLT MASK */
+#define XGMAC_FLOW_CTRL_UP 0x00000008 /* Unicast Pause Frame Detect */
+#define XGMAC_FLOW_CTRL_RFE 0x00000004 /* Rx Flow Control Enable */
+#define XGMAC_FLOW_CTRL_TFE 0x00000002 /* Tx Flow Control Enable */
+#define XGMAC_FLOW_CTRL_FCB_BPA 0x00000001 /* Flow Control Busy ... */
+
+/* XGMAC_INT_STAT reg */
+#define XGMAC_INT_STAT_PMT 0x0080 /* PMT Interrupt Status */
+#define XGMAC_INT_STAT_LPI 0x0040 /* LPI Interrupt Status */
+
+/* DMA Bus Mode register defines */
+#define DMA_BUS_MODE_SFT_RESET 0x00000001 /* Software Reset */
+#define DMA_BUS_MODE_DSL_MASK 0x0000007c /* Descriptor Skip Length */
+#define DMA_BUS_MODE_DSL_SHIFT 2 /* (in DWORDS) */
+#define DMA_BUS_MODE_ATDS 0x00000080 /* Alternate Descriptor Size */
+
+/* Programmable burst length */
+#define DMA_BUS_MODE_PBL_MASK 0x00003f00 /* Programmable Burst Len */
+#define DMA_BUS_MODE_PBL_SHIFT 8
+#define DMA_BUS_MODE_FB 0x00010000 /* Fixed burst */
+#define DMA_BUS_MODE_RPBL_MASK 0x003e0000 /* Rx-Programmable Burst Len */
+#define DMA_BUS_MODE_RPBL_SHIFT 17
+#define DMA_BUS_MODE_USP 0x00800000
+#define DMA_BUS_MODE_8PBL 0x01000000
+#define DMA_BUS_MODE_AAL 0x02000000
+
+/* DMA Bus Mode register defines */
+#define DMA_BUS_PR_RATIO_MASK 0x0000c000 /* Rx/Tx priority ratio */
+#define DMA_BUS_PR_RATIO_SHIFT 14
+#define DMA_BUS_FB 0x00010000 /* Fixed Burst */
+
+/* DMA Control register defines */
+#define DMA_CONTROL_ST 0x00002000 /* Start/Stop Transmission */
+#define DMA_CONTROL_SR 0x00000002 /* Start/Stop Receive */
+#define DMA_CONTROL_DFF 0x01000000 /* Disable flush of rx frames */
+
+/* DMA Normal interrupt */
+#define DMA_INTR_ENA_NIE 0x00010000 /* Normal Summary */
+#define DMA_INTR_ENA_AIE 0x00008000 /* Abnormal Summary */
+#define DMA_INTR_ENA_ERE 0x00004000 /* Early Receive */
+#define DMA_INTR_ENA_FBE 0x00002000 /* Fatal Bus Error */
+#define DMA_INTR_ENA_ETE 0x00000400 /* Early Transmit */
+#define DMA_INTR_ENA_RWE 0x00000200 /* Receive Watchdog */
+#define DMA_INTR_ENA_RSE 0x00000100 /* Receive Stopped */
+#define DMA_INTR_ENA_RUE 0x00000080 /* Receive Buffer Unavailable */
+#define DMA_INTR_ENA_RIE 0x00000040 /* Receive Interrupt */
+#define DMA_INTR_ENA_UNE 0x00000020 /* Tx Underflow */
+#define DMA_INTR_ENA_OVE 0x00000010 /* Receive Overflow */
+#define DMA_INTR_ENA_TJE 0x00000008 /* Transmit Jabber */
+#define DMA_INTR_ENA_TUE 0x00000004 /* Transmit Buffer Unavail */
+#define DMA_INTR_ENA_TSE 0x00000002 /* Transmit Stopped */
+#define DMA_INTR_ENA_TIE 0x00000001 /* Transmit Interrupt */
+
+#define DMA_INTR_NORMAL (DMA_INTR_ENA_NIE | DMA_INTR_ENA_RIE | \
+ DMA_INTR_ENA_TUE)
+
+#define DMA_INTR_ABNORMAL (DMA_INTR_ENA_AIE | DMA_INTR_ENA_FBE | \
+ DMA_INTR_ENA_RWE | DMA_INTR_ENA_RSE | \
+ DMA_INTR_ENA_RUE | DMA_INTR_ENA_UNE | \
+ DMA_INTR_ENA_OVE | DMA_INTR_ENA_TJE | \
+ DMA_INTR_ENA_TSE)
+
+/* DMA default interrupt mask */
+#define DMA_INTR_DEFAULT_MASK (DMA_INTR_NORMAL | DMA_INTR_ABNORMAL)
+
+/* DMA Status register defines */
+#define DMA_STATUS_GMI 0x08000000 /* MMC interrupt */
+#define DMA_STATUS_GLI 0x04000000 /* GMAC Line interface int */
+#define DMA_STATUS_EB_MASK 0x00380000 /* Error Bits Mask */
+#define DMA_STATUS_EB_TX_ABORT 0x00080000 /* Error Bits - TX Abort */
+#define DMA_STATUS_EB_RX_ABORT 0x00100000 /* Error Bits - RX Abort */
+#define DMA_STATUS_TS_MASK 0x00700000 /* Transmit Process State */
+#define DMA_STATUS_TS_SHIFT 20
+#define DMA_STATUS_RS_MASK 0x000e0000 /* Receive Process State */
+#define DMA_STATUS_RS_SHIFT 17
+#define DMA_STATUS_NIS 0x00010000 /* Normal Interrupt Summary */
+#define DMA_STATUS_AIS 0x00008000 /* Abnormal Interrupt Summary */
+#define DMA_STATUS_ERI 0x00004000 /* Early Receive Interrupt */
+#define DMA_STATUS_FBI 0x00002000 /* Fatal Bus Error Interrupt */
+#define DMA_STATUS_ETI 0x00000400 /* Early Transmit Interrupt */
+#define DMA_STATUS_RWT 0x00000200 /* Receive Watchdog Timeout */
+#define DMA_STATUS_RPS 0x00000100 /* Receive Process Stopped */
+#define DMA_STATUS_RU 0x00000080 /* Receive Buffer Unavailable */
+#define DMA_STATUS_RI 0x00000040 /* Receive Interrupt */
+#define DMA_STATUS_UNF 0x00000020 /* Transmit Underflow */
+#define DMA_STATUS_OVF 0x00000010 /* Receive Overflow */
+#define DMA_STATUS_TJT 0x00000008 /* Transmit Jabber Timeout */
+#define DMA_STATUS_TU 0x00000004 /* Transmit Buffer Unavail */
+#define DMA_STATUS_TPS 0x00000002 /* Transmit Process Stopped */
+#define DMA_STATUS_TI 0x00000001 /* Transmit Interrupt */
+
+/* Common MAC defines */
+#define MAC_ENABLE_TX 0x00000008 /* Transmitter Enable */
+#define MAC_ENABLE_RX 0x00000004 /* Receiver Enable */
+
+/* XGMAC Operation Mode Register */
+#define XGMAC_OMR_TSF 0x00200000 /* TX FIFO Store and Forward */
+#define XGMAC_OMR_FTF 0x00100000 /* Flush Transmit FIFO */
+#define XGMAC_OMR_TTC 0x00020000 /* Transmit Threshhold Ctrl */
+#define XGMAC_OMR_TTC_MASK 0x00030000
+#define XGMAC_OMR_RFD 0x00006000 /* FC Deactivation Threshhold */
+#define XGMAC_OMR_RFD_MASK 0x00007000 /* FC Deact Threshhold MASK */
+#define XGMAC_OMR_RFA 0x00000600 /* FC Activation Threshhold */
+#define XGMAC_OMR_RFA_MASK 0x00000E00 /* FC Act Threshhold MASK */
+#define XGMAC_OMR_EFC 0x00000100 /* Enable Hardware FC */
+#define XGMAC_OMR_FEF 0x00000080 /* Forward Error Frames */
+#define XGMAC_OMR_DT 0x00000040 /* Drop TCP/IP csum Errors */
+#define XGMAC_OMR_RSF 0x00000020 /* RX FIFO Store and Forward */
+#define XGMAC_OMR_RTC 0x00000010 /* RX Threshhold Ctrl */
+#define XGMAC_OMR_RTC_MASK 0x00000018 /* RX Threshhold Ctrl MASK */
+
+/* XGMAC HW Features Register */
+#define DMA_HW_FEAT_TXCOESEL 0x00010000 /* TX Checksum offload */
+
+#define XGMAC_MMC_CTRL_CNT_FRZ 0x00000008
+
+/* XGMAC Descriptor Defines */
+#define MAX_DESC_BUF_SZ (0x2000 - 8)
+
+#define RXDESC_EXT_STATUS 0x00000001
+#define RXDESC_CRC_ERR 0x00000002
+#define RXDESC_RX_ERR 0x00000008
+#define RXDESC_RX_WDOG 0x00000010
+#define RXDESC_FRAME_TYPE 0x00000020
+#define RXDESC_GIANT_FRAME 0x00000080
+#define RXDESC_LAST_SEG 0x00000100
+#define RXDESC_FIRST_SEG 0x00000200
+#define RXDESC_VLAN_FRAME 0x00000400
+#define RXDESC_OVERFLOW_ERR 0x00000800
+#define RXDESC_LENGTH_ERR 0x00001000
+#define RXDESC_SA_FILTER_FAIL 0x00002000
+#define RXDESC_DESCRIPTOR_ERR 0x00004000
+#define RXDESC_ERROR_SUMMARY 0x00008000
+#define RXDESC_FRAME_LEN_OFFSET 16
+#define RXDESC_FRAME_LEN_MASK 0x3fff0000
+#define RXDESC_DA_FILTER_FAIL 0x40000000
+
+#define RXDESC1_END_RING 0x00008000
+
+#define RXDESC_IP_PAYLOAD_MASK 0x00000003
+#define RXDESC_IP_PAYLOAD_UDP 0x00000001
+#define RXDESC_IP_PAYLOAD_TCP 0x00000002
+#define RXDESC_IP_PAYLOAD_ICMP 0x00000003
+#define RXDESC_IP_HEADER_ERR 0x00000008
+#define RXDESC_IP_PAYLOAD_ERR 0x00000010
+#define RXDESC_IPV4_PACKET 0x00000040
+#define RXDESC_IPV6_PACKET 0x00000080
+#define TXDESC_UNDERFLOW_ERR 0x00000001
+#define TXDESC_JABBER_TIMEOUT 0x00000002
+#define TXDESC_LOCAL_FAULT 0x00000004
+#define TXDESC_REMOTE_FAULT 0x00000008
+#define TXDESC_VLAN_FRAME 0x00000010
+#define TXDESC_FRAME_FLUSHED 0x00000020
+#define TXDESC_IP_HEADER_ERR 0x00000040
+#define TXDESC_PAYLOAD_CSUM_ERR 0x00000080
+#define TXDESC_ERROR_SUMMARY 0x00008000
+#define TXDESC_SA_CTRL_INSERT 0x00040000
+#define TXDESC_SA_CTRL_REPLACE 0x00080000
+#define TXDESC_2ND_ADDR_CHAINED 0x00100000
+#define TXDESC_END_RING 0x00200000
+#define TXDESC_CSUM_IP 0x00400000
+#define TXDESC_CSUM_IP_PAYLD 0x00800000
+#define TXDESC_CSUM_ALL 0x00C00000
+#define TXDESC_CRC_EN_REPLACE 0x01000000
+#define TXDESC_CRC_EN_APPEND 0x02000000
+#define TXDESC_DISABLE_PAD 0x04000000
+#define TXDESC_FIRST_SEG 0x10000000
+#define TXDESC_LAST_SEG 0x20000000
+#define TXDESC_INTERRUPT 0x40000000
+
+#define DESC_OWN 0x80000000
+#define DESC_BUFFER1_SZ_MASK 0x00001fff
+#define DESC_BUFFER2_SZ_MASK 0x1fff0000
+#define DESC_BUFFER2_SZ_OFFSET 16
+
+struct xgmac_dma_desc {
+ __le32 flags;
+ __le32 buf_size;
+ __le32 buf1_addr; /* Buffer 1 Address Pointer */
+ __le32 buf2_addr; /* Buffer 2 Address Pointer */
+ __le32 ext_status;
+ __le32 res[3];
+};
+
+struct xgmac_extra_stats {
+ /* Transmit errors */
+ unsigned long tx_jabber;
+ unsigned long tx_frame_flushed;
+ unsigned long tx_payload_error;
+ unsigned long tx_ip_header_error;
+ unsigned long tx_local_fault;
+ unsigned long tx_remote_fault;
+ /* Receive errors */
+ unsigned long rx_watchdog;
+ unsigned long rx_da_filter_fail;
+ unsigned long rx_sa_filter_fail;
+ unsigned long rx_payload_error;
+ unsigned long rx_ip_header_error;
+ /* Tx/Rx IRQ errors */
+ unsigned long tx_undeflow;
+ unsigned long tx_process_stopped;
+ unsigned long rx_buf_unav;
+ unsigned long rx_process_stopped;
+ unsigned long tx_early;
+ unsigned long fatal_bus_error;
+};
+
+struct xgmac_priv {
+ struct xgmac_dma_desc *dma_rx;
+ struct sk_buff **rx_skbuff;
+ unsigned int rx_tail;
+ unsigned int rx_head;
+
+ struct xgmac_dma_desc *dma_tx;
+ struct sk_buff **tx_skbuff;
+ unsigned int tx_head;
+ unsigned int tx_tail;
+
+ void __iomem *base;
+ struct sk_buff_head rx_recycle;
+ unsigned int dma_buf_sz;
+ dma_addr_t dma_rx_phy;
+ dma_addr_t dma_tx_phy;
+
+ struct net_device *dev;
+ struct device *device;
+ struct napi_struct napi;
+
+ struct xgmac_extra_stats xstats;
+
+ spinlock_t stats_lock;
+ int pmt_irq;
+ char rx_pause;
+ char tx_pause;
+ int wolopts;
+};
+
+/* XGMAC Configuration Settings */
+#define MAX_MTU 9000
+#define PAUSE_TIME 0x400
+
+#define DMA_RX_RING_SZ 256
+#define DMA_TX_RING_SZ 128
+/* minimum number of free TX descriptors required to wake up TX process */
+#define TX_THRESH (DMA_TX_RING_SZ/4)
+
+/* DMA descriptor ring helpers */
+#define dma_ring_incr(n, s) (((n) + 1) & ((s) - 1))
+#define dma_ring_space(h, t, s) CIRC_SPACE(h, t, s)
+#define dma_ring_cnt(h, t, s) CIRC_CNT(h, t, s)
+
+/* XGMAC Descriptor Access Helpers */
+static inline void desc_set_buf_len(struct xgmac_dma_desc *p, u32 buf_sz)
+{
+ if (buf_sz > MAX_DESC_BUF_SZ)
+ p->buf_size = cpu_to_le32(MAX_DESC_BUF_SZ |
+ (buf_sz - MAX_DESC_BUF_SZ) << DESC_BUFFER2_SZ_OFFSET);
+ else
+ p->buf_size = cpu_to_le32(buf_sz);
+}
+
+static inline int desc_get_buf_len(struct xgmac_dma_desc *p)
+{
+ u32 len = cpu_to_le32(p->flags);
+ return (len & DESC_BUFFER1_SZ_MASK) +
+ ((len & DESC_BUFFER2_SZ_MASK) >> DESC_BUFFER2_SZ_OFFSET);
+}
+
+static inline void desc_init_rx_desc(struct xgmac_dma_desc *p, int ring_size,
+ int buf_sz)
+{
+ struct xgmac_dma_desc *end = p + ring_size - 1;
+
+ memset(p, 0, sizeof(*p) * ring_size);
+
+ for (; p <= end; p++)
+ desc_set_buf_len(p, buf_sz);
+
+ end->buf_size |= cpu_to_le32(RXDESC1_END_RING);
+}
+
+static inline void desc_init_tx_desc(struct xgmac_dma_desc *p, u32 ring_size)
+{
+ memset(p, 0, sizeof(*p) * ring_size);
+ p[ring_size - 1].flags = cpu_to_le32(TXDESC_END_RING);
+}
+
+static inline int desc_get_owner(struct xgmac_dma_desc *p)
+{
+ return le32_to_cpu(p->flags) & DESC_OWN;
+}
+
+static inline void desc_set_rx_owner(struct xgmac_dma_desc *p)
+{
+ /* Clear all fields and set the owner */
+ p->flags = cpu_to_le32(DESC_OWN);
+}
+
+static inline void desc_set_tx_owner(struct xgmac_dma_desc *p, u32 flags)
+{
+ u32 tmpflags = le32_to_cpu(p->flags);
+ tmpflags &= TXDESC_END_RING;
+ tmpflags |= flags | DESC_OWN;
+ p->flags = cpu_to_le32(tmpflags);
+}
+
+static inline int desc_get_tx_ls(struct xgmac_dma_desc *p)
+{
+ return le32_to_cpu(p->flags) & TXDESC_LAST_SEG;
+}
+
+static inline u32 desc_get_buf_addr(struct xgmac_dma_desc *p)
+{
+ return le32_to_cpu(p->buf1_addr);
+}
+
+static inline void desc_set_buf_addr(struct xgmac_dma_desc *p,
+ u32 paddr, int len)
+{
+ p->buf1_addr = cpu_to_le32(paddr);
+ if (len > MAX_DESC_BUF_SZ)
+ p->buf2_addr = cpu_to_le32(paddr + MAX_DESC_BUF_SZ);
+}
+
+static inline void desc_set_buf_addr_and_size(struct xgmac_dma_desc *p,
+ u32 paddr, int len)
+{
+ desc_set_buf_len(p, len);
+ desc_set_buf_addr(p, paddr, len);
+}
+
+static inline int desc_get_rx_frame_len(struct xgmac_dma_desc *p)
+{
+ u32 data = le32_to_cpu(p->flags);
+ u32 len = (data & RXDESC_FRAME_LEN_MASK) >> RXDESC_FRAME_LEN_OFFSET;
+ if (data & RXDESC_FRAME_TYPE)
+ len -= ETH_FCS_LEN;
+
+ return len;
+}
+
+static void xgmac_dma_flush_tx_fifo(void __iomem *ioaddr)
+{
+ int timeout = 1000;
+ u32 reg = readl(ioaddr + XGMAC_OMR);
+ writel(reg | XGMAC_OMR_FTF, ioaddr + XGMAC_OMR);
+
+ while ((timeout-- > 0) && readl(ioaddr + XGMAC_OMR) & XGMAC_OMR_FTF)
+ udelay(1);
+}
+
+static int desc_get_tx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p)
+{
+ struct xgmac_extra_stats *x = &priv->xstats;
+ u32 status = le32_to_cpu(p->flags);
+
+ if (!(status & TXDESC_ERROR_SUMMARY))
+ return 0;
+
+ netdev_dbg(priv->dev, "tx desc error = 0x%08x\n", status);
+ if (status & TXDESC_JABBER_TIMEOUT)
+ x->tx_jabber++;
+ if (status & TXDESC_FRAME_FLUSHED)
+ x->tx_frame_flushed++;
+ if (status & TXDESC_UNDERFLOW_ERR)
+ xgmac_dma_flush_tx_fifo(priv->base);
+ if (status & TXDESC_IP_HEADER_ERR)
+ x->tx_ip_header_error++;
+ if (status & TXDESC_LOCAL_FAULT)
+ x->tx_local_fault++;
+ if (status & TXDESC_REMOTE_FAULT)
+ x->tx_remote_fault++;
+ if (status & TXDESC_PAYLOAD_CSUM_ERR)
+ x->tx_payload_error++;
+
+ return -1;
+}
+
+static int desc_get_rx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p)
+{
+ struct xgmac_extra_stats *x = &priv->xstats;
+ int ret = CHECKSUM_UNNECESSARY;
+ u32 status = le32_to_cpu(p->flags);
+ u32 ext_status = le32_to_cpu(p->ext_status);
+
+ if (status & RXDESC_DA_FILTER_FAIL) {
+ netdev_dbg(priv->dev, "XGMAC RX : Dest Address filter fail\n");
+ x->rx_da_filter_fail++;
+ return -1;
+ }
+
+ /* Check if packet has checksum already */
+ if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) &&
+ !(ext_status & RXDESC_IP_PAYLOAD_MASK))
+ ret = CHECKSUM_NONE;
+
+ netdev_dbg(priv->dev, "rx status - frame type=%d, csum = %d, ext stat %08x\n",
+ (status & RXDESC_FRAME_TYPE) ? 1 : 0, ret, ext_status);
+
+ if (!(status & RXDESC_ERROR_SUMMARY))
+ return ret;
+
+ /* Handle any errors */
+ if (status & (RXDESC_DESCRIPTOR_ERR | RXDESC_OVERFLOW_ERR |
+ RXDESC_GIANT_FRAME | RXDESC_LENGTH_ERR | RXDESC_CRC_ERR))
+ return -1;
+
+ if (status & RXDESC_EXT_STATUS) {
+ if (ext_status & RXDESC_IP_HEADER_ERR)
+ x->rx_ip_header_error++;
+ if (ext_status & RXDESC_IP_PAYLOAD_ERR)
+ x->rx_payload_error++;
+ netdev_dbg(priv->dev, "IP checksum error - stat %08x\n",
+ ext_status);
+ return CHECKSUM_NONE;
+ }
+
+ return ret;
+}
+
+static inline void xgmac_mac_enable(void __iomem *ioaddr)
+{
+ u32 value = readl(ioaddr + XGMAC_CONTROL);
+ value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
+ writel(value, ioaddr + XGMAC_CONTROL);
+
+ value = readl(ioaddr + XGMAC_DMA_CONTROL);
+ value |= DMA_CONTROL_ST | DMA_CONTROL_SR;
+ writel(value, ioaddr + XGMAC_DMA_CONTROL);
+}
+
+static inline void xgmac_mac_disable(void __iomem *ioaddr)
+{
+ u32 value = readl(ioaddr + XGMAC_DMA_CONTROL);
+ value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
+ writel(value, ioaddr + XGMAC_DMA_CONTROL);
+
+ value = readl(ioaddr + XGMAC_CONTROL);
+ value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
+ writel(value, ioaddr + XGMAC_CONTROL);
+}
+
+static void xgmac_set_mac_addr(void __iomem *ioaddr, unsigned char *addr,
+ int num)
+{
+ u32 data;
+
+ data = (addr[5] << 8) | addr[4] | (num ? XGMAC_ADDR_AE : 0);
+ writel(data, ioaddr + XGMAC_ADDR_HIGH(num));
+ data = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+ writel(data, ioaddr + XGMAC_ADDR_LOW(num));
+}
+
+static void xgmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
+ int num)
+{
+ u32 hi_addr, lo_addr;
+
+ /* Read the MAC address from the hardware */
+ hi_addr = readl(ioaddr + XGMAC_ADDR_HIGH(num));
+ lo_addr = readl(ioaddr + XGMAC_ADDR_LOW(num));
+
+ /* Extract the MAC address from the high and low words */
+ addr[0] = lo_addr & 0xff;
+ addr[1] = (lo_addr >> 8) & 0xff;
+ addr[2] = (lo_addr >> 16) & 0xff;
+ addr[3] = (lo_addr >> 24) & 0xff;
+ addr[4] = hi_addr & 0xff;
+ addr[5] = (hi_addr >> 8) & 0xff;
+}
+
+static int xgmac_set_flow_ctrl(struct xgmac_priv *priv, int rx, int tx)
+{
+ u32 reg;
+ unsigned int flow = 0;
+
+ priv->rx_pause = rx;
+ priv->tx_pause = tx;
+
+ if (rx || tx) {
+ if (rx)
+ flow |= XGMAC_FLOW_CTRL_RFE;
+ if (tx)
+ flow |= XGMAC_FLOW_CTRL_TFE;
+
+ flow |= XGMAC_FLOW_CTRL_PLT | XGMAC_FLOW_CTRL_UP;
+ flow |= (PAUSE_TIME << XGMAC_FLOW_CTRL_PT_SHIFT);
+
+ writel(flow, priv->base + XGMAC_FLOW_CTRL);
+
+ reg = readl(priv->base + XGMAC_OMR);
+ reg |= XGMAC_OMR_EFC;
+ writel(reg, priv->base + XGMAC_OMR);
+ } else {
+ writel(0, priv->base + XGMAC_FLOW_CTRL);
+
+ reg = readl(priv->base + XGMAC_OMR);
+ reg &= ~XGMAC_OMR_EFC;
+ writel(reg, priv->base + XGMAC_OMR);
+ }
+
+ return 0;
+}
+
+static void xgmac_rx_refill(struct xgmac_priv *priv)
+{
+ struct xgmac_dma_desc *p;
+ dma_addr_t paddr;
+
+ while (dma_ring_space(priv->rx_head, priv->rx_tail, DMA_RX_RING_SZ) > 1) {
+ int entry = priv->rx_head;
+ struct sk_buff *skb;
+
+ p = priv->dma_rx + entry;
+
+ if (priv->rx_skbuff[entry] != NULL)
+ continue;
+
+ skb = __skb_dequeue(&priv->rx_recycle);
+ if (skb == NULL)
+ skb = netdev_alloc_skb(priv->dev, priv->dma_buf_sz);
+ if (unlikely(skb == NULL))
+ break;
+
+ priv->rx_skbuff[entry] = skb;
+ paddr = dma_map_single(priv->device, skb->data,
+ priv->dma_buf_sz, DMA_FROM_DEVICE);
+ desc_set_buf_addr(p, paddr, priv->dma_buf_sz);
+
+ netdev_dbg(priv->dev, "rx ring: head %d, tail %d\n",
+ priv->rx_head, priv->rx_tail);
+
+ priv->rx_head = dma_ring_incr(priv->rx_head, DMA_RX_RING_SZ);
+ /* Ensure descriptor is in memory before handing to h/w */
+ wmb();
+ desc_set_rx_owner(p);
+ }
+}
+
+/**
+ * init_xgmac_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * Description: this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers.
+ */
+static int xgmac_dma_desc_rings_init(struct net_device *dev)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ unsigned int bfsize;
+
+ /* Set the Buffer size according to the MTU;
+ * indeed, in case of jumbo we need to bump-up the buffer sizes.
+ */
+ bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN + 64,
+ 64);
+
+ netdev_dbg(priv->dev, "mtu [%d] bfsize [%d]\n", dev->mtu, bfsize);
+
+ priv->rx_skbuff = kzalloc(sizeof(struct sk_buff *) * DMA_RX_RING_SZ,
+ GFP_KERNEL);
+ if (!priv->rx_skbuff)
+ return -ENOMEM;
+
+ priv->dma_rx = dma_alloc_coherent(priv->device,
+ DMA_RX_RING_SZ *
+ sizeof(struct xgmac_dma_desc),
+ &priv->dma_rx_phy,
+ GFP_KERNEL);
+ if (!priv->dma_rx)
+ goto err_dma_rx;
+
+ priv->tx_skbuff = kzalloc(sizeof(struct sk_buff *) * DMA_TX_RING_SZ,
+ GFP_KERNEL);
+ if (!priv->tx_skbuff)
+ goto err_tx_skb;
+
+ priv->dma_tx = dma_alloc_coherent(priv->device,
+ DMA_TX_RING_SZ *
+ sizeof(struct xgmac_dma_desc),
+ &priv->dma_tx_phy,
+ GFP_KERNEL);
+ if (!priv->dma_tx)
+ goto err_dma_tx;
+
+ netdev_dbg(priv->dev, "DMA desc rings: virt addr (Rx %p, "
+ "Tx %p)\n\tDMA phy addr (Rx 0x%08x, Tx 0x%08x)\n",
+ priv->dma_rx, priv->dma_tx,
+ (unsigned int)priv->dma_rx_phy, (unsigned int)priv->dma_tx_phy);
+
+ priv->rx_tail = 0;
+ priv->rx_head = 0;
+ priv->dma_buf_sz = bfsize;
+ desc_init_rx_desc(priv->dma_rx, DMA_RX_RING_SZ, priv->dma_buf_sz);
+ xgmac_rx_refill(priv);
+
+ priv->tx_tail = 0;
+ priv->tx_head = 0;
+ desc_init_tx_desc(priv->dma_tx, DMA_TX_RING_SZ);
+
+ writel(priv->dma_tx_phy, priv->base + XGMAC_DMA_TX_BASE_ADDR);
+ writel(priv->dma_rx_phy, priv->base + XGMAC_DMA_RX_BASE_ADDR);
+
+ return 0;
+
+err_dma_tx:
+ kfree(priv->tx_skbuff);
+err_tx_skb:
+ dma_free_coherent(priv->device,
+ DMA_RX_RING_SZ * sizeof(struct xgmac_dma_desc),
+ priv->dma_rx, priv->dma_rx_phy);
+err_dma_rx:
+ kfree(priv->rx_skbuff);
+ return -ENOMEM;
+}
+
+static void xgmac_free_rx_skbufs(struct xgmac_priv *priv)
+{
+ int i;
+ struct xgmac_dma_desc *p;
+
+ if (!priv->rx_skbuff)
+ return;
+
+ for (i = 0; i < DMA_RX_RING_SZ; i++) {
+ if (priv->rx_skbuff[i] == NULL)
+ continue;
+
+ p = priv->dma_rx + i;
+ dma_unmap_single(priv->device, desc_get_buf_addr(p),
+ priv->dma_buf_sz, DMA_FROM_DEVICE);
+ dev_kfree_skb_any(priv->rx_skbuff[i]);
+ priv->rx_skbuff[i] = NULL;
+ }
+}
+
+static void xgmac_free_tx_skbufs(struct xgmac_priv *priv)
+{
+ int i, f;
+ struct xgmac_dma_desc *p;
+
+ if (!priv->tx_skbuff)
+ return;
+
+ for (i = 0; i < DMA_TX_RING_SZ; i++) {
+ if (priv->tx_skbuff[i] == NULL)
+ continue;
+
+ p = priv->dma_tx + i;
+ dma_unmap_single(priv->device, desc_get_buf_addr(p),
+ desc_get_buf_len(p), DMA_TO_DEVICE);
+
+ for (f = 0; f < skb_shinfo(priv->tx_skbuff[i])->nr_frags; f++) {
+ p = priv->dma_tx + i++;
+ dma_unmap_page(priv->device, desc_get_buf_addr(p),
+ desc_get_buf_len(p), DMA_TO_DEVICE);
+ }
+
+ dev_kfree_skb_any(priv->tx_skbuff[i]);
+ priv->tx_skbuff[i] = NULL;
+ }
+}
+
+static void xgmac_free_dma_desc_rings(struct xgmac_priv *priv)
+{
+ /* Release the DMA TX/RX socket buffers */
+ xgmac_free_rx_skbufs(priv);
+ xgmac_free_tx_skbufs(priv);
+
+ /* Free the consistent memory allocated for descriptor rings */
+ if (priv->dma_tx) {
+ dma_free_coherent(priv->device,
+ DMA_TX_RING_SZ * sizeof(struct xgmac_dma_desc),
+ priv->dma_tx, priv->dma_tx_phy);
+ priv->dma_tx = NULL;
+ }
+ if (priv->dma_rx) {
+ dma_free_coherent(priv->device,
+ DMA_RX_RING_SZ * sizeof(struct xgmac_dma_desc),
+ priv->dma_rx, priv->dma_rx_phy);
+ priv->dma_rx = NULL;
+ }
+ kfree(priv->rx_skbuff);
+ priv->rx_skbuff = NULL;
+ kfree(priv->tx_skbuff);
+ priv->tx_skbuff = NULL;
+}
+
+/**
+ * xgmac_tx:
+ * @priv: private driver structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void xgmac_tx_complete(struct xgmac_priv *priv)
+{
+ int i;
+ void __iomem *ioaddr = priv->base;
+
+ writel(DMA_STATUS_TU | DMA_STATUS_NIS, ioaddr + XGMAC_DMA_STATUS);
+
+ while (dma_ring_cnt(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ)) {
+ unsigned int entry = priv->tx_tail;
+ struct sk_buff *skb = priv->tx_skbuff[entry];
+ struct xgmac_dma_desc *p = priv->dma_tx + entry;
+
+ /* Check if the descriptor is owned by the DMA. */
+ if (desc_get_owner(p))
+ break;
+
+ /* Verify tx error by looking at the last segment */
+ if (desc_get_tx_ls(p))
+ desc_get_tx_status(priv, p);
+
+ netdev_dbg(priv->dev, "tx ring: curr %d, dirty %d\n",
+ priv->tx_head, priv->tx_tail);
+
+ dma_unmap_single(priv->device, desc_get_buf_addr(p),
+ desc_get_buf_len(p), DMA_TO_DEVICE);
+
+ priv->tx_skbuff[entry] = NULL;
+ priv->tx_tail = dma_ring_incr(entry, DMA_TX_RING_SZ);
+
+ if (!skb) {
+ continue;
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ entry = priv->tx_tail = dma_ring_incr(priv->tx_tail,
+ DMA_TX_RING_SZ);
+ p = priv->dma_tx + priv->tx_tail;
+
+ dma_unmap_page(priv->device, desc_get_buf_addr(p),
+ desc_get_buf_len(p), DMA_TO_DEVICE);
+ }
+
+ /*
+ * If there's room in the queue (limit it to size)
+ * we add this skb back into the pool,
+ * if it's the right size.
+ */
+ if ((skb_queue_len(&priv->rx_recycle) <
+ DMA_RX_RING_SZ) &&
+ skb_recycle_check(skb, priv->dma_buf_sz))
+ __skb_queue_head(&priv->rx_recycle, skb);
+ else
+ dev_kfree_skb(skb);
+ }
+
+ if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) >
+ TX_THRESH)
+ netif_wake_queue(priv->dev);
+}
+
+/**
+ * xgmac_tx_err:
+ * @priv: pointer to the private device structure
+ * Description: it cleans the descriptors and restarts the transmission
+ * in case of errors.
+ */
+static void xgmac_tx_err(struct xgmac_priv *priv)
+{
+ u32 reg, value, inten;
+
+ netif_stop_queue(priv->dev);
+
+ inten = readl(priv->base + XGMAC_DMA_INTR_ENA);
+ writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+
+ reg = readl(priv->base + XGMAC_DMA_CONTROL);
+ writel(reg & ~DMA_CONTROL_ST, priv->base + XGMAC_DMA_CONTROL);
+ do {
+ value = readl(priv->base + XGMAC_DMA_STATUS) & 0x700000;
+ } while (value && (value != 0x600000));
+
+ xgmac_free_tx_skbufs(priv);
+ desc_init_tx_desc(priv->dma_tx, DMA_TX_RING_SZ);
+ priv->tx_tail = 0;
+ priv->tx_head = 0;
+ writel(reg | DMA_CONTROL_ST, priv->base + XGMAC_DMA_CONTROL);
+
+ writel(DMA_STATUS_TU | DMA_STATUS_TPS | DMA_STATUS_NIS | DMA_STATUS_AIS,
+ priv->base + XGMAC_DMA_STATUS);
+ writel(inten, priv->base + XGMAC_DMA_INTR_ENA);
+
+ netif_wake_queue(priv->dev);
+}
+
+static int xgmac_hw_init(struct net_device *dev)
+{
+ u32 value, ctrl;
+ int limit;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+
+ /* Save the ctrl register value */
+ ctrl = readl(ioaddr + XGMAC_CONTROL) & XGMAC_CONTROL_SPD_MASK;
+
+ /* SW reset */
+ value = DMA_BUS_MODE_SFT_RESET;
+ writel(value, ioaddr + XGMAC_DMA_BUS_MODE);
+ limit = 15000;
+ while (limit-- &&
+ (readl(ioaddr + XGMAC_DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
+ cpu_relax();
+ if (limit < 0)
+ return -EBUSY;
+
+ value = (0x10 << DMA_BUS_MODE_PBL_SHIFT) |
+ (0x10 << DMA_BUS_MODE_RPBL_SHIFT) |
+ DMA_BUS_MODE_FB | DMA_BUS_MODE_ATDS | DMA_BUS_MODE_AAL;
+ writel(value, ioaddr + XGMAC_DMA_BUS_MODE);
+
+ /* Enable interrupts */
+ writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_STATUS);
+ writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_INTR_ENA);
+
+ /* XGMAC requires AXI bus init. This is a 'magic number' for now */
+ writel(0x000100E, ioaddr + XGMAC_DMA_AXI_BUS);
+
+ ctrl |= XGMAC_CONTROL_DDIC | XGMAC_CONTROL_JE | XGMAC_CONTROL_ACS |
+ XGMAC_CONTROL_CAR;
+ if (dev->features & NETIF_F_RXCSUM)
+ ctrl |= XGMAC_CONTROL_IPC;
+ writel(ctrl, ioaddr + XGMAC_CONTROL);
+
+ value = DMA_CONTROL_DFF;
+ writel(value, ioaddr + XGMAC_DMA_CONTROL);
+
+ /* Set the HW DMA mode and the COE */
+ writel(XGMAC_OMR_TSF | XGMAC_OMR_RSF | XGMAC_OMR_RFD | XGMAC_OMR_RFA,
+ ioaddr + XGMAC_OMR);
+
+ /* Reset the MMC counters */
+ writel(1, ioaddr + XGMAC_MMC_CTRL);
+ return 0;
+}
+
+/**
+ * xgmac_open - open entry point of the driver
+ * @dev : pointer to the device structure.
+ * Description:
+ * This function is the open entry point of the driver.
+ * Return value:
+ * 0 on success and an appropriate (-)ve integer as defined in errno.h
+ * file on failure.
+ */
+static int xgmac_open(struct net_device *dev)
+{
+ int ret;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+
+ /* Check that the MAC address is valid. If its not, refuse
+ * to bring the device up. The user must specify an
+ * address using the following linux command:
+ * ifconfig eth0 hw ether xx:xx:xx:xx:xx:xx */
+ if (!is_valid_ether_addr(dev->dev_addr)) {
+ random_ether_addr(dev->dev_addr);
+ netdev_dbg(priv->dev, "generated random MAC address %pM\n",
+ dev->dev_addr);
+ }
+
+ skb_queue_head_init(&priv->rx_recycle);
+ memset(&priv->xstats, 0, sizeof(struct xgmac_extra_stats));
+
+ /* Initialize the XGMAC and descriptors */
+ xgmac_hw_init(dev);
+ xgmac_set_mac_addr(ioaddr, dev->dev_addr, 0);
+ xgmac_set_flow_ctrl(priv, priv->rx_pause, priv->tx_pause);
+
+ ret = xgmac_dma_desc_rings_init(dev);
+ if (ret < 0)
+ return ret;
+
+ /* Enable the MAC Rx/Tx */
+ xgmac_mac_enable(ioaddr);
+
+ napi_enable(&priv->napi);
+ netif_start_queue(dev);
+
+ return 0;
+}
+
+/**
+ * xgmac_release - close entry point of the driver
+ * @dev : device pointer.
+ * Description:
+ * This is the stop entry point of the driver.
+ */
+static int xgmac_stop(struct net_device *dev)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+
+ netif_stop_queue(dev);
+
+ if (readl(priv->base + XGMAC_DMA_INTR_ENA))
+ napi_disable(&priv->napi);
+
+ writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+ skb_queue_purge(&priv->rx_recycle);
+
+ /* Disable the MAC core */
+ xgmac_mac_disable(priv->base);
+
+ /* Release and free the Rx/Tx resources */
+ xgmac_free_dma_desc_rings(priv);
+
+ return 0;
+}
+
+/**
+ * xgmac_xmit:
+ * @skb : the socket buffer
+ * @dev : device pointer
+ * Description : Tx entry point of the driver.
+ */
+static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ unsigned int entry;
+ int i;
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ struct xgmac_dma_desc *desc, *first;
+ unsigned int desc_flags;
+ unsigned int len;
+ dma_addr_t paddr;
+
+ if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) <
+ (nfrags + 1)) {
+ writel(DMA_INTR_DEFAULT_MASK | DMA_INTR_ENA_TIE,
+ priv->base + XGMAC_DMA_INTR_ENA);
+ netif_stop_queue(dev);
+ return NETDEV_TX_BUSY;
+ }
+
+ desc_flags = (skb->ip_summed == CHECKSUM_PARTIAL) ?
+ TXDESC_CSUM_ALL : 0;
+ entry = priv->tx_head;
+ desc = priv->dma_tx + entry;
+ first = desc;
+
+ len = skb_headlen(skb);
+ paddr = dma_map_single(priv->device, skb->data, len, DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, paddr)) {
+ dev_kfree_skb(skb);
+ return -EIO;
+ }
+ priv->tx_skbuff[entry] = skb;
+ desc_set_buf_addr_and_size(desc, paddr, len);
+
+ for (i = 0; i < nfrags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ len = frag->size;
+
+ paddr = skb_frag_dma_map(priv->device, frag, 0, len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, paddr)) {
+ dev_kfree_skb(skb);
+ return -EIO;
+ }
+
+ entry = dma_ring_incr(entry, DMA_TX_RING_SZ);
+ desc = priv->dma_tx + entry;
+ priv->tx_skbuff[entry] = NULL;
+
+ desc_set_buf_addr_and_size(desc, paddr, len);
+ if (i < (nfrags - 1))
+ desc_set_tx_owner(desc, desc_flags);
+ }
+
+ /* Interrupt on completition only for the latest segment */
+ if (desc != first)
+ desc_set_tx_owner(desc, desc_flags |
+ TXDESC_LAST_SEG | TXDESC_INTERRUPT);
+ else
+ desc_flags |= TXDESC_LAST_SEG | TXDESC_INTERRUPT;
+
+ /* Set owner on first desc last to avoid race condition */
+ wmb();
+ desc_set_tx_owner(first, desc_flags | TXDESC_FIRST_SEG);
+
+ priv->tx_head = dma_ring_incr(entry, DMA_TX_RING_SZ);
+
+ writel(1, priv->base + XGMAC_DMA_TX_POLL);
+
+ return NETDEV_TX_OK;
+}
+
+static int xgmac_rx(struct xgmac_priv *priv, int limit)
+{
+ unsigned int entry;
+ unsigned int count = 0;
+ struct xgmac_dma_desc *p;
+
+ while (count < limit) {
+ int ip_checksum;
+ struct sk_buff *skb;
+ int frame_len;
+
+ writel(DMA_STATUS_RI | DMA_STATUS_NIS,
+ priv->base + XGMAC_DMA_STATUS);
+
+ entry = priv->rx_tail;
+ p = priv->dma_rx + entry;
+ if (desc_get_owner(p))
+ break;
+
+ count++;
+ priv->rx_tail = dma_ring_incr(priv->rx_tail, DMA_RX_RING_SZ);
+
+ /* read the status of the incoming frame */
+ ip_checksum = desc_get_rx_status(priv, p);
+ if (ip_checksum < 0)
+ continue;
+
+ skb = priv->rx_skbuff[entry];
+ if (unlikely(!skb)) {
+ netdev_err(priv->dev, "Inconsistent Rx descriptor chain\n");
+ break;
+ }
+ priv->rx_skbuff[entry] = NULL;
+
+ frame_len = desc_get_rx_frame_len(p);
+ netdev_dbg(priv->dev, "RX frame size %d, COE status: %d\n",
+ frame_len, ip_checksum);
+
+ skb_put(skb, frame_len);
+ dma_unmap_single(priv->device, desc_get_buf_addr(p),
+ frame_len, DMA_FROM_DEVICE);
+
+ skb->protocol = eth_type_trans(skb, priv->dev);
+ skb->ip_summed = ip_checksum;
+ if (ip_checksum == CHECKSUM_NONE)
+ netif_receive_skb(skb);
+ else
+ napi_gro_receive(&priv->napi, skb);
+ }
+
+ xgmac_rx_refill(priv);
+
+ writel(1, priv->base + XGMAC_DMA_RX_POLL);
+
+ return count;
+}
+
+/**
+ * xgmac_poll - xgmac poll method (NAPI)
+ * @napi : pointer to the napi structure.
+ * @budget : maximum number of packets that the current CPU can receive from
+ * all interfaces.
+ * Description :
+ * This function implements the the reception process.
+ * Also it runs the TX completion thread
+ */
+static int xgmac_poll(struct napi_struct *napi, int budget)
+{
+ struct xgmac_priv *priv = container_of(napi,
+ struct xgmac_priv, napi);
+ int work_done = 0;
+
+ xgmac_tx_complete(priv);
+ work_done = xgmac_rx(priv, budget);
+
+ if (work_done < budget) {
+ napi_complete(napi);
+ writel(DMA_INTR_DEFAULT_MASK, priv->base + XGMAC_DMA_INTR_ENA);
+ }
+ return work_done;
+}
+
+/**
+ * xgmac_tx_timeout
+ * @dev : Pointer to net device structure
+ * Description: this function is called when a packet transmission fails to
+ * complete within a reasonable tmrate. The driver will mark the error in the
+ * netdev structure and arrange for the device to be reset to a sane state
+ * in order to transmit a new packet.
+ */
+static void xgmac_tx_timeout(struct net_device *dev)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+
+ /* Clear Tx resources and restart transmitting again */
+ xgmac_tx_err(priv);
+}
+
+/**
+ * xgmac_set_rx_mode - entry point for multicast addressing
+ * @dev : pointer to the device structure
+ * Description:
+ * This function is a driver entry point which gets called by the kernel
+ * whenever multicast addresses must be enabled/disabled.
+ * Return value:
+ * void.
+ */
+static void xgmac_set_rx_mode(struct net_device *dev)
+{
+ int i;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+ unsigned int value = 0;
+ u32 hash_filter[XGMAC_NUM_HASH];
+ int reg = 1;
+ struct netdev_hw_addr *ha;
+ bool use_hash = false;
+
+ netdev_dbg(priv->dev, "# mcasts %d, # unicast %d\n",
+ netdev_mc_count(dev), netdev_uc_count(dev));
+
+ if (dev->flags & IFF_PROMISC) {
+ writel(XGMAC_FRAME_FILTER_PR, ioaddr + XGMAC_FRAME_FILTER);
+ return;
+ }
+
+ memset(hash_filter, 0, sizeof(hash_filter));
+
+ if (netdev_uc_count(dev) > XGMAC_MAX_FILTER_ADDR) {
+ use_hash = true;
+ value |= XGMAC_FRAME_FILTER_HUC | XGMAC_FRAME_FILTER_HPF;
+ }
+ netdev_for_each_uc_addr(ha, dev) {
+ if (use_hash) {
+ u32 bit_nr = ~ether_crc(ETH_ALEN, ha->addr) >> 23;
+
+ /* The most significant 4 bits determine the register to
+ * use (H/L) while the other 5 bits determine the bit
+ * within the register. */
+ hash_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+ } else {
+ xgmac_set_mac_addr(ioaddr, ha->addr, reg);
+ reg++;
+ }
+ }
+
+ if (dev->flags & IFF_ALLMULTI) {
+ value |= XGMAC_FRAME_FILTER_PM;
+ goto out;
+ }
+
+ if ((netdev_mc_count(dev) + reg - 1) > XGMAC_MAX_FILTER_ADDR) {
+ use_hash = true;
+ value |= XGMAC_FRAME_FILTER_HMC | XGMAC_FRAME_FILTER_HPF;
+ }
+ netdev_for_each_mc_addr(ha, dev) {
+ if (use_hash) {
+ u32 bit_nr = ~ether_crc(ETH_ALEN, ha->addr) >> 23;
+
+ /* The most significant 4 bits determine the register to
+ * use (H/L) while the other 5 bits determine the bit
+ * within the register. */
+ hash_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+ } else {
+ xgmac_set_mac_addr(ioaddr, ha->addr, reg);
+ reg++;
+ }
+ }
+
+out:
+ for (i = 0; i < XGMAC_NUM_HASH; i++)
+ writel(hash_filter[i], ioaddr + XGMAC_HASH(i));
+
+ writel(value, ioaddr + XGMAC_FRAME_FILTER);
+}
+
+/**
+ * xgmac_change_mtu - entry point to change MTU size for the device.
+ * @dev : device pointer.
+ * @new_mtu : the new MTU size for the device.
+ * Description: the Maximum Transfer Unit (MTU) is used by the network layer
+ * to drive packet transmission. Ethernet has an MTU of 1500 octets
+ * (ETH_DATA_LEN). This value can be changed with ifconfig.
+ * Return value:
+ * 0 on success and an appropriate (-)ve integer as defined in errno.h
+ * file on failure.
+ */
+static int xgmac_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ int old_mtu;
+
+ if ((new_mtu < 46) || (new_mtu > MAX_MTU)) {
+ netdev_err(priv->dev, "invalid MTU, max MTU is: %d\n", MAX_MTU);
+ return -EINVAL;
+ }
+
+ old_mtu = dev->mtu;
+ dev->mtu = new_mtu;
+
+ /* return early if the buffer sizes will not change */
+ if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
+ return 0;
+ if (old_mtu == new_mtu)
+ return 0;
+
+ /* Stop everything, get ready to change the MTU */
+ if (!netif_running(dev))
+ return 0;
+
+ /* Bring the interface down and then back up */
+ xgmac_stop(dev);
+ return xgmac_open(dev);
+}
+
+static irqreturn_t xgmac_pmt_interrupt(int irq, void *dev_id)
+{
+ u32 intr_status;
+ struct net_device *dev = (struct net_device *)dev_id;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+
+ intr_status = readl(ioaddr + XGMAC_INT_STAT);
+ if (intr_status & XGMAC_INT_STAT_PMT) {
+ netdev_dbg(priv->dev, "received Magic frame\n");
+ /* clear the PMT bits 5 and 6 by reading the PMT */
+ readl(ioaddr + XGMAC_PMT);
+ }
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t xgmac_interrupt(int irq, void *dev_id)
+{
+ u32 intr_status;
+ bool tx_err = false;
+ struct net_device *dev = (struct net_device *)dev_id;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ struct xgmac_extra_stats *x = &priv->xstats;
+
+ /* read the status register (CSR5) */
+ intr_status = readl(priv->base + XGMAC_DMA_STATUS);
+ intr_status &= readl(priv->base + XGMAC_DMA_INTR_ENA);
+ writel(intr_status, priv->base + XGMAC_DMA_STATUS);
+
+ /* It displays the DMA process states (CSR5 register) */
+ /* ABNORMAL interrupts */
+ if (unlikely(intr_status & DMA_STATUS_AIS)) {
+ if (intr_status & DMA_STATUS_TJT) {
+ netdev_err(priv->dev, "transmit jabber\n");
+ x->tx_jabber++;
+ }
+ if (intr_status & DMA_STATUS_RU)
+ x->rx_buf_unav++;
+ if (intr_status & DMA_STATUS_RPS) {
+ netdev_err(priv->dev, "receive process stopped\n");
+ x->rx_process_stopped++;
+ }
+ if (intr_status & DMA_STATUS_ETI) {
+ netdev_err(priv->dev, "transmit early interrupt\n");
+ x->tx_early++;
+ }
+ if (intr_status & DMA_STATUS_TPS) {
+ netdev_err(priv->dev, "transmit process stopped\n");
+ x->tx_process_stopped++;
+ tx_err = true;
+ }
+ if (intr_status & DMA_STATUS_FBI) {
+ netdev_err(priv->dev, "fatal bus error\n");
+ x->fatal_bus_error++;
+ tx_err = true;
+ }
+
+ if (tx_err)
+ xgmac_tx_err(priv);
+ }
+
+ /* TX/RX NORMAL interrupts */
+ if (intr_status & (DMA_STATUS_RI | DMA_STATUS_TU)) {
+ writel(DMA_INTR_ABNORMAL, priv->base + XGMAC_DMA_INTR_ENA);
+ napi_schedule(&priv->napi);
+ }
+
+ return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/* Polling receive - used by NETCONSOLE and other diagnostic tools
+ * to allow network I/O with interrupts disabled. */
+static void xgmac_poll_controller(struct net_device *dev)
+{
+ disable_irq(dev->irq);
+ xgmac_interrupt(dev->irq, dev);
+ enable_irq(dev->irq);
+}
+#endif
+
+struct rtnl_link_stats64 *
+xgmac_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *storage)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *base = priv->base;
+ u32 count;
+
+ spin_lock_bh(&priv->stats_lock);
+ writel(XGMAC_MMC_CTRL_CNT_FRZ, base + XGMAC_MMC_CTRL);
+
+ storage->rx_bytes = readl(base + XGMAC_MMC_RXOCTET_G_LO);
+ storage->rx_bytes |= (u64)(readl(base + XGMAC_MMC_RXOCTET_G_HI)) << 32;
+
+ storage->rx_packets = readl(base + XGMAC_MMC_RXFRAME_GB_LO);
+ storage->multicast = readl(base + XGMAC_MMC_RXMCFRAME_G);
+ storage->rx_crc_errors = readl(base + XGMAC_MMC_RXCRCERR);
+ storage->rx_length_errors = readl(base + XGMAC_MMC_RXLENGTHERR);
+ storage->rx_missed_errors = readl(base + XGMAC_MMC_RXOVERFLOW);
+
+ storage->tx_bytes = readl(base + XGMAC_MMC_TXOCTET_G_LO);
+ storage->tx_bytes |= (u64)(readl(base + XGMAC_MMC_TXOCTET_G_HI)) << 32;
+
+ count = readl(base + XGMAC_MMC_TXFRAME_GB_LO);
+ storage->tx_errors = count - readl(base + XGMAC_MMC_TXFRAME_G_LO);
+ storage->tx_packets = count;
+ storage->tx_fifo_errors = readl(base + XGMAC_MMC_TXUNDERFLOW);
+
+ writel(0, base + XGMAC_MMC_CTRL);
+ spin_unlock_bh(&priv->stats_lock);
+ return storage;
+}
+
+static int xgmac_set_mac_address(struct net_device *dev, void *p)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+ struct sockaddr *addr = p;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+
+ xgmac_set_mac_addr(ioaddr, dev->dev_addr, 0);
+
+ return 0;
+}
+
+static int xgmac_set_features(struct net_device *dev, netdev_features_t features)
+{
+ u32 ctrl;
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->base;
+ u32 changed = dev->features ^ features;
+
+ if (!(changed & NETIF_F_RXCSUM))
+ return 0;
+
+ ctrl = readl(ioaddr + XGMAC_CONTROL);
+ if (features & NETIF_F_RXCSUM)
+ ctrl |= XGMAC_CONTROL_IPC;
+ else
+ ctrl &= ~XGMAC_CONTROL_IPC;
+ writel(ctrl, ioaddr + XGMAC_CONTROL);
+
+ return 0;
+}
+
+static const struct net_device_ops xgmac_netdev_ops = {
+ .ndo_open = xgmac_open,
+ .ndo_start_xmit = xgmac_xmit,
+ .ndo_stop = xgmac_stop,
+ .ndo_change_mtu = xgmac_change_mtu,
+ .ndo_set_rx_mode = xgmac_set_rx_mode,
+ .ndo_tx_timeout = xgmac_tx_timeout,
+ .ndo_get_stats64 = xgmac_get_stats64,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = xgmac_poll_controller,
+#endif
+ .ndo_set_mac_address = xgmac_set_mac_address,
+ .ndo_set_features = xgmac_set_features,
+};
+
+static int xgmac_ethtool_getsettings(struct net_device *dev,
+ struct ethtool_cmd *cmd)
+{
+ cmd->autoneg = 0;
+ cmd->duplex = DUPLEX_FULL;
+ ethtool_cmd_speed_set(cmd, 10000);
+ cmd->supported = 0;
+ cmd->advertising = 0;
+ cmd->transceiver = XCVR_INTERNAL;
+ return 0;
+}
+
+static void xgmac_get_pauseparam(struct net_device *netdev,
+ struct ethtool_pauseparam *pause)
+{
+ struct xgmac_priv *priv = netdev_priv(netdev);
+
+ pause->rx_pause = priv->rx_pause;
+ pause->tx_pause = priv->tx_pause;
+}
+
+static int xgmac_set_pauseparam(struct net_device *netdev,
+ struct ethtool_pauseparam *pause)
+{
+ struct xgmac_priv *priv = netdev_priv(netdev);
+
+ if (pause->autoneg)
+ return -EINVAL;
+
+ return xgmac_set_flow_ctrl(priv, pause->rx_pause, pause->tx_pause);
+}
+
+struct xgmac_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int stat_offset;
+ bool is_reg;
+};
+
+#define XGMAC_STAT(m) \
+ { #m, offsetof(struct xgmac_priv, xstats.m), false }
+#define XGMAC_HW_STAT(m, reg_offset) \
+ { #m, reg_offset, true }
+
+static const struct xgmac_stats xgmac_gstrings_stats[] = {
+ XGMAC_STAT(tx_frame_flushed),
+ XGMAC_STAT(tx_payload_error),
+ XGMAC_STAT(tx_ip_header_error),
+ XGMAC_STAT(tx_local_fault),
+ XGMAC_STAT(tx_remote_fault),
+ XGMAC_STAT(tx_early),
+ XGMAC_STAT(tx_process_stopped),
+ XGMAC_STAT(tx_jabber),
+ XGMAC_STAT(rx_buf_unav),
+ XGMAC_STAT(rx_process_stopped),
+ XGMAC_STAT(rx_payload_error),
+ XGMAC_STAT(rx_ip_header_error),
+ XGMAC_STAT(rx_da_filter_fail),
+ XGMAC_STAT(rx_sa_filter_fail),
+ XGMAC_STAT(fatal_bus_error),
+ XGMAC_HW_STAT(rx_watchdog, XGMAC_MMC_RXWATCHDOG),
+ XGMAC_HW_STAT(tx_vlan, XGMAC_MMC_TXVLANFRAME),
+ XGMAC_HW_STAT(rx_vlan, XGMAC_MMC_RXVLANFRAME),
+ XGMAC_HW_STAT(tx_pause, XGMAC_MMC_TXPAUSEFRAME),
+ XGMAC_HW_STAT(rx_pause, XGMAC_MMC_RXPAUSEFRAME),
+};
+#define XGMAC_STATS_LEN ARRAY_SIZE(xgmac_gstrings_stats)
+
+static void xgmac_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *dummy,
+ u64 *data)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ void *p = priv;
+ int i;
+
+ for (i = 0; i < XGMAC_STATS_LEN; i++) {
+ if (xgmac_gstrings_stats[i].is_reg)
+ *data++ = readl(priv->base +
+ xgmac_gstrings_stats[i].stat_offset);
+ else
+ *data++ = *(u32 *)(p +
+ xgmac_gstrings_stats[i].stat_offset);
+ }
+}
+
+static int xgmac_get_sset_count(struct net_device *netdev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return XGMAC_STATS_LEN;
+ default:
+ return -EINVAL;
+ }
+}
+
+static void xgmac_get_strings(struct net_device *dev, u32 stringset,
+ u8 *data)
+{
+ int i;
+ u8 *p = data;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < XGMAC_STATS_LEN; i++) {
+ memcpy(p, xgmac_gstrings_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+static void xgmac_get_wol(struct net_device *dev,
+ struct ethtool_wolinfo *wol)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+
+ if (device_can_wakeup(priv->device)) {
+ wol->supported = WAKE_MAGIC | WAKE_UCAST;
+ wol->wolopts = priv->wolopts;
+ }
+}
+
+static int xgmac_set_wol(struct net_device *dev,
+ struct ethtool_wolinfo *wol)
+{
+ struct xgmac_priv *priv = netdev_priv(dev);
+ u32 support = WAKE_MAGIC | WAKE_UCAST;
+
+ if (!device_can_wakeup(priv->device))
+ return -ENOTSUPP;
+
+ if (wol->wolopts & ~support)
+ return -EINVAL;
+
+ priv->wolopts = wol->wolopts;
+
+ if (wol->wolopts) {
+ device_set_wakeup_enable(priv->device, 1);
+ enable_irq_wake(dev->irq);
+ } else {
+ device_set_wakeup_enable(priv->device, 0);
+ disable_irq_wake(dev->irq);
+ }
+
+ return 0;
+}
+
+static struct ethtool_ops xgmac_ethtool_ops = {
+ .get_settings = xgmac_ethtool_getsettings,
+ .get_link = ethtool_op_get_link,
+ .get_pauseparam = xgmac_get_pauseparam,
+ .set_pauseparam = xgmac_set_pauseparam,
+ .get_ethtool_stats = xgmac_get_ethtool_stats,
+ .get_strings = xgmac_get_strings,
+ .get_wol = xgmac_get_wol,
+ .set_wol = xgmac_set_wol,
+ .get_sset_count = xgmac_get_sset_count,
+};
+
+/**
+ * xgmac_probe
+ * @pdev: platform device pointer
+ * Description: the driver is initialized through platform_device.
+ */
+static int xgmac_probe(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct resource *res;
+ struct net_device *ndev = NULL;
+ struct xgmac_priv *priv = NULL;
+ u32 uid;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENODEV;
+
+ if (!request_mem_region(res->start, resource_size(res), pdev->name))
+ return -EBUSY;
+
+ ndev = alloc_etherdev(sizeof(struct xgmac_priv));
+ if (!ndev) {
+ ret = -ENOMEM;
+ goto err_alloc;
+ }
+
+ SET_NETDEV_DEV(ndev, &pdev->dev);
+ priv = netdev_priv(ndev);
+ platform_set_drvdata(pdev, ndev);
+ ether_setup(ndev);
+ ndev->netdev_ops = &xgmac_netdev_ops;
+ SET_ETHTOOL_OPS(ndev, &xgmac_ethtool_ops);
+ spin_lock_init(&priv->stats_lock);
+
+ priv->device = &pdev->dev;
+ priv->dev = ndev;
+ priv->rx_pause = 1;
+ priv->tx_pause = 1;
+
+ priv->base = ioremap(res->start, resource_size(res));
+ if (!priv->base) {
+ netdev_err(ndev, "ioremap failed\n");
+ ret = -ENOMEM;
+ goto err_io;
+ }
+
+ uid = readl(priv->base + XGMAC_VERSION);
+ netdev_info(ndev, "h/w version is 0x%x\n", uid);
+
+ writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+ ndev->irq = platform_get_irq(pdev, 0);
+ if (ndev->irq == -ENXIO) {
+ netdev_err(ndev, "No irq resource\n");
+ ret = ndev->irq;
+ goto err_irq;
+ }
+
+ ret = request_irq(ndev->irq, xgmac_interrupt, 0,
+ dev_name(&pdev->dev), ndev);
+ if (ret < 0) {
+ netdev_err(ndev, "Could not request irq %d - ret %d)\n",
+ ndev->irq, ret);
+ goto err_irq;
+ }
+
+ priv->pmt_irq = platform_get_irq(pdev, 1);
+ if (priv->pmt_irq == -ENXIO) {
+ netdev_err(ndev, "No pmt irq resource\n");
+ ret = priv->pmt_irq;
+ goto err_pmt_irq;
+ }
+
+ ret = request_irq(priv->pmt_irq, xgmac_pmt_interrupt, 0,
+ dev_name(&pdev->dev), ndev);
+ if (ret < 0) {
+ netdev_err(ndev, "Could not request irq %d - ret %d)\n",
+ priv->pmt_irq, ret);
+ goto err_pmt_irq;
+ }
+
+ device_set_wakeup_capable(&pdev->dev, 1);
+ if (device_can_wakeup(priv->device))
+ priv->wolopts = WAKE_MAGIC; /* Magic Frame as default */
+
+ ndev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
+ if (readl(priv->base + XGMAC_DMA_HW_FEATURE) & DMA_HW_FEAT_TXCOESEL)
+ ndev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_RXCSUM;
+ ndev->features |= ndev->hw_features;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
+
+ /* Get the MAC address */
+ xgmac_get_mac_addr(priv->base, ndev->dev_addr, 0);
+ if (!is_valid_ether_addr(ndev->dev_addr))
+ netdev_warn(ndev, "MAC address %pM not valid",
+ ndev->dev_addr);
+
+ netif_napi_add(ndev, &priv->napi, xgmac_poll, 64);
+ ret = register_netdev(ndev);
+ if (ret)
+ goto err_reg;
+
+ return 0;
+
+err_reg:
+ netif_napi_del(&priv->napi);
+ free_irq(priv->pmt_irq, ndev);
+err_pmt_irq:
+ free_irq(ndev->irq, ndev);
+err_irq:
+ iounmap(priv->base);
+err_io:
+ free_netdev(ndev);
+err_alloc:
+ release_mem_region(res->start, resource_size(res));
+ platform_set_drvdata(pdev, NULL);
+ return ret;
+}
+
+/**
+ * xgmac_dvr_remove
+ * @pdev: platform device pointer
+ * Description: this function resets the TX/RX processes, disables the MAC RX/TX
+ * changes the link status, releases the DMA descriptor rings,
+ * unregisters the MDIO bus and unmaps the allocated memory.
+ */
+static int xgmac_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct xgmac_priv *priv = netdev_priv(ndev);
+ struct resource *res;
+
+ xgmac_mac_disable(priv->base);
+
+ /* Free the IRQ lines */
+ free_irq(ndev->irq, ndev);
+ free_irq(priv->pmt_irq, ndev);
+
+ platform_set_drvdata(pdev, NULL);
+ unregister_netdev(ndev);
+ netif_napi_del(&priv->napi);
+
+ iounmap(priv->base);
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ release_mem_region(res->start, resource_size(res));
+
+ free_netdev(ndev);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static void xgmac_pmt(void __iomem *ioaddr, unsigned long mode)
+{
+ unsigned int pmt = 0;
+
+ if (mode & WAKE_MAGIC)
+ pmt |= XGMAC_PMT_POWERDOWN | XGMAC_PMT_MAGIC_PKT;
+ if (mode & WAKE_UCAST)
+ pmt |= XGMAC_PMT_POWERDOWN | XGMAC_PMT_GLBL_UNICAST;
+
+ writel(pmt, ioaddr + XGMAC_PMT);
+}
+
+static int xgmac_suspend(struct device *dev)
+{
+ struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+ struct xgmac_priv *priv = netdev_priv(ndev);
+ u32 value;
+
+ if (!ndev || !netif_running(ndev))
+ return 0;
+
+ netif_device_detach(ndev);
+ napi_disable(&priv->napi);
+ writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+
+ if (device_may_wakeup(priv->device)) {
+ /* Stop TX/RX DMA Only */
+ value = readl(priv->base + XGMAC_DMA_CONTROL);
+ value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
+ writel(value, priv->base + XGMAC_DMA_CONTROL);
+
+ xgmac_pmt(priv->base, priv->wolopts);
+ } else
+ xgmac_mac_disable(priv->base);
+
+ return 0;
+}
+
+static int xgmac_resume(struct device *dev)
+{
+ struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+ struct xgmac_priv *priv = netdev_priv(ndev);
+ void __iomem *ioaddr = priv->base;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ xgmac_pmt(ioaddr, 0);
+
+ /* Enable the MAC and DMA */
+ xgmac_mac_enable(ioaddr);
+ writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_STATUS);
+ writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_INTR_ENA);
+
+ netif_device_attach(ndev);
+ napi_enable(&priv->napi);
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(xgmac_pm_ops, xgmac_suspend, xgmac_resume);
+#define XGMAC_PM_OPS (&xgmac_pm_ops)
+#else
+#define XGMAC_PM_OPS NULL
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct of_device_id xgmac_of_match[] = {
+ { .compatible = "calxeda,hb-xgmac", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, xgmac_of_match);
+
+static struct platform_driver xgmac_driver = {
+ .driver = {
+ .name = "calxedaxgmac",
+ .of_match_table = xgmac_of_match,
+ },
+ .probe = xgmac_probe,
+ .remove = xgmac_remove,
+ .driver.pm = XGMAC_PM_OPS,
+};
+
+module_platform_driver(xgmac_driver);
+
+MODULE_AUTHOR("Calxeda, Inc.");
+MODULE_DESCRIPTION("Calxeda 10G XGMAC driver");
+MODULE_LICENSE("GPL v2");
{
struct adapter *adapter = dev->ml_priv;
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
- strcpy(info->bus_info, pci_name(adapter->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(adapter->pdev),
+ sizeof(info->bus_info));
}
static int get_sset_count(struct net_device *dev, int sset)
return 0;
}
-static u32 t1_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t t1_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int t1_set_features(struct net_device *dev, u32 features)
+static int t1_set_features(struct net_device *dev, netdev_features_t features)
{
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
struct adapter *adapter = dev->ml_priv;
if (changed & NETIF_F_HW_VLAN_RX)
/*
* Enable/disable VLAN acceleration.
*/
-void t1_vlan_mode(struct adapter *adapter, u32 features)
+void t1_vlan_mode(struct adapter *adapter, netdev_features_t features)
{
struct sge *sge = adapter->sge;
int t1_poll(struct napi_struct *, int);
netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev);
-void t1_vlan_mode(struct adapter *adapter, u32 features);
+void t1_vlan_mode(struct adapter *adapter, netdev_features_t features);
void t1_sge_start(struct sge *);
void t1_sge_stop(struct sge *);
int t1_sge_intr_error_handler(struct sge *);
t3_get_tp_version(adapter, &tp_vers);
spin_unlock(&adapter->stats_lock);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(adapter->pdev));
- if (!fw_vers)
- strcpy(info->fw_version, "N/A");
- else {
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(adapter->pdev),
+ sizeof(info->bus_info));
+ if (fw_vers)
snprintf(info->fw_version, sizeof(info->fw_version),
"%s %u.%u.%u TP %u.%u.%u",
G_FW_VERSION_TYPE(fw_vers) ? "T" : "N",
G_TP_VERSION_MAJOR(tp_vers),
G_TP_VERSION_MINOR(tp_vers),
G_TP_VERSION_MICRO(tp_vers));
- }
}
static void get_strings(struct net_device *dev, u32 stringset, u8 * data)
}
}
-static void cxgb_vlan_mode(struct net_device *dev, u32 features)
+static void cxgb_vlan_mode(struct net_device *dev, netdev_features_t features)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adapter = pi->adapter;
t3_synchronize_rx(adapter, pi);
}
-static u32 cxgb_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t cxgb_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int cxgb_set_features(struct net_device *dev, u32 features)
+static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
{
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
cxgb_vlan_mode(dev, features);
case (NETEVENT_REDIRECT):{
struct netevent_redirect *nr = ctx;
cxgb_redirect(nr->old, nr->new);
- cxgb_neigh_update(dst_get_neighbour(nr->new));
+ cxgb_neigh_update(dst_get_neighbour_noref(nr->new));
break;
}
default:
static void cxgb_neigh_update(struct neighbour *neigh)
{
- struct net_device *dev = neigh->dev;
+ struct net_device *dev;
+ if (!neigh)
+ return;
+ dev = neigh->dev;
if (dev && (is_offloading(dev))) {
struct t3cdev *tdev = dev2t3cdev(dev);
static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
{
struct net_device *olddev, *newdev;
+ struct neighbour *n;
struct tid_info *ti;
struct t3cdev *tdev;
u32 tid;
struct l2t_entry *e;
struct t3c_tid_entry *te;
- olddev = dst_get_neighbour(old)->dev;
- newdev = dst_get_neighbour(new)->dev;
+ n = dst_get_neighbour_noref(old);
+ if (!n)
+ return;
+ olddev = n->dev;
+
+ n = dst_get_neighbour_noref(new);
+ if (!n)
+ return;
+ newdev = n->dev;
+
if (!is_offloading(olddev))
return;
if (!is_offloading(newdev)) {
}
/* Add new L2T entry */
- e = t3_l2t_get(tdev, dst_get_neighbour(new), newdev);
+ e = t3_l2t_get(tdev, new, newdev);
if (!e) {
printk(KERN_ERR "%s: couldn't allocate new l2t entry!\n",
__func__);
out_free_l2t:
t3_free_l2t(L2DATA(dev));
- rcu_assign_pointer(dev->l2opt, NULL);
+ RCU_INIT_POINTER(dev->l2opt, NULL);
out_free:
kfree(t);
return err;
rcu_read_lock();
d = L2DATA(tdev);
rcu_read_unlock();
- rcu_assign_pointer(tdev->l2opt, NULL);
+ RCU_INIT_POINTER(tdev->l2opt, NULL);
call_rcu(&d->rcu_head, clean_l2_data);
if (t->nofail_skb)
kfree_skb(t->nofail_skb);
spin_unlock(&e->lock);
}
-struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
+struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst,
struct net_device *dev)
{
struct l2t_entry *e = NULL;
+ struct neighbour *neigh;
+ struct port_info *p;
struct l2t_data *d;
int hash;
- u32 addr = *(u32 *) neigh->primary_key;
- int ifidx = neigh->dev->ifindex;
- struct port_info *p = netdev_priv(dev);
- int smt_idx = p->port_id;
+ u32 addr;
+ int ifidx;
+ int smt_idx;
rcu_read_lock();
+ neigh = dst_get_neighbour_noref(dst);
+ if (!neigh)
+ goto done_rcu;
+
+ addr = *(u32 *) neigh->primary_key;
+ ifidx = neigh->dev->ifindex;
+
+ if (!dev)
+ dev = neigh->dev;
+ p = netdev_priv(dev);
+ smt_idx = p->port_id;
+
d = L2DATA(cdev);
if (!d)
goto done_rcu;
l2t_hold(d, e);
if (atomic_read(&e->refcnt) == 1)
reuse_entry(e, neigh);
- goto done;
+ goto done_unlock;
}
/* Need to allocate a new entry */
e->vlan = VLAN_NONE;
spin_unlock(&e->lock);
}
-done:
+done_unlock:
write_unlock_bh(&d->lock);
done_rcu:
rcu_read_unlock();
void t3_l2e_free(struct l2t_data *d, struct l2t_entry *e);
void t3_l2t_update(struct t3cdev *dev, struct neighbour *neigh);
-struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
+struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst,
struct net_device *dev);
int t3_l2t_send_slow(struct t3cdev *dev, struct sk_buff *skb,
struct l2t_entry *e);
MODULE_PARM_DESC(intr_cnt,
"thresholds 1..3 for queue interrupt packet counters");
-static int vf_acls;
+static bool vf_acls;
#ifdef CONFIG_PCI_IOV
module_param(vf_acls, bool, 0644);
{
struct adapter *adapter = netdev2adap(dev);
- strcpy(info->driver, KBUILD_MODNAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(adapter->pdev));
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(adapter->pdev),
+ sizeof(info->bus_info));
- if (!adapter->params.fw_vers)
- strcpy(info->fw_version, "N/A");
- else
+ if (adapter->params.fw_vers)
snprintf(info->fw_version, sizeof(info->fw_version),
"%u.%u.%u.%u, TP %u.%u.%u.%u",
FW_HDR_FW_VER_MAJOR_GET(adapter->params.fw_vers),
return err;
}
-static int cxgb_set_features(struct net_device *dev, u32 features)
+static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
{
const struct port_info *pi = netdev_priv(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
int err;
if (!(changed & NETIF_F_HW_VLAN_RX))
return err;
}
-static int get_rss_table(struct net_device *dev, struct ethtool_rxfh_indir *p)
+static u32 get_rss_table_size(struct net_device *dev)
+{
+ const struct port_info *pi = netdev_priv(dev);
+
+ return pi->rss_size;
+}
+
+static int get_rss_table(struct net_device *dev, u32 *p)
{
const struct port_info *pi = netdev_priv(dev);
- unsigned int n = min_t(unsigned int, p->size, pi->rss_size);
+ unsigned int n = pi->rss_size;
- p->size = pi->rss_size;
while (n--)
- p->ring_index[n] = pi->rss[n];
+ p[n] = pi->rss[n];
return 0;
}
-static int set_rss_table(struct net_device *dev,
- const struct ethtool_rxfh_indir *p)
+static int set_rss_table(struct net_device *dev, const u32 *p)
{
unsigned int i;
struct port_info *pi = netdev_priv(dev);
- if (p->size != pi->rss_size)
- return -EINVAL;
- for (i = 0; i < p->size; i++)
- if (p->ring_index[i] >= pi->nqsets)
- return -EINVAL;
- for (i = 0; i < p->size; i++)
- pi->rss[i] = p->ring_index[i];
+ for (i = 0; i < pi->rss_size; i++)
+ pi->rss[i] = p[i];
if (pi->adapter->flags & FULL_INIT_DONE)
return write_rss(pi, pi->rss);
return 0;
.get_wol = get_wol,
.set_wol = set_wol,
.get_rxnfc = get_rxnfc,
+ .get_rxfh_indir_size = get_rss_table_size,
.get_rxfh_indir = get_rss_table,
.set_rxfh_indir = set_rss_table,
.flash_device = set_flash,
if (!pi->rss)
return -ENOMEM;
for (j = 0; j < pi->rss_size; j++)
- pi->rss[j] = j % pi->nqsets;
+ pi->rss[j] = ethtool_rxfh_indir_default(j, pi->nqsets);
}
return 0;
}
{
int func, i, err;
struct port_info *pi;
- unsigned int highdma = 0;
+ bool highdma = false;
struct adapter *adapter = NULL;
printk_once(KERN_INFO "%s - version %s\n", DRV_DESC, DRV_VERSION);
}
if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
- highdma = NETIF_F_HIGHDMA;
+ highdma = true;
err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
if (err) {
dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM | NETIF_F_RXHASH |
NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
- netdev->features |= netdev->hw_features | highdma;
+ if (highdma)
+ netdev->hw_features |= NETIF_F_HIGHDMA;
+ netdev->features |= netdev->hw_features;
netdev->vlan_features = netdev->features & VLAN_FEAT;
netdev->priv_flags |= IFF_UNICAST_FLT;
__be64 *d = &q->desc[q->pidx];
struct rx_sw_desc *sd = &q->sdesc[q->pidx];
- gfp |= __GFP_NOWARN; /* failures are expected */
+ gfp |= __GFP_NOWARN | __GFP_COLD;
#if FL_PG_ORDER > 0
/*
#endif
while (n--) {
- pg = __netdev_alloc_page(adap->port[0], gfp);
+ pg = alloc_page(gfp);
if (unlikely(!pg)) {
q->alloc_failed++;
break;
mapping = dma_map_page(adap->pdev_dev, pg, 0, PAGE_SIZE,
PCI_DMA_FROMDEVICE);
if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) {
- netdev_free_page(adap->port[0], pg);
+ put_page(pg);
goto out;
}
*d++ = cpu_to_be64(mapping);
return ret;
}
-static u32 cxgb4vf_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t cxgb4vf_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int cxgb4vf_set_features(struct net_device *dev, u32 features)
+static int cxgb4vf_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct port_info *pi = netdev_priv(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
t4vf_set_rxmode(pi->adapter, pi->viid, -1, -1, -1, -1,
{
struct adapter *adapter = netdev2adap(dev);
- strcpy(drvinfo->driver, KBUILD_MODNAME);
- strcpy(drvinfo->version, DRV_VERSION);
- strcpy(drvinfo->bus_info, pci_name(to_pci_dev(dev->dev.parent)));
+ strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(to_pci_dev(dev->dev.parent)),
+ sizeof(drvinfo->bus_info));
snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
"%u.%u.%u.%u, TP %u.%u.%u.%u",
FW_HDR_FW_VER_MAJOR_GET(adapter->params.dev.fwrev),
alloc_small_pages:
while (n--) {
- page = __netdev_alloc_page(adapter->port[0],
- gfp | __GFP_NOWARN);
+ page = alloc_page(gfp | __GFP_NOWARN | __GFP_COLD);
if (unlikely(!page)) {
fl->alloc_failed++;
break;
dma_addr = dma_map_page(adapter->pdev_dev, page, 0, PAGE_SIZE,
PCI_DMA_FROMDEVICE);
if (unlikely(dma_mapping_error(adapter->pdev_dev, dma_addr))) {
- netdev_free_page(adapter->port[0], page);
+ put_page(page);
break;
}
*d++ = cpu_to_be64(dma_addr);
}
/* rtnl lock is held */
-void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+int enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct enic *enic = netdev_priv(netdev);
+ int err;
spin_lock(&enic->devcmd_lock);
- enic_add_vlan(enic, vid);
+ err = enic_add_vlan(enic, vid);
spin_unlock(&enic->devcmd_lock);
+
+ return err;
}
/* rtnl lock is held */
-void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+int enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct enic *enic = netdev_priv(netdev);
+ int err;
spin_lock(&enic->devcmd_lock);
- enic_del_vlan(enic, vid);
+ err = enic_del_vlan(enic, vid);
spin_unlock(&enic->devcmd_lock);
+
+ return err;
}
int enic_dev_enable2(struct enic *enic, int active)
int broadcast, int promisc, int allmulti);
int enic_dev_add_addr(struct enic *enic, u8 *addr);
int enic_dev_del_addr(struct enic *enic, u8 *addr);
-void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+int enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+int enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
int enic_dev_notify_unset(struct enic *enic);
int enic_dev_hang_notify(struct enic *enic);
int enic_dev_set_ig_vlan_rewrite_mode(struct enic *enic);
enic_dev_fw_info(enic, &fw_info);
- strncpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
- strncpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
- strncpy(drvinfo->fw_version, fw_info->fw_version,
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, fw_info->fw_version,
sizeof(drvinfo->fw_version));
- strncpy(drvinfo->bus_info, pci_name(enic->pdev),
+ strlcpy(drvinfo->bus_info, pci_name(enic->pdev),
sizeof(drvinfo->bus_info));
}
#endif
/* Allocate structure for port profiles */
- enic->pp = kzalloc(num_pps * sizeof(*enic->pp), GFP_KERNEL);
+ enic->pp = kcalloc(num_pps, sizeof(*enic->pp), GFP_KERNEL);
if (!enic->pp) {
pr_err("port profile alloc failed, aborting\n");
err = -ENOMEM;
return mii_nway_restart(&dm->mii);
}
-static int dm9000_set_features(struct net_device *dev, u32 features)
+static int dm9000_set_features(struct net_device *dev,
+ netdev_features_t features)
{
board_info_t *dm = to_dm9000_board(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
unsigned long flags;
if (!(changed & NETIF_F_RXCSUM))
if (!dm->wake_state)
irq_set_irq_wake(dm->irq_wake, 1);
- else if (dm->wake_state & !opts)
+ else if (dm->wake_state && !opts)
irq_set_irq_wake(dm->irq_wake, 0);
}
{
struct de_private *de = netdev_priv(dev);
- strcpy (info->driver, DRV_NAME);
- strcpy (info->version, DRV_VERSION);
- strcpy (info->bus_info, pci_name(de->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(de->pdev), sizeof(info->bus_info));
info->eedump_len = DE_EEPROM_SIZE;
}
u_long iobase = 0; /* Clear upper 32 bits in Alphas */
int i, j;
struct de4x5_private *lp = netdev_priv(dev);
- struct list_head *walk;
-
- list_for_each(walk, &pdev->bus_list) {
- struct pci_dev *this_dev = pci_dev_b(walk);
-
- /* Skip the pci_bus list entry */
- if (list_entry(walk, struct pci_bus, devices) == pdev->bus) continue;
+ struct pci_dev *this_dev;
+ list_for_each_entry(this_dev, &pdev->bus->devices, bus_list) {
vendor = this_dev->vendor;
device = this_dev->device << 8;
if (!(is_DC21040 || is_DC21041 || is_DC21140 || is_DC2114x)) continue;
struct de4x5_private *lp = netdev_priv(dev);
char *p, *q, t;
- lp->params.fdx = 0;
+ lp->params.fdx = false;
lp->params.autosense = AUTO;
if (args == NULL) return;
t = *q;
*q = '\0';
- if (strstr(p, "fdx") || strstr(p, "FDX")) lp->params.fdx = 1;
+ if (strstr(p, "fdx") || strstr(p, "FDX")) lp->params.fdx = true;
if (strstr(p, "autosense") || strstr(p, "AUTOSENSE")) {
if (strstr(p, "TP")) {
{
struct dmfe_board_info *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
if (np->pdev)
- strcpy(info->bus_info, pci_name(np->pdev));
+ strlcpy(info->bus_info, pci_name(np->pdev),
+ sizeof(info->bus_info));
else
sprintf(info->bus_info, "EISA 0x%lx %d",
dev->base_addr, dev->irq);
static void tulip_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct tulip_private *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(np->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pdev), sizeof(info->bus_info));
}
{
struct uli526x_board_info *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
if (np->pdev)
- strcpy(info->bus_info, pci_name(np->pdev));
+ strlcpy(info->bus_info, pci_name(np->pdev),
+ sizeof(info->bus_info));
else
sprintf(info->bus_info, "EISA 0x%lx %d",
dev->base_addr, dev->irq);
{
struct netdev_private *np = netdev_priv(dev);
- strcpy (info->driver, DRV_NAME);
- strcpy (info->version, DRV_VERSION);
- strcpy (info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
#include "de600.h"
-static unsigned int check_lost = 1;
+static bool check_lost = true;
module_param(check_lost, bool, 0);
MODULE_PARM_DESC(check_lost, "If set then check for unplugged de600");
static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct netdev_private *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
static void dnet_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, "0");
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, "0", sizeof(info->bus_info));
}
static const struct ethtool_ops dnet_ethtool_ops = {
},
};
-static int __init dnet_init(void)
-{
- return platform_driver_register(&dnet_driver);
-}
-
-static void __exit dnet_exit(void)
-{
- platform_driver_unregister(&dnet_driver);
-}
-
-module_init(dnet_init);
-module_exit(dnet_exit);
+module_platform_driver(dnet_driver);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Dave DNET Ethernet driver");
#define OC_NAME "Emulex OneConnect 10Gbps NIC"
#define OC_NAME_BE OC_NAME "(be3)"
#define OC_NAME_LANCER OC_NAME "(Lancer)"
+#define OC_NAME_SH OC_NAME "(Skyhawk)"
#define DRV_DESC "ServerEngines BladeEngine 10Gbps NIC Driver"
#define BE_VENDOR_ID 0x19a2
#define OC_DEVICE_ID2 0x710 /* Device Id for BE3 cards */
#define OC_DEVICE_ID3 0xe220 /* Device id for Lancer cards */
#define OC_DEVICE_ID4 0xe228 /* Device id for VF in Lancer */
+#define OC_DEVICE_ID5 0x720 /* Device Id for Skyhawk cards */
static inline char *nic_name(struct pci_dev *pdev)
{
return OC_NAME_LANCER;
case BE_DEVICE_ID2:
return BE3_NAME;
+ case OC_DEVICE_ID5:
+ return OC_NAME_SH;
default:
return BE_NAME;
}
};
struct be_vf_cfg {
- unsigned char vf_mac_addr[ETH_ALEN];
- u32 vf_if_handle;
- u32 vf_pmac_id;
- u16 vf_vlan_tag;
- u32 vf_tx_rate;
+ unsigned char mac_addr[ETH_ALEN];
+ int if_handle;
+ int pmac_id;
+ u16 vlan_tag;
+ u32 tx_rate;
};
-#define BE_INVALID_PMAC_ID 0xffffffff
+#define BE_FLAGS_LINK_STATUS_INIT 1
struct be_adapter {
struct pci_dev *pdev;
struct delayed_work work;
u16 work_counter;
+ u32 flags;
/* Ethtool knobs and info */
char fw_ver[FW_VER_LEN];
- u32 if_handle; /* Used to configure filtering */
+ int if_handle; /* Used to configure filtering */
u32 pmac_id; /* MAC addr handle used by BE card */
u32 beacon_state; /* for set_phys_id */
bool eeh_err;
+ bool ue_detected;
+ bool fw_timeout;
u32 port_num;
bool promiscuous;
bool wol;
u32 function_caps;
u32 rx_fc; /* Rx flow control */
u32 tx_fc; /* Tx flow control */
- bool ue_detected;
bool stats_cmd_sent;
int link_speed;
u8 port_type;
u32 flash_status;
struct completion flash_compl;
- bool be3_native;
- bool sriov_enabled;
- struct be_vf_cfg *vf_cfg;
+ u32 num_vfs;
u8 is_virtfn;
+ struct be_vf_cfg *vf_cfg;
+ bool be3_native;
u32 sli_family;
u8 hba_port_num;
u16 pvid;
};
#define be_physfn(adapter) (!adapter->is_virtfn)
+#define sriov_enabled(adapter) (adapter->num_vfs > 0)
+#define for_all_vfs(adapter, vf_cfg, i) \
+ for (i = 0, vf_cfg = &adapter->vf_cfg[i]; i < adapter->num_vfs; \
+ i++, vf_cfg++)
/* BladeEngine Generation numbers */
#define BE_GEN2 2
return adapter->num_rx_qs > 1;
}
+static inline bool be_error(struct be_adapter *adapter)
+{
+ return adapter->eeh_err || adapter->ue_detected || adapter->fw_timeout;
+}
+
extern void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm,
u16 num_popped);
-extern void be_link_status_update(struct be_adapter *adapter, u32 link_status);
+extern void be_link_status_update(struct be_adapter *adapter, u8 link_status);
extern void be_parse_stats(struct be_adapter *adapter);
extern int be_load_fw(struct be_adapter *adapter, u8 *func);
#endif /* BE_H */
struct be_queue_info *mccq = &adapter->mcc_obj.q;
u32 val = 0;
- if (adapter->eeh_err) {
- dev_info(&adapter->pdev->dev,
- "Error in Card Detected! Cannot issue commands\n");
+ if (be_error(adapter))
return;
- }
val |= mccq->id & DB_MCCQ_RING_ID_MASK;
val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT;
static void be_async_link_state_process(struct be_adapter *adapter,
struct be_async_event_link_state *evt)
{
- be_link_status_update(adapter, evt->port_link_status);
+ /* When link status changes, link speed must be re-queried from FW */
+ adapter->link_speed = -1;
+
+ /* For the initial link status do not rely on the ASYNC event as
+ * it may not be received in some cases.
+ */
+ if (adapter->flags & BE_FLAGS_LINK_STATUS_INIT)
+ be_link_status_update(adapter, evt->port_link_status);
}
/* Grp5 CoS Priority evt */
int i, num, status = 0;
struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
- if (adapter->eeh_err)
- return -EIO;
-
for (i = 0; i < mcc_timeout; i++) {
+ if (be_error(adapter))
+ return -EIO;
+
num = be_process_mcc(adapter, &status);
if (num)
be_cq_notify(adapter, mcc_obj->cq.id,
udelay(100);
}
if (i == mcc_timeout) {
- dev_err(&adapter->pdev->dev, "mccq poll timed out\n");
+ dev_err(&adapter->pdev->dev, "FW not responding\n");
+ adapter->fw_timeout = true;
return -1;
}
return status;
int msecs = 0;
u32 ready;
- if (adapter->eeh_err) {
- dev_err(&adapter->pdev->dev,
- "Error detected in card.Cannot issue commands\n");
- return -EIO;
- }
-
do {
+ if (be_error(adapter))
+ return -EIO;
+
ready = ioread32(db);
- if (ready == 0xffffffff) {
- dev_err(&adapter->pdev->dev,
- "pci slot disconnected\n");
+ if (ready == 0xffffffff)
return -1;
- }
ready &= MPU_MAILBOX_DB_RDY_MASK;
if (ready)
break;
if (msecs > 4000) {
- dev_err(&adapter->pdev->dev, "mbox poll timed out\n");
+ dev_err(&adapter->pdev->dev, "FW not responding\n");
+ adapter->fw_timeout = true;
be_detect_dump_ue(adapter);
return -1;
}
u8 *wrb;
int status;
- if (adapter->eeh_err)
- return -EIO;
-
if (mutex_lock_interruptible(&adapter->mbox_lock))
return -1;
/* Use MCC */
int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
- u8 type, bool permanent, u32 if_handle)
+ u8 type, bool permanent, u32 if_handle, u32 pmac_id)
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_mac_query *req;
req->permanent = 1;
} else {
req->if_id = cpu_to_le16((u16) if_handle);
+ req->pmac_id = cpu_to_le32(pmac_id);
req->permanent = 0;
}
}
/* Uses synchronous MCCQ */
-int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id, u32 dom)
+int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_pmac_del *req;
int status;
+ if (pmac_id == -1)
+ return 0;
+
spin_lock_bh(&adapter->mcc_lock);
wrb = wrb_from_mccq(adapter);
void *ctxt;
int status;
- if (mutex_lock_interruptible(&adapter->mbox_lock))
- return -1;
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
- wrb = wrb_from_mbox(adapter);
req = embedded_payload(wrb);
ctxt = &req->context;
be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
- status = be_mbox_notify_wait(adapter);
+ status = be_mcc_notify_wait(adapter);
if (!status) {
struct be_cmd_resp_eth_tx_create *resp = embedded_payload(wrb);
txq->id = le16_to_cpu(resp->cid);
txq->created = true;
}
- mutex_unlock(&adapter->mbox_lock);
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
return status;
}
u8 subsys = 0, opcode = 0;
int status;
- if (adapter->eeh_err)
- return -EIO;
-
if (mutex_lock_interruptible(&adapter->mbox_lock))
return -1;
}
/* Uses MCCQ */
-int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id, u32 domain)
+int be_cmd_if_destroy(struct be_adapter *adapter, int interface_id, u32 domain)
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_if_destroy *req;
int status;
- if (adapter->eeh_err)
- return -EIO;
-
- if (!interface_id)
+ if (interface_id == -1)
return 0;
spin_lock_bh(&adapter->mcc_lock);
/* Uses synchronous mcc */
int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
- u16 *link_speed, u32 dom)
+ u16 *link_speed, u8 *link_status, u32 dom)
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_link_status *req;
spin_lock_bh(&adapter->mcc_lock);
+ if (link_status)
+ *link_status = LINK_DOWN;
+
wrb = wrb_from_mccq(adapter);
if (!wrb) {
status = -EBUSY;
}
req = embedded_payload(wrb);
+ if (adapter->generation == BE_GEN3 || lancer_chip(adapter))
+ req->hdr.version = 1;
+
be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
OPCODE_COMMON_NTWK_LINK_STATUS_QUERY, sizeof(*req), wrb, NULL);
if (!status) {
struct be_cmd_resp_link_status *resp = embedded_payload(wrb);
if (resp->mac_speed != PHY_LINK_SPEED_ZERO) {
- *link_speed = le16_to_cpu(resp->link_speed);
+ if (link_speed)
+ *link_speed = le16_to_cpu(resp->link_speed);
if (mac_speed)
*mac_speed = resp->mac_speed;
}
+ if (link_status)
+ *link_status = resp->logical_link_status;
}
err:
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_rss_config *req;
- u32 myhash[10] = {0x0123, 0x4567, 0x89AB, 0xCDEF, 0x01EF,
- 0x0123, 0x4567, 0x89AB, 0xCDEF, 0x01EF};
+ u32 myhash[10] = {0x15d43fa5, 0x2534685a, 0x5f87693a, 0x5668494e,
+ 0x33cf6a53, 0x383334c6, 0x76ac4257, 0x59b242b2,
+ 0x3ea83c02, 0x4a110304};
int status;
if (mutex_lock_interruptible(&adapter->mbox_lock))
return status;
}
+int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
+ u32 data_size, u32 data_offset, const char *obj_name,
+ u32 *data_read, u32 *eof, u8 *addn_status)
+{
+ struct be_mcc_wrb *wrb;
+ struct lancer_cmd_req_read_object *req;
+ struct lancer_cmd_resp_read_object *resp;
+ int status;
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err_unlock;
+ }
+
+ req = embedded_payload(wrb);
+
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_READ_OBJECT,
+ sizeof(struct lancer_cmd_req_read_object), wrb,
+ NULL);
+
+ req->desired_read_len = cpu_to_le32(data_size);
+ req->read_offset = cpu_to_le32(data_offset);
+ strcpy(req->object_name, obj_name);
+ req->descriptor_count = cpu_to_le32(1);
+ req->buf_len = cpu_to_le32(data_size);
+ req->addr_low = cpu_to_le32((cmd->dma & 0xFFFFFFFF));
+ req->addr_high = cpu_to_le32(upper_32_bits(cmd->dma));
+
+ status = be_mcc_notify_wait(adapter);
+
+ resp = embedded_payload(wrb);
+ if (!status) {
+ *data_read = le32_to_cpu(resp->actual_read_len);
+ *eof = le32_to_cpu(resp->eof);
+ } else {
+ *addn_status = resp->additional_status;
+ }
+
+err_unlock:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd,
u32 flash_type, u32 flash_opcode, u32 buf_size)
{
mutex_unlock(&adapter->mbox_lock);
return status;
}
+
+/* Uses synchronous MCCQ */
+int be_cmd_get_mac_from_list(struct be_adapter *adapter, u32 domain,
+ u32 *pmac_id)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_get_mac_list *req;
+ int status;
+ int mac_count;
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+ req = embedded_payload(wrb);
+
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_GET_MAC_LIST, sizeof(*req),
+ wrb, NULL);
+
+ req->hdr.domain = domain;
+
+ status = be_mcc_notify_wait(adapter);
+ if (!status) {
+ struct be_cmd_resp_get_mac_list *resp =
+ embedded_payload(wrb);
+ int i;
+ u8 *ctxt = &resp->context[0][0];
+ status = -EIO;
+ mac_count = resp->mac_count;
+ be_dws_le_to_cpu(&resp->context, sizeof(resp->context));
+ for (i = 0; i < mac_count; i++) {
+ if (!AMAP_GET_BITS(struct amap_get_mac_list_context,
+ act, ctxt)) {
+ *pmac_id = AMAP_GET_BITS
+ (struct amap_get_mac_list_context,
+ macid, ctxt);
+ status = 0;
+ break;
+ }
+ ctxt += sizeof(struct amap_get_mac_list_context) / 8;
+ }
+ }
+
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
+/* Uses synchronous MCCQ */
+int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
+ u8 mac_count, u32 domain)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_set_mac_list *req;
+ int status;
+ struct be_dma_mem cmd;
+
+ memset(&cmd, 0, sizeof(struct be_dma_mem));
+ cmd.size = sizeof(struct be_cmd_req_set_mac_list);
+ cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
+ &cmd.dma, GFP_KERNEL);
+ if (!cmd.va) {
+ dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
+ return -ENOMEM;
+ }
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+
+ req = cmd.va;
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_SET_MAC_LIST, sizeof(*req),
+ wrb, &cmd);
+
+ req->hdr.domain = domain;
+ req->mac_count = mac_count;
+ if (mac_count)
+ memcpy(req->mac, mac_array, ETH_ALEN*mac_count);
+
+ status = be_mcc_notify_wait(adapter);
+
+err:
+ dma_free_coherent(&adapter->pdev->dev, cmd.size,
+ cmd.va, cmd.dma);
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
#define OPCODE_COMMON_GET_PHY_DETAILS 102
#define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP 103
#define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES 121
+#define OPCODE_COMMON_GET_MAC_LIST 147
+#define OPCODE_COMMON_SET_MAC_LIST 148
+#define OPCODE_COMMON_READ_OBJECT 171
#define OPCODE_COMMON_WRITE_OBJECT 172
#define OPCODE_ETH_RSS_CONFIG 1
u8 type;
u8 permanent;
u16 if_id;
+ u32 pmac_id;
} __packed;
struct be_cmd_resp_mac_query {
u8 mgmt_mac_duplex;
u8 mgmt_mac_speed;
u16 link_speed;
- u32 rsvd0;
+ u8 logical_link_status;
+ u8 rsvd1[3];
} __packed;
/******************** Port Identification ***************************/
u32 actual_write_len;
};
+/************************ Lancer Read FW info **************/
+#define LANCER_READ_FILE_CHUNK (32*1024)
+#define LANCER_READ_FILE_EOF_MASK 0x80000000
+
+#define LANCER_FW_DUMP_FILE "/dbg/dump.bin"
+#define LANCER_VPD_PF_FILE "/vpd/ntr_pf.vpd"
+#define LANCER_VPD_VF_FILE "/vpd/ntr_vf.vpd"
+
+struct lancer_cmd_req_read_object {
+ struct be_cmd_req_hdr hdr;
+ u32 desired_read_len;
+ u32 read_offset;
+ u8 object_name[104];
+ u32 descriptor_count;
+ u32 buf_len;
+ u32 addr_low;
+ u32 addr_high;
+};
+
+struct lancer_cmd_resp_read_object {
+ u8 opcode;
+ u8 subsystem;
+ u8 rsvd1[2];
+ u8 status;
+ u8 additional_status;
+ u8 rsvd2[2];
+ u32 resp_len;
+ u32 actual_resp_len;
+ u32 actual_read_len;
+ u32 eof;
+};
+
/************************ WOL *******************************/
struct be_cmd_req_acpi_wol_magic_config{
struct be_cmd_req_hdr hdr;
u8 rsvd[212];
};
+/******************** GET/SET_MACLIST **************************/
+#define BE_MAX_MAC 64
+struct amap_get_mac_list_context {
+ u8 macid[31];
+ u8 act;
+} __packed;
+
+struct be_cmd_req_get_mac_list {
+ struct be_cmd_req_hdr hdr;
+ u32 rsvd;
+} __packed;
+
+struct be_cmd_resp_get_mac_list {
+ struct be_cmd_resp_hdr hdr;
+ u8 mac_count;
+ u8 rsvd1;
+ u16 rsvd2;
+ u8 context[sizeof(struct amap_get_mac_list_context) / 8][BE_MAX_MAC];
+} __packed;
+
+struct be_cmd_req_set_mac_list {
+ struct be_cmd_req_hdr hdr;
+ u8 mac_count;
+ u8 rsvd1;
+ u16 rsvd2;
+ struct macaddr mac[BE_MAX_MAC];
+} __packed;
+
/*************** HW Stats Get v1 **********************************/
#define BE_TXP_SW_SZ 48
struct be_port_rxf_stats_v1 {
extern int be_pci_fnum_get(struct be_adapter *adapter);
extern int be_cmd_POST(struct be_adapter *adapter);
extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
- u8 type, bool permanent, u32 if_handle);
+ u8 type, bool permanent, u32 if_handle, u32 pmac_id);
extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
u32 if_id, u32 *pmac_id, u32 domain);
extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id,
- u32 pmac_id, u32 domain);
+ int pmac_id, u32 domain);
extern int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags,
u32 en_flags, u8 *mac, u32 *if_handle, u32 *pmac_id,
u32 domain);
-extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle,
+extern int be_cmd_if_destroy(struct be_adapter *adapter, int if_handle,
u32 domain);
extern int be_cmd_eq_create(struct be_adapter *adapter,
struct be_queue_info *eq, int eq_delay);
int type);
extern int be_cmd_rxq_destroy(struct be_adapter *adapter,
struct be_queue_info *q);
-extern int be_cmd_link_status_query(struct be_adapter *adapter,
- u8 *mac_speed, u16 *link_speed, u32 dom);
+extern int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
+ u16 *link_speed, u8 *link_status, u32 dom);
extern int be_cmd_reset(struct be_adapter *adapter);
extern int be_cmd_get_stats(struct be_adapter *adapter,
struct be_dma_mem *nonemb_cmd);
u32 data_size, u32 data_offset,
const char *obj_name,
u32 *data_written, u8 *addn_status);
+int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
+ u32 data_size, u32 data_offset, const char *obj_name,
+ u32 *data_read, u32 *eof, u8 *addn_status);
int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
int offset);
extern int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
extern int be_cmd_req_native_mode(struct be_adapter *adapter);
extern int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size);
extern void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf);
+extern int be_cmd_get_mac_from_list(struct be_adapter *adapter, u32 domain,
+ u32 *pmac_id);
+extern int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
+ u8 mac_count, u32 domain);
memset(fw_on_flash, 0 , sizeof(fw_on_flash));
be_cmd_get_fw_ver(adapter, adapter->fw_ver, fw_on_flash);
- strcpy(drvinfo->driver, DRV_NAME);
- strcpy(drvinfo->version, DRV_VER);
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VER, sizeof(drvinfo->version));
strncpy(drvinfo->fw_version, adapter->fw_ver, FW_VER_LEN);
if (memcmp(adapter->fw_ver, fw_on_flash, FW_VER_LEN) != 0) {
strcat(drvinfo->fw_version, " [");
strcat(drvinfo->fw_version, "]");
}
- strcpy(drvinfo->bus_info, pci_name(adapter->pdev));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->testinfo_len = 0;
drvinfo->regdump_len = 0;
drvinfo->eedump_len = 0;
}
+static u32
+lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name)
+{
+ u32 data_read = 0, eof;
+ u8 addn_status;
+ struct be_dma_mem data_len_cmd;
+ int status;
+
+ memset(&data_len_cmd, 0, sizeof(data_len_cmd));
+ /* data_offset and data_size should be 0 to get reg len */
+ status = lancer_cmd_read_object(adapter, &data_len_cmd, 0, 0,
+ file_name, &data_read, &eof, &addn_status);
+
+ return data_read;
+}
+
+static int
+lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
+ u32 buf_len, void *buf)
+{
+ struct be_dma_mem read_cmd;
+ u32 read_len = 0, total_read_len = 0, chunk_size;
+ u32 eof = 0;
+ u8 addn_status;
+ int status = 0;
+
+ read_cmd.size = LANCER_READ_FILE_CHUNK;
+ read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
+ &read_cmd.dma);
+
+ if (!read_cmd.va) {
+ dev_err(&adapter->pdev->dev,
+ "Memory allocation failure while reading dump\n");
+ return -ENOMEM;
+ }
+
+ while ((total_read_len < buf_len) && !eof) {
+ chunk_size = min_t(u32, (buf_len - total_read_len),
+ LANCER_READ_FILE_CHUNK);
+ chunk_size = ALIGN(chunk_size, 4);
+ status = lancer_cmd_read_object(adapter, &read_cmd, chunk_size,
+ total_read_len, file_name, &read_len,
+ &eof, &addn_status);
+ if (!status) {
+ memcpy(buf + total_read_len, read_cmd.va, read_len);
+ total_read_len += read_len;
+ eof &= LANCER_READ_FILE_EOF_MASK;
+ } else {
+ status = -EIO;
+ break;
+ }
+ }
+ pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
+ read_cmd.dma);
+
+ return status;
+}
+
static int
be_get_reg_len(struct net_device *netdev)
{
struct be_adapter *adapter = netdev_priv(netdev);
u32 log_size = 0;
- if (be_physfn(adapter))
- be_cmd_get_reg_len(adapter, &log_size);
-
+ if (be_physfn(adapter)) {
+ if (lancer_chip(adapter))
+ log_size = lancer_cmd_get_file_len(adapter,
+ LANCER_FW_DUMP_FILE);
+ else
+ be_cmd_get_reg_len(adapter, &log_size);
+ }
return log_size;
}
if (be_physfn(adapter)) {
memset(buf, 0, regs->len);
- be_cmd_get_regs(adapter, regs->len, buf);
+ if (lancer_chip(adapter))
+ lancer_cmd_read_file(adapter, LANCER_FW_DUMP_FILE,
+ regs->len, buf);
+ else
+ be_cmd_get_regs(adapter, regs->len, buf);
}
}
struct be_phy_info phy_info;
u8 mac_speed = 0;
u16 link_speed = 0;
+ u8 link_status;
int status;
if ((adapter->link_speed < 0) || (!(netdev->flags & IFF_UP))) {
status = be_cmd_link_status_query(adapter, &mac_speed,
- &link_speed, 0);
+ &link_speed, &link_status, 0);
+ if (!status)
+ be_link_status_update(adapter, link_status);
/* link_speed is in units of 10 Mbps */
if (link_speed) {
return 0;
}
-static void
-be_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
+static void be_get_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
{
struct be_adapter *adapter = netdev_priv(netdev);
- ring->rx_max_pending = adapter->rx_obj[0].q.len;
- ring->tx_max_pending = adapter->tx_obj[0].q.len;
-
- ring->rx_pending = atomic_read(&adapter->rx_obj[0].q.used);
- ring->tx_pending = atomic_read(&adapter->tx_obj[0].q.used);
+ ring->rx_max_pending = ring->rx_pending = adapter->rx_obj[0].q.len;
+ ring->tx_max_pending = ring->tx_pending = adapter->tx_obj[0].q.len;
}
static void
}
if (be_cmd_link_status_query(adapter, &mac_speed,
- &qos_link_speed, 0) != 0) {
+ &qos_link_speed, NULL, 0) != 0) {
test->flags |= ETH_TEST_FL_FAILED;
data[4] = -1;
} else if (!mac_speed) {
static int
be_get_eeprom_len(struct net_device *netdev)
{
- return BE_READ_SEEPROM_LEN;
+ struct be_adapter *adapter = netdev_priv(netdev);
+ if (lancer_chip(adapter)) {
+ if (be_physfn(adapter))
+ return lancer_cmd_get_file_len(adapter,
+ LANCER_VPD_PF_FILE);
+ else
+ return lancer_cmd_get_file_len(adapter,
+ LANCER_VPD_VF_FILE);
+ } else {
+ return BE_READ_SEEPROM_LEN;
+ }
}
static int
if (!eeprom->len)
return -EINVAL;
+ if (lancer_chip(adapter)) {
+ if (be_physfn(adapter))
+ return lancer_cmd_read_file(adapter, LANCER_VPD_PF_FILE,
+ eeprom->len, data);
+ else
+ return lancer_cmd_read_file(adapter, LANCER_VPD_VF_FILE,
+ eeprom->len, data);
+ }
+
eeprom->magic = BE_VENDOR_ID | (adapter->pdev->device<<16);
memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
MODULE_AUTHOR("ServerEngines Corporation");
MODULE_LICENSE("GPL");
-static ushort rx_frag_size = 2048;
static unsigned int num_vfs;
-module_param(rx_frag_size, ushort, S_IRUGO);
module_param(num_vfs, uint, S_IRUGO);
-MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
MODULE_PARM_DESC(num_vfs, "Number of PCI VFs to initialize");
+static ushort rx_frag_size = 2048;
+module_param(rx_frag_size, ushort, S_IRUGO);
+MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
+
static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
+ { PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
{ 0 }
};
MODULE_DEVICE_TABLE(pci, be_dev_ids);
return -EADDRNOTAVAIL;
status = be_cmd_mac_addr_query(adapter, current_mac,
- MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);
+ MAC_ADDRESS_TYPE_NETWORK, false,
+ adapter->if_handle, 0);
if (status)
goto err;
struct be_drv_stats *drvs = &adapter->drv_stats;
be_dws_le_to_cpu(hw_stats, sizeof(*hw_stats));
+ drvs->pmem_fifo_overflow_drop = port_stats->pmem_fifo_overflow_drop;
+ drvs->rx_priority_pause_frames = port_stats->rx_priority_pause_frames;
drvs->rx_pause_frames = port_stats->rx_pause_frames;
drvs->rx_crc_errors = port_stats->rx_crc_errors;
drvs->rx_control_frames = port_stats->rx_control_frames;
return stats;
}
-void be_link_status_update(struct be_adapter *adapter, u32 link_status)
+void be_link_status_update(struct be_adapter *adapter, u8 link_status)
{
struct net_device *netdev = adapter->netdev;
- /* when link status changes, link speed must be re-queried from card */
- adapter->link_speed = -1;
- if ((link_status & LINK_STATUS_MASK) == LINK_UP) {
- netif_carrier_on(netdev);
- dev_info(&adapter->pdev->dev, "%s: Link up\n", netdev->name);
- } else {
+ if (!(adapter->flags & BE_FLAGS_LINK_STATUS_INIT)) {
netif_carrier_off(netdev);
- dev_info(&adapter->pdev->dev, "%s: Link down\n", netdev->name);
+ adapter->flags |= BE_FLAGS_LINK_STATUS_INIT;
}
+
+ if ((link_status & LINK_STATUS_MASK) == LINK_UP)
+ netif_carrier_on(netdev);
+ else
+ netif_carrier_off(netdev);
}
static void be_tx_stats_update(struct be_tx_obj *txo,
wrb->frag_len = len & ETH_WRB_FRAG_LEN_MASK;
}
+static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
+ struct sk_buff *skb)
+{
+ u8 vlan_prio;
+ u16 vlan_tag;
+
+ vlan_tag = vlan_tx_tag_get(skb);
+ vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+ /* If vlan priority provided by OS is NOT in available bmap */
+ if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
+ vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
+ adapter->recommended_prio;
+
+ return vlan_tag;
+}
+
static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
struct sk_buff *skb, u32 wrb_cnt, u32 len)
{
- u8 vlan_prio = 0;
- u16 vlan_tag = 0;
+ u16 vlan_tag;
memset(hdr, 0, sizeof(*hdr));
if (vlan_tx_tag_present(skb)) {
AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan, hdr, 1);
- vlan_tag = vlan_tx_tag_get(skb);
- vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
- /* If vlan priority provided by OS is NOT in available bmap */
- if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
- vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
- adapter->recommended_prio;
+ vlan_tag = be_get_tx_vlan_tag(adapter, skb);
AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan_tag, hdr, vlan_tag);
}
u32 start = txq->head;
bool dummy_wrb, stopped = false;
+ /* For vlan tagged pkts, BE
+ * 1) calculates checksum even when CSO is not requested
+ * 2) calculates checksum wrongly for padded pkt less than
+ * 60 bytes long.
+ * As a workaround disable TX vlan offloading in such cases.
+ */
+ if (unlikely(vlan_tx_tag_present(skb) &&
+ (skb->ip_summed != CHECKSUM_PARTIAL || skb->len <= 60))) {
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ goto tx_drop;
+
+ skb = __vlan_put_tag(skb, be_get_tx_vlan_tag(adapter, skb));
+ if (unlikely(!skb))
+ goto tx_drop;
+
+ skb->vlan_tci = 0;
+ }
+
wrb_cnt = wrb_cnt_for_skb(adapter, skb, &dummy_wrb);
copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb);
txq->head = start;
dev_kfree_skb_any(skb);
}
+tx_drop:
return NETDEV_TX_OK;
}
*/
static int be_vid_config(struct be_adapter *adapter, bool vf, u32 vf_num)
{
+ struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf_num];
u16 vtag[BE_NUM_VLANS_SUPPORTED];
u16 ntags = 0, i;
int status = 0;
- u32 if_handle;
if (vf) {
- if_handle = adapter->vf_cfg[vf_num].vf_if_handle;
- vtag[0] = cpu_to_le16(adapter->vf_cfg[vf_num].vf_vlan_tag);
- status = be_cmd_vlan_config(adapter, if_handle, vtag, 1, 1, 0);
+ vtag[0] = cpu_to_le16(vf_cfg->vlan_tag);
+ status = be_cmd_vlan_config(adapter, vf_cfg->if_handle, vtag,
+ 1, 1, 0);
}
/* No need to further configure vids if in promiscuous mode */
return status;
}
-static void be_vlan_add_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_add_vid(struct net_device *netdev, u16 vid)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ int status = 0;
- adapter->vlans_added++;
- if (!be_physfn(adapter))
- return;
+ if (!be_physfn(adapter)) {
+ status = -EINVAL;
+ goto ret;
+ }
adapter->vlan_tag[vid] = 1;
if (adapter->vlans_added <= (adapter->max_vlans + 1))
- be_vid_config(adapter, false, 0);
+ status = be_vid_config(adapter, false, 0);
+
+ if (!status)
+ adapter->vlans_added++;
+ else
+ adapter->vlan_tag[vid] = 0;
+ret:
+ return status;
}
-static void be_vlan_rem_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_rem_vid(struct net_device *netdev, u16 vid)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ int status = 0;
- adapter->vlans_added--;
-
- if (!be_physfn(adapter))
- return;
+ if (!be_physfn(adapter)) {
+ status = -EINVAL;
+ goto ret;
+ }
adapter->vlan_tag[vid] = 0;
if (adapter->vlans_added <= adapter->max_vlans)
- be_vid_config(adapter, false, 0);
+ status = be_vid_config(adapter, false, 0);
+
+ if (!status)
+ adapter->vlans_added--;
+ else
+ adapter->vlan_tag[vid] = 1;
+ret:
+ return status;
}
static void be_set_rx_mode(struct net_device *netdev)
static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
int status;
- if (!adapter->sriov_enabled)
+ if (!sriov_enabled(adapter))
return -EPERM;
- if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
+ if (!is_valid_ether_addr(mac) || vf >= adapter->num_vfs)
return -EINVAL;
- if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID)
- status = be_cmd_pmac_del(adapter,
- adapter->vf_cfg[vf].vf_if_handle,
- adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
+ if (lancer_chip(adapter)) {
+ status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1);
+ } else {
+ status = be_cmd_pmac_del(adapter, vf_cfg->if_handle,
+ vf_cfg->pmac_id, vf + 1);
- status = be_cmd_pmac_add(adapter, mac,
- adapter->vf_cfg[vf].vf_if_handle,
- &adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
+ status = be_cmd_pmac_add(adapter, mac, vf_cfg->if_handle,
+ &vf_cfg->pmac_id, vf + 1);
+ }
if (status)
dev_err(&adapter->pdev->dev, "MAC %pM set on VF %d Failed\n",
mac, vf);
else
- memcpy(adapter->vf_cfg[vf].vf_mac_addr, mac, ETH_ALEN);
+ memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
return status;
}
struct ifla_vf_info *vi)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
- if (!adapter->sriov_enabled)
+ if (!sriov_enabled(adapter))
return -EPERM;
- if (vf >= num_vfs)
+ if (vf >= adapter->num_vfs)
return -EINVAL;
vi->vf = vf;
- vi->tx_rate = adapter->vf_cfg[vf].vf_tx_rate;
- vi->vlan = adapter->vf_cfg[vf].vf_vlan_tag;
+ vi->tx_rate = vf_cfg->tx_rate;
+ vi->vlan = vf_cfg->vlan_tag;
vi->qos = 0;
- memcpy(&vi->mac, adapter->vf_cfg[vf].vf_mac_addr, ETH_ALEN);
+ memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN);
return 0;
}
struct be_adapter *adapter = netdev_priv(netdev);
int status = 0;
- if (!adapter->sriov_enabled)
+ if (!sriov_enabled(adapter))
return -EPERM;
- if ((vf >= num_vfs) || (vlan > 4095))
+ if (vf >= adapter->num_vfs || vlan > 4095)
return -EINVAL;
if (vlan) {
- adapter->vf_cfg[vf].vf_vlan_tag = vlan;
+ adapter->vf_cfg[vf].vlan_tag = vlan;
adapter->vlans_added++;
} else {
- adapter->vf_cfg[vf].vf_vlan_tag = 0;
+ adapter->vf_cfg[vf].vlan_tag = 0;
adapter->vlans_added--;
}
struct be_adapter *adapter = netdev_priv(netdev);
int status = 0;
- if (!adapter->sriov_enabled)
+ if (!sriov_enabled(adapter))
return -EPERM;
- if ((vf >= num_vfs) || (rate < 0))
+ if (vf >= adapter->num_vfs)
return -EINVAL;
- if (rate > 10000)
- rate = 10000;
+ if (rate < 100 || rate > 10000) {
+ dev_err(&adapter->pdev->dev,
+ "tx rate must be between 100 and 10000 Mbps\n");
+ return -EINVAL;
+ }
- adapter->vf_cfg[vf].vf_tx_rate = rate;
status = be_cmd_set_qos(adapter, rate / 10, vf + 1);
if (status)
- dev_info(&adapter->pdev->dev,
+ dev_err(&adapter->pdev->dev,
"tx rate %d on VF %d failed\n", rate, vf);
+ else
+ adapter->vf_cfg[vf].tx_rate = rate;
return status;
}
static int be_num_txqs_want(struct be_adapter *adapter)
{
- if ((num_vfs && adapter->sriov_enabled) ||
- be_is_mc(adapter) ||
+ if (sriov_enabled(adapter) || be_is_mc(adapter) ||
lancer_chip(adapter) || !be_physfn(adapter) ||
adapter->generation == BE_GEN2)
return 1;
u8 i;
adapter->num_tx_qs = be_num_txqs_want(adapter);
- if (adapter->num_tx_qs != MAX_TX_QS)
+ if (adapter->num_tx_qs != MAX_TX_QS) {
+ rtnl_lock();
netif_set_real_num_tx_queues(adapter->netdev,
adapter->num_tx_qs);
+ rtnl_unlock();
+ }
adapter->tx_eq.max_eqd = 0;
adapter->tx_eq.min_eqd = 0;
if (be_queue_alloc(adapter, q, TX_Q_LEN,
sizeof(struct be_eth_wrb)))
goto err;
-
- if (be_cmd_txq_create(adapter, q, cq))
- goto err;
}
return 0;
static u32 be_num_rxqs_want(struct be_adapter *adapter)
{
if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
- !adapter->sriov_enabled && be_physfn(adapter) &&
- !be_is_mc(adapter)) {
+ !sriov_enabled(adapter) && be_physfn(adapter) &&
+ !be_is_mc(adapter)) {
return 1 + MAX_RSS_QS; /* one default non-RSS queue */
} else {
dev_warn(&adapter->pdev->dev,
struct be_eq_obj *tx_eq = container_of(napi, struct be_eq_obj, napi);
struct be_adapter *adapter =
container_of(tx_eq, struct be_adapter, tx_eq);
+ struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
struct be_tx_obj *txo;
struct be_eth_tx_compl *txcp;
int tx_compl, mcc_compl, status = 0;
mcc_compl = be_process_mcc(adapter, &status);
if (mcc_compl) {
- struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
be_cq_notify(adapter, mcc_obj->cq.id, true, mcc_compl);
}
napi_complete(napi);
+ /* Arm CQ again to regenerate EQEs for Lancer in INTx mode */
+ if (lancer_chip(adapter) && !msix_enabled(adapter)) {
+ for_all_tx_queues(adapter, txo, i)
+ be_cq_notify(adapter, txo->cq.id, true, 0);
+
+ be_cq_notify(adapter, mcc_obj->cq.id, true, 0);
+ }
+
be_eq_notify(adapter, tx_eq->q.id, true, false, 0);
adapter->drv_stats.tx_events++;
return 1;
u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
u32 i;
+ if (adapter->eeh_err || adapter->ue_detected)
+ return;
+
if (lancer_chip(adapter)) {
sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
sliport_status & SLIPORT_STATUS_ERR_MASK) {
adapter->ue_detected = true;
adapter->eeh_err = true;
- dev_err(&adapter->pdev->dev, "UE Detected!!\n");
+ dev_err(&adapter->pdev->dev,
+ "Unrecoverable error in the card\n");
}
if (ue_lo) {
}
}
-static void be_worker(struct work_struct *work)
-{
- struct be_adapter *adapter =
- container_of(work, struct be_adapter, work.work);
- struct be_rx_obj *rxo;
- int i;
-
- if (!adapter->ue_detected)
- be_detect_dump_ue(adapter);
-
- /* when interrupts are not yet enabled, just reap any pending
- * mcc completions */
- if (!netif_running(adapter->netdev)) {
- int mcc_compl, status = 0;
-
- mcc_compl = be_process_mcc(adapter, &status);
-
- if (mcc_compl) {
- struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
- be_cq_notify(adapter, mcc_obj->cq.id, false, mcc_compl);
- }
-
- goto reschedule;
- }
-
- if (!adapter->stats_cmd_sent) {
- if (lancer_chip(adapter))
- lancer_cmd_get_pport_stats(adapter,
- &adapter->stats_cmd);
- else
- be_cmd_get_stats(adapter, &adapter->stats_cmd);
- }
-
- for_all_rx_queues(adapter, rxo, i) {
- be_rx_eqd_update(adapter, rxo);
-
- if (rxo->rx_post_starved) {
- rxo->rx_post_starved = false;
- be_post_rx_frags(rxo, GFP_KERNEL);
- }
- }
-
-reschedule:
- adapter->work_counter++;
- schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
-}
-
static void be_msix_disable(struct be_adapter *adapter)
{
if (msix_enabled(adapter)) {
static int be_sriov_enable(struct be_adapter *adapter)
{
be_check_sriov_fn_type(adapter);
+
#ifdef CONFIG_PCI_IOV
if (be_physfn(adapter) && num_vfs) {
int status, pos;
- u16 nvfs;
+ u16 dev_vfs;
pos = pci_find_ext_capability(adapter->pdev,
PCI_EXT_CAP_ID_SRIOV);
pci_read_config_word(adapter->pdev,
- pos + PCI_SRIOV_TOTAL_VF, &nvfs);
+ pos + PCI_SRIOV_TOTAL_VF, &dev_vfs);
- if (num_vfs > nvfs) {
+ adapter->num_vfs = min_t(u16, num_vfs, dev_vfs);
+ if (adapter->num_vfs != num_vfs)
dev_info(&adapter->pdev->dev,
- "Device supports %d VFs and not %d\n",
- nvfs, num_vfs);
- num_vfs = nvfs;
- }
+ "Device supports %d VFs and not %d\n",
+ adapter->num_vfs, num_vfs);
- status = pci_enable_sriov(adapter->pdev, num_vfs);
- adapter->sriov_enabled = status ? false : true;
+ status = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+ if (status)
+ adapter->num_vfs = 0;
- if (adapter->sriov_enabled) {
+ if (adapter->num_vfs) {
adapter->vf_cfg = kcalloc(num_vfs,
sizeof(struct be_vf_cfg),
GFP_KERNEL);
static void be_sriov_disable(struct be_adapter *adapter)
{
#ifdef CONFIG_PCI_IOV
- if (adapter->sriov_enabled) {
+ if (sriov_enabled(adapter)) {
pci_disable_sriov(adapter->pdev);
kfree(adapter->vf_cfg);
- adapter->sriov_enabled = false;
+ adapter->num_vfs = 0;
}
#endif
}
static int be_rx_queues_setup(struct be_adapter *adapter)
{
struct be_rx_obj *rxo;
- int rc, i;
- u8 rsstable[MAX_RSS_QS];
+ int rc, i, j;
+ u8 rsstable[128];
for_all_rx_queues(adapter, rxo, i) {
rc = be_cmd_rxq_create(adapter, &rxo->q, rxo->cq.id,
}
if (be_multi_rxq(adapter)) {
- for_all_rss_queues(adapter, rxo, i)
- rsstable[i] = rxo->rss_id;
+ for (j = 0; j < 128; j += adapter->num_rx_qs - 1) {
+ for_all_rss_queues(adapter, rxo, i) {
+ if ((j + i) >= 128)
+ break;
+ rsstable[j + i] = rxo->rss_id;
+ }
+ }
+ rc = be_cmd_rss_config(adapter, rsstable, 128);
- rc = be_cmd_rss_config(adapter, rsstable,
- adapter->num_rx_qs - 1);
if (rc)
return rc;
}
struct be_adapter *adapter = netdev_priv(netdev);
struct be_eq_obj *tx_eq = &adapter->tx_eq;
struct be_rx_obj *rxo;
+ u8 link_status;
int status, i;
status = be_rx_queues_setup(adapter);
/* Now that interrupts are on we can process async mcc */
be_async_mcc_enable(adapter);
+ status = be_cmd_link_status_query(adapter, NULL, NULL,
+ &link_status, 0);
+ if (!status)
+ be_link_status_update(adapter, link_status);
+
return 0;
err:
be_close(adapter->netdev);
u32 vf;
int status = 0;
u8 mac[ETH_ALEN];
+ struct be_vf_cfg *vf_cfg;
be_vf_eth_addr_generate(adapter, mac);
- for (vf = 0; vf < num_vfs; vf++) {
- status = be_cmd_pmac_add(adapter, mac,
- adapter->vf_cfg[vf].vf_if_handle,
- &adapter->vf_cfg[vf].vf_pmac_id,
- vf + 1);
+ for_all_vfs(adapter, vf_cfg, vf) {
+ if (lancer_chip(adapter)) {
+ status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1);
+ } else {
+ status = be_cmd_pmac_add(adapter, mac,
+ vf_cfg->if_handle,
+ &vf_cfg->pmac_id, vf + 1);
+ }
+
if (status)
dev_err(&adapter->pdev->dev,
- "Mac address add failed for VF %d\n", vf);
+ "Mac address assignment failed for VF %d\n", vf);
else
- memcpy(adapter->vf_cfg[vf].vf_mac_addr, mac, ETH_ALEN);
+ memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
mac[5] += 1;
}
static void be_vf_clear(struct be_adapter *adapter)
{
+ struct be_vf_cfg *vf_cfg;
u32 vf;
- for (vf = 0; vf < num_vfs; vf++) {
- if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID)
- be_cmd_pmac_del(adapter,
- adapter->vf_cfg[vf].vf_if_handle,
- adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
- }
+ for_all_vfs(adapter, vf_cfg, vf) {
+ if (lancer_chip(adapter))
+ be_cmd_set_mac_list(adapter, NULL, 0, vf + 1);
+ else
+ be_cmd_pmac_del(adapter, vf_cfg->if_handle,
+ vf_cfg->pmac_id, vf + 1);
- for (vf = 0; vf < num_vfs; vf++)
- if (adapter->vf_cfg[vf].vf_if_handle)
- be_cmd_if_destroy(adapter,
- adapter->vf_cfg[vf].vf_if_handle, vf + 1);
+ be_cmd_if_destroy(adapter, vf_cfg->if_handle, vf + 1);
+ }
}
static int be_clear(struct be_adapter *adapter)
{
- if (be_physfn(adapter) && adapter->sriov_enabled)
+ if (sriov_enabled(adapter))
be_vf_clear(adapter);
be_cmd_if_destroy(adapter, adapter->if_handle, 0);
be_mcc_queues_destroy(adapter);
be_rx_queues_destroy(adapter);
be_tx_queues_destroy(adapter);
- adapter->eq_next_idx = 0;
-
- adapter->be3_native = false;
- adapter->promiscuous = false;
/* tell fw we're done with firing cmds */
be_cmd_fw_clean(adapter);
return 0;
}
+static void be_vf_setup_init(struct be_adapter *adapter)
+{
+ struct be_vf_cfg *vf_cfg;
+ int vf;
+
+ for_all_vfs(adapter, vf_cfg, vf) {
+ vf_cfg->if_handle = -1;
+ vf_cfg->pmac_id = -1;
+ }
+}
+
static int be_vf_setup(struct be_adapter *adapter)
{
+ struct be_vf_cfg *vf_cfg;
u32 cap_flags, en_flags, vf;
u16 lnk_speed;
int status;
- cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST;
- for (vf = 0; vf < num_vfs; vf++) {
+ be_vf_setup_init(adapter);
+
+ cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
+ BE_IF_FLAGS_MULTICAST;
+ for_all_vfs(adapter, vf_cfg, vf) {
status = be_cmd_if_create(adapter, cap_flags, en_flags, NULL,
- &adapter->vf_cfg[vf].vf_if_handle,
- NULL, vf+1);
+ &vf_cfg->if_handle, NULL, vf + 1);
if (status)
goto err;
- adapter->vf_cfg[vf].vf_pmac_id = BE_INVALID_PMAC_ID;
}
- if (!lancer_chip(adapter)) {
- status = be_vf_eth_addr_config(adapter);
- if (status)
- goto err;
- }
+ status = be_vf_eth_addr_config(adapter);
+ if (status)
+ goto err;
- for (vf = 0; vf < num_vfs; vf++) {
+ for_all_vfs(adapter, vf_cfg, vf) {
status = be_cmd_link_status_query(adapter, NULL, &lnk_speed,
- vf + 1);
+ NULL, vf + 1);
if (status)
goto err;
- adapter->vf_cfg[vf].vf_tx_rate = lnk_speed * 10;
+ vf_cfg->tx_rate = lnk_speed * 10;
}
return 0;
err:
return status;
}
+static void be_setup_init(struct be_adapter *adapter)
+{
+ adapter->vlan_prio_bmap = 0xff;
+ adapter->link_speed = -1;
+ adapter->if_handle = -1;
+ adapter->be3_native = false;
+ adapter->promiscuous = false;
+ adapter->eq_next_idx = 0;
+}
+
+static int be_configure_mac_from_list(struct be_adapter *adapter, u8 *mac)
+{
+ u32 pmac_id;
+ int status = be_cmd_get_mac_from_list(adapter, 0, &pmac_id);
+ if (status != 0)
+ goto do_none;
+ status = be_cmd_mac_addr_query(adapter, mac,
+ MAC_ADDRESS_TYPE_NETWORK,
+ false, adapter->if_handle, pmac_id);
+ if (status != 0)
+ goto do_none;
+ status = be_cmd_pmac_add(adapter, mac, adapter->if_handle,
+ &adapter->pmac_id, 0);
+do_none:
+ return status;
+}
+
static int be_setup(struct be_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
u32 cap_flags, en_flags;
u32 tx_fc, rx_fc;
- int status;
+ int status, i;
u8 mac[ETH_ALEN];
+ struct be_tx_obj *txo;
- /* Allow all priorities by default. A GRP5 evt may modify this */
- adapter->vlan_prio_bmap = 0xff;
- adapter->link_speed = -1;
+ be_setup_init(adapter);
be_cmd_req_native_mode(adapter);
memset(mac, 0, ETH_ALEN);
status = be_cmd_mac_addr_query(adapter, mac, MAC_ADDRESS_TYPE_NETWORK,
- true /*permanent */, 0);
+ true /*permanent */, 0, 0);
if (status)
return status;
memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
cap_flags = en_flags | BE_IF_FLAGS_MCAST_PROMISCUOUS |
- BE_IF_FLAGS_PROMISCUOUS;
+ BE_IF_FLAGS_VLAN_PROMISCUOUS | BE_IF_FLAGS_PROMISCUOUS;
+
if (adapter->function_caps & BE_FUNCTION_CAPS_RSS) {
cap_flags |= BE_IF_FLAGS_RSS;
en_flags |= BE_IF_FLAGS_RSS;
if (status != 0)
goto err;
- /* For BEx, the VF's permanent mac queried from card is incorrect.
- * Query the mac configued by the PF using if_handle
- */
- if (!be_physfn(adapter) && !lancer_chip(adapter)) {
- status = be_cmd_mac_addr_query(adapter, mac,
- MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);
+ for_all_tx_queues(adapter, txo, i) {
+ status = be_cmd_txq_create(adapter, &txo->q, &txo->cq);
+ if (status)
+ goto err;
+ }
+
+ /* The VF's permanent mac queried from card is incorrect.
+ * For BEx: Query the mac configued by the PF using if_handle
+ * For Lancer: Get and use mac_list to obtain mac address.
+ */
+ if (!be_physfn(adapter)) {
+ if (lancer_chip(adapter))
+ status = be_configure_mac_from_list(adapter, mac);
+ else
+ status = be_cmd_mac_addr_query(adapter, mac,
+ MAC_ADDRESS_TYPE_NETWORK, false,
+ adapter->if_handle, 0);
if (!status) {
memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
be_set_rx_mode(adapter->netdev);
status = be_cmd_get_flow_control(adapter, &tx_fc, &rx_fc);
- if (status)
+ /* For Lancer: It is legal for this cmd to fail on VF */
+ if (status && (be_physfn(adapter) || !lancer_chip(adapter)))
goto err;
+
if (rx_fc != adapter->rx_fc || tx_fc != adapter->tx_fc) {
status = be_cmd_set_flow_control(adapter, adapter->tx_fc,
adapter->rx_fc);
- if (status)
+ /* For Lancer: It is legal for this cmd to fail on VF */
+ if (status && (be_physfn(adapter) || !lancer_chip(adapter)))
goto err;
}
pcie_set_readrq(adapter->pdev, 4096);
- if (be_physfn(adapter) && adapter->sriov_enabled) {
+ if (sriov_enabled(adapter)) {
status = be_vf_setup(adapter);
if (status)
goto err;
return status;
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void be_netpoll(struct net_device *netdev)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+ struct be_rx_obj *rxo;
+ int i;
+
+ event_handle(adapter, &adapter->tx_eq, false);
+ for_all_rx_queues(adapter, rxo, i)
+ event_handle(adapter, &rxo->rx_eq, true);
+}
+#endif
+
#define FW_FILE_HDR_SIGN "ServerEngines Corp. "
static bool be_flash_redboot(struct be_adapter *adapter,
const u8 *p, u32 img_start, int image_size,
.ndo_set_vf_mac = be_set_vf_mac,
.ndo_set_vf_vlan = be_set_vf_vlan,
.ndo_set_vf_tx_rate = be_set_vf_tx_rate,
- .ndo_get_vf_config = be_get_vf_config
+ .ndo_get_vf_config = be_get_vf_config,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = be_netpoll,
+#endif
};
static void be_netdev_init(struct net_device *netdev)
break;
case BE_DEVICE_ID2:
case OC_DEVICE_ID2:
+ case OC_DEVICE_ID5:
adapter->generation = BE_GEN3;
break;
case OC_DEVICE_ID3:
static int lancer_wait_ready(struct be_adapter *adapter)
{
-#define SLIPORT_READY_TIMEOUT 500
+#define SLIPORT_READY_TIMEOUT 30
u32 sliport_status;
int status = 0, i;
if (sliport_status & SLIPORT_STATUS_RDY_MASK)
break;
- msleep(20);
+ msleep(1000);
}
if (i == SLIPORT_READY_TIMEOUT)
return status;
}
+static void lancer_test_and_recover_fn_err(struct be_adapter *adapter)
+{
+ int status;
+ u32 sliport_status;
+
+ if (adapter->eeh_err || adapter->ue_detected)
+ return;
+
+ sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
+
+ if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
+ dev_err(&adapter->pdev->dev,
+ "Adapter in error state."
+ "Trying to recover.\n");
+
+ status = lancer_test_and_set_rdy_state(adapter);
+ if (status)
+ goto err;
+
+ netif_device_detach(adapter->netdev);
+
+ if (netif_running(adapter->netdev))
+ be_close(adapter->netdev);
+
+ be_clear(adapter);
+
+ adapter->fw_timeout = false;
+
+ status = be_setup(adapter);
+ if (status)
+ goto err;
+
+ if (netif_running(adapter->netdev)) {
+ status = be_open(adapter->netdev);
+ if (status)
+ goto err;
+ }
+
+ netif_device_attach(adapter->netdev);
+
+ dev_err(&adapter->pdev->dev,
+ "Adapter error recovery succeeded\n");
+ }
+ return;
+err:
+ dev_err(&adapter->pdev->dev,
+ "Adapter error recovery failed\n");
+}
+
+static void be_worker(struct work_struct *work)
+{
+ struct be_adapter *adapter =
+ container_of(work, struct be_adapter, work.work);
+ struct be_rx_obj *rxo;
+ int i;
+
+ if (lancer_chip(adapter))
+ lancer_test_and_recover_fn_err(adapter);
+
+ be_detect_dump_ue(adapter);
+
+ /* when interrupts are not yet enabled, just reap any pending
+ * mcc completions */
+ if (!netif_running(adapter->netdev)) {
+ int mcc_compl, status = 0;
+
+ mcc_compl = be_process_mcc(adapter, &status);
+
+ if (mcc_compl) {
+ struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
+ be_cq_notify(adapter, mcc_obj->cq.id, false, mcc_compl);
+ }
+
+ goto reschedule;
+ }
+
+ if (!adapter->stats_cmd_sent) {
+ if (lancer_chip(adapter))
+ lancer_cmd_get_pport_stats(adapter,
+ &adapter->stats_cmd);
+ else
+ be_cmd_get_stats(adapter, &adapter->stats_cmd);
+ }
+
+ for_all_rx_queues(adapter, rxo, i) {
+ be_rx_eqd_update(adapter, rxo);
+
+ if (rxo->rx_post_starved) {
+ rxo->rx_post_starved = false;
+ be_post_rx_frags(rxo, GFP_KERNEL);
+ }
+ }
+
+reschedule:
+ adapter->work_counter++;
+ schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
+}
+
static int __devinit be_probe(struct pci_dev *pdev,
const struct pci_device_id *pdev_id)
{
goto disable_sriov;
if (lancer_chip(adapter)) {
- status = lancer_test_and_set_rdy_state(adapter);
+ status = lancer_wait_ready(adapter);
+ if (!status) {
+ iowrite32(SLI_PORT_CONTROL_IP_MASK,
+ adapter->db + SLIPORT_CONTROL_OFFSET);
+ status = lancer_test_and_set_rdy_state(adapter);
+ }
if (status) {
dev_err(&pdev->dev, "Adapter in non recoverable error\n");
goto ctrl_clean;
dev_info(&adapter->pdev->dev, "EEH reset\n");
adapter->eeh_err = false;
+ adapter->ue_detected = false;
+ adapter->fw_timeout = false;
status = pci_enable_device(pdev);
if (status)
},
};
-static int __init ethoc_init(void)
-{
- return platform_driver_register(ðoc_driver);
-}
-
-static void __exit ethoc_exit(void)
-{
- platform_driver_unregister(ðoc_driver);
-}
-
-module_init(ethoc_init);
-module_exit(ethoc_exit);
+module_platform_driver(ethoc_driver);
MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
MODULE_DESCRIPTION("OpenCores Ethernet MAC driver");
{
struct netdev_private *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
if NET_VENDOR_FREESCALE
config FEC
- bool "FEC ethernet controller (of ColdFire and some i.MX CPUs)"
+ tristate "FEC ethernet controller (of ColdFire and some i.MX CPUs)"
depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \
- ARCH_MXC || ARCH_MXS)
+ ARCH_MXC || SOC_IMX28)
+ default ARCH_MXC || SOC_IMX28 if ARM
select PHYLIB
---help---
Say Y here if you want to use the built-in 10/100 Fast ethernet
MODULE_DEVICE_TABLE(platform, fec_devtype);
enum imx_fec_type {
- IMX25_FEC = 1, /* runs on i.mx25/50/53 */
+ IMX25_FEC = 1, /* runs on i.mx25/50/53 */
IMX27_FEC, /* runs on i.mx27/35/51 */
IMX28_FEC,
IMX6Q_FEC,
#elif defined (CONFIG_M5272C3)
#define FEC_FLASHMAC (0xffe04000 + 4)
#elif defined(CONFIG_MOD5272)
-#define FEC_FLASHMAC 0xffc0406b
+#define FEC_FLASHMAC 0xffc0406b
#else
#define FEC_FLASHMAC 0
#endif
struct platform_device *pdev;
int opened;
+ int dev_id;
/* Phylib and MDIO interface */
struct mii_bus *mii_bus;
#define FEC_MMFR_TA (2 << 16)
#define FEC_MMFR_DATA(v) (v & 0xffff)
-#define FEC_MII_TIMEOUT 1000 /* us */
+#define FEC_MII_TIMEOUT 30000 /* us */
/* Transmitter timeout */
#define TX_TIMEOUT (2 * HZ)
+static int mii_cnt;
+
static void *swap_buffer(void *bufaddr, int len)
{
int i;
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
platform_get_device_id(fep->pdev);
+ u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
/* We cannot expect a graceful transmit stop without link !!! */
if (fep->link) {
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
/* We have to keep ENET enabled to have MII interrupt stay working */
- if (id_entry->driver_data & FEC_QUIRK_ENET_MAC)
+ if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) {
writel(2, fep->hwp + FEC_ECNTRL);
+ writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
+ }
}
iap = (unsigned char *)FEC_FLASHMAC;
#else
if (pdata)
- memcpy(iap, pdata->mac, ETH_ALEN);
+ iap = (unsigned char *)&pdata->mac;
#endif
}
/* Adjust MAC if using macaddr */
if (iap == macaddr)
- ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->pdev->id;
+ ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id;
}
/* ------------------------------------------------------------------------- */
if (phy_dev->link) {
if (fep->full_duplex != phy_dev->duplex) {
fec_restart(ndev, phy_dev->duplex);
+ /* prevent unnecessary second fec_restart() below */
+ fep->link = phy_dev->link;
status_change = 1;
}
}
char mdio_bus_id[MII_BUS_ID_SIZE];
char phy_name[MII_BUS_ID_SIZE + 3];
int phy_id;
- int dev_id = fep->pdev->id;
+ int dev_id = fep->dev_id;
fep->phy_dev = NULL;
}
if (phy_id >= PHY_MAX_ADDR) {
- printk(KERN_INFO "%s: no PHY, assuming direct connection "
- "to switch\n", ndev->name);
+ printk(KERN_INFO
+ "%s: no PHY, assuming direct connection to switch\n",
+ ndev->name);
strncpy(mdio_bus_id, "0", MII_BUS_ID_SIZE);
phy_id = 0;
}
fep->link = 0;
fep->full_duplex = 0;
- printk(KERN_INFO "%s: Freescale FEC PHY driver [%s] "
- "(mii_bus:phy_addr=%s, irq=%d)\n", ndev->name,
+ printk(KERN_INFO
+ "%s: Freescale FEC PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n",
+ ndev->name,
fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev),
fep->phy_dev->irq);
* mdio interface in board design, and need to be configured by
* fec0 mii_bus.
*/
- if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && pdev->id > 0) {
+ if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && fep->dev_id > 0) {
/* fec1 uses fec0 mii_bus */
- fep->mii_bus = fec0_mii_bus;
- return 0;
+ if (mii_cnt && fec0_mii_bus) {
+ fep->mii_bus = fec0_mii_bus;
+ mii_cnt++;
+ return 0;
+ }
+ return -ENOENT;
}
fep->mii_timeout = 0;
fep->mii_bus->read = fec_enet_mdio_read;
fep->mii_bus->write = fec_enet_mdio_write;
fep->mii_bus->reset = fec_enet_mdio_reset;
- snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id + 1);
+ snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", fep->dev_id + 1);
fep->mii_bus->priv = fep;
fep->mii_bus->parent = &pdev->dev;
if (mdiobus_register(fep->mii_bus))
goto err_out_free_mdio_irq;
+ mii_cnt++;
+
/* save fec0 mii_bus */
if (id_entry->driver_data & FEC_QUIRK_ENET_MAC)
fec0_mii_bus = fep->mii_bus;
static void fec_enet_mii_remove(struct fec_enet_private *fep)
{
- if (fep->phy_dev)
- phy_disconnect(fep->phy_dev);
- mdiobus_unregister(fep->mii_bus);
- kfree(fep->mii_bus->irq);
- mdiobus_free(fep->mii_bus);
+ if (--mii_cnt == 0) {
+ mdiobus_unregister(fep->mii_bus);
+ kfree(fep->mii_bus->irq);
+ mdiobus_free(fep->mii_bus);
+ }
}
static int fec_enet_get_settings(struct net_device *ndev,
int i, irq, ret = 0;
struct resource *r;
const struct of_device_id *of_id;
+ static int dev_id;
of_id = of_match_device(fec_dt_ids, &pdev->dev);
if (of_id)
fep->hwp = ioremap(r->start, resource_size(r));
fep->pdev = pdev;
+ fep->dev_id = dev_id++;
if (!fep->hwp) {
ret = -ENOMEM;
for (i = 0; i < FEC_IRQ_NUM; i++) {
irq = platform_get_irq(pdev, i);
- if (i && irq < 0)
- break;
+ if (irq < 0) {
+ if (i)
+ break;
+ ret = irq;
+ goto failed_irq;
+ }
ret = request_irq(irq, fec_enet_interrupt, IRQF_DISABLED, pdev->name, ndev);
if (ret) {
while (--i >= 0) {
}
}
- fep->clk = clk_get(&pdev->dev, "fec_clk");
+ fep->clk = clk_get(&pdev->dev, NULL);
if (IS_ERR(fep->clk)) {
ret = PTR_ERR(fep->clk);
goto failed_clk;
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
struct resource *r;
+ int i;
- fec_stop(ndev);
+ unregister_netdev(ndev);
fec_enet_mii_remove(fep);
+ for (i = 0; i < FEC_IRQ_NUM; i++) {
+ int irq = platform_get_irq(pdev, i);
+ if (irq > 0)
+ free_irq(irq, ndev);
+ }
clk_disable(fep->clk);
clk_put(fep->clk);
iounmap(fep->hwp);
- unregister_netdev(ndev);
free_netdev(ndev);
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
.remove = fs_enet_remove,
};
-static int __init fs_init(void)
-{
- return platform_driver_register(&fs_enet_driver);
-}
-
-static void __exit fs_cleanup(void)
-{
- platform_driver_unregister(&fs_enet_driver);
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void fs_enet_netpoll(struct net_device *dev)
{
}
#endif
-/**************************************************************************************/
-
-module_init(fs_init);
-module_exit(fs_cleanup);
+module_platform_driver(fs_enet_driver);
.remove = fs_enet_mdio_remove,
};
-static int fs_enet_mdio_bb_init(void)
-{
- return platform_driver_register(&fs_enet_bb_mdio_driver);
-}
-
-static void fs_enet_mdio_bb_exit(void)
-{
- platform_driver_unregister(&fs_enet_bb_mdio_driver);
-}
-
-module_init(fs_enet_mdio_bb_init);
-module_exit(fs_enet_mdio_bb_exit);
+module_platform_driver(fs_enet_bb_mdio_driver);
.remove = fs_enet_mdio_remove,
};
-static int fs_enet_mdio_fec_init(void)
-{
- return platform_driver_register(&fs_enet_fec_mdio_driver);
-}
-
-static void fs_enet_mdio_fec_exit(void)
-{
- platform_driver_unregister(&fs_enet_fec_mdio_driver);
-}
-
-module_init(fs_enet_mdio_fec_init);
-module_exit(fs_enet_mdio_fec_exit);
+module_platform_driver(fs_enet_fec_mdio_driver);
}
EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name);
-/* Scan the bus in reverse, looking for an empty spot */
-static int fsl_pq_mdio_find_free(struct mii_bus *new_bus)
-{
- int i;
-
- for (i = PHY_MAX_ADDR; i > 0; i--) {
- u32 phy_id;
-
- if (get_phy_id(new_bus, i, &phy_id))
- return -1;
-
- if (phy_id == 0xffffffff)
- break;
- }
- return i;
-}
-
-
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np)
{
+#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
struct gfar __iomem *enet_regs;
/*
} else if (of_device_is_compatible(np, "fsl,etsec2-mdio") ||
of_device_is_compatible(np, "fsl,etsec2-tbi")) {
return of_iomap(np, 1);
- } else
- return NULL;
-}
+ }
#endif
+ return NULL;
+}
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id)
{
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
struct device_node *np = NULL;
int err = 0;
return err;
else
return -EINVAL;
-}
+#else
+ return -ENODEV;
#endif
-
+}
static int fsl_pq_mdio_probe(struct platform_device *ofdev)
{
of_device_is_compatible(np, "fsl,etsec2-mdio") ||
of_device_is_compatible(np, "fsl,etsec2-tbi") ||
of_device_is_compatible(np, "gianfar")) {
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
tbipa = get_gfar_tbipa(regs, np);
if (!tbipa) {
err = -EINVAL;
goto err_free_irqs;
}
-#else
- err = -ENODEV;
- goto err_free_irqs;
-#endif
} else if (of_device_is_compatible(np, "fsl,ucc-mdio") ||
of_device_is_compatible(np, "ucc_geth_phy")) {
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
u32 id;
static u32 mii_mng_master;
mii_mng_master = id;
ucc_set_qe_mux_mii_mng(id - 1);
}
-#else
- err = -ENODEV;
- goto err_free_irqs;
-#endif
} else {
err = -ENODEV;
goto err_free_irqs;
}
if (tbiaddr == -1) {
- out_be32(tbipa, 0);
-
- tbiaddr = fsl_pq_mdio_find_free(new_bus);
- }
-
- /*
- * We define TBIPA at 0 to be illegal, opting to fail for boards that
- * have PHYs at 1-31, rather than change tbipa and rescan.
- */
- if (tbiaddr == 0) {
err = -EBUSY;
-
goto err_free_irqs;
+ } else {
+ out_be32(tbipa, tbiaddr);
}
- out_be32(tbipa, tbiaddr);
-
err = of_mdiobus_register(new_bus, np);
if (err) {
printk (KERN_ERR "%s: Cannot register as MDIO bus\n",
.remove = fsl_pq_mdio_remove,
};
-int __init fsl_pq_mdio_init(void)
-{
- return platform_driver_register(&fsl_pq_mdio_driver);
-}
-module_init(fsl_pq_mdio_init);
+module_platform_driver(fsl_pq_mdio_driver);
-void fsl_pq_mdio_exit(void)
-{
- platform_driver_unregister(&fsl_pq_mdio_driver);
-}
-module_exit(fsl_pq_mdio_exit);
MODULE_LICENSE("GPL");
mac_addr = of_get_mac_address(np);
if (mac_addr)
- memcpy(dev->dev_addr, mac_addr, MAC_ADDR_LEN);
+ memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
if (model && !strcasecmp(model, "TSEC"))
priv->device_flags =
}
/* Enables and disables VLAN insertion/extraction */
-void gfar_vlan_mode(struct net_device *dev, u32 features)
+void gfar_vlan_mode(struct net_device *dev, netdev_features_t features)
{
struct gfar_private *priv = netdev_priv(dev);
struct gfar __iomem *regs = NULL;
static void gfar_clear_exact_match(struct net_device *dev)
{
int idx;
- static const u8 zero_arr[MAC_ADDR_LEN] = {0, 0, 0, 0, 0, 0};
+ static const u8 zero_arr[ETH_ALEN] = {0, 0, 0, 0, 0, 0};
for(idx = 1;idx < GFAR_EM_NUM + 1;idx++)
gfar_set_mac_for_addr(dev, idx, zero_arr);
{
u32 tempval;
struct gfar_private *priv = netdev_priv(dev);
- u32 result = ether_crc(MAC_ADDR_LEN, addr);
+ u32 result = ether_crc(ETH_ALEN, addr);
int width = priv->hash_width;
u8 whichbit = (result >> (32 - width)) & 0x1f;
u8 whichreg = result >> (32 - width + 5);
struct gfar_private *priv = netdev_priv(dev);
struct gfar __iomem *regs = priv->gfargrp[0].regs;
int idx;
- char tmpbuf[MAC_ADDR_LEN];
+ char tmpbuf[ETH_ALEN];
u32 tempval;
u32 __iomem *macptr = ®s->macstnaddr1;
/* Now copy it into the mac registers backwards, cuz */
/* little endian is silly */
- for (idx = 0; idx < MAC_ADDR_LEN; idx++)
- tmpbuf[MAC_ADDR_LEN - 1 - idx] = addr[idx];
+ for (idx = 0; idx < ETH_ALEN; idx++)
+ tmpbuf[ETH_ALEN - 1 - idx] = addr[idx];
gfar_write(macptr, *((u32 *) (tmpbuf)));
.remove = gfar_remove,
};
-static int __init gfar_init(void)
-{
- return platform_driver_register(&gfar_driver);
-}
-
-static void __exit gfar_exit(void)
-{
- platform_driver_unregister(&gfar_driver);
-}
-
-module_init(gfar_init);
-module_exit(gfar_exit);
-
+module_platform_driver(gfar_driver);
* will be the next highest multiple of 512 bytes. */
#define INCREMENTAL_BUFFER_SIZE 512
-
-#define MAC_ADDR_LEN 6
-
#define PHY_INIT_TIMEOUT 100000
#define GFAR_PHY_CHANGE_TIME 2
extern void gfar_configure_coalescing(struct gfar_private *priv,
unsigned long tx_mask, unsigned long rx_mask);
void gfar_init_sysfs(struct net_device *dev);
-int gfar_set_features(struct net_device *dev, u32 features);
+int gfar_set_features(struct net_device *dev, netdev_features_t features);
extern void gfar_check_rx_parser_mode(struct gfar_private *priv);
-extern void gfar_vlan_mode(struct net_device *dev, u32 features);
+extern void gfar_vlan_mode(struct net_device *dev, netdev_features_t features);
extern const struct ethtool_ops gfar_ethtool_ops;
return err;
}
-int gfar_set_features(struct net_device *dev, u32 features)
+int gfar_set_features(struct net_device *dev, netdev_features_t features)
{
struct gfar_private *priv = netdev_priv(dev);
unsigned long flags;
int err = 0, i = 0;
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if (changed & (NETIF_F_HW_VLAN_TX|NETIF_F_HW_VLAN_RX))
gfar_vlan_mode(dev, features);
/* We need a copy of the filer table because
* we want to change its order */
- temp_table = kmalloc(sizeof(*temp_table), GFP_KERNEL);
+ temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL);
if (temp_table == NULL)
return -ENOMEM;
- memcpy(temp_table, tab, sizeof(*temp_table));
mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1,
sizeof(struct gfar_mask_entry), GFP_KERNEL);
ret = gfar_set_hash_opts(priv, cmd);
break;
case ETHTOOL_SRXCLSRLINS:
- if (cmd->fs.ring_cookie != RX_CLS_FLOW_DISC &&
- cmd->fs.ring_cookie >= priv->num_rx_queues) {
+ if ((cmd->fs.ring_cookie != RX_CLS_FLOW_DISC &&
+ cmd->fs.ring_cookie >= priv->num_rx_queues) ||
+ cmd->fs.location >= MAX_FILER_IDX) {
ret = -EINVAL;
break;
}
.remove = gianfar_ptp_remove,
};
-/* module operations */
-
-static int __init ptp_gianfar_init(void)
-{
- return platform_driver_register(&gianfar_ptp_driver);
-}
-
-module_init(ptp_gianfar_init);
-
-static void __exit ptp_gianfar_exit(void)
-{
- platform_driver_unregister(&gianfar_ptp_driver);
-}
-
-module_exit(ptp_gianfar_exit);
+module_platform_driver(gianfar_ptp_driver);
MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
MODULE_DESCRIPTION("PTP clock using the eTSEC");
static inline int compare_addr(u8 **addr1, u8 **addr2)
{
- return memcmp(addr1, addr2, ENET_NUM_OCTETS_PER_ADDRESS);
+ return memcmp(addr1, addr2, ETH_ALEN);
}
#ifdef DEBUG
#include <linux/kernel.h>
#include <linux/list.h>
+#include <linux/if_ether.h>
#include <asm/immap_qe.h>
#include <asm/qe.h>
#define TX_RING_MOD_MASK(size) (size-1)
#define RX_RING_MOD_MASK(size) (size-1)
-#define ENET_NUM_OCTETS_PER_ADDRESS 6
#define ENET_GROUP_ADDR 0x01 /* Group address mask
for ethernet
addresses */
/* UCC GETH 82xx Ethernet Address Container */
struct enet_addr_container {
- u8 address[ENET_NUM_OCTETS_PER_ADDRESS]; /* ethernet address */
+ u8 address[ETH_ALEN]; /* ethernet address */
enum ucc_geth_enet_address_recognition_location location; /* location in
82xx address
recognition
u16 cpucount[NUM_TX_QUEUES];
u16 __iomem *p_cpucount[NUM_TX_QUEUES];
int indAddrRegUsed[NUM_OF_PADDRS];
- u8 paddr[NUM_OF_PADDRS][ENET_NUM_OCTETS_PER_ADDRESS]; /* ethernet address */
+ u8 paddr[NUM_OF_PADDRS][ETH_ALEN]; /* ethernet address */
u8 numGroupAddrInHash;
u8 numIndAddrInHash;
u8 numIndAddrInReg;
static void netdev_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "PCMCIA 0x%lx", dev->base_addr);
}
static const struct ethtool_ops netdev_ethtool_ops = {
static void eepro_ethtool_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
{
- strcpy(drvinfo->driver, DRV_NAME);
- strcpy(drvinfo->version, DRV_VERSION);
- sprintf(drvinfo->bus_info, "ISA 0x%lx", dev->base_addr);
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+ snprintf(drvinfo->bus_info, sizeof(drvinfo->bus_info),
+ "ISA 0x%lx", dev->base_addr);
}
static const struct ethtool_ops eepro_ethtool_ops = {
#ifdef EHEA_SMALL_QUEUES
#define EHEA_MAX_CQE_COUNT 1023
#define EHEA_DEF_ENTRIES_SQ 1023
-#define EHEA_DEF_ENTRIES_RQ1 4095
+#define EHEA_DEF_ENTRIES_RQ1 1023
#define EHEA_DEF_ENTRIES_RQ2 1023
-#define EHEA_DEF_ENTRIES_RQ3 1023
+#define EHEA_DEF_ENTRIES_RQ3 511
#else
#define EHEA_MAX_CQE_COUNT 4080
#define EHEA_DEF_ENTRIES_SQ 4080
out_herr:
free_page((unsigned long)cb2);
resched:
- schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000));
+ schedule_delayed_work(&port->stats_work,
+ round_jiffies_relative(msecs_to_jiffies(1000)));
}
static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes)
return NETDEV_TX_OK;
}
-static void ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct ehea_port *port = netdev_priv(dev);
struct ehea_adapter *adapter = port->adapter;
struct hcp_ehea_port_cb1 *cb1;
int index;
u64 hret;
+ int err = 0;
cb1 = (void *)get_zeroed_page(GFP_KERNEL);
if (!cb1) {
pr_err("no mem for cb1\n");
+ err = -ENOMEM;
goto out;
}
H_PORT_CB1, H_PORT_CB1_ALL, cb1);
if (hret != H_SUCCESS) {
pr_err("query_ehea_port failed\n");
+ err = -EINVAL;
goto out;
}
hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
H_PORT_CB1, H_PORT_CB1_ALL, cb1);
- if (hret != H_SUCCESS)
+ if (hret != H_SUCCESS) {
pr_err("modify_ehea_port failed\n");
+ err = -EINVAL;
+ }
out:
free_page((unsigned long)cb1);
- return;
+ return err;
}
-static void ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct ehea_port *port = netdev_priv(dev);
struct ehea_adapter *adapter = port->adapter;
struct hcp_ehea_port_cb1 *cb1;
int index;
u64 hret;
+ int err = 0;
cb1 = (void *)get_zeroed_page(GFP_KERNEL);
if (!cb1) {
pr_err("no mem for cb1\n");
+ err = -ENOMEM;
goto out;
}
H_PORT_CB1, H_PORT_CB1_ALL, cb1);
if (hret != H_SUCCESS) {
pr_err("query_ehea_port failed\n");
+ err = -EINVAL;
goto out;
}
hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
H_PORT_CB1, H_PORT_CB1_ALL, cb1);
- if (hret != H_SUCCESS)
+ if (hret != H_SUCCESS) {
pr_err("modify_ehea_port failed\n");
+ err = -EINVAL;
+ }
out:
free_page((unsigned long)cb1);
+ return err;
}
int ehea_activate_qp(struct ehea_adapter *adapter, struct ehea_qp *qp)
}
mutex_unlock(&port->port_lock);
- schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000));
+ schedule_delayed_work(&port->stats_work,
+ round_jiffies_relative(msecs_to_jiffies(1000)));
return ret;
}
if (emac_has_feature(dev, EMAC_FTR_HAS_ZMII))
zmii_detach(dev->zmii_dev, dev->zmii_port);
+ busy_phy_map &= ~(1 << dev->phy.address);
+ DBG(dev, "busy_phy_map now %#x" NL, busy_phy_map);
+
mal_unregister_commac(dev->mal, &dev->commac);
emac_put_deps(dev);
sizeof(info->version) - 1);
}
-static u32 ibmveth_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t ibmveth_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/*
* Since the ibmveth firmware interface does not have the
return rc1 ? rc1 : rc2;
}
-static int ibmveth_set_features(struct net_device *dev, u32 features)
+static int ibmveth_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
int rx_csum = !!(features & NETIF_F_RXCSUM);
/* FIXME: do we need this? */
memset(local_list, 0, sizeof(local_list));
- memset(remote_list, 0, sizeof(VETH_MAX_FRAMES_PER_MSG));
+ memset(remote_list, 0, sizeof(remote_list));
/* a 0 address marks the end of the valid entries */
if (senddata->addr[startchunk] == 0)
}
/* The last cycle is a tri-state, so read from the PHY. */
- for (j = 7; j < 8; j++) {
- for (i = 0; i < p[j].len; i++) {
- ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity);
-
- p[j].field |= ((ipg_r8(PHY_CTRL) &
- IPG_PC_MGMTDATA) >> 1) << (p[j].len - 1 - i);
-
- ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity);
- }
- }
+ ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity);
+ ipg_r8(PHY_CTRL);
+ ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity);
}
static void ipg_set_led_mode(struct net_device *dev)
struct ethtool_drvinfo *info)
{
struct nic *nic = netdev_priv(netdev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
- strcpy(info->bus_info, pci_name(nic->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(nic->pdev),
+ sizeof(info->bus_info));
}
#define E100_PHY_REGS 0x1C
struct ethtool_drvinfo *drvinfo)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- char firmware_version[32];
- strncpy(drvinfo->driver, e1000_driver_name, 32);
- strncpy(drvinfo->version, e1000_driver_version, 32);
+ strlcpy(drvinfo->driver, e1000_driver_name,
+ sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, e1000_driver_version,
+ sizeof(drvinfo->version));
- sprintf(firmware_version, "N/A");
- strncpy(drvinfo->fw_version, firmware_version, 32);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = e1000_get_regs_len(netdev);
drvinfo->eedump_len = e1000_get_eeprom_len(netdev);
}
#define E1000_DEV_ID_INTEL_CE4100_GBE 0x2E6E
#define NODE_ADDRESS_SIZE 6
-#define ETH_LENGTH_OF_ADDRESS 6
/* MAC decode size is 128K - This is the size of BAR0 */
#define MAC_DECODE_SIZE (128 * 1024)
struct sk_buff *skb);
static bool e1000_vlan_used(struct e1000_adapter *adapter);
-static void e1000_vlan_mode(struct net_device *netdev, u32 features);
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+static void e1000_vlan_mode(struct net_device *netdev,
+ netdev_features_t features);
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
static void e1000_restore_vlan(struct e1000_adapter *adapter);
#ifdef CONFIG_PM
}
}
-static u32 e1000_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t e1000_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int e1000_set_features(struct net_device *netdev, u32 features)
+static int e1000_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
if (changed & NETIF_F_HW_VLAN_RX)
e1000_vlan_mode(netdev, features);
if (global_quad_port_a != 0)
adapter->eeprom_wol = 0;
else
- adapter->quad_port_a = 1;
+ adapter->quad_port_a = true;
/* Reset for multiple quad port adapters */
if (++global_quad_port_a == 4)
global_quad_port_a = 0;
* need this to apply a workaround later in the send path. */
if (hw->mac_type == e1000_82544 &&
hw->bus_type == e1000_bus_type_pcix)
- adapter->pcix_82544 = 1;
+ adapter->pcix_82544 = true;
ew32(TCTL, tctl);
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
- tx_ring->last_tx_tso = 0;
+ tx_ring->last_tx_tso = false;
writel(0, hw->hw_addr + tx_ring->tdh);
writel(0, hw->hw_addr + tx_ring->tdt);
* DMA'd to the controller */
if (!skb->data_len && tx_ring->last_tx_tso &&
!skb_is_gso(skb)) {
- tx_ring->last_tx_tso = 0;
+ tx_ring->last_tx_tso = false;
size -= 4;
}
if (likely(tso)) {
if (likely(hw->mac_type != e1000_82544))
- tx_ring->last_tx_tso = 1;
+ tx_ring->last_tx_tso = true;
tx_flags |= E1000_TX_FLAGS_TSO;
} else if (likely(e1000_tx_csum(adapter, tx_ring, skb)))
tx_flags |= E1000_TX_FLAGS_CSUM;
e1000_irq_enable(adapter);
}
-static void e1000_vlan_mode(struct net_device *netdev, u32 features)
+static void e1000_vlan_mode(struct net_device *netdev,
+ netdev_features_t features)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
e1000_irq_enable(adapter);
}
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
if ((hw->mng_cookie.status &
E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) &&
(vid == adapter->mng_vlan_id))
- return;
+ return 0;
if (!e1000_vlan_used(adapter))
e1000_vlan_filter_on_off(adapter, true);
e1000_write_vfta(hw, index, vfta);
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
if (!e1000_vlan_used(adapter))
e1000_vlan_filter_on_off(adapter, false);
+
+ return 0;
}
static void e1000_restore_vlan(struct e1000_adapter *adapter)
u32 txd_cmd;
bool detect_tx_hung;
+ bool tx_hang_recheck;
u8 tx_timeout_factor;
u32 tx_int_delay;
struct ethtool_drvinfo *drvinfo)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- char firmware_version[32];
- strncpy(drvinfo->driver, e1000e_driver_name,
- sizeof(drvinfo->driver) - 1);
- strncpy(drvinfo->version, e1000e_driver_version,
- sizeof(drvinfo->version) - 1);
+ strlcpy(drvinfo->driver, e1000e_driver_name,
+ sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, e1000e_driver_version,
+ sizeof(drvinfo->version));
/*
* EEPROM image version # is reported as firmware version # for
* PCI-E controllers
*/
- snprintf(firmware_version, sizeof(firmware_version), "%d.%d-%d",
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d-%d",
(adapter->eeprom_vers & 0xF000) >> 12,
(adapter->eeprom_vers & 0x0FF0) >> 4,
(adapter->eeprom_vers & 0x000F));
- strncpy(drvinfo->fw_version, firmware_version,
- sizeof(drvinfo->fw_version) - 1);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
- sizeof(drvinfo->bus_info) - 1);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = e1000_get_regs_len(netdev);
drvinfo->eedump_len = e1000_get_eeprom_len(netdev);
}
regs[n] = __er32(hw, E1000_TARC(n));
break;
default:
- printk(KERN_INFO "%-15s %08x\n",
- reginfo->name, __er32(hw, reginfo->ofs));
+ pr_info("%-15s %08x\n",
+ reginfo->name, __er32(hw, reginfo->ofs));
return;
}
snprintf(rname, 16, "%s%s", reginfo->name, "[0-1]");
- printk(KERN_INFO "%-15s ", rname);
- for (n = 0; n < 2; n++)
- printk(KERN_CONT "%08x ", regs[n]);
- printk(KERN_CONT "\n");
+ pr_info("%-15s %08x %08x\n", rname, regs[0], regs[1]);
}
/*
/* Print netdevice Info */
if (netdev) {
dev_info(&adapter->pdev->dev, "Net device Info\n");
- printk(KERN_INFO "Device Name state "
- "trans_start last_rx\n");
- printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
- netdev->name, netdev->state, netdev->trans_start,
- netdev->last_rx);
+ pr_info("Device Name state trans_start last_rx\n");
+ pr_info("%-15s %016lX %016lX %016lX\n",
+ netdev->name, netdev->state, netdev->trans_start,
+ netdev->last_rx);
}
/* Print Registers */
dev_info(&adapter->pdev->dev, "Register Dump\n");
- printk(KERN_INFO " Register Name Value\n");
+ pr_info(" Register Name Value\n");
for (reginfo = (struct e1000_reg_info *)e1000_reg_info_tbl;
reginfo->name; reginfo++) {
e1000_regdump(hw, reginfo);
goto exit;
dev_info(&adapter->pdev->dev, "Tx Ring Summary\n");
- printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ]"
- " leng ntw timestamp\n");
+ pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n");
buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean];
- printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n",
- 0, tx_ring->next_to_use, tx_ring->next_to_clean,
- (unsigned long long)buffer_info->dma,
- buffer_info->length,
- buffer_info->next_to_watch,
- (unsigned long long)buffer_info->time_stamp);
+ pr_info(" %5d %5X %5X %016llX %04X %3X %016llX\n",
+ 0, tx_ring->next_to_use, tx_ring->next_to_clean,
+ (unsigned long long)buffer_info->dma,
+ buffer_info->length,
+ buffer_info->next_to_watch,
+ (unsigned long long)buffer_info->time_stamp);
/* Print Tx Ring */
if (!netif_msg_tx_done(adapter))
* +----------------------------------------------------------------+
* 63 48 47 40 39 36 35 32 31 24 23 20 19 0
*/
- printk(KERN_INFO "Tl[desc] [address 63:0 ] [SpeCssSCmCsLen]"
- " [bi->dma ] leng ntw timestamp bi->skb "
- "<-- Legacy format\n");
- printk(KERN_INFO "Tc[desc] [Ce CoCsIpceCoS] [MssHlRSCm0Plen]"
- " [bi->dma ] leng ntw timestamp bi->skb "
- "<-- Ext Context format\n");
- printk(KERN_INFO "Td[desc] [address 63:0 ] [VlaPoRSCm1Dlen]"
- " [bi->dma ] leng ntw timestamp bi->skb "
- "<-- Ext Data format\n");
+ pr_info("Tl[desc] [address 63:0 ] [SpeCssSCmCsLen] [bi->dma ] leng ntw timestamp bi->skb <-- Legacy format\n");
+ pr_info("Tc[desc] [Ce CoCsIpceCoS] [MssHlRSCm0Plen] [bi->dma ] leng ntw timestamp bi->skb <-- Ext Context format\n");
+ pr_info("Td[desc] [address 63:0 ] [VlaPoRSCm1Dlen] [bi->dma ] leng ntw timestamp bi->skb <-- Ext Data format\n");
for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
+ const char *next_desc;
tx_desc = E1000_TX_DESC(*tx_ring, i);
buffer_info = &tx_ring->buffer_info[i];
u0 = (struct my_u0 *)tx_desc;
- printk(KERN_INFO "T%c[0x%03X] %016llX %016llX %016llX "
- "%04X %3X %016llX %p",
- (!(le64_to_cpu(u0->b) & (1 << 29)) ? 'l' :
- ((le64_to_cpu(u0->b) & (1 << 20)) ? 'd' : 'c')), i,
- (unsigned long long)le64_to_cpu(u0->a),
- (unsigned long long)le64_to_cpu(u0->b),
- (unsigned long long)buffer_info->dma,
- buffer_info->length, buffer_info->next_to_watch,
- (unsigned long long)buffer_info->time_stamp,
- buffer_info->skb);
if (i == tx_ring->next_to_use && i == tx_ring->next_to_clean)
- printk(KERN_CONT " NTC/U\n");
+ next_desc = " NTC/U";
else if (i == tx_ring->next_to_use)
- printk(KERN_CONT " NTU\n");
+ next_desc = " NTU";
else if (i == tx_ring->next_to_clean)
- printk(KERN_CONT " NTC\n");
+ next_desc = " NTC";
else
- printk(KERN_CONT "\n");
+ next_desc = "";
+ pr_info("T%c[0x%03X] %016llX %016llX %016llX %04X %3X %016llX %p%s\n",
+ (!(le64_to_cpu(u0->b) & (1 << 29)) ? 'l' :
+ ((le64_to_cpu(u0->b) & (1 << 20)) ? 'd' : 'c')),
+ i,
+ (unsigned long long)le64_to_cpu(u0->a),
+ (unsigned long long)le64_to_cpu(u0->b),
+ (unsigned long long)buffer_info->dma,
+ buffer_info->length, buffer_info->next_to_watch,
+ (unsigned long long)buffer_info->time_stamp,
+ buffer_info->skb, next_desc);
if (netif_msg_pktdata(adapter) && buffer_info->dma != 0)
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS,
/* Print Rx Ring Summary */
rx_ring_summary:
dev_info(&adapter->pdev->dev, "Rx Ring Summary\n");
- printk(KERN_INFO "Queue [NTU] [NTC]\n");
- printk(KERN_INFO " %5d %5X %5X\n", 0,
- rx_ring->next_to_use, rx_ring->next_to_clean);
+ pr_info("Queue [NTU] [NTC]\n");
+ pr_info(" %5d %5X %5X\n",
+ 0, rx_ring->next_to_use, rx_ring->next_to_clean);
/* Print Rx Ring */
if (!netif_msg_rx_status(adapter))
* 24 | Buffer Address 3 [63:0] |
* +-----------------------------------------------------+
*/
- printk(KERN_INFO "R [desc] [buffer 0 63:0 ] "
- "[buffer 1 63:0 ] "
- "[buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma ] "
- "[bi->skb] <-- Ext Pkt Split format\n");
+ pr_info("R [desc] [buffer 0 63:0 ] [buffer 1 63:0 ] [buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma ] [bi->skb] <-- Ext Pkt Split format\n");
/* [Extended] Receive Descriptor (Write-Back) Format
*
* 63 48 47 32 31 13 12 8 7 4 3 0
* +------------------------------------------------------+
* 63 48 47 32 31 20 19 0
*/
- printk(KERN_INFO "RWB[desc] [ck ipid mrqhsh] "
- "[vl l0 ee es] "
- "[ l3 l2 l1 hs] [reserved ] ---------------- "
- "[bi->skb] <-- Ext Rx Write-Back format\n");
+ pr_info("RWB[desc] [ck ipid mrqhsh] [vl l0 ee es] [ l3 l2 l1 hs] [reserved ] ---------------- [bi->skb] <-- Ext Rx Write-Back format\n");
for (i = 0; i < rx_ring->count; i++) {
+ const char *next_desc;
buffer_info = &rx_ring->buffer_info[i];
rx_desc_ps = E1000_RX_DESC_PS(*rx_ring, i);
u1 = (struct my_u1 *)rx_desc_ps;
staterr =
le32_to_cpu(rx_desc_ps->wb.middle.status_error);
+
+ if (i == rx_ring->next_to_use)
+ next_desc = " NTU";
+ else if (i == rx_ring->next_to_clean)
+ next_desc = " NTC";
+ else
+ next_desc = "";
+
if (staterr & E1000_RXD_STAT_DD) {
/* Descriptor Done */
- printk(KERN_INFO "RWB[0x%03X] %016llX "
- "%016llX %016llX %016llX "
- "---------------- %p", i,
- (unsigned long long)le64_to_cpu(u1->a),
- (unsigned long long)le64_to_cpu(u1->b),
- (unsigned long long)le64_to_cpu(u1->c),
- (unsigned long long)le64_to_cpu(u1->d),
- buffer_info->skb);
+ pr_info("%s[0x%03X] %016llX %016llX %016llX %016llX ---------------- %p%s\n",
+ "RWB", i,
+ (unsigned long long)le64_to_cpu(u1->a),
+ (unsigned long long)le64_to_cpu(u1->b),
+ (unsigned long long)le64_to_cpu(u1->c),
+ (unsigned long long)le64_to_cpu(u1->d),
+ buffer_info->skb, next_desc);
} else {
- printk(KERN_INFO "R [0x%03X] %016llX "
- "%016llX %016llX %016llX %016llX %p", i,
- (unsigned long long)le64_to_cpu(u1->a),
- (unsigned long long)le64_to_cpu(u1->b),
- (unsigned long long)le64_to_cpu(u1->c),
- (unsigned long long)le64_to_cpu(u1->d),
- (unsigned long long)buffer_info->dma,
- buffer_info->skb);
+ pr_info("%s[0x%03X] %016llX %016llX %016llX %016llX %016llX %p%s\n",
+ "R ", i,
+ (unsigned long long)le64_to_cpu(u1->a),
+ (unsigned long long)le64_to_cpu(u1->b),
+ (unsigned long long)le64_to_cpu(u1->c),
+ (unsigned long long)le64_to_cpu(u1->d),
+ (unsigned long long)buffer_info->dma,
+ buffer_info->skb, next_desc);
if (netif_msg_pktdata(adapter))
print_hex_dump(KERN_INFO, "",
phys_to_virt(buffer_info->dma),
adapter->rx_ps_bsize0, true);
}
-
- if (i == rx_ring->next_to_use)
- printk(KERN_CONT " NTU\n");
- else if (i == rx_ring->next_to_clean)
- printk(KERN_CONT " NTC\n");
- else
- printk(KERN_CONT "\n");
}
break;
default:
* 8 | Reserved |
* +-----------------------------------------------------+
*/
- printk(KERN_INFO "R [desc] [buf addr 63:0 ] "
- "[reserved 63:0 ] [bi->dma ] "
- "[bi->skb] <-- Ext (Read) format\n");
+ pr_info("R [desc] [buf addr 63:0 ] [reserved 63:0 ] [bi->dma ] [bi->skb] <-- Ext (Read) format\n");
/* Extended Receive Descriptor (Write-Back) Format
*
* 63 48 47 32 31 24 23 4 3 0
* +------------------------------------------------------+
* 63 48 47 32 31 20 19 0
*/
- printk(KERN_INFO "RWB[desc] [cs ipid mrq] "
- "[vt ln xe xs] "
- "[bi->skb] <-- Ext (Write-Back) format\n");
+ pr_info("RWB[desc] [cs ipid mrq] [vt ln xe xs] [bi->skb] <-- Ext (Write-Back) format\n");
for (i = 0; i < rx_ring->count; i++) {
+ const char *next_desc;
+
buffer_info = &rx_ring->buffer_info[i];
rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
u1 = (struct my_u1 *)rx_desc;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
+
+ if (i == rx_ring->next_to_use)
+ next_desc = " NTU";
+ else if (i == rx_ring->next_to_clean)
+ next_desc = " NTC";
+ else
+ next_desc = "";
+
if (staterr & E1000_RXD_STAT_DD) {
/* Descriptor Done */
- printk(KERN_INFO "RWB[0x%03X] %016llX "
- "%016llX ---------------- %p", i,
- (unsigned long long)le64_to_cpu(u1->a),
- (unsigned long long)le64_to_cpu(u1->b),
- buffer_info->skb);
+ pr_info("%s[0x%03X] %016llX %016llX ---------------- %p%s\n",
+ "RWB", i,
+ (unsigned long long)le64_to_cpu(u1->a),
+ (unsigned long long)le64_to_cpu(u1->b),
+ buffer_info->skb, next_desc);
} else {
- printk(KERN_INFO "R [0x%03X] %016llX "
- "%016llX %016llX %p", i,
- (unsigned long long)le64_to_cpu(u1->a),
- (unsigned long long)le64_to_cpu(u1->b),
- (unsigned long long)buffer_info->dma,
- buffer_info->skb);
+ pr_info("%s[0x%03X] %016llX %016llX %016llX %p%s\n",
+ "R ", i,
+ (unsigned long long)le64_to_cpu(u1->a),
+ (unsigned long long)le64_to_cpu(u1->b),
+ (unsigned long long)buffer_info->dma,
+ buffer_info->skb, next_desc);
if (netif_msg_pktdata(adapter))
print_hex_dump(KERN_INFO, "",
adapter->rx_buffer_len,
true);
}
-
- if (i == rx_ring->next_to_use)
- printk(KERN_CONT " NTU\n");
- else if (i == rx_ring->next_to_clean)
- printk(KERN_CONT " NTC\n");
- else
- printk(KERN_CONT "\n");
}
}
u32 length, staterr;
unsigned int i;
int cleaned_count = 0;
- bool cleaned = 0;
+ bool cleaned = false;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
i = rx_ring->next_to_clean;
next_buffer = &rx_ring->buffer_info[i];
- cleaned = 1;
+ cleaned = true;
cleaned_count++;
dma_unmap_single(&pdev->dev,
buffer_info->dma,
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter,
print_hang_task);
+ struct net_device *netdev = adapter->netdev;
struct e1000_ring *tx_ring = adapter->tx_ring;
unsigned int i = tx_ring->next_to_clean;
unsigned int eop = tx_ring->buffer_info[i].next_to_watch;
if (test_bit(__E1000_DOWN, &adapter->state))
return;
+ if (!adapter->tx_hang_recheck &&
+ (adapter->flags2 & FLAG2_DMA_BURST)) {
+ /* May be block on write-back, flush and detect again
+ * flush pending descriptor writebacks to memory
+ */
+ ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
+ /* execute the writes immediately */
+ e1e_flush();
+ adapter->tx_hang_recheck = true;
+ return;
+ }
+ /* Real hang detected */
+ adapter->tx_hang_recheck = false;
+ netif_stop_queue(netdev);
+
e1e_rphy(hw, PHY_STATUS, &phy_status);
e1e_rphy(hw, PHY_1000T_STATUS, &phy_1000t_status);
e1e_rphy(hw, PHY_EXT_STATUS, &phy_ext_status);
unsigned int i, eop;
unsigned int count = 0;
unsigned int total_tx_bytes = 0, total_tx_packets = 0;
+ unsigned int bytes_compl = 0, pkts_compl = 0;
i = tx_ring->next_to_clean;
eop = tx_ring->buffer_info[i].next_to_watch;
if (cleaned) {
total_tx_packets += buffer_info->segs;
total_tx_bytes += buffer_info->bytecount;
+ if (buffer_info->skb) {
+ bytes_compl += buffer_info->skb->len;
+ pkts_compl++;
+ }
}
e1000_put_txbuf(adapter, buffer_info);
tx_ring->next_to_clean = i;
+ netdev_completed_queue(netdev, pkts_compl, bytes_compl);
+
#define TX_WAKE_THRESHOLD 32
if (count && netif_carrier_ok(netdev) &&
e1000_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD) {
* Detect a transmit hang in hardware, this serializes the
* check with the clearing of time_stamp and movement of i
*/
- adapter->detect_tx_hung = 0;
+ adapter->detect_tx_hung = false;
if (tx_ring->buffer_info[i].time_stamp &&
time_after(jiffies, tx_ring->buffer_info[i].time_stamp
+ (adapter->tx_timeout_factor * HZ)) &&
- !(er32(STATUS) & E1000_STATUS_TXOFF)) {
+ !(er32(STATUS) & E1000_STATUS_TXOFF))
schedule_work(&adapter->print_hang_task);
- netif_stop_queue(netdev);
- }
+ else
+ adapter->tx_hang_recheck = false;
}
adapter->total_tx_bytes += total_tx_bytes;
adapter->total_tx_packets += total_tx_packets;
unsigned int i, j;
u32 length, staterr;
int cleaned_count = 0;
- bool cleaned = 0;
+ bool cleaned = false;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
i = rx_ring->next_to_clean;
next_buffer = &rx_ring->buffer_info[i];
- cleaned = 1;
+ cleaned = true;
cleaned_count++;
dma_unmap_single(&pdev->dev, buffer_info->dma,
adapter->rx_ps_bsize0, DMA_FROM_DEVICE);
adapter->flags2 |= FLAG2_IS_DISCARDING;
if (adapter->flags2 & FLAG2_IS_DISCARDING) {
- e_dbg("Packet Split buffers didn't pick up the full "
- "packet\n");
+ e_dbg("Packet Split buffers didn't pick up the full packet\n");
dev_kfree_skb_irq(skb);
if (staterr & E1000_RXD_STAT_EOP)
adapter->flags2 &= ~FLAG2_IS_DISCARDING;
length = le16_to_cpu(rx_desc->wb.middle.length0);
if (!length) {
- e_dbg("Last part of the packet spanning multiple "
- "descriptors\n");
+ e_dbg("Last part of the packet spanning multiple descriptors\n");
dev_kfree_skb_irq(skb);
goto next_desc;
}
return;
}
/* MSI-X failed, so fall through and try MSI */
- e_err("Failed to initialize MSI-X interrupts. "
- "Falling back to MSI interrupts.\n");
+ e_err("Failed to initialize MSI-X interrupts. Falling back to MSI interrupts.\n");
e1000e_reset_interrupt_capability(adapter);
}
adapter->int_mode = E1000E_INT_MODE_MSI;
adapter->flags |= FLAG_MSI_ENABLED;
} else {
adapter->int_mode = E1000E_INT_MODE_LEGACY;
- e_err("Failed to initialize MSI interrupts. Falling "
- "back to legacy interrupts.\n");
+ e_err("Failed to initialize MSI interrupts. Falling back to legacy interrupts.\n");
}
/* Fall through */
case E1000E_INT_MODE_LEGACY:
e1000_put_txbuf(adapter, buffer_info);
}
+ netdev_reset_queue(adapter->netdev);
size = sizeof(struct e1000_buffer) * tx_ring->count;
memset(tx_ring->buffer_info, 0, size);
return work_done;
}
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
if ((adapter->hw.mng_cookie.status &
E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
(vid == adapter->mng_vlan_id))
- return;
+ return 0;
/* add VID to filter table */
if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
}
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
(vid == adapter->mng_vlan_id)) {
/* release control to f/w */
e1000e_release_hw_control(adapter);
- return;
+ return 0;
}
/* remove VID from filter table */
}
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
/**
}
/**
- * e1000_update_mc_addr_list - Update Multicast addresses
- * @hw: pointer to the HW structure
- * @mc_addr_list: array of multicast addresses to program
- * @mc_addr_count: number of multicast addresses to program
+ * e1000e_write_mc_addr_list - write multicast addresses to MTA
+ * @netdev: network interface device structure
+ *
+ * Writes multicast address list to the MTA hash table.
+ * Returns: -ENOMEM on failure
+ * 0 on no addresses written
+ * X on writing X addresses to MTA
+ */
+static int e1000e_write_mc_addr_list(struct net_device *netdev)
+{
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
+ struct netdev_hw_addr *ha;
+ u8 *mta_list;
+ int i;
+
+ if (netdev_mc_empty(netdev)) {
+ /* nothing to program, so clear mc list */
+ hw->mac.ops.update_mc_addr_list(hw, NULL, 0);
+ return 0;
+ }
+
+ mta_list = kzalloc(netdev_mc_count(netdev) * ETH_ALEN, GFP_ATOMIC);
+ if (!mta_list)
+ return -ENOMEM;
+
+ /* update_mc_addr_list expects a packed array of only addresses. */
+ i = 0;
+ netdev_for_each_mc_addr(ha, netdev)
+ memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
+
+ hw->mac.ops.update_mc_addr_list(hw, mta_list, i);
+ kfree(mta_list);
+
+ return netdev_mc_count(netdev);
+}
+
+/**
+ * e1000e_write_uc_addr_list - write unicast addresses to RAR table
+ * @netdev: network interface device structure
*
- * Updates the Multicast Table Array.
- * The caller must have a packed mc_addr_list of multicast addresses.
+ * Writes unicast address list to the RAR table.
+ * Returns: -ENOMEM on failure/insufficient address space
+ * 0 on no addresses written
+ * X on writing X addresses to the RAR table
**/
-static void e1000_update_mc_addr_list(struct e1000_hw *hw, u8 *mc_addr_list,
- u32 mc_addr_count)
+static int e1000e_write_uc_addr_list(struct net_device *netdev)
{
- hw->mac.ops.update_mc_addr_list(hw, mc_addr_list, mc_addr_count);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
+ unsigned int rar_entries = hw->mac.rar_entry_count;
+ int count = 0;
+
+ /* save a rar entry for our hardware address */
+ rar_entries--;
+
+ /* save a rar entry for the LAA workaround */
+ if (adapter->flags & FLAG_RESET_OVERWRITES_LAA)
+ rar_entries--;
+
+ /* return ENOMEM indicating insufficient memory for addresses */
+ if (netdev_uc_count(netdev) > rar_entries)
+ return -ENOMEM;
+
+ if (!netdev_uc_empty(netdev) && rar_entries) {
+ struct netdev_hw_addr *ha;
+
+ /*
+ * write the addresses in reverse order to avoid write
+ * combining
+ */
+ netdev_for_each_uc_addr(ha, netdev) {
+ if (!rar_entries)
+ break;
+ e1000e_rar_set(hw, ha->addr, rar_entries--);
+ count++;
+ }
+ }
+
+ /* zero out the remaining RAR entries not used above */
+ for (; rar_entries > 0; rar_entries--) {
+ ew32(RAH(rar_entries), 0);
+ ew32(RAL(rar_entries), 0);
+ }
+ e1e_flush();
+
+ return count;
}
/**
- * e1000_set_multi - Multicast and Promiscuous mode set
+ * e1000e_set_rx_mode - secondary unicast, Multicast and Promiscuous mode set
* @netdev: network interface device structure
*
- * The set_multi entry point is called whenever the multicast address
- * list or the network interface flags are updated. This routine is
- * responsible for configuring the hardware for proper multicast,
+ * The ndo_set_rx_mode entry point is called whenever the unicast or multicast
+ * address list or the network interface flags are updated. This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
* promiscuous mode, and all-multi behavior.
**/
-static void e1000_set_multi(struct net_device *netdev)
+static void e1000e_set_rx_mode(struct net_device *netdev)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- struct netdev_hw_addr *ha;
- u8 *mta_list;
u32 rctl;
/* Check for Promiscuous and All Multicast modes */
-
rctl = er32(RCTL);
+ /* clear the affected bits */
+ rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
+
if (netdev->flags & IFF_PROMISC) {
rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
- rctl &= ~E1000_RCTL_VFE;
/* Do not hardware filter VLANs in promisc mode */
e1000e_vlan_filter_disable(adapter);
} else {
+ int count;
if (netdev->flags & IFF_ALLMULTI) {
rctl |= E1000_RCTL_MPE;
- rctl &= ~E1000_RCTL_UPE;
} else {
- rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
+ /*
+ * Write addresses to the MTA, if the attempt fails
+ * then we should just turn on promiscuous mode so
+ * that we can at least receive multicast traffic
+ */
+ count = e1000e_write_mc_addr_list(netdev);
+ if (count < 0)
+ rctl |= E1000_RCTL_MPE;
}
e1000e_vlan_filter_enable(adapter);
- }
-
- ew32(RCTL, rctl);
-
- if (!netdev_mc_empty(netdev)) {
- int i = 0;
-
- mta_list = kmalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC);
- if (!mta_list)
- return;
-
- /* prepare a packed array of only addresses. */
- netdev_for_each_mc_addr(ha, netdev)
- memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
-
- e1000_update_mc_addr_list(hw, mta_list, i);
- kfree(mta_list);
- } else {
/*
- * if we're called from probe, we might not have
- * anything to do here, so clear out the list
+ * Write addresses to available RAR registers, if there is not
+ * sufficient space to store all the addresses then enable
+ * unicast promiscuous mode
*/
- e1000_update_mc_addr_list(hw, NULL, 0);
+ count = e1000e_write_uc_addr_list(netdev);
+ if (count < 0)
+ rctl |= E1000_RCTL_UPE;
}
+ ew32(RCTL, rctl);
+
if (netdev->features & NETIF_F_HW_VLAN_RX)
e1000e_vlan_strip_enable(adapter);
else
**/
static void e1000_configure(struct e1000_adapter *adapter)
{
- e1000_set_multi(adapter->netdev);
+ e1000e_set_rx_mode(adapter->netdev);
e1000_restore_vlan(adapter);
e1000_init_manageability_pt(adapter);
clear_bit(__E1000_DOWN, &adapter->state);
- napi_enable(&adapter->napi);
if (adapter->msix_entries)
e1000_configure_msix(adapter);
e1000_irq_enable(adapter);
e1e_flush();
usleep_range(10000, 20000);
- napi_disable(&adapter->napi);
e1000_irq_disable(adapter);
del_timer_sync(&adapter->watchdog_timer);
e1000_irq_enable(adapter);
+ adapter->tx_hang_recheck = false;
netif_start_queue(netdev);
adapter->idle_check = true;
pm_runtime_get_sync(&pdev->dev);
+ napi_disable(&adapter->napi);
+
if (!test_bit(__E1000_DOWN, &adapter->state)) {
e1000e_down(adapter);
e1000_free_irq(adapter);
u32 ctrl = er32(CTRL);
/* Link status message must follow this format for user tools */
- printk(KERN_INFO "e1000e: %s NIC Link is Up %d Mbps %s, "
- "Flow Control: %s\n",
- adapter->netdev->name,
- adapter->link_speed,
- (adapter->link_duplex == FULL_DUPLEX) ?
- "Full Duplex" : "Half Duplex",
- ((ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE)) ?
- "Rx/Tx" :
- ((ctrl & E1000_CTRL_RFCE) ? "Rx" :
- ((ctrl & E1000_CTRL_TFCE) ? "Tx" : "None")));
+ printk(KERN_INFO "e1000e: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
+ adapter->netdev->name,
+ adapter->link_speed,
+ adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half",
+ (ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE) ? "Rx/Tx" :
+ (ctrl & E1000_CTRL_RFCE) ? "Rx" :
+ (ctrl & E1000_CTRL_TFCE) ? "Tx" : "None");
}
static bool e1000e_has_link(struct e1000_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
- bool link_active = 0;
+ bool link_active = false;
s32 ret_val = 0;
/*
ret_val = hw->mac.ops.check_for_link(hw);
link_active = !hw->mac.get_link_status;
} else {
- link_active = 1;
+ link_active = true;
}
break;
case e1000_media_type_fiber:
if (link) {
if (!netif_carrier_ok(netdev)) {
- bool txb2b = 1;
+ bool txb2b = true;
/* Cancel scheduled suspend requests. */
pm_runtime_resume(netdev->dev.parent);
e1e_rphy(hw, PHY_AUTONEG_EXP, &autoneg_exp);
if (!(autoneg_exp & NWAY_ER_LP_NWAY_CAPS))
- e_info("Autonegotiated half duplex but"
- " link partner cannot autoneg. "
- " Try forcing full duplex if "
- "link gets many collisions.\n");
+ e_info("Autonegotiated half duplex but link partner cannot autoneg. Try forcing full duplex if link gets many collisions.\n");
}
/* adjust timeout factor according to speed/duplex */
adapter->tx_timeout_factor = 1;
switch (adapter->link_speed) {
case SPEED_10:
- txb2b = 0;
+ txb2b = false;
adapter->tx_timeout_factor = 16;
break;
case SPEED_100:
- txb2b = 0;
+ txb2b = false;
adapter->tx_timeout_factor = 10;
break;
}
e1000e_flush_descriptors(adapter);
/* Force detection of hung controller every watchdog period */
- adapter->detect_tx_hung = 1;
+ adapter->detect_tx_hung = true;
/*
* With 82571 controllers, LAA may be overwritten due to controller
/* if count is 0 then mapping error has occurred */
count = e1000_tx_map(adapter, skb, first, max_per_txd, nr_frags, mss);
if (count) {
+ netdev_sent_queue(netdev, skb->len);
e1000_tx_queue(adapter, tx_flags, count);
/* Make sure there is space in the ring for the next send. */
e1000_maybe_stop_tx(netdev, MAX_SKB_FRAGS + 2);
if ((adapter->hw.mac.type == e1000_pch2lan) &&
!(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
(new_mtu > ETH_DATA_LEN)) {
- e_err("Jumbo Frames not supported on 82579 when CRC "
- "stripping is disabled.\n");
+ e_err("Jumbo Frames not supported on 82579 when CRC stripping is disabled.\n");
return -EINVAL;
}
if (wufc) {
e1000_setup_rctl(adapter);
- e1000_set_multi(netdev);
+ e1000e_set_rx_mode(netdev);
/* turn on all-multi mode if wake on multicast is enabled */
if (wufc & E1000_WUFC_MC) {
phy_data & E1000_WUS_MC ? "Multicast Packet" :
phy_data & E1000_WUS_BC ? "Broadcast Packet" :
phy_data & E1000_WUS_MAG ? "Magic Packet" :
- phy_data & E1000_WUS_LNKC ? "Link Status "
- " Change" : "other");
+ phy_data & E1000_WUS_LNKC ?
+ "Link Status Change" : "other");
}
e1e_wphy(&adapter->hw, BM_WUS, ~0);
} else {
}
}
-static int e1000_set_features(struct net_device *netdev, u32 features)
+static int e1000_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
if (changed & (NETIF_F_TSO | NETIF_F_TSO6))
adapter->flags |= FLAG_TSO_FORCE;
.ndo_stop = e1000_close,
.ndo_start_xmit = e1000_xmit_frame,
.ndo_get_stats64 = e1000e_get_stats64,
- .ndo_set_rx_mode = e1000_set_multi,
+ .ndo_set_rx_mode = e1000e_set_rx_mode,
.ndo_set_mac_address = e1000_set_mac,
.ndo_change_mtu = e1000_change_mtu,
.ndo_do_ioctl = e1000_ioctl,
err = dma_set_coherent_mask(&pdev->dev,
DMA_BIT_MASK(32));
if (err) {
- dev_err(&pdev->dev, "No usable DMA "
- "configuration, aborting\n");
+ dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
goto err_dma;
}
}
NETIF_F_TSO6 |
NETIF_F_HW_CSUM);
+ netdev->priv_flags |= IFF_UNICAST_FLT;
+
if (pci_using_dac) {
netdev->features |= NETIF_F_HIGHDMA;
netdev->vlan_features |= NETIF_F_HIGHDMA;
/* Initialize link parameters. User can change them with ethtool */
adapter->hw.mac.autoneg = 1;
- adapter->fc_autoneg = 1;
+ adapter->fc_autoneg = true;
adapter->hw.fc.requested_mode = e1000_fc_default;
adapter->hw.fc.current_mode = e1000_fc_default;
adapter->hw.phy.autoneg_advertised = 0x2f;
* e1000_82576
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/types.h>
#include <linux/if_ether.h>
* Check for invalid size
*/
if ((hw->mac.type == e1000_82576) && (size > 15)) {
- printk("igb: The NVM size is not valid, "
- "defaulting to 32K.\n");
+ pr_notice("The NVM size is not valid, defaulting to 32K\n");
size = 15;
}
nvm->word_size = 1 << size;
SUPPORTED_1000baseT_Full|
SUPPORTED_Autoneg |
SUPPORTED_TP);
- ecmd->advertising = ADVERTISED_TP;
+ ecmd->advertising = (ADVERTISED_TP |
+ ADVERTISED_Pause);
if (hw->mac.autoneg == 1) {
ecmd->advertising |= ADVERTISED_Autoneg;
ecmd->advertising = (ADVERTISED_1000baseT_Full |
ADVERTISED_FIBRE |
- ADVERTISED_Autoneg);
+ ADVERTISED_Autoneg |
+ ADVERTISED_Pause);
ecmd->port = PORT_FIBRE;
}
struct ethtool_drvinfo *drvinfo)
{
struct igb_adapter *adapter = netdev_priv(netdev);
- char firmware_version[32];
u16 eeprom_data;
- strncpy(drvinfo->driver, igb_driver_name, sizeof(drvinfo->driver) - 1);
- strncpy(drvinfo->version, igb_driver_version,
- sizeof(drvinfo->version) - 1);
+ strlcpy(drvinfo->driver, igb_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, igb_driver_version, sizeof(drvinfo->version));
/* EEPROM image version # is reported as firmware version # for
* 82575 controllers */
adapter->hw.nvm.ops.read(&adapter->hw, 5, 1, &eeprom_data);
- sprintf(firmware_version, "%d.%d-%d",
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d-%d",
(eeprom_data & 0xF000) >> 12,
(eeprom_data & 0x0FF0) >> 4,
eeprom_data & 0x000F);
- strncpy(drvinfo->fw_version, firmware_version,
- sizeof(drvinfo->fw_version) - 1);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
- sizeof(drvinfo->bus_info) - 1);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = IGB_STATS_LEN;
drvinfo->testinfo_len = IGB_TEST_LEN;
drvinfo->regdump_len = igb_get_regs_len(netdev);
*******************************************************************************/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/types.h>
#include <linux/init.h>
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
static void igb_tx_timeout(struct net_device *);
static void igb_reset_task(struct work_struct *);
-static void igb_vlan_mode(struct net_device *netdev, u32 features);
-static void igb_vlan_rx_add_vid(struct net_device *, u16);
-static void igb_vlan_rx_kill_vid(struct net_device *, u16);
+static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features);
+static int igb_vlan_rx_add_vid(struct net_device *, u16);
+static int igb_vlan_rx_kill_vid(struct net_device *, u16);
static void igb_restore_vlan(struct igb_adapter *);
static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8);
static void igb_ping_all_vfs(struct igb_adapter *);
regs[n] = rd32(E1000_TXDCTL(n));
break;
default:
- printk(KERN_INFO "%-15s %08x\n",
- reginfo->name, rd32(reginfo->ofs));
+ pr_info("%-15s %08x\n", reginfo->name, rd32(reginfo->ofs));
return;
}
snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]");
- printk(KERN_INFO "%-15s ", rname);
- for (n = 0; n < 4; n++)
- printk(KERN_CONT "%08x ", regs[n]);
- printk(KERN_CONT "\n");
+ pr_info("%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1],
+ regs[2], regs[3]);
}
/*
/* Print netdevice Info */
if (netdev) {
dev_info(&adapter->pdev->dev, "Net device Info\n");
- printk(KERN_INFO "Device Name state "
- "trans_start last_rx\n");
- printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
- netdev->name,
- netdev->state,
- netdev->trans_start,
- netdev->last_rx);
+ pr_info("Device Name state trans_start "
+ "last_rx\n");
+ pr_info("%-15s %016lX %016lX %016lX\n", netdev->name,
+ netdev->state, netdev->trans_start, netdev->last_rx);
}
/* Print Registers */
dev_info(&adapter->pdev->dev, "Register Dump\n");
- printk(KERN_INFO " Register Name Value\n");
+ pr_info(" Register Name Value\n");
for (reginfo = (struct igb_reg_info *)igb_reg_info_tbl;
reginfo->name; reginfo++) {
igb_regdump(hw, reginfo);
goto exit;
dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
- printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ]"
- " leng ntw timestamp\n");
+ pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n");
for (n = 0; n < adapter->num_tx_queues; n++) {
struct igb_tx_buffer *buffer_info;
tx_ring = adapter->tx_ring[n];
buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
- printk(KERN_INFO " %5d %5X %5X %016llX %04X %p %016llX\n",
- n, tx_ring->next_to_use, tx_ring->next_to_clean,
- (u64)buffer_info->dma,
- buffer_info->length,
- buffer_info->next_to_watch,
- (u64)buffer_info->time_stamp);
+ pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n",
+ n, tx_ring->next_to_use, tx_ring->next_to_clean,
+ (u64)buffer_info->dma,
+ buffer_info->length,
+ buffer_info->next_to_watch,
+ (u64)buffer_info->time_stamp);
}
/* Print TX Rings */
for (n = 0; n < adapter->num_tx_queues; n++) {
tx_ring = adapter->tx_ring[n];
- printk(KERN_INFO "------------------------------------\n");
- printk(KERN_INFO "TX QUEUE INDEX = %d\n", tx_ring->queue_index);
- printk(KERN_INFO "------------------------------------\n");
- printk(KERN_INFO "T [desc] [address 63:0 ] "
- "[PlPOCIStDDM Ln] [bi->dma ] "
- "leng ntw timestamp bi->skb\n");
+ pr_info("------------------------------------\n");
+ pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
+ pr_info("------------------------------------\n");
+ pr_info("T [desc] [address 63:0 ] [PlPOCIStDDM Ln] "
+ "[bi->dma ] leng ntw timestamp "
+ "bi->skb\n");
for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
+ const char *next_desc;
struct igb_tx_buffer *buffer_info;
tx_desc = IGB_TX_DESC(tx_ring, i);
buffer_info = &tx_ring->tx_buffer_info[i];
u0 = (struct my_u0 *)tx_desc;
- printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX"
- " %04X %p %016llX %p", i,
+ if (i == tx_ring->next_to_use &&
+ i == tx_ring->next_to_clean)
+ next_desc = " NTC/U";
+ else if (i == tx_ring->next_to_use)
+ next_desc = " NTU";
+ else if (i == tx_ring->next_to_clean)
+ next_desc = " NTC";
+ else
+ next_desc = "";
+
+ pr_info("T [0x%03X] %016llX %016llX %016llX"
+ " %04X %p %016llX %p%s\n", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
(u64)buffer_info->dma,
buffer_info->length,
buffer_info->next_to_watch,
(u64)buffer_info->time_stamp,
- buffer_info->skb);
- if (i == tx_ring->next_to_use &&
- i == tx_ring->next_to_clean)
- printk(KERN_CONT " NTC/U\n");
- else if (i == tx_ring->next_to_use)
- printk(KERN_CONT " NTU\n");
- else if (i == tx_ring->next_to_clean)
- printk(KERN_CONT " NTC\n");
- else
- printk(KERN_CONT "\n");
+ buffer_info->skb, next_desc);
if (netif_msg_pktdata(adapter) && buffer_info->dma != 0)
print_hex_dump(KERN_INFO, "",
/* Print RX Rings Summary */
rx_ring_summary:
dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
- printk(KERN_INFO "Queue [NTU] [NTC]\n");
+ pr_info("Queue [NTU] [NTC]\n");
for (n = 0; n < adapter->num_rx_queues; n++) {
rx_ring = adapter->rx_ring[n];
- printk(KERN_INFO " %5d %5X %5X\n", n,
- rx_ring->next_to_use, rx_ring->next_to_clean);
+ pr_info(" %5d %5X %5X\n",
+ n, rx_ring->next_to_use, rx_ring->next_to_clean);
}
/* Print RX Rings */
for (n = 0; n < adapter->num_rx_queues; n++) {
rx_ring = adapter->rx_ring[n];
- printk(KERN_INFO "------------------------------------\n");
- printk(KERN_INFO "RX QUEUE INDEX = %d\n", rx_ring->queue_index);
- printk(KERN_INFO "------------------------------------\n");
- printk(KERN_INFO "R [desc] [ PktBuf A0] "
- "[ HeadBuf DD] [bi->dma ] [bi->skb] "
- "<-- Adv Rx Read format\n");
- printk(KERN_INFO "RWB[desc] [PcsmIpSHl PtRs] "
- "[vl er S cks ln] ---------------- [bi->skb] "
- "<-- Adv Rx Write-Back format\n");
+ pr_info("------------------------------------\n");
+ pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
+ pr_info("------------------------------------\n");
+ pr_info("R [desc] [ PktBuf A0] [ HeadBuf DD] "
+ "[bi->dma ] [bi->skb] <-- Adv Rx Read format\n");
+ pr_info("RWB[desc] [PcsmIpSHl PtRs] [vl er S cks ln] -----"
+ "----------- [bi->skb] <-- Adv Rx Write-Back format\n");
for (i = 0; i < rx_ring->count; i++) {
+ const char *next_desc;
struct igb_rx_buffer *buffer_info;
buffer_info = &rx_ring->rx_buffer_info[i];
rx_desc = IGB_RX_DESC(rx_ring, i);
u0 = (struct my_u0 *)rx_desc;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
+
+ if (i == rx_ring->next_to_use)
+ next_desc = " NTU";
+ else if (i == rx_ring->next_to_clean)
+ next_desc = " NTC";
+ else
+ next_desc = "";
+
if (staterr & E1000_RXD_STAT_DD) {
/* Descriptor Done */
- printk(KERN_INFO "RWB[0x%03X] %016llX "
- "%016llX ---------------- %p", i,
+ pr_info("%s[0x%03X] %016llX %016llX -------"
+ "--------- %p%s\n", "RWB", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
- buffer_info->skb);
+ buffer_info->skb, next_desc);
} else {
- printk(KERN_INFO "R [0x%03X] %016llX "
- "%016llX %016llX %p", i,
+ pr_info("%s[0x%03X] %016llX %016llX %016llX"
+ " %p%s\n", "R ", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
(u64)buffer_info->dma,
- buffer_info->skb);
+ buffer_info->skb, next_desc);
if (netif_msg_pktdata(adapter)) {
print_hex_dump(KERN_INFO, "",
PAGE_SIZE/2, true);
}
}
-
- if (i == rx_ring->next_to_use)
- printk(KERN_CONT " NTU\n");
- else if (i == rx_ring->next_to_clean)
- printk(KERN_CONT " NTC\n");
- else
- printk(KERN_CONT "\n");
-
}
}
static int __init igb_init_module(void)
{
int ret;
- printk(KERN_INFO "%s - version %s\n",
+ pr_info("%s - version %s\n",
igb_driver_string, igb_driver_version);
- printk(KERN_INFO "%s\n", igb_copyright);
+ pr_info("%s\n", igb_copyright);
#ifdef CONFIG_IGB_DCA
dca_register_notify(&dca_notifier);
igb_get_phy_info(hw);
}
-static u32 igb_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t igb_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int igb_set_features(struct net_device *netdev, u32 features)
+static int igb_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
igb_vlan_mode(netdev, features);
ctrl = rd32(E1000_CTRL);
/* Links status message must follow this format */
- printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s, "
- "Flow Control: %s\n",
+ printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s "
+ "Duplex, Flow Control: %s\n",
netdev->name,
adapter->link_speed,
adapter->link_duplex == FULL_DUPLEX ?
- "Full Duplex" : "Half Duplex",
- ((ctrl & E1000_CTRL_TFCE) &&
- (ctrl & E1000_CTRL_RFCE)) ? "RX/TX" :
- ((ctrl & E1000_CTRL_RFCE) ? "RX" :
- ((ctrl & E1000_CTRL_TFCE) ? "TX" : "None")));
+ "Full" : "Half",
+ (ctrl & E1000_CTRL_TFCE) &&
+ (ctrl & E1000_CTRL_RFCE) ? "RX/TX" :
+ (ctrl & E1000_CTRL_RFCE) ? "RX" :
+ (ctrl & E1000_CTRL_TFCE) ? "TX" : "None");
/* check for thermal sensor event */
- if (igb_thermal_sensor_event(hw, E1000_THSTAT_LINK_THROTTLE)) {
- printk(KERN_INFO "igb: %s The network adapter "
- "link speed was downshifted "
- "because it overheated.\n",
- netdev->name);
+ if (igb_thermal_sensor_event(hw,
+ E1000_THSTAT_LINK_THROTTLE)) {
+ netdev_info(netdev, "The network adapter link "
+ "speed was downshifted because it "
+ "overheated\n");
}
/* adjust timeout factor according to speed/duplex */
adapter->link_duplex = 0;
/* check for thermal sensor event */
- if (igb_thermal_sensor_event(hw, E1000_THSTAT_PWR_DOWN)) {
- printk(KERN_ERR "igb: %s The network adapter "
- "was stopped because it "
- "overheated.\n",
- netdev->name);
+ if (igb_thermal_sensor_event(hw,
+ E1000_THSTAT_PWR_DOWN)) {
+ netdev_err(netdev, "The network adapter was "
+ "stopped because it overheated\n");
}
/* Links status message must follow this format */
return true;
if (!page) {
- page = netdev_alloc_page(rx_ring->netdev);
+ page = alloc_page(GFP_ATOMIC | __GFP_COLD);
bi->page = page;
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_failed++;
return 0;
}
-static void igb_vlan_mode(struct net_device *netdev, u32 features)
+static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
igb_rlpml_set(adapter);
}
-static void igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
igb_vfta_set(hw, vid, true);
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
igb_vfta_set(hw, vid, false);
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
static void igb_restore_vlan(struct igb_adapter *adapter)
wr32(E1000_DMCTXTH, 0);
/*
- * DMA Coalescing high water mark needs to be higher
- * than the RX threshold. set hwm to PBA - 2 * max
- * frame size
+ * DMA Coalescing high water mark needs to be greater
+ * than the Rx threshold. Set hwm to PBA - max frame
+ * size in 16B units, capping it at PBA - 6KB.
*/
- hwm = pba - (2 * adapter->max_frame_size);
+ hwm = 64 * pba - adapter->max_frame_size / 16;
+ if (hwm < 64 * (pba - 6))
+ hwm = 64 * (pba - 6);
+ reg = rd32(E1000_FCRTC);
+ reg &= ~E1000_FCRTC_RTH_COAL_MASK;
+ reg |= ((hwm << E1000_FCRTC_RTH_COAL_SHIFT)
+ & E1000_FCRTC_RTH_COAL_MASK);
+ wr32(E1000_FCRTC, reg);
+
+ /*
+ * Set the DMA Coalescing Rx threshold to PBA - 2 * max
+ * frame size, capping it at PBA - 10KB.
+ */
+ dmac_thr = pba - adapter->max_frame_size / 512;
+ if (dmac_thr < pba - 10)
+ dmac_thr = pba - 10;
reg = rd32(E1000_DMACR);
reg &= ~E1000_DMACR_DMACTHR_MASK;
- dmac_thr = pba - 4;
-
reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT)
& E1000_DMACR_DMACTHR_MASK);
* coalescing(smart fifb)-UTRESH=0
*/
wr32(E1000_DMCRTRH, 0);
- wr32(E1000_FCRTC, hwm);
reg = (IGB_DMCTLX_DCFLUSH_DIS | 0x4);
struct ethtool_drvinfo *drvinfo)
{
struct igbvf_adapter *adapter = netdev_priv(netdev);
- char firmware_version[32] = "N/A";
- strncpy(drvinfo->driver, igbvf_driver_name, 32);
- strncpy(drvinfo->version, igbvf_driver_version, 32);
- strncpy(drvinfo->fw_version, firmware_version, 32);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->driver, igbvf_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, igbvf_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = igbvf_get_regs_len(netdev);
drvinfo->eedump_len = igbvf_get_eeprom_len(netdev);
}
*******************************************************************************/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/types.h>
#include <linux/init.h>
e1000_rlpml_set_vf(hw, max_frame_size);
}
-static void igbvf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int igbvf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct igbvf_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- if (hw->mac.ops.set_vfta(hw, vid, true))
+ if (hw->mac.ops.set_vfta(hw, vid, true)) {
dev_err(&adapter->pdev->dev, "Failed to add vlan id %d\n", vid);
- else
- set_bit(vid, adapter->active_vlans);
+ return -EINVAL;
+ }
+ set_bit(vid, adapter->active_vlans);
+ return 0;
}
-static void igbvf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int igbvf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct igbvf_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
if (!test_bit(__IGBVF_DOWN, &adapter->state))
igbvf_irq_enable(adapter);
- if (hw->mac.ops.set_vfta(hw, vid, false))
+ if (hw->mac.ops.set_vfta(hw, vid, false)) {
dev_err(&adapter->pdev->dev,
"Failed to remove vlan id %d\n", vid);
- else
- clear_bit(vid, adapter->active_vlans);
+ return -EINVAL;
+ }
+ clear_bit(vid, adapter->active_vlans);
+ return 0;
}
static void igbvf_restore_vlan(struct igbvf_adapter *adapter)
static void igbvf_print_link_info(struct igbvf_adapter *adapter)
{
- dev_info(&adapter->pdev->dev, "Link is Up %d Mbps %s\n",
- adapter->link_speed,
- ((adapter->link_duplex == FULL_DUPLEX) ?
- "Full Duplex" : "Half Duplex"));
+ dev_info(&adapter->pdev->dev, "Link is Up %d Mbps %s Duplex\n",
+ adapter->link_speed,
+ adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half");
}
static bool igbvf_has_link(struct igbvf_adapter *adapter)
dev_info(&pdev->dev, "Address: %pM\n", netdev->dev_addr);
}
-static int igbvf_set_features(struct net_device *netdev, u32 features)
+static int igbvf_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct igbvf_adapter *adapter = netdev_priv(netdev);
static int __init igbvf_init_module(void)
{
int ret;
- printk(KERN_INFO "%s - version %s\n",
- igbvf_driver_string, igbvf_driver_version);
- printk(KERN_INFO "%s\n", igbvf_copyright);
+ pr_info("%s - version %s\n", igbvf_driver_string, igbvf_driver_version);
+ pr_info("%s\n", igbvf_copyright);
ret = pci_register_driver(&igbvf_driver);
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
- strncpy(drvinfo->driver, ixgb_driver_name, 32);
- strncpy(drvinfo->version, ixgb_driver_version, 32);
- strncpy(drvinfo->fw_version, "N/A", 32);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->driver, ixgb_driver_name,
+ sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ixgb_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = IXGB_STATS_LEN;
drvinfo->regdump_len = ixgb_get_regs_len(netdev);
drvinfo->eedump_len = ixgb_get_eeprom_len(netdev);
static void ixgb_vlan_strip_enable(struct ixgb_adapter *adapter);
static void ixgb_vlan_strip_disable(struct ixgb_adapter *adapter);
-static void ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-static void ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+static int ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+static int ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
static void ixgb_restore_vlan(struct ixgb_adapter *adapter);
#ifdef CONFIG_NET_POLL_CONTROLLER
if (IXGB_READ_REG(&adapter->hw, STATUS) & IXGB_STATUS_PCIX_MODE) {
err = pci_enable_msi(adapter->pdev);
if (!err) {
- adapter->have_msi = 1;
+ adapter->have_msi = true;
irq_flags = 0;
}
/* proceed to try to request regular interrupt */
}
}
-static u32
-ixgb_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t
+ixgb_fix_features(struct net_device *netdev, netdev_features_t features)
{
/*
* Tx VLAN insertion does not work per HW design when Rx stripping is
}
static int
-ixgb_set_features(struct net_device *netdev, u32 features)
+ixgb_set_features(struct net_device *netdev, netdev_features_t features)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
if (!(changed & (NETIF_F_RXCSUM|NETIF_F_HW_VLAN_RX)))
return 0;
IXGB_WRITE_REG(&adapter->hw, CTRL0, ctrl);
}
-static void
+static int
ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
vfta |= (1 << (vid & 0x1F));
ixgb_write_vfta(&adapter->hw, index, vfta);
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void
+static int
ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
vfta &= ~(1 << (vid & 0x1F));
ixgb_write_vfta(&adapter->hw, index, vfta);
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
static void
case IXGBE_DEV_ID_82599_SFP_FCOE:
case IXGBE_DEV_ID_82599_SFP_EM:
case IXGBE_DEV_ID_82599_SFP_SF2:
+ case IXGBE_DEV_ID_82599_SFP_SF_QP:
case IXGBE_DEV_ID_82599EN_SFP:
media_type = ixgbe_media_type_fiber;
break;
if (hw->mac.type == ixgbe_mac_X540) {
if (hw->phy.id == 0)
hw->phy.ops.identify(hw);
- hw->phy.ops.read_reg(hw, 0x3, IXGBE_PCRC8ECL, &i);
- hw->phy.ops.read_reg(hw, 0x3, IXGBE_PCRC8ECH, &i);
- hw->phy.ops.read_reg(hw, 0x3, IXGBE_LDPCECL, &i);
- hw->phy.ops.read_reg(hw, 0x3, IXGBE_LDPCECH, &i);
+ hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i);
+ hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i);
+ hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i);
+ hw->phy.ops.read_reg(hw, IXGBE_LDPCECH, MDIO_MMD_PCS, &i);
}
return 0;
s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index)
{
ixgbe_link_speed speed = 0;
- bool link_up = 0;
+ bool link_up = false;
u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC);
u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- /* Abort a bad configuration */
- if (ffs(up_map) > adapter->dcb_cfg.num_tcs.pg_tcs)
- return;
-
if (prio != DCB_ATTR_VALUE_UNDEFINED)
adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio;
if (bwg_id != DCB_ATTR_VALUE_UNDEFINED)
if (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap !=
adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)
- adapter->dcb_set_bitmap |= BIT_PFC;
+ adapter->dcb_set_bitmap |= BIT_PFC | BIT_APP_UPCHG;
}
static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- /* Abort bad configurations */
- if (ffs(up_map) > adapter->dcb_cfg.num_tcs.pg_tcs)
- return;
-
if (prio != DCB_ATTR_VALUE_UNDEFINED)
adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio;
if (bwg_id != DCB_ATTR_VALUE_UNDEFINED)
*setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc;
}
+#ifdef IXGBE_FCOE
+static void ixgbe_dcbnl_devreset(struct net_device *dev)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+ while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
+ usleep_range(1000, 2000);
+
+ if (netif_running(dev))
+ dev->netdev_ops->ndo_stop(dev);
+
+ ixgbe_clear_interrupt_scheme(adapter);
+ ixgbe_init_interrupt_scheme(adapter);
+
+ if (netif_running(dev))
+ dev->netdev_ops->ndo_open(dev);
+
+ clear_bit(__IXGBE_RESETTING, &adapter->state);
+}
+#endif
+
static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
if (ret)
return DCB_NO_HW_CHG;
-#ifdef IXGBE_FCOE
- if (up && !(up & (1 << adapter->fcoe.up)))
- adapter->dcb_set_bitmap |= BIT_APP_UPCHG;
-
- /*
- * Only take down the adapter if an app change occurred. FCoE
- * may shuffle tx rings in this case and this can not be done
- * without a reset currently.
- */
- if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
- while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
- usleep_range(1000, 2000);
-
- adapter->fcoe.up = ffs(up) - 1;
-
- if (netif_running(netdev))
- netdev->netdev_ops->ndo_stop(netdev);
- ixgbe_clear_interrupt_scheme(adapter);
- }
-#endif
-
if (adapter->dcb_cfg.pfc_mode_enable) {
switch (adapter->hw.mac.type) {
case ixgbe_mac_82599EB:
}
}
-#ifdef IXGBE_FCOE
- if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
- ixgbe_init_interrupt_scheme(adapter);
- if (netif_running(netdev))
- netdev->netdev_ops->ndo_open(netdev);
- ret = DCB_HW_CHG_RST;
- }
-#endif
-
if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) {
u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS];
u8 bwg_id[MAX_TRAFFIC_CLASS], prio_type[MAX_TRAFFIC_CLASS];
if (adapter->dcb_cfg.pfc_mode_enable)
adapter->hw.fc.current_mode = ixgbe_fc_pfc;
- if (adapter->dcb_set_bitmap & BIT_APP_UPCHG)
- clear_bit(__IXGBE_RESETTING, &adapter->state);
+#ifdef IXGBE_FCOE
+ /* Reprogam FCoE hardware offloads when the traffic class
+ * FCoE is using changes. This happens if the APP info
+ * changes or the up2tc mapping is updated.
+ */
+ if ((up && !(up & (1 << adapter->fcoe.up))) ||
+ (adapter->dcb_set_bitmap & BIT_APP_UPCHG)) {
+ adapter->fcoe.up = ffs(up) - 1;
+ ixgbe_dcbnl_devreset(netdev);
+ ret = DCB_HW_CHG_RST;
+ }
+#endif
+
adapter->dcb_set_bitmap = 0x00;
return ret;
}
return ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en, prio_tc);
}
-#ifdef IXGBE_FCOE
-static void ixgbe_dcbnl_devreset(struct net_device *dev)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
-
- if (netif_running(dev))
- dev->netdev_ops->ndo_stop(dev);
-
- ixgbe_clear_interrupt_scheme(adapter);
- ixgbe_init_interrupt_scheme(adapter);
-
- if (netif_running(dev))
- dev->netdev_ops->ndo_open(dev);
-}
-#endif
-
static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
struct dcb_app *app)
{
ixgbe_dcbnl_ieee_setets(dev, &ets);
ixgbe_dcbnl_ieee_setpfc(dev, &pfc);
} else if (mode & DCB_CAP_DCBX_VER_CEE) {
- adapter->dcb_set_bitmap |= (BIT_PFC & BIT_PG_TX & BIT_PG_RX);
+ u8 mask = BIT_PFC | BIT_PG_TX | BIT_PG_RX | BIT_APP_UPCHG;
+
+ adapter->dcb_set_bitmap |= mask;
ixgbe_dcbnl_set_all(dev);
} else {
/* Drop into single TC mode strict priority as this
struct ethtool_drvinfo *drvinfo)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- char firmware_version[32];
u32 nvm_track_id;
- strncpy(drvinfo->driver, ixgbe_driver_name,
- sizeof(drvinfo->driver) - 1);
- strncpy(drvinfo->version, ixgbe_driver_version,
- sizeof(drvinfo->version) - 1);
+ strlcpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ixgbe_driver_version,
+ sizeof(drvinfo->version));
nvm_track_id = (adapter->eeprom_verh << 16) |
adapter->eeprom_verl;
- snprintf(firmware_version, sizeof(firmware_version), "0x%08x",
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "0x%08x",
nvm_track_id);
- strncpy(drvinfo->fw_version, firmware_version,
- sizeof(drvinfo->fw_version) - 1);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
- sizeof(drvinfo->bus_info) - 1);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = IXGBE_STATS_LEN;
drvinfo->testinfo_len = IXGBE_TEST_LEN;
drvinfo->regdump_len = ixgbe_get_regs_len(netdev);
/* WOL not supported except for the following */
switch(hw->device_id) {
case IXGBE_DEV_ID_82599_SFP:
- /* Only this subdevice supports WOL */
- if (hw->subsystem_device_id != IXGBE_SUBDEV_ID_82599_SFP) {
+ /* Only these subdevices could supports WOL */
+ switch (hw->subsystem_device_id) {
+ case IXGBE_SUBDEV_ID_82599_560FLR:
+ /* only support first port */
+ if (hw->bus.func != 0) {
+ wol->supported = 0;
+ break;
+ }
+ case IXGBE_SUBDEV_ID_82599_SFP:
+ retval = 0;
+ break;
+ default:
wol->supported = 0;
break;
}
- retval = 0;
break;
case IXGBE_DEV_ID_82599_COMBO_BACKPLANE:
/* All except this subdevice support WOL */
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 },
/* required last entry */
{0, }
};
{
BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));
- /* flush memory to make sure state is correct before next watchog */
+ /* flush memory to make sure state is correct before next watchdog */
smp_mb__before_clear_bit();
clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
}
if (ring_is_ps_enabled(rx_ring)) {
if (!bi->page) {
- bi->page = netdev_alloc_page(rx_ring->netdev);
+ bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
if (!bi->page) {
rx_ring->rx_stats.alloc_rx_page_failed++;
goto no_buffers;
IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK);
/* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read
- * therefore no explict interrupt disable is necessary */
+ * therefore no explicit interrupt disable is necessary */
eicr = IXGBE_READ_REG(hw, IXGBE_EICR);
if (!eicr) {
/*
hw->mac.ops.enable_rx_dma(hw, rxctrl);
}
-static void ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
/* add VID to filter table */
hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true);
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
/* remove VID from filter table */
hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false);
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
/**
static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter)
{
/*
- * We are assuming the worst case scenerio here, and that
+ * We are assuming the worst case scenario here, and that
* is that an SFP was inserted/removed after the reset
* but before SFP detection was enabled. As such the best
* solution is to just start searching as soon as we start
case IXGBE_ERR_EEPROM_VERSION:
/* We are running on a pre-production device, log a warning */
e_dev_warn("This device is a pre-production adapter/LOM. "
- "Please be aware there may be issuesassociated with "
+ "Please be aware there may be issues associated with "
"your hardware. If you are experiencing problems "
"please contact your Intel or hardware "
"representative who provided you with this "
/* Mark all the VFs as inactive */
for (i = 0 ; i < adapter->num_vfs; i++)
- adapter->vfinfo[i].clear_to_send = 0;
+ adapter->vfinfo[i].clear_to_send = false;
/* ping all the active vfs to let them know we are going down */
ixgbe_ping_all_vfs(adapter);
* @adapter - pointer to the device adapter structure
*
* This function serves two purposes. First it strobes the interrupt lines
- * in order to make certain interrupts are occuring. Secondly it sets the
+ * in order to make certain interrupts are occurring. Secondly it sets the
* bits needed to check for TX hangs. As a result we should immediately
- * determine if a hang has occured.
+ * determine if a hang has occurred.
*/
static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
{
return -EINVAL;
/* Hardware has to reinitialize queues and interrupts to
- * match packet buffer alignment. Unfortunantly, the
+ * match packet buffer alignment. Unfortunately, the
* hardware is not flexible enough to do this dynamically.
*/
if (netif_running(dev))
ixgbe_reset(adapter);
}
-static u32 ixgbe_fix_features(struct net_device *netdev, u32 data)
+static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
+ netdev_features_t data)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
return data;
}
-static int ixgbe_set_features(struct net_device *netdev, u32 data)
+static int ixgbe_set_features(struct net_device *netdev,
+ netdev_features_t data)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
bool need_reset = false;
adapter->wol = 0;
switch (pdev->device) {
case IXGBE_DEV_ID_82599_SFP:
- /* Only this subdevice supports WOL */
- if (pdev->subsystem_device == IXGBE_SUBDEV_ID_82599_SFP)
+ /* Only these subdevice supports WOL */
+ switch (pdev->subsystem_device) {
+ case IXGBE_SUBDEV_ID_82599_560FLR:
+ /* only support first port */
+ if (hw->bus.func != 0)
+ break;
+ case IXGBE_SUBDEV_ID_82599_SFP:
adapter->wol = IXGBE_WUFC_MAG;
+ break;
+ }
break;
case IXGBE_DEV_ID_82599_COMBO_BACKPLANE:
/* All except this subdevice support WOL */
u32 max_retry = 10;
u32 retry = 0;
u16 swfw_mask = 0;
- bool nack = 1;
+ bool nack = true;
*data = 0;
if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)
static s32 ixgbe_clock_in_i2c_byte(struct ixgbe_hw *hw, u8 *data)
{
s32 i;
- bool bit = 0;
+ bool bit = false;
for (i = 7; i >= 0; i--) {
ixgbe_clock_in_i2c_bit(hw, &bit);
s32 status = 0;
s32 i;
u32 i2cctl;
- bool bit = 0;
+ bool bit = false;
for (i = 7; i >= 0; i--) {
bit = (data >> i) & 0x1;
i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL);
i2cctl |= IXGBE_I2C_DATA_OUT;
IXGBE_WRITE_REG(hw, IXGBE_I2CCTL, i2cctl);
+ IXGBE_WRITE_FLUSH(hw);
return status;
}
u32 i = 0;
u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL);
u32 timeout = 10;
- bool ack = 1;
+ bool ack = true;
ixgbe_raise_i2c_clk(hw, &i2cctl);
bool data;
if (*i2cctl & IXGBE_I2C_DATA_IN)
- data = 1;
+ data = true;
else
- data = 0;
+ data = false;
return data;
}
/* reply to reset with ack and vf mac address */
msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
- memcpy(new_mac, vf_mac, IXGBE_ETH_LENGTH_OF_ADDRESS);
+ memcpy(new_mac, vf_mac, ETH_ALEN);
/*
* Piggyback the multicast filter type so VF can compute the
* correct vectors
int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask);
void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter);
void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter);
-void ixgbe_dump_registers(struct ixgbe_adapter *adapter);
int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac);
int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan,
u8 qos);
#define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a
#define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529
#define IXGBE_SUBDEV_ID_82599_SFP 0x11A9
+#define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0
#define IXGBE_DEV_ID_82599_SFP_EM 0x1507
#define IXGBE_DEV_ID_82599_SFP_SF2 0x154D
#define IXGBE_DEV_ID_82599EN_SFP 0x1557
#define IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ 0x000C
#define IXGBE_DEV_ID_82599_LS 0x154F
#define IXGBE_DEV_ID_X540T 0x1528
+#define IXGBE_DEV_ID_82599_SFP_SF_QP 0x154A
/* VF Device IDs */
#define IXGBE_DEV_ID_82599_VF 0x10ED
#define IXGBE_NVM_POLL_WRITE 1 /* Flag for polling for write complete */
#define IXGBE_NVM_POLL_READ 0 /* Flag for polling for read complete */
-#define IXGBE_ETH_LENGTH_OF_ADDRESS 6
-
#define IXGBE_EEPROM_PAGE_SIZE_MAX 128
#define IXGBE_EEPROM_RD_BUFFER_MAX_COUNT 512 /* EEPROM words # read in burst */
#define IXGBE_EEPROM_WR_BUFFER_MAX_COUNT 256 /* EEPROM words # wr in burst */
struct ixgbe_mac_info {
struct ixgbe_mac_operations ops;
enum ixgbe_mac_type type;
- u8 addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
- u8 perm_addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
- u8 san_addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
+ u8 addr[ETH_ALEN];
+ u8 perm_addr[ETH_ALEN];
+ u8 san_addr[ETH_ALEN];
/* prefix for World Wide Node Name (WWNN) */
u16 wwnn_prefix;
/* prefix for World Wide Port Name (WWPN) */
{
u32 macc_reg;
u32 ledctl_reg;
+ ixgbe_link_speed speed;
+ bool link_up;
/*
- * In order for the blink bit in the LED control register
- * to work, link and speed must be forced in the MAC. We
- * will reverse this when we stop the blinking.
+ * Link should be up in order for the blink bit in the LED control
+ * register to work. Force link and speed in the MAC if link is down.
+ * This will be reversed when we stop the blinking.
*/
- macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC);
- macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS;
- IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg);
-
+ hw->mac.ops.check_link(hw, &speed, &link_up, false);
+ if (link_up == false) {
+ macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC);
+ macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS;
+ IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg);
+ }
/* Set the LED to LINK_UP + BLINK. */
ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
ledctl_reg &= ~IXGBE_LED_MODE_MASK(index);
#define IXGBE_VF_IRQ_CLEAR_MASK 7
#define IXGBE_VF_MAX_TX_QUEUES 1
#define IXGBE_VF_MAX_RX_QUEUES 1
-#define IXGBE_ETH_LENGTH_OF_ADDRESS 6
/* Link speed */
typedef u32 ixgbe_link_speed;
/* ethtool support for ixgbevf */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/types.h>
#include <linux/module.h>
#include <linux/slab.h>
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
- strlcpy(drvinfo->driver, ixgbevf_driver_name, 32);
- strlcpy(drvinfo->version, ixgbevf_driver_version, 32);
-
- strlcpy(drvinfo->fw_version, "N/A", 4);
- strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->driver, ixgbevf_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ixgbevf_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
}
static void ixgbevf_get_ringparam(struct net_device *netdev,
writel((W & M), (adapter->hw.hw_addr + R)); \
val = readl(adapter->hw.hw_addr + R); \
if ((W & M) != (val & M)) { \
- printk(KERN_ERR "set/check reg %04X test failed: got 0x%08X " \
- "expected 0x%08X\n", R, (val & M), (W & M)); \
+ pr_err("set/check reg %04X test failed: got 0x%08X expected " \
+ "0x%08X\n", R, (val & M), (W & M)); \
*data = R; \
writel(before, (adapter->hw.hw_addr + R)); \
return 1; \
/******************************************************************************
Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
******************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/module.h>
if (!bi->page_dma &&
(adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
if (!bi->page) {
- bi->page = netdev_alloc_page(adapter->netdev);
+ bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
if (!bi->page) {
adapter->alloc_rx_page_failed++;
goto no_buffers;
}
}
-static void ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
if (hw->mac.ops.set_vfta)
hw->mac.ops.set_vfta(hw, vid, 0, true);
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
if (hw->mac.ops.set_vfta)
hw->mac.ops.set_vfta(hw, vid, 0, false);
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
int count = 0;
if ((netdev_uc_count(netdev)) > 10) {
- printk(KERN_ERR "Too many unicast filters - No Space\n");
+ pr_err("Too many unicast filters - No Space\n");
return -ENOSPC;
}
err = ixgbevf_alloc_queues(adapter);
if (err) {
- printk(KERN_ERR "Unable to allocate memory for queues\n");
+ pr_err("Unable to allocate memory for queues\n");
goto err_alloc_queues;
}
} else {
err = hw->mac.ops.init_hw(hw);
if (err) {
- printk(KERN_ERR "init_shared_code failed: %d\n", err);
+ pr_err("init_shared_code failed: %d\n", err);
goto out;
}
}
* the vf can't start. */
if (hw->adapter_stopped) {
err = IXGBE_ERR_MBX;
- printk(KERN_ERR "Unable to start - perhaps the PF"
- " Driver isn't up yet\n");
+ pr_err("Unable to start - perhaps the PF Driver isn't "
+ "up yet\n");
goto err_setup_reset;
}
}
break;
default:
if (unlikely(net_ratelimit())) {
- printk(KERN_WARNING
- "partial checksum but "
- "proto=%x!\n",
- skb->protocol);
+ pr_warn("partial checksum but "
+ "proto=%x!\n", skb->protocol);
}
break;
}
return stats;
}
-static int ixgbevf_set_features(struct net_device *netdev, u32 features)
+static int ixgbevf_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
if (!is_valid_ether_addr(netdev->dev_addr)) {
- printk(KERN_ERR "invalid MAC address\n");
+ pr_err("invalid MAC address\n");
err = -EIO;
goto err_sw_init;
}
static int __init ixgbevf_init_module(void)
{
int ret;
- printk(KERN_INFO "ixgbevf: %s - version %s\n", ixgbevf_driver_string,
- ixgbevf_driver_version);
+ pr_info("%s - version %s\n", ixgbevf_driver_string,
+ ixgbevf_driver_version);
- printk(KERN_INFO "%s\n", ixgbevf_copyright);
+ pr_info("%s\n", ixgbevf_copyright);
ret = pci_register_driver(&ixgbevf_driver);
return ret;
#define IXGBE_VFMAILBOX_RSTD 0x00000080 /* PF has indicated reset done */
#define IXGBE_VFMAILBOX_R2C_BITS 0x000000B0 /* All read to clear bits */
-#define IXGBE_PFMAILBOX(x) (0x04B00 + (4 * x))
-#define IXGBE_PFMBMEM(vfn) (0x13000 + (64 * vfn))
+#define IXGBE_PFMAILBOX(x) (0x04B00 + (4 * (x)))
+#define IXGBE_PFMBMEM(vfn) (0x13000 + (64 * (vfn)))
#define IXGBE_PFMAILBOX_STS 0x00000001 /* Initiate message send to VF */
#define IXGBE_PFMAILBOX_ACK 0x00000002 /* Ack message recv'd from VF */
#define IXGBE_VTEIMC 0x0010C
#define IXGBE_VTEIAC 0x00110
#define IXGBE_VTEIAM 0x00114
-#define IXGBE_VTEITR(x) (0x00820 + (4 * x))
-#define IXGBE_VTIVAR(x) (0x00120 + (4 * x))
+#define IXGBE_VTEITR(x) (0x00820 + (4 * (x)))
+#define IXGBE_VTIVAR(x) (0x00120 + (4 * (x)))
#define IXGBE_VTIVAR_MISC 0x00140
-#define IXGBE_VTRSCINT(x) (0x00180 + (4 * x))
-#define IXGBE_VFRDBAL(x) (0x01000 + (0x40 * x))
-#define IXGBE_VFRDBAH(x) (0x01004 + (0x40 * x))
-#define IXGBE_VFRDLEN(x) (0x01008 + (0x40 * x))
-#define IXGBE_VFRDH(x) (0x01010 + (0x40 * x))
-#define IXGBE_VFRDT(x) (0x01018 + (0x40 * x))
-#define IXGBE_VFRXDCTL(x) (0x01028 + (0x40 * x))
-#define IXGBE_VFSRRCTL(x) (0x01014 + (0x40 * x))
-#define IXGBE_VFRSCCTL(x) (0x0102C + (0x40 * x))
+#define IXGBE_VTRSCINT(x) (0x00180 + (4 * (x)))
+#define IXGBE_VFRDBAL(x) (0x01000 + (0x40 * (x)))
+#define IXGBE_VFRDBAH(x) (0x01004 + (0x40 * (x)))
+#define IXGBE_VFRDLEN(x) (0x01008 + (0x40 * (x)))
+#define IXGBE_VFRDH(x) (0x01010 + (0x40 * (x)))
+#define IXGBE_VFRDT(x) (0x01018 + (0x40 * (x)))
+#define IXGBE_VFRXDCTL(x) (0x01028 + (0x40 * (x)))
+#define IXGBE_VFSRRCTL(x) (0x01014 + (0x40 * (x)))
+#define IXGBE_VFRSCCTL(x) (0x0102C + (0x40 * (x)))
#define IXGBE_VFPSRTYPE 0x00300
-#define IXGBE_VFTDBAL(x) (0x02000 + (0x40 * x))
-#define IXGBE_VFTDBAH(x) (0x02004 + (0x40 * x))
-#define IXGBE_VFTDLEN(x) (0x02008 + (0x40 * x))
-#define IXGBE_VFTDH(x) (0x02010 + (0x40 * x))
-#define IXGBE_VFTDT(x) (0x02018 + (0x40 * x))
-#define IXGBE_VFTXDCTL(x) (0x02028 + (0x40 * x))
-#define IXGBE_VFTDWBAL(x) (0x02038 + (0x40 * x))
-#define IXGBE_VFTDWBAH(x) (0x0203C + (0x40 * x))
-#define IXGBE_VFDCA_RXCTRL(x) (0x0100C + (0x40 * x))
-#define IXGBE_VFDCA_TXCTRL(x) (0x0200c + (0x40 * x))
+#define IXGBE_VFTDBAL(x) (0x02000 + (0x40 * (x)))
+#define IXGBE_VFTDBAH(x) (0x02004 + (0x40 * (x)))
+#define IXGBE_VFTDLEN(x) (0x02008 + (0x40 * (x)))
+#define IXGBE_VFTDH(x) (0x02010 + (0x40 * (x)))
+#define IXGBE_VFTDT(x) (0x02018 + (0x40 * (x)))
+#define IXGBE_VFTXDCTL(x) (0x02028 + (0x40 * (x)))
+#define IXGBE_VFTDWBAL(x) (0x02038 + (0x40 * (x)))
+#define IXGBE_VFTDWBAH(x) (0x0203C + (0x40 * (x)))
+#define IXGBE_VFDCA_RXCTRL(x) (0x0100C + (0x40 * (x)))
+#define IXGBE_VFDCA_TXCTRL(x) (0x0200c + (0x40 * (x)))
#define IXGBE_VFGPRC 0x0101C
#define IXGBE_VFGPTC 0x0201C
#define IXGBE_VFGORC_LSB 0x01020
if (msgbuf[0] != (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK))
return IXGBE_ERR_INVALID_MAC_ADDR;
- memcpy(hw->mac.perm_addr, addr, IXGBE_ETH_LENGTH_OF_ADDRESS);
+ memcpy(hw->mac.perm_addr, addr, ETH_ALEN);
hw->mac.mc_filter_type = msgbuf[IXGBE_VF_MC_TYPE_WORD];
return 0;
**/
static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr)
{
- memcpy(mac_addr, hw->mac.perm_addr, IXGBE_ETH_LENGTH_OF_ADDRESS);
+ memcpy(mac_addr, hw->mac.perm_addr, ETH_ALEN);
return 0;
}
jme_new_phy_off(jme);
}
+static int
+jme_phy_specreg_read(struct jme_adapter *jme, u32 specreg)
+{
+ u32 phy_addr;
+
+ phy_addr = JM_PHY_SPEC_REG_READ | specreg;
+ jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG,
+ phy_addr);
+ return jme_mdio_read(jme->dev, jme->mii_if.phy_id,
+ JM_PHY_SPEC_DATA_REG);
+}
+
+static void
+jme_phy_specreg_write(struct jme_adapter *jme, u32 ext_reg, u32 phy_data)
+{
+ u32 phy_addr;
+
+ phy_addr = JM_PHY_SPEC_REG_WRITE | ext_reg;
+ jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_DATA_REG,
+ phy_data);
+ jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG,
+ phy_addr);
+}
+
+static int
+jme_phy_calibration(struct jme_adapter *jme)
+{
+ u32 ctrl1000, phy_data;
+
+ jme_phy_off(jme);
+ jme_phy_on(jme);
+ /* Enabel PHY test mode 1 */
+ ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000);
+ ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK;
+ ctrl1000 |= PHY_GAD_TEST_MODE_1;
+ jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000);
+
+ phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG);
+ phy_data &= ~JM_PHY_EXT_COMM_2_CALI_MODE_0;
+ phy_data |= JM_PHY_EXT_COMM_2_CALI_LATCH |
+ JM_PHY_EXT_COMM_2_CALI_ENABLE;
+ jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data);
+ msleep(20);
+ phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG);
+ phy_data &= ~(JM_PHY_EXT_COMM_2_CALI_ENABLE |
+ JM_PHY_EXT_COMM_2_CALI_MODE_0 |
+ JM_PHY_EXT_COMM_2_CALI_LATCH);
+ jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data);
+
+ /* Disable PHY test mode */
+ ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000);
+ ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK;
+ jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000);
+ return 0;
+}
+
+static int
+jme_phy_setEA(struct jme_adapter *jme)
+{
+ u32 phy_comm0 = 0, phy_comm1 = 0;
+ u8 nic_ctrl;
+
+ pci_read_config_byte(jme->pdev, PCI_PRIV_SHARE_NICCTRL, &nic_ctrl);
+ if ((nic_ctrl & 0x3) == JME_FLAG_PHYEA_ENABLE)
+ return 0;
+
+ switch (jme->pdev->device) {
+ case PCI_DEVICE_ID_JMICRON_JMC250:
+ if (((jme->chip_main_rev == 5) &&
+ ((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) ||
+ (jme->chip_sub_rev == 3))) ||
+ (jme->chip_main_rev >= 6)) {
+ phy_comm0 = 0x008A;
+ phy_comm1 = 0x4109;
+ }
+ if ((jme->chip_main_rev == 3) &&
+ ((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2)))
+ phy_comm0 = 0xE088;
+ break;
+ case PCI_DEVICE_ID_JMICRON_JMC260:
+ if (((jme->chip_main_rev == 5) &&
+ ((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) ||
+ (jme->chip_sub_rev == 3))) ||
+ (jme->chip_main_rev >= 6)) {
+ phy_comm0 = 0x008A;
+ phy_comm1 = 0x4109;
+ }
+ if ((jme->chip_main_rev == 3) &&
+ ((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2)))
+ phy_comm0 = 0xE088;
+ if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 0))
+ phy_comm0 = 0x608A;
+ if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 2))
+ phy_comm0 = 0x408A;
+ break;
+ default:
+ return -ENODEV;
+ }
+ if (phy_comm0)
+ jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_0_REG, phy_comm0);
+ if (phy_comm1)
+ jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_1_REG, phy_comm1);
+
+ return 0;
+}
+
static int
jme_open(struct net_device *netdev)
{
jme_set_settings(netdev, &jme->old_ecmd);
else
jme_reset_phy_processor(jme);
-
+ jme_phy_calibration(jme);
+ jme_phy_setEA(jme);
jme_reset_link(jme);
return 0;
struct page *page,
u32 page_offset,
u32 len,
- u8 hidma)
+ bool hidma)
{
dma_addr_t dmaaddr;
struct jme_ring *txring = &(jme->txring[0]);
struct txdesc *txdesc = txring->desc, *ctxdesc;
struct jme_buffer_info *txbi = txring->bufinf, *ctxbi;
- u8 hidma = jme->dev->features & NETIF_F_HIGHDMA;
+ bool hidma = jme->dev->features & NETIF_F_HIGHDMA;
int i, nr_frags = skb_shinfo(skb)->nr_frags;
int mask = jme->tx_ring_mask;
const struct skb_frag_struct *frag;
{
struct jme_adapter *jme = netdev_priv(netdev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(jme->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(jme->pdev), sizeof(info->bus_info));
}
static int
jme->msg_enable = value;
}
-static u32
-jme_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t
+jme_fix_features(struct net_device *netdev, netdev_features_t features)
{
if (netdev->mtu > 1900)
features &= ~(NETIF_F_ALL_TSO | NETIF_F_ALL_CSUM);
}
static int
-jme_set_features(struct net_device *netdev, u32 features)
+jme_set_features(struct net_device *netdev, netdev_features_t features)
{
struct jme_adapter *jme = netdev_priv(netdev);
jme_set_settings(netdev, &jme->old_ecmd);
else
jme_reset_phy_processor(jme);
-
+ jme_phy_calibration(jme);
+ jme_phy_setEA(jme);
jme_start_irq(jme);
netif_device_attach(netdev);
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, jme_pci_tbl);
-
RXMCS_CHECKSUM,
};
+/* Extern PHY common register 2 */
+
+#define PHY_GAD_TEST_MODE_1 0x00002000
+#define PHY_GAD_TEST_MODE_MSK 0x0000E000
+#define JM_PHY_SPEC_REG_READ 0x00004000
+#define JM_PHY_SPEC_REG_WRITE 0x00008000
+#define PHY_CALIBRATION_DELAY 20
+#define JM_PHY_SPEC_ADDR_REG 0x1E
+#define JM_PHY_SPEC_DATA_REG 0x1F
+
+#define JM_PHY_EXT_COMM_0_REG 0x30
+#define JM_PHY_EXT_COMM_1_REG 0x31
+#define JM_PHY_EXT_COMM_2_REG 0x32
+#define JM_PHY_EXT_COMM_2_CALI_ENABLE 0x01
+#define JM_PHY_EXT_COMM_2_CALI_MODE_0 0x02
+#define JM_PHY_EXT_COMM_2_CALI_LATCH 0x10
+#define PCI_PRIV_SHARE_NICCTRL 0xF5
+#define JME_FLAG_PHYEA_ENABLE 0x2
+
/*
* Wakeup Frame setup interface registers
*/
.remove = korina_remove,
};
-static int __init korina_init_module(void)
-{
- return platform_driver_register(&korina_driver);
-}
-
-static void korina_cleanup_module(void)
-{
- return platform_driver_unregister(&korina_driver);
-}
-
-module_init(korina_init_module);
-module_exit(korina_cleanup_module);
+module_platform_driver(korina_driver);
MODULE_AUTHOR("Philip Rischel <rischelp@idt.com>");
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/io.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
#include <asm/checksum.h>
static void mv643xx_eth_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
{
- strncpy(drvinfo->driver, mv643xx_eth_driver_name, 32);
- strncpy(drvinfo->version, mv643xx_eth_driver_version, 32);
- strncpy(drvinfo->fw_version, "N/A", 32);
- strncpy(drvinfo->bus_info, "platform", 32);
+ strlcpy(drvinfo->driver, mv643xx_eth_driver_name,
+ sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, mv643xx_eth_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
+ strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
drvinfo->n_stats = ARRAY_SIZE(mv643xx_eth_stats);
}
static int
-mv643xx_eth_set_features(struct net_device *dev, u32 features)
+mv643xx_eth_set_features(struct net_device *dev, netdev_features_t features)
{
struct mv643xx_eth_private *mp = netdev_priv(dev);
- u32 rx_csum = features & NETIF_F_RXCSUM;
+ bool rx_csum = features & NETIF_F_RXCSUM;
wrlp(mp, PORT_CONFIG, rx_csum ? 0x02000000 : 0x00000000);
},
};
-static int __init pxa168_init_module(void)
-{
- return platform_driver_register(&pxa168_eth_driver);
-}
-
-static void __exit pxa168_cleanup_module(void)
-{
- platform_driver_unregister(&pxa168_eth_driver);
-}
-
-module_init(pxa168_init_module);
-module_exit(pxa168_cleanup_module);
+module_platform_driver(pxa168_eth_driver);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Ethernet driver for Marvell PXA168");
{
struct skge_port *skge = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
- strcpy(info->bus_info, pci_name(skge->hw->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(skge->hw->pdev),
+ sizeof(info->bus_info));
}
static const struct skge_stat {
spin_unlock_irq(&hw->hw_lock);
napi_enable(&skge->napi);
+
+ skge_set_multicast(dev);
+
return 0;
free_tx_ring:
pci_set_drvdata(pdev, NULL);
}
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
static int skge_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
#else
#define SKGE_PM_OPS NULL
-#endif
+#endif /* CONFIG_PM_SLEEP */
static void skge_shutdown(struct pci_dev *pdev)
{
#include "sky2.h"
#define DRV_NAME "sky2"
-#define DRV_VERSION "1.29"
+#define DRV_VERSION "1.30"
/*
* The Yukon II chipset takes 64 bit command blocks (called list elements)
#define MAX_SKB_TX_LE (2 + (sizeof(dma_addr_t)/sizeof(u32))*(MAX_SKB_FRAGS+1))
#define TX_MIN_PENDING (MAX_SKB_TX_LE+1)
#define TX_MAX_PENDING 1024
-#define TX_DEF_PENDING 127
+#define TX_DEF_PENDING 63
#define TX_WATCHDOG (5 * HZ)
#define NAPI_WEIGHT 64
/* block receiver */
sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_SET);
+ sky2_read32(hw, B0_CTST);
}
static void sky2_set_tx_stfwd(struct sky2_hw *hw, unsigned port)
sky2->tx_prod = sky2->tx_cons = 0;
sky2->tx_tcpsum = 0;
sky2->tx_last_mss = 0;
+ netdev_reset_queue(sky2->netdev);
le = get_tx_le(sky2, &sky2->tx_prod);
le->addr = 0;
? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
}
+/*
+ * Fixed initial key as seed to RSS.
+ */
+static const uint32_t rss_init_key[10] = {
+ 0x7c3351da, 0x51c5cf4e, 0x44adbdd1, 0xe8d38d18, 0x48897c43,
+ 0xb1d60e7e, 0x6a3dd760, 0x01a2e453, 0x16f46f13, 0x1a0e7b30
+};
+
/* Enable/disable receive hash calculation (RSS) */
-static void rx_set_rss(struct net_device *dev, u32 features)
+static void rx_set_rss(struct net_device *dev, netdev_features_t features)
{
struct sky2_port *sky2 = netdev_priv(dev);
struct sky2_hw *hw = sky2->hw;
/* Program RSS initial values */
if (features & NETIF_F_RXHASH) {
- u32 key[nkeys];
-
- get_random_bytes(key, nkeys * sizeof(u32));
for (i = 0; i < nkeys; i++)
sky2_write32(hw, SK_REG(sky2->port, RSS_KEY + i * 4),
- key[i]);
+ rss_init_key[i]);
/* Need to turn on (undocumented) flag to make hashing work */
sky2_write32(hw, SK_REG(sky2->port, RX_GMF_CTRL_T),
#define SKY2_VLAN_OFFLOADS (NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO)
-static void sky2_vlan_mode(struct net_device *dev, u32 features)
+static void sky2_vlan_mode(struct net_device *dev, netdev_features_t features)
{
struct sky2_port *sky2 = netdev_priv(dev);
struct sky2_hw *hw = sky2->hw;
if (err)
dev_err(&pdev->dev, "cannot assign irq %d\n", pdev->irq);
else {
+ hw->flags |= SKY2_HW_IRQ_SETUP;
+
napi_enable(&hw->napi);
sky2_write32(hw, B0_IMSK, Y2_IS_BASE);
sky2_read32(hw, B0_IMSK);
/* Bring up network interface. */
-static int sky2_up(struct net_device *dev)
+static int sky2_open(struct net_device *dev)
{
struct sky2_port *sky2 = netdev_priv(dev);
struct sky2_hw *hw = sky2->hw;
sky2_hw_up(sky2);
+ if (hw->chip_id == CHIP_ID_YUKON_OPT ||
+ hw->chip_id == CHIP_ID_YUKON_PRM ||
+ hw->chip_id == CHIP_ID_YUKON_OP_2)
+ imask |= Y2_IS_PHY_QLNK; /* enable PHY Quick Link */
+
/* Enable interrupts from phy/mac for port */
imask = sky2_read32(hw, B0_IMSK);
imask |= portirq_msk[port];
if (tx_avail(sky2) <= MAX_SKB_TX_LE)
netif_stop_queue(dev);
+ netdev_sent_queue(dev, skb->len);
sky2_put_idx(hw, txqaddr[sky2->port], sky2->tx_prod);
return NETDEV_TX_OK;
static void sky2_tx_complete(struct sky2_port *sky2, u16 done)
{
struct net_device *dev = sky2->netdev;
- unsigned idx;
+ u16 idx;
+ unsigned int bytes_compl = 0, pkts_compl = 0;
BUG_ON(done >= sky2->tx_ring_size);
netif_printk(sky2, tx_done, KERN_DEBUG, dev,
"tx done %u\n", idx);
- u64_stats_update_begin(&sky2->tx_stats.syncp);
- ++sky2->tx_stats.packets;
- sky2->tx_stats.bytes += skb->len;
- u64_stats_update_end(&sky2->tx_stats.syncp);
+ pkts_compl++;
+ bytes_compl += skb->len;
re->skb = NULL;
dev_kfree_skb_any(skb);
sky2->tx_cons = idx;
smp_mb();
+
+ netdev_completed_queue(dev, pkts_compl, bytes_compl);
+
+ u64_stats_update_begin(&sky2->tx_stats.syncp);
+ sky2->tx_stats.packets += pkts_compl;
+ sky2->tx_stats.bytes += bytes_compl;
+ u64_stats_update_end(&sky2->tx_stats.syncp);
}
static void sky2_tx_reset(struct sky2_hw *hw, unsigned port)
sky2_write32(hw, RB_ADDR(txqaddr[port], RB_CTRL), RB_RST_SET);
sky2_write8(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_RST_SET);
+
+ sky2_read32(hw, B0_CTST);
}
static void sky2_hw_down(struct sky2_port *sky2)
}
/* Network shutdown */
-static int sky2_down(struct net_device *dev)
+static int sky2_close(struct net_device *dev)
{
struct sky2_port *sky2 = netdev_priv(dev);
struct sky2_hw *hw = sky2->hw;
netif_info(sky2, ifdown, dev, "disabling interface\n");
- /* Disable port IRQ */
- sky2_write32(hw, B0_IMSK,
- sky2_read32(hw, B0_IMSK) & ~portirq_msk[sky2->port]);
- sky2_read32(hw, B0_IMSK);
-
if (hw->ports == 1) {
+ sky2_write32(hw, B0_IMSK, 0);
+ sky2_read32(hw, B0_IMSK);
+
napi_disable(&hw->napi);
free_irq(hw->pdev->irq, hw);
+ hw->flags &= ~SKY2_HW_IRQ_SETUP;
} else {
+ u32 imask;
+
+ /* Disable port IRQ */
+ imask = sky2_read32(hw, B0_IMSK);
+ imask &= ~portirq_msk[sky2->port];
+ sky2_write32(hw, B0_IMSK, imask);
+ sky2_read32(hw, B0_IMSK);
+
synchronize_irq(hw->pdev->irq);
napi_synchronize(&hw->napi);
}
if (netif_running(dev)) {
sky2_tx_complete(sky2, last);
- /* Wake unless it's detached, and called e.g. from sky2_down() */
+ /* Wake unless it's detached, and called e.g. from sky2_close() */
if (tx_avail(sky2) > MAX_SKB_TX_LE + 4)
netif_wake_queue(dev);
}
hw->chip_id == CHIP_ID_YUKON_PRM ||
hw->chip_id == CHIP_ID_YUKON_OP_2) {
u16 reg;
- u32 msk;
if (hw->chip_id == CHIP_ID_YUKON_OPT && hw->chip_rev == 0) {
/* disable PCI-E PHY power down (set PHY reg 0x80, bit 7 */
sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
sky2_pci_write16(hw, PSM_CONFIG_REG4, reg);
- /* enable PHY Quick Link */
- msk = sky2_read32(hw, B0_IMSK);
- msk |= Y2_IS_PHY_QLNK;
- sky2_write32(hw, B0_IMSK, msk);
-
/* check if PSMv2 was running before */
reg = sky2_pci_read16(hw, PSM_CONFIG_REG3);
if (reg & PCI_EXP_LNKCTL_ASPMC)
netif_tx_lock(dev);
netif_device_detach(dev); /* stop txq */
netif_tx_unlock(dev);
- sky2_down(dev);
+ sky2_close(dev);
}
}
int err = 0;
if (netif_running(dev)) {
- err = sky2_up(dev);
+ err = sky2_open(dev);
if (err) {
netdev_info(dev, "could not restart %d\n", err);
dev_close(dev);
{
int i;
- sky2_read32(hw, B0_IMSK);
- sky2_write32(hw, B0_IMSK, 0);
- synchronize_irq(hw->pdev->irq);
- napi_disable(&hw->napi);
+ if (hw->flags & SKY2_HW_IRQ_SETUP) {
+ sky2_read32(hw, B0_IMSK);
+ sky2_write32(hw, B0_IMSK, 0);
+
+ synchronize_irq(hw->pdev->irq);
+ napi_disable(&hw->napi);
+ }
for (i = 0; i < hw->ports; i++) {
struct net_device *dev = hw->dev[i];
netif_wake_queue(dev);
}
- sky2_write32(hw, B0_IMSK, imask);
- sky2_read32(hw, B0_IMSK);
-
- sky2_read32(hw, B0_Y2_SP_LISR);
- napi_enable(&hw->napi);
+ if (hw->flags & SKY2_HW_IRQ_SETUP) {
+ sky2_write32(hw, B0_IMSK, imask);
+ sky2_read32(hw, B0_IMSK);
+ sky2_read32(hw, B0_Y2_SP_LISR);
+ napi_enable(&hw->napi);
+ }
}
static void sky2_restart(struct work_struct *work)
{
struct sky2_port *sky2 = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
- strcpy(info->bus_info, pci_name(sky2->hw->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(sky2->hw->pdev),
+ sizeof(info->bus_info));
}
static const struct sky2_stat {
return 0;
}
+/*
+ * Hardware is limited to min of 128 and max of 2048 for ring size
+ * and rounded up to next power of two
+ * to avoid division in modulus calclation
+ */
+static unsigned long roundup_ring_size(unsigned long pending)
+{
+ return max(128ul, roundup_pow_of_two(pending+1));
+}
+
static void sky2_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *ering)
{
sky2->rx_pending = ering->rx_pending;
sky2->tx_pending = ering->tx_pending;
- sky2->tx_ring_size = roundup_pow_of_two(sky2->tx_pending+1);
+ sky2->tx_ring_size = roundup_ring_size(sky2->tx_pending);
return sky2_reattach(dev);
}
return sky2_vpd_write(sky2->hw, cap, data, eeprom->offset, eeprom->len);
}
-static u32 sky2_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t sky2_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
const struct sky2_port *sky2 = netdev_priv(dev);
const struct sky2_hw *hw = sky2->hw;
return features;
}
-static int sky2_set_features(struct net_device *dev, u32 features)
+static int sky2_set_features(struct net_device *dev, netdev_features_t features)
{
struct sky2_port *sky2 = netdev_priv(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if (changed & NETIF_F_RXCSUM) {
- u32 on = features & NETIF_F_RXCSUM;
+ bool on = features & NETIF_F_RXCSUM;
sky2_write32(sky2->hw, Q_ADDR(rxqaddr[sky2->port], Q_CSR),
on ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
}
struct net_device *dev = ptr;
struct sky2_port *sky2 = netdev_priv(dev);
- if (dev->netdev_ops->ndo_open != sky2_up || !sky2_debug)
+ if (dev->netdev_ops->ndo_open != sky2_open || !sky2_debug)
return NOTIFY_DONE;
switch (event) {
not allowing netpoll on second port */
static const struct net_device_ops sky2_netdev_ops[2] = {
{
- .ndo_open = sky2_up,
- .ndo_stop = sky2_down,
+ .ndo_open = sky2_open,
+ .ndo_stop = sky2_close,
.ndo_start_xmit = sky2_xmit_frame,
.ndo_do_ioctl = sky2_ioctl,
.ndo_validate_addr = eth_validate_addr,
#endif
},
{
- .ndo_open = sky2_up,
- .ndo_stop = sky2_down,
+ .ndo_open = sky2_open,
+ .ndo_stop = sky2_close,
.ndo_start_xmit = sky2_xmit_frame,
.ndo_do_ioctl = sky2_ioctl,
.ndo_validate_addr = eth_validate_addr,
spin_lock_init(&sky2->phy_lock);
sky2->tx_pending = TX_DEF_PENDING;
- sky2->tx_ring_size = roundup_pow_of_two(TX_DEF_PENDING+1);
+ sky2->tx_ring_size = roundup_ring_size(TX_DEF_PENDING);
sky2->rx_pending = RX_DEF_PENDING;
hw->dev[port] = dev;
#define SKY2_HW_RSS_BROKEN 0x00000100
#define SKY2_HW_VLAN_BROKEN 0x00000200
#define SKY2_HW_RSS_CHKSUM 0x00000400 /* RSS requires chksum */
+#define SKY2_HW_IRQ_SETUP 0x00000800
u8 chip_id;
u8 chip_rev;
obj-$(CONFIG_MLX4_CORE) += mlx4_core.o
mlx4_core-y := alloc.o catas.o cmd.o cq.o eq.o fw.o icm.o intf.o main.o mcg.o \
- mr.o pd.o port.o profile.o qp.o reset.o sense.o srq.o
+ mr.o pd.o port.o profile.o qp.o reset.o sense.o srq.o resource_tracker.o
obj-$(CONFIG_MLX4_EN) += mlx4_en.o
static int internal_err_reset = 1;
module_param(internal_err_reset, int, 0644);
MODULE_PARM_DESC(internal_err_reset,
- "Reset device on internal errors if non-zero (default 1)");
+ "Reset device on internal errors if non-zero"
+ " (default 1, in SRIOV mode default is 0)");
static void dump_err_buf(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
phys_addr_t addr;
+ /*If we are in SRIOV the default of the module param must be 0*/
+ if (mlx4_is_mfunc(dev))
+ internal_err_reset = 0;
+
INIT_LIST_HEAD(&priv->catas_err.list);
init_timer(&priv->catas_err.timer);
priv->catas_err.map = NULL;
#include <linux/errno.h>
#include <linux/mlx4/cmd.h>
+#include <linux/semaphore.h>
#include <asm/io.h>
#include "mlx4.h"
+#include "fw.h"
#define CMD_POLL_TOKEN 0xffff
+#define INBOX_MASK 0xffffffffffffff00ULL
+
+#define CMD_CHAN_VER 1
+#define CMD_CHAN_IF_REV 1
enum {
/* command completed successfully: */
int next;
u64 out_param;
u16 token;
+ u8 fw_status;
};
+static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr_cmd *in_vhcr);
+
static int mlx4_status_to_errno(u8 status)
{
static const int trans_table[] = {
return trans_table[status];
}
+static u8 mlx4_errno_to_status(int errno)
+{
+ switch (errno) {
+ case -EPERM:
+ return CMD_STAT_BAD_OP;
+ case -EINVAL:
+ return CMD_STAT_BAD_PARAM;
+ case -ENXIO:
+ return CMD_STAT_BAD_SYS_STATE;
+ case -EBUSY:
+ return CMD_STAT_RESOURCE_BUSY;
+ case -ENOMEM:
+ return CMD_STAT_EXCEED_LIM;
+ case -ENFILE:
+ return CMD_STAT_ICM_ERROR;
+ default:
+ return CMD_STAT_INTERNAL_ERR;
+ }
+}
+
+static int comm_pending(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ u32 status = readl(&priv->mfunc.comm->slave_read);
+
+ return (swab32(status) >> 31) != priv->cmd.comm_toggle;
+}
+
+static void mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ u32 val;
+
+ priv->cmd.comm_toggle ^= 1;
+ val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
+ __raw_writel((__force u32) cpu_to_be32(val),
+ &priv->mfunc.comm->slave_write);
+ mmiowb();
+}
+
+static int mlx4_comm_cmd_poll(struct mlx4_dev *dev, u8 cmd, u16 param,
+ unsigned long timeout)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ unsigned long end;
+ int err = 0;
+ int ret_from_pending = 0;
+
+ /* First, verify that the master reports correct status */
+ if (comm_pending(dev)) {
+ mlx4_warn(dev, "Communication channel is not idle."
+ "my toggle is %d (cmd:0x%x)\n",
+ priv->cmd.comm_toggle, cmd);
+ return -EAGAIN;
+ }
+
+ /* Write command */
+ down(&priv->cmd.poll_sem);
+ mlx4_comm_cmd_post(dev, cmd, param);
+
+ end = msecs_to_jiffies(timeout) + jiffies;
+ while (comm_pending(dev) && time_before(jiffies, end))
+ cond_resched();
+ ret_from_pending = comm_pending(dev);
+ if (ret_from_pending) {
+ /* check if the slave is trying to boot in the middle of
+ * FLR process. The only non-zero result in the RESET command
+ * is MLX4_DELAY_RESET_SLAVE*/
+ if ((MLX4_COMM_CMD_RESET == cmd)) {
+ mlx4_warn(dev, "Got slave FLRed from Communication"
+ " channel (ret:0x%x)\n", ret_from_pending);
+ err = MLX4_DELAY_RESET_SLAVE;
+ } else {
+ mlx4_warn(dev, "Communication channel timed out\n");
+ err = -ETIMEDOUT;
+ }
+ }
+
+ up(&priv->cmd.poll_sem);
+ return err;
+}
+
+static int mlx4_comm_cmd_wait(struct mlx4_dev *dev, u8 op,
+ u16 param, unsigned long timeout)
+{
+ struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
+ struct mlx4_cmd_context *context;
+ int err = 0;
+
+ down(&cmd->event_sem);
+
+ spin_lock(&cmd->context_lock);
+ BUG_ON(cmd->free_head < 0);
+ context = &cmd->context[cmd->free_head];
+ context->token += cmd->token_mask + 1;
+ cmd->free_head = context->next;
+ spin_unlock(&cmd->context_lock);
+
+ init_completion(&context->done);
+
+ mlx4_comm_cmd_post(dev, op, param);
+
+ if (!wait_for_completion_timeout(&context->done,
+ msecs_to_jiffies(timeout))) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ err = context->result;
+ if (err && context->fw_status != CMD_STAT_MULTI_FUNC_REQ) {
+ mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+ op, context->fw_status);
+ goto out;
+ }
+
+out:
+ spin_lock(&cmd->context_lock);
+ context->next = cmd->free_head;
+ cmd->free_head = context - cmd->context;
+ spin_unlock(&cmd->context_lock);
+
+ up(&cmd->event_sem);
+ return err;
+}
+
+int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
+ unsigned long timeout)
+{
+ if (mlx4_priv(dev)->cmd.use_events)
+ return mlx4_comm_cmd_wait(dev, cmd, param, timeout);
+ return mlx4_comm_cmd_poll(dev, cmd, param, timeout);
+}
+
static int cmd_pending(struct mlx4_dev *dev)
{
u32 status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
while (cmd_pending(dev)) {
- if (time_after_eq(jiffies, end))
+ if (time_after_eq(jiffies, end)) {
+ mlx4_err(dev, "%s:cmd_pending failed\n", __func__);
goto out;
+ }
cond_resched();
}
(cmd->toggle << HCR_T_BIT) |
(event ? (1 << HCR_E_BIT) : 0) |
(op_modifier << HCR_OPMOD_SHIFT) |
- op), hcr + 6);
+ op), hcr + 6);
/*
* Make sure that our HCR writes don't get mixed in with
return ret;
}
+static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
+ int out_is_imm, u32 in_modifier, u8 op_modifier,
+ u16 op, unsigned long timeout)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_vhcr_cmd *vhcr = priv->mfunc.vhcr;
+ int ret;
+
+ down(&priv->cmd.slave_sem);
+ vhcr->in_param = cpu_to_be64(in_param);
+ vhcr->out_param = out_param ? cpu_to_be64(*out_param) : 0;
+ vhcr->in_modifier = cpu_to_be32(in_modifier);
+ vhcr->opcode = cpu_to_be16((((u16) op_modifier) << 12) | (op & 0xfff));
+ vhcr->token = cpu_to_be16(CMD_POLL_TOKEN);
+ vhcr->status = 0;
+ vhcr->flags = !!(priv->cmd.use_events) << 6;
+ if (mlx4_is_master(dev)) {
+ ret = mlx4_master_process_vhcr(dev, dev->caps.function, vhcr);
+ if (!ret) {
+ if (out_is_imm) {
+ if (out_param)
+ *out_param =
+ be64_to_cpu(vhcr->out_param);
+ else {
+ mlx4_err(dev, "response expected while"
+ "output mailbox is NULL for "
+ "command 0x%x\n", op);
+ vhcr->status = CMD_STAT_BAD_PARAM;
+ }
+ }
+ ret = mlx4_status_to_errno(vhcr->status);
+ }
+ } else {
+ ret = mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_POST, 0,
+ MLX4_COMM_TIME + timeout);
+ if (!ret) {
+ if (out_is_imm) {
+ if (out_param)
+ *out_param =
+ be64_to_cpu(vhcr->out_param);
+ else {
+ mlx4_err(dev, "response expected while"
+ "output mailbox is NULL for "
+ "command 0x%x\n", op);
+ vhcr->status = CMD_STAT_BAD_PARAM;
+ }
+ }
+ ret = mlx4_status_to_errno(vhcr->status);
+ } else
+ mlx4_err(dev, "failed execution of VHCR_POST command"
+ "opcode 0x%x\n", op);
+ }
+ up(&priv->cmd.slave_sem);
+ return ret;
+}
+
static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
u16 op, unsigned long timeout)
void __iomem *hcr = priv->cmd.hcr;
int err = 0;
unsigned long end;
+ u32 stat;
down(&priv->cmd.poll_sem);
__raw_readl(hcr + HCR_OUT_PARAM_OFFSET)) << 32 |
(u64) be32_to_cpu((__force __be32)
__raw_readl(hcr + HCR_OUT_PARAM_OFFSET + 4));
-
- err = mlx4_status_to_errno(be32_to_cpu((__force __be32)
- __raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24);
+ stat = be32_to_cpu((__force __be32)
+ __raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24;
+ err = mlx4_status_to_errno(stat);
+ if (err)
+ mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+ op, stat);
out:
up(&priv->cmd.poll_sem);
if (token != context->token)
return;
+ context->fw_status = status;
context->result = mlx4_status_to_errno(status);
context->out_param = out_param;
mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
in_modifier, op_modifier, op, context->token, 1);
- if (!wait_for_completion_timeout(&context->done, msecs_to_jiffies(timeout))) {
+ if (!wait_for_completion_timeout(&context->done,
+ msecs_to_jiffies(timeout))) {
err = -EBUSY;
goto out;
}
err = context->result;
- if (err)
+ if (err) {
+ mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+ op, context->fw_status);
goto out;
+ }
if (out_is_imm)
*out_param = context->out_param;
int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
- u16 op, unsigned long timeout)
+ u16 op, unsigned long timeout, int native)
{
- if (mlx4_priv(dev)->cmd.use_events)
- return mlx4_cmd_wait(dev, in_param, out_param, out_is_imm,
- in_modifier, op_modifier, op, timeout);
- else
- return mlx4_cmd_poll(dev, in_param, out_param, out_is_imm,
- in_modifier, op_modifier, op, timeout);
+ if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
+ if (mlx4_priv(dev)->cmd.use_events)
+ return mlx4_cmd_wait(dev, in_param, out_param,
+ out_is_imm, in_modifier,
+ op_modifier, op, timeout);
+ else
+ return mlx4_cmd_poll(dev, in_param, out_param,
+ out_is_imm, in_modifier,
+ op_modifier, op, timeout);
+ }
+ return mlx4_slave_cmd(dev, in_param, out_param, out_is_imm,
+ in_modifier, op_modifier, op, timeout);
}
EXPORT_SYMBOL_GPL(__mlx4_cmd);
+
+static int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev)
+{
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_ARM_COMM_CHANNEL,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+}
+
+static int mlx4_ACCESS_MEM(struct mlx4_dev *dev, u64 master_addr,
+ int slave, u64 slave_addr,
+ int size, int is_read)
+{
+ u64 in_param;
+ u64 out_param;
+
+ if ((slave_addr & 0xfff) | (master_addr & 0xfff) |
+ (slave & ~0x7f) | (size & 0xff)) {
+ mlx4_err(dev, "Bad access mem params - slave_addr:0x%llx "
+ "master_addr:0x%llx slave_id:%d size:%d\n",
+ slave_addr, master_addr, slave, size);
+ return -EINVAL;
+ }
+
+ if (is_read) {
+ in_param = (u64) slave | slave_addr;
+ out_param = (u64) dev->caps.function | master_addr;
+ } else {
+ in_param = (u64) dev->caps.function | master_addr;
+ out_param = (u64) slave | slave_addr;
+ }
+
+ return mlx4_cmd_imm(dev, in_param, &out_param, size, 0,
+ MLX4_CMD_ACCESS_MEM,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+}
+
+int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ u64 in_param;
+ u64 out_param;
+ int err;
+
+ in_param = cmd->has_inbox ? (u64) inbox->dma : vhcr->in_param;
+ out_param = cmd->has_outbox ? (u64) outbox->dma : vhcr->out_param;
+ if (cmd->encode_slave_id) {
+ in_param &= 0xffffffffffffff00ll;
+ in_param |= slave;
+ }
+
+ err = __mlx4_cmd(dev, in_param, &out_param, cmd->out_is_imm,
+ vhcr->in_modifier, vhcr->op_modifier, vhcr->op,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+ if (cmd->out_is_imm)
+ vhcr->out_param = out_param;
+
+ return err;
+}
+
+static struct mlx4_cmd_info cmd_info[] = {
+ {
+ .opcode = MLX4_CMD_QUERY_FW,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_HCA,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_DEV_CAP,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_FUNC_CAP,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_FUNC_CAP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_ADAPTER,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_INIT_PORT,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_INIT_PORT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_CLOSE_PORT,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_CLOSE_PORT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_PORT,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_PORT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SET_PORT,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_SET_PORT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_MAP_EQ,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_MAP_EQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SW2HW_EQ,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_SW2HW_EQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_HW_HEALTH_CHECK,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_NOP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_ALLOC_RES,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = true,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_ALLOC_RES_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_FREE_RES,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_FREE_RES_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SW2HW_MPT,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_SW2HW_MPT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_MPT,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_MPT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_HW2SW_MPT,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_HW2SW_MPT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_READ_MTT,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_WRITE_MTT,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_WRITE_MTT_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SYNC_TPT,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+ {
+ .opcode = MLX4_CMD_HW2SW_EQ,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_HW2SW_EQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_EQ,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_EQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SW2HW_CQ,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_SW2HW_CQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_HW2SW_CQ,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_HW2SW_CQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_CQ,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_CQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_MODIFY_CQ,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = true,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_MODIFY_CQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SW2HW_SRQ,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_SW2HW_SRQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_HW2SW_SRQ,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_HW2SW_SRQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_SRQ,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_SRQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_ARM_SRQ,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_ARM_SRQ_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_RST2INIT_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = true,
+ .verify = NULL,
+ .wrapper = mlx4_RST2INIT_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_INIT2INIT_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_INIT2RTR_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_INIT2RTR_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_RTR2RTS_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_RTS2RTS_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SQERR2RTS_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_2ERR_QP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_RTS2SQD_QP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SQD2SQD_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SQD2RTS_QP,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_2RST_QP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_2RST_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_QP,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SUSPEND_QP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_UNSUSPEND_QP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_GEN_QP_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_QUERY_IF_STAT,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QUERY_IF_STAT_wrapper
+ },
+ /* Native multicast commands are not available for guests */
+ {
+ .opcode = MLX4_CMD_QP_ATTACH,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QP_ATTACH_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_PROMISC,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_PROMISC_wrapper
+ },
+ /* Ethernet specific commands */
+ {
+ .opcode = MLX4_CMD_SET_VLAN_FLTR,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_SET_VLAN_FLTR_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_SET_MCAST_FLTR,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_SET_MCAST_FLTR_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_DUMP_ETH_STATS,
+ .has_inbox = false,
+ .has_outbox = true,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_DUMP_ETH_STATS_wrapper
+ },
+ {
+ .opcode = MLX4_CMD_INFORM_FLR_DONE,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = NULL
+ },
+};
+
+static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr_cmd *in_vhcr)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_cmd_info *cmd = NULL;
+ struct mlx4_vhcr_cmd *vhcr_cmd = in_vhcr ? in_vhcr : priv->mfunc.vhcr;
+ struct mlx4_vhcr *vhcr;
+ struct mlx4_cmd_mailbox *inbox = NULL;
+ struct mlx4_cmd_mailbox *outbox = NULL;
+ u64 in_param;
+ u64 out_param;
+ int ret = 0;
+ int i;
+ int err = 0;
+
+ /* Create sw representation of Virtual HCR */
+ vhcr = kzalloc(sizeof(struct mlx4_vhcr), GFP_KERNEL);
+ if (!vhcr)
+ return -ENOMEM;
+
+ /* DMA in the vHCR */
+ if (!in_vhcr) {
+ ret = mlx4_ACCESS_MEM(dev, priv->mfunc.vhcr_dma, slave,
+ priv->mfunc.master.slave_state[slave].vhcr_dma,
+ ALIGN(sizeof(struct mlx4_vhcr_cmd),
+ MLX4_ACCESS_MEM_ALIGN), 1);
+ if (ret) {
+ mlx4_err(dev, "%s:Failed reading vhcr"
+ "ret: 0x%x\n", __func__, ret);
+ kfree(vhcr);
+ return ret;
+ }
+ }
+
+ /* Fill SW VHCR fields */
+ vhcr->in_param = be64_to_cpu(vhcr_cmd->in_param);
+ vhcr->out_param = be64_to_cpu(vhcr_cmd->out_param);
+ vhcr->in_modifier = be32_to_cpu(vhcr_cmd->in_modifier);
+ vhcr->token = be16_to_cpu(vhcr_cmd->token);
+ vhcr->op = be16_to_cpu(vhcr_cmd->opcode) & 0xfff;
+ vhcr->op_modifier = (u8) (be16_to_cpu(vhcr_cmd->opcode) >> 12);
+ vhcr->e_bit = vhcr_cmd->flags & (1 << 6);
+
+ /* Lookup command */
+ for (i = 0; i < ARRAY_SIZE(cmd_info); ++i) {
+ if (vhcr->op == cmd_info[i].opcode) {
+ cmd = &cmd_info[i];
+ break;
+ }
+ }
+ if (!cmd) {
+ mlx4_err(dev, "Unknown command:0x%x accepted from slave:%d\n",
+ vhcr->op, slave);
+ vhcr_cmd->status = CMD_STAT_BAD_PARAM;
+ goto out_status;
+ }
+
+ /* Read inbox */
+ if (cmd->has_inbox) {
+ vhcr->in_param &= INBOX_MASK;
+ inbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(inbox)) {
+ vhcr_cmd->status = CMD_STAT_BAD_SIZE;
+ inbox = NULL;
+ goto out_status;
+ }
+
+ if (mlx4_ACCESS_MEM(dev, inbox->dma, slave,
+ vhcr->in_param,
+ MLX4_MAILBOX_SIZE, 1)) {
+ mlx4_err(dev, "%s: Failed reading inbox (cmd:0x%x)\n",
+ __func__, cmd->opcode);
+ vhcr_cmd->status = CMD_STAT_INTERNAL_ERR;
+ goto out_status;
+ }
+ }
+
+ /* Apply permission and bound checks if applicable */
+ if (cmd->verify && cmd->verify(dev, slave, vhcr, inbox)) {
+ mlx4_warn(dev, "Command:0x%x from slave: %d failed protection "
+ "checks for resource_id:%d\n", vhcr->op, slave,
+ vhcr->in_modifier);
+ vhcr_cmd->status = CMD_STAT_BAD_OP;
+ goto out_status;
+ }
+
+ /* Allocate outbox */
+ if (cmd->has_outbox) {
+ outbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(outbox)) {
+ vhcr_cmd->status = CMD_STAT_BAD_SIZE;
+ outbox = NULL;
+ goto out_status;
+ }
+ }
+
+ /* Execute the command! */
+ if (cmd->wrapper) {
+ err = cmd->wrapper(dev, slave, vhcr, inbox, outbox,
+ cmd);
+ if (cmd->out_is_imm)
+ vhcr_cmd->out_param = cpu_to_be64(vhcr->out_param);
+ } else {
+ in_param = cmd->has_inbox ? (u64) inbox->dma :
+ vhcr->in_param;
+ out_param = cmd->has_outbox ? (u64) outbox->dma :
+ vhcr->out_param;
+ err = __mlx4_cmd(dev, in_param, &out_param,
+ cmd->out_is_imm, vhcr->in_modifier,
+ vhcr->op_modifier, vhcr->op,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+
+ if (cmd->out_is_imm) {
+ vhcr->out_param = out_param;
+ vhcr_cmd->out_param = cpu_to_be64(vhcr->out_param);
+ }
+ }
+
+ if (err) {
+ mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with"
+ " error:%d, status %d\n",
+ vhcr->op, slave, vhcr->errno, err);
+ vhcr_cmd->status = mlx4_errno_to_status(err);
+ goto out_status;
+ }
+
+
+ /* Write outbox if command completed successfully */
+ if (cmd->has_outbox && !vhcr_cmd->status) {
+ ret = mlx4_ACCESS_MEM(dev, outbox->dma, slave,
+ vhcr->out_param,
+ MLX4_MAILBOX_SIZE, MLX4_CMD_WRAPPED);
+ if (ret) {
+ /* If we failed to write back the outbox after the
+ *command was successfully executed, we must fail this
+ * slave, as it is now in undefined state */
+ mlx4_err(dev, "%s:Failed writing outbox\n", __func__);
+ goto out;
+ }
+ }
+
+out_status:
+ /* DMA back vhcr result */
+ if (!in_vhcr) {
+ ret = mlx4_ACCESS_MEM(dev, priv->mfunc.vhcr_dma, slave,
+ priv->mfunc.master.slave_state[slave].vhcr_dma,
+ ALIGN(sizeof(struct mlx4_vhcr),
+ MLX4_ACCESS_MEM_ALIGN),
+ MLX4_CMD_WRAPPED);
+ if (ret)
+ mlx4_err(dev, "%s:Failed writing vhcr result\n",
+ __func__);
+ else if (vhcr->e_bit &&
+ mlx4_GEN_EQE(dev, slave, &priv->mfunc.master.cmd_eqe))
+ mlx4_warn(dev, "Failed to generate command completion "
+ "eqe for slave %d\n", slave);
+ }
+
+out:
+ kfree(vhcr);
+ mlx4_free_cmd_mailbox(dev, inbox);
+ mlx4_free_cmd_mailbox(dev, outbox);
+ return ret;
+}
+
+static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
+ u16 param, u8 toggle)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
+ u32 reply;
+ u32 slave_status = 0;
+ u8 is_going_down = 0;
+
+ slave_state[slave].comm_toggle ^= 1;
+ reply = (u32) slave_state[slave].comm_toggle << 31;
+ if (toggle != slave_state[slave].comm_toggle) {
+ mlx4_warn(dev, "Incorrect toggle %d from slave %d. *** MASTER"
+ "STATE COMPROMISIED ***\n", toggle, slave);
+ goto reset_slave;
+ }
+ if (cmd == MLX4_COMM_CMD_RESET) {
+ mlx4_warn(dev, "Received reset from slave:%d\n", slave);
+ slave_state[slave].active = false;
+ /*check if we are in the middle of FLR process,
+ if so return "retry" status to the slave*/
+ if (MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) {
+ slave_status = MLX4_DELAY_RESET_SLAVE;
+ goto inform_slave_state;
+ }
+
+ /* write the version in the event field */
+ reply |= mlx4_comm_get_version();
+
+ goto reset_slave;
+ }
+ /*command from slave in the middle of FLR*/
+ if (cmd != MLX4_COMM_CMD_RESET &&
+ MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) {
+ mlx4_warn(dev, "slave:%d is Trying to run cmd(0x%x) "
+ "in the middle of FLR\n", slave, cmd);
+ return;
+ }
+
+ switch (cmd) {
+ case MLX4_COMM_CMD_VHCR0:
+ if (slave_state[slave].last_cmd != MLX4_COMM_CMD_RESET)
+ goto reset_slave;
+ slave_state[slave].vhcr_dma = ((u64) param) << 48;
+ priv->mfunc.master.slave_state[slave].cookie = 0;
+ mutex_init(&priv->mfunc.master.gen_eqe_mutex[slave]);
+ break;
+ case MLX4_COMM_CMD_VHCR1:
+ if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR0)
+ goto reset_slave;
+ slave_state[slave].vhcr_dma |= ((u64) param) << 32;
+ break;
+ case MLX4_COMM_CMD_VHCR2:
+ if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR1)
+ goto reset_slave;
+ slave_state[slave].vhcr_dma |= ((u64) param) << 16;
+ break;
+ case MLX4_COMM_CMD_VHCR_EN:
+ if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR2)
+ goto reset_slave;
+ slave_state[slave].vhcr_dma |= param;
+ slave_state[slave].active = true;
+ break;
+ case MLX4_COMM_CMD_VHCR_POST:
+ if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) &&
+ (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_POST))
+ goto reset_slave;
+ down(&priv->cmd.slave_sem);
+ if (mlx4_master_process_vhcr(dev, slave, NULL)) {
+ mlx4_err(dev, "Failed processing vhcr for slave:%d,"
+ " reseting slave.\n", slave);
+ up(&priv->cmd.slave_sem);
+ goto reset_slave;
+ }
+ up(&priv->cmd.slave_sem);
+ break;
+ default:
+ mlx4_warn(dev, "Bad comm cmd:%d from slave:%d\n", cmd, slave);
+ goto reset_slave;
+ }
+ spin_lock(&priv->mfunc.master.slave_state_lock);
+ if (!slave_state[slave].is_slave_going_down)
+ slave_state[slave].last_cmd = cmd;
+ else
+ is_going_down = 1;
+ spin_unlock(&priv->mfunc.master.slave_state_lock);
+ if (is_going_down) {
+ mlx4_warn(dev, "Slave is going down aborting command(%d)"
+ " executing from slave:%d\n",
+ cmd, slave);
+ return;
+ }
+ __raw_writel((__force u32) cpu_to_be32(reply),
+ &priv->mfunc.comm[slave].slave_read);
+ mmiowb();
+
+ return;
+
+reset_slave:
+ /* cleanup any slave resources */
+ mlx4_delete_all_resources_for_slave(dev, slave);
+ spin_lock(&priv->mfunc.master.slave_state_lock);
+ if (!slave_state[slave].is_slave_going_down)
+ slave_state[slave].last_cmd = MLX4_COMM_CMD_RESET;
+ spin_unlock(&priv->mfunc.master.slave_state_lock);
+ /*with slave in the middle of flr, no need to clean resources again.*/
+inform_slave_state:
+ memset(&slave_state[slave].event_eq, 0,
+ sizeof(struct mlx4_slave_event_eq_info));
+ __raw_writel((__force u32) cpu_to_be32(reply),
+ &priv->mfunc.comm[slave].slave_read);
+ wmb();
+}
+
+/* master command processing */
+void mlx4_master_comm_channel(struct work_struct *work)
+{
+ struct mlx4_mfunc_master_ctx *master =
+ container_of(work,
+ struct mlx4_mfunc_master_ctx,
+ comm_work);
+ struct mlx4_mfunc *mfunc =
+ container_of(master, struct mlx4_mfunc, master);
+ struct mlx4_priv *priv =
+ container_of(mfunc, struct mlx4_priv, mfunc);
+ struct mlx4_dev *dev = &priv->dev;
+ __be32 *bit_vec;
+ u32 comm_cmd;
+ u32 vec;
+ int i, j, slave;
+ int toggle;
+ int served = 0;
+ int reported = 0;
+ u32 slt;
+
+ bit_vec = master->comm_arm_bit_vector;
+ for (i = 0; i < COMM_CHANNEL_BIT_ARRAY_SIZE; i++) {
+ vec = be32_to_cpu(bit_vec[i]);
+ for (j = 0; j < 32; j++) {
+ if (!(vec & (1 << j)))
+ continue;
+ ++reported;
+ slave = (i * 32) + j;
+ comm_cmd = swab32(readl(
+ &mfunc->comm[slave].slave_write));
+ slt = swab32(readl(&mfunc->comm[slave].slave_read))
+ >> 31;
+ toggle = comm_cmd >> 31;
+ if (toggle != slt) {
+ if (master->slave_state[slave].comm_toggle
+ != slt) {
+ printk(KERN_INFO "slave %d out of sync."
+ " read toggle %d, state toggle %d. "
+ "Resynching.\n", slave, slt,
+ master->slave_state[slave].comm_toggle);
+ master->slave_state[slave].comm_toggle =
+ slt;
+ }
+ mlx4_master_do_cmd(dev, slave,
+ comm_cmd >> 16 & 0xff,
+ comm_cmd & 0xffff, toggle);
+ ++served;
+ }
+ }
+ }
+
+ if (reported && reported != served)
+ mlx4_warn(dev, "Got command event with bitmask from %d slaves"
+ " but %d were served\n",
+ reported, served);
+
+ if (mlx4_ARM_COMM_CHANNEL(dev))
+ mlx4_warn(dev, "Failed to arm comm channel events\n");
+}
+
+static int sync_toggles(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int wr_toggle;
+ int rd_toggle;
+ unsigned long end;
+
+ wr_toggle = swab32(readl(&priv->mfunc.comm->slave_write)) >> 31;
+ end = jiffies + msecs_to_jiffies(5000);
+
+ while (time_before(jiffies, end)) {
+ rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read)) >> 31;
+ if (rd_toggle == wr_toggle) {
+ priv->cmd.comm_toggle = rd_toggle;
+ return 0;
+ }
+
+ cond_resched();
+ }
+
+ /*
+ * we could reach here if for example the previous VM using this
+ * function misbehaved and left the channel with unsynced state. We
+ * should fix this here and give this VM a chance to use a properly
+ * synced channel
+ */
+ mlx4_warn(dev, "recovering from previously mis-behaved VM\n");
+ __raw_writel((__force u32) 0, &priv->mfunc.comm->slave_read);
+ __raw_writel((__force u32) 0, &priv->mfunc.comm->slave_write);
+ priv->cmd.comm_toggle = 0;
+
+ return 0;
+}
+
+int mlx4_multi_func_init(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_state *s_state;
+ int i, err, port;
+
+ priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE,
+ &priv->mfunc.vhcr_dma,
+ GFP_KERNEL);
+ if (!priv->mfunc.vhcr) {
+ mlx4_err(dev, "Couldn't allocate vhcr.\n");
+ return -ENOMEM;
+ }
+
+ if (mlx4_is_master(dev))
+ priv->mfunc.comm =
+ ioremap(pci_resource_start(dev->pdev, priv->fw.comm_bar) +
+ priv->fw.comm_base, MLX4_COMM_PAGESIZE);
+ else
+ priv->mfunc.comm =
+ ioremap(pci_resource_start(dev->pdev, 2) +
+ MLX4_SLAVE_COMM_BASE, MLX4_COMM_PAGESIZE);
+ if (!priv->mfunc.comm) {
+ mlx4_err(dev, "Couldn't map communication vector.\n");
+ goto err_vhcr;
+ }
+
+ if (mlx4_is_master(dev)) {
+ priv->mfunc.master.slave_state =
+ kzalloc(dev->num_slaves *
+ sizeof(struct mlx4_slave_state), GFP_KERNEL);
+ if (!priv->mfunc.master.slave_state)
+ goto err_comm;
+
+ for (i = 0; i < dev->num_slaves; ++i) {
+ s_state = &priv->mfunc.master.slave_state[i];
+ s_state->last_cmd = MLX4_COMM_CMD_RESET;
+ __raw_writel((__force u32) 0,
+ &priv->mfunc.comm[i].slave_write);
+ __raw_writel((__force u32) 0,
+ &priv->mfunc.comm[i].slave_read);
+ mmiowb();
+ for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+ s_state->vlan_filter[port] =
+ kzalloc(sizeof(struct mlx4_vlan_fltr),
+ GFP_KERNEL);
+ if (!s_state->vlan_filter[port]) {
+ if (--port)
+ kfree(s_state->vlan_filter[port]);
+ goto err_slaves;
+ }
+ INIT_LIST_HEAD(&s_state->mcast_filters[port]);
+ }
+ spin_lock_init(&s_state->lock);
+ }
+
+ memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
+ priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
+ INIT_WORK(&priv->mfunc.master.comm_work,
+ mlx4_master_comm_channel);
+ INIT_WORK(&priv->mfunc.master.slave_event_work,
+ mlx4_gen_slave_eqe);
+ INIT_WORK(&priv->mfunc.master.slave_flr_event_work,
+ mlx4_master_handle_slave_flr);
+ spin_lock_init(&priv->mfunc.master.slave_state_lock);
+ priv->mfunc.master.comm_wq =
+ create_singlethread_workqueue("mlx4_comm");
+ if (!priv->mfunc.master.comm_wq)
+ goto err_slaves;
+
+ if (mlx4_init_resource_tracker(dev))
+ goto err_thread;
+
+ sema_init(&priv->cmd.slave_sem, 1);
+ err = mlx4_ARM_COMM_CHANNEL(dev);
+ if (err) {
+ mlx4_err(dev, " Failed to arm comm channel eq: %x\n",
+ err);
+ goto err_resource;
+ }
+
+ } else {
+ err = sync_toggles(dev);
+ if (err) {
+ mlx4_err(dev, "Couldn't sync toggles\n");
+ goto err_comm;
+ }
+
+ sema_init(&priv->cmd.slave_sem, 1);
+ }
+ return 0;
+
+err_resource:
+ mlx4_free_resource_tracker(dev);
+err_thread:
+ flush_workqueue(priv->mfunc.master.comm_wq);
+ destroy_workqueue(priv->mfunc.master.comm_wq);
+err_slaves:
+ while (--i) {
+ for (port = 1; port <= MLX4_MAX_PORTS; port++)
+ kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
+ }
+ kfree(priv->mfunc.master.slave_state);
+err_comm:
+ iounmap(priv->mfunc.comm);
+err_vhcr:
+ dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+ priv->mfunc.vhcr,
+ priv->mfunc.vhcr_dma);
+ priv->mfunc.vhcr = NULL;
+ return -ENOMEM;
+}
+
int mlx4_cmd_init(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
priv->cmd.use_events = 0;
priv->cmd.toggle = 1;
- priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_HCR_BASE,
- MLX4_HCR_SIZE);
- if (!priv->cmd.hcr) {
- mlx4_err(dev, "Couldn't map command register.");
- return -ENOMEM;
+ priv->cmd.hcr = NULL;
+ priv->mfunc.vhcr = NULL;
+
+ if (!mlx4_is_slave(dev)) {
+ priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) +
+ MLX4_HCR_BASE, MLX4_HCR_SIZE);
+ if (!priv->cmd.hcr) {
+ mlx4_err(dev, "Couldn't map command register.\n");
+ return -ENOMEM;
+ }
}
priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev,
MLX4_MAILBOX_SIZE,
MLX4_MAILBOX_SIZE, 0);
- if (!priv->cmd.pool) {
- iounmap(priv->cmd.hcr);
- return -ENOMEM;
- }
+ if (!priv->cmd.pool)
+ goto err_hcr;
return 0;
+
+err_hcr:
+ if (!mlx4_is_slave(dev))
+ iounmap(priv->cmd.hcr);
+ return -ENOMEM;
+}
+
+void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int i, port;
+
+ if (mlx4_is_master(dev)) {
+ flush_workqueue(priv->mfunc.master.comm_wq);
+ destroy_workqueue(priv->mfunc.master.comm_wq);
+ for (i = 0; i < dev->num_slaves; i++) {
+ for (port = 1; port <= MLX4_MAX_PORTS; port++)
+ kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
+ }
+ kfree(priv->mfunc.master.slave_state);
+ iounmap(priv->mfunc.comm);
+ dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+ priv->mfunc.vhcr,
+ priv->mfunc.vhcr_dma);
+ priv->mfunc.vhcr = NULL;
+ }
}
void mlx4_cmd_cleanup(struct mlx4_dev *dev)
struct mlx4_priv *priv = mlx4_priv(dev);
pci_pool_destroy(priv->cmd.pool);
- iounmap(priv->cmd.hcr);
+
+ if (!mlx4_is_slave(dev))
+ iounmap(priv->cmd.hcr);
}
/*
{
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
+ int err = 0;
priv->cmd.context = kmalloc(priv->cmd.max_cmds *
sizeof (struct mlx4_cmd_context),
; /* nothing */
--priv->cmd.token_mask;
- priv->cmd.use_events = 1;
-
down(&priv->cmd.poll_sem);
+ priv->cmd.use_events = 1;
- return 0;
+ return err;
}
/*
}
EXPORT_SYMBOL_GPL(mlx4_alloc_cmd_mailbox);
-void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox)
+void mlx4_free_cmd_mailbox(struct mlx4_dev *dev,
+ struct mlx4_cmd_mailbox *mailbox)
{
if (!mailbox)
return;
kfree(mailbox);
}
EXPORT_SYMBOL_GPL(mlx4_free_cmd_mailbox);
+
+u32 mlx4_comm_get_version(void)
+{
+ return ((u32) CMD_CHAN_IF_REV << 8) | (u32) CMD_CHAN_VER;
+}
* SOFTWARE.
*/
+#include <linux/init.h>
#include <linux/hardirq.h>
#include <linux/export.h>
-#include <linux/gfp.h>
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/cq.h>
#include "mlx4.h"
#include "icm.h"
-struct mlx4_cq_context {
- __be32 flags;
- u16 reserved1[3];
- __be16 page_offset;
- __be32 logsize_usrpage;
- __be16 cq_period;
- __be16 cq_max_count;
- u8 reserved2[3];
- u8 comp_eqn;
- u8 log_page_size;
- u8 reserved3[2];
- u8 mtt_base_addr_h;
- __be32 mtt_base_addr_l;
- __be32 last_notified_index;
- __be32 solicit_producer_index;
- __be32 consumer_index;
- __be32 producer_index;
- u32 reserved4[2];
- __be64 db_rec_addr;
-};
-
#define MLX4_CQ_STATUS_OK ( 0 << 28)
#define MLX4_CQ_STATUS_OVERFLOW ( 9 << 28)
#define MLX4_CQ_STATUS_WRITE_FAIL (10 << 28)
cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
cqn & (dev->caps.num_cqs - 1));
if (!cq) {
- mlx4_warn(dev, "Completion event for bogus CQ %08x\n", cqn);
+ mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
return;
}
static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num)
{
- return mlx4_cmd(dev, mailbox->dma, cq_num, 0, MLX4_CMD_SW2HW_CQ,
- MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd(dev, mailbox->dma | dev->caps.function, cq_num, 0,
+ MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_MODIFY_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num, u32 opmod)
{
return mlx4_cmd(dev, mailbox->dma, cq_num, opmod, MLX4_CMD_MODIFY_CQ,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
static int mlx4_HW2SW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int cq_num)
{
- return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, cq_num,
- mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
- MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd_box(dev, dev->caps.function, mailbox ? mailbox->dma : 0,
+ cq_num, mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
}
EXPORT_SYMBOL_GPL(mlx4_cq_resize);
+int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_cq_table *cq_table = &priv->cq_table;
+ int err;
+
+ *cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
+ if (*cqn == -1)
+ return -ENOMEM;
+
+ err = mlx4_table_get(dev, &cq_table->table, *cqn);
+ if (err)
+ goto err_out;
+
+ err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
+ if (err)
+ goto err_put;
+ return 0;
+
+err_put:
+ mlx4_table_put(dev, &cq_table->table, *cqn);
+
+err_out:
+ mlx4_bitmap_free(&cq_table->bitmap, *cqn);
+ return err;
+}
+
+static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+{
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ err = mlx4_cmd_imm(dev, 0, &out_param, RES_CQ,
+ RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ return err;
+ else {
+ *cqn = get_param_l(&out_param);
+ return 0;
+ }
+ }
+ return __mlx4_cq_alloc_icm(dev, cqn);
+}
+
+void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_cq_table *cq_table = &priv->cq_table;
+
+ mlx4_table_put(dev, &cq_table->cmpt_table, cqn);
+ mlx4_table_put(dev, &cq_table->table, cqn);
+ mlx4_bitmap_free(&cq_table->bitmap, cqn);
+}
+
+static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+ u64 in_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, cqn);
+ err = mlx4_cmd(dev, in_param, RES_CQ, RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ mlx4_warn(dev, "Failed freeing cq:%d\n", cqn);
+ } else
+ __mlx4_cq_free_icm(dev, cqn);
+}
+
int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
unsigned vector, int collapsed)
cq->vector = vector;
- cq->cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
- if (cq->cqn == -1)
- return -ENOMEM;
-
- err = mlx4_table_get(dev, &cq_table->table, cq->cqn);
- if (err)
- goto err_out;
-
- err = mlx4_table_get(dev, &cq_table->cmpt_table, cq->cqn);
+ err = mlx4_cq_alloc_icm(dev, &cq->cqn);
if (err)
- goto err_put;
+ return err;
spin_lock_irq(&cq_table->lock);
err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
spin_unlock_irq(&cq_table->lock);
if (err)
- goto err_cmpt_put;
+ goto err_icm;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox)) {
radix_tree_delete(&cq_table->tree, cq->cqn);
spin_unlock_irq(&cq_table->lock);
-err_cmpt_put:
- mlx4_table_put(dev, &cq_table->cmpt_table, cq->cqn);
-
-err_put:
- mlx4_table_put(dev, &cq_table->table, cq->cqn);
-
-err_out:
- mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
+err_icm:
+ mlx4_cq_free_icm(dev, cq->cqn);
return err;
}
complete(&cq->free);
wait_for_completion(&cq->free);
- mlx4_table_put(dev, &cq_table->table, cq->cqn);
- mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
+ mlx4_cq_free_icm(dev, cq->cqn);
}
EXPORT_SYMBOL_GPL(mlx4_cq_free);
spin_lock_init(&cq_table->lock);
INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
+ if (mlx4_is_slave(dev))
+ return 0;
err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
void mlx4_cleanup_cq_table(struct mlx4_dev *dev)
{
+ if (mlx4_is_slave(dev))
+ return;
/* Nothing to do to clean up radix_tree */
mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap);
}
int err;
cq->size = entries;
- if (mode == RX)
- cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
- else
- cq->buf_size = sizeof(struct mlx4_cqe);
+ cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
cq->ring = ring;
cq->is_tx = mode;
cq->size = priv->rx_ring[cq->ring].actual_size;
err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar,
- cq->wqres.db.dma, &cq->mcq, cq->vector, cq->is_tx);
+ cq->wqres.db.dma, &cq->mcq, cq->vector, 0);
if (err)
return err;
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
if (priv->mdev->dev->caps.comp_pool && cq->vector)
mlx4_release_eq(priv->mdev->dev, cq->vector);
+ cq->vector = 0;
cq->buf_size = 0;
cq->buf = NULL;
}
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
- strncpy(drvinfo->driver, DRV_NAME, 32);
- strncpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")", 32);
- sprintf(drvinfo->fw_version, "%d.%d.%d",
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")",
+ sizeof(drvinfo->version));
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%d",
(u16) (mdev->dev->caps.fw_ver >> 32),
(u16) ((mdev->dev->caps.fw_ver >> 16) & 0xffff),
(u16) (mdev->dev->caps.fw_ver & 0xffff));
- strncpy(drvinfo->bus_info, pci_name(mdev->dev->pdev), 32);
+ strlcpy(drvinfo->bus_info, pci_name(mdev->dev->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = 0;
drvinfo->regdump_len = 0;
drvinfo->eedump_len = 0;
struct mlx4_en_priv *priv = netdev_priv(netdev);
int err = 0;
u64 config = 0;
+ u64 mask;
- if (!(priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_WOL)) {
+ if ((priv->port < 1) || (priv->port > 2)) {
+ en_err(priv, "Failed to get WoL information\n");
+ return;
+ }
+
+ mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 :
+ MLX4_DEV_CAP_FLAG_WOL_PORT2;
+
+ if (!(priv->mdev->dev->caps.flags & mask)) {
wol->supported = 0;
wol->wolopts = 0;
return;
struct mlx4_en_priv *priv = netdev_priv(netdev);
u64 config = 0;
int err = 0;
+ u64 mask;
+
+ if ((priv->port < 1) || (priv->port > 2))
+ return -EOPNOTSUPP;
+
+ mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 :
+ MLX4_DEV_CAP_FLAG_WOL_PORT2;
- if (!(priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_WOL))
+ if (!(priv->mdev->dev->caps.flags & mask))
return -EOPNOTSUPP;
if (wol->supported & ~WAKE_MAGIC)
#include "mlx4_en.h"
#include "en_port.h"
-static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
en_err(priv, "failed adding vlan %d\n", vid);
mutex_unlock(&mdev->state_lock);
+ return 0;
}
-static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
en_err(priv, "Failed configuring VLAN filter\n");
}
mutex_unlock(&mdev->state_lock);
+
+ return 0;
}
u64 mlx4_en_mac_to_u64(u8 *addr)
if (priv->port_up) {
/* Remove old MAC and insert the new one */
err = mlx4_replace_mac(mdev->dev, priv->port,
- priv->base_qpn, priv->mac, 0);
+ priv->base_qpn, priv->mac);
if (err)
en_err(priv, "Failed changing HW MAC address\n");
} else
struct mlx4_en_priv *priv = netdev_priv(dev);
kfree(priv->mc_addrs);
+ priv->mc_addrs = NULL;
priv->mc_addrs_cnt = 0;
}
i = 0;
netdev_for_each_mc_addr(ha, dev)
memcpy(mc_addrs + i++ * ETH_ALEN, ha->addr, ETH_ALEN);
+ mlx4_en_clear_list(dev);
priv->mc_addrs = mc_addrs;
priv->mc_addrs_cnt = mc_addrs_cnt;
}
goto out;
}
+ if (!netif_carrier_ok(dev)) {
+ if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
+ if (priv->port_state.link_state) {
+ priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
+ netif_carrier_on(dev);
+ en_dbg(LINK, priv, "Link Up\n");
+ }
+ }
+ }
+
/*
* Promsicuous mode: disable all filters
*/
++rx_index;
}
- /* Set port mac number */
- en_dbg(DRV, priv, "Setting mac for port %d\n", priv->port);
- err = mlx4_register_mac(mdev->dev, priv->port,
- priv->mac, &priv->base_qpn, 0);
+ /* Set qp number */
+ en_dbg(DRV, priv, "Getting qp number for port %d\n", priv->port);
+ err = mlx4_get_eth_qp(mdev->dev, priv->port,
+ priv->mac, &priv->base_qpn);
if (err) {
- en_err(priv, "Failed setting port mac\n");
+ en_err(priv, "Failed getting eth qp\n");
goto cq_err;
}
mdev->mac_removed[priv->port] = 0;
mlx4_en_release_rss_steer(priv);
mac_err:
- mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
+ mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
cq_err:
while (rx_index--)
mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
/* Flush multicast filter */
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);
- /* Unregister Mac address for the port */
- mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
- mdev->mac_removed[priv->port] = 1;
-
/* Free TX Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[i]);
/* Free RSS qps */
mlx4_en_release_rss_steer(priv);
+ /* Unregister Mac address for the port */
+ mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
+ mdev->mac_removed[priv->port] = 1;
+
/* Free RX Rings */
for (i = 0; i < priv->rx_ring_num; i++) {
mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
return 0;
}
+static int mlx4_en_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+ if (features & NETIF_F_LOOPBACK)
+ priv->ctrl_flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
+ else
+ priv->ctrl_flags &=
+ cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);
+
+ return 0;
+
+}
+
static const struct net_device_ops mlx4_netdev_ops = {
.ndo_open = mlx4_en_open,
.ndo_stop = mlx4_en_close,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = mlx4_en_netpoll,
#endif
+ .ndo_set_features = mlx4_en_set_features,
};
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->port = port;
priv->port_up = false;
priv->flags = prof->flags;
+ priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
+ MLX4_WQE_CTRL_SOLICITED);
priv->tx_ring_num = prof->tx_ring_num;
priv->rx_ring_num = prof->rx_ring_num;
priv->mac_index = -1;
dev->features = dev->hw_features | NETIF_F_HIGHDMA |
NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
NETIF_F_HW_VLAN_FILTER;
+ dev->hw_features |= NETIF_F_LOOPBACK;
mdev->pndev[port] = dev;
#include "mlx4_en.h"
-int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port,
- u64 mac, u64 clear, u8 mode)
-{
- return mlx4_cmd(dev, (mac | (clear << 63)), port, mode,
- MLX4_CMD_SET_MCAST_FLTR, MLX4_CMD_TIME_CLASS_B);
-}
-
int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv)
{
struct mlx4_cmd_mailbox *mailbox;
filter->entry[i] = cpu_to_be32(entry);
}
err = mlx4_cmd(dev, mailbox->dma, priv->port, 0, MLX4_CMD_SET_VLAN_FLTR,
- MLX4_CMD_TIME_CLASS_B);
- mlx4_free_cmd_mailbox(dev, mailbox);
- return err;
-}
-
-
-int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
- u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx)
-{
- struct mlx4_cmd_mailbox *mailbox;
- struct mlx4_set_port_general_context *context;
- int err;
- u32 in_mod;
-
- mailbox = mlx4_alloc_cmd_mailbox(dev);
- if (IS_ERR(mailbox))
- return PTR_ERR(mailbox);
- context = mailbox->buf;
- memset(context, 0, sizeof *context);
-
- context->flags = SET_PORT_GEN_ALL_VALID;
- context->mtu = cpu_to_be16(mtu);
- context->pptx = (pptx * (!pfctx)) << 7;
- context->pfctx = pfctx;
- context->pprx = (pprx * (!pfcrx)) << 7;
- context->pfcrx = pfcrx;
-
- in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
- err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
-
- mlx4_free_cmd_mailbox(dev, mailbox);
- return err;
-}
-
-int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
- u8 promisc)
-{
- struct mlx4_cmd_mailbox *mailbox;
- struct mlx4_set_port_rqp_calc_context *context;
- int err;
- u32 in_mod;
- u32 m_promisc = (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) ?
- MCAST_DIRECT : MCAST_DEFAULT;
-
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER &&
- dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)
- return 0;
-
- mailbox = mlx4_alloc_cmd_mailbox(dev);
- if (IS_ERR(mailbox))
- return PTR_ERR(mailbox);
- context = mailbox->buf;
- memset(context, 0, sizeof *context);
-
- context->base_qpn = cpu_to_be32(base_qpn);
- context->n_mac = dev->caps.log_num_macs;
- context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
- base_qpn);
- context->mcast = cpu_to_be32(m_promisc << SET_PORT_MC_PROMISC_SHIFT |
- base_qpn);
- context->intra_no_vlan = 0;
- context->no_vlan = MLX4_NO_VLAN_IDX;
- context->intra_vlan_miss = 0;
- context->vlan_miss = MLX4_VLAN_MISS_IDX;
-
- in_mod = MLX4_SET_PORT_RQP_CALC << 8 | port;
- err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
-
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
return PTR_ERR(mailbox);
memset(mailbox->buf, 0, sizeof(*qport_context));
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, port, 0,
- MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
if (err)
goto out;
qport_context = mailbox->buf;
return PTR_ERR(mailbox);
memset(mailbox->buf, 0, sizeof(*mlx4_en_stats));
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
- MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
if (err)
goto out;
#define SET_PORT_PROMISC_SHIFT 31
#define SET_PORT_MC_PROMISC_SHIFT 30
-enum {
- MLX4_CMD_SET_VLAN_FLTR = 0x47,
- MLX4_CMD_SET_MCAST_FLTR = 0x48,
- MLX4_CMD_DUMP_ETH_STATS = 0x49,
-};
-
-enum {
- MCAST_DIRECT_ONLY = 0,
- MCAST_DIRECT = 1,
- MCAST_DEFAULT = 2
-};
-
-struct mlx4_set_port_general_context {
- u8 reserved[3];
- u8 flags;
- u16 reserved2;
- __be16 mtu;
- u8 pptx;
- u8 pfctx;
- u16 reserved3;
- u8 pprx;
- u8 pfcrx;
- u16 reserved4;
-};
-
-struct mlx4_set_port_rqp_calc_context {
- __be32 base_qpn;
- u8 rererved;
- u8 n_mac;
- u8 n_vlan;
- u8 n_prio;
- u8 reserved2[3];
- u8 mac_miss;
- u8 intra_no_vlan;
- u8 no_vlan;
- u8 intra_vlan_miss;
- u8 vlan_miss;
- u8 reserved3[3];
- u8 no_vlan_prio;
- __be32 promisc;
- __be32 mcast;
-};
-
#define VLAN_FLTR_SIZE 128
struct mlx4_set_vlan_fltr_mbox {
__be32 entry[VLAN_FLTR_SIZE];
struct mlx4_en_dev *mdev = priv->mdev;
memset(context, 0, sizeof *context);
- context->flags = cpu_to_be32(7 << 16 | rss << 13);
+ context->flags = cpu_to_be32(7 << 16 | rss << MLX4_RSS_QPC_FLAG_OFFSET);
context->pd = cpu_to_be32(mdev->priv_pdn);
context->mtu_msgmax = 0xff;
if (!is_tx && !rss)
unsigned int length;
int polled = 0;
int ip_summed;
+ struct ethhdr *ethh;
+ u64 s_mac;
if (!priv->port_up)
return 0;
goto next;
}
+ /* Get pointer to first fragment since we haven't skb yet and
+ * cast it to ethhdr struct */
+ ethh = (struct ethhdr *)(page_address(skb_frags[0].page) +
+ skb_frags[0].offset);
+ s_mac = mlx4_en_mac_to_u64(ethh->h_source);
+
+ /* If source MAC is equal to our own MAC and not performing
+ * the selftest or flb disabled - drop the packet */
+ if (s_mac == priv->mac &&
+ (!(dev->features & NETIF_F_LOOPBACK) ||
+ !priv->validate_loopback))
+ goto next;
+
/*
* Packet is OK - process it.
*/
length = be32_to_cpu(cqe->byte_cnt);
+ length -= ring->fcs_del;
ring->bytes += length;
ring->packets++;
context->db_rec_addr = cpu_to_be64(ring->wqres.db.dma);
/* Cancel FCS removal if FW allows */
- if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)
+ if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP) {
context->param3 |= cpu_to_be32(1 << 29);
+ ring->fcs_del = ETH_FCS_LEN;
+ } else
+ ring->fcs_del = 0;
err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, context, qp, state);
if (err) {
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_rss_map *rss_map = &priv->rss_map;
struct mlx4_qp_context context;
- struct mlx4_en_rss_context *rss_context;
+ struct mlx4_rss_context *rss_context;
void *ptr;
- u8 rss_mask = 0x3f;
+ u8 rss_mask = (MLX4_RSS_IPV4 | MLX4_RSS_TCP_IPV4 | MLX4_RSS_IPV6 |
+ MLX4_RSS_TCP_IPV6);
int i, qpn;
int err = 0;
int good_qps = 0;
mlx4_en_fill_qp_context(priv, 0, 0, 0, 1, priv->base_qpn,
priv->rx_ring[0].cqn, &context);
- ptr = ((void *) &context) + 0x3c;
+ ptr = ((void *) &context) + offsetof(struct mlx4_qp_context, pri_path)
+ + MLX4_RSS_OFFSET_IN_QPC_PRI_PATH;
rss_context = ptr;
rss_context->base_qpn = cpu_to_be32(ilog2(priv->rx_ring_num) << 24 |
(rss_map->base_qpn));
rss_context->default_qpn = cpu_to_be32(rss_map->base_qpn);
+ if (priv->mdev->profile.udp_rss) {
+ rss_mask |= MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6;
+ rss_context->base_qpn_udp = rss_context->default_qpn;
+ }
rss_context->flags = rss_mask;
- rss_context->hash_fn = 1;
+ rss_context->hash_fn = MLX4_RSS_HASH_TOP;
for (i = 0; i < 10; i++)
rss_context->rss_key[i] = rsskey[i];
- if (priv->mdev->profile.udp_rss)
- rss_context->base_qpn_udp = rss_context->default_qpn;
err = mlx4_qp_to_ready(mdev->dev, &priv->res.mtt, &context,
&rss_map->indir_qp, &rss_map->indir_state);
if (err)
static int mlx4_en_test_registers(struct mlx4_en_priv *priv)
{
return mlx4_cmd(priv->mdev->dev, 0, 0, 0, MLX4_CMD_HW_HEALTH_CHECK,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
static int mlx4_en_test_loopback_xmit(struct mlx4_en_priv *priv)
return cnt;
}
-
static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cq *mcq = &cq->mcq;
struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
- struct mlx4_cqe *cqe = cq->buf;
+ struct mlx4_cqe *cqe;
u16 index;
- u16 new_index;
+ u16 new_index, ring_index;
u32 txbbs_skipped = 0;
- u32 cq_last_sav;
-
- /* index always points to the first TXBB of the last polled descriptor */
- index = ring->cons & ring->size_mask;
- new_index = be16_to_cpu(cqe->wqe_index) & ring->size_mask;
- if (index == new_index)
- return;
+ u32 cons_index = mcq->cons_index;
+ int size = cq->size;
+ u32 size_mask = ring->size_mask;
+ struct mlx4_cqe *buf = cq->buf;
if (!priv->port_up)
return;
- /*
- * We use a two-stage loop:
- * - the first samples the HW-updated CQE
- * - the second frees TXBBs until the last sample
- * This lets us amortize CQE cache misses, while still polling the CQ
- * until is quiescent.
- */
- cq_last_sav = mcq->cons_index;
- do {
+ index = cons_index & size_mask;
+ cqe = &buf[index];
+ ring_index = ring->cons & size_mask;
+
+ /* Process all completed CQEs */
+ while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
+ cons_index & size)) {
+ /*
+ * make sure we read the CQE after we read the
+ * ownership bit
+ */
+ rmb();
+
+ /* Skip over last polled CQE */
+ new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
+
do {
- /* Skip over last polled CQE */
- index = (index + ring->last_nr_txbb) & ring->size_mask;
txbbs_skipped += ring->last_nr_txbb;
-
- /* Poll next CQE */
+ ring_index = (ring_index + ring->last_nr_txbb) & size_mask;
+ /* free next descriptor */
ring->last_nr_txbb = mlx4_en_free_tx_desc(
- priv, ring, index,
- !!((ring->cons + txbbs_skipped) &
- ring->size));
- ++mcq->cons_index;
-
- } while (index != new_index);
+ priv, ring, ring_index,
+ !!((ring->cons + txbbs_skipped) &
+ ring->size));
+ } while (ring_index != new_index);
+
+ ++cons_index;
+ index = cons_index & size_mask;
+ cqe = &buf[index];
+ }
- new_index = be16_to_cpu(cqe->wqe_index) & ring->size_mask;
- } while (index != new_index);
- AVG_PERF_COUNTER(priv->pstats.tx_coal_avg,
- (u32) (mcq->cons_index - cq_last_sav));
/*
* To prevent CQ overflow we first update CQ consumer and only then
* the ring consumer.
*/
+ mcq->cons_index = cons_index;
mlx4_cq_set_ci(mcq);
wmb();
ring->cons += txbbs_skipped;
inl->byte_count = cpu_to_be32(1 << 31 | (skb->len - spc));
}
tx_desc->ctrl.vlan_tag = cpu_to_be16(*vlan_tag);
- tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN * !!(*vlan_tag);
+ tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+ (!!vlan_tx_tag_present(skb));
tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
}
/* Prepare ctrl segement apart opcode+ownership, which depends on
* whether LSO is used */
tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
- tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN * !!vlan_tag;
+ tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+ !!vlan_tx_tag_present(skb);
tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
- tx_desc->ctrl.srcrb_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
- MLX4_WQE_CTRL_SOLICITED);
+ tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
MLX4_WQE_CTRL_TCP_UDP_CSUM);
ring->tx_csum++;
}
- if (unlikely(priv->validate_loopback)) {
- /* Copy dst mac address to wqe */
- skb_reset_mac_header(skb);
- ethh = eth_hdr(skb);
- if (ethh && ethh->h_dest) {
- mac = mlx4_en_mac_to_u64(ethh->h_dest);
- mac_h = (u32) ((mac & 0xffff00000000ULL) >> 16);
- mac_l = (u32) (mac & 0xffffffff);
- tx_desc->ctrl.srcrb_flags |= cpu_to_be32(mac_h);
- tx_desc->ctrl.imm = cpu_to_be32(mac_l);
- }
+ /* Copy dst mac address to wqe */
+ skb_reset_mac_header(skb);
+ ethh = eth_hdr(skb);
+ if (ethh && ethh->h_dest) {
+ mac = mlx4_en_mac_to_u64(ethh->h_dest);
+ mac_h = (u32) ((mac & 0xffff00000000ULL) >> 16);
+ mac_l = (u32) (mac & 0xffffffff);
+ tx_desc->ctrl.srcrb_flags |= cpu_to_be32(mac_h);
+ tx_desc->ctrl.imm = cpu_to_be32(mac_l);
}
/* Handle LSO (TSO) packets */
* SOFTWARE.
*/
+#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/export.h>
MLX4_EQ_ENTRY_SIZE = 0x20
};
-/*
- * Must be packed because start is 64 bits but only aligned to 32 bits.
- */
-struct mlx4_eq_context {
- __be32 flags;
- u16 reserved1[3];
- __be16 page_offset;
- u8 log_eq_size;
- u8 reserved2[4];
- u8 eq_period;
- u8 reserved3;
- u8 eq_max_count;
- u8 reserved4[3];
- u8 intr;
- u8 log_page_size;
- u8 reserved5[2];
- u8 mtt_base_addr_h;
- __be32 mtt_base_addr_l;
- u32 reserved6[2];
- __be32 consumer_index;
- __be32 producer_index;
- u32 reserved7[4];
-};
-
#define MLX4_EQ_STATUS_OK ( 0 << 28)
#define MLX4_EQ_STATUS_WRITE_FAIL (10 << 28)
#define MLX4_EQ_OWNER_SW ( 0 << 24)
(1ull << MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) | \
(1ull << MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE) | \
(1ull << MLX4_EVENT_TYPE_SRQ_LIMIT) | \
- (1ull << MLX4_EVENT_TYPE_CMD))
-
-struct mlx4_eqe {
- u8 reserved1;
- u8 type;
- u8 reserved2;
- u8 subtype;
- union {
- u32 raw[6];
- struct {
- __be32 cqn;
- } __packed comp;
- struct {
- u16 reserved1;
- __be16 token;
- u32 reserved2;
- u8 reserved3[3];
- u8 status;
- __be64 out_param;
- } __packed cmd;
- struct {
- __be32 qpn;
- } __packed qp;
- struct {
- __be32 srqn;
- } __packed srq;
- struct {
- __be32 cqn;
- u32 reserved1;
- u8 reserved2[3];
- u8 syndrome;
- } __packed cq_err;
- struct {
- u32 reserved1[2];
- __be32 port;
- } __packed port_change;
- } event;
- u8 reserved3[3];
- u8 owner;
-} __packed;
+ (1ull << MLX4_EVENT_TYPE_CMD) | \
+ (1ull << MLX4_EVENT_TYPE_COMM_CHANNEL) | \
+ (1ull << MLX4_EVENT_TYPE_FLR_EVENT))
static void eq_set_ci(struct mlx4_eq *eq, int req_not)
{
return !!(eqe->owner & 0x80) ^ !!(eq->cons_index & eq->nent) ? NULL : eqe;
}
+static struct mlx4_eqe *next_slave_event_eqe(struct mlx4_slave_event_eq *slave_eq)
+{
+ struct mlx4_eqe *eqe =
+ &slave_eq->event_eqe[slave_eq->cons & (SLAVE_EVENT_EQ_SIZE - 1)];
+ return (!!(eqe->owner & 0x80) ^
+ !!(slave_eq->cons & SLAVE_EVENT_EQ_SIZE)) ?
+ eqe : NULL;
+}
+
+void mlx4_gen_slave_eqe(struct work_struct *work)
+{
+ struct mlx4_mfunc_master_ctx *master =
+ container_of(work, struct mlx4_mfunc_master_ctx,
+ slave_event_work);
+ struct mlx4_mfunc *mfunc =
+ container_of(master, struct mlx4_mfunc, master);
+ struct mlx4_priv *priv = container_of(mfunc, struct mlx4_priv, mfunc);
+ struct mlx4_dev *dev = &priv->dev;
+ struct mlx4_slave_event_eq *slave_eq = &mfunc->master.slave_eq;
+ struct mlx4_eqe *eqe;
+ u8 slave;
+ int i;
+
+ for (eqe = next_slave_event_eqe(slave_eq); eqe;
+ eqe = next_slave_event_eqe(slave_eq)) {
+ slave = eqe->slave_id;
+
+ /* All active slaves need to receive the event */
+ if (slave == ALL_SLAVES) {
+ for (i = 0; i < dev->num_slaves; i++) {
+ if (i != dev->caps.function &&
+ master->slave_state[i].active)
+ if (mlx4_GEN_EQE(dev, i, eqe))
+ mlx4_warn(dev, "Failed to "
+ " generate event "
+ "for slave %d\n", i);
+ }
+ } else {
+ if (mlx4_GEN_EQE(dev, slave, eqe))
+ mlx4_warn(dev, "Failed to generate event "
+ "for slave %d\n", slave);
+ }
+ ++slave_eq->cons;
+ }
+}
+
+
+static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_event_eq *slave_eq = &priv->mfunc.master.slave_eq;
+ struct mlx4_eqe *s_eqe =
+ &slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)];
+
+ if ((!!(s_eqe->owner & 0x80)) ^
+ (!!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE))) {
+ mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. "
+ "No free EQE on slave events queue\n", slave);
+ return;
+ }
+
+ memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
+ s_eqe->slave_id = slave;
+ /* ensure all information is written before setting the ownersip bit */
+ wmb();
+ s_eqe->owner = !!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE) ? 0x0 : 0x80;
+ ++slave_eq->prod;
+
+ queue_work(priv->mfunc.master.comm_wq,
+ &priv->mfunc.master.slave_event_work);
+}
+
+static void mlx4_slave_event(struct mlx4_dev *dev, int slave,
+ struct mlx4_eqe *eqe)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_state *s_slave =
+ &priv->mfunc.master.slave_state[slave];
+
+ if (!s_slave->active) {
+ /*mlx4_warn(dev, "Trying to pass event to inactive slave\n");*/
+ return;
+ }
+
+ slave_event(dev, slave, eqe);
+}
+
+void mlx4_master_handle_slave_flr(struct work_struct *work)
+{
+ struct mlx4_mfunc_master_ctx *master =
+ container_of(work, struct mlx4_mfunc_master_ctx,
+ slave_flr_event_work);
+ struct mlx4_mfunc *mfunc =
+ container_of(master, struct mlx4_mfunc, master);
+ struct mlx4_priv *priv =
+ container_of(mfunc, struct mlx4_priv, mfunc);
+ struct mlx4_dev *dev = &priv->dev;
+ struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
+ int i;
+ int err;
+
+ mlx4_dbg(dev, "mlx4_handle_slave_flr\n");
+
+ for (i = 0 ; i < dev->num_slaves; i++) {
+
+ if (MLX4_COMM_CMD_FLR == slave_state[i].last_cmd) {
+ mlx4_dbg(dev, "mlx4_handle_slave_flr: "
+ "clean slave: %d\n", i);
+
+ mlx4_delete_all_resources_for_slave(dev, i);
+ /*return the slave to running mode*/
+ spin_lock(&priv->mfunc.master.slave_state_lock);
+ slave_state[i].last_cmd = MLX4_COMM_CMD_RESET;
+ slave_state[i].is_slave_going_down = 0;
+ spin_unlock(&priv->mfunc.master.slave_state_lock);
+ /*notify the FW:*/
+ err = mlx4_cmd(dev, 0, i, 0, MLX4_CMD_INFORM_FLR_DONE,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ mlx4_warn(dev, "Failed to notify FW on "
+ "FLR done (slave:%d)\n", i);
+ }
+ }
+}
+
static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
{
+ struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_eqe *eqe;
int cqn;
int eqes_found = 0;
int set_ci = 0;
int port;
+ int slave = 0;
+ int ret;
+ u32 flr_slave;
+ u8 update_slave_state;
+ int i;
while ((eqe = next_eqe_sw(eq))) {
/*
case MLX4_EVENT_TYPE_PATH_MIG_FAILED:
case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR:
- mlx4_qp_event(dev, be32_to_cpu(eqe->event.qp.qpn) & 0xffffff,
- eqe->type);
+ mlx4_dbg(dev, "event %d arrived\n", eqe->type);
+ if (mlx4_is_master(dev)) {
+ /* forward only to slave owning the QP */
+ ret = mlx4_get_slave_from_resource_id(dev,
+ RES_QP,
+ be32_to_cpu(eqe->event.qp.qpn)
+ & 0xffffff, &slave);
+ if (ret && ret != -ENOENT) {
+ mlx4_dbg(dev, "QP event %02x(%02x) on "
+ "EQ %d at index %u: could "
+ "not get slave id (%d)\n",
+ eqe->type, eqe->subtype,
+ eq->eqn, eq->cons_index, ret);
+ break;
+ }
+
+ if (!ret && slave != dev->caps.function) {
+ mlx4_slave_event(dev, slave, eqe);
+ break;
+ }
+
+ }
+ mlx4_qp_event(dev, be32_to_cpu(eqe->event.qp.qpn) &
+ 0xffffff, eqe->type);
break;
case MLX4_EVENT_TYPE_SRQ_LIMIT:
+ mlx4_warn(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
+ __func__);
case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
- mlx4_srq_event(dev, be32_to_cpu(eqe->event.srq.srqn) & 0xffffff,
- eqe->type);
+ if (mlx4_is_master(dev)) {
+ /* forward only to slave owning the SRQ */
+ ret = mlx4_get_slave_from_resource_id(dev,
+ RES_SRQ,
+ be32_to_cpu(eqe->event.srq.srqn)
+ & 0xffffff,
+ &slave);
+ if (ret && ret != -ENOENT) {
+ mlx4_warn(dev, "SRQ event %02x(%02x) "
+ "on EQ %d at index %u: could"
+ " not get slave id (%d)\n",
+ eqe->type, eqe->subtype,
+ eq->eqn, eq->cons_index, ret);
+ break;
+ }
+ mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x,"
+ " event: %02x(%02x)\n", __func__,
+ slave,
+ be32_to_cpu(eqe->event.srq.srqn),
+ eqe->type, eqe->subtype);
+
+ if (!ret && slave != dev->caps.function) {
+ mlx4_warn(dev, "%s: sending event "
+ "%02x(%02x) to slave:%d\n",
+ __func__, eqe->type,
+ eqe->subtype, slave);
+ mlx4_slave_event(dev, slave, eqe);
+ break;
+ }
+ }
+ mlx4_srq_event(dev, be32_to_cpu(eqe->event.srq.srqn) &
+ 0xffffff, eqe->type);
break;
case MLX4_EVENT_TYPE_CMD:
case MLX4_EVENT_TYPE_PORT_CHANGE:
port = be32_to_cpu(eqe->event.port_change.port) >> 28;
if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) {
- mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN,
+ mlx4_dispatch_event(dev,
+ MLX4_DEV_EVENT_PORT_DOWN,
port);
mlx4_priv(dev)->sense.do_sense_port[port] = 1;
+ if (mlx4_is_master(dev))
+ /*change the state of all slave's port
+ * to down:*/
+ for (i = 0; i < dev->num_slaves; i++) {
+ mlx4_dbg(dev, "%s: Sending "
+ "MLX4_PORT_CHANGE_SUBTYPE_DOWN"
+ " to slave: %d, port:%d\n",
+ __func__, i, port);
+ if (i == dev->caps.function)
+ continue;
+ mlx4_slave_event(dev, i, eqe);
+ }
} else {
- mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP,
+ mlx4_dispatch_event(dev,
+ MLX4_DEV_EVENT_PORT_UP,
port);
mlx4_priv(dev)->sense.do_sense_port[port] = 0;
+
+ if (mlx4_is_master(dev)) {
+ for (i = 0; i < dev->num_slaves; i++) {
+ if (i == dev->caps.function)
+ continue;
+ mlx4_slave_event(dev, i, eqe);
+ }
+ }
}
break;
eqe->event.cq_err.syndrome == 1 ?
"overrun" : "access violation",
be32_to_cpu(eqe->event.cq_err.cqn) & 0xffffff);
- mlx4_cq_event(dev, be32_to_cpu(eqe->event.cq_err.cqn),
+ if (mlx4_is_master(dev)) {
+ ret = mlx4_get_slave_from_resource_id(dev,
+ RES_CQ,
+ be32_to_cpu(eqe->event.cq_err.cqn)
+ & 0xffffff, &slave);
+ if (ret && ret != -ENOENT) {
+ mlx4_dbg(dev, "CQ event %02x(%02x) on "
+ "EQ %d at index %u: could "
+ "not get slave id (%d)\n",
+ eqe->type, eqe->subtype,
+ eq->eqn, eq->cons_index, ret);
+ break;
+ }
+
+ if (!ret && slave != dev->caps.function) {
+ mlx4_slave_event(dev, slave, eqe);
+ break;
+ }
+ }
+ mlx4_cq_event(dev,
+ be32_to_cpu(eqe->event.cq_err.cqn)
+ & 0xffffff,
eqe->type);
break;
mlx4_warn(dev, "EQ overrun on EQN %d\n", eq->eqn);
break;
+ case MLX4_EVENT_TYPE_COMM_CHANNEL:
+ if (!mlx4_is_master(dev)) {
+ mlx4_warn(dev, "Received comm channel event "
+ "for non master device\n");
+ break;
+ }
+ memcpy(&priv->mfunc.master.comm_arm_bit_vector,
+ eqe->event.comm_channel_arm.bit_vec,
+ sizeof eqe->event.comm_channel_arm.bit_vec);
+ queue_work(priv->mfunc.master.comm_wq,
+ &priv->mfunc.master.comm_work);
+ break;
+
+ case MLX4_EVENT_TYPE_FLR_EVENT:
+ flr_slave = be32_to_cpu(eqe->event.flr_event.slave_id);
+ if (!mlx4_is_master(dev)) {
+ mlx4_warn(dev, "Non-master function received"
+ "FLR event\n");
+ break;
+ }
+
+ mlx4_dbg(dev, "FLR event for slave: %d\n", flr_slave);
+
+ if (flr_slave > dev->num_slaves) {
+ mlx4_warn(dev,
+ "Got FLR for unknown function: %d\n",
+ flr_slave);
+ update_slave_state = 0;
+ } else
+ update_slave_state = 1;
+
+ spin_lock(&priv->mfunc.master.slave_state_lock);
+ if (update_slave_state) {
+ priv->mfunc.master.slave_state[flr_slave].active = false;
+ priv->mfunc.master.slave_state[flr_slave].last_cmd = MLX4_COMM_CMD_FLR;
+ priv->mfunc.master.slave_state[flr_slave].is_slave_going_down = 1;
+ }
+ spin_unlock(&priv->mfunc.master.slave_state_lock);
+ queue_work(priv->mfunc.master.comm_wq,
+ &priv->mfunc.master.slave_flr_event_work);
+ break;
case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
case MLX4_EVENT_TYPE_ECC_DETECT:
default:
- mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at index %u\n",
- eqe->type, eqe->subtype, eq->eqn, eq->cons_index);
+ mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at "
+ "index %u. owner=%x, nent=0x%x, slave=%x, "
+ "ownership=%s\n",
+ eqe->type, eqe->subtype, eq->eqn,
+ eq->cons_index, eqe->owner, eq->nent,
+ eqe->slave_id,
+ !!(eqe->owner & 0x80) ^
+ !!(eq->cons_index & eq->nent) ? "HW" : "SW");
break;
- }
+ };
++eq->cons_index;
eqes_found = 1;
return IRQ_HANDLED;
}
+int mlx4_MAP_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_event_eq_info *event_eq =
+ &priv->mfunc.master.slave_state[slave].event_eq;
+ u32 in_modifier = vhcr->in_modifier;
+ u32 eqn = in_modifier & 0x1FF;
+ u64 in_param = vhcr->in_param;
+ int err = 0;
+
+ if (slave == dev->caps.function)
+ err = mlx4_cmd(dev, in_param, (in_modifier & 0x80000000) | eqn,
+ 0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
+ if (!err) {
+ if (in_modifier >> 31) {
+ /* unmap */
+ event_eq->event_type &= ~in_param;
+ } else {
+ event_eq->eqn = eqn;
+ event_eq->event_type = in_param;
+ }
+ }
+ return err;
+}
+
static int mlx4_MAP_EQ(struct mlx4_dev *dev, u64 event_mask, int unmap,
int eq_num)
{
return mlx4_cmd(dev, event_mask, (unmap << 31) | eq_num,
- 0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B);
+ 0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_SW2HW_EQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int eq_num)
{
- return mlx4_cmd(dev, mailbox->dma, eq_num, 0, MLX4_CMD_SW2HW_EQ,
- MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd(dev, mailbox->dma | dev->caps.function, eq_num, 0,
+ MLX4_CMD_SW2HW_EQ, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_HW2SW_EQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int eq_num)
{
- return mlx4_cmd_box(dev, 0, mailbox->dma, eq_num, 0, MLX4_CMD_HW2SW_EQ,
- MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd_box(dev, dev->caps.function, mailbox->dma, eq_num,
+ 0, MLX4_CMD_HW2SW_EQ, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_num_eq_uar(struct mlx4_dev *dev)
for (i = 0; i < mlx4_num_eq_uar(dev); ++i)
priv->eq_table.uar_map[i] = NULL;
- err = mlx4_map_clr_int(dev);
- if (err)
- goto err_out_bitmap;
+ if (!mlx4_is_slave(dev)) {
+ err = mlx4_map_clr_int(dev);
+ if (err)
+ goto err_out_bitmap;
- priv->eq_table.clr_mask =
- swab32(1 << (priv->eq_table.inta_pin & 31));
- priv->eq_table.clr_int = priv->clr_base +
- (priv->eq_table.inta_pin < 32 ? 4 : 0);
+ priv->eq_table.clr_mask =
+ swab32(1 << (priv->eq_table.inta_pin & 31));
+ priv->eq_table.clr_int = priv->clr_base +
+ (priv->eq_table.inta_pin < 32 ? 4 : 0);
+ }
priv->eq_table.irq_names =
kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 +
mlx4_free_eq(dev, &priv->eq_table.eq[i]);
--i;
}
- mlx4_unmap_clr_int(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_unmap_clr_int(dev);
mlx4_free_irqs(dev);
err_out_bitmap:
for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i)
mlx4_free_eq(dev, &priv->eq_table.eq[i]);
- mlx4_unmap_clr_int(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_unmap_clr_int(dev);
for (i = 0; i < mlx4_num_eq_uar(dev); ++i)
if (priv->eq_table.uar_map[i])
err = mlx4_NOP(dev);
/* When not in MSI_X, there is only one irq to check */
- if (!(dev->flags & MLX4_FLAG_MSI_X))
+ if (!(dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(dev))
return err;
/* A loop over all completion vectors, for each vector we will check
* SOFTWARE.
*/
+#include <linux/etherdevice.h>
#include <linux/mlx4/cmd.h>
#include <linux/module.h>
#include <linux/cache.h>
extern void __buggy_use_of_MLX4_GET(void);
extern void __buggy_use_of_MLX4_PUT(void);
-static int enable_qos;
+static bool enable_qos;
module_param(enable_qos, bool, 0444);
MODULE_PARM_DESC(enable_qos, "Enable Quality of Service support in the HCA (default: off)");
MLX4_PUT(inbox, cfg->log_pg_sz_m, MOD_STAT_CFG_PG_SZ_M_OFFSET);
err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_MOD_STAT_CFG,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
+int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ u8 field;
+ u32 size;
+ int err = 0;
+
+#define QUERY_FUNC_CAP_FLAGS_OFFSET 0x0
+#define QUERY_FUNC_CAP_NUM_PORTS_OFFSET 0x1
+#define QUERY_FUNC_CAP_FUNCTION_OFFSET 0x3
+#define QUERY_FUNC_CAP_PF_BHVR_OFFSET 0x4
+#define QUERY_FUNC_CAP_QP_QUOTA_OFFSET 0x10
+#define QUERY_FUNC_CAP_CQ_QUOTA_OFFSET 0x14
+#define QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET 0x18
+#define QUERY_FUNC_CAP_MPT_QUOTA_OFFSET 0x20
+#define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET 0x24
+#define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET 0x28
+#define QUERY_FUNC_CAP_MAX_EQ_OFFSET 0x2c
+#define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET 0X30
+
+#define QUERY_FUNC_CAP_PHYS_PORT_OFFSET 0x3
+#define QUERY_FUNC_CAP_ETH_PROPS_OFFSET 0xc
+
+ if (vhcr->op_modifier == 1) {
+ field = vhcr->in_modifier;
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
+
+ field = 0; /* ensure fvl bit is not set */
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
+ } else if (vhcr->op_modifier == 0) {
+ field = 1 << 7; /* enable only ethernet interface */
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
+
+ field = slave;
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FUNCTION_OFFSET);
+
+ field = dev->caps.num_ports;
+ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
+
+ size = 0; /* no PF behavious is set for now */
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_PF_BHVR_OFFSET);
+
+ size = dev->caps.num_qps;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP_QUOTA_OFFSET);
+
+ size = dev->caps.num_srqs;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET);
+
+ size = dev->caps.num_cqs;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET);
+
+ size = dev->caps.num_eqs;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+
+ size = dev->caps.reserved_eqs;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+
+ size = dev->caps.num_mpts;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
+
+ size = dev->caps.num_mtts;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET);
+
+ size = dev->caps.num_mgms + dev->caps.num_amgms;
+ MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
+
+ } else
+ err = -EINVAL;
+
+ return err;
+}
+
+int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ u32 *outbox;
+ u8 field;
+ u32 size;
+ int i;
+ int err = 0;
+
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_FUNC_CAP,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ goto out;
+
+ outbox = mailbox->buf;
+
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS_OFFSET);
+ if (!(field & (1 << 7))) {
+ mlx4_err(dev, "The host doesn't support eth interface\n");
+ err = -EPROTONOSUPPORT;
+ goto out;
+ }
+
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_FUNCTION_OFFSET);
+ func_cap->function = field;
+
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
+ func_cap->num_ports = field;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_PF_BHVR_OFFSET);
+ func_cap->pf_context_behaviour = size;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP_QUOTA_OFFSET);
+ func_cap->qp_quota = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET);
+ func_cap->srq_quota = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET);
+ func_cap->cq_quota = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+ func_cap->max_eq = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+ func_cap->reserved_eq = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
+ func_cap->mpt_quota = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET);
+ func_cap->mtt_quota = size & 0xFFFFFF;
+
+ MLX4_GET(size, outbox, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
+ func_cap->mcg_quota = size & 0xFFFFFF;
+
+ for (i = 1; i <= func_cap->num_ports; ++i) {
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 1,
+ MLX4_CMD_QUERY_FUNC_CAP,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ goto out;
+
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
+ if (field & (1 << 7)) {
+ mlx4_err(dev, "VLAN is enforced on this port\n");
+ err = -EPROTONOSUPPORT;
+ goto out;
+ }
+
+ if (field & (1 << 6)) {
+ mlx4_err(dev, "Force mac is enabled on this port\n");
+ err = -EPROTONOSUPPORT;
+ goto out;
+ }
+
+ MLX4_GET(field, outbox, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
+ func_cap->physical_port[i] = field;
+ }
+
+ /* All other resources are allocated by the master, but we still report
+ * 'num' and 'reserved' capabilities as follows:
+ * - num remains the maximum resource index
+ * - 'num - reserved' is the total available objects of a resource, but
+ * resource indices may be less than 'reserved'
+ * TODO: set per-resource quotas */
+
+out:
+ mlx4_free_cmd_mailbox(dev, mailbox);
+
+ return err;
+}
+
int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
struct mlx4_cmd_mailbox *mailbox;
outbox = mailbox->buf;
err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, !mlx4_is_slave(dev));
if (err)
goto out;
for (i = 1; i <= dev_cap->num_ports; ++i) {
err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B,
+ !mlx4_is_slave(dev));
if (err)
goto out;
MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
dev_cap->supported_port_types[i] = field & 3;
+ dev_cap->suggested_type[i] = (field >> 3) & 1;
+ dev_cap->default_sense[i] = (field >> 4) & 1;
MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
dev_cap->ib_mtu[i] = field & 0xf;
MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
return err;
}
+int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ u64 def_mac;
+ u8 port_type;
+ int err;
+
+#define MLX4_PORT_SUPPORT_IB (1 << 0)
+#define MLX4_PORT_SUGGEST_TYPE (1 << 3)
+#define MLX4_PORT_DEFAULT_SENSE (1 << 4)
+#define MLX4_VF_PORT_ETH_ONLY_MASK (0xff & ~MLX4_PORT_SUPPORT_IB & \
+ ~MLX4_PORT_SUGGEST_TYPE & \
+ ~MLX4_PORT_DEFAULT_SENSE)
+
+ err = mlx4_cmd_box(dev, 0, outbox->dma, vhcr->in_modifier, 0,
+ MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
+
+ if (!err && dev->caps.function != slave) {
+ /* set slave default_mac address */
+ MLX4_GET(def_mac, outbox->buf, QUERY_PORT_MAC_OFFSET);
+ def_mac += slave << 8;
+ MLX4_PUT(outbox->buf, def_mac, QUERY_PORT_MAC_OFFSET);
+
+ /* get port type - currently only eth is enabled */
+ MLX4_GET(port_type, outbox->buf,
+ QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+
+ /* Allow only Eth port, no link sensing allowed */
+ port_type &= MLX4_VF_PORT_ETH_ONLY_MASK;
+
+ /* check eth is enabled for this port */
+ if (!(port_type & 2))
+ mlx4_dbg(dev, "QUERY PORT: eth not supported by host");
+
+ MLX4_PUT(outbox->buf, port_type,
+ QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+ }
+
+ return err;
+}
+
+static int mlx4_QUERY_PORT(struct mlx4_dev *dev, void *ptr, u8 port)
+{
+ struct mlx4_cmd_mailbox *outbox = ptr;
+
+ return mlx4_cmd_box(dev, 0, outbox->dma, port, 0,
+ MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+}
+EXPORT_SYMBOL_GPL(mlx4_QUERY_PORT);
+
int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
{
struct mlx4_cmd_mailbox *mailbox;
if (++nent == MLX4_MAILBOX_SIZE / 16) {
err = mlx4_cmd(dev, mailbox->dma, nent, 0, op,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
if (err)
goto out;
nent = 0;
}
if (nent)
- err = mlx4_cmd(dev, mailbox->dma, nent, 0, op, MLX4_CMD_TIME_CLASS_B);
+ err = mlx4_cmd(dev, mailbox->dma, nent, 0, op,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
if (err)
goto out;
int mlx4_UNMAP_FA(struct mlx4_dev *dev)
{
- return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_FA, MLX4_CMD_TIME_CLASS_B);
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_FA,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_RUN_FW(struct mlx4_dev *dev)
{
- return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_RUN_FW, MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_RUN_FW,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
}
int mlx4_QUERY_FW(struct mlx4_dev *dev)
#define QUERY_FW_OUT_SIZE 0x100
#define QUERY_FW_VER_OFFSET 0x00
+#define QUERY_FW_PPF_ID 0x09
#define QUERY_FW_CMD_IF_REV_OFFSET 0x0a
#define QUERY_FW_MAX_CMD_OFFSET 0x0f
#define QUERY_FW_ERR_START_OFFSET 0x30
#define QUERY_FW_CLR_INT_BASE_OFFSET 0x20
#define QUERY_FW_CLR_INT_BAR_OFFSET 0x28
+#define QUERY_FW_COMM_BASE_OFFSET 0x40
+#define QUERY_FW_COMM_BAR_OFFSET 0x48
+
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
outbox = mailbox->buf;
err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_FW,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
if (err)
goto out;
((fw_ver & 0xffff0000ull) >> 16) |
((fw_ver & 0x0000ffffull) << 16);
+ MLX4_GET(lg, outbox, QUERY_FW_PPF_ID);
+ dev->caps.function = lg;
+
MLX4_GET(cmd_if_rev, outbox, QUERY_FW_CMD_IF_REV_OFFSET);
if (cmd_if_rev < MLX4_COMMAND_INTERFACE_MIN_REV ||
cmd_if_rev > MLX4_COMMAND_INTERFACE_MAX_REV) {
MLX4_GET(fw->clr_int_bar, outbox, QUERY_FW_CLR_INT_BAR_OFFSET);
fw->clr_int_bar = (fw->clr_int_bar >> 6) * 2;
+ MLX4_GET(fw->comm_base, outbox, QUERY_FW_COMM_BASE_OFFSET);
+ MLX4_GET(fw->comm_bar, outbox, QUERY_FW_COMM_BAR_OFFSET);
+ fw->comm_bar = (fw->comm_bar >> 6) * 2;
+ mlx4_dbg(dev, "Communication vector bar:%d offset:0x%llx\n",
+ fw->comm_bar, fw->comm_base);
mlx4_dbg(dev, "FW size %d KB\n", fw->fw_pages >> 2);
/*
outbox = mailbox->buf;
err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_ADAPTER,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
if (err)
goto out;
#define INIT_HCA_LOG_SRQ_OFFSET (INIT_HCA_QPC_OFFSET + 0x2f)
#define INIT_HCA_CQC_BASE_OFFSET (INIT_HCA_QPC_OFFSET + 0x30)
#define INIT_HCA_LOG_CQ_OFFSET (INIT_HCA_QPC_OFFSET + 0x37)
+#define INIT_HCA_EQE_CQE_OFFSETS (INIT_HCA_QPC_OFFSET + 0x38)
#define INIT_HCA_ALTC_BASE_OFFSET (INIT_HCA_QPC_OFFSET + 0x40)
#define INIT_HCA_AUXC_BASE_OFFSET (INIT_HCA_QPC_OFFSET + 0x50)
#define INIT_HCA_EQC_BASE_OFFSET (INIT_HCA_QPC_OFFSET + 0x60)
/* UAR attributes */
- MLX4_PUT(inbox, (u8) (PAGE_SHIFT - 12), INIT_HCA_UAR_PAGE_SZ_OFFSET);
+ MLX4_PUT(inbox, param->uar_page_sz, INIT_HCA_UAR_PAGE_SZ_OFFSET);
MLX4_PUT(inbox, param->log_uar_sz, INIT_HCA_LOG_UAR_SZ_OFFSET);
- err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000);
+ err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000,
+ MLX4_CMD_NATIVE);
if (err)
mlx4_err(dev, "INIT_HCA returns %d\n", err);
return err;
}
+int mlx4_QUERY_HCA(struct mlx4_dev *dev,
+ struct mlx4_init_hca_param *param)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ __be32 *outbox;
+ int err;
+
+#define QUERY_HCA_GLOBAL_CAPS_OFFSET 0x04
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ outbox = mailbox->buf;
+
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0,
+ MLX4_CMD_QUERY_HCA,
+ MLX4_CMD_TIME_CLASS_B,
+ !mlx4_is_slave(dev));
+ if (err)
+ goto out;
+
+ MLX4_GET(param->global_caps, outbox, QUERY_HCA_GLOBAL_CAPS_OFFSET);
+
+ /* QPC/EEC/CQC/EQC/RDMARC attributes */
+
+ MLX4_GET(param->qpc_base, outbox, INIT_HCA_QPC_BASE_OFFSET);
+ MLX4_GET(param->log_num_qps, outbox, INIT_HCA_LOG_QP_OFFSET);
+ MLX4_GET(param->srqc_base, outbox, INIT_HCA_SRQC_BASE_OFFSET);
+ MLX4_GET(param->log_num_srqs, outbox, INIT_HCA_LOG_SRQ_OFFSET);
+ MLX4_GET(param->cqc_base, outbox, INIT_HCA_CQC_BASE_OFFSET);
+ MLX4_GET(param->log_num_cqs, outbox, INIT_HCA_LOG_CQ_OFFSET);
+ MLX4_GET(param->altc_base, outbox, INIT_HCA_ALTC_BASE_OFFSET);
+ MLX4_GET(param->auxc_base, outbox, INIT_HCA_AUXC_BASE_OFFSET);
+ MLX4_GET(param->eqc_base, outbox, INIT_HCA_EQC_BASE_OFFSET);
+ MLX4_GET(param->log_num_eqs, outbox, INIT_HCA_LOG_EQ_OFFSET);
+ MLX4_GET(param->rdmarc_base, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+ MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+
+ /* multicast attributes */
+
+ MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
+ MLX4_GET(param->log_mc_entry_sz, outbox,
+ INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+ MLX4_GET(param->log_mc_hash_sz, outbox,
+ INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+ MLX4_GET(param->log_mc_table_sz, outbox,
+ INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+
+ /* TPT attributes */
+
+ MLX4_GET(param->dmpt_base, outbox, INIT_HCA_DMPT_BASE_OFFSET);
+ MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+ MLX4_GET(param->mtt_base, outbox, INIT_HCA_MTT_BASE_OFFSET);
+ MLX4_GET(param->cmpt_base, outbox, INIT_HCA_CMPT_BASE_OFFSET);
+
+ /* UAR attributes */
+
+ MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
+ MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+
+out:
+ mlx4_free_cmd_mailbox(dev, mailbox);
+
+ return err;
+}
+
+int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int port = vhcr->in_modifier;
+ int err;
+
+ if (priv->mfunc.master.slave_state[slave].init_port_mask & (1 << port))
+ return 0;
+
+ if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB)
+ return -ENODEV;
+
+ /* Enable port only if it was previously disabled */
+ if (!priv->mfunc.master.init_port_ref[port]) {
+ err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+ if (err)
+ return err;
+ priv->mfunc.master.slave_state[slave].init_port_mask |=
+ (1 << port);
+ }
+ ++priv->mfunc.master.init_port_ref[port];
+ return 0;
+}
+
int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
{
struct mlx4_cmd_mailbox *mailbox;
MLX4_PUT(inbox, field, INIT_PORT_MAX_PKEY_OFFSET);
err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_INIT_PORT,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
mlx4_free_cmd_mailbox(dev, mailbox);
} else
err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_INIT_PORT);
+int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int port = vhcr->in_modifier;
+ int err;
+
+ if (!(priv->mfunc.master.slave_state[slave].init_port_mask &
+ (1 << port)))
+ return 0;
+
+ if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB)
+ return -ENODEV;
+ if (priv->mfunc.master.init_port_ref[port] == 1) {
+ err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000,
+ MLX4_CMD_NATIVE);
+ if (err)
+ return err;
+ }
+ priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port);
+ --priv->mfunc.master.init_port_ref[port];
+ return 0;
+}
+
int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port)
{
- return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000);
+ return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000,
+ MLX4_CMD_WRAPPED);
}
EXPORT_SYMBOL_GPL(mlx4_CLOSE_PORT);
int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
{
- return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA, 1000);
+ return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA, 1000,
+ MLX4_CMD_NATIVE);
}
int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
{
int ret = mlx4_cmd_imm(dev, icm_size, aux_pages, 0, 0,
MLX4_CMD_SET_ICM_SIZE,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
if (ret)
return ret;
int mlx4_NOP(struct mlx4_dev *dev)
{
/* Input modifier of 0x1f means "finish as soon as possible." */
- return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100);
+ return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE);
}
#define MLX4_WOL_SETUP_MODE (5 << 28)
u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
return mlx4_cmd_imm(dev, 0, config, in_mod, 0x3,
- MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
}
EXPORT_SYMBOL_GPL(mlx4_wol_read);
u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
return mlx4_cmd(dev, config, in_mod, 0x1, MLX4_CMD_MOD_STAT_CFG,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
}
EXPORT_SYMBOL_GPL(mlx4_wol_write);
u64 max_icm_sz;
int max_gso_sz;
u8 supported_port_types[MLX4_MAX_PORTS + 1];
+ u8 suggested_type[MLX4_MAX_PORTS + 1];
+ u8 default_sense[MLX4_MAX_PORTS + 1];
u8 log_max_macs[MLX4_MAX_PORTS + 1];
u8 log_max_vlans[MLX4_MAX_PORTS + 1];
u32 max_counters;
};
+struct mlx4_func_cap {
+ u8 function;
+ u8 num_ports;
+ u8 flags;
+ u32 pf_context_behaviour;
+ int qp_quota;
+ int cq_quota;
+ int srq_quota;
+ int mpt_quota;
+ int mtt_quota;
+ int max_eq;
+ int reserved_eq;
+ int mcg_quota;
+ u8 physical_port[MLX4_MAX_PORTS + 1];
+ u8 port_flags[MLX4_MAX_PORTS + 1];
+};
+
struct mlx4_adapter {
char board_id[MLX4_BOARD_ID_LEN];
u8 inta_pin;
u64 dmpt_base;
u64 cmpt_base;
u64 mtt_base;
+ u64 global_caps;
u16 log_mc_entry_sz;
u16 log_mc_hash_sz;
u8 log_num_qps;
u8 log_mc_table_sz;
u8 log_mpt_sz;
u8 log_uar_sz;
+ u8 uar_page_sz; /* log pg sz in 4k chunks */
};
struct mlx4_init_ib_param {
};
int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap);
+int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap);
+int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
int mlx4_MAP_FA(struct mlx4_dev *dev, struct mlx4_icm *icm);
int mlx4_UNMAP_FA(struct mlx4_dev *dev);
int mlx4_RUN_FW(struct mlx4_dev *dev);
int mlx4_QUERY_FW(struct mlx4_dev *dev);
int mlx4_QUERY_ADAPTER(struct mlx4_dev *dev, struct mlx4_adapter *adapter);
int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param);
+int mlx4_QUERY_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param);
int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic);
int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt);
int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages);
static int mlx4_UNMAP_ICM(struct mlx4_dev *dev, u64 virt, u32 page_count)
{
return mlx4_cmd(dev, virt, page_count, 0, MLX4_CMD_UNMAP_ICM,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm)
int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev)
{
- return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_ICM_AUX, MLX4_CMD_TIME_CLASS_B);
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_ICM_AUX,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj)
mlx4_add_device(intf, priv);
mutex_unlock(&intf_mutex);
- mlx4_start_catas_poll(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_start_catas_poll(dev);
return 0;
}
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_interface *intf;
- mlx4_stop_catas_poll(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_stop_catas_poll(dev);
mutex_lock(&intf_mutex);
list_for_each_entry(intf, &intf_list, list)
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/io-mapping.h>
+#include <linux/delay.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
#endif /* CONFIG_PCI_MSI */
+static int num_vfs;
+module_param(num_vfs, int, 0444);
+MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0");
+
+static int probe_vf;
+module_param(probe_vf, int, 0644);
+MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
+
+int mlx4_log_num_mgm_entry_size = 10;
+module_param_named(log_num_mgm_entry_size,
+ mlx4_log_num_mgm_entry_size, int, 0444);
+MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
+ " of qp per mcg, for example:"
+ " 10 gives 248.range: 9<="
+ " log_num_mgm_entry_size <= 12");
+
+#define MLX4_VF (1 << 0)
+
+#define HCA_GLOBAL_CAP_MASK 0
+#define PF_CONTEXT_BEHAVIOUR_MASK 0
+
static char mlx4_version[] __devinitdata =
DRV_NAME ": Mellanox ConnectX core driver v"
DRV_VERSION " (" DRV_RELDATE ")\n";
static struct mlx4_profile default_profile = {
- .num_qp = 1 << 17,
+ .num_qp = 1 << 18,
.num_srq = 1 << 16,
.rdmarc_per_qp = 1 << 4,
.num_cq = 1 << 16,
.num_mcg = 1 << 13,
- .num_mpt = 1 << 17,
+ .num_mpt = 1 << 19,
.num_mtt = 1 << 20,
};
-static int log_num_mac = 2;
+static int log_num_mac = 7;
module_param_named(log_num_mac, log_num_mac, int, 0444);
MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
/* Log2 max number of VLANs per ETH port (0-7) */
#define MLX4_LOG_NUM_VLANS 7
-static int use_prio;
+static bool use_prio;
module_param_named(use_prio, use_prio, bool, 0444);
MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
"(0/1, default 0)");
-static int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
+int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
+static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
+static int arr_argc = 2;
+module_param_array(port_type_array, int, &arr_argc, 0444);
+MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
+ "1 for IB, 2 for Ethernet");
+
+struct mlx4_port_config {
+ struct list_head list;
+ enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
+ struct pci_dev *pdev;
+};
+
+static inline int mlx4_master_get_num_eqs(struct mlx4_dev *dev)
+{
+ return dev->caps.reserved_eqs +
+ MLX4_MFUNC_EQ_NUM * (dev->num_slaves + 1);
+}
+
int mlx4_check_port_params(struct mlx4_dev *dev,
enum mlx4_port_type *port_type)
{
{
int i;
- dev->caps.port_mask = 0;
for (i = 1; i <= dev->caps.num_ports; ++i)
- if (dev->caps.port_type[i] == MLX4_PORT_TYPE_IB)
- dev->caps.port_mask |= 1 << (i - 1);
+ dev->caps.port_mask[i] = dev->caps.port_type[i];
}
static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev->caps.eth_mtu_cap[i] = dev_cap->eth_mtu[i];
dev->caps.def_mac[i] = dev_cap->def_mac[i];
dev->caps.supported_type[i] = dev_cap->supported_port_types[i];
+ dev->caps.suggested_type[i] = dev_cap->suggested_type[i];
+ dev->caps.default_sense[i] = dev_cap->default_sense[i];
dev->caps.trans_type[i] = dev_cap->trans_type[i];
dev->caps.vendor_oui[i] = dev_cap->vendor_oui[i];
dev->caps.wavelength[i] = dev_cap->wavelength[i];
dev->caps.trans_code[i] = dev_cap->trans_code[i];
}
+ dev->caps.uar_page_size = PAGE_SIZE;
dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE;
dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
dev->caps.bf_reg_size = dev_cap->bf_reg_size;
dev->caps.reserved_srqs = dev_cap->reserved_srqs;
dev->caps.max_sq_desc_sz = dev_cap->max_sq_desc_sz;
dev->caps.max_rq_desc_sz = dev_cap->max_rq_desc_sz;
- dev->caps.num_qp_per_mgm = MLX4_QP_PER_MGM;
+ dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
/*
* Subtract 1 from the limit because we need to allocate a
* spare CQE so the HCA HW can tell the difference between an
dev->caps.max_cqes = dev_cap->max_cq_sz - 1;
dev->caps.reserved_cqs = dev_cap->reserved_cqs;
dev->caps.reserved_eqs = dev_cap->reserved_eqs;
- dev->caps.mtts_per_seg = 1 << log_mtts_per_seg;
- dev->caps.reserved_mtts = DIV_ROUND_UP(dev_cap->reserved_mtts,
- dev->caps.mtts_per_seg);
+ dev->caps.reserved_mtts = dev_cap->reserved_mtts;
dev->caps.reserved_mrws = dev_cap->reserved_mrws;
- dev->caps.reserved_uars = dev_cap->reserved_uars;
+
+ /* The first 128 UARs are used for EQ doorbells */
+ dev->caps.reserved_uars = max_t(int, 128, dev_cap->reserved_uars);
dev->caps.reserved_pds = dev_cap->reserved_pds;
dev->caps.reserved_xrcds = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
dev_cap->reserved_xrcds : 0;
dev->caps.max_xrcds = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
dev_cap->max_xrcds : 0;
- dev->caps.mtt_entry_sz = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
+ dev->caps.mtt_entry_sz = dev_cap->mtt_entry_sz;
+
dev->caps.max_msg_sz = dev_cap->max_msg_sz;
dev->caps.page_size_cap = ~(u32) (dev_cap->min_page_sz - 1);
dev->caps.flags = dev_cap->flags;
dev->caps.stat_rate_support = dev_cap->stat_rate_support;
dev->caps.max_gso_sz = dev_cap->max_gso_sz;
+ /* Sense port always allowed on supported devices for ConnectX1 and 2 */
+ if (dev->pdev->device != 0x1003)
+ dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
+
dev->caps.log_num_macs = log_num_mac;
dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
dev->caps.log_num_prios = use_prio ? 3 : 0;
for (i = 1; i <= dev->caps.num_ports; ++i) {
- if (dev->caps.supported_type[i] != MLX4_PORT_TYPE_ETH)
- dev->caps.port_type[i] = MLX4_PORT_TYPE_IB;
- else
- dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
- dev->caps.possible_type[i] = dev->caps.port_type[i];
+ dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
+ if (dev->caps.supported_type[i]) {
+ /* if only ETH is supported - assign ETH */
+ if (dev->caps.supported_type[i] == MLX4_PORT_TYPE_ETH)
+ dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+ /* if only IB is supported,
+ * assign IB only if SRIOV is off*/
+ else if (dev->caps.supported_type[i] ==
+ MLX4_PORT_TYPE_IB) {
+ if (dev->flags & MLX4_FLAG_SRIOV)
+ dev->caps.port_type[i] =
+ MLX4_PORT_TYPE_NONE;
+ else
+ dev->caps.port_type[i] =
+ MLX4_PORT_TYPE_IB;
+ /* if IB and ETH are supported,
+ * first of all check if SRIOV is on */
+ } else if (dev->flags & MLX4_FLAG_SRIOV)
+ dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+ else {
+ /* In non-SRIOV mode, we set the port type
+ * according to user selection of port type,
+ * if usere selected none, take the FW hint */
+ if (port_type_array[i-1] == MLX4_PORT_TYPE_NONE)
+ dev->caps.port_type[i] = dev->caps.suggested_type[i] ?
+ MLX4_PORT_TYPE_ETH : MLX4_PORT_TYPE_IB;
+ else
+ dev->caps.port_type[i] = port_type_array[i-1];
+ }
+ }
+ /*
+ * Link sensing is allowed on the port if 3 conditions are true:
+ * 1. Both protocols are supported on the port.
+ * 2. Different types are supported on the port
+ * 3. FW declared that it supports link sensing
+ */
mlx4_priv(dev)->sense.sense_allowed[i] =
- dev->caps.supported_type[i] == MLX4_PORT_TYPE_AUTO;
+ ((dev->caps.supported_type[i] == MLX4_PORT_TYPE_AUTO) &&
+ (dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
+ (dev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT));
+
+ /*
+ * If "default_sense" bit is set, we move the port to "AUTO" mode
+ * and perform sense_port FW command to try and set the correct
+ * port type from beginning
+ */
+ if (mlx4_priv(dev)->sense.sense_allowed[i] && dev->caps.default_sense[i]) {
+ enum mlx4_port_type sensed_port = MLX4_PORT_TYPE_NONE;
+ dev->caps.possible_type[i] = MLX4_PORT_TYPE_AUTO;
+ mlx4_SENSE_PORT(dev, i, &sensed_port);
+ if (sensed_port != MLX4_PORT_TYPE_NONE)
+ dev->caps.port_type[i] = sensed_port;
+ } else {
+ dev->caps.possible_type[i] = dev->caps.port_type[i];
+ }
if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
dev->caps.log_num_macs = dev_cap->log_max_macs[i];
}
}
- mlx4_set_port_mask(dev);
-
dev->caps.max_counters = 1 << ilog2(dev_cap->max_counters);
dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
return 0;
}
+/*The function checks if there are live vf, return the num of them*/
+static int mlx4_how_many_lives_vf(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_state *s_state;
+ int i;
+ int ret = 0;
+
+ for (i = 1/*the ppf is 0*/; i < dev->num_slaves; ++i) {
+ s_state = &priv->mfunc.master.slave_state[i];
+ if (s_state->active && s_state->last_cmd !=
+ MLX4_COMM_CMD_RESET) {
+ mlx4_warn(dev, "%s: slave: %d is still active\n",
+ __func__, i);
+ ret++;
+ }
+ }
+ return ret;
+}
+
+static int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_state *s_slave;
+
+ if (!mlx4_is_master(dev))
+ return 0;
+
+ s_slave = &priv->mfunc.master.slave_state[slave];
+ return !!s_slave->active;
+}
+EXPORT_SYMBOL(mlx4_is_slave_active);
+
+static int mlx4_slave_cap(struct mlx4_dev *dev)
+{
+ int err;
+ u32 page_size;
+ struct mlx4_dev_cap dev_cap;
+ struct mlx4_func_cap func_cap;
+ struct mlx4_init_hca_param hca_param;
+ int i;
+
+ memset(&hca_param, 0, sizeof(hca_param));
+ err = mlx4_QUERY_HCA(dev, &hca_param);
+ if (err) {
+ mlx4_err(dev, "QUERY_HCA command failed, aborting.\n");
+ return err;
+ }
+
+ /*fail if the hca has an unknown capability */
+ if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) !=
+ HCA_GLOBAL_CAP_MASK) {
+ mlx4_err(dev, "Unknown hca global capabilities\n");
+ return -ENOSYS;
+ }
+
+ mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;
+
+ memset(&dev_cap, 0, sizeof(dev_cap));
+ err = mlx4_dev_cap(dev, &dev_cap);
+ if (err) {
+ mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+ return err;
+ }
+
+ page_size = ~dev->caps.page_size_cap + 1;
+ mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
+ if (page_size > PAGE_SIZE) {
+ mlx4_err(dev, "HCA minimum page size of %d bigger than "
+ "kernel PAGE_SIZE of %ld, aborting.\n",
+ page_size, PAGE_SIZE);
+ return -ENODEV;
+ }
+
+ /* slave gets uar page size from QUERY_HCA fw command */
+ dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);
+
+ /* TODO: relax this assumption */
+ if (dev->caps.uar_page_size != PAGE_SIZE) {
+ mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
+ dev->caps.uar_page_size, PAGE_SIZE);
+ return -ENODEV;
+ }
+
+ memset(&func_cap, 0, sizeof(func_cap));
+ err = mlx4_QUERY_FUNC_CAP(dev, &func_cap);
+ if (err) {
+ mlx4_err(dev, "QUERY_FUNC_CAP command failed, aborting.\n");
+ return err;
+ }
+
+ if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
+ PF_CONTEXT_BEHAVIOUR_MASK) {
+ mlx4_err(dev, "Unknown pf context behaviour\n");
+ return -ENOSYS;
+ }
+
+ dev->caps.function = func_cap.function;
+ dev->caps.num_ports = func_cap.num_ports;
+ dev->caps.num_qps = func_cap.qp_quota;
+ dev->caps.num_srqs = func_cap.srq_quota;
+ dev->caps.num_cqs = func_cap.cq_quota;
+ dev->caps.num_eqs = func_cap.max_eq;
+ dev->caps.reserved_eqs = func_cap.reserved_eq;
+ dev->caps.num_mpts = func_cap.mpt_quota;
+ dev->caps.num_mtts = func_cap.mtt_quota;
+ dev->caps.num_pds = MLX4_NUM_PDS;
+ dev->caps.num_mgms = 0;
+ dev->caps.num_amgms = 0;
+
+ for (i = 1; i <= dev->caps.num_ports; ++i)
+ dev->caps.port_mask[i] = dev->caps.port_type[i];
+
+ if (dev->caps.num_ports > MLX4_MAX_PORTS) {
+ mlx4_err(dev, "HCA has %d ports, but we only support %d, "
+ "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS);
+ return -ENODEV;
+ }
+
+ if (dev->caps.uar_page_size * (dev->caps.num_uars -
+ dev->caps.reserved_uars) >
+ pci_resource_len(dev->pdev, 2)) {
+ mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than "
+ "PCI resource 2 size of 0x%llx, aborting.\n",
+ dev->caps.uar_page_size * dev->caps.num_uars,
+ (unsigned long long) pci_resource_len(dev->pdev, 2));
+ return -ENODEV;
+ }
+
+#if 0
+ mlx4_warn(dev, "sqp_demux:%d\n", dev->caps.sqp_demux);
+ mlx4_warn(dev, "num_uars:%d reserved_uars:%d uar region:0x%x bar2:0x%llx\n",
+ dev->caps.num_uars, dev->caps.reserved_uars,
+ dev->caps.uar_page_size * dev->caps.num_uars,
+ pci_resource_len(dev->pdev, 2));
+ mlx4_warn(dev, "num_eqs:%d reserved_eqs:%d\n", dev->caps.num_eqs,
+ dev->caps.reserved_eqs);
+ mlx4_warn(dev, "num_pds:%d reserved_pds:%d slave_pd_shift:%d pd_base:%d\n",
+ dev->caps.num_pds, dev->caps.reserved_pds,
+ dev->caps.slave_pd_shift, dev->caps.pd_base);
+#endif
+ return 0;
+}
/*
* Change the port configuration of the device.
types[i] = mdev->caps.port_type[i+1];
}
- if (!(mdev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) {
+ if (!(mdev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP) &&
+ !(mdev->caps.flags & MLX4_DEV_CAP_FLAG_SENSE_SUPPORT)) {
for (i = 1; i <= mdev->caps.num_ports; i++) {
if (mdev->caps.possible_type[i] == MLX4_PORT_TYPE_AUTO) {
mdev->caps.possible_type[i] = mdev->caps.port_type[i];
{
struct mlx4_priv *priv = mlx4_priv(dev);
int err;
+ int num_eqs;
err = mlx4_init_icm_table(dev, &priv->qp_table.cmpt_table,
cmpt_base +
if (err)
goto err_srq;
+ num_eqs = (mlx4_is_master(dev)) ?
+ roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
+ dev->caps.num_eqs;
err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
cmpt_base +
((u64) (MLX4_CMPT_TYPE_EQ *
cmpt_entry_sz) << MLX4_CMPT_SHIFT),
- cmpt_entry_sz,
- dev->caps.num_eqs, dev->caps.num_eqs, 0, 0);
+ cmpt_entry_sz, num_eqs, num_eqs, 0, 0);
if (err)
goto err_cq;
{
struct mlx4_priv *priv = mlx4_priv(dev);
u64 aux_pages;
+ int num_eqs;
int err;
err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages);
goto err_unmap_aux;
}
+
+ num_eqs = (mlx4_is_master(dev)) ?
+ roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
+ dev->caps.num_eqs;
err = mlx4_init_icm_table(dev, &priv->eq_table.table,
init_hca->eqc_base, dev_cap->eqc_entry_sz,
- dev->caps.num_eqs, dev->caps.num_eqs,
- 0, 0);
+ num_eqs, num_eqs, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map EQ context memory, aborting.\n");
goto err_unmap_cmpt;
err = mlx4_init_icm_table(dev, &priv->mr_table.mtt_table,
init_hca->mtt_base,
dev->caps.mtt_entry_sz,
- dev->caps.num_mtt_segs,
+ dev->caps.num_mtts,
dev->caps.reserved_mtts, 1, 0);
if (err) {
mlx4_err(dev, "Failed to map MTT context memory, aborting.\n");
* and it's a lot easier than trying to track ref counts.
*/
err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
- init_hca->mc_base, MLX4_MGM_ENTRY_SIZE,
+ init_hca->mc_base,
+ mlx4_get_mgm_entry_size(dev),
dev->caps.num_mgms + dev->caps.num_amgms,
dev->caps.num_mgms + dev->caps.num_amgms,
0, 0);
mlx4_free_icm(dev, priv->fw.aux_icm, 0);
}
+static void mlx4_slave_exit(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ down(&priv->cmd.slave_sem);
+ if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME))
+ mlx4_warn(dev, "Failed to close slave function.\n");
+ up(&priv->cmd.slave_sem);
+}
+
static int map_bf_area(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
resource_size_t bf_len;
int err = 0;
- bf_start = pci_resource_start(dev->pdev, 2) + (dev->caps.num_uars << PAGE_SHIFT);
- bf_len = pci_resource_len(dev->pdev, 2) - (dev->caps.num_uars << PAGE_SHIFT);
+ bf_start = pci_resource_start(dev->pdev, 2) +
+ (dev->caps.num_uars << PAGE_SHIFT);
+ bf_len = pci_resource_len(dev->pdev, 2) -
+ (dev->caps.num_uars << PAGE_SHIFT);
priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
if (!priv->bf_mapping)
err = -ENOMEM;
static void mlx4_close_hca(struct mlx4_dev *dev)
{
unmap_bf_area(dev);
- mlx4_CLOSE_HCA(dev, 0);
- mlx4_free_icms(dev);
- mlx4_UNMAP_FA(dev);
- mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
+ if (mlx4_is_slave(dev))
+ mlx4_slave_exit(dev);
+ else {
+ mlx4_CLOSE_HCA(dev, 0);
+ mlx4_free_icms(dev);
+ mlx4_UNMAP_FA(dev);
+ mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
+ }
+}
+
+static int mlx4_init_slave(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ u64 dma = (u64) priv->mfunc.vhcr_dma;
+ int num_of_reset_retries = NUM_OF_RESET_RETRIES;
+ int ret_from_reset = 0;
+ u32 slave_read;
+ u32 cmd_channel_ver;
+
+ down(&priv->cmd.slave_sem);
+ priv->cmd.max_cmds = 1;
+ mlx4_warn(dev, "Sending reset\n");
+ ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0,
+ MLX4_COMM_TIME);
+ /* if we are in the middle of flr the slave will try
+ * NUM_OF_RESET_RETRIES times before leaving.*/
+ if (ret_from_reset) {
+ if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) {
+ msleep(SLEEP_TIME_IN_RESET);
+ while (ret_from_reset && num_of_reset_retries) {
+ mlx4_warn(dev, "slave is currently in the"
+ "middle of FLR. retrying..."
+ "(try num:%d)\n",
+ (NUM_OF_RESET_RETRIES -
+ num_of_reset_retries + 1));
+ ret_from_reset =
+ mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET,
+ 0, MLX4_COMM_TIME);
+ num_of_reset_retries = num_of_reset_retries - 1;
+ }
+ } else
+ goto err;
+ }
+
+ /* check the driver version - the slave I/F revision
+ * must match the master's */
+ slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
+ cmd_channel_ver = mlx4_comm_get_version();
+
+ if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) !=
+ MLX4_COMM_GET_IF_REV(slave_read)) {
+ mlx4_err(dev, "slave driver version is not supported"
+ " by the master\n");
+ goto err;
+ }
+
+ mlx4_warn(dev, "Sending vhcr0\n");
+ if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR0, dma >> 48,
+ MLX4_COMM_TIME))
+ goto err;
+ if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR1, dma >> 32,
+ MLX4_COMM_TIME))
+ goto err;
+ if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR2, dma >> 16,
+ MLX4_COMM_TIME))
+ goto err;
+ if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_EN, dma, MLX4_COMM_TIME))
+ goto err;
+ up(&priv->cmd.slave_sem);
+ return 0;
+
+err:
+ mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, 0);
+ up(&priv->cmd.slave_sem);
+ return -EIO;
}
static int mlx4_init_hca(struct mlx4_dev *dev)
u64 icm_size;
int err;
- err = mlx4_QUERY_FW(dev);
- if (err) {
- if (err == -EACCES)
- mlx4_info(dev, "non-primary physical function, skipping.\n");
- else
- mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
- return err;
- }
+ if (!mlx4_is_slave(dev)) {
+ err = mlx4_QUERY_FW(dev);
+ if (err) {
+ if (err == -EACCES)
+ mlx4_info(dev, "non-primary physical function, skipping.\n");
+ else
+ mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
+ goto unmap_bf;
+ }
- err = mlx4_load_fw(dev);
- if (err) {
- mlx4_err(dev, "Failed to start FW, aborting.\n");
- return err;
- }
+ err = mlx4_load_fw(dev);
+ if (err) {
+ mlx4_err(dev, "Failed to start FW, aborting.\n");
+ goto unmap_bf;
+ }
- mlx4_cfg.log_pg_sz_m = 1;
- mlx4_cfg.log_pg_sz = 0;
- err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
- if (err)
- mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");
+ mlx4_cfg.log_pg_sz_m = 1;
+ mlx4_cfg.log_pg_sz = 0;
+ err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
+ if (err)
+ mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");
- err = mlx4_dev_cap(dev, &dev_cap);
- if (err) {
- mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
- goto err_stop_fw;
- }
+ err = mlx4_dev_cap(dev, &dev_cap);
+ if (err) {
+ mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+ goto err_stop_fw;
+ }
- profile = default_profile;
+ profile = default_profile;
- icm_size = mlx4_make_profile(dev, &profile, &dev_cap, &init_hca);
- if ((long long) icm_size < 0) {
- err = icm_size;
- goto err_stop_fw;
- }
+ icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
+ &init_hca);
+ if ((long long) icm_size < 0) {
+ err = icm_size;
+ goto err_stop_fw;
+ }
- if (map_bf_area(dev))
- mlx4_dbg(dev, "Failed to map blue flame area\n");
+ init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
+ init_hca.uar_page_sz = PAGE_SHIFT - 12;
- init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
+ err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
+ if (err)
+ goto err_stop_fw;
- err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
- if (err)
- goto err_stop_fw;
+ err = mlx4_INIT_HCA(dev, &init_hca);
+ if (err) {
+ mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
+ goto err_free_icm;
+ }
+ } else {
+ err = mlx4_init_slave(dev);
+ if (err) {
+ mlx4_err(dev, "Failed to initialize slave\n");
+ goto unmap_bf;
+ }
- err = mlx4_INIT_HCA(dev, &init_hca);
- if (err) {
- mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
- goto err_free_icm;
+ err = mlx4_slave_cap(dev);
+ if (err) {
+ mlx4_err(dev, "Failed to obtain slave caps\n");
+ goto err_close;
+ }
}
+ if (map_bf_area(dev))
+ mlx4_dbg(dev, "Failed to map blue flame area\n");
+
+ /*Only the master set the ports, all the rest got it from it.*/
+ if (!mlx4_is_slave(dev))
+ mlx4_set_port_mask(dev);
+
err = mlx4_QUERY_ADAPTER(dev, &adapter);
if (err) {
mlx4_err(dev, "QUERY_ADAPTER command failed, aborting.\n");
return 0;
err_close:
- mlx4_CLOSE_HCA(dev, 0);
+ mlx4_close_hca(dev);
err_free_icm:
- mlx4_free_icms(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_free_icms(dev);
err_stop_fw:
+ if (!mlx4_is_slave(dev)) {
+ mlx4_UNMAP_FA(dev);
+ mlx4_free_icm(dev, priv->fw.fw_icm, 0);
+ }
+unmap_bf:
unmap_bf_area(dev);
- mlx4_UNMAP_FA(dev);
- mlx4_free_icm(dev, priv->fw.fw_icm, 0);
-
return err;
}
goto err_srq_table_free;
}
- err = mlx4_init_mcg_table(dev);
- if (err) {
- mlx4_err(dev, "Failed to initialize "
- "multicast group table, aborting.\n");
- goto err_qp_table_free;
+ if (!mlx4_is_slave(dev)) {
+ err = mlx4_init_mcg_table(dev);
+ if (err) {
+ mlx4_err(dev, "Failed to initialize "
+ "multicast group table, aborting.\n");
+ goto err_qp_table_free;
+ }
}
err = mlx4_init_counters_table(dev);
if (err && err != -ENOENT) {
mlx4_err(dev, "Failed to initialize counters table, aborting.\n");
- goto err_counters_table_free;
+ goto err_mcg_table_free;
}
- for (port = 1; port <= dev->caps.num_ports; port++) {
- enum mlx4_port_type port_type = 0;
- mlx4_SENSE_PORT(dev, port, &port_type);
- if (port_type)
- dev->caps.port_type[port] = port_type;
- ib_port_default_caps = 0;
- err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps);
- if (err)
- mlx4_warn(dev, "failed to get port %d default "
- "ib capabilities (%d). Continuing with "
- "caps = 0\n", port, err);
- dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
-
- err = mlx4_check_ext_port_caps(dev, port);
- if (err)
- mlx4_warn(dev, "failed to get port %d extended "
- "port capabilities support info (%d)."
- " Assuming not supported\n", port, err);
+ if (!mlx4_is_slave(dev)) {
+ for (port = 1; port <= dev->caps.num_ports; port++) {
+ ib_port_default_caps = 0;
+ err = mlx4_get_port_ib_caps(dev, port,
+ &ib_port_default_caps);
+ if (err)
+ mlx4_warn(dev, "failed to get port %d default "
+ "ib capabilities (%d). Continuing "
+ "with caps = 0\n", port, err);
+ dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
+
+ err = mlx4_check_ext_port_caps(dev, port);
+ if (err)
+ mlx4_warn(dev, "failed to get port %d extended "
+ "port capabilities support info (%d)."
+ " Assuming not supported\n",
+ port, err);
- err = mlx4_SET_PORT(dev, port);
- if (err) {
- mlx4_err(dev, "Failed to set port %d, aborting\n",
- port);
- goto err_mcg_table_free;
+ err = mlx4_SET_PORT(dev, port);
+ if (err) {
+ mlx4_err(dev, "Failed to set port %d, aborting\n",
+ port);
+ goto err_counters_table_free;
+ }
}
}
- mlx4_set_port_mask(dev);
return 0;
-err_mcg_table_free:
- mlx4_cleanup_mcg_table(dev);
-
err_counters_table_free:
mlx4_cleanup_counters_table(dev);
+err_mcg_table_free:
+ mlx4_cleanup_mcg_table(dev);
+
err_qp_table_free:
mlx4_cleanup_qp_table(dev);
int i;
if (msi_x) {
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
+ /* In multifunction mode each function gets 2 msi-X vectors
+ * one for data path completions anf the other for asynch events
+ * or command completions */
+ if (mlx4_is_mfunc(dev)) {
+ nreq = 2;
+ } else {
+ nreq = min_t(int, dev->caps.num_eqs -
+ dev->caps.reserved_eqs, nreq);
+ }
+
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
goto no_msi;
info->dev = dev;
info->port = port;
- mlx4_init_mac_table(dev, &info->mac_table);
- mlx4_init_vlan_table(dev, &info->vlan_table);
- info->base_qpn = dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
+ if (!mlx4_is_slave(dev)) {
+ INIT_RADIX_TREE(&info->mac_tree, GFP_KERNEL);
+ mlx4_init_mac_table(dev, &info->mac_table);
+ mlx4_init_vlan_table(dev, &info->vlan_table);
+ info->base_qpn =
+ dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
(port - 1) * (1 << log_num_mac);
+ }
sprintf(info->dev_name, "mlx4_port%d", port);
info->port_attr.attr.name = info->dev_name;
- info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
+ if (mlx4_is_mfunc(dev))
+ info->port_attr.attr.mode = S_IRUGO;
+ else {
+ info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
+ info->port_attr.store = set_port_type;
+ }
info->port_attr.show = show_port_type;
- info->port_attr.store = set_port_type;
sysfs_attr_init(&info->port_attr.attr);
err = device_create_file(&dev->pdev->dev, &info->port_attr);
kfree(priv->steer);
}
+static int extended_func_num(struct pci_dev *pdev)
+{
+ return PCI_SLOT(pdev->devfn) * 8 + PCI_FUNC(pdev->devfn);
+}
+
+#define MLX4_OWNER_BASE 0x8069c
+#define MLX4_OWNER_SIZE 4
+
+static int mlx4_get_ownership(struct mlx4_dev *dev)
+{
+ void __iomem *owner;
+ u32 ret;
+
+ owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+ MLX4_OWNER_SIZE);
+ if (!owner) {
+ mlx4_err(dev, "Failed to obtain ownership bit\n");
+ return -ENOMEM;
+ }
+
+ ret = readl(owner);
+ iounmap(owner);
+ return (int) !!ret;
+}
+
+static void mlx4_free_ownership(struct mlx4_dev *dev)
+{
+ void __iomem *owner;
+
+ owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+ MLX4_OWNER_SIZE);
+ if (!owner) {
+ mlx4_err(dev, "Failed to obtain ownership bit\n");
+ return;
+ }
+ writel(0, owner);
+ msleep(1000);
+ iounmap(owner);
+}
+
static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct mlx4_priv *priv;
"aborting.\n");
return err;
}
-
+ if (num_vfs > MLX4_MAX_NUM_VF) {
+ printk(KERN_ERR "There are more VF's (%d) than allowed(%d)\n",
+ num_vfs, MLX4_MAX_NUM_VF);
+ return -EINVAL;
+ }
/*
- * Check for BARs. We expect 0: 1MB
+ * Check for BARs.
*/
- if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM) ||
- pci_resource_len(pdev, 0) != 1 << 20) {
- dev_err(&pdev->dev, "Missing DCS, aborting.\n");
+ if (((id == NULL) || !(id->driver_data & MLX4_VF)) &&
+ !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
+ dev_err(&pdev->dev, "Missing DCS, aborting."
+ "(id == 0X%p, id->driver_data: 0x%lx,"
+ " pci_resource_flags(pdev, 0):0x%lx)\n", id,
+ id ? id->driver_data : 0, pci_resource_flags(pdev, 0));
err = -ENODEV;
goto err_disable_pdev;
}
mutex_init(&priv->bf_mutex);
dev->rev_id = pdev->revision;
+ /* Detect if this device is a virtual function */
+ if (id && id->driver_data & MLX4_VF) {
+ /* When acting as pf, we normally skip vfs unless explicitly
+ * requested to probe them. */
+ if (num_vfs && extended_func_num(pdev) > probe_vf) {
+ mlx4_warn(dev, "Skipping virtual function:%d\n",
+ extended_func_num(pdev));
+ err = -ENODEV;
+ goto err_free_dev;
+ }
+ mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
+ dev->flags |= MLX4_FLAG_SLAVE;
+ } else {
+ /* We reset the device and enable SRIOV only for physical
+ * devices. Try to claim ownership on the device;
+ * if already taken, skip -- do not allow multiple PFs */
+ err = mlx4_get_ownership(dev);
+ if (err) {
+ if (err < 0)
+ goto err_free_dev;
+ else {
+ mlx4_warn(dev, "Multiple PFs not yet supported."
+ " Skipping PF.\n");
+ err = -EINVAL;
+ goto err_free_dev;
+ }
+ }
- /*
- * Now reset the HCA before we touch the PCI capabilities or
- * attempt a firmware command, since a boot ROM may have left
- * the HCA in an undefined state.
- */
- err = mlx4_reset(dev);
- if (err) {
- mlx4_err(dev, "Failed to reset HCA, aborting.\n");
- goto err_free_dev;
+ if (num_vfs) {
+ mlx4_warn(dev, "Enabling sriov with:%d vfs\n", num_vfs);
+ err = pci_enable_sriov(pdev, num_vfs);
+ if (err) {
+ mlx4_err(dev, "Failed to enable sriov,"
+ "continuing without sriov enabled"
+ " (err = %d).\n", err);
+ num_vfs = 0;
+ err = 0;
+ } else {
+ mlx4_warn(dev, "Running in master mode\n");
+ dev->flags |= MLX4_FLAG_SRIOV |
+ MLX4_FLAG_MASTER;
+ dev->num_vfs = num_vfs;
+ }
+ }
+
+ /*
+ * Now reset the HCA before we touch the PCI capabilities or
+ * attempt a firmware command, since a boot ROM may have left
+ * the HCA in an undefined state.
+ */
+ err = mlx4_reset(dev);
+ if (err) {
+ mlx4_err(dev, "Failed to reset HCA, aborting.\n");
+ goto err_rel_own;
+ }
}
+slave_start:
if (mlx4_cmd_init(dev)) {
mlx4_err(dev, "Failed to init command interface, aborting.\n");
- goto err_free_dev;
+ goto err_sriov;
+ }
+
+ /* In slave functions, the communication channel must be initialized
+ * before posting commands. Also, init num_slaves before calling
+ * mlx4_init_hca */
+ if (mlx4_is_mfunc(dev)) {
+ if (mlx4_is_master(dev))
+ dev->num_slaves = MLX4_MAX_NUM_SLAVES;
+ else {
+ dev->num_slaves = 0;
+ if (mlx4_multi_func_init(dev)) {
+ mlx4_err(dev, "Failed to init slave mfunc"
+ " interface, aborting.\n");
+ goto err_cmd;
+ }
+ }
}
err = mlx4_init_hca(dev);
- if (err)
- goto err_cmd;
+ if (err) {
+ if (err == -EACCES) {
+ /* Not primary Physical function
+ * Running in slave mode */
+ mlx4_cmd_cleanup(dev);
+ dev->flags |= MLX4_FLAG_SLAVE;
+ dev->flags &= ~MLX4_FLAG_MASTER;
+ goto slave_start;
+ } else
+ goto err_mfunc;
+ }
+
+ /* In master functions, the communication channel must be initialized
+ * after obtaining its address from fw */
+ if (mlx4_is_master(dev)) {
+ if (mlx4_multi_func_init(dev)) {
+ mlx4_err(dev, "Failed to init master mfunc"
+ "interface, aborting.\n");
+ goto err_close;
+ }
+ }
err = mlx4_alloc_eq_table(dev);
if (err)
- goto err_close;
+ goto err_master_mfunc;
priv->msix_ctl.pool_bm = 0;
spin_lock_init(&priv->msix_ctl.pool_lock);
mlx4_enable_msi_x(dev);
-
- err = mlx4_init_steering(dev);
- if (err)
+ if ((mlx4_is_mfunc(dev)) &&
+ !(dev->flags & MLX4_FLAG_MSI_X)) {
+ mlx4_err(dev, "INTx is not supported in multi-function mode."
+ " aborting.\n");
goto err_free_eq;
+ }
+
+ if (!mlx4_is_slave(dev)) {
+ err = mlx4_init_steering(dev);
+ if (err)
+ goto err_free_eq;
+ }
err = mlx4_setup_hca(dev);
- if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X)) {
+ if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X) &&
+ !mlx4_is_mfunc(dev)) {
dev->flags &= ~MLX4_FLAG_MSI_X;
pci_disable_msix(pdev);
err = mlx4_setup_hca(dev);
mlx4_cleanup_uar_table(dev);
err_steer:
- mlx4_clear_steering(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_clear_steering(dev);
err_free_eq:
mlx4_free_eq_table(dev);
+err_master_mfunc:
+ if (mlx4_is_master(dev))
+ mlx4_multi_func_cleanup(dev);
+
err_close:
if (dev->flags & MLX4_FLAG_MSI_X)
pci_disable_msix(pdev);
mlx4_close_hca(dev);
+err_mfunc:
+ if (mlx4_is_slave(dev))
+ mlx4_multi_func_cleanup(dev);
+
err_cmd:
mlx4_cmd_cleanup(dev);
+err_sriov:
+ if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV))
+ pci_disable_sriov(pdev);
+
+err_rel_own:
+ if (!mlx4_is_slave(dev))
+ mlx4_free_ownership(dev);
+
err_free_dev:
kfree(priv);
int p;
if (dev) {
+ /* in SRIOV it is not allowed to unload the pf's
+ * driver while there are alive vf's */
+ if (mlx4_is_master(dev)) {
+ if (mlx4_how_many_lives_vf(dev))
+ printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+ }
mlx4_stop_sense(dev);
mlx4_unregister_device(dev);
mlx4_cleanup_xrcd_table(dev);
mlx4_cleanup_pd_table(dev);
+ if (mlx4_is_master(dev))
+ mlx4_free_resource_tracker(dev);
+
iounmap(priv->kar);
mlx4_uar_free(dev, &priv->driver_uar);
mlx4_cleanup_uar_table(dev);
- mlx4_clear_steering(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_clear_steering(dev);
mlx4_free_eq_table(dev);
+ if (mlx4_is_master(dev))
+ mlx4_multi_func_cleanup(dev);
mlx4_close_hca(dev);
+ if (mlx4_is_slave(dev))
+ mlx4_multi_func_cleanup(dev);
mlx4_cmd_cleanup(dev);
if (dev->flags & MLX4_FLAG_MSI_X)
pci_disable_msix(pdev);
+ if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV)) {
+ mlx4_warn(dev, "Disabling sriov\n");
+ pci_disable_sriov(pdev);
+ }
+ if (!mlx4_is_slave(dev))
+ mlx4_free_ownership(dev);
kfree(priv);
pci_release_regions(pdev);
pci_disable_device(pdev);
}
static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = {
- { PCI_VDEVICE(MELLANOX, 0x6340) }, /* MT25408 "Hermon" SDR */
- { PCI_VDEVICE(MELLANOX, 0x634a) }, /* MT25408 "Hermon" DDR */
- { PCI_VDEVICE(MELLANOX, 0x6354) }, /* MT25408 "Hermon" QDR */
- { PCI_VDEVICE(MELLANOX, 0x6732) }, /* MT25408 "Hermon" DDR PCIe gen2 */
- { PCI_VDEVICE(MELLANOX, 0x673c) }, /* MT25408 "Hermon" QDR PCIe gen2 */
- { PCI_VDEVICE(MELLANOX, 0x6368) }, /* MT25408 "Hermon" EN 10GigE */
- { PCI_VDEVICE(MELLANOX, 0x6750) }, /* MT25408 "Hermon" EN 10GigE PCIe gen2 */
- { PCI_VDEVICE(MELLANOX, 0x6372) }, /* MT25458 ConnectX EN 10GBASE-T 10GigE */
- { PCI_VDEVICE(MELLANOX, 0x675a) }, /* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
- { PCI_VDEVICE(MELLANOX, 0x6764) }, /* MT26468 ConnectX EN 10GigE PCIe gen2*/
- { PCI_VDEVICE(MELLANOX, 0x6746) }, /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
- { PCI_VDEVICE(MELLANOX, 0x676e) }, /* MT26478 ConnectX2 40GigE PCIe gen2 */
- { PCI_VDEVICE(MELLANOX, 0x1002) }, /* MT25400 Family [ConnectX-2 Virtual Function] */
- { PCI_VDEVICE(MELLANOX, 0x1003) }, /* MT27500 Family [ConnectX-3] */
- { PCI_VDEVICE(MELLANOX, 0x1004) }, /* MT27500 Family [ConnectX-3 Virtual Function] */
- { PCI_VDEVICE(MELLANOX, 0x1005) }, /* MT27510 Family */
- { PCI_VDEVICE(MELLANOX, 0x1006) }, /* MT27511 Family */
- { PCI_VDEVICE(MELLANOX, 0x1007) }, /* MT27520 Family */
- { PCI_VDEVICE(MELLANOX, 0x1008) }, /* MT27521 Family */
- { PCI_VDEVICE(MELLANOX, 0x1009) }, /* MT27530 Family */
- { PCI_VDEVICE(MELLANOX, 0x100a) }, /* MT27531 Family */
- { PCI_VDEVICE(MELLANOX, 0x100b) }, /* MT27540 Family */
- { PCI_VDEVICE(MELLANOX, 0x100c) }, /* MT27541 Family */
- { PCI_VDEVICE(MELLANOX, 0x100d) }, /* MT27550 Family */
- { PCI_VDEVICE(MELLANOX, 0x100e) }, /* MT27551 Family */
- { PCI_VDEVICE(MELLANOX, 0x100f) }, /* MT27560 Family */
- { PCI_VDEVICE(MELLANOX, 0x1010) }, /* MT27561 Family */
+ /* MT25408 "Hermon" SDR */
+ { PCI_VDEVICE(MELLANOX, 0x6340), 0 },
+ /* MT25408 "Hermon" DDR */
+ { PCI_VDEVICE(MELLANOX, 0x634a), 0 },
+ /* MT25408 "Hermon" QDR */
+ { PCI_VDEVICE(MELLANOX, 0x6354), 0 },
+ /* MT25408 "Hermon" DDR PCIe gen2 */
+ { PCI_VDEVICE(MELLANOX, 0x6732), 0 },
+ /* MT25408 "Hermon" QDR PCIe gen2 */
+ { PCI_VDEVICE(MELLANOX, 0x673c), 0 },
+ /* MT25408 "Hermon" EN 10GigE */
+ { PCI_VDEVICE(MELLANOX, 0x6368), 0 },
+ /* MT25408 "Hermon" EN 10GigE PCIe gen2 */
+ { PCI_VDEVICE(MELLANOX, 0x6750), 0 },
+ /* MT25458 ConnectX EN 10GBASE-T 10GigE */
+ { PCI_VDEVICE(MELLANOX, 0x6372), 0 },
+ /* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
+ { PCI_VDEVICE(MELLANOX, 0x675a), 0 },
+ /* MT26468 ConnectX EN 10GigE PCIe gen2*/
+ { PCI_VDEVICE(MELLANOX, 0x6764), 0 },
+ /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
+ { PCI_VDEVICE(MELLANOX, 0x6746), 0 },
+ /* MT26478 ConnectX2 40GigE PCIe gen2 */
+ { PCI_VDEVICE(MELLANOX, 0x676e), 0 },
+ /* MT25400 Family [ConnectX-2 Virtual Function] */
+ { PCI_VDEVICE(MELLANOX, 0x1002), MLX4_VF },
+ /* MT27500 Family [ConnectX-3] */
+ { PCI_VDEVICE(MELLANOX, 0x1003), 0 },
+ /* MT27500 Family [ConnectX-3 Virtual Function] */
+ { PCI_VDEVICE(MELLANOX, 0x1004), MLX4_VF },
+ { PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */
+ { PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */
+ { PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */
+ { PCI_VDEVICE(MELLANOX, 0x1008), 0 }, /* MT27521 Family */
+ { PCI_VDEVICE(MELLANOX, 0x1009), 0 }, /* MT27530 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100a), 0 }, /* MT27531 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100b), 0 }, /* MT27540 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100c), 0 }, /* MT27541 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100d), 0 }, /* MT27550 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100e), 0 }, /* MT27551 Family */
+ { PCI_VDEVICE(MELLANOX, 0x100f), 0 }, /* MT27560 Family */
+ { PCI_VDEVICE(MELLANOX, 0x1010), 0 }, /* MT27561 Family */
{ 0, }
};
return -1;
}
+ /* Check if module param for ports type has legal combination */
+ if (port_type_array[0] == false && port_type_array[1] == true) {
+ printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
+ port_type_array[0] = true;
+ }
+
return 0;
}
static const u8 zero_gid[16]; /* automatically initialized to 0 */
+struct mlx4_mgm {
+ __be32 next_gid_index;
+ __be32 members_count;
+ u32 reserved[2];
+ u8 gid[16];
+ __be32 qp[MLX4_MAX_QP_PER_MGM];
+};
+
+int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
+{
+ return min((1 << mlx4_log_num_mgm_entry_size), MLX4_MAX_MGM_ENTRY_SIZE);
+}
+
+int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
+{
+ return 4 * (mlx4_get_mgm_entry_size(dev) / 16 - 2);
+}
+
static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
struct mlx4_cmd_mailbox *mailbox)
{
return mlx4_cmd_box(dev, 0, mailbox->dma, index, 0, MLX4_CMD_READ_MCG,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
}
static int mlx4_WRITE_ENTRY(struct mlx4_dev *dev, int index,
struct mlx4_cmd_mailbox *mailbox)
{
return mlx4_cmd(dev, mailbox->dma, index, 0, MLX4_CMD_WRITE_MCG,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
}
-static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 vep_num, u8 port, u8 steer,
+static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 port, u8 steer,
struct mlx4_cmd_mailbox *mailbox)
{
u32 in_mod;
- in_mod = (u32) vep_num << 24 | (u32) port << 16 | steer << 1;
+ in_mod = (u32) port << 16 | steer << 1;
return mlx4_cmd(dev, mailbox->dma, in_mod, 0x1,
- MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
}
static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int err;
err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, op_mod,
- MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
if (!err)
*hash = imm;
* Add new entry to steering data structure.
* All promisc QPs should be added as well
*/
-static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int new_steering_entry(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer,
unsigned int index, u32 qpn)
{
struct mlx4_promisc_qp *dqp = NULL;
u32 prot;
int err;
- u8 pf_num;
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+ s_steer = &mlx4_priv(dev)->steer[0];
new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
if (!new_entry)
return -ENOMEM;
/* If the given qpn is also a promisc qp,
* it should be inserted to duplicates list
*/
- pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+ pqp = get_promisc_qp(dev, 0, steer, qpn);
if (pqp) {
dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
if (!dqp) {
/* don't add already existing qpn */
if (pqp->qpn == qpn)
continue;
- if (members_count == MLX4_QP_PER_MGM) {
+ if (members_count == dev->caps.num_qp_per_mgm) {
/* out of space */
err = -ENOMEM;
goto out_mailbox;
}
/* update the data structures with existing steering entry */
-static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int existing_steering_entry(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer,
unsigned int index, u32 qpn)
{
struct mlx4_steer_index *tmp_entry, *entry = NULL;
struct mlx4_promisc_qp *pqp;
struct mlx4_promisc_qp *dqp;
- u8 pf_num;
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+ s_steer = &mlx4_priv(dev)->steer[0];
- pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+ pqp = get_promisc_qp(dev, 0, steer, qpn);
if (!pqp)
return 0; /* nothing to do */
* we need to add it as a duplicate to this entry
* for future references */
list_for_each_entry(dqp, &entry->duplicates, list) {
- if (qpn == dqp->qpn)
+ if (qpn == pqp->qpn)
return 0; /* qp is already duplicated */
}
/* Check whether a qpn is a duplicate on steering entry
* If so, it should not be removed from mgm */
-static bool check_duplicate_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static bool check_duplicate_entry(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer,
unsigned int index, u32 qpn)
{
struct mlx4_steer *s_steer;
struct mlx4_steer_index *tmp_entry, *entry = NULL;
struct mlx4_promisc_qp *dqp, *tmp_dqp;
- u8 pf_num;
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+ s_steer = &mlx4_priv(dev)->steer[0];
/* if qp is not promisc, it cannot be duplicated */
- if (!get_promisc_qp(dev, pf_num, steer, qpn))
+ if (!get_promisc_qp(dev, 0, steer, qpn))
return false;
/* The qp is promisc qp so it is a duplicate on this index
}
/* I a steering entry contains only promisc QPs, it can be removed. */
-static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer,
unsigned int index, u32 tqpn)
{
u32 members_count;
bool ret = false;
int i;
- u8 pf_num;
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+ s_steer = &mlx4_priv(dev)->steer[0];
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
for (i = 0; i < members_count; i++) {
qpn = be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK;
- if (!get_promisc_qp(dev, pf_num, steer, qpn) && qpn != tqpn) {
+ if (!get_promisc_qp(dev, 0, steer, qpn) && qpn != tqpn) {
/* the qp is not promisc, the entry can't be removed */
goto out;
}
return ret;
}
-static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int add_promisc_qp(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer, u32 qpn)
{
struct mlx4_steer *s_steer;
bool found;
int last_index;
int err;
- u8 pf_num;
struct mlx4_priv *priv = mlx4_priv(dev);
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+ s_steer = &mlx4_priv(dev)->steer[0];
mutex_lock(&priv->mcg_table.mutex);
- if (get_promisc_qp(dev, pf_num, steer, qpn)) {
+ if (get_promisc_qp(dev, 0, steer, qpn)) {
err = 0; /* Noting to do, already exists */
goto out_mutex;
}
}
if (!found) {
/* Need to add the qpn to mgm */
- if (members_count == MLX4_QP_PER_MGM) {
+ if (members_count == dev->caps.num_qp_per_mgm) {
/* entry is full */
err = -ENOMEM;
goto out_mailbox;
mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
- err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+ err = mlx4_WRITE_PROMISC(dev, port, steer, mailbox);
if (err)
goto out_list;
return err;
}
-static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
enum mlx4_steer_type steer, u32 qpn)
{
struct mlx4_priv *priv = mlx4_priv(dev);
bool back_to_list = false;
int loc, i;
int err;
- u8 pf_num;
- pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
- s_steer = &mlx4_priv(dev)->steer[pf_num];
+ s_steer = &mlx4_priv(dev)->steer[0];
mutex_lock(&priv->mcg_table.mutex);
- pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+ pqp = get_promisc_qp(dev, 0, steer, qpn);
if (unlikely(!pqp)) {
mlx4_warn(dev, "QP %x is not promiscuous QP\n", qpn);
/* nothing to do */
goto out_list;
}
mgm = mailbox->buf;
+ memset(mgm, 0, sizeof *mgm);
members_count = 0;
list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
- err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+ err = mlx4_WRITE_PROMISC(dev, port, steer, mailbox);
if (err)
goto out_mailbox;
}
index += dev->caps.num_mgms;
+ new_entry = 1;
memset(mgm, 0, sizeof *mgm);
memcpy(mgm->gid, gid, 16);
}
members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
- if (members_count == MLX4_QP_PER_MGM) {
+ if (members_count == dev->caps.num_qp_per_mgm) {
mlx4_err(dev, "MGM at index %x is full.\n", index);
err = -ENOMEM;
goto out;
if (prot == MLX4_PROT_ETH) {
/* manage the steering entry for promisc mode */
if (new_entry)
- new_steering_entry(dev, 0, port, steer, index, qp->qpn);
+ new_steering_entry(dev, port, steer, index, qp->qpn);
else
- existing_steering_entry(dev, 0, port, steer,
+ existing_steering_entry(dev, port, steer,
index, qp->qpn);
}
if (err && link && index != -1) {
/* if this pq is also a promisc qp, it shouldn't be removed */
if (prot == MLX4_PROT_ETH &&
- check_duplicate_entry(dev, 0, port, steer, index, qp->qpn))
+ check_duplicate_entry(dev, port, steer, index, qp->qpn))
goto out;
members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
mgm->qp[i - 1] = 0;
if (prot == MLX4_PROT_ETH)
- removed_entry = can_remove_steering_entry(dev, 0, port, steer, index, qp->qpn);
+ removed_entry = can_remove_steering_entry(dev, port, steer,
+ index, qp->qpn);
if (i != 1 && (prot != MLX4_PROT_ETH || !removed_entry)) {
err = mlx4_WRITE_ENTRY(dev, index, mailbox);
goto out;
return err;
}
+static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp,
+ u8 gid[16], u8 attach, u8 block_loopback,
+ enum mlx4_protocol prot)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ int err = 0;
+ int qpn;
+
+ if (!mlx4_is_mfunc(dev))
+ return -EBADF;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+
+ memcpy(mailbox->buf, gid, 16);
+ qpn = qp->qpn;
+ qpn |= (prot << 28);
+ if (attach && block_loopback)
+ qpn |= (1 << 31);
+
+ err = mlx4_cmd(dev, mailbox->dma, qpn, attach,
+ MLX4_CMD_QP_ATTACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot)
if (prot == MLX4_PROT_ETH)
gid[7] |= (steer << 1);
- return mlx4_qp_attach_common(dev, qp, gid,
- block_mcast_loopback, prot,
- steer);
+ if (mlx4_is_mfunc(dev))
+ return mlx4_QP_ATTACH(dev, qp, gid, 1,
+ block_mcast_loopback, prot);
+
+ return mlx4_qp_attach_common(dev, qp, gid, block_mcast_loopback,
+ prot, steer);
}
EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
return 0;
- if (prot == MLX4_PROT_ETH) {
+ if (prot == MLX4_PROT_ETH)
gid[7] |= (steer << 1);
- }
+
+ if (mlx4_is_mfunc(dev))
+ return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot);
return mlx4_qp_detach_common(dev, qp, gid, prot, steer);
}
EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
+int mlx4_unicast_attach(struct mlx4_dev *dev,
+ struct mlx4_qp *qp, u8 gid[16],
+ int block_mcast_loopback, enum mlx4_protocol prot)
+{
+ if (prot == MLX4_PROT_ETH &&
+ !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
+ return 0;
+
+ if (prot == MLX4_PROT_ETH)
+ gid[7] |= (MLX4_UC_STEER << 1);
+
+ if (mlx4_is_mfunc(dev))
+ return mlx4_QP_ATTACH(dev, qp, gid, 1,
+ block_mcast_loopback, prot);
+
+ return mlx4_qp_attach_common(dev, qp, gid, block_mcast_loopback,
+ prot, MLX4_UC_STEER);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_attach);
+
+int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp,
+ u8 gid[16], enum mlx4_protocol prot)
+{
+ if (prot == MLX4_PROT_ETH &&
+ !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
+ return 0;
+
+ if (prot == MLX4_PROT_ETH)
+ gid[7] |= (MLX4_UC_STEER << 1);
+
+ if (mlx4_is_mfunc(dev))
+ return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot);
+
+ return mlx4_qp_detach_common(dev, qp, gid, prot, MLX4_UC_STEER);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_detach);
+
+int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ u32 qpn = (u32) vhcr->in_param & 0xffffffff;
+ u8 port = vhcr->in_param >> 62;
+ enum mlx4_steer_type steer = vhcr->in_modifier;
+
+ /* Promiscuous unicast is not allowed in mfunc */
+ if (mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)
+ return 0;
+
+ if (vhcr->op_modifier)
+ return add_promisc_qp(dev, port, steer, qpn);
+ else
+ return remove_promisc_qp(dev, port, steer, qpn);
+}
+
+static int mlx4_PROMISC(struct mlx4_dev *dev, u32 qpn,
+ enum mlx4_steer_type steer, u8 add, u8 port)
+{
+ return mlx4_cmd(dev, (u64) qpn | (u64) port << 62, (u32) steer, add,
+ MLX4_CMD_PROMISC, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+}
int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
{
if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
return 0;
+ if (mlx4_is_mfunc(dev))
+ return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 1, port);
- return add_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+ return add_promisc_qp(dev, port, MLX4_MC_STEER, qpn);
}
EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_add);
if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
return 0;
+ if (mlx4_is_mfunc(dev))
+ return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 0, port);
- return remove_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+ return remove_promisc_qp(dev, port, MLX4_MC_STEER, qpn);
}
EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_remove);
if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
return 0;
+ if (mlx4_is_mfunc(dev))
+ return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 1, port);
- return add_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+ return add_promisc_qp(dev, port, MLX4_UC_STEER, qpn);
}
EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_add);
if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
return 0;
- return remove_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+ if (mlx4_is_mfunc(dev))
+ return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 0, port);
+
+ return remove_promisc_qp(dev, port, MLX4_UC_STEER, qpn);
}
EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_remove);
#include <linux/mlx4/device.h>
#include <linux/mlx4/driver.h>
#include <linux/mlx4/doorbell.h>
+#include <linux/mlx4/cmd.h>
#define DRV_NAME "mlx4_core"
-#define DRV_VERSION "1.0"
-#define DRV_RELDATE "July 14, 2011"
+#define PFX DRV_NAME ": "
+#define DRV_VERSION "1.1"
+#define DRV_RELDATE "Dec, 2011"
enum {
MLX4_HCR_BASE = 0x80680,
MLX4_HCR_SIZE = 0x0001c,
- MLX4_CLR_INT_SIZE = 0x00008
+ MLX4_CLR_INT_SIZE = 0x00008,
+ MLX4_SLAVE_COMM_BASE = 0x0,
+ MLX4_COMM_PAGESIZE = 0x1000
};
enum {
- MLX4_MGM_ENTRY_SIZE = 0x100,
- MLX4_QP_PER_MGM = 4 * (MLX4_MGM_ENTRY_SIZE / 16 - 2),
- MLX4_MTT_ENTRY_PER_SEG = 8
+ MLX4_MAX_MGM_ENTRY_SIZE = 0x1000,
+ MLX4_MAX_QP_PER_MGM = 4 * (MLX4_MAX_MGM_ENTRY_SIZE / 16 - 2),
+ MLX4_MTT_ENTRY_PER_SEG = 8,
};
enum {
MLX4_NUM_CMPTS = MLX4_CMPT_NUM_TYPE << MLX4_CMPT_SHIFT
};
+enum mlx4_mr_state {
+ MLX4_MR_DISABLED = 0,
+ MLX4_MR_EN_HW,
+ MLX4_MR_EN_SW
+};
+
+#define MLX4_COMM_TIME 10000
+enum {
+ MLX4_COMM_CMD_RESET,
+ MLX4_COMM_CMD_VHCR0,
+ MLX4_COMM_CMD_VHCR1,
+ MLX4_COMM_CMD_VHCR2,
+ MLX4_COMM_CMD_VHCR_EN,
+ MLX4_COMM_CMD_VHCR_POST,
+ MLX4_COMM_CMD_FLR = 254
+};
+
+/*The flag indicates that the slave should delay the RESET cmd*/
+#define MLX4_DELAY_RESET_SLAVE 0xbbbbbbb
+/*indicates how many retries will be done if we are in the middle of FLR*/
+#define NUM_OF_RESET_RETRIES 10
+#define SLEEP_TIME_IN_RESET (2 * 1000)
+enum mlx4_resource {
+ RES_QP,
+ RES_CQ,
+ RES_SRQ,
+ RES_XRCD,
+ RES_MPT,
+ RES_MTT,
+ RES_MAC,
+ RES_VLAN,
+ RES_EQ,
+ RES_COUNTER,
+ MLX4_NUM_OF_RESOURCE_TYPE
+};
+
+enum mlx4_alloc_mode {
+ RES_OP_RESERVE,
+ RES_OP_RESERVE_AND_MAP,
+ RES_OP_MAP_ICM,
+};
+
+
+/*
+ *Virtual HCR structures.
+ * mlx4_vhcr is the sw representation, in machine endianess
+ *
+ * mlx4_vhcr_cmd is the formalized structure, the one that is passed
+ * to FW to go through communication channel.
+ * It is big endian, and has the same structure as the physical HCR
+ * used by command interface
+ */
+struct mlx4_vhcr {
+ u64 in_param;
+ u64 out_param;
+ u32 in_modifier;
+ u32 errno;
+ u16 op;
+ u16 token;
+ u8 op_modifier;
+ u8 e_bit;
+};
+
+struct mlx4_vhcr_cmd {
+ __be64 in_param;
+ __be32 in_modifier;
+ __be64 out_param;
+ __be16 token;
+ u16 reserved;
+ u8 status;
+ u8 flags;
+ __be16 opcode;
+};
+
+struct mlx4_cmd_info {
+ u16 opcode;
+ bool has_inbox;
+ bool has_outbox;
+ bool out_is_imm;
+ bool encode_slave_id;
+ int (*verify)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox);
+ int (*wrapper)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+};
+
#ifdef CONFIG_MLX4_DEBUG
extern int mlx4_debug_level;
#else /* CONFIG_MLX4_DEBUG */
#define mlx4_warn(mdev, format, arg...) \
dev_warn(&mdev->pdev->dev, format, ##arg)
+extern int mlx4_log_num_mgm_entry_size;
+extern int log_mtts_per_seg;
+
+#define MLX4_MAX_NUM_SLAVES (MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
+#define ALL_SLAVES 0xff
+
struct mlx4_bitmap {
u32 last;
u32 top;
struct mlx4_icm **icm;
};
+/*
+ * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
+ */
+struct mlx4_mpt_entry {
+ __be32 flags;
+ __be32 qpn;
+ __be32 key;
+ __be32 pd_flags;
+ __be64 start;
+ __be64 length;
+ __be32 lkey;
+ __be32 win_cnt;
+ u8 reserved1[3];
+ u8 mtt_rep;
+ __be64 mtt_addr;
+ __be32 mtt_sz;
+ __be32 entity_size;
+ __be32 first_byte_offset;
+} __packed;
+
+/*
+ * Must be packed because start is 64 bits but only aligned to 32 bits.
+ */
+struct mlx4_eq_context {
+ __be32 flags;
+ u16 reserved1[3];
+ __be16 page_offset;
+ u8 log_eq_size;
+ u8 reserved2[4];
+ u8 eq_period;
+ u8 reserved3;
+ u8 eq_max_count;
+ u8 reserved4[3];
+ u8 intr;
+ u8 log_page_size;
+ u8 reserved5[2];
+ u8 mtt_base_addr_h;
+ __be32 mtt_base_addr_l;
+ u32 reserved6[2];
+ __be32 consumer_index;
+ __be32 producer_index;
+ u32 reserved7[4];
+};
+
+struct mlx4_cq_context {
+ __be32 flags;
+ u16 reserved1[3];
+ __be16 page_offset;
+ __be32 logsize_usrpage;
+ __be16 cq_period;
+ __be16 cq_max_count;
+ u8 reserved2[3];
+ u8 comp_eqn;
+ u8 log_page_size;
+ u8 reserved3[2];
+ u8 mtt_base_addr_h;
+ __be32 mtt_base_addr_l;
+ __be32 last_notified_index;
+ __be32 solicit_producer_index;
+ __be32 consumer_index;
+ __be32 producer_index;
+ u32 reserved4[2];
+ __be64 db_rec_addr;
+};
+
+struct mlx4_srq_context {
+ __be32 state_logsize_srqn;
+ u8 logstride;
+ u8 reserved1;
+ __be16 xrcd;
+ __be32 pg_offset_cqn;
+ u32 reserved2;
+ u8 log_page_size;
+ u8 reserved3[2];
+ u8 mtt_base_addr_h;
+ __be32 mtt_base_addr_l;
+ __be32 pd;
+ __be16 limit_watermark;
+ __be16 wqe_cnt;
+ u16 reserved4;
+ __be16 wqe_counter;
+ u32 reserved5;
+ __be64 db_rec_addr;
+};
+
+struct mlx4_eqe {
+ u8 reserved1;
+ u8 type;
+ u8 reserved2;
+ u8 subtype;
+ union {
+ u32 raw[6];
+ struct {
+ __be32 cqn;
+ } __packed comp;
+ struct {
+ u16 reserved1;
+ __be16 token;
+ u32 reserved2;
+ u8 reserved3[3];
+ u8 status;
+ __be64 out_param;
+ } __packed cmd;
+ struct {
+ __be32 qpn;
+ } __packed qp;
+ struct {
+ __be32 srqn;
+ } __packed srq;
+ struct {
+ __be32 cqn;
+ u32 reserved1;
+ u8 reserved2[3];
+ u8 syndrome;
+ } __packed cq_err;
+ struct {
+ u32 reserved1[2];
+ __be32 port;
+ } __packed port_change;
+ struct {
+ #define COMM_CHANNEL_BIT_ARRAY_SIZE 4
+ u32 reserved;
+ u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
+ } __packed comm_channel_arm;
+ struct {
+ u8 port;
+ u8 reserved[3];
+ __be64 mac;
+ } __packed mac_update;
+ struct {
+ u8 port;
+ } __packed sw_event;
+ struct {
+ __be32 slave_id;
+ } __packed flr_event;
+ } event;
+ u8 slave_id;
+ u8 reserved3[2];
+ u8 owner;
+} __packed;
+
struct mlx4_eq {
struct mlx4_dev *dev;
void __iomem *doorbell;
struct mlx4_mtt mtt;
};
+struct mlx4_slave_eqe {
+ u8 type;
+ u8 port;
+ u32 param;
+};
+
+struct mlx4_slave_event_eq_info {
+ u32 eqn;
+ u16 token;
+ u64 event_type;
+};
+
struct mlx4_profile {
int num_qp;
int rdmarc_per_qp;
struct mlx4_fw {
u64 clr_int_base;
u64 catas_offset;
+ u64 comm_base;
struct mlx4_icm *fw_icm;
struct mlx4_icm *aux_icm;
u32 catas_size;
u16 fw_pages;
u8 clr_int_bar;
u8 catas_bar;
+ u8 comm_bar;
};
-#define MGM_QPN_MASK 0x00FFFFFF
-#define MGM_BLCK_LB_BIT 30
+struct mlx4_comm {
+ u32 slave_write;
+ u32 slave_read;
+};
+
+enum {
+ MLX4_MCAST_CONFIG = 0,
+ MLX4_MCAST_DISABLE = 1,
+ MLX4_MCAST_ENABLE = 2,
+};
+
+#define VLAN_FLTR_SIZE 128
+
+struct mlx4_vlan_fltr {
+ __be32 entry[VLAN_FLTR_SIZE];
+};
+
+struct mlx4_mcast_entry {
+ struct list_head list;
+ u64 addr;
+};
struct mlx4_promisc_qp {
struct list_head list;
struct list_head duplicates;
};
-struct mlx4_mgm {
- __be32 next_gid_index;
- __be32 members_count;
- u32 reserved[2];
- u8 gid[16];
- __be32 qp[MLX4_QP_PER_MGM];
+struct mlx4_slave_state {
+ u8 comm_toggle;
+ u8 last_cmd;
+ u8 init_port_mask;
+ bool active;
+ u8 function;
+ dma_addr_t vhcr_dma;
+ u16 mtu[MLX4_MAX_PORTS + 1];
+ __be32 ib_cap_mask[MLX4_MAX_PORTS + 1];
+ struct mlx4_slave_eqe eq[MLX4_MFUNC_MAX_EQES];
+ struct list_head mcast_filters[MLX4_MAX_PORTS + 1];
+ struct mlx4_vlan_fltr *vlan_filter[MLX4_MAX_PORTS + 1];
+ struct mlx4_slave_event_eq_info event_eq;
+ u16 eq_pi;
+ u16 eq_ci;
+ spinlock_t lock;
+ /*initialized via the kzalloc*/
+ u8 is_slave_going_down;
+ u32 cookie;
+};
+
+struct slave_list {
+ struct mutex mutex;
+ struct list_head res_list[MLX4_NUM_OF_RESOURCE_TYPE];
+};
+
+struct mlx4_resource_tracker {
+ spinlock_t lock;
+ /* tree for each resources */
+ struct radix_tree_root res_tree[MLX4_NUM_OF_RESOURCE_TYPE];
+ /* num_of_slave's lists, one per slave */
+ struct slave_list *slave_list;
+};
+
+#define SLAVE_EVENT_EQ_SIZE 128
+struct mlx4_slave_event_eq {
+ u32 eqn;
+ u32 cons;
+ u32 prod;
+ struct mlx4_eqe event_eqe[SLAVE_EVENT_EQ_SIZE];
+};
+
+struct mlx4_master_qp0_state {
+ int proxy_qp0_active;
+ int qp0_active;
+ int port_active;
+};
+
+struct mlx4_mfunc_master_ctx {
+ struct mlx4_slave_state *slave_state;
+ struct mlx4_master_qp0_state qp0_state[MLX4_MAX_PORTS + 1];
+ int init_port_ref[MLX4_MAX_PORTS + 1];
+ u16 max_mtu[MLX4_MAX_PORTS + 1];
+ int disable_mcast_ref[MLX4_MAX_PORTS + 1];
+ struct mlx4_resource_tracker res_tracker;
+ struct workqueue_struct *comm_wq;
+ struct work_struct comm_work;
+ struct work_struct slave_event_work;
+ struct work_struct slave_flr_event_work;
+ spinlock_t slave_state_lock;
+ __be32 comm_arm_bit_vector[4];
+ struct mlx4_eqe cmd_eqe;
+ struct mlx4_slave_event_eq slave_eq;
+ struct mutex gen_eqe_mutex[MLX4_MFUNC_MAX];
+};
+
+struct mlx4_mfunc {
+ struct mlx4_comm __iomem *comm;
+ struct mlx4_vhcr_cmd *vhcr;
+ dma_addr_t vhcr_dma;
+
+ struct mlx4_mfunc_master_ctx master;
};
+
struct mlx4_cmd {
struct pci_pool *pool;
void __iomem *hcr;
struct mutex hcr_mutex;
struct semaphore poll_sem;
struct semaphore event_sem;
+ struct semaphore slave_sem;
int max_cmds;
spinlock_t context_lock;
int free_head;
u16 token_mask;
u8 use_events;
u8 toggle;
+ u8 comm_toggle;
};
struct mlx4_uar_table {
int max;
};
+#define SET_PORT_GEN_ALL_VALID 0x7
+#define SET_PORT_PROMISC_SHIFT 31
+#define SET_PORT_MC_PROMISC_SHIFT 30
+
+enum {
+ MCAST_DIRECT_ONLY = 0,
+ MCAST_DIRECT = 1,
+ MCAST_DEFAULT = 2
+};
+
+
+struct mlx4_set_port_general_context {
+ u8 reserved[3];
+ u8 flags;
+ u16 reserved2;
+ __be16 mtu;
+ u8 pptx;
+ u8 pfctx;
+ u16 reserved3;
+ u8 pprx;
+ u8 pfcrx;
+ u16 reserved4;
+};
+
+struct mlx4_set_port_rqp_calc_context {
+ __be32 base_qpn;
+ u8 rererved;
+ u8 n_mac;
+ u8 n_vlan;
+ u8 n_prio;
+ u8 reserved2[3];
+ u8 mac_miss;
+ u8 intra_no_vlan;
+ u8 no_vlan;
+ u8 intra_vlan_miss;
+ u8 vlan_miss;
+ u8 reserved3[3];
+ u8 no_vlan_prio;
+ __be32 promisc;
+ __be32 mcast;
+};
+
struct mlx4_mac_entry {
u64 mac;
};
struct mlx4_fw fw;
struct mlx4_cmd cmd;
+ struct mlx4_mfunc mfunc;
struct mlx4_bitmap pd_bitmap;
struct mlx4_bitmap xrcd_bitmap;
struct list_head bf_list;
struct mutex bf_mutex;
struct io_mapping *bf_mapping;
+ int reserved_mtts;
};
static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn);
+void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn);
+int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
+void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
+int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
+void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
+int __mlx4_mr_reserve(struct mlx4_dev *dev);
+void __mlx4_mr_release(struct mlx4_dev *dev, u32 index);
+int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index);
+void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index);
+u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
+void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
+
+int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SYNC_TPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+ int *base);
+void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
+int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
+int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ int start_index, int npages, u64 *page_list);
void mlx4_start_catas_poll(struct mlx4_dev *dev);
void mlx4_stop_catas_poll(struct mlx4_dev *dev);
struct mlx4_profile *request,
struct mlx4_dev_cap *dev_cap,
struct mlx4_init_hca_param *init_hca);
+void mlx4_master_comm_channel(struct work_struct *work);
+void mlx4_gen_slave_eqe(struct work_struct *work);
+void mlx4_master_handle_slave_flr(struct work_struct *work);
+
+int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_MAP_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_COMM_INT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_MODIFY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_ARM_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_GEN_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+
+int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe);
int mlx4_cmd_init(struct mlx4_dev *dev);
void mlx4_cmd_cleanup(struct mlx4_dev *dev);
+int mlx4_multi_func_init(struct mlx4_dev *dev);
+void mlx4_multi_func_cleanup(struct mlx4_dev *dev);
void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param);
int mlx4_cmd_use_events(struct mlx4_dev *dev);
void mlx4_cmd_use_polling(struct mlx4_dev *dev);
+int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
+ unsigned long timeout);
+
void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
+/* resource tracker functions*/
+int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
+ enum mlx4_resource resource_type,
+ int resource_id, int *slave);
+void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave_id);
+int mlx4_init_resource_tracker(struct mlx4_dev *dev);
+
+void mlx4_free_resource_tracker(struct mlx4_dev *dev);
+
+int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port);
+
+int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+
+int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
enum mlx4_protocol prot, enum mlx4_steer_type steer);
int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot,
enum mlx4_steer_type steer);
+int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function,
+ int port, void *buf);
+int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, u32 in_mod,
+ struct mlx4_cmd_mailbox *outbox);
+int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_PKEY_TABLE_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+
+int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
+int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
+
+static inline void set_param_l(u64 *arg, u32 val)
+{
+ *((u32 *)arg) = val;
+}
+
+static inline void set_param_h(u64 *arg, u32 val)
+{
+ *arg = (*arg & 0xffffffff) | ((u64) val << 32);
+}
+
+static inline u32 get_param_l(u64 *arg)
+{
+ return (u32) (*arg & 0xffffffff);
+}
+
+static inline u32 get_param_h(u64 *arg)
+{
+ return (u32)(*arg >> 32);
+}
+
+static inline spinlock_t *mlx4_tlock(struct mlx4_dev *dev)
+{
+ return &mlx4_priv(dev)->mfunc.master.res_tracker.lock;
+}
+
+#define NOT_MASKED_PD_BITS 17
+
#endif /* MLX4_H */
#include "en_port.h"
#define DRV_NAME "mlx4_en"
-#define DRV_VERSION "1.5.4.2"
-#define DRV_RELDATE "October 2011"
+#define DRV_VERSION "2.0"
+#define DRV_RELDATE "Dec 2011"
#define MLX4_EN_MSG_LEVEL (NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
u32 prod;
u32 cons;
u32 buf_size;
+ u8 fcs_del;
void *buf;
void *rx_info;
unsigned long bytes;
enum mlx4_qp_state indir_state;
};
-struct mlx4_en_rss_context {
- __be32 base_qpn;
- __be32 default_qpn;
- u16 reserved;
- u8 hash_fn;
- u8 flags;
- __be32 rss_key[10];
- __be32 base_qpn_udp;
-};
-
struct mlx4_en_port_state {
int link_state;
int link_speed;
int base_qpn;
struct mlx4_en_rss_map rss_map;
+ u32 ctrl_flags;
u32 flags;
#define MLX4_EN_FLAG_PROMISC 0x1
#define MLX4_EN_FLAG_MC_PROMISC 0x2
enum mlx4_en_wol {
MLX4_EN_WOL_MAGIC = (1ULL << 61),
MLX4_EN_WOL_ENABLED = (1ULL << 62),
- MLX4_EN_WOL_DO_MODIFY = (1ULL << 63),
};
+#define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
void mlx4_en_destroy_netdev(struct net_device *dev);
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
* SOFTWARE.
*/
+#include <linux/init.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/slab.h>
+#include <linux/kernel.h>
#include <linux/mlx4/cmd.h>
#include "mlx4.h"
#include "icm.h"
-/*
- * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
- */
-struct mlx4_mpt_entry {
- __be32 flags;
- __be32 qpn;
- __be32 key;
- __be32 pd_flags;
- __be64 start;
- __be64 length;
- __be32 lkey;
- __be32 win_cnt;
- u8 reserved1[3];
- u8 mtt_rep;
- __be64 mtt_seg;
- __be32 mtt_sz;
- __be32 entity_size;
- __be32 first_byte_offset;
-} __packed;
-
#define MLX4_MPT_FLAG_SW_OWNS (0xfUL << 28)
#define MLX4_MPT_FLAG_FREE (0x3UL << 28)
#define MLX4_MPT_FLAG_MIO (1 << 17)
kfree(buddy->num_free);
}
-static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
+u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
{
struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
u32 seg;
+ int seg_order;
+ u32 offset;
- seg = mlx4_buddy_alloc(&mr_table->mtt_buddy, order);
+ seg_order = max_t(int, order - log_mtts_per_seg, 0);
+
+ seg = mlx4_buddy_alloc(&mr_table->mtt_buddy, seg_order);
if (seg == -1)
return -1;
- if (mlx4_table_get_range(dev, &mr_table->mtt_table, seg,
- seg + (1 << order) - 1)) {
- mlx4_buddy_free(&mr_table->mtt_buddy, seg, order);
+ offset = seg * (1 << log_mtts_per_seg);
+
+ if (mlx4_table_get_range(dev, &mr_table->mtt_table, offset,
+ offset + (1 << order) - 1)) {
+ mlx4_buddy_free(&mr_table->mtt_buddy, seg, seg_order);
return -1;
}
- return seg;
+ return offset;
+}
+
+static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
+{
+ u64 in_param;
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, order);
+ err = mlx4_cmd_imm(dev, in_param, &out_param, RES_MTT,
+ RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+ if (err)
+ return -1;
+ return get_param_l(&out_param);
+ }
+ return __mlx4_alloc_mtt_range(dev, order);
}
int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
} else
mtt->page_shift = page_shift;
- for (mtt->order = 0, i = dev->caps.mtts_per_seg; i < npages; i <<= 1)
+ for (mtt->order = 0, i = 1; i < npages; i <<= 1)
++mtt->order;
- mtt->first_seg = mlx4_alloc_mtt_range(dev, mtt->order);
- if (mtt->first_seg == -1)
+ mtt->offset = mlx4_alloc_mtt_range(dev, mtt->order);
+ if (mtt->offset == -1)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL_GPL(mlx4_mtt_init);
-void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
+void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
{
+ u32 first_seg;
+ int seg_order;
struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+ seg_order = max_t(int, order - log_mtts_per_seg, 0);
+ first_seg = offset / (1 << log_mtts_per_seg);
+
+ mlx4_buddy_free(&mr_table->mtt_buddy, first_seg, seg_order);
+ mlx4_table_put_range(dev, &mr_table->mtt_table, offset,
+ offset + (1 << order) - 1);
+}
+
+static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
+{
+ u64 in_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, offset);
+ set_param_h(&in_param, order);
+ err = mlx4_cmd(dev, in_param, RES_MTT, RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+ if (err)
+ mlx4_warn(dev, "Failed to free mtt range at:"
+ "%d order:%d\n", offset, order);
+ return;
+ }
+ __mlx4_free_mtt_range(dev, offset, order);
+}
+
+void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
+{
if (mtt->order < 0)
return;
- mlx4_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, mtt->order);
- mlx4_table_put_range(dev, &mr_table->mtt_table, mtt->first_seg,
- mtt->first_seg + (1 << mtt->order) - 1);
+ mlx4_free_mtt_range(dev, mtt->offset, mtt->order);
}
EXPORT_SYMBOL_GPL(mlx4_mtt_cleanup);
u64 mlx4_mtt_addr(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
{
- return (u64) mtt->first_seg * dev->caps.mtt_entry_sz;
+ return (u64) mtt->offset * dev->caps.mtt_entry_sz;
}
EXPORT_SYMBOL_GPL(mlx4_mtt_addr);
static int mlx4_SW2HW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int mpt_index)
{
- return mlx4_cmd(dev, mailbox->dma, mpt_index, 0, MLX4_CMD_SW2HW_MPT,
- MLX4_CMD_TIME_CLASS_B);
+ return mlx4_cmd(dev, mailbox->dma | dev->caps.function , mpt_index,
+ 0, MLX4_CMD_SW2HW_MPT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_HW2SW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int mpt_index)
{
return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, mpt_index,
- !mailbox, MLX4_CMD_HW2SW_MPT, MLX4_CMD_TIME_CLASS_B);
+ !mailbox, MLX4_CMD_HW2SW_MPT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
}
-int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
- int npages, int page_shift, struct mlx4_mr *mr)
+static int mlx4_mr_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+ u32 *base_mridx)
{
struct mlx4_priv *priv = mlx4_priv(dev);
- u32 index;
- int err;
+ u32 mridx;
- index = mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
- if (index == -1)
+ mridx = mlx4_bitmap_alloc_range(&priv->mr_table.mpt_bitmap, cnt, align);
+ if (mridx == -1)
return -ENOMEM;
+ *base_mridx = mridx;
+ return 0;
+
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_reserve_range);
+
+static void mlx4_mr_release_range(struct mlx4_dev *dev, u32 base_mridx, int cnt)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ mlx4_bitmap_free_range(&priv->mr_table.mpt_bitmap, base_mridx, cnt);
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_release_range);
+
+static int mlx4_mr_alloc_reserved(struct mlx4_dev *dev, u32 mridx, u32 pd,
+ u64 iova, u64 size, u32 access, int npages,
+ int page_shift, struct mlx4_mr *mr)
+{
mr->iova = iova;
mr->size = size;
mr->pd = pd;
mr->access = access;
- mr->enabled = 0;
- mr->key = hw_index_to_key(index);
+ mr->enabled = MLX4_MR_DISABLED;
+ mr->key = hw_index_to_key(mridx);
+
+ return mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_alloc_reserved);
+
+static int mlx4_WRITE_MTT(struct mlx4_dev *dev,
+ struct mlx4_cmd_mailbox *mailbox,
+ int num_entries)
+{
+ return mlx4_cmd(dev, mailbox->dma, num_entries, 0, MLX4_CMD_WRITE_MTT,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+}
- err = mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
+int __mlx4_mr_reserve(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ return mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
+}
+
+static int mlx4_mr_reserve(struct mlx4_dev *dev)
+{
+ u64 out_param;
+
+ if (mlx4_is_mfunc(dev)) {
+ if (mlx4_cmd_imm(dev, 0, &out_param, RES_MPT, RES_OP_RESERVE,
+ MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+ return -1;
+ return get_param_l(&out_param);
+ }
+ return __mlx4_mr_reserve(dev);
+}
+
+void __mlx4_mr_release(struct mlx4_dev *dev, u32 index)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
+}
+
+static void mlx4_mr_release(struct mlx4_dev *dev, u32 index)
+{
+ u64 in_param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, index);
+ if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_RESERVE,
+ MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+ mlx4_warn(dev, "Failed to release mr index:%d\n",
+ index);
+ return;
+ }
+ __mlx4_mr_release(dev, index);
+}
+
+int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
+{
+ struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+
+ return mlx4_table_get(dev, &mr_table->dmpt_table, index);
+}
+
+static int mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
+{
+ u64 param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(¶m, index);
+ return mlx4_cmd_imm(dev, param, ¶m, RES_MPT, RES_OP_MAP_ICM,
+ MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+ }
+ return __mlx4_mr_alloc_icm(dev, index);
+}
+
+void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
+{
+ struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+
+ mlx4_table_put(dev, &mr_table->dmpt_table, index);
+}
+
+static void mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
+{
+ u64 in_param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, index);
+ if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_MAP_ICM,
+ MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED))
+ mlx4_warn(dev, "Failed to free icm of mr index:%d\n",
+ index);
+ return;
+ }
+ return __mlx4_mr_free_icm(dev, index);
+}
+
+int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
+ int npages, int page_shift, struct mlx4_mr *mr)
+{
+ u32 index;
+ int err;
+
+ index = mlx4_mr_reserve(dev);
+ if (index == -1)
+ return -ENOMEM;
+
+ err = mlx4_mr_alloc_reserved(dev, index, pd, iova, size,
+ access, npages, page_shift, mr);
if (err)
- mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
+ mlx4_mr_release(dev, index);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_mr_alloc);
-void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
+static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
{
- struct mlx4_priv *priv = mlx4_priv(dev);
int err;
- if (mr->enabled) {
+ if (mr->enabled == MLX4_MR_EN_HW) {
err = mlx4_HW2SW_MPT(dev, NULL,
key_to_hw_index(mr->key) &
(dev->caps.num_mpts - 1));
if (err)
- mlx4_warn(dev, "HW2SW_MPT failed (%d)\n", err);
- }
+ mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
+ mr->enabled = MLX4_MR_EN_SW;
+ }
mlx4_mtt_cleanup(dev, &mr->mtt);
- mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, key_to_hw_index(mr->key));
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_free_reserved);
+
+void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
+{
+ mlx4_mr_free_reserved(dev, mr);
+ if (mr->enabled)
+ mlx4_mr_free_icm(dev, key_to_hw_index(mr->key));
+ mlx4_mr_release(dev, key_to_hw_index(mr->key));
}
EXPORT_SYMBOL_GPL(mlx4_mr_free);
int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
{
- struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_mpt_entry *mpt_entry;
int err;
- err = mlx4_table_get(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key));
+ err = mlx4_mr_alloc_icm(dev, key_to_hw_index(mr->key));
if (err)
return err;
if (mr->mtt.order < 0) {
mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_PHYSICAL);
- mpt_entry->mtt_seg = 0;
+ mpt_entry->mtt_addr = 0;
} else {
- mpt_entry->mtt_seg = cpu_to_be64(mlx4_mtt_addr(dev, &mr->mtt));
+ mpt_entry->mtt_addr = cpu_to_be64(mlx4_mtt_addr(dev,
+ &mr->mtt));
}
if (mr->mtt.order >= 0 && mr->mtt.page_shift == 0) {
mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_FREE);
mpt_entry->pd_flags |= cpu_to_be32(MLX4_MPT_PD_FLAG_FAST_REG |
MLX4_MPT_PD_FLAG_RAE);
- mpt_entry->mtt_sz = cpu_to_be32((1 << mr->mtt.order) *
- dev->caps.mtts_per_seg);
+ mpt_entry->mtt_sz = cpu_to_be32(1 << mr->mtt.order);
} else {
mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_SW_OWNS);
}
mlx4_warn(dev, "SW2HW_MPT failed (%d)\n", err);
goto err_cmd;
}
-
- mr->enabled = 1;
+ mr->enabled = MLX4_MR_EN_HW;
mlx4_free_cmd_mailbox(dev, mailbox);
mlx4_free_cmd_mailbox(dev, mailbox);
err_table:
- mlx4_table_put(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key));
+ mlx4_mr_free_icm(dev, key_to_hw_index(mr->key));
return err;
}
EXPORT_SYMBOL_GPL(mlx4_mr_enable);
__be64 *mtts;
dma_addr_t dma_handle;
int i;
- int s = start_index * sizeof (u64);
- /* All MTTs must fit in the same page */
- if (start_index / (PAGE_SIZE / sizeof (u64)) !=
- (start_index + npages - 1) / (PAGE_SIZE / sizeof (u64)))
- return -EINVAL;
-
- if (start_index & (dev->caps.mtts_per_seg - 1))
- return -EINVAL;
+ mtts = mlx4_table_find(&priv->mr_table.mtt_table, mtt->offset +
+ start_index, &dma_handle);
- mtts = mlx4_table_find(&priv->mr_table.mtt_table, mtt->first_seg +
- s / dev->caps.mtt_entry_sz, &dma_handle);
if (!mtts)
return -ENOMEM;
return 0;
}
-int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
- int start_index, int npages, u64 *page_list)
+int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ int start_index, int npages, u64 *page_list)
{
+ int err = 0;
int chunk;
- int err;
+ int mtts_per_page;
+ int max_mtts_first_page;
- if (mtt->order < 0)
- return -EINVAL;
+ /* compute how may mtts fit in the first page */
+ mtts_per_page = PAGE_SIZE / sizeof(u64);
+ max_mtts_first_page = mtts_per_page - (mtt->offset + start_index)
+ % mtts_per_page;
+
+ chunk = min_t(int, max_mtts_first_page, npages);
while (npages > 0) {
- chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages);
err = mlx4_write_mtt_chunk(dev, mtt, start_index, chunk, page_list);
if (err)
return err;
-
npages -= chunk;
start_index += chunk;
page_list += chunk;
+
+ chunk = min_t(int, mtts_per_page, npages);
}
+ return err;
+}
- return 0;
+int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ int start_index, int npages, u64 *page_list)
+{
+ struct mlx4_cmd_mailbox *mailbox = NULL;
+ __be64 *inbox = NULL;
+ int chunk;
+ int err = 0;
+ int i;
+
+ if (mtt->order < 0)
+ return -EINVAL;
+
+ if (mlx4_is_mfunc(dev)) {
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ inbox = mailbox->buf;
+
+ while (npages > 0) {
+ chunk = min_t(int, MLX4_MAILBOX_SIZE / sizeof(u64) - 2,
+ npages);
+ inbox[0] = cpu_to_be64(mtt->offset + start_index);
+ inbox[1] = 0;
+ for (i = 0; i < chunk; ++i)
+ inbox[i + 2] = cpu_to_be64(page_list[i] |
+ MLX4_MTT_FLAG_PRESENT);
+ err = mlx4_WRITE_MTT(dev, mailbox, chunk);
+ if (err) {
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+ }
+
+ npages -= chunk;
+ start_index += chunk;
+ page_list += chunk;
+ }
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+ }
+
+ return __mlx4_write_mtt(dev, mtt, start_index, npages, page_list);
}
EXPORT_SYMBOL_GPL(mlx4_write_mtt);
int mlx4_init_mr_table(struct mlx4_dev *dev)
{
- struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_mr_table *mr_table = &priv->mr_table;
int err;
+ if (!is_power_of_2(dev->caps.num_mpts))
+ return -EINVAL;
+
+ /* Nothing to do for slaves - all MR handling is forwarded
+ * to the master */
+ if (mlx4_is_slave(dev))
+ return 0;
+
err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts,
~0, dev->caps.reserved_mrws, 0);
if (err)
return err;
err = mlx4_buddy_init(&mr_table->mtt_buddy,
- ilog2(dev->caps.num_mtt_segs));
+ ilog2(dev->caps.num_mtts /
+ (1 << log_mtts_per_seg)));
if (err)
goto err_buddy;
if (dev->caps.reserved_mtts) {
- if (mlx4_alloc_mtt_range(dev, fls(dev->caps.reserved_mtts - 1)) == -1) {
+ priv->reserved_mtts =
+ mlx4_alloc_mtt_range(dev,
+ fls(dev->caps.reserved_mtts - 1));
+ if (priv->reserved_mtts < 0) {
mlx4_warn(dev, "MTT table of order %d is too small.\n",
mr_table->mtt_buddy.max_order);
err = -ENOMEM;
void mlx4_cleanup_mr_table(struct mlx4_dev *dev)
{
- struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_mr_table *mr_table = &priv->mr_table;
+ if (mlx4_is_slave(dev))
+ return;
+ if (priv->reserved_mtts >= 0)
+ mlx4_free_mtt_range(dev, priv->reserved_mtts,
+ fls(dev->caps.reserved_mtts - 1));
mlx4_buddy_cleanup(&mr_table->mtt_buddy);
mlx4_bitmap_cleanup(&mr_table->mpt_bitmap);
}
int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
{
struct mlx4_priv *priv = mlx4_priv(dev);
- u64 mtt_seg;
+ u64 mtt_offset;
int err = -ENOMEM;
if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
if (err)
return err;
- mtt_seg = fmr->mr.mtt.first_seg * dev->caps.mtt_entry_sz;
+ mtt_offset = fmr->mr.mtt.offset * dev->caps.mtt_entry_sz;
fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
- fmr->mr.mtt.first_seg,
+ fmr->mr.mtt.offset,
&fmr->dma_handle);
+
if (!fmr->mtts) {
err = -ENOMEM;
goto err_free;
}
EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
+static int mlx4_fmr_alloc_reserved(struct mlx4_dev *dev, u32 mridx,
+ u32 pd, u32 access, int max_pages,
+ int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int err = -ENOMEM;
+
+ if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
+ return -EINVAL;
+
+ /* All MTTs must fit in the same page */
+ if (max_pages * sizeof *fmr->mtts > PAGE_SIZE)
+ return -EINVAL;
+
+ fmr->page_shift = page_shift;
+ fmr->max_pages = max_pages;
+ fmr->max_maps = max_maps;
+ fmr->maps = 0;
+
+ err = mlx4_mr_alloc_reserved(dev, mridx, pd, 0, 0, access, max_pages,
+ page_shift, &fmr->mr);
+ if (err)
+ return err;
+
+ fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
+ fmr->mr.mtt.offset,
+ &fmr->dma_handle);
+ if (!fmr->mtts) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ return 0;
+
+err_free:
+ mlx4_mr_free_reserved(dev, &fmr->mr);
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_alloc_reserved);
+
int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
{
struct mlx4_priv *priv = mlx4_priv(dev);
void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
u32 *lkey, u32 *rkey)
{
+ struct mlx4_cmd_mailbox *mailbox;
+ int err;
+
if (!fmr->maps)
return;
fmr->maps = 0;
- *(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ err = PTR_ERR(mailbox);
+ printk(KERN_WARNING "mlx4_ib: mlx4_alloc_cmd_mailbox"
+ " failed (%d)\n", err);
+ return;
+ }
+
+ err = mlx4_HW2SW_MPT(dev, NULL,
+ key_to_hw_index(fmr->mr.key) &
+ (dev->caps.num_mpts - 1));
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ if (err) {
+ printk(KERN_WARNING "mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n",
+ err);
+ return;
+ }
+ fmr->mr.enabled = MLX4_MR_EN_SW;
}
EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
if (fmr->maps)
return -EBUSY;
- fmr->mr.enabled = 0;
mlx4_mr_free(dev, &fmr->mr);
+ fmr->mr.enabled = MLX4_MR_DISABLED;
return 0;
}
EXPORT_SYMBOL_GPL(mlx4_fmr_free);
+static int mlx4_fmr_free_reserved(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
+{
+ if (fmr->maps)
+ return -EBUSY;
+
+ mlx4_mr_free_reserved(dev, &fmr->mr);
+ fmr->mr.enabled = MLX4_MR_DISABLED;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_free_reserved);
+
int mlx4_SYNC_TPT(struct mlx4_dev *dev)
{
- return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000);
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000,
+ MLX4_CMD_WRAPPED);
}
EXPORT_SYMBOL_GPL(mlx4_SYNC_TPT);
* SOFTWARE.
*/
+#include <linux/init.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/io-mapping.h>
*pdn = mlx4_bitmap_alloc(&priv->pd_bitmap);
if (*pdn == -1)
return -ENOMEM;
-
+ if (mlx4_is_mfunc(dev))
+ *pdn |= (dev->caps.function + 1) << NOT_MASKED_PD_BITS;
return 0;
}
EXPORT_SYMBOL_GPL(mlx4_pd_alloc);
struct mlx4_priv *priv = mlx4_priv(dev);
return mlx4_bitmap_init(&priv->pd_bitmap, dev->caps.num_pds,
- (1 << 24) - 1, dev->caps.reserved_pds, 0);
+ (1 << NOT_MASKED_PD_BITS) - 1,
+ dev->caps.reserved_pds, 0);
}
void mlx4_cleanup_pd_table(struct mlx4_dev *dev)
int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
{
+ int offset;
+
uar->index = mlx4_bitmap_alloc(&mlx4_priv(dev)->uar_table.bitmap);
if (uar->index == -1)
return -ENOMEM;
- uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + uar->index;
+ if (mlx4_is_slave(dev))
+ offset = uar->index % ((int) pci_resource_len(dev->pdev, 2) /
+ dev->caps.uar_page_size);
+ else
+ offset = uar->index;
+ uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + offset;
uar->map = NULL;
-
return 0;
}
EXPORT_SYMBOL_GPL(mlx4_uar_alloc);
return mlx4_bitmap_init(&mlx4_priv(dev)->uar_table.bitmap,
dev->caps.num_uars, dev->caps.num_uars - 1,
- max(128, dev->caps.reserved_uars), 0);
+ dev->caps.reserved_uars, 0);
}
void mlx4_cleanup_uar_table(struct mlx4_dev *dev)
table->total = 0;
}
-static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
- __be64 *entries)
-{
- struct mlx4_cmd_mailbox *mailbox;
- u32 in_mod;
- int err;
-
- mailbox = mlx4_alloc_cmd_mailbox(dev);
- if (IS_ERR(mailbox))
- return PTR_ERR(mailbox);
-
- memcpy(mailbox->buf, entries, MLX4_MAC_TABLE_SIZE);
-
- in_mod = MLX4_SET_PORT_MAC_TABLE << 8 | port;
- err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
-
- mlx4_free_cmd_mailbox(dev, mailbox);
- return err;
-}
-
-static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
- u64 mac, int *qpn, u8 reserve)
+static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
{
struct mlx4_qp qp;
u8 gid[16] = {0};
int err;
- if (reserve) {
- err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
- if (err) {
- mlx4_err(dev, "Failed to reserve qp for mac registration\n");
- return err;
- }
- }
qp.qpn = *qpn;
mac &= 0xffffffffffffULL;
gid[5] = port;
gid[7] = MLX4_UC_STEER << 1;
- err = mlx4_qp_attach_common(dev, &qp, gid, 0,
- MLX4_PROT_ETH, MLX4_UC_STEER);
- if (err && reserve)
- mlx4_qp_release_range(dev, *qpn, 1);
+ err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+ if (err)
+ mlx4_warn(dev, "Failed Attaching Unicast\n");
return err;
}
static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
- u64 mac, int qpn, u8 free)
+ u64 mac, int qpn)
{
struct mlx4_qp qp;
u8 gid[16] = {0};
gid[5] = port;
gid[7] = MLX4_UC_STEER << 1;
- mlx4_qp_detach_common(dev, &qp, gid, MLX4_PROT_ETH, MLX4_UC_STEER);
- if (free)
- mlx4_qp_release_range(dev, qpn, 1);
+ mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+}
+
+static int validate_index(struct mlx4_dev *dev,
+ struct mlx4_mac_table *table, int index)
+{
+ int err = 0;
+
+ if (index < 0 || index >= table->max || !table->entries[index]) {
+ mlx4_warn(dev, "No valid Mac entry for the given index\n");
+ err = -EINVAL;
+ }
+ return err;
+}
+
+static int find_index(struct mlx4_dev *dev,
+ struct mlx4_mac_table *table, u64 mac)
+{
+ int i;
+
+ for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+ if ((mac & MLX4_MAC_MASK) ==
+ (MLX4_MAC_MASK & be64_to_cpu(table->entries[i])))
+ return i;
+ }
+ /* Mac not found */
+ return -EINVAL;
}
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap)
+int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
{
struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
- struct mlx4_mac_table *table = &info->mac_table;
struct mlx4_mac_entry *entry;
- int i, err = 0;
- int free = -1;
+ int index = 0;
+ int err = 0;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
- err = mlx4_uc_steer_add(dev, port, mac, qpn, 1);
- if (err)
- return err;
+ mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n",
+ (unsigned long long) mac);
+ index = mlx4_register_mac(dev, port, mac);
+ if (index < 0) {
+ err = index;
+ mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+ (unsigned long long) mac);
+ return err;
+ }
- entry = kmalloc(sizeof *entry, GFP_KERNEL);
- if (!entry) {
- mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
- return -ENOMEM;
- }
+ if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) {
+ *qpn = info->base_qpn + index;
+ return 0;
+ }
+
+ err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+ mlx4_dbg(dev, "Reserved qp %d\n", *qpn);
+ if (err) {
+ mlx4_err(dev, "Failed to reserve qp for mac registration\n");
+ goto qp_err;
+ }
+
+ err = mlx4_uc_steer_add(dev, port, mac, qpn);
+ if (err)
+ goto steer_err;
- entry->mac = mac;
- err = radix_tree_insert(&info->mac_tree, *qpn, entry);
- if (err) {
+ entry = kmalloc(sizeof *entry, GFP_KERNEL);
+ if (!entry) {
+ err = -ENOMEM;
+ goto alloc_err;
+ }
+ entry->mac = mac;
+ err = radix_tree_insert(&info->mac_tree, *qpn, entry);
+ if (err)
+ goto insert_err;
+ return 0;
+
+insert_err:
+ kfree(entry);
+
+alloc_err:
+ mlx4_uc_steer_release(dev, port, mac, *qpn);
+
+steer_err:
+ mlx4_qp_release_range(dev, *qpn, 1);
+
+qp_err:
+ mlx4_unregister_mac(dev, port, mac);
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_eth_qp);
+
+void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn)
+{
+ struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+ struct mlx4_mac_entry *entry;
+
+ mlx4_dbg(dev, "Registering MAC: 0x%llx for deleting\n",
+ (unsigned long long) mac);
+ mlx4_unregister_mac(dev, port, mac);
+
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
+ entry = radix_tree_lookup(&info->mac_tree, qpn);
+ if (entry) {
+ mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx,"
+ " qpn %d\n", port,
+ (unsigned long long) mac, qpn);
+ mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+ mlx4_qp_release_range(dev, qpn, 1);
+ radix_tree_delete(&info->mac_tree, qpn);
kfree(entry);
- mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
- return err;
}
}
+}
+EXPORT_SYMBOL_GPL(mlx4_put_eth_qp);
+
+static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
+ __be64 *entries)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ u32 in_mod;
+ int err;
- mlx4_dbg(dev, "Registering MAC: 0x%llx\n", (unsigned long long) mac);
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+
+ memcpy(mailbox->buf, entries, MLX4_MAC_TABLE_SIZE);
+
+ in_mod = MLX4_SET_PORT_MAC_TABLE << 8 | port;
+
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+
+int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
+{
+ struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+ struct mlx4_mac_table *table = &info->mac_table;
+ int i, err = 0;
+ int free = -1;
+
+ mlx4_dbg(dev, "Registering MAC: 0x%llx for port %d\n",
+ (unsigned long long) mac, port);
mutex_lock(&table->mutex);
- for (i = 0; i < MLX4_MAX_MAC_NUM - 1; i++) {
- if (free < 0 && !table->refs[i]) {
+ for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+ if (free < 0 && !table->entries[i]) {
free = i;
continue;
}
if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
- /* MAC already registered, increase references count */
- ++table->refs[i];
+ /* MAC already registered, Must not have duplicates */
+ err = -EEXIST;
goto out;
}
}
- if (free < 0) {
- err = -ENOMEM;
- goto out;
- }
-
mlx4_dbg(dev, "Free MAC index is %d\n", free);
if (table->total == table->max) {
}
/* Register new MAC */
- table->refs[free] = 1;
table->entries[free] = cpu_to_be64(mac | MLX4_MAC_VALID);
err = mlx4_set_port_mac_table(dev, port, table->entries);
if (unlikely(err)) {
- mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) mac);
- table->refs[free] = 0;
+ mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+ (unsigned long long) mac);
table->entries[free] = 0;
goto out;
}
- if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
- *qpn = info->base_qpn + free;
+ err = free;
++table->total;
out:
mutex_unlock(&table->mutex);
return err;
}
-EXPORT_SYMBOL_GPL(mlx4_register_mac);
+EXPORT_SYMBOL_GPL(__mlx4_register_mac);
-static int validate_index(struct mlx4_dev *dev,
- struct mlx4_mac_table *table, int index)
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
{
- int err = 0;
+ u64 out_param;
+ int err;
- if (index < 0 || index >= table->max || !table->entries[index]) {
- mlx4_warn(dev, "No valid Mac entry for the given index\n");
- err = -EINVAL;
- }
- return err;
-}
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&out_param, port);
+ err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+ RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ return err;
-static int find_index(struct mlx4_dev *dev,
- struct mlx4_mac_table *table, u64 mac)
-{
- int i;
- for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
- if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i])))
- return i;
+ return get_param_l(&out_param);
}
- /* Mac not found */
- return -EINVAL;
+ return __mlx4_register_mac(dev, port, mac);
}
+EXPORT_SYMBOL_GPL(mlx4_register_mac);
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn)
+
+void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
{
struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
struct mlx4_mac_table *table = &info->mac_table;
- int index = qpn - info->base_qpn;
- struct mlx4_mac_entry *entry;
+ int index;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
- entry = radix_tree_lookup(&info->mac_tree, qpn);
- if (entry) {
- mlx4_uc_steer_release(dev, port, entry->mac, qpn, 1);
- radix_tree_delete(&info->mac_tree, qpn);
- index = find_index(dev, table, entry->mac);
- kfree(entry);
- }
- }
+ index = find_index(dev, table, mac);
mutex_lock(&table->mutex);
if (validate_index(dev, table, index))
goto out;
- /* Check whether this address has reference count */
- if (!(--table->refs[index])) {
- table->entries[index] = 0;
- mlx4_set_port_mac_table(dev, port, table->entries);
- --table->total;
- }
+ table->entries[index] = 0;
+ mlx4_set_port_mac_table(dev, port, table->entries);
+ --table->total;
out:
mutex_unlock(&table->mutex);
}
+EXPORT_SYMBOL_GPL(__mlx4_unregister_mac);
+
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
+{
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&out_param, port);
+ err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+ RES_OP_RESERVE_AND_MAP, MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ return;
+ }
+ __mlx4_unregister_mac(dev, port, mac);
+ return;
+}
EXPORT_SYMBOL_GPL(mlx4_unregister_mac);
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap)
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
{
struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
struct mlx4_mac_table *table = &info->mac_table;
- int index = qpn - info->base_qpn;
struct mlx4_mac_entry *entry;
- int err;
+ int index = qpn - info->base_qpn;
+ int err = 0;
if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
entry = radix_tree_lookup(&info->mac_tree, qpn);
if (!entry)
return -EINVAL;
- index = find_index(dev, table, entry->mac);
- mlx4_uc_steer_release(dev, port, entry->mac, qpn, 0);
+ mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+ mlx4_unregister_mac(dev, port, entry->mac);
entry->mac = new_mac;
- err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn, 0);
- if (err || index < 0)
- return err;
+ mlx4_register_mac(dev, port, new_mac);
+ err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn);
+ return err;
}
+ /* CX1 doesn't support multi-functions */
mutex_lock(&table->mutex);
err = validate_index(dev, table, index);
err = mlx4_set_port_mac_table(dev, port, table->entries);
if (unlikely(err)) {
- mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) new_mac);
+ mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+ (unsigned long long) new_mac);
table->entries[index] = 0;
}
out:
return err;
}
EXPORT_SYMBOL_GPL(mlx4_replace_mac);
+
static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
__be32 *entries)
{
memcpy(mailbox->buf, entries, MLX4_VLAN_TABLE_SIZE);
in_mod = MLX4_SET_PORT_VLAN_TABLE << 8 | port;
err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
mlx4_free_cmd_mailbox(dev, mailbox);
}
EXPORT_SYMBOL_GPL(mlx4_find_cached_vlan);
-int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
+static int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan,
+ int *index)
{
struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
int i, err = 0;
goto out;
}
- /* Register new MAC */
+ /* Register new VLAN */
table->refs[free] = 1;
table->entries[free] = cpu_to_be32(vlan | MLX4_VLAN_VALID);
mutex_unlock(&table->mutex);
return err;
}
+
+int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
+{
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&out_param, port);
+ err = mlx4_cmd_imm(dev, vlan, &out_param, RES_VLAN,
+ RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (!err)
+ *index = get_param_l(&out_param);
+
+ return err;
+ }
+ return __mlx4_register_vlan(dev, port, vlan, index);
+}
EXPORT_SYMBOL_GPL(mlx4_register_vlan);
-void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+static void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
{
struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
out:
mutex_unlock(&table->mutex);
}
+
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+{
+ u64 in_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, port);
+ err = mlx4_cmd(dev, in_param, RES_VLAN, RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+ if (!err)
+ mlx4_warn(dev, "Failed freeing vlan at index:%d\n",
+ index);
+
+ return;
+ }
+ __mlx4_unregister_vlan(dev, port, index);
+}
EXPORT_SYMBOL_GPL(mlx4_unregister_vlan);
int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
*(__be32 *) (&inbuf[20]) = cpu_to_be32(port);
err = mlx4_cmd_box(dev, inmailbox->dma, outmailbox->dma, port, 3,
- MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+ MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+ MLX4_CMD_NATIVE);
if (!err)
*caps = *(__be32 *) (outbuf + 84);
mlx4_free_cmd_mailbox(dev, inmailbox);
*(__be32 *) (&inbuf[20]) = cpu_to_be32(port);
err = mlx4_cmd_box(dev, inmailbox->dma, outmailbox->dma, port, 3,
- MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+ MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+ MLX4_CMD_NATIVE);
packet_error = be16_to_cpu(*(__be16 *) (outbuf + 4));
return err;
}
+static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
+ u8 op_mod, struct mlx4_cmd_mailbox *inbox)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_port_info *port_info;
+ struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
+ struct mlx4_slave_state *slave_st = &master->slave_state[slave];
+ struct mlx4_set_port_rqp_calc_context *qpn_context;
+ struct mlx4_set_port_general_context *gen_context;
+ int reset_qkey_viols;
+ int port;
+ int is_eth;
+ u32 in_modifier;
+ u32 promisc;
+ u16 mtu, prev_mtu;
+ int err;
+ int i;
+ __be32 agg_cap_mask;
+ __be32 slave_cap_mask;
+ __be32 new_cap_mask;
+
+ port = in_mod & 0xff;
+ in_modifier = in_mod >> 8;
+ is_eth = op_mod;
+ port_info = &priv->port[port];
+
+ /* Slaves cannot perform SET_PORT operations except changing MTU */
+ if (is_eth) {
+ if (slave != dev->caps.function &&
+ in_modifier != MLX4_SET_PORT_GENERAL) {
+ mlx4_warn(dev, "denying SET_PORT for slave:%d\n",
+ slave);
+ return -EINVAL;
+ }
+ switch (in_modifier) {
+ case MLX4_SET_PORT_RQP_CALC:
+ qpn_context = inbox->buf;
+ qpn_context->base_qpn =
+ cpu_to_be32(port_info->base_qpn);
+ qpn_context->n_mac = 0x7;
+ promisc = be32_to_cpu(qpn_context->promisc) >>
+ SET_PORT_PROMISC_SHIFT;
+ qpn_context->promisc = cpu_to_be32(
+ promisc << SET_PORT_PROMISC_SHIFT |
+ port_info->base_qpn);
+ promisc = be32_to_cpu(qpn_context->mcast) >>
+ SET_PORT_MC_PROMISC_SHIFT;
+ qpn_context->mcast = cpu_to_be32(
+ promisc << SET_PORT_MC_PROMISC_SHIFT |
+ port_info->base_qpn);
+ break;
+ case MLX4_SET_PORT_GENERAL:
+ gen_context = inbox->buf;
+ /* Mtu is configured as the max MTU among all the
+ * the functions on the port. */
+ mtu = be16_to_cpu(gen_context->mtu);
+ mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port]);
+ prev_mtu = slave_st->mtu[port];
+ slave_st->mtu[port] = mtu;
+ if (mtu > master->max_mtu[port])
+ master->max_mtu[port] = mtu;
+ if (mtu < prev_mtu && prev_mtu ==
+ master->max_mtu[port]) {
+ slave_st->mtu[port] = mtu;
+ master->max_mtu[port] = mtu;
+ for (i = 0; i < dev->num_slaves; i++) {
+ master->max_mtu[port] =
+ max(master->max_mtu[port],
+ master->slave_state[i].mtu[port]);
+ }
+ }
+
+ gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
+ break;
+ }
+ return mlx4_cmd(dev, inbox->dma, in_mod, op_mod,
+ MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
+ }
+
+ /* For IB, we only consider:
+ * - The capability mask, which is set to the aggregate of all
+ * slave function capabilities
+ * - The QKey violatin counter - reset according to each request.
+ */
+
+ if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+ reset_qkey_viols = (*(u8 *) inbox->buf) & 0x40;
+ new_cap_mask = ((__be32 *) inbox->buf)[2];
+ } else {
+ reset_qkey_viols = ((u8 *) inbox->buf)[3] & 0x1;
+ new_cap_mask = ((__be32 *) inbox->buf)[1];
+ }
+
+ agg_cap_mask = 0;
+ slave_cap_mask =
+ priv->mfunc.master.slave_state[slave].ib_cap_mask[port];
+ priv->mfunc.master.slave_state[slave].ib_cap_mask[port] = new_cap_mask;
+ for (i = 0; i < dev->num_slaves; i++)
+ agg_cap_mask |=
+ priv->mfunc.master.slave_state[i].ib_cap_mask[port];
+
+ /* only clear mailbox for guests. Master may be setting
+ * MTU or PKEY table size
+ */
+ if (slave != dev->caps.function)
+ memset(inbox->buf, 0, 256);
+ if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+ *(u8 *) inbox->buf = !!reset_qkey_viols << 6;
+ ((__be32 *) inbox->buf)[2] = agg_cap_mask;
+ } else {
+ ((u8 *) inbox->buf)[3] = !!reset_qkey_viols;
+ ((__be32 *) inbox->buf)[1] = agg_cap_mask;
+ }
+
+ err = mlx4_cmd(dev, inbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+ if (err)
+ priv->mfunc.master.slave_state[slave].ib_cap_mask[port] =
+ slave_cap_mask;
+ return err;
+}
+
+int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ return mlx4_common_set_port(dev, slave, vhcr->in_modifier,
+ vhcr->op_modifier, inbox);
+}
+
int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
{
struct mlx4_cmd_mailbox *mailbox;
((__be32 *) mailbox->buf)[1] = dev->caps.ib_port_def_cap[port];
err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
mlx4_free_cmd_mailbox(dev, mailbox);
return err;
}
+
+int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
+ u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_set_port_general_context *context;
+ int err;
+ u32 in_mod;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ context = mailbox->buf;
+ memset(context, 0, sizeof *context);
+
+ context->flags = SET_PORT_GEN_ALL_VALID;
+ context->mtu = cpu_to_be16(mtu);
+ context->pptx = (pptx * (!pfctx)) << 7;
+ context->pfctx = pfctx;
+ context->pprx = (pprx * (!pfcrx)) << 7;
+ context->pfcrx = pfcrx;
+
+ in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_general);
+
+int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
+ u8 promisc)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_set_port_rqp_calc_context *context;
+ int err;
+ u32 in_mod;
+ u32 m_promisc = (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) ?
+ MCAST_DIRECT : MCAST_DEFAULT;
+
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER &&
+ dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)
+ return 0;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ context = mailbox->buf;
+ memset(context, 0, sizeof *context);
+
+ context->base_qpn = cpu_to_be32(base_qpn);
+ context->n_mac = dev->caps.log_num_macs;
+ context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
+ base_qpn);
+ context->mcast = cpu_to_be32(m_promisc << SET_PORT_MC_PROMISC_SHIFT |
+ base_qpn);
+ context->intra_no_vlan = 0;
+ context->no_vlan = MLX4_NO_VLAN_IDX;
+ context->intra_vlan_miss = 0;
+ context->vlan_miss = MLX4_VLAN_MISS_IDX;
+
+ in_mod = MLX4_SET_PORT_RQP_CALC << 8 | port;
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_qpn_calc);
+
+int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err = 0;
+
+ return err;
+}
+
+int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port,
+ u64 mac, u64 clear, u8 mode)
+{
+ return mlx4_cmd(dev, (mac | (clear << 63)), port, mode,
+ MLX4_CMD_SET_MCAST_FLTR, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+}
+EXPORT_SYMBOL(mlx4_SET_MCAST_FLTR);
+
+int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err = 0;
+
+ return err;
+}
+
+int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave,
+ u32 in_mod, struct mlx4_cmd_mailbox *outbox)
+{
+ return mlx4_cmd_box(dev, 0, outbox->dma, in_mod, 0,
+ MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
+}
+
+int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ return mlx4_common_dump_eth_stats(dev, slave,
+ vhcr->in_modifier, outbox);
+}
profile[MLX4_RES_EQ].size = dev_cap->eqc_entry_sz;
profile[MLX4_RES_DMPT].size = dev_cap->dmpt_entry_sz;
profile[MLX4_RES_CMPT].size = dev_cap->cmpt_entry_sz;
- profile[MLX4_RES_MTT].size = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
- profile[MLX4_RES_MCG].size = MLX4_MGM_ENTRY_SIZE;
+ profile[MLX4_RES_MTT].size = dev_cap->mtt_entry_sz;
+ profile[MLX4_RES_MCG].size = mlx4_get_mgm_entry_size(dev);
profile[MLX4_RES_QP].num = request->num_qp;
profile[MLX4_RES_RDMARC].num = request->num_qp * request->rdmarc_per_qp;
init_hca->cmpt_base = profile[i].start;
break;
case MLX4_RES_MTT:
- dev->caps.num_mtt_segs = profile[i].num;
+ dev->caps.num_mtts = profile[i].num;
priv->mr_table.mtt_base = profile[i].start;
init_hca->mtt_base = profile[i].start;
break;
dev->caps.num_mgms = profile[i].num >> 1;
dev->caps.num_amgms = profile[i].num >> 1;
init_hca->mc_base = profile[i].start;
- init_hca->log_mc_entry_sz = ilog2(MLX4_MGM_ENTRY_SIZE);
+ init_hca->log_mc_entry_sz =
+ ilog2(mlx4_get_mgm_entry_size(dev));
init_hca->log_mc_table_sz = profile[i].log_num;
init_hca->log_mc_hash_sz = profile[i].log_num - 1;
break;
#include <linux/gfp.h>
#include <linux/export.h>
+#include <linux/init.h>
+
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/qp.h>
spin_unlock(&qp_table->lock);
if (!qp) {
- mlx4_warn(dev, "Async event for bogus QP %08x\n", qpn);
+ mlx4_dbg(dev, "Async event for none existent QP %08x\n", qpn);
return;
}
complete(&qp->free);
}
-int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
- enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
- struct mlx4_qp_context *context, enum mlx4_qp_optpar optpar,
- int sqd_event, struct mlx4_qp *qp)
+static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp)
+{
+ return qp->qpn >= dev->caps.sqp_start &&
+ qp->qpn <= dev->caps.sqp_start + 1;
+}
+
+static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
+ struct mlx4_qp_context *context,
+ enum mlx4_qp_optpar optpar,
+ int sqd_event, struct mlx4_qp *qp, int native)
{
static const u16 op[MLX4_QP_NUM_STATE][MLX4_QP_NUM_STATE] = {
[MLX4_QP_STATE_RST] = {
}
};
+ struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cmd_mailbox *mailbox;
int ret = 0;
+ u8 port;
if (cur_state >= MLX4_QP_NUM_STATE || new_state >= MLX4_QP_NUM_STATE ||
!op[cur_state][new_state])
return -EINVAL;
- if (op[cur_state][new_state] == MLX4_CMD_2RST_QP)
- return mlx4_cmd(dev, 0, qp->qpn, 2,
- MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A);
+ if (op[cur_state][new_state] == MLX4_CMD_2RST_QP) {
+ ret = mlx4_cmd(dev, 0, qp->qpn, 2,
+ MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native);
+ if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR &&
+ cur_state != MLX4_QP_STATE_RST &&
+ is_qp0(dev, qp)) {
+ port = (qp->qpn & 1) + 1;
+ priv->mfunc.master.qp0_state[port].qp0_active = 0;
+ }
+ return ret;
+ }
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
}
+ port = ((context->pri_path.sched_queue >> 6) & 1) + 1;
+ if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
+ context->pri_path.sched_queue = (context->pri_path.sched_queue &
+ 0xc3);
+
*(__be32 *) mailbox->buf = cpu_to_be32(optpar);
memcpy(mailbox->buf + 8, context, sizeof *context);
((struct mlx4_qp_context *) (mailbox->buf + 8))->local_qpn =
cpu_to_be32(qp->qpn);
- ret = mlx4_cmd(dev, mailbox->dma, qp->qpn | (!!sqd_event << 31),
+ ret = mlx4_cmd(dev, mailbox->dma | dev->caps.function,
+ qp->qpn | (!!sqd_event << 31),
new_state == MLX4_QP_STATE_RST ? 2 : 0,
- op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C);
+ op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native);
mlx4_free_cmd_mailbox(dev, mailbox);
return ret;
}
+
+int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
+ struct mlx4_qp_context *context,
+ enum mlx4_qp_optpar optpar,
+ int sqd_event, struct mlx4_qp *qp)
+{
+ return __mlx4_qp_modify(dev, mtt, cur_state, new_state, context,
+ optpar, sqd_event, qp, 0);
+}
EXPORT_SYMBOL_GPL(mlx4_qp_modify);
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+ int *base)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
- int qpn;
- qpn = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
- if (qpn == -1)
+ *base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+ if (*base == -1)
return -ENOMEM;
- *base = qpn;
return 0;
}
+
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+{
+ u64 in_param;
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, cnt);
+ set_param_h(&in_param, align);
+ err = mlx4_cmd_imm(dev, in_param, &out_param,
+ RES_QP, RES_OP_RESERVE,
+ MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err)
+ return err;
+
+ *base = get_param_l(&out_param);
+ return 0;
+ }
+ return __mlx4_qp_reserve_range(dev, cnt, align, base);
+}
EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
-void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
+void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
- if (base_qpn < dev->caps.sqp_start + 8)
- return;
+ if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
+ return;
mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
}
+
+void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
+{
+ u64 in_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, base_qpn);
+ set_param_h(&in_param, cnt);
+ err = mlx4_cmd(dev, in_param, RES_QP, RES_OP_RESERVE,
+ MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (err) {
+ mlx4_warn(dev, "Failed to release qp range"
+ " base:%d cnt:%d\n", base_qpn, cnt);
+ }
+ } else
+ __mlx4_qp_release_range(dev, base_qpn, cnt);
+}
EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_qp_table *qp_table = &priv->qp_table;
int err;
- if (!qpn)
- return -EINVAL;
-
- qp->qpn = qpn;
-
- err = mlx4_table_get(dev, &qp_table->qp_table, qp->qpn);
+ err = mlx4_table_get(dev, &qp_table->qp_table, qpn);
if (err)
goto err_out;
- err = mlx4_table_get(dev, &qp_table->auxc_table, qp->qpn);
+ err = mlx4_table_get(dev, &qp_table->auxc_table, qpn);
if (err)
goto err_put_qp;
- err = mlx4_table_get(dev, &qp_table->altc_table, qp->qpn);
+ err = mlx4_table_get(dev, &qp_table->altc_table, qpn);
if (err)
goto err_put_auxc;
- err = mlx4_table_get(dev, &qp_table->rdmarc_table, qp->qpn);
+ err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn);
if (err)
goto err_put_altc;
- err = mlx4_table_get(dev, &qp_table->cmpt_table, qp->qpn);
+ err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn);
if (err)
goto err_put_rdmarc;
- spin_lock_irq(&qp_table->lock);
- err = radix_tree_insert(&dev->qp_table_tree, qp->qpn & (dev->caps.num_qps - 1), qp);
- spin_unlock_irq(&qp_table->lock);
- if (err)
- goto err_put_cmpt;
-
- atomic_set(&qp->refcount, 1);
- init_completion(&qp->free);
-
return 0;
-err_put_cmpt:
- mlx4_table_put(dev, &qp_table->cmpt_table, qp->qpn);
-
err_put_rdmarc:
- mlx4_table_put(dev, &qp_table->rdmarc_table, qp->qpn);
+ mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
err_put_altc:
- mlx4_table_put(dev, &qp_table->altc_table, qp->qpn);
+ mlx4_table_put(dev, &qp_table->altc_table, qpn);
err_put_auxc:
- mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
+ mlx4_table_put(dev, &qp_table->auxc_table, qpn);
err_put_qp:
- mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
+ mlx4_table_put(dev, &qp_table->qp_table, qpn);
err_out:
return err;
}
+
+static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
+{
+ u64 param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(¶m, qpn);
+ return mlx4_cmd_imm(dev, param, ¶m, RES_QP, RES_OP_MAP_ICM,
+ MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
+ }
+ return __mlx4_qp_alloc_icm(dev, qpn);
+}
+
+void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_qp_table *qp_table = &priv->qp_table;
+
+ mlx4_table_put(dev, &qp_table->cmpt_table, qpn);
+ mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
+ mlx4_table_put(dev, &qp_table->altc_table, qpn);
+ mlx4_table_put(dev, &qp_table->auxc_table, qpn);
+ mlx4_table_put(dev, &qp_table->qp_table, qpn);
+}
+
+static void mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
+{
+ u64 in_param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, qpn);
+ if (mlx4_cmd(dev, in_param, RES_QP, RES_OP_MAP_ICM,
+ MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED))
+ mlx4_warn(dev, "Failed to free icm of qp:%d\n", qpn);
+ } else
+ __mlx4_qp_free_icm(dev, qpn);
+}
+
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_qp_table *qp_table = &priv->qp_table;
+ int err;
+
+ if (!qpn)
+ return -EINVAL;
+
+ qp->qpn = qpn;
+
+ err = mlx4_qp_alloc_icm(dev, qpn);
+ if (err)
+ return err;
+
+ spin_lock_irq(&qp_table->lock);
+ err = radix_tree_insert(&dev->qp_table_tree, qp->qpn &
+ (dev->caps.num_qps - 1), qp);
+ spin_unlock_irq(&qp_table->lock);
+ if (err)
+ goto err_icm;
+
+ atomic_set(&qp->refcount, 1);
+ init_completion(&qp->free);
+
+ return 0;
+
+err_icm:
+ mlx4_qp_free_icm(dev, qpn);
+ return err;
+}
+
EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp)
void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
- struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
-
if (atomic_dec_and_test(&qp->refcount))
complete(&qp->free);
wait_for_completion(&qp->free);
- mlx4_table_put(dev, &qp_table->cmpt_table, qp->qpn);
- mlx4_table_put(dev, &qp_table->rdmarc_table, qp->qpn);
- mlx4_table_put(dev, &qp_table->altc_table, qp->qpn);
- mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
- mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
+ mlx4_qp_free_icm(dev, qp->qpn);
}
EXPORT_SYMBOL_GPL(mlx4_qp_free);
static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
{
return mlx4_cmd(dev, 0, base_qpn, 0, MLX4_CMD_CONF_SPECIAL_QP,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_init_qp_table(struct mlx4_dev *dev)
spin_lock_init(&qp_table->lock);
INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
+ if (mlx4_is_slave(dev))
+ return 0;
/*
* We reserve 2 extra QPs per port for the special QPs. The
void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
{
+ if (mlx4_is_slave(dev))
+ return;
+
mlx4_CONF_SPECIAL_QP(dev, 0);
mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
}
return PTR_ERR(mailbox);
err = mlx4_cmd_box(dev, 0, mailbox->dma, qp->qpn, 0,
- MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
if (!err)
memcpy(context, mailbox->buf + 8, sizeof *context);
--- /dev/null
+/*
+ * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
+ * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies.
+ * All rights reserved.
+ * Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/qp.h>
+
+#include "mlx4.h"
+#include "fw.h"
+
+#define MLX4_MAC_VALID (1ull << 63)
+#define MLX4_MAC_MASK 0x7fffffffffffffffULL
+#define ETH_ALEN 6
+
+struct mac_res {
+ struct list_head list;
+ u64 mac;
+ u8 port;
+};
+
+struct res_common {
+ struct list_head list;
+ u32 res_id;
+ int owner;
+ int state;
+ int from_state;
+ int to_state;
+ int removing;
+};
+
+enum {
+ RES_ANY_BUSY = 1
+};
+
+struct res_gid {
+ struct list_head list;
+ u8 gid[16];
+ enum mlx4_protocol prot;
+};
+
+enum res_qp_states {
+ RES_QP_BUSY = RES_ANY_BUSY,
+
+ /* QP number was allocated */
+ RES_QP_RESERVED,
+
+ /* ICM memory for QP context was mapped */
+ RES_QP_MAPPED,
+
+ /* QP is in hw ownership */
+ RES_QP_HW
+};
+
+static inline const char *qp_states_str(enum res_qp_states state)
+{
+ switch (state) {
+ case RES_QP_BUSY: return "RES_QP_BUSY";
+ case RES_QP_RESERVED: return "RES_QP_RESERVED";
+ case RES_QP_MAPPED: return "RES_QP_MAPPED";
+ case RES_QP_HW: return "RES_QP_HW";
+ default: return "Unknown";
+ }
+}
+
+struct res_qp {
+ struct res_common com;
+ struct res_mtt *mtt;
+ struct res_cq *rcq;
+ struct res_cq *scq;
+ struct res_srq *srq;
+ struct list_head mcg_list;
+ spinlock_t mcg_spl;
+ int local_qpn;
+};
+
+enum res_mtt_states {
+ RES_MTT_BUSY = RES_ANY_BUSY,
+ RES_MTT_ALLOCATED,
+};
+
+static inline const char *mtt_states_str(enum res_mtt_states state)
+{
+ switch (state) {
+ case RES_MTT_BUSY: return "RES_MTT_BUSY";
+ case RES_MTT_ALLOCATED: return "RES_MTT_ALLOCATED";
+ default: return "Unknown";
+ }
+}
+
+struct res_mtt {
+ struct res_common com;
+ int order;
+ atomic_t ref_count;
+};
+
+enum res_mpt_states {
+ RES_MPT_BUSY = RES_ANY_BUSY,
+ RES_MPT_RESERVED,
+ RES_MPT_MAPPED,
+ RES_MPT_HW,
+};
+
+struct res_mpt {
+ struct res_common com;
+ struct res_mtt *mtt;
+ int key;
+};
+
+enum res_eq_states {
+ RES_EQ_BUSY = RES_ANY_BUSY,
+ RES_EQ_RESERVED,
+ RES_EQ_HW,
+};
+
+struct res_eq {
+ struct res_common com;
+ struct res_mtt *mtt;
+};
+
+enum res_cq_states {
+ RES_CQ_BUSY = RES_ANY_BUSY,
+ RES_CQ_ALLOCATED,
+ RES_CQ_HW,
+};
+
+struct res_cq {
+ struct res_common com;
+ struct res_mtt *mtt;
+ atomic_t ref_count;
+};
+
+enum res_srq_states {
+ RES_SRQ_BUSY = RES_ANY_BUSY,
+ RES_SRQ_ALLOCATED,
+ RES_SRQ_HW,
+};
+
+static inline const char *srq_states_str(enum res_srq_states state)
+{
+ switch (state) {
+ case RES_SRQ_BUSY: return "RES_SRQ_BUSY";
+ case RES_SRQ_ALLOCATED: return "RES_SRQ_ALLOCATED";
+ case RES_SRQ_HW: return "RES_SRQ_HW";
+ default: return "Unknown";
+ }
+}
+
+struct res_srq {
+ struct res_common com;
+ struct res_mtt *mtt;
+ struct res_cq *cq;
+ atomic_t ref_count;
+};
+
+enum res_counter_states {
+ RES_COUNTER_BUSY = RES_ANY_BUSY,
+ RES_COUNTER_ALLOCATED,
+};
+
+static inline const char *counter_states_str(enum res_counter_states state)
+{
+ switch (state) {
+ case RES_COUNTER_BUSY: return "RES_COUNTER_BUSY";
+ case RES_COUNTER_ALLOCATED: return "RES_COUNTER_ALLOCATED";
+ default: return "Unknown";
+ }
+}
+
+struct res_counter {
+ struct res_common com;
+ int port;
+};
+
+/* For Debug uses */
+static const char *ResourceType(enum mlx4_resource rt)
+{
+ switch (rt) {
+ case RES_QP: return "RES_QP";
+ case RES_CQ: return "RES_CQ";
+ case RES_SRQ: return "RES_SRQ";
+ case RES_MPT: return "RES_MPT";
+ case RES_MTT: return "RES_MTT";
+ case RES_MAC: return "RES_MAC";
+ case RES_EQ: return "RES_EQ";
+ case RES_COUNTER: return "RES_COUNTER";
+ default: return "Unknown resource type !!!";
+ };
+}
+
+int mlx4_init_resource_tracker(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int i;
+ int t;
+
+ priv->mfunc.master.res_tracker.slave_list =
+ kzalloc(dev->num_slaves * sizeof(struct slave_list),
+ GFP_KERNEL);
+ if (!priv->mfunc.master.res_tracker.slave_list)
+ return -ENOMEM;
+
+ for (i = 0 ; i < dev->num_slaves; i++) {
+ for (t = 0; t < MLX4_NUM_OF_RESOURCE_TYPE; ++t)
+ INIT_LIST_HEAD(&priv->mfunc.master.res_tracker.
+ slave_list[i].res_list[t]);
+ mutex_init(&priv->mfunc.master.res_tracker.slave_list[i].mutex);
+ }
+
+ mlx4_dbg(dev, "Started init_resource_tracker: %ld slaves\n",
+ dev->num_slaves);
+ for (i = 0 ; i < MLX4_NUM_OF_RESOURCE_TYPE; i++)
+ INIT_RADIX_TREE(&priv->mfunc.master.res_tracker.res_tree[i],
+ GFP_ATOMIC|__GFP_NOWARN);
+
+ spin_lock_init(&priv->mfunc.master.res_tracker.lock);
+ return 0 ;
+}
+
+void mlx4_free_resource_tracker(struct mlx4_dev *dev)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int i;
+
+ if (priv->mfunc.master.res_tracker.slave_list) {
+ for (i = 0 ; i < dev->num_slaves; i++)
+ mlx4_delete_all_resources_for_slave(dev, i);
+
+ kfree(priv->mfunc.master.res_tracker.slave_list);
+ }
+}
+
+static void update_ud_gid(struct mlx4_dev *dev,
+ struct mlx4_qp_context *qp_ctx, u8 slave)
+{
+ u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
+
+ if (MLX4_QP_ST_UD == ts)
+ qp_ctx->pri_path.mgid_index = 0x80 | slave;
+
+ mlx4_dbg(dev, "slave %d, new gid index: 0x%x ",
+ slave, qp_ctx->pri_path.mgid_index);
+}
+
+static int mpt_mask(struct mlx4_dev *dev)
+{
+ return dev->caps.num_mpts - 1;
+}
+
+static void *find_res(struct mlx4_dev *dev, int res_id,
+ enum mlx4_resource type)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ return radix_tree_lookup(&priv->mfunc.master.res_tracker.res_tree[type],
+ res_id);
+}
+
+static int get_res(struct mlx4_dev *dev, int slave, int res_id,
+ enum mlx4_resource type,
+ void *res)
+{
+ struct res_common *r;
+ int err = 0;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = find_res(dev, res_id, type);
+ if (!r) {
+ err = -ENONET;
+ goto exit;
+ }
+
+ if (r->state == RES_ANY_BUSY) {
+ err = -EBUSY;
+ goto exit;
+ }
+
+ if (r->owner != slave) {
+ err = -EPERM;
+ goto exit;
+ }
+
+ r->from_state = r->state;
+ r->state = RES_ANY_BUSY;
+ mlx4_dbg(dev, "res %s id 0x%x to busy\n",
+ ResourceType(type), r->res_id);
+
+ if (res)
+ *((struct res_common **)res) = r;
+
+exit:
+ spin_unlock_irq(mlx4_tlock(dev));
+ return err;
+}
+
+int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
+ enum mlx4_resource type,
+ int res_id, int *slave)
+{
+
+ struct res_common *r;
+ int err = -ENOENT;
+ int id = res_id;
+
+ if (type == RES_QP)
+ id &= 0x7fffff;
+ spin_lock(mlx4_tlock(dev));
+
+ r = find_res(dev, id, type);
+ if (r) {
+ *slave = r->owner;
+ err = 0;
+ }
+ spin_unlock(mlx4_tlock(dev));
+
+ return err;
+}
+
+static void put_res(struct mlx4_dev *dev, int slave, int res_id,
+ enum mlx4_resource type)
+{
+ struct res_common *r;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = find_res(dev, res_id, type);
+ if (r)
+ r->state = r->from_state;
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static struct res_common *alloc_qp_tr(int id)
+{
+ struct res_qp *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_QP_RESERVED;
+ INIT_LIST_HEAD(&ret->mcg_list);
+ spin_lock_init(&ret->mcg_spl);
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_mtt_tr(int id, int order)
+{
+ struct res_mtt *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->order = order;
+ ret->com.state = RES_MTT_ALLOCATED;
+ atomic_set(&ret->ref_count, 0);
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_mpt_tr(int id, int key)
+{
+ struct res_mpt *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_MPT_RESERVED;
+ ret->key = key;
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_eq_tr(int id)
+{
+ struct res_eq *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_EQ_RESERVED;
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_cq_tr(int id)
+{
+ struct res_cq *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_CQ_ALLOCATED;
+ atomic_set(&ret->ref_count, 0);
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_srq_tr(int id)
+{
+ struct res_srq *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_SRQ_ALLOCATED;
+ atomic_set(&ret->ref_count, 0);
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_counter_tr(int id)
+{
+ struct res_counter *ret;
+
+ ret = kzalloc(sizeof *ret, GFP_KERNEL);
+ if (!ret)
+ return NULL;
+
+ ret->com.res_id = id;
+ ret->com.state = RES_COUNTER_ALLOCATED;
+
+ return &ret->com;
+}
+
+static struct res_common *alloc_tr(int id, enum mlx4_resource type, int slave,
+ int extra)
+{
+ struct res_common *ret;
+
+ switch (type) {
+ case RES_QP:
+ ret = alloc_qp_tr(id);
+ break;
+ case RES_MPT:
+ ret = alloc_mpt_tr(id, extra);
+ break;
+ case RES_MTT:
+ ret = alloc_mtt_tr(id, extra);
+ break;
+ case RES_EQ:
+ ret = alloc_eq_tr(id);
+ break;
+ case RES_CQ:
+ ret = alloc_cq_tr(id);
+ break;
+ case RES_SRQ:
+ ret = alloc_srq_tr(id);
+ break;
+ case RES_MAC:
+ printk(KERN_ERR "implementation missing\n");
+ return NULL;
+ case RES_COUNTER:
+ ret = alloc_counter_tr(id);
+ break;
+
+ default:
+ return NULL;
+ }
+ if (ret)
+ ret->owner = slave;
+
+ return ret;
+}
+
+static int add_res_range(struct mlx4_dev *dev, int slave, int base, int count,
+ enum mlx4_resource type, int extra)
+{
+ int i;
+ int err;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct res_common **res_arr;
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct radix_tree_root *root = &tracker->res_tree[type];
+
+ res_arr = kzalloc(count * sizeof *res_arr, GFP_KERNEL);
+ if (!res_arr)
+ return -ENOMEM;
+
+ for (i = 0; i < count; ++i) {
+ res_arr[i] = alloc_tr(base + i, type, slave, extra);
+ if (!res_arr[i]) {
+ for (--i; i >= 0; --i)
+ kfree(res_arr[i]);
+
+ kfree(res_arr);
+ return -ENOMEM;
+ }
+ }
+
+ spin_lock_irq(mlx4_tlock(dev));
+ for (i = 0; i < count; ++i) {
+ if (find_res(dev, base + i, type)) {
+ err = -EEXIST;
+ goto undo;
+ }
+ err = radix_tree_insert(root, base + i, res_arr[i]);
+ if (err)
+ goto undo;
+ list_add_tail(&res_arr[i]->list,
+ &tracker->slave_list[slave].res_list[type]);
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(res_arr);
+
+ return 0;
+
+undo:
+ for (--i; i >= base; --i)
+ radix_tree_delete(&tracker->res_tree[type], i);
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ for (i = 0; i < count; ++i)
+ kfree(res_arr[i]);
+
+ kfree(res_arr);
+
+ return err;
+}
+
+static int remove_qp_ok(struct res_qp *res)
+{
+ if (res->com.state == RES_QP_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_QP_RESERVED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_mtt_ok(struct res_mtt *res, int order)
+{
+ if (res->com.state == RES_MTT_BUSY ||
+ atomic_read(&res->ref_count)) {
+ printk(KERN_DEBUG "%s-%d: state %s, ref_count %d\n",
+ __func__, __LINE__,
+ mtt_states_str(res->com.state),
+ atomic_read(&res->ref_count));
+ return -EBUSY;
+ } else if (res->com.state != RES_MTT_ALLOCATED)
+ return -EPERM;
+ else if (res->order != order)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int remove_mpt_ok(struct res_mpt *res)
+{
+ if (res->com.state == RES_MPT_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_MPT_RESERVED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_eq_ok(struct res_eq *res)
+{
+ if (res->com.state == RES_MPT_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_MPT_RESERVED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_counter_ok(struct res_counter *res)
+{
+ if (res->com.state == RES_COUNTER_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_COUNTER_ALLOCATED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_cq_ok(struct res_cq *res)
+{
+ if (res->com.state == RES_CQ_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_CQ_ALLOCATED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_srq_ok(struct res_srq *res)
+{
+ if (res->com.state == RES_SRQ_BUSY)
+ return -EBUSY;
+ else if (res->com.state != RES_SRQ_ALLOCATED)
+ return -EPERM;
+
+ return 0;
+}
+
+static int remove_ok(struct res_common *res, enum mlx4_resource type, int extra)
+{
+ switch (type) {
+ case RES_QP:
+ return remove_qp_ok((struct res_qp *)res);
+ case RES_CQ:
+ return remove_cq_ok((struct res_cq *)res);
+ case RES_SRQ:
+ return remove_srq_ok((struct res_srq *)res);
+ case RES_MPT:
+ return remove_mpt_ok((struct res_mpt *)res);
+ case RES_MTT:
+ return remove_mtt_ok((struct res_mtt *)res, extra);
+ case RES_MAC:
+ return -ENOSYS;
+ case RES_EQ:
+ return remove_eq_ok((struct res_eq *)res);
+ case RES_COUNTER:
+ return remove_counter_ok((struct res_counter *)res);
+ default:
+ return -EINVAL;
+ }
+}
+
+static int rem_res_range(struct mlx4_dev *dev, int slave, int base, int count,
+ enum mlx4_resource type, int extra)
+{
+ int i;
+ int err;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_common *r;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ for (i = base; i < base + count; ++i) {
+ r = radix_tree_lookup(&tracker->res_tree[type], i);
+ if (!r) {
+ err = -ENOENT;
+ goto out;
+ }
+ if (r->owner != slave) {
+ err = -EPERM;
+ goto out;
+ }
+ err = remove_ok(r, type, extra);
+ if (err)
+ goto out;
+ }
+
+ for (i = base; i < base + count; ++i) {
+ r = radix_tree_lookup(&tracker->res_tree[type], i);
+ radix_tree_delete(&tracker->res_tree[type], i);
+ list_del(&r->list);
+ kfree(r);
+ }
+ err = 0;
+
+out:
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static int qp_res_start_move_to(struct mlx4_dev *dev, int slave, int qpn,
+ enum res_qp_states state, struct res_qp **qp,
+ int alloc)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_qp *r;
+ int err = 0;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[RES_QP], qpn);
+ if (!r)
+ err = -ENOENT;
+ else if (r->com.owner != slave)
+ err = -EPERM;
+ else {
+ switch (state) {
+ case RES_QP_BUSY:
+ mlx4_dbg(dev, "%s: failed RES_QP, 0x%x\n",
+ __func__, r->com.res_id);
+ err = -EBUSY;
+ break;
+
+ case RES_QP_RESERVED:
+ if (r->com.state == RES_QP_MAPPED && !alloc)
+ break;
+
+ mlx4_dbg(dev, "failed RES_QP, 0x%x\n", r->com.res_id);
+ err = -EINVAL;
+ break;
+
+ case RES_QP_MAPPED:
+ if ((r->com.state == RES_QP_RESERVED && alloc) ||
+ r->com.state == RES_QP_HW)
+ break;
+ else {
+ mlx4_dbg(dev, "failed RES_QP, 0x%x\n",
+ r->com.res_id);
+ err = -EINVAL;
+ }
+
+ break;
+
+ case RES_QP_HW:
+ if (r->com.state != RES_QP_MAPPED)
+ err = -EINVAL;
+ break;
+ default:
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_QP_BUSY;
+ if (qp)
+ *qp = (struct res_qp *)r;
+ }
+ }
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static int mr_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+ enum res_mpt_states state, struct res_mpt **mpt)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_mpt *r;
+ int err = 0;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[RES_MPT], index);
+ if (!r)
+ err = -ENOENT;
+ else if (r->com.owner != slave)
+ err = -EPERM;
+ else {
+ switch (state) {
+ case RES_MPT_BUSY:
+ err = -EINVAL;
+ break;
+
+ case RES_MPT_RESERVED:
+ if (r->com.state != RES_MPT_MAPPED)
+ err = -EINVAL;
+ break;
+
+ case RES_MPT_MAPPED:
+ if (r->com.state != RES_MPT_RESERVED &&
+ r->com.state != RES_MPT_HW)
+ err = -EINVAL;
+ break;
+
+ case RES_MPT_HW:
+ if (r->com.state != RES_MPT_MAPPED)
+ err = -EINVAL;
+ break;
+ default:
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_MPT_BUSY;
+ if (mpt)
+ *mpt = (struct res_mpt *)r;
+ }
+ }
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static int eq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+ enum res_eq_states state, struct res_eq **eq)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_eq *r;
+ int err = 0;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[RES_EQ], index);
+ if (!r)
+ err = -ENOENT;
+ else if (r->com.owner != slave)
+ err = -EPERM;
+ else {
+ switch (state) {
+ case RES_EQ_BUSY:
+ err = -EINVAL;
+ break;
+
+ case RES_EQ_RESERVED:
+ if (r->com.state != RES_EQ_HW)
+ err = -EINVAL;
+ break;
+
+ case RES_EQ_HW:
+ if (r->com.state != RES_EQ_RESERVED)
+ err = -EINVAL;
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_EQ_BUSY;
+ if (eq)
+ *eq = r;
+ }
+ }
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static int cq_res_start_move_to(struct mlx4_dev *dev, int slave, int cqn,
+ enum res_cq_states state, struct res_cq **cq)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_cq *r;
+ int err;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[RES_CQ], cqn);
+ if (!r)
+ err = -ENOENT;
+ else if (r->com.owner != slave)
+ err = -EPERM;
+ else {
+ switch (state) {
+ case RES_CQ_BUSY:
+ err = -EBUSY;
+ break;
+
+ case RES_CQ_ALLOCATED:
+ if (r->com.state != RES_CQ_HW)
+ err = -EINVAL;
+ else if (atomic_read(&r->ref_count))
+ err = -EBUSY;
+ else
+ err = 0;
+ break;
+
+ case RES_CQ_HW:
+ if (r->com.state != RES_CQ_ALLOCATED)
+ err = -EINVAL;
+ else
+ err = 0;
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_CQ_BUSY;
+ if (cq)
+ *cq = r;
+ }
+ }
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static int srq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+ enum res_cq_states state, struct res_srq **srq)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_srq *r;
+ int err = 0;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[RES_SRQ], index);
+ if (!r)
+ err = -ENOENT;
+ else if (r->com.owner != slave)
+ err = -EPERM;
+ else {
+ switch (state) {
+ case RES_SRQ_BUSY:
+ err = -EINVAL;
+ break;
+
+ case RES_SRQ_ALLOCATED:
+ if (r->com.state != RES_SRQ_HW)
+ err = -EINVAL;
+ else if (atomic_read(&r->ref_count))
+ err = -EBUSY;
+ break;
+
+ case RES_SRQ_HW:
+ if (r->com.state != RES_SRQ_ALLOCATED)
+ err = -EINVAL;
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+ if (!err) {
+ r->com.from_state = r->com.state;
+ r->com.to_state = state;
+ r->com.state = RES_SRQ_BUSY;
+ if (srq)
+ *srq = r;
+ }
+ }
+
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+static void res_abort_move(struct mlx4_dev *dev, int slave,
+ enum mlx4_resource type, int id)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_common *r;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[type], id);
+ if (r && (r->owner == slave))
+ r->state = r->from_state;
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void res_end_move(struct mlx4_dev *dev, int slave,
+ enum mlx4_resource type, int id)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_common *r;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ r = radix_tree_lookup(&tracker->res_tree[type], id);
+ if (r && (r->owner == slave))
+ r->state = r->to_state;
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static int valid_reserved(struct mlx4_dev *dev, int slave, int qpn)
+{
+ return mlx4_is_qp_reserved(dev, qpn);
+}
+
+static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int err;
+ int count;
+ int align;
+ int base;
+ int qpn;
+
+ switch (op) {
+ case RES_OP_RESERVE:
+ count = get_param_l(&in_param);
+ align = get_param_h(&in_param);
+ err = __mlx4_qp_reserve_range(dev, count, align, &base);
+ if (err)
+ return err;
+
+ err = add_res_range(dev, slave, base, count, RES_QP, 0);
+ if (err) {
+ __mlx4_qp_release_range(dev, base, count);
+ return err;
+ }
+ set_param_l(out_param, base);
+ break;
+ case RES_OP_MAP_ICM:
+ qpn = get_param_l(&in_param) & 0x7fffff;
+ if (valid_reserved(dev, slave, qpn)) {
+ err = add_res_range(dev, slave, qpn, 1, RES_QP, 0);
+ if (err)
+ return err;
+ }
+
+ err = qp_res_start_move_to(dev, slave, qpn, RES_QP_MAPPED,
+ NULL, 1);
+ if (err)
+ return err;
+
+ if (!valid_reserved(dev, slave, qpn)) {
+ err = __mlx4_qp_alloc_icm(dev, qpn);
+ if (err) {
+ res_abort_move(dev, slave, RES_QP, qpn);
+ return err;
+ }
+ }
+
+ res_end_move(dev, slave, RES_QP, qpn);
+ break;
+
+ default:
+ err = -EINVAL;
+ break;
+ }
+ return err;
+}
+
+static int mtt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int err = -EINVAL;
+ int base;
+ int order;
+
+ if (op != RES_OP_RESERVE_AND_MAP)
+ return err;
+
+ order = get_param_l(&in_param);
+ base = __mlx4_alloc_mtt_range(dev, order);
+ if (base == -1)
+ return -ENOMEM;
+
+ err = add_res_range(dev, slave, base, 1, RES_MTT, order);
+ if (err)
+ __mlx4_free_mtt_range(dev, base, order);
+ else
+ set_param_l(out_param, base);
+
+ return err;
+}
+
+static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int err = -EINVAL;
+ int index;
+ int id;
+ struct res_mpt *mpt;
+
+ switch (op) {
+ case RES_OP_RESERVE:
+ index = __mlx4_mr_reserve(dev);
+ if (index == -1)
+ break;
+ id = index & mpt_mask(dev);
+
+ err = add_res_range(dev, slave, id, 1, RES_MPT, index);
+ if (err) {
+ __mlx4_mr_release(dev, index);
+ break;
+ }
+ set_param_l(out_param, index);
+ break;
+ case RES_OP_MAP_ICM:
+ index = get_param_l(&in_param);
+ id = index & mpt_mask(dev);
+ err = mr_res_start_move_to(dev, slave, id,
+ RES_MPT_MAPPED, &mpt);
+ if (err)
+ return err;
+
+ err = __mlx4_mr_alloc_icm(dev, mpt->key);
+ if (err) {
+ res_abort_move(dev, slave, RES_MPT, id);
+ return err;
+ }
+
+ res_end_move(dev, slave, RES_MPT, id);
+ break;
+ }
+ return err;
+}
+
+static int cq_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int cqn;
+ int err;
+
+ switch (op) {
+ case RES_OP_RESERVE_AND_MAP:
+ err = __mlx4_cq_alloc_icm(dev, &cqn);
+ if (err)
+ break;
+
+ err = add_res_range(dev, slave, cqn, 1, RES_CQ, 0);
+ if (err) {
+ __mlx4_cq_free_icm(dev, cqn);
+ break;
+ }
+
+ set_param_l(out_param, cqn);
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+static int srq_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int srqn;
+ int err;
+
+ switch (op) {
+ case RES_OP_RESERVE_AND_MAP:
+ err = __mlx4_srq_alloc_icm(dev, &srqn);
+ if (err)
+ break;
+
+ err = add_res_range(dev, slave, srqn, 1, RES_SRQ, 0);
+ if (err) {
+ __mlx4_srq_free_icm(dev, srqn);
+ break;
+ }
+
+ set_param_l(out_param, srqn);
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct mac_res *res;
+
+ res = kzalloc(sizeof *res, GFP_KERNEL);
+ if (!res)
+ return -ENOMEM;
+ res->mac = mac;
+ res->port = (u8) port;
+ list_add_tail(&res->list,
+ &tracker->slave_list[slave].res_list[RES_MAC]);
+ return 0;
+}
+
+static void mac_del_from_slave(struct mlx4_dev *dev, int slave, u64 mac,
+ int port)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *mac_list =
+ &tracker->slave_list[slave].res_list[RES_MAC];
+ struct mac_res *res, *tmp;
+
+ list_for_each_entry_safe(res, tmp, mac_list, list) {
+ if (res->mac == mac && res->port == (u8) port) {
+ list_del(&res->list);
+ kfree(res);
+ break;
+ }
+ }
+}
+
+static void rem_slave_macs(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *mac_list =
+ &tracker->slave_list[slave].res_list[RES_MAC];
+ struct mac_res *res, *tmp;
+
+ list_for_each_entry_safe(res, tmp, mac_list, list) {
+ list_del(&res->list);
+ __mlx4_unregister_mac(dev, res->port, res->mac);
+ kfree(res);
+ }
+}
+
+static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int err = -EINVAL;
+ int port;
+ u64 mac;
+
+ if (op != RES_OP_RESERVE_AND_MAP)
+ return err;
+
+ port = get_param_l(out_param);
+ mac = in_param;
+
+ err = __mlx4_register_mac(dev, port, mac);
+ if (err >= 0) {
+ set_param_l(out_param, err);
+ err = 0;
+ }
+
+ if (!err) {
+ err = mac_add_to_slave(dev, slave, mac, port);
+ if (err)
+ __mlx4_unregister_mac(dev, port, mac);
+ }
+ return err;
+}
+
+static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ return 0;
+}
+
+int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int alop = vhcr->op_modifier;
+
+ switch (vhcr->in_modifier) {
+ case RES_QP:
+ err = qp_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_MTT:
+ err = mtt_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_MPT:
+ err = mpt_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_CQ:
+ err = cq_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_SRQ:
+ err = srq_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_MAC:
+ err = mac_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_VLAN:
+ err = vlan_alloc_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
+
+static int qp_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param)
+{
+ int err;
+ int count;
+ int base;
+ int qpn;
+
+ switch (op) {
+ case RES_OP_RESERVE:
+ base = get_param_l(&in_param) & 0x7fffff;
+ count = get_param_h(&in_param);
+ err = rem_res_range(dev, slave, base, count, RES_QP, 0);
+ if (err)
+ break;
+ __mlx4_qp_release_range(dev, base, count);
+ break;
+ case RES_OP_MAP_ICM:
+ qpn = get_param_l(&in_param) & 0x7fffff;
+ err = qp_res_start_move_to(dev, slave, qpn, RES_QP_RESERVED,
+ NULL, 0);
+ if (err)
+ return err;
+
+ if (!valid_reserved(dev, slave, qpn))
+ __mlx4_qp_free_icm(dev, qpn);
+
+ res_end_move(dev, slave, RES_QP, qpn);
+
+ if (valid_reserved(dev, slave, qpn))
+ err = rem_res_range(dev, slave, qpn, 1, RES_QP, 0);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+ return err;
+}
+
+static int mtt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int err = -EINVAL;
+ int base;
+ int order;
+
+ if (op != RES_OP_RESERVE_AND_MAP)
+ return err;
+
+ base = get_param_l(&in_param);
+ order = get_param_h(&in_param);
+ err = rem_res_range(dev, slave, base, 1, RES_MTT, order);
+ if (!err)
+ __mlx4_free_mtt_range(dev, base, order);
+ return err;
+}
+
+static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param)
+{
+ int err = -EINVAL;
+ int index;
+ int id;
+ struct res_mpt *mpt;
+
+ switch (op) {
+ case RES_OP_RESERVE:
+ index = get_param_l(&in_param);
+ id = index & mpt_mask(dev);
+ err = get_res(dev, slave, id, RES_MPT, &mpt);
+ if (err)
+ break;
+ index = mpt->key;
+ put_res(dev, slave, id, RES_MPT);
+
+ err = rem_res_range(dev, slave, id, 1, RES_MPT, 0);
+ if (err)
+ break;
+ __mlx4_mr_release(dev, index);
+ break;
+ case RES_OP_MAP_ICM:
+ index = get_param_l(&in_param);
+ id = index & mpt_mask(dev);
+ err = mr_res_start_move_to(dev, slave, id,
+ RES_MPT_RESERVED, &mpt);
+ if (err)
+ return err;
+
+ __mlx4_mr_free_icm(dev, mpt->key);
+ res_end_move(dev, slave, RES_MPT, id);
+ return err;
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+ return err;
+}
+
+static int cq_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int cqn;
+ int err;
+
+ switch (op) {
+ case RES_OP_RESERVE_AND_MAP:
+ cqn = get_param_l(&in_param);
+ err = rem_res_range(dev, slave, cqn, 1, RES_CQ, 0);
+ if (err)
+ break;
+
+ __mlx4_cq_free_icm(dev, cqn);
+ break;
+
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
+
+static int srq_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int srqn;
+ int err;
+
+ switch (op) {
+ case RES_OP_RESERVE_AND_MAP:
+ srqn = get_param_l(&in_param);
+ err = rem_res_range(dev, slave, srqn, 1, RES_SRQ, 0);
+ if (err)
+ break;
+
+ __mlx4_srq_free_icm(dev, srqn);
+ break;
+
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
+
+static int mac_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ int port;
+ int err = 0;
+
+ switch (op) {
+ case RES_OP_RESERVE_AND_MAP:
+ port = get_param_l(out_param);
+ mac_del_from_slave(dev, slave, in_param, port);
+ __mlx4_unregister_mac(dev, port, in_param);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+
+}
+
+static int vlan_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+ u64 in_param, u64 *out_param)
+{
+ return 0;
+}
+
+int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err = -EINVAL;
+ int alop = vhcr->op_modifier;
+
+ switch (vhcr->in_modifier) {
+ case RES_QP:
+ err = qp_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param);
+ break;
+
+ case RES_MTT:
+ err = mtt_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_MPT:
+ err = mpt_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param);
+ break;
+
+ case RES_CQ:
+ err = cq_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_SRQ:
+ err = srq_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_MAC:
+ err = mac_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ case RES_VLAN:
+ err = vlan_free_res(dev, slave, vhcr->op_modifier, alop,
+ vhcr->in_param, &vhcr->out_param);
+ break;
+
+ default:
+ break;
+ }
+ return err;
+}
+
+/* ugly but other choices are uglier */
+static int mr_phys_mpt(struct mlx4_mpt_entry *mpt)
+{
+ return (be32_to_cpu(mpt->flags) >> 9) & 1;
+}
+
+static int mr_get_mtt_addr(struct mlx4_mpt_entry *mpt)
+{
+ return (int)be64_to_cpu(mpt->mtt_addr) & 0xfffffff8;
+}
+
+static int mr_get_mtt_size(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->mtt_sz);
+}
+
+static int mr_get_pdn(struct mlx4_mpt_entry *mpt)
+{
+ return be32_to_cpu(mpt->pd_flags) & 0xffffff;
+}
+
+static int qp_get_mtt_addr(struct mlx4_qp_context *qpc)
+{
+ return be32_to_cpu(qpc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int srq_get_mtt_addr(struct mlx4_srq_context *srqc)
+{
+ return be32_to_cpu(srqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
+{
+ int page_shift = (qpc->log_page_size & 0x3f) + 12;
+ int log_sq_size = (qpc->sq_size_stride >> 3) & 0xf;
+ int log_sq_sride = qpc->sq_size_stride & 7;
+ int log_rq_size = (qpc->rq_size_stride >> 3) & 0xf;
+ int log_rq_stride = qpc->rq_size_stride & 7;
+ int srq = (be32_to_cpu(qpc->srqn) >> 24) & 1;
+ int rss = (be32_to_cpu(qpc->flags) >> 13) & 1;
+ int xrc = (be32_to_cpu(qpc->local_qpn) >> 23) & 1;
+ int sq_size;
+ int rq_size;
+ int total_pages;
+ int total_mem;
+ int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+
+ sq_size = 1 << (log_sq_size + log_sq_sride + 4);
+ rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
+ total_mem = sq_size + rq_size;
+ total_pages =
+ roundup_pow_of_two((total_mem + (page_offset << 6)) >>
+ page_shift);
+
+ return total_pages;
+}
+
+static int qp_get_pdn(struct mlx4_qp_context *qpc)
+{
+ return be32_to_cpu(qpc->pd) & 0xffffff;
+}
+
+static int pdn2slave(int pdn)
+{
+ return (pdn >> NOT_MASKED_PD_BITS) - 1;
+}
+
+static int check_mtt_range(struct mlx4_dev *dev, int slave, int start,
+ int size, struct res_mtt *mtt)
+{
+ int res_start = mtt->com.res_id;
+ int res_size = (1 << mtt->order);
+
+ if (start < res_start || start + size > res_start + res_size)
+ return -EPERM;
+ return 0;
+}
+
+int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int index = vhcr->in_modifier;
+ struct res_mtt *mtt;
+ struct res_mpt *mpt;
+ int mtt_base = mr_get_mtt_addr(inbox->buf) / dev->caps.mtt_entry_sz;
+ int phys;
+ int id;
+
+ id = index & mpt_mask(dev);
+ err = mr_res_start_move_to(dev, slave, id, RES_MPT_HW, &mpt);
+ if (err)
+ return err;
+
+ phys = mr_phys_mpt(inbox->buf);
+ if (!phys) {
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto ex_abort;
+
+ err = check_mtt_range(dev, slave, mtt_base,
+ mr_get_mtt_size(inbox->buf), mtt);
+ if (err)
+ goto ex_put;
+
+ mpt->mtt = mtt;
+ }
+
+ if (pdn2slave(mr_get_pdn(inbox->buf)) != slave) {
+ err = -EPERM;
+ goto ex_put;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_put;
+
+ if (!phys) {
+ atomic_inc(&mtt->ref_count);
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ }
+
+ res_end_move(dev, slave, RES_MPT, id);
+ return 0;
+
+ex_put:
+ if (!phys)
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_abort:
+ res_abort_move(dev, slave, RES_MPT, id);
+
+ return err;
+}
+
+int mlx4_HW2SW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int index = vhcr->in_modifier;
+ struct res_mpt *mpt;
+ int id;
+
+ id = index & mpt_mask(dev);
+ err = mr_res_start_move_to(dev, slave, id, RES_MPT_MAPPED, &mpt);
+ if (err)
+ return err;
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_abort;
+
+ if (mpt->mtt)
+ atomic_dec(&mpt->mtt->ref_count);
+
+ res_end_move(dev, slave, RES_MPT, id);
+ return 0;
+
+ex_abort:
+ res_abort_move(dev, slave, RES_MPT, id);
+
+ return err;
+}
+
+int mlx4_QUERY_MPT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int index = vhcr->in_modifier;
+ struct res_mpt *mpt;
+ int id;
+
+ id = index & mpt_mask(dev);
+ err = get_res(dev, slave, id, RES_MPT, &mpt);
+ if (err)
+ return err;
+
+ if (mpt->com.from_state != RES_MPT_HW) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+out:
+ put_res(dev, slave, id, RES_MPT);
+ return err;
+}
+
+static int qp_get_rcqn(struct mlx4_qp_context *qpc)
+{
+ return be32_to_cpu(qpc->cqn_recv) & 0xffffff;
+}
+
+static int qp_get_scqn(struct mlx4_qp_context *qpc)
+{
+ return be32_to_cpu(qpc->cqn_send) & 0xffffff;
+}
+
+static u32 qp_get_srqn(struct mlx4_qp_context *qpc)
+{
+ return be32_to_cpu(qpc->srqn) & 0x1ffffff;
+}
+
+int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int qpn = vhcr->in_modifier & 0x7fffff;
+ struct res_mtt *mtt;
+ struct res_qp *qp;
+ struct mlx4_qp_context *qpc = inbox->buf + 8;
+ int mtt_base = qp_get_mtt_addr(qpc) / dev->caps.mtt_entry_sz;
+ int mtt_size = qp_get_mtt_size(qpc);
+ struct res_cq *rcq;
+ struct res_cq *scq;
+ int rcqn = qp_get_rcqn(qpc);
+ int scqn = qp_get_scqn(qpc);
+ u32 srqn = qp_get_srqn(qpc) & 0xffffff;
+ int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
+ struct res_srq *srq;
+ int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+
+ err = qp_res_start_move_to(dev, slave, qpn, RES_QP_HW, &qp, 0);
+ if (err)
+ return err;
+ qp->local_qpn = local_qpn;
+
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto ex_abort;
+
+ err = check_mtt_range(dev, slave, mtt_base, mtt_size, mtt);
+ if (err)
+ goto ex_put_mtt;
+
+ if (pdn2slave(qp_get_pdn(qpc)) != slave) {
+ err = -EPERM;
+ goto ex_put_mtt;
+ }
+
+ err = get_res(dev, slave, rcqn, RES_CQ, &rcq);
+ if (err)
+ goto ex_put_mtt;
+
+ if (scqn != rcqn) {
+ err = get_res(dev, slave, scqn, RES_CQ, &scq);
+ if (err)
+ goto ex_put_rcq;
+ } else
+ scq = rcq;
+
+ if (use_srq) {
+ err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+ if (err)
+ goto ex_put_scq;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_put_srq;
+ atomic_inc(&mtt->ref_count);
+ qp->mtt = mtt;
+ atomic_inc(&rcq->ref_count);
+ qp->rcq = rcq;
+ atomic_inc(&scq->ref_count);
+ qp->scq = scq;
+
+ if (scqn != rcqn)
+ put_res(dev, slave, scqn, RES_CQ);
+
+ if (use_srq) {
+ atomic_inc(&srq->ref_count);
+ put_res(dev, slave, srqn, RES_SRQ);
+ qp->srq = srq;
+ }
+ put_res(dev, slave, rcqn, RES_CQ);
+ put_res(dev, slave, mtt_base, RES_MTT);
+ res_end_move(dev, slave, RES_QP, qpn);
+
+ return 0;
+
+ex_put_srq:
+ if (use_srq)
+ put_res(dev, slave, srqn, RES_SRQ);
+ex_put_scq:
+ if (scqn != rcqn)
+ put_res(dev, slave, scqn, RES_CQ);
+ex_put_rcq:
+ put_res(dev, slave, rcqn, RES_CQ);
+ex_put_mtt:
+ put_res(dev, slave, mtt_base, RES_MTT);
+ex_abort:
+ res_abort_move(dev, slave, RES_QP, qpn);
+
+ return err;
+}
+
+static int eq_get_mtt_addr(struct mlx4_eq_context *eqc)
+{
+ return be32_to_cpu(eqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int eq_get_mtt_size(struct mlx4_eq_context *eqc)
+{
+ int log_eq_size = eqc->log_eq_size & 0x1f;
+ int page_shift = (eqc->log_page_size & 0x3f) + 12;
+
+ if (log_eq_size + 5 < page_shift)
+ return 1;
+
+ return 1 << (log_eq_size + 5 - page_shift);
+}
+
+static int cq_get_mtt_addr(struct mlx4_cq_context *cqc)
+{
+ return be32_to_cpu(cqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int cq_get_mtt_size(struct mlx4_cq_context *cqc)
+{
+ int log_cq_size = (be32_to_cpu(cqc->logsize_usrpage) >> 24) & 0x1f;
+ int page_shift = (cqc->log_page_size & 0x3f) + 12;
+
+ if (log_cq_size + 5 < page_shift)
+ return 1;
+
+ return 1 << (log_cq_size + 5 - page_shift);
+}
+
+int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int eqn = vhcr->in_modifier;
+ int res_id = (slave << 8) | eqn;
+ struct mlx4_eq_context *eqc = inbox->buf;
+ int mtt_base = eq_get_mtt_addr(eqc) / dev->caps.mtt_entry_sz;
+ int mtt_size = eq_get_mtt_size(eqc);
+ struct res_eq *eq;
+ struct res_mtt *mtt;
+
+ err = add_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+ if (err)
+ return err;
+ err = eq_res_start_move_to(dev, slave, res_id, RES_EQ_HW, &eq);
+ if (err)
+ goto out_add;
+
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto out_move;
+
+ err = check_mtt_range(dev, slave, mtt_base, mtt_size, mtt);
+ if (err)
+ goto out_put;
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto out_put;
+
+ atomic_inc(&mtt->ref_count);
+ eq->mtt = mtt;
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ res_end_move(dev, slave, RES_EQ, res_id);
+ return 0;
+
+out_put:
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+out_move:
+ res_abort_move(dev, slave, RES_EQ, res_id);
+out_add:
+ rem_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+ return err;
+}
+
+static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start,
+ int len, struct res_mtt **res)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct res_mtt *mtt;
+ int err = -EINVAL;
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry(mtt, &tracker->slave_list[slave].res_list[RES_MTT],
+ com.list) {
+ if (!check_mtt_range(dev, slave, start, len, mtt)) {
+ *res = mtt;
+ mtt->com.from_state = mtt->com.state;
+ mtt->com.state = RES_MTT_BUSY;
+ err = 0;
+ break;
+ }
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return err;
+}
+
+int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_mtt mtt;
+ __be64 *page_list = inbox->buf;
+ u64 *pg_list = (u64 *)page_list;
+ int i;
+ struct res_mtt *rmtt = NULL;
+ int start = be64_to_cpu(page_list[0]);
+ int npages = vhcr->in_modifier;
+ int err;
+
+ err = get_containing_mtt(dev, slave, start, npages, &rmtt);
+ if (err)
+ return err;
+
+ /* Call the SW implementation of write_mtt:
+ * - Prepare a dummy mtt struct
+ * - Translate inbox contents to simple addresses in host endianess */
+ mtt.offset = 0; /* TBD this is broken but I don't handle it since
+ we don't really use it */
+ mtt.order = 0;
+ mtt.page_shift = 0;
+ for (i = 0; i < npages; ++i)
+ pg_list[i + 2] = (be64_to_cpu(page_list[i + 2]) & ~1ULL);
+
+ err = __mlx4_write_mtt(dev, &mtt, be64_to_cpu(page_list[0]), npages,
+ ((u64 *)page_list + 2));
+
+ if (rmtt)
+ put_res(dev, slave, rmtt->com.res_id, RES_MTT);
+
+ return err;
+}
+
+int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int eqn = vhcr->in_modifier;
+ int res_id = eqn | (slave << 8);
+ struct res_eq *eq;
+ int err;
+
+ err = eq_res_start_move_to(dev, slave, res_id, RES_EQ_RESERVED, &eq);
+ if (err)
+ return err;
+
+ err = get_res(dev, slave, eq->mtt->com.res_id, RES_MTT, NULL);
+ if (err)
+ goto ex_abort;
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_put;
+
+ atomic_dec(&eq->mtt->ref_count);
+ put_res(dev, slave, eq->mtt->com.res_id, RES_MTT);
+ res_end_move(dev, slave, RES_EQ, res_id);
+ rem_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+
+ return 0;
+
+ex_put:
+ put_res(dev, slave, eq->mtt->com.res_id, RES_MTT);
+ex_abort:
+ res_abort_move(dev, slave, RES_EQ, res_id);
+
+ return err;
+}
+
+int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_slave_event_eq_info *event_eq;
+ struct mlx4_cmd_mailbox *mailbox;
+ u32 in_modifier = 0;
+ int err;
+ int res_id;
+ struct res_eq *req;
+
+ if (!priv->mfunc.master.slave_state)
+ return -EINVAL;
+
+ event_eq = &priv->mfunc.master.slave_state[slave].event_eq;
+
+ /* Create the event only if the slave is registered */
+ if ((event_eq->event_type & (1 << eqe->type)) == 0)
+ return 0;
+
+ mutex_lock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+ res_id = (slave << 8) | event_eq->eqn;
+ err = get_res(dev, slave, res_id, RES_EQ, &req);
+ if (err)
+ goto unlock;
+
+ if (req->com.from_state != RES_EQ_HW) {
+ err = -EINVAL;
+ goto put;
+ }
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ err = PTR_ERR(mailbox);
+ goto put;
+ }
+
+ if (eqe->type == MLX4_EVENT_TYPE_CMD) {
+ ++event_eq->token;
+ eqe->event.cmd.token = cpu_to_be16(event_eq->token);
+ }
+
+ memcpy(mailbox->buf, (u8 *) eqe, 28);
+
+ in_modifier = (slave & 0xff) | ((event_eq->eqn & 0xff) << 16);
+
+ err = mlx4_cmd(dev, mailbox->dma, in_modifier, 0,
+ MLX4_CMD_GEN_EQE, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_NATIVE);
+
+ put_res(dev, slave, res_id, RES_EQ);
+ mutex_unlock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+
+put:
+ put_res(dev, slave, res_id, RES_EQ);
+
+unlock:
+ mutex_unlock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+ return err;
+}
+
+int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int eqn = vhcr->in_modifier;
+ int res_id = eqn | (slave << 8);
+ struct res_eq *eq;
+ int err;
+
+ err = get_res(dev, slave, res_id, RES_EQ, &eq);
+ if (err)
+ return err;
+
+ if (eq->com.from_state != RES_EQ_HW) {
+ err = -EINVAL;
+ goto ex_put;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+ex_put:
+ put_res(dev, slave, res_id, RES_EQ);
+ return err;
+}
+
+int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int cqn = vhcr->in_modifier;
+ struct mlx4_cq_context *cqc = inbox->buf;
+ int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
+ struct res_cq *cq;
+ struct res_mtt *mtt;
+
+ err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq);
+ if (err)
+ return err;
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto out_move;
+ err = check_mtt_range(dev, slave, mtt_base, cq_get_mtt_size(cqc), mtt);
+ if (err)
+ goto out_put;
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto out_put;
+ atomic_inc(&mtt->ref_count);
+ cq->mtt = mtt;
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ res_end_move(dev, slave, RES_CQ, cqn);
+ return 0;
+
+out_put:
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+out_move:
+ res_abort_move(dev, slave, RES_CQ, cqn);
+ return err;
+}
+
+int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int cqn = vhcr->in_modifier;
+ struct res_cq *cq;
+
+ err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq);
+ if (err)
+ return err;
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto out_move;
+ atomic_dec(&cq->mtt->ref_count);
+ res_end_move(dev, slave, RES_CQ, cqn);
+ return 0;
+
+out_move:
+ res_abort_move(dev, slave, RES_CQ, cqn);
+ return err;
+}
+
+int mlx4_QUERY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int cqn = vhcr->in_modifier;
+ struct res_cq *cq;
+ int err;
+
+ err = get_res(dev, slave, cqn, RES_CQ, &cq);
+ if (err)
+ return err;
+
+ if (cq->com.from_state != RES_CQ_HW)
+ goto ex_put;
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ex_put:
+ put_res(dev, slave, cqn, RES_CQ);
+
+ return err;
+}
+
+static int handle_resize(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd,
+ struct res_cq *cq)
+{
+ int err;
+ struct res_mtt *orig_mtt;
+ struct res_mtt *mtt;
+ struct mlx4_cq_context *cqc = inbox->buf;
+ int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
+
+ err = get_res(dev, slave, cq->mtt->com.res_id, RES_MTT, &orig_mtt);
+ if (err)
+ return err;
+
+ if (orig_mtt != cq->mtt) {
+ err = -EINVAL;
+ goto ex_put;
+ }
+
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto ex_put;
+
+ err = check_mtt_range(dev, slave, mtt_base, cq_get_mtt_size(cqc), mtt);
+ if (err)
+ goto ex_put1;
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_put1;
+ atomic_dec(&orig_mtt->ref_count);
+ put_res(dev, slave, orig_mtt->com.res_id, RES_MTT);
+ atomic_inc(&mtt->ref_count);
+ cq->mtt = mtt;
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ return 0;
+
+ex_put1:
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_put:
+ put_res(dev, slave, orig_mtt->com.res_id, RES_MTT);
+
+ return err;
+
+}
+
+int mlx4_MODIFY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int cqn = vhcr->in_modifier;
+ struct res_cq *cq;
+ int err;
+
+ err = get_res(dev, slave, cqn, RES_CQ, &cq);
+ if (err)
+ return err;
+
+ if (cq->com.from_state != RES_CQ_HW)
+ goto ex_put;
+
+ if (vhcr->op_modifier == 0) {
+ err = handle_resize(dev, slave, vhcr, inbox, outbox, cmd, cq);
+ if (err)
+ goto ex_put;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ex_put:
+ put_res(dev, slave, cqn, RES_CQ);
+
+ return err;
+}
+
+static int srq_get_pdn(struct mlx4_srq_context *srqc)
+{
+ return be32_to_cpu(srqc->pd) & 0xffffff;
+}
+
+static int srq_get_mtt_size(struct mlx4_srq_context *srqc)
+{
+ int log_srq_size = (be32_to_cpu(srqc->state_logsize_srqn) >> 24) & 0xf;
+ int log_rq_stride = srqc->logstride & 7;
+ int page_shift = (srqc->log_page_size & 0x3f) + 12;
+
+ if (log_srq_size + log_rq_stride + 4 < page_shift)
+ return 1;
+
+ return 1 << (log_srq_size + log_rq_stride + 4 - page_shift);
+}
+
+int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int srqn = vhcr->in_modifier;
+ struct res_mtt *mtt;
+ struct res_srq *srq;
+ struct mlx4_srq_context *srqc = inbox->buf;
+ int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz;
+
+ if (srqn != (be32_to_cpu(srqc->state_logsize_srqn) & 0xffffff))
+ return -EINVAL;
+
+ err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_HW, &srq);
+ if (err)
+ return err;
+ err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+ if (err)
+ goto ex_abort;
+ err = check_mtt_range(dev, slave, mtt_base, srq_get_mtt_size(srqc),
+ mtt);
+ if (err)
+ goto ex_put_mtt;
+
+ if (pdn2slave(srq_get_pdn(srqc)) != slave) {
+ err = -EPERM;
+ goto ex_put_mtt;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_put_mtt;
+
+ atomic_inc(&mtt->ref_count);
+ srq->mtt = mtt;
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ res_end_move(dev, slave, RES_SRQ, srqn);
+ return 0;
+
+ex_put_mtt:
+ put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_abort:
+ res_abort_move(dev, slave, RES_SRQ, srqn);
+
+ return err;
+}
+
+int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int srqn = vhcr->in_modifier;
+ struct res_srq *srq;
+
+ err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq);
+ if (err)
+ return err;
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_abort;
+ atomic_dec(&srq->mtt->ref_count);
+ if (srq->cq)
+ atomic_dec(&srq->cq->ref_count);
+ res_end_move(dev, slave, RES_SRQ, srqn);
+
+ return 0;
+
+ex_abort:
+ res_abort_move(dev, slave, RES_SRQ, srqn);
+
+ return err;
+}
+
+int mlx4_QUERY_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int srqn = vhcr->in_modifier;
+ struct res_srq *srq;
+
+ err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+ if (err)
+ return err;
+ if (srq->com.from_state != RES_SRQ_HW) {
+ err = -EBUSY;
+ goto out;
+ }
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+ put_res(dev, slave, srqn, RES_SRQ);
+ return err;
+}
+
+int mlx4_ARM_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int srqn = vhcr->in_modifier;
+ struct res_srq *srq;
+
+ err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+ if (err)
+ return err;
+
+ if (srq->com.from_state != RES_SRQ_HW) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+ put_res(dev, slave, srqn, RES_SRQ);
+ return err;
+}
+
+int mlx4_GEN_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int qpn = vhcr->in_modifier & 0x7fffff;
+ struct res_qp *qp;
+
+ err = get_res(dev, slave, qpn, RES_QP, &qp);
+ if (err)
+ return err;
+ if (qp->com.from_state != RES_QP_HW) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+ put_res(dev, slave, qpn, RES_QP);
+ return err;
+}
+
+int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_qp_context *qpc = inbox->buf + 8;
+
+ update_ud_gid(dev, qpc, (u8)slave);
+
+ return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+}
+
+int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int qpn = vhcr->in_modifier & 0x7fffff;
+ struct res_qp *qp;
+
+ err = qp_res_start_move_to(dev, slave, qpn, RES_QP_MAPPED, &qp, 0);
+ if (err)
+ return err;
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ if (err)
+ goto ex_abort;
+
+ atomic_dec(&qp->mtt->ref_count);
+ atomic_dec(&qp->rcq->ref_count);
+ atomic_dec(&qp->scq->ref_count);
+ if (qp->srq)
+ atomic_dec(&qp->srq->ref_count);
+ res_end_move(dev, slave, RES_QP, qpn);
+ return 0;
+
+ex_abort:
+ res_abort_move(dev, slave, RES_QP, qpn);
+
+ return err;
+}
+
+static struct res_gid *find_gid(struct mlx4_dev *dev, int slave,
+ struct res_qp *rqp, u8 *gid)
+{
+ struct res_gid *res;
+
+ list_for_each_entry(res, &rqp->mcg_list, list) {
+ if (!memcmp(res->gid, gid, 16))
+ return res;
+ }
+ return NULL;
+}
+
+static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp,
+ u8 *gid, enum mlx4_protocol prot)
+{
+ struct res_gid *res;
+ int err;
+
+ res = kzalloc(sizeof *res, GFP_KERNEL);
+ if (!res)
+ return -ENOMEM;
+
+ spin_lock_irq(&rqp->mcg_spl);
+ if (find_gid(dev, slave, rqp, gid)) {
+ kfree(res);
+ err = -EEXIST;
+ } else {
+ memcpy(res->gid, gid, 16);
+ res->prot = prot;
+ list_add_tail(&res->list, &rqp->mcg_list);
+ err = 0;
+ }
+ spin_unlock_irq(&rqp->mcg_spl);
+
+ return err;
+}
+
+static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp,
+ u8 *gid, enum mlx4_protocol prot)
+{
+ struct res_gid *res;
+ int err;
+
+ spin_lock_irq(&rqp->mcg_spl);
+ res = find_gid(dev, slave, rqp, gid);
+ if (!res || res->prot != prot)
+ err = -EINVAL;
+ else {
+ list_del(&res->list);
+ kfree(res);
+ err = 0;
+ }
+ spin_unlock_irq(&rqp->mcg_spl);
+
+ return err;
+}
+
+int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ struct mlx4_qp qp; /* dummy for calling attach/detach */
+ u8 *gid = inbox->buf;
+ enum mlx4_protocol prot = (vhcr->in_modifier >> 28) & 0x7;
+ int err, err1;
+ int qpn;
+ struct res_qp *rqp;
+ int attach = vhcr->op_modifier;
+ int block_loopback = vhcr->in_modifier >> 31;
+ u8 steer_type_mask = 2;
+ enum mlx4_steer_type type = gid[7] & steer_type_mask;
+
+ qpn = vhcr->in_modifier & 0xffffff;
+ err = get_res(dev, slave, qpn, RES_QP, &rqp);
+ if (err)
+ return err;
+
+ qp.qpn = qpn;
+ if (attach) {
+ err = add_mcg_res(dev, slave, rqp, gid, prot);
+ if (err)
+ goto ex_put;
+
+ err = mlx4_qp_attach_common(dev, &qp, gid,
+ block_loopback, prot, type);
+ if (err)
+ goto ex_rem;
+ } else {
+ err = rem_mcg_res(dev, slave, rqp, gid, prot);
+ if (err)
+ goto ex_put;
+ err = mlx4_qp_detach_common(dev, &qp, gid, prot, type);
+ }
+
+ put_res(dev, slave, qpn, RES_QP);
+ return 0;
+
+ex_rem:
+ /* ignore error return below, already in error */
+ err1 = rem_mcg_res(dev, slave, rqp, gid, prot);
+ex_put:
+ put_res(dev, slave, qpn, RES_QP);
+
+ return err;
+}
+
+enum {
+ BUSY_MAX_RETRIES = 10
+};
+
+int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ int err;
+ int index = vhcr->in_modifier & 0xffff;
+
+ err = get_res(dev, slave, index, RES_COUNTER, NULL);
+ if (err)
+ return err;
+
+ err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ put_res(dev, slave, index, RES_COUNTER);
+ return err;
+}
+
+static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp)
+{
+ struct res_gid *rgid;
+ struct res_gid *tmp;
+ int err;
+ struct mlx4_qp qp; /* dummy for calling attach/detach */
+
+ list_for_each_entry_safe(rgid, tmp, &rqp->mcg_list, list) {
+ qp.qpn = rqp->local_qpn;
+ err = mlx4_qp_detach_common(dev, &qp, rgid->gid, rgid->prot,
+ MLX4_MC_STEER);
+ list_del(&rgid->list);
+ kfree(rgid);
+ }
+}
+
+static int _move_all_busy(struct mlx4_dev *dev, int slave,
+ enum mlx4_resource type, int print)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker =
+ &priv->mfunc.master.res_tracker;
+ struct list_head *rlist = &tracker->slave_list[slave].res_list[type];
+ struct res_common *r;
+ struct res_common *tmp;
+ int busy;
+
+ busy = 0;
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(r, tmp, rlist, list) {
+ if (r->owner == slave) {
+ if (!r->removing) {
+ if (r->state == RES_ANY_BUSY) {
+ if (print)
+ mlx4_dbg(dev,
+ "%s id 0x%x is busy\n",
+ ResourceType(type),
+ r->res_id);
+ ++busy;
+ } else {
+ r->from_state = r->state;
+ r->state = RES_ANY_BUSY;
+ r->removing = 1;
+ }
+ }
+ }
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+
+ return busy;
+}
+
+static int move_all_busy(struct mlx4_dev *dev, int slave,
+ enum mlx4_resource type)
+{
+ unsigned long begin;
+ int busy;
+
+ begin = jiffies;
+ do {
+ busy = _move_all_busy(dev, slave, type, 0);
+ if (time_after(jiffies, begin + 5 * HZ))
+ break;
+ if (busy)
+ cond_resched();
+ } while (busy);
+
+ if (busy)
+ busy = _move_all_busy(dev, slave, type, 1);
+
+ return busy;
+}
+static void rem_slave_qps(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *qp_list =
+ &tracker->slave_list[slave].res_list[RES_QP];
+ struct res_qp *qp;
+ struct res_qp *tmp;
+ int state;
+ u64 in_param;
+ int qpn;
+ int err;
+
+ err = move_all_busy(dev, slave, RES_QP);
+ if (err)
+ mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy"
+ "for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(qp, tmp, qp_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (qp->com.owner == slave) {
+ qpn = qp->com.res_id;
+ detach_qp(dev, slave, qp);
+ state = qp->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_QP_RESERVED:
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_QP],
+ qp->com.res_id);
+ list_del(&qp->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(qp);
+ state = 0;
+ break;
+ case RES_QP_MAPPED:
+ if (!valid_reserved(dev, slave, qpn))
+ __mlx4_qp_free_icm(dev, qpn);
+ state = RES_QP_RESERVED;
+ break;
+ case RES_QP_HW:
+ in_param = slave;
+ err = mlx4_cmd(dev, in_param,
+ qp->local_qpn, 2,
+ MLX4_CMD_2RST_QP,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ mlx4_dbg(dev, "rem_slave_qps: failed"
+ " to move slave %d qpn %d to"
+ " reset\n", slave,
+ qp->local_qpn);
+ atomic_dec(&qp->rcq->ref_count);
+ atomic_dec(&qp->scq->ref_count);
+ atomic_dec(&qp->mtt->ref_count);
+ if (qp->srq)
+ atomic_dec(&qp->srq->ref_count);
+ state = RES_QP_MAPPED;
+ break;
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *srq_list =
+ &tracker->slave_list[slave].res_list[RES_SRQ];
+ struct res_srq *srq;
+ struct res_srq *tmp;
+ int state;
+ u64 in_param;
+ LIST_HEAD(tlist);
+ int srqn;
+ int err;
+
+ err = move_all_busy(dev, slave, RES_SRQ);
+ if (err)
+ mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs to "
+ "busy for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(srq, tmp, srq_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (srq->com.owner == slave) {
+ srqn = srq->com.res_id;
+ state = srq->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_SRQ_ALLOCATED:
+ __mlx4_srq_free_icm(dev, srqn);
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_SRQ],
+ srqn);
+ list_del(&srq->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(srq);
+ state = 0;
+ break;
+
+ case RES_SRQ_HW:
+ in_param = slave;
+ err = mlx4_cmd(dev, in_param, srqn, 1,
+ MLX4_CMD_HW2SW_SRQ,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ mlx4_dbg(dev, "rem_slave_srqs: failed"
+ " to move slave %d srq %d to"
+ " SW ownership\n",
+ slave, srqn);
+
+ atomic_dec(&srq->mtt->ref_count);
+ if (srq->cq)
+ atomic_dec(&srq->cq->ref_count);
+ state = RES_SRQ_ALLOCATED;
+ break;
+
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *cq_list =
+ &tracker->slave_list[slave].res_list[RES_CQ];
+ struct res_cq *cq;
+ struct res_cq *tmp;
+ int state;
+ u64 in_param;
+ LIST_HEAD(tlist);
+ int cqn;
+ int err;
+
+ err = move_all_busy(dev, slave, RES_CQ);
+ if (err)
+ mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs to "
+ "busy for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(cq, tmp, cq_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (cq->com.owner == slave && !atomic_read(&cq->ref_count)) {
+ cqn = cq->com.res_id;
+ state = cq->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_CQ_ALLOCATED:
+ __mlx4_cq_free_icm(dev, cqn);
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_CQ],
+ cqn);
+ list_del(&cq->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(cq);
+ state = 0;
+ break;
+
+ case RES_CQ_HW:
+ in_param = slave;
+ err = mlx4_cmd(dev, in_param, cqn, 1,
+ MLX4_CMD_HW2SW_CQ,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ mlx4_dbg(dev, "rem_slave_cqs: failed"
+ " to move slave %d cq %d to"
+ " SW ownership\n",
+ slave, cqn);
+ atomic_dec(&cq->mtt->ref_count);
+ state = RES_CQ_ALLOCATED;
+ break;
+
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *mpt_list =
+ &tracker->slave_list[slave].res_list[RES_MPT];
+ struct res_mpt *mpt;
+ struct res_mpt *tmp;
+ int state;
+ u64 in_param;
+ LIST_HEAD(tlist);
+ int mptn;
+ int err;
+
+ err = move_all_busy(dev, slave, RES_MPT);
+ if (err)
+ mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts to "
+ "busy for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(mpt, tmp, mpt_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (mpt->com.owner == slave) {
+ mptn = mpt->com.res_id;
+ state = mpt->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_MPT_RESERVED:
+ __mlx4_mr_release(dev, mpt->key);
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_MPT],
+ mptn);
+ list_del(&mpt->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(mpt);
+ state = 0;
+ break;
+
+ case RES_MPT_MAPPED:
+ __mlx4_mr_free_icm(dev, mpt->key);
+ state = RES_MPT_RESERVED;
+ break;
+
+ case RES_MPT_HW:
+ in_param = slave;
+ err = mlx4_cmd(dev, in_param, mptn, 0,
+ MLX4_CMD_HW2SW_MPT,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ mlx4_dbg(dev, "rem_slave_mrs: failed"
+ " to move slave %d mpt %d to"
+ " SW ownership\n",
+ slave, mptn);
+ if (mpt->mtt)
+ atomic_dec(&mpt->mtt->ref_count);
+ state = RES_MPT_MAPPED;
+ break;
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_mtts(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker =
+ &priv->mfunc.master.res_tracker;
+ struct list_head *mtt_list =
+ &tracker->slave_list[slave].res_list[RES_MTT];
+ struct res_mtt *mtt;
+ struct res_mtt *tmp;
+ int state;
+ LIST_HEAD(tlist);
+ int base;
+ int err;
+
+ err = move_all_busy(dev, slave, RES_MTT);
+ if (err)
+ mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts to "
+ "busy for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(mtt, tmp, mtt_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (mtt->com.owner == slave) {
+ base = mtt->com.res_id;
+ state = mtt->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_MTT_ALLOCATED:
+ __mlx4_free_mtt_range(dev, base,
+ mtt->order);
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_MTT],
+ base);
+ list_del(&mtt->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(mtt);
+ state = 0;
+ break;
+
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *eq_list =
+ &tracker->slave_list[slave].res_list[RES_EQ];
+ struct res_eq *eq;
+ struct res_eq *tmp;
+ int err;
+ int state;
+ LIST_HEAD(tlist);
+ int eqn;
+ struct mlx4_cmd_mailbox *mailbox;
+
+ err = move_all_busy(dev, slave, RES_EQ);
+ if (err)
+ mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs to "
+ "busy for slave %d\n", slave);
+
+ spin_lock_irq(mlx4_tlock(dev));
+ list_for_each_entry_safe(eq, tmp, eq_list, com.list) {
+ spin_unlock_irq(mlx4_tlock(dev));
+ if (eq->com.owner == slave) {
+ eqn = eq->com.res_id;
+ state = eq->com.from_state;
+ while (state != 0) {
+ switch (state) {
+ case RES_EQ_RESERVED:
+ spin_lock_irq(mlx4_tlock(dev));
+ radix_tree_delete(&tracker->res_tree[RES_EQ],
+ eqn);
+ list_del(&eq->com.list);
+ spin_unlock_irq(mlx4_tlock(dev));
+ kfree(eq);
+ state = 0;
+ break;
+
+ case RES_EQ_HW:
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ cond_resched();
+ continue;
+ }
+ err = mlx4_cmd_box(dev, slave, 0,
+ eqn & 0xff, 0,
+ MLX4_CMD_HW2SW_EQ,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ mlx4_dbg(dev, "rem_slave_eqs: failed"
+ " to move slave %d eqs %d to"
+ " SW ownership\n", slave, eqn);
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ if (!err) {
+ atomic_dec(&eq->mtt->ref_count);
+ state = RES_EQ_RESERVED;
+ }
+ break;
+
+ default:
+ state = 0;
+ }
+ }
+ }
+ spin_lock_irq(mlx4_tlock(dev));
+ }
+ spin_unlock_irq(mlx4_tlock(dev));
+}
+
+void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ mutex_lock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
+ /*VLAN*/
+ rem_slave_macs(dev, slave);
+ rem_slave_qps(dev, slave);
+ rem_slave_srqs(dev, slave);
+ rem_slave_cqs(dev, slave);
+ rem_slave_mrs(dev, slave);
+ rem_slave_eqs(dev, slave);
+ rem_slave_mtts(dev, slave);
+ mutex_unlock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
+}
int err = 0;
err = mlx4_cmd_imm(dev, 0, &out_param, port, 0,
- MLX4_CMD_SENSE_PORT, MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_SENSE_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
if (err) {
mlx4_err(dev, "Sense command failed for port: %d\n", port);
return err;
* SOFTWARE.
*/
+#include <linux/init.h>
+
#include <linux/mlx4/cmd.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include "mlx4.h"
#include "icm.h"
-struct mlx4_srq_context {
- __be32 state_logsize_srqn;
- u8 logstride;
- u8 reserved1;
- __be16 xrcd;
- __be32 pg_offset_cqn;
- u32 reserved2;
- u8 log_page_size;
- u8 reserved3[2];
- u8 mtt_base_addr_h;
- __be32 mtt_base_addr_l;
- __be32 pd;
- __be16 limit_watermark;
- __be16 wqe_cnt;
- u16 reserved4;
- __be16 wqe_counter;
- u32 reserved5;
- __be64 db_rec_addr;
-};
-
void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
{
struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
static int mlx4_SW2HW_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int srq_num)
{
- return mlx4_cmd(dev, mailbox->dma, srq_num, 0, MLX4_CMD_SW2HW_SRQ,
- MLX4_CMD_TIME_CLASS_A);
+ return mlx4_cmd(dev, mailbox->dma | dev->caps.function, srq_num, 0,
+ MLX4_CMD_SW2HW_SRQ, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_WRAPPED);
}
static int mlx4_HW2SW_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
{
return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, srq_num,
mailbox ? 0 : 1, MLX4_CMD_HW2SW_SRQ,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
static int mlx4_ARM_SRQ(struct mlx4_dev *dev, int srq_num, int limit_watermark)
{
return mlx4_cmd(dev, limit_watermark, srq_num, 0, MLX4_CMD_ARM_SRQ,
- MLX4_CMD_TIME_CLASS_B);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
}
static int mlx4_QUERY_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
int srq_num)
{
return mlx4_cmd_box(dev, 0, mailbox->dma, srq_num, 0, MLX4_CMD_QUERY_SRQ,
- MLX4_CMD_TIME_CLASS_A);
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}
-int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
- struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq)
+int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
{
struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
- struct mlx4_cmd_mailbox *mailbox;
- struct mlx4_srq_context *srq_context;
- u64 mtt_addr;
int err;
- srq->srqn = mlx4_bitmap_alloc(&srq_table->bitmap);
- if (srq->srqn == -1)
+
+ *srqn = mlx4_bitmap_alloc(&srq_table->bitmap);
+ if (*srqn == -1)
return -ENOMEM;
- err = mlx4_table_get(dev, &srq_table->table, srq->srqn);
+ err = mlx4_table_get(dev, &srq_table->table, *srqn);
if (err)
goto err_out;
- err = mlx4_table_get(dev, &srq_table->cmpt_table, srq->srqn);
+ err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn);
if (err)
goto err_put;
+ return 0;
+
+err_put:
+ mlx4_table_put(dev, &srq_table->table, *srqn);
+
+err_out:
+ mlx4_bitmap_free(&srq_table->bitmap, *srqn);
+ return err;
+}
+
+static int mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
+{
+ u64 out_param;
+ int err;
+
+ if (mlx4_is_mfunc(dev)) {
+ err = mlx4_cmd_imm(dev, 0, &out_param, RES_SRQ,
+ RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_ALLOC_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+ if (!err)
+ *srqn = get_param_l(&out_param);
+
+ return err;
+ }
+ return __mlx4_srq_alloc_icm(dev, srqn);
+}
+
+void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn)
+{
+ struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
+
+ mlx4_table_put(dev, &srq_table->cmpt_table, srqn);
+ mlx4_table_put(dev, &srq_table->table, srqn);
+ mlx4_bitmap_free(&srq_table->bitmap, srqn);
+}
+
+static void mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn)
+{
+ u64 in_param;
+
+ if (mlx4_is_mfunc(dev)) {
+ set_param_l(&in_param, srqn);
+ if (mlx4_cmd(dev, in_param, RES_SRQ, RES_OP_RESERVE_AND_MAP,
+ MLX4_CMD_FREE_RES,
+ MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+ mlx4_warn(dev, "Failed freeing cq:%d\n", srqn);
+ return;
+ }
+ __mlx4_srq_free_icm(dev, srqn);
+}
+
+int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
+ struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq)
+{
+ struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_srq_context *srq_context;
+ u64 mtt_addr;
+ int err;
+
+ err = mlx4_srq_alloc_icm(dev, &srq->srqn);
+ if (err)
+ return err;
spin_lock_irq(&srq_table->lock);
err = radix_tree_insert(&srq_table->tree, srq->srqn, srq);
spin_unlock_irq(&srq_table->lock);
if (err)
- goto err_cmpt_put;
+ goto err_icm;
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox)) {
radix_tree_delete(&srq_table->tree, srq->srqn);
spin_unlock_irq(&srq_table->lock);
-err_cmpt_put:
- mlx4_table_put(dev, &srq_table->cmpt_table, srq->srqn);
-
-err_put:
- mlx4_table_put(dev, &srq_table->table, srq->srqn);
-
-err_out:
- mlx4_bitmap_free(&srq_table->bitmap, srq->srqn);
-
+err_icm:
+ mlx4_srq_free_icm(dev, srq->srqn);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_srq_alloc);
complete(&srq->free);
wait_for_completion(&srq->free);
- mlx4_table_put(dev, &srq_table->table, srq->srqn);
- mlx4_bitmap_free(&srq_table->bitmap, srq->srqn);
+ mlx4_srq_free_icm(dev, srq->srqn);
}
EXPORT_SYMBOL_GPL(mlx4_srq_free);
spin_lock_init(&srq_table->lock);
INIT_RADIX_TREE(&srq_table->tree, GFP_ATOMIC);
+ if (mlx4_is_slave(dev))
+ return 0;
err = mlx4_bitmap_init(&srq_table->bitmap, dev->caps.num_srqs,
dev->caps.num_srqs - 1, dev->caps.reserved_srqs, 0);
void mlx4_cleanup_srq_table(struct mlx4_dev *dev)
{
+ if (mlx4_is_slave(dev))
+ return;
mlx4_bitmap_cleanup(&mlx4_priv(dev)->srq_table.bitmap);
}
select NET_CORE
select MII
select CRC32
+ select MISC_DEVICES
+ select EEPROM_93CX6
---help---
SPI driver for Micrel KS8851 SPI attached network chip.
.remove = ks8842_remove,
};
-static int __init ks8842_init(void)
-{
- return platform_driver_register(&ks8842_platform_driver);
-}
-
-static void __exit ks8842_exit(void)
-{
- platform_driver_unregister(&ks8842_platform_driver);
-}
-
-module_init(ks8842_init);
-module_exit(ks8842_exit);
+module_platform_driver(ks8842_platform_driver);
MODULE_DESCRIPTION("Timberdale KS8842 ethernet driver");
MODULE_AUTHOR("Mocean Laboratories <info@mocean-labs.com>");
#include <linux/cache.h>
#include <linux/crc32.h>
#include <linux/mii.h>
+#include <linux/eeprom_93cx6.h>
#include <linux/spi/spi.h>
* @rc_ccr: Cached copy of KS_CCR.
* @rc_rxqcr: Cached copy of KS_RXQCR.
* @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom
+ * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
*
* The @lock ensures that the chip is protected when certain operations are
* in progress. When the read or write packet transfer is in progress, most
struct spi_message spi_msg2;
struct spi_transfer spi_xfer1;
struct spi_transfer spi_xfer2[2];
+
+ struct eeprom_93cx6 eeprom;
};
static int msg_enable;
mdelay(1); /* wait for condition to clear */
}
+/**
+ * ks8851_set_powermode - set power mode of the device
+ * @ks: The device state
+ * @pwrmode: The power mode value to write to KS_PMECR.
+ *
+ * Change the power mode of the chip.
+ */
+static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
+{
+ unsigned pmecr;
+
+ netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
+
+ pmecr = ks8851_rdreg16(ks, KS_PMECR);
+ pmecr &= ~PMECR_PM_MASK;
+ pmecr |= pwrmode;
+
+ ks8851_wrreg16(ks, KS_PMECR, pmecr);
+}
+
/**
* ks8851_write_mac_addr - write mac address to device registers
* @dev: The network device
mutex_lock(&ks->lock);
+ /*
+ * Wake up chip in case it was powered off when stopped; otherwise,
+ * the first write to the MAC address does not take effect.
+ */
+ ks8851_set_powermode(ks, PMECR_PM_NORMAL);
for (i = 0; i < ETH_ALEN; i++)
ks8851_wrreg8(ks, KS_MAR(i), dev->dev_addr[i]);
+ if (!netif_running(dev))
+ ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
mutex_unlock(&ks->lock);
return 0;
}
+/**
+ * ks8851_read_mac_addr - read mac address from device registers
+ * @dev: The network device
+ *
+ * Update our copy of the KS8851 MAC address from the registers of @dev.
+*/
+static void ks8851_read_mac_addr(struct net_device *dev)
+{
+ struct ks8851_net *ks = netdev_priv(dev);
+ int i;
+
+ mutex_lock(&ks->lock);
+
+ for (i = 0; i < ETH_ALEN; i++)
+ dev->dev_addr[i] = ks8851_rdreg8(ks, KS_MAR(i));
+
+ mutex_unlock(&ks->lock);
+}
+
/**
* ks8851_init_mac - initialise the mac address
* @ks: The device structure
*
* Get or create the initial mac address for the device and then set that
- * into the station address register. Currently we assume that the device
- * does not have a valid mac address in it, and so we use random_ether_addr()
+ * into the station address register. If there is an EEPROM present, then
+ * we try that. If no valid mac address is found we use random_ether_addr()
* to create a new one.
- *
- * In future, the driver should check to see if the device has an EEPROM
- * attached and whether that has a valid ethernet address in it.
*/
static void ks8851_init_mac(struct ks8851_net *ks)
{
struct net_device *dev = ks->netdev;
+ /* first, try reading what we've got already */
+ if (ks->rc_ccr & CCR_EEPROM) {
+ ks8851_read_mac_addr(dev);
+ if (is_valid_ether_addr(dev->dev_addr))
+ return;
+
+ netdev_err(ks->netdev, "invalid mac address read %pM\n",
+ dev->dev_addr);
+ }
+
random_ether_addr(dev->dev_addr);
ks8851_write_mac_addr(dev);
}
mutex_unlock(&ks->lock);
}
-/**
- * ks8851_set_powermode - set power mode of the device
- * @ks: The device state
- * @pwrmode: The power mode value to write to KS_PMECR.
- *
- * Change the power mode of the chip.
- */
-static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
-{
- unsigned pmecr;
-
- netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
-
- pmecr = ks8851_rdreg16(ks, KS_PMECR);
- pmecr &= ~PMECR_PM_MASK;
- pmecr |= pwrmode;
-
- ks8851_wrreg16(ks, KS_PMECR, pmecr);
-}
-
/**
* ks8851_net_open - open network device
* @dev: The network device being opened.
.ndo_validate_addr = eth_validate_addr,
};
-/* Companion eeprom access */
-
-enum { /* EEPROM programming states */
- EEPROM_CONTROL,
- EEPROM_ADDRESS,
- EEPROM_DATA,
- EEPROM_COMPLETE
-};
-
-/**
- * ks8851_eeprom_read - read a 16bits word in ks8851 companion EEPROM
- * @dev: The network device the PHY is on.
- * @addr: EEPROM address to read
- *
- * eeprom_size: used to define the data coding length. Can be changed
- * through debug-fs.
- *
- * Programs a read on the EEPROM using ks8851 EEPROM SW access feature.
- * Warning: The READ feature is not supported on ks8851 revision 0.
- *
- * Rough programming model:
- * - on period start: set clock high and read value on bus
- * - on period / 2: set clock low and program value on bus
- * - start on period / 2
- */
-unsigned int ks8851_eeprom_read(struct net_device *dev, unsigned int addr)
-{
- struct ks8851_net *ks = netdev_priv(dev);
- int eepcr;
- int ctrl = EEPROM_OP_READ;
- int state = EEPROM_CONTROL;
- int bit_count = EEPROM_OP_LEN - 1;
- unsigned int data = 0;
- int dummy;
- unsigned int addr_len;
-
- addr_len = (ks->eeprom_size == 128) ? 6 : 8;
-
- /* start transaction: chip select high, authorize write */
- mutex_lock(&ks->lock);
- eepcr = EEPCR_EESA | EEPCR_EESRWA;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- eepcr |= EEPCR_EECS;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- while (state != EEPROM_COMPLETE) {
- /* falling clock period starts... */
- /* set EED_IO pin for control and address */
- eepcr &= ~EEPCR_EEDO;
- switch (state) {
- case EEPROM_CONTROL:
- eepcr |= ((ctrl >> bit_count) & 1) << 2;
- if (bit_count-- <= 0) {
- bit_count = addr_len - 1;
- state = EEPROM_ADDRESS;
- }
- break;
- case EEPROM_ADDRESS:
- eepcr |= ((addr >> bit_count) & 1) << 2;
- bit_count--;
- break;
- case EEPROM_DATA:
- /* Change to receive mode */
- eepcr &= ~EEPCR_EESRWA;
- break;
- }
-
- /* lower clock */
- eepcr &= ~EEPCR_EESCK;
-
- mutex_lock(&ks->lock);
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- /* waitread period / 2 */
- udelay(EEPROM_SK_PERIOD / 2);
-
- /* rising clock period starts... */
-
- /* raise clock */
- mutex_lock(&ks->lock);
- eepcr |= EEPCR_EESCK;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- /* Manage read */
- switch (state) {
- case EEPROM_ADDRESS:
- if (bit_count < 0) {
- bit_count = EEPROM_DATA_LEN - 1;
- state = EEPROM_DATA;
- }
- break;
- case EEPROM_DATA:
- mutex_lock(&ks->lock);
- dummy = ks8851_rdreg16(ks, KS_EEPCR);
- mutex_unlock(&ks->lock);
- data |= ((dummy >> EEPCR_EESB_OFFSET) & 1) << bit_count;
- if (bit_count-- <= 0)
- state = EEPROM_COMPLETE;
- break;
- }
-
- /* wait period / 2 */
- udelay(EEPROM_SK_PERIOD / 2);
- }
-
- /* close transaction */
- mutex_lock(&ks->lock);
- eepcr &= ~EEPCR_EECS;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- eepcr = 0;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- return data;
-}
-
-/**
- * ks8851_eeprom_write - write a 16bits word in ks8851 companion EEPROM
- * @dev: The network device the PHY is on.
- * @op: operand (can be WRITE, EWEN, EWDS)
- * @addr: EEPROM address to write
- * @data: data to write
- *
- * eeprom_size: used to define the data coding length. Can be changed
- * through debug-fs.
- *
- * Programs a write on the EEPROM using ks8851 EEPROM SW access feature.
- *
- * Note that a write enable is required before writing data.
- *
- * Rough programming model:
- * - on period start: set clock high
- * - on period / 2: set clock low and program value on bus
- * - start on period / 2
- */
-void ks8851_eeprom_write(struct net_device *dev, unsigned int op,
- unsigned int addr, unsigned int data)
-{
- struct ks8851_net *ks = netdev_priv(dev);
- int eepcr;
- int state = EEPROM_CONTROL;
- int bit_count = EEPROM_OP_LEN - 1;
- unsigned int addr_len;
-
- addr_len = (ks->eeprom_size == 128) ? 6 : 8;
-
- switch (op) {
- case EEPROM_OP_EWEN:
- addr = 0x30;
- break;
- case EEPROM_OP_EWDS:
- addr = 0;
- break;
- }
-
- /* start transaction: chip select high, authorize write */
- mutex_lock(&ks->lock);
- eepcr = EEPCR_EESA | EEPCR_EESRWA;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- eepcr |= EEPCR_EECS;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- while (state != EEPROM_COMPLETE) {
- /* falling clock period starts... */
- /* set EED_IO pin for control and address */
- eepcr &= ~EEPCR_EEDO;
- switch (state) {
- case EEPROM_CONTROL:
- eepcr |= ((op >> bit_count) & 1) << 2;
- if (bit_count-- <= 0) {
- bit_count = addr_len - 1;
- state = EEPROM_ADDRESS;
- }
- break;
- case EEPROM_ADDRESS:
- eepcr |= ((addr >> bit_count) & 1) << 2;
- if (bit_count-- <= 0) {
- if (op == EEPROM_OP_WRITE) {
- bit_count = EEPROM_DATA_LEN - 1;
- state = EEPROM_DATA;
- } else {
- state = EEPROM_COMPLETE;
- }
- }
- break;
- case EEPROM_DATA:
- eepcr |= ((data >> bit_count) & 1) << 2;
- if (bit_count-- <= 0)
- state = EEPROM_COMPLETE;
- break;
- }
-
- /* lower clock */
- eepcr &= ~EEPCR_EESCK;
-
- mutex_lock(&ks->lock);
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- /* wait period / 2 */
- udelay(EEPROM_SK_PERIOD / 2);
-
- /* rising clock period starts... */
-
- /* raise clock */
- eepcr |= EEPCR_EESCK;
- mutex_lock(&ks->lock);
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
- /* wait period / 2 */
- udelay(EEPROM_SK_PERIOD / 2);
- }
-
- /* close transaction */
- mutex_lock(&ks->lock);
- eepcr &= ~EEPCR_EECS;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- eepcr = 0;
- ks8851_wrreg16(ks, KS_EEPCR, eepcr);
- mutex_unlock(&ks->lock);
-
-}
-
/* ethtool support */
static void ks8851_get_drvinfo(struct net_device *dev,
return mii_nway_restart(&ks->mii);
}
-static int ks8851_get_eeprom_len(struct net_device *dev)
-{
- struct ks8851_net *ks = netdev_priv(dev);
- return ks->eeprom_size;
-}
+/* EEPROM support */
-static int ks8851_get_eeprom(struct net_device *dev,
- struct ethtool_eeprom *eeprom, u8 *bytes)
+static void ks8851_eeprom_regread(struct eeprom_93cx6 *ee)
{
- struct ks8851_net *ks = netdev_priv(dev);
- u16 *eeprom_buff;
- int first_word;
- int last_word;
- int ret_val = 0;
- u16 i;
-
- if (eeprom->len == 0)
- return -EINVAL;
+ struct ks8851_net *ks = ee->data;
+ unsigned val;
- if (eeprom->len > ks->eeprom_size)
- return -EINVAL;
+ val = ks8851_rdreg16(ks, KS_EEPCR);
- eeprom->magic = ks8851_rdreg16(ks, KS_CIDER);
+ ee->reg_data_out = (val & EEPCR_EESB) ? 1 : 0;
+ ee->reg_data_clock = (val & EEPCR_EESCK) ? 1 : 0;
+ ee->reg_chip_select = (val & EEPCR_EECS) ? 1 : 0;
+}
- first_word = eeprom->offset >> 1;
- last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+static void ks8851_eeprom_regwrite(struct eeprom_93cx6 *ee)
+{
+ struct ks8851_net *ks = ee->data;
+ unsigned val = EEPCR_EESA; /* default - eeprom access on */
+
+ if (ee->drive_data)
+ val |= EEPCR_EESRWA;
+ if (ee->reg_data_in)
+ val |= EEPCR_EEDO;
+ if (ee->reg_data_clock)
+ val |= EEPCR_EESCK;
+ if (ee->reg_chip_select)
+ val |= EEPCR_EECS;
+
+ ks8851_wrreg16(ks, KS_EEPCR, val);
+}
- eeprom_buff = kmalloc(sizeof(u16) *
- (last_word - first_word + 1), GFP_KERNEL);
- if (!eeprom_buff)
- return -ENOMEM;
+/**
+ * ks8851_eeprom_claim - claim device EEPROM and activate the interface
+ * @ks: The network device state.
+ *
+ * Check for the presence of an EEPROM, and then activate software access
+ * to the device.
+ */
+static int ks8851_eeprom_claim(struct ks8851_net *ks)
+{
+ if (!(ks->rc_ccr & CCR_EEPROM))
+ return -ENOENT;
- for (i = 0; i < last_word - first_word + 1; i++)
- eeprom_buff[i] = ks8851_eeprom_read(dev, first_word + 1);
+ mutex_lock(&ks->lock);
- /* Device's eeprom is little-endian, word addressable */
- for (i = 0; i < last_word - first_word + 1; i++)
- le16_to_cpus(&eeprom_buff[i]);
+ /* start with clock low, cs high */
+ ks8851_wrreg16(ks, KS_EEPCR, EEPCR_EESA | EEPCR_EECS);
+ return 0;
+}
- memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len);
- kfree(eeprom_buff);
+/**
+ * ks8851_eeprom_release - release the EEPROM interface
+ * @ks: The device state
+ *
+ * Release the software access to the device EEPROM
+ */
+static void ks8851_eeprom_release(struct ks8851_net *ks)
+{
+ unsigned val = ks8851_rdreg16(ks, KS_EEPCR);
- return ret_val;
+ ks8851_wrreg16(ks, KS_EEPCR, val & ~EEPCR_EESA);
+ mutex_unlock(&ks->lock);
}
+#define KS_EEPROM_MAGIC (0x00008851)
+
static int ks8851_set_eeprom(struct net_device *dev,
- struct ethtool_eeprom *eeprom, u8 *bytes)
+ struct ethtool_eeprom *ee, u8 *data)
{
struct ks8851_net *ks = netdev_priv(dev);
- u16 *eeprom_buff;
- void *ptr;
- int max_len;
- int first_word;
- int last_word;
- int ret_val = 0;
- u16 i;
-
- if (eeprom->len == 0)
- return -EOPNOTSUPP;
-
- if (eeprom->len > ks->eeprom_size)
+ int offset = ee->offset;
+ int len = ee->len;
+ u16 tmp;
+
+ /* currently only support byte writing */
+ if (len != 1)
return -EINVAL;
- if (eeprom->magic != ks8851_rdreg16(ks, KS_CIDER))
- return -EFAULT;
+ if (ee->magic != KS_EEPROM_MAGIC)
+ return -EINVAL;
- first_word = eeprom->offset >> 1;
- last_word = (eeprom->offset + eeprom->len - 1) >> 1;
- max_len = (last_word - first_word + 1) * 2;
- eeprom_buff = kmalloc(max_len, GFP_KERNEL);
- if (!eeprom_buff)
- return -ENOMEM;
+ if (ks8851_eeprom_claim(ks))
+ return -ENOENT;
- ptr = (void *)eeprom_buff;
+ eeprom_93cx6_wren(&ks->eeprom, true);
- if (eeprom->offset & 1) {
- /* need read/modify/write of first changed EEPROM word */
- /* only the second byte of the word is being modified */
- eeprom_buff[0] = ks8851_eeprom_read(dev, first_word);
- ptr++;
+ /* ethtool currently only supports writing bytes, which means
+ * we have to read/modify/write our 16bit EEPROMs */
+
+ eeprom_93cx6_read(&ks->eeprom, offset/2, &tmp);
+
+ if (offset & 1) {
+ tmp &= 0xff;
+ tmp |= *data << 8;
+ } else {
+ tmp &= 0xff00;
+ tmp |= *data;
}
- if ((eeprom->offset + eeprom->len) & 1)
- /* need read/modify/write of last changed EEPROM word */
- /* only the first byte of the word is being modified */
- eeprom_buff[last_word - first_word] =
- ks8851_eeprom_read(dev, last_word);
+ eeprom_93cx6_write(&ks->eeprom, offset/2, tmp);
+ eeprom_93cx6_wren(&ks->eeprom, false);
- /* Device's eeprom is little-endian, word addressable */
- le16_to_cpus(&eeprom_buff[0]);
- le16_to_cpus(&eeprom_buff[last_word - first_word]);
+ ks8851_eeprom_release(ks);
- memcpy(ptr, bytes, eeprom->len);
+ return 0;
+}
- for (i = 0; i < last_word - first_word + 1; i++)
- eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+static int ks8851_get_eeprom(struct net_device *dev,
+ struct ethtool_eeprom *ee, u8 *data)
+{
+ struct ks8851_net *ks = netdev_priv(dev);
+ int offset = ee->offset;
+ int len = ee->len;
- ks8851_eeprom_write(dev, EEPROM_OP_EWEN, 0, 0);
+ /* must be 2 byte aligned */
+ if (len & 1 || offset & 1)
+ return -EINVAL;
- for (i = 0; i < last_word - first_word + 1; i++) {
- ks8851_eeprom_write(dev, EEPROM_OP_WRITE, first_word + i,
- eeprom_buff[i]);
- mdelay(EEPROM_WRITE_TIME);
- }
+ if (ks8851_eeprom_claim(ks))
+ return -ENOENT;
+
+ ee->magic = KS_EEPROM_MAGIC;
- ks8851_eeprom_write(dev, EEPROM_OP_EWDS, 0, 0);
+ eeprom_93cx6_multiread(&ks->eeprom, offset/2, (__le16 *)data, len/2);
+ ks8851_eeprom_release(ks);
- kfree(eeprom_buff);
- return ret_val;
+ return 0;
+}
+
+static int ks8851_get_eeprom_len(struct net_device *dev)
+{
+ struct ks8851_net *ks = netdev_priv(dev);
+
+ /* currently, we assume it is an 93C46 attached, so return 128 */
+ return ks->rc_ccr & CCR_EEPROM ? 128 : 0;
}
static const struct ethtool_ops ks8851_ethtool_ops = {
spi_message_add_tail(&ks->spi_xfer2[0], &ks->spi_msg2);
spi_message_add_tail(&ks->spi_xfer2[1], &ks->spi_msg2);
+ /* setup EEPROM state */
+
+ ks->eeprom.data = ks;
+ ks->eeprom.width = PCI_EEPROM_WIDTH_93C46;
+ ks->eeprom.register_read = ks8851_eeprom_regread;
+ ks->eeprom.register_write = ks8851_eeprom_regwrite;
+
/* setup mii state */
ks->mii.dev = ndev;
ks->mii.phy_id = 1,
goto err_netdev;
}
- netdev_info(ndev, "revision %d, MAC %pM, IRQ %d\n",
+ netdev_info(ndev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
- ndev->dev_addr, ndev->irq);
+ ndev->dev_addr, ndev->irq,
+ ks->rc_ccr & CCR_EEPROM ? "has" : "no");
return 0;
#define CCR_32PIN (1 << 0)
/* MAC address registers */
-#define KS_MAR(_m) 0x15 - (_m)
+#define KS_MAR(_m) (0x15 - (_m))
#define KS_MARL 0x10
#define KS_MARM 0x12
#define KS_MARH 0x14
#define KS_EEPCR 0x22
#define EEPCR_EESRWA (1 << 5)
#define EEPCR_EESA (1 << 4)
-#define EEPCR_EESB_OFFSET 3
-#define EEPCR_EESB (1 << EEPCR_EESB_OFFSET)
+#define EEPCR_EESB (1 << 3)
#define EEPCR_EEDO (1 << 2)
#define EEPCR_EESCK (1 << 1)
#define EEPCR_EECS (1 << 0)
-#define EEPROM_OP_LEN 3 /* bits:*/
-#define EEPROM_OP_READ 0x06
-#define EEPROM_OP_EWEN 0x04
-#define EEPROM_OP_WRITE 0x05
-#define EEPROM_OP_EWDS 0x14
-
-#define EEPROM_DATA_LEN 16 /* 16 bits EEPROM */
-#define EEPROM_WRITE_TIME 4 /* wrt ack time in ms */
-#define EEPROM_SK_PERIOD 400 /* in us */
-
#define KS_MBIR 0x24
#define MBIR_TXMBF (1 << 12)
#define MBIR_TXMBFA (1 << 11)
ks->all_mcast = 0;
ks->mcast_lst_size = 0;
- ks->frame_head_info = (struct type_frame_head *) \
- kmalloc(MHEADER_SIZE, GFP_KERNEL);
+ ks->frame_head_info = kmalloc(MHEADER_SIZE, GFP_KERNEL);
if (!ks->frame_head_info) {
pr_err("Error: Fail to allocate frame memory\n");
return false;
.remove = __devexit_p(ks8851_remove),
};
-static int __init ks8851_init(void)
-{
- return platform_driver_register(&ks8851_platform_driver);
-}
-
-static void __exit ks8851_exit(void)
-{
- platform_driver_unregister(&ks8851_platform_driver);
-}
-
-module_init(ks8851_init);
-module_exit(ks8851_exit);
+module_platform_driver(ks8851_platform_driver);
MODULE_DESCRIPTION("KS8851 MLL Network driver");
MODULE_AUTHOR("David Choi <david.choi@micrel.com>");
/* Change default LED mode. */
#define SET_DEFAULT_LED LED_SPEED_DUPLEX_ACT
-#define MAC_ADDR_LEN 6
-#define MAC_ADDR_ORDER(i) (MAC_ADDR_LEN - 1 - (i))
+#define MAC_ADDR_ORDER(i) (ETH_ALEN - 1 - (i))
#define MAX_ETHERNET_BODY_SIZE 1500
#define ETHERNET_HEADER_SIZE 14
* @valid: Valid setting indicating the entry is being used.
*/
struct ksz_mac_table {
- u8 mac_addr[MAC_ADDR_LEN];
+ u8 mac_addr[ETH_ALEN];
u16 vid;
u8 fid;
u8 ports;
u8 diffserv[DIFFSERV_ENTRIES];
u8 p_802_1p[PRIO_802_1P_ENTRIES];
- u8 br_addr[MAC_ADDR_LEN];
- u8 other_addr[MAC_ADDR_LEN];
+ u8 br_addr[ETH_ALEN];
+ u8 other_addr[ETH_ALEN];
u8 broad_per;
u8 member;
int tx_int_mask;
int tx_size;
- u8 perm_addr[MAC_ADDR_LEN];
- u8 override_addr[MAC_ADDR_LEN];
- u8 address[ADDITIONAL_ENTRIES][MAC_ADDR_LEN];
+ u8 perm_addr[ETH_ALEN];
+ u8 override_addr[ETH_ALEN];
+ u8 address[ADDITIONAL_ENTRIES][ETH_ALEN];
u8 addr_list_size;
u8 mac_override;
u8 promiscuous;
u8 all_multi;
- u8 multi_list[MAX_MULTICAST_LIST][MAC_ADDR_LEN];
+ u8 multi_list[MAX_MULTICAST_LIST][ETH_ALEN];
u8 multi_bits[HW_MULTICAST_SIZE];
u8 multi_list_size;
static const u8 mask[] = { 0x3F };
static const u8 pattern[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
- hw_set_wol_frame(hw, 2, 1, mask, MAC_ADDR_LEN, pattern);
+ hw_set_wol_frame(hw, 2, 1, mask, ETH_ALEN, pattern);
}
/**
{
static const u8 mask[] = { 0x3F };
- hw_set_wol_frame(hw, 0, 1, mask, MAC_ADDR_LEN, hw->override_addr);
+ hw_set_wol_frame(hw, 0, 1, mask, ETH_ALEN, hw->override_addr);
}
/**
{
int i;
- for (i = 0; i < MAC_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
writeb(hw->override_addr[MAC_ADDR_ORDER(i)],
hw->io + KS884X_ADDR_0_OFFSET + i);
{
int i;
- for (i = 0; i < MAC_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
hw->perm_addr[MAC_ADDR_ORDER(i)] = readb(hw->io +
KS884X_ADDR_0_OFFSET + i);
if (!hw->mac_override) {
- memcpy(hw->override_addr, hw->perm_addr, MAC_ADDR_LEN);
+ memcpy(hw->override_addr, hw->perm_addr, ETH_ALEN);
if (empty_addr(hw->override_addr)) {
- memcpy(hw->perm_addr, DEFAULT_MAC_ADDRESS,
- MAC_ADDR_LEN);
+ memcpy(hw->perm_addr, DEFAULT_MAC_ADDRESS, ETH_ALEN);
memcpy(hw->override_addr, DEFAULT_MAC_ADDRESS,
- MAC_ADDR_LEN);
+ ETH_ALEN);
hw->override_addr[5] += hw->id;
hw_set_addr(hw);
}
int i;
int j = ADDITIONAL_ENTRIES;
- if (!memcmp(hw->override_addr, mac_addr, MAC_ADDR_LEN))
+ if (!memcmp(hw->override_addr, mac_addr, ETH_ALEN))
return 0;
for (i = 0; i < hw->addr_list_size; i++) {
- if (!memcmp(hw->address[i], mac_addr, MAC_ADDR_LEN))
+ if (!memcmp(hw->address[i], mac_addr, ETH_ALEN))
return 0;
if (ADDITIONAL_ENTRIES == j && empty_addr(hw->address[i]))
j = i;
}
if (j < ADDITIONAL_ENTRIES) {
- memcpy(hw->address[j], mac_addr, MAC_ADDR_LEN);
+ memcpy(hw->address[j], mac_addr, ETH_ALEN);
hw_ena_add_addr(hw, j, hw->address[j]);
return 0;
}
int i;
for (i = 0; i < hw->addr_list_size; i++) {
- if (!memcmp(hw->address[i], mac_addr, MAC_ADDR_LEN)) {
- memset(hw->address[i], 0, MAC_ADDR_LEN);
+ if (!memcmp(hw->address[i], mac_addr, ETH_ALEN)) {
+ memset(hw->address[i], 0, ETH_ALEN);
writel(0, hw->io + ADD_ADDR_INCR * i +
KS_ADD_ADDR_0_HI);
return 0;
*/
static int ksz_alloc_soft_desc(struct ksz_desc_info *desc_info, int transmit)
{
- desc_info->ring = kmalloc(sizeof(struct ksz_desc) * desc_info->alloc,
- GFP_KERNEL);
+ desc_info->ring = kzalloc(sizeof(struct ksz_desc) * desc_info->alloc,
+ GFP_KERNEL);
if (!desc_info->ring)
return 1;
- memset((void *) desc_info->ring, 0,
- sizeof(struct ksz_desc) * desc_info->alloc);
hw_init_desc(desc_info, transmit);
return 0;
}
hw_del_addr(hw, dev->dev_addr);
else {
hw->mac_override = 1;
- memcpy(hw->override_addr, mac->sa_data, MAC_ADDR_LEN);
+ memcpy(hw->override_addr, mac->sa_data, ETH_ALEN);
}
memcpy(dev->dev_addr, mac->sa_data, MAX_ADDR_LEN);
netdev_for_each_mc_addr(ha, dev) {
if (i >= MAX_MULTICAST_LIST)
break;
- memcpy(hw->multi_list[i++], ha->addr, MAC_ADDR_LEN);
+ memcpy(hw->multi_list[i++], ha->addr, ETH_ALEN);
}
hw->multi_list_size = (u8) i;
hw_set_grp_addr(hw);
struct dev_priv *priv = netdev_priv(dev);
struct dev_info *hw_priv = priv->adapter;
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(hw_priv->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(hw_priv->pdev),
+ sizeof(info->bus_info));
}
/**
*
* Return 0 if successful; otherwise an error code.
*/
-static int netdev_set_features(struct net_device *dev, u32 features)
+static int netdev_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct dev_priv *priv = netdev_priv(dev);
struct dev_info *hw_priv = priv->adapter;
int num;
i = j = num = got_num = 0;
- while (j < MAC_ADDR_LEN) {
+ while (j < ETH_ALEN) {
if (macaddr[i]) {
int digit;
}
i++;
}
- if (MAC_ADDR_LEN == j) {
+ if (ETH_ALEN == j) {
if (MAIN_PORT == port)
hw_priv->hw.mac_override = 1;
}
/* Multiple device interfaces mode requires a second MAC address. */
if (hw->dev_count > 1) {
- memcpy(sw->other_addr, hw->override_addr, MAC_ADDR_LEN);
+ memcpy(sw->other_addr, hw->override_addr, ETH_ALEN);
read_other_addr(hw);
if (mac1addr[0] != ':')
get_mac_addr(hw_priv, mac1addr, OTHER_PORT);
dev->irq = pdev->irq;
if (MAIN_PORT == i)
memcpy(dev->dev_addr, hw_priv->hw.override_addr,
- MAC_ADDR_LEN);
+ ETH_ALEN);
else {
- memcpy(dev->dev_addr, sw->other_addr,
- MAC_ADDR_LEN);
+ memcpy(dev->dev_addr, sw->other_addr, ETH_ALEN);
if (!memcmp(sw->other_addr, hw->override_addr,
- MAC_ADDR_LEN))
+ ETH_ALEN))
dev->dev_addr[5] += port->first_port;
}
* access to avoid theoretical race condition with functions that
* change NETIF_F_LRO flag at runtime.
*/
- bool lro_enabled = ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO;
+ bool lro_enabled = !!(ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO);
while (rx_done->entry[idx].length != 0 && work_done < budget) {
length = ntohs(rx_done->entry[idx].length);
return 0;
}
-static u32 myri10ge_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t myri10ge_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
if (!(features & NETIF_F_RXCSUM))
features &= ~NETIF_F_LRO;
MXGEFW_CMD_GET_DCA_OFFSET = 56,
/* offset of dca control for WDMAs */
- /* VMWare NetQueue commands */
+ /* VMware NetQueue commands */
MXGEFW_CMD_NETQ_GET_FILTERS_PER_QUEUE = 57,
MXGEFW_CMD_NETQ_ADD_FILTER = 58,
/* data0 = filter_id << 16 | queue << 8 | type */
},
};
-static int __init jazz_sonic_init_module(void)
-{
- return platform_driver_register(&jazz_sonic_driver);
-}
-
-static void __exit jazz_sonic_cleanup_module(void)
-{
- platform_driver_unregister(&jazz_sonic_driver);
-}
-
-module_init(jazz_sonic_init_module);
-module_exit(jazz_sonic_cleanup_module);
+module_platform_driver(jazz_sonic_driver);
},
};
-static int __init mac_sonic_init_module(void)
-{
- return platform_driver_register(&mac_sonic_driver);
-}
-
-static void __exit mac_sonic_cleanup_module(void)
-{
- platform_driver_unregister(&mac_sonic_driver);
-}
-
-module_init(mac_sonic_init_module);
-module_exit(mac_sonic_cleanup_module);
+module_platform_driver(mac_sonic_driver);
static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct netdev_private *np = netdev_priv(dev);
- strncpy(info->driver, DRV_NAME, ETHTOOL_BUSINFO_LEN);
- strncpy(info->version, DRV_VERSION, ETHTOOL_BUSINFO_LEN);
- strncpy(info->bus_info, pci_name(np->pci_dev), ETHTOOL_BUSINFO_LEN);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int get_regs_len(struct net_device *dev)
static void ns83820_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info)
{
struct ns83820 *dev = PRIV(ndev);
- strcpy(info->driver, "ns83820");
- strcpy(info->version, VERSION);
- strcpy(info->bus_info, pci_name(dev->pci_dev));
+ strlcpy(info->driver, "ns83820", sizeof(info->driver));
+ strlcpy(info->version, VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(dev->pci_dev), sizeof(info->bus_info));
}
static u32 ns83820_get_link(struct net_device *ndev)
},
};
-static int __init xtsonic_init(void)
-{
- return platform_driver_register(&xtsonic_driver);
-}
-
-static void __exit xtsonic_cleanup(void)
-{
- platform_driver_unregister(&xtsonic_driver);
-}
-
-module_init(xtsonic_init);
-module_exit(xtsonic_cleanup);
+module_platform_driver(xtsonic_driver);
{
struct s2io_nic *sp = netdev_priv(dev);
- strncpy(info->driver, s2io_driver_name, sizeof(info->driver));
- strncpy(info->version, s2io_driver_version, sizeof(info->version));
- strncpy(info->fw_version, "", sizeof(info->fw_version));
- strncpy(info->bus_info, pci_name(sp->pdev), sizeof(info->bus_info));
+ strlcpy(info->driver, s2io_driver_name, sizeof(info->driver));
+ strlcpy(info->version, s2io_driver_version, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(sp->pdev), sizeof(info->bus_info));
info->regdump_len = XENA_REG_SPACE;
info->eedump_len = XENA_EEPROM_SPACE;
}
}
}
-static int s2io_set_features(struct net_device *dev, u32 features)
+static int s2io_set_features(struct net_device *dev, netdev_features_t features)
{
struct s2io_nic *sp = netdev_priv(dev);
- u32 changed = (features ^ dev->features) & NETIF_F_LRO;
+ netdev_features_t changed = (features ^ dev->features) & NETIF_F_LRO;
if (changed && netif_running(dev)) {
int rc;
mod_timer(&vdev->vp_lockup_timer, jiffies + HZ / 1000);
}
-static u32 vxge_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t vxge_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
/* Enabling RTH requires some of the logic in vxge_device_register and a
* vpath reset. Due to these restrictions, only allow modification
return features;
}
-static int vxge_set_features(struct net_device *dev, u32 features)
+static int vxge_set_features(struct net_device *dev, netdev_features_t features)
{
struct vxgedev *vdev = netdev_priv(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
if (!(changed & NETIF_F_RXHASH))
return 0;
*
* Add the vlan id to the devices vlan id table
*/
-static void
+static int
vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct vxgedev *vdev = netdev_priv(dev);
vxge_hw_vpath_vid_add(vpath->handle, vid);
}
set_bit(vid, vdev->active_vlans);
+ return 0;
}
/**
*
* Remove the vlan id from the device's vlan id table
*/
-static void
+static int
vxge_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct vxgedev *vdev = netdev_priv(dev);
vxge_debug_entryexit(VXGE_TRACE,
"%s:%d Exiting...", __func__, __LINE__);
clear_bit(vid, vdev->active_vlans);
+ return 0;
}
static const struct net_device_ops vxge_netdev_ops = {
},
};
-static int __init w90p910_ether_init(void)
-{
- return platform_driver_register(&w90p910_ether_driver);
-}
-
-static void __exit w90p910_ether_exit(void)
-{
- platform_driver_unregister(&w90p910_ether_driver);
-}
-
-module_init(w90p910_ether_init);
-module_exit(w90p910_ether_exit);
+module_platform_driver(w90p910_ether_driver);
MODULE_AUTHOR("Wan ZongShun <mcuos.com@gmail.com>");
MODULE_DESCRIPTION("w90p910 MAC driver!");
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/prefetch.h>
-#include <linux/io.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/io.h>
#include <asm/irq.h>
#include <asm/system.h>
};
static const struct nv_ethtool_str nv_estats_str[] = {
- { "tx_bytes" },
+ { "tx_bytes" }, /* includes Ethernet FCS CRC */
{ "tx_zero_rexmt" },
{ "tx_one_rexmt" },
{ "tx_many_rexmt" },
/* version 2 stats */
{ "tx_deferral" },
{ "tx_packets" },
- { "rx_bytes" },
+ { "rx_bytes" }, /* includes Ethernet FCS CRC */
{ "tx_pause" },
{ "rx_pause" },
{ "rx_drop_frame" },
};
struct nv_ethtool_stats {
- u64 tx_bytes;
+ u64 tx_bytes; /* should be ifconfig->tx_bytes + 4*tx_packets */
u64 tx_zero_rexmt;
u64 tx_one_rexmt;
u64 tx_many_rexmt;
u64 rx_unicast;
u64 rx_multicast;
u64 rx_broadcast;
- u64 rx_packets;
+ u64 rx_packets; /* should be ifconfig->rx_packets */
u64 rx_errors_total;
u64 tx_errors_total;
/* version 2 stats */
u64 tx_deferral;
- u64 tx_packets;
- u64 rx_bytes;
+ u64 tx_packets; /* should be ifconfig->tx_packets */
+ u64 rx_bytes; /* should be ifconfig->rx_bytes + 4*rx_packets */
u64 tx_pause;
u64 rx_pause;
u64 rx_drop_frame;
* - tx setup is lockless: it relies on netif_tx_lock. Actual submission
* needs netdev_priv(dev)->lock :-(
* - set_multicast_list: preparation lockless, relies on netif_tx_lock.
+ *
+ * Hardware stats updates are protected by hwstats_lock:
+ * - updated by nv_do_stats_poll (timer). This is meant to avoid
+ * integer wraparound in the NIC stats registers, at low frequency
+ * (0.1 Hz)
+ * - updated by nv_get_ethtool_stats + nv_get_stats64
+ *
+ * Software stats are accessed only through 64b synchronization points
+ * and are not subject to other synchronization techniques (single
+ * update thread on the TX or RX paths).
*/
/* in dev: base, irq */
struct net_device *dev;
struct napi_struct napi;
- /* General data:
- * Locking: spin_lock(&np->lock); */
+ /* hardware stats are updated in syscall and timer */
+ spinlock_t hwstats_lock;
struct nv_ethtool_stats estats;
+
int in_shutdown;
u32 linkspeed;
int duplex;
u32 nic_poll_irq;
int rx_ring_size;
+ /* RX software stats */
+ struct u64_stats_sync swstats_rx_syncp;
+ u64 stat_rx_packets;
+ u64 stat_rx_bytes; /* not always available in HW */
+ u64 stat_rx_missed_errors;
+ u64 stat_rx_dropped;
+
/* media detection workaround.
* Locking: Within irq hander or disable_irq+spin_lock(&np->lock);
*/
struct nv_skb_map *tx_end_flip;
int tx_stop;
+ /* TX software stats */
+ struct u64_stats_sync swstats_tx_syncp;
+ u64 stat_tx_packets; /* not always available in HW */
+ u64 stat_tx_bytes;
+ u64 stat_tx_dropped;
+
/* msi/msi-x fields */
u32 msi_flags;
struct msix_entry msi_x_entry[NV_MSI_X_MAX_VECTORS];
};
static int dma_64bit = NV_DMA_64BIT_ENABLED;
+/*
+ * Debug output control for tx_timeout
+ */
+static bool debug_tx_timeout = false;
+
/*
* Crossover Detection
* Realtek 8201 phy + some OEM boards do not work properly.
pci_push(base);
}
-static void nv_get_hw_stats(struct net_device *dev)
+/* Caller must appropriately lock netdev_priv(dev)->hwstats_lock */
+static void nv_update_stats(struct net_device *dev)
{
struct fe_priv *np = netdev_priv(dev);
u8 __iomem *base = get_hwbase(dev);
+ /* If it happens that this is run in top-half context, then
+ * replace the spin_lock of hwstats_lock with
+ * spin_lock_irqsave() in calling functions. */
+ WARN_ONCE(in_irq(), "forcedeth: estats spin_lock(_bh) from top-half");
+ assert_spin_locked(&np->hwstats_lock);
+
+ /* query hardware */
np->estats.tx_bytes += readl(base + NvRegTxCnt);
np->estats.tx_zero_rexmt += readl(base + NvRegTxZeroReXmt);
np->estats.tx_one_rexmt += readl(base + NvRegTxOneReXmt);
}
/*
- * nv_get_stats: dev->get_stats function
+ * nv_get_stats64: dev->ndo_get_stats64 function
* Get latest stats value from the nic.
* Called with read_lock(&dev_base_lock) held for read -
* only synchronized against unregister_netdevice.
*/
-static struct net_device_stats *nv_get_stats(struct net_device *dev)
+static struct rtnl_link_stats64*
+nv_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *storage)
+ __acquires(&netdev_priv(dev)->hwstats_lock)
+ __releases(&netdev_priv(dev)->hwstats_lock)
{
struct fe_priv *np = netdev_priv(dev);
+ unsigned int syncp_start;
+
+ /*
+ * Note: because HW stats are not always available and for
+ * consistency reasons, the following ifconfig stats are
+ * managed by software: rx_bytes, tx_bytes, rx_packets and
+ * tx_packets. The related hardware stats reported by ethtool
+ * should be equivalent to these ifconfig stats, with 4
+ * additional bytes per packet (Ethernet FCS CRC), except for
+ * tx_packets when TSO kicks in.
+ */
+
+ /* software stats */
+ do {
+ syncp_start = u64_stats_fetch_begin_bh(&np->swstats_rx_syncp);
+ storage->rx_packets = np->stat_rx_packets;
+ storage->rx_bytes = np->stat_rx_bytes;
+ storage->rx_dropped = np->stat_rx_dropped;
+ storage->rx_missed_errors = np->stat_rx_missed_errors;
+ } while (u64_stats_fetch_retry_bh(&np->swstats_rx_syncp, syncp_start));
+
+ do {
+ syncp_start = u64_stats_fetch_begin_bh(&np->swstats_tx_syncp);
+ storage->tx_packets = np->stat_tx_packets;
+ storage->tx_bytes = np->stat_tx_bytes;
+ storage->tx_dropped = np->stat_tx_dropped;
+ } while (u64_stats_fetch_retry_bh(&np->swstats_tx_syncp, syncp_start));
/* If the nic supports hw counters then retrieve latest values */
- if (np->driver_data & (DEV_HAS_STATISTICS_V1|DEV_HAS_STATISTICS_V2|DEV_HAS_STATISTICS_V3)) {
- nv_get_hw_stats(dev);
-
- /* copy to net_device stats */
- dev->stats.tx_packets = np->estats.tx_packets;
- dev->stats.rx_bytes = np->estats.rx_bytes;
- dev->stats.tx_bytes = np->estats.tx_bytes;
- dev->stats.tx_fifo_errors = np->estats.tx_fifo_errors;
- dev->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
- dev->stats.rx_crc_errors = np->estats.rx_crc_errors;
- dev->stats.rx_over_errors = np->estats.rx_over_errors;
- dev->stats.rx_fifo_errors = np->estats.rx_drop_frame;
- dev->stats.rx_errors = np->estats.rx_errors_total;
- dev->stats.tx_errors = np->estats.tx_errors_total;
- }
-
- return &dev->stats;
+ if (np->driver_data & DEV_HAS_STATISTICS_V123) {
+ spin_lock_bh(&np->hwstats_lock);
+
+ nv_update_stats(dev);
+
+ /* generic stats */
+ storage->rx_errors = np->estats.rx_errors_total;
+ storage->tx_errors = np->estats.tx_errors_total;
+
+ /* meaningful only when NIC supports stats v3 */
+ storage->multicast = np->estats.rx_multicast;
+
+ /* detailed rx_errors */
+ storage->rx_length_errors = np->estats.rx_length_error;
+ storage->rx_over_errors = np->estats.rx_over_errors;
+ storage->rx_crc_errors = np->estats.rx_crc_errors;
+ storage->rx_frame_errors = np->estats.rx_frame_align_error;
+ storage->rx_fifo_errors = np->estats.rx_drop_frame;
+
+ /* detailed tx_errors */
+ storage->tx_carrier_errors = np->estats.tx_carrier_errors;
+ storage->tx_fifo_errors = np->estats.tx_fifo_errors;
+
+ spin_unlock_bh(&np->hwstats_lock);
+ }
+
+ return storage;
}
/*
np->put_rx.orig = np->first_rx.orig;
if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
np->put_rx_ctx = np->first_rx_ctx;
- } else
+ } else {
+ u64_stats_update_begin(&np->swstats_rx_syncp);
+ np->stat_rx_dropped++;
+ u64_stats_update_end(&np->swstats_rx_syncp);
return 1;
+ }
}
return 0;
}
np->put_rx.ex = np->first_rx.ex;
if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
np->put_rx_ctx = np->first_rx_ctx;
- } else
+ } else {
+ u64_stats_update_begin(&np->swstats_rx_syncp);
+ np->stat_rx_dropped++;
+ u64_stats_update_end(&np->swstats_rx_syncp);
return 1;
+ }
}
return 0;
}
np->last_tx.ex = &np->tx_ring.ex[np->tx_ring_size-1];
np->get_tx_ctx = np->put_tx_ctx = np->first_tx_ctx = np->tx_skb;
np->last_tx_ctx = &np->tx_skb[np->tx_ring_size-1];
+ netdev_reset_queue(np->dev);
np->tx_pkts_in_progress = 0;
np->tx_change_owner = NULL;
np->tx_end_flip = NULL;
np->tx_ring.ex[i].bufhigh = 0;
np->tx_ring.ex[i].buflow = 0;
}
- if (nv_release_txskb(np, &np->tx_skb[i]))
- dev->stats.tx_dropped++;
+ if (nv_release_txskb(np, &np->tx_skb[i])) {
+ u64_stats_update_begin(&np->swstats_tx_syncp);
+ np->stat_tx_dropped++;
+ u64_stats_update_end(&np->swstats_tx_syncp);
+ }
np->tx_skb[i].dma = 0;
np->tx_skb[i].dma_len = 0;
np->tx_skb[i].dma_single = 0;
/* set tx flags */
start_tx->flaglen |= cpu_to_le32(tx_flags | tx_flags_extra);
+
+ netdev_sent_queue(np->dev, skb->len);
+
np->put_tx.orig = put_tx;
spin_unlock_irqrestore(&np->lock, flags);
/* set tx flags */
start_tx->flaglen |= cpu_to_le32(tx_flags | tx_flags_extra);
+
+ netdev_sent_queue(np->dev, skb->len);
+
np->put_tx.ex = put_tx;
spin_unlock_irqrestore(&np->lock, flags);
u32 flags;
int tx_work = 0;
struct ring_desc *orig_get_tx = np->get_tx.orig;
+ unsigned int bytes_compl = 0;
while ((np->get_tx.orig != np->put_tx.orig) &&
!((flags = le32_to_cpu(np->get_tx.orig->flaglen)) & NV_TX_VALID) &&
if (np->desc_ver == DESC_VER_1) {
if (flags & NV_TX_LASTPACKET) {
if (flags & NV_TX_ERROR) {
- if ((flags & NV_TX_RETRYERROR) && !(flags & NV_TX_RETRYCOUNT_MASK))
+ if ((flags & NV_TX_RETRYERROR)
+ && !(flags & NV_TX_RETRYCOUNT_MASK))
nv_legacybackoff_reseed(dev);
+ } else {
+ u64_stats_update_begin(&np->swstats_tx_syncp);
+ np->stat_tx_packets++;
+ np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+ u64_stats_update_end(&np->swstats_tx_syncp);
}
+ bytes_compl += np->get_tx_ctx->skb->len;
dev_kfree_skb_any(np->get_tx_ctx->skb);
np->get_tx_ctx->skb = NULL;
tx_work++;
} else {
if (flags & NV_TX2_LASTPACKET) {
if (flags & NV_TX2_ERROR) {
- if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK))
+ if ((flags & NV_TX2_RETRYERROR)
+ && !(flags & NV_TX2_RETRYCOUNT_MASK))
nv_legacybackoff_reseed(dev);
+ } else {
+ u64_stats_update_begin(&np->swstats_tx_syncp);
+ np->stat_tx_packets++;
+ np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+ u64_stats_update_end(&np->swstats_tx_syncp);
}
+ bytes_compl += np->get_tx_ctx->skb->len;
dev_kfree_skb_any(np->get_tx_ctx->skb);
np->get_tx_ctx->skb = NULL;
tx_work++;
if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
np->get_tx_ctx = np->first_tx_ctx;
}
+
+ netdev_completed_queue(np->dev, tx_work, bytes_compl);
+
if (unlikely((np->tx_stop == 1) && (np->get_tx.orig != orig_get_tx))) {
np->tx_stop = 0;
netif_wake_queue(dev);
u32 flags;
int tx_work = 0;
struct ring_desc_ex *orig_get_tx = np->get_tx.ex;
+ unsigned long bytes_cleaned = 0;
while ((np->get_tx.ex != np->put_tx.ex) &&
!((flags = le32_to_cpu(np->get_tx.ex->flaglen)) & NV_TX2_VALID) &&
if (flags & NV_TX2_LASTPACKET) {
if (flags & NV_TX2_ERROR) {
- if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
+ if ((flags & NV_TX2_RETRYERROR)
+ && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
if (np->driver_data & DEV_HAS_GEAR_MODE)
nv_gear_backoff_reseed(dev);
else
nv_legacybackoff_reseed(dev);
}
+ } else {
+ u64_stats_update_begin(&np->swstats_tx_syncp);
+ np->stat_tx_packets++;
+ np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+ u64_stats_update_end(&np->swstats_tx_syncp);
}
+ bytes_cleaned += np->get_tx_ctx->skb->len;
dev_kfree_skb_any(np->get_tx_ctx->skb);
np->get_tx_ctx->skb = NULL;
tx_work++;
if (np->tx_limit)
nv_tx_flip_ownership(dev);
}
+
if (unlikely(np->get_tx.ex++ == np->last_tx.ex))
np->get_tx.ex = np->first_tx.ex;
if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
np->get_tx_ctx = np->first_tx_ctx;
}
+
+ netdev_completed_queue(np->dev, tx_work, bytes_cleaned);
+
if (unlikely((np->tx_stop == 1) && (np->get_tx.ex != orig_get_tx))) {
np->tx_stop = 0;
netif_wake_queue(dev);
u32 status;
union ring_type put_tx;
int saved_tx_limit;
- int i;
if (np->msi_flags & NV_MSI_X_ENABLED)
status = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
else
status = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK;
- netdev_info(dev, "Got tx_timeout. irq: %08x\n", status);
+ netdev_warn(dev, "Got tx_timeout. irq status: %08x\n", status);
- netdev_info(dev, "Ring at %lx\n", (unsigned long)np->ring_addr);
- netdev_info(dev, "Dumping tx registers\n");
- for (i = 0; i <= np->register_size; i += 32) {
- netdev_info(dev,
- "%3x: %08x %08x %08x %08x %08x %08x %08x %08x\n",
- i,
- readl(base + i + 0), readl(base + i + 4),
- readl(base + i + 8), readl(base + i + 12),
- readl(base + i + 16), readl(base + i + 20),
- readl(base + i + 24), readl(base + i + 28));
- }
- netdev_info(dev, "Dumping tx ring\n");
- for (i = 0; i < np->tx_ring_size; i += 4) {
- if (!nv_optimized(np)) {
- netdev_info(dev,
- "%03x: %08x %08x // %08x %08x // %08x %08x // %08x %08x\n",
- i,
- le32_to_cpu(np->tx_ring.orig[i].buf),
- le32_to_cpu(np->tx_ring.orig[i].flaglen),
- le32_to_cpu(np->tx_ring.orig[i+1].buf),
- le32_to_cpu(np->tx_ring.orig[i+1].flaglen),
- le32_to_cpu(np->tx_ring.orig[i+2].buf),
- le32_to_cpu(np->tx_ring.orig[i+2].flaglen),
- le32_to_cpu(np->tx_ring.orig[i+3].buf),
- le32_to_cpu(np->tx_ring.orig[i+3].flaglen));
- } else {
+ if (unlikely(debug_tx_timeout)) {
+ int i;
+
+ netdev_info(dev, "Ring at %lx\n", (unsigned long)np->ring_addr);
+ netdev_info(dev, "Dumping tx registers\n");
+ for (i = 0; i <= np->register_size; i += 32) {
netdev_info(dev,
- "%03x: %08x %08x %08x // %08x %08x %08x // %08x %08x %08x // %08x %08x %08x\n",
+ "%3x: %08x %08x %08x %08x "
+ "%08x %08x %08x %08x\n",
i,
- le32_to_cpu(np->tx_ring.ex[i].bufhigh),
- le32_to_cpu(np->tx_ring.ex[i].buflow),
- le32_to_cpu(np->tx_ring.ex[i].flaglen),
- le32_to_cpu(np->tx_ring.ex[i+1].bufhigh),
- le32_to_cpu(np->tx_ring.ex[i+1].buflow),
- le32_to_cpu(np->tx_ring.ex[i+1].flaglen),
- le32_to_cpu(np->tx_ring.ex[i+2].bufhigh),
- le32_to_cpu(np->tx_ring.ex[i+2].buflow),
- le32_to_cpu(np->tx_ring.ex[i+2].flaglen),
- le32_to_cpu(np->tx_ring.ex[i+3].bufhigh),
- le32_to_cpu(np->tx_ring.ex[i+3].buflow),
- le32_to_cpu(np->tx_ring.ex[i+3].flaglen));
+ readl(base + i + 0), readl(base + i + 4),
+ readl(base + i + 8), readl(base + i + 12),
+ readl(base + i + 16), readl(base + i + 20),
+ readl(base + i + 24), readl(base + i + 28));
+ }
+ netdev_info(dev, "Dumping tx ring\n");
+ for (i = 0; i < np->tx_ring_size; i += 4) {
+ if (!nv_optimized(np)) {
+ netdev_info(dev,
+ "%03x: %08x %08x // %08x %08x "
+ "// %08x %08x // %08x %08x\n",
+ i,
+ le32_to_cpu(np->tx_ring.orig[i].buf),
+ le32_to_cpu(np->tx_ring.orig[i].flaglen),
+ le32_to_cpu(np->tx_ring.orig[i+1].buf),
+ le32_to_cpu(np->tx_ring.orig[i+1].flaglen),
+ le32_to_cpu(np->tx_ring.orig[i+2].buf),
+ le32_to_cpu(np->tx_ring.orig[i+2].flaglen),
+ le32_to_cpu(np->tx_ring.orig[i+3].buf),
+ le32_to_cpu(np->tx_ring.orig[i+3].flaglen));
+ } else {
+ netdev_info(dev,
+ "%03x: %08x %08x %08x "
+ "// %08x %08x %08x "
+ "// %08x %08x %08x "
+ "// %08x %08x %08x\n",
+ i,
+ le32_to_cpu(np->tx_ring.ex[i].bufhigh),
+ le32_to_cpu(np->tx_ring.ex[i].buflow),
+ le32_to_cpu(np->tx_ring.ex[i].flaglen),
+ le32_to_cpu(np->tx_ring.ex[i+1].bufhigh),
+ le32_to_cpu(np->tx_ring.ex[i+1].buflow),
+ le32_to_cpu(np->tx_ring.ex[i+1].flaglen),
+ le32_to_cpu(np->tx_ring.ex[i+2].bufhigh),
+ le32_to_cpu(np->tx_ring.ex[i+2].buflow),
+ le32_to_cpu(np->tx_ring.ex[i+2].flaglen),
+ le32_to_cpu(np->tx_ring.ex[i+3].bufhigh),
+ le32_to_cpu(np->tx_ring.ex[i+3].buflow),
+ le32_to_cpu(np->tx_ring.ex[i+3].flaglen));
+ }
}
}
}
/* the rest are hard errors */
else {
- if (flags & NV_RX_MISSEDFRAME)
- dev->stats.rx_missed_errors++;
+ if (flags & NV_RX_MISSEDFRAME) {
+ u64_stats_update_begin(&np->swstats_rx_syncp);
+ np->stat_rx_missed_errors++;
+ u64_stats_update_end(&np->swstats_rx_syncp);
+ }
dev_kfree_skb(skb);
goto next_pkt;
}
skb_put(skb, len);
skb->protocol = eth_type_trans(skb, dev);
napi_gro_receive(&np->napi, skb);
- dev->stats.rx_packets++;
+ u64_stats_update_begin(&np->swstats_rx_syncp);
+ np->stat_rx_packets++;
+ np->stat_rx_bytes += len;
+ u64_stats_update_end(&np->swstats_rx_syncp);
next_pkt:
if (unlikely(np->get_rx.orig++ == np->last_rx.orig))
np->get_rx.orig = np->first_rx.orig;
__vlan_hwaccel_put_tag(skb, vid);
}
napi_gro_receive(&np->napi, skb);
- dev->stats.rx_packets++;
+ u64_stats_update_begin(&np->swstats_rx_syncp);
+ np->stat_rx_packets++;
+ np->stat_rx_bytes += len;
+ u64_stats_update_end(&np->swstats_rx_syncp);
} else {
dev_kfree_skb(skb);
}
}
}
+static void nv_force_linkspeed(struct net_device *dev, int speed, int duplex)
+{
+ struct fe_priv *np = netdev_priv(dev);
+ u8 __iomem *base = get_hwbase(dev);
+ u32 phyreg, txreg;
+ int mii_status;
+
+ np->linkspeed = NVREG_LINKSPEED_FORCE|speed;
+ np->duplex = duplex;
+
+ /* see if gigabit phy */
+ mii_status = mii_rw(dev, np->phyaddr, MII_BMSR, MII_READ);
+ if (mii_status & PHY_GIGABIT) {
+ np->gigabit = PHY_GIGABIT;
+ phyreg = readl(base + NvRegSlotTime);
+ phyreg &= ~(0x3FF00);
+ if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_10)
+ phyreg |= NVREG_SLOTTIME_10_100_FULL;
+ else if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_100)
+ phyreg |= NVREG_SLOTTIME_10_100_FULL;
+ else if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_1000)
+ phyreg |= NVREG_SLOTTIME_1000_FULL;
+ writel(phyreg, base + NvRegSlotTime);
+ }
+
+ phyreg = readl(base + NvRegPhyInterface);
+ phyreg &= ~(PHY_HALF|PHY_100|PHY_1000);
+ if (np->duplex == 0)
+ phyreg |= PHY_HALF;
+ if ((np->linkspeed & NVREG_LINKSPEED_MASK) == NVREG_LINKSPEED_100)
+ phyreg |= PHY_100;
+ else if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+ NVREG_LINKSPEED_1000)
+ phyreg |= PHY_1000;
+ writel(phyreg, base + NvRegPhyInterface);
+
+ if (phyreg & PHY_RGMII) {
+ if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+ NVREG_LINKSPEED_1000)
+ txreg = NVREG_TX_DEFERRAL_RGMII_1000;
+ else
+ txreg = NVREG_TX_DEFERRAL_RGMII_10_100;
+ } else {
+ txreg = NVREG_TX_DEFERRAL_DEFAULT;
+ }
+ writel(txreg, base + NvRegTxDeferral);
+
+ if (np->desc_ver == DESC_VER_1) {
+ txreg = NVREG_TX_WM_DESC1_DEFAULT;
+ } else {
+ if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+ NVREG_LINKSPEED_1000)
+ txreg = NVREG_TX_WM_DESC2_3_1000;
+ else
+ txreg = NVREG_TX_WM_DESC2_3_DEFAULT;
+ }
+ writel(txreg, base + NvRegTxWatermark);
+
+ writel(NVREG_MISC1_FORCE | (np->duplex ? 0 : NVREG_MISC1_HD),
+ base + NvRegMisc1);
+ pci_push(base);
+ writel(np->linkspeed, base + NvRegLinkSpeed);
+ pci_push(base);
+
+ return;
+}
+
/**
* nv_update_linkspeed: Setup the MAC according to the link partner
* @dev: Network device to be configured
int newls = np->linkspeed;
int newdup = np->duplex;
int mii_status;
+ u32 bmcr;
int retval = 0;
u32 control_1000, status_1000, phyreg, pause_flags, txreg;
u32 txrxFlags = 0;
u32 phy_exp;
+ /* If device loopback is enabled, set carrier on and enable max link
+ * speed.
+ */
+ bmcr = mii_rw(dev, np->phyaddr, MII_BMCR, MII_READ);
+ if (bmcr & BMCR_LOOPBACK) {
+ if (netif_running(dev)) {
+ nv_force_linkspeed(dev, NVREG_LINKSPEED_1000, 1);
+ if (!netif_carrier_ok(dev))
+ netif_carrier_on(dev);
+ }
+ return 1;
+ }
+
/* BMSR_LSTATUS is latched, read it twice:
* we want the current value.
*/
writel(0, base + NvRegMSIXMap0);
writel(0, base + NvRegMSIXMap1);
}
+ netdev_info(dev, "MSI-X enabled\n");
}
}
if (ret != 0 && np->msi_flags & NV_MSI_CAPABLE) {
writel(0, base + NvRegMSIMap1);
/* enable msi vector 0 */
writel(NVREG_MSI_VECTOR_0_ENABLED, base + NvRegMSIIrqMask);
+ netdev_info(dev, "MSI enabled\n");
}
}
if (ret != 0) {
#endif
static void nv_do_stats_poll(unsigned long data)
+ __acquires(&netdev_priv(dev)->hwstats_lock)
+ __releases(&netdev_priv(dev)->hwstats_lock)
{
struct net_device *dev = (struct net_device *) data;
struct fe_priv *np = netdev_priv(dev);
- nv_get_hw_stats(dev);
+ /* If lock is currently taken, the stats are being refreshed
+ * and hence fresh enough */
+ if (spin_trylock(&np->hwstats_lock)) {
+ nv_update_stats(dev);
+ spin_unlock(&np->hwstats_lock);
+ }
if (!np->in_shutdown)
mod_timer(&np->stats_poll,
static void nv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct fe_priv *np = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, FORCEDETH_VERSION);
- strcpy(info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, FORCEDETH_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static void nv_get_wol(struct net_device *dev, struct ethtool_wolinfo *wolinfo)
return 0;
}
-static u32 nv_fix_features(struct net_device *dev, u32 features)
+static int nv_set_loopback(struct net_device *dev, netdev_features_t features)
+{
+ struct fe_priv *np = netdev_priv(dev);
+ unsigned long flags;
+ u32 miicontrol;
+ int err, retval = 0;
+
+ spin_lock_irqsave(&np->lock, flags);
+ miicontrol = mii_rw(dev, np->phyaddr, MII_BMCR, MII_READ);
+ if (features & NETIF_F_LOOPBACK) {
+ if (miicontrol & BMCR_LOOPBACK) {
+ spin_unlock_irqrestore(&np->lock, flags);
+ netdev_info(dev, "Loopback already enabled\n");
+ return 0;
+ }
+ nv_disable_irq(dev);
+ /* Turn on loopback mode */
+ miicontrol |= BMCR_LOOPBACK | BMCR_FULLDPLX | BMCR_SPEED1000;
+ err = mii_rw(dev, np->phyaddr, MII_BMCR, miicontrol);
+ if (err) {
+ retval = PHY_ERROR;
+ spin_unlock_irqrestore(&np->lock, flags);
+ phy_init(dev);
+ } else {
+ if (netif_running(dev)) {
+ /* Force 1000 Mbps full-duplex */
+ nv_force_linkspeed(dev, NVREG_LINKSPEED_1000,
+ 1);
+ /* Force link up */
+ netif_carrier_on(dev);
+ }
+ spin_unlock_irqrestore(&np->lock, flags);
+ netdev_info(dev,
+ "Internal PHY loopback mode enabled.\n");
+ }
+ } else {
+ if (!(miicontrol & BMCR_LOOPBACK)) {
+ spin_unlock_irqrestore(&np->lock, flags);
+ netdev_info(dev, "Loopback already disabled\n");
+ return 0;
+ }
+ nv_disable_irq(dev);
+ /* Turn off loopback */
+ spin_unlock_irqrestore(&np->lock, flags);
+ netdev_info(dev, "Internal PHY loopback mode disabled.\n");
+ phy_init(dev);
+ }
+ msleep(500);
+ spin_lock_irqsave(&np->lock, flags);
+ nv_enable_irq(dev);
+ spin_unlock_irqrestore(&np->lock, flags);
+
+ return retval;
+}
+
+static netdev_features_t nv_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/* vlan is dependent on rx checksum offload */
if (features & (NETIF_F_HW_VLAN_TX|NETIF_F_HW_VLAN_RX))
return features;
}
-static void nv_vlan_mode(struct net_device *dev, u32 features)
+static void nv_vlan_mode(struct net_device *dev, netdev_features_t features)
{
struct fe_priv *np = get_nvpriv(dev);
spin_unlock_irq(&np->lock);
}
-static int nv_set_features(struct net_device *dev, u32 features)
+static int nv_set_features(struct net_device *dev, netdev_features_t features)
{
struct fe_priv *np = netdev_priv(dev);
u8 __iomem *base = get_hwbase(dev);
- u32 changed = dev->features ^ features;
+ netdev_features_t changed = dev->features ^ features;
+ int retval;
+
+ if ((changed & NETIF_F_LOOPBACK) && netif_running(dev)) {
+ retval = nv_set_loopback(dev, features);
+ if (retval != 0)
+ return retval;
+ }
if (changed & NETIF_F_RXCSUM) {
spin_lock_irq(&np->lock);
}
}
-static void nv_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *estats, u64 *buffer)
+static void nv_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *estats, u64 *buffer)
+ __acquires(&netdev_priv(dev)->hwstats_lock)
+ __releases(&netdev_priv(dev)->hwstats_lock)
{
struct fe_priv *np = netdev_priv(dev);
- /* update stats */
- nv_get_hw_stats(dev);
-
- memcpy(buffer, &np->estats, nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+ spin_lock_bh(&np->hwstats_lock);
+ nv_update_stats(dev);
+ memcpy(buffer, &np->estats,
+ nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+ spin_unlock_bh(&np->hwstats_lock);
}
static int nv_link_test(struct net_device *dev)
spin_unlock_irq(&np->lock);
+ /* If the loopback feature was set while the device was down, make sure
+ * that it's set correctly now.
+ */
+ if (dev->features & NETIF_F_LOOPBACK)
+ nv_set_loopback(dev, dev->features);
+
return 0;
out_drain:
nv_drain_rxtx(dev);
static const struct net_device_ops nv_netdev_ops = {
.ndo_open = nv_open,
.ndo_stop = nv_close,
- .ndo_get_stats = nv_get_stats,
+ .ndo_get_stats64 = nv_get_stats64,
.ndo_start_xmit = nv_start_xmit,
.ndo_tx_timeout = nv_tx_timeout,
.ndo_change_mtu = nv_change_mtu,
static const struct net_device_ops nv_netdev_ops_optimized = {
.ndo_open = nv_open,
.ndo_stop = nv_close,
- .ndo_get_stats = nv_get_stats,
+ .ndo_get_stats64 = nv_get_stats64,
.ndo_start_xmit = nv_start_xmit_optimized,
.ndo_tx_timeout = nv_tx_timeout,
.ndo_change_mtu = nv_change_mtu,
np->dev = dev;
np->pci_dev = pci_dev;
spin_lock_init(&np->lock);
+ spin_lock_init(&np->hwstats_lock);
SET_NETDEV_DEV(dev, &pci_dev->dev);
init_timer(&np->oom_kick);
init_timer(&np->nic_poll);
np->nic_poll.data = (unsigned long) dev;
np->nic_poll.function = nv_do_nic_poll; /* timer handler */
- init_timer(&np->stats_poll);
+ init_timer_deferrable(&np->stats_poll);
np->stats_poll.data = (unsigned long) dev;
np->stats_poll.function = nv_do_stats_poll; /* timer handler */
dev->features |= dev->hw_features;
+ /* Add loopback capability to the device. */
+ dev->hw_features |= NETIF_F_LOOPBACK;
+
np->pause_flags = NV_PAUSEFRAME_RX_CAPABLE | NV_PAUSEFRAME_RX_REQ | NV_PAUSEFRAME_AUTONEG;
if ((id->driver_data & DEV_HAS_PAUSEFRAME_TX_V1) ||
(id->driver_data & DEV_HAS_PAUSEFRAME_TX_V2) ||
dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n",
dev->name, np->phy_oui, np->phyaddr, dev->dev_addr);
- dev_info(&pci_dev->dev, "%s%s%s%s%s%s%s%s%s%sdesc-v%u\n",
+ dev_info(&pci_dev->dev, "%s%s%s%s%s%s%s%s%s%s%sdesc-v%u\n",
dev->features & NETIF_F_HIGHDMA ? "highdma " : "",
dev->features & (NETIF_F_IP_CSUM | NETIF_F_SG) ?
"csum " : "",
dev->features & (NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX) ?
"vlan " : "",
+ dev->features & (NETIF_F_LOOPBACK) ?
+ "loopback " : "",
id->driver_data & DEV_HAS_POWER_CNTRL ? "pwrctl " : "",
id->driver_data & DEV_HAS_MGMT_UNIT ? "mgmt " : "",
id->driver_data & DEV_NEED_TIMERIRQ ? "timirq " : "",
MODULE_PARM_DESC(phy_cross, "Phy crossover detection for Realtek 8201 phy is enabled by setting to 1 and disabled by setting to 0.");
module_param(phy_power_down, int, 0);
MODULE_PARM_DESC(phy_power_down, "Power down phy and disable link when interface is down (1), or leave phy powered up (0).");
+module_param(debug_tx_timeout, bool, 0);
+MODULE_PARM_DESC(debug_tx_timeout,
+ "Dump tx related registers and ring when tx_timeout happens");
MODULE_AUTHOR("Manfred Spraul <manfred@colorfullife.com>");
MODULE_DESCRIPTION("Reverse Engineered nForce ethernet driver");
{
struct pch_gbe_adapter *adapter = netdev_priv(netdev);
- strcpy(drvinfo->driver, KBUILD_MODNAME);
- strcpy(drvinfo->version, pch_driver_version);
- strcpy(drvinfo->fw_version, "N/A");
- strcpy(drvinfo->bus_info, pci_name(adapter->pdev));
+ strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, pch_driver_version, sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = pch_gbe_get_regs_len(netdev);
}
* Returns
* 0: HW state updated successfully
*/
-static int pch_gbe_set_features(struct net_device *netdev, u32 features)
+static int pch_gbe_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct pch_gbe_adapter *adapter = netdev_priv(netdev);
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
if (!(changed & NETIF_F_RXCSUM))
return 0;
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
*/
-#include <linux/module.h> /* for __MODULE_STRING */
#include "pch_gbe.h"
+#include <linux/module.h> /* for __MODULE_STRING */
#define OPTION_UNSET -1
#define OPTION_DISABLED 0
# Makefile for the A Semi network device drivers.
#
-obj-$(CONFIG_PASEMI_MAC) += pasemi_mac.o pasemi_mac_ethtool.o
+obj-$(CONFIG_PASEMI_MAC) += pasemi_mac_driver.o
+pasemi_mac_driver-objs := pasemi_mac.o pasemi_mac_ethtool.o
u32 fw_minor = 0;
u32 fw_build = 0;
- strncpy(drvinfo->driver, netxen_nic_driver_name, 32);
- strncpy(drvinfo->version, NETXEN_NIC_LINUX_VERSIONID, 32);
+ strlcpy(drvinfo->driver, netxen_nic_driver_name,
+ sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, NETXEN_NIC_LINUX_VERSIONID,
+ sizeof(drvinfo->version));
fw_major = NXRD32(adapter, NETXEN_FW_VERSION_MAJOR);
fw_minor = NXRD32(adapter, NETXEN_FW_VERSION_MINOR);
fw_build = NXRD32(adapter, NETXEN_FW_VERSION_SUB);
- sprintf(drvinfo->fw_version, "%d.%d.%d", fw_major, fw_minor, fw_build);
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%d", fw_major, fw_minor, fw_build);
- strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = NETXEN_NIC_REGS_LEN;
drvinfo->eedump_len = netxen_nic_get_eeprom_len(dev);
}
adapter->set_multi(dev);
}
-static u32 netxen_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t netxen_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
if (!(features & NETIF_F_RXCSUM)) {
netdev_info(dev, "disabling LRO as RXCSUM is off\n");
return features;
}
-static int netxen_set_features(struct net_device *dev, u32 features)
+static int netxen_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct netxen_adapter *adapter = netdev_priv(dev);
int hw_lro;
struct ethtool_drvinfo *drvinfo)
{
struct ql3_adapter *qdev = netdev_priv(ndev);
- strncpy(drvinfo->driver, ql3xxx_driver_name, 32);
- strncpy(drvinfo->version, ql3xxx_driver_version, 32);
- strncpy(drvinfo->fw_version, "N/A", 32);
- strncpy(drvinfo->bus_info, pci_name(qdev->pdev), 32);
+ strlcpy(drvinfo->driver, ql3xxx_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ql3xxx_driver_version,
+ sizeof(drvinfo->version));
+ strlcpy(drvinfo->bus_info, pci_name(qdev->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->regdump_len = 0;
drvinfo->eedump_len = 0;
}
int qlcnic_fw_cmd_set_mtu(struct qlcnic_adapter *adapter, int mtu);
int qlcnic_change_mtu(struct net_device *netdev, int new_mtu);
-u32 qlcnic_fix_features(struct net_device *netdev, u32 features);
-int qlcnic_set_features(struct net_device *netdev, u32 features);
+netdev_features_t qlcnic_fix_features(struct net_device *netdev,
+ netdev_features_t features);
+int qlcnic_set_features(struct net_device *netdev, netdev_features_t features);
int qlcnic_config_hw_lro(struct qlcnic_adapter *adapter, int enable);
int qlcnic_config_bridged_mode(struct qlcnic_adapter *adapter, u32 enable);
int qlcnic_send_lro_cleanup(struct qlcnic_adapter *adapter);
fw_major = QLCRD32(adapter, QLCNIC_FW_VERSION_MAJOR);
fw_minor = QLCRD32(adapter, QLCNIC_FW_VERSION_MINOR);
fw_build = QLCRD32(adapter, QLCNIC_FW_VERSION_SUB);
- sprintf(drvinfo->fw_version, "%d.%d.%d", fw_major, fw_minor, fw_build);
-
- strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
- strlcpy(drvinfo->driver, qlcnic_driver_name, 32);
- strlcpy(drvinfo->version, QLCNIC_LINUX_VERSIONID, 32);
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%d", fw_major, fw_minor, fw_build);
+
+ strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+ sizeof(drvinfo->bus_info));
+ strlcpy(drvinfo->driver, qlcnic_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, QLCNIC_LINUX_VERSIONID,
+ sizeof(drvinfo->version));
}
static int
}
-u32 qlcnic_fix_features(struct net_device *netdev, u32 features)
+netdev_features_t qlcnic_fix_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
if ((adapter->flags & QLCNIC_ESWITCH_ENABLED)) {
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
features ^= changed & (NETIF_F_ALL_CSUM | NETIF_F_RXCSUM);
}
}
-int qlcnic_set_features(struct net_device *netdev, u32 features)
+int qlcnic_set_features(struct net_device *netdev, netdev_features_t features)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
- u32 changed = netdev->features ^ features;
+ netdev_features_t changed = netdev->features ^ features;
int hw_lro = (features & NETIF_F_LRO) ? QLCNIC_LRO_ENABLED : 0;
if (!(changed & NETIF_F_LRO))
static int qlcnicvf_start_firmware(struct qlcnic_adapter *);
static void qlcnic_set_netdev_features(struct qlcnic_adapter *,
struct qlcnic_esw_func_cfg *);
-static void qlcnic_vlan_rx_add(struct net_device *, u16);
-static void qlcnic_vlan_rx_del(struct net_device *, u16);
+static int qlcnic_vlan_rx_add(struct net_device *, u16);
+static int qlcnic_vlan_rx_del(struct net_device *, u16);
/* PCI Device ID Table */
#define ENTRY(device) \
adapter->pvid = 0;
}
-static void
+static int
qlcnic_vlan_rx_add(struct net_device *netdev, u16 vid)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
set_bit(vid, adapter->vlans);
+ return 0;
}
-static void
+static int
qlcnic_vlan_rx_del(struct net_device *netdev, u16 vid)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
qlcnic_restore_indev_addr(netdev, NETDEV_DOWN);
clear_bit(vid, adapter->vlans);
+ return 0;
}
static void
struct qlcnic_esw_func_cfg *esw_cfg)
{
struct net_device *netdev = adapter->netdev;
- unsigned long features, vlan_features;
+ netdev_features_t features, vlan_features;
features = (NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
NETIF_F_IPV6_CSUM | NETIF_F_GRO);
#define TX_DESC_PER_IOCB 8
-/* The maximum number of frags we handle is based
- * on PAGE_SIZE...
- */
-#if (PAGE_SHIFT == 12) || (PAGE_SHIFT == 13) /* 4k & 8k pages */
+
+#if ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) > 0
#define TX_DESC_PER_OAL ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2)
#else /* all other page sizes */
#define TX_DESC_PER_OAL 0
struct ob_mac_iocb_req *queue_entry;
u32 index;
struct oal oal;
- struct map_list map[MAX_SKB_FRAGS + 1];
+ struct map_list map[MAX_SKB_FRAGS + 2];
int map_cnt;
struct tx_ring_desc *next;
};
struct ethtool_drvinfo *drvinfo)
{
struct ql_adapter *qdev = netdev_priv(ndev);
- strncpy(drvinfo->driver, qlge_driver_name, 32);
- strncpy(drvinfo->version, qlge_driver_version, 32);
- snprintf(drvinfo->fw_version, 32, "v%d.%d.%d",
+ strlcpy(drvinfo->driver, qlge_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, qlge_driver_version,
+ sizeof(drvinfo->version));
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "v%d.%d.%d",
(qdev->fw_rev_id & 0x00ff0000) >> 16,
(qdev->fw_rev_id & 0x0000ff00) >> 8,
(qdev->fw_rev_id & 0x000000ff));
- strncpy(drvinfo->bus_info, pci_name(qdev->pdev), 32);
+ strlcpy(drvinfo->bus_info, pci_name(qdev->pdev),
+ sizeof(drvinfo->bus_info));
drvinfo->n_stats = 0;
drvinfo->testinfo_len = 0;
if (!test_bit(QL_FRC_COREDUMP, &qdev->flags))
return work_done;
}
-static void qlge_vlan_mode(struct net_device *ndev, u32 features)
+static void qlge_vlan_mode(struct net_device *ndev, netdev_features_t features)
{
struct ql_adapter *qdev = netdev_priv(ndev);
}
}
-static u32 qlge_fix_features(struct net_device *ndev, u32 features)
+static netdev_features_t qlge_fix_features(struct net_device *ndev,
+ netdev_features_t features)
{
/*
* Since there is no support for separate rx/tx vlan accel
return features;
}
-static int qlge_set_features(struct net_device *ndev, u32 features)
+static int qlge_set_features(struct net_device *ndev,
+ netdev_features_t features)
{
- u32 changed = ndev->features ^ features;
+ netdev_features_t changed = ndev->features ^ features;
if (changed & NETIF_F_HW_VLAN_RX)
qlge_vlan_mode(ndev, features);
return 0;
}
-static void __qlge_vlan_rx_add_vid(struct ql_adapter *qdev, u16 vid)
+static int __qlge_vlan_rx_add_vid(struct ql_adapter *qdev, u16 vid)
{
u32 enable_bit = MAC_ADDR_E;
+ int err;
- if (ql_set_mac_addr_reg
- (qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
+ err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit,
+ MAC_ADDR_TYPE_VLAN, vid);
+ if (err)
netif_err(qdev, ifup, qdev->ndev,
"Failed to init vlan address.\n");
- }
+ return err;
}
-static void qlge_vlan_rx_add_vid(struct net_device *ndev, u16 vid)
+static int qlge_vlan_rx_add_vid(struct net_device *ndev, u16 vid)
{
struct ql_adapter *qdev = netdev_priv(ndev);
int status;
+ int err;
status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
if (status)
- return;
+ return status;
- __qlge_vlan_rx_add_vid(qdev, vid);
+ err = __qlge_vlan_rx_add_vid(qdev, vid);
set_bit(vid, qdev->active_vlans);
ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
+
+ return err;
}
-static void __qlge_vlan_rx_kill_vid(struct ql_adapter *qdev, u16 vid)
+static int __qlge_vlan_rx_kill_vid(struct ql_adapter *qdev, u16 vid)
{
u32 enable_bit = 0;
+ int err;
- if (ql_set_mac_addr_reg
- (qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
+ err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit,
+ MAC_ADDR_TYPE_VLAN, vid);
+ if (err)
netif_err(qdev, ifup, qdev->ndev,
"Failed to clear vlan address.\n");
- }
+ return err;
}
-static void qlge_vlan_rx_kill_vid(struct net_device *ndev, u16 vid)
+static int qlge_vlan_rx_kill_vid(struct net_device *ndev, u16 vid)
{
struct ql_adapter *qdev = netdev_priv(ndev);
int status;
+ int err;
status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
if (status)
- return;
+ return status;
- __qlge_vlan_rx_kill_vid(qdev, vid);
+ err = __qlge_vlan_rx_kill_vid(qdev, vid);
clear_bit(vid, qdev->active_vlans);
ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
+
+ return err;
}
static void qlge_restore_vlan(struct ql_adapter *qdev)
#define DRV_VERSION "0.28"
#define DRV_RELDATE "07Oct2011"
-/* PHY CHIP Address */
-#define PHY1_ADDR 1 /* For MAC1 */
-#define PHY2_ADDR 3 /* For MAC2 */
-#define PHY_MODE 0x3100 /* PHY CHIP Register 0 */
-#define PHY_CAP 0x01E1 /* PHY CHIP Register 4 */
-
/* Time in jiffies before concluding the transmitter is hung. */
#define TX_TIMEOUT (6000 * HZ / 1000)
/* MAC registers */
#define MCR0 0x00 /* Control register 0 */
+#define MCR0_RCVEN 0x0002 /* Receive enable */
#define MCR0_PROMISC 0x0020 /* Promiscuous mode */
#define MCR0_HASH_EN 0x0100 /* Enable multicast hash table function */
+#define MCR0_XMTEN 0x1000 /* Transmission enable */
+#define MCR0_FD 0x8000 /* Full/Half duplex */
#define MCR1 0x04 /* Control register 1 */
#define MAC_RST 0x0001 /* Reset the MAC */
#define MBCR 0x08 /* Bus control */
#define PHY_CC 0x88 /* PHY status change configuration register */
#define PHY_ST 0x8A /* PHY status register */
#define MAC_SM 0xAC /* MAC status machine */
+#define MAC_SM_RST 0x0002 /* MAC status machine reset */
#define MAC_ID 0xBE /* Identifier register */
#define TX_DCNT 0x80 /* TX descriptor count */
#define DSC_RX_MIDH_HIT 0x0004 /* RX MID table hit (no error) */
#define DSC_RX_IDX_MID_MASK 3 /* RX mask for the index of matched MIDx */
-/* PHY settings */
-#define ICPLUS_PHY_ID 0x0243
-
MODULE_AUTHOR("Sten Wang <sten.wang@rdc.com.tw>,"
"Daniel Gimpelevich <daniel@gimpelevich.san-francisco.ca.us>,"
"Florian Fainelli <florian@openwrt.org>");
struct r6040_descriptor *vndescp; /* 14-17 */
struct sk_buff *skb_ptr; /* 18-1B */
u32 rev2; /* 1C-1F */
-} __attribute__((aligned(32)));
+} __aligned(32);
struct r6040_private {
spinlock_t lock; /* driver lock */
struct r6040_descriptor *tx_ring;
dma_addr_t rx_ring_dma;
dma_addr_t tx_ring_dma;
- u16 tx_free_desc, phy_addr;
+ u16 tx_free_desc;
u16 mcr0, mcr1;
struct net_device *dev;
struct mii_bus *mii_bus;
": RDC R6040 NAPI net driver,"
"version "DRV_VERSION " (" DRV_RELDATE ")";
-static int phy_table[] = { PHY1_ADDR, PHY2_ADDR };
-
/* Read a word data from PHY Chip */
static int r6040_phy_read(void __iomem *ioaddr, int phy_addr, int reg)
{
iowrite16(MAC_RST, ioaddr + MCR1);
while (limit--) {
cmd = ioread16(ioaddr + MCR1);
- if (cmd & 0x1)
+ if (cmd & MAC_RST)
break;
}
/* Reset internal state machine */
- iowrite16(2, ioaddr + MAC_SM);
+ iowrite16(MAC_SM_RST, ioaddr + MAC_SM);
iowrite16(0, ioaddr + MAC_SM);
mdelay(5);
iowrite16(INT_MASK, ioaddr + MIER);
/* Enable TX and RX */
- iowrite16(lp->mcr0 | 0x0002, ioaddr);
+ iowrite16(lp->mcr0 | MCR0_RCVEN, ioaddr);
/* Let TX poll the descriptors
* we may got called by r6040_tx_timeout which has left
iowrite16(MAC_RST, ioaddr + MCR1); /* Reset RDC MAC */
while (limit--) {
cmd = ioread16(ioaddr + MCR1);
- if (cmd & 0x1)
+ if (cmd & MAC_RST)
break;
}
void __iomem *ioaddr = lp->base;
u16 *adrp;
- /* MAC operation register */
- iowrite16(0x01, ioaddr + MCR1); /* Reset MAC */
- iowrite16(2, ioaddr + MAC_SM); /* Reset internal state machine */
+ /* Reset MAC */
+ iowrite16(MAC_RST, ioaddr + MCR1);
+ /* Reset internal state machine */
+ iowrite16(MAC_SM_RST, ioaddr + MAC_SM);
iowrite16(0, ioaddr + MAC_SM);
mdelay(5);
iowrite16(lp->mcr0, ioaddr + MCR0);
/* Fill the MAC hash tables with their values */
- if (lp->mcr0 && MCR0_HASH_EN) {
+ if (lp->mcr0 & MCR0_HASH_EN) {
iowrite16(hash_table[0], ioaddr + MAR0);
iowrite16(hash_table[1], ioaddr + MAR1);
iowrite16(hash_table[2], ioaddr + MAR2);
/* reflect duplex change */
if (phydev->link && (lp->old_duplex != phydev->duplex)) {
- lp->mcr0 |= (phydev->duplex == DUPLEX_FULL ? 0x8000 : 0);
+ lp->mcr0 |= (phydev->duplex == DUPLEX_FULL ? MCR0_FD : 0);
iowrite16(lp->mcr0, ioaddr);
status_changed = 1;
lp->dev = dev;
/* Init RDC private data */
- lp->mcr0 = 0x1002;
- lp->phy_addr = phy_table[card_idx];
+ lp->mcr0 = MCR0_XMTEN | MCR0;
/* The RDC-specific entries in the device structure. */
dev->netdev_ops = &r6040_netdev_ops;
lp->mii_bus->write = r6040_mdiobus_write;
lp->mii_bus->reset = r6040_mdiobus_reset;
lp->mii_bus->name = "r6040_eth_mii";
- snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%x", card_idx);
+ snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+ dev_name(&pdev->dev), card_idx);
lp->mii_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL);
if (!lp->mii_bus->irq) {
dev_err(&pdev->dev, "mii_bus irq allocation failed\n");
struct cp_private *cp = netdev_priv(dev);
u32 mc_filter[2]; /* Multicast hash filter */
int rx_mode;
- u32 tmp;
/* Note: do not reorder, GCC is clever about common statements. */
if (dev->flags & IFF_PROMISC) {
}
/* We can safely update without stopping the chip. */
- tmp = cp_rx_config | rx_mode;
- if (cp->rx_config != tmp) {
- cpw32_f (RxConfig, tmp);
- cp->rx_config = tmp;
- }
+ cp->rx_config = cp_rx_config | rx_mode;
+ cpw32_f(RxConfig, cp->rx_config);
+
cpw32_f (MAR0 + 0, mc_filter[0]);
cpw32_f (MAR0 + 4, mc_filter[1]);
}
{
struct cp_private *cp = netdev_priv(dev);
- strcpy (info->driver, DRV_NAME);
- strcpy (info->version, DRV_VERSION);
- strcpy (info->bus_info, pci_name(cp->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
}
static void cp_get_ringparam(struct net_device *dev,
cp->msg_enable = value;
}
-static int cp_set_features(struct net_device *dev, u32 features)
+static int cp_set_features(struct net_device *dev, netdev_features_t features)
{
struct cp_private *cp = netdev_priv(dev);
unsigned long flags;
No extra delay is needed with 33Mhz PCI, but 66Mhz may change this.
*/
-#define eeprom_delay() readl(ee_addr)
+#define eeprom_delay() readb(ee_addr)
/* The EEPROM commands include the alway-set leading bit. */
#define EE_EXTEND_CMD (4)
No extra delay is needed with 33Mhz PCI, but 66Mhz may change this.
*/
-#define eeprom_delay() (void)RTL_R32(Cfg9346)
+#define eeprom_delay() (void)RTL_R8(Cfg9346)
/* The EEPROM commands include the alway-set leading bit. */
#define EE_WRITE_CMD (5)
static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct rtl8139_private *tp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(tp->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
info->regdump_len = tp->regs_len;
}
The RTL chips use a 64 element hash table based on the Ethernet CRC. */
static const int multicast_filter_limit = 32;
-/* MAC address length */
-#define MAC_ADDR_LEN 6
-
#define MAX_READ_REQUEST_SHIFT 12
#define TX_DMA_BURST 6 /* Maximum PCI burst, '6' is 1024 */
#define SafeMtu 0x1c20 /* ... actually life sucks beyond ~7k */
/* Config1 register p.24 */
LEDS1 = (1 << 7),
LEDS0 = (1 << 6),
- MSIEnable = (1 << 5), /* Enable Message Signaled Interrupt */
Speed_down = (1 << 4),
MEMMAP = (1 << 3),
IOMAP = (1 << 2),
PMEnable = (1 << 0), /* Power Management Enable */
/* Config2 register p. 25 */
+ MSIEnable = (1 << 5), /* 8169 only. Reserved in the 8168. */
PCI_Clock_66MHz = 0x01,
PCI_Clock_33MHz = 0x00,
return value;
}
-static void rtl8169_irq_mask_and_ack(void __iomem *ioaddr)
+static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
{
- RTL_W16(IntrMask, 0x0000);
+ void __iomem *ioaddr = tp->mmio_addr;
- RTL_W16(IntrStatus, 0xffff);
+ RTL_W16(IntrMask, 0x0000);
+ RTL_W16(IntrStatus, tp->intr_event);
+ RTL_R8(ChipCmd);
}
static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp)
netif_carrier_off(dev);
netif_info(tp, ifdown, dev, "link down\n");
if (pm)
- pm_schedule_suspend(&tp->pci_dev->dev, 100);
+ pm_schedule_suspend(&tp->pci_dev->dev, 5000);
}
spin_unlock_irqrestore(&tp->lock, flags);
}
struct rtl8169_private *tp = netdev_priv(dev);
struct rtl_fw *rtl_fw = tp->rtl_fw;
- strcpy(info->driver, MODULENAME);
- strcpy(info->version, RTL8169_VERSION);
- strcpy(info->bus_info, pci_name(tp->pci_dev));
+ strlcpy(info->driver, MODULENAME, sizeof(info->driver));
+ strlcpy(info->version, RTL8169_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
- strcpy(info->fw_version, IS_ERR_OR_NULL(rtl_fw) ? "N/A" :
- rtl_fw->version);
+ if (!IS_ERR_OR_NULL(rtl_fw))
+ strlcpy(info->fw_version, rtl_fw->version,
+ sizeof(info->fw_version));
}
static int rtl8169_get_regs_len(struct net_device *dev)
return ret;
}
-static u32 rtl8169_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t rtl8169_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct rtl8169_private *tp = netdev_priv(dev);
return features;
}
-static int rtl8169_set_features(struct net_device *dev, u32 features)
+static int rtl8169_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct rtl8169_private *tp = netdev_priv(dev);
void __iomem *ioaddr = tp->mmio_addr;
};
/* Cfg9346_Unlock assumed. */
-static unsigned rtl_try_msi(struct pci_dev *pdev, void __iomem *ioaddr,
+static unsigned rtl_try_msi(struct rtl8169_private *tp,
const struct rtl_cfg_info *cfg)
{
+ void __iomem *ioaddr = tp->mmio_addr;
unsigned msi = 0;
u8 cfg2;
cfg2 = RTL_R8(Config2) & ~MSIEnable;
if (cfg->features & RTL_FEATURE_MSI) {
- if (pci_enable_msi(pdev)) {
- dev_info(&pdev->dev, "no MSI. Back to INTx.\n");
+ if (pci_enable_msi(tp->pci_dev)) {
+ netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n");
} else {
cfg2 |= MSIEnable;
msi = RTL_FEATURE_MSI;
}
}
- RTL_W8(Config2, cfg2);
+ if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
+ RTL_W8(Config2, cfg2);
return msi;
}
break;
udelay(100);
}
-
- rtl8169_init_ring_indexes(tp);
}
static int __devinit
tp->features |= RTL_FEATURE_WOL;
if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0)
tp->features |= RTL_FEATURE_WOL;
- tp->features |= rtl_try_msi(pdev, ioaddr, cfg);
+ tp->features |= rtl_try_msi(tp, cfg);
RTL_W8(Cfg9346, Cfg9346_Lock);
if (rtl_tbi_enabled(tp)) {
spin_lock_init(&tp->lock);
/* Get MAC address */
- for (i = 0; i < MAC_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = RTL_R8(MAC0 + i);
memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
void __iomem *ioaddr = tp->mmio_addr;
/* Disable interrupts */
- rtl8169_irq_mask_and_ack(ioaddr);
+ rtl8169_irq_mask_and_ack(tp);
rtl_rx_close(tp);
RTL_W16(IntrMitigate, 0x5151);
/* Work around for RxFIFO overflow. */
- if (tp->mac_version == RTL_GIGA_MAC_VER_11 ||
- tp->mac_version == RTL_GIGA_MAC_VER_22) {
+ if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
tp->intr_event |= RxFIFOOver | PCSTimeout;
tp->intr_event &= ~RxOverflow;
}
void __iomem *ioaddr = tp->mmio_addr;
struct pci_dev *pdev = tp->pci_dev;
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_30) {
+ tp->intr_event &= ~RxFIFOOver;
+ tp->napi_event &= ~RxFIFOOver;
+ }
+
if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
tp->mac_version == RTL_GIGA_MAC_VER_16) {
int cap = pci_pcie_cap(pdev);
/* Wait for any pending NAPI task to complete */
napi_disable(&tp->napi);
- rtl8169_irq_mask_and_ack(ioaddr);
+ rtl8169_irq_mask_and_ack(tp);
tp->intr_mask = 0xffff;
RTL_W16(IntrMask, tp->intr_event);
if (!netif_running(dev))
goto out_unlock;
+ rtl8169_hw_reset(tp);
+
rtl8169_wait_for_quiescence(dev);
for (i = 0; i < NUM_RX_DESC; i++)
rtl8169_mark_to_asic(tp->RxDescArray + i, rx_buf_sz);
rtl8169_tx_clear(tp);
+ rtl8169_init_ring_indexes(tp);
- rtl8169_hw_reset(tp);
rtl_hw_start(dev);
netif_wake_queue(dev);
rtl8169_check_link_status(dev, tp, tp->mmio_addr);
static void rtl8169_tx_timeout(struct net_device *dev)
{
- struct rtl8169_private *tp = netdev_priv(dev);
-
- rtl8169_hw_reset(tp);
-
- /* Let's wait a bit while any (async) irq lands on */
rtl8169_schedule_work(dev, rtl8169_reset_task);
}
*/
status = RTL_R16(IntrStatus);
while (status && status != 0xffff) {
+ status &= tp->intr_event;
+ if (!status)
+ break;
+
handled = 1;
/* Handle all of the error cases first. These will reset
switch (tp->mac_version) {
/* Work around for rx fifo overflow */
case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_22:
- case RTL_GIGA_MAC_VER_26:
netif_stop_queue(dev);
rtl8169_tx_timeout(dev);
goto done;
- /* Testers needed. */
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_19:
- case RTL_GIGA_MAC_VER_20:
- case RTL_GIGA_MAC_VER_21:
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- /* Experimental science. Pktgen proof. */
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_25:
- if (status == RxFIFOOver)
- goto done;
- break;
default:
break;
}
},
};
-static int __init sh_eth_init(void)
-{
- return platform_driver_register(&sh_eth_driver);
-}
-
-static void __exit sh_eth_cleanup(void)
-{
- platform_driver_unregister(&sh_eth_driver);
-}
-
-module_init(sh_eth_init);
-module_exit(sh_eth_cleanup);
+module_platform_driver(sh_eth_driver);
MODULE_AUTHOR("Nobuhiro Iwamatsu, Yoshihiro Shimoda");
MODULE_DESCRIPTION("Renesas SuperH Ethernet driver");
}
};
-static int __init sgiseeq_module_init(void)
-{
- if (platform_driver_register(&sgiseeq_driver)) {
- printk(KERN_ERR "Driver registration failed\n");
- return -ENODEV;
- }
-
- return 0;
-}
-
-static void __exit sgiseeq_module_exit(void)
-{
- platform_driver_unregister(&sgiseeq_driver);
-}
-
-module_init(sgiseeq_module_init);
-module_exit(sgiseeq_module_exit);
+module_platform_driver(sgiseeq_driver);
MODULE_DESCRIPTION("SGI Seeq 8003 driver");
MODULE_AUTHOR("Linux/MIPS Mailing List <linux-mips@linux-mips.org>");
if (efx->n_channels > 1)
get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
- efx->rx_indir_table[i] = i % efx->n_rx_channels;
+ efx->rx_indir_table[i] =
+ ethtool_rxfh_indir_default(i, efx->n_rx_channels);
efx_set_channels(efx);
netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
/* Otherwise efx_start_port() will do this */
}
-static int efx_set_features(struct net_device *net_dev, u32 data)
+static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
{
struct efx_nic *efx = netdev_priv(net_dev);
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE,
PCI_DEVICE_ID_SOLARFLARE_SFC4000B),
.driver_data = (unsigned long) &falcon_b0_nic_type},
- {PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, BETHPAGE_A_P_DEVID),
+ {PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0803), /* SFC9020 */
.driver_data = (unsigned long) &siena_a0_nic_type},
- {PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, SIENA_A_P_DEVID),
+ {PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0813), /* SFL9021 */
.driver_data = (unsigned long) &siena_a0_nic_type},
{0} /* end of list */
};
#include "net_driver.h"
#include "filter.h"
-/* PCI IDs */
-#define BETHPAGE_A_P_DEVID 0x0803
-#define SIENA_A_P_DEVID 0x0813
-
/* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
#define EFX_MEM_BAR 2
extern int efx_probe_filters(struct efx_nic *efx);
extern void efx_restore_filters(struct efx_nic *efx);
extern void efx_remove_filters(struct efx_nic *efx);
-extern int efx_filter_insert_filter(struct efx_nic *efx,
+extern s32 efx_filter_insert_filter(struct efx_nic *efx,
struct efx_filter_spec *spec,
bool replace);
-extern int efx_filter_remove_filter(struct efx_nic *efx,
- struct efx_filter_spec *spec);
+extern int efx_filter_remove_id_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id);
+extern int efx_filter_get_filter_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *);
extern void efx_filter_clear_rx(struct efx_nic *efx,
enum efx_filter_priority priority);
+extern u32 efx_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority);
+extern u32 efx_filter_get_rx_id_limit(struct efx_nic *efx);
+extern s32 efx_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size);
#ifdef CONFIG_RFS_ACCEL
extern int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
u16 rxq_index, u32 flow_id);
return efx_reset(efx, rc);
}
+static int efx_ethtool_get_class_rule(struct efx_nic *efx,
+ struct ethtool_rx_flow_spec *rule)
+{
+ struct ethtool_tcpip4_spec *ip_entry = &rule->h_u.tcp_ip4_spec;
+ struct ethtool_tcpip4_spec *ip_mask = &rule->m_u.tcp_ip4_spec;
+ struct efx_filter_spec spec;
+ u16 vid;
+ u8 proto;
+ int rc;
+
+ rc = efx_filter_get_filter_safe(efx, EFX_FILTER_PRI_MANUAL,
+ rule->location, &spec);
+ if (rc)
+ return rc;
+
+ if (spec.dmaq_id == 0xfff)
+ rule->ring_cookie = RX_CLS_FLOW_DISC;
+ else
+ rule->ring_cookie = spec.dmaq_id;
+
+ rc = efx_filter_get_eth_local(&spec, &vid,
+ rule->h_u.ether_spec.h_dest);
+ if (rc == 0) {
+ rule->flow_type = ETHER_FLOW;
+ memset(rule->m_u.ether_spec.h_dest, ~0, ETH_ALEN);
+ if (vid != EFX_FILTER_VID_UNSPEC) {
+ rule->flow_type |= FLOW_EXT;
+ rule->h_ext.vlan_tci = htons(vid);
+ rule->m_ext.vlan_tci = htons(0xfff);
+ }
+ return 0;
+ }
+
+ rc = efx_filter_get_ipv4_local(&spec, &proto,
+ &ip_entry->ip4dst, &ip_entry->pdst);
+ if (rc != 0) {
+ rc = efx_filter_get_ipv4_full(
+ &spec, &proto, &ip_entry->ip4src, &ip_entry->psrc,
+ &ip_entry->ip4dst, &ip_entry->pdst);
+ EFX_WARN_ON_PARANOID(rc);
+ ip_mask->ip4src = ~0;
+ ip_mask->psrc = ~0;
+ }
+ rule->flow_type = (proto == IPPROTO_TCP) ? TCP_V4_FLOW : UDP_V4_FLOW;
+ ip_mask->ip4dst = ~0;
+ ip_mask->pdst = ~0;
+ return rc;
+}
+
static int
efx_ethtool_get_rxnfc(struct net_device *net_dev,
- struct ethtool_rxnfc *info, u32 *rules __always_unused)
+ struct ethtool_rxnfc *info, u32 *rule_locs)
{
struct efx_nic *efx = netdev_priv(net_dev);
return 0;
}
+ case ETHTOOL_GRXCLSRLCNT:
+ info->data = efx_filter_get_rx_id_limit(efx);
+ if (info->data == 0)
+ return -EOPNOTSUPP;
+ info->data |= RX_CLS_LOC_SPECIAL;
+ info->rule_cnt =
+ efx_filter_count_rx_used(efx, EFX_FILTER_PRI_MANUAL);
+ return 0;
+
+ case ETHTOOL_GRXCLSRULE:
+ if (efx_filter_get_rx_id_limit(efx) == 0)
+ return -EOPNOTSUPP;
+ return efx_ethtool_get_class_rule(efx, &info->fs);
+
+ case ETHTOOL_GRXCLSRLALL: {
+ s32 rc;
+ info->data = efx_filter_get_rx_id_limit(efx);
+ if (info->data == 0)
+ return -EOPNOTSUPP;
+ rc = efx_filter_get_rx_ids(efx, EFX_FILTER_PRI_MANUAL,
+ rule_locs, info->rule_cnt);
+ if (rc < 0)
+ return rc;
+ info->rule_cnt = rc;
+ return 0;
+ }
+
default:
return -EOPNOTSUPP;
}
}
-static int efx_ethtool_set_rx_ntuple(struct net_device *net_dev,
- struct ethtool_rx_ntuple *ntuple)
+static int efx_ethtool_set_class_rule(struct efx_nic *efx,
+ struct ethtool_rx_flow_spec *rule)
{
- struct efx_nic *efx = netdev_priv(net_dev);
- struct ethtool_tcpip4_spec *ip_entry = &ntuple->fs.h_u.tcp_ip4_spec;
- struct ethtool_tcpip4_spec *ip_mask = &ntuple->fs.m_u.tcp_ip4_spec;
- struct ethhdr *mac_entry = &ntuple->fs.h_u.ether_spec;
- struct ethhdr *mac_mask = &ntuple->fs.m_u.ether_spec;
- struct efx_filter_spec filter;
+ struct ethtool_tcpip4_spec *ip_entry = &rule->h_u.tcp_ip4_spec;
+ struct ethtool_tcpip4_spec *ip_mask = &rule->m_u.tcp_ip4_spec;
+ struct ethhdr *mac_entry = &rule->h_u.ether_spec;
+ struct ethhdr *mac_mask = &rule->m_u.ether_spec;
+ struct efx_filter_spec spec;
int rc;
- /* Range-check action */
- if (ntuple->fs.action < ETHTOOL_RXNTUPLE_ACTION_CLEAR ||
- ntuple->fs.action >= (s32)efx->n_rx_channels)
+ /* Check that user wants us to choose the location */
+ if (rule->location != RX_CLS_LOC_ANY &&
+ rule->location != RX_CLS_LOC_FIRST &&
+ rule->location != RX_CLS_LOC_LAST)
+ return -EINVAL;
+
+ /* Range-check ring_cookie */
+ if (rule->ring_cookie >= efx->n_rx_channels &&
+ rule->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
- if (~ntuple->fs.data_mask)
+ /* Check for unsupported extensions */
+ if ((rule->flow_type & FLOW_EXT) &&
+ (rule->m_ext.vlan_etype | rule->m_ext.data[0] |
+ rule->m_ext.data[1]))
return -EINVAL;
- efx_filter_init_rx(&filter, EFX_FILTER_PRI_MANUAL, 0,
- (ntuple->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) ?
- 0xfff : ntuple->fs.action);
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL,
+ (rule->location == RX_CLS_LOC_FIRST) ?
+ EFX_FILTER_FLAG_RX_OVERRIDE_IP : 0,
+ (rule->ring_cookie == RX_CLS_FLOW_DISC) ?
+ 0xfff : rule->ring_cookie);
- switch (ntuple->fs.flow_type) {
+ switch (rule->flow_type) {
case TCP_V4_FLOW:
case UDP_V4_FLOW: {
- u8 proto = (ntuple->fs.flow_type == TCP_V4_FLOW ?
+ u8 proto = (rule->flow_type == TCP_V4_FLOW ?
IPPROTO_TCP : IPPROTO_UDP);
/* Must match all of destination, */
- if (ip_mask->ip4dst | ip_mask->pdst)
+ if ((__force u32)~ip_mask->ip4dst |
+ (__force u16)~ip_mask->pdst)
return -EINVAL;
/* all or none of source, */
if ((ip_mask->ip4src | ip_mask->psrc) &&
(__force u16)~ip_mask->psrc))
return -EINVAL;
/* and nothing else */
- if ((u8)~ip_mask->tos | (u16)~ntuple->fs.vlan_tag_mask)
+ if (ip_mask->tos | rule->m_ext.vlan_tci)
return -EINVAL;
- if (!ip_mask->ip4src)
- rc = efx_filter_set_ipv4_full(&filter, proto,
+ if (ip_mask->ip4src)
+ rc = efx_filter_set_ipv4_full(&spec, proto,
ip_entry->ip4dst,
ip_entry->pdst,
ip_entry->ip4src,
ip_entry->psrc);
else
- rc = efx_filter_set_ipv4_local(&filter, proto,
+ rc = efx_filter_set_ipv4_local(&spec, proto,
ip_entry->ip4dst,
ip_entry->pdst);
if (rc)
break;
}
- case ETHER_FLOW:
- /* Must match all of destination, */
- if (!is_zero_ether_addr(mac_mask->h_dest))
+ case ETHER_FLOW | FLOW_EXT:
+ /* Must match all or none of VID */
+ if (rule->m_ext.vlan_tci != htons(0xfff) &&
+ rule->m_ext.vlan_tci != 0)
return -EINVAL;
- /* all or none of VID, */
- if (ntuple->fs.vlan_tag_mask != 0xf000 &&
- ntuple->fs.vlan_tag_mask != 0xffff)
+ case ETHER_FLOW:
+ /* Must match all of destination */
+ if (!is_broadcast_ether_addr(mac_mask->h_dest))
return -EINVAL;
/* and nothing else */
- if (!is_broadcast_ether_addr(mac_mask->h_source) ||
- mac_mask->h_proto != htons(0xffff))
+ if (!is_zero_ether_addr(mac_mask->h_source) ||
+ mac_mask->h_proto)
return -EINVAL;
rc = efx_filter_set_eth_local(
- &filter,
- (ntuple->fs.vlan_tag_mask == 0xf000) ?
- ntuple->fs.vlan_tag : EFX_FILTER_VID_UNSPEC,
+ &spec,
+ (rule->flow_type & FLOW_EXT && rule->m_ext.vlan_tci) ?
+ ntohs(rule->h_ext.vlan_tci) : EFX_FILTER_VID_UNSPEC,
mac_entry->h_dest);
if (rc)
return rc;
return -EINVAL;
}
- if (ntuple->fs.action == ETHTOOL_RXNTUPLE_ACTION_CLEAR)
- return efx_filter_remove_filter(efx, &filter);
+ rc = efx_filter_insert_filter(efx, &spec, true);
+ if (rc < 0)
+ return rc;
- rc = efx_filter_insert_filter(efx, &filter, true);
- return rc < 0 ? rc : 0;
+ rule->location = rc;
+ return 0;
}
-static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev,
- struct ethtool_rxfh_indir *indir)
+static int efx_ethtool_set_rxnfc(struct net_device *net_dev,
+ struct ethtool_rxnfc *info)
{
struct efx_nic *efx = netdev_priv(net_dev);
- size_t copy_size =
- min_t(size_t, indir->size, ARRAY_SIZE(efx->rx_indir_table));
- if (efx_nic_rev(efx) < EFX_REV_FALCON_B0)
+ if (efx_filter_get_rx_id_limit(efx) == 0)
return -EOPNOTSUPP;
- indir->size = ARRAY_SIZE(efx->rx_indir_table);
- memcpy(indir->ring_index, efx->rx_indir_table,
- copy_size * sizeof(indir->ring_index[0]));
- return 0;
+ switch (info->cmd) {
+ case ETHTOOL_SRXCLSRLINS:
+ return efx_ethtool_set_class_rule(efx, &info->fs);
+
+ case ETHTOOL_SRXCLSRLDEL:
+ return efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_MANUAL,
+ info->fs.location);
+
+ default:
+ return -EOPNOTSUPP;
+ }
}
-static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
- const struct ethtool_rxfh_indir *indir)
+static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
- size_t i;
- if (efx_nic_rev(efx) < EFX_REV_FALCON_B0)
- return -EOPNOTSUPP;
+ return (efx_nic_rev(efx) < EFX_REV_FALCON_B0 ?
+ 0 : ARRAY_SIZE(efx->rx_indir_table));
+}
- /* Validate size and indices */
- if (indir->size != ARRAY_SIZE(efx->rx_indir_table))
- return -EINVAL;
- for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
- if (indir->ring_index[i] >= efx->n_rx_channels)
- return -EINVAL;
+static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
+ return 0;
+}
+
+static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
+ const u32 *indir)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
- memcpy(efx->rx_indir_table, indir->ring_index,
- sizeof(efx->rx_indir_table));
+ memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table));
efx_nic_push_rx_indir_table(efx);
return 0;
}
.set_wol = efx_ethtool_set_wol,
.reset = efx_ethtool_reset,
.get_rxnfc = efx_ethtool_get_rxnfc,
- .set_rx_ntuple = efx_ethtool_set_rx_ntuple,
+ .set_rxnfc = efx_ethtool_set_rxnfc,
+ .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size,
.get_rxfh_indir = efx_ethtool_get_rxfh_indir,
.set_rxfh_indir = efx_ethtool_set_rxfh_indir,
};
if (!nic_data->stats_pending)
return;
- nic_data->stats_pending = 0;
+ nic_data->stats_pending = false;
if (*nic_data->stats_dma_done == FALCON_STATS_DONE) {
rmb(); /* read the done flag before the stats */
efx->mac_op->update_stats(efx);
spec->data[2] = ntohl(host2);
}
+static inline void __efx_filter_get_ipv4(const struct efx_filter_spec *spec,
+ __be32 *host1, __be16 *port1,
+ __be32 *host2, __be16 *port2)
+{
+ *host1 = htonl(spec->data[0] >> 16 | spec->data[1] << 16);
+ *port1 = htons(spec->data[0]);
+ *host2 = htonl(spec->data[2]);
+ *port2 = htons(spec->data[1] >> 16);
+}
+
/**
* efx_filter_set_ipv4_local - specify IPv4 host, transport protocol and port
* @spec: Specification to initialise
return 0;
}
+int efx_filter_get_ipv4_local(const struct efx_filter_spec *spec,
+ u8 *proto, __be32 *host, __be16 *port)
+{
+ __be32 host1;
+ __be16 port1;
+
+ switch (spec->type) {
+ case EFX_FILTER_TCP_WILD:
+ *proto = IPPROTO_TCP;
+ __efx_filter_get_ipv4(spec, &host1, &port1, host, port);
+ return 0;
+ case EFX_FILTER_UDP_WILD:
+ *proto = IPPROTO_UDP;
+ __efx_filter_get_ipv4(spec, &host1, port, host, &port1);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
/**
* efx_filter_set_ipv4_full - specify IPv4 hosts, transport protocol and ports
* @spec: Specification to initialise
return 0;
}
+int efx_filter_get_ipv4_full(const struct efx_filter_spec *spec,
+ u8 *proto, __be32 *host, __be16 *port,
+ __be32 *rhost, __be16 *rport)
+{
+ switch (spec->type) {
+ case EFX_FILTER_TCP_FULL:
+ *proto = IPPROTO_TCP;
+ break;
+ case EFX_FILTER_UDP_FULL:
+ *proto = IPPROTO_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ __efx_filter_get_ipv4(spec, rhost, rport, host, port);
+ return 0;
+}
+
/**
* efx_filter_set_eth_local - specify local Ethernet address and optional VID
* @spec: Specification to initialise
return 0;
}
+int efx_filter_get_eth_local(const struct efx_filter_spec *spec,
+ u16 *vid, u8 *addr)
+{
+ switch (spec->type) {
+ case EFX_FILTER_MAC_WILD:
+ *vid = EFX_FILTER_VID_UNSPEC;
+ break;
+ case EFX_FILTER_MAC_FULL:
+ *vid = spec->data[0];
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ addr[0] = spec->data[2] >> 8;
+ addr[1] = spec->data[2];
+ addr[2] = spec->data[1] >> 24;
+ addr[3] = spec->data[1] >> 16;
+ addr[4] = spec->data[1] >> 8;
+ addr[5] = spec->data[1];
+ return 0;
+}
+
/* Build a filter entry and return its n-tuple key. */
static u32 efx_filter_build(efx_oword_t *filter, struct efx_filter_spec *spec)
{
static int efx_filter_search(struct efx_filter_table *table,
struct efx_filter_spec *spec, u32 key,
- bool for_insert, int *depth_required)
+ bool for_insert, unsigned int *depth_required)
{
unsigned hash, incr, filter_idx, depth, depth_max;
}
}
-/* Construct/deconstruct external filter IDs */
+/*
+ * Construct/deconstruct external filter IDs. These must be ordered
+ * by matching priority, for RX NFC semantics.
+ *
+ * Each RX MAC filter entry has a flag for whether it can override an
+ * RX IP filter that also matches. So we assign locations for MAC
+ * filters with overriding behaviour, then for IP filters, then for
+ * MAC filters without overriding behaviour.
+ */
+
+#define EFX_FILTER_INDEX_WIDTH 13
+#define EFX_FILTER_INDEX_MASK ((1 << EFX_FILTER_INDEX_WIDTH) - 1)
+
+static inline u32 efx_filter_make_id(enum efx_filter_table_id table_id,
+ unsigned int index, u8 flags)
+{
+ return (table_id == EFX_FILTER_TABLE_RX_MAC &&
+ flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP) ?
+ index :
+ (table_id + 1) << EFX_FILTER_INDEX_WIDTH | index;
+}
+
+static inline enum efx_filter_table_id efx_filter_id_table_id(u32 id)
+{
+ return (id <= EFX_FILTER_INDEX_MASK) ?
+ EFX_FILTER_TABLE_RX_MAC :
+ (id >> EFX_FILTER_INDEX_WIDTH) - 1;
+}
+
+static inline unsigned int efx_filter_id_index(u32 id)
+{
+ return id & EFX_FILTER_INDEX_MASK;
+}
-static inline int
-efx_filter_make_id(enum efx_filter_table_id table_id, unsigned index)
+static inline u8 efx_filter_id_flags(u32 id)
{
- return table_id << 16 | index;
+ return (id <= EFX_FILTER_INDEX_MASK) ?
+ EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_OVERRIDE_IP :
+ EFX_FILTER_FLAG_RX;
+}
+
+u32 efx_filter_get_rx_id_limit(struct efx_nic *efx)
+{
+ struct efx_filter_state *state = efx->filter_state;
+
+ if (state->table[EFX_FILTER_TABLE_RX_MAC].size != 0)
+ return ((EFX_FILTER_TABLE_RX_MAC + 1) << EFX_FILTER_INDEX_WIDTH)
+ + state->table[EFX_FILTER_TABLE_RX_MAC].size;
+ else if (state->table[EFX_FILTER_TABLE_RX_IP].size != 0)
+ return ((EFX_FILTER_TABLE_RX_IP + 1) << EFX_FILTER_INDEX_WIDTH)
+ + state->table[EFX_FILTER_TABLE_RX_IP].size;
+ else
+ return 0;
}
/**
* On success, return the filter ID.
* On failure, return a negative error code.
*/
-int efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
+s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
bool replace)
{
struct efx_filter_state *state = efx->filter_state;
struct efx_filter_table *table = efx_filter_spec_table(state, spec);
struct efx_filter_spec *saved_spec;
efx_oword_t filter;
- int filter_idx, depth;
+ unsigned int filter_idx, depth;
u32 key;
int rc;
netif_vdbg(efx, hw, efx->net_dev,
"%s: filter type %d index %d rxq %u set",
__func__, spec->type, filter_idx, spec->dmaq_id);
- rc = efx_filter_make_id(table->id, filter_idx);
+ rc = efx_filter_make_id(table->id, filter_idx, spec->flags);
out:
spin_unlock_bh(&state->lock);
static void efx_filter_table_clear_entry(struct efx_nic *efx,
struct efx_filter_table *table,
- int filter_idx)
+ unsigned int filter_idx)
{
static efx_oword_t filter;
}
/**
- * efx_filter_remove_filter - remove a filter by specification
+ * efx_filter_remove_id_safe - remove a filter by ID, carefully
* @efx: NIC from which to remove the filter
- * @spec: Specification for the filter
+ * @priority: Priority of filter, as passed to @efx_filter_insert_filter
+ * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
*
- * On success, return zero.
- * On failure, return a negative error code.
+ * This function will range-check @filter_id, so it is safe to call
+ * with a value passed from userland.
*/
-int efx_filter_remove_filter(struct efx_nic *efx, struct efx_filter_spec *spec)
+int efx_filter_remove_id_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id)
{
struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_table *table = efx_filter_spec_table(state, spec);
- struct efx_filter_spec *saved_spec;
- efx_oword_t filter;
- int filter_idx, depth;
- u32 key;
+ enum efx_filter_table_id table_id;
+ struct efx_filter_table *table;
+ unsigned int filter_idx;
+ struct efx_filter_spec *spec;
+ u8 filter_flags;
int rc;
- if (!table)
- return -EINVAL;
+ table_id = efx_filter_id_table_id(filter_id);
+ if ((unsigned int)table_id >= EFX_FILTER_TABLE_COUNT)
+ return -ENOENT;
+ table = &state->table[table_id];
- key = efx_filter_build(&filter, spec);
+ filter_idx = efx_filter_id_index(filter_id);
+ if (filter_idx >= table->size)
+ return -ENOENT;
+ spec = &table->spec[filter_idx];
- spin_lock_bh(&state->lock);
+ filter_flags = efx_filter_id_flags(filter_id);
- rc = efx_filter_search(table, spec, key, false, &depth);
- if (rc < 0)
- goto out;
- filter_idx = rc;
- saved_spec = &table->spec[filter_idx];
+ spin_lock_bh(&state->lock);
- if (spec->priority < saved_spec->priority) {
- rc = -EPERM;
- goto out;
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ spec->priority == priority && spec->flags == filter_flags) {
+ efx_filter_table_clear_entry(efx, table, filter_idx);
+ if (table->used == 0)
+ efx_filter_table_reset_search_depth(table);
+ rc = 0;
+ } else {
+ rc = -ENOENT;
}
- efx_filter_table_clear_entry(efx, table, filter_idx);
- if (table->used == 0)
- efx_filter_table_reset_search_depth(table);
- rc = 0;
+ spin_unlock_bh(&state->lock);
+
+ return rc;
+}
+
+/**
+ * efx_filter_get_filter_safe - retrieve a filter by ID, carefully
+ * @efx: NIC from which to remove the filter
+ * @priority: Priority of filter, as passed to @efx_filter_insert_filter
+ * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
+ * @spec: Buffer in which to store filter specification
+ *
+ * This function will range-check @filter_id, so it is safe to call
+ * with a value passed from userland.
+ */
+int efx_filter_get_filter_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *spec_buf)
+{
+ struct efx_filter_state *state = efx->filter_state;
+ enum efx_filter_table_id table_id;
+ struct efx_filter_table *table;
+ struct efx_filter_spec *spec;
+ unsigned int filter_idx;
+ u8 filter_flags;
+ int rc;
+
+ table_id = efx_filter_id_table_id(filter_id);
+ if ((unsigned int)table_id >= EFX_FILTER_TABLE_COUNT)
+ return -ENOENT;
+ table = &state->table[table_id];
+
+ filter_idx = efx_filter_id_index(filter_id);
+ if (filter_idx >= table->size)
+ return -ENOENT;
+ spec = &table->spec[filter_idx];
+
+ filter_flags = efx_filter_id_flags(filter_id);
+
+ spin_lock_bh(&state->lock);
+
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ spec->priority == priority && spec->flags == filter_flags) {
+ *spec_buf = *spec;
+ rc = 0;
+ } else {
+ rc = -ENOENT;
+ }
-out:
spin_unlock_bh(&state->lock);
+
return rc;
}
{
struct efx_filter_state *state = efx->filter_state;
struct efx_filter_table *table = &state->table[table_id];
- int filter_idx;
+ unsigned int filter_idx;
spin_lock_bh(&state->lock);
efx_filter_table_clear(efx, EFX_FILTER_TABLE_RX_MAC, priority);
}
+u32 efx_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ struct efx_filter_state *state = efx->filter_state;
+ enum efx_filter_table_id table_id;
+ struct efx_filter_table *table;
+ unsigned int filter_idx;
+ u32 count = 0;
+
+ spin_lock_bh(&state->lock);
+
+ for (table_id = EFX_FILTER_TABLE_RX_IP;
+ table_id <= EFX_FILTER_TABLE_RX_MAC;
+ table_id++) {
+ table = &state->table[table_id];
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ table->spec[filter_idx].priority == priority)
+ ++count;
+ }
+ }
+
+ spin_unlock_bh(&state->lock);
+
+ return count;
+}
+
+s32 efx_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size)
+{
+ struct efx_filter_state *state = efx->filter_state;
+ enum efx_filter_table_id table_id;
+ struct efx_filter_table *table;
+ unsigned int filter_idx;
+ s32 count = 0;
+
+ spin_lock_bh(&state->lock);
+
+ for (table_id = EFX_FILTER_TABLE_RX_IP;
+ table_id <= EFX_FILTER_TABLE_RX_MAC;
+ table_id++) {
+ table = &state->table[table_id];
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ table->spec[filter_idx].priority == priority) {
+ if (count == size) {
+ count = -EMSGSIZE;
+ goto out;
+ }
+ buf[count++] = efx_filter_make_id(
+ table_id, filter_idx,
+ table->spec[filter_idx].flags);
+ }
+ }
+ }
+out:
+ spin_unlock_bh(&state->lock);
+
+ return count;
+}
+
/* Restore filter stater after reset */
void efx_restore_filters(struct efx_nic *efx)
{
enum efx_filter_table_id table_id;
struct efx_filter_table *table;
efx_oword_t filter;
- int filter_idx;
+ unsigned int filter_idx;
spin_lock_bh(&state->lock);
*
* Use the efx_filter_set_*() functions to initialise the @type and
* @data fields.
+ *
+ * The @priority field is used by software to determine whether a new
+ * filter may replace an old one. The hardware priority of a filter
+ * depends on the filter type and %EFX_FILTER_FLAG_RX_OVERRIDE_IP
+ * flag.
*/
struct efx_filter_spec {
u8 type:4;
extern int efx_filter_set_ipv4_local(struct efx_filter_spec *spec, u8 proto,
__be32 host, __be16 port);
+extern int efx_filter_get_ipv4_local(const struct efx_filter_spec *spec,
+ u8 *proto, __be32 *host, __be16 *port);
extern int efx_filter_set_ipv4_full(struct efx_filter_spec *spec, u8 proto,
__be32 host, __be16 port,
__be32 rhost, __be16 rport);
+extern int efx_filter_get_ipv4_full(const struct efx_filter_spec *spec,
+ u8 *proto, __be32 *host, __be16 *port,
+ __be32 *rhost, __be16 *rport);
extern int efx_filter_set_eth_local(struct efx_filter_spec *spec,
u16 vid, const u8 *addr);
+extern int efx_filter_get_eth_local(const struct efx_filter_spec *spec,
+ u16 *vid, u8 *addr);
enum {
EFX_FILTER_VID_UNSPEC = 0xffff,
};
rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type);
if (rc)
goto out;
- part->mcdi.updating = 1;
+ part->mcdi.updating = true;
}
/* The MCDI interface can in fact do multiple erase blocks at once;
rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type);
if (rc)
goto out;
- part->mcdi.updating = 1;
+ part->mcdi.updating = true;
}
while (offset < end) {
int rc = 0;
if (part->mcdi.updating) {
- part->mcdi.updating = 0;
+ part->mcdi.updating = false;
rc = efx_mcdi_nvram_update_finish(efx, part->mcdi.nvram_type);
}
unsigned int phys_addr_channels;
unsigned int tx_dc_base;
unsigned int rx_dc_base;
- u32 offload_features;
+ netdev_features_t offload_features;
};
/**************************************************************************
if (efx->net_dev->features & NETIF_F_RXHASH)
skb->rxhash = efx_rx_buf_hash(eh);
- skb_frag_set_page(skb, 0, page);
- skb_shinfo(skb)->frags[0].page_offset =
- efx_rx_buf_offset(efx, rx_buf);
- skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx_buf->len);
- skb_shinfo(skb)->nr_frags = 1;
+ skb_fill_page_desc(skb, 0, page,
+ efx_rx_buf_offset(efx, rx_buf), rx_buf->len);
skb->len = rx_buf->len;
skb->data_len = rx_buf->len;
rx_queue->ptr_mask);
/* Allocate RX buffers */
- rx_queue->buffer = kzalloc(entries * sizeof(*rx_queue->buffer),
+ rx_queue->buffer = kcalloc(entries, sizeof(*rx_queue->buffer),
GFP_KERNEL);
if (!rx_queue->buffer)
return -ENOMEM;
/* Determine how many packets to send */
state->packet_count = efx->txq_entries / 3;
state->packet_count = min(1 << (i << 2), state->packet_count);
- state->skbs = kzalloc(sizeof(state->skbs[0]) *
- state->packet_count, GFP_KERNEL);
+ state->skbs = kcalloc(state->packet_count,
+ sizeof(state->skbs[0]), GFP_KERNEL);
if (!state->skbs)
return -ENOMEM;
state->flush = false;
static int siena_probe_nic(struct efx_nic *efx)
{
struct siena_nic_data *nic_data;
- bool already_attached = 0;
+ bool already_attached = false;
efx_oword_t reg;
int rc;
#define EFX_TXQ_THRESHOLD(_efx) ((_efx)->txq_entries / 2u)
static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
- struct efx_tx_buffer *buffer)
+ struct efx_tx_buffer *buffer,
+ unsigned int *pkts_compl,
+ unsigned int *bytes_compl)
{
if (buffer->unmap_len) {
struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
}
if (buffer->skb) {
+ (*pkts_compl)++;
+ (*bytes_compl) += buffer->skb->len;
dev_kfree_skb_any((struct sk_buff *) buffer->skb);
buffer->skb = NULL;
netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
buffer->skb = skb;
buffer->continuation = false;
+ netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
+
/* Pass off to hardware */
efx_nic_push_buffers(tx_queue);
unwind:
/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
+ unsigned int pkts_compl = 0, bytes_compl = 0;
--tx_queue->insert_count;
insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
buffer = &tx_queue->buffer[insert_ptr];
- efx_dequeue_buffer(tx_queue, buffer);
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
buffer->len = 0;
}
* specified index.
*/
static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
- unsigned int index)
+ unsigned int index,
+ unsigned int *pkts_compl,
+ unsigned int *bytes_compl)
{
struct efx_nic *efx = tx_queue->efx;
unsigned int stop_index, read_ptr;
return;
}
- efx_dequeue_buffer(tx_queue, buffer);
+ efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
buffer->continuation = true;
buffer->len = 0;
{
unsigned fill_level;
struct efx_nic *efx = tx_queue->efx;
+ unsigned int pkts_compl = 0, bytes_compl = 0;
EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask);
- efx_dequeue_buffers(tx_queue, index);
+ efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
+ netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
/* See if we need to restart the netif queue. This barrier
* separates the update of read_count from the test of the
tx_queue->queue, efx->txq_entries, tx_queue->ptr_mask);
/* Allocate software ring */
- tx_queue->buffer = kzalloc(entries * sizeof(*tx_queue->buffer),
+ tx_queue->buffer = kcalloc(entries, sizeof(*tx_queue->buffer),
GFP_KERNEL);
if (!tx_queue->buffer)
return -ENOMEM;
/* Free any buffers left in the ring */
while (tx_queue->read_count != tx_queue->write_count) {
+ unsigned int pkts_compl = 0, bytes_compl = 0;
buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
- efx_dequeue_buffer(tx_queue, buffer);
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
buffer->continuation = true;
buffer->len = 0;
++tx_queue->read_count;
}
+ netdev_tx_reset_queue(tx_queue->core_txq);
}
void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
goto mem_err;
}
+ netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
+
/* Pass off to hardware */
efx_nic_push_buffers(tx_queue);
#include <linux/tcp.h> /* struct tcphdr */
#include <linux/skbuff.h>
#include <linux/mii.h> /* MII definitions */
+#include <linux/crc32.h>
#include <asm/ip32/mace.h>
#include <asm/ip32/ip32_ints.h>
static int timeout = TX_TIMEOUT;
module_param(timeout, int, 0);
+/*
+ * Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
+ * MACE Ethernet uses a 64 element hash table based on the Ethernet CRC.
+ */
+#define METH_MCF_LIMIT 32
+
/*
* This structure is private to each device. It is used to pass
* packets in and out, so there is place for a packet
*/
struct meth_private {
/* in-memory copy of MAC Control register */
- unsigned long mac_ctrl;
+ u64 mac_ctrl;
+
/* in-memory copy of DMA Control register */
unsigned long dma_ctrl;
/* address of PHY, used by mdio_* functions, initialized in mdio_probe */
struct sk_buff *rx_skbs[RX_RING_ENTRIES];
unsigned long rx_write;
+ /* Multicast filter. */
+ u64 mcast_filter;
+
spinlock_t meth_lock;
};
}
}
+static void meth_set_rx_mode(struct net_device *dev)
+{
+ struct meth_private *priv = netdev_priv(dev);
+ unsigned long flags;
+
+ netif_stop_queue(dev);
+ spin_lock_irqsave(&priv->meth_lock, flags);
+ priv->mac_ctrl &= ~METH_PROMISC;
+
+ if (dev->flags & IFF_PROMISC) {
+ priv->mac_ctrl |= METH_PROMISC;
+ priv->mcast_filter = 0xffffffffffffffffUL;
+ } else if ((netdev_mc_count(dev) > METH_MCF_LIMIT) ||
+ (dev->flags & IFF_ALLMULTI)) {
+ priv->mac_ctrl |= METH_ACCEPT_AMCAST;
+ priv->mcast_filter = 0xffffffffffffffffUL;
+ } else {
+ struct netdev_hw_addr *ha;
+ priv->mac_ctrl |= METH_ACCEPT_MCAST;
+
+ netdev_for_each_mc_addr(ha, dev)
+ set_bit((ether_crc(ETH_ALEN, ha->addr) >> 26),
+ (volatile unsigned long *)&priv->mcast_filter);
+ }
+
+ /* Write the changes to the chip registers. */
+ mace->eth.mac_ctrl = priv->mac_ctrl;
+ mace->eth.mcast_filter = priv->mcast_filter;
+
+ /* Done! */
+ spin_unlock_irqrestore(&priv->meth_lock, flags);
+ netif_wake_queue(dev);
+}
+
static const struct net_device_ops meth_netdev_ops = {
.ndo_open = meth_open,
.ndo_stop = meth_release,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_rx_mode = meth_set_rx_mode,
};
/*
}
};
-static int __init meth_init_module(void)
-{
- int err;
-
- err = platform_driver_register(&meth_driver);
- if (err)
- printk(KERN_ERR "Driver registration failed\n");
-
- return err;
-}
-
-static void __exit meth_exit_module(void)
-{
- platform_driver_unregister(&meth_driver);
-}
-
-module_init(meth_init_module);
-module_exit(meth_exit_module);
+module_platform_driver(meth_driver);
MODULE_AUTHOR("Ilya Volynets <ilya@theIlya.com>");
MODULE_DESCRIPTION("SGI O2 Builtin Fast Ethernet driver");
#define sis190_rx_skb netif_rx
#define sis190_rx_quota(count, quota) count
-#define MAC_ADDR_LEN 6
-
#define NUM_TX_DESC 64 /* [8..1024] */
#define NUM_RX_DESC 64 /* [8..8192] */
#define TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc))
}
/* Get MAC address from EEPROM */
- for (i = 0; i < MAC_ADDR_LEN / 2; i++) {
+ for (i = 0; i < ETH_ALEN / 2; i++) {
u16 w = sis190_read_eeprom(ioaddr, EEPROMMACAddr + i);
((__le16 *)dev->dev_addr)[i] = cpu_to_le16(w);
udelay(50);
pci_read_config_byte(isa_bridge, 0x48, ®);
- for (i = 0; i < MAC_ADDR_LEN; i++) {
+ for (i = 0; i < ETH_ALEN; i++) {
outb(0x9 + i, 0x78);
dev->dev_addr[i] = inb(0x79);
}
*/
SIS_W16(RxMacControl, ctl & ~0x0f00);
- for (i = 0; i < MAC_ADDR_LEN; i++)
+ for (i = 0; i < ETH_ALEN; i++)
SIS_W8(RxMacAddr + i, dev->dev_addr[i]);
SIS_W16(RxMacControl, ctl);
{
struct sis190_private *tp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(tp->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(tp->pci_dev),
+ sizeof(info->bus_info));
}
static int sis190_get_regs_len(struct net_device *dev)
{
struct sis900_private *sis_priv = netdev_priv(net_dev);
- strcpy (info->driver, SIS900_MODULE_NAME);
- strcpy (info->version, SIS900_DRV_VERSION);
- strcpy (info->bus_info, pci_name(sis_priv->pci_dev));
+ strlcpy(info->driver, SIS900_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, SIS900_DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(sis_priv->pci_dev),
+ sizeof(info->bus_info));
}
static u32 sis900_get_msglevel(struct net_device *net_dev)
{
struct epic_private *np = netdev_priv(dev);
- strcpy (info->driver, DRV_NAME);
- strcpy (info->version, DRV_VERSION);
- strcpy (info->bus_info, pci_name(np->pci_dev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
},
};
-static int __init smc911x_init(void)
-{
- return platform_driver_register(&smc911x_driver);
-}
-
-static void __exit smc911x_cleanup(void)
-{
- platform_driver_unregister(&smc911x_driver);
-}
-
-module_init(smc911x_init);
-module_exit(smc911x_cleanup);
+module_platform_driver(smc911x_driver);
static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
},
};
-static int __init smc_init(void)
-{
- return platform_driver_register(&smc_driver);
-}
-
-static void __exit smc_cleanup(void)
-{
- platform_driver_unregister(&smc_driver);
-}
-
-module_init(smc_init);
-module_exit(smc_cleanup);
+module_platform_driver(smc_driver);
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/bug.h>
unsigned int *buf, unsigned int wordcount);
};
+#define SMSC911X_NUM_SUPPLIES 2
+
struct smsc911x_data {
void __iomem *ioaddr;
/* register access functions */
const struct smsc911x_ops *ops;
+
+ /* regulators */
+ struct regulator_bulk_data supplies[SMSC911X_NUM_SUPPLIES];
};
/* Easy access to information */
spin_unlock_irqrestore(&pdata->dev_lock, flags);
}
+/*
+ * enable resources, currently just regulators.
+ */
+static int smsc911x_enable_resources(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct smsc911x_data *pdata = netdev_priv(ndev);
+ int ret = 0;
+
+ ret = regulator_bulk_enable(ARRAY_SIZE(pdata->supplies),
+ pdata->supplies);
+ if (ret)
+ netdev_err(ndev, "failed to enable regulators %d\n",
+ ret);
+ return ret;
+}
+
+/*
+ * disable resources, currently just regulators.
+ */
+static int smsc911x_disable_resources(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct smsc911x_data *pdata = netdev_priv(ndev);
+ int ret = 0;
+
+ ret = regulator_bulk_disable(ARRAY_SIZE(pdata->supplies),
+ pdata->supplies);
+ return ret;
+}
+
+/*
+ * Request resources, currently just regulators.
+ *
+ * The SMSC911x has two power pins: vddvario and vdd33a, in designs where
+ * these are not always-on we need to request regulators to be turned on
+ * before we can try to access the device registers.
+ */
+static int smsc911x_request_resources(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct smsc911x_data *pdata = netdev_priv(ndev);
+ int ret = 0;
+
+ /* Request regulators */
+ pdata->supplies[0].supply = "vdd33a";
+ pdata->supplies[1].supply = "vddvario";
+ ret = regulator_bulk_get(&pdev->dev,
+ ARRAY_SIZE(pdata->supplies),
+ pdata->supplies);
+ if (ret)
+ netdev_err(ndev, "couldn't get regulators %d\n",
+ ret);
+ return ret;
+}
+
+/*
+ * Free resources, currently just regulators.
+ *
+ */
+static void smsc911x_free_resources(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct smsc911x_data *pdata = netdev_priv(ndev);
+
+ /* Free regulators */
+ regulator_bulk_free(ARRAY_SIZE(pdata->supplies),
+ pdata->supplies);
+}
+
/* waits for MAC not busy, with timeout. Only called by smsc911x_mac_read
* and smsc911x_mac_write, so assumes mac_lock is held */
static int smsc911x_mac_complete(struct smsc911x_data *pdata)
spin_unlock(&pdata->mac_lock);
}
+static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata)
+{
+ int rc = 0;
+
+ if (!pdata->phy_dev)
+ return rc;
+
+ rc = phy_read(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS);
+
+ if (rc < 0) {
+ SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
+ return rc;
+ }
+
+ /*
+ * If energy is detected the PHY is already awake so is not necessary
+ * to disable the energy detect power-down mode.
+ */
+ if ((rc & MII_LAN83C185_EDPWRDOWN) &&
+ !(rc & MII_LAN83C185_ENERGYON)) {
+ /* Disable energy detect mode for this SMSC Transceivers */
+ rc = phy_write(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS,
+ rc & (~MII_LAN83C185_EDPWRDOWN));
+
+ if (rc < 0) {
+ SMSC_WARN(pdata, drv, "Failed writing PHY control reg");
+ return rc;
+ }
+
+ mdelay(1);
+ }
+
+ return 0;
+}
+
+static int smsc911x_phy_enable_energy_detect(struct smsc911x_data *pdata)
+{
+ int rc = 0;
+
+ if (!pdata->phy_dev)
+ return rc;
+
+ rc = phy_read(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS);
+
+ if (rc < 0) {
+ SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
+ return rc;
+ }
+
+ /* Only enable if energy detect mode is already disabled */
+ if (!(rc & MII_LAN83C185_EDPWRDOWN)) {
+ mdelay(100);
+ /* Enable energy detect mode for this SMSC Transceivers */
+ rc = phy_write(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS,
+ rc | MII_LAN83C185_EDPWRDOWN);
+
+ if (rc < 0) {
+ SMSC_WARN(pdata, drv, "Failed writing PHY control reg");
+ return rc;
+ }
+
+ mdelay(1);
+ }
+ return 0;
+}
+
static int smsc911x_soft_reset(struct smsc911x_data *pdata)
{
unsigned int timeout;
unsigned int temp;
+ int ret;
+
+ /*
+ * LAN9210/LAN9211/LAN9220/LAN9221 chips have an internal PHY that
+ * are initialized in a Energy Detect Power-Down mode that prevents
+ * the MAC chip to be software reseted. So we have to wakeup the PHY
+ * before.
+ */
+ if (pdata->generation == 4) {
+ ret = smsc911x_phy_disable_energy_detect(pdata);
+
+ if (ret) {
+ SMSC_WARN(pdata, drv, "Failed to wakeup the PHY chip");
+ return ret;
+ }
+ }
/* Reset the LAN911x */
smsc911x_reg_write(pdata, HW_CFG, HW_CFG_SRST_);
SMSC_WARN(pdata, drv, "Failed to complete reset");
return -EIO;
}
+
+ if (pdata->generation == 4) {
+ ret = smsc911x_phy_enable_energy_detect(pdata);
+
+ if (ret) {
+ SMSC_WARN(pdata, drv, "Failed to wakeup the PHY chip");
+ return ret;
+ }
+ }
+
return 0;
}
{
struct smsc911x_data *pdata = netdev_priv(dev);
unsigned int byte_test;
+ unsigned int to = 100;
SMSC_TRACE(pdata, probe, "Driver Parameters:");
SMSC_TRACE(pdata, probe, "LAN base: 0x%08lX",
return -ENODEV;
}
+ /*
+ * poll the READY bit in PMT_CTRL. Any other access to the device is
+ * forbidden while this bit isn't set. Try for 100ms
+ */
+ while (!(smsc911x_reg_read(pdata, PMT_CTRL) & PMT_CTRL_READY_) && --to)
+ udelay(1000);
+ if (to == 0) {
+ pr_err("Device not READY in 100ms aborting\n");
+ return -ENODEV;
+ }
+
/* Check byte ordering */
byte_test = smsc911x_reg_read(pdata, BYTE_TEST);
SMSC_TRACE(pdata, probe, "BYTE_TEST: 0x%08X", byte_test);
iounmap(pdata->ioaddr);
+ (void)smsc911x_disable_resources(pdev);
+ smsc911x_free_resources(pdev);
+
free_netdev(dev);
return 0;
pdata->dev = dev;
pdata->msg_enable = ((1 << debug) - 1);
+ platform_set_drvdata(pdev, dev);
+
+ retval = smsc911x_request_resources(pdev);
+ if (retval)
+ goto out_return_resources;
+
+ retval = smsc911x_enable_resources(pdev);
+ if (retval)
+ goto out_disable_resources;
+
if (pdata->ioaddr == NULL) {
SMSC_WARN(pdata, probe, "Error smsc911x base address invalid");
retval = -ENOMEM;
- goto out_free_netdev_2;
+ goto out_disable_resources;
}
retval = smsc911x_probe_config_dt(&pdata->config, np);
if (retval) {
SMSC_WARN(pdata, probe, "Error smsc911x config not found");
- goto out_unmap_io_3;
+ goto out_disable_resources;
}
/* assume standard, non-shifted, access to HW registers */
retval = smsc911x_init(dev);
if (retval < 0)
- goto out_unmap_io_3;
+ goto out_disable_resources;
/* configure irq polarity and type before connecting isr */
if (pdata->config.irq_polarity == SMSC911X_IRQ_POLARITY_ACTIVE_HIGH)
if (retval) {
SMSC_WARN(pdata, probe,
"Unable to claim requested irq: %d", dev->irq);
- goto out_unmap_io_3;
+ goto out_free_irq;
}
- platform_set_drvdata(pdev, dev);
-
retval = register_netdev(dev);
if (retval) {
SMSC_WARN(pdata, probe, "Error %i registering device", retval);
- goto out_unset_drvdata_4;
+ goto out_free_irq;
} else {
SMSC_TRACE(pdata, probe,
"Network interface: \"%s\"", dev->name);
out_unregister_netdev_5:
unregister_netdev(dev);
-out_unset_drvdata_4:
- platform_set_drvdata(pdev, NULL);
+out_free_irq:
free_irq(dev->irq, dev);
-out_unmap_io_3:
+out_disable_resources:
+ (void)smsc911x_disable_resources(pdev);
+out_return_resources:
+ smsc911x_free_resources(pdev);
+ platform_set_drvdata(pdev, NULL);
iounmap(pdata->ioaddr);
-out_free_netdev_2:
free_netdev(dev);
out_release_io_1:
release_mem_region(res->start, resource_size(res));
#include <asm/smsc911x.h>
#endif
+#ifdef CONFIG_SMSC_PHY
+#include <linux/smscphy.h>
+#endif
+
#endif /* __SMSC911X_H__ */
{
struct smsc9420_pdata *pd = netdev_priv(netdev);
- strcpy(drvinfo->driver, DRV_NAME);
- strcpy(drvinfo->bus_info, pci_name(pd->pdev));
- strcpy(drvinfo->version, DRV_VERSION);
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->bus_info, pci_name(pd->pdev),
+ sizeof(drvinfo->bus_info));
+ strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
}
static u32 smsc9420_ethtool_get_msglevel(struct net_device *netdev)
if STMMAC_ETH
+config STMMAC_PLATFORM
+ tristate "STMMAC platform bus support"
+ depends on STMMAC_ETH
+ default y
+ ---help---
+ This selects the platform specific bus support for
+ the stmmac device driver. This is the driver used
+ on many embedded STM platforms based on ARM and SuperH
+ processors.
+ If you have a controller with this interface, say Y or M here.
+
+ If unsure, say N.
+
+config STMMAC_PCI
+ tristate "STMMAC support on PCI bus (EXPERIMENTAL)"
+ depends on STMMAC_ETH && PCI && EXPERIMENTAL
+ ---help---
+ This is to select the Synopsys DWMAC available on PCI devices,
+ if you have a controller with this interface, say Y or M here.
+
+ This PCI support is tested on XLINX XC2V3000 FF1152AMT0221
+ D1215994A VIRTEX FPGA board.
+
+ If unsure, say N.
+
config STMMAC_DEBUG_FS
bool "Enable monitoring via sysFS "
default n
depends on STMMAC_ETH && DEBUG_FS
- -- help
+ ---help---
The stmmac entry in /sys reports DMA TX/RX rings
or (if supported) the HW cap register.
stmmac-$(CONFIG_STMMAC_TIMER) += stmmac_timer.o
stmmac-$(CONFIG_STMMAC_RING) += ring_mode.o
stmmac-$(CONFIG_STMMAC_CHAINED) += chain_mode.o
+stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o
+stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o
stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o \
dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
*******************************************************************************/
+#include <linux/etherdevice.h>
#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/module.h>
+#include <linux/init.h>
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
#define STMMAC_VLAN_TAG_USED
#include <linux/if_vlan.h>
unsigned int high, unsigned int low);
extern void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
unsigned int high, unsigned int low);
+
+extern void stmmac_set_mac(void __iomem *ioaddr, bool enable);
+
extern void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
extern const struct stmmac_ring_mode_ops ring_mode_ops;
/* DMA SW reset */
value |= DMA_BUS_MODE_SFT_RESET;
writel(value, ioaddr + DMA_BUS_MODE);
- limit = 15000;
+ limit = 10;
while (limit--) {
if (!(readl(ioaddr + DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
break;
+ mdelay(10);
}
if (limit < 0)
return -EBUSY;
/* DMA SW reset */
value |= DMA_BUS_MODE_SFT_RESET;
writel(value, ioaddr + DMA_BUS_MODE);
- limit = 15000;
+ limit = 10;
while (limit--) {
if (!(readl(ioaddr + DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
break;
+ mdelay(10);
}
if (limit < 0)
return -EBUSY;
writel(data, ioaddr + low);
}
+/* Enable disable MAC RX/TX */
+void stmmac_set_mac(void __iomem *ioaddr, bool enable)
+{
+ u32 value = readl(ioaddr + MAC_CTRL_REG);
+
+ if (enable)
+ value |= MAC_RNABLE_RX | MAC_ENABLE_TX;
+ else
+ value &= ~(MAC_ENABLE_TX | MAC_RNABLE_RX);
+
+ writel(value, ioaddr + MAC_CTRL_REG);
+}
+
void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
unsigned int high, unsigned int low)
{
Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
*******************************************************************************/
-#define DRV_MODULE_VERSION "Oct_2011"
+#define STMMAC_RESOURCE_NAME "stmmaceth"
+#define DRV_MODULE_VERSION "Dec_2011"
#include <linux/stmmac.h>
#include <linux/phy.h>
#include "common.h"
spinlock_t lock;
spinlock_t tx_lock;
int wolopts;
- int wolenabled;
int wol_irq;
#ifdef CONFIG_STMMAC_TIMER
struct stmmac_timer *tm;
struct plat_stmmacenet_data *plat;
struct stmmac_counters mmc;
struct dma_features dma_cap;
+ int hw_cap_support;
};
+extern int phyaddr;
+
extern int stmmac_mdio_unregister(struct net_device *ndev);
extern int stmmac_mdio_register(struct net_device *ndev);
extern void stmmac_set_ethtool_ops(struct net_device *netdev);
extern const struct stmmac_desc_ops enh_desc_ops;
extern const struct stmmac_desc_ops ndesc_ops;
+
+int stmmac_freeze(struct net_device *ndev);
+int stmmac_restore(struct net_device *ndev);
+int stmmac_resume(struct net_device *ndev);
+int stmmac_suspend(struct net_device *ndev);
+int stmmac_dvr_remove(struct net_device *ndev);
+struct stmmac_priv *stmmac_dvr_probe(struct device *device,
+ struct plat_stmmacenet_data *plat_dat);
struct stmmac_priv *priv = netdev_priv(dev);
if (priv->plat->has_gmac)
- strcpy(info->driver, GMAC_ETHTOOL_NAME);
+ strlcpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver));
else
- strcpy(info->driver, MAC100_ETHTOOL_NAME);
+ strlcpy(info->driver, MAC100_ETHTOOL_NAME,
+ sizeof(info->driver));
strcpy(info->version, DRV_MODULE_VERSION);
info->fw_version[0] = '\0';
struct stmmac_priv *priv = netdev_priv(dev);
u32 support = WAKE_MAGIC | WAKE_UCAST;
+ /* By default almost all GMAC devices support the WoL via
+ * magic frame but we can disable it if the HW capability
+ * register shows no support for pmt_magic_frame. */
+ if ((priv->hw_cap_support) && (!priv->dma_cap.pmt_magic_frame))
+ wol->wolopts &= ~WAKE_MAGIC;
+
if (!device_can_wakeup(priv->device))
return -EINVAL;
https://bugzilla.stlinux.com/
*******************************************************************************/
-#include <linux/module.h>
-#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
-#include <linux/etherdevice.h>
-#include <linux/platform_device.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/skbuff.h>
#endif
#include "stmmac.h"
-#define STMMAC_RESOURCE_NAME "stmmaceth"
-
#undef STMMAC_DEBUG
/*#define STMMAC_DEBUG*/
#ifdef STMMAC_DEBUG
module_param(debug, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(debug, "Message Level (0: no output, 16: all)");
-static int phyaddr = -1;
+int phyaddr = -1;
module_param(phyaddr, int, S_IRUGO);
MODULE_PARM_DESC(phyaddr, "Physical device address");
static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
+#ifdef CONFIG_STMMAC_DEBUG_FS
+static int stmmac_init_fs(struct net_device *dev);
+static void stmmac_exit_fs(void);
+#endif
+
/**
* stmmac_verify_args - verify the driver parameters.
* Description: it verifies if some wrong parameter is passed to the driver.
}
/* Stop Advertising 1000BASE Capability if interface is not GMII */
- if ((interface) && ((interface == PHY_INTERFACE_MODE_MII) ||
- (interface == PHY_INTERFACE_MODE_RMII))) {
- phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
- SUPPORTED_Asym_Pause);
- phydev->advertising = phydev->supported;
- }
+ if ((interface == PHY_INTERFACE_MODE_MII) ||
+ (interface == PHY_INTERFACE_MODE_RMII))
+ phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
+ SUPPORTED_1000baseT_Full);
/*
* Broken HW is sometimes missing the pull-up resistor on the
return 0;
}
-static inline void stmmac_enable_mac(void __iomem *ioaddr)
-{
- u32 value = readl(ioaddr + MAC_CTRL_REG);
-
- value |= MAC_RNABLE_RX | MAC_ENABLE_TX;
- writel(value, ioaddr + MAC_CTRL_REG);
-}
-
-static inline void stmmac_disable_mac(void __iomem *ioaddr)
-{
- u32 value = readl(ioaddr + MAC_CTRL_REG);
-
- value &= ~(MAC_ENABLE_TX | MAC_RNABLE_RX);
- writel(value, ioaddr + MAC_CTRL_REG);
-}
-
/**
* display_ring
* @p: pointer to the ring.
unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
- /* Do not manage MMC IRQ (FIXME) */
+ /* Mask MMC irq, counters are managed in SW and registers
+ * are cleared on each READ eventually. */
dwmac_mmc_intr_all_mask(priv->ioaddr);
- dwmac_mmc_ctrl(priv->ioaddr, mode);
- memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
+
+ if (priv->dma_cap.rmon) {
+ dwmac_mmc_ctrl(priv->ioaddr, mode);
+ memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
+ } else
+ pr_info(" No MAC Management Counters available");
}
static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv)
return 0;
}
-/* New GMAC chips support a new register to indicate the
- * presence of the optional feature/functions.
+/**
+ * stmmac_selec_desc_mode
+ * @dev : device pointer
+ * Description: select the Enhanced/Alternate or Normal descriptors */
+static void stmmac_selec_desc_mode(struct stmmac_priv *priv)
+{
+ if (priv->plat->enh_desc) {
+ pr_info(" Enhanced/Alternate descriptors\n");
+ priv->hw->desc = &enh_desc_ops;
+ } else {
+ pr_info(" Normal descriptors\n");
+ priv->hw->desc = &ndesc_ops;
+ }
+}
+
+/**
+ * stmmac_get_hw_features
+ * @priv : private device pointer
+ * Description:
+ * new GMAC chip generations have a new register to indicate the
+ * presence of the optional feature/functions.
+ * This can be also used to override the value passed through the
+ * platform and necessary for old MAC10/100 and GMAC chips.
*/
static int stmmac_get_hw_features(struct stmmac_priv *priv)
{
(hw_cap & DMA_HW_FEAT_RWKSEL) >> 9;
priv->dma_cap.pmt_magic_frame =
(hw_cap & DMA_HW_FEAT_MGKSEL) >> 10;
- /*MMC*/
+ /* MMC */
priv->dma_cap.rmon = (hw_cap & DMA_HW_FEAT_MMCSEL) >> 11;
/* IEEE 1588-2002*/
priv->dma_cap.time_stamp =
priv->dma_cap.enh_desc =
(hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
- } else
- pr_debug("\tNo HW DMA feature register supported");
+ }
return hw_cap;
}
+/**
+ * stmmac_mac_device_setup
+ * @dev : device pointer
+ * Description: this is to attach the GMAC or MAC 10/100
+ * main core structures that will be completed during the
+ * open step.
+ */
+static int stmmac_mac_device_setup(struct net_device *dev)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ struct mac_device_info *device;
+
+ if (priv->plat->has_gmac)
+ device = dwmac1000_setup(priv->ioaddr);
+ else
+ device = dwmac100_setup(priv->ioaddr);
+
+ if (!device)
+ return -ENOMEM;
+
+ priv->hw = device;
+ priv->hw->ring = &ring_mode_ops;
+
+ if (device_can_wakeup(priv->device)) {
+ priv->wolopts = WAKE_MAGIC; /* Magic Frame as default */
+ enable_irq_wake(priv->wol_irq);
+ }
+
+ return 0;
+}
+
+static void stmmac_check_ether_addr(struct stmmac_priv *priv)
+{
+ /* verify if the MAC address is valid, in case of failures it
+ * generates a random MAC address */
+ if (!is_valid_ether_addr(priv->dev->dev_addr)) {
+ priv->hw->mac->get_umac_addr((void __iomem *)
+ priv->dev->base_addr,
+ priv->dev->dev_addr, 0);
+ if (!is_valid_ether_addr(priv->dev->dev_addr))
+ random_ether_addr(priv->dev->dev_addr);
+ }
+ pr_warning("%s: device MAC address %pM\n", priv->dev->name,
+ priv->dev->dev_addr);
+}
+
/**
* stmmac_open - open entry point of the driver
* @dev : pointer to the device structure.
struct stmmac_priv *priv = netdev_priv(dev);
int ret;
- /* Check that the MAC address is valid. If its not, refuse
- * to bring the device up. The user must specify an
- * address using the following linux command:
- * ifconfig eth0 hw ether xx:xx:xx:xx:xx:xx */
- if (!is_valid_ether_addr(dev->dev_addr)) {
- random_ether_addr(dev->dev_addr);
- pr_warning("%s: generated random MAC address %pM\n", dev->name,
- dev->dev_addr);
- }
+ /* MAC HW device setup */
+ ret = stmmac_mac_device_setup(dev);
+ if (ret < 0)
+ return ret;
+
+ stmmac_check_ether_addr(priv);
stmmac_verify_args();
+ /* Override with kernel parameters if supplied XXX CRS XXX
+ * this needs to have multiple instances */
+ if ((phyaddr >= 0) && (phyaddr <= 31))
+ priv->plat->phy_addr = phyaddr;
+
+ /* MDIO bus Registration */
+ ret = stmmac_mdio_register(dev);
+ if (ret < 0) {
+ pr_debug("%s: MDIO bus (id: %d) registration failed",
+ __func__, priv->plat->bus_id);
+ return ret;
+ }
+
#ifdef CONFIG_STMMAC_TIMER
priv->tm = kzalloc(sizeof(struct stmmac_timer *), GFP_KERNEL);
if (unlikely(priv->tm == NULL)) {
goto open_error;
}
+ stmmac_get_synopsys_id(priv);
+
+ priv->hw_cap_support = stmmac_get_hw_features(priv);
+
+ if (priv->hw_cap_support) {
+ pr_info(" Support DMA HW capability register");
+
+ /* We can override some gmac/dma configuration fields: e.g.
+ * enh_desc, tx_coe (e.g. that are passed through the
+ * platform) with the values from the HW capability
+ * register (if supported).
+ */
+ priv->plat->enh_desc = priv->dma_cap.enh_desc;
+ priv->plat->tx_coe = priv->dma_cap.tx_coe;
+ priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up;
+
+ /* By default disable wol on magic frame if not supported */
+ if (!priv->dma_cap.pmt_magic_frame)
+ priv->wolopts &= ~WAKE_MAGIC;
+
+ } else
+ pr_info(" No HW DMA feature register supported");
+
+ /* Select the enhnaced/normal descriptor structures */
+ stmmac_selec_desc_mode(priv);
+
+ /* PMT module is not integrated in all the MAC devices. */
+ if (priv->plat->pmt) {
+ pr_info(" Remote wake-up capable\n");
+ device_set_wakeup_capable(priv->device, 1);
+ }
+
+ priv->rx_coe = priv->hw->mac->rx_coe(priv->ioaddr);
+ if (priv->rx_coe)
+ pr_info(" Checksum Offload Engine supported\n");
+ if (priv->plat->tx_coe)
+ pr_info(" Checksum insertion supported\n");
+
/* Create and initialize the TX/RX descriptors chains. */
priv->dma_tx_size = STMMAC_ALIGN(dma_txsize);
priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
/* Initialize the MAC Core */
priv->hw->mac->core_init(priv->ioaddr);
- stmmac_get_synopsys_id(priv);
-
- stmmac_get_hw_features(priv);
-
- priv->rx_coe = priv->hw->mac->rx_coe(priv->ioaddr);
- if (priv->rx_coe)
- pr_info("stmmac: Rx Checksum Offload Engine supported\n");
- if (priv->plat->tx_coe)
- pr_info("\tTX Checksum insertion supported\n");
netdev_update_features(dev);
/* Request the IRQ lines */
}
/* Enable the MAC Rx/Tx */
- stmmac_enable_mac(priv->ioaddr);
+ stmmac_set_mac(priv->ioaddr, true);
/* Set the HW DMA mode and the COE */
stmmac_dma_operation_mode(priv);
memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats));
priv->xstats.threshold = tc;
- if (priv->dma_cap.rmon)
- stmmac_mmc_setup(priv);
+ stmmac_mmc_setup(priv);
+#ifdef CONFIG_STMMAC_DEBUG_FS
+ ret = stmmac_init_fs(dev);
+ if (ret < 0)
+ pr_warning("\tFailed debugFS registration");
+#endif
/* Start the ball rolling... */
DBG(probe, DEBUG, "%s: DMA RX/TX processes started...\n", dev->name);
priv->hw->dma->start_tx(priv->ioaddr);
free_dma_desc_resources(priv);
/* Disable the MAC Rx/Tx */
- stmmac_disable_mac(priv->ioaddr);
+ stmmac_set_mac(priv->ioaddr, false);
netif_carrier_off(dev);
+#ifdef CONFIG_STMMAC_DEBUG_FS
+ stmmac_exit_fs();
+#endif
+ stmmac_mdio_unregister(dev);
+
return 0;
}
return 0;
}
-static u32 stmmac_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t stmmac_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct stmmac_priv *priv = netdev_priv(dev);
if (!priv->phydev)
return -EINVAL;
- spin_lock(&priv->lock);
ret = phy_mii_ioctl(priv->phydev, rq, cmd);
- spin_unlock(&priv->lock);
return ret;
}
struct net_device *dev = seq->private;
struct stmmac_priv *priv = netdev_priv(dev);
- if (!stmmac_get_hw_features(priv)) {
+ if (!priv->hw_cap_support) {
seq_printf(seq, "DMA HW features not supported\n");
return 0;
}
};
/**
- * stmmac_probe - Initialization of the adapter .
- * @dev : device pointer
- * Description: The function initializes the network device structure for
- * the STMMAC driver. It also calls the low level routines
- * in order to init the HW (i.e. the DMA engine)
+ * stmmac_dvr_probe
+ * @device: device pointer
+ * Description: this is the main probe function used to
+ * call the alloc_etherdev, allocate the priv structure.
*/
-static int stmmac_probe(struct net_device *dev)
+struct stmmac_priv *stmmac_dvr_probe(struct device *device,
+ struct plat_stmmacenet_data *plat_dat)
{
int ret = 0;
- struct stmmac_priv *priv = netdev_priv(dev);
+ struct net_device *ndev = NULL;
+ struct stmmac_priv *priv;
+
+ ndev = alloc_etherdev(sizeof(struct stmmac_priv));
+ if (!ndev) {
+ pr_err("%s: ERROR: allocating the device\n", __func__);
+ return NULL;
+ }
+
+ SET_NETDEV_DEV(ndev, device);
+
+ priv = netdev_priv(ndev);
+ priv->device = device;
+ priv->dev = ndev;
- ether_setup(dev);
+ ether_setup(ndev);
- dev->netdev_ops = &stmmac_netdev_ops;
- stmmac_set_ethtool_ops(dev);
+ ndev->netdev_ops = &stmmac_netdev_ops;
+ stmmac_set_ethtool_ops(ndev);
- dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- dev->features |= dev->hw_features | NETIF_F_HIGHDMA;
- dev->watchdog_timeo = msecs_to_jiffies(watchdog);
+ ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
+ ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
#ifdef STMMAC_VLAN_TAG_USED
/* Both mac100 and gmac support receive VLAN tag detection */
- dev->features |= NETIF_F_HW_VLAN_RX;
+ ndev->features |= NETIF_F_HW_VLAN_RX;
#endif
priv->msg_enable = netif_msg_init(debug, default_msg_level);
priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */
priv->pause = pause;
- netif_napi_add(dev, &priv->napi, stmmac_poll, 64);
-
- /* Get the MAC address */
- priv->hw->mac->get_umac_addr((void __iomem *) dev->base_addr,
- dev->dev_addr, 0);
-
- if (!is_valid_ether_addr(dev->dev_addr))
- pr_warning("\tno valid MAC address;"
- "please, use ifconfig or nwhwconfig!\n");
+ priv->plat = plat_dat;
+ netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
spin_lock_init(&priv->lock);
spin_lock_init(&priv->tx_lock);
- ret = register_netdev(dev);
+ ret = register_netdev(ndev);
if (ret) {
pr_err("%s: ERROR %i registering the device\n",
__func__, ret);
- return -ENODEV;
+ goto error;
}
DBG(probe, DEBUG, "%s: Scatter/Gather: %s - HW checksums: %s\n",
- dev->name, (dev->features & NETIF_F_SG) ? "on" : "off",
- (dev->features & NETIF_F_IP_CSUM) ? "on" : "off");
-
- return ret;
-}
-
-/**
- * stmmac_mac_device_setup
- * @dev : device pointer
- * Description: select and initialise the mac device (mac100 or Gmac).
- */
-static int stmmac_mac_device_setup(struct net_device *dev)
-{
- struct stmmac_priv *priv = netdev_priv(dev);
-
- struct mac_device_info *device;
-
- if (priv->plat->has_gmac) {
- dev->priv_flags |= IFF_UNICAST_FLT;
- device = dwmac1000_setup(priv->ioaddr);
- } else {
- device = dwmac100_setup(priv->ioaddr);
- }
-
- if (!device)
- return -ENOMEM;
-
- if (priv->plat->enh_desc) {
- device->desc = &enh_desc_ops;
- pr_info("\tEnhanced descriptor structure\n");
- } else
- device->desc = &ndesc_ops;
-
- priv->hw = device;
- priv->hw->ring = &ring_mode_ops;
-
- if (device_can_wakeup(priv->device)) {
- priv->wolopts = WAKE_MAGIC; /* Magic Frame as default */
- enable_irq_wake(priv->wol_irq);
- }
-
- return 0;
-}
-
-/**
- * stmmac_dvr_probe
- * @pdev: platform device pointer
- * Description: the driver is initialized through platform_device.
- */
-static int stmmac_dvr_probe(struct platform_device *pdev)
-{
- int ret = 0;
- struct resource *res;
- void __iomem *addr = NULL;
- struct net_device *ndev = NULL;
- struct stmmac_priv *priv = NULL;
- struct plat_stmmacenet_data *plat_dat;
-
- pr_info("STMMAC driver:\n\tplatform registration... ");
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
- pr_info("\tdone!\n");
-
- if (!request_mem_region(res->start, resource_size(res),
- pdev->name)) {
- pr_err("%s: ERROR: memory allocation failed"
- "cannot get the I/O addr 0x%x\n",
- __func__, (unsigned int)res->start);
- return -EBUSY;
- }
-
- addr = ioremap(res->start, resource_size(res));
- if (!addr) {
- pr_err("%s: ERROR: memory mapping failed\n", __func__);
- ret = -ENOMEM;
- goto out_release_region;
- }
-
- ndev = alloc_etherdev(sizeof(struct stmmac_priv));
- if (!ndev) {
- pr_err("%s: ERROR: allocating the device\n", __func__);
- ret = -ENOMEM;
- goto out_unmap;
- }
-
- SET_NETDEV_DEV(ndev, &pdev->dev);
-
- /* Get the MAC information */
- ndev->irq = platform_get_irq_byname(pdev, "macirq");
- if (ndev->irq == -ENXIO) {
- pr_err("%s: ERROR: MAC IRQ configuration "
- "information not found\n", __func__);
- ret = -ENXIO;
- goto out_free_ndev;
- }
-
- priv = netdev_priv(ndev);
- priv->device = &(pdev->dev);
- priv->dev = ndev;
- plat_dat = pdev->dev.platform_data;
-
- priv->plat = plat_dat;
-
- priv->ioaddr = addr;
-
- /* PMT module is not integrated in all the MAC devices. */
- if (plat_dat->pmt) {
- pr_info("\tPMT module supported\n");
- device_set_wakeup_capable(&pdev->dev, 1);
- }
- /*
- * On some platforms e.g. SPEAr the wake up irq differs from the mac irq
- * The external wake up irq can be passed through the platform code
- * named as "eth_wake_irq"
- *
- * In case the wake up interrupt is not passed from the platform
- * so the driver will continue to use the mac irq (ndev->irq)
- */
- priv->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
- if (priv->wol_irq == -ENXIO)
- priv->wol_irq = ndev->irq;
-
-
- platform_set_drvdata(pdev, ndev);
-
- /* Set the I/O base addr */
- ndev->base_addr = (unsigned long)addr;
+ ndev->name, (ndev->features & NETIF_F_SG) ? "on" : "off",
+ (ndev->features & NETIF_F_IP_CSUM) ? "on" : "off");
- /* Custom initialisation */
- if (priv->plat->init) {
- ret = priv->plat->init(pdev);
- if (unlikely(ret))
- goto out_free_ndev;
- }
-
- /* MAC HW revice detection */
- ret = stmmac_mac_device_setup(ndev);
- if (ret < 0)
- goto out_plat_exit;
-
- /* Network Device Registration */
- ret = stmmac_probe(ndev);
- if (ret < 0)
- goto out_plat_exit;
-
- /* Override with kernel parameters if supplied XXX CRS XXX
- * this needs to have multiple instances */
- if ((phyaddr >= 0) && (phyaddr <= 31))
- priv->plat->phy_addr = phyaddr;
-
- pr_info("\t%s - (dev. name: %s - id: %d, IRQ #%d\n"
- "\tIO base addr: 0x%p)\n", ndev->name, pdev->name,
- pdev->id, ndev->irq, addr);
-
- /* MDIO bus Registration */
- pr_debug("\tMDIO bus (id: %d)...", priv->plat->bus_id);
- ret = stmmac_mdio_register(ndev);
- if (ret < 0)
- goto out_unregister;
- pr_debug("registered!\n");
-
-#ifdef CONFIG_STMMAC_DEBUG_FS
- ret = stmmac_init_fs(ndev);
- if (ret < 0)
- pr_warning("\tFailed debugFS registration");
-#endif
+ return priv;
- return 0;
+error:
+ netif_napi_del(&priv->napi);
-out_unregister:
unregister_netdev(ndev);
-out_plat_exit:
- if (priv->plat->exit)
- priv->plat->exit(pdev);
-out_free_ndev:
free_netdev(ndev);
- platform_set_drvdata(pdev, NULL);
-out_unmap:
- iounmap(addr);
-out_release_region:
- release_mem_region(res->start, resource_size(res));
- return ret;
+ return NULL;
}
/**
* stmmac_dvr_remove
- * @pdev: platform device pointer
+ * @ndev: net device pointer
* Description: this function resets the TX/RX processes, disables the MAC RX/TX
- * changes the link status, releases the DMA descriptor rings,
- * unregisters the MDIO bus and unmaps the allocated memory.
+ * changes the link status, releases the DMA descriptor rings.
*/
-static int stmmac_dvr_remove(struct platform_device *pdev)
+int stmmac_dvr_remove(struct net_device *ndev)
{
- struct net_device *ndev = platform_get_drvdata(pdev);
struct stmmac_priv *priv = netdev_priv(ndev);
- struct resource *res;
pr_info("%s:\n\tremoving driver", __func__);
priv->hw->dma->stop_rx(priv->ioaddr);
priv->hw->dma->stop_tx(priv->ioaddr);
- stmmac_disable_mac(priv->ioaddr);
-
+ stmmac_set_mac(priv->ioaddr, false);
netif_carrier_off(ndev);
-
- stmmac_mdio_unregister(ndev);
-
- if (priv->plat->exit)
- priv->plat->exit(pdev);
-
- platform_set_drvdata(pdev, NULL);
unregister_netdev(ndev);
-
- iounmap((void *)priv->ioaddr);
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- release_mem_region(res->start, resource_size(res));
-
-#ifdef CONFIG_STMMAC_DEBUG_FS
- stmmac_exit_fs();
-#endif
-
free_netdev(ndev);
return 0;
}
#ifdef CONFIG_PM
-static int stmmac_suspend(struct device *dev)
+int stmmac_suspend(struct net_device *ndev)
{
- struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
int dis_ic = 0;
if (!ndev || !netif_running(ndev))
return 0;
+ if (priv->phydev)
+ phy_stop(priv->phydev);
+
spin_lock(&priv->lock);
netif_device_detach(ndev);
netif_stop_queue(ndev);
- if (priv->phydev)
- phy_stop(priv->phydev);
#ifdef CONFIG_STMMAC_TIMER
priv->tm->timer_stop();
if (device_may_wakeup(priv->device))
priv->hw->mac->pmt(priv->ioaddr, priv->wolopts);
else
- stmmac_disable_mac(priv->ioaddr);
+ stmmac_set_mac(priv->ioaddr, false);
spin_unlock(&priv->lock);
return 0;
}
-static int stmmac_resume(struct device *dev)
+int stmmac_resume(struct net_device *ndev)
{
- struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
if (!netif_running(ndev))
netif_device_attach(ndev);
/* Enable the MAC and DMA */
- stmmac_enable_mac(priv->ioaddr);
+ stmmac_set_mac(priv->ioaddr, true);
priv->hw->dma->start_tx(priv->ioaddr);
priv->hw->dma->start_rx(priv->ioaddr);
#endif
napi_enable(&priv->napi);
- if (priv->phydev)
- phy_start(priv->phydev);
-
netif_start_queue(ndev);
spin_unlock(&priv->lock);
+
+ if (priv->phydev)
+ phy_start(priv->phydev);
+
return 0;
}
-static int stmmac_freeze(struct device *dev)
+int stmmac_freeze(struct net_device *ndev)
{
- struct net_device *ndev = dev_get_drvdata(dev);
-
if (!ndev || !netif_running(ndev))
return 0;
return stmmac_release(ndev);
}
-static int stmmac_restore(struct device *dev)
+int stmmac_restore(struct net_device *ndev)
{
- struct net_device *ndev = dev_get_drvdata(dev);
-
if (!ndev || !netif_running(ndev))
return 0;
return stmmac_open(ndev);
}
-
-static const struct dev_pm_ops stmmac_pm_ops = {
- .suspend = stmmac_suspend,
- .resume = stmmac_resume,
- .freeze = stmmac_freeze,
- .thaw = stmmac_restore,
- .restore = stmmac_restore,
-};
-#else
-static const struct dev_pm_ops stmmac_pm_ops;
#endif /* CONFIG_PM */
-static struct platform_driver stmmac_driver = {
- .probe = stmmac_dvr_probe,
- .remove = stmmac_dvr_remove,
- .driver = {
- .name = STMMAC_RESOURCE_NAME,
- .owner = THIS_MODULE,
- .pm = &stmmac_pm_ops,
- },
-};
-
-/**
- * stmmac_init_module - Entry point for the driver
- * Description: This function is the entry point for the driver.
- */
-static int __init stmmac_init_module(void)
-{
- int ret;
-
- ret = platform_driver_register(&stmmac_driver);
- return ret;
-}
-
-/**
- * stmmac_cleanup_module - Cleanup routine for the driver
- * Description: This function is the cleanup routine for the driver.
- */
-static void __exit stmmac_cleanup_module(void)
-{
- platform_driver_unregister(&stmmac_driver);
-}
-
#ifndef MODULE
static int __init stmmac_cmdline_opt(char *str)
{
__setup("stmmaceth=", stmmac_cmdline_opt);
#endif
-module_init(stmmac_init_module);
-module_exit(stmmac_cleanup_module);
-
-MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet driver");
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet device driver");
MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
MODULE_LICENSE("GPL");
*/
static int stmmac_mdio_reset(struct mii_bus *bus)
{
+#if defined(CONFIG_STMMAC_PLATFORM)
struct net_device *ndev = bus->priv;
struct stmmac_priv *priv = netdev_priv(ndev);
unsigned int mii_address = priv->hw->mii.addr;
* on MDC, so perform a dummy mdio read.
*/
writel(0, priv->ioaddr + mii_address);
-
+#endif
return 0;
}
--- /dev/null
+/*******************************************************************************
+ This contains the functions to handle the pci driver.
+
+ Copyright (C) 2011-2012 Vayavya Labs Pvt Ltd
+
+ This program is free software; you can redistribute it and/or modify it
+ under the terms and conditions of the GNU General Public License,
+ version 2, as published by the Free Software Foundation.
+
+ This program is distributed in the hope it will be useful, but WITHOUT
+ ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ You should have received a copy of the GNU General Public License along with
+ this program; if not, write to the Free Software Foundation, Inc.,
+ 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+ The full GNU General Public License is included in this distribution in
+ the file called "COPYING".
+
+ Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
+ Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+*******************************************************************************/
+
+#include <linux/pci.h>
+#include "stmmac.h"
+
+struct plat_stmmacenet_data plat_dat;
+struct stmmac_mdio_bus_data mdio_data;
+
+static void stmmac_default_data(void)
+{
+ memset(&plat_dat, 0, sizeof(struct plat_stmmacenet_data));
+ plat_dat.bus_id = 1;
+ plat_dat.phy_addr = 0;
+ plat_dat.interface = PHY_INTERFACE_MODE_GMII;
+ plat_dat.pbl = 32;
+ plat_dat.clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
+ plat_dat.has_gmac = 1;
+ plat_dat.force_sf_dma_mode = 1;
+
+ mdio_data.bus_id = 1;
+ mdio_data.phy_reset = NULL;
+ mdio_data.phy_mask = 0;
+ plat_dat.mdio_bus_data = &mdio_data;
+}
+
+/**
+ * stmmac_pci_probe
+ *
+ * @pdev: pci device pointer
+ * @id: pointer to table of device id/id's.
+ *
+ * Description: This probing function gets called for all PCI devices which
+ * match the ID table and are not "owned" by other driver yet. This function
+ * gets passed a "struct pci_dev *" for each device whose entry in the ID table
+ * matches the device. The probe functions returns zero when the driver choose
+ * to take "ownership" of the device or an error code(-ve no) otherwise.
+ */
+static int __devinit stmmac_pci_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ int ret = 0;
+ void __iomem *addr = NULL;
+ struct stmmac_priv *priv = NULL;
+ int i;
+
+ /* Enable pci device */
+ ret = pci_enable_device(pdev);
+ if (ret) {
+ pr_err("%s : ERROR: failed to enable %s device\n", __func__,
+ pci_name(pdev));
+ return ret;
+ }
+ if (pci_request_regions(pdev, STMMAC_RESOURCE_NAME)) {
+ pr_err("%s: ERROR: failed to get PCI region\n", __func__);
+ ret = -ENODEV;
+ goto err_out_req_reg_failed;
+ }
+
+ /* Get the base address of device */
+ for (i = 0; i <= 5; i++) {
+ if (pci_resource_len(pdev, i) == 0)
+ continue;
+ addr = pci_iomap(pdev, i, 0);
+ if (addr == NULL) {
+ pr_err("%s: ERROR: cannot map regiser memory, aborting",
+ __func__);
+ ret = -EIO;
+ goto err_out_map_failed;
+ }
+ break;
+ }
+ pci_set_master(pdev);
+
+ stmmac_default_data();
+
+ priv = stmmac_dvr_probe(&(pdev->dev), &plat_dat);
+ if (!priv) {
+ pr_err("%s: main drivr probe failed", __func__);
+ goto err_out;
+ }
+ priv->ioaddr = addr;
+ priv->dev->base_addr = (unsigned long)addr;
+ priv->dev->irq = pdev->irq;
+ priv->wol_irq = pdev->irq;
+
+ pci_set_drvdata(pdev, priv->dev);
+
+ pr_debug("STMMAC platform driver registration completed");
+
+ return 0;
+
+err_out:
+ pci_clear_master(pdev);
+err_out_map_failed:
+ pci_release_regions(pdev);
+err_out_req_reg_failed:
+ pci_disable_device(pdev);
+
+ return ret;
+}
+
+/**
+ * stmmac_dvr_remove
+ *
+ * @pdev: platform device pointer
+ * Description: this function calls the main to free the net resources
+ * and releases the PCI resources.
+ */
+static void __devexit stmmac_pci_remove(struct pci_dev *pdev)
+{
+ struct net_device *ndev = pci_get_drvdata(pdev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+
+ stmmac_dvr_remove(ndev);
+
+ pci_set_drvdata(pdev, NULL);
+ pci_iounmap(pdev, priv->ioaddr);
+ pci_release_regions(pdev);
+ pci_disable_device(pdev);
+}
+
+#ifdef CONFIG_PM
+static int stmmac_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct net_device *ndev = pci_get_drvdata(pdev);
+ int ret;
+
+ ret = stmmac_suspend(ndev);
+ pci_save_state(pdev);
+ pci_set_power_state(pdev, pci_choose_state(pdev, state));
+
+ return ret;
+}
+
+static int stmmac_pci_resume(struct pci_dev *pdev)
+{
+ struct net_device *ndev = pci_get_drvdata(pdev);
+
+ pci_set_power_state(pdev, PCI_D0);
+ pci_restore_state(pdev);
+
+ return stmmac_resume(ndev);
+}
+#endif
+
+#define STMMAC_VENDOR_ID 0x700
+#define STMMAC_DEVICE_ID 0x1108
+
+static DEFINE_PCI_DEVICE_TABLE(stmmac_id_table) = {
+ {
+ PCI_DEVICE(STMMAC_VENDOR_ID, STMMAC_DEVICE_ID)}, {
+ }
+};
+
+MODULE_DEVICE_TABLE(pci, stmmac_id_table);
+
+static struct pci_driver stmmac_driver = {
+ .name = STMMAC_RESOURCE_NAME,
+ .id_table = stmmac_id_table,
+ .probe = stmmac_pci_probe,
+ .remove = __devexit_p(stmmac_pci_remove),
+#ifdef CONFIG_PM
+ .suspend = stmmac_pci_suspend,
+ .resume = stmmac_pci_resume,
+#endif
+};
+
+/**
+ * stmmac_init_module - Entry point for the driver
+ * Description: This function is the entry point for the driver.
+ */
+static int __init stmmac_init_module(void)
+{
+ int ret;
+
+ ret = pci_register_driver(&stmmac_driver);
+ if (ret < 0)
+ pr_err("%s: ERROR: driver registration failed\n", __func__);
+
+ return ret;
+}
+
+/**
+ * stmmac_cleanup_module - Cleanup routine for the driver
+ * Description: This function is the cleanup routine for the driver.
+ */
+static void __exit stmmac_cleanup_module(void)
+{
+ pci_unregister_driver(&stmmac_driver);
+}
+
+module_init(stmmac_init_module);
+module_exit(stmmac_cleanup_module);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet PCI driver");
+MODULE_AUTHOR("Rayagond Kokatanur <rayagond.kokatanur@vayavyalabs.com>");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
--- /dev/null
+/*******************************************************************************
+ This contains the functions to handle the platform driver.
+
+ Copyright (C) 2007-2011 STMicroelectronics Ltd
+
+ This program is free software; you can redistribute it and/or modify it
+ under the terms and conditions of the GNU General Public License,
+ version 2, as published by the Free Software Foundation.
+
+ This program is distributed in the hope it will be useful, but WITHOUT
+ ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ You should have received a copy of the GNU General Public License along with
+ this program; if not, write to the Free Software Foundation, Inc.,
+ 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+ The full GNU General Public License is included in this distribution in
+ the file called "COPYING".
+
+ Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+*******************************************************************************/
+
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include "stmmac.h"
+
+/**
+ * stmmac_pltfr_probe
+ * @pdev: platform device pointer
+ * Description: platform_device probe function. It allocates
+ * the necessary resources and invokes the main to init
+ * the net device, register the mdio bus etc.
+ */
+static int stmmac_pltfr_probe(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct resource *res;
+ void __iomem *addr = NULL;
+ struct stmmac_priv *priv = NULL;
+ struct plat_stmmacenet_data *plat_dat;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENODEV;
+
+ if (!request_mem_region(res->start, resource_size(res), pdev->name)) {
+ pr_err("%s: ERROR: memory allocation failed"
+ "cannot get the I/O addr 0x%x\n",
+ __func__, (unsigned int)res->start);
+ return -EBUSY;
+ }
+
+ addr = ioremap(res->start, resource_size(res));
+ if (!addr) {
+ pr_err("%s: ERROR: memory mapping failed", __func__);
+ ret = -ENOMEM;
+ goto out_release_region;
+ }
+ plat_dat = pdev->dev.platform_data;
+ priv = stmmac_dvr_probe(&(pdev->dev), plat_dat);
+ if (!priv) {
+ pr_err("%s: main drivr probe failed", __func__);
+ goto out_release_region;
+ }
+
+ priv->ioaddr = addr;
+ /* Set the I/O base addr */
+ priv->dev->base_addr = (unsigned long)addr;
+
+ /* Get the MAC information */
+ priv->dev->irq = platform_get_irq_byname(pdev, "macirq");
+ if (priv->dev->irq == -ENXIO) {
+ pr_err("%s: ERROR: MAC IRQ configuration "
+ "information not found\n", __func__);
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ /*
+ * On some platforms e.g. SPEAr the wake up irq differs from the mac irq
+ * The external wake up irq can be passed through the platform code
+ * named as "eth_wake_irq"
+ *
+ * In case the wake up interrupt is not passed from the platform
+ * so the driver will continue to use the mac irq (ndev->irq)
+ */
+ priv->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
+ if (priv->wol_irq == -ENXIO)
+ priv->wol_irq = priv->dev->irq;
+
+ platform_set_drvdata(pdev, priv->dev);
+
+ /* Custom initialisation */
+ if (priv->plat->init) {
+ ret = priv->plat->init(pdev);
+ if (unlikely(ret))
+ goto out_unmap;
+ }
+
+ pr_debug("STMMAC platform driver registration completed");
+
+ return 0;
+
+out_unmap:
+ iounmap(addr);
+ platform_set_drvdata(pdev, NULL);
+
+out_release_region:
+ release_mem_region(res->start, resource_size(res));
+
+ return ret;
+}
+
+/**
+ * stmmac_pltfr_remove
+ * @pdev: platform device pointer
+ * Description: this function calls the main to free the net resources
+ * and calls the platforms hook and release the resources (e.g. mem).
+ */
+static int stmmac_pltfr_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ struct resource *res;
+ int ret = stmmac_dvr_remove(ndev);
+
+ if (priv->plat->exit)
+ priv->plat->exit(pdev);
+
+ if (priv->plat->exit)
+ priv->plat->exit(pdev);
+
+ platform_set_drvdata(pdev, NULL);
+
+ iounmap((void *)priv->ioaddr);
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ release_mem_region(res->start, resource_size(res));
+
+ return ret;
+}
+
+#ifdef CONFIG_PM
+static int stmmac_pltfr_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return stmmac_suspend(ndev);
+}
+
+static int stmmac_pltfr_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return stmmac_resume(ndev);
+}
+
+int stmmac_pltfr_freeze(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return stmmac_freeze(ndev);
+}
+
+int stmmac_pltfr_restore(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return stmmac_restore(ndev);
+}
+
+static const struct dev_pm_ops stmmac_pltfr_pm_ops = {
+ .suspend = stmmac_pltfr_suspend,
+ .resume = stmmac_pltfr_resume,
+ .freeze = stmmac_pltfr_freeze,
+ .thaw = stmmac_pltfr_restore,
+ .restore = stmmac_pltfr_restore,
+};
+#else
+static const struct dev_pm_ops stmmac_pltfr_pm_ops;
+#endif /* CONFIG_PM */
+
+static struct platform_driver stmmac_driver = {
+ .probe = stmmac_pltfr_probe,
+ .remove = stmmac_pltfr_remove,
+ .driver = {
+ .name = STMMAC_RESOURCE_NAME,
+ .owner = THIS_MODULE,
+ .pm = &stmmac_pltfr_pm_ops,
+ },
+};
+
+module_platform_driver(stmmac_driver);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet PLATFORM driver");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct cas *cp = netdev_priv(dev);
- strncpy(info->driver, DRV_MODULE_NAME, ETHTOOL_BUSINFO_LEN);
- strncpy(info->version, DRV_MODULE_VERSION, ETHTOOL_BUSINFO_LEN);
- info->fw_version[0] = '\0';
- strncpy(info->bus_info, pci_name(cp->pdev), ETHTOOL_BUSINFO_LEN);
+ strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
info->regdump_len = cp->casreg_len < CAS_MAX_REGS ?
cp->casreg_len : CAS_MAX_REGS;
info->n_stats = CAS_NUM_STAT_KEYS;
supported |= SUPPORTED_1000baseT_Full;
lp->supported = supported;
- advertising = 0;
- if (advert & ADVERTISE_10HALF)
- advertising |= ADVERTISED_10baseT_Half;
- if (advert & ADVERTISE_10FULL)
- advertising |= ADVERTISED_10baseT_Full;
- if (advert & ADVERTISE_100HALF)
- advertising |= ADVERTISED_100baseT_Half;
- if (advert & ADVERTISE_100FULL)
- advertising |= ADVERTISED_100baseT_Full;
- if (ctrl1000 & ADVERTISE_1000HALF)
- advertising |= ADVERTISED_1000baseT_Half;
- if (ctrl1000 & ADVERTISE_1000FULL)
- advertising |= ADVERTISED_1000baseT_Full;
+ advertising = mii_adv_to_ethtool_adv_t(advert);
+ advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
if (bmcr & BMCR_ANENABLE) {
int neg, neg1000;
static void niu_tx_work(struct niu *np, struct tx_ring_info *rp)
{
struct netdev_queue *txq;
+ unsigned int tx_bytes;
u16 pkt_cnt, tmp;
int cons, index;
u64 cs;
netif_printk(np, tx_done, KERN_DEBUG, np->dev,
"%s() pkt_cnt[%u] cons[%d]\n", __func__, pkt_cnt, cons);
- while (pkt_cnt--)
+ tx_bytes = 0;
+ tmp = pkt_cnt;
+ while (tmp--) {
+ tx_bytes += rp->tx_buffs[cons].skb->len;
cons = release_tx_packet(np, rp, cons);
+ }
rp->cons = cons;
smp_mb();
+ netdev_tx_completed_queue(txq, pkt_cnt, tx_bytes);
+
out:
if (unlikely(netif_tx_queue_stopped(txq) &&
(niu_tx_avail(rp) > NIU_TX_WAKEUP_THRESH(rp)))) {
struct tx_ring_info *rp = &np->tx_rings[i];
niu_free_tx_ring_info(np, rp);
+ netdev_tx_reset_queue(netdev_get_tx_queue(np->dev, i));
}
kfree(np->tx_rings);
np->tx_rings = NULL;
prod = NEXT_TX(rp, prod);
}
+ netdev_tx_sent_queue(txq, skb->len);
+
if (prod < rp->prod)
rp->wrap_bit ^= TX_RING_KICK_WRAP;
rp->prod = prod;
struct niu *np = netdev_priv(dev);
struct niu_vpd *vpd = &np->vpd;
- strcpy(info->driver, DRV_MODULE_NAME);
- strcpy(info->version, DRV_MODULE_VERSION);
- sprintf(info->fw_version, "%d.%d",
+ strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+ snprintf(info->fw_version, sizeof(info->fw_version), "%d.%d",
vpd->fcode_major, vpd->fcode_minor);
if (np->parent->plat_type != PLAT_TYPE_NIU)
- strcpy(info->bus_info, pci_name(np->pdev));
+ strlcpy(info->bus_info, pci_name(np->pdev),
+ sizeof(info->bus_info));
}
static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
if (dev_id_1 < 0 || dev_id_2 < 0)
return 0;
if (type == PHY_TYPE_PMA_PMD || type == PHY_TYPE_PCS) {
+ /* Because of the NIU_PHY_ID_MASK being applied, the 8704
+ * test covers the 8706 as well.
+ */
if (((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM8704) &&
- ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_MRVL88X2011) &&
- ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM8706))
+ ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_MRVL88X2011))
return 0;
} else {
if ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM5464R)
.remove = __devexit_p(bigmac_sbus_remove),
};
-static int __init bigmac_init(void)
-{
- return platform_driver_register(&bigmac_sbus_driver);
-}
-
-static void __exit bigmac_exit(void)
-{
- platform_driver_unregister(&bigmac_sbus_driver);
-}
-
-module_init(bigmac_init);
-module_exit(bigmac_exit);
+module_platform_driver(bigmac_sbus_driver);
{
struct gem *gp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(gp->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info));
}
static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
struct happy_meal *hp = netdev_priv(dev);
- strcpy(info->driver, "sunhme");
- strcpy(info->version, "2.02");
+ strlcpy(info->driver, "sunhme", sizeof(info->driver));
+ strlcpy(info->version, "2.02", sizeof(info->version));
if (hp->happy_flags & HFLAG_PCI) {
struct pci_dev *pdev = hp->happy_dev;
- strcpy(info->bus_info, pci_name(pdev));
+ strlcpy(info->bus_info, pci_name(pdev), sizeof(info->bus_info));
}
#ifdef CONFIG_SBUS
else {
struct platform_device *op = hp->happy_dev;
regs = of_get_property(op->dev.of_node, "regs", NULL);
if (regs)
- sprintf(info->bus_info, "SBUS:%d",
+ snprintf(info->bus_info, sizeof(info->bus_info),
+ "SBUS:%d",
regs->which_io);
}
#endif
sbus_dp = op->dev.parent->of_node;
/* We can match PCI devices too, do not accept those here. */
- if (strcmp(sbus_dp->name, "sbus"))
+ if (strcmp(sbus_dp->name, "sbus") && strcmp(sbus_dp->name, "sbi"))
return err;
if (is_qfe) {
static int is_quattro_p(struct pci_dev *pdev)
{
struct pci_dev *busdev = pdev->bus->self;
- struct list_head *tmp;
+ struct pci_dev *this_pdev;
int n_hmes;
if (busdev == NULL ||
return 0;
n_hmes = 0;
- tmp = pdev->bus->devices.next;
- while (tmp != &pdev->bus->devices) {
- struct pci_dev *this_pdev = pci_dev_b(tmp);
-
+ list_for_each_entry(this_pdev, &pdev->bus->devices, bus_list) {
if (this_pdev->vendor == PCI_VENDOR_ID_SUN &&
this_pdev->device == PCI_DEVICE_ID_SUN_HAPPYMEAL)
n_hmes++;
-
- tmp = tmp->next;
}
if (n_hmes != 4)
* @ndev network device
* @vid VLAN vid to add
*/
-static void bdx_vlan_rx_add_vid(struct net_device *ndev, uint16_t vid)
+static int bdx_vlan_rx_add_vid(struct net_device *ndev, uint16_t vid)
{
__bdx_vlan_rx_vid(ndev, vid, 1);
+ return 0;
}
/*
* @ndev network device
* @vid VLAN vid to kill
*/
-static void bdx_vlan_rx_kill_vid(struct net_device *ndev, unsigned short vid)
+static int bdx_vlan_rx_kill_vid(struct net_device *ndev, unsigned short vid)
{
__bdx_vlan_rx_vid(ndev, vid, 0);
+ return 0;
}
/**
chan_write(chan, cp, CPDMA_TEARDOWN_VALUE);
/* handle completed packets */
+ spin_unlock_irqrestore(&chan->lock, flags);
do {
ret = __cpdma_chan_process(chan);
if (ret < 0)
break;
} while ((ret & CPDMA_DESC_TD_COMPLETE) == 0);
+ spin_lock_irqsave(&chan->lock, flags);
/* remaining packets haven't been tx/rx'ed, clean them up */
while (chan->head) {
#define EMAC_DEF_TX_CH (0) /* Default 0th channel */
#define EMAC_DEF_RX_CH (0) /* Default 0th channel */
#define EMAC_DEF_RX_NUM_DESC (128)
+#define EMAC_DEF_TX_NUM_DESC (128)
#define EMAC_DEF_MAX_TX_CH (1) /* Max TX channels configured */
#define EMAC_DEF_MAX_RX_CH (1) /* Max RX channels configured */
#define EMAC_POLL_WEIGHT (64) /* Default NAPI poll weight */
u32 mac_hash2;
u32 multicast_hash_cnt[EMAC_NUM_MULTICAST_BITS];
u32 rx_addr_type;
+ atomic_t cur_tx;
const char *phy_id;
struct phy_device *phydev;
spinlock_t lock;
{
struct sk_buff *skb = token;
struct net_device *ndev = skb->dev;
+ struct emac_priv *priv = netdev_priv(ndev);
+
+ atomic_dec(&priv->cur_tx);
if (unlikely(netif_queue_stopped(ndev)))
netif_start_queue(ndev);
goto fail_tx;
}
+ if (atomic_inc_return(&priv->cur_tx) >= EMAC_DEF_TX_NUM_DESC)
+ netif_stop_queue(ndev);
+
return NETDEV_TX_OK;
fail_tx:
goto done;
/* Re-enable the ingress interrupt. */
- enable_percpu_irq(priv->intr_id);
+ enable_percpu_irq(priv->intr_id, 0);
/* HACK: Avoid the "rotting packet" problem (see above). */
if (qup->__packet_receive_read !=
sizeof(dummy), NETIO_IPP_STOP_SHIM_OFF) < 0)
panic("Failed to stop LIPP/LEPP!\n");
- priv->partly_opened = 0;
+ priv->partly_opened = false;
}
info->napi_enabled = true;
/* Enable the ingress interrupt. */
- enable_percpu_irq(priv->intr_id);
+ enable_percpu_irq(priv->intr_id, 0);
}
priv->network_cpus_count, priv->network_cpus_credits);
#endif
- priv->partly_opened = 1;
+ priv->partly_opened = true;
} else {
/* FIXME: Is this possible? */
for (i = 0; i < sh->nr_frags; i++) {
skb_frag_t *f = &sh->frags[i];
- unsigned long pfn = page_to_pfn(f->page);
+ unsigned long pfn = page_to_pfn(skb_frag_page(f));
/* FIXME: Compute "hash_for_home" properly. */
/* ISSUE: The hypervisor checks CHIP_HAS_REV1_DMA_PACKETS(). */
/* FIXME: Hmmm. */
if (!hash_default) {
void *va = pfn_to_kaddr(pfn) + f->page_offset;
- BUG_ON(PageHighMem(f->page));
+ BUG_ON(PageHighMem(skb_frag_page(f)));
finv_buffer_remote(va, f->size, 0);
}
mod_timer(&data->timer, jiffies + CHECK_PHY_INTERVAL);
}
-static int tsi108_ether_init(void)
-{
- int ret;
- ret = platform_driver_register (&tsi_eth_driver);
- if (ret < 0){
- printk("tsi108_ether_init: error initializing ethernet "
- "device\n");
- return ret;
- }
- return 0;
-}
-
static int tsi108_ether_remove(struct platform_device *pdev)
{
struct net_device *dev = platform_get_drvdata(pdev);
return 0;
}
-static void tsi108_ether_exit(void)
-{
- platform_driver_unregister(&tsi_eth_driver);
-}
-
-module_init(tsi108_ether_init);
-module_exit(tsi108_ether_exit);
+module_platform_driver(tsi_eth_driver);
MODULE_AUTHOR("Tundra Semiconductor Corporation");
MODULE_DESCRIPTION("Tsi108 Gigabit Ethernet driver");
#define DRV_VERSION "1.5.0"
#define DRV_RELDATE "2010-10-09"
+#include <linux/types.h>
/* A few user-configurable values.
These may be modified when a driver module is loaded. */
/* Work-around for broken BIOSes: they are unable to get the chip back out of
power state D3 so PXE booting fails. bootparam(7): via-rhine.avoid_D3=1 */
-static int avoid_D3;
+static bool avoid_D3;
/*
* In case you are looking for 'options[]' or 'full_duplex[]', they
static const struct ethtool_ops netdev_ethtool_ops;
static int rhine_close(struct net_device *dev);
static void rhine_shutdown (struct pci_dev *pdev);
-static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid);
-static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid);
+static int rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid);
+static int rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid);
static void rhine_set_cam(void __iomem *ioaddr, int idx, u8 *addr);
static void rhine_set_vlan_cam(void __iomem *ioaddr, int idx, u8 *addr);
static void rhine_set_cam_mask(void __iomem *ioaddr, u32 mask);
rhine_set_vlan_cam_mask(ioaddr, vCAMmask);
}
-static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct rhine_private *rp = netdev_priv(dev);
set_bit(vid, rp->active_vlans);
rhine_update_vcam(dev);
spin_unlock_irq(&rp->lock);
+ return 0;
}
-static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct rhine_private *rp = netdev_priv(dev);
clear_bit(vid, rp->active_vlans);
rhine_update_vcam(dev);
spin_unlock_irq(&rp->lock);
+ return 0;
}
static void init_registers(struct net_device *dev)
{
struct rhine_private *rp = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->bus_info, pci_name(rp->pdev));
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(rp->pdev), sizeof(info->bus_info));
}
static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
#endif
if (dmi_check_system(rhine_dmi_table)) {
/* these BIOSes fail at PXE boot if chip is in D3 */
- avoid_D3 = 1;
+ avoid_D3 = true;
pr_warn("Broken BIOS detected, avoid_D3 enabled\n");
}
else if (avoid_D3)
mac_set_vlan_cam_mask(regs, vptr->vCAMmask);
}
-static void velocity_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int velocity_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct velocity_info *vptr = netdev_priv(dev);
set_bit(vid, vptr->active_vlans);
velocity_init_cam_filter(vptr);
spin_unlock_irq(&vptr->lock);
+ return 0;
}
-static void velocity_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int velocity_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct velocity_info *vptr = netdev_priv(dev);
clear_bit(vid, vptr->active_vlans);
velocity_init_cam_filter(vptr);
spin_unlock_irq(&vptr->lock);
+ return 0;
}
static void velocity_init_rx_ring_indexes(struct velocity_info *vptr)
static void velocity_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
struct velocity_info *vptr = netdev_priv(dev);
- strcpy(info->driver, VELOCITY_NAME);
- strcpy(info->version, VELOCITY_VERSION);
- strcpy(info->bus_info, pci_name(vptr->pdev));
+ strlcpy(info->driver, VELOCITY_NAME, sizeof(info->driver));
+ strlcpy(info->version, VELOCITY_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, pci_name(vptr->pdev), sizeof(info->bus_info));
}
static void velocity_ethtool_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
return;
temac_iow(lp, XTE_LSW0_OFFSET, value);
temac_iow(lp, XTE_CTL0_OFFSET, CNTLREG_WRITE_ENABLE_MASK | reg);
+ temac_indirect_busywait(lp);
}
/**
struct temac_local *lp = netdev_priv(ndev);
int i;
+ /* Reset Local Link (DMA) */
+ lp->dma_out(lp, DMA_CONTROL_REG, DMA_CONTROL_RST);
+
for (i = 0; i < RX_BD_NUM; i++) {
if (!lp->rx_skb[i])
break;
struct sk_buff *skb;
int i;
- lp->rx_skb = kzalloc(sizeof(*lp->rx_skb) * RX_BD_NUM, GFP_KERNEL);
+ lp->rx_skb = kcalloc(RX_BD_NUM, sizeof(*lp->rx_skb), GFP_KERNEL);
if (!lp->rx_skb) {
dev_err(&ndev->dev,
"can't allocate memory for DMA RX buffer\n");
phy_start(lp->phy_dev);
}
+ temac_device_reset(ndev);
+
rc = request_irq(lp->tx_irq, ll_temac_tx_irq, 0, ndev->name, ndev);
if (rc)
goto err_tx_irq;
if (rc)
goto err_rx_irq;
- temac_device_reset(ndev);
return 0;
err_rx_irq:
}
#endif
+static int temac_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
+{
+ struct temac_local *lp = netdev_priv(ndev);
+
+ if (!netif_running(ndev))
+ return -EINVAL;
+
+ if (!lp->phy_dev)
+ return -EINVAL;
+
+ return phy_mii_ioctl(lp->phy_dev, rq, cmd);
+}
+
static const struct net_device_ops temac_netdev_ops = {
.ndo_open = temac_open,
.ndo_stop = temac_stop,
.ndo_start_xmit = temac_start_xmit,
.ndo_set_mac_address = netdev_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
+ .ndo_do_ioctl = temac_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = temac_poll_controller,
#endif
of_node_put(np); /* Finished with the DMA node; drop the reference */
- if ((lp->rx_irq == NO_IRQ) || (lp->tx_irq == NO_IRQ)) {
+ if (!lp->rx_irq || !lp->tx_irq) {
dev_err(&op->dev, "could not determine irqs\n");
rc = -ENOMEM;
goto err_iounmap_2;
},
};
-static int __init temac_init(void)
-{
- return platform_driver_register(&temac_of_driver);
-}
-module_init(temac_init);
-
-static void __exit temac_exit(void)
-{
- platform_driver_unregister(&temac_of_driver);
-}
-module_exit(temac_exit);
+module_platform_driver(temac_of_driver);
MODULE_DESCRIPTION("Xilinx LL_TEMAC Ethernet driver");
MODULE_AUTHOR("Yoshio Kashiwagi");
*/
static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
{
- bool tx_complete = 0;
+ bool tx_complete = false;
struct net_device *dev = dev_id;
struct net_local *lp = netdev_priv(dev);
void __iomem *base_addr = lp->base_addr;
tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
out_be32(base_addr + XEL_TSR_OFFSET, tx_status);
- tx_complete = 1;
+ tx_complete = true;
}
/* Check if the Transmission for the second buffer is completed */
out_be32(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET,
tx_status);
- tx_complete = 1;
+ tx_complete = true;
}
/* If there was a Tx interrupt, call the Tx Handler */
/* Get IRQ for the device */
rc = of_irq_to_resource(ofdev->dev.of_node, 0, &r_irq);
- if (rc == NO_IRQ) {
+ if (!rc) {
dev_err(dev, "no IRQ found\n");
return rc;
}
.remove = __devexit_p(xemaclite_of_remove),
};
-/**
- * xgpiopss_init - Initial driver registration call
- *
- * Return: 0 upon success, or a negative error upon failure.
- */
-static int __init xemaclite_init(void)
-{
- /* No kernel boot options used, we just need to register the driver */
- return platform_driver_register(&xemaclite_of_driver);
-}
-
-/**
- * xemaclite_cleanup - Driver un-registration call
- */
-static void __exit xemaclite_cleanup(void)
-{
- platform_driver_unregister(&xemaclite_of_driver);
-}
-
-module_init(xemaclite_init);
-module_exit(xemaclite_cleanup);
+module_platform_driver(xemaclite_of_driver);
MODULE_AUTHOR("Xilinx, Inc.");
MODULE_DESCRIPTION("Xilinx Ethernet MAC Lite driver");
static void netdev_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *info)
{
- strcpy(info->driver, "xirc2ps_cs");
+ strlcpy(info->driver, "xirc2ps_cs", sizeof(info->driver));
sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
}
kernel code or by user space programs. Say Y here only if you have
the memory.
-endif /* HIPPI */
+endif # HIPPI
.ndo_validate_addr = eth_validate_addr,
};
-#define IFB_FEATURES (NETIF_F_NO_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \
+#define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \
NETIF_F_TSO_ECN | NETIF_F_TSO | NETIF_F_TSO6 | \
NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_TX)
},
};
-static int __init bfin_sir_init(void)
-{
- return platform_driver_register(&bfin_ir_driver);
-}
-
-static void __exit bfin_sir_exit(void)
-{
- platform_driver_unregister(&bfin_ir_driver);
-}
-
-module_init(bfin_sir_init);
-module_exit(bfin_sir_exit);
+module_platform_driver(bfin_ir_driver);
module_param(max_rate, int, 0);
MODULE_PARM_DESC(max_rate, "Maximum baud rate (115200, 57600, 38400, 19200, 9600)");
static int max_baud = 4000000;
#ifdef USE_PROBE
-static int do_probe = 0;
+static bool do_probe = false;
#endif
.resume = pxa_irda_resume,
};
-static int __init pxa_irda_init(void)
-{
- return platform_driver_register(&pxa_ir_driver);
-}
-
-static void __exit pxa_irda_exit(void)
-{
- platform_driver_unregister(&pxa_ir_driver);
-}
-
-module_init(pxa_irda_init);
-module_exit(pxa_irda_exit);
+module_platform_driver(pxa_ir_driver);
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:pxa2xx-ir");
},
};
-static int __init sh_irda_init(void)
-{
- return platform_driver_register(&sh_irda_driver);
-}
-
-static void __exit sh_irda_exit(void)
-{
- platform_driver_unregister(&sh_irda_driver);
-}
-
-module_init(sh_irda_init);
-module_exit(sh_irda_exit);
+module_platform_driver(sh_irda_driver);
MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
MODULE_DESCRIPTION("SuperH IrDA driver");
},
};
-static int __init sh_sir_init(void)
-{
- return platform_driver_register(&sh_sir_driver);
-}
-
-static void __exit sh_sir_exit(void)
-{
- platform_driver_unregister(&sh_sir_driver);
-}
-
-module_init(sh_sir_init);
-module_exit(sh_sir_exit);
+module_platform_driver(sh_sir_driver);
MODULE_AUTHOR("Kuninori Morimoto <morimoto.kuninori@renesas.com>");
MODULE_DESCRIPTION("SuperH IrDA driver");
MODULE_DESCRIPTION("SMC IrCC SIR/FIR controller driver");
MODULE_LICENSE("GPL");
-static int smsc_nopnp = 1;
+static bool smsc_nopnp = true;
module_param_named(nopnp, smsc_nopnp, bool, 0);
MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings, defaults to true");
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
| NETIF_F_ALL_TSO
| NETIF_F_UFO
- | NETIF_F_NO_CSUM
+ | NETIF_F_HW_CSUM
| NETIF_F_RXCSUM
| NETIF_F_HIGHDMA
| NETIF_F_LLTX
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
#include <linux/if_link.h>
#include <linux/if_macvlan.h>
#include <net/rtnetlink.h>
return stats;
}
-static void macvlan_vlan_rx_add_vid(struct net_device *dev,
+static int macvlan_vlan_rx_add_vid(struct net_device *dev,
unsigned short vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
- const struct net_device_ops *ops = lowerdev->netdev_ops;
- if (ops->ndo_vlan_rx_add_vid)
- ops->ndo_vlan_rx_add_vid(lowerdev, vid);
+ return vlan_vid_add(lowerdev, vid);
}
-static void macvlan_vlan_rx_kill_vid(struct net_device *dev,
+static int macvlan_vlan_rx_kill_vid(struct net_device *dev,
unsigned short vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
- const struct net_device_ops *ops = lowerdev->netdev_ops;
- if (ops->ndo_vlan_rx_kill_vid)
- ops->ndo_vlan_rx_kill_vid(lowerdev, vid);
+ vlan_vid_del(lowerdev, vid);
+ return 0;
}
static void macvlan_ethtool_get_drvinfo(struct net_device *dev,
if (vlan) {
int index = get_slot(vlan, q);
- rcu_assign_pointer(vlan->taps[index], NULL);
- rcu_assign_pointer(q->vlan, NULL);
+ RCU_INIT_POINTER(vlan->taps[index], NULL);
+ RCU_INIT_POINTER(q->vlan, NULL);
sock_put(&q->sk);
--vlan->numvtaps;
}
if (!numvtaps)
goto out;
+ /* Check if we can use flow to select a queue */
+ rxq = skb_get_rxhash(skb);
+ if (rxq) {
+ tap = rcu_dereference(vlan->taps[rxq % numvtaps]);
+ if (tap)
+ goto out;
+ }
+
if (likely(skb_rx_queue_recorded(skb))) {
rxq = skb_get_rx_queue(skb);
goto out;
}
- /* Check if we can use flow to select a queue */
- rxq = skb_get_rxhash(skb);
- if (rxq) {
- tap = rcu_dereference(vlan->taps[rxq % numvtaps]);
- if (tap)
- goto out;
- }
-
/* Everything failed - find first available queue */
for (rxq = 0; rxq < MAX_MACVTAP_QUEUES; rxq++) {
tap = rcu_dereference(vlan->taps[rxq]);
lockdep_is_held(&macvtap_lock));
if (q) {
qlist[j++] = q;
- rcu_assign_pointer(vlan->taps[i], NULL);
- rcu_assign_pointer(q->vlan, NULL);
+ RCU_INIT_POINTER(vlan->taps[i], NULL);
+ RCU_INIT_POINTER(q->vlan, NULL);
vlan->numvtaps--;
}
}
static u32 mii_get_an(struct mii_if_info *mii, u16 addr)
{
- u32 result = 0;
int advert;
advert = mii->mdio_read(mii->dev, mii->phy_id, addr);
- if (advert & LPA_LPACK)
- result |= ADVERTISED_Autoneg;
- if (advert & ADVERTISE_10HALF)
- result |= ADVERTISED_10baseT_Half;
- if (advert & ADVERTISE_10FULL)
- result |= ADVERTISED_10baseT_Full;
- if (advert & ADVERTISE_100HALF)
- result |= ADVERTISED_100baseT_Half;
- if (advert & ADVERTISE_100FULL)
- result |= ADVERTISED_100baseT_Full;
- if (advert & ADVERTISE_PAUSE_CAP)
- result |= ADVERTISED_Pause;
- if (advert & ADVERTISE_PAUSE_ASYM)
- result |= ADVERTISED_Asym_Pause;
-
- return result;
+
+ return mii_lpa_to_ethtool_lpa_t(advert);
}
/**
ecmd->autoneg = AUTONEG_ENABLE;
ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE);
- if (ctrl1000 & ADVERTISE_1000HALF)
- ecmd->advertising |= ADVERTISED_1000baseT_Half;
- if (ctrl1000 & ADVERTISE_1000FULL)
- ecmd->advertising |= ADVERTISED_1000baseT_Full;
+ if (mii->supports_gmii)
+ ecmd->advertising |=
+ mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
if (bmsr & BMSR_ANEGCOMPLETE) {
ecmd->lp_advertising = mii_get_an(mii, MII_LPA);
- if (stat1000 & LPA_1000HALF)
- ecmd->lp_advertising |=
- ADVERTISED_1000baseT_Half;
- if (stat1000 & LPA_1000FULL)
- ecmd->lp_advertising |=
- ADVERTISED_1000baseT_Full;
+ ecmd->lp_advertising |=
+ mii_stat1000_to_ethtool_lpa_t(stat1000);
} else {
ecmd->lp_advertising = 0;
}
advert2 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
tmp2 = advert2 & ~(ADVERTISE_1000HALF | ADVERTISE_1000FULL);
}
- if (ecmd->advertising & ADVERTISED_10baseT_Half)
- tmp |= ADVERTISE_10HALF;
- if (ecmd->advertising & ADVERTISED_10baseT_Full)
- tmp |= ADVERTISE_10FULL;
- if (ecmd->advertising & ADVERTISED_100baseT_Half)
- tmp |= ADVERTISE_100HALF;
- if (ecmd->advertising & ADVERTISED_100baseT_Full)
- tmp |= ADVERTISE_100FULL;
- if (mii->supports_gmii) {
- if (ecmd->advertising & ADVERTISED_1000baseT_Half)
- tmp2 |= ADVERTISE_1000HALF;
- if (ecmd->advertising & ADVERTISED_1000baseT_Full)
- tmp2 |= ADVERTISE_1000FULL;
- }
+ tmp |= ethtool_adv_to_mii_adv_t(ecmd->advertising);
+
+ if (mii->supports_gmii)
+ tmp2 |=
+ ethtool_adv_to_mii_ctrl1000_t(ecmd->advertising);
if (advert != tmp) {
mii->mdio_write(dev, mii->phy_id, MII_ADVERTISE, tmp);
mii->advertising = tmp;
#
menuconfig PHYLIB
- bool "PHY Device support and infrastructure"
+ tristate "PHY Device support and infrastructure"
depends on !S390
depends on NETDEVICES
help
If in doubt, say Y.
endif # PHYLIB
+
+config MICREL_KS8995MA
+ tristate "Micrel KS8995MA 5-ports 10/100 managed Ethernet switch"
+ depends on SPI
obj-$(CONFIG_STE10XP) += ste10Xp.o
obj-$(CONFIG_MICREL_PHY) += micrel.o
obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o
+obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o
return 0;
}
+static int mdiobb_reset(struct mii_bus *bus)
+{
+ struct mdiobb_ctrl *ctrl = bus->priv;
+ if (ctrl->reset)
+ ctrl->reset(bus);
+ return 0;
+}
+
struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
{
struct mii_bus *bus;
bus->read = mdiobb_read;
bus->write = mdiobb_write;
+ bus->reset = mdiobb_reset;
bus->priv = ctrl;
return bus;
goto out;
bitbang->ctrl.ops = &mdio_gpio_ops;
+ bitbang->ctrl.reset = pdata->reset;
bitbang->mdc = pdata->mdc;
bitbang->mdio = pdata->mdio;
if (adv < 0)
return adv;
- adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP |
+ adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP |
ADVERTISE_PAUSE_ASYM);
- if (advertise & ADVERTISED_10baseT_Half)
- adv |= ADVERTISE_10HALF;
- if (advertise & ADVERTISED_10baseT_Full)
- adv |= ADVERTISE_10FULL;
- if (advertise & ADVERTISED_100baseT_Half)
- adv |= ADVERTISE_100HALF;
- if (advertise & ADVERTISED_100baseT_Full)
- adv |= ADVERTISE_100FULL;
- if (advertise & ADVERTISED_Pause)
- adv |= ADVERTISE_PAUSE_CAP;
- if (advertise & ADVERTISED_Asym_Pause)
- adv |= ADVERTISE_PAUSE_ASYM;
+ adv |= ethtool_adv_to_mii_adv_t(advertise);
if (adv != oldadv) {
err = phy_write(phydev, MII_ADVERTISE, adv);
return adv;
adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
- if (advertise & SUPPORTED_1000baseT_Half)
- adv |= ADVERTISE_1000HALF;
- if (advertise & SUPPORTED_1000baseT_Full)
- adv |= ADVERTISE_1000FULL;
+ adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
if (adv != oldadv) {
err = phy_write(phydev, MII_CTRL1000, adv);
#include <linux/ethtool.h>
#include <linux/phy.h>
#include <linux/netdevice.h>
-
-#define MII_LAN83C185_ISF 29 /* Interrupt Source Flags */
-#define MII_LAN83C185_IM 30 /* Interrupt Mask */
-#define MII_LAN83C185_CTRL_STATUS 17 /* Mode/Status Register */
-
-#define MII_LAN83C185_ISF_INT1 (1<<1) /* Auto-Negotiation Page Received */
-#define MII_LAN83C185_ISF_INT2 (1<<2) /* Parallel Detection Fault */
-#define MII_LAN83C185_ISF_INT3 (1<<3) /* Auto-Negotiation LP Ack */
-#define MII_LAN83C185_ISF_INT4 (1<<4) /* Link Down */
-#define MII_LAN83C185_ISF_INT5 (1<<5) /* Remote Fault Detected */
-#define MII_LAN83C185_ISF_INT6 (1<<6) /* Auto-Negotiation complete */
-#define MII_LAN83C185_ISF_INT7 (1<<7) /* ENERGYON */
-
-#define MII_LAN83C185_ISF_INT_ALL (0x0e)
-
-#define MII_LAN83C185_ISF_INT_PHYLIB_EVENTS \
- (MII_LAN83C185_ISF_INT6 | MII_LAN83C185_ISF_INT4 | \
- MII_LAN83C185_ISF_INT7)
-
-#define MII_LAN83C185_EDPWRDOWN (1 << 13) /* EDPWRDOWN */
+#include <linux/smscphy.h>
static int smsc_phy_config_intr(struct phy_device *phydev)
{
--- /dev/null
+/*
+ * SPI driver for Micrel/Kendin KS8995M ethernet switch
+ *
+ * Copyright (C) 2008 Gabor Juhos <juhosg at openwrt.org>
+ *
+ * This file was based on: drivers/spi/at25.c
+ * Copyright (C) 2006 David Brownell
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+
+#include <linux/spi/spi.h>
+
+#define DRV_VERSION "0.1.1"
+#define DRV_DESC "Micrel KS8995 Ethernet switch SPI driver"
+
+/* ------------------------------------------------------------------------ */
+
+#define KS8995_REG_ID0 0x00 /* Chip ID0 */
+#define KS8995_REG_ID1 0x01 /* Chip ID1 */
+
+#define KS8995_REG_GC0 0x02 /* Global Control 0 */
+#define KS8995_REG_GC1 0x03 /* Global Control 1 */
+#define KS8995_REG_GC2 0x04 /* Global Control 2 */
+#define KS8995_REG_GC3 0x05 /* Global Control 3 */
+#define KS8995_REG_GC4 0x06 /* Global Control 4 */
+#define KS8995_REG_GC5 0x07 /* Global Control 5 */
+#define KS8995_REG_GC6 0x08 /* Global Control 6 */
+#define KS8995_REG_GC7 0x09 /* Global Control 7 */
+#define KS8995_REG_GC8 0x0a /* Global Control 8 */
+#define KS8995_REG_GC9 0x0b /* Global Control 9 */
+
+#define KS8995_REG_PC(p, r) ((0x10 * p) + r) /* Port Control */
+#define KS8995_REG_PS(p, r) ((0x10 * p) + r + 0xe) /* Port Status */
+
+#define KS8995_REG_TPC0 0x60 /* TOS Priority Control 0 */
+#define KS8995_REG_TPC1 0x61 /* TOS Priority Control 1 */
+#define KS8995_REG_TPC2 0x62 /* TOS Priority Control 2 */
+#define KS8995_REG_TPC3 0x63 /* TOS Priority Control 3 */
+#define KS8995_REG_TPC4 0x64 /* TOS Priority Control 4 */
+#define KS8995_REG_TPC5 0x65 /* TOS Priority Control 5 */
+#define KS8995_REG_TPC6 0x66 /* TOS Priority Control 6 */
+#define KS8995_REG_TPC7 0x67 /* TOS Priority Control 7 */
+
+#define KS8995_REG_MAC0 0x68 /* MAC address 0 */
+#define KS8995_REG_MAC1 0x69 /* MAC address 1 */
+#define KS8995_REG_MAC2 0x6a /* MAC address 2 */
+#define KS8995_REG_MAC3 0x6b /* MAC address 3 */
+#define KS8995_REG_MAC4 0x6c /* MAC address 4 */
+#define KS8995_REG_MAC5 0x6d /* MAC address 5 */
+
+#define KS8995_REG_IAC0 0x6e /* Indirect Access Control 0 */
+#define KS8995_REG_IAC1 0x6f /* Indirect Access Control 0 */
+#define KS8995_REG_IAD7 0x70 /* Indirect Access Data 7 */
+#define KS8995_REG_IAD6 0x71 /* Indirect Access Data 6 */
+#define KS8995_REG_IAD5 0x72 /* Indirect Access Data 5 */
+#define KS8995_REG_IAD4 0x73 /* Indirect Access Data 4 */
+#define KS8995_REG_IAD3 0x74 /* Indirect Access Data 3 */
+#define KS8995_REG_IAD2 0x75 /* Indirect Access Data 2 */
+#define KS8995_REG_IAD1 0x76 /* Indirect Access Data 1 */
+#define KS8995_REG_IAD0 0x77 /* Indirect Access Data 0 */
+
+#define KS8995_REGS_SIZE 0x80
+
+#define ID1_CHIPID_M 0xf
+#define ID1_CHIPID_S 4
+#define ID1_REVISION_M 0x7
+#define ID1_REVISION_S 1
+#define ID1_START_SW 1 /* start the switch */
+
+#define FAMILY_KS8995 0x95
+#define CHIPID_M 0
+
+#define KS8995_CMD_WRITE 0x02U
+#define KS8995_CMD_READ 0x03U
+
+#define KS8995_RESET_DELAY 10 /* usec */
+
+struct ks8995_pdata {
+ /* not yet implemented */
+};
+
+struct ks8995_switch {
+ struct spi_device *spi;
+ struct mutex lock;
+ struct ks8995_pdata *pdata;
+};
+
+static inline u8 get_chip_id(u8 val)
+{
+ return (val >> ID1_CHIPID_S) & ID1_CHIPID_M;
+}
+
+static inline u8 get_chip_rev(u8 val)
+{
+ return (val >> ID1_REVISION_S) & ID1_REVISION_M;
+}
+
+/* ------------------------------------------------------------------------ */
+static int ks8995_read(struct ks8995_switch *ks, char *buf,
+ unsigned offset, size_t count)
+{
+ u8 cmd[2];
+ struct spi_transfer t[2];
+ struct spi_message m;
+ int err;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].rx_buf = buf;
+ t[1].len = count;
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = KS8995_CMD_READ;
+ cmd[1] = offset;
+
+ mutex_lock(&ks->lock);
+ err = spi_sync(ks->spi, &m);
+ mutex_unlock(&ks->lock);
+
+ return err ? err : count;
+}
+
+
+static int ks8995_write(struct ks8995_switch *ks, char *buf,
+ unsigned offset, size_t count)
+{
+ u8 cmd[2];
+ struct spi_transfer t[2];
+ struct spi_message m;
+ int err;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].tx_buf = buf;
+ t[1].len = count;
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = KS8995_CMD_WRITE;
+ cmd[1] = offset;
+
+ mutex_lock(&ks->lock);
+ err = spi_sync(ks->spi, &m);
+ mutex_unlock(&ks->lock);
+
+ return err ? err : count;
+}
+
+static inline int ks8995_read_reg(struct ks8995_switch *ks, u8 addr, u8 *buf)
+{
+ return (ks8995_read(ks, buf, addr, 1) != 1);
+}
+
+static inline int ks8995_write_reg(struct ks8995_switch *ks, u8 addr, u8 val)
+{
+ char buf = val;
+
+ return (ks8995_write(ks, &buf, addr, 1) != 1);
+}
+
+/* ------------------------------------------------------------------------ */
+
+static int ks8995_stop(struct ks8995_switch *ks)
+{
+ return ks8995_write_reg(ks, KS8995_REG_ID1, 0);
+}
+
+static int ks8995_start(struct ks8995_switch *ks)
+{
+ return ks8995_write_reg(ks, KS8995_REG_ID1, 1);
+}
+
+static int ks8995_reset(struct ks8995_switch *ks)
+{
+ int err;
+
+ err = ks8995_stop(ks);
+ if (err)
+ return err;
+
+ udelay(KS8995_RESET_DELAY);
+
+ return ks8995_start(ks);
+}
+
+/* ------------------------------------------------------------------------ */
+
+static ssize_t ks8995_registers_read(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count)
+{
+ struct device *dev;
+ struct ks8995_switch *ks8995;
+
+ dev = container_of(kobj, struct device, kobj);
+ ks8995 = dev_get_drvdata(dev);
+
+ if (unlikely(off > KS8995_REGS_SIZE))
+ return 0;
+
+ if ((off + count) > KS8995_REGS_SIZE)
+ count = KS8995_REGS_SIZE - off;
+
+ if (unlikely(!count))
+ return count;
+
+ return ks8995_read(ks8995, buf, off, count);
+}
+
+
+static ssize_t ks8995_registers_write(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count)
+{
+ struct device *dev;
+ struct ks8995_switch *ks8995;
+
+ dev = container_of(kobj, struct device, kobj);
+ ks8995 = dev_get_drvdata(dev);
+
+ if (unlikely(off >= KS8995_REGS_SIZE))
+ return -EFBIG;
+
+ if ((off + count) > KS8995_REGS_SIZE)
+ count = KS8995_REGS_SIZE - off;
+
+ if (unlikely(!count))
+ return count;
+
+ return ks8995_write(ks8995, buf, off, count);
+}
+
+
+static struct bin_attribute ks8995_registers_attr = {
+ .attr = {
+ .name = "registers",
+ .mode = S_IRUSR | S_IWUSR,
+ },
+ .size = KS8995_REGS_SIZE,
+ .read = ks8995_registers_read,
+ .write = ks8995_registers_write,
+};
+
+/* ------------------------------------------------------------------------ */
+
+static int __devinit ks8995_probe(struct spi_device *spi)
+{
+ struct ks8995_switch *ks;
+ struct ks8995_pdata *pdata;
+ u8 ids[2];
+ int err;
+
+ /* Chip description */
+ pdata = spi->dev.platform_data;
+
+ ks = kzalloc(sizeof(*ks), GFP_KERNEL);
+ if (!ks) {
+ dev_err(&spi->dev, "no memory for private data\n");
+ return -ENOMEM;
+ }
+
+ mutex_init(&ks->lock);
+ ks->pdata = pdata;
+ ks->spi = spi_dev_get(spi);
+ dev_set_drvdata(&spi->dev, ks);
+
+ spi->mode = SPI_MODE_0;
+ spi->bits_per_word = 8;
+ err = spi_setup(spi);
+ if (err) {
+ dev_err(&spi->dev, "spi_setup failed, err=%d\n", err);
+ goto err_drvdata;
+ }
+
+ err = ks8995_read(ks, ids, KS8995_REG_ID0, sizeof(ids));
+ if (err < 0) {
+ dev_err(&spi->dev, "unable to read id registers, err=%d\n",
+ err);
+ goto err_drvdata;
+ }
+
+ switch (ids[0]) {
+ case FAMILY_KS8995:
+ break;
+ default:
+ dev_err(&spi->dev, "unknown family id:%02x\n", ids[0]);
+ err = -ENODEV;
+ goto err_drvdata;
+ }
+
+ err = ks8995_reset(ks);
+ if (err)
+ goto err_drvdata;
+
+ err = sysfs_create_bin_file(&spi->dev.kobj, &ks8995_registers_attr);
+ if (err) {
+ dev_err(&spi->dev, "unable to create sysfs file, err=%d\n",
+ err);
+ goto err_drvdata;
+ }
+
+ dev_info(&spi->dev, "KS89%02X device found, Chip ID:%01x, "
+ "Revision:%01x\n", ids[0],
+ get_chip_id(ids[1]), get_chip_rev(ids[1]));
+
+ return 0;
+
+err_drvdata:
+ dev_set_drvdata(&spi->dev, NULL);
+ kfree(ks);
+ return err;
+}
+
+static int __devexit ks8995_remove(struct spi_device *spi)
+{
+ struct ks8995_data *ks8995;
+
+ ks8995 = dev_get_drvdata(&spi->dev);
+ sysfs_remove_bin_file(&spi->dev.kobj, &ks8995_registers_attr);
+
+ dev_set_drvdata(&spi->dev, NULL);
+ kfree(ks8995);
+
+ return 0;
+}
+
+/* ------------------------------------------------------------------------ */
+
+static struct spi_driver ks8995_driver = {
+ .driver = {
+ .name = "spi-ks8995",
+ .bus = &spi_bus_type,
+ .owner = THIS_MODULE,
+ },
+ .probe = ks8995_probe,
+ .remove = __devexit_p(ks8995_remove),
+};
+
+static int __init ks8995_init(void)
+{
+ printk(KERN_INFO DRV_DESC " version " DRV_VERSION"\n");
+
+ return spi_register_driver(&ks8995_driver);
+}
+module_init(ks8995_init);
+
+static void __exit ks8995_exit(void)
+{
+ spi_unregister_driver(&ks8995_driver);
+}
+module_exit(ks8995_exit);
+
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_VERSION(DRV_VERSION);
+MODULE_AUTHOR("Gabor Juhos <juhosg at openwrt.org>");
+MODULE_LICENSE("GPL v2");
{
spin_lock(&chan_lock);
clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
- rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], NULL);
+ RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL);
spin_unlock(&chan_lock);
synchronize_rcu();
}
lock_sock(sk);
opt->src_addr = sp->sa_addr.pptp;
- if (add_chan(po)) {
- release_sock(sk);
+ if (add_chan(po))
error = -EBUSY;
- }
release_sock(sk);
return error;
--- /dev/null
+menuconfig NET_TEAM
+ tristate "Ethernet team driver support (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ ---help---
+ This allows one to create virtual interfaces that teams together
+ multiple ethernet devices.
+
+ Team devices can be added using the "ip" command from the
+ iproute2 package:
+
+ "ip link add link [ address MAC ] [ NAME ] type team"
+
+ To compile this driver as a module, choose M here: the module
+ will be called team.
+
+if NET_TEAM
+
+config NET_TEAM_MODE_ROUNDROBIN
+ tristate "Round-robin mode support"
+ depends on NET_TEAM
+ ---help---
+ Basic mode where port used for transmitting packets is selected in
+ round-robin fashion using packet counter.
+
+ All added ports are setup to have bond's mac address.
+
+ To compile this team mode as a module, choose M here: the module
+ will be called team_mode_roundrobin.
+
+config NET_TEAM_MODE_ACTIVEBACKUP
+ tristate "Active-backup mode support"
+ depends on NET_TEAM
+ ---help---
+ Only one port is active at a time and the rest of ports are used
+ for backup.
+
+ Mac addresses of ports are not modified. Userspace is responsible
+ to do so.
+
+ To compile this team mode as a module, choose M here: the module
+ will be called team_mode_activebackup.
+
+endif # NET_TEAM
--- /dev/null
+#
+# Makefile for the network team driver
+#
+
+obj-$(CONFIG_NET_TEAM) += team.o
+obj-$(CONFIG_NET_TEAM_MODE_ROUNDROBIN) += team_mode_roundrobin.o
+obj-$(CONFIG_NET_TEAM_MODE_ACTIVEBACKUP) += team_mode_activebackup.o
--- /dev/null
+/*
+ * net/drivers/team/team.c - Network team device driver
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/errno.h>
+#include <linux/ctype.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/if_arp.h>
+#include <linux/socket.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/rtnetlink.h>
+#include <net/genetlink.h>
+#include <net/netlink.h>
+#include <linux/if_team.h>
+
+#define DRV_NAME "team"
+
+
+/**********
+ * Helpers
+ **********/
+
+#define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT)
+
+static struct team_port *team_port_get_rcu(const struct net_device *dev)
+{
+ struct team_port *port = rcu_dereference(dev->rx_handler_data);
+
+ return team_port_exists(dev) ? port : NULL;
+}
+
+static struct team_port *team_port_get_rtnl(const struct net_device *dev)
+{
+ struct team_port *port = rtnl_dereference(dev->rx_handler_data);
+
+ return team_port_exists(dev) ? port : NULL;
+}
+
+/*
+ * Since the ability to change mac address for open port device is tested in
+ * team_port_add, this function can be called without control of return value
+ */
+static int __set_port_mac(struct net_device *port_dev,
+ const unsigned char *dev_addr)
+{
+ struct sockaddr addr;
+
+ memcpy(addr.sa_data, dev_addr, ETH_ALEN);
+ addr.sa_family = ARPHRD_ETHER;
+ return dev_set_mac_address(port_dev, &addr);
+}
+
+int team_port_set_orig_mac(struct team_port *port)
+{
+ return __set_port_mac(port->dev, port->orig.dev_addr);
+}
+
+int team_port_set_team_mac(struct team_port *port)
+{
+ return __set_port_mac(port->dev, port->team->dev->dev_addr);
+}
+EXPORT_SYMBOL(team_port_set_team_mac);
+
+
+/*******************
+ * Options handling
+ *******************/
+
+struct team_option *__team_find_option(struct team *team, const char *opt_name)
+{
+ struct team_option *option;
+
+ list_for_each_entry(option, &team->option_list, list) {
+ if (strcmp(option->name, opt_name) == 0)
+ return option;
+ }
+ return NULL;
+}
+
+int team_options_register(struct team *team,
+ const struct team_option *option,
+ size_t option_count)
+{
+ int i;
+ struct team_option **dst_opts;
+ int err;
+
+ dst_opts = kzalloc(sizeof(struct team_option *) * option_count,
+ GFP_KERNEL);
+ if (!dst_opts)
+ return -ENOMEM;
+ for (i = 0; i < option_count; i++, option++) {
+ if (__team_find_option(team, option->name)) {
+ err = -EEXIST;
+ goto rollback;
+ }
+ dst_opts[i] = kmemdup(option, sizeof(*option), GFP_KERNEL);
+ if (!dst_opts[i]) {
+ err = -ENOMEM;
+ goto rollback;
+ }
+ }
+
+ for (i = 0; i < option_count; i++)
+ list_add_tail(&dst_opts[i]->list, &team->option_list);
+
+ kfree(dst_opts);
+ return 0;
+
+rollback:
+ for (i = 0; i < option_count; i++)
+ kfree(dst_opts[i]);
+
+ kfree(dst_opts);
+ return err;
+}
+
+EXPORT_SYMBOL(team_options_register);
+
+static void __team_options_change_check(struct team *team,
+ struct team_option *changed_option);
+
+static void __team_options_unregister(struct team *team,
+ const struct team_option *option,
+ size_t option_count)
+{
+ int i;
+
+ for (i = 0; i < option_count; i++, option++) {
+ struct team_option *del_opt;
+
+ del_opt = __team_find_option(team, option->name);
+ if (del_opt) {
+ list_del(&del_opt->list);
+ kfree(del_opt);
+ }
+ }
+}
+
+void team_options_unregister(struct team *team,
+ const struct team_option *option,
+ size_t option_count)
+{
+ __team_options_unregister(team, option, option_count);
+ __team_options_change_check(team, NULL);
+}
+EXPORT_SYMBOL(team_options_unregister);
+
+static int team_option_get(struct team *team, struct team_option *option,
+ void *arg)
+{
+ return option->getter(team, arg);
+}
+
+static int team_option_set(struct team *team, struct team_option *option,
+ void *arg)
+{
+ int err;
+
+ err = option->setter(team, arg);
+ if (err)
+ return err;
+
+ __team_options_change_check(team, option);
+ return err;
+}
+
+/****************
+ * Mode handling
+ ****************/
+
+static LIST_HEAD(mode_list);
+static DEFINE_SPINLOCK(mode_list_lock);
+
+static struct team_mode *__find_mode(const char *kind)
+{
+ struct team_mode *mode;
+
+ list_for_each_entry(mode, &mode_list, list) {
+ if (strcmp(mode->kind, kind) == 0)
+ return mode;
+ }
+ return NULL;
+}
+
+static bool is_good_mode_name(const char *name)
+{
+ while (*name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return false;
+ name++;
+ }
+ return true;
+}
+
+int team_mode_register(struct team_mode *mode)
+{
+ int err = 0;
+
+ if (!is_good_mode_name(mode->kind) ||
+ mode->priv_size > TEAM_MODE_PRIV_SIZE)
+ return -EINVAL;
+ spin_lock(&mode_list_lock);
+ if (__find_mode(mode->kind)) {
+ err = -EEXIST;
+ goto unlock;
+ }
+ list_add_tail(&mode->list, &mode_list);
+unlock:
+ spin_unlock(&mode_list_lock);
+ return err;
+}
+EXPORT_SYMBOL(team_mode_register);
+
+int team_mode_unregister(struct team_mode *mode)
+{
+ spin_lock(&mode_list_lock);
+ list_del_init(&mode->list);
+ spin_unlock(&mode_list_lock);
+ return 0;
+}
+EXPORT_SYMBOL(team_mode_unregister);
+
+static struct team_mode *team_mode_get(const char *kind)
+{
+ struct team_mode *mode;
+
+ spin_lock(&mode_list_lock);
+ mode = __find_mode(kind);
+ if (!mode) {
+ spin_unlock(&mode_list_lock);
+ request_module("team-mode-%s", kind);
+ spin_lock(&mode_list_lock);
+ mode = __find_mode(kind);
+ }
+ if (mode)
+ if (!try_module_get(mode->owner))
+ mode = NULL;
+
+ spin_unlock(&mode_list_lock);
+ return mode;
+}
+
+static void team_mode_put(const struct team_mode *mode)
+{
+ module_put(mode->owner);
+}
+
+static bool team_dummy_transmit(struct team *team, struct sk_buff *skb)
+{
+ dev_kfree_skb_any(skb);
+ return false;
+}
+
+rx_handler_result_t team_dummy_receive(struct team *team,
+ struct team_port *port,
+ struct sk_buff *skb)
+{
+ return RX_HANDLER_ANOTHER;
+}
+
+static void team_adjust_ops(struct team *team)
+{
+ /*
+ * To avoid checks in rx/tx skb paths, ensure here that non-null and
+ * correct ops are always set.
+ */
+
+ if (list_empty(&team->port_list) ||
+ !team->mode || !team->mode->ops->transmit)
+ team->ops.transmit = team_dummy_transmit;
+ else
+ team->ops.transmit = team->mode->ops->transmit;
+
+ if (list_empty(&team->port_list) ||
+ !team->mode || !team->mode->ops->receive)
+ team->ops.receive = team_dummy_receive;
+ else
+ team->ops.receive = team->mode->ops->receive;
+}
+
+/*
+ * We can benefit from the fact that it's ensured no port is present
+ * at the time of mode change. Therefore no packets are in fly so there's no
+ * need to set mode operations in any special way.
+ */
+static int __team_change_mode(struct team *team,
+ const struct team_mode *new_mode)
+{
+ /* Check if mode was previously set and do cleanup if so */
+ if (team->mode) {
+ void (*exit_op)(struct team *team) = team->ops.exit;
+
+ /* Clear ops area so no callback is called any longer */
+ memset(&team->ops, 0, sizeof(struct team_mode_ops));
+ team_adjust_ops(team);
+
+ if (exit_op)
+ exit_op(team);
+ team_mode_put(team->mode);
+ team->mode = NULL;
+ /* zero private data area */
+ memset(&team->mode_priv, 0,
+ sizeof(struct team) - offsetof(struct team, mode_priv));
+ }
+
+ if (!new_mode)
+ return 0;
+
+ if (new_mode->ops->init) {
+ int err;
+
+ err = new_mode->ops->init(team);
+ if (err)
+ return err;
+ }
+
+ team->mode = new_mode;
+ memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops));
+ team_adjust_ops(team);
+
+ return 0;
+}
+
+static int team_change_mode(struct team *team, const char *kind)
+{
+ struct team_mode *new_mode;
+ struct net_device *dev = team->dev;
+ int err;
+
+ if (!list_empty(&team->port_list)) {
+ netdev_err(dev, "No ports can be present during mode change\n");
+ return -EBUSY;
+ }
+
+ if (team->mode && strcmp(team->mode->kind, kind) == 0) {
+ netdev_err(dev, "Unable to change to the same mode the team is in\n");
+ return -EINVAL;
+ }
+
+ new_mode = team_mode_get(kind);
+ if (!new_mode) {
+ netdev_err(dev, "Mode \"%s\" not found\n", kind);
+ return -EINVAL;
+ }
+
+ err = __team_change_mode(team, new_mode);
+ if (err) {
+ netdev_err(dev, "Failed to change to mode \"%s\"\n", kind);
+ team_mode_put(new_mode);
+ return err;
+ }
+
+ netdev_info(dev, "Mode changed to \"%s\"\n", kind);
+ return 0;
+}
+
+
+/************************
+ * Rx path frame handler
+ ************************/
+
+/* note: already called with rcu_read_lock */
+static rx_handler_result_t team_handle_frame(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct team_port *port;
+ struct team *team;
+ rx_handler_result_t res;
+
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ return RX_HANDLER_CONSUMED;
+
+ *pskb = skb;
+
+ port = team_port_get_rcu(skb->dev);
+ team = port->team;
+
+ res = team->ops.receive(team, port, skb);
+ if (res == RX_HANDLER_ANOTHER) {
+ struct team_pcpu_stats *pcpu_stats;
+
+ pcpu_stats = this_cpu_ptr(team->pcpu_stats);
+ u64_stats_update_begin(&pcpu_stats->syncp);
+ pcpu_stats->rx_packets++;
+ pcpu_stats->rx_bytes += skb->len;
+ if (skb->pkt_type == PACKET_MULTICAST)
+ pcpu_stats->rx_multicast++;
+ u64_stats_update_end(&pcpu_stats->syncp);
+
+ skb->dev = team->dev;
+ } else {
+ this_cpu_inc(team->pcpu_stats->rx_dropped);
+ }
+
+ return res;
+}
+
+
+/****************
+ * Port handling
+ ****************/
+
+static bool team_port_find(const struct team *team,
+ const struct team_port *port)
+{
+ struct team_port *cur;
+
+ list_for_each_entry(cur, &team->port_list, list)
+ if (cur == port)
+ return true;
+ return false;
+}
+
+/*
+ * Add/delete port to the team port list. Write guarded by rtnl_lock.
+ * Takes care of correct port->index setup (might be racy).
+ */
+static void team_port_list_add_port(struct team *team,
+ struct team_port *port)
+{
+ port->index = team->port_count++;
+ hlist_add_head_rcu(&port->hlist,
+ team_port_index_hash(team, port->index));
+ list_add_tail_rcu(&port->list, &team->port_list);
+}
+
+static void __reconstruct_port_hlist(struct team *team, int rm_index)
+{
+ int i;
+ struct team_port *port;
+
+ for (i = rm_index + 1; i < team->port_count; i++) {
+ port = team_get_port_by_index(team, i);
+ hlist_del_rcu(&port->hlist);
+ port->index--;
+ hlist_add_head_rcu(&port->hlist,
+ team_port_index_hash(team, port->index));
+ }
+}
+
+static void team_port_list_del_port(struct team *team,
+ struct team_port *port)
+{
+ int rm_index = port->index;
+
+ hlist_del_rcu(&port->hlist);
+ list_del_rcu(&port->list);
+ __reconstruct_port_hlist(team, rm_index);
+ team->port_count--;
+}
+
+#define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \
+ NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_HIGHDMA | NETIF_F_LRO)
+
+static void __team_compute_features(struct team *team)
+{
+ struct team_port *port;
+ u32 vlan_features = TEAM_VLAN_FEATURES;
+ unsigned short max_hard_header_len = ETH_HLEN;
+
+ list_for_each_entry(port, &team->port_list, list) {
+ vlan_features = netdev_increment_features(vlan_features,
+ port->dev->vlan_features,
+ TEAM_VLAN_FEATURES);
+
+ if (port->dev->hard_header_len > max_hard_header_len)
+ max_hard_header_len = port->dev->hard_header_len;
+ }
+
+ team->dev->vlan_features = vlan_features;
+ team->dev->hard_header_len = max_hard_header_len;
+
+ netdev_change_features(team->dev);
+}
+
+static void team_compute_features(struct team *team)
+{
+ mutex_lock(&team->lock);
+ __team_compute_features(team);
+ mutex_unlock(&team->lock);
+}
+
+static int team_port_enter(struct team *team, struct team_port *port)
+{
+ int err = 0;
+
+ dev_hold(team->dev);
+ port->dev->priv_flags |= IFF_TEAM_PORT;
+ if (team->ops.port_enter) {
+ err = team->ops.port_enter(team, port);
+ if (err) {
+ netdev_err(team->dev, "Device %s failed to enter team mode\n",
+ port->dev->name);
+ goto err_port_enter;
+ }
+ }
+
+ return 0;
+
+err_port_enter:
+ port->dev->priv_flags &= ~IFF_TEAM_PORT;
+ dev_put(team->dev);
+
+ return err;
+}
+
+static void team_port_leave(struct team *team, struct team_port *port)
+{
+ if (team->ops.port_leave)
+ team->ops.port_leave(team, port);
+ port->dev->priv_flags &= ~IFF_TEAM_PORT;
+ dev_put(team->dev);
+}
+
+static void __team_port_change_check(struct team_port *port, bool linkup);
+
+static int team_port_add(struct team *team, struct net_device *port_dev)
+{
+ struct net_device *dev = team->dev;
+ struct team_port *port;
+ char *portname = port_dev->name;
+ int err;
+
+ if (port_dev->flags & IFF_LOOPBACK ||
+ port_dev->type != ARPHRD_ETHER) {
+ netdev_err(dev, "Device %s is of an unsupported type\n",
+ portname);
+ return -EINVAL;
+ }
+
+ if (team_port_exists(port_dev)) {
+ netdev_err(dev, "Device %s is already a port "
+ "of a team device\n", portname);
+ return -EBUSY;
+ }
+
+ if (port_dev->flags & IFF_UP) {
+ netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n",
+ portname);
+ return -EBUSY;
+ }
+
+ port = kzalloc(sizeof(struct team_port), GFP_KERNEL);
+ if (!port)
+ return -ENOMEM;
+
+ port->dev = port_dev;
+ port->team = team;
+
+ port->orig.mtu = port_dev->mtu;
+ err = dev_set_mtu(port_dev, dev->mtu);
+ if (err) {
+ netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err);
+ goto err_set_mtu;
+ }
+
+ memcpy(port->orig.dev_addr, port_dev->dev_addr, ETH_ALEN);
+
+ err = team_port_enter(team, port);
+ if (err) {
+ netdev_err(dev, "Device %s failed to enter team mode\n",
+ portname);
+ goto err_port_enter;
+ }
+
+ err = dev_open(port_dev);
+ if (err) {
+ netdev_dbg(dev, "Device %s opening failed\n",
+ portname);
+ goto err_dev_open;
+ }
+
+ err = vlan_vids_add_by_dev(port_dev, dev);
+ if (err) {
+ netdev_err(dev, "Failed to add vlan ids to device %s\n",
+ portname);
+ goto err_vids_add;
+ }
+
+ err = netdev_set_master(port_dev, dev);
+ if (err) {
+ netdev_err(dev, "Device %s failed to set master\n", portname);
+ goto err_set_master;
+ }
+
+ err = netdev_rx_handler_register(port_dev, team_handle_frame,
+ port);
+ if (err) {
+ netdev_err(dev, "Device %s failed to register rx_handler\n",
+ portname);
+ goto err_handler_register;
+ }
+
+ team_port_list_add_port(team, port);
+ team_adjust_ops(team);
+ __team_compute_features(team);
+ __team_port_change_check(port, !!netif_carrier_ok(port_dev));
+
+ netdev_info(dev, "Port device %s added\n", portname);
+
+ return 0;
+
+err_handler_register:
+ netdev_set_master(port_dev, NULL);
+
+err_set_master:
+ vlan_vids_del_by_dev(port_dev, dev);
+
+err_vids_add:
+ dev_close(port_dev);
+
+err_dev_open:
+ team_port_leave(team, port);
+ team_port_set_orig_mac(port);
+
+err_port_enter:
+ dev_set_mtu(port_dev, port->orig.mtu);
+
+err_set_mtu:
+ kfree(port);
+
+ return err;
+}
+
+static int team_port_del(struct team *team, struct net_device *port_dev)
+{
+ struct net_device *dev = team->dev;
+ struct team_port *port;
+ char *portname = port_dev->name;
+
+ port = team_port_get_rtnl(port_dev);
+ if (!port || !team_port_find(team, port)) {
+ netdev_err(dev, "Device %s does not act as a port of this team\n",
+ portname);
+ return -ENOENT;
+ }
+
+ __team_port_change_check(port, false);
+ team_port_list_del_port(team, port);
+ team_adjust_ops(team);
+ netdev_rx_handler_unregister(port_dev);
+ netdev_set_master(port_dev, NULL);
+ vlan_vids_del_by_dev(port_dev, dev);
+ dev_close(port_dev);
+ team_port_leave(team, port);
+ team_port_set_orig_mac(port);
+ dev_set_mtu(port_dev, port->orig.mtu);
+ synchronize_rcu();
+ kfree(port);
+ netdev_info(dev, "Port device %s removed\n", portname);
+ __team_compute_features(team);
+
+ return 0;
+}
+
+
+/*****************
+ * Net device ops
+ *****************/
+
+static const char team_no_mode_kind[] = "*NOMODE*";
+
+static int team_mode_option_get(struct team *team, void *arg)
+{
+ const char **str = arg;
+
+ *str = team->mode ? team->mode->kind : team_no_mode_kind;
+ return 0;
+}
+
+static int team_mode_option_set(struct team *team, void *arg)
+{
+ const char **str = arg;
+
+ return team_change_mode(team, *str);
+}
+
+static const struct team_option team_options[] = {
+ {
+ .name = "mode",
+ .type = TEAM_OPTION_TYPE_STRING,
+ .getter = team_mode_option_get,
+ .setter = team_mode_option_set,
+ },
+};
+
+static int team_init(struct net_device *dev)
+{
+ struct team *team = netdev_priv(dev);
+ int i;
+ int err;
+
+ team->dev = dev;
+ mutex_init(&team->lock);
+
+ team->pcpu_stats = alloc_percpu(struct team_pcpu_stats);
+ if (!team->pcpu_stats)
+ return -ENOMEM;
+
+ for (i = 0; i < TEAM_PORT_HASHENTRIES; i++)
+ INIT_HLIST_HEAD(&team->port_hlist[i]);
+ INIT_LIST_HEAD(&team->port_list);
+
+ team_adjust_ops(team);
+
+ INIT_LIST_HEAD(&team->option_list);
+ err = team_options_register(team, team_options, ARRAY_SIZE(team_options));
+ if (err)
+ goto err_options_register;
+ netif_carrier_off(dev);
+
+ return 0;
+
+err_options_register:
+ free_percpu(team->pcpu_stats);
+
+ return err;
+}
+
+static void team_uninit(struct net_device *dev)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+ struct team_port *tmp;
+
+ mutex_lock(&team->lock);
+ list_for_each_entry_safe(port, tmp, &team->port_list, list)
+ team_port_del(team, port->dev);
+
+ __team_change_mode(team, NULL); /* cleanup */
+ __team_options_unregister(team, team_options, ARRAY_SIZE(team_options));
+ mutex_unlock(&team->lock);
+}
+
+static void team_destructor(struct net_device *dev)
+{
+ struct team *team = netdev_priv(dev);
+
+ free_percpu(team->pcpu_stats);
+ free_netdev(dev);
+}
+
+static int team_open(struct net_device *dev)
+{
+ netif_carrier_on(dev);
+ return 0;
+}
+
+static int team_close(struct net_device *dev)
+{
+ netif_carrier_off(dev);
+ return 0;
+}
+
+/*
+ * note: already called with rcu_read_lock
+ */
+static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct team *team = netdev_priv(dev);
+ bool tx_success = false;
+ unsigned int len = skb->len;
+
+ tx_success = team->ops.transmit(team, skb);
+ if (tx_success) {
+ struct team_pcpu_stats *pcpu_stats;
+
+ pcpu_stats = this_cpu_ptr(team->pcpu_stats);
+ u64_stats_update_begin(&pcpu_stats->syncp);
+ pcpu_stats->tx_packets++;
+ pcpu_stats->tx_bytes += len;
+ u64_stats_update_end(&pcpu_stats->syncp);
+ } else {
+ this_cpu_inc(team->pcpu_stats->tx_dropped);
+ }
+
+ return NETDEV_TX_OK;
+}
+
+static void team_change_rx_flags(struct net_device *dev, int change)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+ int inc;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &team->port_list, list) {
+ if (change & IFF_PROMISC) {
+ inc = dev->flags & IFF_PROMISC ? 1 : -1;
+ dev_set_promiscuity(port->dev, inc);
+ }
+ if (change & IFF_ALLMULTI) {
+ inc = dev->flags & IFF_ALLMULTI ? 1 : -1;
+ dev_set_allmulti(port->dev, inc);
+ }
+ }
+ rcu_read_unlock();
+}
+
+static void team_set_rx_mode(struct net_device *dev)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &team->port_list, list) {
+ dev_uc_sync(port->dev, dev);
+ dev_mc_sync(port->dev, dev);
+ }
+ rcu_read_unlock();
+}
+
+static int team_set_mac_address(struct net_device *dev, void *p)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+ struct sockaddr *addr = p;
+
+ memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &team->port_list, list)
+ if (team->ops.port_change_mac)
+ team->ops.port_change_mac(team, port);
+ rcu_read_unlock();
+ return 0;
+}
+
+static int team_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+ int err;
+
+ /*
+ * Alhough this is reader, it's guarded by team lock. It's not possible
+ * to traverse list in reverse under rcu_read_lock
+ */
+ mutex_lock(&team->lock);
+ list_for_each_entry(port, &team->port_list, list) {
+ err = dev_set_mtu(port->dev, new_mtu);
+ if (err) {
+ netdev_err(dev, "Device %s failed to change mtu",
+ port->dev->name);
+ goto unwind;
+ }
+ }
+ mutex_unlock(&team->lock);
+
+ dev->mtu = new_mtu;
+
+ return 0;
+
+unwind:
+ list_for_each_entry_continue_reverse(port, &team->port_list, list)
+ dev_set_mtu(port->dev, dev->mtu);
+ mutex_unlock(&team->lock);
+
+ return err;
+}
+
+static struct rtnl_link_stats64 *
+team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_pcpu_stats *p;
+ u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
+ u32 rx_dropped = 0, tx_dropped = 0;
+ unsigned int start;
+ int i;
+
+ for_each_possible_cpu(i) {
+ p = per_cpu_ptr(team->pcpu_stats, i);
+ do {
+ start = u64_stats_fetch_begin_bh(&p->syncp);
+ rx_packets = p->rx_packets;
+ rx_bytes = p->rx_bytes;
+ rx_multicast = p->rx_multicast;
+ tx_packets = p->tx_packets;
+ tx_bytes = p->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->multicast += rx_multicast;
+ stats->tx_packets += tx_packets;
+ stats->tx_bytes += tx_bytes;
+ /*
+ * rx_dropped & tx_dropped are u32, updated
+ * without syncp protection.
+ */
+ rx_dropped += p->rx_dropped;
+ tx_dropped += p->tx_dropped;
+ }
+ stats->rx_dropped = rx_dropped;
+ stats->tx_dropped = tx_dropped;
+ return stats;
+}
+
+static int team_vlan_rx_add_vid(struct net_device *dev, uint16_t vid)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+ int err;
+
+ /*
+ * Alhough this is reader, it's guarded by team lock. It's not possible
+ * to traverse list in reverse under rcu_read_lock
+ */
+ mutex_lock(&team->lock);
+ list_for_each_entry(port, &team->port_list, list) {
+ err = vlan_vid_add(port->dev, vid);
+ if (err)
+ goto unwind;
+ }
+ mutex_unlock(&team->lock);
+
+ return 0;
+
+unwind:
+ list_for_each_entry_continue_reverse(port, &team->port_list, list)
+ vlan_vid_del(port->dev, vid);
+ mutex_unlock(&team->lock);
+
+ return err;
+}
+
+static int team_vlan_rx_kill_vid(struct net_device *dev, uint16_t vid)
+{
+ struct team *team = netdev_priv(dev);
+ struct team_port *port;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &team->port_list, list)
+ vlan_vid_del(port->dev, vid);
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
+{
+ struct team *team = netdev_priv(dev);
+ int err;
+
+ mutex_lock(&team->lock);
+ err = team_port_add(team, port_dev);
+ mutex_unlock(&team->lock);
+ return err;
+}
+
+static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
+{
+ struct team *team = netdev_priv(dev);
+ int err;
+
+ mutex_lock(&team->lock);
+ err = team_port_del(team, port_dev);
+ mutex_unlock(&team->lock);
+ return err;
+}
+
+static netdev_features_t team_fix_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct team_port *port;
+ struct team *team = netdev_priv(dev);
+ netdev_features_t mask;
+
+ mask = features;
+ features &= ~NETIF_F_ONE_FOR_ALL;
+ features |= NETIF_F_ALL_FOR_ALL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &team->port_list, list) {
+ features = netdev_increment_features(features,
+ port->dev->features,
+ mask);
+ }
+ rcu_read_unlock();
+ return features;
+}
+
+static const struct net_device_ops team_netdev_ops = {
+ .ndo_init = team_init,
+ .ndo_uninit = team_uninit,
+ .ndo_open = team_open,
+ .ndo_stop = team_close,
+ .ndo_start_xmit = team_xmit,
+ .ndo_change_rx_flags = team_change_rx_flags,
+ .ndo_set_rx_mode = team_set_rx_mode,
+ .ndo_set_mac_address = team_set_mac_address,
+ .ndo_change_mtu = team_change_mtu,
+ .ndo_get_stats64 = team_get_stats64,
+ .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid,
+ .ndo_add_slave = team_add_slave,
+ .ndo_del_slave = team_del_slave,
+ .ndo_fix_features = team_fix_features,
+};
+
+
+/***********************
+ * rt netlink interface
+ ***********************/
+
+static void team_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+
+ dev->netdev_ops = &team_netdev_ops;
+ dev->destructor = team_destructor;
+ dev->tx_queue_len = 0;
+ dev->flags |= IFF_MULTICAST;
+ dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+
+ /*
+ * Indicate we support unicast address filtering. That way core won't
+ * bring us to promisc mode in case a unicast addr is added.
+ * Let this up to underlay drivers.
+ */
+ dev->priv_flags |= IFF_UNICAST_FLT;
+
+ dev->features |= NETIF_F_LLTX;
+ dev->features |= NETIF_F_GRO;
+ dev->hw_features = NETIF_F_HW_VLAN_TX |
+ NETIF_F_HW_VLAN_RX |
+ NETIF_F_HW_VLAN_FILTER;
+
+ dev->features |= dev->hw_features;
+}
+
+static int team_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ int err;
+
+ if (tb[IFLA_ADDRESS] == NULL)
+ random_ether_addr(dev->dev_addr);
+
+ err = register_netdevice(dev);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int team_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ if (tb[IFLA_ADDRESS]) {
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ return -EINVAL;
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ return -EADDRNOTAVAIL;
+ }
+ return 0;
+}
+
+static struct rtnl_link_ops team_link_ops __read_mostly = {
+ .kind = DRV_NAME,
+ .priv_size = sizeof(struct team),
+ .setup = team_setup,
+ .newlink = team_newlink,
+ .validate = team_validate,
+};
+
+
+/***********************************
+ * Generic netlink custom interface
+ ***********************************/
+
+static struct genl_family team_nl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = TEAM_GENL_NAME,
+ .version = TEAM_GENL_VERSION,
+ .maxattr = TEAM_ATTR_MAX,
+ .netnsok = true,
+};
+
+static const struct nla_policy team_nl_policy[TEAM_ATTR_MAX + 1] = {
+ [TEAM_ATTR_UNSPEC] = { .type = NLA_UNSPEC, },
+ [TEAM_ATTR_TEAM_IFINDEX] = { .type = NLA_U32 },
+ [TEAM_ATTR_LIST_OPTION] = { .type = NLA_NESTED },
+ [TEAM_ATTR_LIST_PORT] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
+ [TEAM_ATTR_OPTION_UNSPEC] = { .type = NLA_UNSPEC, },
+ [TEAM_ATTR_OPTION_NAME] = {
+ .type = NLA_STRING,
+ .len = TEAM_STRING_MAX_LEN,
+ },
+ [TEAM_ATTR_OPTION_CHANGED] = { .type = NLA_FLAG },
+ [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 },
+ [TEAM_ATTR_OPTION_DATA] = {
+ .type = NLA_BINARY,
+ .len = TEAM_STRING_MAX_LEN,
+ },
+};
+
+static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
+{
+ struct sk_buff *msg;
+ void *hdr;
+ int err;
+
+ msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq,
+ &team_nl_family, 0, TEAM_CMD_NOOP);
+ if (IS_ERR(hdr)) {
+ err = PTR_ERR(hdr);
+ goto err_msg_put;
+ }
+
+ genlmsg_end(msg, hdr);
+
+ return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid);
+
+err_msg_put:
+ nlmsg_free(msg);
+
+ return err;
+}
+
+/*
+ * Netlink cmd functions should be locked by following two functions.
+ * Since dev gets held here, that ensures dev won't disappear in between.
+ */
+static struct team *team_nl_team_get(struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ int ifindex;
+ struct net_device *dev;
+ struct team *team;
+
+ if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX])
+ return NULL;
+
+ ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]);
+ dev = dev_get_by_index(net, ifindex);
+ if (!dev || dev->netdev_ops != &team_netdev_ops) {
+ if (dev)
+ dev_put(dev);
+ return NULL;
+ }
+
+ team = netdev_priv(dev);
+ mutex_lock(&team->lock);
+ return team;
+}
+
+static void team_nl_team_put(struct team *team)
+{
+ mutex_unlock(&team->lock);
+ dev_put(team->dev);
+}
+
+static int team_nl_send_generic(struct genl_info *info, struct team *team,
+ int (*fill_func)(struct sk_buff *skb,
+ struct genl_info *info,
+ int flags, struct team *team))
+{
+ struct sk_buff *skb;
+ int err;
+
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ err = fill_func(skb, info, NLM_F_ACK, team);
+ if (err < 0)
+ goto err_fill;
+
+ err = genlmsg_unicast(genl_info_net(info), skb, info->snd_pid);
+ return err;
+
+err_fill:
+ nlmsg_free(skb);
+ return err;
+}
+
+static int team_nl_fill_options_get_changed(struct sk_buff *skb,
+ u32 pid, u32 seq, int flags,
+ struct team *team,
+ struct team_option *changed_option)
+{
+ struct nlattr *option_list;
+ void *hdr;
+ struct team_option *option;
+
+ hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags,
+ TEAM_CMD_OPTIONS_GET);
+ if (IS_ERR(hdr))
+ return PTR_ERR(hdr);
+
+ NLA_PUT_U32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex);
+ option_list = nla_nest_start(skb, TEAM_ATTR_LIST_OPTION);
+ if (!option_list)
+ return -EMSGSIZE;
+
+ list_for_each_entry(option, &team->option_list, list) {
+ struct nlattr *option_item;
+ long arg;
+
+ option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION);
+ if (!option_item)
+ goto nla_put_failure;
+ NLA_PUT_STRING(skb, TEAM_ATTR_OPTION_NAME, option->name);
+ if (option == changed_option)
+ NLA_PUT_FLAG(skb, TEAM_ATTR_OPTION_CHANGED);
+ switch (option->type) {
+ case TEAM_OPTION_TYPE_U32:
+ NLA_PUT_U8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32);
+ team_option_get(team, option, &arg);
+ NLA_PUT_U32(skb, TEAM_ATTR_OPTION_DATA, arg);
+ break;
+ case TEAM_OPTION_TYPE_STRING:
+ NLA_PUT_U8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING);
+ team_option_get(team, option, &arg);
+ NLA_PUT_STRING(skb, TEAM_ATTR_OPTION_DATA,
+ (char *) arg);
+ break;
+ default:
+ BUG();
+ }
+ nla_nest_end(skb, option_item);
+ }
+
+ nla_nest_end(skb, option_list);
+ return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
+}
+
+static int team_nl_fill_options_get(struct sk_buff *skb,
+ struct genl_info *info, int flags,
+ struct team *team)
+{
+ return team_nl_fill_options_get_changed(skb, info->snd_pid,
+ info->snd_seq, NLM_F_ACK,
+ team, NULL);
+}
+
+static int team_nl_cmd_options_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct team *team;
+ int err;
+
+ team = team_nl_team_get(info);
+ if (!team)
+ return -EINVAL;
+
+ err = team_nl_send_generic(info, team, team_nl_fill_options_get);
+
+ team_nl_team_put(team);
+
+ return err;
+}
+
+static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
+{
+ struct team *team;
+ int err = 0;
+ int i;
+ struct nlattr *nl_option;
+
+ team = team_nl_team_get(info);
+ if (!team)
+ return -EINVAL;
+
+ err = -EINVAL;
+ if (!info->attrs[TEAM_ATTR_LIST_OPTION]) {
+ err = -EINVAL;
+ goto team_put;
+ }
+
+ nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) {
+ struct nlattr *mode_attrs[TEAM_ATTR_OPTION_MAX + 1];
+ enum team_option_type opt_type;
+ struct team_option *option;
+ char *opt_name;
+ bool opt_found = false;
+
+ if (nla_type(nl_option) != TEAM_ATTR_ITEM_OPTION) {
+ err = -EINVAL;
+ goto team_put;
+ }
+ err = nla_parse_nested(mode_attrs, TEAM_ATTR_OPTION_MAX,
+ nl_option, team_nl_option_policy);
+ if (err)
+ goto team_put;
+ if (!mode_attrs[TEAM_ATTR_OPTION_NAME] ||
+ !mode_attrs[TEAM_ATTR_OPTION_TYPE] ||
+ !mode_attrs[TEAM_ATTR_OPTION_DATA]) {
+ err = -EINVAL;
+ goto team_put;
+ }
+ switch (nla_get_u8(mode_attrs[TEAM_ATTR_OPTION_TYPE])) {
+ case NLA_U32:
+ opt_type = TEAM_OPTION_TYPE_U32;
+ break;
+ case NLA_STRING:
+ opt_type = TEAM_OPTION_TYPE_STRING;
+ break;
+ default:
+ goto team_put;
+ }
+
+ opt_name = nla_data(mode_attrs[TEAM_ATTR_OPTION_NAME]);
+ list_for_each_entry(option, &team->option_list, list) {
+ long arg;
+ struct nlattr *opt_data_attr;
+
+ if (option->type != opt_type ||
+ strcmp(option->name, opt_name))
+ continue;
+ opt_found = true;
+ opt_data_attr = mode_attrs[TEAM_ATTR_OPTION_DATA];
+ switch (opt_type) {
+ case TEAM_OPTION_TYPE_U32:
+ arg = nla_get_u32(opt_data_attr);
+ break;
+ case TEAM_OPTION_TYPE_STRING:
+ arg = (long) nla_data(opt_data_attr);
+ break;
+ default:
+ BUG();
+ }
+ err = team_option_set(team, option, &arg);
+ if (err)
+ goto team_put;
+ }
+ if (!opt_found) {
+ err = -ENOENT;
+ goto team_put;
+ }
+ }
+
+team_put:
+ team_nl_team_put(team);
+
+ return err;
+}
+
+static int team_nl_fill_port_list_get_changed(struct sk_buff *skb,
+ u32 pid, u32 seq, int flags,
+ struct team *team,
+ struct team_port *changed_port)
+{
+ struct nlattr *port_list;
+ void *hdr;
+ struct team_port *port;
+
+ hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags,
+ TEAM_CMD_PORT_LIST_GET);
+ if (IS_ERR(hdr))
+ return PTR_ERR(hdr);
+
+ NLA_PUT_U32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex);
+ port_list = nla_nest_start(skb, TEAM_ATTR_LIST_PORT);
+ if (!port_list)
+ return -EMSGSIZE;
+
+ list_for_each_entry(port, &team->port_list, list) {
+ struct nlattr *port_item;
+
+ port_item = nla_nest_start(skb, TEAM_ATTR_ITEM_PORT);
+ if (!port_item)
+ goto nla_put_failure;
+ NLA_PUT_U32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex);
+ if (port == changed_port)
+ NLA_PUT_FLAG(skb, TEAM_ATTR_PORT_CHANGED);
+ if (port->linkup)
+ NLA_PUT_FLAG(skb, TEAM_ATTR_PORT_LINKUP);
+ NLA_PUT_U32(skb, TEAM_ATTR_PORT_SPEED, port->speed);
+ NLA_PUT_U8(skb, TEAM_ATTR_PORT_DUPLEX, port->duplex);
+ nla_nest_end(skb, port_item);
+ }
+
+ nla_nest_end(skb, port_list);
+ return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
+}
+
+static int team_nl_fill_port_list_get(struct sk_buff *skb,
+ struct genl_info *info, int flags,
+ struct team *team)
+{
+ return team_nl_fill_port_list_get_changed(skb, info->snd_pid,
+ info->snd_seq, NLM_F_ACK,
+ team, NULL);
+}
+
+static int team_nl_cmd_port_list_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct team *team;
+ int err;
+
+ team = team_nl_team_get(info);
+ if (!team)
+ return -EINVAL;
+
+ err = team_nl_send_generic(info, team, team_nl_fill_port_list_get);
+
+ team_nl_team_put(team);
+
+ return err;
+}
+
+static struct genl_ops team_nl_ops[] = {
+ {
+ .cmd = TEAM_CMD_NOOP,
+ .doit = team_nl_cmd_noop,
+ .policy = team_nl_policy,
+ },
+ {
+ .cmd = TEAM_CMD_OPTIONS_SET,
+ .doit = team_nl_cmd_options_set,
+ .policy = team_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = TEAM_CMD_OPTIONS_GET,
+ .doit = team_nl_cmd_options_get,
+ .policy = team_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = TEAM_CMD_PORT_LIST_GET,
+ .doit = team_nl_cmd_port_list_get,
+ .policy = team_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static struct genl_multicast_group team_change_event_mcgrp = {
+ .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME,
+};
+
+static int team_nl_send_event_options_get(struct team *team,
+ struct team_option *changed_option)
+{
+ struct sk_buff *skb;
+ int err;
+ struct net *net = dev_net(team->dev);
+
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ err = team_nl_fill_options_get_changed(skb, 0, 0, 0, team,
+ changed_option);
+ if (err < 0)
+ goto err_fill;
+
+ err = genlmsg_multicast_netns(net, skb, 0, team_change_event_mcgrp.id,
+ GFP_KERNEL);
+ return err;
+
+err_fill:
+ nlmsg_free(skb);
+ return err;
+}
+
+static int team_nl_send_event_port_list_get(struct team_port *port)
+{
+ struct sk_buff *skb;
+ int err;
+ struct net *net = dev_net(port->team->dev);
+
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ err = team_nl_fill_port_list_get_changed(skb, 0, 0, 0,
+ port->team, port);
+ if (err < 0)
+ goto err_fill;
+
+ err = genlmsg_multicast_netns(net, skb, 0, team_change_event_mcgrp.id,
+ GFP_KERNEL);
+ return err;
+
+err_fill:
+ nlmsg_free(skb);
+ return err;
+}
+
+static int team_nl_init(void)
+{
+ int err;
+
+ err = genl_register_family_with_ops(&team_nl_family, team_nl_ops,
+ ARRAY_SIZE(team_nl_ops));
+ if (err)
+ return err;
+
+ err = genl_register_mc_group(&team_nl_family, &team_change_event_mcgrp);
+ if (err)
+ goto err_change_event_grp_reg;
+
+ return 0;
+
+err_change_event_grp_reg:
+ genl_unregister_family(&team_nl_family);
+
+ return err;
+}
+
+static void team_nl_fini(void)
+{
+ genl_unregister_family(&team_nl_family);
+}
+
+
+/******************
+ * Change checkers
+ ******************/
+
+static void __team_options_change_check(struct team *team,
+ struct team_option *changed_option)
+{
+ int err;
+
+ err = team_nl_send_event_options_get(team, changed_option);
+ if (err)
+ netdev_warn(team->dev, "Failed to send options change via netlink\n");
+}
+
+/* rtnl lock is held */
+static void __team_port_change_check(struct team_port *port, bool linkup)
+{
+ int err;
+
+ if (port->linkup == linkup)
+ return;
+
+ port->linkup = linkup;
+ if (linkup) {
+ struct ethtool_cmd ecmd;
+
+ err = __ethtool_get_settings(port->dev, &ecmd);
+ if (!err) {
+ port->speed = ethtool_cmd_speed(&ecmd);
+ port->duplex = ecmd.duplex;
+ goto send_event;
+ }
+ }
+ port->speed = 0;
+ port->duplex = 0;
+
+send_event:
+ err = team_nl_send_event_port_list_get(port);
+ if (err)
+ netdev_warn(port->team->dev, "Failed to send port change of device %s via netlink\n",
+ port->dev->name);
+
+}
+
+static void team_port_change_check(struct team_port *port, bool linkup)
+{
+ struct team *team = port->team;
+
+ mutex_lock(&team->lock);
+ __team_port_change_check(port, linkup);
+ mutex_unlock(&team->lock);
+}
+
+/************************************
+ * Net device notifier event handler
+ ************************************/
+
+static int team_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = (struct net_device *) ptr;
+ struct team_port *port;
+
+ port = team_port_get_rtnl(dev);
+ if (!port)
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ if (netif_carrier_ok(dev))
+ team_port_change_check(port, true);
+ case NETDEV_DOWN:
+ team_port_change_check(port, false);
+ case NETDEV_CHANGE:
+ if (netif_running(port->dev))
+ team_port_change_check(port,
+ !!netif_carrier_ok(port->dev));
+ break;
+ case NETDEV_UNREGISTER:
+ team_del_slave(port->team->dev, dev);
+ break;
+ case NETDEV_FEAT_CHANGE:
+ team_compute_features(port->team);
+ break;
+ case NETDEV_CHANGEMTU:
+ /* Forbid to change mtu of underlaying device */
+ return NOTIFY_BAD;
+ case NETDEV_PRE_TYPE_CHANGE:
+ /* Forbid to change type of underlaying device */
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block team_notifier_block __read_mostly = {
+ .notifier_call = team_device_event,
+};
+
+
+/***********************
+ * Module init and exit
+ ***********************/
+
+static int __init team_module_init(void)
+{
+ int err;
+
+ register_netdevice_notifier(&team_notifier_block);
+
+ err = rtnl_link_register(&team_link_ops);
+ if (err)
+ goto err_rtnl_reg;
+
+ err = team_nl_init();
+ if (err)
+ goto err_nl_init;
+
+ return 0;
+
+err_nl_init:
+ rtnl_link_unregister(&team_link_ops);
+
+err_rtnl_reg:
+ unregister_netdevice_notifier(&team_notifier_block);
+
+ return err;
+}
+
+static void __exit team_module_exit(void)
+{
+ team_nl_fini();
+ rtnl_link_unregister(&team_link_ops);
+ unregister_netdevice_notifier(&team_notifier_block);
+}
+
+module_init(team_module_init);
+module_exit(team_module_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Ethernet team device driver");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
--- /dev/null
+/*
+ * net/drivers/team/team_mode_activebackup.c - Active-backup mode for team
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <net/rtnetlink.h>
+#include <linux/if_team.h>
+
+struct ab_priv {
+ struct team_port __rcu *active_port;
+};
+
+static struct ab_priv *ab_priv(struct team *team)
+{
+ return (struct ab_priv *) &team->mode_priv;
+}
+
+static rx_handler_result_t ab_receive(struct team *team, struct team_port *port,
+ struct sk_buff *skb) {
+ struct team_port *active_port;
+
+ active_port = rcu_dereference(ab_priv(team)->active_port);
+ if (active_port != port)
+ return RX_HANDLER_EXACT;
+ return RX_HANDLER_ANOTHER;
+}
+
+static bool ab_transmit(struct team *team, struct sk_buff *skb)
+{
+ struct team_port *active_port;
+
+ active_port = rcu_dereference(ab_priv(team)->active_port);
+ if (unlikely(!active_port))
+ goto drop;
+ skb->dev = active_port->dev;
+ if (dev_queue_xmit(skb))
+ return false;
+ return true;
+
+drop:
+ dev_kfree_skb_any(skb);
+ return false;
+}
+
+static void ab_port_leave(struct team *team, struct team_port *port)
+{
+ if (ab_priv(team)->active_port == port)
+ RCU_INIT_POINTER(ab_priv(team)->active_port, NULL);
+}
+
+static int ab_active_port_get(struct team *team, void *arg)
+{
+ u32 *ifindex = arg;
+
+ *ifindex = 0;
+ if (ab_priv(team)->active_port)
+ *ifindex = ab_priv(team)->active_port->dev->ifindex;
+ return 0;
+}
+
+static int ab_active_port_set(struct team *team, void *arg)
+{
+ u32 *ifindex = arg;
+ struct team_port *port;
+
+ list_for_each_entry_rcu(port, &team->port_list, list) {
+ if (port->dev->ifindex == *ifindex) {
+ rcu_assign_pointer(ab_priv(team)->active_port, port);
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+static const struct team_option ab_options[] = {
+ {
+ .name = "activeport",
+ .type = TEAM_OPTION_TYPE_U32,
+ .getter = ab_active_port_get,
+ .setter = ab_active_port_set,
+ },
+};
+
+int ab_init(struct team *team)
+{
+ return team_options_register(team, ab_options, ARRAY_SIZE(ab_options));
+}
+
+void ab_exit(struct team *team)
+{
+ team_options_unregister(team, ab_options, ARRAY_SIZE(ab_options));
+}
+
+static const struct team_mode_ops ab_mode_ops = {
+ .init = ab_init,
+ .exit = ab_exit,
+ .receive = ab_receive,
+ .transmit = ab_transmit,
+ .port_leave = ab_port_leave,
+};
+
+static struct team_mode ab_mode = {
+ .kind = "activebackup",
+ .owner = THIS_MODULE,
+ .priv_size = sizeof(struct ab_priv),
+ .ops = &ab_mode_ops,
+};
+
+static int __init ab_init_module(void)
+{
+ return team_mode_register(&ab_mode);
+}
+
+static void __exit ab_cleanup_module(void)
+{
+ team_mode_unregister(&ab_mode);
+}
+
+module_init(ab_init_module);
+module_exit(ab_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Active-backup mode for team");
+MODULE_ALIAS("team-mode-activebackup");
--- /dev/null
+/*
+ * net/drivers/team/team_mode_roundrobin.c - Round-robin mode for team
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/if_team.h>
+
+struct rr_priv {
+ unsigned int sent_packets;
+};
+
+static struct rr_priv *rr_priv(struct team *team)
+{
+ return (struct rr_priv *) &team->mode_priv;
+}
+
+static struct team_port *__get_first_port_up(struct team *team,
+ struct team_port *port)
+{
+ struct team_port *cur;
+
+ if (port->linkup)
+ return port;
+ cur = port;
+ list_for_each_entry_continue_rcu(cur, &team->port_list, list)
+ if (cur->linkup)
+ return cur;
+ list_for_each_entry_rcu(cur, &team->port_list, list) {
+ if (cur == port)
+ break;
+ if (cur->linkup)
+ return cur;
+ }
+ return NULL;
+}
+
+static bool rr_transmit(struct team *team, struct sk_buff *skb)
+{
+ struct team_port *port;
+ int port_index;
+
+ port_index = rr_priv(team)->sent_packets++ % team->port_count;
+ port = team_get_port_by_index_rcu(team, port_index);
+ port = __get_first_port_up(team, port);
+ if (unlikely(!port))
+ goto drop;
+ skb->dev = port->dev;
+ if (dev_queue_xmit(skb))
+ return false;
+ return true;
+
+drop:
+ dev_kfree_skb_any(skb);
+ return false;
+}
+
+static int rr_port_enter(struct team *team, struct team_port *port)
+{
+ return team_port_set_team_mac(port);
+}
+
+static void rr_port_change_mac(struct team *team, struct team_port *port)
+{
+ team_port_set_team_mac(port);
+}
+
+static const struct team_mode_ops rr_mode_ops = {
+ .transmit = rr_transmit,
+ .port_enter = rr_port_enter,
+ .port_change_mac = rr_port_change_mac,
+};
+
+static struct team_mode rr_mode = {
+ .kind = "roundrobin",
+ .owner = THIS_MODULE,
+ .priv_size = sizeof(struct rr_priv),
+ .ops = &rr_mode_ops,
+};
+
+static int __init rr_init_module(void)
+{
+ return team_mode_register(&rr_mode);
+}
+
+static void __exit rr_cleanup_module(void)
+{
+ team_mode_unregister(&rr_mode);
+}
+
+module_init(rr_init_module);
+module_exit(rr_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Round-robin mode for team");
+MODULE_ALIAS("team-mode-roundrobin");
gid_t group;
struct net_device *dev;
- u32 set_features;
+ netdev_features_t set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
NETIF_F_TSO6|NETIF_F_UFO)
struct fasync_struct *fasync;
return 0;
}
-static u32 tun_net_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t tun_net_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct tun_struct *tun = netdev_priv(dev);
* privs required. */
static int set_offload(struct tun_struct *tun, unsigned long arg)
{
- u32 features = 0;
+ netdev_features_t features = 0;
if (arg & TUN_F_CSUM) {
features |= NETIF_F_HW_CSUM;
{
struct tun_struct *tun = netdev_priv(dev);
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
switch (tun->flags & TUN_TYPE_MASK) {
case TUN_TUN_DEV:
- strcpy(info->bus_info, "tun");
+ strlcpy(info->bus_info, "tun", sizeof(info->bus_info));
break;
case TUN_TAP_DEV:
- strcpy(info->bus_info, "tap");
+ strlcpy(info->bus_info, "tap", sizeof(info->bus_info));
break;
}
}
#include <linux/usb/usbnet.h>
#include <linux/slab.h>
-#define DRIVER_VERSION "26-Sep-2011"
+#define DRIVER_VERSION "22-Dec-2011"
#define DRIVER_NAME "asix"
/* ASIX AX8817X based USB 2.0 Ethernet Devices */
#define MARVELL_CTRL_TXDELAY 0x0002
#define MARVELL_CTRL_RXDELAY 0x0080
-#define PHY_MODE_RTL8211CL 0x0004
+#define PHY_MODE_RTL8211CL 0x000C
/* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */
struct asix_data {
{
int phy_reg;
u32 phy_id;
+ int i;
- phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
- if (phy_reg < 0)
+ /* Poll for the rare case the FW or phy isn't ready yet. */
+ for (i = 0; i < 100; i++) {
+ phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
+ if (phy_reg != 0 && phy_reg != 0xFFFF)
+ break;
+ mdelay(1);
+ }
+
+ if (phy_reg <= 0 || phy_reg == 0xFFFF)
return 0;
phy_id = (phy_reg & 0xffff) << 16;
}
wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
wolinfo->wolopts = 0;
+ if (opt & AX_MONITOR_LINK)
+ wolinfo->wolopts |= WAKE_PHY;
+ if (opt & AX_MONITOR_MAGIC)
+ wolinfo->wolopts |= WAKE_MAGIC;
}
static int
static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
{
- int ret;
+ int ret, embd_phy;
struct asix_data *data = (struct asix_data *)&dev->data;
u8 buf[ETH_ALEN];
u32 phyid;
dev->mii.reg_num_mask = 0x1f;
dev->mii.phy_id = asix_get_phy_addr(dev);
- phyid = asix_get_phyid(dev);
- dbg("PHYID=0x%08x", phyid);
-
dev->net->netdev_ops = &ax88772_netdev_ops;
dev->net->ethtool_ops = &ax88772_ethtool_ops;
- ret = ax88772_reset(dev);
+ embd_phy = ((dev->mii.phy_id & 0x1f) == 0x10 ? 1 : 0);
+
+ /* Reset the PHY to normal operation mode */
+ ret = asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+ if (ret < 0) {
+ dbg("Select PHY #1 failed: %d", ret);
+ return ret;
+ }
+
+ ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_PRL);
+ if (ret < 0)
+ return ret;
+
+ msleep(150);
+
+ ret = asix_sw_reset(dev, AX_SWRESET_CLEAR);
if (ret < 0)
return ret;
+ msleep(150);
+
+ ret = asix_sw_reset(dev, embd_phy ? AX_SWRESET_IPRL : AX_SWRESET_PRTE);
+
+ /* Read PHYID register *AFTER* the PHY was reset properly */
+ phyid = asix_get_phyid(dev);
+ dbg("PHYID=0x%08x", phyid);
+
/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
if (dev->driver_info->flags & FLAG_FRAMING_AX) {
/* hard_mtu is still the default - the device does not support
__le16 eeprom;
u8 status;
int gpio0 = 0;
+ u32 phyid;
asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status);
dbg("GPIO Status: 0x%04x", status);
data->ledmode = 0;
gpio0 = 1;
} else {
- data->phymode = le16_to_cpu(eeprom) & 7;
+ data->phymode = le16_to_cpu(eeprom) & 0x7F;
data->ledmode = le16_to_cpu(eeprom) >> 8;
gpio0 = (le16_to_cpu(eeprom) & 0x80) ? 0 : 1;
}
dbg("GPIO0: %d, PhyMode: %d", gpio0, data->phymode);
+ /* Power up external GigaPHY through AX88178 GPIO pin */
asix_write_gpio(dev, AX_GPIO_RSE | AX_GPIO_GPO_1 | AX_GPIO_GPO1EN, 40);
if ((le16_to_cpu(eeprom) >> 8) != 1) {
asix_write_gpio(dev, 0x003c, 30);
asix_write_gpio(dev, AX_GPIO_GPO1EN | AX_GPIO_GPO_1, 30);
}
+ /* Read PHYID register *AFTER* powering up PHY */
+ phyid = asix_get_phyid(dev);
+ dbg("PHYID=0x%08x", phyid);
+
+ /* Set AX88178 to enable MII/GMII/RGMII interface for external PHY */
+ asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, 0, 0, 0, NULL);
+
asix_sw_reset(dev, 0);
msleep(150);
{
int ret;
u8 buf[ETH_ALEN];
- u32 phyid;
struct asix_data *data = (struct asix_data *)&dev->data;
data->eeprom_len = AX88772_EEPROM_LEN;
dev->net->netdev_ops = &ax88178_netdev_ops;
dev->net->ethtool_ops = &ax88178_ethtool_ops;
- phyid = asix_get_phyid(dev);
- dbg("PHYID=0x%08x", phyid);
+ /* Blink LEDS so users know driver saw dongle */
+ asix_sw_reset(dev, 0);
+ msleep(150);
- ret = ax88178_reset(dev);
- if (ret < 0)
- return ret;
+ asix_sw_reset(dev, AX_SWRESET_PRL | AX_SWRESET_IPPD);
+ msleep(150);
/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
if (dev->driver_info->flags & FLAG_FRAMING_AX) {
// ASIX 88772a
USB_DEVICE(0x0db0, 0xa877),
.driver_info = (unsigned long) &ax88772_info,
+}, {
+ // Asus USB Ethernet Adapter
+ USB_DEVICE (0x0b95, 0x7e2b),
+ .driver_info = (unsigned long) &ax88772_info,
},
{ }, // END
};
struct page *page;
int err;
- page = __netdev_alloc_page(dev, gfp_flags);
+ page = alloc_page(gfp_flags);
if (!page)
return -ENOMEM;
err = usb_submit_urb(req, gfp_flags);
if (unlikely(err)) {
dev_dbg(&dev->dev, "RX submit error (%d)\n", err);
- netdev_free_page(dev, page);
+ put_page(page);
}
return err;
}
dev->stats.rx_errors++;
resubmit:
if (page)
- netdev_free_page(dev, page);
+ put_page(page);
if (req)
- rx_submit(pnd, req, GFP_ATOMIC);
+ rx_submit(pnd, req, GFP_ATOMIC | __GFP_COLD);
}
static int usbpn_close(struct net_device *dev);
for (i = 0; i < rxq_size; i++) {
struct urb *req = usb_alloc_urb(0, GFP_KERNEL);
- if (!req || rx_submit(pnd, req, GFP_KERNEL)) {
+ if (!req || rx_submit(pnd, req, GFP_KERNEL | __GFP_COLD)) {
usbpn_close(dev);
return -ENOMEM;
}
{
USB_DEVICE_AND_INTERFACE_INFO(0x1004, 0x61aa, USB_CLASS_COMM,
USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
- .driver_info = (unsigned long)&wwan_info,
+ .driver_info = 0,
},
/*
int temp;
u8 iface_no;
- ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx == NULL)
return -ENODEV;
- memset(ctx, 0, sizeof(*ctx));
-
init_timer(&ctx->tx_timer);
spin_lock_init(&ctx->mtx);
ctx->netdev = dev->net;
}
frame = (struct vl600_frame_hdr *) buf->data;
- /* NOTE: Should check that frame->magic == 0x53544448?
- * Otherwise if we receive garbage at the beginning of the frame
- * we may end up allocating a huge buffer and saving all the
- * future incoming data into it. */
+ /* Yes, check that frame->magic == 0x53544448 (or 0x44544d48),
+ * otherwise we may run out of memory w/a bad packet */
+ if (ntohl(frame->magic) != 0x53544448 &&
+ ntohl(frame->magic) != 0x44544d48)
+ goto error;
if (buf->len < sizeof(*frame) ||
buf->len != le32_to_cpup(&frame->len)) {
* overwrite the remaining fields.
*/
packet = (struct vl600_pkt_hdr *) skb->data;
+ /* The VL600 wants IPv6 packets to have an IPv4 ethertype
+ * Since this modem only supports IPv4 and IPv6, just set all
+ * frames to 0x0800 (ETH_P_IP)
+ */
+ packet->h_proto = htons(ETH_P_IP);
memset(&packet->dummy, 0, sizeof(packet->dummy));
packet->len = cpu_to_le32(orig_len);
if (skb->len < full_len) /* Pad */
skb_put(skb, full_len - skb->len);
- /* The VL600 wants IPv6 packets to have an IPv4 ethertype
- * Check if this is an IPv6 packet, and set the ethertype
- * to 0x800
- */
- if ((skb->data[sizeof(struct vl600_pkt_hdr *) + 0x22] & 0xf0) == 0x60) {
- skb->data[sizeof(struct vl600_pkt_hdr *) + 0x20] = 0x08;
- skb->data[sizeof(struct vl600_pkt_hdr *) + 0x21] = 0;
- }
-
return skb;
}
static const struct driver_info vl600_info = {
.description = "LG VL600 modem",
- .flags = FLAG_ETHER | FLAG_RX_ASSEMBLE,
+ .flags = FLAG_RX_ASSEMBLE | FLAG_WWAN,
.bind = vl600_bind,
.unbind = vl600_unbind,
.status = usbnet_cdc_status,
#define BMSR_MEDIA (BMSR_10HALF | BMSR_10FULL | BMSR_100HALF | \
BMSR_100FULL | BMSR_ANEGCAPABLE)
-static int loopback;
-static int mii_mode;
+static bool loopback;
+static bool mii_mode;
static char *devid;
static struct usb_eth_dev usb_dev_id[] = {
for (i = 0; i < REG_TIMEOUT; i++) {
get_registers(pegasus, EthCtrl1, 1, &data);
if (~data & 0x08) {
- if (loopback & 1)
+ if (loopback)
break;
if (mii_mode && (pegasus->features & HAS_HOME_PNA))
set_register(pegasus, Gpio1, 0x34);
data[1] |= 0x10; /* set 100 Mbps */
if (mii_mode)
data[1] = 0;
- data[2] = (loopback & 1) ? 0x09 : 0x01;
+ data[2] = loopback ? 0x09 : 0x01;
memcpy(pegasus->eth_regs, data, sizeof(data));
ret = set_registers(pegasus, EthCtrl0, 3, data);
#define USB_VENDOR_ID_SMSC (0x0424)
#define USB_PRODUCT_ID_LAN7500 (0x7500)
#define USB_PRODUCT_ID_LAN7505 (0x7505)
+#define RXW_PADDING 2
#define check_warn(ret, fmt, args...) \
({ if (ret < 0) netdev_warn(dev->net, fmt, ##args); })
struct usbnet *dev;
};
-static int turbo_mode = true;
+static bool turbo_mode = true;
module_param(turbo_mode, bool, 0644);
MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
}
/* Enable or disable Rx checksum offload engine */
-static int smsc75xx_set_features(struct net_device *netdev, u32 features)
+static int smsc75xx_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct usbnet *dev = netdev_priv(netdev);
struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
memcpy(&rx_cmd_b, skb->data, sizeof(rx_cmd_b));
le32_to_cpus(&rx_cmd_b);
- skb_pull(skb, 4 + NET_IP_ALIGN);
+ skb_pull(skb, 4 + RXW_PADDING);
packet = skb->data;
/* get the packet length */
- size = (rx_cmd_a & RX_CMD_A_LEN) - NET_IP_ALIGN;
- align_count = (4 - ((size + NET_IP_ALIGN) % 4)) % 4;
+ size = (rx_cmd_a & RX_CMD_A_LEN) - RXW_PADDING;
+ align_count = (4 - ((size + RXW_PADDING) % 4)) % 4;
if (unlikely(rx_cmd_a & RX_CMD_A_RED)) {
netif_dbg(dev, rx_err, dev->net,
struct usbnet *dev;
};
-static int turbo_mode = true;
+static bool turbo_mode = true;
module_param(turbo_mode, bool, 0644);
MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
}
/* Enable or disable Tx & Rx checksum offload engines */
-static int smsc95xx_set_features(struct net_device *netdev, u32 features)
+static int smsc95xx_set_features(struct net_device *netdev,
+ netdev_features_t features)
{
struct usbnet *dev = netdev_priv(netdev);
u32 read_buf;
struct veth_net_stats {
u64 rx_packets;
- u64 tx_packets;
u64 rx_bytes;
+ u64 tx_packets;
u64 tx_bytes;
u64 rx_dropped;
struct u64_stats_sync syncp;
static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
- strcpy(info->driver, DRV_NAME);
- strcpy(info->version, DRV_VERSION);
- strcpy(info->fw_version, "N/A");
+ strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
dev->features |= NETIF_F_LLTX;
dev->destructor = veth_dev_free;
- dev->hw_features = NETIF_F_NO_CSUM | NETIF_F_SG | NETIF_F_RXCSUM;
+ dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_RXCSUM;
}
/*
static int napi_weight = 128;
module_param(napi_weight, int, 0444);
-static int csum = 1, gso = 1;
+static bool csum = true, gso = true;
module_param(csum, bool, 0444);
module_param(gso, bool, 0444);
#define GOOD_COPY_LEN 128
#define VIRTNET_SEND_COMMAND_SG_MAX 2
+#define VIRTNET_DRIVER_VERSION "1.0.0"
struct virtnet_stats {
struct u64_stats_sync syncp;
return err;
}
-/* Returns false if we couldn't fill entirely (OOM). */
+/*
+ * Returns false if we couldn't fill entirely (OOM).
+ *
+ * Normally run in the receive path, but can also be run from ndo_open
+ * before we're receiving packets, or from refill_work which is
+ * careful to disable receiving (using napi_disable).
+ */
static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
{
int err;
/* In theory, this can happen: if we don't get any buffers in
* we will *never* try to fill again. */
if (still_empty)
- schedule_delayed_work(&vi->refill, HZ/2);
+ queue_delayed_work(system_nrt_wq, &vi->refill, HZ/2);
}
static int virtnet_poll(struct napi_struct *napi, int budget)
if (vi->num < vi->max / 2) {
if (!try_fill_recv(vi, GFP_ATOMIC))
- schedule_delayed_work(&vi->refill, 0);
+ queue_delayed_work(system_nrt_wq, &vi->refill, 0);
}
/* Out of packets? */
}
tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->rx_dropped = dev->stats.rx_dropped;
tot->rx_length_errors = dev->stats.rx_length_errors;
tot->rx_frame_errors = dev->stats.rx_frame_errors;
{
struct virtnet_info *vi = netdev_priv(dev);
+ /* Make sure we have some buffers: if oom use wq. */
+ if (!try_fill_recv(vi, GFP_KERNEL))
+ queue_delayed_work(system_nrt_wq, &vi->refill, 0);
+
virtnet_napi_enable(vi);
return 0;
}
{
struct virtnet_info *vi = netdev_priv(dev);
+ /* Make sure refill_work doesn't re-enable napi! */
+ cancel_delayed_work_sync(&vi->refill);
napi_disable(&vi->napi);
return 0;
kfree(buf);
}
-static void virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
+static int virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
{
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_ADD, &sg, 1, 0))
dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
+ return 0;
}
-static void virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
+static int virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
{
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_DEL, &sg, 1, 0))
dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
+ return 0;
}
static void virtnet_get_ringparam(struct net_device *dev,
}
+
+static void virtnet_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *info)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct virtio_device *vdev = vi->vdev;
+
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
+ strlcpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));
+
+}
+
static const struct ethtool_ops virtnet_ethtool_ops = {
+ .get_drvinfo = virtnet_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = virtnet_get_ringparam,
};
unregister:
unregister_netdev(dev);
- cancel_delayed_work_sync(&vi->refill);
free_vqs:
vdev->config->del_vqs(vdev);
free_stats:
/* Stop all the virtqueues. */
vdev->config->reset(vdev);
-
unregister_netdev(vi->dev);
- cancel_delayed_work_sync(&vi->refill);
/* Free unused buffers in both send and recv, if any. */
free_unused_bufs(vi);
}
-static void
+static int
vmxnet3_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
}
set_bit(vid, adapter->active_vlans);
+
+ return 0;
}
-static void
+static int
vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
}
clear_bit(vid, adapter->active_vlans);
+
+ return 0;
}
rssConf->indTableSize = VMXNET3_RSS_IND_TABLE_SIZE;
get_random_bytes(&rssConf->hashKey[0], rssConf->hashKeySize);
for (i = 0; i < rssConf->indTableSize; i++)
- rssConf->indTable[i] = i % adapter->num_rx_queues;
+ rssConf->indTable[i] = ethtool_rxfh_indir_default(
+ i, adapter->num_rx_queues);
devRead->rssConfDesc.confVer = 1;
devRead->rssConfDesc.confLen = sizeof(*rssConf);
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
strlcpy(drvinfo->driver, vmxnet3_driver_name, sizeof(drvinfo->driver));
- drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0';
strlcpy(drvinfo->version, VMXNET3_DRIVER_VERSION_REPORT,
sizeof(drvinfo->version));
- drvinfo->driver[sizeof(drvinfo->version) - 1] = '\0';
-
- strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
- drvinfo->fw_version[sizeof(drvinfo->fw_version) - 1] = '\0';
strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
ETHTOOL_BUSINFO_LEN);
}
}
-int vmxnet3_set_features(struct net_device *netdev, u32 features)
+int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
unsigned long flags;
- u32 changed = features ^ netdev->features;
+ netdev_features_t changed = features ^ netdev->features;
if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_HW_VLAN_RX)) {
if (features & NETIF_F_RXCSUM)
}
#ifdef VMXNET3_RSS
+static u32
+vmxnet3_get_rss_indir_size(struct net_device *netdev)
+{
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+ struct UPT1_RSSConf *rssConf = adapter->rss_conf;
+
+ return rssConf->indTableSize;
+}
+
static int
-vmxnet3_get_rss_indir(struct net_device *netdev,
- struct ethtool_rxfh_indir *p)
+vmxnet3_get_rss_indir(struct net_device *netdev, u32 *p)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
struct UPT1_RSSConf *rssConf = adapter->rss_conf;
- unsigned int n = min_t(unsigned int, p->size, rssConf->indTableSize);
+ unsigned int n = rssConf->indTableSize;
- p->size = rssConf->indTableSize;
while (n--)
- p->ring_index[n] = rssConf->indTable[n];
+ p[n] = rssConf->indTable[n];
return 0;
}
static int
-vmxnet3_set_rss_indir(struct net_device *netdev,
- const struct ethtool_rxfh_indir *p)
+vmxnet3_set_rss_indir(struct net_device *netdev, const u32 *p)
{
unsigned int i;
unsigned long flags;
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
struct UPT1_RSSConf *rssConf = adapter->rss_conf;
- if (p->size != rssConf->indTableSize)
- return -EINVAL;
- for (i = 0; i < rssConf->indTableSize; i++) {
- /*
- * Return with error code if any of the queue indices
- * is out of range
- */
- if (p->ring_index[i] < 0 ||
- p->ring_index[i] >= adapter->num_rx_queues)
- return -EINVAL;
- }
-
for (i = 0; i < rssConf->indTableSize; i++)
- rssConf->indTable[i] = p->ring_index[i];
+ rssConf->indTable[i] = p[i];
spin_lock_irqsave(&adapter->cmd_lock, flags);
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
.set_ringparam = vmxnet3_set_ringparam,
.get_rxnfc = vmxnet3_get_rxnfc,
#ifdef VMXNET3_RSS
+ .get_rxfh_indir_size = vmxnet3_get_rss_indir_size,
.get_rxfh_indir = vmxnet3_get_rss_indir,
.set_rxfh_indir = vmxnet3_set_rss_indir,
#endif
vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter);
int
-vmxnet3_set_features(struct net_device *netdev, u32 features);
+vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);
int
vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
static const char version[] =
"Granch SBNI12 driver ver 5.0.1 Jun 22 2001 Denis I.Timofeev.\n";
-static int skip_pci_probe __initdata = 0;
+static bool skip_pci_probe __initdata = false;
static int scandone __initdata = 0;
static int num __initdata = 0;
static int txdma=1;
static int rxdma=3;
static int irq=5;
-static int slow=0;
+static bool slow=false;
module_param(io, int, 0);
MODULE_PARM_DESC(io, "The I/O base of the Sealevel card");
{
struct device *dev = i2400m_dev(i2400m);
struct i2400m_msg_hdr *tx_msg;
- bool try_head = 0;
+ bool try_head = false;
BUG_ON(i2400m->tx_msg != NULL);
/*
* In certain situations, TX queue might have enough space to
else if (tx_msg == TAIL_FULL) {
i2400m_tx_skip_tail(i2400m);
d_printf(2, dev, "new TX message: tail full, trying head\n");
- try_head = 1;
+ try_head = true;
goto try_head;
}
memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
unsigned long flags;
size_t padded_len;
void *ptr;
- bool try_head = 0;
+ bool try_head = false;
unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
|| pl_type == I2400M_PT_RESET_COLD;
d_printf(2, dev, "pl append: tail full\n");
i2400m_tx_close(i2400m);
i2400m_tx_skip_tail(i2400m);
- try_head = 1;
+ try_head = true;
goto try_new;
} else if (ptr == NULL) { /* All full */
result = -ENOSPC;
static
int i2400mu_txd(void *_i2400mu)
{
- int result = 0;
struct i2400mu *i2400mu = _i2400mu;
struct i2400m *i2400m = &i2400mu->i2400m;
struct device *dev = &i2400mu->usb_iface->dev;
/* Yeah, we ignore errors ... not much we can do */
i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
i2400m_tx_msg_sent(i2400m); /* ack it, advance the FIFO */
- if (result < 0)
- break;
}
spin_lock_irqsave(&i2400m->tx_lock, flags);
i2400mu->tx_kthread = NULL;
spin_unlock_irqrestore(&i2400m->tx_lock, flags);
- d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
- return result;
+ d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+ return 0;
}
emmh32_update(&context->seed,frame->da,ETH_ALEN * 2); // DA,SA
emmh32_update(&context->seed,(u8*)&mic->typelen,10); // Type/Length and Snap
emmh32_update(&context->seed,(u8*)&mic->seq,sizeof(mic->seq)); //SEQ
- emmh32_update(&context->seed,frame->da + ETH_ALEN * 2,payLen); //payload
+ emmh32_update(&context->seed,(u8*)(frame + 1),payLen); //payload
emmh32_final(&context->seed, (u8*)&mic->mic);
/* New Type/length ?????????? */
emmh32_update(&context->seed, eth->da, ETH_ALEN*2);
emmh32_update(&context->seed, (u8 *)&mic->typelen, sizeof(mic->typelen)+sizeof(mic->u.snap));
emmh32_update(&context->seed, (u8 *)&mic->seq,sizeof(mic->seq));
- emmh32_update(&context->seed, eth->da + ETH_ALEN*2,payLen);
+ emmh32_update(&context->seed, (u8 *)(eth + 1),payLen);
//Calculate MIC
emmh32_final(&context->seed, digest);
*/
#define AR5K_KEYCACHE_SIZE 8
-extern int ath5k_modparam_nohwcrypt;
+extern bool ath5k_modparam_nohwcrypt;
/***********************\
HW RELATED DEFINITIONS
#define CREATE_TRACE_POINTS
#include "trace.h"
-int ath5k_modparam_nohwcrypt;
+bool ath5k_modparam_nohwcrypt;
module_param_named(nohwcrypt, ath5k_modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
-static int modparam_all_channels;
+static bool modparam_all_channels;
module_param_named(all_channels, modparam_all_channels, bool, S_IRUGO);
MODULE_PARM_DESC(all_channels, "Expose all channels the device can use.");
-static int modparam_fastchanswitch;
+static bool modparam_fastchanswitch;
module_param_named(fastchanswitch, modparam_fastchanswitch, bool, S_IRUGO);
MODULE_PARM_DESC(fastchanswitch, "Enable fast channel switching for AR2413/AR5413 radios.");
*/
if (fast && (ah->ah_radio != AR5K_RF2413) &&
(ah->ah_radio != AR5K_RF5413))
- fast = 0;
+ fast = false;
/* Disable sleep clock operation
* to avoid register access delay on certain
if (ret && fast) {
ATH5K_DBG(ah, ATH5K_DEBUG_RESET,
"DMA didn't stop, falling back to normal reset\n");
- fast = 0;
+ fast = false;
/* Non fatal, just continue with
* normal reset */
ret = 0;
ath6kl_dbg(ATH6KL_DBG_TRC, "failed to request P2P "
"capabilities (%d) - assuming P2P not "
"supported\n", ret);
- ar->p2p = 0;
+ ar->p2p = false;
}
}
if ((ah->hw_version.devid == AR9280_DEVID_PCI) &&
((eep->baseEepHeader.version & 0xff) > 0x0a) &&
(eep->baseEepHeader.pwdclkind == 0))
- ah->need_an_top2_fixup = 1;
+ ah->need_an_top2_fixup = true;
if ((common->bus_ops->ath_bus_type == ATH_USB) &&
(AR_SREV_9280(ah)))
struct ath_softc *sc = hw->priv;
struct ath_node *an = (struct ath_node *) sta->drv_priv;
+ if (!(sc->sc_flags & SC_OP_TXAGGR))
+ return;
+
switch (cmd) {
case STA_NOTIFY_SLEEP:
an->sleeping = true;
if (txq == sc->tx.txq_map[q] &&
++txq->pending_frames > ATH_MAX_QDEPTH && !txq->stopped) {
ieee80211_stop_queue(sc->hw, q);
- txq->stopped = 1;
+ txq->stopped = true;
}
ath_tx_start_dma(sc, skb, txctl);
if (txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) {
ieee80211_wake_queue(sc->hw, q);
- txq->stopped = 0;
+ txq->stopped = false;
}
}
#include "carl9170.h"
#include "cmd.h"
-static int modparam_nohwcrypt;
+static bool modparam_nohwcrypt;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware crypto offload.");
mutex_lock(&ar->mutex);
if (IS_ACCEPTING_CMD(ar)) {
- rcu_assign_pointer(ar->beacon_iter, NULL);
+ RCU_INIT_POINTER(ar->beacon_iter, NULL);
carl9170_led_set_state(ar, 0);
vif_priv->active = false;
bitmap_release_region(&ar->vif_bitmap, vif_id, 0);
ar->vifs--;
- rcu_assign_pointer(ar->vif_priv[vif_id].vif, NULL);
+ RCU_INIT_POINTER(ar->vif_priv[vif_id].vif, NULL);
list_del_rcu(&vif_priv->list);
mutex_unlock(&ar->mutex);
synchronize_rcu();
WARN_ON(vif_priv->enable_beacon);
vif_priv->enable_beacon = false;
list_del_rcu(&vif_priv->list);
- rcu_assign_pointer(ar->vif_priv[id].vif, NULL);
+ RCU_INIT_POINTER(ar->vif_priv[id].vif, NULL);
if (vif == main_vif) {
rcu_read_unlock();
}
for (i = 0; i < CARL9170_NUM_TID; i++)
- rcu_assign_pointer(sta_info->agg[i], NULL);
+ RCU_INIT_POINTER(sta_info->agg[i], NULL);
sta_info->ampdu_max_len = 1 << (3 + sta->ht_cap.ampdu_factor);
sta_info->ht_sta = true;
struct carl9170_sta_tid *tid_info;
tid_info = rcu_dereference(sta_info->agg[i]);
- rcu_assign_pointer(sta_info->agg[i], NULL);
+ RCU_INIT_POINTER(sta_info->agg[i], NULL);
if (!tid_info)
continue;
spin_unlock_bh(&ar->tx_ampdu_list_lock);
}
- rcu_assign_pointer(sta_info->agg[tid], NULL);
+ RCU_INIT_POINTER(sta_info->agg[tid], NULL);
rcu_read_unlock();
ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
else
ring->ops = &dma32_ops;
if (for_tx) {
- ring->tx = 1;
+ ring->tx = true;
ring->current_slot = -1;
} else {
if (ring->index == 0) {
static int b43_dma_set_mask(struct b43_wldev *dev, u64 mask)
{
u64 orig_mask = mask;
- bool fallback = 0;
+ bool fallback = false;
int err;
/* Try to set the DMA mask. If it fails, try falling back to a
}
if (mask == DMA_BIT_MASK(64)) {
mask = DMA_BIT_MASK(32);
- fallback = 1;
+ fallback = true;
continue;
}
if (mask == DMA_BIT_MASK(32)) {
mask = DMA_BIT_MASK(30);
- fallback = 1;
+ fallback = true;
continue;
}
b43err(dev->wl, "The machine/kernel does not support "
memset(meta, 0, sizeof(*meta));
meta->skb = skb;
- meta->is_last_fragment = 1;
+ meta->is_last_fragment = true;
priv_info->bouncebuffer = NULL;
meta->dmaaddr = map_descbuffer(ring, skb->data, skb->len, 1);
unsigned int skb_mapping = skb_get_queue_mapping(skb);
ieee80211_stop_queue(dev->wl->hw, skb_mapping);
dev->wl->tx_queue_stopped[skb_mapping] = 1;
- ring->stopped = 1;
+ ring->stopped = true;
if (b43_debug(dev, B43_DBG_DMAVERBOSE)) {
b43dbg(dev->wl, "Stopped TX ring %d\n", ring->index);
}
}
if (ring->stopped) {
B43_WARN_ON(free_slots(ring) < TX_SLOTS_PER_FRAME);
- ring->stopped = 0;
+ ring->stopped = false;
}
if (dev->wl->tx_queue_stopped[ring->queue_prio]) {
if (radio_enabled)
turn_on = atomic_read(&led->state) != LED_OFF;
else
- turn_on = 0;
+ turn_on = false;
if (turn_on == led->hw_state)
return;
led->hw_state = turn_on;
if (sprom[led_index] == 0xFF) {
/* There is no LED information in the SPROM
* for this LED. Hardcode it here. */
- *activelow = 0;
+ *activelow = false;
switch (led_index) {
case 0:
*behaviour = B43_LED_ACTIVITY;
- *activelow = 1;
+ *activelow = true;
if (dev->dev->board_vendor == PCI_VENDOR_ID_COMPAQ)
*behaviour = B43_LED_RADIO_ALL;
break;
if (led->wl) {
if (dev->phy.radio_on && b43_is_hw_radio_enabled(dev)) {
b43_led_turn_on(dev, led->index, led->activelow);
- led->hw_state = 1;
+ led->hw_state = true;
atomic_set(&led->state, 1);
} else {
b43_led_turn_off(dev, led->index, led->activelow);
- led->hw_state = 0;
+ led->hw_state = false;
atomic_set(&led->state, 0);
}
}
led = &dev->wl->leds.led_tx;
if (led->wl) {
b43_led_turn_off(dev, led->index, led->activelow);
- led->hw_state = 0;
+ led->hw_state = false;
atomic_set(&led->state, 0);
}
led = &dev->wl->leds.led_rx;
if (led->wl) {
b43_led_turn_off(dev, led->index, led->activelow);
- led->hw_state = 0;
+ led->hw_state = false;
atomic_set(&led->state, 0);
}
led = &dev->wl->leds.led_assoc;
if (led->wl) {
b43_led_turn_off(dev, led->index, led->activelow);
- led->hw_state = 0;
+ led->hw_state = false;
atomic_set(&led->state, 0);
}
const struct b43_rfatt *rfatt;
const struct b43_bbatt *bbatt;
u64 power_vector;
- bool table_changed = 0;
+ bool table_changed = false;
BUILD_BUG_ON(B43_DC_LT_SIZE != 32);
B43_WARN_ON(lo->rfatt_list.len * lo->bbatt_list.len > 64);
lo->dc_lt[idx] = (lo->dc_lt[idx] & 0xFF00)
| (val & 0x00FF);
}
- table_changed = 1;
+ table_changed = true;
}
if (table_changed) {
/* The table changed in memory. Update the hardware table. */
unsigned long now;
unsigned long expire;
struct b43_lo_calib *cal, *tmp;
- bool current_item_expired = 0;
+ bool current_item_expired = false;
bool hwpctl;
if (!lo)
if (b43_compare_bbatt(&cal->bbatt, &gphy->bbatt) &&
b43_compare_rfatt(&cal->rfatt, &gphy->rfatt)) {
B43_WARN_ON(current_item_expired);
- current_item_expired = 1;
+ current_item_expired = true;
}
if (b43_debug(dev, B43_DBG_LO)) {
b43dbg(dev->wl, "LO: Item BB(%u), RF(%u,%u), "
B43_WARN_ON((ps_flags & B43_PS_AWAKE) && (ps_flags & B43_PS_ASLEEP));
if (ps_flags & B43_PS_ENABLED) {
- hwps = 1;
+ hwps = true;
} else if (ps_flags & B43_PS_DISABLED) {
- hwps = 0;
+ hwps = false;
} else {
//TODO: If powersave is not off and FIXME is not set and we are not in adhoc
// and thus is not an AP and we are associated, set bit 25
}
if (ps_flags & B43_PS_AWAKE) {
- awake = 1;
+ awake = true;
} else if (ps_flags & B43_PS_ASLEEP) {
- awake = 0;
+ awake = false;
} else {
//TODO: If the device is awake or this is an AP, or we are scanning, or FIXME,
// or we are associated, or FIXME, or the latest PS-Poll packet sent was
}
/* FIXME: For now we force awake-on and hwps-off */
- hwps = 0;
- awake = 1;
+ hwps = false;
+ awake = true;
macctl = b43_read32(dev, B43_MMIO_MACCTL);
if (hwps)
return;
if (dev->noisecalc.calculation_running)
return;
- dev->noisecalc.calculation_running = 1;
+ dev->noisecalc.calculation_running = true;
dev->noisecalc.nr_samples = 0;
b43_generate_noise_sample(dev);
average -= 48;
dev->stats.link_noise = average;
- dev->noisecalc.calculation_running = 0;
+ dev->noisecalc.calculation_running = false;
return;
}
generate_new:
b43_power_saving_ctl_bits(dev, 0);
}
if (b43_is_mode(dev->wl, NL80211_IFTYPE_ADHOC))
- dev->dfq_valid = 1;
+ dev->dfq_valid = true;
}
static void handle_irq_atim_end(struct b43_wldev *dev)
b43_write32(dev, B43_MMIO_MACCMD,
b43_read32(dev, B43_MMIO_MACCMD)
| B43_MACCMD_DFQ_VALID);
- dev->dfq_valid = 0;
+ dev->dfq_valid = false;
}
}
unsigned int i, len, variable_len;
const struct ieee80211_mgmt *bcn;
const u8 *ie;
- bool tim_found = 0;
+ bool tim_found = false;
unsigned int rate;
u16 ctl;
int antenna;
/* A valid TIM is at least 4 bytes long. */
if (ie_len < 4)
break;
- tim_found = 1;
+ tim_found = true;
tim_position = sizeof(struct b43_plcp_hdr6);
tim_position += offsetof(struct ieee80211_mgmt, u.beacon.variable);
if (wl->beacon0_uploaded)
return;
b43_write_beacon_template(dev, 0x68, 0x18);
- wl->beacon0_uploaded = 1;
+ wl->beacon0_uploaded = true;
}
static void b43_upload_beacon1(struct b43_wldev *dev)
if (wl->beacon1_uploaded)
return;
b43_write_beacon_template(dev, 0x468, 0x1A);
- wl->beacon1_uploaded = 1;
+ wl->beacon1_uploaded = true;
}
static void handle_irq_beacon(struct b43_wldev *dev)
if (unlikely(wl->beacon_templates_virgin)) {
/* We never uploaded a beacon before.
* Upload both templates now, but only mark one valid. */
- wl->beacon_templates_virgin = 0;
+ wl->beacon_templates_virgin = false;
b43_upload_beacon0(dev);
b43_upload_beacon1(dev);
cmd = b43_read32(dev, B43_MMIO_MACCMD);
if (wl->current_beacon)
dev_kfree_skb_any(wl->current_beacon);
wl->current_beacon = beacon;
- wl->beacon0_uploaded = 0;
- wl->beacon1_uploaded = 0;
+ wl->beacon0_uploaded = false;
+ wl->beacon1_uploaded = false;
ieee80211_queue_work(wl->hw, &wl->beacon_update_trigger);
}
b43err(dev->wl, "This device does not support DMA "
"on your system. It will now be switched to PIO.\n");
/* Fall back to PIO transfers if we get fatal DMA errors! */
- dev->use_pio = 1;
+ dev->use_pio = true;
b43_controller_restart(dev, "DMA error");
return;
}
filename = NULL;
else
goto err_no_pcm;
- fw->pcm_request_failed = 0;
+ fw->pcm_request_failed = false;
err = b43_do_request_fw(ctx, filename, &fw->pcm);
if (err == -ENOENT) {
/* We did not find a PCM file? Not fatal, but
* core rev <= 10 must do without hwcrypto then. */
- fw->pcm_request_failed = 1;
+ fw->pcm_request_failed = true;
} else if (err)
goto err_load;
dev->wl->hw->queues = dev->wl->mac80211_initially_registered_queues;
dev->qos_enabled = !!modparam_qos;
/* Default to firmware/hardware crypto acceleration. */
- dev->hwcrypto_enabled = 1;
+ dev->hwcrypto_enabled = true;
if (dev->fw.opensource) {
u16 fwcapa;
if (!(fwcapa & B43_FWCAPA_HWCRYPTO) || dev->fw.pcm_request_failed) {
b43info(dev->wl, "Hardware crypto acceleration not supported by firmware\n");
/* Disable hardware crypto and fall back to software crypto. */
- dev->hwcrypto_enabled = 0;
+ dev->hwcrypto_enabled = false;
}
if (!(fwcapa & B43_FWCAPA_QOS)) {
b43info(dev->wl, "QoS not supported by firmware\n");
* ieee80211_unregister to make sure the networking core can
* properly free possible resources. */
dev->wl->hw->queues = 1;
- dev->qos_enabled = 0;
+ dev->qos_enabled = false;
}
} else {
b43info(dev->wl, "Loading firmware version %u.%u "
wl->rng.name = wl->rng_name;
wl->rng.data_read = b43_rng_read;
wl->rng.priv = (unsigned long)wl;
- wl->rng_initialized = 1;
+ wl->rng_initialized = true;
err = hwrng_register(&wl->rng);
if (err) {
- wl->rng_initialized = 0;
+ wl->rng_initialized = false;
b43err(wl, "Failed to register the random "
"number generator (%d)\n", err);
}
case IEEE80211_BAND_5GHZ:
if (d->phy.supports_5ghz) {
up_dev = d;
- gmode = 0;
+ gmode = false;
}
break;
case IEEE80211_BAND_2GHZ:
if (d->phy.supports_2ghz) {
up_dev = d;
- gmode = 1;
+ gmode = true;
}
break;
default:
atomic_set(&phy->txerr_cnt, B43_PHY_TX_BADNESS_LIMIT);
#if B43_DEBUG
- phy->phy_locked = 0;
- phy->radio_locked = 0;
+ phy->phy_locked = false;
+ phy->radio_locked = false;
#endif
}
static void setup_struct_wldev_for_init(struct b43_wldev *dev)
{
- dev->dfq_valid = 0;
+ dev->dfq_valid = false;
/* Assume the radio is enabled. If it's not enabled, the state will
* immediately get fixed on the first periodic work run. */
- dev->radio_hw_enable = 1;
+ dev->radio_hw_enable = true;
/* Stats */
memset(&dev->stats, 0, sizeof(dev->stats));
if (b43_bus_host_is_pcmcia(dev->dev) ||
b43_bus_host_is_sdio(dev->dev)) {
- dev->__using_pio_transfers = 1;
+ dev->__using_pio_transfers = true;
err = b43_pio_init(dev);
} else if (dev->use_pio) {
b43warn(dev->wl, "Forced PIO by use_pio module parameter. "
"This should not be needed and will result in lower "
"performance.\n");
- dev->__using_pio_transfers = 1;
+ dev->__using_pio_transfers = true;
err = b43_pio_init(dev);
} else {
- dev->__using_pio_transfers = 0;
+ dev->__using_pio_transfers = false;
err = b43_dma_init(dev);
}
if (err)
b43dbg(wl, "Adding Interface type %d\n", vif->type);
dev = wl->current_dev;
- wl->operating = 1;
+ wl->operating = true;
wl->vif = vif;
wl->if_type = vif->type;
memcpy(wl->mac_addr, vif->addr, ETH_ALEN);
B43_WARN_ON(wl->vif != vif);
wl->vif = NULL;
- wl->operating = 0;
+ wl->operating = false;
b43_adjust_opmode(dev);
memset(wl->mac_addr, 0, ETH_ALEN);
memset(wl->bssid, 0, ETH_ALEN);
memset(wl->mac_addr, 0, ETH_ALEN);
wl->filter_flags = 0;
- wl->radiotap_enabled = 0;
+ wl->radiotap_enabled = false;
b43_qos_clear(wl);
- wl->beacon0_uploaded = 0;
- wl->beacon1_uploaded = 0;
- wl->beacon_templates_virgin = 1;
- wl->radio_enabled = 1;
+ wl->beacon0_uploaded = false;
+ wl->beacon1_uploaded = false;
+ wl->beacon_templates_virgin = true;
+ wl->radio_enabled = true;
mutex_lock(&wl->mutex);
goto out_unlock;
}
b43_wireless_core_exit(dev);
- wl->radio_enabled = 0;
+ wl->radio_enabled = false;
out_unlock:
mutex_unlock(&wl->mutex);
struct pci_dev *pdev = NULL;
int err;
u32 tmp;
- bool have_2ghz_phy = 0, have_5ghz_phy = 0;
+ bool have_2ghz_phy = false, have_5ghz_phy = false;
/* Do NOT do any device initialization here.
* Do it in wireless_core_init() instead.
}
dev->phy.gmode = have_2ghz_phy;
- dev->phy.radio_on = 1;
+ dev->phy.radio_on = true;
b43_wireless_core_reset(dev, dev->phy.gmode);
err = b43_phy_versioning(dev);
(pdev->device != 0x4312 &&
pdev->device != 0x4319 && pdev->device != 0x4324)) {
/* No multiband support. */
- have_2ghz_phy = 0;
- have_5ghz_phy = 0;
+ have_2ghz_phy = false;
+ have_5ghz_phy = false;
switch (dev->phy.type) {
case B43_PHYTYPE_A:
- have_5ghz_phy = 1;
+ have_5ghz_phy = true;
break;
case B43_PHYTYPE_LP: //FIXME not always!
#if 0 //FIXME enabling 5GHz causes a NULL pointer dereference
case B43_PHYTYPE_N:
case B43_PHYTYPE_HT:
case B43_PHYTYPE_LCN:
- have_2ghz_phy = 1;
+ have_2ghz_phy = true;
break;
default:
B43_WARN_ON(1);
/* FIXME: For now we disable the A-PHY on multi-PHY devices. */
if (dev->phy.type != B43_PHYTYPE_N &&
dev->phy.type != B43_PHYTYPE_LP) {
- have_2ghz_phy = 1;
- have_5ghz_phy = 0;
+ have_2ghz_phy = true;
+ have_5ghz_phy = false;
}
}
#if B43_DEBUG
B43_WARN_ON(dev->phy.radio_locked);
- dev->phy.radio_locked = 1;
+ dev->phy.radio_locked = true;
#endif
macctl = b43_read32(dev, B43_MMIO_MACCTL);
#if B43_DEBUG
B43_WARN_ON(!dev->phy.radio_locked);
- dev->phy.radio_locked = 0;
+ dev->phy.radio_locked = false;
#endif
/* Commit any write */
{
#if B43_DEBUG
B43_WARN_ON(dev->phy.phy_locked);
- dev->phy.phy_locked = 1;
+ dev->phy.phy_locked = true;
#endif
B43_WARN_ON(dev->dev->core_rev < 3);
{
#if B43_DEBUG
B43_WARN_ON(!dev->phy.phy_locked);
- dev->phy.phy_locked = 0;
+ dev->phy.phy_locked = false;
#endif
B43_WARN_ON(dev->dev->core_rev < 3);
if (b43_phy_read(dev, 0x0033) & 0x0800)
break;
- gphy->aci_enable = 1;
+ gphy->aci_enable = true;
phy_stacksave(B43_PHY_RADIO_BITFIELD);
phy_stacksave(B43_PHY_G_CRS);
if (!(b43_phy_read(dev, 0x0033) & 0x0800))
break;
- gphy->aci_enable = 0;
+ gphy->aci_enable = false;
phy_stackrestore(B43_PHY_RADIO_BITFIELD);
phy_stackrestore(B43_PHY_G_CRS);
bbatt.att = 11;
if (phy->radio_rev == 8) {
rfatt.att = 15;
- rfatt.with_padmix = 1;
+ rfatt.with_padmix = true;
} else {
rfatt.att = 9;
- rfatt.with_padmix = 0;
+ rfatt.with_padmix = false;
}
b43_set_txpower_g(dev, &bbatt, &rfatt, 0);
}
struct b43_bus_dev *bdev = dev->dev;
struct b43_phy *phy = &dev->phy;
- rf->with_padmix = 0;
+ rf->with_padmix = false;
if (dev->dev->board_vendor == SSB_BOARDVENDOR_BCM &&
dev->dev->board_type == SSB_BOARD_BCM4309G) {
return;
case 8:
rf->att = 0xA;
- rf->with_padmix = 1;
+ rf->with_padmix = true;
return;
case 9:
default:
B43_WARN_ON((dev->dev->chip_id == 0x4301) &&
(phy->radio_ver != 0x2050)); /* Not supported anymore */
- gphy->dyn_tssi_tbl = 0;
+ gphy->dyn_tssi_tbl = false;
if (pab0 != 0 && pab1 != 0 && pab2 != 0 &&
pab0 != -1 && pab1 != -1 && pab2 != -1) {
pab1, pab2);
if (!gphy->tssi2dbm)
return -ENOMEM;
- gphy->dyn_tssi_tbl = 1;
+ gphy->dyn_tssi_tbl = true;
} else {
/* pabX values not set in SPROM. */
gphy->tgt_idle_tssi = 52;
if (gphy->dyn_tssi_tbl)
kfree(gphy->tssi2dbm);
- gphy->dyn_tssi_tbl = 0;
+ gphy->dyn_tssi_tbl = false;
gphy->tssi2dbm = NULL;
kfree(gphy);
if (phy->rev == 1) {
/* Workaround: Temporarly disable gmode through the early init
* phase, as the gmode stuff is not needed for phy rev 1 */
- phy->gmode = 0;
+ phy->gmode = false;
b43_wireless_core_reset(dev, 0);
b43_phy_initg(dev);
- phy->gmode = 1;
+ phy->gmode = true;
b43_wireless_core_reset(dev, 1);
}
gphy->radio_off_context.rfover);
b43_phy_write(dev, B43_PHY_RFOVERVAL,
gphy->radio_off_context.rfoverval);
- gphy->radio_off_context.valid = 0;
+ gphy->radio_off_context.valid = false;
}
channel = phy->channel;
b43_gphy_channel_switch(dev, 6, 1);
rfoverval = b43_phy_read(dev, B43_PHY_RFOVERVAL);
gphy->radio_off_context.rfover = rfover;
gphy->radio_off_context.rfoverval = rfoverval;
- gphy->radio_off_context.valid = 1;
+ gphy->radio_off_context.valid = true;
b43_phy_write(dev, B43_PHY_RFOVER, rfover | 0x008C);
b43_phy_write(dev, B43_PHY_RFOVERVAL, rfoverval & 0xFF73);
}
if ((phy->rev == 0) || (!phy->gmode))
return -ENODEV;
- gphy->aci_wlan_automatic = 0;
+ gphy->aci_wlan_automatic = false;
switch (mode) {
case B43_INTERFMODE_AUTOWLAN:
- gphy->aci_wlan_automatic = 1;
+ gphy->aci_wlan_automatic = true;
if (gphy->aci_enable)
mode = B43_INTERFMODE_MANUALWLAN;
else
b43_radio_interference_mitigation_disable(dev, currentmode);
if (mode == B43_INTERFMODE_NONE) {
- gphy->aci_enable = 0;
- gphy->aci_hw_rssi = 0;
+ gphy->aci_enable = false;
+ gphy->aci_hw_rssi = false;
} else
b43_radio_interference_mitigation_enable(dev, mode);
gphy->interfmode = mode;
struct b43_phy_lp *lpphy = dev->phy.lp;
if (user)
- lpphy->crs_usr_disable = 1;
+ lpphy->crs_usr_disable = true;
else
- lpphy->crs_sys_disable = 1;
+ lpphy->crs_sys_disable = true;
b43_phy_maskset(dev, B43_LPPHY_CRSGAIN_CTL, 0xFF1F, 0x80);
}
struct b43_phy_lp *lpphy = dev->phy.lp;
if (user)
- lpphy->crs_usr_disable = 0;
+ lpphy->crs_usr_disable = false;
else
- lpphy->crs_sys_disable = 0;
+ lpphy->crs_sys_disable = false;
if (!lpphy->crs_usr_disable && !lpphy->crs_sys_disable) {
if (b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ)
if (dev->phy.rev >= 4) {
avoid = nphy->hang_avoid;
- nphy->hang_avoid = 0;
+ nphy->hang_avoid = false;
}
b43_ntab_read_bulk(dev, B43_NTAB16(7, 0x110), 2, save);
if (phy6or5x && updated[core] == 0) {
b43_nphy_update_tx_cal_ladder(dev, core);
- updated[core] = 1;
+ updated[core] = true;
}
tmp = (params[core].ncorr[type] << 8) | 0x66;
/* Not enough memory on the queue. */
err = -EBUSY;
ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb));
- q->stopped = 1;
+ q->stopped = true;
goto out;
}
(q->free_packet_slots == 0)) {
/* The queue is full. */
ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb));
- q->stopped = 1;
+ q->stopped = true;
}
out:
if (q->stopped) {
ieee80211_wake_queue(dev->wl->hw, q->queue_prio);
- q->stopped = 0;
+ q->stopped = false;
}
}
const char *err_msg = NULL;
struct b43_rxhdr_fw4 *rxhdr =
(struct b43_rxhdr_fw4 *)wl->pio_scratchspace;
+ size_t rxhdr_size = sizeof(*rxhdr);
BUILD_BUG_ON(sizeof(wl->pio_scratchspace) < sizeof(*rxhdr));
- memset(rxhdr, 0, sizeof(*rxhdr));
+ switch (dev->fw.hdr_format) {
+ case B43_FW_HDR_410:
+ case B43_FW_HDR_351:
+ rxhdr_size -= sizeof(rxhdr->format_598) -
+ sizeof(rxhdr->format_351);
+ break;
+ case B43_FW_HDR_598:
+ break;
+ }
+ memset(rxhdr, 0, rxhdr_size);
/* Check if we have data and wait for it to get ready. */
if (q->rev >= 8) {
/* Get the preamble (RX header) */
if (q->rev >= 8) {
- b43_block_read(dev, rxhdr, sizeof(*rxhdr),
+ b43_block_read(dev, rxhdr, rxhdr_size,
q->mmio_base + B43_PIO8_RXDATA,
sizeof(u32));
} else {
- b43_block_read(dev, rxhdr, sizeof(*rxhdr),
+ b43_block_read(dev, rxhdr, rxhdr_size,
q->mmio_base + B43_PIO_RXDATA,
sizeof(u16));
}
struct ieee80211_tx_info *report,
const struct b43_txstatus *status)
{
- bool frame_success = 1;
+ bool frame_success = true;
int retry_limit;
/* preserve the confiured retry limit before clearing the status
/* The frame was not ACKed... */
if (!(report->flags & IEEE80211_TX_CTL_NO_ACK)) {
/* ...but we expected an ACK. */
- frame_success = 0;
+ frame_success = false;
}
}
if (status->frame_count == 0) {
ring->mmio_base = b43legacy_dmacontroller_base(type, controller_index);
ring->index = controller_index;
if (for_tx) {
- ring->tx = 1;
+ ring->tx = true;
ring->current_slot = -1;
} else {
if (ring->index == 0) {
static int b43legacy_dma_set_mask(struct b43legacy_wldev *dev, u64 mask)
{
u64 orig_mask = mask;
- bool fallback = 0;
+ bool fallback = false;
int err;
/* Try to set the DMA mask. If it fails, try falling back to a
}
if (mask == DMA_BIT_MASK(64)) {
mask = DMA_BIT_MASK(32);
- fallback = 1;
+ fallback = true;
continue;
}
if (mask == DMA_BIT_MASK(32)) {
mask = DMA_BIT_MASK(30);
- fallback = 1;
+ fallback = true;
continue;
}
b43legacyerr(dev->wl, "The machine/kernel does not support "
#ifdef CONFIG_B43LEGACY_PIO
b43legacywarn(dev->wl, "DMA for this device not supported. "
"Falling back to PIO\n");
- dev->__using_pio = 1;
+ dev->__using_pio = true;
return -EAGAIN;
#else
b43legacyerr(dev->wl, "DMA for this device not supported and "
memset(meta, 0, sizeof(*meta));
meta->skb = skb;
- meta->is_last_fragment = 1;
+ meta->is_last_fragment = true;
meta->dmaaddr = map_descbuffer(ring, skb->data, skb->len, 1);
/* create a bounce buffer in zone_dma on mapping failure. */
unsigned int skb_mapping = skb_get_queue_mapping(skb);
ieee80211_stop_queue(dev->wl->hw, skb_mapping);
dev->wl->tx_queue_stopped[skb_mapping] = 1;
- ring->stopped = 1;
+ ring->stopped = true;
if (b43legacy_debug(dev, B43legacy_DBG_DMAVERBOSE))
b43legacydbg(dev->wl, "Stopped TX ring %d\n",
ring->index);
dev->stats.last_tx = jiffies;
if (ring->stopped) {
B43legacy_WARN_ON(free_slots(ring) < SLOTS_PER_PACKET);
- ring->stopped = 0;
+ ring->stopped = false;
}
if (dev->wl->tx_queue_stopped[ring->queue_prio]) {
if (sprom[i] == 0xFF) {
/* There is no LED information in the SPROM
* for this LED. Hardcode it here. */
- activelow = 0;
+ activelow = false;
switch (i) {
case 0:
behaviour = B43legacy_LED_ACTIVITY;
- activelow = 1;
+ activelow = true;
if (bus->boardinfo.vendor == PCI_VENDOR_ID_COMPAQ)
behaviour = B43legacy_LED_RADIO_ALL;
break;
macctl &= ~B43legacy_MACCTL_GMODE;
if (flags & B43legacy_TMSLOW_GMODE) {
macctl |= B43legacy_MACCTL_GMODE;
- dev->phy.gmode = 1;
+ dev->phy.gmode = true;
} else
- dev->phy.gmode = 0;
+ dev->phy.gmode = false;
macctl |= B43legacy_MACCTL_IHR_ENABLED;
b43legacy_write32(dev, B43legacy_MMIO_MACCTL, macctl);
}
if (dev->noisecalc.calculation_running)
return;
dev->noisecalc.channel_at_start = dev->phy.channel;
- dev->noisecalc.calculation_running = 1;
+ dev->noisecalc.calculation_running = true;
dev->noisecalc.nr_samples = 0;
b43legacy_generate_noise_sample(dev);
dev->stats.link_noise = average;
drop_calculation:
- dev->noisecalc.calculation_running = 0;
+ dev->noisecalc.calculation_running = false;
return;
}
generate_new:
b43legacy_power_saving_ctl_bits(dev, -1, -1);
}
if (b43legacy_is_mode(dev->wl, NL80211_IFTYPE_ADHOC))
- dev->dfq_valid = 1;
+ dev->dfq_valid = true;
}
static void handle_irq_atim_end(struct b43legacy_wldev *dev)
b43legacy_write32(dev, B43legacy_MMIO_MACCMD,
b43legacy_read32(dev, B43legacy_MMIO_MACCMD)
| B43legacy_MACCMD_DFQ_VALID);
- dev->dfq_valid = 0;
+ dev->dfq_valid = false;
}
}
unsigned int i, len, variable_len;
const struct ieee80211_mgmt *bcn;
const u8 *ie;
- bool tim_found = 0;
+ bool tim_found = false;
unsigned int rate;
u16 ctl;
int antenna;
/* A valid TIM is at least 4 bytes long. */
if (ie_len < 4)
break;
- tim_found = 1;
+ tim_found = true;
tim_position = sizeof(struct b43legacy_plcp_hdr6);
tim_position += offsetof(struct ieee80211_mgmt,
* but we don't use that feature anyway. */
b43legacy_write_probe_resp_template(dev, 0x268, 0x4A,
&__b43legacy_ratetable[3]);
- wl->beacon0_uploaded = 1;
+ wl->beacon0_uploaded = true;
}
static void b43legacy_upload_beacon1(struct b43legacy_wldev *dev)
if (wl->beacon1_uploaded)
return;
b43legacy_write_beacon_template(dev, 0x468, 0x1A);
- wl->beacon1_uploaded = 1;
+ wl->beacon1_uploaded = true;
}
static void handle_irq_beacon(struct b43legacy_wldev *dev)
if (unlikely(wl->beacon_templates_virgin)) {
/* We never uploaded a beacon before.
* Upload both templates now, but only mark one valid. */
- wl->beacon_templates_virgin = 0;
+ wl->beacon_templates_virgin = false;
b43legacy_upload_beacon0(dev);
b43legacy_upload_beacon1(dev);
cmd = b43legacy_read32(dev, B43legacy_MMIO_MACCMD);
if (wl->current_beacon)
dev_kfree_skb_any(wl->current_beacon);
wl->current_beacon = beacon;
- wl->beacon0_uploaded = 0;
- wl->beacon1_uploaded = 0;
+ wl->beacon0_uploaded = false;
+ wl->beacon1_uploaded = false;
ieee80211_queue_work(wl->hw, &wl->beacon_update_trigger);
}
if (d->phy.possible_phymodes & phymode) {
/* Ok, this device supports the PHY-mode.
* Set the gmode bit. */
- *gmode = 1;
+ *gmode = true;
*dev = d;
return 0;
struct b43legacy_wldev *uninitialized_var(up_dev);
struct b43legacy_wldev *down_dev;
int err;
- bool gmode = 0;
+ bool gmode = false;
int prev_status;
err = find_wldev_for_phymode(wl, new_mode, &up_dev, &gmode);
/* Assume the radio is enabled. If it's not enabled, the state will
* immediately get fixed on the first periodic work run. */
- dev->radio_hw_enable = 1;
+ dev->radio_hw_enable = true;
phy->savedpctlreg = 0xFFFF;
- phy->aci_enable = 0;
- phy->aci_wlan_automatic = 0;
- phy->aci_hw_rssi = 0;
+ phy->aci_enable = false;
+ phy->aci_wlan_automatic = false;
+ phy->aci_hw_rssi = false;
lo = phy->_lo_pairs;
if (lo)
static void setup_struct_wldev_for_init(struct b43legacy_wldev *dev)
{
/* Flags */
- dev->dfq_valid = 0;
+ dev->dfq_valid = false;
/* Stats */
memset(&dev->stats, 0, sizeof(dev->stats));
phy->lofcal = 0xFFFF;
phy->initval = 0xFFFF;
- phy->aci_enable = 0;
- phy->aci_wlan_automatic = 0;
- phy->aci_hw_rssi = 0;
+ phy->aci_enable = false;
+ phy->aci_wlan_automatic = false;
+ phy->aci_hw_rssi = false;
phy->antenna_diversity = 0xFFFF;
memset(phy->minlowsig, 0xFF, sizeof(phy->minlowsig));
b43legacydbg(wl, "Adding Interface type %d\n", vif->type);
dev = wl->current_dev;
- wl->operating = 1;
+ wl->operating = true;
wl->vif = vif;
wl->if_type = vif->type;
memcpy(wl->mac_addr, vif->addr, ETH_ALEN);
B43legacy_WARN_ON(wl->vif != vif);
wl->vif = NULL;
- wl->operating = 0;
+ wl->operating = false;
spin_lock_irqsave(&wl->irq_lock, flags);
b43legacy_adjust_opmode(dev);
memset(wl->bssid, 0, ETH_ALEN);
memset(wl->mac_addr, 0, ETH_ALEN);
wl->filter_flags = 0;
- wl->beacon0_uploaded = 0;
- wl->beacon1_uploaded = 0;
- wl->beacon_templates_virgin = 1;
- wl->radio_enabled = 1;
+ wl->beacon0_uploaded = false;
+ wl->beacon1_uploaded = false;
+ wl->beacon_templates_virgin = true;
+ wl->radio_enabled = true;
mutex_lock(&wl->mutex);
if (b43legacy_status(dev) >= B43legacy_STAT_STARTED)
b43legacy_wireless_core_stop(dev);
b43legacy_wireless_core_exit(dev);
- wl->radio_enabled = 0;
+ wl->radio_enabled = false;
mutex_unlock(&wl->mutex);
}
have_bphy = 1;
dev->phy.gmode = (have_gphy || have_bphy);
- dev->phy.radio_on = 1;
+ dev->phy.radio_on = true;
tmp = dev->phy.gmode ? B43legacy_TMSLOW_GMODE : 0;
b43legacy_wireless_core_reset(dev, tmp);
(void (*)(unsigned long))b43legacy_interrupt_tasklet,
(unsigned long)wldev);
if (modparam_pio)
- wldev->__using_pio = 1;
+ wldev->__using_pio = true;
INIT_LIST_HEAD(&wldev->list);
err = b43legacy_wireless_core_attach(wldev);
if (b43legacy_phy_read(dev, 0x0033) & 0x0800)
break;
- phy->aci_enable = 1;
+ phy->aci_enable = true;
phy_stacksave(B43legacy_PHY_RADIO_BITFIELD);
phy_stacksave(B43legacy_PHY_G_CRS);
if (!(b43legacy_phy_read(dev, 0x0033) & 0x0800))
break;
- phy->aci_enable = 0;
+ phy->aci_enable = false;
phy_stackrestore(B43legacy_PHY_RADIO_BITFIELD);
phy_stackrestore(B43legacy_PHY_G_CRS);
(phy->rev == 0) || (!phy->gmode))
return -ENODEV;
- phy->aci_wlan_automatic = 0;
+ phy->aci_wlan_automatic = false;
switch (mode) {
case B43legacy_RADIO_INTERFMODE_AUTOWLAN:
- phy->aci_wlan_automatic = 1;
+ phy->aci_wlan_automatic = true;
if (phy->aci_enable)
mode = B43legacy_RADIO_INTERFMODE_MANUALWLAN;
else
currentmode);
if (mode == B43legacy_RADIO_INTERFMODE_NONE) {
- phy->aci_enable = 0;
- phy->aci_hw_rssi = 0;
+ phy->aci_enable = false;
+ phy->aci_hw_rssi = false;
} else
b43legacy_radio_interference_mitigation_enable(dev, mode);
phy->interfmode = mode;
phy->radio_off_context.rfover);
b43legacy_phy_write(dev, B43legacy_PHY_RFOVERVAL,
phy->radio_off_context.rfoverval);
- phy->radio_off_context.valid = 0;
+ phy->radio_off_context.valid = false;
}
channel = phy->channel;
err = b43legacy_radio_selectchannel(dev,
default:
B43legacy_BUG_ON(1);
}
- phy->radio_on = 1;
+ phy->radio_on = true;
}
void b43legacy_radio_turn_off(struct b43legacy_wldev *dev, bool force)
if (!force) {
phy->radio_off_context.rfover = rfover;
phy->radio_off_context.rfoverval = rfoverval;
- phy->radio_off_context.valid = 1;
+ phy->radio_off_context.valid = true;
}
b43legacy_phy_write(dev, B43legacy_PHY_RFOVER, rfover | 0x008C);
b43legacy_phy_write(dev, B43legacy_PHY_RFOVERVAL,
rfoverval & 0xFF73);
} else
b43legacy_phy_write(dev, 0x0015, 0xAA00);
- phy->radio_on = 0;
+ phy->radio_on = false;
b43legacydbg(dev->wl, "Radio initialized\n");
}
return 0;
/* Set state and stop OS transmissions */
- drvr->bus_if->drvr_up = 0;
+ drvr->bus_if->drvr_up = false;
netif_stop_queue(ndev);
return 0;
}
/* Allow transmit calls */
netif_start_queue(ndev);
- drvr->bus_if->drvr_up = 1;
+ drvr->bus_if->drvr_up = true;
if (brcmf_cfg80211_up(drvr->config)) {
brcmf_dbg(ERROR, "failed to bring up cfg80211\n");
return -1;
/* WAR64450 : DMACtl.Addr ext fields are not supported in SDIOD core. */
if ((core->id.id == SDIOD_CORE_ID)
&& ((rev > 0) && (rev <= 2)))
- di->addrext = 0;
+ di->addrext = false;
else if ((core->id.id == I2S_CORE_ID) &&
((rev == 0) || (rev == 1)))
- di->addrext = 0;
+ di->addrext = false;
else
di->addrext = _dma_isaddrext(di);
brcms_c_reset(wl->wlc);
/* dpc will not be rescheduled */
- wl->resched = 0;
+ wl->resched = false;
return 0;
}
si_pmu_pllupd(pi->sh->sih);
write_phy_reg(pi, 0x942, 0);
wlc_lcnphy_txrx_spur_avoidance_mode(pi, false);
- pi_lcn->lcnphy_spurmod = 0;
+ pi_lcn->lcnphy_spurmod = false;
mod_phy_reg(pi, 0x424, (0xff << 8), (0x1b) << 8);
write_phy_reg(pi, 0x425, 0x5907);
write_phy_reg(pi, 0x942, 0);
wlc_lcnphy_txrx_spur_avoidance_mode(pi, true);
- pi_lcn->lcnphy_spurmod = 0;
+ pi_lcn->lcnphy_spurmod = false;
mod_phy_reg(pi, 0x424, (0xff << 8), (0x1f) << 8);
write_phy_reg(pi, 0x425, 0x590a);
{
s8 index, delta_brd, delta_temp, new_index, tempcorrx;
s16 manp, meas_temp, temp_diff;
- bool neg = 0;
+ bool neg = false;
u16 temp;
struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy;
manp = LCNPHY_TEMPSENSE(pi_lcn->lcnphy_rawtempsense);
temp_diff = manp - meas_temp;
if (temp_diff < 0) {
- neg = 1;
+ neg = true;
temp_diff = -temp_diff;
}
wlc_lcnphy_set_cc(pi, cal_type, phy_c15, phy_c16);
udelay(20);
for (phy_c8 = 0; phy_c7 != 0 && phy_c8 < num_levels; phy_c8++) {
- phy_c23 = 1;
- phy_c22 = 0;
+ phy_c23 = true;
+ phy_c22 = false;
switch (cal_type) {
case 0:
phy_c10 = 511;
phy_c9 = read_phy_reg(pi, 0x93d);
phy_c9 = 2 * phy_c9;
- phy_c24 = 0;
+ phy_c24 = false;
phy_c5 = 7;
- phy_c25 = 1;
+ phy_c25 = true;
while (1) {
write_radio_reg(pi, RADIO_2064_REG026,
(phy_c5 & 0x7) | ((phy_c5 & 0x7) << 4));
udelay(50);
- phy_c22 = 0;
+ phy_c22 = false;
ptr[130] = 0;
wlc_lcnphy_samp_cap(pi, 1, phy_c9, &ptr[0], 2);
if (ptr[130] == 1)
- phy_c22 = 1;
+ phy_c22 = true;
if (phy_c22)
phy_c5 -= 1;
if ((phy_c22 != phy_c24) && (!phy_c25))
if (phy_c5 <= 0 || phy_c5 >= 7)
break;
phy_c24 = phy_c22;
- phy_c25 = 0;
+ phy_c25 = false;
}
if (phy_c5 < 0)
phy_c13 = phy_c11;
phy_c14 = phy_c12;
}
- phy_c23 = 0;
+ phy_c23 = false;
}
}
- phy_c23 = 1;
+ phy_c23 = true;
phy_c15 = phy_c13;
phy_c16 = phy_c14;
phy_c7 = phy_c7 >> 1;
{
u16 tempsenseval1, tempsenseval2;
s16 avg = 0;
- bool suspend = 0;
+ bool suspend = false;
if (mode == 1) {
suspend = (0 == (bcma_read32(pi->d11core,
{
u16 tempsenseval1, tempsenseval2;
s32 avg = 0;
- bool suspend = 0;
+ bool suspend = false;
u16 SAVE_txpwrctrl = wlc_lcnphy_get_tx_pwr_ctrl(pi);
struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy;
{
u16 vbatsenseval;
s32 avg = 0;
- bool suspend = 0;
+ bool suspend = false;
if (mode == 1) {
suspend = (0 == (bcma_read32(pi->d11core,
iwl_print_hex_dump(trans, IWL_DL_TX, (u8 *)tx_cmd->hdr, hdr_len);
/* Set up entry for this TFD in Tx byte-count array */
- if (is_agg)
- iwl_trans_txq_update_byte_cnt_tbl(trans, txq,
- le16_to_cpu(tx_cmd->len));
+ iwl_trans_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len));
dma_sync_single_for_device(bus(trans)->dev, txcmd_phys, firstlen,
DMA_BIDIRECTIONAL);
.mac_addr = {0x00, 0x02, 0xb3, 0x01, 0x02, 0x03},
};
-static int modparam_reset;
+static bool modparam_reset;
module_param_named(reset, modparam_reset, bool, 0644);
MODULE_PARM_DESC(reset, "reset on firmware errors (default 0 [not reset])");
-static int modparam_wimax_enable = 1;
+static bool modparam_wimax_enable = true;
module_param_named(wimax_enable, modparam_wimax_enable, bool, 0644);
MODULE_PARM_DESC(wimax_enable, "Enable wimax core (default 1 [wimax enabled])");
iwm_invalidate_mlme_profile(iwm);
clear_bit(IWM_STATUS_ASSOCIATED, &iwm->status);
- iwm->umac_profile_active = 0;
+ iwm->umac_profile_active = false;
memset(iwm->bssid, 0, ETH_ALEN);
iwm->channel = 0;
clear_bit(IWM_STATUS_SME_CONNECTING, &iwm->status);
clear_bit(IWM_STATUS_ASSOCIATED, &iwm->status);
- iwm->umac_profile_active = 0;
+ iwm->umac_profile_active = false;
memset(iwm->bssid, 0, ETH_ALEN);
iwm->channel = 0;
umac_sta->mac_addr,
umac_sta->flags & UMAC_STA_FLAG_QOS);
- sta->valid = 1;
+ sta->valid = true;
sta->qos = umac_sta->flags & UMAC_STA_FLAG_QOS;
sta->color = GET_VAL8(umac_sta->sta_id, LMAC_STA_COLOR);
memcpy(sta->addr, umac_sta->mac_addr, ETH_ALEN);
sta = &iwm->sta_table[GET_VAL8(umac_sta->sta_id, LMAC_STA_ID)];
if (!memcmp(sta->addr, umac_sta->mac_addr, ETH_ALEN))
- sta->valid = 0;
+ sta->valid = false;
break;
case UMAC_OPCODE_CLEAR_ALL:
for (i = 0; i < IWM_STA_TABLE_NUM; i++)
- iwm->sta_table[i].valid = 0;
+ iwm->sta_table[i].valid = false;
break;
default:
switch (hdr->oid) {
case UMAC_WIFI_IF_CMD_SET_PROFILE:
- iwm->umac_profile_active = 1;
+ iwm->umac_profile_active = true;
break;
default:
break;
*/
list_for_each_entry(cmd, &iwm->nonwifi_pending_cmd, pending)
if (cmd->seq_num == seq_num) {
- cmd->resp_received = 1;
+ cmd->resp_received = true;
cmd->buf.len = buf_size;
memcpy(cmd->buf.hdr, buf, buf_size);
wake_up_interruptible(&iwm->nonwifi_queue);
* Most of the libertas cards can do unaligned register access, but some
* weird ones cannot. That's especially true for the CF8305 card.
*/
- card->align_regs = 0;
+ card->align_regs = false;
card->model = get_model(p_dev->manf_id, p_dev->card_id);
if (card->model == MODEL_UNKNOWN) {
/* Check if we have a current silicon */
prod_id = if_cs_read8(card, IF_CS_PRODUCT_ID);
if (card->model == MODEL_8305) {
- card->align_regs = 1;
+ card->align_regs = true;
if (prod_id < IF_CS_CF8305_B1_REV) {
pr_err("8305 rev B0 and older are not supported\n");
ret = -ENODEV;
return;
if (skb_queue_empty(&priv->bc_ps_buf)) {
- bool tx_buff_bc = 0;
+ bool tx_buff_bc = false;
while ((skb = ieee80211_get_buffered_bc(priv->hw, priv->vif))) {
skb_queue_tail(&priv->bc_ps_buf, skb);
- tx_buff_bc = 1;
+ tx_buff_bc = true;
}
if (tx_buff_bc) {
ieee80211_stop_queues(priv->hw);
{
struct mac80211_hwsim_data *data = hw->priv;
wiphy_debug(hw->wiphy, "%s\n", __func__);
- data->started = 1;
+ data->started = true;
return 0;
}
static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
{
struct mac80211_hwsim_data *data = hw->priv;
- data->started = 0;
+ data->started = false;
del_timer(&data->beacon_timer);
wiphy_debug(hw->wiphy, "%s\n", __func__);
}
{
bool cancel_flag = false;
int status = adapter->cmd_wait_q.status;
- struct cmd_ctrl_node *cmd_queued = adapter->cmd_queued;
+ struct cmd_ctrl_node *cmd_queued;
+ if (!adapter->cmd_queued)
+ return 0;
+
+ cmd_queued = adapter->cmd_queued;
adapter->cmd_queued = NULL;
+
dev_dbg(adapter->dev, "cmd pending\n");
atomic_inc(&adapter->cmd_pending);
#define MWL8K_VERSION "0.13"
/* Module parameters */
-static unsigned ap_mode_default;
+static bool ap_mode_default;
module_param(ap_mode_default, bool, 0);
MODULE_PARM_DESC(ap_mode_default,
"Set to 1 to make ap mode the default instead of sta mode");
ready_code = ioread32(priv->regs + MWL8K_HIU_INT_CODE);
if (ready_code == MWL8K_FWAP_READY) {
- priv->ap_fw = 1;
+ priv->ap_fw = true;
break;
} else if (ready_code == MWL8K_FWSTA_READY) {
- priv->ap_fw = 0;
+ priv->ap_fw = false;
break;
}
INIT_LIST_HEAD(&priv->vif_list);
/* Set default radio state and preamble */
- priv->radio_on = 0;
- priv->radio_short_preamble = 0;
+ priv->radio_on = false;
+ priv->radio_short_preamble = false;
/* Finalize join worker */
INIT_WORK(&priv->finalize_join_worker, mwl8k_finalize_join_worker);
MODULE_PARM_DESC(orinoco_debug, "Debug level");
#endif
-static int suppress_linkstatus; /* = 0 */
+static bool suppress_linkstatus; /* = 0 */
module_param(suppress_linkstatus, bool, 0644);
MODULE_PARM_DESC(suppress_linkstatus, "Don't log link status changes");
#include "p54.h"
#include "lmac.h"
-static int modparam_nohwcrypt;
+static bool modparam_nohwcrypt;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
MODULE_AUTHOR("Michael Wu <flamingice@sourmilk.net>");
unsigned int pkt_addr, int rx_len)
{
UCHAR buff[256];
- struct rx_msg *msg = (struct rx_msg *)buff;
+ struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
del_timer(&local->timer);
unsigned int pkt_addr, int rx_len)
{
/* UCHAR buff[256];
- struct rx_msg *msg = (struct rx_msg *)buff;
+ struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
*/
pr_debug("Deauthentication frame received\n");
local->authentication_state = UNAUTHENTICATED;
UCHAR hdr_3;
UCHAR hdr_4;
};
-struct rx_msg {
+struct ray_rx_msg {
struct mac_header mac;
- UCHAR var[1];
+ UCHAR var[0];
};
struct tx_msg {
/*
* Allow hardware encryption to be disabled.
*/
-static int modparam_nohwcrypt;
+static bool modparam_nohwcrypt;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
/*
* Allow hardware encryption to be disabled.
*/
-static int modparam_nohwcrypt = 0;
+static bool modparam_nohwcrypt = false;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
/*
* Allow hardware encryption to be disabled.
*/
-static int modparam_nohwcrypt;
+static bool modparam_nohwcrypt;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
/*
* Allow hardware encryption to be disabled.
*/
-static int modparam_nohwcrypt = 0;
+static bool modparam_nohwcrypt = false;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
/*
* Allow hardware encryption to be disabled.
*/
-static int modparam_nohwcrypt;
+static bool modparam_nohwcrypt;
module_param_named(nohwcrypt, modparam_nohwcrypt, bool, S_IRUGO);
MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption.");
u8 valid = 0;
/*set init state to on */
- rtlpriv->rfkill.rfkill_state = 1;
+ rtlpriv->rfkill.rfkill_state = true;
wiphy_rfkill_set_hw_state(hw->wiphy, 0);
radio_state = rtlpriv->cfg->ops->radio_onoff_checking(hw, &valid);
u8 init_aspm;
ppsc->reg_rfps_level = 0;
- ppsc->support_aspm = 0;
+ ppsc->support_aspm = false;
/*Update PCI ASPM setting */
ppsc->const_amdpci_aspm = rtlpci->const_amdpci_aspm;
if (ieee80211_is_nullfunc(fc)) {
if (ieee80211_has_pm(fc)) {
rtlpriv->mac80211.offchan_delay = true;
- rtlpriv->psc.state_inap = 1;
+ rtlpriv->psc.state_inap = true;
} else {
- rtlpriv->psc.state_inap = 0;
+ rtlpriv->psc.state_inap = false;
}
}
rtl8192ce_bt_reg_init(hw);
- rtlpriv->dm.dm_initialgain_enable = 1;
+ rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
- rtlpriv->dm.disable_framebursting = 0;
+ rtlpriv->dm.disable_framebursting = false;
rtlpriv->dm.thermalvalue = 0;
rtlpci->transmit_config = CFENDFORM | BIT(12) | BIT(13);
"%x\n", ppsc->hwradiooff, e_rfpowerstate_toset));
}
if (actuallyset) {
- ppsc->hwradiooff = 1;
+ ppsc->hwradiooff = true;
if (e_rfpowerstate_toset == ERFON) {
if ((ppsc->reg_rfps_level & RT_RF_OFF_LEVL_ASPM) &&
RT_IN_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_ASPM))
const struct firmware *firmware;
int err;
- rtlpriv->dm.dm_initialgain_enable = 1;
+ rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
- rtlpriv->dm.disable_framebursting = 0;
+ rtlpriv->dm.disable_framebursting = false;
rtlpriv->dm.thermalvalue = 0;
rtlpriv->dbg.global_debuglevel = rtlpriv->cfg->mod_params->debug;
rtlpriv->rtlhal.pfirmware = vmalloc(0x4000);
rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
- rtlpriv->dm.disable_framebursting = 0;
+ rtlpriv->dm.disable_framebursting = false;
rtlpriv->dm.thermalvalue = 0;
- rtlpriv->dm.useramask = 1;
+ rtlpriv->dm.useramask = true;
/* dual mac */
if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G)
int err = 0;
u16 earlyrxthreshold = 7;
- rtlpriv->dm.dm_initialgain_enable = 1;
+ rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
- rtlpriv->dm.disable_framebursting = 0;
+ rtlpriv->dm.disable_framebursting = false;
rtlpriv->dm.thermalvalue = 0;
rtlpriv->dm.useramask = true;
struct rtl_mod_params {
/* default: 0 = using hardware encryption */
- int sw_crypto;
+ bool sw_crypto;
/* default: 0 = DBG_EMERG (0)*/
int debug;
return 0;
}
-static u32 xenvif_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t xenvif_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct xenvif *vif = netdev_priv(dev);
struct gnttab_copy *copy_gop;
struct netbk_rx_meta *meta;
/*
- * These variables a used iff get_page_ext returns true,
+ * These variables are used iff get_page_ext returns true,
* in which case they are guaranteed to be initialized.
*/
unsigned int uninitialized_var(group), uninitialized_var(idx);
if (!page)
return NULL;
- netbk->mmap_pages[pending_idx] = page;
-
gop->source.u.ref = txp->gref;
gop->source.domid = vif->domid;
gop->source.offset = txp->offset;
pending_idx = *((u16 *)skb->data);
xen_netbk_idx_release(netbk, pending_idx);
for (j = start; j < i; j++) {
- pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
+ pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
xen_netbk_idx_release(netbk, pending_idx);
}
continue;
}
- netbk->mmap_pages[pending_idx] = page;
-
gop->source.u.ref = txreq.gref;
gop->source.domid = vif->domid;
gop->source.offset = txreq.offset;
"netback/%u", group);
if (IS_ERR(netbk->task)) {
- printk(KERN_ALERT "kthread_run() fails at netback\n");
+ printk(KERN_ALERT "kthread_create() fails at netback\n");
del_timer(&netbk->net_timer);
rc = PTR_ERR(netbk->task);
goto failed_init;
#define xennet_sysfs_delif(dev) do { } while (0)
#endif
-static int xennet_can_sg(struct net_device *dev)
+static bool xennet_can_sg(struct net_device *dev)
{
return dev->features & NETIF_F_SG;
}
gnttab_free_grant_references(np->gref_rx_head);
}
-static u32 xennet_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t xennet_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct netfront_info *np = netdev_priv(dev);
int val;
return features;
}
-static int xennet_set_features(struct net_device *dev, u32 features)
+static int xennet_set_features(struct net_device *dev,
+ netdev_features_t features)
{
if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN) {
netdev_info(dev, "Reducing MTU because no SG offload");
case XenbusStateInitialised:
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
- case XenbusStateConnected:
case XenbusStateUnknown:
case XenbusStateClosed:
break;
if (xennet_connect(netdev) != 0)
break;
xenbus_switch_state(dev, XenbusStateConnected);
+ break;
+
+ case XenbusStateConnected:
netif_notify_peers(netdev);
break;
#include <linux/string.h>
#include <linux/slab.h>
-/* For archs that don't support NO_IRQ (such as x86), provide a dummy value */
-#ifndef NO_IRQ
-#define NO_IRQ 0
-#endif
-
/**
* irq_of_parse_and_map - Parse and map an interrupt into linux virq space
* @device: Device node of the device whose interrupt is to be mapped
struct of_irq oirq;
if (of_irq_map_one(dev, index, &oirq))
- return NO_IRQ;
+ return 0;
return irq_create_of_mapping(oirq.controller, oirq.specifier,
oirq.size);
*/
struct device_node *of_irq_find_parent(struct device_node *child)
{
- struct device_node *p, *c = child;
+ struct device_node *p;
const __be32 *parp;
- if (!of_node_get(c))
+ if (!of_node_get(child))
return NULL;
do {
- parp = of_get_property(c, "interrupt-parent", NULL);
+ parp = of_get_property(child, "interrupt-parent", NULL);
if (parp == NULL)
- p = of_get_parent(c);
+ p = of_get_parent(child);
else {
if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
p = of_node_get(of_irq_dflt_pic);
else
p = of_find_node_by_phandle(be32_to_cpup(parp));
}
- of_node_put(c);
- c = p;
+ of_node_put(child);
+ child = p;
} while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL);
- return (p == child) ? NULL : p;
+ return p;
}
/**
/* Only dereference the resource if both the
* resource and the irq are valid. */
- if (r && irq != NO_IRQ) {
+ if (r && irq) {
r->start = r->end = irq;
r->flags = IORESOURCE_IRQ;
r->name = dev->full_name;
{
int nr = 0;
- while (of_irq_to_resource(dev, nr, NULL) != NO_IRQ)
+ while (of_irq_to_resource(dev, nr, NULL))
nr++;
return nr;
int i;
for (i = 0; i < nr_irqs; i++, res++)
- if (of_irq_to_resource(dev, i, res) == NO_IRQ)
+ if (!of_irq_to_resource(dev, i, res))
break;
return i;
desc->dev = np;
desc->interrupt_parent = of_irq_find_parent(np);
+ if (desc->interrupt_parent == np)
+ desc->interrupt_parent = NULL;
list_add_tail(&desc->list, &intc_desc_list);
}
if (!lookup)
return NULL;
- for(; lookup->name != NULL; lookup++) {
+ for(; lookup->compatible != NULL; lookup++) {
if (!of_device_is_compatible(np, lookup->compatible))
continue;
if (of_address_to_resource(np, 0, &res))
return err;
}
+static int timer_mode;
+
static int __init oprofile_init(void)
{
int err;
+ /* always init architecture to setup backtrace support */
err = oprofile_arch_init(&oprofile_ops);
- if (err < 0 || timer) {
- printk(KERN_INFO "oprofile: using timer interrupt.\n");
+
+ timer_mode = err || timer; /* fall back to timer mode on errors */
+ if (timer_mode) {
+ if (!err)
+ oprofile_arch_exit();
err = oprofile_timer_init(&oprofile_ops);
if (err)
return err;
}
- return oprofilefs_register();
+
+ err = oprofilefs_register();
+ if (!err)
+ return 0;
+
+ /* failed */
+ if (timer_mode)
+ oprofile_timer_exit();
+ else
+ oprofile_arch_exit();
+
+ return err;
}
static void __exit oprofile_exit(void)
{
- oprofile_timer_exit();
oprofilefs_unregister();
- oprofile_arch_exit();
+ if (timer_mode)
+ oprofile_timer_exit();
+ else
+ oprofile_arch_exit();
}
return -EINVAL;
retval = oprofilefs_ulong_from_user(&val, buf, count);
- if (retval)
+ if (retval <= 0)
return retval;
retval = oprofile_set_timeout(val);
return -EINVAL;
retval = oprofilefs_ulong_from_user(&val, buf, count);
- if (retval)
+ if (retval <= 0)
return retval;
retval = oprofile_set_ulong(&oprofile_backtrace_depth, val);
return -EINVAL;
retval = oprofilefs_ulong_from_user(&val, buf, count);
- if (retval)
+ if (retval <= 0)
return retval;
+ retval = 0;
if (val)
retval = oprofile_start();
else
}
+/*
+ * Note: If oprofilefs_ulong_from_user() returns 0, then *val remains
+ * unchanged and might be uninitialized. This follows write syscall
+ * implementation when count is zero: "If count is zero ... [and if]
+ * no errors are detected, 0 will be returned without causing any
+ * other effect." (man 2 write)
+ */
int oprofilefs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count)
{
char tmpbuf[TMPBUFSIZE];
raw_spin_lock_irqsave(&oprofilefs_lock, flags);
*val = simple_strtoul(tmpbuf, NULL, 0);
raw_spin_unlock_irqrestore(&oprofilefs_lock, flags);
- return 0;
+ return count;
}
return -EINVAL;
retval = oprofilefs_ulong_from_user(&value, buf, count);
- if (retval)
+ if (retval <= 0)
return retval;
retval = oprofile_set_ulong(file->private_data, value);
ops->start = oprofile_hrtimer_start;
ops->stop = oprofile_hrtimer_stop;
ops->cpu_type = "timer";
+ printk(KERN_INFO "oprofile: using timer interrupt.\n");
return 0;
}
config PCI_PRI
bool "PCI PRI support"
+ depends on PCI
select PCI_ATS
help
PRI is the PCI Page Request Interface. It allows PCI devices that are
#include <linux/export.h>
#include <linux/pci-ats.h>
#include <linux/pci.h>
+#include <linux/slab.h>
#include "pci.h"
if (!acpi_pci_check_ejectable(pbus, handle) && !is_dock_device(handle))
return AE_OK;
+ pdev = pbus->self;
+ if (pdev && pci_is_pcie(pdev)) {
+ tmp = acpi_find_root_bridge_handle(pdev);
+ if (tmp) {
+ struct acpi_pci_root *root = acpi_pci_find_root(tmp);
+
+ if (root && (root->osc_control_set &
+ OSC_PCI_EXPRESS_NATIVE_HP_CONTROL))
+ return AE_OK;
+ }
+ }
+
acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
device = (adr >> 16) & 0xffff;
function = adr & 0xffff;
pdev = pci_get_slot(pbus, PCI_DEVFN(device, function));
if (pdev) {
- pdev->current_state = PCI_D0;
slot->flags |= (SLOT_ENABLED | SLOT_POWEREDON);
pci_dev_put(pdev);
}
{
int *count = (int *)context;
- if (acpi_is_root_bridge(handle)) {
- acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
- handle_hotplug_event_bridge, NULL);
- (*count)++;
- }
+ if (!acpi_is_root_bridge(handle))
+ return AE_OK;
+
+ (*count)++;
+ acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+ handle_hotplug_event_bridge, NULL);
+
return AE_OK ;
}
goto err_exit;
}
- /* Wait for 1 second after checking link training status */
- msleep(1000);
-
/* Check for a power fault */
if (ctrl->power_fault_detected || pciehp_query_power_fault(p_slot)) {
ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
else
msleep(1000);
+ /*
+ * Need to wait for 1000 ms after Data Link Layer Link Active
+ * (DLLLA) bit reads 1b before sending configuration request.
+ * We need it before checking Link Training (LT) bit becuase
+ * LT is still set even after DLLLA bit is set on some platform.
+ */
+ msleep(1000);
+
retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
if (retval) {
ctrl_err(ctrl, "Cannot read LNKSTATUS register\n");
return retval;
}
+ /*
+ * If the port supports Link speeds greater than 5.0 GT/s, we
+ * must wait for 100 ms after Link training completes before
+ * sending configuration request.
+ */
+ if (ctrl->pcie->port->subordinate->max_bus_speed > PCIE_SPEED_5_0GT)
+ msleep(100);
+
+ pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+
return retval;
}
u16 slot_cmd;
u16 cmd_mask;
u16 slot_status;
- u16 lnk_status;
int retval = 0;
/* Clear sticky power-fault bit from previous power failures */
ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
- retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
- if (retval) {
- ctrl_err(ctrl, "%s: Cannot read LNKSTA register\n",
- __func__);
- return retval;
- }
- pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
-
return retval;
}
static int is_shpc_capable(struct pci_dev *dev)
{
- if ((dev->vendor == PCI_VENDOR_ID_AMD) || (dev->device ==
- PCI_DEVICE_ID_AMD_GOLAM_7450))
+ if (dev->vendor == PCI_VENDOR_ID_AMD &&
+ dev->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
return 1;
if (!pci_find_capability(dev, PCI_CAP_ID_SHPC))
return 0;
ctrl->pci_dev = pdev; /* pci_dev of the P2P bridge */
ctrl_dbg(ctrl, "Hotplug Controller:\n");
- if ((pdev->vendor == PCI_VENDOR_ID_AMD) || (pdev->device ==
- PCI_DEVICE_ID_AMD_GOLAM_7450)) {
+ if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+ pdev->device == PCI_DEVICE_ID_AMD_GOLAM_7450) {
/* amd shpc driver doesn't use Base Offset; assume 0 */
ctrl->mmio_base = pci_resource_start(pdev, 0);
ctrl->mmio_size = pci_resource_len(pdev, 0);
struct resource *res;
struct pci_dev *pdev;
struct pci_sriov *iov = dev->sriov;
+ int bars = 0;
if (!nr_virtfn)
return 0;
nres = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ bars |= (1 << (i + PCI_IOV_RESOURCES));
res = dev->resource + PCI_IOV_RESOURCES + i;
if (res->parent)
nres++;
return -ENOMEM;
}
+ if (pci_enable_resources(dev, bars)) {
+ dev_err(&dev->dev, "SR-IOV: IOV BARS not allocated\n");
+ return -ENOMEM;
+ }
+
if (iov->link != dev->devfn) {
pdev = pci_get_slot(dev->bus, iov->link);
if (!pdev)
error = platform_pci_set_power_state(dev, state);
if (!error)
pci_update_current_state(dev, state);
+ /* Fall back to PCI_D0 if native PM is not supported */
+ if (!dev->pm_cap)
+ dev->current_state = PCI_D0;
} else {
error = -ENODEV;
/* Fall back to PCI_D0 if native PM is not supported */
if (atomic_add_return(1, &dev->enable_cnt) > 1)
return 0; /* already enabled */
- for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
+ /* only skip sriov related */
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++)
+ if (dev->resource[i].flags & flags)
+ bars |= (1 << i);
+ for (i = PCI_BRIDGE_RESOURCES; i < DEVICE_COUNT_RESOURCE; i++)
if (dev->resource[i].flags & flags)
bars |= (1 << i);
.update_status = dell_send_intensity,
};
-static void touchpad_led_on()
+static void touchpad_led_on(void)
{
int command = 0x97;
char data = 1;
i8042_command(&data, command | 1 << 12);
}
-static void touchpad_led_off()
+static void touchpad_led_off(void)
{
int command = 0x97;
char data = 2;
int illumination_supported:1;
int video_supported:1;
int fan_supported:1;
+ int system_event_supported:1;
struct mutex mutex;
};
u32 hci_result;
u32 value;
- if (!dev->key_event_valid) {
+ if (!dev->key_event_valid && dev->system_event_supported) {
hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
if (hci_result == HCI_SUCCESS) {
dev->key_event_valid = 1;
/* enable event fifo */
hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
+ if (hci_result == HCI_SUCCESS)
+ dev->system_event_supported = 1;
props.type = BACKLIGHT_PLATFORM;
props.max_brightness = HCI_LCD_BRIGHTNESS_LEVELS - 1;
{
struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev);
u32 hci_result, value;
+ int retries = 3;
- if (event != 0x80)
+ if (!dev->system_event_supported || event != 0x80)
return;
+
do {
hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
- if (hci_result == HCI_SUCCESS) {
+ switch (hci_result) {
+ case HCI_SUCCESS:
if (value == 0x100)
continue;
/* act on key press; ignore key release */
pr_info("Unknown key %x\n",
value);
}
- } else if (hci_result == HCI_NOT_SUPPORTED) {
+ break;
+ case HCI_NOT_SUPPORTED:
/* This is a workaround for an unresolved issue on
* some machines where system events sporadically
* become disabled. */
hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
pr_notice("Re-enabled hotkeys\n");
+ /* fall through */
+ default:
+ retries--;
+ break;
}
- } while (hci_result != HCI_EMPTY);
+ } while (retries && hci_result != HCI_EMPTY);
}
#define PMIC_BATT_CHR_SBATDET_MASK (1 << 5)
#define PMIC_BATT_CHR_SDCLMT_MASK (1 << 6)
#define PMIC_BATT_CHR_SUSBOVP_MASK (1 << 7)
-#define PMIC_BATT_CHR_EXCPT_MASK 0xC6
+#define PMIC_BATT_CHR_EXCPT_MASK 0x86
+
#define PMIC_BATT_ADC_ACCCHRG_MASK (1 << 31)
#define PMIC_BATT_ADC_ACCCHRGVAL_MASK 0x7FFFFFFF
pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
pmic_battery_log_event(BATT_EVENT_BATOVP_EXCPT);
batt_exception = 1;
- } else if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
- pbi->batt_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
- pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
- pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
- batt_exception = 1;
} else if (r8 & PMIC_BATT_CHR_STEMP_MASK) {
pbi->batt_health = POWER_SUPPLY_HEALTH_OVERHEAT;
pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
batt_exception = 1;
} else {
pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
+ if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
+ /* PMIC will change charging current automatically */
+ pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
+ }
}
}
static int ptp_clock_getres(struct posix_clock *pc, struct timespec *tp)
{
- return 1; /* always round timer functions to one nanosecond */
+ tp->tv_sec = 0;
+ tp->tv_nsec = 1;
+ return 0;
}
static int ptp_clock_settime(struct posix_clock *pc, const struct timespec *tp)
INIT_WORK(&priv->idb_work, tsi721_db_dpc);
/* Allocate buffer for inbound doorbells queue */
- priv->idb_base = dma_alloc_coherent(&priv->pdev->dev,
+ priv->idb_base = dma_zalloc_coherent(&priv->pdev->dev,
IDB_QSIZE * TSI721_IDB_ENTRY_SIZE,
&priv->idb_dma, GFP_KERNEL);
if (!priv->idb_base)
return -ENOMEM;
- memset(priv->idb_base, 0, IDB_QSIZE * TSI721_IDB_ENTRY_SIZE);
-
dev_dbg(&priv->pdev->dev, "Allocated IDB buffer @ %p (phys = %llx)\n",
priv->idb_base, (unsigned long long)priv->idb_dma);
*/
/* Allocate space for DMA descriptors */
- bd_ptr = dma_alloc_coherent(&priv->pdev->dev,
+ bd_ptr = dma_zalloc_coherent(&priv->pdev->dev,
bd_num * sizeof(struct tsi721_dma_desc),
&bd_phys, GFP_KERNEL);
if (!bd_ptr)
priv->bdma[chnum].bd_phys = bd_phys;
priv->bdma[chnum].bd_base = bd_ptr;
- memset(bd_ptr, 0, bd_num * sizeof(struct tsi721_dma_desc));
-
dev_dbg(&priv->pdev->dev, "DMA descriptors @ %p (phys = %llx)\n",
bd_ptr, (unsigned long long)bd_phys);
sts_size = (bd_num >= TSI721_DMA_MINSTSSZ) ?
bd_num : TSI721_DMA_MINSTSSZ;
sts_size = roundup_pow_of_two(sts_size);
- sts_ptr = dma_alloc_coherent(&priv->pdev->dev,
+ sts_ptr = dma_zalloc_coherent(&priv->pdev->dev,
sts_size * sizeof(struct tsi721_dma_sts),
&sts_phys, GFP_KERNEL);
if (!sts_ptr) {
priv->bdma[chnum].sts_base = sts_ptr;
priv->bdma[chnum].sts_size = sts_size;
- memset(sts_ptr, 0, sts_size);
-
dev_dbg(&priv->pdev->dev,
"desc status FIFO @ %p (phys = %llx) size=0x%x\n",
sts_ptr, (unsigned long long)sts_phys, sts_size);
/* Outbound message descriptor status FIFO allocation */
priv->omsg_ring[mbox].sts_size = roundup_pow_of_two(entries + 1);
- priv->omsg_ring[mbox].sts_base = dma_alloc_coherent(&priv->pdev->dev,
+ priv->omsg_ring[mbox].sts_base = dma_zalloc_coherent(&priv->pdev->dev,
priv->omsg_ring[mbox].sts_size *
sizeof(struct tsi721_dma_sts),
&priv->omsg_ring[mbox].sts_phys, GFP_KERNEL);
goto out_desc;
}
- memset(priv->omsg_ring[mbox].sts_base, 0,
- entries * sizeof(struct tsi721_dma_sts));
-
/*
* Configure Outbound Messaging Engine
*/
INIT_LIST_HEAD(&mport->dbells);
rio_init_dbell_res(&mport->riores[RIO_DOORBELL_RESOURCE], 0, 0xffff);
- rio_init_mbox_res(&mport->riores[RIO_INB_MBOX_RESOURCE], 0, 0);
- rio_init_mbox_res(&mport->riores[RIO_OUTB_MBOX_RESOURCE], 0, 0);
+ rio_init_mbox_res(&mport->riores[RIO_INB_MBOX_RESOURCE], 0, 3);
+ rio_init_mbox_res(&mport->riores[RIO_OUTB_MBOX_RESOURCE], 0, 3);
strcpy(mport->name, "Tsi721 mport");
/* Hook up interrupt handler */
const struct pci_device_id *id)
{
struct tsi721_device *priv;
- int i;
+ int i, cap;
int err;
u32 regval;
dev_info(&pdev->dev, "Unable to set consistent DMA mask\n");
}
- /* Clear "no snoop" and "relaxed ordering" bits. */
- pci_read_config_dword(pdev, 0x40 + PCI_EXP_DEVCTL, ®val);
- regval &= ~(PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN);
- pci_write_config_dword(pdev, 0x40 + PCI_EXP_DEVCTL, regval);
+ cap = pci_pcie_cap(pdev);
+ BUG_ON(cap == 0);
+
+ /* Clear "no snoop" and "relaxed ordering" bits, use default MRRS. */
+ pci_read_config_dword(pdev, cap + PCI_EXP_DEVCTL, ®val);
+ regval &= ~(PCI_EXP_DEVCTL_READRQ | PCI_EXP_DEVCTL_RELAX_EN |
+ PCI_EXP_DEVCTL_NOSNOOP_EN);
+ regval |= 0x2 << MAX_READ_REQUEST_SZ_SHIFT;
+ pci_write_config_dword(pdev, cap + PCI_EXP_DEVCTL, regval);
+
+ /* Adjust PCIe completion timeout. */
+ pci_read_config_dword(pdev, cap + PCI_EXP_DEVCTL2, ®val);
+ regval &= ~(0x0f);
+ pci_write_config_dword(pdev, cap + PCI_EXP_DEVCTL2, regval | 0x2);
/*
* FIXUP: correct offsets of MSI-X tables in the MSI-X Capability Block
#define TSI721_MSIXPBA_OFFSET 0x2a000
#define TSI721_PCIECFG_EPCTL 0x400
+#define MAX_READ_REQUEST_SZ_SHIFT 12
+
/*
* Event Management Registers
*/
break;
}
- if (!ri)
+ if (i == ARRAY_SIZE(aat2870_regulators))
return NULL;
ri->enable_addr = AAT2870_LDO_EN;
list_del(&rdev->list);
if (rdev->supply)
regulator_put(rdev->supply);
- device_unregister(&rdev->dev);
kfree(rdev->constraints);
+ device_unregister(&rdev->dev);
mutex_unlock(®ulator_list_mutex);
}
EXPORT_SYMBOL_GPL(regulator_unregister);
switch (id) {
case TPS65910_REG_VDD1:
- dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+ dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
if (dcdc_mult == 1)
dcdc_mult--;
- vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+ vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
tps65910_modify_bits(pmic, TPS65910_VDD1,
(dcdc_mult << VDD1_VGAIN_SEL_SHIFT),
tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel);
break;
case TPS65910_REG_VDD2:
- dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+ dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
if (dcdc_mult == 1)
dcdc_mult--;
- vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+ vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
tps65910_modify_bits(pmic, TPS65910_VDD2,
(dcdc_mult << VDD2_VGAIN_SEL_SHIFT),
switch (id) {
case TPS65910_REG_VDD1:
case TPS65910_REG_VDD2:
- mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+ mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
volt = VDD1_2_MIN_VOLT +
- (selector % VDD1_2_NUM_VOLTS) * VDD1_2_OFFSET;
+ (selector % VDD1_2_NUM_VOLT_FINE) * VDD1_2_OFFSET;
break;
case TPS65911_REG_VDDCTRL:
volt = VDDCTRL_MIN_VOLT + (selector * VDDCTRL_OFFSET);
if (i == TPS65910_REG_VDD1 || i == TPS65910_REG_VDD2) {
pmic->desc[i].ops = &tps65910_ops_dcdc;
+ pmic->desc[i].n_voltages = VDD1_2_NUM_VOLT_FINE *
+ VDD1_2_NUM_VOLT_COARSE;
} else if (i == TPS65910_REG_VDD3) {
if (tps65910_chip_id(tps65910) == TPS65910)
pmic->desc[i].ops = &tps65910_ops_vdd3;
#define VREG_TYPE 1
#define VREG_REMAP 2
#define VREG_DEDICATED 3 /* LDO control */
+#define VREG_VOLTAGE_SMPS_4030 9
/* TWL6030 register offsets */
#define VREG_TRANS 1
#define VREG_STATE 2
.get_status = twl4030reg_get_status,
};
+static int
+twl4030smps_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV,
+ unsigned *selector)
+{
+ struct twlreg_info *info = rdev_get_drvdata(rdev);
+ int vsel = DIV_ROUND_UP(min_uV - 600000, 12500);
+
+ twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE_SMPS_4030,
+ vsel);
+ return 0;
+}
+
+static int twl4030smps_get_voltage(struct regulator_dev *rdev)
+{
+ struct twlreg_info *info = rdev_get_drvdata(rdev);
+ int vsel = twlreg_read(info, TWL_MODULE_PM_RECEIVER,
+ VREG_VOLTAGE_SMPS_4030);
+
+ return vsel * 12500 + 600000;
+}
+
+static struct regulator_ops twl4030smps_ops = {
+ .set_voltage = twl4030smps_set_voltage,
+ .get_voltage = twl4030smps_get_voltage,
+};
+
static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned index)
{
struct twlreg_info *info = rdev_get_drvdata(rdev);
}, \
}
+#define TWL4030_ADJUSTABLE_SMPS(label, offset, num, turnon_delay, remap_conf) \
+ { \
+ .base = offset, \
+ .id = num, \
+ .delay = turnon_delay, \
+ .remap = remap_conf, \
+ .desc = { \
+ .name = #label, \
+ .id = TWL4030_REG_##label, \
+ .ops = &twl4030smps_ops, \
+ .type = REGULATOR_VOLTAGE, \
+ .owner = THIS_MODULE, \
+ }, \
+ }
+
#define TWL6030_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts) { \
.base = offset, \
.min_mV = min_mVolts, \
TWL4030_ADJUSTABLE_LDO(VINTANA2, 0x43, 12, 100, 0x08),
TWL4030_FIXED_LDO(VINTDIG, 0x47, 1500, 13, 100, 0x08),
TWL4030_ADJUSTABLE_LDO(VIO, 0x4b, 14, 1000, 0x08),
- TWL4030_ADJUSTABLE_LDO(VDD1, 0x55, 15, 1000, 0x08),
- TWL4030_ADJUSTABLE_LDO(VDD2, 0x63, 16, 1000, 0x08),
+ TWL4030_ADJUSTABLE_SMPS(VDD1, 0x55, 15, 1000, 0x08),
+ TWL4030_ADJUSTABLE_SMPS(VDD2, 0x63, 16, 1000, 0x08),
TWL4030_FIXED_LDO(VUSB1V5, 0x71, 1500, 17, 100, 0x08),
TWL4030_FIXED_LDO(VUSB1V8, 0x74, 1800, 18, 100, 0x08),
TWL4030_FIXED_LDO(VUSB3V1, 0x77, 3100, 19, 150, 0x08),
*/
delta = timespec_sub(old_system, old_rtc);
delta_delta = timespec_sub(delta, old_delta);
- if (abs(delta_delta.tv_sec) >= 2) {
+ if (delta_delta.tv_sec < -2 || delta_delta.tv_sec >= 2) {
/*
* if delta_delta is too large, assume time correction
* has occured and set old_delta to the current delta.
rtc_tm_to_time(&tm, &new_rtc.tv_sec);
new_rtc.tv_nsec = 0;
- if (new_rtc.tv_sec <= old_rtc.tv_sec) {
- if (new_rtc.tv_sec < old_rtc.tv_sec)
- pr_debug("%s: time travel!\n", dev_name(&rtc->dev));
+ if (new_rtc.tv_sec < old_rtc.tv_sec) {
+ pr_debug("%s: time travel!\n", dev_name(&rtc->dev));
return 0;
}
sleep_time = timespec_sub(sleep_time,
timespec_sub(new_system, old_system));
- timekeeping_inject_sleeptime(&sleep_time);
+ if (sleep_time.tv_sec >= 0)
+ timekeeping_inject_sleeptime(&sleep_time);
return 0;
}
static struct rtc_class_ops m41t80_rtc_ops = {
.read_time = m41t80_rtc_read_time,
.set_time = m41t80_rtc_set_time,
+ /*
+ * XXX - m41t80 alarm functionality is reported broken.
+ * until it is fixed, don't register alarm functions.
+ *
.read_alarm = m41t80_rtc_read_alarm,
.set_alarm = m41t80_rtc_set_alarm,
+ */
.proc = m41t80_rtc_proc,
+ /*
+ * See above comment on broken alarm
+ *
.alarm_irq_enable = m41t80_rtc_alarm_irq_enable,
+ */
};
#if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE)
}
}
-static int puv3_rtc_remove(struct platform_device *dev)
+static int __devexit puv3_rtc_remove(struct platform_device *dev)
{
struct rtc_device *rtc = platform_get_drvdata(dev);
return 0;
}
-static int puv3_rtc_probe(struct platform_device *pdev)
+static int __devinit puv3_rtc_probe(struct platform_device *pdev)
{
struct rtc_device *rtc;
struct resource *res;
void __iomem *base = s3c_rtc_base;
int year = tm->tm_year - 100;
- clk_enable(rtc_clk);
pr_debug("set time %04d.%02d.%02d %02d:%02d:%02d\n",
1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
tm->tm_hour, tm->tm_min, tm->tm_sec);
return -EINVAL;
}
+ clk_enable(rtc_clk);
writeb(bin2bcd(tm->tm_sec), base + S3C2410_RTCSEC);
writeb(bin2bcd(tm->tm_min), base + S3C2410_RTCMIN);
writeb(bin2bcd(tm->tm_hour), base + S3C2410_RTCHOUR);
if (ipl_info.type != IPL_TYPE_FCP_DUMP)
return -ENODATA;
+ if (OLDMEM_BASE)
+ return -ENODATA;
zcore_dbf = debug_register("zcore", 4, 1, 4 * sizeof(long));
debug_register_view(zcore_dbf, &debug_sprintf_view);
int chsc_chp_vary(struct chp_id chpid, int on)
{
struct channel_path *chp = chpid_to_chp(chpid);
- struct chp_link link;
- memset(&link, 0, sizeof(struct chp_link));
- link.chpid = chpid;
/* Wait until previous actions have settled. */
css_wait_for_slow_path();
/*
/* Try to update the channel path descritor. */
chsc_determine_base_channel_path_desc(chpid, &chp->desc);
for_each_subchannel_staged(s390_subchannel_vary_chpid_on,
- __s390_vary_chpid_on, &link);
+ __s390_vary_chpid_on, &chpid);
} else
for_each_subchannel_staged(s390_subchannel_vary_chpid_off,
- NULL, &link);
+ NULL, &chpid);
return 0;
}
__u8 mda[4]; /* model dependent area */
} __attribute__ ((packed,aligned(4)));
+/*
+ * When rescheduled, todo's with higher values will overwrite those
+ * with lower values.
+ */
enum sch_todo {
SCH_TODO_NOTHING,
+ SCH_TODO_EVAL,
SCH_TODO_UNREG,
};
}
EXPORT_SYMBOL_GPL(css_sch_device_unregister);
-static void css_sch_todo(struct work_struct *work)
-{
- struct subchannel *sch;
- enum sch_todo todo;
-
- sch = container_of(work, struct subchannel, todo_work);
- /* Find out todo. */
- spin_lock_irq(sch->lock);
- todo = sch->todo;
- CIO_MSG_EVENT(4, "sch_todo: sch=0.%x.%04x, todo=%d\n", sch->schid.ssid,
- sch->schid.sch_no, todo);
- sch->todo = SCH_TODO_NOTHING;
- spin_unlock_irq(sch->lock);
- /* Perform todo. */
- if (todo == SCH_TODO_UNREG)
- css_sch_device_unregister(sch);
- /* Release workqueue ref. */
- put_device(&sch->dev);
-}
-
-/**
- * css_sched_sch_todo - schedule a subchannel operation
- * @sch: subchannel
- * @todo: todo
- *
- * Schedule the operation identified by @todo to be performed on the slow path
- * workqueue. Do nothing if another operation with higher priority is already
- * scheduled. Needs to be called with subchannel lock held.
- */
-void css_sched_sch_todo(struct subchannel *sch, enum sch_todo todo)
-{
- CIO_MSG_EVENT(4, "sch_todo: sched sch=0.%x.%04x todo=%d\n",
- sch->schid.ssid, sch->schid.sch_no, todo);
- if (sch->todo >= todo)
- return;
- /* Get workqueue ref. */
- if (!get_device(&sch->dev))
- return;
- sch->todo = todo;
- if (!queue_work(cio_work_q, &sch->todo_work)) {
- /* Already queued, release workqueue ref. */
- put_device(&sch->dev);
- }
-}
-
static void ssd_from_pmcw(struct chsc_ssd_info *ssd, struct pmcw *pmcw)
{
int i;
css_schedule_eval(schid);
}
+/**
+ * css_sched_sch_todo - schedule a subchannel operation
+ * @sch: subchannel
+ * @todo: todo
+ *
+ * Schedule the operation identified by @todo to be performed on the slow path
+ * workqueue. Do nothing if another operation with higher priority is already
+ * scheduled. Needs to be called with subchannel lock held.
+ */
+void css_sched_sch_todo(struct subchannel *sch, enum sch_todo todo)
+{
+ CIO_MSG_EVENT(4, "sch_todo: sched sch=0.%x.%04x todo=%d\n",
+ sch->schid.ssid, sch->schid.sch_no, todo);
+ if (sch->todo >= todo)
+ return;
+ /* Get workqueue ref. */
+ if (!get_device(&sch->dev))
+ return;
+ sch->todo = todo;
+ if (!queue_work(cio_work_q, &sch->todo_work)) {
+ /* Already queued, release workqueue ref. */
+ put_device(&sch->dev);
+ }
+}
+
+static void css_sch_todo(struct work_struct *work)
+{
+ struct subchannel *sch;
+ enum sch_todo todo;
+ int ret;
+
+ sch = container_of(work, struct subchannel, todo_work);
+ /* Find out todo. */
+ spin_lock_irq(sch->lock);
+ todo = sch->todo;
+ CIO_MSG_EVENT(4, "sch_todo: sch=0.%x.%04x, todo=%d\n", sch->schid.ssid,
+ sch->schid.sch_no, todo);
+ sch->todo = SCH_TODO_NOTHING;
+ spin_unlock_irq(sch->lock);
+ /* Perform todo. */
+ switch (todo) {
+ case SCH_TODO_NOTHING:
+ break;
+ case SCH_TODO_EVAL:
+ ret = css_evaluate_known_subchannel(sch, 1);
+ if (ret == -EAGAIN) {
+ spin_lock_irq(sch->lock);
+ css_sched_sch_todo(sch, todo);
+ spin_unlock_irq(sch->lock);
+ }
+ break;
+ case SCH_TODO_UNREG:
+ css_sch_device_unregister(sch);
+ break;
+ }
+ /* Release workqueue ref. */
+ put_device(&sch->dev);
+}
+
static struct idset *slow_subchannel_set;
static spinlock_t slow_subchannel_lock;
static wait_queue_head_t css_eval_wq;
*/
cdev->private->flags.resuming = 1;
cdev->private->path_new_mask = LPM_ANYPATH;
- css_schedule_eval(sch->schid);
+ css_sched_sch_todo(sch, SCH_TODO_EVAL);
spin_unlock_irq(sch->lock);
- css_complete_work();
+ css_wait_for_slow_path();
/* cdev may have been moved to a different subchannel. */
sch = to_subchannel(cdev->dev.parent);
cdev->private->pgid_reset_mask = 0;
}
-void
-ccw_device_verify_done(struct ccw_device *cdev, int err)
+static void create_fake_irb(struct irb *irb, int type)
+{
+ memset(irb, 0, sizeof(*irb));
+ if (type == FAKE_CMD_IRB) {
+ struct cmd_scsw *scsw = &irb->scsw.cmd;
+ scsw->cc = 1;
+ scsw->fctl = SCSW_FCTL_START_FUNC;
+ scsw->actl = SCSW_ACTL_START_PEND;
+ scsw->stctl = SCSW_STCTL_STATUS_PEND;
+ } else if (type == FAKE_TM_IRB) {
+ struct tm_scsw *scsw = &irb->scsw.tm;
+ scsw->x = 1;
+ scsw->cc = 1;
+ scsw->fctl = SCSW_FCTL_START_FUNC;
+ scsw->actl = SCSW_ACTL_START_PEND;
+ scsw->stctl = SCSW_STCTL_STATUS_PEND;
+ }
+}
+
+void ccw_device_verify_done(struct ccw_device *cdev, int err)
{
struct subchannel *sch;
ccw_device_done(cdev, DEV_STATE_ONLINE);
/* Deliver fake irb to device driver, if needed. */
if (cdev->private->flags.fake_irb) {
- memset(&cdev->private->irb, 0, sizeof(struct irb));
- cdev->private->irb.scsw.cmd.cc = 1;
- cdev->private->irb.scsw.cmd.fctl = SCSW_FCTL_START_FUNC;
- cdev->private->irb.scsw.cmd.actl = SCSW_ACTL_START_PEND;
- cdev->private->irb.scsw.cmd.stctl =
- SCSW_STCTL_STATUS_PEND;
+ create_fake_irb(&cdev->private->irb,
+ cdev->private->flags.fake_irb);
cdev->private->flags.fake_irb = 0;
if (cdev->handler)
cdev->handler(cdev, cdev->private->intparm,
if (cdev->private->state == DEV_STATE_VERIFY) {
/* Remember to fake irb when finished. */
if (!cdev->private->flags.fake_irb) {
- cdev->private->flags.fake_irb = 1;
+ cdev->private->flags.fake_irb = FAKE_CMD_IRB;
cdev->private->intparm = intparm;
return 0;
} else
ret = cio_set_options (sch, flags);
if (ret)
return ret;
- /* Adjust requested path mask to excluded varied off paths. */
+ /* Adjust requested path mask to exclude unusable paths. */
if (lpm) {
- lpm &= sch->opm;
+ lpm &= sch->lpm;
if (lpm == 0)
return -EACCES;
}
sch = to_subchannel(cdev->dev.parent);
if (!sch->schib.pmcw.ena)
return -EINVAL;
+ if (cdev->private->state == DEV_STATE_VERIFY) {
+ /* Remember to fake irb when finished. */
+ if (!cdev->private->flags.fake_irb) {
+ cdev->private->flags.fake_irb = FAKE_TM_IRB;
+ cdev->private->intparm = intparm;
+ return 0;
+ } else
+ /* There's already a fake I/O around. */
+ return -EBUSY;
+ }
if (cdev->private->state != DEV_STATE_ONLINE)
return -EIO;
- /* Adjust requested path mask to excluded varied off paths. */
+ /* Adjust requested path mask to exclude unusable paths. */
if (lpm) {
- lpm &= sch->opm;
+ lpm &= sch->lpm;
if (lpm == 0)
return -EACCES;
}
CDEV_TODO_UNREG_EVAL,
};
+#define FAKE_CMD_IRB 1
+#define FAKE_TM_IRB 2
+
struct ccw_device_private {
struct ccw_device *cdev;
struct subchannel *sch;
unsigned int doverify:1; /* delayed path verification */
unsigned int donotify:1; /* call notify function */
unsigned int recog_done:1; /* dev. recog. complete */
- unsigned int fake_irb:1; /* deliver faked irb */
+ unsigned int fake_irb:2; /* deliver faked irb */
unsigned int resuming:1; /* recognition while resume */
unsigned int pgroup:1; /* pathgroup is set up */
unsigned int mpath:1; /* multipathing is set up */
}
/**
- * ap_schedule_poll_timer(): Schedule poll timer.
+ * __ap_schedule_poll_timer(): Schedule poll timer.
*
* Set up the timer to run the poll tasklet
*/
-static inline void ap_schedule_poll_timer(void)
+static inline void __ap_schedule_poll_timer(void)
{
ktime_t hr_time;
spin_lock_bh(&ap_poll_timer_lock);
- if (ap_using_interrupts() || ap_suspend_flag)
- goto out;
- if (hrtimer_is_queued(&ap_poll_timer))
+ if (hrtimer_is_queued(&ap_poll_timer) || ap_suspend_flag)
goto out;
if (ktime_to_ns(hrtimer_expires_remaining(&ap_poll_timer)) <= 0) {
hr_time = ktime_set(0, poll_timeout);
spin_unlock_bh(&ap_poll_timer_lock);
}
+/**
+ * ap_schedule_poll_timer(): Schedule poll timer.
+ *
+ * Set up the timer to run the poll tasklet
+ */
+static inline void ap_schedule_poll_timer(void)
+{
+ if (ap_using_interrupts())
+ return;
+ __ap_schedule_poll_timer();
+}
+
/**
* ap_poll_read(): Receive pending reply messages from an AP device.
* @ap_dev: pointer to the AP device
*flags |= 1;
*flags |= 2;
break;
- case AP_RESPONSE_Q_FULL:
case AP_RESPONSE_RESET_IN_PROGRESS:
+ __ap_schedule_poll_timer();
+ case AP_RESPONSE_Q_FULL:
*flags |= 2;
break;
case AP_RESPONSE_MESSAGE_TOO_BIG:
rc = ap_init_queue(ap_dev->qid);
if (rc == -ENODEV)
ap_dev->unregistered = 1;
+ else
+ __ap_schedule_poll_timer();
}
static int __ap_poll_device(struct ap_device *ap_dev, unsigned long *flags)
return PTR_ERR(vqs[i]);
}
+static const char *kvm_bus_name(struct virtio_device *vdev)
+{
+ return "";
+}
+
/*
* The config ops structure as defined by virtio config
*/
.reset = kvm_reset,
.find_vqs = kvm_find_vqs,
.del_vqs = kvm_del_vqs,
+ .bus_name = kvm_bus_name,
};
/*
config LCS
def_tristate m
prompt "Lan Channel Station Interface"
- depends on CCW && NETDEVICES && (NET_ETHERNET || TR || FDDI)
+ depends on CCW && NETDEVICES && (ETHERNET || TR || FDDI)
help
Select this option if you want to use LCS networking on IBM System z.
This device driver supports Token Ring (IEEE 802.5),
#include "lcs.h"
-#if !defined(CONFIG_NET_ETHERNET) && \
+#if !defined(CONFIG_ETHERNET) && \
!defined(CONFIG_TR) && !defined(CONFIG_FDDI)
#error Cannot compile lcs.c without some net devices switched on.
#endif
int rc;
LCS_DBF_TEXT(2, trace, "strtauto");
-#ifdef CONFIG_NET_ETHERNET
+#ifdef CONFIG_ETHERNET
card->lan_type = LCS_FRAME_TYPE_ENET;
rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
if (rc == 0)
goto netdev_out;
}
switch (card->lan_type) {
-#ifdef CONFIG_NET_ETHERNET
+#ifdef CONFIG_ETHERNET
case LCS_FRAME_TYPE_ENET:
card->lan_type_trans = eth_type_trans;
dev = alloc_etherdev(0);
#include <asm/io.h>
#include <asm/uaccess.h>
+#include <asm/ebcdic.h>
#include <net/iucv/iucv.h>
#include "fsm.h"
* Debug Facility stuff
*/
#define IUCV_DBF_SETUP_NAME "iucv_setup"
-#define IUCV_DBF_SETUP_LEN 32
+#define IUCV_DBF_SETUP_LEN 64
#define IUCV_DBF_SETUP_PAGES 2
#define IUCV_DBF_SETUP_NR_AREAS 1
#define IUCV_DBF_SETUP_LEVEL 3
struct net_device *netdev;
struct connection_profile prof;
char userid[9];
+ char userdata[17];
};
/**
};
#define NETIUCV_HDRLEN (sizeof(struct ll_header))
-#define NETIUCV_BUFSIZE_MAX 32768
+#define NETIUCV_BUFSIZE_MAX 65537
#define NETIUCV_BUFSIZE_DEFAULT NETIUCV_BUFSIZE_MAX
#define NETIUCV_MTU_MAX (NETIUCV_BUFSIZE_MAX - NETIUCV_HDRLEN)
#define NETIUCV_MTU_DEFAULT 9216
return test_and_set_bit(0, &priv->tbusy);
}
-static u8 iucvMagic[16] = {
+static u8 iucvMagic_ascii[16] = {
+ 0x30, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+ 0x30, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20
+};
+
+static u8 iucvMagic_ebcdic[16] = {
0xF0, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
0xF0, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40
};
*
* @returns The printable string (static data!!)
*/
-static char *netiucv_printname(char *name)
+static char *netiucv_printname(char *name, int len)
{
- static char tmp[9];
+ static char tmp[17];
char *p = tmp;
- memcpy(tmp, name, 8);
- tmp[8] = '\0';
- while (*p && (!isspace(*p)))
+ memcpy(tmp, name, len);
+ tmp[len] = '\0';
+ while (*p && ((p - tmp) < len) && (!isspace(*p)))
p++;
*p = '\0';
return tmp;
}
+static char *netiucv_printuser(struct iucv_connection *conn)
+{
+ static char tmp_uid[9];
+ static char tmp_udat[17];
+ static char buf[100];
+
+ if (memcmp(conn->userdata, iucvMagic_ebcdic, 16)) {
+ tmp_uid[8] = '\0';
+ tmp_udat[16] = '\0';
+ memcpy(tmp_uid, conn->userid, 8);
+ memcpy(tmp_uid, netiucv_printname(tmp_uid, 8), 8);
+ memcpy(tmp_udat, conn->userdata, 16);
+ EBCASC(tmp_udat, 16);
+ memcpy(tmp_udat, netiucv_printname(tmp_udat, 16), 16);
+ sprintf(buf, "%s.%s", tmp_uid, tmp_udat);
+ return buf;
+ } else
+ return netiucv_printname(conn->userid, 8);
+}
+
/**
* States of the interface statemachine.
*/
{
struct iucv_connection *conn = path->private;
struct iucv_event ev;
+ static char tmp_user[9];
+ static char tmp_udat[17];
int rc;
- if (memcmp(iucvMagic, ipuser, 16))
- /* ipuser must match iucvMagic. */
- return -EINVAL;
rc = -EINVAL;
+ memcpy(tmp_user, netiucv_printname(ipvmid, 8), 8);
+ memcpy(tmp_udat, ipuser, 16);
+ EBCASC(tmp_udat, 16);
read_lock_bh(&iucv_connection_rwlock);
list_for_each_entry(conn, &iucv_connection_list, list) {
- if (strncmp(ipvmid, conn->userid, 8))
+ if (strncmp(ipvmid, conn->userid, 8) ||
+ strncmp(ipuser, conn->userdata, 16))
continue;
/* Found a matching connection for this path. */
conn->path = path;
fsm_event(conn->fsm, CONN_EVENT_CONN_REQ, &ev);
rc = 0;
}
+ IUCV_DBF_TEXT_(setup, 2, "Connection requested for %s.%s\n",
+ tmp_user, netiucv_printname(tmp_udat, 16));
read_unlock_bh(&iucv_connection_rwlock);
return rc;
}
conn->path = path;
path->msglim = NETIUCV_QUEUELEN_DEFAULT;
path->flags = 0;
- rc = iucv_path_accept(path, &netiucv_handler, NULL, conn);
+ rc = iucv_path_accept(path, &netiucv_handler, conn->userdata , conn);
if (rc) {
IUCV_DBF_TEXT_(setup, 2, "rc %d from iucv_accept", rc);
return;
IUCV_DBF_TEXT(trace, 3, __func__);
fsm_deltimer(&conn->timer);
- iucv_path_sever(conn->path, NULL);
+ iucv_path_sever(conn->path, conn->userdata);
fsm_newstate(fi, CONN_STATE_STARTWAIT);
}
IUCV_DBF_TEXT(trace, 3, __func__);
fsm_deltimer(&conn->timer);
- iucv_path_sever(conn->path, NULL);
- dev_info(privptr->dev, "The peer interface of the IUCV device"
- " has closed the connection\n");
+ iucv_path_sever(conn->path, conn->userdata);
+ dev_info(privptr->dev, "The peer z/VM guest %s has closed the "
+ "connection\n", netiucv_printuser(conn));
IUCV_DBF_TEXT(data, 2,
"conn_action_connsever: Remote dropped connection\n");
fsm_newstate(fi, CONN_STATE_STARTWAIT);
IUCV_DBF_TEXT(trace, 3, __func__);
fsm_newstate(fi, CONN_STATE_STARTWAIT);
- IUCV_DBF_TEXT_(setup, 2, "%s('%s'): connecting ...\n",
- netdev->name, conn->userid);
/*
* We must set the state before calling iucv_connect because the
fsm_newstate(fi, CONN_STATE_SETUPWAIT);
conn->path = iucv_path_alloc(NETIUCV_QUEUELEN_DEFAULT, 0, GFP_KERNEL);
+ IUCV_DBF_TEXT_(setup, 2, "%s: connecting to %s ...\n",
+ netdev->name, netiucv_printuser(conn));
+
rc = iucv_path_connect(conn->path, &netiucv_handler, conn->userid,
- NULL, iucvMagic, conn);
+ NULL, conn->userdata, conn);
switch (rc) {
case 0:
netdev->tx_queue_len = conn->path->msglim;
case 11:
dev_warn(privptr->dev,
"The IUCV device failed to connect to z/VM guest %s\n",
- netiucv_printname(conn->userid));
+ netiucv_printname(conn->userid, 8));
fsm_newstate(fi, CONN_STATE_STARTWAIT);
break;
case 12:
dev_warn(privptr->dev,
"The IUCV device failed to connect to the peer on z/VM"
- " guest %s\n", netiucv_printname(conn->userid));
+ " guest %s\n", netiucv_printname(conn->userid, 8));
fsm_newstate(fi, CONN_STATE_STARTWAIT);
break;
case 13:
dev_err(privptr->dev,
"z/VM guest %s has too many IUCV connections"
" to connect with the IUCV device\n",
- netiucv_printname(conn->userid));
+ netiucv_printname(conn->userid, 8));
fsm_newstate(fi, CONN_STATE_CONNERR);
break;
case 15:
netiucv_purge_skb_queue(&conn->collect_queue);
if (conn->path) {
IUCV_DBF_TEXT(trace, 5, "calling iucv_path_sever\n");
- iucv_path_sever(conn->path, iucvMagic);
+ iucv_path_sever(conn->path, conn->userdata);
kfree(conn->path);
conn->path = NULL;
}
fsm_newstate(fi, DEV_STATE_RUNNING);
dev_info(privptr->dev,
"The IUCV device has been connected"
- " successfully to %s\n", privptr->conn->userid);
+ " successfully to %s\n",
+ netiucv_printuser(privptr->conn));
IUCV_DBF_TEXT(setup, 3,
"connection is up and running\n");
break;
struct netiucv_priv *priv = dev_get_drvdata(dev);
IUCV_DBF_TEXT(trace, 5, __func__);
- return sprintf(buf, "%s\n", netiucv_printname(priv->conn->userid));
+ return sprintf(buf, "%s\n", netiucv_printuser(priv->conn));
}
-static ssize_t user_write(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+static int netiucv_check_user(const char *buf, size_t count, char *username,
+ char *userdata)
{
- struct netiucv_priv *priv = dev_get_drvdata(dev);
- struct net_device *ndev = priv->conn->netdev;
- char *p;
- char *tmp;
- char username[9];
- int i;
- struct iucv_connection *cp;
+ const char *p;
+ int i;
- IUCV_DBF_TEXT(trace, 3, __func__);
- if (count > 9) {
- IUCV_DBF_TEXT_(setup, 2,
- "%d is length of username\n", (int) count);
+ p = strchr(buf, '.');
+ if ((p && ((count > 26) ||
+ ((p - buf) > 8) ||
+ (buf + count - p > 18))) ||
+ (!p && (count > 9))) {
+ IUCV_DBF_TEXT(setup, 2, "conn_write: too long\n");
return -EINVAL;
}
- tmp = strsep((char **) &buf, "\n");
- for (i = 0, p = tmp; i < 8 && *p; i++, p++) {
- if (isalnum(*p) || (*p == '$')) {
- username[i]= toupper(*p);
+ for (i = 0, p = buf; i < 8 && *p && *p != '.'; i++, p++) {
+ if (isalnum(*p) || *p == '$') {
+ username[i] = toupper(*p);
continue;
}
- if (*p == '\n') {
+ if (*p == '\n')
/* trailing lf, grr */
break;
- }
IUCV_DBF_TEXT_(setup, 2,
- "username: invalid character %c\n", *p);
+ "conn_write: invalid character %02x\n", *p);
return -EINVAL;
}
while (i < 8)
username[i++] = ' ';
username[8] = '\0';
+ if (*p == '.') {
+ p++;
+ for (i = 0; i < 16 && *p; i++, p++) {
+ if (*p == '\n')
+ break;
+ userdata[i] = toupper(*p);
+ }
+ while (i > 0 && i < 16)
+ userdata[i++] = ' ';
+ } else
+ memcpy(userdata, iucvMagic_ascii, 16);
+ userdata[16] = '\0';
+ ASCEBC(userdata, 16);
+
+ return 0;
+}
+
+static ssize_t user_write(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct netiucv_priv *priv = dev_get_drvdata(dev);
+ struct net_device *ndev = priv->conn->netdev;
+ char username[9];
+ char userdata[17];
+ int rc;
+ struct iucv_connection *cp;
+
+ IUCV_DBF_TEXT(trace, 3, __func__);
+ rc = netiucv_check_user(buf, count, username, userdata);
+ if (rc)
+ return rc;
+
if (memcmp(username, priv->conn->userid, 9) &&
(ndev->flags & (IFF_UP | IFF_RUNNING))) {
/* username changed while the interface is active. */
}
read_lock_bh(&iucv_connection_rwlock);
list_for_each_entry(cp, &iucv_connection_list, list) {
- if (!strncmp(username, cp->userid, 9) && cp->netdev != ndev) {
+ if (!strncmp(username, cp->userid, 9) &&
+ !strncmp(userdata, cp->userdata, 17) && cp->netdev != ndev) {
read_unlock_bh(&iucv_connection_rwlock);
- IUCV_DBF_TEXT_(setup, 2, "user_write: Connection "
- "to %s already exists\n", username);
+ IUCV_DBF_TEXT_(setup, 2, "user_write: Connection to %s "
+ "already exists\n", netiucv_printuser(cp));
return -EEXIST;
}
}
read_unlock_bh(&iucv_connection_rwlock);
memcpy(priv->conn->userid, username, 9);
+ memcpy(priv->conn->userdata, userdata, 17);
return count;
}
bs1 = simple_strtoul(buf, &e, 0);
if (e && (!isspace(*e))) {
- IUCV_DBF_TEXT_(setup, 2, "buffer_write: invalid char %c\n", *e);
+ IUCV_DBF_TEXT_(setup, 2, "buffer_write: invalid char %02x\n",
+ *e);
return -EINVAL;
}
if (bs1 > NETIUCV_BUFSIZE_MAX) {
* Add it to the list of netiucv connections;
*/
static struct iucv_connection *netiucv_new_connection(struct net_device *dev,
- char *username)
+ char *username,
+ char *userdata)
{
struct iucv_connection *conn;
fsm_settimer(conn->fsm, &conn->timer);
fsm_newstate(conn->fsm, CONN_STATE_INVALID);
+ if (userdata)
+ memcpy(conn->userdata, userdata, 17);
if (username) {
memcpy(conn->userid, username, 9);
fsm_newstate(conn->fsm, CONN_STATE_STOPPED);
*/
static void netiucv_remove_connection(struct iucv_connection *conn)
{
+
IUCV_DBF_TEXT(trace, 3, __func__);
write_lock_bh(&iucv_connection_rwlock);
list_del_init(&conn->list);
fsm_deltimer(&conn->timer);
netiucv_purge_skb_queue(&conn->collect_queue);
if (conn->path) {
- iucv_path_sever(conn->path, iucvMagic);
+ iucv_path_sever(conn->path, conn->userdata);
kfree(conn->path);
conn->path = NULL;
}
/**
* Allocate and initialize everything of a net device.
*/
-static struct net_device *netiucv_init_netdevice(char *username)
+static struct net_device *netiucv_init_netdevice(char *username, char *userdata)
{
struct netiucv_priv *privptr;
struct net_device *dev;
netiucv_setup_netdevice);
if (!dev)
return NULL;
+ if (dev_alloc_name(dev, dev->name) < 0)
+ goto out_netdev;
privptr = netdev_priv(dev);
privptr->fsm = init_fsm("netiucvdev", dev_state_names,
if (!privptr->fsm)
goto out_netdev;
- privptr->conn = netiucv_new_connection(dev, username);
+ privptr->conn = netiucv_new_connection(dev, username, userdata);
if (!privptr->conn) {
IUCV_DBF_TEXT(setup, 2, "NULL from netiucv_new_connection\n");
goto out_fsm;
static ssize_t conn_write(struct device_driver *drv,
const char *buf, size_t count)
{
- const char *p;
char username[9];
- int i, rc;
+ char userdata[17];
+ int rc;
struct net_device *dev;
struct netiucv_priv *priv;
struct iucv_connection *cp;
IUCV_DBF_TEXT(trace, 3, __func__);
- if (count>9) {
- IUCV_DBF_TEXT(setup, 2, "conn_write: too long\n");
- return -EINVAL;
- }
-
- for (i = 0, p = buf; i < 8 && *p; i++, p++) {
- if (isalnum(*p) || *p == '$') {
- username[i] = toupper(*p);
- continue;
- }
- if (*p == '\n')
- /* trailing lf, grr */
- break;
- IUCV_DBF_TEXT_(setup, 2,
- "conn_write: invalid character %c\n", *p);
- return -EINVAL;
- }
- while (i < 8)
- username[i++] = ' ';
- username[8] = '\0';
+ rc = netiucv_check_user(buf, count, username, userdata);
+ if (rc)
+ return rc;
read_lock_bh(&iucv_connection_rwlock);
list_for_each_entry(cp, &iucv_connection_list, list) {
- if (!strncmp(username, cp->userid, 9)) {
+ if (!strncmp(username, cp->userid, 9) &&
+ !strncmp(userdata, cp->userdata, 17)) {
read_unlock_bh(&iucv_connection_rwlock);
- IUCV_DBF_TEXT_(setup, 2, "conn_write: Connection "
- "to %s already exists\n", username);
+ IUCV_DBF_TEXT_(setup, 2, "conn_write: Connection to %s "
+ "already exists\n", netiucv_printuser(cp));
return -EEXIST;
}
}
read_unlock_bh(&iucv_connection_rwlock);
- dev = netiucv_init_netdevice(username);
+ dev = netiucv_init_netdevice(username, userdata);
if (!dev) {
IUCV_DBF_TEXT(setup, 2, "NULL from netiucv_init_netdevice\n");
return -ENODEV;
if (rc)
goto out_unreg;
- dev_info(priv->dev, "The IUCV interface to %s has been"
- " established successfully\n", netiucv_printname(username));
+ dev_info(priv->dev, "The IUCV interface to %s has been established "
+ "successfully\n",
+ netiucv_printuser(priv->conn));
return count;
#define QETH_IN_BUF_COUNT_MAX 128
#define QETH_MAX_BUFFER_ELEMENTS(card) ((card)->qdio.in_buf_size >> 12)
#define QETH_IN_BUF_REQUEUE_THRESHOLD(card) \
- ((card)->ssqd.qdioac1 & AC1_SIGA_INPUT_NEEDED ? 1 : \
- ((card)->qdio.in_buf_pool.buf_count / 2))
+ ((card)->qdio.in_buf_pool.buf_count / 2)
/* buffers we have to be behind before we get a PCI */
#define QETH_PCI_THRESHOLD_A(card) ((card)->qdio.in_buf_pool.buf_count+1)
static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
struct qeth_qdio_out_buffer *buf,
enum qeth_qdio_buffer_states newbufstate);
-
+static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
static inline const char *qeth_get_cardname(struct qeth_card *card)
{
static inline void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q,
int bidx, int forced_cleanup)
{
+ if (q->card->options.cq != QETH_CQ_ENABLED)
+ return;
+
if (q->bufs[bidx]->next_pending != NULL) {
struct qeth_qdio_out_buffer *head = q->bufs[bidx];
struct qeth_qdio_out_buffer *c = q->bufs[bidx]->next_pending;
}
}
+ if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) ==
+ QETH_QDIO_BUF_HANDLED_DELAYED)) {
+ /* for recovery situations */
+ q->bufs[bidx]->aob = q->bufstates[bidx].aob;
+ qeth_init_qdio_out_buf(q, bidx);
+ QETH_CARD_TEXT(q->card, 2, "clprecov");
+ }
}
notification = TX_NOTIFY_OK;
} else {
BUG_ON(atomic_read(&buffer->state) != QETH_QDIO_BUF_PENDING);
-
atomic_set(&buffer->state, QETH_QDIO_BUF_IN_CQ);
notification = TX_NOTIFY_DELAYED_OK;
}
buffer->aob = NULL;
qeth_clear_output_buffer(buffer->q, buffer,
- QETH_QDIO_BUF_HANDLED_DELAYED);
+ QETH_QDIO_BUF_HANDLED_DELAYED);
+
/* from here on: do not touch buffer anymore */
qdio_release_aob(aob);
}
void qeth_schedule_recovery(struct qeth_card *card)
{
QETH_CARD_TEXT(card, 2, "startrec");
- WARN_ON(1);
if (qeth_set_thread_start_bit(card, QETH_RECOVER_THREAD) == 0)
schedule_work(&card->kernel_thread_starter);
}
static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
{
struct sk_buff *skb;
+ struct iucv_sock *iucv;
+ int notify_general_error = 0;
+
+ if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING)
+ notify_general_error = 1;
+
+ /* release may never happen from within CQ tasklet scope */
+ BUG_ON(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ);
skb = skb_dequeue(&buf->skb_list);
while (skb) {
QETH_CARD_TEXT(buf->q->card, 5, "skbr");
QETH_CARD_TEXT_(buf->q->card, 5, "%lx", (long) skb);
+ if (notify_general_error && skb->protocol == ETH_P_AF_IUCV) {
+ if (skb->sk) {
+ iucv = iucv_sk(skb->sk);
+ iucv->sk_txnotify(skb, TX_NOTIFY_GENERALERROR);
+ }
+ }
atomic_dec(&skb->users);
dev_kfree_skb_any(skb);
skb = skb_dequeue(&buf->skb_list);
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
if (!q->bufs[j])
continue;
- qeth_cleanup_handled_pending(q, j, free);
+ qeth_cleanup_handled_pending(q, j, 1);
qeth_clear_output_buffer(q, q->bufs[j], QETH_QDIO_BUF_EMPTY);
if (free) {
kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
qeth_free_cq(card);
cancel_delayed_work_sync(&card->buffer_reclaim_work);
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j)
- kfree_skb(card->qdio.in_q->bufs[j].rx_skb);
+ dev_kfree_skb_any(card->qdio.in_q->bufs[j].rx_skb);
kfree(card->qdio.in_q);
card->qdio.in_q = NULL;
/* inbound buffer pool */
static void qeth_start_kernel_thread(struct work_struct *work)
{
+ struct task_struct *ts;
struct qeth_card *card = container_of(work, struct qeth_card,
kernel_thread_starter);
QETH_CARD_TEXT(card , 2, "strthrd");
if (card->read.state != CH_STATE_UP &&
card->write.state != CH_STATE_UP)
return;
- if (qeth_do_start_thread(card, QETH_RECOVER_THREAD))
- kthread_run(card->discipline.recover, (void *) card,
+ if (qeth_do_start_thread(card, QETH_RECOVER_THREAD)) {
+ ts = kthread_run(card->discipline.recover, (void *)card,
"qeth_recover");
+ if (IS_ERR(ts)) {
+ qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
+ qeth_clear_thread_running_bit(card,
+ QETH_RECOVER_THREAD);
+ }
+ }
}
static int qeth_setup_card(struct qeth_card *card)
spin_unlock_bh(&card->vlanlock);
}
-static void qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct qeth_card *card = dev->ml_priv;
struct qeth_vlan_vid *id;
QETH_CARD_TEXT_(card, 4, "aid:%d", vid);
if (!vid)
- return;
+ return 0;
if (card->info.type == QETH_CARD_TYPE_OSM) {
QETH_CARD_TEXT(card, 3, "aidOSM");
- return;
+ return 0;
}
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "aidREC");
- return;
+ return 0;
}
id = kmalloc(sizeof(struct qeth_vlan_vid), GFP_ATOMIC);
if (id) {
spin_lock_bh(&card->vlanlock);
list_add_tail(&id->list, &card->vid_list);
spin_unlock_bh(&card->vlanlock);
+ } else {
+ return -ENOMEM;
}
+ return 0;
}
-static void qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct qeth_vlan_vid *id, *tmpid = NULL;
struct qeth_card *card = dev->ml_priv;
QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
if (card->info.type == QETH_CARD_TYPE_OSM) {
QETH_CARD_TEXT(card, 3, "kidOSM");
- return;
+ return 0;
}
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "kidREC");
- return;
+ return 0;
}
spin_lock_bh(&card->vlanlock);
list_for_each_entry(id, &card->vid_list, list) {
kfree(tmpid);
}
qeth_l2_set_multicast_list(card->dev);
+ return 0;
}
static int qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
static void qeth_l2_shutdown(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ qeth_set_allowed_threads(card, 0, 1);
if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
qeth_qdio_clear_card(card, 0);
qeth_l3_free_vlan_addresses6(card, vid);
}
-static void qeth_l3_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l3_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
struct qeth_card *card = dev->ml_priv;
set_bit(vid, card->active_vlans);
- return;
+ return 0;
}
-static void qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
struct qeth_card *card = dev->ml_priv;
unsigned long flags;
QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "kidREC");
- return;
+ return 0;
}
spin_lock_irqsave(&card->vlanlock, flags);
/* unregister IP addresses of vlan device */
clear_bit(vid, card->active_vlans);
spin_unlock_irqrestore(&card->vlanlock, flags);
qeth_l3_set_multicast_list(card->dev);
+ return 0;
}
static inline int qeth_l3_rebuild_skb(struct qeth_card *card,
struct neighbour *n = NULL;
struct dst_entry *dst;
+ rcu_read_lock();
dst = skb_dst(skb);
if (dst)
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
if (n) {
cast_type = n->type;
+ rcu_read_unlock();
if ((cast_type == RTN_BROADCAST) ||
(cast_type == RTN_MULTICAST) ||
(cast_type == RTN_ANYCAST))
else
return RTN_UNSPEC;
}
+ rcu_read_unlock();
+
/* try something else */
if (skb->protocol == ETH_P_IPV6)
return (skb_network_header(skb)[24] == 0xff) ?
}
hdr->hdr.l3.length = skb->len - sizeof(struct qeth_hdr);
+
+ rcu_read_lock();
dst = skb_dst(skb);
if (dst)
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
if (ipv == 4) {
/* IPv4 */
hdr->hdr.l3.flags = qeth_l3_get_qeth_hdr_flags4(cast_type);
QETH_CAST_UNICAST | QETH_HDR_PASSTHRU;
}
}
+ rcu_read_unlock();
}
static inline void qeth_l3_hdr_csum(struct qeth_card *card,
return 0;
}
-static u32 qeth_l3_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t qeth_l3_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct qeth_card *card = dev->ml_priv;
return features;
}
-static int qeth_l3_set_features(struct net_device *dev, u32 features)
+static int qeth_l3_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct qeth_card *card = dev->ml_priv;
u32 changed = dev->features ^ features;
else
netif_carrier_off(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
+ rtnl_lock();
if (recovery_mode)
__qeth_l3_open(card->dev);
- else {
- rtnl_lock();
+ else
dev_open(card->dev);
- rtnl_unlock();
- }
qeth_l3_set_multicast_list(card->dev);
+ rtnl_unlock();
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
card->info.hwtrap = 1;
}
qeth_l3_stop_card(card, recovery_mode);
+ if ((card->options.cq == QETH_CQ_ENABLED) && card->dev) {
+ rtnl_lock();
+ call_netdevice_notifiers(NETDEV_REBOOT, card->dev);
+ rtnl_unlock();
+ }
rc = ccw_device_set_offline(CARD_DDEV(card));
rc2 = ccw_device_set_offline(CARD_WDEV(card));
rc3 = ccw_device_set_offline(CARD_RDEV(card));
static void qeth_l3_shutdown(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ qeth_set_allowed_threads(card, 0, 1);
if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
qeth_qdio_clear_card(card, 0);
QETH_IN_BUF_COUNT_MAX)
qeth_realloc_buffer_pool(card,
QETH_IN_BUF_COUNT_MAX);
- break;
} else
rc = -EPERM;
- default: /* fall through */
+ break;
+ default:
rc = -EINVAL;
}
out:
{
struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev);
+ /* if previous slave_alloc returned early, there is nothing to do */
+ if (!zfcp_sdev->port)
+ return;
+
zfcp_erp_lun_shutdown_wait(sdev, "scssd_1");
put_device(&zfcp_sdev->port->dev);
}
int ret = 0;
while (len > 0) {
- int err = bbc_i2c_writeb(client, *buf, off);
-
- if (err < 0) {
- ret = err;
+ ret = bbc_i2c_writeb(client, *buf, off);
+ if (ret < 0)
break;
- }
-
len--;
buf++;
off++;
int ret = 0;
while (len > 0) {
- int err = bbc_i2c_readb(client, buf, off);
- if (err < 0) {
- ret = err;
+ ret = bbc_i2c_readb(client, buf, off);
+ if (ret < 0)
break;
- }
len--;
buf++;
off++;
.remove = __devexit_p(bbc_i2c_remove),
};
-static int __init bbc_i2c_init(void)
-{
- return platform_driver_register(&bbc_i2c_driver);
-}
-
-static void __exit bbc_i2c_exit(void)
-{
- platform_driver_unregister(&bbc_i2c_driver);
-}
-
-module_init(bbc_i2c_init);
-module_exit(bbc_i2c_exit);
+module_platform_driver(bbc_i2c_driver);
MODULE_LICENSE("GPL");
.remove = __devexit_p(d7s_remove),
};
-static int __init d7s_init(void)
-{
- return platform_driver_register(&d7s_driver);
-}
-
-static void __exit d7s_exit(void)
-{
- platform_driver_unregister(&d7s_driver);
-}
-
-module_init(d7s_init);
-module_exit(d7s_exit);
+module_platform_driver(d7s_driver);
.remove = __devexit_p(envctrl_remove),
};
-static int __init envctrl_init(void)
-{
- return platform_driver_register(&envctrl_driver);
-}
-
-static void __exit envctrl_exit(void)
-{
- platform_driver_unregister(&envctrl_driver);
-}
+module_platform_driver(envctrl_driver);
-module_init(envctrl_init);
-module_exit(envctrl_exit);
MODULE_LICENSE("GPL");
.remove = __devexit_p(flash_remove),
};
-static int __init flash_init(void)
-{
- return platform_driver_register(&flash_driver);
-}
-
-static void __exit flash_cleanup(void)
-{
- platform_driver_unregister(&flash_driver);
-}
+module_platform_driver(flash_driver);
-module_init(flash_init);
-module_exit(flash_cleanup);
MODULE_LICENSE("GPL");
};
-static int __init uctrl_init(void)
-{
- return platform_driver_register(&uctrl_driver);
-}
-
-static void __exit uctrl_exit(void)
-{
- platform_driver_unregister(&uctrl_driver);
-}
+module_platform_driver(uctrl_driver);
-module_init(uctrl_init);
-module_exit(uctrl_exit);
MODULE_LICENSE("GPL");
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
+#include <linux/pci-aspm.h>
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
unique_id++;
}
+ pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+ PCIE_LINK_STATE_CLKPM);
+
error = pci_enable_device(pdev);
if (error)
goto out;
spin_lock(&session->lock);
task = iscsi_itt_to_task(bnx2i_conn->cls_conn->dd_data,
cqe->itt & ISCSI_CMD_RESPONSE_INDEX);
- if (!task) {
+ if (!task || !task->sc) {
spin_unlock(&session->lock);
return -EINVAL;
}
sc = task->sc;
- spin_unlock(&session->lock);
if (!blk_rq_cpu_valid(sc->request))
cpu = smp_processor_id();
else
cpu = sc->request->cpu;
+ spin_unlock(&session->lock);
+
p = &per_cpu(bnx2i_percpu, cpu);
spin_lock(&p->p_work_lock);
if (unlikely(!p->iothread)) {
csk->saddr.sin_addr.s_addr = chba->ipv4addr;
csk->rss_qid = 0;
- csk->l2t = t3_l2t_get(t3dev, dst_get_neighbour(dst), ndev);
+ csk->l2t = t3_l2t_get(t3dev, dst, ndev);
if (!csk->l2t) {
pr_err("NO l2t available.\n");
return -EINVAL;
struct net_device *ndev = cdev->ports[csk->port_id];
struct port_info *pi = netdev_priv(ndev);
struct sk_buff *skb = NULL;
+ struct neighbour *n;
unsigned int step;
log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
cxgbi_sock_get(csk);
- csk->l2t = cxgb4_l2t_get(lldi->l2t, dst_get_neighbour(csk->dst), ndev, 0);
+ n = dst_get_neighbour_noref(csk->dst);
+ if (!n) {
+ pr_err("%s, can't get neighbour of csk->dst.\n", ndev->name);
+ goto rel_resource;
+ }
+ csk->l2t = cxgb4_l2t_get(lldi->l2t, n, ndev, 0);
if (!csk->l2t) {
pr_err("%s, cannot alloc l2t.\n", ndev->name);
goto rel_resource;
struct net_device *ndev;
struct cxgbi_device *cdev;
struct rtable *rt = NULL;
+ struct neighbour *n;
struct flowi4 fl4;
struct cxgbi_sock *csk = NULL;
unsigned int mtu = 0;
goto err_out;
}
dst = &rt->dst;
- ndev = dst_get_neighbour(dst)->dev;
+ n = dst_get_neighbour_noref(dst);
+ if (!n) {
+ err = -ENODEV;
+ goto rel_rt;
+ }
+ ndev = n->dev;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
pr_info("multi-cast route %pI4, port %u, dev %s.\n",
ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr);
mtu = ndev->mtu;
pr_info("rt dev %s, loopback -> %s, mtu %u.\n",
- dst_get_neighbour(dst)->dev->name, ndev->name, mtu);
+ n->dev->name, ndev->name, mtu);
}
cdev = cxgbi_device_find_by_netdev(ndev, &port);
#include <linux/sysfs.h>
#include <linux/ctype.h>
#include <linux/workqueue.h>
+#include <net/dcbnl.h>
+#include <net/dcbevent.h>
#include <scsi/scsi_tcq.h>
#include <scsi/scsicam.h>
#include <scsi/scsi_transport.h>
static int fcoe_ddp_target(struct fc_lport *, u16, struct scatterlist *,
unsigned int);
static int fcoe_cpu_callback(struct notifier_block *, unsigned long, void *);
+static int fcoe_dcb_app_notification(struct notifier_block *notifier,
+ ulong event, void *ptr);
static bool fcoe_match(struct net_device *netdev);
static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode);
.notifier_call = fcoe_cpu_callback,
};
+/* notification function for DCB events */
+static struct notifier_block dcb_notifier = {
+ .notifier_call = fcoe_dcb_app_notification,
+};
+
static struct scsi_transport_template *fcoe_nport_scsi_transport;
static struct scsi_transport_template *fcoe_vport_scsi_transport;
skb_reset_network_header(skb);
skb->mac_len = elen;
skb->protocol = htons(ETH_P_FCOE);
+ skb->priority = port->priority;
+
if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN &&
fcoe->realdev->features & NETIF_F_HW_VLAN_TX) {
skb->vlan_tci = VLAN_TAG_PRESENT |
stats->InvalidCRCCount++;
if (stats->InvalidCRCCount < 5)
printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
+ put_cpu();
return -EINVAL;
}
*/
static void fcoe_dev_setup(void)
{
+ register_dcbevent_notifier(&dcb_notifier);
register_netdevice_notifier(&fcoe_notifier);
}
*/
static void fcoe_dev_cleanup(void)
{
+ unregister_dcbevent_notifier(&dcb_notifier);
unregister_netdevice_notifier(&fcoe_notifier);
}
+static struct fcoe_interface *
+fcoe_hostlist_lookup_realdev_port(struct net_device *netdev)
+{
+ struct fcoe_interface *fcoe;
+ struct net_device *real_dev;
+
+ list_for_each_entry(fcoe, &fcoe_hostlist, list) {
+ if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN)
+ real_dev = vlan_dev_real_dev(fcoe->netdev);
+ else
+ real_dev = fcoe->netdev;
+
+ if (netdev == real_dev)
+ return fcoe;
+ }
+ return NULL;
+}
+
+static int fcoe_dcb_app_notification(struct notifier_block *notifier,
+ ulong event, void *ptr)
+{
+ struct dcb_app_type *entry = ptr;
+ struct fcoe_interface *fcoe;
+ struct net_device *netdev;
+ struct fcoe_port *port;
+ int prio;
+
+ if (entry->app.selector != DCB_APP_IDTYPE_ETHTYPE)
+ return NOTIFY_OK;
+
+ netdev = dev_get_by_index(&init_net, entry->ifindex);
+ if (!netdev)
+ return NOTIFY_OK;
+
+ fcoe = fcoe_hostlist_lookup_realdev_port(netdev);
+ dev_put(netdev);
+ if (!fcoe)
+ return NOTIFY_OK;
+
+ if (entry->dcbx & DCB_CAP_DCBX_VER_CEE)
+ prio = ffs(entry->app.priority) - 1;
+ else
+ prio = entry->app.priority;
+
+ if (prio < 0)
+ return NOTIFY_OK;
+
+ if (entry->app.protocol == ETH_P_FIP ||
+ entry->app.protocol == ETH_P_FCOE)
+ fcoe->ctlr.priority = prio;
+
+ if (entry->app.protocol == ETH_P_FCOE) {
+ port = lport_priv(fcoe->ctlr.lp);
+ port->priority = prio;
+ }
+
+ return NOTIFY_OK;
+}
+
/**
* fcoe_device_notification() - Handler for net device events
* @notifier: The context of the notification
return true;
}
+/**
+ * fcoe_dcb_create() - Initialize DCB attributes and hooks
+ * @netdev: The net_device object of the L2 link that should be queried
+ * @port: The fcoe_port to bind FCoE APP priority with
+ * @
+ */
+static void fcoe_dcb_create(struct fcoe_interface *fcoe)
+{
+#ifdef CONFIG_DCB
+ int dcbx;
+ u8 fup, up;
+ struct net_device *netdev = fcoe->realdev;
+ struct fcoe_port *port = lport_priv(fcoe->ctlr.lp);
+ struct dcb_app app = {
+ .priority = 0,
+ .protocol = ETH_P_FCOE
+ };
+
+ /* setup DCB priority attributes. */
+ if (netdev && netdev->dcbnl_ops && netdev->dcbnl_ops->getdcbx) {
+ dcbx = netdev->dcbnl_ops->getdcbx(netdev);
+
+ if (dcbx & DCB_CAP_DCBX_VER_IEEE) {
+ app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
+ up = dcb_ieee_getapp_mask(netdev, &app);
+ app.protocol = ETH_P_FIP;
+ fup = dcb_ieee_getapp_mask(netdev, &app);
+ } else {
+ app.selector = DCB_APP_IDTYPE_ETHTYPE;
+ up = dcb_getapp(netdev, &app);
+ app.protocol = ETH_P_FIP;
+ fup = dcb_getapp(netdev, &app);
+ }
+
+ port->priority = ffs(up) ? ffs(up) - 1 : 0;
+ fcoe->ctlr.priority = ffs(fup) ? ffs(fup) - 1 : port->priority;
+ }
+#endif
+}
+
/**
* fcoe_create() - Create a fcoe interface
* @netdev : The net_device object the Ethernet interface to create on
/* Make this the "master" N_Port */
fcoe->ctlr.lp = lport;
+ /* setup DCB priority attributes. */
+ fcoe_dcb_create(fcoe);
+
/* add to lports list */
fcoe_hostlist_add(lport);
skb_put(skb, sizeof(*sol));
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
fip->send(fip, skb);
}
skb_put(skb, len);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
fip->send(fip, skb);
cap->fip.fip_dl_len = htons(dlen / FIP_BPW);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
return 0;
skb_put(skb, len);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
#include <linux/interrupt.h>
#include <linux/types.h>
#include <linux/pci.h>
+#include <linux/pci-aspm.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/delay.h>
dev_warn(&h->pdev->dev, "controller appears to be disabled\n");
return -ENODEV;
}
+
+ pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
+ PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
+
err = pci_enable_device(h->pdev);
if (err) {
dev_warn(&h->pdev->dev, "unable to enable PCI device\n");
if (ioc->is_driver_loading)
return;
+
+ fw_event = kzalloc(sizeof(struct fw_event_work), GFP_ATOMIC);
+ if (!fw_event)
+ return;
+
fw_event->event = MPT2SAS_REMOVE_UNRESPONDING_DEVICES;
fw_event->ioc = ioc;
_scsih_fw_event_add(ioc, fw_event);
/* insert into event log */
sz = offsetof(Mpi2EventNotificationReply_t, EventData) +
sizeof(Mpi2EventDataSasDeviceStatusChange_t);
- event_reply = kzalloc(sz, GFP_KERNEL);
+ event_reply = kzalloc(sz, GFP_ATOMIC);
if (!event_reply) {
printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n",
ioc->name, __FILE__, __LINE__, __func__);
scsi_qla_host_t *vha = shost_priv(shost);
struct scsi_qla_host *base_vha = pci_get_drvdata(vha->hw->pdev);
- if (!base_vha->flags.online)
+ if (!base_vha->flags.online) {
fc_host_port_state(shost) = FC_PORTSTATE_OFFLINE;
- else if (atomic_read(&base_vha->loop_state) == LOOP_TIMEOUT)
- fc_host_port_state(shost) = FC_PORTSTATE_UNKNOWN;
- else
+ return;
+ }
+
+ switch (atomic_read(&base_vha->loop_state)) {
+ case LOOP_UPDATE:
+ fc_host_port_state(shost) = FC_PORTSTATE_DIAGNOSTICS;
+ break;
+ case LOOP_DOWN:
+ if (test_bit(LOOP_RESYNC_NEEDED, &base_vha->dpc_flags))
+ fc_host_port_state(shost) = FC_PORTSTATE_DIAGNOSTICS;
+ else
+ fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN;
+ break;
+ case LOOP_DEAD:
+ fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN;
+ break;
+ case LOOP_READY:
fc_host_port_state(shost) = FC_PORTSTATE_ONLINE;
+ break;
+ default:
+ fc_host_port_state(shost) = FC_PORTSTATE_UNKNOWN;
+ break;
+ }
}
static int
* | Level | Last Value Used | Holes |
* ----------------------------------------------------------------------
* | Module Init and Probe | 0x0116 | |
- * | Mailbox commands | 0x1129 | |
+ * | Mailbox commands | 0x112b | |
* | Device Discovery | 0x2083 | |
* | Queue Command and IO tracing | 0x302e | 0x3008 |
* | DPC Thread | 0x401c | |
* | Async Events | 0x5059 | |
- * | Timer Routines | 0x600d | |
+ * | Timer Routines | 0x6010 | 0x600e,0x600f |
* | User Space Interactions | 0x709d | |
- * | Task Management | 0x8041 | |
+ * | Task Management | 0x8041 | 0x800b |
* | AER/EEH | 0x900f | |
* | Virtual Port | 0xa007 | |
- * | ISP82XX Specific | 0xb051 | |
+ * | ISP82XX Specific | 0xb052 | |
* | MultiQ | 0xc00b | |
* | Misc | 0xd00b | |
* ----------------------------------------------------------------------
extern void qla82xx_chip_reset_cleanup(scsi_qla_host_t *);
extern int qla82xx_mbx_beacon_ctl(scsi_qla_host_t *, int);
extern char *qdev_state(uint32_t);
+extern void qla82xx_clear_pending_mbx(scsi_qla_host_t *);
/* BSG related functions */
extern int qla24xx_bsg_request(struct fc_bsg_job *);
&ha->fw_xcb_count, NULL, NULL,
&ha->max_npiv_vports, NULL);
- if (!fw_major_version && ql2xallocfwdump)
+ if (!fw_major_version && ql2xallocfwdump
+ && !IS_QLA82XX(ha))
qla2x00_alloc_fw_dump(vha);
}
} else {
* Returns a pointer to the continuation type 1 IOCB packet.
*/
static inline cont_a64_entry_t *
-qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha)
+qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, struct req_que *req)
{
cont_a64_entry_t *cont_pkt;
- struct req_que *req = vha->req;
/* Adjust ring index. */
req->ring_index++;
if (req->ring_index == req->length) {
* Five DSDs are available in the Continuation
* Type 1 IOCB.
*/
- cont_pkt = qla2x00_prep_cont_type1_iocb(vha);
+ cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req);
cur_dsd = (uint32_t *)cont_pkt->dseg_0_address;
avail_dsds = 5;
}
* Five DSDs are available in the Continuation
* Type 1 IOCB.
*/
- cont_pkt = qla2x00_prep_cont_type1_iocb(vha);
+ cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req);
cur_dsd = (uint32_t *)cont_pkt->dseg_0_address;
avail_dsds = 5;
}
* Five DSDs are available in the Cont.
* Type 1 IOCB.
*/
- cont_pkt = qla2x00_prep_cont_type1_iocb(vha);
+ cont_pkt = qla2x00_prep_cont_type1_iocb(vha,
+ vha->hw->req_q_map[0]);
cur_dsd = (uint32_t *) cont_pkt->dseg_0_address;
avail_dsds = 5;
cont_iocb_prsnt = 1;
int index;
uint16_t tot_dsds;
scsi_qla_host_t *vha = sp->fcport->vha;
+ struct qla_hw_data *ha = vha->hw;
struct fc_bsg_job *bsg_job = ((struct srb_ctx *)sp->ctx)->u.bsg_job;
int loop_iterartion = 0;
int cont_iocb_prsnt = 0;
* Five DSDs are available in the Cont.
* Type 1 IOCB.
*/
- cont_pkt = qla2x00_prep_cont_type1_iocb(vha);
+ cont_pkt = qla2x00_prep_cont_type1_iocb(vha,
+ ha->req_q_map[0]);
cur_dsd = (uint32_t *) cont_pkt->dseg_0_address;
avail_dsds = 5;
cont_iocb_prsnt = 1;
resid, scsi_bufflen(cp));
cp->result = DID_ERROR << 16 | lscsi_status;
- break;
+ goto check_scsi_status;
}
if (!lscsi_status &&
mcp->mb[0] = MBS_LINK_DOWN_ERROR;
ql_log(ql_log_warn, base_vha, 0x1004,
"FW hung = %d.\n", ha->flags.isp82xx_fw_hung);
- rval = QLA_FUNCTION_FAILED;
- goto premature_exit;
+ return QLA_FUNCTION_TIMEOUT;
}
/*
HINT_MBX_INT_PENDING) {
spin_unlock_irqrestore(&ha->hardware_lock,
flags);
+ ha->flags.mbox_busy = 0;
ql_dbg(ql_dbg_mbx, base_vha, 0x1010,
"Pending mailbox timeout, exiting.\n");
rval = QLA_FUNCTION_TIMEOUT;
HINT_MBX_INT_PENDING) {
spin_unlock_irqrestore(&ha->hardware_lock,
flags);
+ ha->flags.mbox_busy = 0;
ql_dbg(ql_dbg_mbx, base_vha, 0x1012,
"Pending mailbox timeout, exiting.\n");
rval = QLA_FUNCTION_TIMEOUT;
if (!test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) &&
!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) &&
!test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) {
-
+ if (IS_QLA82XX(ha)) {
+ ql_dbg(ql_dbg_mbx, vha, 0x112a,
+ "disabling pause transmit on port "
+ "0 & 1.\n");
+ qla82xx_wr_32(ha,
+ QLA82XX_CRB_NIU + 0x98,
+ CRB_NIU_XG_PAUSE_CTL_P0|
+ CRB_NIU_XG_PAUSE_CTL_P1);
+ }
ql_log(ql_log_info, base_vha, 0x101c,
"Mailbox cmd timeout occured. "
"Scheduling ISP abort eeh_busy=0x%x.\n",
if (!test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) &&
!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) &&
!test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) {
-
+ if (IS_QLA82XX(ha)) {
+ ql_dbg(ql_dbg_mbx, vha, 0x112b,
+ "disabling pause transmit on port "
+ "0 & 1.\n");
+ qla82xx_wr_32(ha,
+ QLA82XX_CRB_NIU + 0x98,
+ CRB_NIU_XG_PAUSE_CTL_P0|
+ CRB_NIU_XG_PAUSE_CTL_P1);
+ }
ql_log(ql_log_info, base_vha, 0x101e,
"Mailbox cmd timeout occured. "
"Scheduling ISP abort.\n");
return rval;
}
+void qla82xx_clear_pending_mbx(scsi_qla_host_t *vha)
+{
+ struct qla_hw_data *ha = vha->hw;
+
+ if (ha->flags.mbox_busy) {
+ ha->flags.mbox_int = 1;
+ ha->flags.mbox_busy = 0;
+ ql_log(ql_log_warn, vha, 0x6010,
+ "Doing premature completion of mbx command.\n");
+ if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags))
+ complete(&ha->mbx_intr_comp);
+ }
+}
+
void qla82xx_watchdog(scsi_qla_host_t *vha)
{
uint32_t dev_state, halt_status;
qla2xxx_wake_dpc(vha);
} else {
if (qla82xx_check_fw_alive(vha)) {
+ ql_dbg(ql_dbg_timer, vha, 0x6011,
+ "disabling pause transmit on port 0 & 1.\n");
+ qla82xx_wr_32(ha, QLA82XX_CRB_NIU + 0x98,
+ CRB_NIU_XG_PAUSE_CTL_P0|CRB_NIU_XG_PAUSE_CTL_P1);
halt_status = qla82xx_rd_32(ha,
QLA82XX_PEG_HALT_STATUS1);
- ql_dbg(ql_dbg_timer, vha, 0x6005,
+ ql_log(ql_log_info, vha, 0x6005,
"dumping hw/fw registers:.\n "
" PEG_HALT_STATUS1: 0x%x, PEG_HALT_STATUS2: 0x%x,.\n "
" PEG_NET_0_PC: 0x%x, PEG_NET_1_PC: 0x%x,.\n "
QLA82XX_CRB_PEG_NET_3 + 0x3c),
qla82xx_rd_32(ha,
QLA82XX_CRB_PEG_NET_4 + 0x3c));
+ if (LSW(MSB(halt_status)) == 0x67)
+ ql_log(ql_log_warn, vha, 0xb052,
+ "Firmware aborted with "
+ "error code 0x00006700. Device is "
+ "being reset.\n");
if (halt_status & HALT_STATUS_UNRECOVERABLE) {
set_bit(ISP_UNRECOVERABLE,
&vha->dpc_flags);
}
qla2xxx_wake_dpc(vha);
ha->flags.isp82xx_fw_hung = 1;
- if (ha->flags.mbox_busy) {
- ha->flags.mbox_int = 1;
- ql_log(ql_log_warn, vha, 0x6007,
- "Due to FW hung, doing "
- "premature completion of mbx "
- "command.\n");
- if (test_bit(MBX_INTR_WAIT,
- &ha->mbx_cmd_flags))
- complete(&ha->mbx_intr_comp);
- }
+ ql_log(ql_log_warn, vha, 0x6007, "Firmware hung.\n");
+ qla82xx_clear_pending_mbx(vha);
}
}
}
msleep(1000);
if (qla82xx_check_fw_alive(vha)) {
ha->flags.isp82xx_fw_hung = 1;
- if (ha->flags.mbox_busy) {
- ha->flags.mbox_int = 1;
- complete(&ha->mbx_intr_comp);
- }
+ qla82xx_clear_pending_mbx(vha);
break;
}
}
static const int MD_MIU_TEST_AGT_RDDATA[] = { 0x410000A8, 0x410000AC,
0x410000B8, 0x410000BC };
+
+#define CRB_NIU_XG_PAUSE_CTL_P0 0x1
+#define CRB_NIU_XG_PAUSE_CTL_P1 0x8
+
#endif
"Set the Minidump driver capture mask level. "
"Default is 0x7F - Can be set to 0x3, 0x7, 0xF, 0x1F, 0x7F.");
-int ql2xmdenable;
+int ql2xmdenable = 1;
module_param(ql2xmdenable, int, S_IRUGO);
MODULE_PARM_DESC(ql2xmdenable,
"Enable/disable MiniDump. "
- "0 (Default) - MiniDump disabled. "
- "1 - MiniDump enabled.");
+ "0 - MiniDump disabled. "
+ "1 (Default) - MiniDump enabled.");
/*
* SCSI host template entry points
qla25xx_delete_queues(vha);
destroy_workqueue(ha->wq);
ha->wq = NULL;
+ vha->req = ha->req_q_map[0];
fail:
ha->mqenable = 0;
kfree(ha->req_q_map);
return return_status;
}
-/*
- * qla2x00_wait_for_loop_ready
- * Wait for MAX_LOOP_TIMEOUT(5 min) value for loop
- * to be in LOOP_READY state.
- * Input:
- * ha - pointer to host adapter structure
- *
- * Note:
- * Does context switching-Release SPIN_LOCK
- * (if any) before calling this routine.
- *
- *
- * Return:
- * Success (LOOP_READY) : 0
- * Failed (LOOP_NOT_READY) : 1
- */
-static inline int
-qla2x00_wait_for_loop_ready(scsi_qla_host_t *vha)
-{
- int return_status = QLA_SUCCESS;
- unsigned long loop_timeout ;
- struct qla_hw_data *ha = vha->hw;
- scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
-
- /* wait for 5 min at the max for loop to be ready */
- loop_timeout = jiffies + (MAX_LOOP_TIMEOUT * HZ);
-
- while ((!atomic_read(&base_vha->loop_down_timer) &&
- atomic_read(&base_vha->loop_state) == LOOP_DOWN) ||
- atomic_read(&base_vha->loop_state) != LOOP_READY) {
- if (atomic_read(&base_vha->loop_state) == LOOP_DEAD) {
- return_status = QLA_FUNCTION_FAILED;
- break;
- }
- msleep(1000);
- if (time_after_eq(jiffies, loop_timeout)) {
- return_status = QLA_FUNCTION_FAILED;
- break;
- }
- }
- return (return_status);
-}
-
static void
sp_get(struct srb *sp)
{
"Wait for hba online failed for cmd=%p.\n", cmd);
goto eh_reset_failed;
}
- err = 1;
- if (qla2x00_wait_for_loop_ready(vha) != QLA_SUCCESS) {
- ql_log(ql_log_warn, vha, 0x800b,
- "Wait for loop ready failed for cmd=%p.\n", cmd);
- goto eh_reset_failed;
- }
err = 2;
if (do_reset(fcport, cmd->device->lun, cmd->request->cpu + 1)
!= QLA_SUCCESS) {
goto eh_bus_reset_done;
}
- if (qla2x00_wait_for_loop_ready(vha) == QLA_SUCCESS) {
- if (qla2x00_loop_reset(vha) == QLA_SUCCESS)
- ret = SUCCESS;
- }
+ if (qla2x00_loop_reset(vha) == QLA_SUCCESS)
+ ret = SUCCESS;
+
if (ret == FAILED)
goto eh_bus_reset_done;
if (qla2x00_wait_for_reset_ready(vha) != QLA_SUCCESS)
goto eh_host_reset_lock;
- /*
- * Fixme-may be dpc thread is active and processing
- * loop_resync,so wait a while for it to
- * be completed and then issue big hammer.Otherwise
- * it may cause I/O failure as big hammer marks the
- * devices as lost kicking of the port_down_timer
- * while dpc is stuck for the mailbox to complete.
- */
- qla2x00_wait_for_loop_ready(vha);
if (vha != base_vha) {
if (qla2x00_vp_abort_isp(vha))
goto eh_host_reset_lock;
atomic_set(&vha->loop_state, LOOP_DOWN);
atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
qla2x00_mark_all_devices_lost(vha, 0);
- qla2x00_wait_for_loop_ready(vha);
}
if (ha->flags.enable_lip_reset) {
ret = qla2x00_lip_reset(vha);
- if (ret != QLA_SUCCESS) {
+ if (ret != QLA_SUCCESS)
ql_dbg(ql_dbg_taskm, vha, 0x802e,
"lip_reset failed (%d).\n", ret);
- } else
- qla2x00_wait_for_loop_ready(vha);
}
/* Issue marker command only when we are going to start the I/O */
/* For ISP82XX complete any pending mailbox cmd */
if (IS_QLA82XX(ha)) {
ha->flags.isp82xx_fw_hung = 1;
- if (ha->flags.mbox_busy) {
- ha->flags.mbox_int = 1;
- ql_dbg(ql_dbg_aer, vha, 0x9001,
- "Due to pci channel io frozen, doing premature "
- "completion of mbx command.\n");
- complete(&ha->mbx_intr_comp);
- }
+ ql_dbg(ql_dbg_aer, vha, 0x9001, "Pci channel io frozen\n");
+ qla82xx_clear_pending_mbx(vha);
}
qla2x00_free_irqs(vha);
pci_disable_device(pdev);
/*
* Driver version
*/
-#define QLA2XXX_VERSION "8.03.07.07-k"
+#define QLA2XXX_VERSION "8.03.07.12-k"
#define QLA_DRIVER_MAJOR_VER 8
#define QLA_DRIVER_MINOR_VER 3
#define ISCSI_ALIAS_SIZE 32 /* ISCSI Alias name size */
#define ISCSI_NAME_SIZE 0xE0 /* ISCSI Name size */
-#define QL4_SESS_RECOVERY_TMO 30 /* iSCSI session */
+#define QL4_SESS_RECOVERY_TMO 120 /* iSCSI session */
/* recovery timeout */
#define LSDW(x) ((u32)((u64)(x)))
#define ISNS_DEREG_TOV 5
#define HBA_ONLINE_TOV 30
#define DISABLE_ACB_TOV 30
+#define IP_CONFIG_TOV 30
+#define LOGIN_TOV 12
#define MAX_RESET_HA_RETRIES 2
uint16_t fw_ddb_index; /* DDB firmware index */
uint32_t fw_ddb_device_state; /* F/W Device State -- see ql4_fw.h */
+ uint16_t ddb_type;
+#define FLASH_DDB 0x01
+
+ struct dev_db_entry fw_ddb_entry;
+ int (*unblock_sess)(struct iscsi_cls_session *cls_session);
+ int (*ddb_change)(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
+ struct ddb_entry *ddb_entry, uint32_t state);
+
+ /* Driver Re-login */
+ unsigned long flags; /* DDB Flags */
+ uint16_t default_relogin_timeout; /* Max time to wait for
+ * relogin to complete */
+ atomic_t retry_relogin_timer; /* Min Time between relogins
+ * (4000 only) */
+ atomic_t relogin_timer; /* Max Time to wait for
+ * relogin to complete */
+ atomic_t relogin_retry_count; /* Num of times relogin has been
+ * retried */
+ uint32_t default_time2wait; /* Default Min time between
+ * relogins (+aens) */
+
+};
+
+struct qla_ddb_index {
+ struct list_head list;
+ uint16_t fw_ddb_idx;
+ struct dev_db_entry fw_ddb;
+};
+
+#define DDB_IPADDR_LEN 64
+
+struct ql4_tuple_ddb {
+ int port;
+ int tpgt;
+ char ip_addr[DDB_IPADDR_LEN];
+ char iscsi_name[ISCSI_NAME_SIZE];
+ uint16_t options;
+#define DDB_OPT_IPV6 0x0e0e
+#define DDB_OPT_IPV4 0x0f0f
};
/*
#define AF_FW_RECOVERY 19 /* 0x00080000 */
#define AF_EEH_BUSY 20 /* 0x00100000 */
#define AF_PCI_CHANNEL_IO_PERM_FAILURE 21 /* 0x00200000 */
-
+#define AF_BUILD_DDB_LIST 22 /* 0x00400000 */
unsigned long dpc_flags;
#define DPC_RESET_HA 1 /* 0x00000002 */
uint16_t bootload_minor;
uint16_t bootload_patch;
uint16_t bootload_build;
+ uint16_t def_timeout; /* Default login timeout */
uint32_t flash_state;
#define QLFLASH_WAITING 0
uint16_t iscsi_pci_func_cnt;
uint8_t model_name[16];
struct completion disable_acb_comp;
+ struct dma_pool *fw_ddb_dma_pool;
+#define DDB_DMA_BLOCK_SIZE 512
+ uint16_t pri_ddb_idx;
+ uint16_t sec_ddb_idx;
+ int is_reset;
};
struct ql4_task_data {
/*---------------------------------------------------------------------------*/
/* Defines for qla4xxx_initialize_adapter() and qla4xxx_recover_adapter() */
+
+#define INIT_ADAPTER 0
+#define RESET_ADAPTER 1
+
#define PRESERVE_DDB_LIST 0
#define REBUILD_DDB_LIST 1
#define MAX_PRST_DEV_DB_ENTRIES 64
#define MIN_DISC_DEV_DB_ENTRY MAX_PRST_DEV_DB_ENTRIES
#define MAX_DEV_DB_ENTRIES 512
+#define MAX_DEV_DB_ENTRIES_40XX 256
/*************************************************************************
*
uint8_t res14[140]; /* 274-2FF */
};
+#define IP_ADDR_COUNT 4 /* Total 4 IP address supported in one interface
+ * One IPv4, one IPv6 link local and 2 IPv6
+ */
+
+#define IP_STATE_MASK 0x0F000000
+#define IP_STATE_SHIFT 24
+
struct init_fw_ctrl_blk {
struct addr_ctrl_blk pri;
/* struct addr_ctrl_blk sec;*/
int qla4xxx_hw_reset(struct scsi_qla_host *ha);
int ql4xxx_lock_drvr_wait(struct scsi_qla_host *a);
int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb *srb);
-int qla4xxx_initialize_adapter(struct scsi_qla_host *ha);
+int qla4xxx_initialize_adapter(struct scsi_qla_host *ha, int is_reset);
int qla4xxx_soft_reset(struct scsi_qla_host *ha);
irqreturn_t qla4xxx_intr_handler(int irq, void *dev_id);
uint32_t *mbx_sts);
int qla4xxx_clear_ddb_entry(struct scsi_qla_host *ha, uint32_t fw_ddb_index);
int qla4xxx_send_passthru0(struct iscsi_task *task);
+void qla4xxx_free_ddb_index(struct scsi_qla_host *ha);
int qla4xxx_get_mgmt_data(struct scsi_qla_host *ha, uint16_t fw_ddb_index,
uint16_t stats_size, dma_addr_t stats_dma);
void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha,
struct ddb_entry *ddb_entry);
+void qla4xxx_update_session_conn_fwddb_param(struct scsi_qla_host *ha,
+ struct ddb_entry *ddb_entry);
int qla4xxx_bootdb_by_index(struct scsi_qla_host *ha,
struct dev_db_entry *fw_ddb_entry,
dma_addr_t fw_ddb_entry_dma, uint16_t ddb_index);
int qla4xxx_restore_factory_defaults(struct scsi_qla_host *ha,
uint32_t region, uint32_t field0,
uint32_t field1);
+int qla4xxx_get_ddb_index(struct scsi_qla_host *ha, uint16_t *ddb_index);
+void qla4xxx_login_flash_ddb(struct iscsi_cls_session *cls_session);
+int qla4xxx_unblock_ddb(struct iscsi_cls_session *cls_session);
+int qla4xxx_unblock_flash_ddb(struct iscsi_cls_session *cls_session);
+int qla4xxx_flash_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
+ struct ddb_entry *ddb_entry, uint32_t state);
+int qla4xxx_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
+ struct ddb_entry *ddb_entry, uint32_t state);
+void qla4xxx_build_ddb_list(struct scsi_qla_host *ha, int is_reset);
/* BSG Functions */
int qla4xxx_bsg_request(struct bsg_job *bsg_job);
int qla4xxx_process_vendor_specific(struct bsg_job *bsg_job);
+void qla4xxx_arm_relogin_timer(struct ddb_entry *ddb_entry);
+
extern int ql4xextended_error_logging;
extern int ql4xdontresethba;
extern int ql4xenablemsix;
* be freed so that when login happens from user space there are free DDB
* indices available.
**/
-static void qla4xxx_free_ddb_index(struct scsi_qla_host *ha)
+void qla4xxx_free_ddb_index(struct scsi_qla_host *ha)
{
int max_ddbs;
int ret;
uint32_t idx = 0, next_idx = 0;
uint32_t state = 0, conn_err = 0;
- max_ddbs = is_qla40XX(ha) ? MAX_PRST_DEV_DB_ENTRIES :
+ max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX :
MAX_DEV_DB_ENTRIES;
for (idx = 0; idx < max_ddbs; idx = next_idx) {
ret = qla4xxx_get_fwddb_entry(ha, idx, NULL, 0, NULL,
&next_idx, &state, &conn_err,
NULL, NULL);
- if (ret == QLA_ERROR)
+ if (ret == QLA_ERROR) {
+ next_idx++;
continue;
+ }
if (state == DDB_DS_NO_CONNECTION_ACTIVE ||
state == DDB_DS_SESSION_FAILED) {
DEBUG2(ql4_printk(KERN_INFO, ha,
}
}
-
/**
* qla4xxx_initialize_adapter - initiailizes hba
* @ha: Pointer to host adapter structure.
* This routine parforms all of the steps necessary to initialize the adapter.
*
**/
-int qla4xxx_initialize_adapter(struct scsi_qla_host *ha)
+int qla4xxx_initialize_adapter(struct scsi_qla_host *ha, int is_reset)
{
int status = QLA_ERROR;
if (status == QLA_ERROR)
goto exit_init_hba;
- qla4xxx_free_ddb_index(ha);
+ if (is_reset == RESET_ADAPTER)
+ qla4xxx_build_ddb_list(ha, is_reset);
set_bit(AF_ONLINE, &ha->flags);
exit_init_hba:
return status;
}
-/**
- * qla4xxx_process_ddb_changed - process ddb state change
- * @ha - Pointer to host adapter structure.
- * @fw_ddb_index - Firmware's device database index
- * @state - Device state
- *
- * This routine processes a Decive Database Changed AEN Event.
- **/
-int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
- uint32_t state, uint32_t conn_err)
+int qla4xxx_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
+ struct ddb_entry *ddb_entry, uint32_t state)
{
- struct ddb_entry * ddb_entry;
uint32_t old_fw_ddb_device_state;
int status = QLA_ERROR;
- /* check for out of range index */
- if (fw_ddb_index >= MAX_DDB_ENTRIES)
- goto exit_ddb_event;
-
- /* Get the corresponging ddb entry */
- ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, fw_ddb_index);
- /* Device does not currently exist in our database. */
- if (ddb_entry == NULL) {
- ql4_printk(KERN_ERR, ha, "%s: No ddb_entry at FW index [%d]\n",
- __func__, fw_ddb_index);
-
- if (state == DDB_DS_NO_CONNECTION_ACTIVE)
- clear_bit(fw_ddb_index, ha->ddb_idx_map);
-
- goto exit_ddb_event;
- }
-
old_fw_ddb_device_state = ddb_entry->fw_ddb_device_state;
DEBUG2(ql4_printk(KERN_INFO, ha,
"%s: DDB - old state = 0x%x, new state = 0x%x for "
switch (state) {
case DDB_DS_SESSION_ACTIVE:
case DDB_DS_DISCOVERY:
- iscsi_conn_start(ddb_entry->conn);
- iscsi_conn_login_event(ddb_entry->conn,
- ISCSI_CONN_STATE_LOGGED_IN);
+ ddb_entry->unblock_sess(ddb_entry->sess);
qla4xxx_update_session_conn_param(ha, ddb_entry);
status = QLA_SUCCESS;
break;
switch (state) {
case DDB_DS_SESSION_ACTIVE:
case DDB_DS_DISCOVERY:
- iscsi_conn_start(ddb_entry->conn);
- iscsi_conn_login_event(ddb_entry->conn,
- ISCSI_CONN_STATE_LOGGED_IN);
+ ddb_entry->unblock_sess(ddb_entry->sess);
qla4xxx_update_session_conn_param(ha, ddb_entry);
status = QLA_SUCCESS;
break;
__func__));
break;
}
+ return status;
+}
+
+void qla4xxx_arm_relogin_timer(struct ddb_entry *ddb_entry)
+{
+ /*
+ * This triggers a relogin. After the relogin_timer
+ * expires, the relogin gets scheduled. We must wait a
+ * minimum amount of time since receiving an 0x8014 AEN
+ * with failed device_state or a logout response before
+ * we can issue another relogin.
+ *
+ * Firmware pads this timeout: (time2wait +1).
+ * Driver retry to login should be longer than F/W.
+ * Otherwise F/W will fail
+ * set_ddb() mbx cmd with 0x4005 since it still
+ * counting down its time2wait.
+ */
+ atomic_set(&ddb_entry->relogin_timer, 0);
+ atomic_set(&ddb_entry->retry_relogin_timer,
+ ddb_entry->default_time2wait + 4);
+
+}
+
+int qla4xxx_flash_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
+ struct ddb_entry *ddb_entry, uint32_t state)
+{
+ uint32_t old_fw_ddb_device_state;
+ int status = QLA_ERROR;
+
+ old_fw_ddb_device_state = ddb_entry->fw_ddb_device_state;
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "%s: DDB - old state = 0x%x, new state = 0x%x for "
+ "index [%d]\n", __func__,
+ ddb_entry->fw_ddb_device_state, state, fw_ddb_index));
+
+ ddb_entry->fw_ddb_device_state = state;
+
+ switch (old_fw_ddb_device_state) {
+ case DDB_DS_LOGIN_IN_PROCESS:
+ case DDB_DS_NO_CONNECTION_ACTIVE:
+ switch (state) {
+ case DDB_DS_SESSION_ACTIVE:
+ ddb_entry->unblock_sess(ddb_entry->sess);
+ qla4xxx_update_session_conn_fwddb_param(ha, ddb_entry);
+ status = QLA_SUCCESS;
+ break;
+ case DDB_DS_SESSION_FAILED:
+ iscsi_block_session(ddb_entry->sess);
+ if (!test_bit(DF_RELOGIN, &ddb_entry->flags))
+ qla4xxx_arm_relogin_timer(ddb_entry);
+ status = QLA_SUCCESS;
+ break;
+ }
+ break;
+ case DDB_DS_SESSION_ACTIVE:
+ switch (state) {
+ case DDB_DS_SESSION_FAILED:
+ iscsi_block_session(ddb_entry->sess);
+ if (!test_bit(DF_RELOGIN, &ddb_entry->flags))
+ qla4xxx_arm_relogin_timer(ddb_entry);
+ status = QLA_SUCCESS;
+ break;
+ }
+ break;
+ case DDB_DS_SESSION_FAILED:
+ switch (state) {
+ case DDB_DS_SESSION_ACTIVE:
+ ddb_entry->unblock_sess(ddb_entry->sess);
+ qla4xxx_update_session_conn_fwddb_param(ha, ddb_entry);
+ status = QLA_SUCCESS;
+ break;
+ case DDB_DS_SESSION_FAILED:
+ if (!test_bit(DF_RELOGIN, &ddb_entry->flags))
+ qla4xxx_arm_relogin_timer(ddb_entry);
+ status = QLA_SUCCESS;
+ break;
+ }
+ break;
+ default:
+ DEBUG2(ql4_printk(KERN_INFO, ha, "%s: Unknown Event\n",
+ __func__));
+ break;
+ }
+ return status;
+}
+
+/**
+ * qla4xxx_process_ddb_changed - process ddb state change
+ * @ha - Pointer to host adapter structure.
+ * @fw_ddb_index - Firmware's device database index
+ * @state - Device state
+ *
+ * This routine processes a Decive Database Changed AEN Event.
+ **/
+int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha,
+ uint32_t fw_ddb_index,
+ uint32_t state, uint32_t conn_err)
+{
+ struct ddb_entry *ddb_entry;
+ int status = QLA_ERROR;
+
+ /* check for out of range index */
+ if (fw_ddb_index >= MAX_DDB_ENTRIES)
+ goto exit_ddb_event;
+
+ /* Get the corresponging ddb entry */
+ ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, fw_ddb_index);
+ /* Device does not currently exist in our database. */
+ if (ddb_entry == NULL) {
+ ql4_printk(KERN_ERR, ha, "%s: No ddb_entry at FW index [%d]\n",
+ __func__, fw_ddb_index);
+
+ if (state == DDB_DS_NO_CONNECTION_ACTIVE)
+ clear_bit(fw_ddb_index, ha->ddb_idx_map);
+
+ goto exit_ddb_event;
+ }
+
+ ddb_entry->ddb_change(ha, fw_ddb_index, ddb_entry, state);
exit_ddb_event:
return status;
}
+
+/**
+ * qla4xxx_login_flash_ddb - Login to target (DDB)
+ * @cls_session: Pointer to the session to login
+ *
+ * This routine logins to the target.
+ * Issues setddb and conn open mbx
+ **/
+void qla4xxx_login_flash_ddb(struct iscsi_cls_session *cls_session)
+{
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+ struct dev_db_entry *fw_ddb_entry = NULL;
+ dma_addr_t fw_ddb_dma;
+ uint32_t mbx_sts = 0;
+ int ret;
+
+ sess = cls_session->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+
+ if (!test_bit(AF_LINK_UP, &ha->flags))
+ return;
+
+ if (ddb_entry->ddb_type != FLASH_DDB) {
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Skipping login to non FLASH DB"));
+ goto exit_login;
+ }
+
+ fw_ddb_entry = dma_pool_alloc(ha->fw_ddb_dma_pool, GFP_KERNEL,
+ &fw_ddb_dma);
+ if (fw_ddb_entry == NULL) {
+ DEBUG2(ql4_printk(KERN_ERR, ha, "Out of memory\n"));
+ goto exit_login;
+ }
+
+ if (ddb_entry->fw_ddb_index == INVALID_ENTRY) {
+ ret = qla4xxx_get_ddb_index(ha, &ddb_entry->fw_ddb_index);
+ if (ret == QLA_ERROR)
+ goto exit_login;
+
+ ha->fw_ddb_index_map[ddb_entry->fw_ddb_index] = ddb_entry;
+ ha->tot_ddbs++;
+ }
+
+ memcpy(fw_ddb_entry, &ddb_entry->fw_ddb_entry,
+ sizeof(struct dev_db_entry));
+ ddb_entry->sess->target_id = ddb_entry->fw_ddb_index;
+
+ ret = qla4xxx_set_ddb_entry(ha, ddb_entry->fw_ddb_index,
+ fw_ddb_dma, &mbx_sts);
+ if (ret == QLA_ERROR) {
+ DEBUG2(ql4_printk(KERN_ERR, ha, "Set DDB failed\n"));
+ goto exit_login;
+ }
+
+ ddb_entry->fw_ddb_device_state = DDB_DS_LOGIN_IN_PROCESS;
+ ret = qla4xxx_conn_open(ha, ddb_entry->fw_ddb_index);
+ if (ret == QLA_ERROR) {
+ ql4_printk(KERN_ERR, ha, "%s: Login failed: %s\n", __func__,
+ sess->targetname);
+ goto exit_login;
+ }
+
+exit_login:
+ if (fw_ddb_entry)
+ dma_pool_free(ha->fw_ddb_dma_pool, fw_ddb_entry, fw_ddb_dma);
+}
+
return status;
}
+ if (is_qla40XX(ha)) {
+ if (test_bit(AF_HA_REMOVAL, &ha->flags)) {
+ DEBUG2(ql4_printk(KERN_WARNING, ha, "scsi%ld: %s: "
+ "prematurely completing mbx cmd as "
+ "adapter removal detected\n",
+ ha->host_no, __func__));
+ return status;
+ }
+ }
+
if (is_qla8022(ha)) {
if (test_bit(AF_FW_RECOVERY, &ha->flags)) {
DEBUG2(ql4_printk(KERN_WARNING, ha, "scsi%ld: %s: "
memcpy(ha->name_string, init_fw_cb->iscsi_name,
min(sizeof(ha->name_string),
sizeof(init_fw_cb->iscsi_name)));
+ ha->def_timeout = le16_to_cpu(init_fw_cb->def_timeout);
/*memcpy(ha->alias, init_fw_cb->Alias,
min(sizeof(ha->alias), sizeof(init_fw_cb->Alias)));*/
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/iscsi_boot_sysfs.h>
+#include <linux/inet.h>
#include <scsi/scsi_tcq.h>
#include <scsi/scsicam.h>
/*
* Module parameter information and variables
*/
+int ql4xdisablesysfsboot = 1;
+module_param(ql4xdisablesysfsboot, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(ql4xdisablesysfsboot,
+ "Set to disable exporting boot targets to sysfs\n"
+ " 0 - Export boot targets\n"
+ " 1 - Do not export boot targets (Default)");
+
int ql4xdontresethba = 0;
module_param(ql4xdontresethba, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ql4xdontresethba,
module_param(ql4xsess_recovery_tmo, int, S_IRUGO);
MODULE_PARM_DESC(ql4xsess_recovery_tmo,
"Target Session Recovery Timeout.\n"
- " Default: 30 sec.");
+ " Default: 120 sec.");
static int qla4xxx_wait_for_hba_online(struct scsi_qla_host *ha);
/*
qla_ep = ep->dd_data;
ha = to_qla_host(qla_ep->host);
- if (adapter_up(ha))
+ if (adapter_up(ha) && !test_bit(AF_BUILD_DDB_LIST, &ha->flags))
ret = 1;
return ret;
}
+int qla4xxx_get_ddb_index(struct scsi_qla_host *ha, uint16_t *ddb_index)
+{
+ uint32_t mbx_sts = 0;
+ uint16_t tmp_ddb_index;
+ int ret;
+
+get_ddb_index:
+ tmp_ddb_index = find_first_zero_bit(ha->ddb_idx_map, MAX_DDB_ENTRIES);
+
+ if (tmp_ddb_index >= MAX_DDB_ENTRIES) {
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Free DDB index not available\n"));
+ ret = QLA_ERROR;
+ goto exit_get_ddb_index;
+ }
+
+ if (test_and_set_bit(tmp_ddb_index, ha->ddb_idx_map))
+ goto get_ddb_index;
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Found a free DDB index at %d\n", tmp_ddb_index));
+ ret = qla4xxx_req_ddb_entry(ha, tmp_ddb_index, &mbx_sts);
+ if (ret == QLA_ERROR) {
+ if (mbx_sts == MBOX_STS_COMMAND_ERROR) {
+ ql4_printk(KERN_INFO, ha,
+ "DDB index = %d not available trying next\n",
+ tmp_ddb_index);
+ goto get_ddb_index;
+ }
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Free FW DDB not available\n"));
+ }
+
+ *ddb_index = tmp_ddb_index;
+
+exit_get_ddb_index:
+ return ret;
+}
+
+static int qla4xxx_match_ipaddress(struct scsi_qla_host *ha,
+ struct ddb_entry *ddb_entry,
+ char *existing_ipaddr,
+ char *user_ipaddr)
+{
+ uint8_t dst_ipaddr[IPv6_ADDR_LEN];
+ char formatted_ipaddr[DDB_IPADDR_LEN];
+ int status = QLA_SUCCESS, ret = 0;
+
+ if (ddb_entry->fw_ddb_entry.options & DDB_OPT_IPV6_DEVICE) {
+ ret = in6_pton(user_ipaddr, strlen(user_ipaddr), dst_ipaddr,
+ '\0', NULL);
+ if (ret == 0) {
+ status = QLA_ERROR;
+ goto out_match;
+ }
+ ret = sprintf(formatted_ipaddr, "%pI6", dst_ipaddr);
+ } else {
+ ret = in4_pton(user_ipaddr, strlen(user_ipaddr), dst_ipaddr,
+ '\0', NULL);
+ if (ret == 0) {
+ status = QLA_ERROR;
+ goto out_match;
+ }
+ ret = sprintf(formatted_ipaddr, "%pI4", dst_ipaddr);
+ }
+
+ if (strcmp(existing_ipaddr, formatted_ipaddr))
+ status = QLA_ERROR;
+
+out_match:
+ return status;
+}
+
+static int qla4xxx_match_fwdb_session(struct scsi_qla_host *ha,
+ struct iscsi_cls_conn *cls_conn)
+{
+ int idx = 0, max_ddbs, rval;
+ struct iscsi_cls_session *cls_sess = iscsi_conn_to_session(cls_conn);
+ struct iscsi_session *sess, *existing_sess;
+ struct iscsi_conn *conn, *existing_conn;
+ struct ddb_entry *ddb_entry;
+
+ sess = cls_sess->dd_data;
+ conn = cls_conn->dd_data;
+
+ if (sess->targetname == NULL ||
+ conn->persistent_address == NULL ||
+ conn->persistent_port == 0)
+ return QLA_ERROR;
+
+ max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX :
+ MAX_DEV_DB_ENTRIES;
+
+ for (idx = 0; idx < max_ddbs; idx++) {
+ ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx);
+ if (ddb_entry == NULL)
+ continue;
+
+ if (ddb_entry->ddb_type != FLASH_DDB)
+ continue;
+
+ existing_sess = ddb_entry->sess->dd_data;
+ existing_conn = ddb_entry->conn->dd_data;
+
+ if (existing_sess->targetname == NULL ||
+ existing_conn->persistent_address == NULL ||
+ existing_conn->persistent_port == 0)
+ continue;
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "IQN = %s User IQN = %s\n",
+ existing_sess->targetname,
+ sess->targetname));
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "IP = %s User IP = %s\n",
+ existing_conn->persistent_address,
+ conn->persistent_address));
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Port = %d User Port = %d\n",
+ existing_conn->persistent_port,
+ conn->persistent_port));
+
+ if (strcmp(existing_sess->targetname, sess->targetname))
+ continue;
+ rval = qla4xxx_match_ipaddress(ha, ddb_entry,
+ existing_conn->persistent_address,
+ conn->persistent_address);
+ if (rval == QLA_ERROR)
+ continue;
+ if (existing_conn->persistent_port != conn->persistent_port)
+ continue;
+ break;
+ }
+
+ if (idx == max_ddbs)
+ return QLA_ERROR;
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Match found in fwdb sessions\n"));
+ return QLA_SUCCESS;
+}
+
static struct iscsi_cls_session *
qla4xxx_session_create(struct iscsi_endpoint *ep,
uint16_t cmds_max, uint16_t qdepth,
struct scsi_qla_host *ha;
struct qla_endpoint *qla_ep;
struct ddb_entry *ddb_entry;
- uint32_t ddb_index;
- uint32_t mbx_sts = 0;
+ uint16_t ddb_index;
struct iscsi_session *sess;
struct sockaddr *dst_addr;
int ret;
dst_addr = (struct sockaddr *)&qla_ep->dst_addr;
ha = to_qla_host(qla_ep->host);
-get_ddb_index:
- ddb_index = find_first_zero_bit(ha->ddb_idx_map, MAX_DDB_ENTRIES);
-
- if (ddb_index >= MAX_DDB_ENTRIES) {
- DEBUG2(ql4_printk(KERN_INFO, ha,
- "Free DDB index not available\n"));
- return NULL;
- }
-
- if (test_and_set_bit(ddb_index, ha->ddb_idx_map))
- goto get_ddb_index;
-
- DEBUG2(ql4_printk(KERN_INFO, ha,
- "Found a free DDB index at %d\n", ddb_index));
- ret = qla4xxx_req_ddb_entry(ha, ddb_index, &mbx_sts);
- if (ret == QLA_ERROR) {
- if (mbx_sts == MBOX_STS_COMMAND_ERROR) {
- ql4_printk(KERN_INFO, ha,
- "DDB index = %d not available trying next\n",
- ddb_index);
- goto get_ddb_index;
- }
- DEBUG2(ql4_printk(KERN_INFO, ha,
- "Free FW DDB not available\n"));
+ ret = qla4xxx_get_ddb_index(ha, &ddb_index);
+ if (ret == QLA_ERROR)
return NULL;
- }
cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport, qla_ep->host,
cmds_max, sizeof(struct ddb_entry),
ddb_entry->fw_ddb_device_state = DDB_DS_NO_CONNECTION_ACTIVE;
ddb_entry->ha = ha;
ddb_entry->sess = cls_sess;
+ ddb_entry->unblock_sess = qla4xxx_unblock_ddb;
+ ddb_entry->ddb_change = qla4xxx_ddb_change;
cls_sess->recovery_tmo = ql4xsess_recovery_tmo;
ha->fw_ddb_index_map[ddb_entry->fw_ddb_index] = ddb_entry;
ha->tot_ddbs++;
DEBUG2(printk(KERN_INFO "Func: %s\n", __func__));
cls_conn = iscsi_conn_setup(cls_sess, sizeof(struct qla_conn),
conn_idx);
+ if (!cls_conn)
+ return NULL;
+
sess = cls_sess->dd_data;
ddb_entry = sess->dd_data;
ddb_entry->conn = cls_conn;
struct iscsi_session *sess;
struct ddb_entry *ddb_entry;
struct scsi_qla_host *ha;
- struct dev_db_entry *fw_ddb_entry;
+ struct dev_db_entry *fw_ddb_entry = NULL;
dma_addr_t fw_ddb_entry_dma;
uint32_t mbx_sts = 0;
int ret = 0;
ddb_entry = sess->dd_data;
ha = ddb_entry->ha;
+ /* Check if we have matching FW DDB, if yes then do not
+ * login to this target. This could cause target to logout previous
+ * connection
+ */
+ ret = qla4xxx_match_fwdb_session(ha, cls_conn);
+ if (ret == QLA_SUCCESS) {
+ ql4_printk(KERN_INFO, ha,
+ "Session already exist in FW.\n");
+ ret = -EEXIST;
+ goto exit_conn_start;
+ }
+
fw_ddb_entry = dma_alloc_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
&fw_ddb_entry_dma, GFP_KERNEL);
if (!fw_ddb_entry) {
ql4_printk(KERN_ERR, ha,
"%s: Unable to allocate dma buffer\n", __func__);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto exit_conn_start;
}
ret = qla4xxx_set_param_ddbentry(ha, ddb_entry, cls_conn, &mbx_sts);
if (mbx_sts)
if (ddb_entry->fw_ddb_device_state ==
DDB_DS_SESSION_ACTIVE) {
- iscsi_conn_start(ddb_entry->conn);
- iscsi_conn_login_event(ddb_entry->conn,
- ISCSI_CONN_STATE_LOGGED_IN);
+ ddb_entry->unblock_sess(ddb_entry->sess);
goto exit_set_param;
}
ret = 0;
exit_conn_start:
- dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
- fw_ddb_entry, fw_ddb_entry_dma);
+ if (fw_ddb_entry)
+ dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
+ fw_ddb_entry, fw_ddb_entry_dma);
return ret;
}
return -ENOSYS;
}
+static void qla4xxx_copy_fwddb_param(struct scsi_qla_host *ha,
+ struct dev_db_entry *fw_ddb_entry,
+ struct iscsi_cls_session *cls_sess,
+ struct iscsi_cls_conn *cls_conn)
+{
+ int buflen = 0;
+ struct iscsi_session *sess;
+ struct iscsi_conn *conn;
+ char ip_addr[DDB_IPADDR_LEN];
+ uint16_t options = 0;
+
+ sess = cls_sess->dd_data;
+ conn = cls_conn->dd_data;
+
+ conn->max_recv_dlength = BYTE_UNITS *
+ le16_to_cpu(fw_ddb_entry->iscsi_max_rcv_data_seg_len);
+
+ conn->max_xmit_dlength = BYTE_UNITS *
+ le16_to_cpu(fw_ddb_entry->iscsi_max_snd_data_seg_len);
+
+ sess->initial_r2t_en =
+ (BIT_10 & le16_to_cpu(fw_ddb_entry->iscsi_options));
+
+ sess->max_r2t = le16_to_cpu(fw_ddb_entry->iscsi_max_outsnd_r2t);
+
+ sess->imm_data_en = (BIT_11 & le16_to_cpu(fw_ddb_entry->iscsi_options));
+
+ sess->first_burst = BYTE_UNITS *
+ le16_to_cpu(fw_ddb_entry->iscsi_first_burst_len);
+
+ sess->max_burst = BYTE_UNITS *
+ le16_to_cpu(fw_ddb_entry->iscsi_max_burst_len);
+
+ sess->time2wait = le16_to_cpu(fw_ddb_entry->iscsi_def_time2wait);
+
+ sess->time2retain = le16_to_cpu(fw_ddb_entry->iscsi_def_time2retain);
+
+ conn->persistent_port = le16_to_cpu(fw_ddb_entry->port);
+
+ sess->tpgt = le32_to_cpu(fw_ddb_entry->tgt_portal_grp);
+
+ options = le16_to_cpu(fw_ddb_entry->options);
+ if (options & DDB_OPT_IPV6_DEVICE)
+ sprintf(ip_addr, "%pI6", fw_ddb_entry->ip_addr);
+ else
+ sprintf(ip_addr, "%pI4", fw_ddb_entry->ip_addr);
+
+ iscsi_set_param(cls_conn, ISCSI_PARAM_TARGET_NAME,
+ (char *)fw_ddb_entry->iscsi_name, buflen);
+ iscsi_set_param(cls_conn, ISCSI_PARAM_INITIATOR_NAME,
+ (char *)ha->name_string, buflen);
+ iscsi_set_param(cls_conn, ISCSI_PARAM_PERSISTENT_ADDRESS,
+ (char *)ip_addr, buflen);
+}
+
+void qla4xxx_update_session_conn_fwddb_param(struct scsi_qla_host *ha,
+ struct ddb_entry *ddb_entry)
+{
+ struct iscsi_cls_session *cls_sess;
+ struct iscsi_cls_conn *cls_conn;
+ uint32_t ddb_state;
+ dma_addr_t fw_ddb_entry_dma;
+ struct dev_db_entry *fw_ddb_entry;
+
+ fw_ddb_entry = dma_alloc_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
+ &fw_ddb_entry_dma, GFP_KERNEL);
+ if (!fw_ddb_entry) {
+ ql4_printk(KERN_ERR, ha,
+ "%s: Unable to allocate dma buffer\n", __func__);
+ goto exit_session_conn_fwddb_param;
+ }
+
+ if (qla4xxx_get_fwddb_entry(ha, ddb_entry->fw_ddb_index, fw_ddb_entry,
+ fw_ddb_entry_dma, NULL, NULL, &ddb_state,
+ NULL, NULL, NULL) == QLA_ERROR) {
+ DEBUG2(ql4_printk(KERN_ERR, ha, "scsi%ld: %s: failed "
+ "get_ddb_entry for fw_ddb_index %d\n",
+ ha->host_no, __func__,
+ ddb_entry->fw_ddb_index));
+ goto exit_session_conn_fwddb_param;
+ }
+
+ cls_sess = ddb_entry->sess;
+
+ cls_conn = ddb_entry->conn;
+
+ /* Update params */
+ qla4xxx_copy_fwddb_param(ha, fw_ddb_entry, cls_sess, cls_conn);
+
+exit_session_conn_fwddb_param:
+ if (fw_ddb_entry)
+ dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
+ fw_ddb_entry, fw_ddb_entry_dma);
+}
+
void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha,
struct ddb_entry *ddb_entry)
{
if (!fw_ddb_entry) {
ql4_printk(KERN_ERR, ha,
"%s: Unable to allocate dma buffer\n", __func__);
- return;
+ goto exit_session_conn_param;
}
if (qla4xxx_get_fwddb_entry(ha, ddb_entry->fw_ddb_index, fw_ddb_entry,
"get_ddb_entry for fw_ddb_index %d\n",
ha->host_no, __func__,
ddb_entry->fw_ddb_index));
- return;
+ goto exit_session_conn_param;
}
cls_sess = ddb_entry->sess;
cls_conn = ddb_entry->conn;
conn = cls_conn->dd_data;
+ /* Update timers after login */
+ ddb_entry->default_relogin_timeout =
+ le16_to_cpu(fw_ddb_entry->def_timeout);
+ ddb_entry->default_time2wait =
+ le16_to_cpu(fw_ddb_entry->iscsi_def_time2wait);
+
/* Update params */
conn->max_recv_dlength = BYTE_UNITS *
le16_to_cpu(fw_ddb_entry->iscsi_max_rcv_data_seg_len);
memcpy(sess->initiatorname, ha->name_string,
min(sizeof(ha->name_string), sizeof(sess->initiatorname)));
+
+exit_session_conn_param:
+ if (fw_ddb_entry)
+ dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry),
+ fw_ddb_entry, fw_ddb_entry_dma);
}
/*
vfree(ha->chap_list);
ha->chap_list = NULL;
+ if (ha->fw_ddb_dma_pool)
+ dma_pool_destroy(ha->fw_ddb_dma_pool);
+
/* release io space registers */
if (is_qla8022(ha)) {
if (ha->nx_pcibase)
goto mem_alloc_error_exit;
}
+ ha->fw_ddb_dma_pool = dma_pool_create("ql4_fw_ddb", &ha->pdev->dev,
+ DDB_DMA_BLOCK_SIZE, 8, 0);
+
+ if (ha->fw_ddb_dma_pool == NULL) {
+ ql4_printk(KERN_WARNING, ha,
+ "%s: fw_ddb_dma_pool allocation failed..\n",
+ __func__);
+ goto mem_alloc_error_exit;
+ }
+
return QLA_SUCCESS;
mem_alloc_error_exit:
}
}
+void qla4xxx_check_relogin_flash_ddb(struct iscsi_cls_session *cls_sess)
+{
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+
+ sess = cls_sess->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+
+ if (!(ddb_entry->ddb_type == FLASH_DDB))
+ return;
+
+ if (adapter_up(ha) && !test_bit(DF_RELOGIN, &ddb_entry->flags) &&
+ !iscsi_is_session_online(cls_sess)) {
+ if (atomic_read(&ddb_entry->retry_relogin_timer) !=
+ INVALID_ENTRY) {
+ if (atomic_read(&ddb_entry->retry_relogin_timer) ==
+ 0) {
+ atomic_set(&ddb_entry->retry_relogin_timer,
+ INVALID_ENTRY);
+ set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags);
+ set_bit(DF_RELOGIN, &ddb_entry->flags);
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "%s: index [%d] login device\n",
+ __func__, ddb_entry->fw_ddb_index));
+ } else
+ atomic_dec(&ddb_entry->retry_relogin_timer);
+ }
+ }
+
+ /* Wait for relogin to timeout */
+ if (atomic_read(&ddb_entry->relogin_timer) &&
+ (atomic_dec_and_test(&ddb_entry->relogin_timer) != 0)) {
+ /*
+ * If the relogin times out and the device is
+ * still NOT ONLINE then try and relogin again.
+ */
+ if (!iscsi_is_session_online(cls_sess)) {
+ /* Reset retry relogin timer */
+ atomic_inc(&ddb_entry->relogin_retry_count);
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "%s: index[%d] relogin timed out-retrying"
+ " relogin (%d), retry (%d)\n", __func__,
+ ddb_entry->fw_ddb_index,
+ atomic_read(&ddb_entry->relogin_retry_count),
+ ddb_entry->default_time2wait + 4));
+ set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags);
+ atomic_set(&ddb_entry->retry_relogin_timer,
+ ddb_entry->default_time2wait + 4);
+ }
+ }
+}
+
/**
* qla4xxx_timer - checks every second for work to do.
* @ha: Pointer to host adapter structure.
int start_dpc = 0;
uint16_t w;
+ iscsi_host_for_each_session(ha->host, qla4xxx_check_relogin_flash_ddb);
+
/* If we are in the middle of AER/EEH processing
* skip any processing and reschedule the timer
*/
sess = cls_session->dd_data;
ddb_entry = sess->dd_data;
ddb_entry->fw_ddb_device_state = DDB_DS_SESSION_FAILED;
- iscsi_session_failure(cls_session->dd_data, ISCSI_ERR_CONN_FAILED);
+
+ if (ddb_entry->ddb_type == FLASH_DDB)
+ iscsi_block_session(ddb_entry->sess);
+ else
+ iscsi_session_failure(cls_session->dd_data,
+ ISCSI_ERR_CONN_FAILED);
}
/**
/* NOTE: AF_ONLINE flag set upon successful completion of
* qla4xxx_initialize_adapter */
- status = qla4xxx_initialize_adapter(ha);
+ status = qla4xxx_initialize_adapter(ha, RESET_ADAPTER);
}
/* Retry failed adapter initialization, if necessary
iscsi_unblock_session(ddb_entry->sess);
} else {
/* Trigger relogin */
- iscsi_session_failure(cls_session->dd_data,
- ISCSI_ERR_CONN_FAILED);
+ if (ddb_entry->ddb_type == FLASH_DDB) {
+ if (!test_bit(DF_RELOGIN, &ddb_entry->flags))
+ qla4xxx_arm_relogin_timer(ddb_entry);
+ } else
+ iscsi_session_failure(cls_session->dd_data,
+ ISCSI_ERR_CONN_FAILED);
}
}
}
+int qla4xxx_unblock_flash_ddb(struct iscsi_cls_session *cls_session)
+{
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+
+ sess = cls_session->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+ ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]"
+ " unblock session\n", ha->host_no, __func__,
+ ddb_entry->fw_ddb_index);
+
+ iscsi_unblock_session(ddb_entry->sess);
+
+ /* Start scan target */
+ if (test_bit(AF_ONLINE, &ha->flags)) {
+ ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]"
+ " start scan\n", ha->host_no, __func__,
+ ddb_entry->fw_ddb_index);
+ scsi_queue_work(ha->host, &ddb_entry->sess->scan_work);
+ }
+ return QLA_SUCCESS;
+}
+
+int qla4xxx_unblock_ddb(struct iscsi_cls_session *cls_session)
+{
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+
+ sess = cls_session->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+ ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]"
+ " unblock user space session\n", ha->host_no, __func__,
+ ddb_entry->fw_ddb_index);
+ iscsi_conn_start(ddb_entry->conn);
+ iscsi_conn_login_event(ddb_entry->conn,
+ ISCSI_CONN_STATE_LOGGED_IN);
+
+ return QLA_SUCCESS;
+}
+
static void qla4xxx_relogin_all_devices(struct scsi_qla_host *ha)
{
iscsi_host_for_each_session(ha->host, qla4xxx_relogin_devices);
}
+static void qla4xxx_relogin_flash_ddb(struct iscsi_cls_session *cls_sess)
+{
+ uint16_t relogin_timer;
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+
+ sess = cls_sess->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+
+ relogin_timer = max(ddb_entry->default_relogin_timeout,
+ (uint16_t)RELOGIN_TOV);
+ atomic_set(&ddb_entry->relogin_timer, relogin_timer);
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "scsi%ld: Relogin index [%d]. TOV=%d\n", ha->host_no,
+ ddb_entry->fw_ddb_index, relogin_timer));
+
+ qla4xxx_login_flash_ddb(cls_sess);
+}
+
+static void qla4xxx_dpc_relogin(struct iscsi_cls_session *cls_sess)
+{
+ struct iscsi_session *sess;
+ struct ddb_entry *ddb_entry;
+ struct scsi_qla_host *ha;
+
+ sess = cls_sess->dd_data;
+ ddb_entry = sess->dd_data;
+ ha = ddb_entry->ha;
+
+ if (!(ddb_entry->ddb_type == FLASH_DDB))
+ return;
+
+ if (test_and_clear_bit(DF_RELOGIN, &ddb_entry->flags) &&
+ !iscsi_is_session_online(cls_sess)) {
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "relogin issued\n"));
+ qla4xxx_relogin_flash_ddb(cls_sess);
+ }
+}
+
void qla4xxx_wake_dpc(struct scsi_qla_host *ha)
{
if (ha->dpc_thread)
if (test_and_clear_bit(DPC_GET_DHCP_IP_ADDR, &ha->dpc_flags))
qla4xxx_get_dhcp_ip_address(ha);
+ /* ---- relogin device? --- */
+ if (adapter_up(ha) &&
+ test_and_clear_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags)) {
+ iscsi_host_for_each_session(ha->host, qla4xxx_dpc_relogin);
+ }
+
/* ---- link change? --- */
if (test_and_clear_bit(DPC_LINK_CHANGED, &ha->dpc_flags)) {
if (!test_bit(AF_LINK_UP, &ha->flags)) {
* fatal error recovery. Therefore, the driver must
* manually relogin to devices when recovering from
* connection failures, logouts, expired KATO, etc. */
-
- qla4xxx_relogin_all_devices(ha);
+ if (test_and_clear_bit(AF_BUILD_DDB_LIST, &ha->flags)) {
+ qla4xxx_build_ddb_list(ha, ha->is_reset);
+ iscsi_host_for_each_session(ha->host,
+ qla4xxx_login_flash_ddb);
+ } else
+ qla4xxx_relogin_all_devices(ha);
}
}
}
" target ID %d\n", __func__, ddb_index[0],
ddb_index[1]));
+ ha->pri_ddb_idx = ddb_index[0];
+ ha->sec_ddb_idx = ddb_index[1];
+
exit_boot_info_free:
dma_free_coherent(&ha->pdev->dev, size, buf, buf_dma);
exit_boot_info:
return ret;
}
+ if (ql4xdisablesysfsboot)
+ return QLA_SUCCESS;
+
if (ddb_index[0] == 0xffff)
goto sec_target;
struct iscsi_boot_kobj *boot_kobj;
if (qla4xxx_get_boot_info(ha) != QLA_SUCCESS)
- return 0;
+ return QLA_ERROR;
+
+ if (ql4xdisablesysfsboot) {
+ ql4_printk(KERN_INFO, ha,
+ "%s: syfsboot disabled - driver will trigger login"
+ "and publish session for discovery .\n", __func__);
+ return QLA_SUCCESS;
+ }
+
ha->boot_kset = iscsi_boot_create_host_kset(ha->host->host_no);
if (!ha->boot_kset)
if (!boot_kobj)
goto put_host;
- return 0;
+ return QLA_SUCCESS;
put_host:
scsi_host_put(ha->host);
exit_chap_list:
dma_free_coherent(&ha->pdev->dev, chap_size,
chap_flash_data, chap_dma);
- return;
}
+static void qla4xxx_get_param_ddb(struct ddb_entry *ddb_entry,
+ struct ql4_tuple_ddb *tddb)
+{
+ struct scsi_qla_host *ha;
+ struct iscsi_cls_session *cls_sess;
+ struct iscsi_cls_conn *cls_conn;
+ struct iscsi_session *sess;
+ struct iscsi_conn *conn;
+
+ DEBUG2(printk(KERN_INFO "Func: %s\n", __func__));
+ ha = ddb_entry->ha;
+ cls_sess = ddb_entry->sess;
+ sess = cls_sess->dd_data;
+ cls_conn = ddb_entry->conn;
+ conn = cls_conn->dd_data;
+
+ tddb->tpgt = sess->tpgt;
+ tddb->port = conn->persistent_port;
+ strncpy(tddb->iscsi_name, sess->targetname, ISCSI_NAME_SIZE);
+ strncpy(tddb->ip_addr, conn->persistent_address, DDB_IPADDR_LEN);
+}
+
+static void qla4xxx_convert_param_ddb(struct dev_db_entry *fw_ddb_entry,
+ struct ql4_tuple_ddb *tddb)
+{
+ uint16_t options = 0;
+
+ tddb->tpgt = le32_to_cpu(fw_ddb_entry->tgt_portal_grp);
+ memcpy(&tddb->iscsi_name[0], &fw_ddb_entry->iscsi_name[0],
+ min(sizeof(tddb->iscsi_name), sizeof(fw_ddb_entry->iscsi_name)));
+
+ options = le16_to_cpu(fw_ddb_entry->options);
+ if (options & DDB_OPT_IPV6_DEVICE)
+ sprintf(tddb->ip_addr, "%pI6", fw_ddb_entry->ip_addr);
+ else
+ sprintf(tddb->ip_addr, "%pI4", fw_ddb_entry->ip_addr);
+
+ tddb->port = le16_to_cpu(fw_ddb_entry->port);
+}
+
+static int qla4xxx_compare_tuple_ddb(struct scsi_qla_host *ha,
+ struct ql4_tuple_ddb *old_tddb,
+ struct ql4_tuple_ddb *new_tddb)
+{
+ if (strcmp(old_tddb->iscsi_name, new_tddb->iscsi_name))
+ return QLA_ERROR;
+
+ if (strcmp(old_tddb->ip_addr, new_tddb->ip_addr))
+ return QLA_ERROR;
+
+ if (old_tddb->port != new_tddb->port)
+ return QLA_ERROR;
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Match Found, fw[%d,%d,%s,%s], [%d,%d,%s,%s]",
+ old_tddb->port, old_tddb->tpgt, old_tddb->ip_addr,
+ old_tddb->iscsi_name, new_tddb->port, new_tddb->tpgt,
+ new_tddb->ip_addr, new_tddb->iscsi_name));
+
+ return QLA_SUCCESS;
+}
+
+static int qla4xxx_is_session_exists(struct scsi_qla_host *ha,
+ struct dev_db_entry *fw_ddb_entry)
+{
+ struct ddb_entry *ddb_entry;
+ struct ql4_tuple_ddb *fw_tddb = NULL;
+ struct ql4_tuple_ddb *tmp_tddb = NULL;
+ int idx;
+ int ret = QLA_ERROR;
+
+ fw_tddb = vzalloc(sizeof(*fw_tddb));
+ if (!fw_tddb) {
+ DEBUG2(ql4_printk(KERN_WARNING, ha,
+ "Memory Allocation failed.\n"));
+ ret = QLA_SUCCESS;
+ goto exit_check;
+ }
+
+ tmp_tddb = vzalloc(sizeof(*tmp_tddb));
+ if (!tmp_tddb) {
+ DEBUG2(ql4_printk(KERN_WARNING, ha,
+ "Memory Allocation failed.\n"));
+ ret = QLA_SUCCESS;
+ goto exit_check;
+ }
+
+ qla4xxx_convert_param_ddb(fw_ddb_entry, fw_tddb);
+
+ for (idx = 0; idx < MAX_DDB_ENTRIES; idx++) {
+ ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx);
+ if (ddb_entry == NULL)
+ continue;
+
+ qla4xxx_get_param_ddb(ddb_entry, tmp_tddb);
+ if (!qla4xxx_compare_tuple_ddb(ha, fw_tddb, tmp_tddb)) {
+ ret = QLA_SUCCESS; /* found */
+ goto exit_check;
+ }
+ }
+
+exit_check:
+ if (fw_tddb)
+ vfree(fw_tddb);
+ if (tmp_tddb)
+ vfree(tmp_tddb);
+ return ret;
+}
+
+static int qla4xxx_is_flash_ddb_exists(struct scsi_qla_host *ha,
+ struct list_head *list_nt,
+ struct dev_db_entry *fw_ddb_entry)
+{
+ struct qla_ddb_index *nt_ddb_idx, *nt_ddb_idx_tmp;
+ struct ql4_tuple_ddb *fw_tddb = NULL;
+ struct ql4_tuple_ddb *tmp_tddb = NULL;
+ int ret = QLA_ERROR;
+
+ fw_tddb = vzalloc(sizeof(*fw_tddb));
+ if (!fw_tddb) {
+ DEBUG2(ql4_printk(KERN_WARNING, ha,
+ "Memory Allocation failed.\n"));
+ ret = QLA_SUCCESS;
+ goto exit_check;
+ }
+
+ tmp_tddb = vzalloc(sizeof(*tmp_tddb));
+ if (!tmp_tddb) {
+ DEBUG2(ql4_printk(KERN_WARNING, ha,
+ "Memory Allocation failed.\n"));
+ ret = QLA_SUCCESS;
+ goto exit_check;
+ }
+
+ qla4xxx_convert_param_ddb(fw_ddb_entry, fw_tddb);
+
+ list_for_each_entry_safe(nt_ddb_idx, nt_ddb_idx_tmp, list_nt, list) {
+ qla4xxx_convert_param_ddb(&nt_ddb_idx->fw_ddb, tmp_tddb);
+ if (!qla4xxx_compare_tuple_ddb(ha, fw_tddb, tmp_tddb)) {
+ ret = QLA_SUCCESS; /* found */
+ goto exit_check;
+ }
+ }
+
+exit_check:
+ if (fw_tddb)
+ vfree(fw_tddb);
+ if (tmp_tddb)
+ vfree(tmp_tddb);
+ return ret;
+}
+
+static void qla4xxx_free_nt_list(struct list_head *list_nt)
+{
+ struct qla_ddb_index *nt_ddb_idx, *nt_ddb_idx_tmp;
+
+ /* Free up the normaltargets list */
+ list_for_each_entry_safe(nt_ddb_idx, nt_ddb_idx_tmp, list_nt, list) {
+ list_del_init(&nt_ddb_idx->list);
+ vfree(nt_ddb_idx);
+ }
+
+}
+
+static struct iscsi_endpoint *qla4xxx_get_ep_fwdb(struct scsi_qla_host *ha,
+ struct dev_db_entry *fw_ddb_entry)
+{
+ struct iscsi_endpoint *ep;
+ struct sockaddr_in *addr;
+ struct sockaddr_in6 *addr6;
+ struct sockaddr *dst_addr;
+ char *ip;
+
+ /* TODO: need to destroy on unload iscsi_endpoint*/
+ dst_addr = vmalloc(sizeof(*dst_addr));
+ if (!dst_addr)
+ return NULL;
+
+ if (fw_ddb_entry->options & DDB_OPT_IPV6_DEVICE) {
+ dst_addr->sa_family = AF_INET6;
+ addr6 = (struct sockaddr_in6 *)dst_addr;
+ ip = (char *)&addr6->sin6_addr;
+ memcpy(ip, fw_ddb_entry->ip_addr, IPv6_ADDR_LEN);
+ addr6->sin6_port = htons(le16_to_cpu(fw_ddb_entry->port));
+
+ } else {
+ dst_addr->sa_family = AF_INET;
+ addr = (struct sockaddr_in *)dst_addr;
+ ip = (char *)&addr->sin_addr;
+ memcpy(ip, fw_ddb_entry->ip_addr, IP_ADDR_LEN);
+ addr->sin_port = htons(le16_to_cpu(fw_ddb_entry->port));
+ }
+
+ ep = qla4xxx_ep_connect(ha->host, dst_addr, 0);
+ vfree(dst_addr);
+ return ep;
+}
+
+static int qla4xxx_verify_boot_idx(struct scsi_qla_host *ha, uint16_t idx)
+{
+ if (ql4xdisablesysfsboot)
+ return QLA_SUCCESS;
+ if (idx == ha->pri_ddb_idx || idx == ha->sec_ddb_idx)
+ return QLA_ERROR;
+ return QLA_SUCCESS;
+}
+
+static void qla4xxx_setup_flash_ddb_entry(struct scsi_qla_host *ha,
+ struct ddb_entry *ddb_entry)
+{
+ ddb_entry->ddb_type = FLASH_DDB;
+ ddb_entry->fw_ddb_index = INVALID_ENTRY;
+ ddb_entry->fw_ddb_device_state = DDB_DS_NO_CONNECTION_ACTIVE;
+ ddb_entry->ha = ha;
+ ddb_entry->unblock_sess = qla4xxx_unblock_flash_ddb;
+ ddb_entry->ddb_change = qla4xxx_flash_ddb_change;
+
+ atomic_set(&ddb_entry->retry_relogin_timer, INVALID_ENTRY);
+ atomic_set(&ddb_entry->relogin_timer, 0);
+ atomic_set(&ddb_entry->relogin_retry_count, 0);
+
+ ddb_entry->default_relogin_timeout =
+ le16_to_cpu(ddb_entry->fw_ddb_entry.def_timeout);
+ ddb_entry->default_time2wait =
+ le16_to_cpu(ddb_entry->fw_ddb_entry.iscsi_def_time2wait);
+}
+
+static void qla4xxx_wait_for_ip_configuration(struct scsi_qla_host *ha)
+{
+ uint32_t idx = 0;
+ uint32_t ip_idx[IP_ADDR_COUNT] = {0, 1, 2, 3}; /* 4 IP interfaces */
+ uint32_t sts[MBOX_REG_COUNT];
+ uint32_t ip_state;
+ unsigned long wtime;
+ int ret;
+
+ wtime = jiffies + (HZ * IP_CONFIG_TOV);
+ do {
+ for (idx = 0; idx < IP_ADDR_COUNT; idx++) {
+ if (ip_idx[idx] == -1)
+ continue;
+
+ ret = qla4xxx_get_ip_state(ha, 0, ip_idx[idx], sts);
+
+ if (ret == QLA_ERROR) {
+ ip_idx[idx] = -1;
+ continue;
+ }
+
+ ip_state = (sts[1] & IP_STATE_MASK) >> IP_STATE_SHIFT;
+
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Waiting for IP state for idx = %d, state = 0x%x\n",
+ ip_idx[idx], ip_state));
+ if (ip_state == IP_ADDRSTATE_UNCONFIGURED ||
+ ip_state == IP_ADDRSTATE_INVALID ||
+ ip_state == IP_ADDRSTATE_PREFERRED ||
+ ip_state == IP_ADDRSTATE_DEPRICATED ||
+ ip_state == IP_ADDRSTATE_DISABLING)
+ ip_idx[idx] = -1;
+
+ }
+
+ /* Break if all IP states checked */
+ if ((ip_idx[0] == -1) &&
+ (ip_idx[1] == -1) &&
+ (ip_idx[2] == -1) &&
+ (ip_idx[3] == -1))
+ break;
+ schedule_timeout_uninterruptible(HZ);
+ } while (time_after(wtime, jiffies));
+}
+
+void qla4xxx_build_ddb_list(struct scsi_qla_host *ha, int is_reset)
+{
+ int max_ddbs;
+ int ret;
+ uint32_t idx = 0, next_idx = 0;
+ uint32_t state = 0, conn_err = 0;
+ uint16_t conn_id;
+ struct dev_db_entry *fw_ddb_entry;
+ struct ddb_entry *ddb_entry = NULL;
+ dma_addr_t fw_ddb_dma;
+ struct iscsi_cls_session *cls_sess;
+ struct iscsi_session *sess;
+ struct iscsi_cls_conn *cls_conn;
+ struct iscsi_endpoint *ep;
+ uint16_t cmds_max = 32, tmo = 0;
+ uint32_t initial_cmdsn = 0;
+ struct list_head list_st, list_nt; /* List of sendtargets */
+ struct qla_ddb_index *st_ddb_idx, *st_ddb_idx_tmp;
+ int fw_idx_size;
+ unsigned long wtime;
+ struct qla_ddb_index *nt_ddb_idx;
+
+ if (!test_bit(AF_LINK_UP, &ha->flags)) {
+ set_bit(AF_BUILD_DDB_LIST, &ha->flags);
+ ha->is_reset = is_reset;
+ return;
+ }
+ max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX :
+ MAX_DEV_DB_ENTRIES;
+
+ fw_ddb_entry = dma_pool_alloc(ha->fw_ddb_dma_pool, GFP_KERNEL,
+ &fw_ddb_dma);
+ if (fw_ddb_entry == NULL) {
+ DEBUG2(ql4_printk(KERN_ERR, ha, "Out of memory\n"));
+ goto exit_ddb_list;
+ }
+
+ INIT_LIST_HEAD(&list_st);
+ INIT_LIST_HEAD(&list_nt);
+ fw_idx_size = sizeof(struct qla_ddb_index);
+
+ for (idx = 0; idx < max_ddbs; idx = next_idx) {
+ ret = qla4xxx_get_fwddb_entry(ha, idx, fw_ddb_entry,
+ fw_ddb_dma, NULL,
+ &next_idx, &state, &conn_err,
+ NULL, &conn_id);
+ if (ret == QLA_ERROR)
+ break;
+
+ if (qla4xxx_verify_boot_idx(ha, idx) != QLA_SUCCESS)
+ goto continue_next_st;
+
+ /* Check if ST, add to the list_st */
+ if (strlen((char *) fw_ddb_entry->iscsi_name) != 0)
+ goto continue_next_st;
+
+ st_ddb_idx = vzalloc(fw_idx_size);
+ if (!st_ddb_idx)
+ break;
+
+ st_ddb_idx->fw_ddb_idx = idx;
+
+ list_add_tail(&st_ddb_idx->list, &list_st);
+continue_next_st:
+ if (next_idx == 0)
+ break;
+ }
+
+ /* Before issuing conn open mbox, ensure all IPs states are configured
+ * Note, conn open fails if IPs are not configured
+ */
+ qla4xxx_wait_for_ip_configuration(ha);
+
+ /* Go thru the STs and fire the sendtargets by issuing conn open mbx */
+ list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st, list) {
+ qla4xxx_conn_open(ha, st_ddb_idx->fw_ddb_idx);
+ }
+
+ /* Wait to ensure all sendtargets are done for min 12 sec wait */
+ tmo = ((ha->def_timeout < LOGIN_TOV) ? LOGIN_TOV : ha->def_timeout);
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Default time to wait for build ddb %d\n", tmo));
+
+ wtime = jiffies + (HZ * tmo);
+ do {
+ list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st,
+ list) {
+ ret = qla4xxx_get_fwddb_entry(ha,
+ st_ddb_idx->fw_ddb_idx,
+ NULL, 0, NULL, &next_idx,
+ &state, &conn_err, NULL,
+ NULL);
+ if (ret == QLA_ERROR)
+ continue;
+
+ if (state == DDB_DS_NO_CONNECTION_ACTIVE ||
+ state == DDB_DS_SESSION_FAILED) {
+ list_del_init(&st_ddb_idx->list);
+ vfree(st_ddb_idx);
+ }
+ }
+ schedule_timeout_uninterruptible(HZ / 10);
+ } while (time_after(wtime, jiffies));
+
+ /* Free up the sendtargets list */
+ list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st, list) {
+ list_del_init(&st_ddb_idx->list);
+ vfree(st_ddb_idx);
+ }
+
+ for (idx = 0; idx < max_ddbs; idx = next_idx) {
+ ret = qla4xxx_get_fwddb_entry(ha, idx, fw_ddb_entry,
+ fw_ddb_dma, NULL,
+ &next_idx, &state, &conn_err,
+ NULL, &conn_id);
+ if (ret == QLA_ERROR)
+ break;
+
+ if (qla4xxx_verify_boot_idx(ha, idx) != QLA_SUCCESS)
+ goto continue_next_nt;
+
+ /* Check if NT, then add to list it */
+ if (strlen((char *) fw_ddb_entry->iscsi_name) == 0)
+ goto continue_next_nt;
+
+ if (state == DDB_DS_NO_CONNECTION_ACTIVE ||
+ state == DDB_DS_SESSION_FAILED) {
+ DEBUG2(ql4_printk(KERN_INFO, ha,
+ "Adding DDB to session = 0x%x\n",
+ idx));
+ if (is_reset == INIT_ADAPTER) {
+ nt_ddb_idx = vmalloc(fw_idx_size);
+ if (!nt_ddb_idx)
+ break;
+
+ nt_ddb_idx->fw_ddb_idx = idx;
+
+ memcpy(&nt_ddb_idx->fw_ddb, fw_ddb_entry,
+ sizeof(struct dev_db_entry));
+
+ if (qla4xxx_is_flash_ddb_exists(ha, &list_nt,
+ fw_ddb_entry) == QLA_SUCCESS) {
+ vfree(nt_ddb_idx);
+ goto continue_next_nt;
+ }
+ list_add_tail(&nt_ddb_idx->list, &list_nt);
+ } else if (is_reset == RESET_ADAPTER) {
+ if (qla4xxx_is_session_exists(ha,
+ fw_ddb_entry) == QLA_SUCCESS)
+ goto continue_next_nt;
+ }
+
+ /* Create session object, with INVALID_ENTRY,
+ * the targer_id would get set when we issue the login
+ */
+ cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport,
+ ha->host, cmds_max,
+ sizeof(struct ddb_entry),
+ sizeof(struct ql4_task_data),
+ initial_cmdsn, INVALID_ENTRY);
+ if (!cls_sess)
+ goto exit_ddb_list;
+
+ /*
+ * iscsi_session_setup increments the driver reference
+ * count which wouldn't let the driver to be unloaded.
+ * so calling module_put function to decrement the
+ * reference count.
+ **/
+ module_put(qla4xxx_iscsi_transport.owner);
+ sess = cls_sess->dd_data;
+ ddb_entry = sess->dd_data;
+ ddb_entry->sess = cls_sess;
+
+ cls_sess->recovery_tmo = ql4xsess_recovery_tmo;
+ memcpy(&ddb_entry->fw_ddb_entry, fw_ddb_entry,
+ sizeof(struct dev_db_entry));
+
+ qla4xxx_setup_flash_ddb_entry(ha, ddb_entry);
+
+ cls_conn = iscsi_conn_setup(cls_sess,
+ sizeof(struct qla_conn),
+ conn_id);
+ if (!cls_conn)
+ goto exit_ddb_list;
+
+ ddb_entry->conn = cls_conn;
+
+ /* Setup ep, for displaying attributes in sysfs */
+ ep = qla4xxx_get_ep_fwdb(ha, fw_ddb_entry);
+ if (ep) {
+ ep->conn = cls_conn;
+ cls_conn->ep = ep;
+ } else {
+ DEBUG2(ql4_printk(KERN_ERR, ha,
+ "Unable to get ep\n"));
+ }
+
+ /* Update sess/conn params */
+ qla4xxx_copy_fwddb_param(ha, fw_ddb_entry, cls_sess,
+ cls_conn);
+
+ if (is_reset == RESET_ADAPTER) {
+ iscsi_block_session(cls_sess);
+ /* Use the relogin path to discover new devices
+ * by short-circuting the logic of setting
+ * timer to relogin - instead set the flags
+ * to initiate login right away.
+ */
+ set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags);
+ set_bit(DF_RELOGIN, &ddb_entry->flags);
+ }
+ }
+continue_next_nt:
+ if (next_idx == 0)
+ break;
+ }
+exit_ddb_list:
+ qla4xxx_free_nt_list(&list_nt);
+ if (fw_ddb_entry)
+ dma_pool_free(ha->fw_ddb_dma_pool, fw_ddb_entry, fw_ddb_dma);
+
+ qla4xxx_free_ddb_index(ha);
+}
+
+
/**
* qla4xxx_probe_adapter - callback function to probe HBA
* @pdev: pointer to pci_dev structure
* firmware
* NOTE: interrupts enabled upon successful completion
*/
- status = qla4xxx_initialize_adapter(ha);
+ status = qla4xxx_initialize_adapter(ha, INIT_ADAPTER);
while ((!test_bit(AF_ONLINE, &ha->flags)) &&
init_retry_count++ < MAX_INIT_RETRIES) {
if (ha->isp_ops->reset_chip(ha) == QLA_ERROR)
continue;
- status = qla4xxx_initialize_adapter(ha);
+ status = qla4xxx_initialize_adapter(ha, INIT_ADAPTER);
}
if (!test_bit(AF_ONLINE, &ha->flags)) {
ha->host_no, ha->firmware_version[0], ha->firmware_version[1],
ha->patch_number, ha->build_number);
- qla4xxx_create_chap_list(ha);
-
if (qla4xxx_setup_boot_info(ha))
ql4_printk(KERN_ERR, ha, "%s:ISCSI boot info setup failed\n",
__func__);
+ /* Perform the build ddb list and login to each */
+ qla4xxx_build_ddb_list(ha, INIT_ADAPTER);
+ iscsi_host_for_each_session(ha->host, qla4xxx_login_flash_ddb);
+
+ qla4xxx_create_chap_list(ha);
+
qla4xxx_create_ifaces(ha);
return 0;
}
}
+static void qla4xxx_destroy_fw_ddb_session(struct scsi_qla_host *ha)
+{
+ struct ddb_entry *ddb_entry;
+ int options;
+ int idx;
+
+ for (idx = 0; idx < MAX_DDB_ENTRIES; idx++) {
+
+ ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx);
+ if ((ddb_entry != NULL) &&
+ (ddb_entry->ddb_type == FLASH_DDB)) {
+
+ options = LOGOUT_OPTION_CLOSE_SESSION;
+ if (qla4xxx_session_logout_ddb(ha, ddb_entry, options)
+ == QLA_ERROR)
+ ql4_printk(KERN_ERR, ha, "%s: Logout failed\n",
+ __func__);
+
+ qla4xxx_clear_ddb_entry(ha, ddb_entry->fw_ddb_index);
+ /*
+ * we have decremented the reference count of the driver
+ * when we setup the session to have the driver unload
+ * to be seamless without actually destroying the
+ * session
+ **/
+ try_module_get(qla4xxx_iscsi_transport.owner);
+ iscsi_destroy_endpoint(ddb_entry->conn->ep);
+ qla4xxx_free_ddb(ha, ddb_entry);
+ iscsi_session_teardown(ddb_entry->sess);
+ }
+ }
+}
/**
* qla4xxx_remove_adapter - calback function to remove adapter.
* @pci_dev: PCI device pointer
/* destroy iface from sysfs */
qla4xxx_destroy_ifaces(ha);
- if (ha->boot_kset)
+ if ((!ql4xdisablesysfsboot) && ha->boot_kset)
iscsi_boot_destroy_kset(ha->boot_kset);
+ qla4xxx_destroy_fw_ddb_session(ha);
+
scsi_remove_host(ha->host);
qla4xxx_free_adapter(ha);
qla4_8xxx_idc_unlock(ha);
clear_bit(AF_FW_RECOVERY, &ha->flags);
- rval = qla4xxx_initialize_adapter(ha);
+ rval = qla4xxx_initialize_adapter(ha, RESET_ADAPTER);
qla4_8xxx_idc_lock(ha);
if (rval != QLA_SUCCESS) {
if ((qla4_8xxx_rd_32(ha, QLA82XX_CRB_DEV_STATE) ==
QLA82XX_DEV_READY)) {
clear_bit(AF_FW_RECOVERY, &ha->flags);
- rval = qla4xxx_initialize_adapter(ha);
+ rval = qla4xxx_initialize_adapter(ha, RESET_ADAPTER);
if (rval == QLA_SUCCESS) {
ret = qla4xxx_request_irqs(ha);
if (ret) {
* See LICENSE.qla4xxx for copyright and licensing details.
*/
-#define QLA4XXX_DRIVER_VERSION "5.02.00-k8"
+#define QLA4XXX_DRIVER_VERSION "5.02.00-k9"
blk_start_request(req);
+ scmd_printk(KERN_INFO, cmd, "killing request\n");
+
sdev = cmd->device;
starget = scsi_target(sdev);
shost = sdev->host;
struct request *req;
if (!sdev) {
- printk("scsi: killing requests for dead queue\n");
while ((req = blk_peek_request(q)) != NULL)
scsi_kill_request(req, q);
return;
return sdev;
out_device_destroy:
- scsi_device_set_state(sdev, SDEV_DEL);
- transport_destroy_device(&sdev->sdev_gendev);
- put_device(&sdev->sdev_dev);
- scsi_free_queue(sdev->request_queue);
- put_device(&sdev->sdev_gendev);
+ __scsi_remove_device(sdev);
out:
if (display_failure_msg)
printk(ALLOC_FAILURE_MSG, __func__);
depends on FSL_SOC
config SPI_FSL_SPI
- tristate "Freescale SPI controller"
+ bool "Freescale SPI controller"
depends on FSL_SOC
select SPI_FSL_LIB
help
MPC8569 uses the controller in QE mode, MPC8610 in cpu mode.
config SPI_FSL_ESPI
- tristate "Freescale eSPI controller"
+ bool "Freescale eSPI controller"
depends on FSL_SOC
select SPI_FSL_LIB
help
*/
#include <linux/kernel.h>
+#include <linux/module.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
spi_bitbang_cleanup(spi);
}
-static int __init spi_gpio_alloc(unsigned pin, const char *label, bool is_in)
+static int __devinit spi_gpio_alloc(unsigned pin, const char *label, bool is_in)
{
int value;
return value;
}
-static int __init
+static int __devinit
spi_gpio_request(struct spi_gpio_platform_data *pdata, const char *label,
u16 *res_flags)
{
*
*/
+#include <linux/module.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
goto err_clk;
}
- mfp_set_groupg(&pdev->dev);
+ mfp_set_groupg(&pdev->dev, NULL);
nuc900_init_spi(hw);
err = spi_bitbang_start(&hw->bitbang);
goto err_clk_prep;
}
+ status = clk_enable(pl022->clk);
+ if (status) {
+ dev_err(&adev->dev, "could not enable SSP/SPI bus clock\n");
+ goto err_no_clk_en;
+ }
+
/* Disable SSP */
writew((readw(SSP_CR1(pl022->virtbase)) & (~SSP_CR1_MASK_SSE)),
SSP_CR1(pl022->virtbase));
free_irq(adev->irq[0], pl022);
err_no_irq:
+ clk_disable(pl022->clk);
+ err_no_clk_en:
clk_unprepare(pl022->clk);
err_clk_prep:
clk_put(pl022->clk);
}
insns =
- kmalloc(sizeof(struct comedi_insn) * insnlist.n_insns, GFP_KERNEL);
+ kcalloc(insnlist.n_insns, sizeof(struct comedi_insn), GFP_KERNEL);
if (!insns) {
DPRINTK("kmalloc failed\n");
ret = -ENOMEM;
return ret;
}
-static void comedi_unmap(struct vm_area_struct *area)
+
+static void comedi_vm_open(struct vm_area_struct *area)
+{
+ struct comedi_async *async;
+ struct comedi_device *dev;
+
+ async = area->vm_private_data;
+ dev = async->subdevice->device;
+
+ mutex_lock(&dev->mutex);
+ async->mmap_count++;
+ mutex_unlock(&dev->mutex);
+}
+
+static void comedi_vm_close(struct vm_area_struct *area)
{
struct comedi_async *async;
struct comedi_device *dev;
}
static struct vm_operations_struct comedi_vm_ops = {
- .close = comedi_unmap,
+ .open = comedi_vm_open,
+ .close = comedi_vm_close,
};
static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
{
const unsigned minor = iminor(file->f_dentry->d_inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
struct comedi_async *async = NULL;
unsigned long start = vma->vm_start;
unsigned long size;
int i;
int retval;
struct comedi_subdevice *s;
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+
+ dev_file_info = comedi_get_device_file_info(minor);
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
mutex_lock(&dev->mutex);
if (!dev->attached) {
{
unsigned int mask = 0;
const unsigned minor = iminor(file->f_dentry->d_inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
struct comedi_subdevice *read_subdev;
struct comedi_subdevice *write_subdev;
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+ dev_file_info = comedi_get_device_file_info(minor);
+
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
mutex_lock(&dev->mutex);
if (!dev->attached) {
int n, m, count = 0, retval = 0;
DECLARE_WAITQUEUE(wait, current);
const unsigned minor = iminor(file->f_dentry->d_inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+ dev_file_info = comedi_get_device_file_info(minor);
+
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
if (!dev->attached) {
DPRINTK("no driver configured on comedi%i\n", dev->minor);
retval = -EAGAIN;
break;
}
+ schedule();
if (signal_pending(current)) {
retval = -ERESTARTSYS;
break;
}
- schedule();
if (!s->busy)
break;
if (s->busy != file) {
int n, m, count = 0, retval = 0;
DECLARE_WAITQUEUE(wait, current);
const unsigned minor = iminor(file->f_dentry->d_inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+ dev_file_info = comedi_get_device_file_info(minor);
+
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
if (!dev->attached) {
DPRINTK("no driver configured on comedi%i\n", dev->minor);
retval = -EAGAIN;
break;
}
+ schedule();
if (signal_pending(current)) {
retval = -ERESTARTSYS;
break;
}
- schedule();
if (!s->busy) {
retval = 0;
break;
static int comedi_close(struct inode *inode, struct file *file)
{
const unsigned minor = iminor(inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
struct comedi_subdevice *s = NULL;
int i;
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+ dev_file_info = comedi_get_device_file_info(minor);
+
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
mutex_lock(&dev->mutex);
static int comedi_fasync(int fd, struct file *file, int on)
{
const unsigned minor = iminor(file->f_dentry->d_inode);
- struct comedi_device_file_info *dev_file_info =
- comedi_get_device_file_info(minor);
+ struct comedi_device_file_info *dev_file_info;
+ struct comedi_device *dev;
+ dev_file_info = comedi_get_device_file_info(minor);
- struct comedi_device *dev = dev_file_info->device;
+ if (dev_file_info == NULL)
+ return -ENODEV;
+ dev = dev_file_info->device;
+ if (dev == NULL)
+ return -ENODEV;
return fasync_helper(fd, file, on, &dev->async_queue);
}
-#define DRIVER_VERSION "v0.5"
+#define DRIVER_VERSION "v0.6"
#define DRIVER_AUTHOR "Bernd Porr, BerndPorr@f2s.com"
#define DRIVER_DESC "Stirling/ITL USB-DUX SIGMA -- Bernd.Porr@f2s.com"
/*
Description: University of Stirling USB DAQ & INCITE Technology Limited
Devices: [ITL] USB-DUX (usbduxsigma.o)
Author: Bernd Porr <BerndPorr@f2s.com>
-Updated: 21 Jul 2011
+Updated: 8 Nov 2011
Status: testing
*/
/*
* 0.3: proper vendor ID and driver name
* 0.4: fixed D/A voltage range
* 0.5: various bug fixes, health check at startup
+ * 0.6: corrected wrong input range
*/
/* generates loads of debug info */
/* comedi constants */
static const struct comedi_lrange range_usbdux_ai_range = { 1, {
BIP_RANGE
- (2.65)
+ (2.65/2.0)
}
};
config ET131X
tristate "Agere ET-1310 Gigabit Ethernet support"
- depends on PCI
+ depends on PCI && NET && NETDEVICES
+ select PHYLIB
default n
---help---
This driver supports Agere ET-1310 ethernet adapters.
return 0;
}
+static SIMPLE_DEV_PM_OPS(et131x_pm_ops, et131x_suspend, et131x_resume);
+#define ET131X_PM_OPS (&et131x_pm_ops)
+#else
+#define ET131X_PM_OPS NULL
+#endif
+
/* ISR functions */
/**
return result;
}
-static SIMPLE_DEV_PM_OPS(et131x_pm_ops, et131x_suspend, et131x_resume);
-#define ET131X_PM_OPS (&et131x_pm_ops)
-#else
-#define ET131X_PM_OPS NULL
-#endif
-
static DEFINE_PCI_DEVICE_TABLE(et131x_pci_table) = {
{ PCI_VDEVICE(ATT, ET131X_PCI_DEVICE_ID_GIG), 0UL},
{ PCI_VDEVICE(ATT, ET131X_PCI_DEVICE_ID_FAST), 0UL},
static int iio_event_getfd(struct iio_dev *indio_dev)
{
- if (indio_dev->event_interface == NULL)
+ struct iio_event_interface *ev_int = indio_dev->event_interface;
+ int fd;
+
+ if (ev_int == NULL)
return -ENODEV;
- mutex_lock(&indio_dev->event_interface->event_list_lock);
- if (test_and_set_bit(IIO_BUSY_BIT_POS,
- &indio_dev->event_interface->flags)) {
- mutex_unlock(&indio_dev->event_interface->event_list_lock);
+ mutex_lock(&ev_int->event_list_lock);
+ if (test_and_set_bit(IIO_BUSY_BIT_POS, &ev_int->flags)) {
+ mutex_unlock(&ev_int->event_list_lock);
return -EBUSY;
}
- mutex_unlock(&indio_dev->event_interface->event_list_lock);
- return anon_inode_getfd("iio:event",
- &iio_event_chrdev_fileops,
- indio_dev->event_interface, O_RDONLY);
+ mutex_unlock(&ev_int->event_list_lock);
+ fd = anon_inode_getfd("iio:event",
+ &iio_event_chrdev_fileops, ev_int, O_RDONLY);
+ if (fd < 0) {
+ mutex_lock(&ev_int->event_list_lock);
+ clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags);
+ mutex_unlock(&ev_int->event_list_lock);
+ }
+ return fd;
}
static int __init iio_init(void)
#include "as102_fw.h"
#include "dvbdev.h"
-int debug;
-module_param_named(debug, debug, int, 0644);
+int as102_debug;
+module_param_named(debug, as102_debug, int, 0644);
MODULE_PARM_DESC(debug, "Turn on/off debugging (default: off)");
int dual_tuner;
#define DRIVER_FULL_NAME "Abilis Systems as10x usb driver"
#define DRIVER_NAME "as10x_usb"
-extern int debug;
+extern int as102_debug;
+#define debug as102_debug
#define dprintk(debug, args...) \
do { if (debug) { \
CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
struct skb_frag_struct *fs = skb_shinfo(skb)->frags + i;
- hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)(page_address(fs->page) + fs->page_offset));
+ hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)(page_address(fs->page.p) + fs->page_offset));
hw_buffer.s.size = fs->size;
CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64;
}
{USB_DEVICE(0x0DF6, 0x0045)},
{USB_DEVICE(0x0DF6, 0x0059)}, /* 11n mode disable */
{USB_DEVICE(0x0DF6, 0x004B)},
+ {USB_DEVICE(0x0DF6, 0x005D)},
{USB_DEVICE(0x0DF6, 0x0063)},
/* Sweex */
{USB_DEVICE(0x177F, 0x0154)},
th = kthread_create(rtsx_scan_thread, dev, "rtsx-scan");
if (IS_ERR(th)) {
printk(KERN_ERR "Unable to start the device-scanning thread\n");
+ complete(&dev->scanning_done);
quiesce_and_remove_host(dev);
err = PTR_ERR(th);
goto errout;
config SLICOSS
tristate "Alacritech Gigabit IS-NIC support"
- depends on PCI && X86
+ depends on PCI && X86 && NET
default n
help
This driver supports Alacritech's IS-NIC gigabit ethernet cards.
/* Bridge GPT id (1 - 4), DM Timer id (5 - 8) */
#define DMT_ID(id) ((id) + 4)
+#define DM_TIMER_CLOCKS 4
/* Bridge MCBSP id (6 - 10), OMAP Mcbsp id (0 - 4) */
#define MCBSP_ID(id) ((id) - 6)
*/
void dsp_clk_exit(void)
{
+ int i;
+
dsp_clock_disable_all(dsp_clocks);
+ for (i = 0; i < DM_TIMER_CLOCKS; i++)
+ omap_dm_timer_free(timer[i]);
+
clk_put(iva2_clk);
clk_put(ssi.sst_fck);
clk_put(ssi.ssr_fck);
void dsp_clk_init(void)
{
static struct platform_device dspbridge_device;
+ int i, id;
dspbridge_device.dev.bus = &platform_bus_type;
+ for (i = 0, id = 5; i < DM_TIMER_CLOCKS; i++, id++)
+ timer[i] = omap_dm_timer_request_specific(id);
+
iva2_clk = clk_get(&dspbridge_device.dev, "iva2_ck");
if (IS_ERR(iva2_clk))
dev_err(bridge, "failed to get iva2 clock %p\n", iva2_clk);
clk_enable(iva2_clk);
break;
case GPT_CLK:
- timer[clk_id - 1] =
- omap_dm_timer_request_specific(DMT_ID(clk_id));
+ status = omap_dm_timer_start(timer[clk_id - 1]);
break;
#ifdef CONFIG_OMAP_MCBSP
case MCBSP_CLK:
clk_disable(iva2_clk);
break;
case GPT_CLK:
- omap_dm_timer_free(timer[clk_id - 1]);
+ status = omap_dm_timer_stop(timer[clk_id - 1]);
break;
#ifdef CONFIG_OMAP_MCBSP
case MCBSP_CLK:
#include <linux/types.h>
#include <linux/platform_device.h>
#include <linux/pm.h>
-
-#ifdef MODULE
#include <linux/module.h>
-#endif
-
#include <linux/device.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
{
struct usbip_device *ud = &vdev->ud;
struct urb *urb;
+ unsigned long flags;
spin_lock(&vdev->priv_lock);
urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
{
struct vhci_unlink *unlink;
struct urb *urb;
+ unsigned long flags;
usbip_dump_header(pdu);
urb->status = pdu->u.ret_unlink.status;
pr_info("urb->status %d\n", urb->status);
- spin_lock(&the_controller->lock);
+ spin_lock_irqsave(&the_controller->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
- spin_unlock(&the_controller->lock);
+ spin_unlock_irqrestore(&the_controller->lock, flags);
usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
urb->status);
hdr = (struct iscsi_reject *) cmd->pdu;
hdr->reason = reason;
- cmd->buf_ptr = kzalloc(ISCSI_HDR_LEN, GFP_KERNEL);
+ cmd->buf_ptr = kmemdup(buf, ISCSI_HDR_LEN, GFP_KERNEL);
if (!cmd->buf_ptr) {
pr_err("Unable to allocate memory for cmd->buf_ptr\n");
iscsit_release_cmd(cmd);
return -1;
}
- memcpy(cmd->buf_ptr, buf, ISCSI_HDR_LEN);
spin_lock_bh(&conn->cmd_lock);
list_add_tail(&cmd->i_list, &conn->conn_cmd_list);
hdr = (struct iscsi_reject *) cmd->pdu;
hdr->reason = reason;
- cmd->buf_ptr = kzalloc(ISCSI_HDR_LEN, GFP_KERNEL);
+ cmd->buf_ptr = kmemdup(buf, ISCSI_HDR_LEN, GFP_KERNEL);
if (!cmd->buf_ptr) {
pr_err("Unable to allocate memory for cmd->buf_ptr\n");
iscsit_release_cmd(cmd);
return -1;
}
- memcpy(cmd->buf_ptr, buf, ISCSI_HDR_LEN);
if (add_to_conn) {
spin_lock_bh(&conn->cmd_lock);
" non-existent or non-exported iSCSI LUN:"
" 0x%016Lx\n", get_unaligned_le64(&hdr->lun));
}
- if (ret == PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
-
send_check_condition = 1;
goto attach_cmd;
}
*/
send_check_condition = 1;
} else {
+ cmd->data_length = cmd->se_cmd.data_length;
+
if (iscsit_decide_list_to_build(cmd, payload_length) < 0)
return iscsit_add_reject_from_cmd(
ISCSI_REASON_BOOKMARK_NO_RESOURCES,
* the backend memory allocation.
*/
ret = transport_generic_new_cmd(&cmd->se_cmd);
- if ((ret < 0) || (cmd->se_cmd.se_cmd_flags & SCF_SE_CMD_FAILED)) {
+ if (ret < 0) {
immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
dump_immediate_data = 1;
goto after_immediate_data;
spin_lock_irqsave(&se_cmd->t_state_lock, flags);
if (!(se_cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) ||
- (se_cmd->se_cmd_flags & SCF_SE_CMD_FAILED))
+ (se_cmd->se_cmd_flags & SCF_SCSI_CDB_EXCEPTION))
dump_unsolicited_data = 1;
spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
if (hdr->flags & ISCSI_FLAG_DATA_STATUS) {
if (cmd->se_cmd.se_cmd_flags & SCF_OVERFLOW_BIT) {
hdr->flags |= ISCSI_FLAG_DATA_OVERFLOW;
- hdr->residual_count = cpu_to_be32(cmd->residual_count);
+ hdr->residual_count = cpu_to_be32(cmd->se_cmd.residual_count);
} else if (cmd->se_cmd.se_cmd_flags & SCF_UNDERFLOW_BIT) {
hdr->flags |= ISCSI_FLAG_DATA_UNDERFLOW;
- hdr->residual_count = cpu_to_be32(cmd->residual_count);
+ hdr->residual_count = cpu_to_be32(cmd->se_cmd.residual_count);
}
}
hton24(hdr->dlength, datain.length);
hdr->flags |= ISCSI_FLAG_CMD_FINAL;
if (cmd->se_cmd.se_cmd_flags & SCF_OVERFLOW_BIT) {
hdr->flags |= ISCSI_FLAG_CMD_OVERFLOW;
- hdr->residual_count = cpu_to_be32(cmd->residual_count);
+ hdr->residual_count = cpu_to_be32(cmd->se_cmd.residual_count);
} else if (cmd->se_cmd.se_cmd_flags & SCF_UNDERFLOW_BIT) {
hdr->flags |= ISCSI_FLAG_CMD_UNDERFLOW;
- hdr->residual_count = cpu_to_be32(cmd->residual_count);
+ hdr->residual_count = cpu_to_be32(cmd->se_cmd.residual_count);
}
hdr->response = cmd->iscsi_response;
hdr->cmd_status = cmd->se_cmd.scsi_status;
hdr = (struct iscsi_tm_rsp *) cmd->pdu;
memset(hdr, 0, ISCSI_HDR_LEN);
hdr->opcode = ISCSI_OP_SCSI_TMFUNC_RSP;
+ hdr->flags = ISCSI_FLAG_CMD_FINAL;
hdr->response = iscsit_convert_tcm_tmr_rsp(se_tmr);
hdr->itt = cpu_to_be32(cmd->init_task_tag);
cmd->stat_sn = conn->stat_sn++;
static int chap_string_to_hex(unsigned char *dst, unsigned char *src, int len)
{
- int j = DIV_ROUND_UP(len, 2);
+ int j = DIV_ROUND_UP(len, 2), rc;
- hex2bin(dst, src, j);
+ rc = hex2bin(dst, src, j);
+ if (rc < 0)
+ pr_debug("CHAP string contains non hex digit symbols\n");
dst[j] = '\0';
return j;
u32 pdu_send_order;
/* Current struct iscsi_pdu in struct iscsi_cmd->pdu_list */
u32 pdu_start;
- u32 residual_count;
/* Next struct iscsi_seq to send in struct iscsi_cmd->seq_list */
u32 seq_send_order;
/* Number of struct iscsi_seq in struct iscsi_cmd->seq_list */
atomic_t connection_exit;
atomic_t connection_recovery;
atomic_t connection_reinstatement;
- atomic_t connection_wait;
atomic_t connection_wait_rcfr;
atomic_t sleep_on_conn_wait_comp;
atomic_t transport_failed;
atomic_t session_reinstatement;
atomic_t session_stop_active;
atomic_t sleep_on_sess_wait_comp;
- atomic_t transport_wait_cmds;
/* connection list */
struct list_head sess_conn_list;
struct list_head cr_active_list;
* handle the SCF_SCSI_RESERVATION_CONFLICT case here as well.
*/
if (se_cmd->se_cmd_flags & SCF_SCSI_CDB_EXCEPTION) {
- if (se_cmd->se_cmd_flags &
- SCF_SCSI_RESERVATION_CONFLICT) {
+ if (se_cmd->scsi_sense_reason == TCM_RESERVATION_CONFLICT) {
cmd->i_state = ISTATE_SEND_STATUS;
spin_unlock_bh(&cmd->istate_lock);
iscsit_add_cmd_to_response_queue(cmd, cmd->conn,
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
pr_err("Could not allocate memory for session\n");
- return -1;
+ return -ENOMEM;
}
iscsi_login_set_conn_values(sess, conn, pdu->cid);
pr_err("idr_pre_get() for sess_idr failed\n");
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
- return -1;
+ kfree(sess);
+ return -ENOMEM;
}
spin_lock(&sess_idr_lock);
idr_get_new(&sess_idr, NULL, &sess->session_index);
ISCSI_LOGIN_STATUS_NO_RESOURCES);
pr_err("Unable to allocate memory for"
" struct iscsi_sess_ops.\n");
- return -1;
+ kfree(sess);
+ return -ENOMEM;
}
sess->se_sess = transport_init_session();
- if (!sess->se_sess) {
+ if (IS_ERR(sess->se_sess)) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
- return -1;
+ kfree(sess);
+ return -ENOMEM;
}
return 0;
return NULL;
}
- login->req = kzalloc(ISCSI_HDR_LEN, GFP_KERNEL);
+ login->req = kmemdup(login_pdu, ISCSI_HDR_LEN, GFP_KERNEL);
if (!login->req) {
pr_err("Unable to allocate memory for Login Request.\n");
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
goto out;
}
- memcpy(login->req, login_pdu, ISCSI_HDR_LEN);
login->req_buf = kzalloc(MAX_KEY_VALUE_PAIRS, GFP_KERNEL);
if (!login->req_buf) {
scsi_bufflen(sc), sc->sc_data_direction, sam_task_attr,
&tl_cmd->tl_sense_buf[0]);
- /*
- * Signal BIDI usage with T_TASK(cmd)->t_tasks_bidi
- */
if (scsi_bidi_cmnd(sc))
- se_cmd->t_tasks_bidi = 1;
+ se_cmd->se_cmd_flags |= SCF_BIDI;
+
/*
* Locate the struct se_lun pointer and attach it to struct se_cmd
*/
* Allocate the necessary tasks to complete the received CDB+data
*/
ret = transport_generic_allocate_tasks(se_cmd, sc->cmnd);
- if (ret == -ENOMEM) {
- /* Out of Resources */
- return PYX_TRANSPORT_LU_COMM_FAILURE;
- } else if (ret == -EINVAL) {
- /*
- * Handle case for SAM_STAT_RESERVATION_CONFLICT
- */
- if (se_cmd->se_cmd_flags & SCF_SCSI_RESERVATION_CONFLICT)
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
- /*
- * Otherwise, return SAM_STAT_CHECK_CONDITION and return
- * sense data.
- */
- return PYX_TRANSPORT_USE_SENSE_REASON;
- }
-
+ if (ret != 0)
+ return ret;
/*
* For BIDI commands, pass in the extra READ buffer
* to transport_generic_map_mem_to_cmd() below..
*/
- if (se_cmd->t_tasks_bidi) {
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
struct scsi_data_buffer *sdb = scsi_in(sc);
sgl_bidi = sdb->table.sgl;
}
/* Tell the core about our preallocated memory */
- ret = transport_generic_map_mem_to_cmd(se_cmd, scsi_sglist(sc),
+ return transport_generic_map_mem_to_cmd(se_cmd, scsi_sglist(sc),
scsi_sg_count(sc), sgl_bidi, sgl_bidi_count);
- if (ret < 0)
- return PYX_TRANSPORT_LU_COMM_FAILURE;
-
- return 0;
}
/*
{
struct tcm_loop_hba *tl_hba = container_of(wwn,
struct tcm_loop_hba, tl_hba_wwn);
- int host_no = tl_hba->sh->host_no;
+
+ pr_debug("TCM_Loop_ConfigFS: Deallocating emulated Target"
+ " SAS Address: %s at Linux/SCSI Host ID: %d\n",
+ tl_hba->tl_wwn_address, tl_hba->sh->host_no);
/*
* Call device_unregister() on the original tl_hba->dev.
* tcm_loop_fabric_scsi.c:tcm_loop_release_adapter() will
* release *tl_hba;
*/
device_unregister(&tl_hba->dev);
-
- pr_debug("TCM_Loop_ConfigFS: Deallocated emulated Target"
- " SAS Address: %s at Linux/SCSI Host ID: %d\n",
- config_item_name(&wwn->wwn_group.cg_item), host_no);
}
/* Start items for tcm_loop_cit */
int alua_access_state, primary = 0, rc;
u16 tg_pt_id, rtpi;
- if (!l_port)
- return PYX_TRANSPORT_LU_COMM_FAILURE;
-
+ if (!l_port) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
+ }
buf = transport_kmap_first_data_page(cmd);
/*
l_tg_pt_gp_mem = l_port->sep_alua_tg_pt_gp_mem;
if (!l_tg_pt_gp_mem) {
pr_err("Unable to access l_port->sep_alua_tg_pt_gp_mem\n");
- rc = PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ rc = -EINVAL;
goto out;
}
spin_lock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
if (!l_tg_pt_gp) {
spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
pr_err("Unable to access *l_tg_pt_gp_mem->tg_pt_gp\n");
- rc = PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ rc = -EINVAL;
goto out;
}
rc = (l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA);
if (!rc) {
pr_debug("Unable to process SET_TARGET_PORT_GROUPS"
" while TPGS_EXPLICT_ALUA is disabled\n");
- rc = PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ rc = -EINVAL;
goto out;
}
* REQUEST, and the additional sense code set to INVALID
* FIELD IN PARAMETER LIST.
*/
- rc = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ rc = -EINVAL;
goto out;
}
rc = -1;
* throw an exception with ASCQ: INVALID_PARAMETER_LIST
*/
if (rc != 0) {
- rc = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ rc = -EINVAL;
goto out;
}
} else {
* INVALID_PARAMETER_LIST
*/
if (rc != 0) {
- rc = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ rc = -EINVAL;
goto out;
}
}
* struct t10_alua_lu_gp.
*/
spin_lock(&lu_gps_lock);
- atomic_set(&lu_gp->lu_gp_shutdown, 1);
list_del(&lu_gp->lu_gp_node);
alua_lu_gps_count--;
spin_unlock(&lu_gps_lock);
tg_pt_gp_mem->tg_pt = port;
port->sep_alua_tg_pt_gp_mem = tg_pt_gp_mem;
- atomic_set(&port->sep_tg_pt_gp_active, 1);
return tg_pt_gp_mem;
}
if (cmd->data_length < 60)
return 0;
- buf[2] = 0x3c;
+ buf[3] = 0x3c;
/* Set HEADSUP, ORDSUP, SIMPSUP */
buf[5] = 0x07;
if (cmd->data_length < 4) {
pr_err("SCSI Inquiry payload length: %u"
" too small for EVPD=1\n", cmd->data_length);
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
return -EINVAL;
}
}
pr_err("Unknown VPD Code: 0x%02x\n", cdb[2]);
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
ret = -EINVAL;
out_unmap:
default:
pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n",
cdb[2] & 0x3f, cdb[3]);
- return PYX_TRANSPORT_UNKNOWN_MODE_PAGE;
+ cmd->scsi_sense_reason = TCM_UNKNOWN_MODE_PAGE;
+ return -EINVAL;
}
offset += length;
if (cdb[1] & 0x01) {
pr_err("REQUEST_SENSE description emulation not"
" supported\n");
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -ENOSYS;
}
buf = transport_kmap_first_data_page(cmd);
if (!dev->transport->do_discard) {
pr_err("UNMAP emulation not supported for: %s\n",
dev->transport->name);
- return PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ return -ENOSYS;
}
/* First UNMAP block descriptor starts at 8 byte offset */
if (!dev->transport->do_discard) {
pr_err("WRITE_SAME emulation not supported"
" for: %s\n", dev->transport->name);
- return PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ return -ENOSYS;
}
if (cmd->t_task_cdb[0] == WRITE_SAME)
int target_emulate_synchronize_cache(struct se_task *task)
{
struct se_device *dev = task->task_se_cmd->se_dev;
+ struct se_cmd *cmd = task->task_se_cmd;
if (!dev->transport->do_sync_cache) {
pr_err("SYNCHRONIZE_CACHE emulation not supported"
" for: %s\n", dev->transport->name);
- return PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ return -ENOSYS;
}
dev->transport->do_sync_cache(task);
static struct config_group alua_group;
static struct config_group alua_lu_gps_group;
-static DEFINE_SPINLOCK(se_device_lock);
-static LIST_HEAD(se_dev_list);
-
static inline struct se_hba *
item_to_hba(struct config_item *item)
{
" struct se_subsystem_dev\n");
goto unlock;
}
- INIT_LIST_HEAD(&se_dev->se_dev_node);
INIT_LIST_HEAD(&se_dev->t10_wwn.t10_vpd_list);
spin_lock_init(&se_dev->t10_wwn.t10_vpd_lock);
INIT_LIST_HEAD(&se_dev->t10_pr.registration_list);
" from allocate_virtdevice()\n");
goto out;
}
- spin_lock(&se_device_lock);
- list_add_tail(&se_dev->se_dev_node, &se_dev_list);
- spin_unlock(&se_device_lock);
config_group_init_type_name(&se_dev->se_dev_group, name,
&target_core_dev_cit);
mutex_lock(&hba->hba_access_mutex);
t = hba->transport;
- spin_lock(&se_device_lock);
- list_del(&se_dev->se_dev_node);
- spin_unlock(&se_device_lock);
-
dev_stat_grp = &se_dev->dev_stat_grps.stat_group;
for (i = 0; dev_stat_grp->default_groups[i]; i++) {
df_item = &dev_stat_grp->default_groups[i]->cg_item;
se_cmd->se_lun = deve->se_lun;
se_cmd->pr_res_key = deve->pr_res_key;
se_cmd->orig_fe_lun = unpacked_lun;
- se_cmd->se_orig_obj_ptr = se_cmd->se_lun->lun_se_dev;
se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
}
spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
se_lun = &se_sess->se_tpg->tpg_virt_lun0;
se_cmd->se_lun = &se_sess->se_tpg->tpg_virt_lun0;
se_cmd->orig_fe_lun = 0;
- se_cmd->se_orig_obj_ptr = se_cmd->se_lun->lun_se_dev;
se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
}
/*
se_lun = deve->se_lun;
se_cmd->pr_res_key = deve->pr_res_key;
se_cmd->orig_fe_lun = unpacked_lun;
- se_cmd->se_orig_obj_ptr = se_cmd->se_dev;
}
spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
se_task->task_scsi_status = GOOD;
transport_complete_task(se_task, 1);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
/* se_release_device_for_hba():
return -EINVAL;
}
- pr_err("dpo_emulated not supported\n");
- return -EINVAL;
+ if (flag) {
+ pr_err("dpo_emulated not supported\n");
+ return -EINVAL;
+ }
+
+ return 0;
}
int se_dev_set_emulate_fua_write(struct se_device *dev, int flag)
return -EINVAL;
}
- if (dev->transport->fua_write_emulated == 0) {
+ if (flag && dev->transport->fua_write_emulated == 0) {
pr_err("fua_write_emulated not supported\n");
return -EINVAL;
}
return -EINVAL;
}
- pr_err("ua read emulated not supported\n");
- return -EINVAL;
+ if (flag) {
+ pr_err("ua read emulated not supported\n");
+ return -EINVAL;
+ }
+
+ return 0;
}
int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
pr_err("Illegal value %d\n", flag);
return -EINVAL;
}
- if (dev->transport->write_cache_emulated == 0) {
+ if (flag && dev->transport->write_cache_emulated == 0) {
pr_err("write_cache_emulated not supported\n");
return -EINVAL;
}
* We expect this value to be non-zero when generic Block Layer
* Discard supported is detected iblock_create_virtdevice().
*/
- if (!dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
+ if (flag && !dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
pr_err("Generic Block Discard not supported\n");
return -ENOSYS;
}
* We expect this value to be non-zero when generic Block Layer
* Discard supported is detected iblock_create_virtdevice().
*/
- if (!dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
+ if (flag && !dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
pr_err("Generic Block Discard not supported\n");
return -ENOSYS;
}
ret = -ENOMEM;
goto out;
}
- INIT_LIST_HEAD(&se_dev->se_dev_node);
INIT_LIST_HEAD(&se_dev->t10_wwn.t10_vpd_list);
spin_lock_init(&se_dev->t10_wwn.t10_vpd_lock);
INIT_LIST_HEAD(&se_dev->t10_pr.registration_list);
return -ENOMEM;
}
- for (i = 0; i < task->task_sg_nents; i++) {
- iov[i].iov_len = sg[i].length;
- iov[i].iov_base = sg_virt(&sg[i]);
+ for_each_sg(task->task_sg, sg, task->task_sg_nents, i) {
+ iov[i].iov_len = sg->length;
+ iov[i].iov_base = sg_virt(sg);
}
old_fs = get_fs();
return -ENOMEM;
}
- for (i = 0; i < task->task_sg_nents; i++) {
- iov[i].iov_len = sg[i].length;
- iov[i].iov_base = sg_virt(&sg[i]);
+ for_each_sg(task->task_sg, sg, task->task_sg_nents, i) {
+ iov[i].iov_len = sg->length;
+ iov[i].iov_base = sg_virt(sg);
}
old_fs = get_fs();
if (ret > 0 &&
dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0 &&
dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
- cmd->t_tasks_fua) {
+ (cmd->se_cmd_flags & SCF_FUA)) {
/*
* We might need to be a bit smarter here
* and return some sense data to let the initiator
}
- if (ret < 0)
+ if (ret < 0) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
return ret;
+ }
if (ret) {
task->task_scsi_status = GOOD;
transport_complete_task(task, 1);
}
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
/* fd_free_task(): (Part of se_subsystem_api_t template)
*/
if (dev->se_sub_dev->se_dev_attrib.emulate_write_cache == 0 ||
(dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
- task->task_se_cmd->t_tasks_fua))
+ (cmd->se_cmd_flags & SCF_FUA)))
rw = WRITE_FUA;
else
rw = WRITE;
else {
pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
" %u\n", dev->se_sub_dev->se_dev_attrib.block_size);
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOSYS;
}
bio = iblock_get_bio(task, block_lba, sg_num);
- if (!bio)
- return PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES;
+ if (!bio) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOMEM;
+ }
bio_list_init(&list);
bio_list_add(&list, bio);
submit_bio(rw, bio);
blk_finish_plug(&plug);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
fail:
while ((bio = bio_list_pop(&list)))
bio_put(bio);
- return PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOMEM;
}
static u32 iblock_get_device_rev(struct se_device *dev)
pr_err("Received legacy SPC-2 RESERVE/RELEASE"
" while active SPC-3 registrations exist,"
" returning RESERVATION_CONFLICT\n");
- *ret = PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
return true;
}
(cmd->t_task_cdb[1] & 0x02)) {
pr_err("LongIO and Obselete Bits set, returning"
" ILLEGAL_REQUEST\n");
- ret = PYX_TRANSPORT_ILLEGAL_REQUEST;
+ cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+ ret = -EINVAL;
goto out;
}
/*
" from %s \n", cmd->se_lun->unpacked_lun,
cmd->se_deve->mapped_lun,
sess->se_node_acl->initiatorname);
- ret = PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ ret = -EINVAL;
goto out_unlock;
}
tidh_new = kzalloc(sizeof(struct pr_transport_id_holder), GFP_KERNEL);
if (!tidh_new) {
pr_err("Unable to allocate tidh_new\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
INIT_LIST_HEAD(&tidh_new->dest_list);
tidh_new->dest_tpg = tpg;
sa_res_key, all_tg_pt, aptpl);
if (!local_pr_reg) {
kfree(tidh_new);
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOMEM;
}
tidh_new->dest_pr_reg = local_pr_reg;
/*
pr_err("SPC-3 PR: Illegal tpdl: %u + 28 byte header"
" does not equal CDB data_length: %u\n", tpdl,
cmd->data_length);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
/*
" for tmp_tpg\n");
atomic_dec(&tmp_tpg->tpg_pr_ref_count);
smp_mb__after_atomic_dec();
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -EINVAL;
goto out;
}
/*
atomic_dec(&dest_node_acl->acl_pr_ref_count);
smp_mb__after_atomic_dec();
core_scsi3_tpg_undepend_item(tmp_tpg);
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -EINVAL;
goto out;
}
if (!dest_tpg) {
pr_err("SPC-3 PR SPEC_I_PT: Unable to locate"
" dest_tpg\n");
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
#if 0
" %u for Transport ID: %s\n", tid_len, ptr);
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
/*
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
smp_mb__after_atomic_dec();
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -EINVAL;
goto out;
}
#if 0
core_scsi3_lunacl_undepend_item(dest_se_deve);
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -ENOMEM;
goto out;
}
INIT_LIST_HEAD(&tidh_new->dest_list);
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
kfree(tidh_new);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
tidh_new->dest_pr_reg = dest_pr_reg;
if (!se_sess || !se_lun) {
pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
se_tpg = se_sess->se_tpg;
se_deve = &se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
if (res_key) {
pr_warn("SPC-3 PR: Reservation Key non-zero"
" for SA REGISTER, returning CONFLICT\n");
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* Do nothing but return GOOD status.
*/
if (!sa_res_key)
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
if (!spec_i_pt) {
/*
if (ret != 0) {
pr_err("Unable to allocate"
" struct t10_pr_registration\n");
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
} else {
/*
" 0x%016Lx\n", res_key,
pr_reg->pr_res_key);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
}
if (spec_i_pt) {
pr_err("SPC-3 PR UNREGISTER: SPEC_I_PT"
" set while sa_res_key=0\n");
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
/*
* An existing ALL_TG_PT=1 registration being released
" registration exists, but ALL_TG_PT=1 bit not"
" present in received PROUT\n");
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
/*
* Allocate APTPL metadata buffer used for UNREGISTER ops
pr_err("Unable to allocate"
" pr_aptpl_buf\n");
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
}
/*
if (pr_holder < 0) {
kfree(pr_aptpl_buf);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
spin_lock(&pr_tmpl->registration_lock);
if (!se_sess || !se_lun) {
pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
se_tpg = se_sess->se_tpg;
se_deve = &se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
if (!pr_reg) {
pr_err("SPC-3 PR: Unable to locate"
" PR_REGISTERED *pr_reg for RESERVE\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.9: Reserving:
" does not match existing SA REGISTER res_key:"
" 0x%016Lx\n", res_key, pr_reg->pr_res_key);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.9: Reserving:
if (scope != PR_SCOPE_LU_SCOPE) {
pr_err("SPC-3 PR: Illegal SCOPE: 0x%02x\n", scope);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
/*
* See if we have an existing PR reservation holder pointer at
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.9: Reserving:
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.9: Reserving:
*/
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
/*
* Otherwise, our *pr_reg becomes the PR reservation holder for said
default:
pr_err("SPC-3 PR: Unknown Service Action RESERVE Type:"
" 0x%02x\n", type);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
return ret;
if (!se_sess || !se_lun) {
pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
/*
* Locate the existing *pr_reg via struct se_node_acl pointers
if (!pr_reg) {
pr_err("SPC-3 PR: Unable to locate"
" PR_REGISTERED *pr_reg for RELEASE\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.11.2 Releasing:
*/
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
if ((pr_res_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) ||
(pr_res_holder->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG))
*/
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
/*
* From spc4r17 Section 5.7.11.2 Releasing:
" 0x%016Lx\n", res_key, pr_reg->pr_res_key);
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* From spc4r17 Section 5.7.11.2 Releasing and above:
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* In response to a persistent reservation release request from the
if (!pr_reg_n) {
pr_err("SPC-3 PR: Unable to locate"
" PR_REGISTERED *pr_reg for CLEAR\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
/*
* From spc4r17 section 5.7.11.6, Clearing:
" existing SA REGISTER res_key:"
" 0x%016Lx\n", res_key, pr_reg_n->pr_res_key);
core_scsi3_put_pr_reg(pr_reg_n);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* a) Release the persistent reservation, if any;
int all_reg = 0, calling_it_nexus = 0, released_regs = 0;
int prh_type = 0, prh_scope = 0, ret;
- if (!se_sess)
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ if (!se_sess) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
+ }
se_deve = &se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
pr_reg_n = core_scsi3_locate_pr_reg(cmd->se_dev, se_sess->se_node_acl,
pr_err("SPC-3 PR: Unable to locate"
" PR_REGISTERED *pr_reg for PREEMPT%s\n",
(abort) ? "_AND_ABORT" : "");
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
if (pr_reg_n->pr_res_key != res_key) {
core_scsi3_put_pr_reg(pr_reg_n);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
if (scope != PR_SCOPE_LU_SCOPE) {
pr_err("SPC-3 PR: Illegal SCOPE: 0x%02x\n", scope);
core_scsi3_put_pr_reg(pr_reg_n);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
INIT_LIST_HEAD(&preempt_and_abort_list);
if (!all_reg && !sa_res_key) {
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg_n);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
/*
* From spc4r17, section 5.7.11.4.4 Removing Registrations:
if (!released_regs) {
spin_unlock(&dev->dev_reservation_lock);
core_scsi3_put_pr_reg(pr_reg_n);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* For an existing all registrants type reservation
default:
pr_err("SPC-3 PR: Unknown Service Action PREEMPT%s"
" Type: 0x%02x\n", (abort) ? "_AND_ABORT" : "", type);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
return ret;
if (!se_sess || !se_lun) {
pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
memset(dest_iport, 0, 64);
memset(i_buf, 0, PR_REG_ISID_ID_LEN);
if (!pr_reg) {
pr_err("SPC-3 PR: Unable to locate PR_REGISTERED"
" *pr_reg for REGISTER_AND_MOVE\n");
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
/*
* The provided reservation key much match the existing reservation key
" res_key: 0x%016Lx does not match existing SA REGISTER"
" res_key: 0x%016Lx\n", res_key, pr_reg->pr_res_key);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
/*
* The service active reservation key needs to be non zero
pr_warn("SPC-3 PR REGISTER_AND_MOVE: Received zero"
" sa_res_key\n");
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
/*
" does not equal CDB data_length: %u\n", tid_len,
cmd->data_length);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
spin_lock(&dev->se_port_lock);
atomic_dec(&dest_se_tpg->tpg_pr_ref_count);
smp_mb__after_atomic_dec();
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
}
spin_lock(&dev->se_port_lock);
" fabric ops from Relative Target Port Identifier:"
" %hu\n", rtpi);
core_scsi3_put_pr_reg(pr_reg);
- return PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ return -EINVAL;
}
buf = transport_kmap_first_data_page(cmd);
" from fabric: %s\n", proto_ident,
dest_tf_ops->get_fabric_proto_ident(dest_se_tpg),
dest_tf_ops->get_fabric_name());
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
if (dest_tf_ops->tpg_parse_pr_out_transport_id == NULL) {
pr_err("SPC-3 PR REGISTER_AND_MOVE: Fabric does not"
" containg a valid tpg_parse_pr_out_transport_id"
" function pointer\n");
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -EINVAL;
goto out;
}
initiator_str = dest_tf_ops->tpg_parse_pr_out_transport_id(dest_se_tpg,
if (!initiator_str) {
pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
" initiator_str from Transport ID\n");
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
pr_err("SPC-3 PR REGISTER_AND_MOVE: TransportID: %s"
" matches: %s on received I_T Nexus\n", initiator_str,
pr_reg_nacl->initiatorname);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
if (!strcmp(iport_ptr, pr_reg->pr_reg_isid)) {
" matches: %s %s on received I_T Nexus\n",
initiator_str, iport_ptr, pr_reg_nacl->initiatorname,
pr_reg->pr_reg_isid);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
after_iport_check:
pr_err("Unable to locate %s dest_node_acl for"
" TransportID%s\n", dest_tf_ops->get_fabric_name(),
initiator_str);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
ret = core_scsi3_nodeacl_depend_item(dest_node_acl);
atomic_dec(&dest_node_acl->acl_pr_ref_count);
smp_mb__after_atomic_dec();
dest_node_acl = NULL;
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
#if 0
if (!dest_se_deve) {
pr_err("Unable to locate %s dest_se_deve from RTPI:"
" %hu\n", dest_tf_ops->get_fabric_name(), rtpi);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
atomic_dec(&dest_se_deve->pr_ref_count);
smp_mb__after_atomic_dec();
dest_se_deve = NULL;
- ret = PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ ret = -EINVAL;
goto out;
}
#if 0
pr_warn("SPC-3 PR REGISTER_AND_MOVE: No reservation"
" currently held\n");
spin_unlock(&dev->dev_reservation_lock);
- ret = PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ ret = -EINVAL;
goto out;
}
/*
pr_warn("SPC-3 PR REGISTER_AND_MOVE: Calling I_T"
" Nexus is not reservation holder\n");
spin_unlock(&dev->dev_reservation_lock);
- ret = PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ ret = -EINVAL;
goto out;
}
/*
" reservation for type: %s\n",
core_scsi3_pr_dump_type(pr_res_holder->pr_res_type));
spin_unlock(&dev->dev_reservation_lock);
- ret = PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ ret = -EINVAL;
goto out;
}
pr_res_nacl = pr_res_holder->pr_reg_nacl;
sa_res_key, 0, aptpl, 2, 1);
if (ret != 0) {
spin_unlock(&dev->dev_reservation_lock);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
pr_err("Received PERSISTENT_RESERVE CDB while legacy"
" SPC-2 reservation is held, returning"
" RESERVATION_CONFLICT\n");
- ret = PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ ret = EINVAL;
goto out;
}
* FIXME: A NULL struct se_session pointer means an this is not coming from
* a $FABRIC_MOD's nexus, but from internal passthrough ops.
*/
- if (!cmd->se_sess)
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ if (!cmd->se_sess) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -EINVAL;
+ }
if (cmd->data_length < 24) {
pr_warn("SPC-PR: Received PR OUT parameter list"
" length too small: %u\n", cmd->data_length);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
/*
* SPEC_I_PT=1 is only valid for Service action: REGISTER
*/
if (spec_i_pt && ((cdb[1] & 0x1f) != PRO_REGISTER)) {
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
(cmd->data_length != 24)) {
pr_warn("SPC-PR: Received PR OUT illegal parameter"
" list length: %u\n", cmd->data_length);
- ret = PYX_TRANSPORT_INVALID_PARAMETER_LIST;
+ cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
+ ret = -EINVAL;
goto out;
}
/*
default:
pr_err("Unknown PERSISTENT_RESERVE_OUT service"
" action: 0x%02x\n", cdb[1] & 0x1f);
- ret = PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ ret = -EINVAL;
break;
}
if (cmd->data_length < 8) {
pr_err("PRIN SA READ_KEYS SCSI Data Length: %u"
" too small\n", cmd->data_length);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
buf = transport_kmap_first_data_page(cmd);
if (cmd->data_length < 8) {
pr_err("PRIN SA READ_RESERVATIONS SCSI Data Length: %u"
" too small\n", cmd->data_length);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
buf = transport_kmap_first_data_page(cmd);
if (cmd->data_length < 6) {
pr_err("PRIN SA REPORT_CAPABILITIES SCSI Data Length:"
" %u too small\n", cmd->data_length);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
buf = transport_kmap_first_data_page(cmd);
if (cmd->data_length < 8) {
pr_err("PRIN SA READ_FULL_STATUS SCSI Data Length: %u"
" too small\n", cmd->data_length);
- return PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
}
buf = transport_kmap_first_data_page(cmd);
pr_err("Received PERSISTENT_RESERVE CDB while legacy"
" SPC-2 reservation is held, returning"
" RESERVATION_CONFLICT\n");
- return PYX_TRANSPORT_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EINVAL;
}
switch (cmd->t_task_cdb[1] & 0x1f) {
default:
pr_err("Unknown PERSISTENT_RESERVE_IN service"
" action: 0x%02x\n", cmd->t_task_cdb[1] & 0x1f);
- ret = PYX_TRANSPORT_INVALID_CDB_FIELD;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ ret = -EINVAL;
break;
}
static int pscsi_map_sg(struct se_task *task, struct scatterlist *task_sg,
struct bio **hbio)
{
+ struct se_cmd *cmd = task->task_se_cmd;
struct pscsi_dev_virt *pdv = task->task_se_cmd->se_dev->dev_ptr;
u32 task_sg_num = task->task_sg_nents;
struct bio *bio = NULL, *tbio = NULL;
u32 data_len = task->task_size, i, len, bytes, off;
int nr_pages = (task->task_size + task_sg[0].offset +
PAGE_SIZE - 1) >> PAGE_SHIFT;
- int nr_vecs = 0, rc, ret = PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES;
+ int nr_vecs = 0, rc;
int rw = (task->task_data_direction == DMA_TO_DEVICE);
*hbio = NULL;
bio->bi_next = NULL;
bio_endio(bio, 0); /* XXX: should be error */
}
- return ret;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOMEM;
}
static int pscsi_do_task(struct se_task *task)
{
+ struct se_cmd *cmd = task->task_se_cmd;
struct pscsi_dev_virt *pdv = task->task_se_cmd->se_dev->dev_ptr;
struct pscsi_plugin_task *pt = PSCSI_TASK(task);
struct request *req;
if (!req || IS_ERR(req)) {
pr_err("PSCSI: blk_get_request() failed: %ld\n",
req ? IS_ERR(req) : -ENOMEM);
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENODEV;
}
} else {
BUG_ON(!task->task_size);
* Setup the main struct request for the task->task_sg[] payload
*/
ret = pscsi_map_sg(task, task->task_sg, &hbio);
- if (ret < 0)
- return PYX_TRANSPORT_LU_COMM_FAILURE;
+ if (ret < 0) {
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return ret;
+ }
req = blk_make_request(pdv->pdv_sd->request_queue, hbio,
GFP_KERNEL);
(task->task_se_cmd->sam_task_attr == MSG_HEAD_TAG),
pscsi_req_done);
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
fail:
while (hbio) {
bio->bi_next = NULL;
bio_endio(bio, 0); /* XXX: should be error */
}
- return PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES;
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -ENOMEM;
}
/* pscsi_get_sense_buffer():
" 0x%02x Result: 0x%08x\n", task, pt->pscsi_cdb[0],
pt->pscsi_result);
task->task_scsi_status = SAM_STAT_CHECK_CONDITION;
- task->task_error_status = PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
- task->task_se_cmd->transport_error_status =
- PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ task->task_se_cmd->scsi_sense_reason =
+ TCM_UNSUPPORTED_SCSI_OPCODE;
transport_complete_task(task, 0);
break;
}
return NULL;
}
-/* rd_MEMCPY_read():
- *
- *
- */
-static int rd_MEMCPY_read(struct rd_request *req)
+static int rd_MEMCPY(struct rd_request *req, u32 read_rd)
{
struct se_task *task = &req->rd_task;
struct rd_dev *dev = req->rd_task.task_se_cmd->se_dev->dev_ptr;
struct rd_dev_sg_table *table;
- struct scatterlist *sg_d, *sg_s;
- void *dst, *src;
- u32 i = 0, j = 0, dst_offset = 0, src_offset = 0;
- u32 length, page_end = 0, table_sg_end;
+ struct scatterlist *rd_sg;
+ struct sg_mapping_iter m;
u32 rd_offset = req->rd_offset;
+ u32 src_len;
table = rd_get_sg_table(dev, req->rd_page);
if (!table)
return -EINVAL;
- table_sg_end = (table->page_end_offset - req->rd_page);
- sg_d = task->task_sg;
- sg_s = &table->sg_table[req->rd_page - table->page_start_offset];
+ rd_sg = &table->sg_table[req->rd_page - table->page_start_offset];
- pr_debug("RD[%u]: Read LBA: %llu, Size: %u Page: %u, Offset:"
- " %u\n", dev->rd_dev_id, task->task_lba, req->rd_size,
- req->rd_page, req->rd_offset);
-
- src_offset = rd_offset;
+ pr_debug("RD[%u]: %s LBA: %llu, Size: %u Page: %u, Offset: %u\n",
+ dev->rd_dev_id, read_rd ? "Read" : "Write",
+ task->task_lba, req->rd_size, req->rd_page,
+ rd_offset);
+ src_len = PAGE_SIZE - rd_offset;
+ sg_miter_start(&m, task->task_sg, task->task_sg_nents,
+ read_rd ? SG_MITER_TO_SG : SG_MITER_FROM_SG);
while (req->rd_size) {
- if ((sg_d[i].length - dst_offset) <
- (sg_s[j].length - src_offset)) {
- length = (sg_d[i].length - dst_offset);
-
- pr_debug("Step 1 - sg_d[%d]: %p length: %d"
- " offset: %u sg_s[%d].length: %u\n", i,
- &sg_d[i], sg_d[i].length, sg_d[i].offset, j,
- sg_s[j].length);
- pr_debug("Step 1 - length: %u dst_offset: %u"
- " src_offset: %u\n", length, dst_offset,
- src_offset);
-
- if (length > req->rd_size)
- length = req->rd_size;
-
- dst = sg_virt(&sg_d[i++]) + dst_offset;
- BUG_ON(!dst);
-
- src = sg_virt(&sg_s[j]) + src_offset;
- BUG_ON(!src);
-
- dst_offset = 0;
- src_offset = length;
- page_end = 0;
- } else {
- length = (sg_s[j].length - src_offset);
-
- pr_debug("Step 2 - sg_d[%d]: %p length: %d"
- " offset: %u sg_s[%d].length: %u\n", i,
- &sg_d[i], sg_d[i].length, sg_d[i].offset,
- j, sg_s[j].length);
- pr_debug("Step 2 - length: %u dst_offset: %u"
- " src_offset: %u\n", length, dst_offset,
- src_offset);
-
- if (length > req->rd_size)
- length = req->rd_size;
-
- dst = sg_virt(&sg_d[i]) + dst_offset;
- BUG_ON(!dst);
-
- if (sg_d[i].length == length) {
- i++;
- dst_offset = 0;
- } else
- dst_offset = length;
-
- src = sg_virt(&sg_s[j++]) + src_offset;
- BUG_ON(!src);
-
- src_offset = 0;
- page_end = 1;
- }
+ u32 len;
+ void *rd_addr;
- memcpy(dst, src, length);
+ sg_miter_next(&m);
+ len = min((u32)m.length, src_len);
+ m.consumed = len;
- pr_debug("page: %u, remaining size: %u, length: %u,"
- " i: %u, j: %u\n", req->rd_page,
- (req->rd_size - length), length, i, j);
+ rd_addr = sg_virt(rd_sg) + rd_offset;
- req->rd_size -= length;
- if (!req->rd_size)
- return 0;
+ if (read_rd)
+ memcpy(m.addr, rd_addr, len);
+ else
+ memcpy(rd_addr, m.addr, len);
- if (!page_end)
+ req->rd_size -= len;
+ if (!req->rd_size)
continue;
- if (++req->rd_page <= table->page_end_offset) {
- pr_debug("page: %u in same page table\n",
- req->rd_page);
+ src_len -= len;
+ if (src_len) {
+ rd_offset += len;
continue;
}
- pr_debug("getting new page table for page: %u\n",
- req->rd_page);
-
- table = rd_get_sg_table(dev, req->rd_page);
- if (!table)
- return -EINVAL;
-
- sg_s = &table->sg_table[j = 0];
- }
-
- return 0;
-}
-
-/* rd_MEMCPY_write():
- *
- *
- */
-static int rd_MEMCPY_write(struct rd_request *req)
-{
- struct se_task *task = &req->rd_task;
- struct rd_dev *dev = req->rd_task.task_se_cmd->se_dev->dev_ptr;
- struct rd_dev_sg_table *table;
- struct scatterlist *sg_d, *sg_s;
- void *dst, *src;
- u32 i = 0, j = 0, dst_offset = 0, src_offset = 0;
- u32 length, page_end = 0, table_sg_end;
- u32 rd_offset = req->rd_offset;
-
- table = rd_get_sg_table(dev, req->rd_page);
- if (!table)
- return -EINVAL;
-
- table_sg_end = (table->page_end_offset - req->rd_page);
- sg_d = &table->sg_table[req->rd_page - table->page_start_offset];
- sg_s = task->task_sg;
-
- pr_debug("RD[%d] Write LBA: %llu, Size: %u, Page: %u,"
- " Offset: %u\n", dev->rd_dev_id, task->task_lba, req->rd_size,
- req->rd_page, req->rd_offset);
-
- dst_offset = rd_offset;
-
- while (req->rd_size) {
- if ((sg_s[i].length - src_offset) <
- (sg_d[j].length - dst_offset)) {
- length = (sg_s[i].length - src_offset);
-
- pr_debug("Step 1 - sg_s[%d]: %p length: %d"
- " offset: %d sg_d[%d].length: %u\n", i,
- &sg_s[i], sg_s[i].length, sg_s[i].offset,
- j, sg_d[j].length);
- pr_debug("Step 1 - length: %u src_offset: %u"
- " dst_offset: %u\n", length, src_offset,
- dst_offset);
-
- if (length > req->rd_size)
- length = req->rd_size;
-
- src = sg_virt(&sg_s[i++]) + src_offset;
- BUG_ON(!src);
-
- dst = sg_virt(&sg_d[j]) + dst_offset;
- BUG_ON(!dst);
-
- src_offset = 0;
- dst_offset = length;
- page_end = 0;
- } else {
- length = (sg_d[j].length - dst_offset);
-
- pr_debug("Step 2 - sg_s[%d]: %p length: %d"
- " offset: %d sg_d[%d].length: %u\n", i,
- &sg_s[i], sg_s[i].length, sg_s[i].offset,
- j, sg_d[j].length);
- pr_debug("Step 2 - length: %u src_offset: %u"
- " dst_offset: %u\n", length, src_offset,
- dst_offset);
-
- if (length > req->rd_size)
- length = req->rd_size;
-
- src = sg_virt(&sg_s[i]) + src_offset;
- BUG_ON(!src);
-
- if (sg_s[i].length == length) {
- i++;
- src_offset = 0;
- } else
- src_offset = length;
-
- dst = sg_virt(&sg_d[j++]) + dst_offset;
- BUG_ON(!dst);
-
- dst_offset = 0;
- page_end = 1;
- }
-
- memcpy(dst, src, length);
-
- pr_debug("page: %u, remaining size: %u, length: %u,"
- " i: %u, j: %u\n", req->rd_page,
- (req->rd_size - length), length, i, j);
-
- req->rd_size -= length;
- if (!req->rd_size)
- return 0;
-
- if (!page_end)
- continue;
-
- if (++req->rd_page <= table->page_end_offset) {
- pr_debug("page: %u in same page table\n",
- req->rd_page);
+ /* rd page completed, next one please */
+ req->rd_page++;
+ rd_offset = 0;
+ src_len = PAGE_SIZE;
+ if (req->rd_page <= table->page_end_offset) {
+ rd_sg++;
continue;
}
- pr_debug("getting new page table for page: %u\n",
- req->rd_page);
-
table = rd_get_sg_table(dev, req->rd_page);
- if (!table)
+ if (!table) {
+ sg_miter_stop(&m);
return -EINVAL;
+ }
- sg_d = &table->sg_table[j = 0];
+ /* since we increment, the first sg entry is correct */
+ rd_sg = table->sg_table;
}
-
+ sg_miter_stop(&m);
return 0;
}
{
struct se_device *dev = task->task_se_cmd->se_dev;
struct rd_request *req = RD_REQ(task);
- unsigned long long lba;
+ u64 tmp;
int ret;
- req->rd_page = (task->task_lba * dev->se_sub_dev->se_dev_attrib.block_size) / PAGE_SIZE;
- lba = task->task_lba;
- req->rd_offset = (do_div(lba,
- (PAGE_SIZE / dev->se_sub_dev->se_dev_attrib.block_size))) *
- dev->se_sub_dev->se_dev_attrib.block_size;
+ tmp = task->task_lba * dev->se_sub_dev->se_dev_attrib.block_size;
+ req->rd_offset = do_div(tmp, PAGE_SIZE);
+ req->rd_page = tmp;
req->rd_size = task->task_size;
- if (task->task_data_direction == DMA_FROM_DEVICE)
- ret = rd_MEMCPY_read(req);
- else
- ret = rd_MEMCPY_write(req);
-
+ ret = rd_MEMCPY(req, task->task_data_direction == DMA_FROM_DEVICE);
if (ret != 0)
return ret;
task->task_scsi_status = GOOD;
transport_complete_task(task, 1);
-
- return PYX_TRANSPORT_SENT_TO_TRANSPORT;
+ return 0;
}
/* rd_free_task(): (Part of se_subsystem_api_t template)
" %d t_fe_count: %d\n", (preempt_and_abort_list) ?
"Preempt" : "", cmd, cmd->t_state,
atomic_read(&cmd->t_fe_count));
- /*
- * Signal that the command has failed via cmd->se_cmd_flags,
- */
- transport_new_cmd_failure(cmd);
core_tmr_handle_tas_abort(tmr_nacl, cmd, tas,
atomic_read(&cmd->t_fe_count));
static int sub_api_initialized;
static struct workqueue_struct *target_completion_wq;
-static struct kmem_cache *se_cmd_cache;
static struct kmem_cache *se_sess_cache;
struct kmem_cache *se_tmr_req_cache;
struct kmem_cache *se_ua_cache;
static void transport_put_cmd(struct se_cmd *cmd);
static void transport_remove_cmd_from_queue(struct se_cmd *cmd);
static int transport_set_sense_codes(struct se_cmd *cmd, u8 asc, u8 ascq);
-static void transport_generic_request_failure(struct se_cmd *, int, int);
+static void transport_generic_request_failure(struct se_cmd *);
static void target_complete_ok_work(struct work_struct *work);
int init_se_kmem_caches(void)
{
- se_cmd_cache = kmem_cache_create("se_cmd_cache",
- sizeof(struct se_cmd), __alignof__(struct se_cmd), 0, NULL);
- if (!se_cmd_cache) {
- pr_err("kmem_cache_create for struct se_cmd failed\n");
- goto out;
- }
se_tmr_req_cache = kmem_cache_create("se_tmr_cache",
sizeof(struct se_tmr_req), __alignof__(struct se_tmr_req),
0, NULL);
if (!se_tmr_req_cache) {
pr_err("kmem_cache_create() for struct se_tmr_req"
" failed\n");
- goto out_free_cmd_cache;
+ goto out;
}
se_sess_cache = kmem_cache_create("se_sess_cache",
sizeof(struct se_session), __alignof__(struct se_session),
kmem_cache_destroy(se_sess_cache);
out_free_tmr_req_cache:
kmem_cache_destroy(se_tmr_req_cache);
-out_free_cmd_cache:
- kmem_cache_destroy(se_cmd_cache);
out:
return -ENOMEM;
}
void release_se_kmem_caches(void)
{
destroy_workqueue(target_completion_wq);
- kmem_cache_destroy(se_cmd_cache);
kmem_cache_destroy(se_tmr_req_cache);
kmem_cache_destroy(se_sess_cache);
kmem_cache_destroy(se_ua_cache);
task->task_scsi_status = GOOD;
} else {
task->task_scsi_status = SAM_STAT_CHECK_CONDITION;
- task->task_error_status = PYX_TRANSPORT_ILLEGAL_REQUEST;
- task->task_se_cmd->transport_error_status =
- PYX_TRANSPORT_ILLEGAL_REQUEST;
+ task->task_se_cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
}
transport_complete_task(task, good);
{
struct se_cmd *cmd = container_of(work, struct se_cmd, work);
- transport_generic_request_failure(cmd, 1, 1);
+ transport_generic_request_failure(cmd);
}
/* transport_complete_task():
if (cmd->t_tasks_failed) {
if (!task->task_error_status) {
task->task_error_status =
- PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
- cmd->transport_error_status =
- PYX_TRANSPORT_UNKNOWN_SAM_OPCODE;
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
+
INIT_WORK(&cmd->work, target_complete_failure_work);
} else {
atomic_set(&cmd->t_transport_complete, 1);
dev->se_hba = hba;
dev->se_sub_dev = se_dev;
dev->transport = transport;
- atomic_set(&dev->active_cmds, 0);
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_sep_list);
INIT_LIST_HEAD(&dev->dev_tmr_list);
INIT_LIST_HEAD(&dev->execute_task_list);
INIT_LIST_HEAD(&dev->delayed_cmd_list);
- INIT_LIST_HEAD(&dev->ordered_cmd_list);
INIT_LIST_HEAD(&dev->state_task_list);
INIT_LIST_HEAD(&dev->qf_cmd_list);
spin_lock_init(&dev->execute_task_lock);
spin_lock_init(&dev->delayed_cmd_lock);
- spin_lock_init(&dev->ordered_cmd_lock);
- spin_lock_init(&dev->state_task_lock);
- spin_lock_init(&dev->dev_alua_lock);
spin_lock_init(&dev->dev_reservation_lock);
spin_lock_init(&dev->dev_status_lock);
- spin_lock_init(&dev->dev_status_thr_lock);
spin_lock_init(&dev->se_port_lock);
spin_lock_init(&dev->se_tmr_lock);
spin_lock_init(&dev->qf_cmd_lock);
{
INIT_LIST_HEAD(&cmd->se_lun_node);
INIT_LIST_HEAD(&cmd->se_delayed_node);
- INIT_LIST_HEAD(&cmd->se_ordered_node);
INIT_LIST_HEAD(&cmd->se_qf_node);
INIT_LIST_HEAD(&cmd->se_queue_node);
INIT_LIST_HEAD(&cmd->se_cmd_list);
pr_err("Received SCSI CDB with command_size: %d that"
" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
scsi_command_size(cdb), SCSI_MAX_VARLEN_CDB_SIZE);
+ cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
return -EINVAL;
}
/*
" %u > sizeof(cmd->__t_task_cdb): %lu ops\n",
scsi_command_size(cdb),
(unsigned long)sizeof(cmd->__t_task_cdb));
+ cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+ cmd->scsi_sense_reason =
+ TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
return -ENOMEM;
}
} else
* and call transport_generic_request_failure() if necessary..
*/
ret = transport_generic_new_cmd(cmd);
- if (ret < 0) {
- cmd->transport_error_status = ret;
- transport_generic_request_failure(cmd, 0,
- (cmd->data_direction != DMA_TO_DEVICE));
- }
+ if (ret < 0)
+ transport_generic_request_failure(cmd);
+
return 0;
}
EXPORT_SYMBOL(transport_handle_cdb_direct);
/*
* Handle SAM-esque emulation for generic transport request failures.
*/
-static void transport_generic_request_failure(
- struct se_cmd *cmd,
- int complete,
- int sc)
+static void transport_generic_request_failure(struct se_cmd *cmd)
{
int ret = 0;
pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08x"
" CDB: 0x%02x\n", cmd, cmd->se_tfo->get_task_tag(cmd),
cmd->t_task_cdb[0]);
- pr_debug("-----[ i_state: %d t_state: %d transport_error_status: %d\n",
+ pr_debug("-----[ i_state: %d t_state: %d scsi_sense_reason: %d\n",
cmd->se_tfo->get_cmd_state(cmd),
- cmd->t_state,
- cmd->transport_error_status);
+ cmd->t_state, cmd->scsi_sense_reason);
pr_debug("-----[ t_tasks: %d t_task_cdbs_left: %d"
" t_task_cdbs_sent: %d t_task_cdbs_ex_left: %d --"
" t_transport_active: %d t_transport_stop: %d"
if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
transport_complete_task_attr(cmd);
- if (complete) {
- cmd->transport_error_status = PYX_TRANSPORT_LU_COMM_FAILURE;
- }
-
- switch (cmd->transport_error_status) {
- case PYX_TRANSPORT_UNKNOWN_SAM_OPCODE:
- cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
- break;
- case PYX_TRANSPORT_REQ_TOO_MANY_SECTORS:
- cmd->scsi_sense_reason = TCM_SECTOR_COUNT_TOO_MANY;
- break;
- case PYX_TRANSPORT_INVALID_CDB_FIELD:
- cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
- break;
- case PYX_TRANSPORT_INVALID_PARAMETER_LIST:
- cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
- break;
- case PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES:
- if (!sc)
- transport_new_cmd_failure(cmd);
- /*
- * Currently for PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES,
- * we force this session to fall back to session
- * recovery.
- */
- cmd->se_tfo->fall_back_to_erl0(cmd->se_sess);
- cmd->se_tfo->stop_session(cmd->se_sess, 0, 0);
-
- goto check_stop;
- case PYX_TRANSPORT_LU_COMM_FAILURE:
- case PYX_TRANSPORT_ILLEGAL_REQUEST:
- cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- break;
- case PYX_TRANSPORT_UNKNOWN_MODE_PAGE:
- cmd->scsi_sense_reason = TCM_UNKNOWN_MODE_PAGE;
- break;
- case PYX_TRANSPORT_WRITE_PROTECTED:
- cmd->scsi_sense_reason = TCM_WRITE_PROTECTED;
+ switch (cmd->scsi_sense_reason) {
+ case TCM_NON_EXISTENT_LUN:
+ case TCM_UNSUPPORTED_SCSI_OPCODE:
+ case TCM_INVALID_CDB_FIELD:
+ case TCM_INVALID_PARAMETER_LIST:
+ case TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE:
+ case TCM_UNKNOWN_MODE_PAGE:
+ case TCM_WRITE_PROTECTED:
+ case TCM_CHECK_CONDITION_ABORT_CMD:
+ case TCM_CHECK_CONDITION_UNIT_ATTENTION:
+ case TCM_CHECK_CONDITION_NOT_READY:
break;
- case PYX_TRANSPORT_RESERVATION_CONFLICT:
+ case TCM_RESERVATION_CONFLICT:
/*
* No SENSE Data payload for this case, set SCSI Status
* and queue the response to $FABRIC_MOD.
if (ret == -EAGAIN || ret == -ENOMEM)
goto queue_full;
goto check_stop;
- case PYX_TRANSPORT_USE_SENSE_REASON:
- /*
- * struct se_cmd->scsi_sense_reason already set
- */
- break;
default:
pr_err("Unknown transport error for CDB 0x%02x: %d\n",
- cmd->t_task_cdb[0],
- cmd->transport_error_status);
+ cmd->t_task_cdb[0], cmd->scsi_sense_reason);
cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
break;
}
* transport_send_check_condition_and_sense() after handling
* possible unsoliticied write data payloads.
*/
- if (!sc && !cmd->se_tfo->new_cmd_map)
- transport_new_cmd_failure(cmd);
- else {
- ret = transport_send_check_condition_and_sense(cmd,
- cmd->scsi_sense_reason, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
- goto queue_full;
- }
+ ret = transport_send_check_condition_and_sense(cmd,
+ cmd->scsi_sense_reason, 0);
+ if (ret == -EAGAIN || ret == -ENOMEM)
+ goto queue_full;
check_stop:
transport_lun_remove_cmd(cmd);
* to allow the passed struct se_cmd list of tasks to the front of the list.
*/
if (cmd->sam_task_attr == MSG_HEAD_TAG) {
- atomic_inc(&cmd->se_dev->dev_hoq_count);
- smp_mb__after_atomic_inc();
pr_debug("Added HEAD_OF_QUEUE for CDB:"
" 0x%02x, se_ordered_id: %u\n",
cmd->t_task_cdb[0],
cmd->se_ordered_id);
return 1;
} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
- spin_lock(&cmd->se_dev->ordered_cmd_lock);
- list_add_tail(&cmd->se_ordered_node,
- &cmd->se_dev->ordered_cmd_list);
- spin_unlock(&cmd->se_dev->ordered_cmd_lock);
-
atomic_inc(&cmd->se_dev->dev_ordered_sync);
smp_mb__after_atomic_inc();
{
int add_tasks;
- if (se_dev_check_online(cmd->se_orig_obj_ptr) != 0) {
- cmd->transport_error_status = PYX_TRANSPORT_LU_COMM_FAILURE;
- transport_generic_request_failure(cmd, 0, 1);
+ if (se_dev_check_online(cmd->se_dev) != 0) {
+ cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ transport_generic_request_failure(cmd);
return 0;
}
else
error = dev->transport->do_task(task);
if (error != 0) {
- cmd->transport_error_status = error;
spin_lock_irqsave(&cmd->t_state_lock, flags);
task->task_flags &= ~TF_ACTIVE;
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
atomic_set(&cmd->t_transport_sent, 0);
transport_stop_tasks_for_cmd(cmd);
atomic_inc(&dev->depth_left);
- transport_generic_request_failure(cmd, 0, 1);
+ transport_generic_request_failure(cmd);
}
goto check_depth;
return 0;
}
-void transport_new_cmd_failure(struct se_cmd *se_cmd)
-{
- unsigned long flags;
- /*
- * Any unsolicited data will get dumped for failed command inside of
- * the fabric plugin
- */
- spin_lock_irqsave(&se_cmd->t_state_lock, flags);
- se_cmd->se_cmd_flags |= SCF_SE_CMD_FAILED;
- se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
- spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
-}
-
static inline u32 transport_get_sectors_6(
unsigned char *cdb,
struct se_cmd *cmd,
/*
* Everything else assume TYPE_DISK Sector CDB location.
- * Use 8-bit sector value.
+ * Use 8-bit sector value. SBC-3 says:
+ *
+ * A TRANSFER LENGTH field set to zero specifies that 256
+ * logical blocks shall be written. Any other value
+ * specifies the number of logical blocks that shall be
+ * written.
*/
type_disk:
- return (u32)cdb[4];
+ return cdb[4] ? : 256;
}
static inline u32 transport_get_sectors_10(
return -1;
}
-static int
-transport_handle_reservation_conflict(struct se_cmd *cmd)
-{
- cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
- cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
- cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
- /*
- * For UA Interlock Code 11b, a RESERVATION CONFLICT will
- * establish a UNIT ATTENTION with PREVIOUS RESERVATION
- * CONFLICT STATUS.
- *
- * See spc4r17, section 7.4.6 Control Mode Page, Table 349
- */
- if (cmd->se_sess &&
- cmd->se_dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl == 2)
- core_scsi3_ua_allocate(cmd->se_sess->se_node_acl,
- cmd->orig_fe_lun, 0x2C,
- ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS);
- return -EINVAL;
-}
-
static inline long long transport_dev_end_lba(struct se_device *dev)
{
return dev->transport->get_blocks(dev) + 1;
*/
if (su_dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type) != 0) {
if (su_dev->t10_pr.pr_ops.t10_seq_non_holder(
- cmd, cdb, pr_reg_type) != 0)
- return transport_handle_reservation_conflict(cmd);
+ cmd, cdb, pr_reg_type) != 0) {
+ cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+ cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
+ cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+ return -EBUSY;
+ }
/*
* This means the CDB is allowed for the SCSI Initiator port
* when said port is *NOT* holding the legacy SPC-2 or
goto out_unsupported_cdb;
size = transport_get_size(sectors, cdb, cmd);
cmd->t_task_lba = transport_lba_32(cdb);
- cmd->t_tasks_fua = (cdb[1] & 0x8);
+ if (cdb[1] & 0x8)
+ cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB;
break;
case WRITE_12:
goto out_unsupported_cdb;
size = transport_get_size(sectors, cdb, cmd);
cmd->t_task_lba = transport_lba_32(cdb);
- cmd->t_tasks_fua = (cdb[1] & 0x8);
+ if (cdb[1] & 0x8)
+ cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB;
break;
case WRITE_16:
goto out_unsupported_cdb;
size = transport_get_size(sectors, cdb, cmd);
cmd->t_task_lba = transport_lba_64(cdb);
- cmd->t_tasks_fua = (cdb[1] & 0x8);
+ if (cdb[1] & 0x8)
+ cmd->se_cmd_flags |= SCF_FUA;
cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB;
break;
case XDWRITEREAD_10:
if ((cmd->data_direction != DMA_TO_DEVICE) ||
- !(cmd->t_tasks_bidi))
+ !(cmd->se_cmd_flags & SCF_BIDI))
goto out_invalid_cdb_field;
sectors = transport_get_sectors_10(cdb, cmd, §or_ret);
if (sector_ret)
* Setup BIDI XOR callback to be run after I/O completion.
*/
cmd->transport_complete_callback = &transport_xor_callback;
- cmd->t_tasks_fua = (cdb[1] & 0x8);
+ if (cdb[1] & 0x8)
+ cmd->se_cmd_flags |= SCF_FUA;
break;
case VARIABLE_LENGTH_CMD:
service_action = get_unaligned_be16(&cdb[8]);
* completion.
*/
cmd->transport_complete_callback = &transport_xor_callback;
- cmd->t_tasks_fua = (cdb[10] & 0x8);
+ if (cdb[1] & 0x8)
+ cmd->se_cmd_flags |= SCF_FUA;
break;
case WRITE_SAME_32:
sectors = transport_get_sectors_32(cdb, cmd, §or_ret);
" SIMPLE: %u\n", dev->dev_cur_ordered_id,
cmd->se_ordered_id);
} else if (cmd->sam_task_attr == MSG_HEAD_TAG) {
- atomic_dec(&dev->dev_hoq_count);
- smp_mb__after_atomic_dec();
dev->dev_cur_ordered_id++;
pr_debug("Incremented dev_cur_ordered_id: %u for"
" HEAD_OF_QUEUE: %u\n", dev->dev_cur_ordered_id,
cmd->se_ordered_id);
} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
- spin_lock(&dev->ordered_cmd_lock);
- list_del(&cmd->se_ordered_node);
atomic_dec(&dev->dev_ordered_sync);
smp_mb__after_atomic_dec();
- spin_unlock(&dev->ordered_cmd_lock);
dev->dev_cur_ordered_id++;
pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED:"
if ((cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB) ||
(cmd->se_cmd_flags & SCF_SCSI_CONTROL_SG_IO_CDB)) {
+ /*
+ * Reject SCSI data overflow with map_mem_to_cmd() as incoming
+ * scatterlists already have been set to follow what the fabric
+ * passes for the original expected data transfer length.
+ */
+ if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
+ pr_warn("Rejecting SCSI DATA overflow for fabric using"
+ " SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC\n");
+ cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+ cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+ return -EINVAL;
+ }
cmd->t_data_sg = sgl;
cmd->t_data_nents = sgl_count;
cmd->data_length) {
ret = transport_generic_get_mem(cmd);
if (ret < 0)
- return ret;
+ goto out_fail;
}
/*
task_cdbs = transport_allocate_control_task(cmd);
}
- if (task_cdbs <= 0)
+ if (task_cdbs < 0)
goto out_fail;
+ else if (!task_cdbs && (cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB)) {
+ cmd->t_state = TRANSPORT_COMPLETE;
+ atomic_set(&cmd->t_transport_active, 1);
+ INIT_WORK(&cmd->work, target_complete_ok_work);
+ queue_work(target_completion_wq, &cmd->work);
+ return 0;
+ }
if (set_counts) {
atomic_inc(&cmd->t_fe_count);
else if (ret < 0)
return ret;
- return PYX_TRANSPORT_WRITE_PENDING;
+ return 1;
queue_full:
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
if (cmd->se_tfo->write_pending_status(cmd) != 0) {
atomic_inc(&cmd->t_transport_aborted);
smp_mb__after_atomic_inc();
- cmd->scsi_status = SAM_STAT_TASK_ABORTED;
- transport_new_cmd_failure(cmd);
- return;
}
}
cmd->scsi_status = SAM_STAT_TASK_ABORTED;
struct se_cmd *cmd;
struct se_device *dev = (struct se_device *) param;
- set_user_nice(current, -20);
-
while (!kthread_should_stop()) {
ret = wait_event_interruptible(dev->dev_queue_obj.thread_wq,
atomic_read(&dev->dev_queue_obj.queue_cnt) ||
}
ret = cmd->se_tfo->new_cmd_map(cmd);
if (ret < 0) {
- cmd->transport_error_status = ret;
- transport_generic_request_failure(cmd,
- 0, (cmd->data_direction !=
- DMA_TO_DEVICE));
+ transport_generic_request_failure(cmd);
break;
}
ret = transport_generic_new_cmd(cmd);
if (ret < 0) {
- cmd->transport_error_status = ret;
- transport_generic_request_failure(cmd,
- 0, (cmd->data_direction !=
- DMA_TO_DEVICE));
+ transport_generic_request_failure(cmd);
+ break;
}
break;
case TRANSPORT_PROCESS_WRITE:
lport = ep->lp;
fp = fc_frame_alloc(lport, sizeof(*txrdy));
if (!fp)
- return PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES;
+ return -ENOMEM; /* Signal QUEUE_FULL */
txrdy = fc_frame_payload_get(fp, sizeof(*txrdy));
memset(txrdy, 0, sizeof(*txrdy));
struct ft_lport_acl *lacl = container_of(wwn,
struct ft_lport_acl, fc_lport_wwn);
- pr_debug("del lport %s\n",
- config_item_name(&wwn->wwn_group.cg_item));
+ pr_debug("del lport %s\n", lacl->name);
mutex_lock(&ft_lport_lock);
list_del(&lacl->list);
mutex_unlock(&ft_lport_lock);
asm volatile("mrc p14, 0, %0, c0, c5, 0 @ read comms data reg"
: "=r" (__c));
+ isb();
return __c;
}
asm volatile("mcr p14, 0, %0, c0, c5, 0 @ write a char"
: /* no output register */
: "r" (c));
+ isb();
}
static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
Support for the IFX6x60 modem devices on Intel MID platforms.
config SERIAL_PCH_UART
- tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) UART"
+ tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) UART"
depends on PCI
select SERIAL_CORE
help
which is an IOH(Input/Output Hub) for x86 embedded processor.
Enabling PCH_DMA, this PCH UART works as DMA mode.
- This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
- Output Hub), ML7213 and ML7223.
- ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
- for MP(Media Phone) use.
- ML7213/ML7223 is companion chip for Intel Atom E6xx series.
- ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+ This driver also can be used for LAPIS Semiconductor IOH(Input/
+ Output Hub), ML7213, ML7223 and ML7831.
+ ML7213 IOH is for IVI(In-Vehicle Infotainment) use, ML7223 IOH is
+ for MP(Media Phone) use and ML7831 IOH is for general purpose use.
+ ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+ ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
config SERIAL_MSM_SMD
bool "Enable tty device interface for some SMD ports"
if (rs485conf->flags & SER_RS485_ENABLED) {
dev_dbg(port->dev, "Setting UART to RS485\n");
atmel_port->tx_done_mask = ATMEL_US_TXEMPTY;
- if (rs485conf->flags & SER_RS485_RTS_AFTER_SEND)
+ if ((rs485conf->delay_rts_after_send) > 0)
UART_PUT_TTGR(port, rs485conf->delay_rts_after_send);
mode |= ATMEL_US_USMODE_RS485;
} else {
if (atmel_port->rs485.flags & SER_RS485_ENABLED) {
dev_dbg(port->dev, "Setting UART to RS485\n");
- if (atmel_port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
+ if ((atmel_port->rs485.delay_rts_after_send) > 0)
UART_PUT_TTGR(port,
atmel_port->rs485.delay_rts_after_send);
mode |= ATMEL_US_USMODE_RS485;
if (atmel_port->rs485.flags & SER_RS485_ENABLED) {
dev_dbg(port->dev, "Setting UART to RS485\n");
- if (atmel_port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
+ if ((atmel_port->rs485.delay_rts_after_send) > 0)
UART_PUT_TTGR(port,
atmel_port->rs485.delay_rts_after_send);
mode |= ATMEL_US_USMODE_RS485;
rs485conf->delay_rts_after_send = rs485_delay[1];
rs485conf->flags = 0;
- if (rs485conf->delay_rts_before_send == 0 &&
- rs485conf->delay_rts_after_send == 0) {
- rs485conf->flags |= SER_RS485_RTS_ON_SEND;
- } else {
- if (rs485conf->delay_rts_before_send)
- rs485conf->flags |= SER_RS485_RTS_BEFORE_SEND;
- if (rs485conf->delay_rts_after_send)
- rs485conf->flags |= SER_RS485_RTS_AFTER_SEND;
- }
-
if (of_get_property(np, "rs485-rx-during-tx", NULL))
rs485conf->flags |= SER_RS485_RX_DURING_TX;
e100_disable_rx(info);
e100_enable_rx_irq(info);
#endif
- if ((info->rs485.flags & SER_RS485_RTS_BEFORE_SEND) &&
- (info->rs485.delay_rts_before_send > 0))
- msleep(info->rs485.delay_rts_before_send);
+ if (info->rs485.delay_rts_before_send > 0)
+ msleep(info->rs485.delay_rts_before_send);
}
#endif /* CONFIG_ETRAX_RS485 */
rs485data.delay_rts_before_send = rs485ctrl.delay_rts_before_send;
rs485data.flags = 0;
- if (rs485data.delay_rts_before_send != 0)
- rs485data.flags |= SER_RS485_RTS_BEFORE_SEND;
- else
- rs485data.flags &= ~(SER_RS485_RTS_BEFORE_SEND);
if (rs485ctrl.enabled)
rs485data.flags |= SER_RS485_ENABLED;
/* Set sane defaults */
info->rs485.flags &= ~(SER_RS485_RTS_ON_SEND);
info->rs485.flags |= SER_RS485_RTS_AFTER_SEND;
- info->rs485.flags &= ~(SER_RS485_RTS_BEFORE_SEND);
info->rs485.delay_rts_before_send = 0;
info->rs485.flags &= ~(SER_RS485_ENABLED);
#endif
{
struct uart_hsu_port *up =
container_of(port, struct uart_hsu_port, port);
- struct tty_struct *tty = port->state->port.tty;
unsigned char cval, fcr = 0;
unsigned long flags;
unsigned int baud, quot;
}
/* CMSPAR isn't supported by this driver */
- if (tty)
- tty->termios->c_cflag &= ~CMSPAR;
+ termios->c_cflag &= ~CMSPAR;
if (termios->c_cflag & CSTOPB)
cval |= UART_LCR_STOP;
/*
- *Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ *Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
*
*This program is free software; you can redistribute it and/or modify
*it under the terms of the GNU General Public License as published by
/* Set the max number of UART port
* Intel EG20T PCH: 4 port
- * OKI SEMICONDUCTOR ML7213 IOH: 3 port
- * OKI SEMICONDUCTOR ML7223 IOH: 2 port
+ * LAPIS Semiconductor ML7213 IOH: 3 port
+ * LAPIS Semiconductor ML7223 IOH: 2 port
*/
#define PCH_UART_NR 4
pch_ml7213_uart2,
pch_ml7223_uart0,
pch_ml7223_uart1,
+ pch_ml7831_uart0,
+ pch_ml7831_uart1,
};
static struct pch_uart_driver_data drv_dat[] = {
[pch_ml7213_uart2] = {PCH_UART_2LINE, 2},
[pch_ml7223_uart0] = {PCH_UART_8LINE, 0},
[pch_ml7223_uart1] = {PCH_UART_2LINE, 1},
+ [pch_ml7831_uart0] = {PCH_UART_8LINE, 0},
+ [pch_ml7831_uart1] = {PCH_UART_2LINE, 1},
};
static unsigned int default_baud = 9600;
dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Rx)\n",
__func__);
dma_release_channel(priv->chan_tx);
+ priv->chan_tx = NULL;
return;
}
dev_err(priv->port.dev,
"pch_uart_hal_set_fifo Failed(ret=%d)\n", ret);
- if (priv->use_dma_flag)
- pch_free_dma(port);
+ pch_free_dma(port);
free_irq(priv->port.irq, priv);
}
if (rtn)
goto out;
+ pch_uart_set_mctrl(&priv->port, priv->port.mctrl);
/* Don't rewrite B0 */
if (tty_termios_baud_rate(termios))
tty_termios_encode_baud_rate(termios, baud, baud);
.driver_data = pch_ml7223_uart0},
{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x800D),
.driver_data = pch_ml7223_uart1},
+ {PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8811),
+ .driver_data = pch_ml7831_uart0},
+ {PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8812),
+ .driver_data = pch_ml7831_uart1},
{0,},
};
#include <linux/kmod.h>
#include <linux/nsproxy.h>
+#include <linux/ratelimit.h>
/*
* This guards the refcounted line discipline lists. The lock
/**
* tty_ldisc_wait_idle - wait for the ldisc to become idle
* @tty: tty to wait for
+ * @timeout: for how long to wait at most
*
* Wait for the line discipline to become idle. The discipline must
* have been halted for this to guarantee it remains idle.
*/
-static int tty_ldisc_wait_idle(struct tty_struct *tty)
+static int tty_ldisc_wait_idle(struct tty_struct *tty, long timeout)
{
- int ret;
+ long ret;
ret = wait_event_timeout(tty_ldisc_idle,
- atomic_read(&tty->ldisc->users) == 1, 5 * HZ);
+ atomic_read(&tty->ldisc->users) == 1, timeout);
if (ret < 0)
return ret;
return ret > 0 ? 0 : -EBUSY;
tty_ldisc_flush_works(tty);
- retval = tty_ldisc_wait_idle(tty);
+ retval = tty_ldisc_wait_idle(tty, 5 * HZ);
tty_lock();
mutex_lock(&tty->ldisc_mutex);
if (IS_ERR(ld))
return -1;
- WARN_ON_ONCE(tty_ldisc_wait_idle(tty));
-
tty_ldisc_close(tty, tty->ldisc);
tty_ldisc_put(tty->ldisc);
tty->ldisc = NULL;
tty_unlock();
cancel_work_sync(&tty->buf.work);
mutex_unlock(&tty->ldisc_mutex);
-
+retry:
tty_lock();
mutex_lock(&tty->ldisc_mutex);
it means auditing a lot of other paths so this is
a FIXME */
if (tty->ldisc) { /* Not yet closed */
+ if (atomic_read(&tty->ldisc->users) != 1) {
+ char cur_n[TASK_COMM_LEN], tty_n[64];
+ long timeout = 3 * HZ;
+ tty_unlock();
+
+ while (tty_ldisc_wait_idle(tty, timeout) == -EBUSY) {
+ timeout = MAX_SCHEDULE_TIMEOUT;
+ printk_ratelimited(KERN_WARNING
+ "%s: waiting (%s) for %s took too long, but we keep waiting...\n",
+ __func__, get_task_comm(cur_n, current),
+ tty_name(tty, tty_n));
+ }
+ mutex_unlock(&tty->ldisc_mutex);
+ goto retry;
+ }
+
if (reset == 0) {
if (!tty_ldisc_reinit(tty, tty->termios->c_line))
{
int i;
- mutex_lock(&open_mutex);
if (acm->dev) {
usb_autopm_get_interface(acm->control);
acm_set_control(acm, acm->ctrlout = 0);
acm->control->needs_remote_wakeup = 0;
usb_autopm_put_interface(acm->control);
}
- mutex_unlock(&open_mutex);
}
static void acm_tty_hangup(struct tty_struct *tty)
{
struct acm *acm = tty->driver_data;
tty_port_hangup(&acm->port);
+ mutex_lock(&open_mutex);
acm_port_down(acm);
+ mutex_unlock(&open_mutex);
}
static void acm_tty_close(struct tty_struct *tty, struct file *filp)
shutdown */
if (!acm)
return;
+
+ mutex_lock(&open_mutex);
if (tty_port_close_start(&acm->port, tty, filp) == 0) {
- mutex_lock(&open_mutex);
if (!acm->dev) {
tty_port_tty_set(&acm->port, NULL);
acm_tty_unregister(acm);
acm_port_down(acm);
tty_port_close_end(&acm->port, tty);
tty_port_tty_set(&acm->port, NULL);
+ mutex_unlock(&open_mutex);
}
static int acm_tty_write(struct tty_struct *tty,
},
{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
},
+ /* Motorola H24 HSPA module: */
+ { USB_DEVICE(0x22b8, 0x2d91) }, /* modem */
+ { USB_DEVICE(0x22b8, 0x2d92) }, /* modem + diagnostics */
+ { USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port */
+ { USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics */
+ { USB_DEVICE(0x22b8, 0x2d96) }, /* modem + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d97) }, /* modem + diagnostics + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+
{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
data interface instead of
USB_PORT_FEAT_C_PORT_LINK_STATE);
}
+ if ((portchange & USB_PORT_STAT_C_BH_RESET) &&
+ hub_is_superspeed(hub->hdev)) {
+ need_debounce_delay = true;
+ clear_port_feature(hub->hdev, port1,
+ USB_PORT_FEAT_C_BH_PORT_RESET);
+ }
/* We can forget about a "removed" device when there's a
* physical disconnect or the connect status changes.
*/
/* Logitech Webcam B/C500 */
{ USB_DEVICE(0x046d, 0x0807), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech Webcam C600 */
+ { USB_DEVICE(0x046d, 0x0808), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Logitech Webcam Pro 9000 */
{ USB_DEVICE(0x046d, 0x0809), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech Webcam C905 */
+ { USB_DEVICE(0x046d, 0x080a), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* Logitech Webcam C210 */
+ { USB_DEVICE(0x046d, 0x0819), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* Logitech Webcam C260 */
+ { USB_DEVICE(0x046d, 0x081a), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Logitech Webcam C310 */
{ USB_DEVICE(0x046d, 0x081b), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech Webcam C910 */
+ { USB_DEVICE(0x046d, 0x0821), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* Logitech Webcam C160 */
+ { USB_DEVICE(0x046d, 0x0824), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Logitech Webcam C270 */
{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech Quickcam Pro 9000 */
+ { USB_DEVICE(0x046d, 0x0990), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* Logitech Quickcam E3500 */
+ { USB_DEVICE(0x046d, 0x09a4), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* Logitech Quickcam Vision Pro */
+ { USB_DEVICE(0x046d, 0x09a6), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Logitech Harmony 700-series */
{ USB_DEVICE(0x046d, 0xc122), .driver_info = USB_QUIRK_DELAY_INIT },
ret = -ENODEV;
goto err0;
}
- dwc->revision = reg & DWC3_GSNPSREV_MASK;
+ dwc->revision = reg;
dwc3_core_soft_reset(dwc);
int ret;
dep->endpoint.maxpacket = 1024;
+ dep->endpoint.max_streams = 15;
dep->endpoint.ops = &dwc3_gadget_ep_ops;
list_add_tail(&dep->endpoint.ep_list,
&dwc->gadget.ep_list);
gadget drivers to also be dynamically linked.
config USB_EG20T
- tristate "Intel EG20T PCH/OKI SEMICONDUCTOR ML7213 IOH UDC"
+ tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
depends on PCI
select USB_GADGET_DUALSPEED
help
This driver dose not support interrupt transfer or isochronous
transfer modes.
- This driver also can be used for OKI SEMICONDUCTOR's ML7213 which is
+ This driver also can be used for LAPIS Semiconductor's ML7213 which is
for IVI(In-Vehicle Infotainment) use.
- ML7213 is companion chip for Intel Atom E6xx series.
- ML7213 is completely compatible for Intel EG20T PCH.
+ ML7831 is for general purpose use.
+ ML7213/ML7831 is companion chip for Intel Atom E6xx series.
+ ML7213/ML7831 is completely compatible for Intel EG20T PCH.
config USB_CI13XXX_MSM
tristate "MIPS USB CI13xxx for MSM"
u32 tmp;
if (!driver || !bind || !driver->setup
- || driver->speed != USB_SPEED_HIGH)
+ || driver->speed < USB_SPEED_HIGH)
return -EINVAL;
if (!dev)
return -ENODEV;
return platform_driver_register(&ci13xxx_msm_driver);
}
module_init(ci13xxx_msm_init);
+
+MODULE_LICENSE("GPL v2");
/******************************************************************************
* DEFINE
*****************************************************************************/
+
+#define DMA_ADDR_INVALID (~(dma_addr_t)0)
+
/* ctrl register bank access */
static DEFINE_SPINLOCK(udc_lock);
return -EALREADY;
mReq->req.status = -EALREADY;
- if (length && !mReq->req.dma) {
+ if (length && mReq->req.dma == DMA_ADDR_INVALID) {
mReq->req.dma = \
dma_map_single(mEp->device, mReq->req.buf,
length, mEp->dir ? DMA_TO_DEVICE :
dma_unmap_single(mEp->device, mReq->req.dma,
length, mEp->dir ? DMA_TO_DEVICE :
DMA_FROM_DEVICE);
- mReq->req.dma = 0;
+ mReq->req.dma = DMA_ADDR_INVALID;
mReq->map = 0;
}
return -ENOMEM;
if (mReq->map) {
dma_unmap_single(mEp->device, mReq->req.dma, mReq->req.length,
mEp->dir ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
- mReq->req.dma = 0;
+ mReq->req.dma = DMA_ADDR_INVALID;
mReq->map = 0;
}
* @gadget: gadget
*
* This function returns an error code
- * Caller must hold lock
*/
static int _gadget_stop_activity(struct usb_gadget *gadget)
{
mReq = kzalloc(sizeof(struct ci13xxx_req), gfp_flags);
if (mReq != NULL) {
INIT_LIST_HEAD(&mReq->queue);
+ mReq->req.dma = DMA_ADDR_INVALID;
mReq->ptr = dma_pool_alloc(mEp->td_pool, gfp_flags,
&mReq->dma);
if (mReq->map) {
dma_unmap_single(mEp->device, mReq->req.dma, mReq->req.length,
mEp->dir ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
- mReq->req.dma = 0;
+ mReq->req.dma = DMA_ADDR_INVALID;
mReq->map = 0;
}
req->status = -ECONNRESET;
spin_lock_irqsave(udc->lock, flags);
if (!udc->remote_wakeup) {
ret = -EOPNOTSUPP;
- dbg_trace("remote wakeup feature is not enabled\n");
+ trace("remote wakeup feature is not enabled\n");
goto out;
}
if (!hw_cread(CAP_PORTSC, PORTSC_SUSP)) {
ret = -EINVAL;
- dbg_trace("port is not suspended\n");
+ trace("port is not suspended\n");
goto out;
}
hw_cwrite(CAP_PORTSC, PORTSC_FPR, PORTSC_FPR);
if (udc->udc_driver->notify_event)
udc->udc_driver->notify_event(udc,
CI13XXX_CONTROLLER_STOPPED_EVENT);
+ spin_unlock_irqrestore(udc->lock, flags);
_gadget_stop_activity(&udc->gadget);
+ spin_lock_irqsave(udc->lock, flags);
pm_runtime_put(&udc->gadget.dev);
}
struct ci13xxx *udc;
int retval = 0;
- trace("%p, %p, %p", dev, regs, name);
+ trace("%p, %p, %p", dev, regs, driver->name);
if (dev == NULL || regs == NULL || driver == NULL ||
driver->name == NULL)
num_req_streams = ep_comp->bmAttributes & 0x1f;
if (num_req_streams > ep->max_streams)
return 0;
- /* Update the ep_comp descriptor if needed */
- if (num_req_streams != ep->max_streams)
- ep_comp->bmAttributes = ep->max_streams;
}
}
if (ctrl->bRequestType !=
(USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE))
break;
- if (w_index != fsg->interface_number || w_value != 0)
+ if (w_index != fsg->interface_number || w_value != 0 ||
+ w_length != 0)
return -EDOM;
/*
if (ctrl->bRequestType !=
(USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE))
break;
- if (w_index != fsg->interface_number || w_value != 0)
+ if (w_index != fsg->interface_number || w_value != 0 ||
+ w_length != 1)
return -EDOM;
VDBG(fsg, "get max LUN\n");
*(u8 *)req->buf = fsg->common->nluns - 1;
fsg_common_put(common);
usb_free_descriptors(fsg->function.descriptors);
usb_free_descriptors(fsg->function.hs_descriptors);
+ usb_free_descriptors(fsg->function.ss_descriptors);
kfree(fsg);
}
DECLARE_UAC_AC_HEADER_DESCRIPTOR(1);
DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(1);
-DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(16);
DECLARE_USB_MS_ENDPOINT_DESCRIPTOR(16);
/* B.3.1 Standard AC Interface Descriptor */
/* .wTotalLength = DYNAMIC */
};
-/* B.4.3 Embedded MIDI IN Jack Descriptor */
-static struct usb_midi_in_jack_descriptor jack_in_emb_desc = {
- .bLength = USB_DT_MIDI_IN_SIZE,
- .bDescriptorType = USB_DT_CS_INTERFACE,
- .bDescriptorSubtype = USB_MS_MIDI_IN_JACK,
- .bJackType = USB_MS_EMBEDDED,
- /* .bJackID = DYNAMIC */
-};
-
-/* B.4.4 Embedded MIDI OUT Jack Descriptor */
-static struct usb_midi_out_jack_descriptor_16 jack_out_emb_desc = {
- /* .bLength = DYNAMIC */
- .bDescriptorType = USB_DT_CS_INTERFACE,
- .bDescriptorSubtype = USB_MS_MIDI_OUT_JACK,
- .bJackType = USB_MS_EMBEDDED,
- /* .bJackID = DYNAMIC */
- /* .bNrInputPins = DYNAMIC */
- /* .pins = DYNAMIC */
-};
-
/* B.5.1 Standard Bulk OUT Endpoint Descriptor */
static struct usb_endpoint_descriptor bulk_out_desc = {
.bLength = USB_DT_ENDPOINT_AUDIO_SIZE,
static int __init
f_midi_bind(struct usb_configuration *c, struct usb_function *f)
{
- struct usb_descriptor_header *midi_function[(MAX_PORTS * 2) + 12];
+ struct usb_descriptor_header **midi_function;
struct usb_midi_in_jack_descriptor jack_in_ext_desc[MAX_PORTS];
+ struct usb_midi_in_jack_descriptor jack_in_emb_desc[MAX_PORTS];
struct usb_midi_out_jack_descriptor_1 jack_out_ext_desc[MAX_PORTS];
+ struct usb_midi_out_jack_descriptor_1 jack_out_emb_desc[MAX_PORTS];
struct usb_composite_dev *cdev = c->cdev;
struct f_midi *midi = func_to_midi(f);
int status, n, jack = 1, i = 0;
goto fail;
midi->out_ep->driver_data = cdev; /* claim */
+ /* allocate temporary function list */
+ midi_function = kcalloc((MAX_PORTS * 4) + 9, sizeof(midi_function),
+ GFP_KERNEL);
+ if (!midi_function) {
+ status = -ENOMEM;
+ goto fail;
+ }
+
/*
* construct the function's descriptor set. As the number of
* input and output MIDI ports is configurable, we have to do
/* calculate the header's wTotalLength */
n = USB_DT_MS_HEADER_SIZE
- + (1 + midi->in_ports) * USB_DT_MIDI_IN_SIZE
- + (1 + midi->out_ports) * USB_DT_MIDI_OUT_SIZE(1);
+ + (midi->in_ports + midi->out_ports) *
+ (USB_DT_MIDI_IN_SIZE + USB_DT_MIDI_OUT_SIZE(1));
ms_header_desc.wTotalLength = cpu_to_le16(n);
midi_function[i++] = (struct usb_descriptor_header *) &ms_header_desc;
- /* we have one embedded IN jack */
- jack_in_emb_desc.bJackID = jack++;
- midi_function[i++] = (struct usb_descriptor_header *) &jack_in_emb_desc;
-
- /* and a dynamic amount of external IN jacks */
- for (n = 0; n < midi->in_ports; n++) {
- struct usb_midi_in_jack_descriptor *ext = &jack_in_ext_desc[n];
-
- ext->bLength = USB_DT_MIDI_IN_SIZE;
- ext->bDescriptorType = USB_DT_CS_INTERFACE;
- ext->bDescriptorSubtype = USB_MS_MIDI_IN_JACK;
- ext->bJackType = USB_MS_EXTERNAL;
- ext->bJackID = jack++;
- ext->iJack = 0;
-
- midi_function[i++] = (struct usb_descriptor_header *) ext;
- }
-
- /* one embedded OUT jack ... */
- jack_out_emb_desc.bLength = USB_DT_MIDI_OUT_SIZE(midi->in_ports);
- jack_out_emb_desc.bJackID = jack++;
- jack_out_emb_desc.bNrInputPins = midi->in_ports;
- /* ... which referencess all external IN jacks */
+ /* configure the external IN jacks, each linked to an embedded OUT jack */
for (n = 0; n < midi->in_ports; n++) {
- jack_out_emb_desc.pins[n].baSourceID = jack_in_ext_desc[n].bJackID;
- jack_out_emb_desc.pins[n].baSourcePin = 1;
+ struct usb_midi_in_jack_descriptor *in_ext = &jack_in_ext_desc[n];
+ struct usb_midi_out_jack_descriptor_1 *out_emb = &jack_out_emb_desc[n];
+
+ in_ext->bLength = USB_DT_MIDI_IN_SIZE;
+ in_ext->bDescriptorType = USB_DT_CS_INTERFACE;
+ in_ext->bDescriptorSubtype = USB_MS_MIDI_IN_JACK;
+ in_ext->bJackType = USB_MS_EXTERNAL;
+ in_ext->bJackID = jack++;
+ in_ext->iJack = 0;
+ midi_function[i++] = (struct usb_descriptor_header *) in_ext;
+
+ out_emb->bLength = USB_DT_MIDI_OUT_SIZE(1);
+ out_emb->bDescriptorType = USB_DT_CS_INTERFACE;
+ out_emb->bDescriptorSubtype = USB_MS_MIDI_OUT_JACK;
+ out_emb->bJackType = USB_MS_EMBEDDED;
+ out_emb->bJackID = jack++;
+ out_emb->bNrInputPins = 1;
+ out_emb->pins[0].baSourcePin = 1;
+ out_emb->pins[0].baSourceID = in_ext->bJackID;
+ out_emb->iJack = 0;
+ midi_function[i++] = (struct usb_descriptor_header *) out_emb;
+
+ /* link it to the endpoint */
+ ms_in_desc.baAssocJackID[n] = out_emb->bJackID;
}
- midi_function[i++] = (struct usb_descriptor_header *) &jack_out_emb_desc;
-
- /* and multiple external OUT jacks ... */
+ /* configure the external OUT jacks, each linked to an embedded IN jack */
for (n = 0; n < midi->out_ports; n++) {
- struct usb_midi_out_jack_descriptor_1 *ext = &jack_out_ext_desc[n];
- int m;
-
- ext->bLength = USB_DT_MIDI_OUT_SIZE(1);
- ext->bDescriptorType = USB_DT_CS_INTERFACE;
- ext->bDescriptorSubtype = USB_MS_MIDI_OUT_JACK;
- ext->bJackType = USB_MS_EXTERNAL;
- ext->bJackID = jack++;
- ext->bNrInputPins = 1;
- ext->iJack = 0;
- /* ... which all reference the same embedded IN jack */
- for (m = 0; m < midi->out_ports; m++) {
- ext->pins[m].baSourceID = jack_in_emb_desc.bJackID;
- ext->pins[m].baSourcePin = 1;
- }
-
- midi_function[i++] = (struct usb_descriptor_header *) ext;
+ struct usb_midi_in_jack_descriptor *in_emb = &jack_in_emb_desc[n];
+ struct usb_midi_out_jack_descriptor_1 *out_ext = &jack_out_ext_desc[n];
+
+ in_emb->bLength = USB_DT_MIDI_IN_SIZE;
+ in_emb->bDescriptorType = USB_DT_CS_INTERFACE;
+ in_emb->bDescriptorSubtype = USB_MS_MIDI_IN_JACK;
+ in_emb->bJackType = USB_MS_EMBEDDED;
+ in_emb->bJackID = jack++;
+ in_emb->iJack = 0;
+ midi_function[i++] = (struct usb_descriptor_header *) in_emb;
+
+ out_ext->bLength = USB_DT_MIDI_OUT_SIZE(1);
+ out_ext->bDescriptorType = USB_DT_CS_INTERFACE;
+ out_ext->bDescriptorSubtype = USB_MS_MIDI_OUT_JACK;
+ out_ext->bJackType = USB_MS_EXTERNAL;
+ out_ext->bJackID = jack++;
+ out_ext->bNrInputPins = 1;
+ out_ext->iJack = 0;
+ out_ext->pins[0].baSourceID = in_emb->bJackID;
+ out_ext->pins[0].baSourcePin = 1;
+ midi_function[i++] = (struct usb_descriptor_header *) out_ext;
+
+ /* link it to the endpoint */
+ ms_out_desc.baAssocJackID[n] = in_emb->bJackID;
}
/* configure the endpoint descriptors ... */
ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports);
ms_out_desc.bNumEmbMIDIJack = midi->in_ports;
- for (n = 0; n < midi->in_ports; n++)
- ms_out_desc.baAssocJackID[n] = jack_in_emb_desc.bJackID;
ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports);
ms_in_desc.bNumEmbMIDIJack = midi->out_ports;
- for (n = 0; n < midi->out_ports; n++)
- ms_in_desc.baAssocJackID[n] = jack_out_emb_desc.bJackID;
/* ... and add them to the list */
midi_function[i++] = (struct usb_descriptor_header *) &bulk_out_desc;
f->descriptors = usb_copy_descriptors(midi_function);
}
+ kfree(midi_function);
+
return 0;
fail:
static int
pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
{
- struct net_device *dev = fp->dev;
struct page *page;
int err;
- page = __netdev_alloc_page(dev, gfp_flags);
+ page = alloc_page(gfp_flags);
if (!page)
return -ENOMEM;
err = usb_ep_queue(fp->out_ep, req, gfp_flags);
if (unlikely(err))
- netdev_free_page(dev, page);
+ put_page(page);
return err;
}
}
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- skb->len == 0, req->actual);
+ skb->len <= 1, req->actual);
page = NULL;
if (req->actual < req->length) { /* Last fragment */
}
if (page)
- netdev_free_page(dev, page);
+ put_page(page);
if (req)
- pn_rx_submit(fp, req, GFP_ATOMIC);
+ pn_rx_submit(fp, req, GFP_ATOMIC | __GFP_COLD);
}
/*-------------------------------------------------------------------------*/
netif_carrier_on(dev);
for (i = 0; i < phonet_rxq_size; i++)
- pn_rx_submit(fp, fp->out_reqv[i], GFP_ATOMIC);
+ pn_rx_submit(fp, fp->out_reqv[i], GFP_ATOMIC | __GFP_COLD);
}
spin_unlock(&port->lock);
return 0;
}
if (!gser->port.in->desc || !gser->port.out->desc) {
DBG(cdev, "activate generic ttyGS%d\n", gser->port_num);
- if (!config_ep_by_speed(cdev->gadget, f, gser->port.in) ||
- !config_ep_by_speed(cdev->gadget, f, gser->port.out)) {
+ if (config_ep_by_speed(cdev->gadget, f, gser->port.in) ||
+ config_ep_by_speed(cdev->gadget, f, gser->port.out)) {
gser->port.in->desc = NULL;
gser->port.out->desc = NULL;
return -EINVAL;
if (ctrl->bRequestType != (USB_DIR_OUT |
USB_TYPE_CLASS | USB_RECIP_INTERFACE))
break;
- if (w_index != 0 || w_value != 0) {
+ if (w_index != 0 || w_value != 0 || w_length != 0) {
value = -EDOM;
break;
}
if (ctrl->bRequestType != (USB_DIR_IN |
USB_TYPE_CLASS | USB_RECIP_INTERFACE))
break;
- if (w_index != 0 || w_value != 0) {
+ if (w_index != 0 || w_value != 0 || w_length != 1) {
value = -EDOM;
break;
}
#include <linux/err.h>
#include <linux/fsl_devices.h>
#include <linux/platform_device.h>
+#include <linux/io.h>
#include <mach/hardware.h>
void fsl_udc_clk_finalize(struct platform_device *pdev)
{
struct fsl_usb2_platform_data *pdata = pdev->dev.platform_data;
-#if defined(CONFIG_SOC_IMX35)
if (cpu_is_mx35()) {
unsigned int v;
USBPHYCTRL_OTGBASE_OFFSET));
}
}
-#endif
/* ULPI transceivers don't need usbpll */
if (pdata->phy_mode == FSL_USB2_PHY_ULPI) {
if (!udc_controller)
return -ENODEV;
- if (!driver || (driver->speed != USB_SPEED_FULL
- && driver->speed != USB_SPEED_HIGH)
+ if (!driver || driver->speed < USB_SPEED_FULL
|| !bind || !driver->disconnect || !driver->setup)
return -EINVAL;
kfree(req);
}
-/*-------------------------------------------------------------------------*/
+/* Actually add a dTD chain to an empty dQH and let go */
+static void fsl_prime_ep(struct fsl_ep *ep, struct ep_td_struct *td)
+{
+ struct ep_queue_head *qh = get_qh_by_ep(ep);
+
+ /* Write dQH next pointer and terminate bit to 0 */
+ qh->next_dtd_ptr = cpu_to_hc32(td->td_dma
+ & EP_QUEUE_HEAD_NEXT_POINTER_MASK);
+
+ /* Clear active and halt bit */
+ qh->size_ioc_int_sts &= cpu_to_hc32(~(EP_QUEUE_HEAD_STATUS_ACTIVE
+ | EP_QUEUE_HEAD_STATUS_HALT));
+
+ /* Ensure that updates to the QH will occur before priming. */
+ wmb();
+
+ /* Prime endpoint by writing correct bit to ENDPTPRIME */
+ fsl_writel(ep_is_in(ep) ? (1 << (ep_index(ep) + 16))
+ : (1 << (ep_index(ep))), &dr_regs->endpointprime);
+}
+
+/* Add dTD chain to the dQH of an EP */
static void fsl_queue_td(struct fsl_ep *ep, struct fsl_req *req)
{
- int i = ep_index(ep) * 2 + ep_is_in(ep);
u32 temp, bitmask, tmp_stat;
- struct ep_queue_head *dQH = &ep->udc->ep_qh[i];
/* VDBG("QH addr Register 0x%8x", dr_regs->endpointlistaddr);
VDBG("ep_qh[%d] addr is 0x%8x", i, (u32)&(ep->udc->ep_qh[i])); */
cpu_to_hc32(req->head->td_dma & DTD_ADDR_MASK);
/* Read prime bit, if 1 goto done */
if (fsl_readl(&dr_regs->endpointprime) & bitmask)
- goto out;
+ return;
do {
/* Set ATDTW bit in USBCMD */
fsl_writel(temp & ~USB_CMD_ATDTW, &dr_regs->usbcmd);
if (tmp_stat)
- goto out;
+ return;
}
- /* Write dQH next pointer and terminate bit to 0 */
- temp = req->head->td_dma & EP_QUEUE_HEAD_NEXT_POINTER_MASK;
- dQH->next_dtd_ptr = cpu_to_hc32(temp);
-
- /* Clear active and halt bit */
- temp = cpu_to_hc32(~(EP_QUEUE_HEAD_STATUS_ACTIVE
- | EP_QUEUE_HEAD_STATUS_HALT));
- dQH->size_ioc_int_sts &= temp;
-
- /* Ensure that updates to the QH will occur before priming. */
- wmb();
-
- /* Prime endpoint by writing 1 to ENDPTPRIME */
- temp = ep_is_in(ep)
- ? (1 << (ep_index(ep) + 16))
- : (1 << (ep_index(ep)));
- fsl_writel(temp, &dr_regs->endpointprime);
-out:
- return;
+ fsl_prime_ep(ep, req->head);
}
/* Fill in the dTD structure
VDBG("%s, bad ep", __func__);
return -EINVAL;
}
- if (ep->desc->bmAttributes == USB_ENDPOINT_XFER_ISOC) {
+ if (usb_endpoint_xfer_isoc(ep->desc)) {
if (req->req.length > ep->ep.maxpacket)
return -EMSGSIZE;
}
/* The request isn't the last request in this ep queue */
if (req->queue.next != &ep->queue) {
- struct ep_queue_head *qh;
struct fsl_req *next_req;
- qh = ep->qh;
next_req = list_entry(req->queue.next, struct fsl_req,
queue);
- /* Point the QH to the first TD of next request */
- fsl_writel((u32) next_req->head, &qh->curr_dtd_ptr);
+ /* prime with dTD of next request */
+ fsl_prime_ep(ep, next_req->head);
}
-
- /* The request hasn't been processed, patch up the TD chain */
+ /* The request hasn't been processed, patch up the TD chain */
} else {
struct fsl_req *prev_req;
prev_req = list_entry(req->queue.prev, struct fsl_req, queue);
- fsl_writel(fsl_readl(&req->tail->next_td_ptr),
- &prev_req->tail->next_td_ptr);
-
+ prev_req->tail->next_td_ptr = req->tail->next_td_ptr;
}
done(ep, req, -ECONNRESET);
goto out;
}
- if (ep->desc->bmAttributes == USB_ENDPOINT_XFER_ISOC) {
+ if (usb_endpoint_xfer_isoc(ep->desc)) {
status = -EOPNOTSUPP;
goto out;
}
struct fsl_udc *udc;
int size = 0;
u32 bitmask;
- struct ep_queue_head *d_qh;
+ struct ep_queue_head *qh;
ep = container_of(_ep, struct fsl_ep, ep);
if (!_ep || (!ep->desc && ep_index(ep) != 0))
if (!udc->driver || udc->gadget.speed == USB_SPEED_UNKNOWN)
return -ESHUTDOWN;
- d_qh = &ep->udc->ep_qh[ep_index(ep) * 2 + ep_is_in(ep)];
+ qh = get_qh_by_ep(ep);
bitmask = (ep_is_in(ep)) ? (1 << (ep_index(ep) + 16)) :
(1 << (ep_index(ep)));
if (fsl_readl(&dr_regs->endptstatus) & bitmask)
- size = (d_qh->size_ioc_int_sts & DTD_PACKET_SIZE)
+ size = (qh->size_ioc_int_sts & DTD_PACKET_SIZE)
>> DTD_LENGTH_BIT_POS;
pr_debug("%s %u\n", __func__, size);
static inline enum usb_device_speed portscx_device_speed(u32 reg)
{
- switch (speed & PORTSCX_PORT_SPEED_MASK) {
+ switch (reg & PORTSCX_PORT_SPEED_MASK) {
case PORTSCX_PORT_SPEED_HIGH:
return USB_SPEED_HIGH;
case PORTSCX_PORT_SPEED_FULL:
if (!udc_controller)
return -ENODEV;
- if (!driver || (driver->speed != USB_SPEED_FULL
- && driver->speed != USB_SPEED_HIGH)
+ if (!driver || driver->speed < USB_SPEED_FULL
|| !bind || !driver->disconnect || !driver->setup)
return -EINVAL;
#ifndef CONFIG_ARCH_MXC
if (pdata->have_sysif_regs)
- usb_sys_regs = (struct usb_sys_interface *)
- ((u32)dr_regs + USB_DR_SYS_OFFSET);
+ usb_sys_regs = (void *)dr_regs + USB_DR_SYS_OFFSET;
#endif
/* Initialize USB clocks */
* 2 + ((windex & USB_DIR_IN) ? 1 : 0))
#define get_pipe_by_ep(EP) (ep_index(EP) * 2 + ep_is_in(EP))
+static inline struct ep_queue_head *get_qh_by_ep(struct fsl_ep *ep)
+{
+ /* we only have one ep0 structure but two queue heads */
+ if (ep_index(ep) != 0)
+ return ep->qh;
+ else
+ return &ep->udc->ep_qh[(ep->udc->ep0_dir ==
+ USB_DIR_IN) ? 1 : 0];
+}
+
struct platform_device;
#ifdef CONFIG_ARCH_MXC
int fsl_udc_clk_init(struct platform_device *pdev);
gadgetfs_disconnect (struct usb_gadget *gadget)
{
struct dev_data *dev = get_gadget_data (gadget);
+ unsigned long flags;
- spin_lock (&dev->lock);
+ spin_lock_irqsave (&dev->lock, flags);
if (dev->state == STATE_DEV_UNCONNECTED)
goto exit;
dev->state = STATE_DEV_UNCONNECTED;
next_event (dev, GADGETFS_DISCONNECT);
ep0_readable (dev);
exit:
- spin_unlock (&dev->lock);
+ spin_unlock_irqrestore (&dev->lock, flags);
}
static void
int retval;
if (!driver
- || driver->speed != USB_SPEED_HIGH
+ || driver->speed < USB_SPEED_HIGH
|| !bind
|| !driver->setup)
return -EINVAL;
* (dev->usb->xcvrdiag & FORCE_FULL_SPEED_MODE)
* "must not be used in normal operation"
*/
- if (!driver || driver->speed != USB_SPEED_HIGH
+ if (!driver || driver->speed < USB_SPEED_HIGH
|| !driver->setup)
return -EINVAL;
/*
- * Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ * Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
#define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808
#define PCI_VENDOR_ID_ROHM 0x10DB
#define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D
+#define PCI_DEVICE_ID_ML7831_IOH_UDC 0x8808
static const char ep0_string[] = "ep0in";
static DEFINE_SPINLOCK(udc_stall_spinlock); /* stall spin lock */
.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
.class_mask = 0xffffffff,
},
+ {
+ PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7831_IOH_UDC),
+ .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+ .class_mask = 0xffffffff,
+ },
{ 0 },
};
module_exit(pch_udc_pci_exit);
MODULE_DESCRIPTION("Intel EG20T USB Device Controller");
-MODULE_AUTHOR("OKI SEMICONDUCTOR, <toshiharu-linux@dsn.okisemi.com>");
+MODULE_AUTHOR("LAPIS Semiconductor, <tomoya-linux@dsn.lapis-semi.com>");
MODULE_LICENSE("GPL");
if (list_empty(&ep->queue) && !ep->busy) {
pipe_stop(ep->r8a66597, ep->pipenum);
r8a66597_bclr(ep->r8a66597, BCLR, ep->fifoctr);
+ r8a66597_write(ep->r8a66597, ACLRM, ep->pipectr);
+ r8a66597_write(ep->r8a66597, 0, ep->pipectr);
}
spin_unlock_irqrestore(&ep->r8a66597->lock, flags);
}
struct usb_gadget_driver *driver)
{
struct r8a66597 *r8a66597 = gadget_to_r8a66597(gadget);
- int retval;
if (!driver
- || driver->speed != USB_SPEED_HIGH
+ || driver->speed < USB_SPEED_HIGH
|| !driver->setup)
return -EINVAL;
if (!r8a66597)
return -ENODEV;
/* hook up the driver */
- driver->driver.bus = NULL;
r8a66597->driver = driver;
- r8a66597->gadget.dev.driver = &driver->driver;
-
- retval = device_add(&r8a66597->gadget.dev);
- if (retval) {
- dev_err(r8a66597_to_dev(r8a66597), "device_add error (%d)\n",
- retval);
- goto error;
- }
init_controller(r8a66597);
r8a66597_bset(r8a66597, VBSE, INTENB0);
}
return 0;
-
-error:
- r8a66597->driver = NULL;
- r8a66597->gadget.dev.driver = NULL;
-
- return retval;
}
static int r8a66597_stop(struct usb_gadget *gadget,
disable_controller(r8a66597);
spin_unlock_irqrestore(&r8a66597->lock, flags);
- device_del(&r8a66597->gadget.dev);
r8a66597->driver = NULL;
return 0;
}
clk_put(r8a66597->clk);
}
#endif
+ device_unregister(&r8a66597->gadget.dev);
kfree(r8a66597);
return 0;
}
r8a66597->irq_sense_low = irq_trigger == IRQF_TRIGGER_LOW;
r8a66597->gadget.ops = &r8a66597_gadget_ops;
- device_initialize(&r8a66597->gadget.dev);
dev_set_name(&r8a66597->gadget.dev, "gadget");
r8a66597->gadget.is_dualspeed = 1;
r8a66597->gadget.dev.parent = &pdev->dev;
r8a66597->gadget.dev.dma_mask = pdev->dev.dma_mask;
r8a66597->gadget.dev.release = pdev->dev.release;
r8a66597->gadget.name = udc_name;
+ ret = device_register(&r8a66597->gadget.dev);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "device_register failed\n");
+ goto clean_up;
+ }
init_timer(&r8a66597->timer);
r8a66597->timer.function = r8a66597_timer;
dev_err(&pdev->dev, "cannot get clock \"%s\"\n",
clk_name);
ret = PTR_ERR(r8a66597->clk);
- goto clean_up;
+ goto clean_up_dev;
}
clk_enable(r8a66597->clk);
}
clk_disable(r8a66597->clk);
clk_put(r8a66597->clk);
}
+clean_up_dev:
#endif
+ device_unregister(&r8a66597->gadget.dev);
clean_up:
if (r8a66597) {
if (r8a66597->sudmac_reg)
return -EINVAL;
}
- if (driver->speed != USB_SPEED_HIGH &&
- driver->speed != USB_SPEED_FULL) {
+ if (driver->speed < USB_SPEED_FULL)
dev_err(hsotg->dev, "%s: bad speed\n", __func__);
- }
if (!bind || !driver->setup) {
dev_err(hsotg->dev, "%s: missing entry points\n", __func__);
int ret;
if (!driver
- || (driver->speed != USB_SPEED_FULL &&
- driver->speed != USB_SPEED_HIGH)
+ || driver->speed < USB_SPEED_FULL
|| !bind
|| !driver->unbind || !driver->disconnect || !driver->setup)
return -EINVAL;
kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
if (udc_is_newstyle(udc)) {
- usb_gadget_disconnect(udc->gadget);
+ udc->driver->disconnect(udc->gadget);
udc->driver->unbind(udc->gadget);
usb_gadget_udc_stop(udc->gadget, udc->driver);
-
+ usb_gadget_disconnect(udc->gadget);
} else {
usb_gadget_stop(udc->gadget, udc->driver);
}
static ssize_t usb_udc_srp_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t n)
{
- struct usb_udc *udc = dev_get_drvdata(dev);
+ struct usb_udc *udc = container_of(dev, struct usb_udc, dev);
if (sysfs_streq(buf, "1"))
usb_gadget_wakeup(udc->gadget);
return snprintf(buf, PAGE_SIZE, "%s\n",
usb_speed_string(udc->gadget->speed));
}
-static DEVICE_ATTR(speed, S_IRUSR, usb_udc_speed_show, NULL);
+static DEVICE_ATTR(speed, S_IRUGO, usb_udc_speed_show, NULL);
#define USB_UDC_ATTR(name) \
ssize_t usb_udc_##name##_show(struct device *dev, \
\
return snprintf(buf, PAGE_SIZE, "%d\n", gadget->name); \
} \
-static DEVICE_ATTR(name, S_IRUSR, usb_udc_##name##_show, NULL)
+static DEVICE_ATTR(name, S_IRUGO, usb_udc_##name##_show, NULL)
static USB_UDC_ATTR(is_dualspeed);
static USB_UDC_ATTR(is_otg);
* jump until after the queue is primed.
*/
else {
+ int done = 0;
start = SCHEDULE_SLOP + (now & ~0x07);
/* NOTE: assumes URB_ISO_ASAP, to limit complexity/bugs */
- /* find a uframe slot with enough bandwidth */
- next = start + period;
- for (; start < next; start++) {
-
+ /* find a uframe slot with enough bandwidth.
+ * Early uframes are more precious because full-speed
+ * iso IN transfers can't use late uframes,
+ * and therefore they should be allocated last.
+ */
+ next = start;
+ start += period;
+ do {
+ start--;
/* check schedule: enough space? */
if (stream->highspeed) {
if (itd_slot_ok(ehci, mod, start,
stream->usecs, period))
- break;
+ done = 1;
} else {
if ((start % 8) >= 6)
continue;
if (sitd_slot_ok(ehci, mod, stream,
start, sched, period))
- break;
+ done = 1;
}
- }
+ } while (start > next && !done);
/* no room in the schedule */
- if (start == next) {
+ if (!done) {
ehci_dbg(ehci, "iso resched full %p (now %d max %d)\n",
urb, now, now + mod);
status = -ENOSPC;
ehci->caps = hcd->regs;
ehci->regs = hcd->regs +
- HC_LENGTH(ehci_readl(ehci, &ehci->caps->hc_capbase));
+ HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase));
dbg_hcs_params(ehci, "reset");
dbg_hcc_params(ehci, "reset");
#include "isp1760-hcd.h"
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
#include <linux/slab.h>
#include <linux/of.h>
#include <linux/of_platform.h>
#include <linux/pci.h>
#endif
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
struct isp1760 {
struct usb_hcd *hcd;
int rst_gpio;
ret = platform_driver_register(&isp1760_plat_driver);
if (!ret)
any_ret = 0;
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
ret = platform_driver_register(&isp1760_of_driver);
if (!ret)
any_ret = 0;
static void __exit isp1760_exit(void)
{
platform_driver_unregister(&isp1760_plat_driver);
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
platform_driver_unregister(&isp1760_of_driver);
#endif
#ifdef CONFIG_PCI
if (port < 0 || port >= 2)
return;
+ if (pdata->vbus_pin[port] <= 0)
+ return;
+
gpio_set_value(pdata->vbus_pin[port], !pdata->vbus_pin_inverted ^ enable);
}
if (port < 0 || port >= 2)
return -EINVAL;
+ if (pdata->vbus_pin[port] <= 0)
+ return -EINVAL;
+
return gpio_get_value(pdata->vbus_pin[port]) ^ !pdata->vbus_pin_inverted;
}
struct ohci_hcd *ohci;
ohci = hcd_to_ohci (hcd);
- ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable);
- ohci->hc_control = ohci_readl(ohci, &ohci->regs->control);
+ ohci_writel(ohci, (u32) ~0, &ohci->regs->intrdisable);
- /* If the SHUTDOWN quirk is set, don't put the controller in RESET */
- ohci->hc_control &= (ohci->flags & OHCI_QUIRK_SHUTDOWN ?
- OHCI_CTRL_RWC | OHCI_CTRL_HCFS :
- OHCI_CTRL_RWC);
- ohci_writel(ohci, ohci->hc_control, &ohci->regs->control);
+ /* Software reset, after which the controller goes into SUSPEND */
+ ohci_writel(ohci, OHCI_HCR, &ohci->regs->cmdstatus);
+ ohci_readl(ohci, &ohci->regs->cmdstatus); /* flush the writes */
+ udelay(10);
- /* flush the writes */
- (void) ohci_readl (ohci, &ohci->regs->control);
+ ohci_writel(ohci, ohci->fminterval, &ohci->regs->fminterval);
}
static int check_ed(struct ohci_hcd *ohci, struct ed *ed)
return 0;
}
-/* nVidia controllers continue to drive Reset signalling on the bus
- * even after system shutdown, wasting power. This flag tells the
- * shutdown routine to leave the controller OPERATIONAL instead of RESET.
- */
-static int ohci_quirk_nvidia_shutdown(struct usb_hcd *hcd)
-{
- struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
- struct ohci_hcd *ohci = hcd_to_ohci(hcd);
-
- /* Evidently nVidia fixed their later hardware; this is a guess at
- * the changeover point.
- */
-#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_USB 0x026d
-
- if (pdev->device < PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_USB) {
- ohci->flags |= OHCI_QUIRK_SHUTDOWN;
- ohci_dbg(ohci, "enabled nVidia shutdown quirk\n");
- }
-
- return 0;
-}
-
static void sb800_prefetch(struct ohci_hcd *ohci, int on)
{
struct pci_dev *pdev;
PCI_DEVICE(PCI_VENDOR_ID_ATI, 0x4399),
.driver_data = (unsigned long)ohci_quirk_amd700,
},
- {
- PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID),
- .driver_data = (unsigned long) ohci_quirk_nvidia_shutdown,
- },
/* FIXME for some of the early AMD 760 southbridges, OHCI
* won't work at all. blacklist them.
#define OHCI_QUIRK_HUB_POWER 0x100 /* distrust firmware power/oc setup */
#define OHCI_QUIRK_AMD_PLL 0x200 /* AMD PLL quirk*/
#define OHCI_QUIRK_AMD_PREFETCH 0x400 /* pre-fetch for ISO transfer */
-#define OHCI_QUIRK_SHUTDOWN 0x800 /* nVidia power bug */
// there are also chip quirks/bugs in init logic
struct work_struct nec_work; /* Worker for NEC quirk */
#define OHCI_INTRENABLE 0x10
#define OHCI_INTRDISABLE 0x14
#define OHCI_FMINTERVAL 0x34
+#define OHCI_HCFS (3 << 6) /* hc functional state */
#define OHCI_HCR (1 << 0) /* host controller reset */
#define OHCI_OCR (1 << 3) /* ownership change request */
#define OHCI_CTRL_RWC (1 << 9) /* remote wakeup connected */
{
void __iomem *base;
u32 control;
+ u32 fminterval;
+ int cnt;
if (!mmio_resource_enabled(pdev, 0))
return;
}
#endif
- /* reset controller, preserving RWC (and possibly IR) */
- writel(control & OHCI_CTRL_MASK, base + OHCI_CONTROL);
- readl(base + OHCI_CONTROL);
+ /* disable interrupts */
+ writel((u32) ~0, base + OHCI_INTRDISABLE);
- /* Some NVIDIA controllers stop working if kept in RESET for too long */
- if (pdev->vendor == PCI_VENDOR_ID_NVIDIA) {
- u32 fminterval;
- int cnt;
+ /* Reset the USB bus, if the controller isn't already in RESET */
+ if (control & OHCI_HCFS) {
+ /* Go into RESET, preserving RWC (and possibly IR) */
+ writel(control & OHCI_CTRL_MASK, base + OHCI_CONTROL);
+ readl(base + OHCI_CONTROL);
- /* drive reset for at least 50 ms (7.1.7.5) */
+ /* drive bus reset for at least 50 ms (7.1.7.5) */
msleep(50);
+ }
- /* software reset of the controller, preserving HcFmInterval */
- fminterval = readl(base + OHCI_FMINTERVAL);
- writel(OHCI_HCR, base + OHCI_CMDSTATUS);
+ /* software reset of the controller, preserving HcFmInterval */
+ fminterval = readl(base + OHCI_FMINTERVAL);
+ writel(OHCI_HCR, base + OHCI_CMDSTATUS);
- /* reset requires max 10 us delay */
- for (cnt = 30; cnt > 0; --cnt) { /* ... allow extra time */
- if ((readl(base + OHCI_CMDSTATUS) & OHCI_HCR) == 0)
- break;
- udelay(1);
- }
- writel(fminterval, base + OHCI_FMINTERVAL);
-
- /* Now we're in the SUSPEND state with all devices reset
- * and wakeups and interrupts disabled
- */
+ /* reset requires max 10 us delay */
+ for (cnt = 30; cnt > 0; --cnt) { /* ... allow extra time */
+ if ((readl(base + OHCI_CMDSTATUS) & OHCI_HCR) == 0)
+ break;
+ udelay(1);
}
+ writel(fminterval, base + OHCI_FMINTERVAL);
- /*
- * disable interrupts
- */
- writel(~(u32)0, base + OHCI_INTRDISABLE);
- writel(~(u32)0, base + OHCI_INTRSTATUS);
-
+ /* Now the controller is safely in SUSPEND and nothing can wake it up */
iounmap(base);
}
void __iomem *base, *op_reg_base;
u32 hcc_params, cap, val;
u8 offset, cap_length;
- int wait_time, delta, count = 256/4;
+ int wait_time, count = 256/4;
if (!mmio_resource_enabled(pdev, 0))
return;
writel(val, op_reg_base + EHCI_USBCMD);
wait_time = 2000;
- delta = 100;
do {
writel(0x3f, op_reg_base + EHCI_USBSTS);
- udelay(delta);
- wait_time -= delta;
+ udelay(100);
+ wait_time -= 100;
val = readl(op_reg_base + EHCI_USBSTS);
if ((val == ~(u32)0) || (val & EHCI_USBSTS_HALTED)) {
break;
{
qset->td_start = qset->td_end = qset->ntds = 0;
- qset->qh.link = cpu_to_le32(QH_LINK_NTDS(8) | QH_LINK_T);
+ qset->qh.link = cpu_to_le64(QH_LINK_NTDS(8) | QH_LINK_T);
qset->qh.status = qset->qh.status & QH_STATUS_SEQ_MASK;
qset->qh.err_count = 0;
qset->qh.scratch[0] = 0;
struct xhci_virt_device *dev;
struct xhci_ep_ctx *ep0_ctx;
struct xhci_slot_ctx *slot_ctx;
- struct xhci_input_control_ctx *ctrl_ctx;
u32 port_num;
struct usb_device *top_dev;
return -EINVAL;
}
ep0_ctx = xhci_get_ep_ctx(xhci, dev->in_ctx, 0);
- ctrl_ctx = xhci_get_input_control_ctx(xhci, dev->in_ctx);
slot_ctx = xhci_get_slot_ctx(xhci, dev->in_ctx);
- /* 2) New slot context and endpoint 0 context are valid*/
- ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
-
/* 3) Only the control endpoint is valid - one endpoint context */
slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | udev->route);
switch (udev->speed) {
struct xhci_ring *ring;
struct xhci_td *cur_td;
int ret, i, j;
+ unsigned long flags;
ep = (struct xhci_virt_ep *) arg;
xhci = ep->xhci;
- spin_lock(&xhci->lock);
+ spin_lock_irqsave(&xhci->lock, flags);
ep->stop_cmds_pending--;
if (xhci->xhc_state & XHCI_STATE_DYING) {
xhci_dbg(xhci, "Stop EP timer ran, but another timer marked "
"xHCI as DYING, exiting.\n");
- spin_unlock(&xhci->lock);
+ spin_unlock_irqrestore(&xhci->lock, flags);
return;
}
if (!(ep->stop_cmds_pending == 0 && (ep->ep_state & EP_HALT_PENDING))) {
xhci_dbg(xhci, "Stop EP timer ran, but no command pending, "
"exiting.\n");
- spin_unlock(&xhci->lock);
+ spin_unlock_irqrestore(&xhci->lock, flags);
return;
}
xhci->xhc_state |= XHCI_STATE_DYING;
/* Disable interrupts from the host controller and start halting it */
xhci_quiesce(xhci);
- spin_unlock(&xhci->lock);
+ spin_unlock_irqrestore(&xhci->lock, flags);
ret = xhci_halt(xhci);
- spin_lock(&xhci->lock);
+ spin_lock_irqsave(&xhci->lock, flags);
if (ret < 0) {
/* This is bad; the host is not responding to commands and it's
* not allowing itself to be halted. At least interrupts are
}
}
}
- spin_unlock(&xhci->lock);
+ spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg(xhci, "Calling usb_hc_died()\n");
usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
xhci_dbg(xhci, "xHCI host controller is dead.\n");
ring = xhci->cmd_ring;
seg = ring->deq_seg;
do {
- memset(seg->trbs, 0, SEGMENT_SIZE);
+ memset(seg->trbs, 0,
+ sizeof(union xhci_trb) * (TRBS_PER_SEGMENT - 1));
+ seg->trbs[TRBS_PER_SEGMENT - 1].link.control &=
+ cpu_to_le32(~TRB_CYCLE);
seg = seg->next;
} while (seg != ring->deq_seg);
u32 command, temp = 0;
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct usb_hcd *secondary_hcd;
- int retval;
+ int retval = 0;
/* Wait a bit if either of the roothubs need to settle from the
* transition into bus suspend.
xhci->bus_state[1].next_statechange))
msleep(100);
+ set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+ set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
+
spin_lock_irq(&xhci->lock);
if (xhci->quirks & XHCI_RESET_ON_RESUME)
hibernated = true;
return retval;
xhci_dbg(xhci, "Start the primary HCD\n");
retval = xhci_run(hcd->primary_hcd);
- if (retval)
- goto failed_restart;
-
- xhci_dbg(xhci, "Start the secondary HCD\n");
- retval = xhci_run(secondary_hcd);
if (!retval) {
- set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
- set_bit(HCD_FLAG_HW_ACCESSIBLE,
- &xhci->shared_hcd->flags);
+ xhci_dbg(xhci, "Start the secondary HCD\n");
+ retval = xhci_run(secondary_hcd);
}
-failed_restart:
hcd->state = HC_STATE_SUSPENDED;
xhci->shared_hcd->state = HC_STATE_SUSPENDED;
- return retval;
+ goto done;
}
/* step 4: set Run/Stop bit */
* Running endpoints by ringing their doorbells
*/
- set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
- set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
-
spin_unlock_irq(&xhci->lock);
- return 0;
+
+ done:
+ if (retval == 0) {
+ usb_hcd_resume_root_hub(hcd);
+ usb_hcd_resume_root_hub(xhci->shared_hcd);
+ }
+ return retval;
}
#endif /* CONFIG_PM */
/* Otherwise, update the control endpoint ring enqueue pointer. */
else
xhci_copy_ep0_dequeue_into_input_ctx(xhci, udev);
+ ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
+ ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
+ ctrl_ctx->drop_flags = 0;
+
xhci_dbg(xhci, "Slot ID %d Input Context:\n", udev->slot_id);
xhci_dbg_ctx(xhci, virt_dev->in_ctx, 2);
virt_dev->address = (le32_to_cpu(slot_ctx->dev_state) & DEV_ADDR_MASK)
+ 1;
/* Zero the input context control for later use */
- ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
ctrl_ctx->add_flags = 0;
ctrl_ctx->drop_flags = 0;
select TWL4030_USB if MACH_OMAP_3430SDP
select TWL6030_USB if MACH_OMAP_4430SDP || MACH_OMAP4_PANDA
select USB_OTG_UTILS
+ select USB_GADGET_DUALSPEED
tristate 'Inventra Highspeed Dual Role Controller (TI, ADI, ...)'
help
Say Y here if your system has a dual role high speed USB
config USB_MUSB_UX500
tristate "U8500 and U5500"
- depends on (ARCH_U8500 && AB8500_USB) || (ARCH_U5500)
+ depends on (ARCH_U8500 && AB8500_USB)
endchoice
*/
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/clk.h>
#include <linux/io.h>
#include <linux/platform_device.h>
*/
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/clk.h>
#include <linux/io.h>
#include <linux/platform_device.h>
/*-------------------------------------------------------------------------*/
#if defined(CONFIG_SOC_OMAP2430) || defined(CONFIG_SOC_OMAP3430) || \
- defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_ARCH_U8500) || \
- defined(CONFIG_ARCH_U5500)
+ defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_ARCH_U8500)
static irqreturn_t generic_interrupt(int irq, void *__hci)
{
*/
}
- musb_save_context(musb);
-
spin_unlock_irqrestore(&musb->lock, flags);
return 0;
}
static int musb_resume_noirq(struct device *dev)
{
- struct musb *musb = dev_to_musb(dev);
-
- musb_restore_context(musb);
-
/* for static cmos like DaVinci, register values were preserved
* unless for some reason the whole soc powered down or the USB
* module got reset through the PSC (vs just being disabled).
unsigned long flags;
int retval = -EINVAL;
- if (driver->speed != USB_SPEED_HIGH)
+ if (driver->speed < USB_SPEED_HIGH)
goto err0;
pm_runtime_get_sync(musb->controller);
nuke(&hw_ep->ep_out, -ESHUTDOWN);
}
}
-
- spin_unlock(&musb->lock);
- driver->disconnect(&musb->g);
- spin_lock(&musb->lock);
}
}
if (musb->double_buffer_not_ok)
musb_writew(epio, MUSB_TXMAXP,
hw_ep->max_packet_sz_tx);
+ else if (can_bulk_split(musb, qh->type))
+ musb_writew(epio, MUSB_TXMAXP, packet_sz
+ | ((hw_ep->max_packet_sz_tx /
+ packet_sz) - 1) << 11);
else
musb_writew(epio, MUSB_TXMAXP,
qh->maxpacket |
/*
* platform functions
*/
-static int __devinit usbhs_probe(struct platform_device *pdev)
+static int usbhs_probe(struct platform_device *pdev)
{
struct renesas_usbhs_platform_info *info = pdev->dev.platform_data;
struct renesas_usbhs_driver_callback *dfunc;
if (len % 4) /* 32bit alignment */
goto usbhsf_pio_prepare_push;
- if ((*(u32 *) pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
+ if ((uintptr_t)(pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
goto usbhsf_pio_prepare_push;
/* get enable DMA fifo */
if (!fifo)
goto usbhsf_pio_prepare_pop;
- if ((*(u32 *) pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
+ if ((uintptr_t)(pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
goto usbhsf_pio_prepare_pop;
ret = usbhsf_fifo_select(pipe, fifo, 0);
if (mod->irq_attch)
intenb1 |= ATTCHE;
- if (mod->irq_attch)
+ if (mod->irq_dtch)
intenb1 |= DTCHE;
if (mod->irq_sign)
*/
#if defined(CONFIG_USB_RENESAS_USBHS_HCD) || \
defined(CONFIG_USB_RENESAS_USBHS_HCD_MODULE)
-extern int __devinit usbhs_mod_host_probe(struct usbhs_priv *priv);
-extern int __devexit usbhs_mod_host_remove(struct usbhs_priv *priv);
+extern int usbhs_mod_host_probe(struct usbhs_priv *priv);
+extern int usbhs_mod_host_remove(struct usbhs_priv *priv);
#else
static inline int usbhs_mod_host_probe(struct usbhs_priv *priv)
{
#if defined(CONFIG_USB_RENESAS_USBHS_UDC) || \
defined(CONFIG_USB_RENESAS_USBHS_UDC_MODULE)
-extern int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv);
-extern void __devexit usbhs_mod_gadget_remove(struct usbhs_priv *priv);
+extern int usbhs_mod_gadget_probe(struct usbhs_priv *priv);
+extern void usbhs_mod_gadget_remove(struct usbhs_priv *priv);
#else
static inline int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
{
struct usb_gadget_driver *driver)
{
struct usbhsg_gpriv *gpriv = usbhsg_gadget_to_gpriv(gadget);
- struct usbhs_priv *priv;
- struct device *dev;
- int ret;
+ struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
if (!driver ||
!driver->setup ||
- driver->speed != USB_SPEED_HIGH)
+ driver->speed < USB_SPEED_FULL)
return -EINVAL;
- dev = usbhsg_gpriv_to_dev(gpriv);
- priv = usbhsg_gpriv_to_priv(gpriv);
-
/* first hook up the driver ... */
gpriv->driver = driver;
gpriv->gadget.dev.driver = &driver->driver;
- ret = device_add(&gpriv->gadget.dev);
- if (ret) {
- dev_err(dev, "device_add error %d\n", ret);
- goto add_fail;
- }
-
return usbhsg_try_start(priv, USBHSG_STATUS_REGISTERD);
-
-add_fail:
- gpriv->driver = NULL;
- gpriv->gadget.dev.driver = NULL;
-
- return ret;
}
static int usbhsg_gadget_stop(struct usb_gadget *gadget,
struct usb_gadget_driver *driver)
{
struct usbhsg_gpriv *gpriv = usbhsg_gadget_to_gpriv(gadget);
- struct usbhs_priv *priv;
- struct device *dev;
+ struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
if (!driver ||
!driver->unbind)
return -EINVAL;
- dev = usbhsg_gpriv_to_dev(gpriv);
- priv = usbhsg_gpriv_to_priv(gpriv);
-
usbhsg_try_stop(priv, USBHSG_STATUS_REGISTERD);
- device_del(&gpriv->gadget.dev);
+ gpriv->gadget.dev.driver = NULL;
gpriv->driver = NULL;
return 0;
static int usbhsg_stop(struct usbhs_priv *priv)
{
+ struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
+
+ /* cable disconnect */
+ if (gpriv->driver &&
+ gpriv->driver->disconnect)
+ gpriv->driver->disconnect(&gpriv->gadget);
+
return usbhsg_try_stop(priv, USBHSG_STATUS_STARTED);
}
-int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv)
+int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
{
struct usbhsg_gpriv *gpriv;
struct usbhsg_uep *uep;
/*
* init gadget
*/
- device_initialize(&gpriv->gadget.dev);
dev_set_name(&gpriv->gadget.dev, "gadget");
gpriv->gadget.dev.parent = dev;
gpriv->gadget.name = "renesas_usbhs_udc";
gpriv->gadget.ops = &usbhsg_gadget_ops;
gpriv->gadget.is_dualspeed = 1;
+ ret = device_register(&gpriv->gadget.dev);
+ if (ret < 0)
+ goto err_add_udc;
INIT_LIST_HEAD(&gpriv->gadget.ep_list);
ret = usb_add_gadget_udc(dev, &gpriv->gadget);
if (ret)
- goto err_add_udc;
+ goto err_register;
dev_info(dev, "gadget probed\n");
return 0;
+
+err_register:
+ device_unregister(&gpriv->gadget.dev);
err_add_udc:
kfree(gpriv->uep);
return ret;
}
-void __devexit usbhs_mod_gadget_remove(struct usbhs_priv *priv)
+void usbhs_mod_gadget_remove(struct usbhs_priv *priv)
{
struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
usb_del_gadget_udc(&gpriv->gadget);
+ device_unregister(&gpriv->gadget.dev);
+
usbhsg_controller_unregister(gpriv);
kfree(gpriv->uep);
u32 port_stat; /* USB_PORT_STAT_xxx */
- struct completion *done;
+ struct completion setup_ack_done;
/* see usbhsh_req_alloc/free */
struct list_head ureq_link_active;
struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
struct usbhsh_device *udev,
struct usb_host_endpoint *ep,
+ int dir_in_req,
gfp_t mem_flags)
{
struct usbhs_priv *priv = usbhsh_hpriv_to_priv(hpriv);
struct usbhs_pipe *pipe, *best_pipe;
struct device *dev = usbhsh_hcd_to_dev(hcd);
struct usb_endpoint_descriptor *desc = &ep->desc;
- int type, i;
+ int type, i, dir_in;
unsigned int min_usr;
+ dir_in_req = !!dir_in_req;
+
uep = kzalloc(sizeof(struct usbhsh_ep), mem_flags);
if (!uep) {
dev_err(dev, "usbhsh_ep alloc fail\n");
return NULL;
}
- type = usb_endpoint_type(desc);
+
+ if (usb_endpoint_xfer_control(desc)) {
+ best_pipe = usbhsh_hpriv_to_dcp(hpriv);
+ goto usbhsh_endpoint_alloc_find_pipe;
+ }
/*
* find best pipe for endpoint
* see
* HARDWARE LIMITATION
*/
+ type = usb_endpoint_type(desc);
min_usr = ~0;
best_pipe = NULL;
- usbhs_for_each_pipe_with_dcp(pipe, priv, i) {
+ usbhs_for_each_pipe(pipe, priv, i) {
if (!usbhs_pipe_type_is(pipe, type))
continue;
+ dir_in = !!usbhs_pipe_is_dir_in(pipe);
+ if (0 != (dir_in - dir_in_req))
+ continue;
+
info = usbhsh_pipe_info(pipe);
if (min_usr > info->usr_cnt) {
kfree(uep);
return NULL;
}
-
+usbhsh_endpoint_alloc_find_pipe:
/*
* init uep
*/
* see
* DCPMAXP/PIPEMAXP
*/
+ usbhs_pipe_sequence_data0(uep->pipe);
usbhs_pipe_config_update(uep->pipe,
usbhsh_device_number(hpriv, udev),
usb_endpoint_num(desc),
dev_dbg(dev, "%s [%d-%s](%p)\n", __func__,
usbhsh_device_number(hpriv, udev),
- usbhs_pipe_name(pipe), uep);
+ usbhs_pipe_name(uep->pipe), uep);
return uep;
}
* usbhsh_irq_setup_ack()
* usbhsh_irq_setup_err()
*/
- DECLARE_COMPLETION(done);
- hpriv->done = &done;
+ init_completion(&hpriv->setup_ack_done);
/* copy original request */
memcpy(&req, urb->setup_packet, sizeof(struct usb_ctrlrequest));
/*
* wait setup packet ACK
*/
- wait_for_completion(&done);
- hpriv->done = NULL;
+ wait_for_completion(&hpriv->setup_ack_done);
dev_dbg(dev, "%s done\n", __func__);
}
struct usbhsh_device *udev, *new_udev = NULL;
struct usbhs_pipe *pipe;
struct usbhsh_ep *uep;
+ int is_dir_in = usb_pipein(urb->pipe);
int ret;
- dev_dbg(dev, "%s (%s)\n",
- __func__, usb_pipein(urb->pipe) ? "in" : "out");
+ dev_dbg(dev, "%s (%s)\n", __func__, is_dir_in ? "in" : "out");
ret = usb_hcd_link_urb_to_ep(hcd, urb);
if (ret)
*/
uep = usbhsh_ep_to_uep(ep);
if (!uep) {
- uep = usbhsh_endpoint_alloc(hpriv, udev, ep, mem_flags);
+ uep = usbhsh_endpoint_alloc(hpriv, udev, ep,
+ is_dir_in, mem_flags);
if (!uep)
goto usbhsh_urb_enqueue_error_free_device;
}
dev_dbg(dev, "setup packet OK\n");
- if (unlikely(!hpriv->done))
- dev_err(dev, "setup ack happen without necessary data\n");
- else
- complete(hpriv->done); /* see usbhsh_urb_enqueue() */
+ complete(&hpriv->setup_ack_done); /* see usbhsh_urb_enqueue() */
return 0;
}
dev_dbg(dev, "setup packet Err\n");
- if (unlikely(!hpriv->done))
- dev_err(dev, "setup err happen without necessary data\n");
- else
- complete(hpriv->done); /* see usbhsh_urb_enqueue() */
+ complete(&hpriv->setup_ack_done); /* see usbhsh_urb_enqueue() */
return 0;
}
{
struct usbhsh_hpriv *hpriv = usbhsh_priv_to_hpriv(priv);
struct usb_hcd *hcd = usbhsh_hpriv_to_hcd(hpriv);
+ struct usbhs_mod *mod = usbhs_mod_get_current(priv);
struct device *dev = usbhs_priv_to_dev(priv);
+ /*
+ * disable irq callback
+ */
+ mod->irq_attch = NULL;
+ mod->irq_dtch = NULL;
+ mod->irq_sack = NULL;
+ mod->irq_sign = NULL;
+ usbhs_irq_callback_update(priv, mod);
+
usb_remove_hcd(hcd);
/* disable sys */
return 0;
}
-int __devinit usbhs_mod_host_probe(struct usbhs_priv *priv)
+int usbhs_mod_host_probe(struct usbhs_priv *priv)
{
struct usbhsh_hpriv *hpriv;
struct usb_hcd *hcd;
dev_err(dev, "Failed to create hcd\n");
return -ENOMEM;
}
+ hcd->has_tt = 1; /* for low/full speed */
pipe_info = kzalloc(sizeof(*pipe_info) * pipe_size, GFP_KERNEL);
if (!pipe_info) {
hpriv->mod.stop = usbhsh_stop;
hpriv->pipe_info = pipe_info;
hpriv->pipe_size = pipe_size;
- hpriv->done = NULL;
usbhsh_req_list_init(hpriv);
usbhsh_port_stat_init(hpriv);
return -ENOMEM;
}
-int __devexit usbhs_mod_host_remove(struct usbhs_priv *priv)
+int usbhs_mod_host_remove(struct usbhs_priv *priv)
{
struct usbhsh_hpriv *hpriv = usbhsh_priv_to_hpriv(priv);
struct usb_hcd *hcd = usbhsh_hpriv_to_hcd(hpriv);
* Version information
*/
-#define DRIVER_VERSION "v0.6"
+#define DRIVER_VERSION "v0.7"
#define DRIVER_AUTHOR "Bart Hartgers <bart.hartgers+ark3116@gmail.com>"
#define DRIVER_DESC "USB ARK3116 serial/IrDA driver"
#define DRIVER_DEV_DESC "ARK3116 RS232/IrDA"
goto err_out;
}
- /* setup termios */
- if (tty)
- ark3116_set_termios(tty, port, NULL);
-
/* remove any data still left: also clears error state */
ark3116_read_reg(serial, UART_RX, buf);
/* enable DMA */
ark3116_write_reg(port->serial, UART_FCR, UART_FCR_DMA_SELECT);
+ /* setup termios */
+ if (tty)
+ ark3116_set_termios(tty, port, NULL);
+
err_out:
kfree(buf);
return result;
{ USB_DEVICE(TML_VID, TML_USB_SERIAL_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
cflag = termios->c_cflag;
- /* FIXME -For this cut I don't care if the line is really changing or
- not - so just do the change regardless - should be able to
- compare old_termios and tty->termios */
+ if (old_termios->c_cflag == termios->c_cflag
+ && old_termios->c_ispeed == termios->c_ispeed
+ && old_termios->c_ospeed == termios->c_ospeed)
+ goto no_c_cflag_changes;
+
/* NOTE These routines can get interrupted by
ftdi_sio_read_bulk_callback - need to examine what this means -
don't see any problems yet */
+ if ((old_termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)) ==
+ (termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)))
+ goto no_data_parity_stop_changes;
+
/* Set number of data bits, parity, stop bits */
urb_value = 0;
}
/* Now do the baudrate */
+no_data_parity_stop_changes:
if ((cflag & CBAUD) == B0) {
/* Disable flow control */
if (usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
/* Set flow control */
/* Note device also supports DTR/CD (ugh) and Xon/Xoff in hardware */
+no_c_cflag_changes:
if (cflag & CRTSCTS) {
dbg("%s Setting to CRTSCTS flow control", __func__);
if (usb_control_msg(dev,
/* Propox devices */
#define FTDI_PROPOX_JTAGCABLEII_PID 0xD738
+#define FTDI_PROPOX_ISPCABLEIII_PID 0xD739
/* Lenz LI-USB Computer Interface. */
#define FTDI_LENZ_LIUSB_PID 0xD780
#define HUAWEI_PRODUCT_K4511 0x14CC
#define HUAWEI_PRODUCT_ETS1220 0x1803
#define HUAWEI_PRODUCT_E353 0x1506
+#define HUAWEI_PRODUCT_E173S 0x1C05
#define QUANTA_VENDOR_ID 0x0408
#define QUANTA_PRODUCT_Q101 0xEA02
#define ZTE_PRODUCT_AC8710 0xfff1
#define ZTE_PRODUCT_AC2726 0xfff5
#define ZTE_PRODUCT_AC8710T 0xffff
+#define ZTE_PRODUCT_MC2718 0xffe8
+#define ZTE_PRODUCT_AD3812 0xffeb
+#define ZTE_PRODUCT_MC2716 0xffed
#define BENQ_VENDOR_ID 0x04a5
#define BENQ_PRODUCT_H10 0x4068
#define YUGA_PRODUCT_CLU528 0x260D
#define YUGA_PRODUCT_CLU526 0x260F
+/* Viettel products */
+#define VIETTEL_VENDOR_ID 0x2262
+#define VIETTEL_PRODUCT_VT1000 0x0002
+
/* some devices interfaces need special handling due to a number of reasons */
enum option_blacklist_reason {
OPTION_BLACKLIST_NONE = 0,
.reserved = BIT(4),
};
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+ .sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
+static const struct option_blacklist_info zte_mc2718_z_blacklist = {
+ .sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+ .sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
static const struct option_blacklist_info huawei_cdc12_blacklist = {
.reserved = BIT(1) | BIT(2),
};
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143D, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143E, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143F, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3765, 0xff, 0xff, 0xff),
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x31) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x32) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x01) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x02) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x03) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x10) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x12) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x13) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x01) }, /* E398 3G Modem */
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x02) }, /* E398 3G PC UI Interface */
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x03) }, /* E398 3G Application Interface */
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V740) },
{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
{ USB_DEVICE(ALINK_VENDOR_ID, DLINK_PRODUCT_DWM_652_U5) }, /* Yes, ALINK_VENDOR_ID */
{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU516) },
{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU528) },
{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU526) },
+ { USB_DEVICE_AND_INTERFACE_INFO(VIETTEL_VENDOR_ID, VIETTEL_PRODUCT_VT1000, 0xff, 0xff, 0xff) },
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
{ USB_DEVICE(SANWA_VENDOR_ID, SANWA_PRODUCT_ID) },
{ USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530_PRODUCT_ID) },
- { USB_DEVICE(WINCHIPHEAD_VENDOR_ID, WINCHIPHEAD_USBSER_PRODUCT_ID) },
{ USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) },
{ } /* Terminating entry */
};
#define ADLINK_VENDOR_ID 0x0b63
#define ADLINK_ND6530_PRODUCT_ID 0x6530
-/* WinChipHead USB->RS 232 adapter */
-#define WINCHIPHEAD_VENDOR_ID 0x4348
-#define WINCHIPHEAD_USBSER_PRODUCT_ID 0x5523
-
/* SMART USB Serial Adapter */
#define SMART_VENDOR_ID 0x0b8c
#define SMART_PRODUCT_ID 0x2303
result = ene_send_scsi_cmd(us, FDIR_WRITE, scsi_sglist(srb), 1);
} else {
void *buf;
- int offset;
+ int offset = 0;
u16 PhyBlockAddr;
u8 PageNum;
- u32 result;
u16 len, oldphy, newphy;
buf = kmalloc(blenByte, GFP_KERNEL);
void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
{
- /* Pad the SCSI command with zeros out to 12 bytes
+ /*
+ * Pad the SCSI command with zeros out to 12 bytes. If the
+ * command already is 12 bytes or longer, leave it alone.
*
* NOTE: This only works because a scsi_cmnd struct field contains
* a unsigned char cmnd[16], so we know we have storage available
for (; srb->cmd_len<12; srb->cmd_len++)
srb->cmnd[srb->cmd_len] = 0;
- /* set command length to 12 bytes */
- srb->cmd_len = 12;
-
/* send the command to the transport layer */
usb_stor_invoke_transport(srb, us);
}
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE ),
+/* Reported by Qinglin Ye <yestyle@gmail.com> */
+UNUSUAL_DEV( 0x13fe, 0x3600, 0x0100, 0x0100,
+ "Kingston",
+ "DT 101 G2",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_BULK_IGNORE_TAG ),
+
/* Reported by Francesco Foresti <frafore@tiscali.it> */
UNUSUAL_DEV( 0x14cd, 0x6600, 0x0201, 0x0201,
"Super Top",
/* Clock registers available only on Version 2 */
#define LCD_CLK_ENABLE_REG 0x6c
#define LCD_CLK_RESET_REG 0x70
+#define LCD_CLK_MAIN_RESET BIT(3)
#define LCD_NUM_BUFFERS 2
{
u32 reg;
+ /* Bring LCDC out of reset */
+ if (lcd_revision == LCD_VERSION_2)
+ lcdc_write(0, LCD_CLK_RESET_REG);
+
reg = lcdc_read(LCD_RASTER_CTRL_REG);
if (!(reg & LCD_RASTER_ENABLE))
lcdc_write(reg | LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
reg = lcdc_read(LCD_RASTER_CTRL_REG);
if (reg & LCD_RASTER_ENABLE)
lcdc_write(reg & ~LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
+
+ if (lcd_revision == LCD_VERSION_2)
+ /* Write 1 to reset LCDC */
+ lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
}
static void lcd_blit(int load_mode, struct da8xx_fb_par *par)
lcdc_write(0, LCD_DMA_CTRL_REG);
lcdc_write(0, LCD_RASTER_CTRL_REG);
- if (lcd_revision == LCD_VERSION_2)
+ if (lcd_revision == LCD_VERSION_2) {
lcdc_write(0, LCD_INT_ENABLE_SET_REG);
+ /* Write 1 to reset */
+ lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
+ lcdc_write(0, LCD_CLK_RESET_REG);
+ }
}
static void lcd_calc_clk_divider(struct da8xx_fb_par *par)
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include <linux/kernel.h>
+#include <linux/module.h>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
const int maxdownscale = dss_feat_get_param_max(FEAT_PARAM_DOWNSCALE);
unsigned long fclk = 0;
- if ((ovl->caps & OMAP_DSS_OVL_CAP_SCALE) == 0) {
- if (width != out_width || height != out_height)
- return -EINVAL;
- else
- return 0;
- }
+ if (width == out_width && height == out_height)
+ return 0;
+
+ if ((ovl->caps & OMAP_DSS_OVL_CAP_SCALE) == 0)
+ return -EINVAL;
if (out_width < width / maxdownscale ||
out_width > width * 8)
unsigned long hdmi_get_pixel_clock(void)
{
/* HDMI Pixel Clock in Mhz */
- return hdmi.ip_data.cfg.timings.timings.pixel_clock * 10000;
+ return hdmi.ip_data.cfg.timings.timings.pixel_clock * 1000;
}
static void hdmi_compute_pll(struct omap_dss_device *dssdev, int phy,
#define M1200X720_R60_VSP POSITIVE
/* 1200x900@60 Sync Polarity (DCON) */
-#define M1200X900_R60_HSP NEGATIVE
-#define M1200X900_R60_VSP NEGATIVE
+#define M1200X900_R60_HSP POSITIVE
+#define M1200X900_R60_VSP POSITIVE
/* 1280x600@60 Sync Polarity (GTF Mode) */
#define M1280x600_R60_HSP NEGATIVE
config VIRTIO_MMIO
tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ depends on HAS_IOMEM && EXPERIMENTAL
select VIRTIO
select VIRTIO_RING
---help---
vring_transport_features(vdev);
for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
- writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SET);
+ writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
writel(vdev->features[i],
vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
}
return 0;
}
+static const char *vm_bus_name(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ return vm_dev->pdev->name;
+}
static struct virtio_config_ops virtio_mmio_config_ops = {
.get = vm_get,
.del_vqs = vm_del_vqs,
.get_features = vm_get_features,
.finalize_features = vm_finalize_features,
+ .bus_name = vm_bus_name,
};
iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
}
+/* wait for pending irq handlers */
+static void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ int i;
+
+ if (vp_dev->intx_enabled)
+ synchronize_irq(vp_dev->pci_dev->irq);
+
+ for (i = 0; i < vp_dev->msix_vectors; ++i)
+ synchronize_irq(vp_dev->msix_entries[i].vector);
+}
+
static void vp_reset(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
/* 0 status means a reset. */
iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush out the status write, and flush in device writes,
+ * including MSi-X interrupts, if any. */
+ ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush pending VQ/configuration callbacks. */
+ vp_synchronize_vectors(vdev);
}
/* the notify function used when creating a virt queue */
false, false);
}
+static const char *vp_bus_name(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ return pci_name(vp_dev->pci_dev);
+}
+
static struct virtio_config_ops virtio_pci_config_ops = {
.get = vp_get,
.set = vp_set,
.del_vqs = vp_del_vqs,
.get_features = vp_get_features,
.finalize_features = vp_finalize_features,
+ .bus_name = vp_bus_name,
};
static void virtio_pci_release_dev(struct device *_d)
To compile this driver as a module, choose M here: the
module will be called nuc900_wdt.
-config ADX_WATCHDOG
- tristate "Avionic Design Xanthos watchdog"
- depends on ARCH_PXA_ADX
- help
- Say Y here if you want support for the watchdog timer on Avionic
- Design Xanthos boards.
-
config TS72XX_WATCHDOG
tristate "TS-72XX SBC Watchdog"
depends on MACH_TS72XX
obj-$(CONFIG_COH901327_WATCHDOG) += coh901327_wdt.o
obj-$(CONFIG_STMP3XXX_WATCHDOG) += stmp3xxx_wdt.o
obj-$(CONFIG_NUC900_WATCHDOG) += nuc900_wdt.o
-obj-$(CONFIG_ADX_WATCHDOG) += adx_wdt.o
obj-$(CONFIG_TS72XX_WATCHDOG) += ts72xx_wdt.o
obj-$(CONFIG_IMX2_WDT) += imx2_wdt.o
+++ /dev/null
-/*
- * Copyright (C) 2008-2009 Avionic Design GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/io.h>
-#include <linux/miscdevice.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-#include <linux/watchdog.h>
-
-#define WATCHDOG_NAME "adx-wdt"
-
-/* register offsets */
-#define ADX_WDT_CONTROL 0x00
-#define ADX_WDT_CONTROL_ENABLE (1 << 0)
-#define ADX_WDT_CONTROL_nRESET (1 << 1)
-#define ADX_WDT_TIMEOUT 0x08
-
-static struct platform_device *adx_wdt_dev;
-static unsigned long driver_open;
-
-#define WDT_STATE_STOP 0
-#define WDT_STATE_START 1
-
-struct adx_wdt {
- void __iomem *base;
- unsigned long timeout;
- unsigned int state;
- unsigned int wake;
- spinlock_t lock;
-};
-
-static const struct watchdog_info adx_wdt_info = {
- .identity = "Avionic Design Xanthos Watchdog",
- .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
-};
-
-static void adx_wdt_start_locked(struct adx_wdt *wdt)
-{
- u32 ctrl;
-
- ctrl = readl(wdt->base + ADX_WDT_CONTROL);
- ctrl |= ADX_WDT_CONTROL_ENABLE;
- writel(ctrl, wdt->base + ADX_WDT_CONTROL);
- wdt->state = WDT_STATE_START;
-}
-
-static void adx_wdt_start(struct adx_wdt *wdt)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&wdt->lock, flags);
- adx_wdt_start_locked(wdt);
- spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_stop_locked(struct adx_wdt *wdt)
-{
- u32 ctrl;
-
- ctrl = readl(wdt->base + ADX_WDT_CONTROL);
- ctrl &= ~ADX_WDT_CONTROL_ENABLE;
- writel(ctrl, wdt->base + ADX_WDT_CONTROL);
- wdt->state = WDT_STATE_STOP;
-}
-
-static void adx_wdt_stop(struct adx_wdt *wdt)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&wdt->lock, flags);
- adx_wdt_stop_locked(wdt);
- spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_set_timeout(struct adx_wdt *wdt, unsigned long seconds)
-{
- unsigned long timeout = seconds * 1000;
- unsigned long flags;
- unsigned int state;
-
- spin_lock_irqsave(&wdt->lock, flags);
- state = wdt->state;
- adx_wdt_stop_locked(wdt);
- writel(timeout, wdt->base + ADX_WDT_TIMEOUT);
-
- if (state == WDT_STATE_START)
- adx_wdt_start_locked(wdt);
-
- wdt->timeout = timeout;
- spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_get_timeout(struct adx_wdt *wdt, unsigned long *seconds)
-{
- *seconds = wdt->timeout / 1000;
-}
-
-static void adx_wdt_keepalive(struct adx_wdt *wdt)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&wdt->lock, flags);
- writel(wdt->timeout, wdt->base + ADX_WDT_TIMEOUT);
- spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static int adx_wdt_open(struct inode *inode, struct file *file)
-{
- struct adx_wdt *wdt = platform_get_drvdata(adx_wdt_dev);
-
- if (test_and_set_bit(0, &driver_open))
- return -EBUSY;
-
- file->private_data = wdt;
- adx_wdt_set_timeout(wdt, 30);
- adx_wdt_start(wdt);
-
- return nonseekable_open(inode, file);
-}
-
-static int adx_wdt_release(struct inode *inode, struct file *file)
-{
- struct adx_wdt *wdt = file->private_data;
-
- adx_wdt_stop(wdt);
- clear_bit(0, &driver_open);
-
- return 0;
-}
-
-static long adx_wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- struct adx_wdt *wdt = file->private_data;
- void __user *argp = (void __user *)arg;
- unsigned long __user *p = argp;
- unsigned long seconds = 0;
- unsigned int options;
- long ret = -EINVAL;
-
- switch (cmd) {
- case WDIOC_GETSUPPORT:
- if (copy_to_user(argp, &adx_wdt_info, sizeof(adx_wdt_info)))
- return -EFAULT;
- else
- return 0;
-
- case WDIOC_GETSTATUS:
- case WDIOC_GETBOOTSTATUS:
- return put_user(0, p);
-
- case WDIOC_KEEPALIVE:
- adx_wdt_keepalive(wdt);
- return 0;
-
- case WDIOC_SETTIMEOUT:
- if (get_user(seconds, p))
- return -EFAULT;
-
- adx_wdt_set_timeout(wdt, seconds);
-
- /* fallthrough */
- case WDIOC_GETTIMEOUT:
- adx_wdt_get_timeout(wdt, &seconds);
- return put_user(seconds, p);
-
- case WDIOC_SETOPTIONS:
- if (copy_from_user(&options, argp, sizeof(options)))
- return -EFAULT;
-
- if (options & WDIOS_DISABLECARD) {
- adx_wdt_stop(wdt);
- ret = 0;
- }
-
- if (options & WDIOS_ENABLECARD) {
- adx_wdt_start(wdt);
- ret = 0;
- }
-
- return ret;
-
- default:
- break;
- }
-
- return -ENOTTY;
-}
-
-static ssize_t adx_wdt_write(struct file *file, const char __user *data,
- size_t len, loff_t *ppos)
-{
- struct adx_wdt *wdt = file->private_data;
-
- if (len)
- adx_wdt_keepalive(wdt);
-
- return len;
-}
-
-static const struct file_operations adx_wdt_fops = {
- .owner = THIS_MODULE,
- .llseek = no_llseek,
- .open = adx_wdt_open,
- .release = adx_wdt_release,
- .unlocked_ioctl = adx_wdt_ioctl,
- .write = adx_wdt_write,
-};
-
-static struct miscdevice adx_wdt_miscdev = {
- .minor = WATCHDOG_MINOR,
- .name = "watchdog",
- .fops = &adx_wdt_fops,
-};
-
-static int __devinit adx_wdt_probe(struct platform_device *pdev)
-{
- struct resource *res;
- struct adx_wdt *wdt;
- int ret = 0;
- u32 ctrl;
-
- wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
- if (!wdt) {
- dev_err(&pdev->dev, "cannot allocate WDT structure\n");
- return -ENOMEM;
- }
-
- spin_lock_init(&wdt->lock);
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res) {
- dev_err(&pdev->dev, "cannot obtain I/O memory region\n");
- return -ENXIO;
- }
-
- res = devm_request_mem_region(&pdev->dev, res->start,
- resource_size(res), res->name);
- if (!res) {
- dev_err(&pdev->dev, "cannot request I/O memory region\n");
- return -ENXIO;
- }
-
- wdt->base = devm_ioremap_nocache(&pdev->dev, res->start,
- resource_size(res));
- if (!wdt->base) {
- dev_err(&pdev->dev, "cannot remap I/O memory region\n");
- return -ENXIO;
- }
-
- /* disable watchdog and reboot on timeout */
- ctrl = readl(wdt->base + ADX_WDT_CONTROL);
- ctrl &= ~ADX_WDT_CONTROL_ENABLE;
- ctrl &= ~ADX_WDT_CONTROL_nRESET;
- writel(ctrl, wdt->base + ADX_WDT_CONTROL);
-
- platform_set_drvdata(pdev, wdt);
- adx_wdt_dev = pdev;
-
- ret = misc_register(&adx_wdt_miscdev);
- if (ret) {
- dev_err(&pdev->dev, "cannot register miscdev on minor %d "
- "(err=%d)\n", WATCHDOG_MINOR, ret);
- return ret;
- }
-
- return 0;
-}
-
-static int __devexit adx_wdt_remove(struct platform_device *pdev)
-{
- struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
- misc_deregister(&adx_wdt_miscdev);
- adx_wdt_stop(wdt);
- platform_set_drvdata(pdev, NULL);
-
- return 0;
-}
-
-static void adx_wdt_shutdown(struct platform_device *pdev)
-{
- struct adx_wdt *wdt = platform_get_drvdata(pdev);
- adx_wdt_stop(wdt);
-}
-
-#ifdef CONFIG_PM
-static int adx_wdt_suspend(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
- wdt->wake = (wdt->state == WDT_STATE_START) ? 1 : 0;
- adx_wdt_stop(wdt);
-
- return 0;
-}
-
-static int adx_wdt_resume(struct device *dev)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
- if (wdt->wake)
- adx_wdt_start(wdt);
-
- return 0;
-}
-
-static const struct dev_pm_ops adx_wdt_pm_ops = {
- .suspend = adx_wdt_suspend,
- .resume = adx_wdt_resume,
-};
-
-# define ADX_WDT_PM_OPS (&adx_wdt_pm_ops)
-#else
-# define ADX_WDT_PM_OPS NULL
-#endif
-
-static struct platform_driver adx_wdt_driver = {
- .probe = adx_wdt_probe,
- .remove = __devexit_p(adx_wdt_remove),
- .shutdown = adx_wdt_shutdown,
- .driver = {
- .name = WATCHDOG_NAME,
- .owner = THIS_MODULE,
- .pm = ADX_WDT_PM_OPS,
- },
-};
-
-static int __init adx_wdt_init(void)
-{
- return platform_driver_register(&adx_wdt_driver);
-}
-
-static void __exit adx_wdt_exit(void)
-{
- platform_driver_unregister(&adx_wdt_driver);
-}
-
-module_init(adx_wdt_init);
-module_exit(adx_wdt_exit);
-
-MODULE_DESCRIPTION("Avionic Design Xanthos Watchdog Driver");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
static void __iomem *virtbase;
static unsigned long coh901327_users;
static unsigned long boot_status;
-static u16 wdogenablestore;
-static u16 irqmaskstore;
static struct device *parent;
/*
}
#ifdef CONFIG_PM
+
+static u16 wdogenablestore;
+static u16 irqmaskstore;
+
static int coh901327_suspend(struct platform_device *pdev, pm_message_t state)
{
irqmaskstore = readw(virtbase + U300_WDOG_IMR) & 0x0001U;
cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE;
+ set_memory_x((unsigned long)bios32_entrypoint, (2 * PAGE_SIZE));
asminline_call(&cmn_regs, bios32_entrypoint);
if (cmn_regs.u1.ral != 0) {
if ((physical_bios_base + physical_bios_offset)) {
cru_rom_addr =
ioremap(cru_physical_address, cru_length);
- if (cru_rom_addr)
+ if (cru_rom_addr) {
+ set_memory_x((unsigned long)cru_rom_addr, cru_length);
retval = 0;
+ }
}
printk(KERN_DEBUG "hpwdt: CRU Base Address: 0x%lx\n",
"Watchdog cannot be stopped once started (default="
__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
-static int turn_SMI_watchdog_clear_off = 0;
+static int turn_SMI_watchdog_clear_off = 1;
module_param(turn_SMI_watchdog_clear_off, int, 0);
MODULE_PARM_DESC(turn_SMI_watchdog_clear_off,
- "Turn off SMI clearing watchdog (default=0)");
+ "Turn off SMI clearing watchdog (depends on TCO-version)(default=1)");
/*
* Some TCO specific functions
ret = -EIO;
goto out_unmap;
}
- if (turn_SMI_watchdog_clear_off) {
+ if (turn_SMI_watchdog_clear_off >= iTCO_wdt_private.iTCO_version) {
/* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */
val32 = inl(SMI_EN);
val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */
dev_info(dev, "watchdog %sactive, reset %sabled, irq %sabled\n",
(wtcon & S3C2410_WTCON_ENABLE) ? "" : "in",
- (wtcon & S3C2410_WTCON_RSTEN) ? "" : "dis",
- (wtcon & S3C2410_WTCON_INTEN) ? "" : "en");
+ (wtcon & S3C2410_WTCON_RSTEN) ? "en" : "dis",
+ (wtcon & S3C2410_WTCON_INTEN) ? "en" : "dis");
return 0;
return 0;
}
-static struct amba_id sp805_wdt_ids[] __initdata = {
+static struct amba_id sp805_wdt_ids[] = {
{
.id = 0x00141805,
.mask = 0x00ffffff,
if (wm831x_wdt_cfgs[i].time == timeout)
break;
if (i == ARRAY_SIZE(wm831x_wdt_cfgs))
- ret = -EINVAL;
+ return -EINVAL;
ret = wm831x_reg_unlock(wm831x);
if (ret == 0) {
* alloc_xenballooned_pages - get pages that have been ballooned out
* @nr_pages: Number of pages to get
* @pages: pages returned
- * @highmem: highmem or lowmem pages
+ * @highmem: allow highmem pages
* @return 0 on success, error otherwise
*/
int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
mutex_lock(&balloon_mutex);
while (pgno < nr_pages) {
page = balloon_retrieve(highmem);
- if (page && PageHighMem(page) == highmem) {
+ if (page && (highmem || !PageHighMem(page))) {
pages[pgno++] = page;
} else {
enum bp_state st;
/* Grant foreign access to the page. */
gref->gref_id = gnttab_grant_foreign_access(op->domid,
pfn_to_mfn(page_to_pfn(gref->page)), readonly);
- if (gref->gref_id < 0) {
+ if ((int)gref->gref_id < 0) {
rc = gref->gref_id;
goto undo;
}
goto out;
}
- gref_ids = kzalloc(sizeof(gref_ids[0]) * op.count, GFP_TEMPORARY);
+ gref_ids = kcalloc(op.count, sizeof(gref_ids[0]), GFP_TEMPORARY);
if (!gref_ids) {
rc = -ENOMEM;
goto out;
if (NULL == add)
return NULL;
- add->grants = kzalloc(sizeof(add->grants[0]) * count, GFP_KERNEL);
- add->map_ops = kzalloc(sizeof(add->map_ops[0]) * count, GFP_KERNEL);
- add->unmap_ops = kzalloc(sizeof(add->unmap_ops[0]) * count, GFP_KERNEL);
- add->kmap_ops = kzalloc(sizeof(add->kmap_ops[0]) * count, GFP_KERNEL);
- add->pages = kzalloc(sizeof(add->pages[0]) * count, GFP_KERNEL);
+ add->grants = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
+ add->map_ops = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
+ add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
+ add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+ add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
/*
* Get IO TLB memory from any location.
*/
- xen_io_tlb_start = alloc_bootmem(bytes);
+ xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
if (!xen_io_tlb_start) {
m = "Cannot allocate Xen-SWIOTLB buffer!\n";
goto error;
bytes,
xen_io_tlb_nslabs);
if (rc) {
- free_bootmem(__pa(xen_io_tlb_start), bytes);
+ free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
m = "Failed to get contiguous memory for DMA from Xen!\n"\
"You either: don't have the permissions, do not have"\
" enough free memory under 4GB, or the hypervisor memory"\
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <asm/xen/hypervisor.h>
+#include <asm/xen/page.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/events.h>
int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
{
struct gnttab_map_grant_ref op = {
- .flags = GNTMAP_host_map,
+ .flags = GNTMAP_host_map | GNTMAP_contains_pte,
.ref = gnt_ref,
.dom = dev->otherend_id,
};
struct vm_struct *area;
+ pte_t *pte;
*vaddr = NULL;
- area = alloc_vm_area(PAGE_SIZE);
+ area = alloc_vm_area(PAGE_SIZE, &pte);
if (!area)
return -ENOMEM;
- op.host_addr = (unsigned long)area->addr;
+ op.host_addr = arbitrary_virt_to_machine(pte).maddr;
if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
BUG();
struct gnttab_unmap_grant_ref op = {
.host_addr = (unsigned long)vaddr,
};
+ unsigned int level;
/* It'd be nice if linux/vmalloc.h provided a find_vm_area(void *addr)
* method so that we don't have to muck with vmalloc internals here.
}
op.handle = (grant_handle_t)area->phys_addr;
+ op.host_addr = arbitrary_virt_to_machine(
+ lookup_address((unsigned long)vaddr, &level)).maddr;
if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
BUG();
return NULL;
}
-static void xs_reset_watches(void)
-{
- int err;
-
- err = xs_error(xs_single(XBT_NIL, XS_RESET_WATCHES, "", NULL));
- if (err && err != -EEXIST)
- printk(KERN_WARNING "xs_reset_watches failed: %d\n", err);
-}
-
/* Register callback to watch this node. */
int register_xenbus_watch(struct xenbus_watch *watch)
{
if (IS_ERR(task))
return PTR_ERR(task);
- /* shutdown watches for kexec boot */
- if (xen_hvm_domain())
- xs_reset_watches();
-
return 0;
}
This directory is _NOT_ for adding arbitrary new firmware images. The
place to add those is the separate linux-firmware repository:
- git://git.kernel.org/pub/scm/linux/kernel/git/dwmw2/linux-firmware.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git
That repository contains all these firmware images which have been
extracted from older drivers, as well various new firmware images which
To submit firmware to that repository, please send either a git binary
diff or preferably a git pull request to:
David Woodhouse <dwmw2@infradead.org>
+ Ben Hutchings <ben@decadent.org.uk>
Your commit should include an update to the WHENCE file clearly
identifying the licence under which the firmware is available, and
* RETURNS:
* Pointer to new bio on success, NULL on failure.
*/
-struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
+struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
* %__GFP_WAIT, the allocation is guaranteed to succeed.
*
**/
-struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
+struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
struct bio *bio;
kfree(bmd);
}
-static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
+static struct bio_map_data *bio_alloc_map_data(int nr_segs,
+ unsigned int iov_count,
gfp_t gfp_mask)
{
struct bio_map_data *bmd;
int idle;
};
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
/*
* btrfs_start_workers uses kthread_run, which can block waiting for memory
* for a very long time. It will actually throttle on page writeback,
{
struct worker_start *start;
start = container_of(work, struct worker_start, work);
- btrfs_start_workers(start->queue, 1);
+ __btrfs_start_workers(start->queue);
kfree(start);
}
-static int start_new_worker(struct btrfs_workers *queue)
-{
- struct worker_start *start;
- int ret;
-
- start = kzalloc(sizeof(*start), GFP_NOFS);
- if (!start)
- return -ENOMEM;
-
- start->work.func = start_new_worker_func;
- start->queue = queue;
- ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
- if (ret)
- kfree(start);
- return ret;
-}
-
/*
* helper function to move a thread onto the idle list after it
* has finished some requests.
static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
{
struct btrfs_workers *workers = worker->workers;
+ struct worker_start *start;
unsigned long flags;
rmb();
if (!workers->atomic_start_pending)
return;
+ start = kzalloc(sizeof(*start), GFP_NOFS);
+ if (!start)
+ return;
+
+ start->work.func = start_new_worker_func;
+ start->queue = workers;
+
spin_lock_irqsave(&workers->lock, flags);
if (!workers->atomic_start_pending)
goto out;
workers->num_workers_starting += 1;
spin_unlock_irqrestore(&workers->lock, flags);
- start_new_worker(workers);
+ btrfs_queue_worker(workers->atomic_worker_start, &start->work);
return;
out:
+ kfree(start);
spin_unlock_irqrestore(&workers->lock, flags);
}
run_ordered_completions(worker->workers, work);
check_pending_worker_creates(worker);
-
+ cond_resched();
}
spin_lock_irq(&worker->lock);
* starts new worker threads. This does not enforce the max worker
* count in case you need to temporarily go past it.
*/
-static int __btrfs_start_workers(struct btrfs_workers *workers,
- int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
{
struct btrfs_worker_thread *worker;
int ret = 0;
- int i;
- for (i = 0; i < num_workers; i++) {
- worker = kzalloc(sizeof(*worker), GFP_NOFS);
- if (!worker) {
- ret = -ENOMEM;
- goto fail;
- }
+ worker = kzalloc(sizeof(*worker), GFP_NOFS);
+ if (!worker) {
+ ret = -ENOMEM;
+ goto fail;
+ }
- INIT_LIST_HEAD(&worker->pending);
- INIT_LIST_HEAD(&worker->prio_pending);
- INIT_LIST_HEAD(&worker->worker_list);
- spin_lock_init(&worker->lock);
-
- atomic_set(&worker->num_pending, 0);
- atomic_set(&worker->refs, 1);
- worker->workers = workers;
- worker->task = kthread_run(worker_loop, worker,
- "btrfs-%s-%d", workers->name,
- workers->num_workers + i);
- if (IS_ERR(worker->task)) {
- ret = PTR_ERR(worker->task);
- kfree(worker);
- goto fail;
- }
- spin_lock_irq(&workers->lock);
- list_add_tail(&worker->worker_list, &workers->idle_list);
- worker->idle = 1;
- workers->num_workers++;
- workers->num_workers_starting--;
- WARN_ON(workers->num_workers_starting < 0);
- spin_unlock_irq(&workers->lock);
+ INIT_LIST_HEAD(&worker->pending);
+ INIT_LIST_HEAD(&worker->prio_pending);
+ INIT_LIST_HEAD(&worker->worker_list);
+ spin_lock_init(&worker->lock);
+
+ atomic_set(&worker->num_pending, 0);
+ atomic_set(&worker->refs, 1);
+ worker->workers = workers;
+ worker->task = kthread_run(worker_loop, worker,
+ "btrfs-%s-%d", workers->name,
+ workers->num_workers + 1);
+ if (IS_ERR(worker->task)) {
+ ret = PTR_ERR(worker->task);
+ kfree(worker);
+ goto fail;
}
+ spin_lock_irq(&workers->lock);
+ list_add_tail(&worker->worker_list, &workers->idle_list);
+ worker->idle = 1;
+ workers->num_workers++;
+ workers->num_workers_starting--;
+ WARN_ON(workers->num_workers_starting < 0);
+ spin_unlock_irq(&workers->lock);
+
return 0;
fail:
- btrfs_stop_workers(workers);
+ spin_lock_irq(&workers->lock);
+ workers->num_workers_starting--;
+ spin_unlock_irq(&workers->lock);
return ret;
}
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
{
spin_lock_irq(&workers->lock);
- workers->num_workers_starting += num_workers;
+ workers->num_workers_starting++;
spin_unlock_irq(&workers->lock);
- return __btrfs_start_workers(workers, num_workers);
+ return __btrfs_start_workers(workers);
}
/*
struct btrfs_worker_thread *worker;
unsigned long flags;
struct list_head *fallback;
+ int ret;
-again:
spin_lock_irqsave(&workers->lock, flags);
+again:
worker = next_worker(workers);
if (!worker) {
workers->num_workers_starting++;
spin_unlock_irqrestore(&workers->lock, flags);
/* we're below the limit, start another worker */
- __btrfs_start_workers(workers, 1);
+ ret = __btrfs_start_workers(workers);
+ spin_lock_irqsave(&workers->lock, flags);
+ if (ret)
+ goto fallback;
goto again;
}
}
/*
* places a struct btrfs_work into the pending queue of one of the kthreads
*/
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
{
struct btrfs_worker_thread *worker;
unsigned long flags;
/* don't requeue something already on a list */
if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
- goto out;
+ return;
worker = find_worker(workers);
if (workers->ordered) {
if (wake)
wake_up_process(worker->task);
spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
- return 0;
}
char *name;
};
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
int btrfs_stop_workers(struct btrfs_workers *workers);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_starter);
return PTR_ERR(fspath);
if (fspath > fspath_min) {
- ipath->fspath->val[i] = (u64)fspath;
+ ipath->fspath->val[i] = (u64)(unsigned long)fspath;
++ipath->fspath->elem_cnt;
ipath->fspath->bytes_left = fspath - fspath_min;
} else {
struct btrfs_root *root,
struct extent_buffer *buf)
{
+ /* ensure we can see the force_cow */
+ smp_rmb();
+
+ /*
+ * We do not need to cow a block if
+ * 1) this block is not created or changed in this transaction;
+ * 2) this block does not belong to TREE_RELOC tree;
+ * 3) the root is not forced COW.
+ *
+ * What is forced COW:
+ * when we create snapshot during commiting the transaction,
+ * after we've finished coping src root, we must COW the shared
+ * block to ensure the metadata consistency.
+ */
if (btrfs_header_generation(buf) == trans->transid &&
!btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
!(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
- btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+ btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
+ !root->force_cow)
return 0;
return 1;
}
enum btrfs_caching_type {
BTRFS_CACHE_NO = 0,
BTRFS_CACHE_STARTED = 1,
- BTRFS_CACHE_FINISHED = 2,
+ BTRFS_CACHE_FAST = 2,
+ BTRFS_CACHE_FINISHED = 3,
};
enum btrfs_disk_cache_state {
* for stat. It may be used for more later
*/
dev_t anon_dev;
+
+ int force_cow;
};
struct btrfs_ioctl_defrag_range_args {
int btrfs_block_rsv_refill(struct btrfs_root *root,
struct btrfs_block_rsv *block_rsv,
u64 min_reserved);
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv,
u64 num_bytes);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode, int flags);
+int btrfs_dirty_inode(struct inode *inode);
+int btrfs_update_time(struct file *file);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
* Now if src_rsv == delalloc_block_rsv we'll let it just steal since
* we're accounted for.
*/
- if (!trans->bytes_reserved &&
- src_rsv != &root->fs_info->delalloc_block_rsv) {
+ if (!src_rsv || (!trans->bytes_reserved &&
+ src_rsv != &root->fs_info->delalloc_block_rsv)) {
ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
/*
* Since we're under a transaction reserve_metadata_bytes could
static int btree_io_failed_hook(struct bio *failed_bio,
struct page *page, u64 start, u64 end,
- u64 mirror_num, struct extent_state *state)
+ int mirror_num, struct extent_state *state)
{
struct extent_io_tree *tree;
unsigned long len;
fs_info->endio_meta_write_workers.idle_thresh = 2;
fs_info->readahead_workers.idle_thresh = 2;
- btrfs_start_workers(&fs_info->workers, 1);
- btrfs_start_workers(&fs_info->generic_worker, 1);
- btrfs_start_workers(&fs_info->submit_workers, 1);
- btrfs_start_workers(&fs_info->delalloc_workers, 1);
- btrfs_start_workers(&fs_info->fixup_workers, 1);
- btrfs_start_workers(&fs_info->endio_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
- btrfs_start_workers(&fs_info->delayed_workers, 1);
- btrfs_start_workers(&fs_info->caching_workers, 1);
- btrfs_start_workers(&fs_info->readahead_workers, 1);
+ /*
+ * btrfs_start_workers can really only fail because of ENOMEM so just
+ * return -ENOMEM if any of these fail.
+ */
+ ret = btrfs_start_workers(&fs_info->workers);
+ ret |= btrfs_start_workers(&fs_info->generic_worker);
+ ret |= btrfs_start_workers(&fs_info->submit_workers);
+ ret |= btrfs_start_workers(&fs_info->delalloc_workers);
+ ret |= btrfs_start_workers(&fs_info->fixup_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
+ ret |= btrfs_start_workers(&fs_info->delayed_workers);
+ ret |= btrfs_start_workers(&fs_info->caching_workers);
+ ret |= btrfs_start_workers(&fs_info->readahead_workers);
+ if (ret) {
+ ret = -ENOMEM;
+ goto fail_sb_buffer;
+ }
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
int errors = 0;
u32 crc;
u64 bytenr;
- int last_barrier = 0;
if (max_mirrors == 0)
max_mirrors = BTRFS_SUPER_MIRROR_MAX;
- /* make sure only the last submit_bh does a barrier */
- if (do_barriers) {
- for (i = 0; i < max_mirrors; i++) {
- bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >=
- device->total_bytes)
- break;
- last_barrier = i;
- }
- }
-
for (i = 0; i < max_mirrors; i++) {
bytenr = btrfs_sb_offset(i);
if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
bh->b_end_io = btrfs_end_buffer_write_sync;
}
- if (i == last_barrier && do_barriers)
- ret = submit_bh(WRITE_FLUSH_FUA, bh);
- else
- ret = submit_bh(WRITE_SYNC, bh);
-
+ /*
+ * we fua the first super. The others we allow
+ * to go down lazy.
+ */
+ ret = submit_bh(WRITE_FUA, bh);
if (ret)
errors++;
}
return errors < i ? 0 : -1;
}
+/*
+ * endio for the write_dev_flush, this will wake anyone waiting
+ * for the barrier when it is done
+ */
+static void btrfs_end_empty_barrier(struct bio *bio, int err)
+{
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ }
+ if (bio->bi_private)
+ complete(bio->bi_private);
+ bio_put(bio);
+}
+
+/*
+ * trigger flushes for one the devices. If you pass wait == 0, the flushes are
+ * sent down. With wait == 1, it waits for the previous flush.
+ *
+ * any device where the flush fails with eopnotsupp are flagged as not-barrier
+ * capable
+ */
+static int write_dev_flush(struct btrfs_device *device, int wait)
+{
+ struct bio *bio;
+ int ret = 0;
+
+ if (device->nobarriers)
+ return 0;
+
+ if (wait) {
+ bio = device->flush_bio;
+ if (!bio)
+ return 0;
+
+ wait_for_completion(&device->flush_wait);
+
+ if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
+ printk("btrfs: disabling barriers on dev %s\n",
+ device->name);
+ device->nobarriers = 1;
+ }
+ if (!bio_flagged(bio, BIO_UPTODATE)) {
+ ret = -EIO;
+ }
+
+ /* drop the reference from the wait == 0 run */
+ bio_put(bio);
+ device->flush_bio = NULL;
+
+ return ret;
+ }
+
+ /*
+ * one reference for us, and we leave it for the
+ * caller
+ */
+ device->flush_bio = NULL;;
+ bio = bio_alloc(GFP_NOFS, 0);
+ if (!bio)
+ return -ENOMEM;
+
+ bio->bi_end_io = btrfs_end_empty_barrier;
+ bio->bi_bdev = device->bdev;
+ init_completion(&device->flush_wait);
+ bio->bi_private = &device->flush_wait;
+ device->flush_bio = bio;
+
+ bio_get(bio);
+ submit_bio(WRITE_FLUSH, bio);
+
+ return 0;
+}
+
+/*
+ * send an empty flush down to each device in parallel,
+ * then wait for them
+ */
+static int barrier_all_devices(struct btrfs_fs_info *info)
+{
+ struct list_head *head;
+ struct btrfs_device *dev;
+ int errors = 0;
+ int ret;
+
+ /* send down all the barriers */
+ head = &info->fs_devices->devices;
+ list_for_each_entry_rcu(dev, head, dev_list) {
+ if (!dev->bdev) {
+ errors++;
+ continue;
+ }
+ if (!dev->in_fs_metadata || !dev->writeable)
+ continue;
+
+ ret = write_dev_flush(dev, 0);
+ if (ret)
+ errors++;
+ }
+
+ /* wait for all the barriers */
+ list_for_each_entry_rcu(dev, head, dev_list) {
+ if (!dev->bdev) {
+ errors++;
+ continue;
+ }
+ if (!dev->in_fs_metadata || !dev->writeable)
+ continue;
+
+ ret = write_dev_flush(dev, 1);
+ if (ret)
+ errors++;
+ }
+ if (errors)
+ return -EIO;
+ return 0;
+}
+
int write_all_supers(struct btrfs_root *root, int max_mirrors)
{
struct list_head *head;
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
head = &root->fs_info->fs_devices->devices;
+
+ if (do_barriers)
+ barrier_all_devices(root->fs_info);
+
list_for_each_entry_rcu(dev, head, dev_list) {
if (!dev->bdev) {
total_errors++;
struct btrfs_root *root,
int load_cache_only)
{
+ DEFINE_WAIT(wait);
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_caching_control *caching_ctl;
int ret = 0;
- smp_mb();
- if (cache->cached != BTRFS_CACHE_NO)
+ caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
+ BUG_ON(!caching_ctl);
+
+ INIT_LIST_HEAD(&caching_ctl->list);
+ mutex_init(&caching_ctl->mutex);
+ init_waitqueue_head(&caching_ctl->wait);
+ caching_ctl->block_group = cache;
+ caching_ctl->progress = cache->key.objectid;
+ atomic_set(&caching_ctl->count, 1);
+ caching_ctl->work.func = caching_thread;
+
+ spin_lock(&cache->lock);
+ /*
+ * This should be a rare occasion, but this could happen I think in the
+ * case where one thread starts to load the space cache info, and then
+ * some other thread starts a transaction commit which tries to do an
+ * allocation while the other thread is still loading the space cache
+ * info. The previous loop should have kept us from choosing this block
+ * group, but if we've moved to the state where we will wait on caching
+ * block groups we need to first check if we're doing a fast load here,
+ * so we can wait for it to finish, otherwise we could end up allocating
+ * from a block group who's cache gets evicted for one reason or
+ * another.
+ */
+ while (cache->cached == BTRFS_CACHE_FAST) {
+ struct btrfs_caching_control *ctl;
+
+ ctl = cache->caching_ctl;
+ atomic_inc(&ctl->count);
+ prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&cache->lock);
+
+ schedule();
+
+ finish_wait(&ctl->wait, &wait);
+ put_caching_control(ctl);
+ spin_lock(&cache->lock);
+ }
+
+ if (cache->cached != BTRFS_CACHE_NO) {
+ spin_unlock(&cache->lock);
+ kfree(caching_ctl);
return 0;
+ }
+ WARN_ON(cache->caching_ctl);
+ cache->caching_ctl = caching_ctl;
+ cache->cached = BTRFS_CACHE_FAST;
+ spin_unlock(&cache->lock);
/*
* We can't do the read from on-disk cache during a commit since we need
if (trans && (!trans->transaction->in_commit) &&
(root && root != root->fs_info->tree_root) &&
btrfs_test_opt(root, SPACE_CACHE)) {
- spin_lock(&cache->lock);
- if (cache->cached != BTRFS_CACHE_NO) {
- spin_unlock(&cache->lock);
- return 0;
- }
- cache->cached = BTRFS_CACHE_STARTED;
- spin_unlock(&cache->lock);
-
ret = load_free_space_cache(fs_info, cache);
spin_lock(&cache->lock);
if (ret == 1) {
+ cache->caching_ctl = NULL;
cache->cached = BTRFS_CACHE_FINISHED;
cache->last_byte_to_unpin = (u64)-1;
} else {
- cache->cached = BTRFS_CACHE_NO;
+ if (load_cache_only) {
+ cache->caching_ctl = NULL;
+ cache->cached = BTRFS_CACHE_NO;
+ } else {
+ cache->cached = BTRFS_CACHE_STARTED;
+ }
}
spin_unlock(&cache->lock);
+ wake_up(&caching_ctl->wait);
if (ret == 1) {
+ put_caching_control(caching_ctl);
free_excluded_extents(fs_info->extent_root, cache);
return 0;
}
+ } else {
+ /*
+ * We are not going to do the fast caching, set cached to the
+ * appropriate value and wakeup any waiters.
+ */
+ spin_lock(&cache->lock);
+ if (load_cache_only) {
+ cache->caching_ctl = NULL;
+ cache->cached = BTRFS_CACHE_NO;
+ } else {
+ cache->cached = BTRFS_CACHE_STARTED;
+ }
+ spin_unlock(&cache->lock);
+ wake_up(&caching_ctl->wait);
}
- if (load_cache_only)
- return 0;
-
- caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
- BUG_ON(!caching_ctl);
-
- INIT_LIST_HEAD(&caching_ctl->list);
- mutex_init(&caching_ctl->mutex);
- init_waitqueue_head(&caching_ctl->wait);
- caching_ctl->block_group = cache;
- caching_ctl->progress = cache->key.objectid;
- /* one for caching kthread, one for caching block group list */
- atomic_set(&caching_ctl->count, 2);
- caching_ctl->work.func = caching_thread;
-
- spin_lock(&cache->lock);
- if (cache->cached != BTRFS_CACHE_NO) {
- spin_unlock(&cache->lock);
- kfree(caching_ctl);
+ if (load_cache_only) {
+ put_caching_control(caching_ctl);
return 0;
}
- cache->caching_ctl = caching_ctl;
- cache->cached = BTRFS_CACHE_STARTED;
- spin_unlock(&cache->lock);
down_write(&fs_info->extent_commit_sem);
+ atomic_inc(&caching_ctl->count);
list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
up_write(&fs_info->extent_commit_sem);
btrfs_release_path(path);
out:
spin_lock(&block_group->lock);
- if (!ret)
+ if (!ret && dcs == BTRFS_DC_SETUP)
block_group->cache_generation = trans->transid;
block_group->disk_cache_state = dcs;
spin_unlock(&block_group->lock);
return ret;
}
-int btrfs_block_rsv_refill(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv,
- u64 min_reserved)
+static inline int __btrfs_block_rsv_refill(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved, int flush)
{
u64 num_bytes = 0;
int ret = -ENOSPC;
if (!ret)
return 0;
- ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
+ ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
if (!ret) {
block_rsv_add_bytes(block_rsv, num_bytes, 0);
return 0;
return ret;
}
+int btrfs_block_rsv_refill(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved)
+{
+ return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1);
+}
+
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved)
+{
+ return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0);
+}
+
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv,
u64 num_bytes)
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
u64 to_reserve = 0;
+ u64 csum_bytes;
unsigned nr_extents = 0;
+ int extra_reserve = 0;
int flush = 1;
int ret;
+ /* Need to be holding the i_mutex here if we aren't free space cache */
if (btrfs_is_free_space_inode(root, inode))
flush = 0;
+ else
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
if (flush && btrfs_transaction_in_commit(root->fs_info))
schedule_timeout(1);
BTRFS_I(inode)->outstanding_extents++;
if (BTRFS_I(inode)->outstanding_extents >
- BTRFS_I(inode)->reserved_extents) {
+ BTRFS_I(inode)->reserved_extents)
nr_extents = BTRFS_I(inode)->outstanding_extents -
BTRFS_I(inode)->reserved_extents;
- BTRFS_I(inode)->reserved_extents += nr_extents;
- }
/*
* Add an item to reserve for updating the inode when we complete the
*/
if (!BTRFS_I(inode)->delalloc_meta_reserved) {
nr_extents++;
- BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ extra_reserve = 1;
}
to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+ csum_bytes = BTRFS_I(inode)->csum_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
spin_lock(&BTRFS_I(inode)->lock);
dropped = drop_outstanding_extent(inode);
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
/*
- * Somebody could have come in and twiddled with the
- * reservation, so if we have to free more than we would have
- * reserved from this reservation go ahead and release those
- * bytes.
+ * If the inodes csum_bytes is the same as the original
+ * csum_bytes then we know we haven't raced with any free()ers
+ * so we can just reduce our inodes csum bytes and carry on.
+ * Otherwise we have to do the normal free thing to account for
+ * the case that the free side didn't free up its reserve
+ * because of this outstanding reservation.
*/
- to_free -= to_reserve;
+ if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+ calc_csum_metadata_size(inode, num_bytes, 0);
+ else
+ to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+ spin_unlock(&BTRFS_I(inode)->lock);
+ if (dropped)
+ to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
if (to_free)
btrfs_block_rsv_release(root, block_rsv, to_free);
return ret;
}
+ spin_lock(&BTRFS_I(inode)->lock);
+ if (extra_reserve) {
+ BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ nr_extents--;
+ }
+ BTRFS_I(inode)->reserved_extents += nr_extents;
+ spin_unlock(&BTRFS_I(inode)->lock);
+
block_rsv_add_bytes(block_rsv, to_reserve, 1);
return 0;
struct btrfs_root *root = orig_root->fs_info->extent_root;
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
+ struct btrfs_block_group_cache *used_block_group;
int empty_cluster = 2 * 1024 * 1024;
int allowed_chunk_alloc = 0;
int done_chunk_alloc = 0;
struct btrfs_space_info *space_info;
- int last_ptr_loop = 0;
int loop = 0;
int index = 0;
int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
ideal_cache:
block_group = btrfs_lookup_block_group(root->fs_info,
search_start);
+ used_block_group = block_group;
/*
* we don't want to use the block group if it doesn't match our
* allocation bits, or if its not cached.
u64 offset;
int cached;
+ used_block_group = block_group;
btrfs_get_block_group(block_group);
search_start = block_group->key.objectid;
}
have_block_group:
- if (unlikely(block_group->cached == BTRFS_CACHE_NO)) {
+ cached = block_group_cache_done(block_group);
+ if (unlikely(!cached)) {
u64 free_percent;
+ found_uncached_bg = true;
ret = cache_block_group(block_group, trans,
orig_root, 1);
if (block_group->cached == BTRFS_CACHE_FINISHED)
- goto have_block_group;
+ goto alloc;
free_percent = btrfs_block_group_used(&block_group->item);
free_percent *= 100;
orig_root, 0);
BUG_ON(ret);
}
- found_uncached_bg = true;
/*
* If loop is set for cached only, try the next block
goto loop;
}
- cached = block_group_cache_done(block_group);
- if (unlikely(!cached))
- found_uncached_bg = true;
-
+alloc:
if (unlikely(block_group->ro))
goto loop;
spin_lock(&block_group->free_space_ctl->tree_lock);
if (cached &&
block_group->free_space_ctl->free_space <
- num_bytes + empty_size) {
+ num_bytes + empty_cluster + empty_size) {
spin_unlock(&block_group->free_space_ctl->tree_lock);
goto loop;
}
spin_unlock(&block_group->free_space_ctl->tree_lock);
/*
- * Ok we want to try and use the cluster allocator, so lets look
- * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
- * have tried the cluster allocator plenty of times at this
- * point and not have found anything, so we are likely way too
- * fragmented for the clustering stuff to find anything, so lets
- * just skip it and let the allocator find whatever block it can
- * find
+ * Ok we want to try and use the cluster allocator, so
+ * lets look there
*/
- if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+ if (last_ptr) {
/*
* the refill lock keeps out other
* people trying to start a new cluster
*/
spin_lock(&last_ptr->refill_lock);
- if (last_ptr->block_group &&
- (last_ptr->block_group->ro ||
- !block_group_bits(last_ptr->block_group, data))) {
- offset = 0;
+ used_block_group = last_ptr->block_group;
+ if (used_block_group != block_group &&
+ (!used_block_group ||
+ used_block_group->ro ||
+ !block_group_bits(used_block_group, data))) {
+ used_block_group = block_group;
goto refill_cluster;
}
- offset = btrfs_alloc_from_cluster(block_group, last_ptr,
- num_bytes, search_start);
+ if (used_block_group != block_group)
+ btrfs_get_block_group(used_block_group);
+
+ offset = btrfs_alloc_from_cluster(used_block_group,
+ last_ptr, num_bytes, used_block_group->key.objectid);
if (offset) {
/* we have a block, we're done */
spin_unlock(&last_ptr->refill_lock);
goto checks;
}
- spin_lock(&last_ptr->lock);
- /*
- * whoops, this cluster doesn't actually point to
- * this block group. Get a ref on the block
- * group is does point to and try again
- */
- if (!last_ptr_loop && last_ptr->block_group &&
- last_ptr->block_group != block_group &&
- index <=
- get_block_group_index(last_ptr->block_group)) {
-
- btrfs_put_block_group(block_group);
- block_group = last_ptr->block_group;
- btrfs_get_block_group(block_group);
- spin_unlock(&last_ptr->lock);
- spin_unlock(&last_ptr->refill_lock);
-
- last_ptr_loop = 1;
- search_start = block_group->key.objectid;
- /*
- * we know this block group is properly
- * in the list because
- * btrfs_remove_block_group, drops the
- * cluster before it removes the block
- * group from the list
- */
- goto have_block_group;
+ WARN_ON(last_ptr->block_group != used_block_group);
+ if (used_block_group != block_group) {
+ btrfs_put_block_group(used_block_group);
+ used_block_group = block_group;
}
- spin_unlock(&last_ptr->lock);
refill_cluster:
+ BUG_ON(used_block_group != block_group);
+ /* If we are on LOOP_NO_EMPTY_SIZE, we can't
+ * set up a new clusters, so lets just skip it
+ * and let the allocator find whatever block
+ * it can find. If we reach this point, we
+ * will have tried the cluster allocator
+ * plenty of times and not have found
+ * anything, so we are likely way too
+ * fragmented for the clustering stuff to find
+ * anything. */
+ if (loop >= LOOP_NO_EMPTY_SIZE) {
+ spin_unlock(&last_ptr->refill_lock);
+ goto unclustered_alloc;
+ }
+
/*
* this cluster didn't work out, free it and
* start over
*/
btrfs_return_cluster_to_free_space(NULL, last_ptr);
- last_ptr_loop = 0;
-
/* allocate a cluster in this block group */
ret = btrfs_find_space_cluster(trans, root,
block_group, last_ptr,
- offset, num_bytes,
+ search_start, num_bytes,
empty_cluster + empty_size);
if (ret == 0) {
/*
goto loop;
}
+unclustered_alloc:
offset = btrfs_find_space_for_alloc(block_group, search_start,
num_bytes, empty_size);
/*
search_start = stripe_align(root, offset);
/* move on to the next group */
if (search_start + num_bytes >= search_end) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
/* move on to the next group */
if (search_start + num_bytes >
- block_group->key.objectid + block_group->key.offset) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ used_block_group->key.objectid + used_block_group->key.offset) {
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
ins->offset = num_bytes;
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+ ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
alloc_type);
if (ret == -EAGAIN) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
ins->offset = num_bytes;
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
BUG_ON(index != get_block_group_index(block_group));
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
}
up_read(&space_info->groups_sem);
node = tree_search(tree, start);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = insert_state(tree, prealloc, start, end, &bits);
prealloc = NULL;
BUG_ON(err == -EEXIST);
*/
if (state->start < start) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, start);
BUG_ON(err == -EEXIST);
prealloc = NULL;
this_end = last_start - 1;
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
/*
* Avoid to free 'prealloc' if it can be merged with
*/
if (state->start <= end && state->end > end) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, end + 1);
BUG_ON(err == -EEXIST);
clean_io_failure(start, page);
}
if (!uptodate) {
- u64 failed_mirror;
- failed_mirror = (u64)bio->bi_bdev;
- if (tree->ops && tree->ops->readpage_io_failed_hook)
- ret = tree->ops->readpage_io_failed_hook(
- bio, page, start, end,
- failed_mirror, state);
- else
- ret = bio_readpage_error(bio, page, start, end,
- failed_mirror, NULL);
+ int failed_mirror;
+ failed_mirror = (int)(unsigned long)bio->bi_bdev;
+ /*
+ * The generic bio_readpage_error handles errors the
+ * following way: If possible, new read requests are
+ * created and submitted and will end up in
+ * end_bio_extent_readpage as well (if we're lucky, not
+ * in the !uptodate case). In that case it returns 0 and
+ * we just go on with the next page in our bio. If it
+ * can't handle the error it will return -EIO and we
+ * remain responsible for that page.
+ */
+ ret = bio_readpage_error(bio, page, start, end,
+ failed_mirror, NULL);
if (ret == 0) {
+error_handled:
uptodate =
test_bit(BIO_UPTODATE, &bio->bi_flags);
if (err)
uncache_state(&cached);
continue;
}
+ if (tree->ops && tree->ops->readpage_io_failed_hook) {
+ ret = tree->ops->readpage_io_failed_hook(
+ bio, page, start, end,
+ failed_mirror, state);
+ if (ret == 0)
+ goto error_handled;
+ }
}
if (uptodate) {
return -ENOMEM;
path->leave_spinning = 1;
+ start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
+ len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+
/*
* lookup the last file extent. We're not using i_size here
* because there might be preallocation past i_size
lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
&cached_state, GFP_NOFS);
- em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ em = get_extent_skip_holes(inode, start, last_for_get_extent,
get_extent);
if (!em)
goto out;
unsigned long bio_flags);
int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
int (*readpage_io_failed_hook)(struct bio *bio, struct page *page,
- u64 start, u64 end, u64 failed_mirror,
+ u64 start, u64 end, int failed_mirror,
struct extent_state *state);
int (*writepage_io_failed_hook)(struct bio *bio, struct page *page,
u64 start, u64 end,
nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
+ nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+ nrptrs = max(nrptrs, 8);
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
if (!pages)
return -ENOMEM;
goto out;
}
- file_update_time(file);
+ err = btrfs_update_time(file);
+ if (err) {
+ mutex_unlock(&inode->i_mutex);
+ goto out;
+ }
BTRFS_I(inode)->sequence++;
start_pos = round_down(pos, root->sectorsize);
}
}
+ for (i = 0; i < io_ctl->num_pages; i++) {
+ clear_page_dirty_for_io(io_ctl->pages[i]);
+ set_page_extent_mapped(io_ctl->pages[i]);
+ }
+
return 0;
}
{
info->offset = offset_to_bitmap(ctl, offset);
info->bytes = 0;
+ INIT_LIST_HEAD(&info->list);
link_free_space(ctl, info);
ctl->total_bitmaps++;
info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!info) {
- WARN_ON(1);
+ /* the tree logging code might be calling us before we
+ * have fully loaded the free space rbtree for this
+ * block group. So it is possible the entry won't
+ * be in the rbtree yet at all. The caching code
+ * will make sure not to put it in the rbtree if
+ * the logging code has pinned it.
+ */
goto out_lock;
}
}
if (!found) {
start = i;
+ cluster->max_size = 0;
found = true;
}
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
- struct rb_node *node;
int ret = -ENOSPC;
+ u64 bitmap_offset = offset_to_bitmap(ctl, offset);
if (ctl->total_bitmaps == 0)
return -ENOSPC;
/*
- * First check our cached list of bitmaps and see if there is an entry
- * here that will work.
+ * The bitmap that covers offset won't be in the list unless offset
+ * is just its start offset.
*/
+ entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
+ if (entry->offset != bitmap_offset) {
+ entry = tree_search_offset(ctl, bitmap_offset, 1, 0);
+ if (entry && list_empty(&entry->list))
+ list_add(&entry->list, bitmaps);
+ }
+
list_for_each_entry(entry, bitmaps, list) {
if (entry->bytes < min_bytes)
continue;
}
/*
- * If we do have entries on our list and we are here then we didn't find
- * anything, so go ahead and get the next entry after the last entry in
- * this list and start the search from there.
+ * The bitmaps list has all the bitmaps that record free space
+ * starting after offset, so no more search is required.
*/
- if (!list_empty(bitmaps)) {
- entry = list_entry(bitmaps->prev, struct btrfs_free_space,
- list);
- node = rb_next(&entry->offset_index);
- if (!node)
- return -ENOSPC;
- entry = rb_entry(node, struct btrfs_free_space, offset_index);
- goto search;
- }
-
- entry = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 0, 1);
- if (!entry)
- return -ENOSPC;
-
-search:
- node = &entry->offset_index;
- do {
- entry = rb_entry(node, struct btrfs_free_space, offset_index);
- node = rb_next(&entry->offset_index);
- if (!entry->bitmap)
- continue;
- if (entry->bytes < min_bytes)
- continue;
- ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
- bytes, min_bytes);
- } while (ret && node);
-
- return ret;
+ return -ENOSPC;
}
/*
u64 offset, u64 bytes, u64 empty_size)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
- struct list_head bitmaps;
struct btrfs_free_space *entry, *tmp;
+ LIST_HEAD(bitmaps);
u64 min_bytes;
int ret;
goto out;
}
- INIT_LIST_HEAD(&bitmaps);
ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
bytes, min_bytes);
if (ret)
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <linux/mount.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
/* insert an orphan item to track this unlinked/truncated file */
if (insert >= 1) {
ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- BUG_ON(ret);
+ BUG_ON(ret && ret != -EEXIST);
}
/* insert an orphan item to track subvolume contains orphan files */
if (ret && ret != -ESTALE)
goto out;
+ if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ struct btrfs_root *dead_root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ int is_dead_root = 0;
+
+ /*
+ * this is an orphan in the tree root. Currently these
+ * could come from 2 sources:
+ * a) a snapshot deletion in progress
+ * b) a free space cache inode
+ * We need to distinguish those two, as the snapshot
+ * orphan must not get deleted.
+ * find_dead_roots already ran before us, so if this
+ * is a snapshot deletion, we should find the root
+ * in the dead_roots list
+ */
+ spin_lock(&fs_info->trans_lock);
+ list_for_each_entry(dead_root, &fs_info->dead_roots,
+ root_list) {
+ if (dead_root->root_key.objectid ==
+ found_key.objectid) {
+ is_dead_root = 1;
+ break;
+ }
+ }
+ spin_unlock(&fs_info->trans_lock);
+ if (is_dead_root) {
+ /* prevent this orphan from being found again */
+ key.offset = found_key.objectid - 1;
+ continue;
+ }
+ }
/*
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
continue;
}
nr_truncate++;
+ /*
+ * Need to hold the imutex for reservation purposes, not
+ * a huge deal here but I have a WARN_ON in
+ * btrfs_delalloc_reserve_space to catch offenders.
+ */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_truncate(inode);
+ mutex_unlock(&inode->i_mutex);
} else {
nr_unlink++;
}
u64 hint_byte = 0;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 2);
+ trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
break;
cur_offset + hole_size,
&hint_byte, 1);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
0, hole_size, 0, hole_size,
0, 0, 0);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
btrfs_drop_extent_cache(inode, hole_start,
last_byte - 1, 0);
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
}
free_extent_map(em);
static int btrfs_setsize(struct inode *inode, loff_t newsize)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_trans_handle *trans;
loff_t oldsize = i_size_read(inode);
int ret;
return 0;
if (newsize > oldsize) {
- i_size_write(inode, newsize);
- btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
truncate_pagecache(inode, oldsize, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
- if (ret) {
- btrfs_setsize(inode, oldsize);
+ if (ret)
return ret;
- }
- mark_inode_dirty(inode);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ i_size_write(inode, newsize);
+ btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ ret = btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction_throttle(trans, root);
} else {
/*
if (attr->ia_valid) {
setattr_copy(inode, attr);
- mark_inode_dirty(inode);
+ err = btrfs_dirty_inode(inode);
- if (attr->ia_valid & ATTR_MODE)
+ if (!err && attr->ia_valid & ATTR_MODE)
err = btrfs_acl_chmod(inode);
}
* doing the truncate.
*/
while (1) {
- ret = btrfs_block_rsv_refill(root, rsv, min_size);
+ ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size);
/*
* Try and steal from the global reserve since we will
* FIXME, needs more benchmarking...there are no reasons other than performance
* to keep or drop this code.
*/
-void btrfs_dirty_inode(struct inode *inode, int flags)
+int btrfs_dirty_inode(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
if (BTRFS_I(inode)->dummy_inode)
- return;
+ return 0;
trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
if (ret && ret == -ENOSPC) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans, root);
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %ld\n",
- (unsigned long long)btrfs_ino(inode),
- PTR_ERR(trans));
- return;
- }
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %d\n",
- (unsigned long long)btrfs_ino(inode),
- ret);
- }
}
btrfs_end_transaction(trans, root);
if (BTRFS_I(inode)->delayed_node)
btrfs_balance_delayed_items(root);
+
+ return ret;
+}
+
+/*
+ * This is a copy of file_update_time. We need this so we can return error on
+ * ENOSPC for updating the inode in the case of file write and mmap writes.
+ */
+int btrfs_update_time(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct timespec now;
+ int ret;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+ /* First try to exhaust all avenues to not sync */
+ if (IS_NOCMTIME(inode))
+ return 0;
+
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
+ return 0;
+
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return 0;
+
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
+ inode_inc_iversion(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ ret = btrfs_dirty_inode(inode);
+ if (!ret)
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write(file->f_path.mnt);
+ return ret;
}
/*
int err = btrfs_add_link(trans, dir, inode,
dentry->d_name.name, dentry->d_name.len,
backref, index);
- if (!err) {
- d_instantiate(dentry, inode);
- return 0;
- }
if (err > 0)
err = -EEXIST;
return err;
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+
+ inode->i_op = &btrfs_special_inode_operations;
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
- inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
btrfs_update_inode(trans, root, inode);
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
struct dentry *parent = dentry->d_parent;
err = btrfs_update_inode(trans, root, inode);
BUG_ON(err);
+ d_instantiate(dentry, inode);
btrfs_log_new_name(trans, inode, NULL, parent);
}
u64 page_start;
u64 page_end;
+ /* Need this to keep space reservations serialized */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
+ if (!ret)
+ ret = btrfs_update_time(vma->vm_file);
if (ret) {
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
/* Just need the 1 for updating the inode */
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- goto out;
+ ret = err = PTR_ERR(trans);
+ trans = NULL;
+ break;
}
}
struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
+ u32 blocksize = inode->i_sb->s_blocksize;
+
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
stat->blksize = PAGE_CACHE_SIZE;
- stat->blocks = (inode_get_bytes(inode) +
- BTRFS_I(inode)->delalloc_bytes) >> 9;
+ stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
+ ALIGN(BTRFS_I(inode)->delalloc_bytes, blocksize)) >> 9;
return 0;
}
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
if (drop_inode)
drop_inode = 1;
out_unlock:
+ if (!err)
+ d_instantiate(dentry, inode);
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
if (drop_inode) {
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = btrfs_getattr,
+ .setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
trans = btrfs_join_transaction(root);
BUG_ON(IS_ERR(trans));
+ btrfs_update_iflags(inode);
+ inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, inode);
BUG_ON(ret);
- btrfs_update_iflags(inode);
- inode->i_ctime = CURRENT_TIME;
btrfs_end_transaction(trans, root);
mnt_drop_write(file->f_path.mnt);
return 0;
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode,
num_pages << PAGE_CACHE_SHIFT);
+ mutex_unlock(&inode->i_mutex);
if (ret)
return ret;
again:
*devstr = '\0';
devstr = vol_args->name;
devid = simple_strtoull(devstr, &end, 10);
- printk(KERN_INFO "resizing devid %llu\n",
+ printk(KERN_INFO "btrfs: resizing devid %llu\n",
(unsigned long long)devid);
}
device = btrfs_find_device(root, devid, NULL, NULL);
if (!device) {
- printk(KERN_INFO "resizer unable to find device %llu\n",
+ printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
(unsigned long long)devid);
ret = -EINVAL;
goto out_unlock;
do_div(new_size, root->sectorsize);
new_size *= root->sectorsize;
- printk(KERN_INFO "new size for %s is %llu\n",
+ printk(KERN_INFO "btrfs: new size for %s is %llu\n",
device->name, (unsigned long long)new_size);
if (new_size > old_size) {
}
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
- } else {
+ } else if (new_size < old_size) {
ret = btrfs_shrink_device(device, new_size);
}
goto out;
for (i = 0; i < ipath->fspath->elem_cnt; ++i) {
- rel_ptr = ipath->fspath->val[i] - (u64)ipath->fspath->val;
+ rel_ptr = ipath->fspath->val[i] -
+ (u64)(unsigned long)ipath->fspath->val;
ipath->fspath->val[i] = rel_ptr;
}
- ret = copy_to_user((void *)ipa->fspath, (void *)ipath->fspath, size);
+ ret = copy_to_user((void *)(unsigned long)ipa->fspath,
+ (void *)(unsigned long)ipath->fspath, size);
if (ret) {
ret = -EFAULT;
goto out;
if (ret < 0)
goto out;
- ret = copy_to_user((void *)loi->inodes, (void *)inodes, size);
+ ret = copy_to_user((void *)(unsigned long)loi->inodes,
+ (void *)(unsigned long)inodes, size);
if (ret)
ret = -EFAULT;
index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
while (index <= last_index) {
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
if (ret)
goto out;
btrfs_release_path(swarn->path);
ipath = init_ipath(4096, local_root, swarn->path);
+ if (IS_ERR(ipath)) {
+ ret = PTR_ERR(ipath);
+ ipath = NULL;
+ goto err;
+ }
ret = paths_from_inode(inum, ipath);
if (ret < 0)
swarn->logical, swarn->dev->name,
(unsigned long long)swarn->sector, root, inum, offset,
min(isize - offset, (u64)PAGE_SIZE), nlink,
- (char *)ipath->fspath->val[i]);
+ (char *)(unsigned long)ipath->fspath->val[i]);
free_ipath(ipath);
return 0;
static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret = 0;
mutex_lock(&fs_info->scrub_lock);
if (fs_info->scrub_workers_refcnt == 0) {
btrfs_init_workers(&fs_info->scrub_workers, "scrub",
fs_info->thread_pool_size, &fs_info->generic_worker);
fs_info->scrub_workers.idle_thresh = 4;
- btrfs_start_workers(&fs_info->scrub_workers, 1);
+ ret = btrfs_start_workers(&fs_info->scrub_workers);
+ if (ret)
+ goto out;
}
++fs_info->scrub_workers_refcnt;
+out:
mutex_unlock(&fs_info->scrub_lock);
- return 0;
+ return ret;
}
static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/mnt_namespace.h>
+#include <linux/ratelimit.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
static struct dentry *mount_subvol(const char *subvol_name, int flags,
const char *device_name, char *data)
{
- struct super_block *s;
struct dentry *root;
struct vfsmount *mnt;
- struct mnt_namespace *ns_private;
char *newargs;
- struct path path;
- int error;
newargs = setup_root_args(data);
if (!newargs)
if (IS_ERR(mnt))
return ERR_CAST(mnt);
- ns_private = create_mnt_ns(mnt);
- if (IS_ERR(ns_private)) {
- mntput(mnt);
- return ERR_CAST(ns_private);
- }
+ root = mount_subtree(mnt, subvol_name);
- /*
- * This will trigger the automount of the subvol so we can just
- * drop the mnt we have here and return the dentry that we
- * found.
- */
- error = vfs_path_lookup(mnt->mnt_root, mnt, subvol_name,
- LOOKUP_FOLLOW, &path);
- put_mnt_ns(ns_private);
- if (error)
- return ERR_PTR(error);
-
- if (!is_subvolume_inode(path.dentry->d_inode)) {
- path_put(&path);
- mntput(mnt);
- error = -EINVAL;
+ if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+ struct super_block *s = root->d_sb;
+ dput(root);
+ root = ERR_PTR(-EINVAL);
+ deactivate_locked_super(s);
printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
subvol_name);
- return ERR_PTR(-EINVAL);
}
- /* Get a ref to the sb and the dentry we found and return it */
- s = path.mnt->mnt_sb;
- atomic_inc(&s->s_active);
- root = dget(path.dentry);
- path_put(&path);
- down_write(&s->s_umount);
-
return root;
}
u64 avail_space;
u64 used_space;
u64 min_stripe_size;
- int min_stripes = 1;
+ int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
int ret;
- nr_devices = fs_info->fs_devices->rw_devices;
+ nr_devices = fs_info->fs_devices->open_devices;
BUG_ON(!nr_devices);
devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
/* calc min stripe number for data space alloction */
type = btrfs_get_alloc_profile(root, 1);
- if (type & BTRFS_BLOCK_GROUP_RAID0)
+ if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID1)
+ num_stripes = nr_devices;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID10)
+ num_stripes = 2;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
min_stripes = 4;
+ num_stripes = 4;
+ }
if (type & BTRFS_BLOCK_GROUP_DUP)
min_stripe_size = 2 * BTRFS_STRIPE_LEN;
else
min_stripe_size = BTRFS_STRIPE_LEN;
- list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
- if (!device->in_fs_metadata)
+ list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ if (!device->in_fs_metadata || !device->bdev)
continue;
avail_space = device->total_bytes - device->bytes_used;
i = nr_devices - 1;
avail_space = 0;
while (nr_devices >= min_stripes) {
+ if (num_stripes > nr_devices)
+ num_stripes = nr_devices;
+
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
u64 alloc_size;
- avail_space += devices_info[i].max_avail * min_stripes;
+ avail_space += devices_info[i].max_avail * num_stripes;
alloc_size = devices_info[i].max_avail;
- for (j = i + 1 - min_stripes; j <= i; j++)
+ for (j = i + 1 - num_stripes; j <= i; j++)
devices_info[j].max_avail -= alloc_size;
}
i--;
return 0;
}
+static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
+{
+ int ret;
+
+ ret = btrfs_dirty_inode(inode);
+ if (ret)
+ printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
+ "error %d\n", btrfs_ino(inode), ret);
+}
+
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
.sync_fs = btrfs_sync_fs,
.show_options = btrfs_show_options,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_dirty_inode,
+ .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
btrfs_save_ino_cache(root, trans);
+ /* see comments in should_cow_block() */
+ root->force_cow = 0;
+ smp_wmb();
+
if (root->commit_root != root->node) {
mutex_lock(&root->fs_commit_mutex);
switch_commit_root(root);
btrfs_tree_unlock(old);
free_extent_buffer(old);
+ /* see comments in should_cow_block() */
+ root->force_cow = 1;
+ smp_wmb();
+
btrfs_set_root_node(new_root_item, tmp);
/* record when the snapshot was created in key.offset */
key.offset = trans->transid;
btrfs_requeue_work(&device->work);
goto done;
}
+ /* unplug every 64 requests just for good measure */
+ if (batch_run % 64 == 0) {
+ blk_finish_plug(&plug);
+ blk_start_plug(&plug);
+ sync_pending = 0;
+ }
}
cond_resched();
if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
return -EINVAL;
- bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+ bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
root->fs_info->bdev_holder);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
*/
if (atomic_read(&bbio->error) > bbio->max_errors) {
err = -EIO;
- } else if (err) {
+ } else {
/*
* this bio is actually up to date, we didn't
* go over the max number of errors
struct reada_zone *reada_curr_zone;
struct radix_tree_root reada_zones;
struct radix_tree_root reada_extents;
+
+ /* for sending down flush barriers */
+ struct bio *flush_bio;
+ struct completion flush_wait;
+ int nobarriers;
+
};
struct btrfs_fs_devices {
snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
/* dirty the head */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_head_snapc == NULL)
ci->i_head_snapc = ceph_get_snap_context(snapc);
++ci->i_wrbuffer_ref_head;
ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
snapc, snapc->seq, snapc->num_snaps);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* now adjust page */
spin_lock_irq(&mapping->tree_lock);
struct ceph_snap_context *snapc = NULL;
struct ceph_cap_snap *capsnap = NULL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
capsnap->context, capsnap->dirty_pages);
dout(" head snapc %p has %d dirty pages\n",
snapc, ci->i_wrbuffer_ref_head);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return snapc;
}
/*
* Find ceph_cap for given mds, if any.
*
- * Called with i_lock held.
+ * Called with i_ceph_lock held.
*/
static struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds)
{
{
struct ceph_cap *cap;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return cap;
}
int ceph_get_cap_mds(struct inode *inode)
{
+ struct ceph_inode_info *ci = ceph_inode(inode);
int mds;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
mds = __ceph_get_cap_mds(ceph_inode(inode));
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return mds;
}
/*
- * Called under i_lock.
+ * Called under i_ceph_lock.
*/
static void __insert_cap_node(struct ceph_inode_info *ci,
struct ceph_cap *new)
*
* If I_FLUSH is set, leave the inode at the front of the list.
*
- * Caller holds i_lock
+ * Caller holds i_ceph_lock
* -> we take mdsc->cap_delay_lock
*/
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
/*
* Cancel delayed work on cap.
*
- * Caller must hold i_lock.
+ * Caller must hold i_ceph_lock.
*/
static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
wanted |= ceph_caps_for_mode(fmode);
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
if (new_cap) {
cap = new_cap;
new_cap = NULL;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
new_cap = get_cap(mdsc, caps_reservation);
if (new_cap == NULL)
return -ENOMEM;
if (fmode >= 0)
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
wake_up_all(&ci->i_cap_wq);
return 0;
}
struct rb_node *p;
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
cap = rb_entry(p, struct ceph_cap, ci_node);
if (__cap_is_valid(cap) &&
break;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("ceph_caps_revoking %p %s = %d\n", inode,
ceph_cap_string(mask), ret);
return ret;
}
/*
- * called under i_lock
+ * called under i_ceph_lock
*/
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
/*
* Remove a cap. Take steps to deal with a racing iterate_session_caps.
*
- * caller should hold i_lock.
+ * caller should hold i_ceph_lock.
* caller will not hold session s_mutex if called from destroy_inode.
*/
void __ceph_remove_cap(struct ceph_cap *cap)
/*
* Queue cap releases when an inode is dropped from our cache. Since
- * inode is about to be destroyed, there is no need for i_lock.
+ * inode is about to be destroyed, there is no need for i_ceph_lock.
*/
void ceph_queue_caps_release(struct inode *inode)
{
/*
* Send a cap msg on the given inode. Update our caps state, then
- * drop i_lock and send the message.
+ * drop i_ceph_lock and send the message.
*
* Make note of max_size reported/requested from mds, revoked caps
* that have now been implemented.
* Return non-zero if delayed release, or we experienced an error
* such that the caller should requeue + retry later.
*
- * called with i_lock, then drops it.
+ * called with i_ceph_lock, then drops it.
* caller should hold snap_rwsem (read), s_mutex.
*/
static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
int op, int used, int want, int retain, int flushing,
unsigned *pflush_tid)
- __releases(cap->ci->vfs_inode->i_lock)
+ __releases(cap->ci->i_ceph_lock)
{
struct ceph_inode_info *ci = cap->ci;
struct inode *inode = &ci->vfs_inode;
xattr_version = ci->i_xattrs.version;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
op, keep, want, flushing, seq, flush_tid, issue_seq, mseq,
* Unless @again is true, skip cap_snaps that were already sent to
* the MDS (i.e., during this session).
*
- * Called under i_lock. Takes s_mutex as needed.
+ * Called under i_ceph_lock. Takes s_mutex as needed.
*/
void __ceph_flush_snaps(struct ceph_inode_info *ci,
struct ceph_mds_session **psession,
int again)
- __releases(ci->vfs_inode->i_lock)
- __acquires(ci->vfs_inode->i_lock)
+ __releases(ci->i_ceph_lock)
+ __acquires(ci->i_ceph_lock)
{
struct inode *inode = &ci->vfs_inode;
int mds;
session = NULL;
}
if (!session) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
mutex_lock(&mdsc->mutex);
session = __ceph_lookup_mds_session(mdsc, mds);
mutex_unlock(&mdsc->mutex);
* deletion or migration. retry, and we'll
* get a better @mds value next time.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
goto retry;
}
list_del_init(&capsnap->flushing_item);
list_add_tail(&capsnap->flushing_item,
&session->s_cap_snaps_flushing);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
inode, capsnap, capsnap->follows, capsnap->flush_tid);
next_follows = capsnap->follows + 1;
ceph_put_cap_snap(capsnap);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
goto retry;
}
static void ceph_flush_snaps(struct ceph_inode_info *ci)
{
- struct inode *inode = &ci->vfs_inode;
-
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_flush_snaps(ci, NULL, 0);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
* Add dirty inode to the flushing list. Assigned a seq number so we
* can wait for caps to flush without starving.
*
- * Called under i_lock.
+ * Called under i_ceph_lock.
*/
static int __mark_caps_flushing(struct inode *inode,
struct ceph_mds_session *session)
struct ceph_inode_info *ci = ceph_inode(inode);
u32 invalidating_gen = ci->i_rdcache_gen;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
invalidate_mapping_pages(&inode->i_data, 0, -1);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (inode->i_data.nrpages == 0 &&
invalidating_gen == ci->i_rdcache_gen) {
if (mdsc->stopping)
is_delayed = 1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
__ceph_flush_snaps(ci, &session, 0);
goto retry_locked;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
retry_locked:
file_wanted = __ceph_caps_file_wanted(ci);
used = __ceph_caps_used(ci);
if (mutex_trylock(&session->s_mutex) == 0) {
dout("inverting session/ino locks on %p\n",
session);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (took_snap_rwsem) {
up_read(&mdsc->snap_rwsem);
took_snap_rwsem = 0;
if (down_read_trylock(&mdsc->snap_rwsem) == 0) {
dout("inverting snap/in locks on %p\n",
inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
down_read(&mdsc->snap_rwsem);
took_snap_rwsem = 1;
goto retry;
mds = cap->mds; /* remember mds, so we don't repeat */
sent++;
- /* __send_cap drops i_lock */
+ /* __send_cap drops i_ceph_lock */
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
retain, flushing, NULL);
- goto retry; /* retake i_lock and restart our cap scan. */
+ goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
/*
else if (!is_delayed || force_requeue)
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (queue_invalidate)
ceph_queue_invalidate(inode);
int flushing = 0;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
goto out;
int delayed;
if (!session) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
session = cap->session;
mutex_lock(&session->s_mutex);
goto retry;
flushing = __mark_caps_flushing(inode, session);
- /* __send_cap drops i_lock */
+ /* __send_cap drops i_ceph_lock */
delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, used, want,
cap->issued | cap->implemented, flushing,
flush_tid);
if (!delayed)
goto out_unlocked;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
out_unlocked:
if (session && unlock_session)
mutex_unlock(&session->s_mutex);
struct ceph_inode_info *ci = ceph_inode(inode);
int i, ret = 1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_CAP_BITS; i++)
if ((ci->i_flushing_caps & (1 << i)) &&
ci->i_cap_flush_tid[i] <= tid) {
ret = 0;
break;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (__ceph_caps_dirty(ci))
__cap_delay_requeue_front(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
return err;
}
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
if (cap && cap->session == session) {
dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
pr_err("%p auth cap %p not mds%d ???\n", inode,
cap, session->s_mds);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
struct ceph_cap *cap;
int delayed = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
if (cap && cap->session == session) {
dout("kick_flushing_caps %p cap %p %s\n", inode,
cap->issued | cap->implemented,
ci->i_flushing_caps, NULL);
if (delayed) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else {
pr_err("%p auth cap %p not mds%d ???\n", inode,
cap, session->s_mds);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
}
struct ceph_cap *cap;
int delayed = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
cap->issued | cap->implemented,
ci->i_flushing_caps, NULL);
if (delayed) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
* Take references to capabilities we hold, so that we don't release
* them to the MDS prematurely.
*
- * Protected by i_lock.
+ * Protected by i_ceph_lock.
*/
static void __take_cap_refs(struct ceph_inode_info *ci, int got)
{
dout("get_cap_refs %p need %s want %s\n", inode,
ceph_cap_string(need), ceph_cap_string(want));
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/* make sure file is actually open */
file_wanted = __ceph_caps_file_wanted(ci);
ceph_cap_string(have), ceph_cap_string(need));
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("get_cap_refs %p ret %d got %s\n", inode,
ret, ceph_cap_string(*got));
return ret;
int check = 0;
/* do we need to explicitly request a larger max_size? */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if ((endoff >= ci->i_max_size ||
endoff > (inode->i_size << 1)) &&
endoff > ci->i_wanted_max_size) {
ci->i_wanted_max_size = endoff;
check = 1;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (check)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
*/
void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
{
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
__take_cap_refs(ci, caps);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
int last = 0, put = 0, flushsnaps = 0, wake = 0;
struct ceph_cap_snap *capsnap;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (had & CEPH_CAP_PIN)
--ci->i_pin_ref;
if (had & CEPH_CAP_FILE_RD)
}
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
last ? " last" : "", put ? " put" : "");
int found = 0;
struct ceph_cap_snap *capsnap = NULL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_wrbuffer_ref -= nr;
last = !ci->i_wrbuffer_ref;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (last) {
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
* Handle a cap GRANT message from the MDS. (Note that a GRANT may
* actually be a revocation if it specifies a smaller cap set.)
*
- * caller holds s_mutex and i_lock, we drop both.
+ * caller holds s_mutex and i_ceph_lock, we drop both.
*
* return value:
* 0 - ok
struct ceph_mds_session *session,
struct ceph_cap *cap,
struct ceph_buffer *xattr_buf)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
}
BUG_ON(cap->issued & ~cap->implemented);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (writeback)
/*
* queue inode for writeback: we can't actually call
struct ceph_mds_caps *m,
struct ceph_mds_session *session,
struct ceph_cap *cap)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
wake_up_all(&ci->i_cap_wq);
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (drop)
iput(inode);
}
dout("handle_cap_flushsnap_ack inode %p ci %p mds%d follows %lld\n",
inode, ci, session->s_mds, follows);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
if (capsnap->follows == follows) {
if (capsnap->flush_tid != flush_tid) {
capsnap, capsnap->follows);
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (drop)
iput(inode);
}
static void handle_cap_trunc(struct inode *inode,
struct ceph_mds_caps *trunc,
struct ceph_mds_session *session)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
inode, mds, seq, truncate_size, truncate_seq);
queue_trunc = ceph_fill_file_size(inode, issued,
truncate_seq, truncate_size, size);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (queue_trunc)
ceph_queue_vmtruncate(inode);
dout("handle_cap_export inode %p ci %p mds%d mseq %d\n",
inode, ci, mds, mseq);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/* make sure we haven't seen a higher mseq */
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
}
/* else, we already released it */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
up_read(&mdsc->snap_rwsem);
/* make sure we re-request max_size, if necessary */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_requested_max_size = 0;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
struct ceph_mds_client *mdsc = session->s_mdsc;
struct super_block *sb = mdsc->fsc->sb;
struct inode *inode;
+ struct ceph_inode_info *ci;
struct ceph_cap *cap;
struct ceph_mds_caps *h;
int mds = session->s_mds;
/* lookup ino */
inode = ceph_find_inode(sb, vino);
+ ci = ceph_inode(inode);
dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
vino.snap, inode);
if (!inode) {
}
/* the rest require a cap */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ceph_inode(inode), mds);
if (!cap) {
dout(" no cap on %p ino %llx.%llx from mds%d\n",
inode, ceph_ino(inode), ceph_snap(inode), mds);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto flush_cap_releases;
}
- /* note that each of these drops i_lock for us */
+ /* note that each of these drops i_ceph_lock for us */
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
break;
default:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
pr_err("ceph_handle_caps: unknown cap op %d %s\n", op,
ceph_cap_op_name(op));
}
struct inode *inode = &ci->vfs_inode;
int last = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("put_fmode %p fmode %d %d -> %d\n", inode, fmode,
ci->i_nr_by_mode[fmode], ci->i_nr_by_mode[fmode]-1);
BUG_ON(ci->i_nr_by_mode[fmode] == 0);
if (--ci->i_nr_by_mode[fmode] == 0)
last++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (last && ci->i_vino.snap == CEPH_NOSNAP)
ceph_check_caps(ci, 0, NULL);
int used, dirty;
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
used = __ceph_caps_used(ci);
dirty = __ceph_caps_dirty(ci);
inode, cap, ceph_cap_string(cap->issued));
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
/*
* force an record for the directory caps if we have a dentry lease.
- * this is racy (can't take i_lock and d_lock together), but it
+ * this is racy (can't take i_ceph_lock and d_lock together), but it
* doesn't have to be perfect; the mds will revoke anything we don't
* release.
*/
}
/* can we use the dcache? */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if ((filp->f_pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
ceph_dir_test_complete(inode) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(filp, dirent, filldir);
if (err != -EAGAIN)
return err;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
if (fi->dentry) {
err = note_last_dentry(fi, fi->dentry->d_name.name,
* were released during the whole readdir, and we should have
* the complete dir contents in our cache.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_release_count == fi->dir_release_count) {
ceph_dir_set_complete(inode);
ci->i_max_offset = filp->f_pos;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("readdir %p filp %p done.\n", inode, filp);
return 0;
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
- spin_lock(&dir->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
if (strncmp(dentry->d_name.name,
fsc->mount_options->snapdir_name,
!is_root_ceph_dentry(dir, dentry) &&
ceph_dir_test_complete(dir) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
d_add(dentry, NULL);
di->lease_shared_gen = ci->i_shared_gen;
return NULL;
}
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
op = ceph_snap(dir) == CEPH_SNAPDIR ?
struct ceph_inode_info *ci = ceph_inode(inode);
int drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (inode->i_nlink == 1) {
drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN);
ci->i_ceph_flags |= CEPH_I_NODELAY;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return drop;
}
struct ceph_dentry_info *di = ceph_dentry(dentry);
int valid = 0;
- spin_lock(&dir->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_shared_gen == di->lease_shared_gen)
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n",
dir, (unsigned)ci->i_shared_gen, dentry,
(unsigned)di->lease_shared_gen, valid);
/*
* Set/clear/test dir complete flag on the dir's dentry.
*/
-static struct dentry * __d_find_any_alias(struct inode *inode)
-{
- struct dentry *alias;
-
- if (list_empty(&inode->i_dentry))
- return NULL;
- alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
- return alias;
-}
-
void ceph_dir_set_complete(struct inode *inode)
{
- struct dentry *dentry = __d_find_any_alias(inode);
-
- if (dentry && ceph_dentry(dentry)) {
- dout(" marking %p (%p) complete\n", inode, dentry);
- set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
- }
+ /* not yet implemented */
}
void ceph_dir_clear_complete(struct inode *inode)
{
- struct dentry *dentry = __d_find_any_alias(inode);
-
- if (dentry && ceph_dentry(dentry)) {
- dout(" marking %p (%p) NOT complete\n", inode, dentry);
- clear_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
- }
+ /* not yet implemented */
}
bool ceph_dir_test_complete(struct inode *inode)
{
- struct dentry *dentry = __d_find_any_alias(inode);
-
- if (dentry && ceph_dentry(dentry))
- return test_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
+ /* not yet implemented */
return false;
}
{
struct ceph_dentry_info *di;
- dout("d_release %p\n", dentry);
+ dout("ceph_d_prune %p\n", dentry);
/* do we have a valid parent? */
if (!dentry->d_parent || IS_ROOT(dentry))
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
* write) or any MDS (for read). Update wanted set
* asynchronously.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci);
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* adjust wanted? */
if ((issued & wanted) != wanted &&
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
req = prepare_open_request(inode->i_sb, flags, 0);
*/
int dirty;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_put_cap_refs(ci, got);
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (ret >= 0) {
int dirty;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
mutex_lock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode);
- if (origin != SEEK_CUR || origin != SEEK_SET) {
+
+ if (origin == SEEK_END || origin == SEEK_DATA || origin == SEEK_HOLE) {
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
if (ret < 0) {
offset = ret;
dout("alloc_inode %p\n", &ci->vfs_inode);
+ spin_lock_init(&ci->i_ceph_lock);
+
ci->i_version = 0;
ci->i_time_warp_seq = 0;
ci->i_ceph_flags = 0;
iinfo->xattr_len);
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/*
* provided version will be odd if inode value is projected,
char *sym;
BUG_ON(symlen != inode->i_size);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = -ENOMEM;
sym = kmalloc(symlen+1, GFP_NOFS);
memcpy(sym, iinfo->symlink, symlen);
sym[symlen] = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ci->i_symlink)
ci->i_symlink = sym;
else
}
no_change:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* queue truncate if we saw i_size decrease */
if (queue_trunc)
info->cap.flags,
caps_reservation);
} else {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
pr_warning("mds issued no caps on %llx.%llx\n",
{
struct dentry *dir = dn->d_parent;
struct inode *inode = dir->d_inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_dentry_info *di;
BUG_ON(!inode);
di = ceph_dentry(dn);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ceph_dir_test_complete(inode)) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return;
}
di->offset = ceph_inode(inode)->i_max_offset++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
spin_lock(&dir->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
struct ceph_inode_info *ci = ceph_inode(inode);
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
inode->i_size = size;
inode->i_blocks = (size + (1 << 9) - 1) >> 9;
(ci->i_reported_size << 1) < ci->i_max_size)
ret = 1;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
*/
void ceph_queue_writeback(struct inode *inode)
{
+ ihold(inode);
if (queue_work(ceph_inode_to_client(inode)->wb_wq,
&ceph_inode(inode)->i_wb_work)) {
dout("ceph_queue_writeback %p\n", inode);
- ihold(inode);
} else {
dout("ceph_queue_writeback %p failed\n", inode);
+ iput(inode);
}
}
*/
void ceph_queue_invalidate(struct inode *inode)
{
+ ihold(inode);
if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq,
&ceph_inode(inode)->i_pg_inv_work)) {
dout("ceph_queue_invalidate %p\n", inode);
- ihold(inode);
} else {
dout("ceph_queue_invalidate %p failed\n", inode);
+ iput(inode);
}
}
u32 orig_gen;
int check = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("invalidate_pages %p gen %d revoking %d\n", inode,
ci->i_rdcache_gen, ci->i_rdcache_revoking);
if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
/* nevermind! */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto out;
}
orig_gen = ci->i_rdcache_gen;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
truncate_inode_pages(&inode->i_data, 0);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
orig_gen == ci->i_rdcache_revoking) {
dout("invalidate_pages %p gen %d successful\n", inode,
inode, orig_gen, ci->i_rdcache_gen,
ci->i_rdcache_revoking);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (check)
ceph_check_caps(ci, 0, NULL);
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ ihold(inode);
if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
&ci->i_vmtruncate_work)) {
dout("ceph_queue_vmtruncate %p\n", inode);
- ihold(inode);
} else {
dout("ceph_queue_vmtruncate %p failed, pending=%d\n",
inode, ci->i_truncate_pending);
+ iput(inode);
}
}
int wrbuffer_refs, wake = 0;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_truncate_pending == 0) {
dout("__do_pending_vmtruncate %p none pending\n", inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return;
}
if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
dout("__do_pending_vmtruncate %p flushing snaps first\n",
inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
filemap_write_and_wait_range(&inode->i_data, 0,
inode->i_sb->s_maxbytes);
goto retry;
wrbuffer_refs = ci->i_wrbuffer_ref;
dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
ci->i_truncate_pending, to);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
truncate_inode_pages(inode->i_mapping, to);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_truncate_pending--;
if (ci->i_truncate_pending == 0)
wake = 1;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (wrbuffer_refs == 0)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
if (IS_ERR(req))
return PTR_ERR(req);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
}
release &= issued;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (inode_dirty_flags)
__mark_inode_dirty(inode, inode_dirty_flags);
__ceph_do_pending_vmtruncate(inode);
return err;
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_mdsc_put_request(req);
return err;
}
struct ceph_inode_info *ci = ceph_inode(inode);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_nr_by_mode[fi->fmode]--;
fi->fmode |= CEPH_FILE_MODE_LAZY;
ci->i_nr_by_mode[fi->fmode]++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("ioctl_layzio: file %p marked lazy\n", file);
ceph_check_caps(ci, 0, NULL);
}
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = NULL;
if (mode == USE_AUTH_MDS)
cap = ci->i_auth_cap;
if (!cap && !RB_EMPTY_ROOT(&ci->i_caps))
cap = rb_entry(rb_first(&ci->i_caps), struct ceph_cap, ci_node);
if (!cap) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto random;
}
mds = cap->session->s_mds;
dout("choose_mds %p %llx.%llx mds%d (%scap %p)\n",
inode, ceph_vinop(inode), mds,
cap == ci->i_auth_cap ? "auth " : "", cap);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return mds;
random:
dout("removing cap %p, ci is %p, inode is %p\n",
cap, ci, &ci->vfs_inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_remove_cap(cap);
if (!__ceph_is_any_real_caps(ci)) {
struct ceph_mds_client *mdsc =
}
spin_unlock(&mdsc->cap_dirty_lock);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
while (drop--)
iput(inode);
return 0;
wake_up_all(&ci->i_cap_wq);
if (arg) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
return 0;
}
if (session->s_trim_caps <= 0)
return -1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
mine = cap->issued | cap->implemented;
used = __ceph_caps_used(ci);
oissued = __ceph_caps_issued_other(ci, cap);
__ceph_remove_cap(cap);
} else {
/* try to drop referring dentries */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
d_prune_aliases(inode);
dout("trim_caps_cb %p cap %p pruned, count now %d\n",
inode, cap, atomic_read(&inode->i_count));
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return 0;
}
i_flushing_item);
struct inode *inode = &ci->vfs_inode;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_cap_flush_seq <= want_flush_seq) {
dout("check_cap_flush still flushing %p "
"seq %lld <= %lld to mds%d\n", inode,
session->s_mds);
ret = 0;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
mutex_unlock(&session->s_mutex);
ceph_put_mds_session(session);
pos, temp);
} else if (stop_on_nosnap && inode &&
ceph_snap(inode) == CEPH_NOSNAP) {
+ spin_unlock(&temp->d_lock);
break;
} else {
pos -= temp->d_name.len;
struct ceph_inode_info *ci = ceph_inode(inode);
dout("invalidate_dir_request %p (D_COMPLETE, lease(s))\n", inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ceph_dir_clear_complete(inode);
ci->i_release_count++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (req->r_dentry)
ceph_invalidate_dentry_lease(req->r_dentry);
if (err)
goto out_free;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap->seq = 0; /* reset cap seq */
cap->issue_seq = 0; /* and issue_seq */
rec.v1.pathbase = cpu_to_le64(pathbase);
reclen = sizeof(rec.v1);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (recon_state->flock) {
int num_fcntl_locks, num_flock_locks;
*
* mdsc->snap_rwsem
*
- * inode->i_lock
+ * ci->i_ceph_lock
* mdsc->snap_flush_lock
* mdsc->cap_delay_lock
*
return;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
used = __ceph_caps_used(ci);
dirty = __ceph_caps_dirty(ci);
kfree(capsnap);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
*
* If capsnap can now be flushed, add to snap_flush list, and return 1.
*
- * Caller must hold i_lock.
+ * Caller must hold i_ceph_lock.
*/
int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap *capsnap)
inode = &ci->vfs_inode;
ihold(inode);
spin_unlock(&mdsc->snap_flush_lock);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_flush_snaps(ci, &session, 0);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
iput(inode);
spin_lock(&mdsc->snap_flush_lock);
}
continue;
ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ci->i_snap_realm)
goto skip_inode;
/*
oldrealm = ci->i_snap_realm;
ci->i_snap_realm = realm;
spin_unlock(&realm->inodes_with_caps_lock);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_get_snap_realm(mdsc, realm);
ceph_put_snap_realm(mdsc, oldrealm);
continue;
skip_inode:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
iput(inode);
}
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
seq_printf(m, ",rsize=%d", fsopt->rsize);
if (fsopt->rasize != CEPH_RASIZE_DEFAULT)
- seq_printf(m, ",rasize=%d", fsopt->rsize);
+ seq_printf(m, ",rasize=%d", fsopt->rasize);
if (fsopt->congestion_kb != default_congestion_kb())
seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
if (err == 0) {
dout("open_root_inode success\n");
if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
- fsc->sb->s_root == NULL)
+ fsc->sb->s_root == NULL) {
root = d_alloc_root(req->r_target_inode);
- else
+ ceph_init_dentry(root);
+ } else {
root = d_obtain_alias(req->r_target_inode);
+ }
req->r_target_inode = NULL;
dout("open_root_inode success, root dentry is %p\n", root);
} else {
* The locking for D_COMPLETE is a bit odd:
* - we can clear it at almost any time (see ceph_d_prune)
* - it is only meaningful if:
- * - we hold dir inode i_lock
+ * - we hold dir inode i_ceph_lock
* - we hold dir FILE_SHARED caps
* - the dentry D_COMPLETE is set
*/
struct ceph_inode_info {
struct ceph_vino i_vino; /* ceph ino + snap */
+ spinlock_t i_ceph_lock;
+
u64 i_version;
u32 i_time_warp_seq;
struct ceph_inode_xattrs_info i_xattrs;
- /* capabilities. protected _both_ by i_lock and cap->session's
+ /* capabilities. protected _both_ by i_ceph_lock and cap->session's
* s_mutex. */
struct rb_root i_caps; /* cap list */
struct ceph_cap *i_auth_cap; /* authoritative cap, if any */
{
struct ceph_inode_info *ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
static inline void ceph_i_set(struct inode *inode, unsigned mask)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags |= mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
static inline bool ceph_i_test(struct inode *inode, unsigned mask)
struct ceph_inode_info *ci = ceph_inode(inode);
bool r;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
r = (ci->i_ceph_flags & mask) == mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return r;
}
static inline int ceph_caps_issued(struct ceph_inode_info *ci)
{
int issued;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return issued;
}
int touch)
{
int r;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
r = __ceph_caps_issued_mask(ci, mask, touch);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return r;
}
extern void __ceph_remove_cap(struct ceph_cap *cap);
static inline void ceph_remove_cap(struct ceph_cap *cap)
{
- struct inode *inode = &cap->ci->vfs_inode;
- spin_lock(&inode->i_lock);
+ spin_lock(&cap->ci->i_ceph_lock);
__ceph_remove_cap(cap);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&cap->ci->i_ceph_lock);
}
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
}
static int __build_xattrs(struct inode *inode)
- __releases(inode->i_lock)
- __acquires(inode->i_lock)
+ __releases(ci->i_ceph_lock)
+ __acquires(ci->i_ceph_lock)
{
u32 namelen;
u32 numattr = 0;
end = p + ci->i_xattrs.blob->vec.iov_len;
ceph_decode_32_safe(&p, end, numattr, bad);
xattr_version = ci->i_xattrs.version;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
xattrs = kcalloc(numattr, sizeof(struct ceph_xattr *),
GFP_NOFS);
goto bad_lock;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_xattrs.version != xattr_version) {
/* lost a race, retry */
for (i = 0; i < numattr; i++)
return err;
bad_lock:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
bad:
if (xattrs) {
for (i = 0; i < numattr; i++)
if (vxattrs)
vxattr = ceph_match_vxattr(vxattrs, name);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto get_xattr;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* get xattrs from mds (if we don't already have them) */
err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
if (err)
return err;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (vxattr && vxattr->readonly) {
err = vxattr->getxattr_cb(ci, value, size);
memcpy(value, xattr->val, xattr->val_len);
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return err;
}
u32 len;
int i;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto list_xattr;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
if (err)
return err;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
err = __build_xattrs(inode);
if (err < 0)
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return err;
}
if (!xattr)
goto out;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
retry:
issued = __ceph_caps_issued(ci, NULL);
if (!(issued & CEPH_CAP_XATTR_EXCL))
required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
struct ceph_buffer *blob = NULL;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout(" preaallocating new blob size=%d\n", required_blob_size);
blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
if (!blob)
goto out;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_xattrs.prealloc_blob)
ceph_buffer_put(ci->i_xattrs.prealloc_blob);
ci->i_xattrs.prealloc_blob = blob;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
return err;
do_sync:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
kfree(newname);
return -EOPNOTSUPP;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__build_xattrs(inode);
issued = __ceph_caps_issued(ci, NULL);
dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
return err;
do_sync:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_send_removexattr(dentry, name);
return err;
}
byte_count = be32_to_cpu(pTargetSMB->smb_buf_length);
byte_count += total_in_buf2;
/* don't allow buffer to overflow */
- if (byte_count > CIFSMaxBufSize)
+ if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4)
return -ENOBUFS;
pTargetSMB->smb_buf_length = cpu_to_be32(byte_count);
smb_msg.msg_controllen = 0;
for (total_read = 0; to_read; total_read += length, to_read -= length) {
+ try_to_freeze();
+
if (server_unresponsive(server)) {
total_read = -EAGAIN;
break;
warned_on_ntlm = true;
cERROR(1, "default security mechanism requested. The default "
"security mechanism will be upgraded from ntlm to "
- "ntlmv2 in kernel release 3.2");
+ "ntlmv2 in kernel release 3.3");
}
ses->overrideSecFlg = volume_info->secFlg;
lock->type, lock->netfid, conf_lock);
}
+/*
+ * Check if there is another lock that prevents us to set the lock (mandatory
+ * style). If such a lock exists, update the flock structure with its
+ * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
+ * or leave it the same if we can't. Returns 0 if we don't need to request to
+ * the server or 1 otherwise.
+ */
static int
cifs_lock_test(struct cifsInodeInfo *cinode, __u64 offset, __u64 length,
__u8 type, __u16 netfid, struct file_lock *flock)
mutex_unlock(&cinode->lock_mutex);
}
+/*
+ * Set the byte-range lock (mandatory style). Returns:
+ * 1) 0, if we set the lock and don't need to request to the server;
+ * 2) 1, if no locks prevent us but we need to request to the server;
+ * 3) -EACCESS, if there is a lock that prevents us and wait is false.
+ */
static int
cifs_lock_add_if(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock,
bool wait)
return rc;
}
+/*
+ * Check if there is another lock that prevents us to set the lock (posix
+ * style). If such a lock exists, update the flock structure with its
+ * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
+ * or leave it the same if we can't. Returns 0 if we don't need to request to
+ * the server or 1 otherwise.
+ */
static int
cifs_posix_lock_test(struct file *file, struct file_lock *flock)
{
return rc;
}
+/*
+ * Set the byte-range lock (posix style). Returns:
+ * 1) 0, if we set the lock and don't need to request to the server;
+ * 2) 1, if we need to request to the server;
+ * 3) <0, if the error occurs while setting the lock.
+ */
static int
cifs_posix_lock_set(struct file *file, struct file_lock *flock)
{
rc);
return rc;
}
- cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
+ /* FindFirst/Next set last_entry to NULL on malformed reply */
+ if (cifsFile->srch_inf.last_entry)
+ cifs_save_resume_key(cifsFile->srch_inf.last_entry,
+ cifsFile);
}
while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) &&
cFYI(1, "calling findnext2");
rc = CIFSFindNext(xid, pTcon, cifsFile->netfid,
&cifsFile->srch_inf);
- cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
+ /* FindFirst/Next set last_entry to NULL on malformed reply */
+ if (cifsFile->srch_inf.last_entry)
+ cifs_save_resume_key(cifsFile->srch_inf.last_entry,
+ cifsFile);
if (rc)
return -ENOENT;
}
{
int rc;
int len;
- __u16 wpwd[129];
+ __le16 wpwd[129];
/* Password cannot be longer than 128 characters */
if (passwd) /* Password must be converted to NT unicode */
*wpwd = 0; /* Ensure string is null terminated */
}
- rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__u16));
- memset(wpwd, 0, 129 * sizeof(__u16));
+ rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16));
+ memset(wpwd, 0, 129 * sizeof(__le16));
return rc;
}
return bdi_init(&configfs_backing_dev_info);
}
-void __exit configfs_inode_exit(void)
+void configfs_inode_exit(void)
{
bdi_destroy(&configfs_backing_dev_info);
}
goto out;
config_kobj = kobject_create_and_add("config", kernel_kobj);
- if (!config_kobj) {
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- goto out;
- }
+ if (!config_kobj)
+ goto out2;
+
+ err = configfs_inode_init();
+ if (err)
+ goto out3;
err = register_filesystem(&configfs_fs_type);
- if (err) {
- printk(KERN_ERR "configfs: Unable to register filesystem!\n");
- kobject_put(config_kobj);
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- goto out;
- }
+ if (err)
+ goto out4;
- err = configfs_inode_init();
- if (err) {
- unregister_filesystem(&configfs_fs_type);
- kobject_put(config_kobj);
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- }
+ return 0;
+out4:
+ printk(KERN_ERR "configfs: Unable to register filesystem!\n");
+ configfs_inode_exit();
+out3:
+ kobject_put(config_kobj);
+out2:
+ kmem_cache_destroy(configfs_dir_cachep);
+ configfs_dir_cachep = NULL;
out:
return err;
}
#include <linux/bit_spinlock.h>
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
+#include <linux/ratelimit.h>
#include "internal.h"
/*
actual = __d_unalias(inode, dentry, alias);
}
write_sequnlock(&rename_lock);
- if (IS_ERR(actual))
+ if (IS_ERR(actual)) {
+ if (PTR_ERR(actual) == -ELOOP)
+ pr_warn_ratelimited(
+ "VFS: Lookup of '%s' in %s %s"
+ " would have caused loop\n",
+ dentry->d_name.name,
+ inode->i_sb->s_type->name,
+ inode->i_sb->s_id);
dput(alias);
+ }
goto out_nolock;
}
}
/**
* prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
* @buffer: pointer to the end of the buffer
* @buflen: pointer to buffer length
*
* Caller holds the rename_lock.
- *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
*/
-static int prepend_path(const struct path *path, struct path *root,
+static int prepend_path(const struct path *path,
+ const struct path *root,
char **buffer, int *buflen)
{
struct dentry *dentry = path->dentry;
dentry = parent;
}
-out:
if (!error && !slash)
error = prepend(buffer, buflen, "/", 1);
+out:
br_read_unlock(vfsmount_lock);
return error;
WARN(1, "Root dentry has weird name <%.*s>\n",
(int) dentry->d_name.len, dentry->d_name.name);
}
- root->mnt = vfsmnt;
- root->dentry = dentry;
+ if (!slash)
+ error = prepend(buffer, buflen, "/", 1);
+ if (!error)
+ error = vfsmnt->mnt_ns ? 1 : 2;
goto out;
}
/**
* __d_path - return the path of a dentry
* @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
* @buf: buffer to return value in
* @buflen: buffer length
*
*
* "buflen" should be positive.
*
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
+ * If the path is not reachable from the supplied root, return %NULL.
*/
-char *__d_path(const struct path *path, struct path *root,
+char *__d_path(const struct path *path,
+ const struct path *root,
char *buf, int buflen)
{
char *res = buf + buflen;
error = prepend_path(path, root, &res, &buflen);
write_sequnlock(&rename_lock);
- if (error)
+ if (error < 0)
+ return ERR_PTR(error);
+ if (error > 0)
+ return NULL;
+ return res;
+}
+
+char *d_absolute_path(const struct path *path,
+ char *buf, int buflen)
+{
+ struct path root = {};
+ char *res = buf + buflen;
+ int error;
+
+ prepend(&res, &buflen, "\0", 1);
+ write_seqlock(&rename_lock);
+ error = prepend_path(path, &root, &res, &buflen);
+ write_sequnlock(&rename_lock);
+
+ if (error > 1)
+ error = -EINVAL;
+ if (error < 0)
return ERR_PTR(error);
return res;
}
/*
* same as __d_path but appends "(deleted)" for unlinked files.
*/
-static int path_with_deleted(const struct path *path, struct path *root,
- char **buf, int *buflen)
+static int path_with_deleted(const struct path *path,
+ const struct path *root,
+ char **buf, int *buflen)
{
prepend(buf, buflen, "\0", 1);
if (d_unlinked(path->dentry)) {
{
char *res = buf + buflen;
struct path root;
- struct path tmp;
int error;
/*
get_fs_root(current->fs, &root);
write_seqlock(&rename_lock);
- tmp = root;
- error = path_with_deleted(path, &tmp, &res, &buflen);
- if (error)
+ error = path_with_deleted(path, &root, &res, &buflen);
+ if (error < 0)
res = ERR_PTR(error);
write_sequnlock(&rename_lock);
path_put(&root);
{
char *res = buf + buflen;
struct path root;
- struct path tmp;
int error;
if (path->dentry->d_op && path->dentry->d_op->d_dname)
get_fs_root(current->fs, &root);
write_seqlock(&rename_lock);
- tmp = root;
- error = path_with_deleted(path, &tmp, &res, &buflen);
- if (!error && !path_equal(&tmp, &root))
+ error = path_with_deleted(path, &root, &res, &buflen);
+ if (error > 0)
error = prepend_unreachable(&res, &buflen);
write_sequnlock(&rename_lock);
path_put(&root);
write_seqlock(&rename_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
- struct path tmp = root;
char *cwd = page + PAGE_SIZE;
int buflen = PAGE_SIZE;
prepend(&cwd, &buflen, "\0", 1);
- error = prepend_path(&pwd, &tmp, &cwd, &buflen);
+ error = prepend_path(&pwd, &root, &cwd, &buflen);
write_sequnlock(&rename_lock);
- if (error)
+ if (error < 0)
goto out;
/* Unreachable from current root */
- if (!path_equal(&tmp, &root)) {
+ if (error > 0) {
error = prepend_unreachable(&cwd, &buflen);
if (error)
goto out;
} else {
struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) &addr;
struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) retaddr;
- ipv6_addr_copy(&ret6->sin6_addr, &in6->sin6_addr);
+ ret6->sin6_addr = in6->sin6_addr;
}
return 0;
/**
* ecryptfs_new_file_context
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_inode: The eCryptfs inode
*
* If the crypto context for the file has not yet been established,
* this is where we do that. Establishing a new crypto context
*
* Returns zero on success; non-zero otherwise
*/
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry)
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode)
{
struct ecryptfs_crypt_stat *crypt_stat =
- &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+ &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
&ecryptfs_superblock_to_private(
- ecryptfs_dentry->d_sb)->mount_crypt_stat;
+ ecryptfs_inode->i_sb)->mount_crypt_stat;
int cipher_name_len;
int rc = 0;
}
static int
-ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
+ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
char *virt, size_t virt_len)
{
int rc;
- rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
+ rc = ecryptfs_write_lower(ecryptfs_inode, virt,
0, virt_len);
if (rc < 0)
printk(KERN_ERR "%s: Error attempting to write header "
/**
* ecryptfs_write_metadata
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_dentry: The eCryptfs dentry, which should be negative
+ * @ecryptfs_inode: The newly created eCryptfs inode
*
* Write the file headers out. This will likely involve a userspace
* callout, in which the session key is encrypted with one or more
*
* Returns zero on success; non-zero on error
*/
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+ struct inode *ecryptfs_inode)
{
struct ecryptfs_crypt_stat *crypt_stat =
- &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+ &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
unsigned int order;
char *virt;
size_t virt_len;
rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
size);
else
- rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt,
+ rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
virt_len);
if (rc) {
printk(KERN_ERR "%s: Error writing metadata out to lower file; "
/* We could either offset on every reverse map or just pad some 0x00's
* at the front here */
-static const unsigned char filename_rev_map[] = {
+static const unsigned char filename_rev_map[256] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */
0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */
0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */
0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */
- 0x3D, 0x3E, 0x3F
+ 0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */
};
/**
int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode);
int ecryptfs_encrypt_page(struct page *page);
int ecryptfs_decrypt_page(struct page *page);
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+ struct inode *ecryptfs_inode);
int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode);
void ecryptfs_write_crypt_stat_flags(char *page_virt,
struct ecryptfs_crypt_stat *crypt_stat,
size_t *written);
return rc;
}
+static void ecryptfs_vma_close(struct vm_area_struct *vma)
+{
+ filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct ecryptfs_file_vm_ops = {
+ .close = ecryptfs_vma_close,
+ .fault = filemap_fault,
+};
+
+static int ecryptfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int rc;
+
+ rc = generic_file_mmap(file, vma);
+ if (!rc)
+ vma->vm_ops = &ecryptfs_file_vm_ops;
+
+ return rc;
+}
+
struct kmem_cache *ecryptfs_file_info_cache;
/**
#ifdef CONFIG_COMPAT
.compat_ioctl = ecryptfs_compat_ioctl,
#endif
- .mmap = generic_file_mmap,
+ .mmap = ecryptfs_file_mmap,
.open = ecryptfs_open,
.flush = ecryptfs_flush,
.release = ecryptfs_release,
* it. It will also update the eCryptfs directory inode to mimic the
* stat of the lower directory inode.
*
- * Returns zero on success; non-zero on error condition
+ * Returns the new eCryptfs inode on success; an ERR_PTR on error condition
*/
-static int
+static struct inode *
ecryptfs_do_create(struct inode *directory_inode,
struct dentry *ecryptfs_dentry, int mode)
{
int rc;
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
+ struct inode *inode;
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_dir_dentry)) {
ecryptfs_printk(KERN_ERR, "Error locking directory of "
"dentry\n");
- rc = PTR_ERR(lower_dir_dentry);
+ inode = ERR_CAST(lower_dir_dentry);
goto out;
}
rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode,
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
+ inode = ERR_PTR(rc);
goto out_lock;
}
- rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
- directory_inode->i_sb);
- if (rc) {
- ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
+ inode = __ecryptfs_get_inode(lower_dentry->d_inode,
+ directory_inode->i_sb);
+ if (IS_ERR(inode))
goto out_lock;
- }
fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
out_lock:
unlock_dir(lower_dir_dentry);
out:
- return rc;
+ return inode;
}
/**
*
* Returns zero on success
*/
-static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
+static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
+ struct inode *ecryptfs_inode)
{
struct ecryptfs_crypt_stat *crypt_stat =
- &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+ &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
int rc = 0;
- if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
+ if (S_ISDIR(ecryptfs_inode->i_mode)) {
ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
goto out;
}
ecryptfs_printk(KERN_DEBUG, "Initializing crypto context\n");
- rc = ecryptfs_new_file_context(ecryptfs_dentry);
+ rc = ecryptfs_new_file_context(ecryptfs_inode);
if (rc) {
ecryptfs_printk(KERN_ERR, "Error creating new file "
"context; rc = [%d]\n", rc);
goto out;
}
- rc = ecryptfs_get_lower_file(ecryptfs_dentry,
- ecryptfs_dentry->d_inode);
+ rc = ecryptfs_get_lower_file(ecryptfs_dentry, ecryptfs_inode);
if (rc) {
printk(KERN_ERR "%s: Error attempting to initialize "
"the lower file for the dentry with name "
ecryptfs_dentry->d_name.name, rc);
goto out;
}
- rc = ecryptfs_write_metadata(ecryptfs_dentry);
+ rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
if (rc)
printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
- ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+ ecryptfs_put_lower_file(ecryptfs_inode);
out:
return rc;
}
ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
int mode, struct nameidata *nd)
{
+ struct inode *ecryptfs_inode;
int rc;
- /* ecryptfs_do_create() calls ecryptfs_interpose() */
- rc = ecryptfs_do_create(directory_inode, ecryptfs_dentry, mode);
- if (unlikely(rc)) {
+ ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry,
+ mode);
+ if (unlikely(IS_ERR(ecryptfs_inode))) {
ecryptfs_printk(KERN_WARNING, "Failed to create file in"
"lower filesystem\n");
+ rc = PTR_ERR(ecryptfs_inode);
goto out;
}
/* At this point, a file exists on "disk"; we need to make sure
* that this on disk file is prepared to be an ecryptfs file */
- rc = ecryptfs_initialize_file(ecryptfs_dentry);
+ rc = ecryptfs_initialize_file(ecryptfs_dentry, ecryptfs_inode);
+ if (rc) {
+ drop_nlink(ecryptfs_inode);
+ unlock_new_inode(ecryptfs_inode);
+ iput(ecryptfs_inode);
+ goto out;
+ }
+ d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+ unlock_new_inode(ecryptfs_inode);
out:
return rc;
}
brelse(bitmap_bh);
printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
", computed = %llu, %llu\n",
- EXT4_B2C(sbi, ext4_free_blocks_count(es)),
+ EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+ neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1);
ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
/* Pre-conditions */
BUG_ON(!ext4_ext_is_uninitialized(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
- BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
/*
* Attempt to transfer newly initialized blocks from the currently
clear_buffer_unwritten(bh);
}
- /* skip page if block allocation undone */
- if (buffer_delay(bh) || buffer_unwritten(bh))
+ /*
+ * skip page if block allocation undone and
+ * block is dirty
+ */
+ if (ext4_bh_delay_or_unwritten(NULL, bh))
skip_page = 1;
bh = bh->b_this_page;
block_start += bh->b_size;
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
+ blk_finish_plug(&plug);
goto out_writepages;
}
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
- loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
- } else {
- page_len = pos & (PAGE_CACHE_SIZE - 1);
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers_no_lock(handle,
- inode, page, pos - page_len, page_len,
- EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
- }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
- loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
*/
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
+ if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
if (ext4_da_should_update_i_disksize(page, end)) {
down_write(&EXT4_I(inode)->i_data_sem);
if (new_i_size > EXT4_I(inode)->i_disksize) {
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
-
- page_len = PAGE_CACHE_SIZE -
- ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
-
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers_no_lock(handle,
- inode, page, pos + copied - 1, page_len,
- EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
- }
-
copied = ret2;
if (ret2 < 0)
ret = ret2;
iocb->private, io_end->inode->i_ino, iocb, offset,
size);
+ iocb->private = NULL;
+
/* if not aio dio with unwritten extents, just free io and return */
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
- iocb->private = NULL;
out:
if (is_async)
aio_complete(iocb, ret, 0);
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
- iocb->private = NULL;
/* XXX: probably should move into the real I/O completion handler */
inode_dio_done(inode);
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
- if (!page_has_buffers(page)) {
- /*
- * If the range to be discarded covers a partial block
- * we need to get the page buffers. This is because
- * partial blocks cannot be released and the page needs
- * to be updated with the contents of the block before
- * we write the zeros on top of it.
- */
- if ((from & (blocksize - 1)) ||
- ((from + length) & (blocksize - 1))) {
- create_empty_buffers(page, blocksize, 0);
- } else {
- /*
- * If there are no partial blocks,
- * there is nothing to update,
- * so we can return now
- */
- return 0;
- }
- }
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, blocksize, 0);
/* Find the buffer that contains "offset" */
bh = page_buffers(page);
block_end = block_start + blocksize;
if (block_start >= len) {
+ /*
+ * Comments copied from block_write_full_page_endio:
+ *
+ * The page straddles i_size. It must be zeroed out on
+ * each and every writepage invocation because it may
+ * be mmapped. "A file is mapped in multiples of the
+ * page size. For a file that is not a multiple of
+ * the page size, the remaining memory is zeroed when
+ * mapped, and writes to that region are not written
+ * out to the file."
+ */
+ zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
seq_puts(seq, ",block_validity");
if (!test_opt(sb, INIT_INODE_TABLE))
- seq_puts(seq, ",noinit_inode_table");
+ seq_puts(seq, ",noinit_itable");
else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
- seq_printf(seq, ",init_inode_table=%u",
+ seq_printf(seq, ",init_itable=%u",
(unsigned) sbi->s_li_wait_mult);
ext4_show_quota_options(seq, sb);
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
- Opt_discard, Opt_nodiscard,
- Opt_init_inode_table, Opt_noinit_inode_table,
+ Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
};
static const match_table_t tokens = {
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
- {Opt_init_inode_table, "init_itable=%u"},
- {Opt_init_inode_table, "init_itable"},
- {Opt_noinit_inode_table, "noinit_itable"},
+ {Opt_init_itable, "init_itable=%u"},
+ {Opt_init_itable, "init_itable"},
+ {Opt_noinit_itable, "noinit_itable"},
{Opt_err, NULL},
};
data_opt = EXT4_MOUNT_WRITEBACK_DATA;
datacheck:
if (is_remount) {
- if (test_opt(sb, DATA_FLAGS) != data_opt) {
+ if (!sbi->s_journal)
+ ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
+ else if (test_opt(sb, DATA_FLAGS) != data_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return 0;
case Opt_dioread_lock:
clear_opt(sb, DIOREAD_NOLOCK);
break;
- case Opt_init_inode_table:
+ case Opt_init_itable:
set_opt(sb, INIT_INODE_TABLE);
if (args[0].from) {
if (match_int(&args[0], &option))
return 0;
sbi->s_li_wait_mult = option;
break;
- case Opt_noinit_inode_table:
+ case Opt_noinit_itable:
clear_opt(sb, INIT_INODE_TABLE);
break;
default:
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
- __releases(kernel_lock)
- __acquires(kernel_lock)
{
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct completion *done; /* set if the caller waits */
};
-const char *wb_reason_name[] = {
- [WB_REASON_BACKGROUND] = "background",
- [WB_REASON_TRY_TO_FREE_PAGES] = "try_to_free_pages",
- [WB_REASON_SYNC] = "sync",
- [WB_REASON_PERIODIC] = "periodic",
- [WB_REASON_LAPTOP_TIMER] = "laptop_timer",
- [WB_REASON_FREE_MORE_MEM] = "free_more_memory",
- [WB_REASON_FS_FREE_SPACE] = "fs_free_space",
- [WB_REASON_FORKER_THREAD] = "forker_thread"
-};
-
/*
* Include the creation of the trace points after defining the
* wb_writeback_work structure so that the definition remains local to this
* bdi_start_writeback - start writeback
* @bdi: the backing device to write from
* @nr_pages: the number of pages to write
+ * @reason: reason why some writeback work was initiated
*
* Description:
* This does WB_SYNC_NONE opportunistic writeback. The IO is only
* writeback_inodes_sb_nr - writeback dirty inodes from given super_block
* @sb: the superblock
* @nr: the number of pages to write
+ * @reason: reason why some writeback work initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
/**
* writeback_inodes_sb - writeback dirty inodes from given super_block
* @sb: the superblock
+ * @reason: reason why some writeback work was initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
/**
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
+ * @reason: reason why some writeback work was initiated
*
* Invoke writeback_inodes_sb if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
* @nr: the number of pages to write
+ * @reason: reason why some writeback work was initiated
*
* Invoke writeback_inodes_sb if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
else if (outarg->offset + num > file_size)
num = file_size - outarg->offset;
- while (num) {
+ while (num && req->num_pages < FUSE_MAX_PAGES_PER_REQ) {
struct page *page;
unsigned int this_num;
num -= this_num;
total_len += this_num;
+ index++;
}
req->misc.retrieve_in.offset = outarg->offset;
req->misc.retrieve_in.size = total_len;
struct inode *inode = file->f_path.dentry->d_inode;
mutex_lock(&inode->i_mutex);
- if (origin != SEEK_CUR || origin != SEEK_SET) {
+ if (origin != SEEK_CUR && origin != SEEK_SET) {
retval = fuse_update_attributes(inode, NULL, file, NULL);
if (retval)
goto exit;
offset += i_size_read(inode);
break;
case SEEK_CUR:
+ if (offset == 0) {
+ retval = file->f_pos;
+ goto exit;
+ }
offset += file->f_pos;
break;
case SEEK_DATA:
{
int err;
- err = register_filesystem(&fuse_fs_type);
- if (err)
- goto out;
-
- err = register_fuseblk();
- if (err)
- goto out_unreg;
-
fuse_inode_cachep = kmem_cache_create("fuse_inode",
sizeof(struct fuse_inode),
0, SLAB_HWCACHE_ALIGN,
fuse_inode_init_once);
err = -ENOMEM;
if (!fuse_inode_cachep)
- goto out_unreg2;
+ goto out;
+
+ err = register_fuseblk();
+ if (err)
+ goto out2;
+
+ err = register_filesystem(&fuse_fs_type);
+ if (err)
+ goto out3;
return 0;
- out_unreg2:
+ out3:
unregister_fuseblk();
- out_unreg:
- unregister_filesystem(&fuse_fs_type);
+ out2:
+ kmem_cache_destroy(fuse_inode_cachep);
out:
return err;
}
int want_write = (mode & O_ACCMODE) != O_RDONLY;
new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
+ if (IS_ERR(new_fl))
+ return PTR_ERR(new_fl);
lock_flocks();
if (fl->fl_owner == current->files)
i_have_this_lease = 1;
- if (IS_ERR(new_fl) && !i_have_this_lease
- && ((mode & O_NONBLOCK) == 0)) {
- error = PTR_ERR(new_fl);
- goto out;
- }
-
break_time = 0;
if (lease_break_time > 0) {
break_time = jiffies + lease_break_time * HZ;
out:
unlock_flocks();
- if (!IS_ERR(new_fl))
- locks_free_lock(new_fl);
+ locks_free_lock(new_fl);
return error;
}
#include <linux/bitops.h>
#include <linux/sched.h>
-static const int nibblemap[] = { 4,3,3,2,3,2,2,1,3,2,2,1,2,1,1,0 };
-
static DEFINE_SPINLOCK(bitmap_lock);
-static unsigned long count_free(struct buffer_head *map[], unsigned numblocks, __u32 numbits)
+/*
+ * bitmap consists of blocks filled with 16bit words
+ * bit set == busy, bit clear == free
+ * endianness is a mess, but for counting zero bits it really doesn't matter...
+ */
+static __u32 count_free(struct buffer_head *map[], unsigned blocksize, __u32 numbits)
{
- unsigned i, j, sum = 0;
- struct buffer_head *bh;
-
- for (i=0; i<numblocks-1; i++) {
- if (!(bh=map[i]))
- return(0);
- for (j=0; j<bh->b_size; j++)
- sum += nibblemap[bh->b_data[j] & 0xf]
- + nibblemap[(bh->b_data[j]>>4) & 0xf];
- }
+ __u32 sum = 0;
+ unsigned blocks = DIV_ROUND_UP(numbits, blocksize * 8);
- if (numblocks==0 || !(bh=map[numblocks-1]))
- return(0);
- i = ((numbits - (numblocks-1) * bh->b_size * 8) / 16) * 2;
- for (j=0; j<i; j++) {
- sum += nibblemap[bh->b_data[j] & 0xf]
- + nibblemap[(bh->b_data[j]>>4) & 0xf];
+ while (blocks--) {
+ unsigned words = blocksize / 2;
+ __u16 *p = (__u16 *)(*map++)->b_data;
+ while (words--)
+ sum += 16 - hweight16(*p++);
}
- i = numbits%16;
- if (i!=0) {
- i = *(__u16 *)(&bh->b_data[j]) | ~((1<<i) - 1);
- sum += nibblemap[i & 0xf] + nibblemap[(i>>4) & 0xf];
- sum += nibblemap[(i>>8) & 0xf] + nibblemap[(i>>12) & 0xf];
- }
- return(sum);
+ return sum;
}
void minix_free_block(struct inode *inode, unsigned long block)
return 0;
}
-unsigned long minix_count_free_blocks(struct minix_sb_info *sbi)
+unsigned long minix_count_free_blocks(struct super_block *sb)
{
- return (count_free(sbi->s_zmap, sbi->s_zmap_blocks,
- sbi->s_nzones - sbi->s_firstdatazone + 1)
+ struct minix_sb_info *sbi = minix_sb(sb);
+ u32 bits = sbi->s_nzones - (sbi->s_firstdatazone + 1);
+
+ return (count_free(sbi->s_zmap, sb->s_blocksize, bits)
<< sbi->s_log_zone_size);
}
return inode;
}
-unsigned long minix_count_free_inodes(struct minix_sb_info *sbi)
+unsigned long minix_count_free_inodes(struct super_block *sb)
{
- return count_free(sbi->s_imap, sbi->s_imap_blocks, sbi->s_ninodes + 1);
+ struct minix_sb_info *sbi = minix_sb(sb);
+ u32 bits = sbi->s_ninodes + 1;
+
+ return count_free(sbi->s_imap, sb->s_blocksize, bits);
}
goto out_no_root;
}
+ /* Apparently minix can create filesystems that allocate more blocks for
+ * the bitmaps than needed. We simply ignore that, but verify it didn't
+ * create one with not enough blocks and bail out if so.
+ */
+ block = minix_blocks_needed(sbi->s_ninodes, s->s_blocksize);
+ if (sbi->s_imap_blocks < block) {
+ printk("MINIX-fs: file system does not have enough "
+ "imap blocks allocated. Refusing to mount\n");
+ goto out_iput;
+ }
+
+ block = minix_blocks_needed(
+ (sbi->s_nzones - (sbi->s_firstdatazone + 1)),
+ s->s_blocksize);
+ if (sbi->s_zmap_blocks < block) {
+ printk("MINIX-fs: file system does not have enough "
+ "zmap blocks allocated. Refusing to mount.\n");
+ goto out_iput;
+ }
+
ret = -ENOMEM;
s->s_root = d_alloc_root(root_inode);
if (!s->s_root)
if (!(sbi->s_mount_state & MINIX_VALID_FS))
printk("MINIX-fs: mounting unchecked file system, "
"running fsck is recommended\n");
- else if (sbi->s_mount_state & MINIX_ERROR_FS)
+ else if (sbi->s_mount_state & MINIX_ERROR_FS)
printk("MINIX-fs: mounting file system with errors, "
"running fsck is recommended\n");
+
return 0;
out_iput:
buf->f_type = sb->s_magic;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = (sbi->s_nzones - sbi->s_firstdatazone) << sbi->s_log_zone_size;
- buf->f_bfree = minix_count_free_blocks(sbi);
+ buf->f_bfree = minix_count_free_blocks(sb);
buf->f_bavail = buf->f_bfree;
buf->f_files = sbi->s_ninodes;
- buf->f_ffree = minix_count_free_inodes(sbi);
+ buf->f_ffree = minix_count_free_inodes(sb);
buf->f_namelen = sbi->s_namelen;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
extern struct minix2_inode * minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **);
extern struct inode * minix_new_inode(const struct inode *, int, int *);
extern void minix_free_inode(struct inode * inode);
-extern unsigned long minix_count_free_inodes(struct minix_sb_info *sbi);
+extern unsigned long minix_count_free_inodes(struct super_block *sb);
extern int minix_new_block(struct inode * inode);
extern void minix_free_block(struct inode *inode, unsigned long block);
-extern unsigned long minix_count_free_blocks(struct minix_sb_info *sbi);
+extern unsigned long minix_count_free_blocks(struct super_block *sb);
extern int minix_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
return list_entry(inode, struct minix_inode_info, vfs_inode);
}
+static inline unsigned minix_blocks_needed(unsigned bits, unsigned blocksize)
+{
+ return DIV_ROUND_UP(bits, blocksize * 8);
+}
+
#if defined(CONFIG_MINIX_FS_NATIVE_ENDIAN) && \
defined(CONFIG_MINIX_FS_BIG_ENDIAN_16BIT_INDEXED)
if (!size)
return 0;
- size = (size >> 4) + ((size & 15) > 0);
+ size >>= 4;
while (*p++ == 0xffff) {
if (--size == 0)
return (p - addr) << 4;
if (err)
goto out;
seq_putc(m, ' ');
- seq_path_root(m, &mnt_path, &root, " \t\n\\");
- if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
- /*
- * Mountpoint is outside root, discard that one. Ugly,
- * but less so than trying to do that in iterator in a
- * race-free way (due to renames).
- */
- return SEQ_SKIP;
- }
+
+ /* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+ err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
+ if (err)
+ goto out;
+
seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
show_mnt_opts(m, mnt);
__mnt_make_longterm(mnt);
new_ns->root = mnt;
list_add(&new_ns->list, &new_ns->root->mnt_list);
+ } else {
+ mntput(mnt);
}
return new_ns;
}
EXPORT_SYMBOL(create_mnt_ns);
+struct dentry *mount_subtree(struct vfsmount *mnt, const char *name)
+{
+ struct mnt_namespace *ns;
+ struct super_block *s;
+ struct path path;
+ int err;
+
+ ns = create_mnt_ns(mnt);
+ if (IS_ERR(ns))
+ return ERR_CAST(ns);
+
+ err = vfs_path_lookup(mnt->mnt_root, mnt,
+ name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+
+ put_mnt_ns(ns);
+
+ if (err)
+ return ERR_PTR(err);
+
+ /* trade a vfsmount reference for active sb one */
+ s = path.mnt->mnt_sb;
+ atomic_inc(&s->s_active);
+ mntput(path.mnt);
+ /* lock the sucker */
+ down_write(&s->s_umount);
+ /* ... and return the root of (sub)tree on it */
+ return path.dentry;
+}
+EXPORT_SYMBOL(mount_subtree);
+
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
{
}
}
EXPORT_SYMBOL(kern_unmount);
+
+bool our_mnt(struct vfsmount *mnt)
+{
+ return check_mnt(mnt);
+}
error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
if (error)
- goto out_bdi;
+ goto out_fput;
server->ncp_filp = ncp_filp;
server->ncp_sock = sock;
error = -EBADF;
server->info_filp = fget(data.info_fd);
if (!server->info_filp)
- goto out_fput;
+ goto out_bdi;
error = -ENOTSOCK;
sock_inode = server->info_filp->f_path.dentry->d_inode;
if (!S_ISSOCK(sock_inode->i_mode))
out_fput2:
if (server->info_filp)
fput(server->info_filp);
-out_fput:
- bdi_destroy(&server->bdi);
out_bdi:
+ bdi_destroy(&server->bdi);
+out_fput:
/* 23/12/1998 Marcin Dalecki <dalecki@cs.net.pl>:
*
* The previously used put_filp(ncp_filp); was bogus, since
res = NULL;
goto out;
/* This turned out not to be a regular file */
+ case -EISDIR:
case -ENOTDIR:
goto no_open;
case -ELOOP:
if (!(nd->intent.open.flags & O_NOFOLLOW))
goto no_open;
- /* case -EISDIR: */
/* case -EINVAL: */
default:
res = ERR_CAST(inode);
#define NFSDBG_FACILITY NFSDBG_FILE
-static int nfs_file_open(struct inode *, struct file *);
-static int nfs_file_release(struct inode *, struct file *);
-static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin);
-static int nfs_file_mmap(struct file *, struct vm_area_struct *);
-static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t count, unsigned int flags);
-static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
- struct file *filp, loff_t *ppos,
- size_t count, unsigned int flags);
-static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
-static int nfs_file_flush(struct file *, fl_owner_t id);
-static int nfs_file_fsync(struct file *, loff_t, loff_t, int datasync);
-static int nfs_check_flags(int flags);
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
-
static const struct vm_operations_struct nfs_file_vm_ops;
-const struct file_operations nfs_file_operations = {
- .llseek = nfs_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = nfs_file_read,
- .aio_write = nfs_file_write,
- .mmap = nfs_file_mmap,
- .open = nfs_file_open,
- .flush = nfs_file_flush,
- .release = nfs_file_release,
- .fsync = nfs_file_fsync,
- .lock = nfs_lock,
- .flock = nfs_flock,
- .splice_read = nfs_file_splice_read,
- .splice_write = nfs_file_splice_write,
- .check_flags = nfs_check_flags,
- .setlease = nfs_setlease,
-};
-
const struct inode_operations nfs_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
* origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
* the cached file length
*/
- if (origin != SEEK_SET || origin != SEEK_CUR) {
+ if (origin != SEEK_SET && origin != SEEK_CUR) {
struct inode *inode = filp->f_mapping->host;
int retval = nfs_revalidate_file_size(inode, filp);
file->f_path.dentry->d_name.name, arg);
return -EINVAL;
}
+
+const struct file_operations nfs_file_operations = {
+ .llseek = nfs_file_llseek,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = nfs_file_read,
+ .aio_write = nfs_file_write,
+ .mmap = nfs_file_mmap,
+ .open = nfs_file_open,
+ .flush = nfs_file_flush,
+ .release = nfs_file_release,
+ .fsync = nfs_file_fsync,
+ .lock = nfs_lock,
+ .flock = nfs_flock,
+ .splice_read = nfs_file_splice_read,
+ .splice_write = nfs_file_splice_write,
+ .check_flags = nfs_check_flags,
+ .setlease = nfs_setlease,
+};
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+ /*
+ * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+ * this point, then something is very wrong
+ */
+ dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+ return -ENOTDIR;
+}
+
+const struct file_operations nfs4_file_operations = {
+ .llseek = nfs_file_llseek,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = nfs_file_read,
+ .aio_write = nfs_file_write,
+ .mmap = nfs_file_mmap,
+ .open = nfs4_file_open,
+ .flush = nfs_file_flush,
+ .release = nfs_file_release,
+ .fsync = nfs_file_fsync,
+ .lock = nfs_lock,
+ .flock = nfs_flock,
+ .splice_read = nfs_file_splice_read,
+ .splice_write = nfs_file_splice_write,
+ .check_flags = nfs_check_flags,
+ .setlease = nfs_setlease,
+};
+#endif /* CONFIG_NFS_V4 */
*/
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
if (S_ISREG(inode->i_mode)) {
- inode->i_fop = &nfs_file_operations;
+ inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
inode->i_data.a_ops = &nfs_file_aops;
inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
} else if (S_ISDIR(inode->i_mode)) {
extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
struct list_head *head);
+extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+ struct inode *inode);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_readdata_release(struct nfs_read_data *rdata);
.dentry_ops = &nfs_dentry_operations,
.dir_inode_ops = &nfs3_dir_inode_operations,
.file_inode_ops = &nfs3_file_inode_operations,
+ .file_ops = &nfs_file_operations,
.getroot = nfs3_proc_get_root,
.getattr = nfs3_proc_getattr,
.setattr = nfs3_proc_setattr,
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/string.h>
+#include <linux/ratelimit.h>
+#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/gss_api.h>
static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode)
{
+ if (delegation == NULL)
+ return 0;
if ((delegation->type & fmode) != fmode)
return 0;
if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags))
}
rcu_read_lock();
delegation = rcu_dereference(nfsi->delegation);
- if (delegation == NULL ||
- !can_open_delegated(delegation, fmode)) {
+ if (!can_open_delegated(delegation, fmode)) {
rcu_read_unlock();
break;
}
if (delegation)
delegation_flags = delegation->flags;
rcu_read_unlock();
- if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
+ if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
+ pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
+ "returning a delegation for "
+ "OPEN(CLAIM_DELEGATE_CUR)\n",
+ NFS_CLIENT(inode)->cl_server);
+ } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
nfs_inode_set_delegation(state->inode,
data->owner->so_cred,
&data->o_res);
goto out_no_action;
rcu_read_lock();
delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
- if (delegation != NULL &&
- test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) {
- rcu_read_unlock();
- goto out_no_action;
- }
+ if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR &&
+ can_open_delegated(delegation, data->o_arg.fmode))
+ goto unlock_no_action;
rcu_read_unlock();
}
/* Update sequence id. */
return;
rpc_call_start(task);
return;
+unlock_no_action:
+ rcu_read_unlock();
out_no_action:
task->tk_action = NULL;
case -NFS4ERR_BADNAME:
return -ENOENT;
case -NFS4ERR_MOVED:
- err = nfs4_get_referral(dir, name, fattr, fhandle);
- break;
+ return nfs4_get_referral(dir, name, fattr, fhandle);
case -NFS4ERR_WRONGSEC:
nfs_fixup_secinfo_attributes(fattr, fhandle);
}
.dentry_ops = &nfs4_dentry_operations,
.dir_inode_ops = &nfs4_dir_inode_operations,
.file_inode_ops = &nfs4_file_inode_operations,
+ .file_ops = &nfs4_file_operations,
.getroot = nfs4_proc_get_root,
.getattr = nfs4_proc_getattr,
.setattr = nfs4_proc_setattr,
if (status >= 0) {
status = nfs4_reclaim_locks(state, ops);
if (status >= 0) {
+ spin_lock(&state->state_lock);
list_for_each_entry(lock, &state->lock_states, ls_locks) {
if (!(lock->ls_flags & NFS_LOCK_INITIALIZED))
printk("%s: Lock reclaim failed!\n",
__func__);
}
+ spin_unlock(&state->state_lock);
nfs4_put_open_state(state);
goto restart;
}
clear_bit(NFS_O_RDONLY_STATE, &state->flags);
clear_bit(NFS_O_WRONLY_STATE, &state->flags);
clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ spin_lock(&state->state_lock);
list_for_each_entry(lock, &state->lock_states, ls_locks) {
lock->ls_seqid.flags = 0;
lock->ls_flags &= ~NFS_LOCK_INITIALIZED;
}
+ spin_unlock(&state->state_lock);
}
static void nfs4_reset_seqids(struct nfs_server *server,
static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
{
switch (error) {
+ case 0:
+ break;
case -NFS4ERR_CB_PATH_DOWN:
nfs_handle_cb_pathdown(clp);
- return 0;
+ break;
case -NFS4ERR_NO_GRACE:
nfs4_state_end_reclaim_reboot(clp);
- return 0;
+ break;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_LEASE_MOVED:
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
case -NFS4ERR_SEQ_MISORDERED:
set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* Zero session reset errors */
- return 0;
+ break;
case -EKEYEXPIRED:
/* Nothing we can do */
nfs4_warn_keyexpired(clp->cl_hostname);
- return 0;
+ break;
+ default:
+ return error;
}
- return error;
+ return 0;
}
static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops)
struct rpc_cred *cred;
const struct nfs4_state_maintenance_ops *ops =
clp->cl_mvops->state_renewal_ops;
- int status = -NFS4ERR_EXPIRED;
+ int status;
/* Is the client already known to have an expired lease? */
if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
spin_unlock(&clp->cl_lock);
if (cred == NULL) {
cred = nfs4_get_setclientid_cred(clp);
+ status = -ENOKEY;
if (cred == NULL)
goto out;
}
{
if (!flags)
return;
- else if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
+ if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
nfs41_handle_server_reboot(clp);
- else if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
+ if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
SEQ4_STATUS_ADMIN_STATE_REVOKED |
SEQ4_STATUS_LEASE_MOVED))
nfs41_handle_state_revoked(clp);
- else if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
+ if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
nfs41_handle_recallable_state_revoked(clp);
- else if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
+ if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
SEQ4_STATUS_BACKCHANNEL_FAULT |
SEQ4_STATUS_CB_PATH_DOWN_SESSION))
nfs41_handle_cb_path_down(clp);
if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
status = nfs4_check_lease(clp);
+ if (status < 0)
+ goto out_error;
if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
continue;
- if (status < 0 && status != -NFS4ERR_CB_PATH_DOWN)
- goto out_error;
}
/* Initialize or reset the session */
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
+static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+{
+ struct nfs_pageio_descriptor pgio;
+
+ put_lseg(data->lseg);
+ data->lseg = NULL;
+ dprintk("pnfs write error = %d\n", data->pnfs_error);
+
+ nfs_pageio_init_read_mds(&pgio, data->inode);
+
+ while (!list_empty(&data->pages)) {
+ struct nfs_page *req = nfs_list_entry(data->pages.next);
+
+ nfs_list_remove_request(req);
+ nfs_pageio_add_request(&pgio, req);
+ }
+ nfs_pageio_complete(&pgio);
+}
+
/*
* Called by non rpc-based layout drivers
*/
if (likely(!data->pnfs_error)) {
__nfs4_read_done_cb(data);
data->mds_ops->rpc_call_done(&data->task, data);
- } else {
- put_lseg(data->lseg);
- data->lseg = NULL;
- dprintk("pnfs write error = %d\n", data->pnfs_error);
- }
+ } else
+ pnfs_ld_handle_read_error(data);
data->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
.dentry_ops = &nfs_dentry_operations,
.dir_inode_ops = &nfs_dir_inode_operations,
.file_inode_ops = &nfs_file_inode_operations,
+ .file_ops = &nfs_file_operations,
.getroot = nfs_proc_get_root,
.getattr = nfs_proc_getattr,
.setattr = nfs_proc_setattr,
}
}
-static void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode)
{
nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
static void nfs_readpage_release_full(void *calldata)
{
struct nfs_read_data *data = calldata;
- struct nfs_pageio_descriptor pgio;
- if (data->pnfs_error) {
- nfs_pageio_init_read_mds(&pgio, data->inode);
- pgio.pg_recoalesce = 1;
- }
while (!list_empty(&data->pages)) {
struct nfs_page *req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- if (!data->pnfs_error)
- nfs_readpage_release(req);
- else
- nfs_pageio_add_request(&pgio, req);
+ nfs_readpage_release(req);
}
- if (data->pnfs_error)
- nfs_pageio_complete(&pgio);
nfs_readdata_release(calldata);
}
static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
const char *export_path)
{
- struct mnt_namespace *ns_private;
- struct super_block *s;
struct dentry *dentry;
- struct path path;
- int ret;
-
- ns_private = create_mnt_ns(root_mnt);
- ret = PTR_ERR(ns_private);
- if (IS_ERR(ns_private))
- goto out_mntput;
-
- ret = nfs_referral_loop_protect();
- if (ret != 0)
- goto out_put_mnt_ns;
+ int ret = nfs_referral_loop_protect();
- ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
- export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+ if (ret) {
+ mntput(root_mnt);
+ return ERR_PTR(ret);
+ }
+ dentry = mount_subtree(root_mnt, export_path);
nfs_referral_loop_unprotect();
- put_mnt_ns(ns_private);
-
- if (ret != 0)
- goto out_err;
-
- s = path.mnt->mnt_sb;
- atomic_inc(&s->s_active);
- dentry = dget(path.dentry);
- path_put(&path);
- down_write(&s->s_umount);
return dentry;
-out_put_mnt_ns:
- put_mnt_ns(ns_private);
-out_mntput:
- mntput(root_mnt);
-out_err:
- return ERR_PTR(ret);
}
static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
if (argv[n].v_nmembs > nsegs * nilfs->ns_blocks_per_segment)
goto out_free;
+ if (argv[n].v_nmembs >= UINT_MAX / argv[n].v_size)
+ goto out_free;
+
len = argv[n].v_size * argv[n].v_nmembs;
base = (void __user *)(unsigned long)argv[n].v_base;
if (len == 0) {
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
+ case NILFS_IOCTL_CHANGE_CPMODE:
+ case NILFS_IOCTL_DELETE_CHECKPOINT:
+ case NILFS_IOCTL_GET_CPINFO:
+ case NILFS_IOCTL_GET_CPSTAT:
+ case NILFS_IOCTL_GET_SUINFO:
+ case NILFS_IOCTL_GET_SUSTAT:
+ case NILFS_IOCTL_GET_VINFO:
+ case NILFS_IOCTL_GET_BDESCS:
+ case NILFS_IOCTL_CLEAN_SEGMENTS:
+ case NILFS_IOCTL_SYNC:
+ case NILFS_IOCTL_RESIZE:
+ case NILFS_IOCTL_SET_ALLOC_RANGE:
+ break;
default:
return -ENOIOCTLCMD;
}
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
- goto out;
+ goto out_commit;
}
dquot_free_space_nodirty(inode,
}
if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+ /*
+ * Unlock the page and cycle ip_alloc_sem so that we don't
+ * busyloop waiting for ip_alloc_sem to unlock
+ */
ret = AOP_TRUNCATED_PAGE;
+ unlock_page(page);
+ unlock = 0;
+ down_read(&oi->ip_alloc_sem);
+ up_read(&oi->ip_alloc_sem);
goto out_inode_unlock;
}
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int level;
+ wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
/* this io's submitter should not have unlocked this before we could */
BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
if (ocfs2_iocb_is_sem_locked(iocb))
ocfs2_iocb_clear_sem_locked(iocb);
+ if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+ ocfs2_iocb_clear_unaligned_aio(iocb);
+
+ if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
+ waitqueue_active(wq)) {
+ wake_up_all(wq);
+ }
+ }
+
ocfs2_iocb_clear_rw_locked(iocb);
level = ocfs2_iocb_rw_locked_level(iocb);
struct page *w_pages[OCFS2_MAX_CTXT_PAGES];
struct page *w_target_page;
+ /*
+ * w_target_locked is used for page_mkwrite path indicating no unlocking
+ * against w_target_page in ocfs2_write_end_nolock.
+ */
+ unsigned int w_target_locked:1;
+
/*
* ocfs2_write_end() uses this to know what the real range to
* write in the target should be.
static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
{
+ int i;
+
+ /*
+ * w_target_locked is only set to true in the page_mkwrite() case.
+ * The intent is to allow us to lock the target page from write_begin()
+ * to write_end(). The caller must hold a ref on w_target_page.
+ */
+ if (wc->w_target_locked) {
+ BUG_ON(!wc->w_target_page);
+ for (i = 0; i < wc->w_num_pages; i++) {
+ if (wc->w_target_page == wc->w_pages[i]) {
+ wc->w_pages[i] = NULL;
+ break;
+ }
+ }
+ mark_page_accessed(wc->w_target_page);
+ page_cache_release(wc->w_target_page);
+ }
ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
brelse(wc->w_di_bh);
*/
lock_page(mmap_page);
+ /* Exit and let the caller retry */
if (mmap_page->mapping != mapping) {
+ WARN_ON(mmap_page->mapping);
unlock_page(mmap_page);
- /*
- * Sanity check - the locking in
- * ocfs2_pagemkwrite() should ensure
- * that this code doesn't trigger.
- */
- ret = -EINVAL;
- mlog_errno(ret);
+ ret = -EAGAIN;
goto out;
}
page_cache_get(mmap_page);
wc->w_pages[i] = mmap_page;
+ wc->w_target_locked = true;
} else {
wc->w_pages[i] = find_or_create_page(mapping, index,
GFP_NOFS);
wc->w_target_page = wc->w_pages[i];
}
out:
+ if (ret)
+ wc->w_target_locked = false;
return ret;
}
*/
ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
cluster_of_pages, mmap_page);
- if (ret) {
+ if (ret && ret != -EAGAIN) {
mlog_errno(ret);
goto out_quota;
}
+ /*
+ * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
+ * the target page. In this case, we exit with no error and no target
+ * page. This will trigger the caller, page_mkwrite(), to re-try
+ * the operation.
+ */
+ if (ret == -EAGAIN) {
+ BUG_ON(wc->w_target_page);
+ ret = 0;
+ goto out_quota;
+ }
+
ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
len);
if (ret) {
OCFS2_IOCB_RW_LOCK = 0,
OCFS2_IOCB_RW_LOCK_LEVEL,
OCFS2_IOCB_SEM,
+ OCFS2_IOCB_UNALIGNED_IO,
OCFS2_IOCB_NUM_LOCKS
};
clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
#define ocfs2_iocb_is_sem_locked(iocb) \
test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
+
+#define ocfs2_iocb_set_unaligned_aio(iocb) \
+ set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_clear_unaligned_aio(iocb) \
+ clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_is_unaligned_aio(iocb) \
+ test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+
+#define OCFS2_IOEND_WQ_HASH_SZ 37
+#define ocfs2_ioend_wq(v) (&ocfs2__ioend_wq[((unsigned long)(v)) %\
+ OCFS2_IOEND_WQ_HASH_SZ])
+extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
#endif /* OCFS2_FILE_H */
struct list_head hr_all_item;
unsigned hr_unclean_stop:1,
+ hr_aborted_start:1,
hr_item_pinned:1,
hr_item_dropped:1;
* a more complete api that doesn't lead to this sort of fragility. */
atomic_t hr_steady_iterations;
+ /* terminate o2hb thread if it does not reach steady state
+ * (hr_steady_iterations == 0) within hr_unsteady_iterations */
+ atomic_t hr_unsteady_iterations;
+
char hr_dev_name[BDEVNAME_SIZE];
unsigned int hr_timeout_ms;
static void o2hb_arm_write_timeout(struct o2hb_region *reg)
{
+ /* Arm writeout only after thread reaches steady state */
+ if (atomic_read(®->hr_steady_iterations) != 0)
+ return;
+
mlog(ML_HEARTBEAT, "Queue write timeout for %u ms\n",
O2HB_MAX_WRITE_TIMEOUT_MS);
return read == computed;
}
-/* We want to make sure that nobody is heartbeating on top of us --
- * this will help detect an invalid configuration. */
-static void o2hb_check_last_timestamp(struct o2hb_region *reg)
+/*
+ * Compare the slot data with what we wrote in the last iteration.
+ * If the match fails, print an appropriate error message. This is to
+ * detect errors like... another node hearting on the same slot,
+ * flaky device that is losing writes, etc.
+ * Returns 1 if check succeeds, 0 otherwise.
+ */
+static int o2hb_check_own_slot(struct o2hb_region *reg)
{
struct o2hb_disk_slot *slot;
struct o2hb_disk_heartbeat_block *hb_block;
slot = ®->hr_slots[o2nm_this_node()];
/* Don't check on our 1st timestamp */
if (!slot->ds_last_time)
- return;
+ return 0;
hb_block = slot->ds_raw_block;
if (le64_to_cpu(hb_block->hb_seq) == slot->ds_last_time &&
le64_to_cpu(hb_block->hb_generation) == slot->ds_last_generation &&
hb_block->hb_node == slot->ds_node_num)
- return;
+ return 1;
#define ERRSTR1 "Another node is heartbeating on device"
#define ERRSTR2 "Heartbeat generation mismatch on device"
(unsigned long long)slot->ds_last_time, hb_block->hb_node,
(unsigned long long)le64_to_cpu(hb_block->hb_generation),
(unsigned long long)le64_to_cpu(hb_block->hb_seq));
+
+ return 0;
}
static inline void o2hb_prepare_block(struct o2hb_region *reg,
o2nm_node_put(node);
}
-static void o2hb_set_quorum_device(struct o2hb_region *reg,
- struct o2hb_disk_slot *slot)
+static void o2hb_set_quorum_device(struct o2hb_region *reg)
{
- assert_spin_locked(&o2hb_live_lock);
-
if (!o2hb_global_heartbeat_active())
return;
- if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+ /* Prevent race with o2hb_heartbeat_group_drop_item() */
+ if (kthread_should_stop())
+ return;
+
+ /* Tag region as quorum only after thread reaches steady state */
+ if (atomic_read(®->hr_steady_iterations) != 0)
return;
+ spin_lock(&o2hb_live_lock);
+
+ if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+ goto unlock;
+
/*
* A region can be added to the quorum only when it sees all
* live nodes heartbeat on it. In other words, the region has been
*/
if (memcmp(reg->hr_live_node_bitmap, o2hb_live_node_bitmap,
sizeof(o2hb_live_node_bitmap)))
- return;
-
- if (slot->ds_changed_samples < O2HB_LIVE_THRESHOLD)
- return;
+ goto unlock;
- printk(KERN_NOTICE "o2hb: Region %s is now a quorum device\n",
- config_item_name(®->hr_item));
+ printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n",
+ config_item_name(®->hr_item), reg->hr_dev_name);
set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
if (o2hb_pop_count(&o2hb_quorum_region_bitmap,
O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF)
o2hb_region_unpin(NULL);
+unlock:
+ spin_unlock(&o2hb_live_lock);
}
static int o2hb_check_slot(struct o2hb_region *reg,
slot->ds_equal_samples = 0;
}
out:
- o2hb_set_quorum_device(reg, slot);
-
spin_unlock(&o2hb_live_lock);
o2hb_run_event_list(&event);
static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
{
- int i, ret, highest_node, change = 0;
+ int i, ret, highest_node;
+ int membership_change = 0, own_slot_ok = 0;
unsigned long configured_nodes[BITS_TO_LONGS(O2NM_MAX_NODES)];
unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
struct o2hb_bio_wait_ctxt write_wc;
sizeof(configured_nodes));
if (ret) {
mlog_errno(ret);
- return ret;
+ goto bail;
}
/*
highest_node = o2hb_highest_node(configured_nodes, O2NM_MAX_NODES);
if (highest_node >= O2NM_MAX_NODES) {
- mlog(ML_NOTICE, "ocfs2_heartbeat: no configured nodes found!\n");
- return -EINVAL;
+ mlog(ML_NOTICE, "o2hb: No configured nodes found!\n");
+ ret = -EINVAL;
+ goto bail;
}
/* No sense in reading the slots of nodes that don't exist
ret = o2hb_read_slots(reg, highest_node + 1);
if (ret < 0) {
mlog_errno(ret);
- return ret;
+ goto bail;
}
/* With an up to date view of the slots, we can check that no
* other node has been improperly configured to heartbeat in
* our slot. */
- o2hb_check_last_timestamp(reg);
+ own_slot_ok = o2hb_check_own_slot(reg);
/* fill in the proper info for our next heartbeat */
o2hb_prepare_block(reg, reg->hr_generation);
- /* And fire off the write. Note that we don't wait on this I/O
- * until later. */
ret = o2hb_issue_node_write(reg, &write_wc);
if (ret < 0) {
mlog_errno(ret);
- return ret;
+ goto bail;
}
i = -1;
while((i = find_next_bit(configured_nodes,
O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
- change |= o2hb_check_slot(reg, ®->hr_slots[i]);
+ membership_change |= o2hb_check_slot(reg, ®->hr_slots[i]);
}
/*
* disk */
mlog(ML_ERROR, "Write error %d on device \"%s\"\n",
write_wc.wc_error, reg->hr_dev_name);
- return write_wc.wc_error;
+ ret = write_wc.wc_error;
+ goto bail;
}
- o2hb_arm_write_timeout(reg);
+ /* Skip disarming the timeout if own slot has stale/bad data */
+ if (own_slot_ok) {
+ o2hb_set_quorum_device(reg);
+ o2hb_arm_write_timeout(reg);
+ }
+bail:
/* let the person who launched us know when things are steady */
- if (!change && (atomic_read(®->hr_steady_iterations) != 0)) {
- if (atomic_dec_and_test(®->hr_steady_iterations))
+ if (atomic_read(®->hr_steady_iterations) != 0) {
+ if (!ret && own_slot_ok && !membership_change) {
+ if (atomic_dec_and_test(®->hr_steady_iterations))
+ wake_up(&o2hb_steady_queue);
+ }
+ }
+
+ if (atomic_read(®->hr_steady_iterations) != 0) {
+ if (atomic_dec_and_test(®->hr_unsteady_iterations)) {
+ printk(KERN_NOTICE "o2hb: Unable to stabilize "
+ "heartbeart on region %s (%s)\n",
+ config_item_name(®->hr_item),
+ reg->hr_dev_name);
+ atomic_set(®->hr_steady_iterations, 0);
+ reg->hr_aborted_start = 1;
wake_up(&o2hb_steady_queue);
+ ret = -EIO;
+ }
}
- return 0;
+ return ret;
}
/* Subtract b from a, storing the result in a. a *must* have a larger
/* Pin node */
o2nm_depend_this_node();
- while (!kthread_should_stop() && !reg->hr_unclean_stop) {
+ while (!kthread_should_stop() &&
+ !reg->hr_unclean_stop && !reg->hr_aborted_start) {
/* We track the time spent inside
* o2hb_do_disk_heartbeat so that we avoid more than
* hr_timeout_ms between disk writes. On busy systems
* likely to time itself out. */
do_gettimeofday(&before_hb);
- i = 0;
- do {
- ret = o2hb_do_disk_heartbeat(reg);
- } while (ret && ++i < 2);
+ ret = o2hb_do_disk_heartbeat(reg);
do_gettimeofday(&after_hb);
elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
elapsed_msec);
- if (elapsed_msec < reg->hr_timeout_ms) {
+ if (!kthread_should_stop() &&
+ elapsed_msec < reg->hr_timeout_ms) {
/* the kthread api has blocked signals for us so no
* need to record the return value. */
msleep_interruptible(reg->hr_timeout_ms - elapsed_msec);
* to timeout on this region when we could just as easily
* write a clear generation - thus indicating to them that
* this node has left this region.
- *
- * XXX: Should we skip this on unclean_stop? */
- o2hb_prepare_block(reg, 0);
- ret = o2hb_issue_node_write(reg, &write_wc);
- if (ret == 0) {
- o2hb_wait_on_io(reg, &write_wc);
- } else {
- mlog_errno(ret);
+ */
+ if (!reg->hr_unclean_stop && !reg->hr_aborted_start) {
+ o2hb_prepare_block(reg, 0);
+ ret = o2hb_issue_node_write(reg, &write_wc);
+ if (ret == 0)
+ o2hb_wait_on_io(reg, &write_wc);
+ else
+ mlog_errno(ret);
}
/* Unpin node */
o2nm_undepend_this_node();
- mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread exiting\n");
+ mlog(ML_HEARTBEAT|ML_KTHREAD, "o2hb thread exiting\n");
return 0;
}
struct o2hb_debug_buf *db = inode->i_private;
struct o2hb_region *reg;
unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+ unsigned long lts;
char *buf = NULL;
int i = -1;
int out = 0;
case O2HB_DB_TYPE_REGION_ELAPSED_TIME:
reg = (struct o2hb_region *)db->db_data;
- out += snprintf(buf + out, PAGE_SIZE - out, "%u\n",
- jiffies_to_msecs(jiffies -
- reg->hr_last_timeout_start));
+ lts = reg->hr_last_timeout_start;
+ /* If 0, it has never been set before */
+ if (lts)
+ lts = jiffies_to_msecs(jiffies - lts);
+ out += snprintf(buf + out, PAGE_SIZE - out, "%lu\n", lts);
goto done;
case O2HB_DB_TYPE_REGION_PINNED:
struct page *page;
struct o2hb_region *reg = to_o2hb_region(item);
+ mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
+
if (reg->hr_tmp_block)
kfree(reg->hr_tmp_block);
live_threshold <<= 1;
spin_unlock(&o2hb_live_lock);
}
- atomic_set(®->hr_steady_iterations, live_threshold + 1);
+ ++live_threshold;
+ atomic_set(®->hr_steady_iterations, live_threshold);
+ /* unsteady_iterations is double the steady_iterations */
+ atomic_set(®->hr_unsteady_iterations, (live_threshold << 1));
hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s",
reg->hr_item.ci_name);
ret = wait_event_interruptible(o2hb_steady_queue,
atomic_read(®->hr_steady_iterations) == 0);
if (ret) {
- /* We got interrupted (hello ptrace!). Clean up */
- spin_lock(&o2hb_live_lock);
- hb_task = reg->hr_task;
- reg->hr_task = NULL;
- spin_unlock(&o2hb_live_lock);
+ atomic_set(®->hr_steady_iterations, 0);
+ reg->hr_aborted_start = 1;
+ }
- if (hb_task)
- kthread_stop(hb_task);
+ if (reg->hr_aborted_start) {
+ ret = -EIO;
goto out;
}
ret = -EIO;
if (hb_task && o2hb_global_heartbeat_active())
- printk(KERN_NOTICE "o2hb: Heartbeat started on region %s\n",
- config_item_name(®->hr_item));
+ printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
+ config_item_name(®->hr_item), reg->hr_dev_name);
out:
if (filp)
/* stop the thread when the user removes the region dir */
spin_lock(&o2hb_live_lock);
- if (o2hb_global_heartbeat_active()) {
- clear_bit(reg->hr_region_num, o2hb_region_bitmap);
- clear_bit(reg->hr_region_num, o2hb_live_region_bitmap);
- if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
- quorum_region = 1;
- clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
- }
hb_task = reg->hr_task;
reg->hr_task = NULL;
reg->hr_item_dropped = 1;
if (hb_task)
kthread_stop(hb_task);
+ if (o2hb_global_heartbeat_active()) {
+ spin_lock(&o2hb_live_lock);
+ clear_bit(reg->hr_region_num, o2hb_region_bitmap);
+ clear_bit(reg->hr_region_num, o2hb_live_region_bitmap);
+ if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+ quorum_region = 1;
+ clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
+ spin_unlock(&o2hb_live_lock);
+ printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n",
+ ((atomic_read(®->hr_steady_iterations) == 0) ?
+ "stopped" : "start aborted"), config_item_name(item),
+ reg->hr_dev_name);
+ }
+
/*
* If we're racing a dev_write(), we need to wake them. They will
* check reg->hr_task
*/
if (atomic_read(®->hr_steady_iterations) != 0) {
+ reg->hr_aborted_start = 1;
atomic_set(®->hr_steady_iterations, 0);
wake_up(&o2hb_steady_queue);
}
- if (o2hb_global_heartbeat_active())
- printk(KERN_NOTICE "o2hb: Heartbeat stopped on region %s\n",
- config_item_name(®->hr_item));
-
config_item_put(item);
if (!o2hb_global_heartbeat_active() || !quorum_region)
#define SC_DEBUG_NAME "sock_containers"
#define NST_DEBUG_NAME "send_tracking"
#define STATS_DEBUG_NAME "stats"
+#define NODES_DEBUG_NAME "connected_nodes"
#define SHOW_SOCK_CONTAINERS 0
#define SHOW_SOCK_STATS 1
static struct dentry *sc_dentry;
static struct dentry *nst_dentry;
static struct dentry *stats_dentry;
+static struct dentry *nodes_dentry;
static DEFINE_SPINLOCK(o2net_debug_lock);
.release = sc_fop_release,
};
-int o2net_debugfs_init(void)
+static int o2net_fill_bitmap(char *buf, int len)
{
- o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
- if (!o2net_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
+ unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+ int i = -1, out = 0;
- nst_dentry = debugfs_create_file(NST_DEBUG_NAME, S_IFREG|S_IRUSR,
- o2net_dentry, NULL,
- &nst_seq_fops);
- if (!nst_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
+ o2net_fill_node_map(map, sizeof(map));
- sc_dentry = debugfs_create_file(SC_DEBUG_NAME, S_IFREG|S_IRUSR,
- o2net_dentry, NULL,
- &sc_seq_fops);
- if (!sc_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
+ while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+ out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i);
+ out += snprintf(buf + out, PAGE_SIZE - out, "\n");
- stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, S_IFREG|S_IRUSR,
- o2net_dentry, NULL,
- &stats_seq_fops);
- if (!stats_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
+ return out;
+}
+
+static int nodes_fop_open(struct inode *inode, struct file *file)
+{
+ char *buf;
+
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ i_size_write(inode, o2net_fill_bitmap(buf, PAGE_SIZE));
+
+ file->private_data = buf;
return 0;
-bail:
- debugfs_remove(stats_dentry);
- debugfs_remove(sc_dentry);
- debugfs_remove(nst_dentry);
- debugfs_remove(o2net_dentry);
- return -ENOMEM;
}
+static int o2net_debug_release(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
+static ssize_t o2net_debug_read(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+ i_size_read(file->f_mapping->host));
+}
+
+static const struct file_operations nodes_fops = {
+ .open = nodes_fop_open,
+ .release = o2net_debug_release,
+ .read = o2net_debug_read,
+ .llseek = generic_file_llseek,
+};
+
void o2net_debugfs_exit(void)
{
+ debugfs_remove(nodes_dentry);
debugfs_remove(stats_dentry);
debugfs_remove(sc_dentry);
debugfs_remove(nst_dentry);
debugfs_remove(o2net_dentry);
}
+int o2net_debugfs_init(void)
+{
+ mode_t mode = S_IFREG|S_IRUSR;
+
+ o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
+ if (o2net_dentry)
+ nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode,
+ o2net_dentry, NULL, &nst_seq_fops);
+ if (nst_dentry)
+ sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode,
+ o2net_dentry, NULL, &sc_seq_fops);
+ if (sc_dentry)
+ stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode,
+ o2net_dentry, NULL, &stats_seq_fops);
+ if (stats_dentry)
+ nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode,
+ o2net_dentry, NULL, &nodes_fops);
+ if (nodes_dentry)
+ return 0;
+
+ o2net_debugfs_exit();
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
+}
+
#endif /* CONFIG_DEBUG_FS */
}
if (was_valid && !valid) {
- printk(KERN_NOTICE "o2net: no longer connected to "
+ printk(KERN_NOTICE "o2net: No longer connected to "
SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
o2net_complete_nodes_nsw(nn);
}
cancel_delayed_work(&nn->nn_connect_expired);
printk(KERN_NOTICE "o2net: %s " SC_NODEF_FMT "\n",
o2nm_this_node() > sc->sc_node->nd_num ?
- "connected to" : "accepted connection from",
+ "Connected to" : "Accepted connection from",
SC_NODEF_ARGS(sc));
}
o2net_sc_queue_work(sc, &sc->sc_connect_work);
break;
default:
- printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT
+ printk(KERN_INFO "o2net: Connection to " SC_NODEF_FMT
" shutdown, state %d\n",
SC_NODEF_ARGS(sc), sk->sk_state);
o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
return ret;
}
+/* Get a map of all nodes to which this node is currently connected to */
+void o2net_fill_node_map(unsigned long *map, unsigned bytes)
+{
+ struct o2net_sock_container *sc;
+ int node, ret;
+
+ BUG_ON(bytes < (BITS_TO_LONGS(O2NM_MAX_NODES) * sizeof(unsigned long)));
+
+ memset(map, 0, bytes);
+ for (node = 0; node < O2NM_MAX_NODES; ++node) {
+ o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret);
+ if (!ret) {
+ set_bit(node, map);
+ sc_put(sc);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(o2net_fill_node_map);
+
int o2net_send_message_vec(u32 msg_type, u32 key, struct kvec *caller_vec,
size_t caller_veclen, u8 target_node, int *status)
{
struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
if (hand->protocol_version != cpu_to_be64(O2NET_PROTOCOL_VERSION)) {
- mlog(ML_NOTICE, SC_NODEF_FMT " advertised net protocol "
- "version %llu but %llu is required, disconnecting\n",
- SC_NODEF_ARGS(sc),
- (unsigned long long)be64_to_cpu(hand->protocol_version),
- O2NET_PROTOCOL_VERSION);
+ printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " Advertised net "
+ "protocol version %llu but %llu is required. "
+ "Disconnecting.\n", SC_NODEF_ARGS(sc),
+ (unsigned long long)be64_to_cpu(hand->protocol_version),
+ O2NET_PROTOCOL_VERSION);
/* don't bother reconnecting if its the wrong version. */
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
*/
if (be32_to_cpu(hand->o2net_idle_timeout_ms) !=
o2net_idle_timeout()) {
- mlog(ML_NOTICE, SC_NODEF_FMT " uses a network idle timeout of "
- "%u ms, but we use %u ms locally. disconnecting\n",
- SC_NODEF_ARGS(sc),
- be32_to_cpu(hand->o2net_idle_timeout_ms),
- o2net_idle_timeout());
+ printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a network "
+ "idle timeout of %u ms, but we use %u ms locally. "
+ "Disconnecting.\n", SC_NODEF_ARGS(sc),
+ be32_to_cpu(hand->o2net_idle_timeout_ms),
+ o2net_idle_timeout());
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
return -1;
}
if (be32_to_cpu(hand->o2net_keepalive_delay_ms) !=
o2net_keepalive_delay()) {
- mlog(ML_NOTICE, SC_NODEF_FMT " uses a keepalive delay of "
- "%u ms, but we use %u ms locally. disconnecting\n",
- SC_NODEF_ARGS(sc),
- be32_to_cpu(hand->o2net_keepalive_delay_ms),
- o2net_keepalive_delay());
+ printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a keepalive "
+ "delay of %u ms, but we use %u ms locally. "
+ "Disconnecting.\n", SC_NODEF_ARGS(sc),
+ be32_to_cpu(hand->o2net_keepalive_delay_ms),
+ o2net_keepalive_delay());
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
return -1;
}
if (be32_to_cpu(hand->o2hb_heartbeat_timeout_ms) !=
O2HB_MAX_WRITE_TIMEOUT_MS) {
- mlog(ML_NOTICE, SC_NODEF_FMT " uses a heartbeat timeout of "
- "%u ms, but we use %u ms locally. disconnecting\n",
- SC_NODEF_ARGS(sc),
- be32_to_cpu(hand->o2hb_heartbeat_timeout_ms),
- O2HB_MAX_WRITE_TIMEOUT_MS);
+ printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a heartbeat "
+ "timeout of %u ms, but we use %u ms locally. "
+ "Disconnecting.\n", SC_NODEF_ARGS(sc),
+ be32_to_cpu(hand->o2hb_heartbeat_timeout_ms),
+ O2HB_MAX_WRITE_TIMEOUT_MS);
o2net_ensure_shutdown(nn, sc, -ENOTCONN);
return -1;
}
{
struct o2net_sock_container *sc = (struct o2net_sock_container *)data;
struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
-
#ifdef CONFIG_DEBUG_FS
- ktime_t now = ktime_get();
+ unsigned long msecs = ktime_to_ms(ktime_get()) -
+ ktime_to_ms(sc->sc_tv_timer);
+#else
+ unsigned long msecs = o2net_idle_timeout();
#endif
- printk(KERN_NOTICE "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u "
- "seconds, shutting it down.\n", SC_NODEF_ARGS(sc),
- o2net_idle_timeout() / 1000,
- o2net_idle_timeout() % 1000);
-
-#ifdef CONFIG_DEBUG_FS
- mlog(ML_NOTICE, "Here are some times that might help debug the "
- "situation: (Timer: %lld, Now %lld, DataReady %lld, Advance %lld-%lld, "
- "Key 0x%08x, Func %u, FuncTime %lld-%lld)\n",
- (long long)ktime_to_us(sc->sc_tv_timer), (long long)ktime_to_us(now),
- (long long)ktime_to_us(sc->sc_tv_data_ready),
- (long long)ktime_to_us(sc->sc_tv_advance_start),
- (long long)ktime_to_us(sc->sc_tv_advance_stop),
- sc->sc_msg_key, sc->sc_msg_type,
- (long long)ktime_to_us(sc->sc_tv_func_start),
- (long long)ktime_to_us(sc->sc_tv_func_stop));
-#endif
+ printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been "
+ "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc),
+ msecs / 1000, msecs % 1000);
/*
* Initialize the nn_timeout so that the next connection attempt
out:
if (ret) {
- mlog(ML_NOTICE, "connect attempt to " SC_NODEF_FMT " failed "
- "with errno %d\n", SC_NODEF_ARGS(sc), ret);
+ printk(KERN_NOTICE "o2net: Connect attempt to " SC_NODEF_FMT
+ " failed with errno %d\n", SC_NODEF_ARGS(sc), ret);
/* 0 err so that another will be queued and attempted
* from set_nn_state */
if (sc)
spin_lock(&nn->nn_lock);
if (!nn->nn_sc_valid) {
- mlog(ML_ERROR, "no connection established with node %u after "
- "%u.%u seconds, giving up and returning errors.\n",
+ printk(KERN_NOTICE "o2net: No connection established with "
+ "node %u after %u.%u seconds, giving up.\n",
o2net_num_from_nn(nn),
o2net_idle_timeout() / 1000,
o2net_idle_timeout() % 1000);
node = o2nm_get_node_by_ip(sin.sin_addr.s_addr);
if (node == NULL) {
- mlog(ML_NOTICE, "attempt to connect from unknown node at %pI4:%d\n",
- &sin.sin_addr.s_addr, ntohs(sin.sin_port));
+ printk(KERN_NOTICE "o2net: Attempt to connect from unknown "
+ "node at %pI4:%d\n", &sin.sin_addr.s_addr,
+ ntohs(sin.sin_port));
ret = -EINVAL;
goto out;
}
if (o2nm_this_node() >= node->nd_num) {
local_node = o2nm_get_node_by_num(o2nm_this_node());
- mlog(ML_NOTICE, "unexpected connect attempt seen at node '%s' ("
- "%u, %pI4:%d) from node '%s' (%u, %pI4:%d)\n",
- local_node->nd_name, local_node->nd_num,
- &(local_node->nd_ipv4_address),
- ntohs(local_node->nd_ipv4_port),
- node->nd_name, node->nd_num, &sin.sin_addr.s_addr,
- ntohs(sin.sin_port));
+ printk(KERN_NOTICE "o2net: Unexpected connect attempt seen "
+ "at node '%s' (%u, %pI4:%d) from node '%s' (%u, "
+ "%pI4:%d)\n", local_node->nd_name, local_node->nd_num,
+ &(local_node->nd_ipv4_address),
+ ntohs(local_node->nd_ipv4_port), node->nd_name,
+ node->nd_num, &sin.sin_addr.s_addr, ntohs(sin.sin_port));
ret = -EINVAL;
goto out;
}
ret = 0;
spin_unlock(&nn->nn_lock);
if (ret) {
- mlog(ML_NOTICE, "attempt to connect from node '%s' at "
- "%pI4:%d but it already has an open connection\n",
- node->nd_name, &sin.sin_addr.s_addr,
- ntohs(sin.sin_port));
+ printk(KERN_NOTICE "o2net: Attempt to connect from node '%s' "
+ "at %pI4:%d but it already has an open connection\n",
+ node->nd_name, &sin.sin_addr.s_addr,
+ ntohs(sin.sin_port));
goto out;
}
ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
if (ret < 0) {
- mlog(ML_ERROR, "unable to create socket, ret=%d\n", ret);
+ printk(KERN_ERR "o2net: Error %d while creating socket\n", ret);
goto out;
}
sock->sk->sk_reuse = 1;
ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
if (ret < 0) {
- mlog(ML_ERROR, "unable to bind socket at %pI4:%u, "
- "ret=%d\n", &addr, ntohs(port), ret);
+ printk(KERN_ERR "o2net: Error %d while binding socket at "
+ "%pI4:%u\n", ret, &addr, ntohs(port));
goto out;
}
ret = sock->ops->listen(sock, 64);
- if (ret < 0) {
- mlog(ML_ERROR, "unable to listen on %pI4:%u, ret=%d\n",
- &addr, ntohs(port), ret);
- }
+ if (ret < 0)
+ printk(KERN_ERR "o2net: Error %d while listening on %pI4:%u\n",
+ ret, &addr, ntohs(port));
out:
if (ret) {
struct list_head *unreg_list);
void o2net_unregister_handler_list(struct list_head *list);
+void o2net_fill_node_map(unsigned long *map, unsigned bytes);
+
struct o2nm_node;
int o2net_register_hb_callbacks(void);
void o2net_unregister_hb_callbacks(void);
if (pde)
le16_add_cpu(&pde->rec_len,
le16_to_cpu(de->rec_len));
- else
- de->inode = 0;
+ de->inode = 0;
dir->i_version++;
ocfs2_journal_dirty(handle, bh);
goto bail;
void dlm_wait_for_recovery(struct dlm_ctxt *dlm);
void dlm_kick_recovery_thread(struct dlm_ctxt *dlm);
int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node);
-int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
-int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout);
+void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
+void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout);
void dlm_put(struct dlm_ctxt *dlm);
struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm);
kref_get(&res->refs);
}
void dlm_lockres_put(struct dlm_lock_resource *res);
-void __dlm_unhash_lockres(struct dlm_lock_resource *res);
-void __dlm_insert_lockres(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res);
+void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
+void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm,
const char *name,
unsigned int len,
const char *name,
unsigned int namelen);
-#define dlm_lockres_set_refmap_bit(bit,res) \
- __dlm_lockres_set_refmap_bit(bit,res,__FILE__,__LINE__)
-#define dlm_lockres_clear_refmap_bit(bit,res) \
- __dlm_lockres_clear_refmap_bit(bit,res,__FILE__,__LINE__)
+void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int bit);
+void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int bit);
-static inline void __dlm_lockres_set_refmap_bit(int bit,
- struct dlm_lock_resource *res,
- const char *file,
- int line)
-{
- //printk("%s:%d:%.*s: setting bit %d\n", file, line,
- // res->lockname.len, res->lockname.name, bit);
- set_bit(bit, res->refmap);
-}
-
-static inline void __dlm_lockres_clear_refmap_bit(int bit,
- struct dlm_lock_resource *res,
- const char *file,
- int line)
-{
- //printk("%s:%d:%.*s: clearing bit %d\n", file, line,
- // res->lockname.len, res->lockname.name, bit);
- clear_bit(bit, res->refmap);
-}
-
-void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res,
- const char *file,
- int line);
-void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res,
- int new_lockres,
- const char *file,
- int line);
-#define dlm_lockres_drop_inflight_ref(d,r) \
- __dlm_lockres_drop_inflight_ref(d,r,__FILE__,__LINE__)
-#define dlm_lockres_grab_inflight_ref(d,r) \
- __dlm_lockres_grab_inflight_ref(d,r,0,__FILE__,__LINE__)
-#define dlm_lockres_grab_inflight_ref_new(d,r) \
- __dlm_lockres_grab_inflight_ref(d,r,1,__FILE__,__LINE__)
+void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res);
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res);
void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm);
-void __dlm_unhash_lockres(struct dlm_lock_resource *lockres)
+void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
{
- if (!hlist_unhashed(&lockres->hash_node)) {
- hlist_del_init(&lockres->hash_node);
- dlm_lockres_put(lockres);
- }
+ if (hlist_unhashed(&res->hash_node))
+ return;
+
+ mlog(0, "%s: Unhash res %.*s\n", dlm->name, res->lockname.len,
+ res->lockname.name);
+ hlist_del_init(&res->hash_node);
+ dlm_lockres_put(res);
}
-void __dlm_insert_lockres(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res)
+void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
{
struct hlist_head *bucket;
struct qstr *q;
dlm_lockres_get(res);
hlist_add_head(&res->hash_node, bucket);
+
+ mlog(0, "%s: Hash res %.*s\n", dlm->name, res->lockname.len,
+ res->lockname.name);
}
struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm,
static void __dlm_print_nodes(struct dlm_ctxt *dlm)
{
- int node = -1;
+ int node = -1, num = 0;
assert_spin_locked(&dlm->spinlock);
- printk(KERN_NOTICE "o2dlm: Nodes in domain %s: ", dlm->name);
-
+ printk("( ");
while ((node = find_next_bit(dlm->domain_map, O2NM_MAX_NODES,
node + 1)) < O2NM_MAX_NODES) {
printk("%d ", node);
+ ++num;
}
- printk("\n");
+ printk(") %u nodes\n", num);
}
static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
node = exit_msg->node_idx;
- printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s\n", node, dlm->name);
-
spin_lock(&dlm->spinlock);
clear_bit(node, dlm->domain_map);
clear_bit(node, dlm->exit_domain_map);
+ printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s ", node, dlm->name);
__dlm_print_nodes(dlm);
/* notify anything attached to the heartbeat events */
dlm_mark_domain_leaving(dlm);
dlm_leave_domain(dlm);
+ printk(KERN_NOTICE "o2dlm: Leaving domain %s\n", dlm->name);
dlm_force_free_mles(dlm);
dlm_complete_dlm_shutdown(dlm);
}
clear_bit(assert->node_idx, dlm->exit_domain_map);
__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
- printk(KERN_NOTICE "o2dlm: Node %u joins domain %s\n",
+ printk(KERN_NOTICE "o2dlm: Node %u joins domain %s ",
assert->node_idx, dlm->name);
__dlm_print_nodes(dlm);
bail:
spin_lock(&dlm->spinlock);
__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
- if (!status)
+ if (!status) {
+ printk(KERN_NOTICE "o2dlm: Joining domain %s ", dlm->name);
__dlm_print_nodes(dlm);
+ }
spin_unlock(&dlm->spinlock);
if (ctxt) {
goto leave;
}
- if (!o2hb_check_local_node_heartbeating()) {
- mlog(ML_ERROR, "the local node has not been configured, or is "
- "not heartbeating\n");
- ret = -EPROTO;
- goto leave;
- }
-
mlog(0, "register called for domain \"%s\"\n", domain);
retry:
kick_thread = 1;
}
}
- /* reduce the inflight count, this may result in the lockres
- * being purged below during calc_usage */
- if (lock->ml.node == dlm->node_num)
- dlm_lockres_drop_inflight_ref(dlm, res);
spin_unlock(&res->spinlock);
wake_up(&res->wq);
lock->ml.type, res->lockname.len,
res->lockname.name, flags);
+ /*
+ * Wait if resource is getting recovered, remastered, etc.
+ * If the resource was remastered and new owner is self, then exit.
+ */
spin_lock(&res->spinlock);
-
- /* will exit this call with spinlock held */
__dlm_wait_on_lockres(res);
+ if (res->owner == dlm->node_num) {
+ spin_unlock(&res->spinlock);
+ return DLM_RECOVERING;
+ }
res->state |= DLM_LOCK_RES_IN_PROGRESS;
/* add lock to local (secondary) queue */
tmpret = o2net_send_message(DLM_CREATE_LOCK_MSG, dlm->key, &create,
sizeof(create), res->owner, &status);
if (tmpret >= 0) {
- // successfully sent and received
- ret = status; // this is already a dlm_status
+ ret = status;
if (ret == DLM_REJECTED) {
- mlog(ML_ERROR, "%s:%.*s: BUG. this is a stale lockres "
- "no longer owned by %u. that node is coming back "
- "up currently.\n", dlm->name, create.namelen,
+ mlog(ML_ERROR, "%s: res %.*s, Stale lockres no longer "
+ "owned by node %u. That node is coming back up "
+ "currently.\n", dlm->name, create.namelen,
create.name, res->owner);
dlm_print_one_lock_resource(res);
BUG();
}
} else {
- mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
- "node %u\n", tmpret, DLM_CREATE_LOCK_MSG, dlm->key,
- res->owner);
- if (dlm_is_host_down(tmpret)) {
+ mlog(ML_ERROR, "%s: res %.*s, Error %d send CREATE LOCK to "
+ "node %u\n", dlm->name, create.namelen, create.name,
+ tmpret, res->owner);
+ if (dlm_is_host_down(tmpret))
ret = DLM_RECOVERING;
- mlog(0, "node %u died so returning DLM_RECOVERING "
- "from lock message!\n", res->owner);
- } else {
+ else
ret = dlm_err_to_dlm_status(tmpret);
- }
}
return ret;
/* zero memory only if kernel-allocated */
lksb = kzalloc(sizeof(*lksb), GFP_NOFS);
if (!lksb) {
- kfree(lock);
+ kmem_cache_free(dlm_lock_cache, lock);
return NULL;
}
kernel_allocated = 1;
if (status == DLM_RECOVERING || status == DLM_MIGRATING ||
status == DLM_FORWARD) {
- mlog(0, "retrying lock with migration/"
- "recovery/in progress\n");
msleep(100);
- /* no waiting for dlm_reco_thread */
if (recovery) {
if (status != DLM_RECOVERING)
goto retry_lock;
-
- mlog(0, "%s: got RECOVERING "
- "for $RECOVERY lock, master "
- "was %u\n", dlm->name,
- res->owner);
/* wait to see the node go down, then
* drop down and allow the lockres to
* get cleaned up. need to remaster. */
}
}
+ /* Inflight taken in dlm_get_lock_resource() is dropped here */
+ spin_lock(&res->spinlock);
+ dlm_lockres_drop_inflight_ref(dlm, res);
+ spin_unlock(&res->spinlock);
+
+ dlm_lockres_calc_usage(dlm, res);
+ dlm_kick_thread(dlm, res);
+
if (status != DLM_NORMAL) {
lock->lksb->flags &= ~DLM_LKSB_GET_LVB;
if (status != DLM_NOTQUEUED)
return NULL;
}
-void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res,
- int new_lockres,
- const char *file,
- int line)
+void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int bit)
{
- if (!new_lockres)
- assert_spin_locked(&res->spinlock);
+ assert_spin_locked(&res->spinlock);
+
+ mlog(0, "res %.*s, set node %u, %ps()\n", res->lockname.len,
+ res->lockname.name, bit, __builtin_return_address(0));
+
+ set_bit(bit, res->refmap);
+}
+
+void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res, int bit)
+{
+ assert_spin_locked(&res->spinlock);
+
+ mlog(0, "res %.*s, clr node %u, %ps()\n", res->lockname.len,
+ res->lockname.name, bit, __builtin_return_address(0));
+
+ clear_bit(bit, res->refmap);
+}
+
+
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ assert_spin_locked(&res->spinlock);
- if (!test_bit(dlm->node_num, res->refmap)) {
- BUG_ON(res->inflight_locks != 0);
- dlm_lockres_set_refmap_bit(dlm->node_num, res);
- }
res->inflight_locks++;
- mlog(0, "%s:%.*s: inflight++: now %u\n",
- dlm->name, res->lockname.len, res->lockname.name,
- res->inflight_locks);
+
+ mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
+ res->lockname.len, res->lockname.name, res->inflight_locks,
+ __builtin_return_address(0));
}
-void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
- struct dlm_lock_resource *res,
- const char *file,
- int line)
+void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
{
assert_spin_locked(&res->spinlock);
BUG_ON(res->inflight_locks == 0);
+
res->inflight_locks--;
- mlog(0, "%s:%.*s: inflight--: now %u\n",
- dlm->name, res->lockname.len, res->lockname.name,
- res->inflight_locks);
- if (res->inflight_locks == 0)
- dlm_lockres_clear_refmap_bit(dlm->node_num, res);
+
+ mlog(0, "%s: res %.*s, inflight--: now %u, %ps()\n", dlm->name,
+ res->lockname.len, res->lockname.name, res->inflight_locks,
+ __builtin_return_address(0));
+
wake_up(&res->wq);
}
unsigned int hash;
int tries = 0;
int bit, wait_on_recovery = 0;
- int drop_inflight_if_nonlocal = 0;
BUG_ON(!lockid);
spin_lock(&dlm->spinlock);
tmpres = __dlm_lookup_lockres_full(dlm, lockid, namelen, hash);
if (tmpres) {
- int dropping_ref = 0;
-
spin_unlock(&dlm->spinlock);
-
spin_lock(&tmpres->spinlock);
- /* We wait for the other thread that is mastering the resource */
+ /* Wait on the thread that is mastering the resource */
if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
__dlm_wait_on_lockres(tmpres);
BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN);
+ spin_unlock(&tmpres->spinlock);
+ dlm_lockres_put(tmpres);
+ tmpres = NULL;
+ goto lookup;
}
- if (tmpres->owner == dlm->node_num) {
- BUG_ON(tmpres->state & DLM_LOCK_RES_DROPPING_REF);
- dlm_lockres_grab_inflight_ref(dlm, tmpres);
- } else if (tmpres->state & DLM_LOCK_RES_DROPPING_REF)
- dropping_ref = 1;
- spin_unlock(&tmpres->spinlock);
-
- /* wait until done messaging the master, drop our ref to allow
- * the lockres to be purged, start over. */
- if (dropping_ref) {
- spin_lock(&tmpres->spinlock);
- __dlm_wait_on_lockres_flags(tmpres, DLM_LOCK_RES_DROPPING_REF);
+ /* Wait on the resource purge to complete before continuing */
+ if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) {
+ BUG_ON(tmpres->owner == dlm->node_num);
+ __dlm_wait_on_lockres_flags(tmpres,
+ DLM_LOCK_RES_DROPPING_REF);
spin_unlock(&tmpres->spinlock);
dlm_lockres_put(tmpres);
tmpres = NULL;
goto lookup;
}
- mlog(0, "found in hash!\n");
+ /* Grab inflight ref to pin the resource */
+ dlm_lockres_grab_inflight_ref(dlm, tmpres);
+
+ spin_unlock(&tmpres->spinlock);
if (res)
dlm_lockres_put(res);
res = tmpres;
* but they might own this lockres. wait on them. */
bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
if (bit < O2NM_MAX_NODES) {
- mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to "
- "recover before lock mastery can begin\n",
+ mlog(0, "%s: res %.*s, At least one node (%d) "
+ "to recover before lock mastery can begin\n",
dlm->name, namelen, (char *)lockid, bit);
wait_on_recovery = 1;
}
/* finally add the lockres to its hash bucket */
__dlm_insert_lockres(dlm, res);
- /* since this lockres is new it doesn't not require the spinlock */
- dlm_lockres_grab_inflight_ref_new(dlm, res);
- /* if this node does not become the master make sure to drop
- * this inflight reference below */
- drop_inflight_if_nonlocal = 1;
+ /* Grab inflight ref to pin the resource */
+ spin_lock(&res->spinlock);
+ dlm_lockres_grab_inflight_ref(dlm, res);
+ spin_unlock(&res->spinlock);
/* get an extra ref on the mle in case this is a BLOCK
* if so, the creator of the BLOCK may try to put the last
* dlm spinlock would be detectable be a change on the mle,
* so we only need to clear out the recovery map once. */
if (dlm_is_recovery_lock(lockid, namelen)) {
- mlog(ML_NOTICE, "%s: recovery map is not empty, but "
- "must master $RECOVERY lock now\n", dlm->name);
+ mlog(0, "%s: Recovery map is not empty, but must "
+ "master $RECOVERY lock now\n", dlm->name);
if (!dlm_pre_master_reco_lockres(dlm, res))
wait_on_recovery = 0;
else {
spin_lock(&dlm->spinlock);
bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
if (bit < O2NM_MAX_NODES) {
- mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to "
- "recover before lock mastery can begin\n",
+ mlog(0, "%s: res %.*s, At least one node (%d) "
+ "to recover before lock mastery can begin\n",
dlm->name, namelen, (char *)lockid, bit);
wait_on_recovery = 1;
} else
* yet, keep going until it does. this is how the
* master will know that asserts are needed back to
* the lower nodes. */
- mlog(0, "%s:%.*s: requests only up to %u but master "
- "is %u, keep going\n", dlm->name, namelen,
+ mlog(0, "%s: res %.*s, Requests only up to %u but "
+ "master is %u, keep going\n", dlm->name, namelen,
lockid, nodenum, mle->master);
}
}
ret = dlm_wait_for_lock_mastery(dlm, res, mle, &blocked);
if (ret < 0) {
wait_on_recovery = 1;
- mlog(0, "%s:%.*s: node map changed, redo the "
- "master request now, blocked=%d\n",
- dlm->name, res->lockname.len,
+ mlog(0, "%s: res %.*s, Node map changed, redo the master "
+ "request now, blocked=%d\n", dlm->name, res->lockname.len,
res->lockname.name, blocked);
if (++tries > 20) {
- mlog(ML_ERROR, "%s:%.*s: spinning on "
- "dlm_wait_for_lock_mastery, blocked=%d\n",
+ mlog(ML_ERROR, "%s: res %.*s, Spinning on "
+ "dlm_wait_for_lock_mastery, blocked = %d\n",
dlm->name, res->lockname.len,
res->lockname.name, blocked);
dlm_print_one_lock_resource(res);
goto redo_request;
}
- mlog(0, "lockres mastered by %u\n", res->owner);
+ mlog(0, "%s: res %.*s, Mastered by %u\n", dlm->name, res->lockname.len,
+ res->lockname.name, res->owner);
/* make sure we never continue without this */
BUG_ON(res->owner == O2NM_MAX_NODES);
wake_waiters:
spin_lock(&res->spinlock);
- if (res->owner != dlm->node_num && drop_inflight_if_nonlocal)
- dlm_lockres_drop_inflight_ref(dlm, res);
res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
spin_unlock(&res->spinlock);
wake_up(&res->wq);
}
if (res->owner == dlm->node_num) {
- mlog(0, "%s:%.*s: setting bit %u in refmap\n",
- dlm->name, namelen, name, request->node_idx);
- dlm_lockres_set_refmap_bit(request->node_idx, res);
+ dlm_lockres_set_refmap_bit(dlm, res, request->node_idx);
spin_unlock(&res->spinlock);
response = DLM_MASTER_RESP_YES;
if (mle)
* go back and clean the mles on any
* other nodes */
dispatch_assert = 1;
- dlm_lockres_set_refmap_bit(request->node_idx, res);
- mlog(0, "%s:%.*s: setting bit %u in refmap\n",
- dlm->name, namelen, name,
- request->node_idx);
+ dlm_lockres_set_refmap_bit(dlm, res,
+ request->node_idx);
} else
response = DLM_MASTER_RESP_NO;
} else {
"lockres, set the bit in the refmap\n",
namelen, lockname, to);
spin_lock(&res->spinlock);
- dlm_lockres_set_refmap_bit(to, res);
+ dlm_lockres_set_refmap_bit(dlm, res, to);
spin_unlock(&res->spinlock);
}
}
namelen = res->lockname.len;
BUG_ON(namelen > O2NM_MAX_NAME_LEN);
- mlog(0, "%s:%.*s: sending deref to %d\n",
- dlm->name, namelen, lockname, res->owner);
memset(&deref, 0, sizeof(deref));
deref.node_idx = dlm->node_num;
deref.namelen = namelen;
ret = o2net_send_message(DLM_DEREF_LOCKRES_MSG, dlm->key,
&deref, sizeof(deref), res->owner, &r);
if (ret < 0)
- mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
- "node %u\n", ret, DLM_DEREF_LOCKRES_MSG, dlm->key,
- res->owner);
+ mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF to node %u\n",
+ dlm->name, namelen, lockname, ret, res->owner);
else if (r < 0) {
/* BAD. other node says I did not have a ref. */
- mlog(ML_ERROR,"while dropping ref on %s:%.*s "
- "(master=%u) got %d.\n", dlm->name, namelen,
- lockname, res->owner, r);
+ mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
+ dlm->name, namelen, lockname, res->owner, r);
dlm_print_one_lock_resource(res);
BUG();
}
else {
BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
if (test_bit(node, res->refmap)) {
- dlm_lockres_clear_refmap_bit(node, res);
+ dlm_lockres_clear_refmap_bit(dlm, res, node);
cleared = 1;
}
}
BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
if (test_bit(node, res->refmap)) {
__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
- dlm_lockres_clear_refmap_bit(node, res);
+ dlm_lockres_clear_refmap_bit(dlm, res, node);
cleared = 1;
}
spin_unlock(&res->spinlock);
BUG_ON(!list_empty(&lock->bast_list));
BUG_ON(lock->ast_pending);
BUG_ON(lock->bast_pending);
- dlm_lockres_clear_refmap_bit(lock->ml.node, res);
+ dlm_lockres_clear_refmap_bit(dlm, res,
+ lock->ml.node);
list_del_init(&lock->list);
dlm_lock_put(lock);
/* In a normal unlock, we would have added a
mlog(0, "%s:%.*s: node %u had a ref to this "
"migrating lockres, clearing\n", dlm->name,
res->lockname.len, res->lockname.name, bit);
- dlm_lockres_clear_refmap_bit(bit, res);
+ dlm_lockres_clear_refmap_bit(dlm, res, bit);
}
bit++;
}
&migrate, sizeof(migrate), nodenum,
&status);
if (ret < 0) {
- mlog(ML_ERROR, "Error %d when sending message %u (key "
- "0x%x) to node %u\n", ret, DLM_MIGRATE_REQUEST_MSG,
- dlm->key, nodenum);
+ mlog(ML_ERROR, "%s: res %.*s, Error %d send "
+ "MIGRATE_REQUEST to node %u\n", dlm->name,
+ migrate.namelen, migrate.name, ret, nodenum);
if (!dlm_is_host_down(ret)) {
mlog(ML_ERROR, "unhandled error=%d!\n", ret);
BUG();
dlm->name, res->lockname.len, res->lockname.name,
nodenum);
spin_lock(&res->spinlock);
- dlm_lockres_set_refmap_bit(nodenum, res);
+ dlm_lockres_set_refmap_bit(dlm, res, nodenum);
spin_unlock(&res->spinlock);
}
}
* mastery reference here since old_master will briefly have
* a reference after the migration completes */
spin_lock(&res->spinlock);
- dlm_lockres_set_refmap_bit(old_master, res);
+ dlm_lockres_set_refmap_bit(dlm, res, old_master);
spin_unlock(&res->spinlock);
mlog(0, "now time to do a migrate request to other nodes\n");
}
-int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
+void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
{
- if (timeout) {
- mlog(ML_NOTICE, "%s: waiting %dms for notification of "
- "death of node %u\n", dlm->name, timeout, node);
+ if (dlm_is_node_dead(dlm, node))
+ return;
+
+ printk(KERN_NOTICE "o2dlm: Waiting on the death of node %u in "
+ "domain %s\n", node, dlm->name);
+
+ if (timeout)
wait_event_timeout(dlm->dlm_reco_thread_wq,
- dlm_is_node_dead(dlm, node),
- msecs_to_jiffies(timeout));
- } else {
- mlog(ML_NOTICE, "%s: waiting indefinitely for notification "
- "of death of node %u\n", dlm->name, node);
+ dlm_is_node_dead(dlm, node),
+ msecs_to_jiffies(timeout));
+ else
wait_event(dlm->dlm_reco_thread_wq,
dlm_is_node_dead(dlm, node));
- }
- /* for now, return 0 */
- return 0;
}
-int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout)
+void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout)
{
- if (timeout) {
- mlog(0, "%s: waiting %dms for notification of "
- "recovery of node %u\n", dlm->name, timeout, node);
+ if (dlm_is_node_recovered(dlm, node))
+ return;
+
+ printk(KERN_NOTICE "o2dlm: Waiting on the recovery of node %u in "
+ "domain %s\n", node, dlm->name);
+
+ if (timeout)
wait_event_timeout(dlm->dlm_reco_thread_wq,
- dlm_is_node_recovered(dlm, node),
- msecs_to_jiffies(timeout));
- } else {
- mlog(0, "%s: waiting indefinitely for notification "
- "of recovery of node %u\n", dlm->name, node);
+ dlm_is_node_recovered(dlm, node),
+ msecs_to_jiffies(timeout));
+ else
wait_event(dlm->dlm_reco_thread_wq,
dlm_is_node_recovered(dlm, node));
- }
- /* for now, return 0 */
- return 0;
}
/* callers of the top-level api calls (dlmlock/dlmunlock) should
{
spin_lock(&dlm->spinlock);
BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE);
+ printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n",
+ dlm->name, dlm->reco.dead_node);
dlm->reco.state |= DLM_RECO_STATE_ACTIVE;
spin_unlock(&dlm->spinlock);
}
BUG_ON(!(dlm->reco.state & DLM_RECO_STATE_ACTIVE));
dlm->reco.state &= ~DLM_RECO_STATE_ACTIVE;
spin_unlock(&dlm->spinlock);
+ printk(KERN_NOTICE "o2dlm: End recovery on domain %s\n", dlm->name);
wake_up(&dlm->reco.event);
}
+static void dlm_print_recovery_master(struct dlm_ctxt *dlm)
+{
+ printk(KERN_NOTICE "o2dlm: Node %u (%s) is the Recovery Master for the "
+ "dead node %u in domain %s\n", dlm->reco.new_master,
+ (dlm->node_num == dlm->reco.new_master ? "me" : "he"),
+ dlm->reco.dead_node, dlm->name);
+}
+
static int dlm_do_recovery(struct dlm_ctxt *dlm)
{
int status = 0;
}
mlog(0, "another node will master this recovery session.\n");
}
- mlog(0, "dlm=%s (%d), new_master=%u, this node=%u, dead_node=%u\n",
- dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.new_master,
- dlm->node_num, dlm->reco.dead_node);
+
+ dlm_print_recovery_master(dlm);
/* it is safe to start everything back up here
* because all of the dead node's lock resources
return 0;
master_here:
- mlog(ML_NOTICE, "(%d) Node %u is the Recovery Master for the Dead Node "
- "%u for Domain %s\n", task_pid_nr(dlm->dlm_reco_thread_task),
- dlm->node_num, dlm->reco.dead_node, dlm->name);
+ dlm_print_recovery_master(dlm);
status = dlm_remaster_locks(dlm, dlm->reco.dead_node);
if (status < 0) {
/* we should never hit this anymore */
- mlog(ML_ERROR, "error %d remastering locks for node %u, "
- "retrying.\n", status, dlm->reco.dead_node);
+ mlog(ML_ERROR, "%s: Error %d remastering locks for node %u, "
+ "retrying.\n", dlm->name, status, dlm->reco.dead_node);
/* yield a bit to allow any final network messages
* to get handled on remaining nodes */
msleep(100);
BUG_ON(ndata->state != DLM_RECO_NODE_DATA_INIT);
ndata->state = DLM_RECO_NODE_DATA_REQUESTING;
- mlog(0, "requesting lock info from node %u\n",
+ mlog(0, "%s: Requesting lock info from node %u\n", dlm->name,
ndata->node_num);
if (ndata->node_num == dlm->node_num) {
spin_unlock(&dlm_reco_state_lock);
}
- mlog(0, "done requesting all lock info\n");
+ mlog(0, "%s: Done requesting all lock info\n", dlm->name);
/* nodes should be sending reco data now
* just need to wait */
/* negative status is handled by caller */
if (ret < 0)
- mlog(ML_ERROR, "Error %d when sending message %u (key "
- "0x%x) to node %u\n", ret, DLM_LOCK_REQUEST_MSG,
- dlm->key, request_from);
-
+ mlog(ML_ERROR, "%s: Error %d send LOCK_REQUEST to node %u "
+ "to recover dead node %u\n", dlm->name, ret,
+ request_from, dead_node);
// return from here, then
// sleep until all received or error
return ret;
ret = o2net_send_message(DLM_RECO_DATA_DONE_MSG, dlm->key, &done_msg,
sizeof(done_msg), send_to, &tmpret);
if (ret < 0) {
- mlog(ML_ERROR, "Error %d when sending message %u (key "
- "0x%x) to node %u\n", ret, DLM_RECO_DATA_DONE_MSG,
- dlm->key, send_to);
+ mlog(ML_ERROR, "%s: Error %d send RECO_DATA_DONE to node %u "
+ "to recover dead node %u\n", dlm->name, ret, send_to,
+ dead_node);
if (!dlm_is_host_down(ret)) {
BUG();
}
if (ret < 0) {
/* XXX: negative status is not handled.
* this will end up killing this node. */
- mlog(ML_ERROR, "Error %d when sending message %u (key "
- "0x%x) to node %u\n", ret, DLM_MIG_LOCKRES_MSG,
- dlm->key, send_to);
+ mlog(ML_ERROR, "%s: res %.*s, Error %d send MIG_LOCKRES to "
+ "node %u (%s)\n", dlm->name, mres->lockname_len,
+ mres->lockname, ret, send_to,
+ (orig_flags & DLM_MRES_MIGRATION ?
+ "migration" : "recovery"));
} else {
/* might get an -ENOMEM back here */
ret = status;
dlm->name, mres->lockname_len, mres->lockname,
from);
spin_lock(&res->spinlock);
- dlm_lockres_set_refmap_bit(from, res);
+ dlm_lockres_set_refmap_bit(dlm, res, from);
spin_unlock(&res->spinlock);
added++;
break;
mlog(0, "%s:%.*s: added lock for node %u, "
"setting refmap bit\n", dlm->name,
res->lockname.len, res->lockname.name, ml->node);
- dlm_lockres_set_refmap_bit(ml->node, res);
+ dlm_lockres_set_refmap_bit(dlm, res, ml->node);
added++;
}
spin_unlock(&res->spinlock);
list_for_each_entry_safe(res, next, &dlm->reco.resources, recovering) {
if (res->owner == dead_node) {
+ mlog(0, "%s: res %.*s, Changing owner from %u to %u\n",
+ dlm->name, res->lockname.len, res->lockname.name,
+ res->owner, new_master);
list_del_init(&res->recovering);
spin_lock(&res->spinlock);
/* new_master has our reference from
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_lockres_hash(dlm, i);
hlist_for_each_entry(res, hash_iter, bucket, hash_node) {
- if (res->state & DLM_LOCK_RES_RECOVERING) {
- if (res->owner == dead_node) {
- mlog(0, "(this=%u) res %.*s owner=%u "
- "was not on recovering list, but "
- "clearing state anyway\n",
- dlm->node_num, res->lockname.len,
- res->lockname.name, new_master);
- } else if (res->owner == dlm->node_num) {
- mlog(0, "(this=%u) res %.*s owner=%u "
- "was not on recovering list, "
- "owner is THIS node, clearing\n",
- dlm->node_num, res->lockname.len,
- res->lockname.name, new_master);
- } else
- continue;
+ if (!(res->state & DLM_LOCK_RES_RECOVERING))
+ continue;
- if (!list_empty(&res->recovering)) {
- mlog(0, "%s:%.*s: lockres was "
- "marked RECOVERING, owner=%u\n",
- dlm->name, res->lockname.len,
- res->lockname.name, res->owner);
- list_del_init(&res->recovering);
- dlm_lockres_put(res);
- }
- spin_lock(&res->spinlock);
- /* new_master has our reference from
- * the lock state sent during recovery */
- dlm_change_lockres_owner(dlm, res, new_master);
- res->state &= ~DLM_LOCK_RES_RECOVERING;
- if (__dlm_lockres_has_locks(res))
- __dlm_dirty_lockres(dlm, res);
- spin_unlock(&res->spinlock);
- wake_up(&res->wq);
+ if (res->owner != dead_node &&
+ res->owner != dlm->node_num)
+ continue;
+
+ if (!list_empty(&res->recovering)) {
+ list_del_init(&res->recovering);
+ dlm_lockres_put(res);
}
+
+ /* new_master has our reference from
+ * the lock state sent during recovery */
+ mlog(0, "%s: res %.*s, Changing owner from %u to %u\n",
+ dlm->name, res->lockname.len, res->lockname.name,
+ res->owner, new_master);
+ spin_lock(&res->spinlock);
+ dlm_change_lockres_owner(dlm, res, new_master);
+ res->state &= ~DLM_LOCK_RES_RECOVERING;
+ if (__dlm_lockres_has_locks(res))
+ __dlm_dirty_lockres(dlm, res);
+ spin_unlock(&res->spinlock);
+ wake_up(&res->wq);
}
}
}
res->lockname.len, res->lockname.name, freed, dead_node);
__dlm_print_one_lock_resource(res);
}
- dlm_lockres_clear_refmap_bit(dead_node, res);
+ dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
} else if (test_bit(dead_node, res->refmap)) {
mlog(0, "%s:%.*s: dead node %u had a ref, but had "
"no locks and had not purged before dying\n", dlm->name,
res->lockname.len, res->lockname.name, dead_node);
- dlm_lockres_clear_refmap_bit(dead_node, res);
+ dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
}
/* do not kick thread yet */
dlm_revalidate_lvb(dlm, res, dead_node);
if (res->owner == dead_node) {
if (res->state & DLM_LOCK_RES_DROPPING_REF) {
- mlog(ML_NOTICE, "Ignore %.*s for "
+ mlog(ML_NOTICE, "%s: res %.*s, Skip "
"recovery as it is being freed\n",
- res->lockname.len,
+ dlm->name, res->lockname.len,
res->lockname.name);
} else
dlm_move_lockres_to_recovery_list(dlm,
{
int bit;
+ assert_spin_locked(&res->spinlock);
+
if (__dlm_lockres_has_locks(res))
return 0;
+ /* Locks are in the process of being created */
+ if (res->inflight_locks)
+ return 0;
+
if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
return 0;
if (res->state & DLM_LOCK_RES_RECOVERING)
return 0;
+ /* Another node has this resource with this node as the master */
bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
if (bit < O2NM_MAX_NODES)
return 0;
- /*
- * since the bit for dlm->node_num is not set, inflight_locks better
- * be zero
- */
- BUG_ON(res->inflight_locks != 0);
return 1;
}
/* clear our bit from the master's refmap, ignore errors */
ret = dlm_drop_lockres_ref(dlm, res);
if (ret < 0) {
- mlog(ML_ERROR, "%s: deref %.*s failed %d\n", dlm->name,
- res->lockname.len, res->lockname.name, ret);
if (!dlm_is_host_down(ret))
BUG();
}
BUG();
}
- __dlm_unhash_lockres(res);
+ __dlm_unhash_lockres(dlm, res);
/* lockres is not in the hash now. drop the flag and wake up
* any processes waiting in dlm_get_lock_resource. */
mlog(0, "inode %llu take PRMODE open lock\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
- if (ocfs2_mount_local(osb))
+ if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb))
goto out;
lockres = &OCFS2_I(inode)->ip_open_lockres;
(unsigned long long)OCFS2_I(inode)->ip_blkno,
write ? "EXMODE" : "PRMODE");
+ if (ocfs2_is_hard_readonly(osb)) {
+ if (write)
+ status = -EROFS;
+ goto out;
+ }
+
if (ocfs2_mount_local(osb))
goto out;
if (ocfs2_is_hard_readonly(osb)) {
if (ex)
status = -EROFS;
- goto bail;
+ goto getbh;
}
if (ocfs2_mount_local(osb))
mlog_errno(status);
goto bail;
}
-
+getbh:
if (ret_bh) {
status = ocfs2_assign_bh(inode, ret_bh, local_bh);
if (status < 0) {
BUG_ON(!dl);
- if (ocfs2_is_hard_readonly(osb))
- return -EROFS;
+ if (ocfs2_is_hard_readonly(osb)) {
+ if (ex)
+ return -EROFS;
+ return 0;
+ }
if (ocfs2_mount_local(osb))
return 0;
struct ocfs2_dentry_lock *dl = dentry->d_fsdata;
struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
- if (!ocfs2_mount_local(osb))
+ if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb))
ocfs2_cluster_unlock(osb, &dl->dl_lockres, level);
}
return ret;
}
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ int ret;
+ unsigned int is_last = 0, is_data = 0;
+ u16 cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+ u32 cpos, cend, clen, hole_size;
+ u64 extoff, extlen;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_extent_rec rec;
+
+ BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE);
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 0);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ if (*offset >= inode->i_size) {
+ ret = -ENXIO;
+ goto out_unlock;
+ }
+
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ if (origin == SEEK_HOLE)
+ *offset = inode->i_size;
+ goto out_unlock;
+ }
+
+ clen = 0;
+ cpos = *offset >> cs_bits;
+ cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size);
+
+ while (cpos < cend && !is_last) {
+ ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size,
+ &rec, &is_last);
+ if (ret) {
+ mlog_errno(ret);
+ goto out_unlock;
+ }
+
+ extoff = cpos;
+ extoff <<= cs_bits;
+
+ if (rec.e_blkno == 0ULL) {
+ clen = hole_size;
+ is_data = 0;
+ } else {
+ clen = le16_to_cpu(rec.e_leaf_clusters) -
+ (cpos - le32_to_cpu(rec.e_cpos));
+ is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ? 0 : 1;
+ }
+
+ if ((!is_data && origin == SEEK_HOLE) ||
+ (is_data && origin == SEEK_DATA)) {
+ if (extoff > *offset)
+ *offset = extoff;
+ goto out_unlock;
+ }
+
+ if (!is_last)
+ cpos += clen;
+ }
+
+ if (origin == SEEK_HOLE) {
+ extoff = cpos;
+ extoff <<= cs_bits;
+ extlen = clen;
+ extlen <<= cs_bits;
+
+ if ((extoff + extlen) > inode->i_size)
+ extlen = inode->i_size - extoff;
+ extoff += extlen;
+ if (extoff > *offset)
+ *offset = extoff;
+ goto out_unlock;
+ }
+
+ ret = -ENXIO;
+
+out_unlock:
+
+ brelse(di_bh);
+
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ ocfs2_inode_unlock(inode, 0);
+out:
+ if (ret && ret != -ENXIO)
+ ret = -ENXIO;
+ return ret;
+}
+
int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
struct buffer_head *bhs[], int flags,
int (*validate)(struct super_block *sb,
int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 map_start, u64 map_len);
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin);
+
int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
u32 *p_cluster, u32 *num_clusters,
struct ocfs2_extent_list *el,
if (ret < 0)
mlog_errno(ret);
+ if (file->f_flags & O_SYNC)
+ handle->h_sync = 1;
+
ocfs2_commit_trans(osb, handle);
out_inode_unlock:
return ret;
}
+static void ocfs2_aiodio_wait(struct inode *inode)
+{
+ wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
+
+ wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0));
+}
+
+static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
+{
+ int blockmask = inode->i_sb->s_blocksize - 1;
+ loff_t final_size = pos + count;
+
+ if ((pos & blockmask) || (final_size & blockmask))
+ return 1;
+ return 0;
+}
+
static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
struct file *file,
loff_t pos, size_t count,
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int full_coherency = !(osb->s_mount_opt &
OCFS2_MOUNT_COHERENCY_BUFFERED);
+ int unaligned_dio = 0;
trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
goto out;
}
+ if (direct_io && !is_sync_kiocb(iocb))
+ unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_left,
+ *ppos);
+
/*
* We can't complete the direct I/O as requested, fall back to
* buffered I/O.
goto relock;
}
+ if (unaligned_dio) {
+ /*
+ * Wait on previous unaligned aio to complete before
+ * proceeding.
+ */
+ ocfs2_aiodio_wait(inode);
+
+ /* Mark the iocb as needing a decrement in ocfs2_dio_end_io */
+ atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio);
+ ocfs2_iocb_set_unaligned_aio(iocb);
+ }
+
/*
* To later detect whether a journal commit for sync writes is
* necessary, we sample i_size, and cluster count here.
if ((ret == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
rw_level = -1;
have_alloc_sem = 0;
+ unaligned_dio = 0;
}
+ if (unaligned_dio)
+ atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio);
+
out:
if (rw_level != -1)
ocfs2_rw_unlock(inode, rw_level);
return ret;
}
+/* Refer generic_file_llseek_unlocked() */
+static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ int ret = 0;
+
+ mutex_lock(&inode->i_mutex);
+
+ switch (origin) {
+ case SEEK_SET:
+ break;
+ case SEEK_END:
+ offset += inode->i_size;
+ break;
+ case SEEK_CUR:
+ if (offset == 0) {
+ offset = file->f_pos;
+ goto out;
+ }
+ offset += file->f_pos;
+ break;
+ case SEEK_DATA:
+ case SEEK_HOLE:
+ ret = ocfs2_seek_data_hole_offset(file, &offset, origin);
+ if (ret)
+ goto out;
+ break;
+ default:
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+ ret = -EINVAL;
+ if (!ret && offset > inode->i_sb->s_maxbytes)
+ ret = -EINVAL;
+ if (ret)
+ goto out;
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+
+out:
+ mutex_unlock(&inode->i_mutex);
+ if (ret)
+ return ret;
+ return offset;
+}
+
const struct inode_operations ocfs2_file_iops = {
.setattr = ocfs2_setattr,
.getattr = ocfs2_getattr,
* ocfs2_fops_no_plocks and ocfs2_dops_no_plocks!
*/
const struct file_operations ocfs2_fops = {
- .llseek = generic_file_llseek,
+ .llseek = ocfs2_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
.mmap = ocfs2_mmap,
* the cluster.
*/
const struct file_operations ocfs2_fops_no_plocks = {
- .llseek = generic_file_llseek,
+ .llseek = ocfs2_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
.mmap = ocfs2_mmap,
trace_ocfs2_cleanup_delete_inode(
(unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
if (sync_data)
- write_inode_now(inode, 1);
+ filemap_write_and_wait(inode->i_mapping);
truncate_inode_pages(&inode->i_data, 0);
}
/* protects extended attribute changes on this inode */
struct rw_semaphore ip_xattr_sem;
+ /* Number of outstanding AIO's which are not page aligned */
+ atomic_t ip_unaligned_aio;
+
/* These fields are protected by ip_lock */
spinlock_t ip_lock;
u32 ip_open_count;
if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) &
(OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) {
if (!capable(CAP_LINUX_IMMUTABLE))
- goto bail_unlock;
+ goto bail_commit;
}
ocfs2_inode->ip_attr = flags;
if (status < 0)
mlog_errno(status);
+bail_commit:
ocfs2_commit_trans(osb, handle);
bail_unlock:
ocfs2_inode_unlock(inode, 1);
if (!oifi) {
status = -ENOMEM;
mlog_errno(status);
- goto bail;
+ goto out_err;
}
if (o2info_from_user(*oifi, req))
o2info_set_request_error(&oifi->ifi_req, req);
kfree(oifi);
-
+out_err:
return status;
}
if (!oiff) {
status = -ENOMEM;
mlog_errno(status);
- goto bail;
+ goto out_err;
}
if (o2info_from_user(*oiff, req))
o2info_set_request_error(&oiff->iff_req, req);
kfree(oiff);
-
+out_err:
return status;
}
/* we need to run complete recovery for offline orphan slots */
ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
- mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n",
- node_num, slot_num,
- MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
+ printk(KERN_NOTICE "ocfs2: Begin replay journal (node %d, slot %d) on "\
+ "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+ MINOR(osb->sb->s_dev));
OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
jbd2_journal_destroy(journal);
+ printk(KERN_NOTICE "ocfs2: End replay journal (node %d, slot %d) on "\
+ "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+ MINOR(osb->sb->s_dev));
done:
/* drop the lock on this nodes journal */
if (got_lock)
* every slot, queuing a recovery of the slot on the ocfs2_wq thread. This
* is done to catch any orphans that are left over in orphan directories.
*
+ * It scans all slots, even ones that are in use. It does so to handle the
+ * case described below:
+ *
+ * Node 1 has an inode it was using. The dentry went away due to memory
+ * pressure. Node 1 closes the inode, but it's on the free list. The node
+ * has the open lock.
+ * Node 2 unlinks the inode. It grabs the dentry lock to notify others,
+ * but node 1 has no dentry and doesn't get the message. It trylocks the
+ * open lock, sees that another node has a PR, and does nothing.
+ * Later node 2 runs its orphan dir. It igets the inode, trylocks the
+ * open lock, sees the PR still, and does nothing.
+ * Basically, we have to trigger an orphan iput on node 1. The only way
+ * for this to happen is if node 1 runs node 2's orphan dir.
+ *
* ocfs2_queue_orphan_scan gets called every ORPHAN_SCAN_SCHEDULE_TIMEOUT
* seconds. It gets an EX lock on os_lockres and checks sequence number
* stored in LVB. If the sequence number has changed, it means some other
#define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2)
/* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota
- * update on dir + index leaf + dx root update for free list */
+ * update on dir + index leaf + dx root update for free list +
+ * previous dirblock update in the free list */
static inline int ocfs2_link_credits(struct super_block *sb)
{
- return 2*OCFS2_INODE_UPDATE_CREDITS + 3 +
+ return 2*OCFS2_INODE_UPDATE_CREDITS + 4 +
ocfs2_quota_trans_credits(sb);
}
static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
struct page *page)
{
- int ret;
+ int ret = VM_FAULT_NOPAGE;
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
loff_t pos = page_offset(page);
void *fsdata;
loff_t size = i_size_read(inode);
- /*
- * Another node might have truncated while we were waiting on
- * cluster locks.
- * We don't check size == 0 before the shift. This is borrowed
- * from do_generic_file_read.
- */
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(!size || page->index > last_index)) {
- ret = -EINVAL;
- goto out;
- }
/*
- * The i_size check above doesn't catch the case where nodes
- * truncated and then re-extended the file. We'll re-check the
- * page mapping after taking the page lock inside of
- * ocfs2_write_begin_nolock().
+ * There are cases that lead to the page no longer bebongs to the
+ * mapping.
+ * 1) pagecache truncates locally due to memory pressure.
+ * 2) pagecache truncates when another is taking EX lock against
+ * inode lock. see ocfs2_data_convert_worker.
+ *
+ * The i_size check doesn't catch the case where nodes truncated and
+ * then re-extended the file. We'll re-check the page mapping after
+ * taking the page lock inside of ocfs2_write_begin_nolock().
+ *
+ * Let VM retry with these cases.
*/
- if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
- /*
- * the page has been umapped in ocfs2_data_downconvert_worker.
- * So return 0 here and let VFS retry.
- */
- ret = 0;
+ if ((page->mapping != inode->i_mapping) ||
+ (!PageUptodate(page)) ||
+ (page_offset(page) >= size))
goto out;
- }
/*
* Call ocfs2_write_begin() and ocfs2_write_end() to take
if (ret) {
if (ret != -ENOSPC)
mlog_errno(ret);
+ if (ret == -ENOMEM)
+ ret = VM_FAULT_OOM;
+ else
+ ret = VM_FAULT_SIGBUS;
goto out;
}
- ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page,
- fsdata);
- if (ret < 0) {
- mlog_errno(ret);
+ if (!locked_page) {
+ ret = VM_FAULT_NOPAGE;
goto out;
}
+ ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page,
+ fsdata);
BUG_ON(ret != len);
- ret = 0;
+ ret = VM_FAULT_LOCKED;
out:
return ret;
}
out:
ocfs2_unblock_signals(&oldset);
- if (ret)
- ret = VM_FAULT_SIGBUS;
return ret;
}
*/
ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
new_phys_cpos);
- if (!new_phys_cpos) {
+ if (!*new_phys_cpos) {
ret = -ENOSPC;
goto out_commit;
}
static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap)
{
- __test_and_set_bit_le(bit, bitmap);
+ __set_bit_le(bit, bitmap);
}
#define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr))
static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap)
{
- __test_and_clear_bit_le(bit, bitmap);
+ __clear_bit_le(bit, bitmap);
}
#define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr))
#define ocfs2_test_bit test_bit_le
#define ocfs2_find_next_zero_bit find_next_zero_bit_le
#define ocfs2_find_next_bit find_next_bit_le
+
+static inline void *correct_addr_and_bit_unaligned(int *bit, void *addr)
+{
+#if BITS_PER_LONG == 64
+ *bit += ((unsigned long) addr & 7UL) << 3;
+ addr = (void *) ((unsigned long) addr & ~7UL);
+#elif BITS_PER_LONG == 32
+ *bit += ((unsigned long) addr & 3UL) << 3;
+ addr = (void *) ((unsigned long) addr & ~3UL);
+#else
+#error "how many bits you are?!"
+#endif
+ return addr;
+}
+
+static inline void ocfs2_set_bit_unaligned(int bit, void *bitmap)
+{
+ bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+ ocfs2_set_bit(bit, bitmap);
+}
+
+static inline void ocfs2_clear_bit_unaligned(int bit, void *bitmap)
+{
+ bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+ ocfs2_clear_bit(bit, bitmap);
+}
+
+static inline int ocfs2_test_bit_unaligned(int bit, void *bitmap)
+{
+ bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+ return ocfs2_test_bit(bit, bitmap);
+}
+
+static inline int ocfs2_find_next_zero_bit_unaligned(void *bitmap, int max,
+ int start)
+{
+ int fix = 0, ret, tmpmax;
+ bitmap = correct_addr_and_bit_unaligned(&fix, bitmap);
+ tmpmax = max + fix;
+ start += fix;
+
+ ret = ocfs2_find_next_zero_bit(bitmap, tmpmax, start) - fix;
+ if (ret > max)
+ return max;
+ return ret;
+}
+
#endif /* OCFS2_H */
int status = 0;
struct ocfs2_quota_recovery *rec;
- mlog(ML_NOTICE, "Beginning quota recovery in slot %u\n", slot_num);
+ printk(KERN_NOTICE "ocfs2: Beginning quota recovery on device (%s) for "
+ "slot %u\n", osb->dev_str, slot_num);
+
rec = ocfs2_alloc_quota_recovery();
if (!rec)
return ERR_PTR(-ENOMEM);
goto out_commit;
}
lock_buffer(qbh);
- WARN_ON(!ocfs2_test_bit(bit, dchunk->dqc_bitmap));
- ocfs2_clear_bit(bit, dchunk->dqc_bitmap);
+ WARN_ON(!ocfs2_test_bit_unaligned(bit, dchunk->dqc_bitmap));
+ ocfs2_clear_bit_unaligned(bit, dchunk->dqc_bitmap);
le32_add_cpu(&dchunk->dqc_free, 1);
unlock_buffer(qbh);
ocfs2_journal_dirty(handle, qbh);
struct inode *lqinode;
unsigned int flags;
- mlog(ML_NOTICE, "Finishing quota recovery in slot %u\n", slot_num);
+ printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
+ "slot %u\n", osb->dev_str, slot_num);
+
mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
for (type = 0; type < MAXQUOTAS; type++) {
if (list_empty(&(rec->r_list[type])))
/* Someone else is holding the lock? Then he must be
* doing the recovery. Just skip the file... */
if (status == -EAGAIN) {
- mlog(ML_NOTICE, "skipping quota recovery for slot %d "
- "because quota file is locked.\n", slot_num);
+ printk(KERN_NOTICE "ocfs2: Skipping quota recovery on "
+ "device (%s) for slot %d because quota file is "
+ "locked.\n", osb->dev_str, slot_num);
status = 0;
goto out_put;
} else if (status < 0) {
* ol_quota_entries_per_block(sb);
}
- found = ocfs2_find_next_zero_bit(dchunk->dqc_bitmap, len, 0);
+ found = ocfs2_find_next_zero_bit_unaligned(dchunk->dqc_bitmap, len, 0);
/* We failed? */
if (found == len) {
mlog(ML_ERROR, "Did not find empty entry in chunk %d with %u"
struct ocfs2_local_disk_chunk *dchunk;
dchunk = (struct ocfs2_local_disk_chunk *)bh->b_data;
- ocfs2_set_bit(*offset, dchunk->dqc_bitmap);
+ ocfs2_set_bit_unaligned(*offset, dchunk->dqc_bitmap);
le32_add_cpu(&dchunk->dqc_free, -1);
}
(od->dq_chunk->qc_headerbh->b_data);
/* Mark structure as freed */
lock_buffer(od->dq_chunk->qc_headerbh);
- ocfs2_clear_bit(offset, dchunk->dqc_bitmap);
+ ocfs2_clear_bit_unaligned(offset, dchunk->dqc_bitmap);
le32_add_cpu(&dchunk->dqc_free, 1);
unlock_buffer(od->dq_chunk->qc_headerbh);
ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
goto bail;
}
} else
- mlog(ML_NOTICE, "slot %d is already allocated to this node!\n",
- slot);
+ printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+ "allocated to this node!\n", slot, osb->dev_str);
ocfs2_set_slot(si, slot, osb->node_num);
osb->slot_num = slot;
#include "cluster/masklog.h"
#include "cluster/nodemanager.h"
#include "cluster/heartbeat.h"
+#include "cluster/tcp.h"
#include "stackglue.h"
dlm_print_one_lock(lksb->lksb_o2dlm.lockid);
}
+/*
+ * Check if this node is heartbeating and is connected to all other
+ * heartbeating nodes.
+ */
+static int o2cb_cluster_check(void)
+{
+ u8 node_num;
+ int i;
+ unsigned long hbmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+ unsigned long netmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+
+ node_num = o2nm_this_node();
+ if (node_num == O2NM_MAX_NODES) {
+ printk(KERN_ERR "o2cb: This node has not been configured.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * o2dlm expects o2net sockets to be created. If not, then
+ * dlm_join_domain() fails with a stack of errors which are both cryptic
+ * and incomplete. The idea here is to detect upfront whether we have
+ * managed to connect to all nodes or not. If not, then list the nodes
+ * to allow the user to check the configuration (incorrect IP, firewall,
+ * etc.) Yes, this is racy. But its not the end of the world.
+ */
+#define O2CB_MAP_STABILIZE_COUNT 60
+ for (i = 0; i < O2CB_MAP_STABILIZE_COUNT; ++i) {
+ o2hb_fill_node_map(hbmap, sizeof(hbmap));
+ if (!test_bit(node_num, hbmap)) {
+ printk(KERN_ERR "o2cb: %s heartbeat has not been "
+ "started.\n", (o2hb_global_heartbeat_active() ?
+ "Global" : "Local"));
+ return -EINVAL;
+ }
+ o2net_fill_node_map(netmap, sizeof(netmap));
+ /* Force set the current node to allow easy compare */
+ set_bit(node_num, netmap);
+ if (!memcmp(hbmap, netmap, sizeof(hbmap)))
+ return 0;
+ if (i < O2CB_MAP_STABILIZE_COUNT)
+ msleep(1000);
+ }
+
+ printk(KERN_ERR "o2cb: This node could not connect to nodes:");
+ i = -1;
+ while ((i = find_next_bit(hbmap, O2NM_MAX_NODES,
+ i + 1)) < O2NM_MAX_NODES) {
+ if (!test_bit(i, netmap))
+ printk(" %u", i);
+ }
+ printk(".\n");
+
+ return -ENOTCONN;
+}
+
/*
* Called from the dlm when it's about to evict a node. This is how the
* classic stack signals node death.
{
struct ocfs2_cluster_connection *conn = data;
- mlog(ML_NOTICE, "o2dlm has evicted node %d from group %.*s\n",
- node_num, conn->cc_namelen, conn->cc_name);
+ printk(KERN_NOTICE "o2cb: o2dlm has evicted node %d from domain %.*s\n",
+ node_num, conn->cc_namelen, conn->cc_name);
conn->cc_recovery_handler(node_num, conn->cc_recovery_data);
}
BUG_ON(conn == NULL);
BUG_ON(conn->cc_proto == NULL);
- /* for now we only have one cluster/node, make sure we see it
- * in the heartbeat universe */
- if (!o2hb_check_local_node_heartbeating()) {
- if (o2hb_global_heartbeat_active())
- mlog(ML_ERROR, "Global heartbeat not started\n");
- rc = -EINVAL;
+ /* Ensure cluster stack is up and all nodes are connected */
+ rc = o2cb_cluster_check();
+ if (rc) {
+ printk(KERN_ERR "o2cb: Cluster check failed. Fix errors "
+ "before retrying.\n");
goto out;
}
#include "ocfs1_fs_compat.h"
#include "alloc.h"
+#include "aops.h"
#include "blockcheck.h"
#include "dlmglue.h"
#include "export.h"
ocfs2_set_ro_flag(osb, 1);
- printk(KERN_NOTICE "Readonly device detected. No cluster "
- "services will be utilized for this mount. Recovery "
- "will be skipped.\n");
+ printk(KERN_NOTICE "ocfs2: Readonly device (%s) detected. "
+ "Cluster services will not be used for this mount. "
+ "Recovery will be skipped.\n", osb->dev_str);
}
if (!ocfs2_is_hard_readonly(osb)) {
return 0;
}
+wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
static int __init ocfs2_init(void)
{
- int status;
+ int status, i;
ocfs2_print_version();
+ for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++)
+ init_waitqueue_head(&ocfs2__ioend_wq[i]);
+
status = init_ocfs2_uptodate_cache();
if (status < 0) {
mlog_errno(status);
ocfs2_extent_map_init(&oi->vfs_inode);
INIT_LIST_HEAD(&oi->ip_io_markers);
oi->ip_dir_start_lookup = 0;
-
+ atomic_set(&oi->ip_unaligned_aio, 0);
init_rwsem(&oi->ip_alloc_sem);
init_rwsem(&oi->ip_xattr_sem);
mutex_init(&oi->ip_io_mutex);
* If we failed before we got a uuid_str yet, we can't stop
* heartbeat. Otherwise, do it.
*/
- if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str)
+ if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str &&
+ !ocfs2_is_hard_readonly(osb))
hangup_needed = 1;
if (osb->cconn)
mlog_errno(status);
goto bail;
}
- cleancache_init_shared_fs((char *)&uuid_net_key, sb);
+ cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb);
bail:
return status;
goto finally;
}
} else {
- mlog(ML_NOTICE, "File system was not unmounted cleanly, "
- "recovering volume.\n");
+ printk(KERN_NOTICE "ocfs2: File system on device (%s) was not "
+ "unmounted cleanly, recovering it.\n", osb->dev_str);
}
local = ocfs2_mount_local(osb);
}
ret = ocfs2_xattr_value_truncate(inode, vb, 0, &ctxt);
- if (ret < 0) {
- mlog_errno(ret);
- break;
- }
ocfs2_commit_trans(osb, ctxt.handle);
if (ctxt.meta_ac) {
ocfs2_free_alloc_context(ctxt.meta_ac);
ctxt.meta_ac = NULL;
}
+
+ if (ret < 0) {
+ mlog_errno(ret);
+ break;
+ }
+
}
if (ctxt.meta_ac)
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
- K(global_page_state(NR_ANON_PAGES)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ K(global_page_state(NR_ANON_PAGES)
+ global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR
+ HPAGE_PMD_NR),
+#else
+ K(global_page_state(NR_ANON_PAGES)),
#endif
- ),
K(global_page_state(NR_FILE_MAPPED)),
K(global_page_state(NR_SHMEM)),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
void __init proc_root_init(void)
{
- struct vfsmount *mnt;
int err;
proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
- mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
- if (IS_ERR(mnt)) {
+ err = pid_ns_prepare_proc(&init_pid_ns);
+ if (err) {
unregister_filesystem(&proc_fs_type);
return;
}
- init_pid_ns.proc_mnt = mnt;
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
void pid_ns_release_proc(struct pid_namespace *ns)
{
- mntput(ns->proc_mnt);
+ kern_unmount(ns->proc_mnt);
}
idle = kstat_cpu(cpu).cpustat.idle;
idle = cputime64_add(idle, arch_idle_time(cpu));
} else
- idle = usecs_to_cputime(idle_time);
+ idle = usecs_to_cputime64(idle_time);
return idle;
}
/* !NO_HZ so we can rely on cpustat.iowait */
iowait = kstat_cpu(cpu).cpustat.iowait;
else
- iowait = usecs_to_cputime(iowait_time);
+ iowait = usecs_to_cputime64(iowait_time);
return iowait;
}
}
psinfo = psi;
+ mutex_init(&psinfo->read_mutex);
spin_unlock(&pstore_lock);
if (owner && !try_module_get(owner)) {
void pstore_get_records(int quiet)
{
struct pstore_info *psi = psinfo;
+ char *buf = NULL;
ssize_t size;
u64 id;
enum pstore_type_id type;
struct timespec time;
int failed = 0, rc;
- unsigned long flags;
if (!psi)
return;
- spin_lock_irqsave(&psinfo->buf_lock, flags);
+ mutex_lock(&psi->read_mutex);
rc = psi->open(psi);
if (rc)
goto out;
- while ((size = psi->read(&id, &type, &time, psi)) > 0) {
- rc = pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size,
+ while ((size = psi->read(&id, &type, &time, &buf, psi)) > 0) {
+ rc = pstore_mkfile(type, psi->name, id, buf, (size_t)size,
time, psi);
+ kfree(buf);
+ buf = NULL;
if (rc && (rc != -EEXIST || !quiet))
failed++;
}
psi->close(psi);
out:
- spin_unlock_irqrestore(&psinfo->buf_lock, flags);
+ mutex_unlock(&psi->read_mutex);
if (failed)
printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n",
/*
* Same as seq_path, but relative to supplied root.
- *
- * root may be changed, see __d_path().
*/
int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
char *esc)
char *p;
p = __d_path(path, root, buf, size);
+ if (!p)
+ return SEQ_SKIP;
res = PTR_ERR(p);
if (!IS_ERR(p)) {
char *end = mangle_path(buf, p, esc);
}
seq_commit(m, res);
- return res < 0 ? res : 0;
+ return res < 0 && res != -ENAMETOOLONG ? res : 0;
}
/*
return -EINVAL;
}
- err = register_filesystem(&ubifs_fs_type);
- if (err) {
- ubifs_err("cannot register file system, error %d", err);
- return err;
- }
-
- err = -ENOMEM;
ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab",
sizeof(struct ubifs_inode), 0,
SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT,
&inode_slab_ctor);
if (!ubifs_inode_slab)
- goto out_reg;
+ return -ENOMEM;
register_shrinker(&ubifs_shrinker_info);
if (err)
goto out_compr;
+ err = register_filesystem(&ubifs_fs_type);
+ if (err) {
+ ubifs_err("cannot register file system, error %d", err);
+ goto out_dbg;
+ }
return 0;
+out_dbg:
+ dbg_debugfs_exit();
out_compr:
ubifs_compressors_exit();
out_shrinker:
unregister_shrinker(&ubifs_shrinker_info);
kmem_cache_destroy(ubifs_inode_slab);
-out_reg:
- unregister_filesystem(&ubifs_fs_type);
return err;
}
/* late_initcall to let compressors initialize first */
int count, i;
count = be32_to_cpu(aclp->acl_cnt);
+ if (count > XFS_ACL_MAX_ENTRIES)
+ return ERR_PTR(-EFSCORRUPTED);
acl = posix_acl_alloc(count, GFP_KERNEL);
if (!acl)
/*
* Query whether the requested number of additional bytes of extended
* attribute space will be able to fit inline.
+ *
* Returns zero if not, else the di_forkoff fork offset to be used in the
* literal area for attribute data once the new bytes have been added.
*
int offset;
int minforkoff; /* lower limit on valid forkoff locations */
int maxforkoff; /* upper limit on valid forkoff locations */
- int dsize;
+ int dsize;
xfs_mount_t *mp = dp->i_mount;
offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
return (offset >= minforkoff) ? minforkoff : 0;
}
- if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
- if (bytes <= XFS_IFORK_ASIZE(dp))
- return dp->i_d.di_forkoff;
+ /*
+ * If the requested numbers of bytes is smaller or equal to the
+ * current attribute fork size we can always proceed.
+ *
+ * Note that if_bytes in the data fork might actually be larger than
+ * the current data fork size is due to delalloc extents. In that
+ * case either the extent count will go down when they are converted
+ * to real extents, or the delalloc conversion will take care of the
+ * literal area rebalancing.
+ */
+ if (bytes <= XFS_IFORK_ASIZE(dp))
+ return dp->i_d.di_forkoff;
+
+ /*
+ * For attr2 we can try to move the forkoff if there is space in the
+ * literal area, but for the old format we are done if there is no
+ * space in the fixed attribute fork.
+ */
+ if (!(mp->m_flags & XFS_MOUNT_ATTR2))
return 0;
- }
dsize = dp->i_df.if_bytes;
-
+
switch (dp->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
- /*
+ /*
* If there is no attr fork and the data fork is extents,
- * determine if creating the default attr fork will result
- * in the extents form migrating to btree. If so, the
- * minimum offset only needs to be the space required for
+ * determine if creating the default attr fork will result
+ * in the extents form migrating to btree. If so, the
+ * minimum offset only needs to be the space required for
* the btree root.
- */
+ */
if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
xfs_default_attroffset(dp))
dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
break;
-
case XFS_DINODE_FMT_BTREE:
/*
- * If have data btree then keep forkoff if we have one,
- * otherwise we are adding a new attr, so then we set
- * minforkoff to where the btree root can finish so we have
+ * If we have a data btree then keep forkoff if we have one,
+ * otherwise we are adding a new attr, so then we set
+ * minforkoff to where the btree root can finish so we have
* plenty of room for attrs
*/
if (dp->i_d.di_forkoff) {
- if (offset < dp->i_d.di_forkoff)
+ if (offset < dp->i_d.di_forkoff)
return 0;
- else
- return dp->i_d.di_forkoff;
- } else
- dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+ return dp->i_d.di_forkoff;
+ }
+ dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
break;
}
-
- /*
- * A data fork btree root must have space for at least
+
+ /*
+ * A data fork btree root must have space for at least
* MINDBTPTRS key/ptr pairs if the data fork is small or empty.
*/
minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
maxforkoff = maxforkoff >> 3; /* rounded down */
- if (offset >= minforkoff && offset < maxforkoff)
- return offset;
if (offset >= maxforkoff)
return maxforkoff;
+ if (offset >= minforkoff)
+ return offset;
return 0;
}
int tryagain;
int error;
+ ASSERT(ap->length);
+
mp = ap->ip->i_mount;
align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
if (unlikely(align)) {
int error;
int rt;
+ ASSERT(bma->length > 0);
+
rt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(bma->ip);
/*
ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
ASSERT(!(flags & XFS_BMAPI_IGSTATE));
ASSERT(tp != NULL);
+ ASSERT(len > 0);
whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
bma.eof = eof;
bma.conv = !!(flags & XFS_BMAPI_CONVERT);
bma.wasdel = wasdelay;
- bma.length = len;
bma.offset = bno;
+ /*
+ * There's a 32/64 bit type mismatch between the
+ * allocation length request (which can be 64 bits in
+ * length) and the bma length request, which is
+ * xfs_extlen_t and therefore 32 bits. Hence we have to
+ * check for 32-bit overflows and handle them here.
+ */
+ if (len > (xfs_filblks_t)MAXEXTLEN)
+ bma.length = MAXEXTLEN;
+ else
+ bma.length = len;
+
+ ASSERT(len > 0);
+ ASSERT(bma.length > 0);
error = xfs_bmapi_allocate(&bma, flags);
if (error)
goto error0;
switch (fileid_type) {
case FILEID_INO32_GEN_PARENT:
spin_lock(&dentry->d_lock);
- fid->i32.parent_ino = dentry->d_parent->d_inode->i_ino;
+ fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation;
spin_unlock(&dentry->d_lock);
/*FALLTHRU*/
case FILEID_INO32_GEN:
- fid->i32.ino = inode->i_ino;
+ fid->i32.ino = XFS_I(inode)->i_ino;
fid->i32.gen = inode->i_generation;
break;
case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
spin_lock(&dentry->d_lock);
- fid64->parent_ino = dentry->d_parent->d_inode->i_ino;
+ fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
fid64->parent_gen = dentry->d_parent->d_inode->i_generation;
spin_unlock(&dentry->d_lock);
/*FALLTHRU*/
case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG:
- fid64->ino = inode->i_ino;
+ fid64->ino = XFS_I(inode)->i_ino;
fid64->gen = inode->i_generation;
break;
}
return XFS_ERROR(EFSCORRUPTED);
}
+void
+xfs_promote_inode(
+ struct xfs_inode *ip)
+{
+ struct xfs_buf *bp;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+
+ bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
+ ip->i_imap.im_len, XBF_TRYLOCK);
+ if (!bp)
+ return;
+
+ if (XFS_BUF_ISDELAYWRITE(bp)) {
+ xfs_buf_delwri_promote(bp);
+ wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
+ }
+
+ xfs_buf_relse(bp);
+}
+
/*
* Return a pointer to the extent record at file index idx.
*/
void xfs_iext_realloc(xfs_inode_t *, int, int);
void xfs_iunpin_wait(xfs_inode_t *);
int xfs_iflush(xfs_inode_t *, uint);
+void xfs_promote_inode(struct xfs_inode *);
void xfs_lock_inodes(xfs_inode_t **, int, uint);
void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
} while (head_val != old);
}
+STATIC bool
+xlog_reserveq_wake(
+ struct log *log,
+ int *free_bytes)
+{
+ struct xlog_ticket *tic;
+ int need_bytes;
+
+ list_for_each_entry(tic, &log->l_reserveq, t_queue) {
+ if (tic->t_flags & XLOG_TIC_PERM_RESERV)
+ need_bytes = tic->t_unit_res * tic->t_cnt;
+ else
+ need_bytes = tic->t_unit_res;
+
+ if (*free_bytes < need_bytes)
+ return false;
+ *free_bytes -= need_bytes;
+
+ trace_xfs_log_grant_wake_up(log, tic);
+ wake_up(&tic->t_wait);
+ }
+
+ return true;
+}
+
+STATIC bool
+xlog_writeq_wake(
+ struct log *log,
+ int *free_bytes)
+{
+ struct xlog_ticket *tic;
+ int need_bytes;
+
+ list_for_each_entry(tic, &log->l_writeq, t_queue) {
+ ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV);
+
+ need_bytes = tic->t_unit_res;
+
+ if (*free_bytes < need_bytes)
+ return false;
+ *free_bytes -= need_bytes;
+
+ trace_xfs_log_regrant_write_wake_up(log, tic);
+ wake_up(&tic->t_wait);
+ }
+
+ return true;
+}
+
+STATIC int
+xlog_reserveq_wait(
+ struct log *log,
+ struct xlog_ticket *tic,
+ int need_bytes)
+{
+ list_add_tail(&tic->t_queue, &log->l_reserveq);
+
+ do {
+ if (XLOG_FORCED_SHUTDOWN(log))
+ goto shutdown;
+ xlog_grant_push_ail(log, need_bytes);
+
+ XFS_STATS_INC(xs_sleep_logspace);
+ trace_xfs_log_grant_sleep(log, tic);
+
+ xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
+ trace_xfs_log_grant_wake(log, tic);
+
+ spin_lock(&log->l_grant_reserve_lock);
+ if (XLOG_FORCED_SHUTDOWN(log))
+ goto shutdown;
+ } while (xlog_space_left(log, &log->l_grant_reserve_head) < need_bytes);
+
+ list_del_init(&tic->t_queue);
+ return 0;
+shutdown:
+ list_del_init(&tic->t_queue);
+ return XFS_ERROR(EIO);
+}
+
+STATIC int
+xlog_writeq_wait(
+ struct log *log,
+ struct xlog_ticket *tic,
+ int need_bytes)
+{
+ list_add_tail(&tic->t_queue, &log->l_writeq);
+
+ do {
+ if (XLOG_FORCED_SHUTDOWN(log))
+ goto shutdown;
+ xlog_grant_push_ail(log, need_bytes);
+
+ XFS_STATS_INC(xs_sleep_logspace);
+ trace_xfs_log_regrant_write_sleep(log, tic);
+
+ xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
+ trace_xfs_log_regrant_write_wake(log, tic);
+
+ spin_lock(&log->l_grant_write_lock);
+ if (XLOG_FORCED_SHUTDOWN(log))
+ goto shutdown;
+ } while (xlog_space_left(log, &log->l_grant_write_head) < need_bytes);
+
+ list_del_init(&tic->t_queue);
+ return 0;
+shutdown:
+ list_del_init(&tic->t_queue);
+ return XFS_ERROR(EIO);
+}
+
static void
xlog_tic_reset_res(xlog_ticket_t *tic)
{
retval = xlog_grant_log_space(log, internal_ticket);
}
+ if (unlikely(retval)) {
+ /*
+ * If we are failing, make sure the ticket doesn't have any
+ * current reservations. We don't want to add this back
+ * when the ticket/ transaction gets cancelled.
+ */
+ internal_ticket->t_curr_res = 0;
+ /* ungrant will give back unit_res * t_cnt. */
+ internal_ticket->t_cnt = 0;
+ }
+
return retval;
-} /* xfs_log_reserve */
+}
/*
/*
* Atomically get the log space required for a log ticket.
*
- * Once a ticket gets put onto the reserveq, it will only return after
- * the needed reservation is satisfied.
+ * Once a ticket gets put onto the reserveq, it will only return after the
+ * needed reservation is satisfied.
*
* This function is structured so that it has a lock free fast path. This is
* necessary because every new transaction reservation will come through this
* every pass.
*
* As tickets are only ever moved on and off the reserveq under the
- * l_grant_reserve_lock, we only need to take that lock if we are going
- * to add the ticket to the queue and sleep. We can avoid taking the lock if the
- * ticket was never added to the reserveq because the t_queue list head will be
- * empty and we hold the only reference to it so it can safely be checked
- * unlocked.
+ * l_grant_reserve_lock, we only need to take that lock if we are going to add
+ * the ticket to the queue and sleep. We can avoid taking the lock if the ticket
+ * was never added to the reserveq because the t_queue list head will be empty
+ * and we hold the only reference to it so it can safely be checked unlocked.
*/
STATIC int
-xlog_grant_log_space(xlog_t *log,
- xlog_ticket_t *tic)
+xlog_grant_log_space(
+ struct log *log,
+ struct xlog_ticket *tic)
{
- int free_bytes;
- int need_bytes;
+ int free_bytes, need_bytes;
+ int error = 0;
-#ifdef DEBUG
- if (log->l_flags & XLOG_ACTIVE_RECOVERY)
- panic("grant Recovery problem");
-#endif
+ ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
trace_xfs_log_grant_enter(log, tic);
+ /*
+ * If there are other waiters on the queue then give them a chance at
+ * logspace before us. Wake up the first waiters, if we do not wake
+ * up all the waiters then go to sleep waiting for more free space,
+ * otherwise try to get some space for this transaction.
+ */
need_bytes = tic->t_unit_res;
if (tic->t_flags & XFS_LOG_PERM_RESERV)
need_bytes *= tic->t_ocnt;
-
- /* something is already sleeping; insert new transaction at end */
- if (!list_empty_careful(&log->l_reserveq)) {
- spin_lock(&log->l_grant_reserve_lock);
- /* recheck the queue now we are locked */
- if (list_empty(&log->l_reserveq)) {
- spin_unlock(&log->l_grant_reserve_lock);
- goto redo;
- }
- list_add_tail(&tic->t_queue, &log->l_reserveq);
-
- trace_xfs_log_grant_sleep1(log, tic);
-
- /*
- * Gotta check this before going to sleep, while we're
- * holding the grant lock.
- */
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return;
-
- XFS_STATS_INC(xs_sleep_logspace);
- xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
- /*
- * If we got an error, and the filesystem is shutting down,
- * we'll catch it down below. So just continue...
- */
- trace_xfs_log_grant_wake1(log, tic);
- }
-
-redo:
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return_unlocked;
-
free_bytes = xlog_space_left(log, &log->l_grant_reserve_head);
- if (free_bytes < need_bytes) {
+ if (!list_empty_careful(&log->l_reserveq)) {
spin_lock(&log->l_grant_reserve_lock);
- if (list_empty(&tic->t_queue))
- list_add_tail(&tic->t_queue, &log->l_reserveq);
-
- trace_xfs_log_grant_sleep2(log, tic);
-
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return;
-
- xlog_grant_push_ail(log, need_bytes);
-
- XFS_STATS_INC(xs_sleep_logspace);
- xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
- trace_xfs_log_grant_wake2(log, tic);
- goto redo;
- }
-
- if (!list_empty(&tic->t_queue)) {
+ if (!xlog_reserveq_wake(log, &free_bytes) ||
+ free_bytes < need_bytes)
+ error = xlog_reserveq_wait(log, tic, need_bytes);
+ spin_unlock(&log->l_grant_reserve_lock);
+ } else if (free_bytes < need_bytes) {
spin_lock(&log->l_grant_reserve_lock);
- list_del_init(&tic->t_queue);
+ error = xlog_reserveq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_reserve_lock);
}
+ if (error)
+ return error;
- /* we've got enough space */
xlog_grant_add_space(log, &log->l_grant_reserve_head, need_bytes);
xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
trace_xfs_log_grant_exit(log, tic);
xlog_verify_grant_tail(log);
return 0;
-
-error_return_unlocked:
- spin_lock(&log->l_grant_reserve_lock);
-error_return:
- list_del_init(&tic->t_queue);
- spin_unlock(&log->l_grant_reserve_lock);
- trace_xfs_log_grant_error(log, tic);
-
- /*
- * If we are failing, make sure the ticket doesn't have any
- * current reservations. We don't want to add this back when
- * the ticket/transaction gets cancelled.
- */
- tic->t_curr_res = 0;
- tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
- return XFS_ERROR(EIO);
-} /* xlog_grant_log_space */
-
+}
/*
* Replenish the byte reservation required by moving the grant write head.
* free fast path.
*/
STATIC int
-xlog_regrant_write_log_space(xlog_t *log,
- xlog_ticket_t *tic)
+xlog_regrant_write_log_space(
+ struct log *log,
+ struct xlog_ticket *tic)
{
- int free_bytes, need_bytes;
+ int free_bytes, need_bytes;
+ int error = 0;
tic->t_curr_res = tic->t_unit_res;
xlog_tic_reset_res(tic);
if (tic->t_cnt > 0)
return 0;
-#ifdef DEBUG
- if (log->l_flags & XLOG_ACTIVE_RECOVERY)
- panic("regrant Recovery problem");
-#endif
+ ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
trace_xfs_log_regrant_write_enter(log, tic);
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return_unlocked;
- /* If there are other waiters on the queue then give them a
- * chance at logspace before us. Wake up the first waiters,
- * if we do not wake up all the waiters then go to sleep waiting
- * for more free space, otherwise try to get some space for
- * this transaction.
+ /*
+ * If there are other waiters on the queue then give them a chance at
+ * logspace before us. Wake up the first waiters, if we do not wake
+ * up all the waiters then go to sleep waiting for more free space,
+ * otherwise try to get some space for this transaction.
*/
need_bytes = tic->t_unit_res;
- if (!list_empty_careful(&log->l_writeq)) {
- struct xlog_ticket *ntic;
-
- spin_lock(&log->l_grant_write_lock);
- free_bytes = xlog_space_left(log, &log->l_grant_write_head);
- list_for_each_entry(ntic, &log->l_writeq, t_queue) {
- ASSERT(ntic->t_flags & XLOG_TIC_PERM_RESERV);
-
- if (free_bytes < ntic->t_unit_res)
- break;
- free_bytes -= ntic->t_unit_res;
- wake_up(&ntic->t_wait);
- }
-
- if (ntic != list_first_entry(&log->l_writeq,
- struct xlog_ticket, t_queue)) {
- if (list_empty(&tic->t_queue))
- list_add_tail(&tic->t_queue, &log->l_writeq);
- trace_xfs_log_regrant_write_sleep1(log, tic);
-
- xlog_grant_push_ail(log, need_bytes);
-
- XFS_STATS_INC(xs_sleep_logspace);
- xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
- trace_xfs_log_regrant_write_wake1(log, tic);
- } else
- spin_unlock(&log->l_grant_write_lock);
- }
-
-redo:
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return_unlocked;
-
free_bytes = xlog_space_left(log, &log->l_grant_write_head);
- if (free_bytes < need_bytes) {
+ if (!list_empty_careful(&log->l_writeq)) {
spin_lock(&log->l_grant_write_lock);
- if (list_empty(&tic->t_queue))
- list_add_tail(&tic->t_queue, &log->l_writeq);
-
- if (XLOG_FORCED_SHUTDOWN(log))
- goto error_return;
-
- xlog_grant_push_ail(log, need_bytes);
-
- XFS_STATS_INC(xs_sleep_logspace);
- trace_xfs_log_regrant_write_sleep2(log, tic);
- xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
-
- trace_xfs_log_regrant_write_wake2(log, tic);
- goto redo;
- }
-
- if (!list_empty(&tic->t_queue)) {
+ if (!xlog_writeq_wake(log, &free_bytes) ||
+ free_bytes < need_bytes)
+ error = xlog_writeq_wait(log, tic, need_bytes);
+ spin_unlock(&log->l_grant_write_lock);
+ } else if (free_bytes < need_bytes) {
spin_lock(&log->l_grant_write_lock);
- list_del_init(&tic->t_queue);
+ error = xlog_writeq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_write_lock);
}
- /* we've got enough space */
+ if (error)
+ return error;
+
xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
trace_xfs_log_regrant_write_exit(log, tic);
xlog_verify_grant_tail(log);
return 0;
-
-
- error_return_unlocked:
- spin_lock(&log->l_grant_write_lock);
- error_return:
- list_del_init(&tic->t_queue);
- spin_unlock(&log->l_grant_write_lock);
- trace_xfs_log_regrant_write_error(log, tic);
-
- /*
- * If we are failing, make sure the ticket doesn't have any
- * current reservations. We don't want to add this back when
- * the ticket/transaction gets cancelled.
- */
- tic->t_curr_res = 0;
- tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
- return XFS_ERROR(EIO);
-} /* xlog_regrant_write_log_space */
-
+}
/* The first cnt-1 times through here we don't need to
* move the grant write head because the permanent
* disk and we didn't ask it to allocate;
* ESRCH if quotas got turned off suddenly.
*/
- error = xfs_qm_dqget(ip->i_mount, ip, id, type, XFS_QMOPT_DOWARN, &dqp);
+ error = xfs_qm_dqget(ip->i_mount, ip, id, type,
+ doalloc | XFS_QMOPT_DOWARN, &dqp);
if (error)
return error;
XFS_I(inode)->i_update_core = 1;
}
-STATIC int
-xfs_log_inode(
- struct xfs_inode *ip)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_trans *tp;
- int error;
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
- error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
- if (error) {
- xfs_trans_cancel(tp, 0);
- return error;
- }
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- return xfs_trans_commit(tp, 0);
-}
-
STATIC int
xfs_fs_write_inode(
struct inode *inode,
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
- if (!ip->i_update_core)
- return 0;
- if (wbc->sync_mode == WB_SYNC_ALL) {
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) {
/*
* Make sure the inode has made it it into the log. Instead
* of forcing it all the way to stable storage using a
* ->sync_fs call do that for thus, which reduces the number
* of synchronous log forces dramatically.
*/
- error = xfs_log_inode(ip);
+ error = xfs_log_dirty_inode(ip, NULL, 0);
if (error)
goto out;
return 0;
} else {
+ if (!ip->i_update_core)
+ return 0;
+
/*
* We make this non-blocking if the inode is contended, return
* EAGAIN to indicate to the caller that they did not succeed.
return error;
}
+int
+xfs_log_dirty_inode(
+ struct xfs_inode *ip,
+ struct xfs_perag *pag,
+ int flags)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ int error;
+
+ if (!ip->i_update_core)
+ return 0;
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+ error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ return xfs_trans_commit(tp, 0);
+}
+
/*
* When remounting a filesystem read-only or freezing the filesystem, we have
* two phases to execute. This first phase is syncing the data before we
{
int error, error2 = 0;
+ /*
+ * Log all pending size and timestamp updates. The vfs writeback
+ * code is supposed to do this, but due to its overagressive
+ * livelock detection it will skip inodes where appending writes
+ * were written out in the first non-blocking sync phase if their
+ * completion took long enough that it happened after taking the
+ * timestamp for the cut-off in the blocking phase.
+ */
+ xfs_inode_ag_iterator(mp, xfs_log_dirty_inode, 0);
+
xfs_qm_sync(mp, SYNC_TRYLOCK);
xfs_qm_sync(mp, SYNC_WAIT);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
+
+ /*
+ * If we only have a single dirty inode in a cluster there is
+ * a fair chance that the AIL push may have pushed it into
+ * the buffer, but xfsbufd won't touch it until 30 seconds
+ * from now, and thus we will lock up here.
+ *
+ * Promote the inode buffer to the front of the delwri list
+ * and wake up xfsbufd now.
+ */
+ xfs_promote_inode(ip);
xfs_iflock(ip);
}
void xfs_flush_inodes(struct xfs_inode *ip);
+int xfs_log_dirty_inode(struct xfs_inode *ip, struct xfs_perag *pag, int flags);
+
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
int xfs_reclaim_inodes_count(struct xfs_mount *mp);
void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
DEFINE_LOGGRANT_EVENT(xfs_log_grant_enter);
DEFINE_LOGGRANT_EVENT(xfs_log_grant_exit);
DEFINE_LOGGRANT_EVENT(xfs_log_grant_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake);
DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake_up);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_enter);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_exit);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake_up);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_enter);
DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_exit);
*/
#define cputime_to_usecs(__ct) jiffies_to_usecs(__ct)
#define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs)
+#define usecs_to_cputime64(__msecs) nsecs_to_jiffies64((__msecs) * 1000)
/*
* Convert cputime to seconds and back.
__SYSCALL(__NR_setns, sys_setns)
#define __NR_sendmmsg 269
__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+ compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+ compat_sys_process_vm_writev)
#undef __NR_syscalls
-#define __NR_syscalls 270
+#define __NR_syscalls 272
/*
* All syscalls below here should go away really,
#define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02
#define DRM_MODE_FB_DIRTY_FLAGS 0x03
+#define DRM_MODE_FB_DIRTY_MAX_CLIPS 256
+
/*
* Mark a region of a framebuffer as dirty.
*
*/
#define radeon_PCI_IDS \
{0x1002, 0x3150, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
+ {0x1002, 0x3151, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x3152, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x3154, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x3155, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
+ {0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
{0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6751, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6759, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x675B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x675D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x675F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6760, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6761, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6772, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x677B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6840, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6841, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6842, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6843, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6849, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6889, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68f2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68f8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68f9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x68fa, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68fe, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x7100, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R520|RADEON_NEW_MEMMAP}, \
{0x1002, 0x7101, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R520|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9805, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9806, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0, 0, 0}
#define r128_PCI_IDS \
/**
* User-desired buffer creation information structure.
*
- * @size: requested size for the object.
+ * @size: user-desired memory allocation size.
* - this size value would be page-aligned internally.
* @flags: user request for setting memory type or cache attributes.
- * @handle: returned handle for the object.
- * @pad: just padding to be 64-bit aligned.
+ * @handle: returned a handle to created gem object.
+ * - this handle will be set by gem module of kernel side.
*/
struct drm_exynos_gem_create {
- unsigned int size;
+ uint64_t size;
unsigned int flags;
unsigned int handle;
- unsigned int pad;
};
/**
#define RADEON_CHUNK_ID_RELOCS 0x01
#define RADEON_CHUNK_ID_IB 0x02
+#define RADEON_CHUNK_ID_FLAGS 0x03
+
+/* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
+#define RADEON_CS_KEEP_TILING_FLAGS 0x01
struct drm_radeon_cs_chunk {
uint32_t chunk_id;
header-y += if_pppox.h
header-y += if_slip.h
header-y += if_strip.h
+header-y += if_team.h
header-y += if_tr.h
header-y += if_tun.h
header-y += if_tunnel.h
header-y += in.h
header-y += in6.h
header-y += in_route.h
+header-y += sock_diag.h
header-y += inet_diag.h
+header-y += unix_diag.h
header-y += inotify.h
header-y += input.h
header-y += ioctl.h
void atm_dev_release_vccs(struct atm_dev *dev);
-/*
- * This is approximately the algorithm used by alloc_skb.
- *
- */
-
-static inline int atm_guess_pdu2truesize(int size)
-{
- return SKB_DATA_ALIGN(size) + sizeof(struct skb_shared_info);
-}
-
static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
{
extern struct bio_set *bioset_create(unsigned int, unsigned int);
extern void bioset_free(struct bio_set *);
-extern struct bio *bio_alloc(gfp_t, int);
-extern struct bio *bio_kmalloc(gfp_t, int);
+extern struct bio *bio_alloc(gfp_t, unsigned int);
+extern struct bio *bio_kmalloc(gfp_t, unsigned int);
extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
extern void bio_put(struct bio *);
extern void bio_free(struct bio *, struct bio_set *);
#define bioset_integrity_create(a, b) (0)
#define bio_integrity_prep(a) (0)
#define bio_integrity_enabled(a) (0)
-#define bio_integrity_clone(a, b, c, d) (0)
+static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
+ gfp_t gfp_mask, struct bio_set *bs)
+{
+ return 0;
+}
#define bioset_integrity_free(a) do { } while (0)
#define bio_integrity_free(a, b) do { } while (0)
#define bio_integrity_endio(a, b) do { } while (0)
*/
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
spinlock_t *lock, int node_id);
-extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
- request_fn_proc *,
- spinlock_t *, int node_id);
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
request_fn_proc *, spinlock_t *);
--- /dev/null
+#ifndef _CAN_PLATFORM_CC770_H_
+#define _CAN_PLATFORM_CC770_H_
+
+/* CPU Interface Register (0x02) */
+#define CPUIF_CEN 0x01 /* Clock Out Enable */
+#define CPUIF_MUX 0x04 /* Multiplex */
+#define CPUIF_SLP 0x08 /* Sleep */
+#define CPUIF_PWD 0x10 /* Power Down Mode */
+#define CPUIF_DMC 0x20 /* Divide Memory Clock */
+#define CPUIF_DSC 0x40 /* Divide System Clock */
+#define CPUIF_RST 0x80 /* Hardware Reset Status */
+
+/* Clock Out Register (0x1f) */
+#define CLKOUT_CD_MASK 0x0f /* Clock Divider mask */
+#define CLKOUT_SL_MASK 0x30 /* Slew Rate mask */
+#define CLKOUT_SL_SHIFT 4
+
+/* Bus Configuration Register (0x2f) */
+#define BUSCFG_DR0 0x01 /* Disconnect RX0 Input / Select RX input */
+#define BUSCFG_DR1 0x02 /* Disconnect RX1 Input / Silent mode */
+#define BUSCFG_DT1 0x08 /* Disconnect TX1 Output */
+#define BUSCFG_POL 0x20 /* Polarity dominant or recessive */
+#define BUSCFG_CBY 0x40 /* Input Comparator Bypass */
+
+struct cc770_platform_data {
+ u32 osc_freq; /* CAN bus oscillator frequency in Hz */
+
+ u8 cir; /* CPU Interface Register */
+ u8 cor; /* Clock Out Register */
+ u8 bcr; /* Bus Configuration Register */
+};
+
+#endif /* !_CAN_PLATFORM_CC770_H_ */
#include "osdmap.h"
#include "messenger.h"
+/*
+ * Maximum object name size
+ * (must be at least as big as RBD_MAX_MD_NAME_LEN -- currently 100)
+ */
+#define MAX_OBJ_NAME_SIZE 100
+
struct ceph_msg;
struct ceph_snap_context;
struct ceph_osd_request;
struct inode *r_inode; /* for use by callbacks */
void *r_priv; /* ditto */
- char r_oid[40]; /* object name */
+ char r_oid[MAX_OBJ_NAME_SIZE]; /* object name */
int r_oid_len;
unsigned long r_stamp; /* send OR check time */
SUBSYS(blkio)
#endif
+/* */
+
#ifdef CONFIG_CGROUP_PERF
SUBSYS(perf)
#endif
/* */
+
+#ifdef CONFIG_NETPRIO_CGROUP
+SUBSYS(net_prio)
+#endif
+
+/* */
/**
* cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
- * @tc: Pointer to cycle counter.
+ * @cc: Pointer to cycle counter.
* @cycles: Cycles
*
* XXX - This could use some mult_lxl_ll() asm optimization. Same code
* time base as values returned by
* timecounter_read()
* @tc: Pointer to time counter.
- * @cycle: a value returned by tc->cc->read()
+ * @cycle_tstamp: a value returned by tc->cc->read()
*
* Cycle counts that are converted correctly as long as they
* fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
* @mult: cycle to nanosecond multiplier
* @shift: cycle to nanosecond divisor (power of two)
* @max_idle_ns: max idle time permitted by the clocksource (nsecs)
+ * @maxadj: maximum adjustment value to mult (~11%)
* @flags: flags describing special properties
* @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
+ * @cycle_last: most recent cycle counter value seen by ::read()
*/
struct clocksource {
/*
u32 mult;
u32 shift;
u64 max_idle_ns;
-
+ u32 maxadj;
#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
struct arch_clocksource_data archdata;
#endif
void (*suspend)(struct clocksource *cs);
void (*resume)(struct clocksource *cs);
+ /* private: */
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
/* Watchdog related data, used by the framework */
struct list_head wd_list;
/**
* clocksource_cyc2ns - converts clocksource cycles to nanoseconds
+ * @cycles: cycles
+ * @mult: cycle to nanosecond multiplier
+ * @shift: cycle to nanosecond divisor (power of two)
*
* Converts cycles to nanoseconds, using the given mult and shift.
*
extern void __user *compat_alloc_user_space(unsigned long len);
+asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid,
+ const struct compat_iovec __user *lvec,
+ unsigned long liovcnt, const struct compat_iovec __user *rvec,
+ unsigned long riovcnt, unsigned long flags);
+asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
+ const struct compat_iovec __user *lvec,
+ unsigned long liovcnt, const struct compat_iovec __user *rvec,
+ unsigned long riovcnt, unsigned long flags);
+
#endif /* CONFIG_COMPAT */
#endif /* _LINUX_COMPAT_H */
*/
extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
-extern char *__d_path(const struct path *path, struct path *root, char *, int);
+extern char *__d_path(const struct path *, const struct path *, char *, int);
+extern char *d_absolute_path(const struct path *, char *, int);
extern char *d_path(const struct path *, char *, int);
extern char *d_path_with_unreachable(const struct path *, char *, int);
extern char *dentry_path_raw(struct dentry *, char *, int);
* @resume: Called to bring a device on this bus out of sleep mode.
* @pm: Power management operations of this bus, callback the specific
* device driver's pm-ops.
- * @iommu_ops IOMMU specific operations for this bus, used to attach IOMMU
+ * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU
* driver implementations to a bus and allow the driver to do
* bus-specific setup
* @p: The private data of the driver core, only the driver core can
return !!dev->power.async_suspend;
}
+static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
+{
+ dev->power.ignore_children = enable;
+}
+
static inline void device_lock(struct device *dev)
{
mutex_lock(&dev->mutex);
extern int iommu_calculate_agaw(struct intel_iommu *iommu);
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
+extern int intel_iommu_enabled;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
{
}
#define dmar_disabled (1)
+#define intel_iommu_enabled (0)
#endif
--- /dev/null
+/*
+ * Dynamic queue limits (dql) - Definitions
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ *
+ * This header file contains the definitions for dynamic queue limits (dql).
+ * dql would be used in conjunction with a producer/consumer type queue
+ * (possibly a HW queue). Such a queue would have these general properties:
+ *
+ * 1) Objects are queued up to some limit specified as number of objects.
+ * 2) Periodically a completion process executes which retires consumed
+ * objects.
+ * 3) Starvation occurs when limit has been reached, all queued data has
+ * actually been consumed, but completion processing has not yet run
+ * so queuing new data is blocked.
+ * 4) Minimizing the amount of queued data is desirable.
+ *
+ * The goal of dql is to calculate the limit as the minimum number of objects
+ * needed to prevent starvation.
+ *
+ * The primary functions of dql are:
+ * dql_queued - called when objects are enqueued to record number of objects
+ * dql_avail - returns how many objects are available to be queued based
+ * on the object limit and how many objects are already enqueued
+ * dql_completed - called at completion time to indicate how many objects
+ * were retired from the queue
+ *
+ * The dql implementation does not implement any locking for the dql data
+ * structures, the higher layer should provide this. dql_queued should
+ * be serialized to prevent concurrent execution of the function; this
+ * is also true for dql_completed. However, dql_queued and dlq_completed can
+ * be executed concurrently (i.e. they can be protected by different locks).
+ */
+
+#ifndef _LINUX_DQL_H
+#define _LINUX_DQL_H
+
+#ifdef __KERNEL__
+
+struct dql {
+ /* Fields accessed in enqueue path (dql_queued) */
+ unsigned int num_queued; /* Total ever queued */
+ unsigned int adj_limit; /* limit + num_completed */
+ unsigned int last_obj_cnt; /* Count at last queuing */
+
+ /* Fields accessed only by completion path (dql_completed) */
+
+ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */
+ unsigned int num_completed; /* Total ever completed */
+
+ unsigned int prev_ovlimit; /* Previous over limit */
+ unsigned int prev_num_queued; /* Previous queue total */
+ unsigned int prev_last_obj_cnt; /* Previous queuing cnt */
+
+ unsigned int lowest_slack; /* Lowest slack found */
+ unsigned long slack_start_time; /* Time slacks seen */
+
+ /* Configuration */
+ unsigned int max_limit; /* Max limit */
+ unsigned int min_limit; /* Minimum limit */
+ unsigned int slack_hold_time; /* Time to measure slack */
+};
+
+/* Set some static maximums */
+#define DQL_MAX_OBJECT (UINT_MAX / 16)
+#define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT)
+
+/*
+ * Record number of objects queued. Assumes that caller has already checked
+ * availability in the queue with dql_avail.
+ */
+static inline void dql_queued(struct dql *dql, unsigned int count)
+{
+ BUG_ON(count > DQL_MAX_OBJECT);
+
+ dql->num_queued += count;
+ dql->last_obj_cnt = count;
+}
+
+/* Returns how many objects can be queued, < 0 indicates over limit. */
+static inline int dql_avail(const struct dql *dql)
+{
+ return dql->adj_limit - dql->num_queued;
+}
+
+/* Record number of completed objects and recalculate the limit. */
+void dql_completed(struct dql *dql, unsigned int count);
+
+/* Reset dql state */
+void dql_reset(struct dql *dql);
+
+/* Initialize dql state */
+int dql_init(struct dql *dql, unsigned hold_time);
+
+#endif /* _KERNEL_ */
+
+#endif /* _LINUX_DQL_H */
#define PCI_EEPROM_WIDTH_93C86 8
#define PCI_EEPROM_WIDTH_OPCODE 3
#define PCI_EEPROM_WRITE_OPCODE 0x05
+#define PCI_EEPROM_ERASE_OPCODE 0x07
#define PCI_EEPROM_READ_OPCODE 0x06
#define PCI_EEPROM_EWDS_OPCODE 0x10
#define PCI_EEPROM_EWEN_OPCODE 0x13
* @register_write(struct eeprom_93cx6 *eeprom): handler to
* write to the eeprom register by using all reg_* fields.
* @width: eeprom width, should be one of the PCI_EEPROM_WIDTH_* defines
+ * @drive_data: Set if we're driving the data line.
* @reg_data_in: register field to indicate data input
* @reg_data_out: register field to indicate data output
* @reg_data_clock: register field to set the data clock
int width;
+ char drive_data;
char reg_data_in;
char reg_data_out;
char reg_data_clock;
const u8 word, u16 *data);
extern void eeprom_93cx6_multiread(struct eeprom_93cx6 *eeprom,
const u8 word, __le16 *data, const u16 words);
+
+extern void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable);
+
+extern void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom,
+ u8 addr, u16 data);
#ifdef __KERNEL__
#include <net/ip.h>
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif
struct sock_exterr_skb {
union {
struct inet_skb_parm h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header;
* on return.
*
* For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined
- * rules on return.
+ * rules on return. If @data is non-zero on return then it is the
+ * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the
+ * driver supports any special location values. If that flag is not
+ * set in @data then special location values should not be used.
*
* For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an
* existing rule on entry and @fs contains the rule on return.
* must use the second parameter to get_rxnfc() instead of @rule_locs.
*
* For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update.
- * @fs.@location specifies the location to use and must not be ignored.
+ * @fs.@location either specifies the location to use or is a special
+ * location value with %RX_CLS_LOC_SPECIAL flag set. On return,
+ * @fs.@location is the actual rule location.
*
* For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an
* existing rule on entry.
+ *
+ * A driver supporting the special location values for
+ * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused
+ * location, and may remove a rule at a later location (lower
+ * priority) that matches exactly the same set of flows. The special
+ * values are: %RX_CLS_LOC_ANY, selecting any location;
+ * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum
+ * priority); and %RX_CLS_LOC_LAST, selecting the last suitable
+ * location (minimum priority). Additional special values may be
+ * defined in future and drivers must return -%EINVAL for any
+ * unrecognised value.
*/
struct ethtool_rxnfc {
__u32 cmd;
/**
* struct ethtool_rxfh_indir - command to get or set RX flow hash indirection
* @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR
- * @size: On entry, the array size of the user buffer. On return from
- * %ETHTOOL_GRXFHINDIR, the array size of the hardware indirection table.
+ * @size: On entry, the array size of the user buffer, which may be zero.
+ * On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware
+ * indirection table.
* @ring_index: RX ring/queue index for each hash value
+ *
+ * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size
+ * should be returned. For %ETHTOOL_SRXFHINDIR, a @size of zero means
+ * the table should be reset to default values. This last feature
+ * is not supported by the original implementations.
*/
struct ethtool_rxfh_indir {
__u32 cmd;
#include <linux/rculist.h>
-/* needed by dev_disable_lro() */
-extern int __ethtool_set_flags(struct net_device *dev, u32 flags);
-
extern int __ethtool_get_settings(struct net_device *dev,
struct ethtool_cmd *cmd);
/* Some generic methods drivers may use in their ethtool_ops */
u32 ethtool_op_get_link(struct net_device *dev);
-u32 ethtool_op_get_tx_csum(struct net_device *dev);
-int ethtool_op_set_tx_csum(struct net_device *dev, u32 data);
-int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data);
-int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data);
-u32 ethtool_op_get_sg(struct net_device *dev);
-int ethtool_op_set_sg(struct net_device *dev, u32 data);
-u32 ethtool_op_get_tso(struct net_device *dev);
-int ethtool_op_set_tso(struct net_device *dev, u32 data);
-u32 ethtool_op_get_ufo(struct net_device *dev);
-int ethtool_op_set_ufo(struct net_device *dev, u32 data);
-u32 ethtool_op_get_flags(struct net_device *dev);
-int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported);
-bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
+
+/**
+ * ethtool_rxfh_indir_default - get default value for RX flow hash indirection
+ * @index: Index in RX flow hash indirection table
+ * @n_rx_rings: Number of RX rings to use
+ *
+ * This function provides the default policy for RX flow hash indirection.
+ */
+static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
+{
+ return index % n_rx_rings;
+}
/**
* struct ethtool_ops - optional netdev operations
* @get_pauseparam: Report pause parameters
* @set_pauseparam: Set pause parameters. Returns a negative error code
* or zero.
- * @get_rx_csum: Deprecated in favour of the netdev feature %NETIF_F_RXCSUM.
- * Report whether receive checksums are turned on or off.
- * @set_rx_csum: Deprecated in favour of generic netdev features. Turn
- * receive checksum on or off. Returns a negative error code or zero.
- * @get_tx_csum: Deprecated as redundant. Report whether transmit checksums
- * are turned on or off.
- * @set_tx_csum: Deprecated in favour of generic netdev features. Turn
- * transmit checksums on or off. Returns a negative error code or zero.
- * @get_sg: Deprecated as redundant. Report whether scatter-gather is
- * enabled.
- * @set_sg: Deprecated in favour of generic netdev features. Turn
- * scatter-gather on or off. Returns a negative error code or zero.
- * @get_tso: Deprecated as redundant. Report whether TCP segmentation
- * offload is enabled.
- * @set_tso: Deprecated in favour of generic netdev features. Turn TCP
- * segmentation offload on or off. Returns a negative error code or zero.
* @self_test: Run specified self-tests
* @get_strings: Return a set of strings that describe the requested objects
* @set_phys_id: Identify the physical devices, e.g. by flashing an LED
* negative error code or zero.
* @complete: Function to be called after any other operation except
* @begin. Will be called even if the other operation failed.
- * @get_ufo: Deprecated as redundant. Report whether UDP fragmentation
- * offload is enabled.
- * @set_ufo: Deprecated in favour of generic netdev features. Turn UDP
- * fragmentation offload on or off. Returns a negative error code or zero.
- * @get_flags: Deprecated as redundant. Report features included in
- * &enum ethtool_flags that are enabled.
- * @set_flags: Deprecated in favour of generic netdev features. Turn
- * features included in &enum ethtool_flags on or off. Returns a
- * negative error code or zero.
* @get_priv_flags: Report driver-specific feature flags.
* @set_priv_flags: Set driver-specific feature flags. Returns a negative
* error code or zero.
* @reset: Reset (part of) the device, as specified by a bitmask of
* flags from &enum ethtool_reset_flags. Returns a negative
* error code or zero.
- * @set_rx_ntuple: Set an RX n-tuple rule. Returns a negative error code
- * or zero.
+ * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
+ * Returns zero if not supported for this specific device.
* @get_rxfh_indir: Get the contents of the RX flow hash indirection table.
+ * Will not be called if @get_rxfh_indir_size returns zero.
* Returns a negative error code or zero.
* @set_rxfh_indir: Set the contents of the RX flow hash indirection table.
+ * Will not be called if @get_rxfh_indir_size returns zero.
* Returns a negative error code or zero.
* @get_channels: Get number of channels.
* @set_channels: Set number of channels. Returns a negative error code or
struct ethtool_pauseparam*);
int (*set_pauseparam)(struct net_device *,
struct ethtool_pauseparam*);
- u32 (*get_rx_csum)(struct net_device *);
- int (*set_rx_csum)(struct net_device *, u32);
- u32 (*get_tx_csum)(struct net_device *);
- int (*set_tx_csum)(struct net_device *, u32);
- u32 (*get_sg)(struct net_device *);
- int (*set_sg)(struct net_device *, u32);
- u32 (*get_tso)(struct net_device *);
- int (*set_tso)(struct net_device *, u32);
void (*self_test)(struct net_device *, struct ethtool_test *, u64 *);
void (*get_strings)(struct net_device *, u32 stringset, u8 *);
int (*set_phys_id)(struct net_device *, enum ethtool_phys_id_state);
struct ethtool_stats *, u64 *);
int (*begin)(struct net_device *);
void (*complete)(struct net_device *);
- u32 (*get_ufo)(struct net_device *);
- int (*set_ufo)(struct net_device *, u32);
- u32 (*get_flags)(struct net_device *);
- int (*set_flags)(struct net_device *, u32);
u32 (*get_priv_flags)(struct net_device *);
int (*set_priv_flags)(struct net_device *, u32);
int (*get_sset_count)(struct net_device *, int);
int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *);
int (*flash_device)(struct net_device *, struct ethtool_flash *);
int (*reset)(struct net_device *, u32 *);
- int (*set_rx_ntuple)(struct net_device *,
- struct ethtool_rx_ntuple *);
- int (*get_rxfh_indir)(struct net_device *,
- struct ethtool_rxfh_indir *);
- int (*set_rxfh_indir)(struct net_device *,
- const struct ethtool_rxfh_indir *);
+ u32 (*get_rxfh_indir_size)(struct net_device *);
+ int (*get_rxfh_indir)(struct net_device *, u32 *);
+ int (*set_rxfh_indir)(struct net_device *, const u32 *);
void (*get_channels)(struct net_device *, struct ethtool_channels *);
int (*set_channels)(struct net_device *, struct ethtool_channels *);
int (*get_dump_flag)(struct net_device *, struct ethtool_dump *);
#define RX_CLS_FLOW_DISC 0xffffffffffffffffULL
+/* Special RX classification rule insert location values */
+#define RX_CLS_LOC_SPECIAL 0x80000000 /* flag */
+#define RX_CLS_LOC_ANY 0xffffffff
+#define RX_CLS_LOC_FIRST 0xfffffffe
+#define RX_CLS_LOC_LAST 0xfffffffd
+
/* Reset flags */
/* The reset() operation must clear the flags for the components which
* were actually reset. On successful return, the flags indicate the
#include <linux/semaphore.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
-#include <linux/shrinker.h>
#include <linux/atomic.h>
+#include <linux/shrinker.h>
#include <asm/byteorder.h>
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
+extern bool our_mnt(struct vfsmount *mnt);
extern int current_umask(void);
TRACE_EVENT_FL_FILTERED_BIT,
TRACE_EVENT_FL_RECORDED_CMD_BIT,
TRACE_EVENT_FL_CAP_ANY_BIT,
+ TRACE_EVENT_FL_NO_SET_FILTER_BIT,
};
enum {
TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT),
TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
+ TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
};
struct ftrace_event_call {
/* All generic netlink requests are serialized by a global lock. */
extern void genl_lock(void);
extern void genl_unlock(void);
+#ifdef CONFIG_PROVE_LOCKING
+extern int lockdep_genl_is_held(void);
+#endif
+
+/**
+ * rcu_dereference_genl - rcu_dereference with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Do an rcu_dereference(p), but check caller either holds rcu_read_lock()
+ * or genl mutex. Note : Please prefer genl_dereference() or rcu_dereference()
+ */
+#define rcu_dereference_genl(p) \
+ rcu_dereference_check(p, lockdep_genl_is_held())
+
+/**
+ * genl_dereference - fetch RCU pointer when updates are prevented by genl mutex
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Return the value of the specified RCU-protected pointer, but omit
+ * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * caller holds genl mutex.
+ */
+#define genl_dereference(p) \
+ rcu_dereference_protected(p, lockdep_genl_is_held())
#endif /* __KERNEL__ */
#define dev_to_part(device) container_of((device), struct hd_struct, __dev)
#define disk_to_dev(disk) (&(disk)->part0.__dev)
#define part_to_dev(part) (&((part)->__dev))
-#define alias_name(disk) ((disk)->alias ? (disk)->alias : \
- (disk)->disk_name)
extern struct device_type part_type;
extern struct kobject *block_depr;
#define DISK_MAX_PARTS 256
#define DISK_NAME_LEN 32
-#define ALIAS_LEN 256
#include <linux/major.h>
#include <linux/device.h>
* disks that can't be partitioned. */
char disk_name[DISK_NAME_LEN]; /* name of major driver */
- char *alias; /* alias name of disk */
char *(*devnode)(struct gendisk *gd, mode_t *mode);
unsigned int events; /* supported events */
#define hugetlb_change_protection(vma, address, end, newprot)
-#ifndef HPAGE_MASK
-#define HPAGE_MASK PAGE_MASK /* Keep the compiler happy */
-#define HPAGE_SIZE PAGE_SIZE
-#endif
-
#endif /* !CONFIG_HUGETLB_PAGE */
#define HUGETLB_ANON_FILE "anon_hugepage"
/* Internal numbers to terminate lists */
#define I2C_CLIENT_END 0xfffeU
-/* The numbers to use to set I2C bus address */
-#define ANY_I2C_BUS 0xffff
-
/* Construct an I2C_CLIENT_END-terminated array of i2c addresses */
#define I2C_ADDRS(addr, addrs...) \
((const unsigned short []){ addr, ## addrs, I2C_CLIENT_END })
#define IFF_TX_SKB_SHARING 0x10000 /* The interface supports sharing
* skbs on transmit */
#define IFF_UNICAST_FLT 0x20000 /* Supports unicast filtering */
+#define IFF_TEAM_PORT 0x40000 /* device used as team port */
#define IF_GET_IFACE 0x0001 /* for querying only */
#define IF_GET_PROTO 0x0002
#define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */
#define ETH_P_AOE 0x88A2 /* ATA over Ethernet */
#define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */
+#define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */
#define ETH_P_TIPC 0x88CA /* TIPC */
#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */
#define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */
--- /dev/null
+/*
+ * include/linux/if_team.h - Network team device driver header
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_TEAM_H_
+#define _LINUX_IF_TEAM_H_
+
+#ifdef __KERNEL__
+
+struct team_pcpu_stats {
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 rx_multicast;
+ u64 tx_packets;
+ u64 tx_bytes;
+ struct u64_stats_sync syncp;
+ u32 rx_dropped;
+ u32 tx_dropped;
+};
+
+struct team;
+
+struct team_port {
+ struct net_device *dev;
+ struct hlist_node hlist; /* node in hash list */
+ struct list_head list; /* node in ordinary list */
+ struct team *team;
+ int index;
+
+ /*
+ * A place for storing original values of the device before it
+ * become a port.
+ */
+ struct {
+ unsigned char dev_addr[MAX_ADDR_LEN];
+ unsigned int mtu;
+ } orig;
+
+ bool linkup;
+ u32 speed;
+ u8 duplex;
+
+ struct rcu_head rcu;
+};
+
+struct team_mode_ops {
+ int (*init)(struct team *team);
+ void (*exit)(struct team *team);
+ rx_handler_result_t (*receive)(struct team *team,
+ struct team_port *port,
+ struct sk_buff *skb);
+ bool (*transmit)(struct team *team, struct sk_buff *skb);
+ int (*port_enter)(struct team *team, struct team_port *port);
+ void (*port_leave)(struct team *team, struct team_port *port);
+ void (*port_change_mac)(struct team *team, struct team_port *port);
+};
+
+enum team_option_type {
+ TEAM_OPTION_TYPE_U32,
+ TEAM_OPTION_TYPE_STRING,
+};
+
+struct team_option {
+ struct list_head list;
+ const char *name;
+ enum team_option_type type;
+ int (*getter)(struct team *team, void *arg);
+ int (*setter)(struct team *team, void *arg);
+};
+
+struct team_mode {
+ struct list_head list;
+ const char *kind;
+ struct module *owner;
+ size_t priv_size;
+ const struct team_mode_ops *ops;
+};
+
+#define TEAM_PORT_HASHBITS 4
+#define TEAM_PORT_HASHENTRIES (1 << TEAM_PORT_HASHBITS)
+
+#define TEAM_MODE_PRIV_LONGS 4
+#define TEAM_MODE_PRIV_SIZE (sizeof(long) * TEAM_MODE_PRIV_LONGS)
+
+struct team {
+ struct net_device *dev; /* associated netdevice */
+ struct team_pcpu_stats __percpu *pcpu_stats;
+
+ struct mutex lock; /* used for overall locking, e.g. port lists write */
+
+ /*
+ * port lists with port count
+ */
+ int port_count;
+ struct hlist_head port_hlist[TEAM_PORT_HASHENTRIES];
+ struct list_head port_list;
+
+ struct list_head option_list;
+
+ const struct team_mode *mode;
+ struct team_mode_ops ops;
+ long mode_priv[TEAM_MODE_PRIV_LONGS];
+};
+
+static inline struct hlist_head *team_port_index_hash(struct team *team,
+ int port_index)
+{
+ return &team->port_hlist[port_index & (TEAM_PORT_HASHENTRIES - 1)];
+}
+
+static inline struct team_port *team_get_port_by_index(struct team *team,
+ int port_index)
+{
+ struct hlist_node *p;
+ struct team_port *port;
+ struct hlist_head *head = team_port_index_hash(team, port_index);
+
+ hlist_for_each_entry(port, p, head, hlist)
+ if (port->index == port_index)
+ return port;
+ return NULL;
+}
+static inline struct team_port *team_get_port_by_index_rcu(struct team *team,
+ int port_index)
+{
+ struct hlist_node *p;
+ struct team_port *port;
+ struct hlist_head *head = team_port_index_hash(team, port_index);
+
+ hlist_for_each_entry_rcu(port, p, head, hlist)
+ if (port->index == port_index)
+ return port;
+ return NULL;
+}
+
+extern int team_port_set_team_mac(struct team_port *port);
+extern int team_options_register(struct team *team,
+ const struct team_option *option,
+ size_t option_count);
+extern void team_options_unregister(struct team *team,
+ const struct team_option *option,
+ size_t option_count);
+extern int team_mode_register(struct team_mode *mode);
+extern int team_mode_unregister(struct team_mode *mode);
+
+#endif /* __KERNEL__ */
+
+#define TEAM_STRING_MAX_LEN 32
+
+/**********************************
+ * NETLINK_GENERIC netlink family.
+ **********************************/
+
+enum {
+ TEAM_CMD_NOOP,
+ TEAM_CMD_OPTIONS_SET,
+ TEAM_CMD_OPTIONS_GET,
+ TEAM_CMD_PORT_LIST_GET,
+
+ __TEAM_CMD_MAX,
+ TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1),
+};
+
+enum {
+ TEAM_ATTR_UNSPEC,
+ TEAM_ATTR_TEAM_IFINDEX, /* u32 */
+ TEAM_ATTR_LIST_OPTION, /* nest */
+ TEAM_ATTR_LIST_PORT, /* nest */
+
+ __TEAM_ATTR_MAX,
+ TEAM_ATTR_MAX = __TEAM_ATTR_MAX - 1,
+};
+
+/* Nested layout of get/set msg:
+ *
+ * [TEAM_ATTR_LIST_OPTION]
+ * [TEAM_ATTR_ITEM_OPTION]
+ * [TEAM_ATTR_OPTION_*], ...
+ * [TEAM_ATTR_ITEM_OPTION]
+ * [TEAM_ATTR_OPTION_*], ...
+ * ...
+ * [TEAM_ATTR_LIST_PORT]
+ * [TEAM_ATTR_ITEM_PORT]
+ * [TEAM_ATTR_PORT_*], ...
+ * [TEAM_ATTR_ITEM_PORT]
+ * [TEAM_ATTR_PORT_*], ...
+ * ...
+ */
+
+enum {
+ TEAM_ATTR_ITEM_OPTION_UNSPEC,
+ TEAM_ATTR_ITEM_OPTION, /* nest */
+
+ __TEAM_ATTR_ITEM_OPTION_MAX,
+ TEAM_ATTR_ITEM_OPTION_MAX = __TEAM_ATTR_ITEM_OPTION_MAX - 1,
+};
+
+enum {
+ TEAM_ATTR_OPTION_UNSPEC,
+ TEAM_ATTR_OPTION_NAME, /* string */
+ TEAM_ATTR_OPTION_CHANGED, /* flag */
+ TEAM_ATTR_OPTION_TYPE, /* u8 */
+ TEAM_ATTR_OPTION_DATA, /* dynamic */
+
+ __TEAM_ATTR_OPTION_MAX,
+ TEAM_ATTR_OPTION_MAX = __TEAM_ATTR_OPTION_MAX - 1,
+};
+
+enum {
+ TEAM_ATTR_ITEM_PORT_UNSPEC,
+ TEAM_ATTR_ITEM_PORT, /* nest */
+
+ __TEAM_ATTR_ITEM_PORT_MAX,
+ TEAM_ATTR_ITEM_PORT_MAX = __TEAM_ATTR_ITEM_PORT_MAX - 1,
+};
+
+enum {
+ TEAM_ATTR_PORT_UNSPEC,
+ TEAM_ATTR_PORT_IFINDEX, /* u32 */
+ TEAM_ATTR_PORT_CHANGED, /* flag */
+ TEAM_ATTR_PORT_LINKUP, /* flag */
+ TEAM_ATTR_PORT_SPEED, /* u32 */
+ TEAM_ATTR_PORT_DUPLEX, /* u8 */
+
+ __TEAM_ATTR_PORT_MAX,
+ TEAM_ATTR_PORT_MAX = __TEAM_ATTR_PORT_MAX - 1,
+};
+
+/*
+ * NETLINK_GENERIC related info
+ */
+#define TEAM_GENL_NAME "team"
+#define TEAM_GENL_VERSION 0x1
+#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event"
+
+#endif /* _LINUX_IF_TEAM_H_ */
/* found in socket.c */
extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
-/* if this changes, algorithm will have to be reworked because this
- * depends on completely exhausting the VLAN identifier space. Thus
- * it gives constant time look-up, but in many cases it wastes memory.
- */
-#define VLAN_GROUP_ARRAY_SPLIT_PARTS 8
-#define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS)
-
-struct vlan_group {
- struct net_device *real_dev; /* The ethernet(like) device
- * the vlan is attached to.
- */
- unsigned int nr_vlans;
- struct hlist_node hlist; /* linked list */
- struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS];
- struct rcu_head rcu;
-};
+struct vlan_info;
static inline int is_vlan_dev(struct net_device *dev)
{
extern bool vlan_do_receive(struct sk_buff **skb, bool last_handler);
extern struct sk_buff *vlan_untag(struct sk_buff *skb);
+extern int vlan_vid_add(struct net_device *dev, unsigned short vid);
+extern void vlan_vid_del(struct net_device *dev, unsigned short vid);
+
+extern int vlan_vids_add_by_dev(struct net_device *dev,
+ const struct net_device *by_dev);
+extern void vlan_vids_del_by_dev(struct net_device *dev,
+ const struct net_device *by_dev);
#else
static inline struct net_device *
__vlan_find_dev_deep(struct net_device *real_dev, u16 vlan_id)
{
return skb;
}
+
+static inline int vlan_vid_add(struct net_device *dev, unsigned short vid)
+{
+ return 0;
+}
+
+static inline void vlan_vid_del(struct net_device *dev, unsigned short vid)
+{
+}
+
+static inline int vlan_vids_add_by_dev(struct net_device *dev,
+ const struct net_device *by_dev)
+{
+ return 0;
+}
+
+static inline void vlan_vids_del_by_dev(struct net_device *dev,
+ const struct net_device *by_dev)
+{
+}
#endif
/**
return protocol;
}
+
+static inline void vlan_set_encap_proto(struct sk_buff *skb,
+ struct vlan_hdr *vhdr)
+{
+ __be16 proto;
+ unsigned char *rawp;
+
+ /*
+ * Was a VLAN packet, grab the encapsulated protocol, which the layer
+ * three protocols care about.
+ */
+
+ proto = vhdr->h_vlan_encapsulated_proto;
+ if (ntohs(proto) >= 1536) {
+ skb->protocol = proto;
+ return;
+ }
+
+ rawp = skb->data;
+ if (*(unsigned short *) rawp == 0xFFFF)
+ /*
+ * This is a magic hack to spot IPX packets. Older Novell
+ * breaks the protocol design and runs IPX over 802.3 without
+ * an 802.2 LLC layer. We look for FFFF which isn't a used
+ * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
+ * but does for the rest.
+ */
+ skb->protocol = htons(ETH_P_802_3);
+ else
+ /*
+ * Real 802.2 LLC
+ */
+ skb->protocol = htons(ETH_P_802_2);
+}
#endif /* __KERNEL__ */
/* VLAN IOCTLs are found in sockios.h */
unsigned int skb_priority;
unsigned int name_type;
unsigned int bind_type;
- unsigned int flag; /* Matches vlan_dev_info flags */
+ unsigned int flag; /* Matches vlan_dev_priv flags */
} u;
short vlan_qos;
/* Request structure */
-struct inet_diag_req {
+struct inet_diag_req_compat {
__u8 idiag_family; /* Family of addresses. */
__u8 idiag_src_len;
__u8 idiag_dst_len;
__u32 idiag_dbs; /* Tables to dump (NI) */
};
+struct inet_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 pad;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
enum {
INET_DIAG_REQ_NONE,
INET_DIAG_REQ_BYTECODE,
INET_DIAG_VEGASINFO,
INET_DIAG_CONG,
INET_DIAG_TOS,
+ INET_DIAG_TCLASS,
+ INET_DIAG_SKMEMINFO,
};
-#define INET_DIAG_MAX INET_DIAG_TOS
+#define INET_DIAG_MAX INET_DIAG_SKMEMINFO
/* INET_DIAG_MEM */
#ifdef __KERNEL__
struct sock;
struct inet_hashinfo;
+struct nlattr;
+struct nlmsghdr;
+struct sk_buff;
+struct netlink_callback;
struct inet_diag_handler {
- struct inet_hashinfo *idiag_hashinfo;
+ void (*dump)(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct inet_diag_req *r,
+ struct nlattr *bc);
+
+ int (*dump_one)(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct inet_diag_req *req);
+
void (*idiag_get_info)(struct sock *sk,
struct inet_diag_msg *r,
void *info);
- __u16 idiag_info_size;
__u16 idiag_type;
};
+struct inet_connection_sock;
+int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
+ struct sk_buff *skb, struct inet_diag_req *req,
+ u32 pid, u32 seq, u16 nlmsg_flags,
+ const struct nlmsghdr *unlh);
+void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb,
+ struct netlink_callback *cb, struct inet_diag_req *r,
+ struct nlattr *bc);
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
+ struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+ struct inet_diag_req *req);
+
+int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
+
extern int inet_diag_register(const struct inet_diag_handler *handler);
extern void inet_diag_unregister(const struct inet_diag_handler *handler);
#endif /* __KERNEL__ */
# define INIT_PERF_EVENTS(tsk)
#endif
+#define INIT_TASK_COMM "swapper"
+
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
.group_leader = &tsk, \
RCU_INIT_POINTER(.real_cred, &init_cred), \
RCU_INIT_POINTER(.cred, &init_cred), \
- .comm = "swapper", \
+ .comm = INIT_TASK_COMM, \
.thread = INIT_THREAD, \
.fs = &init_fs, \
.files = &init_files, \
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
}, \
.thread_group = LIST_HEAD_INIT(tsk.thread_group), \
- .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \
INIT_IDS \
INIT_PERF_EVENTS(tsk) \
INIT_TRACE_IRQFLAGS \
extern int inet6_sk_rebuild_header(struct sock *sk);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
{
return inet_sk(__sk)->pinet6;
#define inet6_rcv_saddr(__sk) NULL
#define tcp_twsk_ipv6only(__sk) 0
#define inet_v6_ipv6only(__sk) 0
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
#define INET6_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif)\
(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \
#define KVM_CAP_PPC_SMT 64
#define KVM_CAP_PPC_RMA 65
#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */
-#define KVM_CAP_PPC_HIOR 67
#define KVM_CAP_PPC_PAPR 68
#define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
#ifdef KVM_CAP_IRQ_ROUTING
#include <linux/spinlock.h>
#include <linux/lockdep.h>
#include <linux/percpu.h>
+#include <linux/cpu.h>
/* can make br locks by using local lock for read side, global lock for write */
#define br_lock_init(name) name##_lock_init()
#define DEFINE_LGLOCK(name) \
\
+ DEFINE_SPINLOCK(name##_cpu_lock); \
+ cpumask_t name##_cpus __read_mostly; \
DEFINE_PER_CPU(arch_spinlock_t, name##_lock); \
DEFINE_LGLOCK_LOCKDEP(name); \
\
+ static int \
+ name##_lg_cpu_callback(struct notifier_block *nb, \
+ unsigned long action, void *hcpu) \
+ { \
+ switch (action & ~CPU_TASKS_FROZEN) { \
+ case CPU_UP_PREPARE: \
+ spin_lock(&name##_cpu_lock); \
+ cpu_set((unsigned long)hcpu, name##_cpus); \
+ spin_unlock(&name##_cpu_lock); \
+ break; \
+ case CPU_UP_CANCELED: case CPU_DEAD: \
+ spin_lock(&name##_cpu_lock); \
+ cpu_clear((unsigned long)hcpu, name##_cpus); \
+ spin_unlock(&name##_cpu_lock); \
+ } \
+ return NOTIFY_OK; \
+ } \
+ static struct notifier_block name##_lg_cpu_notifier = { \
+ .notifier_call = name##_lg_cpu_callback, \
+ }; \
void name##_lock_init(void) { \
int i; \
LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \
lock = &per_cpu(name##_lock, i); \
*lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; \
} \
+ register_hotcpu_notifier(&name##_lg_cpu_notifier); \
+ get_online_cpus(); \
+ for_each_online_cpu(i) \
+ cpu_set(i, name##_cpus); \
+ put_online_cpus(); \
} \
EXPORT_SYMBOL(name##_lock_init); \
\
\
void name##_global_lock_online(void) { \
int i; \
- preempt_disable(); \
+ spin_lock(&name##_cpu_lock); \
rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \
- for_each_online_cpu(i) { \
+ for_each_cpu(i, &name##_cpus) { \
arch_spinlock_t *lock; \
lock = &per_cpu(name##_lock, i); \
arch_spin_lock(lock); \
void name##_global_unlock_online(void) { \
int i; \
rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \
- for_each_online_cpu(i) { \
+ for_each_cpu(i, &name##_cpus) { \
arch_spinlock_t *lock; \
lock = &per_cpu(name##_lock, i); \
arch_spin_unlock(lock); \
} \
- preempt_enable(); \
+ spin_unlock(&name##_cpu_lock); \
} \
EXPORT_SYMBOL(name##_global_unlock_online); \
\
return ipv4_is_loopback(sin->sin_addr.s_addr);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline int __nlm_privileged_request6(const struct sockaddr *sap)
{
const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
return ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LOOPBACK;
}
-#else /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#else /* IS_ENABLED(CONFIG_IPV6) */
static inline int __nlm_privileged_request6(const struct sockaddr *sap)
{
return 0;
}
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
/*
* Ensure incoming requests are from local privileged callers.
#define rounddown_pow_of_two(n) \
( \
__builtin_constant_p(n) ? ( \
- (n == 1) ? 0 : \
(1UL << ilog2(n))) : \
__rounddown_pow_of_two(n) \
)
struct mdiobb_ctrl {
const struct mdiobb_ops *ops;
+ /* reset callback */
+ int (*reset)(struct mii_bus *bus);
};
/* The returned bus is not yet registered with the phy layer. */
unsigned int phy_mask;
int irqs[PHY_MAX_ADDR];
+ /* reset callback */
+ int (*reset)(struct mii_bus *bus);
};
#endif /* __LINUX_MDIO_GPIO_H */
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
+extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont);
+
static inline
int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
{
}
#endif
+enum {
+ UNDER_LIMIT,
+ SOFT_LIMIT,
+ OVER_LIMIT,
+};
+
+#ifdef CONFIG_INET
+struct sock;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+void sock_update_memcg(struct sock *sk);
+void sock_release_memcg(struct sock *sk);
+#else
+static inline void sock_update_memcg(struct sock *sk)
+{
+}
+static inline void sock_release_memcg(struct sock *sk)
+{
+}
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_INET */
#endif /* _LINUX_MEMCONTROL_H */
/*Registers VDD1, VDD2 voltage values definitions */
-#define VDD1_2_NUM_VOLTS 73
+#define VDD1_2_NUM_VOLT_FINE 73
+#define VDD1_2_NUM_VOLT_COARSE 3
#define VDD1_2_MIN_VOLT 6000
#define VDD1_2_OFFSET 125
#define __LINUX_MII_H__
#include <linux/types.h>
+#include <linux/ethtool.h>
/* Generic MII registers. */
#define MII_BMCR 0x00 /* Basic mode control register */
return 0;
}
+/**
+ * ethtool_adv_to_mii_adv_t
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_ADVERTISE register.
+ */
+static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv)
+{
+ u32 result = 0;
+
+ if (ethadv & ADVERTISED_10baseT_Half)
+ result |= ADVERTISE_10HALF;
+ if (ethadv & ADVERTISED_10baseT_Full)
+ result |= ADVERTISE_10FULL;
+ if (ethadv & ADVERTISED_100baseT_Half)
+ result |= ADVERTISE_100HALF;
+ if (ethadv & ADVERTISED_100baseT_Full)
+ result |= ADVERTISE_100FULL;
+ if (ethadv & ADVERTISED_Pause)
+ result |= ADVERTISE_PAUSE_CAP;
+ if (ethadv & ADVERTISED_Asym_Pause)
+ result |= ADVERTISE_PAUSE_ASYM;
+
+ return result;
+}
+
+/**
+ * mii_adv_to_ethtool_adv_t
+ * @adv: value of the MII_ADVERTISE register
+ *
+ * A small helper function that translates MII_ADVERTISE bits
+ * to ethtool advertisement settings.
+ */
+static inline u32 mii_adv_to_ethtool_adv_t(u32 adv)
+{
+ u32 result = 0;
+
+ if (adv & ADVERTISE_10HALF)
+ result |= ADVERTISED_10baseT_Half;
+ if (adv & ADVERTISE_10FULL)
+ result |= ADVERTISED_10baseT_Full;
+ if (adv & ADVERTISE_100HALF)
+ result |= ADVERTISED_100baseT_Half;
+ if (adv & ADVERTISE_100FULL)
+ result |= ADVERTISED_100baseT_Full;
+ if (adv & ADVERTISE_PAUSE_CAP)
+ result |= ADVERTISED_Pause;
+ if (adv & ADVERTISE_PAUSE_ASYM)
+ result |= ADVERTISED_Asym_Pause;
+
+ return result;
+}
+
+/**
+ * ethtool_adv_to_mii_ctrl1000_t
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_CTRL1000 register when in 1000T mode.
+ */
+static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv)
+{
+ u32 result = 0;
+
+ if (ethadv & ADVERTISED_1000baseT_Half)
+ result |= ADVERTISE_1000HALF;
+ if (ethadv & ADVERTISED_1000baseT_Full)
+ result |= ADVERTISE_1000FULL;
+
+ return result;
+}
+
+/**
+ * mii_ctrl1000_to_ethtool_adv_t
+ * @adv: value of the MII_CTRL1000 register
+ *
+ * A small helper function that translates MII_CTRL1000
+ * bits, when in 1000Base-T mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_ctrl1000_to_ethtool_adv_t(u32 adv)
+{
+ u32 result = 0;
+
+ if (adv & ADVERTISE_1000HALF)
+ result |= ADVERTISED_1000baseT_Half;
+ if (adv & ADVERTISE_1000FULL)
+ result |= ADVERTISED_1000baseT_Full;
+
+ return result;
+}
+
+/**
+ * mii_lpa_to_ethtool_lpa_t
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA
+ * bits, when in 1000Base-T mode, to ethtool
+ * LP advertisement settings.
+ */
+static inline u32 mii_lpa_to_ethtool_lpa_t(u32 lpa)
+{
+ u32 result = 0;
+
+ if (lpa & LPA_LPACK)
+ result |= ADVERTISED_Autoneg;
+
+ return result | mii_adv_to_ethtool_adv_t(lpa);
+}
+
+/**
+ * mii_stat1000_to_ethtool_lpa_t
+ * @adv: value of the MII_STAT1000 register
+ *
+ * A small helper function that translates MII_STAT1000
+ * bits, when in 1000Base-T mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa)
+{
+ u32 result = 0;
+
+ if (lpa & LPA_1000HALF)
+ result |= ADVERTISED_1000baseT_Half;
+ if (lpa & LPA_1000FULL)
+ result |= ADVERTISED_1000baseT_Full;
+
+ return result;
+}
+
+/**
+ * ethtool_adv_to_mii_adv_x
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_CTRL1000 register when in 1000Base-X mode.
+ */
+static inline u32 ethtool_adv_to_mii_adv_x(u32 ethadv)
+{
+ u32 result = 0;
+
+ if (ethadv & ADVERTISED_1000baseT_Half)
+ result |= ADVERTISE_1000XHALF;
+ if (ethadv & ADVERTISED_1000baseT_Full)
+ result |= ADVERTISE_1000XFULL;
+ if (ethadv & ADVERTISED_Pause)
+ result |= ADVERTISE_1000XPAUSE;
+ if (ethadv & ADVERTISED_Asym_Pause)
+ result |= ADVERTISE_1000XPSE_ASYM;
+
+ return result;
+}
+
+/**
+ * mii_adv_to_ethtool_adv_x
+ * @adv: value of the MII_CTRL1000 register
+ *
+ * A small helper function that translates MII_CTRL1000
+ * bits, when in 1000Base-X mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_adv_to_ethtool_adv_x(u32 adv)
+{
+ u32 result = 0;
+
+ if (adv & ADVERTISE_1000XHALF)
+ result |= ADVERTISED_1000baseT_Half;
+ if (adv & ADVERTISE_1000XFULL)
+ result |= ADVERTISED_1000baseT_Full;
+ if (adv & ADVERTISE_1000XPAUSE)
+ result |= ADVERTISED_Pause;
+ if (adv & ADVERTISE_1000XPSE_ASYM)
+ result |= ADVERTISED_Asym_Pause;
+
+ return result;
+}
+
+/**
+ * mii_lpa_to_ethtool_lpa_x
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA
+ * bits, when in 1000Base-X mode, to ethtool
+ * LP advertisement settings.
+ */
+static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa)
+{
+ u32 result = 0;
+
+ if (lpa & LPA_LPACK)
+ result |= ADVERTISED_Autoneg;
+
+ return result | mii_adv_to_ethtool_adv_x(lpa);
+}
+
/**
* mii_advertise_flowctrl - get flow control advertisement flags
* @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both)
MLX4_CMD_HW_HEALTH_CHECK = 0x50,
MLX4_CMD_SET_PORT = 0xc,
MLX4_CMD_SET_NODE = 0x5a,
+ MLX4_CMD_QUERY_FUNC = 0x56,
MLX4_CMD_ACCESS_DDR = 0x2e,
MLX4_CMD_MAP_ICM = 0xffa,
MLX4_CMD_UNMAP_ICM = 0xff9,
MLX4_CMD_MAP_ICM_AUX = 0xffc,
MLX4_CMD_UNMAP_ICM_AUX = 0xffb,
MLX4_CMD_SET_ICM_SIZE = 0xffd,
+ /*master notify fw on finish for slave's flr*/
+ MLX4_CMD_INFORM_FLR_DONE = 0x5b,
/* TPT commands */
MLX4_CMD_SW2HW_MPT = 0xd,
/* miscellaneous commands */
MLX4_CMD_DIAG_RPRT = 0x30,
MLX4_CMD_NOP = 0x31,
+ MLX4_CMD_ACCESS_MEM = 0x2e,
+ MLX4_CMD_SET_VEP = 0x52,
+
+ /* Ethernet specific commands */
+ MLX4_CMD_SET_VLAN_FLTR = 0x47,
+ MLX4_CMD_SET_MCAST_FLTR = 0x48,
+ MLX4_CMD_DUMP_ETH_STATS = 0x49,
+
+ /* Communication channel commands */
+ MLX4_CMD_ARM_COMM_CHANNEL = 0x57,
+ MLX4_CMD_GEN_EQE = 0x58,
+
+ /* virtual commands */
+ MLX4_CMD_ALLOC_RES = 0xf00,
+ MLX4_CMD_FREE_RES = 0xf01,
+ MLX4_CMD_MCAST_ATTACH = 0xf05,
+ MLX4_CMD_UCAST_ATTACH = 0xf06,
+ MLX4_CMD_PROMISC = 0xf08,
+ MLX4_CMD_QUERY_FUNC_CAP = 0xf0a,
+ MLX4_CMD_QP_ATTACH = 0xf0b,
/* debug commands */
MLX4_CMD_QUERY_DEBUG_MSG = 0x2a,
/* statistics commands */
MLX4_CMD_QUERY_IF_STAT = 0X54,
+ MLX4_CMD_SET_IF_STAT = 0X55,
};
enum {
};
enum {
- MLX4_MAILBOX_SIZE = 4096
+ MLX4_MAILBOX_SIZE = 4096,
+ MLX4_ACCESS_MEM_ALIGN = 256,
};
enum {
MLX4_SET_PORT_GID_TABLE = 0x5,
};
+enum {
+ MLX4_CMD_WRAPPED,
+ MLX4_CMD_NATIVE
+};
+
struct mlx4_dev;
struct mlx4_cmd_mailbox {
int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
- u16 op, unsigned long timeout);
+ u16 op, unsigned long timeout, int native);
/* Invoke a command with no output parameter */
static inline int mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u32 in_modifier,
- u8 op_modifier, u16 op, unsigned long timeout)
+ u8 op_modifier, u16 op, unsigned long timeout,
+ int native)
{
return __mlx4_cmd(dev, in_param, NULL, 0, in_modifier,
- op_modifier, op, timeout);
+ op_modifier, op, timeout, native);
}
/* Invoke a command with an output mailbox */
static inline int mlx4_cmd_box(struct mlx4_dev *dev, u64 in_param, u64 out_param,
u32 in_modifier, u8 op_modifier, u16 op,
- unsigned long timeout)
+ unsigned long timeout, int native)
{
return __mlx4_cmd(dev, in_param, &out_param, 0, in_modifier,
- op_modifier, op, timeout);
+ op_modifier, op, timeout, native);
}
/*
*/
static inline int mlx4_cmd_imm(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
u32 in_modifier, u8 op_modifier, u16 op,
- unsigned long timeout)
+ unsigned long timeout, int native)
{
return __mlx4_cmd(dev, in_param, out_param, 1, in_modifier,
- op_modifier, op, timeout);
+ op_modifier, op, timeout, native);
}
struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev);
void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox);
+u32 mlx4_comm_get_version(void);
+
+#define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
+
#endif /* MLX4_CMD_H */
enum {
MLX4_FLAG_MSI_X = 1 << 0,
MLX4_FLAG_OLD_PORT_CMDS = 1 << 1,
+ MLX4_FLAG_MASTER = 1 << 2,
+ MLX4_FLAG_SLAVE = 1 << 3,
+ MLX4_FLAG_SRIOV = 1 << 4,
};
enum {
MLX4_BOARD_ID_LEN = 64
};
+enum {
+ MLX4_MAX_NUM_PF = 16,
+ MLX4_MAX_NUM_VF = 64,
+ MLX4_MFUNC_MAX = 80,
+ MLX4_MFUNC_EQ_NUM = 4,
+ MLX4_MFUNC_MAX_EQES = 8,
+ MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1)
+};
+
enum {
MLX4_DEV_CAP_FLAG_RC = 1LL << 0,
MLX4_DEV_CAP_FLAG_UC = 1LL << 1,
MLX4_DEV_CAP_FLAG_IBOE = 1LL << 30,
MLX4_DEV_CAP_FLAG_UC_LOOPBACK = 1LL << 32,
MLX4_DEV_CAP_FLAG_FCS_KEEP = 1LL << 34,
- MLX4_DEV_CAP_FLAG_WOL = 1LL << 38,
+ MLX4_DEV_CAP_FLAG_WOL_PORT1 = 1LL << 37,
+ MLX4_DEV_CAP_FLAG_WOL_PORT2 = 1LL << 38,
MLX4_DEV_CAP_FLAG_UDP_RSS = 1LL << 40,
MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41,
MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42,
- MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48
+ MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48,
+ MLX4_DEV_CAP_FLAG_SENSE_SUPPORT = 1LL << 55
};
#define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90)
MLX4_EVENT_TYPE_PORT_CHANGE = 0x09,
MLX4_EVENT_TYPE_EQ_OVERFLOW = 0x0f,
MLX4_EVENT_TYPE_ECC_DETECT = 0x0e,
- MLX4_EVENT_TYPE_CMD = 0x0a
+ MLX4_EVENT_TYPE_CMD = 0x0a,
+ MLX4_EVENT_TYPE_VEP_UPDATE = 0x19,
+ MLX4_EVENT_TYPE_COMM_CHANNEL = 0x18,
+ MLX4_EVENT_TYPE_FLR_EVENT = 0x1c,
+ MLX4_EVENT_TYPE_NONE = 0xff,
};
enum {
};
enum mlx4_port_type {
+ MLX4_PORT_TYPE_NONE = 0,
MLX4_PORT_TYPE_IB = 1,
MLX4_PORT_TYPE_ETH = 2,
MLX4_PORT_TYPE_AUTO = 3
struct mlx4_caps {
u64 fw_ver;
+ u32 function;
int num_ports;
int vl_cap[MLX4_MAX_PORTS + 1];
int ib_mtu_cap[MLX4_MAX_PORTS + 1];
u64 trans_code[MLX4_MAX_PORTS + 1];
int local_ca_ack_delay;
int num_uars;
+ u32 uar_page_size;
int bf_reg_size;
int bf_regs_per_page;
int max_sq_sg;
int num_comp_vectors;
int comp_pool;
int num_mpts;
- int num_mtt_segs;
- int mtts_per_seg;
+ int num_mtts;
int fmr_reserved_mtts;
int reserved_mtts;
int reserved_mrws;
int log_num_prios;
enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
u8 supported_type[MLX4_MAX_PORTS + 1];
- u32 port_mask;
+ u8 suggested_type[MLX4_MAX_PORTS + 1];
+ u8 default_sense[MLX4_MAX_PORTS + 1];
+ u32 port_mask[MLX4_MAX_PORTS + 1];
enum mlx4_port_type possible_type[MLX4_MAX_PORTS + 1];
u32 max_counters;
u8 ext_port_cap[MLX4_MAX_PORTS + 1];
};
struct mlx4_mtt {
- u32 first_seg;
+ u32 offset;
int order;
int page_shift;
};
struct mlx4_dev {
struct pci_dev *pdev;
unsigned long flags;
+ unsigned long num_slaves;
struct mlx4_caps caps;
struct radix_tree_root qp_table_tree;
u8 rev_id;
char board_id[MLX4_BOARD_ID_LEN];
+ int num_vfs;
};
struct mlx4_init_port_param {
#define mlx4_foreach_port(port, dev, type) \
for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
- if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \
- ~(dev)->caps.port_mask) & 1 << ((port) - 1))
+ if ((type) == (dev)->caps.port_mask[(port)])
-#define mlx4_foreach_ib_transport_port(port, dev) \
- for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
- if (((dev)->caps.port_mask & 1 << ((port) - 1)) || \
- ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+#define mlx4_foreach_ib_transport_port(port, dev) \
+ for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
+ if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \
+ ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+static inline int mlx4_is_master(struct mlx4_dev *dev)
+{
+ return dev->flags & MLX4_FLAG_MASTER;
+}
+
+static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn)
+{
+ return (qpn < dev->caps.sqp_start + 8);
+}
+
+static inline int mlx4_is_mfunc(struct mlx4_dev *dev)
+{
+ return dev->flags & (MLX4_FLAG_SLAVE | MLX4_FLAG_MASTER);
+}
+
+static inline int mlx4_is_slave(struct mlx4_dev *dev)
+{
+ return dev->flags & MLX4_FLAG_SLAVE;
+}
int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
struct mlx4_buf *buf);
int mlx4_INIT_PORT(struct mlx4_dev *dev, int port);
int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
+int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+ int block_mcast_loopback, enum mlx4_protocol prot);
+int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+ enum mlx4_protocol prot);
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol protocol);
int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mode);
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap);
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn);
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap);
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
+int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn);
+void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
MLX4_QP_BIT_RIC = 1 << 4,
};
+enum {
+ MLX4_RSS_HASH_XOR = 0,
+ MLX4_RSS_HASH_TOP = 1,
+
+ MLX4_RSS_UDP_IPV6 = 1 << 0,
+ MLX4_RSS_UDP_IPV4 = 1 << 1,
+ MLX4_RSS_TCP_IPV6 = 1 << 2,
+ MLX4_RSS_IPV6 = 1 << 3,
+ MLX4_RSS_TCP_IPV4 = 1 << 4,
+ MLX4_RSS_IPV4 = 1 << 5,
+
+ /* offset of mlx4_rss_context within mlx4_qp_context.pri_path */
+ MLX4_RSS_OFFSET_IN_QPC_PRI_PATH = 0x24,
+ /* offset of being RSS indirection QP within mlx4_qp_context.flags */
+ MLX4_RSS_QPC_FLAG_OFFSET = 13,
+};
+
+struct mlx4_rss_context {
+ __be32 base_qpn;
+ __be32 default_qpn;
+ u16 reserved;
+ u8 hash_fn;
+ u8 flags;
+ __be32 rss_key[10];
+ __be32 base_qpn_udp;
+};
+
struct mlx4_qp_path {
u8 fl;
u8 reserved1[2];
* [4] IP checksum
* [3:2] C (generate completion queue entry)
* [1] SE (solicited event)
+ * [0] FL (force loopback)
*/
__be32 srcrb_flags;
/*
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
+#include <linux/atomic.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
#include <linux/range.h>
#define MMC_QUIRK_INAND_CMD38 (1<<6) /* iNAND devices have broken CMD38 */
#define MMC_QUIRK_BLK_NO_CMD23 (1<<7) /* Avoid CMD23 for regular multiblock */
#define MMC_QUIRK_BROKEN_BYTE_MODE_512 (1<<8) /* Avoid sending 512 bytes in */
+#define MMC_QUIRK_LONG_READ_TIME (1<<9) /* Data read time > CSD says */
/* byte mode */
unsigned int poweroff_notify_state; /* eMMC4.5 notify feature */
#define MMC_NO_POWER_NOTIFICATION 0
return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512;
}
+static inline int mmc_card_long_read_time(const struct mmc_card *c)
+{
+ return c->quirks & MMC_QUIRK_LONG_READ_TIME;
+}
+
#define mmc_card_name(c) ((c)->cid.prod_name)
#define mmc_card_id(c) (dev_name(&(c)->dev))
NDTPA_PROXY_DELAY, /* u64, msecs */
NDTPA_PROXY_QLEN, /* u32 */
NDTPA_LOCKTIME, /* u64, msecs */
+ NDTPA_QUEUE_LENBYTES, /* u32 */
__NDTPA_MAX
};
#define NDTPA_MAX (__NDTPA_MAX - 1)
--- /dev/null
+/*
+ * Network device features.
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_NETDEV_FEATURES_H
+#define _LINUX_NETDEV_FEATURES_H
+
+#include <linux/types.h>
+
+typedef u64 netdev_features_t;
+
+enum {
+ NETIF_F_SG_BIT, /* Scatter/gather IO. */
+ NETIF_F_IP_CSUM_BIT, /* Can checksum TCP/UDP over IPv4. */
+ __UNUSED_NETIF_F_1,
+ NETIF_F_HW_CSUM_BIT, /* Can checksum all the packets. */
+ NETIF_F_IPV6_CSUM_BIT, /* Can checksum TCP/UDP over IPV6 */
+ NETIF_F_HIGHDMA_BIT, /* Can DMA to high memory. */
+ NETIF_F_FRAGLIST_BIT, /* Scatter/gather IO. */
+ NETIF_F_HW_VLAN_TX_BIT, /* Transmit VLAN hw acceleration */
+ NETIF_F_HW_VLAN_RX_BIT, /* Receive VLAN hw acceleration */
+ NETIF_F_HW_VLAN_FILTER_BIT, /* Receive filtering on VLAN */
+ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */
+ NETIF_F_GSO_BIT, /* Enable software GSO. */
+ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */
+ /* do not use LLTX in new drivers */
+ NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */
+ NETIF_F_GRO_BIT, /* Generic receive offload */
+ NETIF_F_LRO_BIT, /* large receive offload */
+
+ /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */
+ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */
+ = NETIF_F_GSO_SHIFT,
+ NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */
+ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */
+ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */
+ NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */
+ NETIF_F_FSO_BIT, /* ... FCoE segmentation */
+ NETIF_F_GSO_RESERVED1, /* ... free (fill GSO_MASK to 8 bits) */
+ /**/NETIF_F_GSO_LAST, /* [can't be last bit, see GSO_MASK] */
+ NETIF_F_GSO_RESERVED2 /* ... free (fill GSO_MASK to 8 bits) */
+ = NETIF_F_GSO_LAST,
+
+ NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */
+ NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */
+ NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/
+ NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */
+ NETIF_F_RXHASH_BIT, /* Receive hashing offload */
+ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */
+ NETIF_F_NOCACHE_COPY_BIT, /* Use no-cache copyfromuser */
+ NETIF_F_LOOPBACK_BIT, /* Enable loopback */
+
+ /*
+ * Add your fresh new feature above and remember to update
+ * netdev_features_strings[] in net/core/ethtool.c and maybe
+ * some feature mask #defines below. Please also describe it
+ * in Documentation/networking/netdev-features.txt.
+ */
+
+ /**/NETDEV_FEATURE_COUNT
+};
+
+/* copy'n'paste compression ;) */
+#define __NETIF_F_BIT(bit) ((netdev_features_t)1 << (bit))
+#define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT)
+
+#define NETIF_F_FCOE_CRC __NETIF_F(FCOE_CRC)
+#define NETIF_F_FCOE_MTU __NETIF_F(FCOE_MTU)
+#define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST)
+#define NETIF_F_FSO __NETIF_F(FSO)
+#define NETIF_F_GRO __NETIF_F(GRO)
+#define NETIF_F_GSO __NETIF_F(GSO)
+#define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST)
+#define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA)
+#define NETIF_F_HW_CSUM __NETIF_F(HW_CSUM)
+#define NETIF_F_HW_VLAN_FILTER __NETIF_F(HW_VLAN_FILTER)
+#define NETIF_F_HW_VLAN_RX __NETIF_F(HW_VLAN_RX)
+#define NETIF_F_HW_VLAN_TX __NETIF_F(HW_VLAN_TX)
+#define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM)
+#define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM)
+#define NETIF_F_LLTX __NETIF_F(LLTX)
+#define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK)
+#define NETIF_F_LRO __NETIF_F(LRO)
+#define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL)
+#define NETIF_F_NOCACHE_COPY __NETIF_F(NOCACHE_COPY)
+#define NETIF_F_NTUPLE __NETIF_F(NTUPLE)
+#define NETIF_F_RXCSUM __NETIF_F(RXCSUM)
+#define NETIF_F_RXHASH __NETIF_F(RXHASH)
+#define NETIF_F_SCTP_CSUM __NETIF_F(SCTP_CSUM)
+#define NETIF_F_SG __NETIF_F(SG)
+#define NETIF_F_TSO6 __NETIF_F(TSO6)
+#define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN)
+#define NETIF_F_TSO __NETIF_F(TSO)
+#define NETIF_F_UFO __NETIF_F(UFO)
+#define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED)
+
+/* Features valid for ethtool to change */
+/* = all defined minus driver/device-class-related */
+#define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \
+ NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+
+/* remember that ((t)1 << t_BITS) is undefined in C99 */
+#define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
+ (__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) - 1)) & \
+ ~NETIF_F_NEVER_CHANGE)
+
+/* Segmentation offload feature mask */
+#define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \
+ __NETIF_F_BIT(NETIF_F_GSO_SHIFT))
+
+/* List of features with software fallbacks. */
+#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \
+ NETIF_F_TSO6 | NETIF_F_UFO)
+
+#define NETIF_F_GEN_CSUM NETIF_F_HW_CSUM
+#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
+#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
+#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
+
+#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
+ NETIF_F_FSO)
+
+/*
+ * If one device supports one of these features, then enable them
+ * for all in netdev_increment_features.
+ */
+#define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
+ NETIF_F_SG | NETIF_F_HIGHDMA | \
+ NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
+/*
+ * If one device doesn't support one of these features, then disable it
+ * for all in netdev_increment_features.
+ */
+#define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO)
+
+/* changeable features with no special hardware requirements */
+#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+
+#endif /* _LINUX_NETDEV_FEATURES_H */
#include <linux/rculist.h>
#include <linux/dmaengine.h>
#include <linux/workqueue.h>
+#include <linux/dynamic_queue_limits.h>
#include <linux/ethtool.h>
#include <net/net_namespace.h>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
+#include <net/netprio_cgroup.h>
+
+#include <linux/netdev_features.h>
-struct vlan_group;
struct netpoll_info;
struct phy_device;
/* 802.11 specific */
* used.
*/
-#if defined(CONFIG_WLAN) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
# if defined(CONFIG_MAC80211_MESH)
# define LL_MAX_HEADER 128
# else
# define LL_MAX_HEADER 96
# endif
-#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
+#elif IS_ENABLED(CONFIG_TR)
# define LL_MAX_HEADER 48
#else
# define LL_MAX_HEADER 32
#endif
-#if !defined(CONFIG_NET_IPIP) && !defined(CONFIG_NET_IPIP_MODULE) && \
- !defined(CONFIG_NET_IPGRE) && !defined(CONFIG_NET_IPGRE_MODULE) && \
- !defined(CONFIG_IPV6_SIT) && !defined(CONFIG_IPV6_SIT_MODULE) && \
- !defined(CONFIG_IPV6_TUNNEL) && !defined(CONFIG_IPV6_TUNNEL_MODULE)
+#if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \
+ !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL)
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#include <linux/cache.h>
#include <linux/skbuff.h>
+#ifdef CONFIG_RPS
+#include <linux/jump_label.h>
+extern struct jump_label_key rps_needed;
+#endif
+
struct neighbour;
struct neigh_parms;
struct sk_buff;
*
* We could use other alignment values, but we must maintain the
* relationship HH alignment <= LL alignment.
- *
- * LL_ALLOCATED_SPACE also takes into account the tailroom the device
- * may need.
*/
#define LL_RESERVED_SPACE(dev) \
((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
-#define LL_ALLOCATED_SPACE(dev) \
- ((((dev)->hard_header_len+(dev)->needed_headroom+(dev)->needed_tailroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
struct header_ops {
int (*create) (struct sk_buff *skb, struct net_device *dev,
#endif
enum netdev_queue_state_t {
- __QUEUE_STATE_XOFF,
+ __QUEUE_STATE_DRV_XOFF,
+ __QUEUE_STATE_STACK_XOFF,
__QUEUE_STATE_FROZEN,
-#define QUEUE_STATE_XOFF_OR_FROZEN ((1 << __QUEUE_STATE_XOFF) | \
- (1 << __QUEUE_STATE_FROZEN))
+#define QUEUE_STATE_ANY_XOFF ((1 << __QUEUE_STATE_DRV_XOFF) | \
+ (1 << __QUEUE_STATE_STACK_XOFF))
+#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
+ (1 << __QUEUE_STATE_FROZEN))
};
+/*
+ * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The
+ * netif_tx_* functions below are used to manipulate this flag. The
+ * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit
+ * queue independently. The netif_xmit_*stopped functions below are called
+ * to check if the queue has been stopped by the driver or stack (either
+ * of the XOFF bits are set in the state). Drivers should not need to call
+ * netif_xmit*stopped functions, they should only be using netif_tx_*.
+ */
struct netdev_queue {
/*
*/
struct net_device *dev;
struct Qdisc *qdisc;
- unsigned long state;
struct Qdisc *qdisc_sleeping;
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
struct kobject kobj;
#endif
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
* please use this field instead of dev->trans_start
*/
unsigned long trans_start;
+
+ /*
+ * Number of TX timeouts for this queue
+ * (/sys/class/net/DEV/Q/trans_timeout)
+ */
+ unsigned long trans_timeout;
+
+ unsigned long state;
+
+#ifdef CONFIG_BQL
+ struct dql dql;
+#endif
} ____cacheline_aligned_in_smp;
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
struct rcu_head rcu;
u16 cpus[0];
};
-#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16)))
+#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
/*
* The rps_dev_flow structure contains the mapping of a flow to a CPU, the
struct rps_dev_flow flows[0];
};
#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
- (_num * sizeof(struct rps_dev_flow)))
+ ((_num) * sizeof(struct rps_dev_flow)))
/*
* The rps_sock_flow_table contains mappings of flows to the last CPU
u16 ents[0];
};
#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
- (_num * sizeof(u16)))
+ ((_num) * sizeof(u16)))
#define RPS_NO_CPU 0xffff
struct rcu_head rcu;
u16 queues[0];
};
-#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16)))
+#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \
/ sizeof(u16))
* 3. Update dev->stats asynchronously and atomically, and define
* neither operation.
*
- * void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
* If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
* this function is called when a VLAN id is registered.
*
- * void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
* If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
* this function is called when a VLAN id is unregistered.
*
* Called to release previously enslaved netdev.
*
* Feature/offload setting functions.
- * u32 (*ndo_fix_features)(struct net_device *dev, u32 features);
+ * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ * netdev_features_t features);
* Adjusts the requested feature flags according to device-specific
* constraints, and returns the resulting flags. Must not modify
* the device state.
*
- * int (*ndo_set_features)(struct net_device *dev, u32 features);
+ * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
* Called to update device configuration to new features. Passed
* feature set might be less than what was returned by ndo_fix_features()).
* Must return >0 or -errno if it changed dev->features itself.
struct rtnl_link_stats64 *storage);
struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
- void (*ndo_vlan_rx_add_vid)(struct net_device *dev,
+ int (*ndo_vlan_rx_add_vid)(struct net_device *dev,
unsigned short vid);
- void (*ndo_vlan_rx_kill_vid)(struct net_device *dev,
+ int (*ndo_vlan_rx_kill_vid)(struct net_device *dev,
unsigned short vid);
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_get_vf_port)(struct net_device *dev,
int vf, struct sk_buff *skb);
int (*ndo_setup_tc)(struct net_device *dev, u8 tc);
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
int (*ndo_fcoe_enable)(struct net_device *dev);
int (*ndo_fcoe_disable)(struct net_device *dev);
int (*ndo_fcoe_ddp_setup)(struct net_device *dev,
unsigned int sgc);
#endif
-#if defined(CONFIG_LIBFCOE) || defined(CONFIG_LIBFCOE_MODULE)
+#if IS_ENABLED(CONFIG_LIBFCOE)
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
struct net_device *slave_dev);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
- u32 (*ndo_fix_features)(struct net_device *dev,
- u32 features);
+ netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ netdev_features_t features);
int (*ndo_set_features)(struct net_device *dev,
- u32 features);
+ netdev_features_t features);
+ int (*ndo_neigh_construct)(struct neighbour *n);
+ void (*ndo_neigh_destroy)(struct neighbour *n);
};
/*
struct list_head unreg_list;
/* currently active device features */
- u32 features;
+ netdev_features_t features;
/* user-changeable features */
- u32 hw_features;
+ netdev_features_t hw_features;
/* user-requested features */
- u32 wanted_features;
+ netdev_features_t wanted_features;
/* mask of features inheritable by VLAN devices */
- u32 vlan_features;
-
- /* Net device feature bits; if you change something,
- * also update netdev_features_strings[] in ethtool.c */
-
-#define NETIF_F_SG 1 /* Scatter/gather IO. */
-#define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */
-#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */
-#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */
-#define NETIF_F_IPV6_CSUM 16 /* Can checksum TCP/UDP over IPV6 */
-#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */
-#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */
-#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */
-#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */
-#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */
-#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */
-#define NETIF_F_GSO 2048 /* Enable software GSO. */
-#define NETIF_F_LLTX 4096 /* LockLess TX - deprecated. Please */
- /* do not use LLTX in new drivers */
-#define NETIF_F_NETNS_LOCAL 8192 /* Does not change network namespaces */
-#define NETIF_F_GRO 16384 /* Generic receive offload */
-#define NETIF_F_LRO 32768 /* large receive offload */
-
-/* the GSO_MASK reserves bits 16 through 23 */
-#define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */
-#define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */
-#define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
-#define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */
-#define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */
-#define NETIF_F_RXCSUM (1 << 29) /* Receive checksumming offload */
-#define NETIF_F_NOCACHE_COPY (1 << 30) /* Use no-cache copyfromuser */
-#define NETIF_F_LOOPBACK (1 << 31) /* Enable loopback */
-
- /* Segmentation offload features */
-#define NETIF_F_GSO_SHIFT 16
-#define NETIF_F_GSO_MASK 0x00ff0000
-#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
-#define NETIF_F_UFO (SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
-#define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
-#define NETIF_F_TSO_ECN (SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT)
-#define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
-#define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
-
- /* Features valid for ethtool to change */
- /* = all defined minus driver/device-class-related */
-#define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \
- NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
-#define NETIF_F_ETHTOOL_BITS (0xff3fffff & ~NETIF_F_NEVER_CHANGE)
-
- /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \
- NETIF_F_TSO6 | NETIF_F_UFO)
-
-
-#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
-#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
-#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
-#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
-
-#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
-
-#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
- NETIF_F_FSO)
-
- /*
- * If one device supports one of these features, then enable them
- * for all in netdev_increment_features.
- */
-#define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
- NETIF_F_SG | NETIF_F_HIGHDMA | \
- NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
- /*
- * If one device doesn't support one of these features, then disable it
- * for all in netdev_increment_features.
- */
-#define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO)
-
- /* changeable features with no special hardware requirements */
-#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+ netdev_features_t vlan_features;
/* Interface index. Unique device identifier */
int ifindex;
unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
unsigned char addr_assign_type; /* hw address assignment type */
unsigned char addr_len; /* hardware address length */
+ unsigned char neigh_priv_len;
unsigned short dev_id; /* for shared network cards */
spinlock_t addr_list_lock;
/* Protocol specific pointers */
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
- struct vlan_group __rcu *vlgrp; /* VLAN group */
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+ struct vlan_info __rcu *vlan_info; /* VLAN info */
#endif
-#ifdef CONFIG_NET_DSA
- void *dsa_ptr; /* dsa specific data */
+#if IS_ENABLED(CONFIG_NET_DSA)
+ struct dsa_switch_tree *dsa_ptr; /* dsa specific data */
#endif
void *atalk_ptr; /* AppleTalk link */
struct in_device __rcu *ip_ptr; /* IPv4 specific data */
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
struct kset *queues_kset;
+#endif
+#ifdef CONFIG_RPS
struct netdev_rx_queue *_rx;
/* Number of RX queues allocated at register_netdev() time */
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
/* max exchange id for FCoE LRO by ddp */
unsigned int fcoe_ddp_xid;
+#endif
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+ struct netprio_map __rcu *priomap;
#endif
/* phy device may attach itself for hardware timestamping */
struct phy_device *phydev;
struct packet_type *,
struct net_device *);
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
- u32 features);
+ netdev_features_t features);
int (*gso_send_check)(struct sk_buff *skb);
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
static inline void netif_schedule_queue(struct netdev_queue *txq)
{
- if (!test_bit(__QUEUE_STATE_XOFF, &txq->state))
+ if (!(txq->state & QUEUE_STATE_ANY_XOFF))
__netif_schedule(txq->qdisc);
}
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
- clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+ clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
return;
}
#endif
- if (test_and_clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state))
+ if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
__netif_schedule(dev_queue->qdisc);
}
pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
return;
}
- set_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
static inline int netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
- return test_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+ return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
}
-static inline int netif_tx_queue_frozen_or_stopped(const struct netdev_queue *dev_queue)
+static inline int netif_xmit_stopped(const struct netdev_queue *dev_queue)
{
- return dev_queue->state & QUEUE_STATE_XOFF_OR_FROZEN;
+ return dev_queue->state & QUEUE_STATE_ANY_XOFF;
+}
+
+static inline int netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
+{
+ return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
+}
+
+static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
+ unsigned int bytes)
+{
+#ifdef CONFIG_BQL
+ dql_queued(&dev_queue->dql, bytes);
+ if (unlikely(dql_avail(&dev_queue->dql) < 0)) {
+ set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
+ if (unlikely(dql_avail(&dev_queue->dql) >= 0))
+ clear_bit(__QUEUE_STATE_STACK_XOFF,
+ &dev_queue->state);
+ }
+#endif
+}
+
+static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
+{
+ netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
+}
+
+static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
+ unsigned pkts, unsigned bytes)
+{
+#ifdef CONFIG_BQL
+ if (likely(bytes)) {
+ dql_completed(&dev_queue->dql, bytes);
+ if (unlikely(test_bit(__QUEUE_STATE_STACK_XOFF,
+ &dev_queue->state) &&
+ dql_avail(&dev_queue->dql) >= 0)) {
+ if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF,
+ &dev_queue->state))
+ netif_schedule_queue(dev_queue);
+ }
+ }
+#endif
+}
+
+static inline void netdev_completed_queue(struct net_device *dev,
+ unsigned pkts, unsigned bytes)
+{
+ netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
+}
+
+static inline void netdev_tx_reset_queue(struct netdev_queue *q)
+{
+#ifdef CONFIG_BQL
+ dql_reset(&q->dql);
+#endif
+}
+
+static inline void netdev_reset_queue(struct net_device *dev_queue)
+{
+ netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
}
/**
if (netpoll_trap())
return;
#endif
- if (test_and_clear_bit(__QUEUE_STATE_XOFF, &txq->state))
+ if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
__netif_schedule(txq->qdisc);
}
extern int netdev_set_bond_master(struct net_device *dev,
struct net_device *master);
extern int skb_checksum_help(struct sk_buff *skb);
-extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb,
+ netdev_features_t features);
#ifdef CONFIG_BUG
extern void netdev_rx_csum_fault(struct net_device *dev);
#else
extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
extern void dev_seq_stop(struct seq_file *seq, void *v);
+extern int dev_seq_open_ops(struct inode *inode, struct file *file,
+ const struct seq_operations *ops);
#endif
extern int netdev_class_create_file(struct class_attribute *class_attr);
extern void linkwatch_run_queue(void);
-static inline u32 netdev_get_wanted_features(struct net_device *dev)
+static inline netdev_features_t netdev_get_wanted_features(
+ struct net_device *dev)
{
return (dev->features & ~dev->hw_features) | dev->wanted_features;
}
-u32 netdev_increment_features(u32 all, u32 one, u32 mask);
+netdev_features_t netdev_increment_features(netdev_features_t all,
+ netdev_features_t one, netdev_features_t mask);
int __netdev_update_features(struct net_device *dev);
void netdev_update_features(struct net_device *dev);
void netdev_change_features(struct net_device *dev);
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
-u32 netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_features(struct sk_buff *skb);
-static inline int net_gso_ok(u32 features, int gso_type)
+static inline int net_gso_ok(netdev_features_t features, int gso_type)
{
- int feature = gso_type << NETIF_F_GSO_SHIFT;
+ netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
+
+ /* check flags correspondence */
+ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
+
return (features & feature) == feature;
}
-static inline int skb_gso_ok(struct sk_buff *skb, u32 features)
+static inline int skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
{
return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
(!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
}
-static inline int netif_needs_gso(struct sk_buff *skb, int features)
+static inline int netif_needs_gso(struct sk_buff *skb,
+ netdev_features_t features)
{
return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
extern struct pernet_operations __net_initdata loopback_net_ops;
-static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev)
-{
- if (dev->features & NETIF_F_RXCSUM)
- return 1;
- if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum)
- return 0;
- return dev->ethtool_ops->get_rx_csum(dev);
-}
-
-static inline u32 dev_ethtool_get_flags(struct net_device *dev)
-{
- if (!dev->ethtool_ops || !dev->ethtool_ops->get_flags)
- return 0;
- return dev->ethtool_ops->get_flags(dev);
-}
-
/* Logging, debugging and troubleshooting/diagnostic helpers. */
/* netdev_printk helpers, similar to dev_printk */
extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+#if defined(CONFIG_JUMP_LABEL)
+#include <linux/jump_label.h>
+extern struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
+{
+ if (__builtin_constant_p(pf) &&
+ __builtin_constant_p(hook))
+ return static_branch(&nf_hooks_needed[pf][hook]);
+
+ return !list_empty(&nf_hooks[pf][hook]);
+}
+#else
+static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
+{
+ return !list_empty(&nf_hooks[pf][hook]);
+}
+#endif
+
int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *), int thresh);
struct net_device *outdev,
int (*okfn)(struct sk_buff *), int thresh)
{
-#ifndef CONFIG_NETFILTER_DEBUG
- if (list_empty(&nf_hooks[pf][hook]))
- return 1;
-#endif
- return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
+ if (nf_hooks_active(pf, hook))
+ return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
+ return 1;
}
static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
header-y += nf_conntrack_sctp.h
header-y += nf_conntrack_tcp.h
header-y += nf_conntrack_tuple_common.h
+header-y += nf_nat.h
header-y += nfnetlink.h
+header-y += nfnetlink_acct.h
header-y += nfnetlink_compat.h
header-y += nfnetlink_conntrack.h
header-y += nfnetlink_log.h
header-y += xt_IDLETIMER.h
header-y += xt_LED.h
header-y += xt_MARK.h
+header-y += xt_nfacct.h
header-y += xt_NFLOG.h
header-y += xt_NFQUEUE.h
header-y += xt_RATEEST.h
header-y += xt_dccp.h
header-y += xt_devgroup.h
header-y += xt_dscp.h
+header-y += xt_ecn.h
header-y += xt_esp.h
header-y += xt_hashlimit.h
header-y += xt_helper.h
/* Conntrack is a fake untracked entry */
IPS_UNTRACKED_BIT = 12,
IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
+
+ /* Conntrack has a userspace helper. */
+ IPS_USERSPACE_HELPER_BIT = 13,
+ IPS_USERSPACE_HELPER = (1 << IPS_USERSPACE_HELPER_BIT),
};
/* Connection tracking event types */
IP_CT_DIR_MAX
};
+/* The protocol-specific manipulable parts of the tuple: always in
+ * network order
+ */
+union nf_conntrack_man_proto {
+ /* Add other protocols here. */
+ __be16 all;
+
+ struct {
+ __be16 port;
+ } tcp;
+ struct {
+ __be16 port;
+ } udp;
+ struct {
+ __be16 id;
+ } icmp;
+ struct {
+ __be16 port;
+ } dccp;
+ struct {
+ __be16 port;
+ } sctp;
+ struct {
+ __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
+ } gre;
+};
+
#define CTINFO2DIR(ctinfo) ((ctinfo) >= IP_CT_IS_REPLY ? IP_CT_DIR_REPLY : IP_CT_DIR_ORIGINAL)
#endif /* _NF_CONNTRACK_TUPLE_COMMON_H */
--- /dev/null
+#ifndef _NETFILTER_NF_NAT_H
+#define _NETFILTER_NF_NAT_H
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+
+#define NF_NAT_RANGE_MAP_IPS 1
+#define NF_NAT_RANGE_PROTO_SPECIFIED 2
+#define NF_NAT_RANGE_PROTO_RANDOM 4
+#define NF_NAT_RANGE_PERSISTENT 8
+
+struct nf_nat_ipv4_range {
+ unsigned int flags;
+ __be32 min_ip;
+ __be32 max_ip;
+ union nf_conntrack_man_proto min;
+ union nf_conntrack_man_proto max;
+};
+
+struct nf_nat_ipv4_multi_range_compat {
+ unsigned int rangesize;
+ struct nf_nat_ipv4_range range[1];
+};
+
+#endif /* _NETFILTER_NF_NAT_H */
#define NFNL_SUBSYS_ULOG 4
#define NFNL_SUBSYS_OSF 5
#define NFNL_SUBSYS_IPSET 6
-#define NFNL_SUBSYS_COUNT 7
+#define NFNL_SUBSYS_ACCT 7
+#define NFNL_SUBSYS_COUNT 8
#ifdef __KERNEL__
--- /dev/null
+#ifndef _NFNL_ACCT_H_
+#define _NFNL_ACCT_H_
+
+#ifndef NFACCT_NAME_MAX
+#define NFACCT_NAME_MAX 32
+#endif
+
+enum nfnl_acct_msg_types {
+ NFNL_MSG_ACCT_NEW,
+ NFNL_MSG_ACCT_GET,
+ NFNL_MSG_ACCT_GET_CTRZERO,
+ NFNL_MSG_ACCT_DEL,
+ NFNL_MSG_ACCT_MAX
+};
+
+enum nfnl_acct_type {
+ NFACCT_UNSPEC,
+ NFACCT_NAME,
+ NFACCT_PKTS,
+ NFACCT_BYTES,
+ NFACCT_USE,
+ __NFACCT_MAX
+};
+#define NFACCT_MAX (__NFACCT_MAX - 1)
+
+#ifdef __KERNEL__
+
+struct nf_acct;
+
+extern struct nf_acct *nfnl_acct_find_get(const char *filter_name);
+extern void nfnl_acct_put(struct nf_acct *acct);
+extern void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
+
+#endif /* __KERNEL__ */
+
+#endif /* _NFNL_ACCT_H */
#include <linux/types.h>
-#define XT_CT_NOTRACK 0x1
+#define XT_CT_NOTRACK 0x1
+#define XT_CT_USERSPACE_HELPER 0x2
struct xt_ct_target_info {
__u16 flags;
--- /dev/null
+/* iptables module for matching the ECN header in IPv4 and TCP header
+ *
+ * (C) 2002 Harald Welte <laforge@gnumonks.org>
+ *
+ * This software is distributed under GNU GPL v2, 1991
+ *
+ * ipt_ecn.h,v 1.4 2002/08/05 19:39:00 laforge Exp
+*/
+#ifndef _XT_ECN_H
+#define _XT_ECN_H
+
+#include <linux/types.h>
+#include <linux/netfilter/xt_dscp.h>
+
+#define XT_ECN_IP_MASK (~XT_DSCP_MASK)
+
+#define XT_ECN_OP_MATCH_IP 0x01
+#define XT_ECN_OP_MATCH_ECE 0x10
+#define XT_ECN_OP_MATCH_CWR 0x20
+
+#define XT_ECN_OP_MATCH_MASK 0xce
+
+/* match info */
+struct xt_ecn_info {
+ __u8 operation;
+ __u8 invert;
+ __u8 ip_ect;
+ union {
+ struct {
+ __u8 ect;
+ } tcp;
+ } proto;
+};
+
+#endif /* _XT_ECN_H */
--- /dev/null
+#ifndef _XT_NFACCT_MATCH_H
+#define _XT_NFACCT_MATCH_H
+
+#include <linux/netfilter/nfnetlink_acct.h>
+
+struct nf_acct;
+
+struct xt_nfacct_match_info {
+ char name[NFACCT_NAME_MAX];
+ struct nf_acct *nfacct;
+};
+
+#endif /* _XT_NFACCT_MATCH_H */
--- /dev/null
+#ifndef _XT_RPATH_H
+#define _XT_RPATH_H
+
+#include <linux/types.h>
+
+enum {
+ XT_RPFILTER_LOOSE = 1 << 0,
+ XT_RPFILTER_VALID_MARK = 1 << 1,
+ XT_RPFILTER_ACCEPT_LOCAL = 1 << 2,
+ XT_RPFILTER_INVERT = 1 << 3,
+#ifdef __KERNEL__
+ XT_RPFILTER_OPTION_MASK = XT_RPFILTER_LOOSE |
+ XT_RPFILTER_VALID_MARK |
+ XT_RPFILTER_ACCEPT_LOCAL |
+ XT_RPFILTER_INVERT,
+#endif
+};
+
+struct xt_rpfilter_info {
+ __u8 flags;
+};
+
+#endif
header-y += ipt_ecn.h
header-y += ipt_realm.h
header-y += ipt_ttl.h
-header-y += nf_nat.h
-/* iptables module for matching the ECN header in IPv4 and TCP header
- *
- * (C) 2002 Harald Welte <laforge@gnumonks.org>
- *
- * This software is distributed under GNU GPL v2, 1991
- *
- * ipt_ecn.h,v 1.4 2002/08/05 19:39:00 laforge Exp
-*/
#ifndef _IPT_ECN_H
#define _IPT_ECN_H
-#include <linux/types.h>
-#include <linux/netfilter/xt_dscp.h>
+#include <linux/netfilter/xt_ecn.h>
+#define ipt_ecn_info xt_ecn_info
-#define IPT_ECN_IP_MASK (~XT_DSCP_MASK)
-
-#define IPT_ECN_OP_MATCH_IP 0x01
-#define IPT_ECN_OP_MATCH_ECE 0x10
-#define IPT_ECN_OP_MATCH_CWR 0x20
-
-#define IPT_ECN_OP_MATCH_MASK 0xce
-
-/* match info */
-struct ipt_ecn_info {
- __u8 operation;
- __u8 invert;
- __u8 ip_ect;
- union {
- struct {
- __u8 ect;
- } tcp;
- } proto;
+enum {
+ IPT_ECN_IP_MASK = XT_ECN_IP_MASK,
+ IPT_ECN_OP_MATCH_IP = XT_ECN_OP_MATCH_IP,
+ IPT_ECN_OP_MATCH_ECE = XT_ECN_OP_MATCH_ECE,
+ IPT_ECN_OP_MATCH_CWR = XT_ECN_OP_MATCH_CWR,
+ IPT_ECN_OP_MATCH_MASK = XT_ECN_OP_MATCH_MASK,
};
-#endif /* _IPT_ECN_H */
+#endif /* IPT_ECN_H */
+++ /dev/null
-#ifndef _LINUX_NF_NAT_H
-#define _LINUX_NF_NAT_H
-
-#include <linux/types.h>
-
-#define IP_NAT_RANGE_MAP_IPS 1
-#define IP_NAT_RANGE_PROTO_SPECIFIED 2
-#define IP_NAT_RANGE_PROTO_RANDOM 4
-#define IP_NAT_RANGE_PERSISTENT 8
-
-/* The protocol-specific manipulable parts of the tuple. */
-union nf_conntrack_man_proto {
- /* Add other protocols here. */
- __be16 all;
-
- struct {
- __be16 port;
- } tcp;
- struct {
- __be16 port;
- } udp;
- struct {
- __be16 id;
- } icmp;
- struct {
- __be16 port;
- } dccp;
- struct {
- __be16 port;
- } sctp;
- struct {
- __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
- } gre;
-};
-
-/* Single range specification. */
-struct nf_nat_range {
- /* Set to OR of flags above. */
- unsigned int flags;
-
- /* Inclusive: network order. */
- __be32 min_ip, max_ip;
-
- /* Inclusive: network order */
- union nf_conntrack_man_proto min, max;
-};
-
-/* For backwards compat: don't use in modern code. */
-struct nf_nat_multi_range_compat {
- unsigned int rangesize; /* Must be 1. */
-
- /* hangs off end. */
- struct nf_nat_range range[1];
-};
-
-#define nf_nat_multi_range nf_nat_multi_range_compat
-
-#endif
#define NETLINK_UNUSED 1 /* Unused number */
#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
#define NETLINK_FIREWALL 3 /* Firewalling hook */
-#define NETLINK_INET_DIAG 4 /* INET socket monitoring */
+#define NETLINK_SOCK_DIAG 4 /* socket monitoring */
#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
#define NETLINK_XFRM 6 /* ipsec */
#define NETLINK_SELINUX 7 /* SELinux event notifications */
#define NETLINK_RDMA 20
#define NETLINK_CRYPTO 21 /* Crypto layer */
+#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG
+
#define MAX_LINKS 32
struct sockaddr_nl {
extern const struct inode_operations nfs3_file_inode_operations;
#endif /* CONFIG_NFS_V3 */
extern const struct file_operations nfs_file_operations;
+#ifdef CONFIG_NFS_V4
+extern const struct file_operations nfs4_file_operations;
+#endif /* CONFIG_NFS_V4 */
extern const struct address_space_operations nfs_file_aops;
extern const struct address_space_operations nfs_dir_aops;
const struct dentry_operations *dentry_ops;
const struct inode_operations *dir_inode_ops;
const struct inode_operations *file_inode_ops;
+ const struct file_operations *file_ops;
int (*getroot) (struct nfs_server *, struct nfs_fh *,
struct nfs_fsinfo *);
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef _LINUX_OPENVSWITCH_H
+#define _LINUX_OPENVSWITCH_H 1
+
+#include <linux/types.h>
+
+/**
+ * struct ovs_header - header for OVS Generic Netlink messages.
+ * @dp_ifindex: ifindex of local port for datapath (0 to make a request not
+ * specific to a datapath).
+ *
+ * Attributes following the header are specific to a particular OVS Generic
+ * Netlink family, but all of the OVS families use this header.
+ */
+
+struct ovs_header {
+ int dp_ifindex;
+};
+
+/* Datapaths. */
+
+#define OVS_DATAPATH_FAMILY "ovs_datapath"
+#define OVS_DATAPATH_MCGROUP "ovs_datapath"
+#define OVS_DATAPATH_VERSION 0x1
+
+enum ovs_datapath_cmd {
+ OVS_DP_CMD_UNSPEC,
+ OVS_DP_CMD_NEW,
+ OVS_DP_CMD_DEL,
+ OVS_DP_CMD_GET,
+ OVS_DP_CMD_SET
+};
+
+/**
+ * enum ovs_datapath_attr - attributes for %OVS_DP_* commands.
+ * @OVS_DP_ATTR_NAME: Name of the network device that serves as the "local
+ * port". This is the name of the network device whose dp_ifindex is given in
+ * the &struct ovs_header. Always present in notifications. Required in
+ * %OVS_DP_NEW requests. May be used as an alternative to specifying
+ * dp_ifindex in other requests (with a dp_ifindex of 0).
+ * @OVS_DP_ATTR_UPCALL_PID: The Netlink socket in userspace that is initially
+ * set on the datapath port (for OVS_ACTION_ATTR_MISS). Only valid on
+ * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should
+ * not be sent.
+ * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the
+ * datapath. Always present in notifications.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_DP_* commands.
+ */
+enum ovs_datapath_attr {
+ OVS_DP_ATTR_UNSPEC,
+ OVS_DP_ATTR_NAME, /* name of dp_ifindex netdev */
+ OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */
+ OVS_DP_ATTR_STATS, /* struct ovs_dp_stats */
+ __OVS_DP_ATTR_MAX
+};
+
+#define OVS_DP_ATTR_MAX (__OVS_DP_ATTR_MAX - 1)
+
+struct ovs_dp_stats {
+ __u64 n_hit; /* Number of flow table matches. */
+ __u64 n_missed; /* Number of flow table misses. */
+ __u64 n_lost; /* Number of misses not sent to userspace. */
+ __u64 n_flows; /* Number of flows present */
+};
+
+struct ovs_vport_stats {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* no space in linux buffers */
+ __u64 tx_dropped; /* no space available in linux */
+};
+
+/* Fixed logical ports. */
+#define OVSP_LOCAL ((__u16)0)
+
+/* Packet transfer. */
+
+#define OVS_PACKET_FAMILY "ovs_packet"
+#define OVS_PACKET_VERSION 0x1
+
+enum ovs_packet_cmd {
+ OVS_PACKET_CMD_UNSPEC,
+
+ /* Kernel-to-user notifications. */
+ OVS_PACKET_CMD_MISS, /* Flow table miss. */
+ OVS_PACKET_CMD_ACTION, /* OVS_ACTION_ATTR_USERSPACE action. */
+
+ /* Userspace commands. */
+ OVS_PACKET_CMD_EXECUTE /* Apply actions to a packet. */
+};
+
+/**
+ * enum ovs_packet_attr - attributes for %OVS_PACKET_* commands.
+ * @OVS_PACKET_ATTR_PACKET: Present for all notifications. Contains the entire
+ * packet as received, from the start of the Ethernet header onward. For
+ * %OVS_PACKET_CMD_ACTION, %OVS_PACKET_ATTR_PACKET reflects changes made by
+ * actions preceding %OVS_ACTION_ATTR_USERSPACE, but %OVS_PACKET_ATTR_KEY is
+ * the flow key extracted from the packet as originally received.
+ * @OVS_PACKET_ATTR_KEY: Present for all notifications. Contains the flow key
+ * extracted from the packet as nested %OVS_KEY_ATTR_* attributes. This allows
+ * userspace to adapt its flow setup strategy by comparing its notion of the
+ * flow key against the kernel's.
+ * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used
+ * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes.
+ * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION
+ * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
+ * %OVS_USERSPACE_ATTR_USERDATA attribute.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_PACKET_* commands.
+ */
+enum ovs_packet_attr {
+ OVS_PACKET_ATTR_UNSPEC,
+ OVS_PACKET_ATTR_PACKET, /* Packet data. */
+ OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */
+ OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */
+ OVS_PACKET_ATTR_USERDATA, /* u64 OVS_ACTION_ATTR_USERSPACE arg. */
+ __OVS_PACKET_ATTR_MAX
+};
+
+#define OVS_PACKET_ATTR_MAX (__OVS_PACKET_ATTR_MAX - 1)
+
+/* Virtual ports. */
+
+#define OVS_VPORT_FAMILY "ovs_vport"
+#define OVS_VPORT_MCGROUP "ovs_vport"
+#define OVS_VPORT_VERSION 0x1
+
+enum ovs_vport_cmd {
+ OVS_VPORT_CMD_UNSPEC,
+ OVS_VPORT_CMD_NEW,
+ OVS_VPORT_CMD_DEL,
+ OVS_VPORT_CMD_GET,
+ OVS_VPORT_CMD_SET
+};
+
+enum ovs_vport_type {
+ OVS_VPORT_TYPE_UNSPEC,
+ OVS_VPORT_TYPE_NETDEV, /* network device */
+ OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */
+ __OVS_VPORT_TYPE_MAX
+};
+
+#define OVS_VPORT_TYPE_MAX (__OVS_VPORT_TYPE_MAX - 1)
+
+/**
+ * enum ovs_vport_attr - attributes for %OVS_VPORT_* commands.
+ * @OVS_VPORT_ATTR_PORT_NO: 32-bit port number within datapath.
+ * @OVS_VPORT_ATTR_TYPE: 32-bit %OVS_VPORT_TYPE_* constant describing the type
+ * of vport.
+ * @OVS_VPORT_ATTR_NAME: Name of vport. For a vport based on a network device
+ * this is the name of the network device. Maximum length %IFNAMSIZ-1 bytes
+ * plus a null terminator.
+ * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information.
+ * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that
+ * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on
+ * this port. A value of zero indicates that upcalls should not be sent.
+ * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for
+ * packets sent or received through the vport.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_VPORT_* commands.
+ *
+ * For %OVS_VPORT_CMD_NEW requests, the %OVS_VPORT_ATTR_TYPE and
+ * %OVS_VPORT_ATTR_NAME attributes are required. %OVS_VPORT_ATTR_PORT_NO is
+ * optional; if not specified a free port number is automatically selected.
+ * Whether %OVS_VPORT_ATTR_OPTIONS is required or optional depends on the type
+ * of vport.
+ * and other attributes are ignored.
+ *
+ * For other requests, if %OVS_VPORT_ATTR_NAME is specified then it is used to
+ * look up the vport to operate on; otherwise dp_idx from the &struct
+ * ovs_header plus %OVS_VPORT_ATTR_PORT_NO determine the vport.
+ */
+enum ovs_vport_attr {
+ OVS_VPORT_ATTR_UNSPEC,
+ OVS_VPORT_ATTR_PORT_NO, /* u32 port number within datapath */
+ OVS_VPORT_ATTR_TYPE, /* u32 OVS_VPORT_TYPE_* constant. */
+ OVS_VPORT_ATTR_NAME, /* string name, up to IFNAMSIZ bytes long */
+ OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */
+ OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */
+ OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */
+ __OVS_VPORT_ATTR_MAX
+};
+
+#define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1)
+
+/* Flows. */
+
+#define OVS_FLOW_FAMILY "ovs_flow"
+#define OVS_FLOW_MCGROUP "ovs_flow"
+#define OVS_FLOW_VERSION 0x1
+
+enum ovs_flow_cmd {
+ OVS_FLOW_CMD_UNSPEC,
+ OVS_FLOW_CMD_NEW,
+ OVS_FLOW_CMD_DEL,
+ OVS_FLOW_CMD_GET,
+ OVS_FLOW_CMD_SET
+};
+
+struct ovs_flow_stats {
+ __u64 n_packets; /* Number of matched packets. */
+ __u64 n_bytes; /* Number of matched bytes. */
+};
+
+enum ovs_key_attr {
+ OVS_KEY_ATTR_UNSPEC,
+ OVS_KEY_ATTR_ENCAP, /* Nested set of encapsulated attributes. */
+ OVS_KEY_ATTR_PRIORITY, /* u32 skb->priority */
+ OVS_KEY_ATTR_IN_PORT, /* u32 OVS dp port number */
+ OVS_KEY_ATTR_ETHERNET, /* struct ovs_key_ethernet */
+ OVS_KEY_ATTR_VLAN, /* be16 VLAN TCI */
+ OVS_KEY_ATTR_ETHERTYPE, /* be16 Ethernet type */
+ OVS_KEY_ATTR_IPV4, /* struct ovs_key_ipv4 */
+ OVS_KEY_ATTR_IPV6, /* struct ovs_key_ipv6 */
+ OVS_KEY_ATTR_TCP, /* struct ovs_key_tcp */
+ OVS_KEY_ATTR_UDP, /* struct ovs_key_udp */
+ OVS_KEY_ATTR_ICMP, /* struct ovs_key_icmp */
+ OVS_KEY_ATTR_ICMPV6, /* struct ovs_key_icmpv6 */
+ OVS_KEY_ATTR_ARP, /* struct ovs_key_arp */
+ OVS_KEY_ATTR_ND, /* struct ovs_key_nd */
+ __OVS_KEY_ATTR_MAX
+};
+
+#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1)
+
+/**
+ * enum ovs_frag_type - IPv4 and IPv6 fragment type
+ * @OVS_FRAG_TYPE_NONE: Packet is not a fragment.
+ * @OVS_FRAG_TYPE_FIRST: Packet is a fragment with offset 0.
+ * @OVS_FRAG_TYPE_LATER: Packet is a fragment with nonzero offset.
+ *
+ * Used as the @ipv4_frag in &struct ovs_key_ipv4 and as @ipv6_frag &struct
+ * ovs_key_ipv6.
+ */
+enum ovs_frag_type {
+ OVS_FRAG_TYPE_NONE,
+ OVS_FRAG_TYPE_FIRST,
+ OVS_FRAG_TYPE_LATER,
+ __OVS_FRAG_TYPE_MAX
+};
+
+#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1)
+
+struct ovs_key_ethernet {
+ __u8 eth_src[6];
+ __u8 eth_dst[6];
+};
+
+struct ovs_key_ipv4 {
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ __u8 ipv4_proto;
+ __u8 ipv4_tos;
+ __u8 ipv4_ttl;
+ __u8 ipv4_frag; /* One of OVS_FRAG_TYPE_*. */
+};
+
+struct ovs_key_ipv6 {
+ __be32 ipv6_src[4];
+ __be32 ipv6_dst[4];
+ __be32 ipv6_label; /* 20-bits in least-significant bits. */
+ __u8 ipv6_proto;
+ __u8 ipv6_tclass;
+ __u8 ipv6_hlimit;
+ __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */
+};
+
+struct ovs_key_tcp {
+ __be16 tcp_src;
+ __be16 tcp_dst;
+};
+
+struct ovs_key_udp {
+ __be16 udp_src;
+ __be16 udp_dst;
+};
+
+struct ovs_key_icmp {
+ __u8 icmp_type;
+ __u8 icmp_code;
+};
+
+struct ovs_key_icmpv6 {
+ __u8 icmpv6_type;
+ __u8 icmpv6_code;
+};
+
+struct ovs_key_arp {
+ __be32 arp_sip;
+ __be32 arp_tip;
+ __be16 arp_op;
+ __u8 arp_sha[6];
+ __u8 arp_tha[6];
+};
+
+struct ovs_key_nd {
+ __u32 nd_target[4];
+ __u8 nd_sll[6];
+ __u8 nd_tll[6];
+};
+
+/**
+ * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
+ * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow
+ * key. Always present in notifications. Required for all requests (except
+ * dumps).
+ * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying
+ * the actions to take for packets that match the key. Always present in
+ * notifications. Required for %OVS_FLOW_CMD_NEW requests, optional for
+ * %OVS_FLOW_CMD_SET requests.
+ * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this
+ * flow. Present in notifications if the stats would be nonzero. Ignored in
+ * requests.
+ * @OVS_FLOW_ATTR_TCP_FLAGS: An 8-bit value giving the OR'd value of all of the
+ * TCP flags seen on packets in this flow. Only present in notifications for
+ * TCP flows, and only if it would be nonzero. Ignored in requests.
+ * @OVS_FLOW_ATTR_USED: A 64-bit integer giving the time, in milliseconds on
+ * the system monotonic clock, at which a packet was last processed for this
+ * flow. Only present in notifications if a packet has been processed for this
+ * flow. Ignored in requests.
+ * @OVS_FLOW_ATTR_CLEAR: If present in a %OVS_FLOW_CMD_SET request, clears the
+ * last-used time, accumulated TCP flags, and statistics for this flow.
+ * Otherwise ignored in requests. Never present in notifications.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_FLOW_* commands.
+ */
+enum ovs_flow_attr {
+ OVS_FLOW_ATTR_UNSPEC,
+ OVS_FLOW_ATTR_KEY, /* Sequence of OVS_KEY_ATTR_* attributes. */
+ OVS_FLOW_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */
+ OVS_FLOW_ATTR_STATS, /* struct ovs_flow_stats. */
+ OVS_FLOW_ATTR_TCP_FLAGS, /* 8-bit OR'd TCP flags. */
+ OVS_FLOW_ATTR_USED, /* u64 msecs last used in monotonic time. */
+ OVS_FLOW_ATTR_CLEAR, /* Flag to clear stats, tcp_flags, used. */
+ __OVS_FLOW_ATTR_MAX
+};
+
+#define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1)
+
+/**
+ * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action.
+ * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with
+ * @OVS_ACTION_ATTR_SAMPLE. A value of 0 samples no packets, a value of
+ * %UINT32_MAX samples all packets and intermediate values sample intermediate
+ * fractions of packets.
+ * @OVS_SAMPLE_ATTR_ACTIONS: Set of actions to execute in sampling event.
+ * Actions are passed as nested attributes.
+ *
+ * Executes the specified actions with the given probability on a per-packet
+ * basis.
+ */
+enum ovs_sample_attr {
+ OVS_SAMPLE_ATTR_UNSPEC,
+ OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */
+ OVS_SAMPLE_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */
+ __OVS_SAMPLE_ATTR_MAX,
+};
+
+#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1)
+
+/**
+ * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action.
+ * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION
+ * message should be sent. Required.
+ * @OVS_USERSPACE_ATTR_USERDATA: If present, its u64 argument is copied to the
+ * %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA,
+ */
+enum ovs_userspace_attr {
+ OVS_USERSPACE_ATTR_UNSPEC,
+ OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */
+ OVS_USERSPACE_ATTR_USERDATA, /* u64 optional user-specified cookie. */
+ __OVS_USERSPACE_ATTR_MAX
+};
+
+#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
+
+/**
+ * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument.
+ * @vlan_tpid: Tag protocol identifier (TPID) to push.
+ * @vlan_tci: Tag control identifier (TCI) to push. The CFI bit must be set
+ * (but it will not be set in the 802.1Q header that is pushed).
+ *
+ * The @vlan_tpid value is typically %ETH_P_8021Q. The only acceptable TPID
+ * values are those that the kernel module also parses as 802.1Q headers, to
+ * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN
+ * from having surprising results.
+ */
+struct ovs_action_push_vlan {
+ __be16 vlan_tpid; /* 802.1Q TPID. */
+ __be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */
+};
+
+/**
+ * enum ovs_action_attr - Action types.
+ *
+ * @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
+ * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested
+ * %OVS_USERSPACE_ATTR_* attributes.
+ * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header. The
+ * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its
+ * value.
+ * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the
+ * packet.
+ * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet.
+ * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in
+ * the nested %OVS_SAMPLE_ATTR_* attributes.
+ *
+ * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all
+ * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
+ * type may not be changed.
+ */
+
+enum ovs_action_attr {
+ OVS_ACTION_ATTR_UNSPEC,
+ OVS_ACTION_ATTR_OUTPUT, /* u32 port number. */
+ OVS_ACTION_ATTR_USERSPACE, /* Nested OVS_USERSPACE_ATTR_*. */
+ OVS_ACTION_ATTR_SET, /* One nested OVS_KEY_ATTR_*. */
+ OVS_ACTION_ATTR_PUSH_VLAN, /* struct ovs_action_push_vlan. */
+ OVS_ACTION_ATTR_POP_VLAN, /* No argument. */
+ OVS_ACTION_ATTR_SAMPLE, /* Nested OVS_SAMPLE_ATTR_*. */
+ __OVS_ACTION_ATTR_MAX
+};
+
+#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1)
+
+#endif /* _LINUX_OPENVSWITCH_H */
unsigned int is_enabled:1; /* Enable bit is set */
};
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
extern int pci_enable_ats(struct pci_dev *dev, int ps);
extern void pci_disable_ats(struct pci_dev *dev);
return dev->ats && dev->ats->is_enabled;
}
-#else /* CONFIG_PCI_IOV */
+#else /* CONFIG_PCI_ATS */
static inline int pci_enable_ats(struct pci_dev *dev, int ps)
{
return 0;
}
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_ATS */
#ifdef CONFIG_PCI_PRI
struct list_head msi_list;
#endif
struct pci_vpd *vpd;
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
union {
struct pci_sriov *sriov; /* SR-IOV capability related */
struct pci_dev *physfn; /* the PF this VF is associated with */
#define PCI_DEVICE_ID_AMD_11H_NB_DRAM 0x1302
#define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303
#define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_F0 0x1600
+#define PCI_DEVICE_ID_AMD_15H_NB_F1 0x1601
+#define PCI_DEVICE_ID_AMD_15H_NB_F2 0x1602
#define PCI_DEVICE_ID_AMD_15H_NB_F3 0x1603
#define PCI_DEVICE_ID_AMD_15H_NB_F4 0x1604
+#define PCI_DEVICE_ID_AMD_15H_NB_F5 0x1605
#define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703
#define PCI_DEVICE_ID_AMD_LANCE 0x2000
#define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001
int mmap_locked;
struct user_struct *mmap_user;
struct ring_buffer *rb;
+ struct list_head rb_entry;
/* poll related */
wait_queue_head_t waitq;
#define PNPIPE_ENCAP 1
#define PNPIPE_IFINDEX 2
#define PNPIPE_HANDLE 3
+#define PNPIPE_INITSTATE 4
#define PNADDR_ANY 0
#define PNADDR_BROADCAST 0xFC
/* ioctls */
#define SIOCPNGETOBJECT (SIOCPROTOPRIVATE + 0)
+#define SIOCPNENABLEPIPE (SIOCPROTOPRIVATE + 13)
#define SIOCPNADDRESOURCE (SIOCPROTOPRIVATE + 14)
#define SIOCPNDELRESOURCE (SIOCPROTOPRIVATE + 15)
*/
struct tc_stats {
- __u64 bytes; /* NUmber of enqueues bytes */
+ __u64 bytes; /* Number of enqueued bytes */
__u32 packets; /* Number of enqueued packets */
__u32 drops; /* Packets dropped because of lack of resources */
__u32 overlimits; /* Number of throttle events when this
TCA_RED_UNSPEC,
TCA_RED_PARMS,
TCA_RED_STAB,
+ TCA_RED_MAX_P,
__TCA_RED_MAX,
};
unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
unsigned char Scell_log; /* cell size for idle damping */
unsigned char flags;
-#define TC_RED_ECN 1
-#define TC_RED_HARDDROP 2
+#define TC_RED_ECN 1
+#define TC_RED_HARDDROP 2
+#define TC_RED_ADAPTATIVE 4
};
struct tc_red_xstats {
TCA_GRED_PARMS,
TCA_GRED_STAB,
TCA_GRED_DPS,
+ TCA_GRED_MAX_P,
__TCA_GRED_MAX,
};
TCA_CHOKE_UNSPEC,
TCA_CHOKE_PARMS,
TCA_CHOKE_STAB,
+ TCA_CHOKE_MAX_P,
__TCA_CHOKE_MAX,
};
__u32 debug; /* debug flags */
/* stats */
- __u32 direct_pkts; /* count of non shapped packets */
+ __u32 direct_pkts; /* count of non shaped packets */
};
enum {
TCA_HTB_UNSPEC,
TCA_NETEM_REORDER,
TCA_NETEM_CORRUPT,
TCA_NETEM_LOSS,
+ TCA_NETEM_RATE,
__TCA_NETEM_MAX,
};
__u32 correlation;
};
+struct tc_netem_rate {
+ __u32 rate; /* byte/s */
+ __s32 packet_overhead;
+ __u32 cell_size;
+ __s32 cell_overhead;
+};
+
enum {
NETEM_LOSS_UNSPEC,
NETEM_LOSS_GI, /* General Intuitive - 4 state model */
};
#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
-/* State transition probablities for 4 state model */
+/* State transition probabilities for 4 state model */
struct tc_netem_gimodel {
__u32 p13;
__u32 p31;
/**
* struct dev_pm_ops - device PM callbacks
*
- * Several driver power state transitions are externally visible, affecting
+ * Several device power state transitions are externally visible, affecting
* the state of pending I/O queues and (for drivers that touch hardware)
* interrupts, wakeups, DMA, and other hardware state. There may also be
- * internal transitions to various low power modes, which are transparent
+ * internal transitions to various low-power modes which are transparent
* to the rest of the driver stack (such as a driver that's ON gating off
* clocks which are not in active use).
*
- * The externally visible transitions are handled with the help of the following
- * callbacks included in this structure:
- *
- * @prepare: Prepare the device for the upcoming transition, but do NOT change
- * its hardware state. Prevent new children of the device from being
- * registered after @prepare() returns (the driver's subsystem and
- * generally the rest of the kernel is supposed to prevent new calls to the
- * probe method from being made too once @prepare() has succeeded). If
- * @prepare() detects a situation it cannot handle (e.g. registration of a
- * child already in progress), it may return -EAGAIN, so that the PM core
- * can execute it once again (e.g. after the new child has been registered)
- * to recover from the race condition. This method is executed for all
- * kinds of suspend transitions and is followed by one of the suspend
- * callbacks: @suspend(), @freeze(), or @poweroff().
- * The PM core executes @prepare() for all devices before starting to
- * execute suspend callbacks for any of them, so drivers may assume all of
- * the other devices to be present and functional while @prepare() is being
- * executed. In particular, it is safe to make GFP_KERNEL memory
- * allocations from within @prepare(). However, drivers may NOT assume
- * anything about the availability of the user space at that time and it
- * is not correct to request firmware from within @prepare() (it's too
- * late to do that). [To work around this limitation, drivers may
- * register suspend and hibernation notifiers that are executed before the
- * freezing of tasks.]
+ * The externally visible transitions are handled with the help of callbacks
+ * included in this structure in such a way that two levels of callbacks are
+ * involved. First, the PM core executes callbacks provided by PM domains,
+ * device types, classes and bus types. They are the subsystem-level callbacks
+ * supposed to execute callbacks provided by device drivers, although they may
+ * choose not to do that. If the driver callbacks are executed, they have to
+ * collaborate with the subsystem-level callbacks to achieve the goals
+ * appropriate for the given system transition, given transition phase and the
+ * subsystem the device belongs to.
+ *
+ * @prepare: The principal role of this callback is to prevent new children of
+ * the device from being registered after it has returned (the driver's
+ * subsystem and generally the rest of the kernel is supposed to prevent
+ * new calls to the probe method from being made too once @prepare() has
+ * succeeded). If @prepare() detects a situation it cannot handle (e.g.
+ * registration of a child already in progress), it may return -EAGAIN, so
+ * that the PM core can execute it once again (e.g. after a new child has
+ * been registered) to recover from the race condition.
+ * This method is executed for all kinds of suspend transitions and is
+ * followed by one of the suspend callbacks: @suspend(), @freeze(), or
+ * @poweroff(). The PM core executes subsystem-level @prepare() for all
+ * devices before starting to invoke suspend callbacks for any of them, so
+ * generally devices may be assumed to be functional or to respond to
+ * runtime resume requests while @prepare() is being executed. However,
+ * device drivers may NOT assume anything about the availability of user
+ * space at that time and it is NOT valid to request firmware from within
+ * @prepare() (it's too late to do that). It also is NOT valid to allocate
+ * substantial amounts of memory from @prepare() in the GFP_KERNEL mode.
+ * [To work around these limitations, drivers may register suspend and
+ * hibernation notifiers to be executed before the freezing of tasks.]
*
* @complete: Undo the changes made by @prepare(). This method is executed for
* all kinds of resume transitions, following one of the resume callbacks:
* @resume(), @thaw(), @restore(). Also called if the state transition
- * fails before the driver's suspend callback (@suspend(), @freeze(),
- * @poweroff()) can be executed (e.g. if the suspend callback fails for one
+ * fails before the driver's suspend callback: @suspend(), @freeze() or
+ * @poweroff(), can be executed (e.g. if the suspend callback fails for one
* of the other devices that the PM core has unsuccessfully attempted to
* suspend earlier).
- * The PM core executes @complete() after it has executed the appropriate
- * resume callback for all devices.
+ * The PM core executes subsystem-level @complete() after it has executed
+ * the appropriate resume callbacks for all devices.
*
* @suspend: Executed before putting the system into a sleep state in which the
- * contents of main memory are preserved. Quiesce the device, put it into
- * a low power state appropriate for the upcoming system state (such as
- * PCI_D3hot), and enable wakeup events as appropriate.
+ * contents of main memory are preserved. The exact action to perform
+ * depends on the device's subsystem (PM domain, device type, class or bus
+ * type), but generally the device must be quiescent after subsystem-level
+ * @suspend() has returned, so that it doesn't do any I/O or DMA.
+ * Subsystem-level @suspend() is executed for all devices after invoking
+ * subsystem-level @prepare() for all of them.
*
* @resume: Executed after waking the system up from a sleep state in which the
- * contents of main memory were preserved. Put the device into the
- * appropriate state, according to the information saved in memory by the
- * preceding @suspend(). The driver starts working again, responding to
- * hardware events and software requests. The hardware may have gone
- * through a power-off reset, or it may have maintained state from the
- * previous suspend() which the driver may rely on while resuming. On most
- * platforms, there are no restrictions on availability of resources like
- * clocks during @resume().
+ * contents of main memory were preserved. The exact action to perform
+ * depends on the device's subsystem, but generally the driver is expected
+ * to start working again, responding to hardware events and software
+ * requests (the device itself may be left in a low-power state, waiting
+ * for a runtime resume to occur). The state of the device at the time its
+ * driver's @resume() callback is run depends on the platform and subsystem
+ * the device belongs to. On most platforms, there are no restrictions on
+ * availability of resources like clocks during @resume().
+ * Subsystem-level @resume() is executed for all devices after invoking
+ * subsystem-level @resume_noirq() for all of them.
*
* @freeze: Hibernation-specific, executed before creating a hibernation image.
- * Quiesce operations so that a consistent image can be created, but do NOT
- * otherwise put the device into a low power device state and do NOT emit
- * system wakeup events. Save in main memory the device settings to be
- * used by @restore() during the subsequent resume from hibernation or by
- * the subsequent @thaw(), if the creation of the image or the restoration
- * of main memory contents from it fails.
+ * Analogous to @suspend(), but it should not enable the device to signal
+ * wakeup events or change its power state. The majority of subsystems
+ * (with the notable exception of the PCI bus type) expect the driver-level
+ * @freeze() to save the device settings in memory to be used by @restore()
+ * during the subsequent resume from hibernation.
+ * Subsystem-level @freeze() is executed for all devices after invoking
+ * subsystem-level @prepare() for all of them.
*
* @thaw: Hibernation-specific, executed after creating a hibernation image OR
- * if the creation of the image fails. Also executed after a failing
+ * if the creation of an image has failed. Also executed after a failing
* attempt to restore the contents of main memory from such an image.
* Undo the changes made by the preceding @freeze(), so the device can be
* operated in the same way as immediately before the call to @freeze().
+ * Subsystem-level @thaw() is executed for all devices after invoking
+ * subsystem-level @thaw_noirq() for all of them. It also may be executed
+ * directly after @freeze() in case of a transition error.
*
* @poweroff: Hibernation-specific, executed after saving a hibernation image.
- * Quiesce the device, put it into a low power state appropriate for the
- * upcoming system state (such as PCI_D3hot), and enable wakeup events as
- * appropriate.
+ * Analogous to @suspend(), but it need not save the device's settings in
+ * memory.
+ * Subsystem-level @poweroff() is executed for all devices after invoking
+ * subsystem-level @prepare() for all of them.
*
* @restore: Hibernation-specific, executed after restoring the contents of main
- * memory from a hibernation image. Driver starts working again,
- * responding to hardware events and software requests. Drivers may NOT
- * make ANY assumptions about the hardware state right prior to @restore().
- * On most platforms, there are no restrictions on availability of
- * resources like clocks during @restore().
- *
- * @suspend_noirq: Complete the operations of ->suspend() by carrying out any
- * actions required for suspending the device that need interrupts to be
- * disabled
- *
- * @resume_noirq: Prepare for the execution of ->resume() by carrying out any
- * actions required for resuming the device that need interrupts to be
- * disabled
- *
- * @freeze_noirq: Complete the operations of ->freeze() by carrying out any
- * actions required for freezing the device that need interrupts to be
- * disabled
- *
- * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any
- * actions required for thawing the device that need interrupts to be
- * disabled
- *
- * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any
- * actions required for handling the device that need interrupts to be
- * disabled
- *
- * @restore_noirq: Prepare for the execution of ->restore() by carrying out any
- * actions required for restoring the operations of the device that need
- * interrupts to be disabled
+ * memory from a hibernation image, analogous to @resume().
+ *
+ * @suspend_noirq: Complete the actions started by @suspend(). Carry out any
+ * additional operations required for suspending the device that might be
+ * racing with its driver's interrupt handler, which is guaranteed not to
+ * run while @suspend_noirq() is being executed.
+ * It generally is expected that the device will be in a low-power state
+ * (appropriate for the target system sleep state) after subsystem-level
+ * @suspend_noirq() has returned successfully. If the device can generate
+ * system wakeup signals and is enabled to wake up the system, it should be
+ * configured to do so at that time. However, depending on the platform
+ * and device's subsystem, @suspend() may be allowed to put the device into
+ * the low-power state and configure it to generate wakeup signals, in
+ * which case it generally is not necessary to define @suspend_noirq().
+ *
+ * @resume_noirq: Prepare for the execution of @resume() by carrying out any
+ * operations required for resuming the device that might be racing with
+ * its driver's interrupt handler, which is guaranteed not to run while
+ * @resume_noirq() is being executed.
+ *
+ * @freeze_noirq: Complete the actions started by @freeze(). Carry out any
+ * additional operations required for freezing the device that might be
+ * racing with its driver's interrupt handler, which is guaranteed not to
+ * run while @freeze_noirq() is being executed.
+ * The power state of the device should not be changed by either @freeze()
+ * or @freeze_noirq() and it should not be configured to signal system
+ * wakeup by any of these callbacks.
+ *
+ * @thaw_noirq: Prepare for the execution of @thaw() by carrying out any
+ * operations required for thawing the device that might be racing with its
+ * driver's interrupt handler, which is guaranteed not to run while
+ * @thaw_noirq() is being executed.
+ *
+ * @poweroff_noirq: Complete the actions started by @poweroff(). Analogous to
+ * @suspend_noirq(), but it need not save the device's settings in memory.
+ *
+ * @restore_noirq: Prepare for the execution of @restore() by carrying out any
+ * operations required for thawing the device that might be racing with its
+ * driver's interrupt handler, which is guaranteed not to run while
+ * @restore_noirq() is being executed. Analogous to @resume_noirq().
*
* All of the above callbacks, except for @complete(), return error codes.
* However, the error codes returned by the resume operations, @resume(),
- * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq() do
+ * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do
* not cause the PM core to abort the resume transition during which they are
- * returned. The error codes returned in that cases are only printed by the PM
+ * returned. The error codes returned in those cases are only printed by the PM
* core to the system logs for debugging purposes. Still, it is recommended
* that drivers only return error codes from their resume methods in case of an
* unrecoverable failure (i.e. when the device being handled refuses to resume
* their children.
*
* It is allowed to unregister devices while the above callbacks are being
- * executed. However, it is not allowed to unregister a device from within any
- * of its own callbacks.
+ * executed. However, a callback routine must NOT try to unregister the device
+ * it was called for, although it may unregister children of that device (for
+ * example, if it detects that a child was unplugged while the system was
+ * asleep).
+ *
+ * Refer to Documentation/power/devices.txt for more information about the role
+ * of the above callbacks in the system suspend process.
*
- * There also are the following callbacks related to run-time power management
- * of devices:
+ * There also are callbacks related to runtime power management of devices.
+ * Again, these callbacks are executed by the PM core only for subsystems
+ * (PM domains, device types, classes and bus types) and the subsystem-level
+ * callbacks are supposed to invoke the driver callbacks. Moreover, the exact
+ * actions to be performed by a device driver's callbacks generally depend on
+ * the platform and subsystem the device belongs to.
*
* @runtime_suspend: Prepare the device for a condition in which it won't be
* able to communicate with the CPU(s) and RAM due to power management.
- * This need not mean that the device should be put into a low power state.
+ * This need not mean that the device should be put into a low-power state.
* For example, if the device is behind a link which is about to be turned
* off, the device may remain at full power. If the device does go to low
- * power and is capable of generating run-time wake-up events, remote
- * wake-up (i.e., a hardware mechanism allowing the device to request a
- * change of its power state via a wake-up event, such as PCI PME) should
- * be enabled for it.
+ * power and is capable of generating runtime wakeup events, remote wakeup
+ * (i.e., a hardware mechanism allowing the device to request a change of
+ * its power state via an interrupt) should be enabled for it.
*
* @runtime_resume: Put the device into the fully active state in response to a
- * wake-up event generated by hardware or at the request of software. If
- * necessary, put the device into the full power state and restore its
+ * wakeup event generated by hardware or at the request of software. If
+ * necessary, put the device into the full-power state and restore its
* registers, so that it is fully operational.
*
- * @runtime_idle: Device appears to be inactive and it might be put into a low
- * power state if all of the necessary conditions are satisfied. Check
+ * @runtime_idle: Device appears to be inactive and it might be put into a
+ * low-power state if all of the necessary conditions are satisfied. Check
* these conditions and handle the device as appropriate, possibly queueing
* a suspend request for it. The return value is ignored by the PM core.
+ *
+ * Refer to Documentation/power/runtime_pm.txt for more information about the
+ * role of the above callbacks in device runtime power management.
+ *
*/
struct dev_pm_ops {
unsigned int async_suspend:1;
bool is_prepared:1; /* Owned by the PM core */
bool is_suspended:1; /* Ditto */
+ bool ignore_children:1;
spinlock_t lock;
#ifdef CONFIG_PM_SLEEP
struct list_head entry;
atomic_t usage_count;
atomic_t child_count;
unsigned int disable_depth:3;
- unsigned int ignore_children:1;
unsigned int idle_notification:1;
unsigned int request_pending:1;
unsigned int deferred_resume:1;
|| !atomic_read(&dev->power.child_count);
}
-static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
-{
- dev->power.ignore_children = enable;
-}
-
static inline void pm_runtime_get_noresume(struct device *dev)
{
atomic_inc(&dev->power.usage_count);
static inline void pm_runtime_forbid(struct device *dev) {}
static inline bool pm_children_suspended(struct device *dev) { return false; }
-static inline void pm_suspend_ignore_children(struct device *dev, bool en) {}
static inline void pm_runtime_get_noresume(struct device *dev) {}
static inline void pm_runtime_put_noidle(struct device *dev) {}
static inline bool device_run_wake(struct device *dev) { return false; }
spinlock_t buf_lock; /* serialize access to 'buf' */
char *buf;
size_t bufsize;
+ struct mutex read_mutex; /* serialize open/read/close */
int (*open)(struct pstore_info *psi);
int (*close)(struct pstore_info *psi);
ssize_t (*read)(u64 *id, enum pstore_type_id *type,
- struct timespec *time, struct pstore_info *psi);
+ struct timespec *time, char **buf,
+ struct pstore_info *psi);
int (*write)(enum pstore_type_id type, u64 *id,
unsigned int part, size_t size, struct pstore_info *psi);
int (*erase)(enum pstore_type_id type, u64 id,
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
- struct prop_local_single dirties;
/*
* when (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for some dirty throttling pause
char **name, void **value,
size_t *len)
{
- return 0;
+ return -EOPNOTSUPP;
}
static inline int security_inode_create(struct inode *dir,
struct serial_rs485 {
__u32 flags; /* RS485 feature flags */
-#define SER_RS485_ENABLED (1 << 0)
-#define SER_RS485_RTS_ON_SEND (1 << 1)
-#define SER_RS485_RTS_AFTER_SEND (1 << 2)
-#define SER_RS485_RTS_BEFORE_SEND (1 << 3)
+#define SER_RS485_ENABLED (1 << 0) /* If enabled */
+#define SER_RS485_RTS_ON_SEND (1 << 1) /* Logical level for
+ RTS pin when
+ sending */
+#define SER_RS485_RTS_AFTER_SEND (1 << 2) /* Logical level for
+ RTS pin after sent*/
#define SER_RS485_RX_DURING_TX (1 << 4)
- __u32 delay_rts_before_send; /* Milliseconds */
- __u32 delay_rts_after_send; /* Milliseconds */
+ __u32 delay_rts_before_send; /* Delay before send (milliseconds) */
+ __u32 delay_rts_after_send; /* Delay after send (milliseconds) */
__u32 padding[5]; /* Memory is cheap, new structs
are a royal PITA .. */
};
/* These are for internal use */
struct list_head list;
- long nr; /* objs pending delete */
+ atomic_long_t nr_in_batch; /* objs pending delete */
};
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
extern void register_shrinker(struct shrinker *);
struct sigma_firmware_header {
unsigned char magic[7];
u8 version;
- u32 crc;
+ __le32 crc;
};
enum {
struct sigma_action {
u8 instr;
u8 len_hi;
- u16 len;
- u16 addr;
+ __le16 len;
+ __be16 addr;
unsigned char payload[];
};
static inline u32 sigma_action_len(struct sigma_action *sa)
{
- return (sa->len_hi << 16) | sa->len;
-}
-
-static inline size_t sigma_action_size(struct sigma_action *sa, u32 payload_len)
-{
- return sizeof(*sa) + payload_len + (payload_len % 2);
+ return (sa->len_hi << 16) | le16_to_cpu(sa->len);
}
extern int process_sigma_firmware(struct i2c_client *client, const char *name);
#include <linux/dmaengine.h>
#include <linux/hrtimer.h>
#include <linux/dma-mapping.h>
+#include <linux/netdev_features.h>
/* Don't change this without changing skb_csum_unnecessary! */
#define CHECKSUM_NONE 0
* at device setup time.
* NETIF_F_HW_CSUM - it is clever device, it is able to checksum
* everything.
- * NETIF_F_NO_CSUM - loopback or reliable single hop media.
* NETIF_F_IP_CSUM - device is dumb. It is able to csum only
* TCP/UDP over IPv4. Sigh. Vendors like this
* way by an unknown reason. Though, see comment above
struct sk_buff;
-/* To allow 64K frame to be packed as single skb without frag_list. Since
- * GRO uses frags we allocate at least 16 regardless of page size.
+/* To allow 64K frame to be packed as single skb without frag_list we
+ * require 64K/PAGE_SIZE pages plus 1 additional page to allow for
+ * buffers which do not start on a page boundary.
+ *
+ * Since GRO uses frags we allocate at least 16 regardless of page
+ * size.
*/
-#if (65536/PAGE_SIZE + 2) < 16
+#if (65536/PAGE_SIZE + 1) < 16
#define MAX_SKB_FRAGS 16UL
#else
-#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
+#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
#endif
typedef struct skb_frag_struct skb_frag_t;
extern void __kfree_skb(struct sk_buff *skb);
extern struct sk_buff *__alloc_skb(unsigned int size,
gfp_t priority, int fclone, int node);
+extern struct sk_buff *build_skb(void *data);
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
{
gfp_t priority);
extern struct sk_buff *skb_copy(const struct sk_buff *skb,
gfp_t priority);
-extern struct sk_buff *pskb_copy(struct sk_buff *skb,
- gfp_t gfp_mask);
+extern struct sk_buff *__pskb_copy(struct sk_buff *skb,
+ int headroom, gfp_t gfp_mask);
+
extern int pskb_expand_head(struct sk_buff *skb,
int nhead, int ntail,
gfp_t gfp_mask);
return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
}
-/**
- * __netdev_alloc_page - allocate a page for ps-rx on a specific device
- * @dev: network device to receive on
- * @gfp_mask: alloc_pages_node mask
- *
- * Allocate a new page. dev currently unused.
- *
- * %NULL is returned if there is no free memory.
- */
-static inline struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
-{
- return alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0);
-}
-
-/**
- * netdev_alloc_page - allocate a page for ps-rx on a specific device
- * @dev: network device to receive on
- *
- * Allocate a new page. dev currently unused.
- *
- * %NULL is returned if there is no free memory.
- */
-static inline struct page *netdev_alloc_page(struct net_device *dev)
-{
- return __netdev_alloc_page(dev, GFP_ATOMIC);
-}
-
-static inline void netdev_free_page(struct net_device *dev, struct page *page)
-{
- __free_page(page);
-}
-
/**
* skb_frag_page - retrieve the page refered to by a paged fragment
* @frag: the paged fragment
frag->page_offset + offset, size, dir);
}
+static inline struct sk_buff *pskb_copy(struct sk_buff *skb,
+ gfp_t gfp_mask)
+{
+ return __pskb_copy(skb, skb_headroom(skb), gfp_mask);
+}
+
/**
* skb_clone_writable - is the header of a clone writable
* @skb: buffer to check
extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
int shiftlen);
-extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *skb_segment(struct sk_buff *skb,
+ netdev_features_t features);
static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
int len, void *buffer)
--- /dev/null
+#ifndef __LINUX_SMSCPHY_H__
+#define __LINUX_SMSCPHY_H__
+
+#define MII_LAN83C185_ISF 29 /* Interrupt Source Flags */
+#define MII_LAN83C185_IM 30 /* Interrupt Mask */
+#define MII_LAN83C185_CTRL_STATUS 17 /* Mode/Status Register */
+
+#define MII_LAN83C185_ISF_INT1 (1<<1) /* Auto-Negotiation Page Received */
+#define MII_LAN83C185_ISF_INT2 (1<<2) /* Parallel Detection Fault */
+#define MII_LAN83C185_ISF_INT3 (1<<3) /* Auto-Negotiation LP Ack */
+#define MII_LAN83C185_ISF_INT4 (1<<4) /* Link Down */
+#define MII_LAN83C185_ISF_INT5 (1<<5) /* Remote Fault Detected */
+#define MII_LAN83C185_ISF_INT6 (1<<6) /* Auto-Negotiation complete */
+#define MII_LAN83C185_ISF_INT7 (1<<7) /* ENERGYON */
+
+#define MII_LAN83C185_ISF_INT_ALL (0x0e)
+
+#define MII_LAN83C185_ISF_INT_PHYLIB_EVENTS \
+ (MII_LAN83C185_ISF_INT6 | MII_LAN83C185_ISF_INT4 | \
+ MII_LAN83C185_ISF_INT7)
+
+#define MII_LAN83C185_EDPWRDOWN (1 << 13) /* EDPWRDOWN */
+#define MII_LAN83C185_ENERGYON (1 << 1) /* ENERGYON */
+
+#endif /* __LINUX_SMSCPHY_H__ */
--- /dev/null
+#ifndef __SOCK_DIAG_H__
+#define __SOCK_DIAG_H__
+
+#include <linux/types.h>
+
+#define SOCK_DIAG_BY_FAMILY 20
+
+struct sock_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+};
+
+enum {
+ SK_MEMINFO_RMEM_ALLOC,
+ SK_MEMINFO_RCVBUF,
+ SK_MEMINFO_WMEM_ALLOC,
+ SK_MEMINFO_SNDBUF,
+ SK_MEMINFO_FWD_ALLOC,
+ SK_MEMINFO_WMEM_QUEUED,
+ SK_MEMINFO_OPTMEM,
+
+ SK_MEMINFO_VARS,
+};
+
+#ifdef __KERNEL__
+struct sk_buff;
+struct nlmsghdr;
+struct sock;
+
+struct sock_diag_handler {
+ __u8 family;
+ int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh);
+};
+
+int sock_diag_register(struct sock_diag_handler *h);
+void sock_diag_unregister(struct sock_diag_handler *h);
+
+void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+
+int sock_diag_check_cookie(void *sk, __u32 *cookie);
+void sock_diag_save_cookie(void *sk, __u32 *cookie);
+
+int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
+
+extern struct sock *sock_diag_nlsk;
+#endif /* KERNEL */
+#endif
return true;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
const struct sockaddr *sap2)
{
struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst;
dsin6->sin6_family = ssin6->sin6_family;
- ipv6_addr_copy(&dsin6->sin6_addr, &ssin6->sin6_addr);
+ dsin6->sin6_addr = ssin6->sin6_addr;
return true;
}
-#else /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+#else /* !(IS_ENABLED(CONFIG_IPV6) */
static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
const struct sockaddr *sap2)
{
{
return false;
}
-#endif /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+#endif /* !(IS_ENABLED(CONFIG_IPV6) */
/**
* rpc_cmp_addr - compare the address portion of two sockaddrs.
u32 end_seq;
};
+/*These are used to set the sack_ok field in struct tcp_options_received */
+#define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
+#define TCP_FACK_ENABLED (1 << 1) /*1 = FACK is enabled locally*/
+#define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
+
struct tcp_options_received {
/* PAWS/RTTM data */
long ts_recent_stamp;/* Time we stored ts_recent (for aging) */
--- /dev/null
+#ifndef __UNIX_DIAG_H__
+#define __UNIX_DIAG_H__
+
+#include <linux/types.h>
+
+struct unix_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 udiag_states;
+ __u32 udiag_ino;
+ __u32 udiag_show;
+ __u32 udiag_cookie[2];
+};
+
+#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
+#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
+#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
+#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
+#define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */
+#define UDIAG_SHOW_MEMINFO 0x00000020 /* show memory info of a socket */
+
+struct unix_diag_msg {
+ __u8 udiag_family;
+ __u8 udiag_type;
+ __u8 udiag_state;
+ __u8 pad;
+
+ __u32 udiag_ino;
+ __u32 udiag_cookie[2];
+};
+
+enum {
+ UNIX_DIAG_NAME,
+ UNIX_DIAG_VFS,
+ UNIX_DIAG_PEER,
+ UNIX_DIAG_ICONS,
+ UNIX_DIAG_RQLEN,
+ UNIX_DIAG_MEMINFO,
+
+ UNIX_DIAG_MAX,
+};
+
+struct unix_diag_vfs {
+ __u32 udiag_vfs_ino;
+ __u32 udiag_vfs_dev;
+};
+
+struct unix_diag_rqlen {
+ __u32 udiag_rqueue;
+ __u32 udiag_wqueue;
+};
+
+#endif
* @reset: reset the device
* vdev: the virtio device
* After this, status and feature negotiation must be done again
+ * Device must not be reset from its vq/config callbacks, or in
+ * parallel with being added/removed.
* @find_vqs: find virtqueues and instantiate them.
* vdev: the virtio_device
* nvqs: the number of virtqueues to find
* vdev: the virtio_device
* This gives the final feature bits for the device: it can change
* the dev->feature bits if it wants.
+ * @bus_name: return the bus name associated with the device
+ * vdev: the virtio_device
+ * This returns a pointer to the bus name a la pci_name from which
+ * the caller can then copy.
*/
typedef void vq_callback_t(struct virtqueue *);
struct virtio_config_ops {
void (*del_vqs)(struct virtio_device *);
u32 (*get_features)(struct virtio_device *vdev);
void (*finalize_features)(struct virtio_device *vdev);
+ const char *(*bus_name)(struct virtio_device *vdev);
};
/* If driver didn't advertise the feature, it will never appear. */
return ERR_PTR(err);
return vq;
}
+
+static inline
+const char *virtio_bus_name(struct virtio_device *vdev)
+{
+ if (!vdev->config->bus_name)
+ return "virtio";
+ return vdev->config->bus_name(vdev);
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_VIRTIO_CONFIG_H */
#define VIRTIO_MMIO_GUEST_FEATURES 0x020
/* Activated features set selector - Write Only */
-#define VIRTIO_MMIO_GUEST_FEATURES_SET 0x024
+#define VIRTIO_MMIO_GUEST_FEATURES_SEL 0x024
/* Guest's memory page size in bytes - Write Only */
#define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028
#endif
/* Allocate/destroy a 'vmalloc' VM area. */
-extern struct vm_struct *alloc_vm_area(size_t size);
+extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
extern void free_vm_area(struct vm_struct *area);
/* for /dev/kmem */
static inline struct video_device *soc_camera_i2c_to_vdev(const struct i2c_client *client)
{
struct v4l2_subdev *sd = i2c_get_clientdata(client);
- struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id;
+ struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd);
return icd ? icd->vdev : NULL;
}
return container_of(vq, struct soc_camera_device, vb_vidq);
}
+static inline u32 soc_camera_grp_id(const struct soc_camera_device *icd)
+{
+ return (icd->iface << 8) | (icd->devnum + 1);
+}
+
void soc_camera_lock(struct vb2_queue *vq);
void soc_camera_unlock(struct vb2_queue *vq);
const struct in6_addr *src_addr);
extern int ipv6_is_mld(struct sk_buff *skb, int nexthdr);
-extern void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len);
+extern void addrconf_prefix_rcv(struct net_device *dev,
+ u8 *opt, int len, bool sllao);
/*
* anycast prototypes (anycast.c)
extern void unix_gc(void);
extern void wait_for_unix_gc(void);
extern struct sock *unix_get_socket(struct file *filp);
+extern struct sock *unix_peer_get(struct sock *);
#define UNIX_HASH_SIZE 256
extern unsigned int unix_tot_inflight;
+extern spinlock_t unix_table_lock;
+extern struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
struct unix_address {
atomic_t refcnt;
#define peer_wait peer_wq.wait
+long unix_inq_len(struct sock *sk);
+long unix_outq_len(struct sock *sk);
+
#ifdef CONFIG_SYSCTL
extern int unix_sysctl_register(struct net *net);
extern void unix_sysctl_unregister(struct net *net);
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- hash_val = arp_hashfn(key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+ hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift);
for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
n != NULL;
n = rcu_dereference_bh(n->next)) {
#define CLIP_VCC(vcc) ((struct clip_vcc *) ((vcc)->user_back))
-#define NEIGH2ENTRY(neigh) ((struct atmarp_entry *) (neigh)->primary_key)
struct sk_buff;
struct atmarp_entry {
- __be32 ip; /* IP address */
struct clip_vcc *vccs; /* active VCCs; NULL if resolution is
pending */
unsigned long expires; /* entry expiration time */
struct neighbour *neigh; /* neighbour back-pointer */
};
-
#define PRIV(dev) ((struct clip_priv *) netdev_priv(dev))
-
struct clip_priv {
int number; /* for convenience ... */
spinlock_t xoff_lock; /* ensures that pop is atomic (SMP) */
struct net_device *next; /* next CLIP interface */
};
-
-extern struct neigh_table *clip_tbl_hook;
-
#endif
return L2CAP_ENH_HDR_SIZE - L2CAP_HDR_SIZE;
}
-extern int disable_ertm;
+extern bool disable_ertm;
int l2cap_init_sockets(void);
void l2cap_cleanup_sockets(void);
#include <net/caif/caif_layer.h>
#include <net/caif/cfcnfg.h>
+#include <net/caif/caif_device.h>
#include <linux/caif/caif_socket.h>
#include <linux/if.h>
#include <linux/net.h>
*/
void caif_free_client(struct cflayer *adap_layer);
+/**
+ * struct caif_enroll_dev - Enroll a net-device as a CAIF Link layer
+ * @dev: Network device to enroll.
+ * @caifdev: Configuration information from CAIF Link Layer
+ * @link_support: Link layer support layer
+ * @head_room: Head room needed by link support layer
+ * @layer: Lowest layer in CAIF stack
+ * @rcv_fun: Receive function for CAIF stack.
+ *
+ * This function enroll a CAIF link layer into CAIF Stack and
+ * expects the interface to be able to handle CAIF payload.
+ * The link_support layer is used to add any Link Layer specific
+ * framing.
+ */
+void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+ struct cflayer *link_support, int head_room,
+ struct cflayer **layer, int (**rcv_func)(
+ struct sk_buff *, struct net_device *,
+ struct packet_type *, struct net_device *));
+
#endif /* CAIF_DEV_H_ */
* @transmit: Packet transmit funciton.
* @ctrlcmd: Used for control signalling upwards in the stack.
* @modemcmd: Used for control signaling downwards in the stack.
- * @prio: Priority of this layer.
* @id: The identity of this layer
- * @type: The type of this layer
* @name: Name of the layer.
*
* This structure defines the layered structure in CAIF.
*/
int (*modemcmd) (struct cflayer *layr, enum caif_modemcmd ctrl);
- unsigned short prio;
unsigned int id;
- unsigned int type;
char name[CAIF_LAYER_NAME_SZ];
};
struct cfspi_xfer {
u16 tx_dma_len;
u16 rx_dma_len;
- void *va_tx;
- dma_addr_t pa_tx;
+ void *va_tx[2];
+ dma_addr_t pa_tx[2];
void *va_rx;
dma_addr_t pa_rx;
};
struct cfcnfg;
-/**
- * enum cfcnfg_phy_type - Types of physical layers defined in CAIF Stack
- *
- * @CFPHYTYPE_FRAG: Fragmented frames physical interface.
- * @CFPHYTYPE_CAIF: Generic CAIF physical interface
- */
-enum cfcnfg_phy_type {
- CFPHYTYPE_FRAG = 1,
- CFPHYTYPE_CAIF,
- CFPHYTYPE_MAX
-};
-
/**
* enum cfcnfg_phy_preference - Physical preference HW Abstraction
*
* cfcnfg_add_phy_layer() - Adds a physical layer to the CAIF stack.
* @cnfg: Pointer to a CAIF configuration object, created by
* cfcnfg_create().
- * @phy_type: Specifies the type of physical interface, e.g.
- * CFPHYTYPE_FRAG.
* @dev: Pointer to link layer device
* @phy_layer: Specify the physical layer. The transmit function
* MUST be set in the structure.
* @pref: The phy (link layer) preference.
+ * @link_support: Protocol implementation for link layer specific protocol.
* @fcs: Specify if checksum is used in CAIF Framing Layer.
- * @stx: Specify if Start Of Frame eXtention is used.
+ * @head_room: Head space needed by link specific protocol.
*/
-
void
-cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type,
+cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
struct net_device *dev, struct cflayer *phy_layer,
enum cfcnfg_phy_preference pref,
- bool fcs, bool stx);
+ struct cflayer *link_support,
+ bool fcs, int head_room);
/**
* cfcnfg_del_phy_layer - Deletes an phy layer from the CAIF stack.
#define CFSERL_H_
#include <net/caif/caif_layer.h>
-struct cflayer *cfserl_create(int type, int instance, bool use_stx);
-#endif /* CFSERL_H_ */
+struct cflayer *cfserl_create(int instance, bool use_stx);
+#endif
#ifndef __LINUX_NET_DSA_H
#define __LINUX_NET_DSA_H
+#include <linux/if_ether.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+
#define DSA_MAX_SWITCHES 4
#define DSA_MAX_PORTS 12
struct dsa_chip_data *chip;
};
-extern bool dsa_uses_dsa_tags(void *dsa_ptr);
-extern bool dsa_uses_trailer_tags(void *dsa_ptr);
+struct dsa_switch_tree {
+ /*
+ * Configuration data for the platform device that owns
+ * this dsa switch tree instance.
+ */
+ struct dsa_platform_data *pd;
+
+ /*
+ * Reference to network device to use, and which tagging
+ * protocol to use.
+ */
+ struct net_device *master_netdev;
+ __be16 tag_protocol;
+
+ /*
+ * The switch and port to which the CPU is attached.
+ */
+ s8 cpu_switch;
+ s8 cpu_port;
+
+ /*
+ * Link state polling.
+ */
+ int link_poll_needed;
+ struct work_struct link_poll_work;
+ struct timer_list link_poll_timer;
+
+ /*
+ * Data for the individual switch chips.
+ */
+ struct dsa_switch *ds[DSA_MAX_SWITCHES];
+};
+
+struct dsa_switch {
+ /*
+ * Parent switch tree, and switch index.
+ */
+ struct dsa_switch_tree *dst;
+ int index;
+
+ /*
+ * Configuration data for this switch.
+ */
+ struct dsa_chip_data *pd;
+
+ /*
+ * The used switch driver.
+ */
+ struct dsa_switch_driver *drv;
+
+ /*
+ * Reference to mii bus to use.
+ */
+ struct mii_bus *master_mii_bus;
+
+ /*
+ * Slave mii_bus and devices for the individual ports.
+ */
+ u32 dsa_port_mask;
+ u32 phys_port_mask;
+ struct mii_bus *slave_mii_bus;
+ struct net_device *ports[DSA_MAX_PORTS];
+};
+
+static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
+{
+ return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
+}
+
+static inline u8 dsa_upstream_port(struct dsa_switch *ds)
+{
+ struct dsa_switch_tree *dst = ds->dst;
+
+ /*
+ * If this is the root switch (i.e. the switch that connects
+ * to the CPU), return the cpu port number on this switch.
+ * Else return the (DSA) port number that connects to the
+ * switch that is one hop closer to the cpu.
+ */
+ if (dst->cpu_switch == ds->index)
+ return dst->cpu_port;
+ else
+ return ds->pd->rtable[dst->cpu_switch];
+}
+
+struct dsa_switch_driver {
+ struct list_head list;
+
+ __be16 tag_protocol;
+ int priv_size;
+
+ /*
+ * Probing and setup.
+ */
+ char *(*probe)(struct mii_bus *bus, int sw_addr);
+ int (*setup)(struct dsa_switch *ds);
+ int (*set_addr)(struct dsa_switch *ds, u8 *addr);
+
+ /*
+ * Access to the switch's PHY registers.
+ */
+ int (*phy_read)(struct dsa_switch *ds, int port, int regnum);
+ int (*phy_write)(struct dsa_switch *ds, int port,
+ int regnum, u16 val);
+
+ /*
+ * Link state polling and IRQ handling.
+ */
+ void (*poll_link)(struct dsa_switch *ds);
+
+ /*
+ * ethtool hardware statistics.
+ */
+ void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
+ void (*get_ethtool_stats)(struct dsa_switch *ds,
+ int port, uint64_t *data);
+ int (*get_sset_count)(struct dsa_switch *ds);
+};
+
+void register_switch_driver(struct dsa_switch_driver *type);
+void unregister_switch_driver(struct dsa_switch_driver *type);
+
+/*
+ * The original DSA tag format and some other tag formats have no
+ * ethertype, which means that we need to add a little hack to the
+ * networking receive path to make sure that received frames get
+ * the right ->protocol assigned to them when one of those tag
+ * formats is in use.
+ */
+static inline bool dsa_uses_dsa_tags(struct dsa_switch_tree *dst)
+{
+ return !!(dst->tag_protocol == htons(ETH_P_DSA));
+}
+static inline bool dsa_uses_trailer_tags(struct dsa_switch_tree *dst)
+{
+ return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
+}
#endif
#define DST_NOHASH 0x0008
#define DST_NOCACHE 0x0010
#define DST_NOCOUNT 0x0020
+#define DST_NOPEER 0x0040
short error;
short obsolete;
};
};
-static inline struct neighbour *dst_get_neighbour(struct dst_entry *dst)
+static inline struct neighbour *dst_get_neighbour_noref(struct dst_entry *dst)
{
return rcu_dereference(dst->_neighbour);
}
-static inline struct neighbour *dst_get_neighbour_raw(struct dst_entry *dst)
+static inline struct neighbour *dst_get_neighbour_noref_raw(struct dst_entry *dst)
{
return rcu_dereference_raw(dst->_neighbour);
}
static inline u32 dst_mtu(const struct dst_entry *dst)
{
- u32 mtu = dst_metric_raw(dst, RTAX_MTU);
-
- if (!mtu)
- mtu = dst->ops->default_mtu(dst);
-
- return mtu;
+ return dst->ops->mtu(dst);
}
/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
struct neighbour *n;
rcu_read_lock();
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
neigh_confirm(n);
rcu_read_unlock();
}
int (*gc)(struct dst_ops *ops);
struct dst_entry * (*check)(struct dst_entry *, __u32 cookie);
unsigned int (*default_advmss)(const struct dst_entry *);
- unsigned int (*default_mtu)(const struct dst_entry *);
+ unsigned int (*mtu)(const struct dst_entry *);
u32 * (*cow_metrics)(struct dst_entry *, unsigned long);
void (*destroy)(struct dst_entry *);
void (*ifdown)(struct dst_entry *,
#define flowi4_proto __fl_common.flowic_proto
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
- __be32 daddr;
+
+ /* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
+ __be32 daddr;
+
union flowi_uli uli;
#define fl4_sport uli.ports.sport
#define fl4_dport uli.ports.dport
u8 dir, flow_resolve_t resolver, void *ctx);
extern void flow_cache_flush(void);
+extern void flow_cache_flush_deferred(void);
extern atomic_t flow_cache_genid;
#endif
--- /dev/null
+#ifndef _NET_FLOW_KEYS_H
+#define _NET_FLOW_KEYS_H
+
+struct flow_keys {
+ /* (src,dst) must be grouped, in the same way than in IP header */
+ __be32 src;
+ __be32 dst;
+ union {
+ __be32 ports;
+ __be16 port16[2];
+ };
+ u8 ip_proto;
+};
+
+extern bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
+#endif
struct genl_multicast_group *grp);
extern void genl_unregister_mc_group(struct genl_family *family,
struct genl_multicast_group *grp);
+extern void genl_notify(struct sk_buff *skb, struct net *net, u32 pid,
+ u32 group, struct nlmsghdr *nlh, gfp_t flags);
/**
* genlmsg_put - Add generic netlink header to netlink message
extern const struct icmp_err icmp_err_convert[];
#define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field)
#define ICMP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmp_statistics, field)
-#define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmpmsg_statistics, field+256)
-#define ICMPMSGIN_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmpmsg_statistics, field)
+#define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256)
+#define ICMPMSGIN_INC_STATS_BH(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field)
struct dst_entry;
struct net_proto_family;
* Maxim Gorbachyov <maxim.gorbachev@siemens.com>
* Maxim Osipov <maxim.osipov@siemens.com>
* Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
*/
#ifndef NET_IEEE802154_H
#define NET_IEEE802154_H
+#define IEEE802154_MTU 127
+
#define IEEE802154_FC_TYPE_BEACON 0x0 /* Frame is beacon */
#define IEEE802154_FC_TYPE_DATA 0x1 /* Frame is data */
#define IEEE802154_FC_TYPE_ACK 0x2 /* Frame is acknowledgment */
(((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT)
+/* MAC footer size */
+#define IEEE802154_MFR_SIZE 2 /* 2 octets */
+
/* MAC's Command Frames Identifiers */
#define IEEE802154_CMD_ASSOCIATION_REQ 0x01
#define IEEE802154_CMD_ASSOCIATION_RESP 0x02
#define _INET6_HASHTABLES_H
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/types.h>
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
const int dif);
-#endif /* defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
#endif /* _INET6_HASHTABLES_H */
return (void *)inet_csk(sk)->icsk_ca_priv;
}
-extern struct sock *inet_csk_clone(struct sock *sk,
- const struct request_sock *req,
- const gfp_t priority);
+extern struct sock *inet_csk_clone_lock(const struct sock *sk,
+ const struct request_sock *req,
+ const gfp_t priority);
enum inet_csk_ack_state_t {
ICSK_ACK_SCHED = 1,
/** struct ip_options - IP Options
*
* @faddr - Saved first hop address
+ * @nexthop - Saved nexthop address in LSRR and SSRR
* @is_data - Options in __data, rather than skb
* @is_strictroute - Strict source route
* @srr_is_hit - Packet destination addr was our one
*/
struct ip_options {
__be32 faddr;
+ __be32 nexthop;
unsigned char optlen;
unsigned char srr;
unsigned char rr;
struct inet_request_sock {
struct request_sock req;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
u16 inet6_rsk_offset;
#endif
__be16 loc_port;
struct inet_sock {
/* sk and pinet6 has to be the first two members of inet_sock */
struct sock sk;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct ipv6_pinfo *pinet6;
#endif
/* Socket demultiplex comparisons on incoming packets. */
memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
sk_from->sk_prot->obj_size - ancestor_size);
}
-#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE))
+#if !(IS_ENABLED(CONFIG_IPV6))
static inline void inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
static inline
struct net *twsk_net(const struct inet_timewait_sock *twsk)
{
-#ifdef CONFIG_NET_NS
- return rcu_dereference_raw(twsk->tw_net); /* protected by locking, */
- /* reference counting, */
- /* initialization, or RCU. */
-#else
- return &init_net;
-#endif
+ return read_pnet(&twsk->tw_net);
}
static inline
void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net)
{
-#ifdef CONFIG_NET_NS
- rcu_assign_pointer(twsk->tw_net, net);
-#endif
+ write_pnet(&twsk->tw_net, net);
}
#endif /* _INET_TIMEWAIT_SOCK_ */
u32 metrics[RTAX_MAX];
u32 rate_tokens; /* rate limiting for ICMP */
+ int redirect_genid;
unsigned long rate_last;
unsigned long pmtu_expires;
u32 pmtu_orig;
{
struct inetpeer_addr daddr;
- ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr);
+ *(struct in6_addr *)daddr.addr.a6 = *v6daddr;
daddr.family = AF_INET6;
return inet_getpeer(&daddr, create);
}
memcpy(buf, &naddr, sizeof(naddr));
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif
static __inline__ void inet_reset_saddr(struct sock *sk)
{
inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
switch (sk->sk_family) {
case AF_INET:
return inet_sk(sk)->mc_loop;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return inet6_sk(sk)->mc_loop;
#endif
* Functions provided by ip_sockglue.c
*/
-extern int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+extern void ipv4_pktinfo_prepare(struct sk_buff *skb);
extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
extern int ip_cmsg_send(struct net *net,
struct msghdr *msg, struct ipcm_cookie *ipc);
struct rt6_info {
struct dst_entry dst;
-#define rt6i_dev dst.dev
-#define rt6i_expires dst.expires
-
/*
* Tail elements of dst_entry (__refcnt etc.)
* and these elements (rarely used in hot path) are in
const struct in6_addr *daddr, int dst_len,
const struct in6_addr *saddr, int src_len);
+extern void fib6_clean_all_ro(struct net *net,
+ int (*func)(struct rt6_info *, void *arg),
+ int prune, void *arg);
+
extern void fib6_clean_all(struct net *net,
int (*func)(struct rt6_info *, void *arg),
int prune, void *arg);
extern struct dst_entry * ip6_route_output(struct net *net,
const struct sock *sk,
struct flowi6 *fl6);
+extern struct dst_entry * ip6_route_lookup(struct net *net,
+ struct flowi6 *fl6, int flags);
extern int ip6_route_init(void);
extern void ip6_route_cleanup(void);
extern struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct neighbour *neigh,
- const struct in6_addr *addr);
+ struct flowi6 *fl6);
extern int icmp6_dst_gc(void);
extern void fib6_force_start_gc(struct net *net);
extern struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr,
- int anycast);
+ bool anycast);
extern int ip6_dst_hoplimit(struct dst_entry *dst);
#include <linux/netfilter.h> /* for union nf_inet_addr */
#include <linux/ip.h>
#include <linux/ipv6.h> /* for struct ipv6hdr */
-#include <net/ipv6.h> /* for ipv6_addr_copy */
+#include <net/ipv6.h>
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netfilter/nf_conntrack.h>
#endif
const struct ipv6hdr *iph = nh;
iphdr->len = sizeof(struct ipv6hdr);
iphdr->protocol = iph->nexthdr;
- ipv6_addr_copy(&iphdr->saddr.in6, &iph->saddr);
- ipv6_addr_copy(&iphdr->daddr.in6, &iph->daddr);
+ iphdr->saddr.in6 = iph->saddr;
+ iphdr->daddr.in6 = iph->daddr;
} else
#endif
{
{
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
- ipv6_addr_copy(&dst->in6, &src->in6);
+ dst->in6 = src->in6;
else
#endif
dst->ip = src->ip;
extern struct ip_vs_dest *
ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
- __u16 protocol, __u32 fwmark);
+ __u16 protocol, __u32 fwmark, __u32 flags);
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\
})
+/* per device and per net counters are atomic_long_t */
+#define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \
+({ \
+ struct inet6_dev *_idev = (idev); \
+ if (likely(_idev != NULL)) \
+ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \
+ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\
+})
+
#define _DEVADD(net, statname, modifier, idev, field, val) \
({ \
struct inet6_dev *_idev = (idev); \
_DEVINCATOMIC(net, icmpv6, _BH, idev, field)
#define ICMP6MSGOUT_INC_STATS(net, idev, field) \
- _DEVINCATOMIC(net, icmpv6msg, , idev, field +256)
+ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256)
#define ICMP6MSGOUT_INC_STATS_BH(net, idev, field) \
- _DEVINCATOMIC(net, icmpv6msg, _BH, idev, field +256)
+ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256)
#define ICMP6MSGIN_INC_STATS_BH(net, idev, field) \
- _DEVINCATOMIC(net, icmpv6msg, _BH, idev, field)
+ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field)
struct ip6_ra_chain {
struct ip6_ra_chain *next;
((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3]));
}
-static inline void ipv6_addr_copy(struct in6_addr *a1, const struct in6_addr *a2)
-{
- memcpy(a1, a2, sizeof(struct in6_addr));
-}
-
static inline void ipv6_addr_prefix(struct in6_addr *pfx,
const struct in6_addr *addr,
int plen)
u8 *proto);
extern int ipv6_skip_exthdr(const struct sk_buff *, int start,
- u8 *nexthdrp);
+ u8 *nexthdrp, __be16 *frag_offp);
extern int ipv6_ext_hdr(u8 nexthdr);
IUCV_OPEN,
IUCV_BOUND,
IUCV_LISTEN,
- IUCV_SEVERED,
IUCV_DISCONN,
IUCV_CLOSING,
IUCV_CLOSED
poll_table *wait);
void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
-int iucv_sock_wait_cnt(struct sock *sk, unsigned long timeo);
void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
void iucv_accept_unlink(struct sock *sk);
struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock);
__u8 nd_opt_len;
} __packed;
+static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd)
+{
+ const u32 *p32 = pkey;
+
+ return (((p32[0] ^ dev->ifindex) * hash_rnd[0]) +
+ (p32[1] * hash_rnd[1]) +
+ (p32[2] * hash_rnd[2]) +
+ (p32[3] * hash_rnd[3]));
+}
+
+static inline struct neighbour *__ipv6_neigh_lookup(struct neigh_table *tbl, struct net_device *dev, const void *pkey)
+{
+ struct neigh_hash_table *nht;
+ const u32 *p32 = pkey;
+ struct neighbour *n;
+ u32 hash_val;
+
+ rcu_read_lock_bh();
+ nht = rcu_dereference_bh(tbl->nht);
+ hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+ for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
+ n != NULL;
+ n = rcu_dereference_bh(n->next)) {
+ u32 *n32 = (u32 *) n->primary_key;
+ if (n->dev == dev &&
+ ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) |
+ (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0) {
+ if (!atomic_inc_not_zero(&n->refcnt))
+ n = NULL;
+ break;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return n;
+}
extern int ndisc_init(void);
extern void inet6_ifinfo_notify(int event,
struct inet6_dev *idev);
-static inline struct neighbour * ndisc_get_neigh(struct net_device *dev, const struct in6_addr *addr)
-{
-
- if (dev)
- return __neigh_lookup_errno(&nd_tbl, addr, dev);
-
- return ERR_PTR(-ENODEV);
-}
-
#endif
int reachable_time;
int delay_probe_time;
- int queue_len;
+ int queue_len_bytes;
int ucast_probes;
int app_probes;
int mcast_probes;
rwlock_t lock;
atomic_t refcnt;
struct sk_buff_head arp_queue;
+ unsigned int arp_queue_len_bytes;
struct timer_list timer;
unsigned long used;
atomic_t probes;
* neighbour table manipulation
*/
+#define NEIGH_NUM_HASH_RND 4
+
struct neigh_hash_table {
struct neighbour __rcu **hash_buckets;
unsigned int hash_shift;
- __u32 hash_rnd;
+ __u32 hash_rnd[NEIGH_NUM_HASH_RND];
struct rcu_head rcu;
};
int key_len;
__u32 (*hash)(const void *pkey,
const struct net_device *dev,
- __u32 hash_rnd);
+ __u32 *hash_rnd);
int (*constructor)(struct neighbour *);
int (*pconstructor)(struct pneigh_entry *);
void (*pdestructor)(struct pneigh_entry *);
atomic_t entries;
rwlock_t lock;
unsigned long last_rand;
- struct kmem_cache *kmem_cachep;
struct neigh_statistics __percpu *stats;
struct neigh_hash_table __rcu *nht;
struct pneigh_entry **phash_buckets;
};
+#define NEIGH_PRIV_ALIGN sizeof(long long)
+
+static inline void *neighbour_priv(const struct neighbour *n)
+{
+ return (char *)n + ALIGN(sizeof(*n) + n->tbl->key_len, NEIGH_PRIV_ALIGN);
+}
+
/* flags for neigh_update() */
#define NEIGH_UPDATE_F_OVERRIDE 0x00000001
#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002
struct netns_packet packet;
struct netns_unix unx;
struct netns_ipv4 ipv4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netns_ipv6 ipv6;
#endif
#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
#include <net/netfilter/nf_conntrack_extend.h>
struct nf_conn_counter {
- u_int64_t packets;
- u_int64_t bytes;
+ atomic64_t packets;
+ atomic64_t bytes;
};
static inline
int (*fcn)(unsigned int events, struct nf_ct_event *item);
};
-extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
-extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
-extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
+extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb);
+extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb);
extern void nf_ct_deliver_cached_events(struct nf_conn *ct);
static inline void
nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
{
+ struct net *net = nf_ct_net(ct);
struct nf_conntrack_ecache *e;
- if (nf_conntrack_event_cb == NULL)
+ if (net->ct.nf_conntrack_event_cb == NULL)
return;
e = nf_ct_ecache_find(ct);
int report)
{
int ret = 0;
+ struct net *net = nf_ct_net(ct);
struct nf_ct_event_notifier *notify;
struct nf_conntrack_ecache *e;
rcu_read_lock();
- notify = rcu_dereference(nf_conntrack_event_cb);
+ notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
if (notify == NULL)
goto out_unlock;
int (*fcn)(unsigned int events, struct nf_exp_event *item);
};
-extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
-extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
-extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
+extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb);
+extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb);
static inline void
nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
u32 pid,
int report)
{
+ struct net *net = nf_ct_exp_net(exp);
struct nf_exp_event_notifier *notify;
struct nf_conntrack_ecache *e;
rcu_read_lock();
- notify = rcu_dereference(nf_expect_event_cb);
+ notify = rcu_dereference(net->ct.nf_expect_event_cb);
if (notify == NULL)
goto out_unlock;
void nf_ct_remove_expectations(struct nf_conn *ct);
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp);
-void nf_ct_remove_userspace_expectations(void);
/* Allocate space for an expectation: this is mandatory before calling
nf_ct_expect_related. You will have to call put afterwards. */
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
-#include <linux/netfilter_ipv4/nf_nat.h>
#include <linux/list_nulls.h>
/* A `tuple' is a structure containing the information to uniquely
#ifndef _NF_NAT_H
#define _NF_NAT_H
#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter_ipv4/nf_nat.h>
+#include <linux/netfilter/nf_nat.h>
#include <net/netfilter/nf_conntrack_tuple.h>
-#define NF_NAT_MAPPING_TYPE_MAX_NAMELEN 16
-
enum nf_nat_manip_type {
- IP_NAT_MANIP_SRC,
- IP_NAT_MANIP_DST
+ NF_NAT_MANIP_SRC,
+ NF_NAT_MANIP_DST
};
/* SRC manip occurs POST_ROUTING or LOCAL_IN */
/* Set up the info structure to map into this range. */
extern unsigned int nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype);
/* Is this tuple already taken? (not by us)*/
static inline int nf_nat_initialized(struct nf_conn *ct,
enum nf_nat_manip_type manip)
{
- if (manip == IP_NAT_MANIP_SRC)
+ if (manip == NF_NAT_MANIP_SRC)
return ct->status & IPS_SRC_NAT_DONE;
else
return ct->status & IPS_DST_NAT_DONE;
#include <net/netfilter/nf_nat.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
-struct nf_nat_range;
+struct nf_nat_ipv4_range;
struct nf_nat_protocol {
/* Protocol number. */
unsigned int protonum;
- struct module *me;
-
/* Translate a packet to the target according to manip type.
Return true if succeeded. */
bool (*manip_pkt)(struct sk_buff *skb,
possible. Per-protocol part of tuple is initialized to the
incoming packet. */
void (*unique_tuple)(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct);
- int (*range_to_nlattr)(struct sk_buff *skb,
- const struct nf_nat_range *range);
-
int (*nlattr_to_range)(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_ipv4_range *range);
};
/* Protocol registration. */
const union nf_conntrack_man_proto *max);
extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u_int16_t *rover);
-extern int nf_nat_proto_range_to_nlattr(struct sk_buff *skb,
- const struct nf_nat_range *range);
extern int nf_nat_proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_ipv4_range *range);
#endif /*_NF_NAT_PROTO_H*/
return sk;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline struct sock *
nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
const struct in6_addr *saddr, const struct in6_addr *daddr,
struct hlist_nulls_head unconfirmed;
struct hlist_nulls_head dying;
struct ip_conntrack_stat __percpu *stat;
+ struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
+ struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
int sysctl_events;
unsigned int sysctl_events_retry_timeout;
int sysctl_acct;
int current_rt_cache_rebuild_count;
unsigned int sysctl_ping_group_range[2];
+ long sysctl_tcp_mem[3];
atomic_t rt_genid;
atomic_t dev_addr_genid;
DEFINE_SNMP_STAT(struct udp_mib, udp_statistics);
DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics);
DEFINE_SNMP_STAT(struct icmp_mib, icmp_statistics);
- DEFINE_SNMP_STAT(struct icmpmsg_mib, icmpmsg_statistics);
+ DEFINE_SNMP_STAT_ATOMIC(struct icmpmsg_mib, icmpmsg_statistics);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct proc_dir_entry *proc_net_devsnmp6;
DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6);
DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6);
DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics);
DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics);
- DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics);
+ DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib, icmpv6msg_statistics);
#endif
#ifdef CONFIG_XFRM_STATISTICS
DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics);
#endif
struct dst_ops xfrm4_dst_ops;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct dst_ops xfrm6_dst_ops;
#endif
};
--- /dev/null
+/*
+ * netprio_cgroup.h Control Group Priority set
+ *
+ *
+ * Authors: Neil Horman <nhorman@tuxdriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _NETPRIO_CGROUP_H
+#define _NETPRIO_CGROUP_H
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
+
+
+struct netprio_map {
+ struct rcu_head rcu;
+ u32 priomap_len;
+ u32 priomap[];
+};
+
+#ifdef CONFIG_CGROUPS
+
+struct cgroup_netprio_state {
+ struct cgroup_subsys_state css;
+ u32 prioidx;
+};
+
+#ifndef CONFIG_NETPRIO_CGROUP
+extern int net_prio_subsys_id;
+#endif
+
+extern void sock_update_netprioidx(struct sock *sk);
+
+static inline struct cgroup_netprio_state
+ *task_netprio_state(struct task_struct *p)
+{
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+ return container_of(task_subsys_state(p, net_prio_subsys_id),
+ struct cgroup_netprio_state, css);
+#else
+ return NULL;
+#endif
+}
+
+#else
+
+#define sock_update_netprioidx(sk)
+#endif
+
+#endif /* _NET_CLS_CGROUP_H */
#define _PROTOCOL_H
#include <linux/in6.h>
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif
void (*err_handler)(struct sk_buff *skb, u32 info);
int (*gso_send_check)(struct sk_buff *skb);
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
- u32 features);
+ netdev_features_t features);
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb);
netns_ok:1;
};
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_protocol {
int (*handler)(struct sk_buff *skb);
int (*gso_send_check)(struct sk_buff *skb);
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
- u32 features);
+ netdev_features_t features);
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb);
extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
#endif
extern void inet_register_protosw(struct inet_protosw *p);
extern void inet_unregister_protosw(struct inet_protosw *p);
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
extern int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
extern int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
extern int inet6_register_protosw(struct inet_protosw *p);
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
#include <net/dsfield.h>
+#include <linux/reciprocal_div.h>
/* Random Early Detection (RED) algorithm.
=======================================
etc.
*/
+/*
+ * Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM
+ * (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001
+ *
+ * Every 500 ms:
+ * if (avg > target and max_p <= 0.5)
+ * increase max_p : max_p += alpha;
+ * else if (avg < target and max_p >= 0.01)
+ * decrease max_p : max_p *= beta;
+ *
+ * target :[qth_min + 0.4*(qth_min - qth_max),
+ * qth_min + 0.6*(qth_min - qth_max)].
+ * alpha : min(0.01, max_p / 4)
+ * beta : 0.9
+ * max_P is a Q0.32 fixed point number (with 32 bits mantissa)
+ * max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ]
+ */
+#define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100))
+
+#define MAX_P_MIN (1 * RED_ONE_PERCENT)
+#define MAX_P_MAX (50 * RED_ONE_PERCENT)
+#define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4)
+
#define RED_STAB_SIZE 256
#define RED_STAB_MASK (RED_STAB_SIZE - 1)
struct red_parms {
/* Parameters */
- u32 qth_min; /* Min avg length threshold: A scaled */
- u32 qth_max; /* Max avg length threshold: A scaled */
+ u32 qth_min; /* Min avg length threshold: Wlog scaled */
+ u32 qth_max; /* Max avg length threshold: Wlog scaled */
u32 Scell_max;
- u32 Rmask; /* Cached random mask, see red_rmask */
+ u32 max_P; /* probability, [0 .. 1.0] 32 scaled */
+ u32 max_P_reciprocal; /* reciprocal_value(max_P / qth_delta) */
+ u32 qth_delta; /* max_th - min_th */
+ u32 target_min; /* min_th + 0.4*(max_th - min_th) */
+ u32 target_max; /* min_th + 0.6*(max_th - min_th) */
u8 Scell_log;
u8 Wlog; /* log(W) */
u8 Plog; /* random number bits */
number generation */
u32 qR; /* Cached random number */
- unsigned long qavg; /* Average queue length: A scaled */
- psched_time_t qidlestart; /* Start of current idle period */
+ unsigned long qavg; /* Average queue length: Wlog scaled */
+ ktime_t qidlestart; /* Start of current idle period */
};
-static inline u32 red_rmask(u8 Plog)
+static inline u32 red_maxp(u8 Plog)
{
- return Plog < 32 ? ((1 << Plog) - 1) : ~0UL;
+ return Plog < 32 ? (~0U >> Plog) : ~0U;
}
+
static inline void red_set_parms(struct red_parms *p,
u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog,
- u8 Scell_log, u8 *stab)
+ u8 Scell_log, u8 *stab, u32 max_P)
{
+ int delta = qth_max - qth_min;
+ u32 max_p_delta;
+
/* Reset average queue length, the value is strictly bound
* to the parameters below, reseting hurts a bit but leaving
* it might result in an unreasonable qavg for a while. --TGR
p->qth_max = qth_max << Wlog;
p->Wlog = Wlog;
p->Plog = Plog;
- p->Rmask = red_rmask(Plog);
+ if (delta < 0)
+ delta = 1;
+ p->qth_delta = delta;
+ if (!max_P) {
+ max_P = red_maxp(Plog);
+ max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */
+ }
+ p->max_P = max_P;
+ max_p_delta = max_P / delta;
+ max_p_delta = max(max_p_delta, 1U);
+ p->max_P_reciprocal = reciprocal_value(max_p_delta);
+
+ /* RED Adaptative target :
+ * [min_th + 0.4*(min_th - max_th),
+ * min_th + 0.6*(min_th - max_th)].
+ */
+ delta /= 5;
+ p->target_min = qth_min + 2*delta;
+ p->target_max = qth_min + 3*delta;
+
p->Scell_log = Scell_log;
p->Scell_max = (255 << Scell_log);
memcpy(p->Stab, stab, sizeof(p->Stab));
}
-static inline int red_is_idling(struct red_parms *p)
+static inline int red_is_idling(const struct red_parms *p)
{
- return p->qidlestart != PSCHED_PASTPERFECT;
+ return p->qidlestart.tv64 != 0;
}
static inline void red_start_of_idle_period(struct red_parms *p)
{
- p->qidlestart = psched_get_time();
+ p->qidlestart = ktime_get();
}
static inline void red_end_of_idle_period(struct red_parms *p)
{
- p->qidlestart = PSCHED_PASTPERFECT;
+ p->qidlestart.tv64 = 0;
}
static inline void red_restart(struct red_parms *p)
p->qcount = -1;
}
-static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p)
+static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p)
{
- psched_time_t now;
- long us_idle;
+ s64 delta = ktime_us_delta(ktime_get(), p->qidlestart);
+ long us_idle = min_t(s64, delta, p->Scell_max);
int shift;
- now = psched_get_time();
- us_idle = psched_tdiff_bounded(now, p->qidlestart, p->Scell_max);
-
/*
* The problem: ideally, average length queue recalcultion should
* be done over constant clock intervals. This is too expensive, so
}
}
-static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p,
+static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p,
unsigned int backlog)
{
/*
return p->qavg + (backlog - (p->qavg >> p->Wlog));
}
-static inline unsigned long red_calc_qavg(struct red_parms *p,
+static inline unsigned long red_calc_qavg(const struct red_parms *p,
unsigned int backlog)
{
if (!red_is_idling(p))
return red_calc_qavg_from_idle_time(p);
}
-static inline u32 red_random(struct red_parms *p)
+
+static inline u32 red_random(const struct red_parms *p)
{
- return net_random() & p->Rmask;
+ return reciprocal_divide(net_random(), p->max_P_reciprocal);
}
-static inline int red_mark_probability(struct red_parms *p, unsigned long qavg)
+static inline int red_mark_probability(const struct red_parms *p, unsigned long qavg)
{
/* The formula used below causes questions.
- OK. qR is random number in the interval 0..Rmask
+ OK. qR is random number in the interval
+ (0..1/max_P)*(qth_max-qth_min)
i.e. 0..(2^Plog). If we used floating point
arithmetics, it would be: (2^Plog)*rnd_num,
where rnd_num is less 1.
Taking into account, that qavg have fixed
- point at Wlog, and Plog is related to max_P by
- max_P = (qth_max-qth_min)/2^Plog; two lines
+ point at Wlog, two lines
below have the following floating point equivalent:
max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount
return RED_DONT_MARK;
}
+static inline void red_adaptative_algo(struct red_parms *p)
+{
+ unsigned long qavg;
+ u32 max_p_delta;
+
+ qavg = p->qavg;
+ if (red_is_idling(p))
+ qavg = red_calc_qavg_from_idle_time(p);
+
+ /* p->qavg is fixed point number with point at Wlog */
+ qavg >>= p->Wlog;
+
+ if (qavg > p->target_max && p->max_P <= MAX_P_MAX)
+ p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */
+ else if (qavg < p->target_min && p->max_P >= MAX_P_MIN)
+ p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */
+
+ max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta);
+ max_p_delta = max(max_p_delta, 1U);
+ p->max_P_reciprocal = reciprocal_value(max_p_delta);
+}
#endif
struct fib_info *fi; /* for client ref to shared metrics */
};
-static inline bool rt_is_input_route(struct rtable *rt)
+static inline bool rt_is_input_route(const struct rtable *rt)
{
return rt->rt_route_iif != 0;
}
-static inline bool rt_is_output_route(struct rtable *rt)
+static inline bool rt_is_output_route(const struct rtable *rt)
{
return rt->rt_route_iif == 0;
}
#include <linux/jiffies.h>
#include <linux/idr.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_route.h>
#endif
/* Size of Supported Address Parameter for 'x' address types. */
#define SCTP_SAT_LEN(x) (sizeof(struct sctp_paramhdr) + (x) * sizeof(__u16))
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
void sctp_v6_pf_init(void);
void sctp_v6_pf_exit(void);
/* Flag to indicate whether computing and verifying checksum
* is disabled. */
- int checksum_disable;
+ bool checksum_disable;
/* Threshold for rwnd update SACKS. Receive buffer shifted this many
* bits is an indicator of when to send and window update SACK.
*/
int rwnd_update_shift;
+
+ /* Threshold for autoclose timeout, in seconds. */
+ unsigned long max_autoclose;
} sctp_globals;
#define sctp_rto_initial (sctp_globals.rto_initial)
#define sctp_auth_enable (sctp_globals.auth_enable)
#define sctp_checksum_disable (sctp_globals.checksum_disable)
#define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift)
+#define sctp_max_autoclose (sctp_globals.max_autoclose)
/* SCTP Socket type: UDP or TCP style. */
typedef enum {
return (struct sock *)sp;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct sctp6_sock {
struct sctp_sock sctp;
struct ipv6_pinfo inet6;
unsigned long sctp_transport_timeout(struct sctp_transport *);
void sctp_transport_reset(struct sctp_transport *);
void sctp_transport_update_pmtu(struct sctp_transport *, u32);
+void sctp_transport_immediate_rtx(struct sctp_transport *);
/* This is the structure we use to queue packets as they come into
#define ICMPMSG_MIB_MAX __ICMPMSG_MIB_MAX
struct icmpmsg_mib {
- unsigned long mibs[ICMPMSG_MIB_MAX];
+ atomic_long_t mibs[ICMPMSG_MIB_MAX];
};
/* ICMP6 (IPv6-ICMP) */
#define ICMP6MSG_MIB_MAX __ICMP6MSG_MIB_MAX
/* per network ns counters */
struct icmpv6msg_mib {
- unsigned long mibs[ICMP6MSG_MIB_MAX];
+ atomic_long_t mibs[ICMP6MSG_MIB_MAX];
};
/* per device counters, (shared on all cpus) */
struct icmpv6msg_mib_device {
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/memcontrol.h>
+#include <linux/res_counter.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <net/dst.h>
#include <net/checksum.h>
+struct cgroup;
+struct cgroup_subsys;
+#ifdef CONFIG_NET
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss);
+#else
+static inline
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ return 0;
+}
+static inline
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+}
+#endif
/*
* This structure really needs to be cleaned up.
* Most of it is for TCP, and not used by any of
/* public: */
};
+struct cg_proto;
/**
* struct sock - network layer representation of sockets
* @__sk_common: shared layout with inet_timewait_sock
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_classid: this socket's cgroup classid
+ * @sk_cgrp: this socket's cgroup-specific proto data
* @sk_write_pending: a write to stream socket waits to start
* @sk_state_change: callback to indicate change in the state of the sock
* @sk_data_ready: callback to indicate there is data to be processed
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
- int sk_route_caps;
- int sk_route_nocaps;
+ netdev_features_t sk_route_caps;
+ netdev_features_t sk_route_nocaps;
int sk_gso_type;
unsigned int sk_gso_max_size;
int sk_rcvlowat;
unsigned short sk_ack_backlog;
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
+#ifdef CONFIG_CGROUPS
+ __u32 sk_cgrp_prioidx;
+#endif
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
#endif
__u32 sk_mark;
u32 sk_classid;
+ struct cg_proto *sk_cgrp;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk, int bytes);
void (*sk_write_space)(struct sock *sk);
/*
* Take into account size of receive queue and backlog queue
+ * Do not take into account this skb truesize,
+ * to allow even a single big packet to come.
*/
static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb)
{
unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
- return qsize + skb->truesize > sk->sk_rcvbuf;
+ return qsize > sk->sk_rcvbuf;
}
/* The per-socket spinlock must be held here. */
#ifdef SOCK_REFCNT_DEBUG
atomic_t socks;
#endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ /*
+ * cgroup specific init/deinit functions. Called once for all
+ * protocols that implement it, from cgroups populate function.
+ * This function has to setup any files the protocol want to
+ * appear in the kmem cgroup filesystem.
+ */
+ int (*init_cgroup)(struct cgroup *cgrp,
+ struct cgroup_subsys *ss);
+ void (*destroy_cgroup)(struct cgroup *cgrp,
+ struct cgroup_subsys *ss);
+ struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
+#endif
+};
+
+struct cg_proto {
+ void (*enter_memory_pressure)(struct sock *sk);
+ struct res_counter *memory_allocated; /* Current allocated memory. */
+ struct percpu_counter *sockets_allocated; /* Current number of sockets. */
+ int *memory_pressure;
+ long *sysctl_mem;
+ /*
+ * memcg field is used to find which memcg we belong directly
+ * Each memcg struct can hold more than one cg_proto, so container_of
+ * won't really cut.
+ *
+ * The elegant solution would be having an inverse function to
+ * proto_cgroup in struct proto, but that means polluting the structure
+ * for everybody, instead of just for memcg users.
+ */
+ struct mem_cgroup *memcg;
};
extern int proto_register(struct proto *prot, int alloc_slab);
sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}
-static inline void sk_refcnt_debug_release(const struct sock *sk)
+inline void sk_refcnt_debug_release(const struct sock *sk)
{
if (atomic_read(&sk->sk_refcnt) != 1)
printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+extern struct jump_label_key memcg_socket_limit_enabled;
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+ struct cg_proto *cg_proto)
+{
+ return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
+}
+#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
+#else
+#define mem_cgroup_sockets_enabled 0
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+ struct cg_proto *cg_proto)
+{
+ return NULL;
+}
+#endif
+
+
+static inline bool sk_has_memory_pressure(const struct sock *sk)
+{
+ return sk->sk_prot->memory_pressure != NULL;
+}
+
+static inline bool sk_under_memory_pressure(const struct sock *sk)
+{
+ if (!sk->sk_prot->memory_pressure)
+ return false;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+ return !!*sk->sk_cgrp->memory_pressure;
+
+ return !!*sk->sk_prot->memory_pressure;
+}
+
+static inline void sk_leave_memory_pressure(struct sock *sk)
+{
+ int *memory_pressure = sk->sk_prot->memory_pressure;
+
+ if (!memory_pressure)
+ return;
+
+ if (*memory_pressure)
+ *memory_pressure = 0;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+ struct cg_proto *cg_proto = sk->sk_cgrp;
+ struct proto *prot = sk->sk_prot;
+
+ for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+ if (*cg_proto->memory_pressure)
+ *cg_proto->memory_pressure = 0;
+ }
+
+}
+
+static inline void sk_enter_memory_pressure(struct sock *sk)
+{
+ if (!sk->sk_prot->enter_memory_pressure)
+ return;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+ struct cg_proto *cg_proto = sk->sk_cgrp;
+ struct proto *prot = sk->sk_prot;
+
+ for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+ cg_proto->enter_memory_pressure(sk);
+ }
+
+ sk->sk_prot->enter_memory_pressure(sk);
+}
+
+static inline long sk_prot_mem_limits(const struct sock *sk, int index)
+{
+ long *prot = sk->sk_prot->sysctl_mem;
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+ prot = sk->sk_cgrp->sysctl_mem;
+ return prot[index];
+}
+
+static inline void memcg_memory_allocated_add(struct cg_proto *prot,
+ unsigned long amt,
+ int *parent_status)
+{
+ struct res_counter *fail;
+ int ret;
+
+ ret = res_counter_charge(prot->memory_allocated,
+ amt << PAGE_SHIFT, &fail);
+
+ if (ret < 0)
+ *parent_status = OVER_LIMIT;
+}
+
+static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
+ unsigned long amt)
+{
+ res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+}
+
+static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
+{
+ u64 ret;
+ ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
+ return ret >> PAGE_SHIFT;
+}
+
+static inline long
+sk_memory_allocated(const struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+ return memcg_memory_allocated_read(sk->sk_cgrp);
+
+ return atomic_long_read(prot->memory_allocated);
+}
+
+static inline long
+sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
+{
+ struct proto *prot = sk->sk_prot;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+ memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
+ /* update the root cgroup regardless */
+ atomic_long_add_return(amt, prot->memory_allocated);
+ return memcg_memory_allocated_read(sk->sk_cgrp);
+ }
+
+ return atomic_long_add_return(amt, prot->memory_allocated);
+}
+
+static inline void
+sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status)
+{
+ struct proto *prot = sk->sk_prot;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp &&
+ parent_status != OVER_LIMIT) /* Otherwise was uncharged already */
+ memcg_memory_allocated_sub(sk->sk_cgrp, amt);
+
+ atomic_long_sub(amt, prot->memory_allocated);
+}
+
+static inline void sk_sockets_allocated_dec(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+ struct cg_proto *cg_proto = sk->sk_cgrp;
+
+ for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+ percpu_counter_dec(cg_proto->sockets_allocated);
+ }
+
+ percpu_counter_dec(prot->sockets_allocated);
+}
+
+static inline void sk_sockets_allocated_inc(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+ struct cg_proto *cg_proto = sk->sk_cgrp;
+
+ for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+ percpu_counter_inc(cg_proto->sockets_allocated);
+ }
+
+ percpu_counter_inc(prot->sockets_allocated);
+}
+
+static inline int
+sk_sockets_allocated_read_positive(struct sock *sk)
+{
+ struct proto *prot = sk->sk_prot;
+
+ if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+ return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated);
+
+ return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline int
+proto_sockets_allocated_sum_positive(struct proto *prot)
+{
+ return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline long
+proto_memory_allocated(struct proto *prot)
+{
+ return atomic_long_read(prot->memory_allocated);
+}
+
+static inline bool
+proto_memory_pressure(struct proto *prot)
+{
+ if (!prot->memory_pressure)
+ return false;
+ return !!*prot->memory_pressure;
+}
+
#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
struct proto *prot);
extern void sk_free(struct sock *sk);
extern void sk_release_kernel(struct sock *sk);
-extern struct sock *sk_clone(const struct sock *sk,
- const gfp_t priority);
+extern struct sock *sk_clone_lock(const struct sock *sk,
+ const gfp_t priority);
extern struct sk_buff *sock_wmalloc(struct sock *sk,
unsigned long size, int force,
extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
-static inline void sk_nocaps_add(struct sock *sk, int flags)
+static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
{
sk->sk_route_nocaps |= flags;
sk->sk_route_caps &= ~flags;
page = alloc_pages(sk->sk_allocation, 0);
if (!page) {
- sk->sk_prot->enter_memory_pressure(sk);
+ sk_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
}
return page;
#include <net/dst.h>
#include <linux/seq_file.h>
+#include <linux/memcontrol.h>
extern struct inet_hashinfo tcp_hashinfo;
extern int sysctl_tcp_reordering;
extern int sysctl_tcp_ecn;
extern int sysctl_tcp_dsack;
-extern long sysctl_tcp_mem[3];
extern int sysctl_tcp_wmem[3];
extern int sysctl_tcp_rmem[3];
extern int sysctl_tcp_app_win;
}
if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
- atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
+ sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
return true;
return false;
}
struct tcp_skb_cb {
union {
struct inet_skb_parm h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header; /* For incoming frames */
static inline int tcp_is_fack(const struct tcp_sock *tp)
{
- return tp->rx_opt.sack_ok & 2;
+ return tp->rx_opt.sack_ok & TCP_FACK_ENABLED;
}
static inline void tcp_enable_fack(struct tcp_sock *tp)
{
- tp->rx_opt.sack_ok |= 2;
+ tp->rx_opt.sack_ok |= TCP_FACK_ENABLED;
}
static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
extern __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);
+/* The maximum number of MSS of available cwnd for which TSO defers
+ * sending if not using sysctl_tcp_tso_win_divisor.
+ */
+static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp)
+{
+ return 3;
+}
+
/* Slow start with delack produces 3 packets of burst, so that
* it is safe "de facto". This will be the default - same as
* the default reordering threshold - but if reordering increases,
/* - sock block */
struct tcp_md5sig_info {
struct tcp4_md5sig_key *keys4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct tcp6_md5sig_key *keys6;
u32 entries6;
u32 alloced6;
union tcp_md5sum_block {
struct tcp4_pseudohdr ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct tcp6_pseudohdr ip6;
#endif
};
extern void tcp_v4_destroy_sock(struct sock *sk);
extern int tcp_v4_gso_send_check(struct sk_buff *skb);
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+ netdev_features_t features);
extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
struct sk_buff *skb);
extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
--- /dev/null
+#ifndef _TCP_MEMCG_H
+#define _TCP_MEMCG_H
+
+struct tcp_memcontrol {
+ struct cg_proto cg_proto;
+ /* per-cgroup tcp memory pressure knobs */
+ struct res_counter tcp_memory_allocated;
+ struct percpu_counter tcp_sockets_allocated;
+ /* those two are read-mostly, leave them at the end */
+ long tcp_prot_mem[3];
+ int tcp_memory_pressure;
+};
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
+int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
+void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
+#endif /* _TCP_MEMCG_H */
struct udp_skb_cb {
union {
struct inet_skb_parm h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header;
extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport,
int dif);
+extern struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+ __be32 daddr, __be16 dport,
+ int dif, struct udp_table *tbl);
extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif);
+extern struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, __be16 dport,
+ int dif, struct udp_table *tbl);
/*
* SNMP statistics for UDP and UDP-Lite
else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \
} while(0)
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#define UDPX_INC_STATS_BH(sk, field) \
do { \
if ((sk)->sk_family == AF_INET) \
extern void udp_init(void);
extern int udp4_ufo_send_check(struct sk_buff *skb);
-extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features);
#endif /* _UDP_H */
return true;
}
+static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen)
+{
+ /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */
+ if (prefixlen == 0)
+ return true;
+ return !((a1 ^ a2) & htonl(0xFFFFFFFFu << (32 - prefixlen)));
+}
+
static __inline__
__be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli)
{
memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4));
break;
case AF_INET6:
- ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->u.ip6.saddr);
- ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->u.ip6.daddr);
+ *(struct in6_addr *)saddr->a6 = fl->u.ip6.saddr;
+ *(struct in6_addr *)daddr->a6 = fl->u.ip6.daddr;
break;
}
}
u8 map_dest;
u8 spma;
u8 probe_tries;
+ u8 priority;
u8 dest_addr[ETH_ALEN];
u8 ctl_src_addr[ETH_ALEN];
* @lport: The associated local port
* @fcoe_pending_queue: The pending Rx queue of skbs
* @fcoe_pending_queue_active: Indicates if the pending queue is active
+ * @priority: Packet priority (DCB)
* @max_queue_depth: Max queue depth of pending queue
* @min_queue_depth: Min queue depth of pending queue
* @timer: The queue timer
struct fc_lport *lport;
struct sk_buff_head fcoe_pending_queue;
u8 fcoe_pending_queue_active;
+ u8 priority;
u32 max_queue_depth;
u32 min_queue_depth;
struct timer_list timer;
SCF_SCSI_NON_DATA_CDB = 0x00000040,
SCF_SCSI_CDB_EXCEPTION = 0x00000080,
SCF_SCSI_RESERVATION_CONFLICT = 0x00000100,
- SCF_SE_CMD_FAILED = 0x00000400,
+ SCF_FUA = 0x00000200,
SCF_SE_LUN_CMD = 0x00000800,
SCF_SE_ALLOW_EOO = 0x00001000,
+ SCF_BIDI = 0x00002000,
SCF_SENT_CHECK_CONDITION = 0x00004000,
SCF_OVERFLOW_BIT = 0x00008000,
SCF_UNDERFLOW_BIT = 0x00010000,
TCM_CHECK_CONDITION_ABORT_CMD = 0x0d,
TCM_CHECK_CONDITION_UNIT_ATTENTION = 0x0e,
TCM_CHECK_CONDITION_NOT_READY = 0x0f,
+ TCM_RESERVATION_CONFLICT = 0x10,
};
struct se_obj {
u16 lu_gp_id;
int lu_gp_valid_id;
u32 lu_gp_members;
- atomic_t lu_gp_shutdown;
atomic_t lu_gp_ref_cnt;
spinlock_t lu_gp_lock;
struct config_group lu_gp_group;
int sam_task_attr;
/* Transport protocol dependent state, see transport_state_table */
enum transport_state_table t_state;
- /* Transport specific error status */
- int transport_error_status;
/* Used to signal cmd->se_tfo->check_release_cmd() usage per cmd */
- int check_release:1;
- int cmd_wait_set:1;
+ unsigned check_release:1;
+ unsigned cmd_wait_set:1;
/* See se_cmd_flags_table */
u32 se_cmd_flags;
u32 se_ordered_id;
/* Used for sense data */
void *sense_buffer;
struct list_head se_delayed_node;
- struct list_head se_ordered_node;
struct list_head se_lun_node;
struct list_head se_qf_node;
struct se_device *se_dev;
struct se_dev_entry *se_deve;
- struct se_device *se_obj_ptr;
- struct se_device *se_orig_obj_ptr;
struct se_lun *se_lun;
/* Only used for internal passthrough and legacy TCM fabric modules */
struct se_session *se_sess;
unsigned char __t_task_cdb[TCM_MAX_COMMAND_SIZE];
unsigned long long t_task_lba;
int t_tasks_failed;
- int t_tasks_fua;
- bool t_tasks_bidi;
u32 t_tasks_sg_chained_no;
atomic_t t_fe_count;
atomic_t t_se_count;
struct work_struct work;
- /*
- * Used for pre-registered fabric SGL passthrough WRITE and READ
- * with the special SCF_PASSTHROUGH_CONTIG_TO_SG case for TCM_Loop
- * and other HW target mode fabric modules.
- */
- struct scatterlist *t_task_pt_sgl;
- u32 t_task_pt_sgl_num;
-
struct scatterlist *t_data_sg;
unsigned int t_data_nents;
struct scatterlist *t_bidi_data_sg;
} ____cacheline_aligned;
struct se_session {
- int sess_tearing_down:1;
+ unsigned sess_tearing_down:1;
u64 sess_bin_isid;
struct se_node_acl *se_node_acl;
struct se_portal_group *se_tpg;
struct t10_reservation t10_pr;
spinlock_t se_dev_lock;
void *se_dev_su_ptr;
- struct list_head se_dev_node;
struct config_group se_dev_group;
/* For T10 Reservations */
struct config_group se_dev_pr_group;
} ____cacheline_aligned;
struct se_device {
- /* Set to 1 if thread is NOT sleeping on thread_sem */
- u8 thread_active;
- u8 dev_status_timer_flags;
/* RELATIVE TARGET PORT IDENTIFER Counter */
u16 dev_rpti_counter;
/* Used for SAM Task Attribute ordering */
u64 write_bytes;
spinlock_t stats_lock;
/* Active commands on this virtual SE device */
- atomic_t active_cmds;
atomic_t simple_cmds;
atomic_t depth_left;
atomic_t dev_ordered_id;
- atomic_t dev_tur_active;
atomic_t execute_tasks;
- atomic_t dev_status_thr_count;
- atomic_t dev_hoq_count;
atomic_t dev_ordered_sync;
atomic_t dev_qf_count;
struct se_obj dev_obj;
struct se_obj dev_export_obj;
struct se_queue_obj dev_queue_obj;
spinlock_t delayed_cmd_lock;
- spinlock_t ordered_cmd_lock;
spinlock_t execute_task_lock;
- spinlock_t state_task_lock;
- spinlock_t dev_alua_lock;
spinlock_t dev_reservation_lock;
- spinlock_t dev_state_lock;
spinlock_t dev_status_lock;
- spinlock_t dev_status_thr_lock;
spinlock_t se_port_lock;
spinlock_t se_tmr_lock;
spinlock_t qf_cmd_lock;
struct t10_pr_registration *dev_pr_res_holder;
struct list_head dev_sep_list;
struct list_head dev_tmr_list;
- struct timer_list dev_status_timer;
/* Pointer to descriptor for processing thread */
struct task_struct *process_thread;
- pid_t process_thread_pid;
- struct task_struct *dev_mgmt_thread;
struct work_struct qf_work_queue;
struct list_head delayed_cmd_list;
- struct list_head ordered_cmd_list;
struct list_head execute_task_list;
struct list_head state_task_list;
struct list_head qf_cmd_list;
struct se_subsystem_api *transport;
/* Linked list for struct se_hba struct se_device list */
struct list_head dev_list;
- /* Linked list for struct se_global->g_se_dev_list */
- struct list_head g_se_dev_list;
} ____cacheline_aligned;
struct se_hba {
u32 sep_index;
struct scsi_port_stats sep_stats;
/* Used for ALUA Target Port Groups membership */
- atomic_t sep_tg_pt_gp_active;
atomic_t sep_tg_pt_secondary_offline;
/* Used for PR ALL_TG_PT=1 */
atomic_t sep_tg_pt_ref_cnt;
#define PYX_TRANSPORT_STATUS_INTERVAL 5 /* In seconds */
-#define PYX_TRANSPORT_SENT_TO_TRANSPORT 0
-#define PYX_TRANSPORT_WRITE_PENDING 1
-
-#define PYX_TRANSPORT_UNKNOWN_SAM_OPCODE -1
-#define PYX_TRANSPORT_HBA_QUEUE_FULL -2
-#define PYX_TRANSPORT_REQ_TOO_MANY_SECTORS -3
-#define PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES -4
-#define PYX_TRANSPORT_INVALID_CDB_FIELD -5
-#define PYX_TRANSPORT_INVALID_PARAMETER_LIST -6
-#define PYX_TRANSPORT_LU_COMM_FAILURE -7
-#define PYX_TRANSPORT_UNKNOWN_MODE_PAGE -8
-#define PYX_TRANSPORT_WRITE_PROTECTED -9
-#define PYX_TRANSPORT_RESERVATION_CONFLICT -10
-#define PYX_TRANSPORT_ILLEGAL_REQUEST -11
-#define PYX_TRANSPORT_USE_SENSE_REASON -12
-
-#ifndef SAM_STAT_RESERVATION_CONFLICT
-#define SAM_STAT_RESERVATION_CONFLICT 0x18
-#endif
-
-#define TRANSPORT_PLUGIN_FREE 0
-#define TRANSPORT_PLUGIN_REGISTERED 1
-
#define TRANSPORT_PLUGIN_PHBA_PDEV 1
#define TRANSPORT_PLUGIN_VHBA_PDEV 2
#define TRANSPORT_PLUGIN_VHBA_VDEV 3
extern int transport_handle_cdb_direct(struct se_cmd *);
extern int transport_generic_handle_cdb_map(struct se_cmd *);
extern int transport_generic_handle_data(struct se_cmd *);
-extern void transport_new_cmd_failure(struct se_cmd *);
extern int transport_generic_handle_tmr(struct se_cmd *);
extern bool target_stop_task(struct se_task *task, unsigned long *flags);
extern int transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *, u32,
{I_REFERENCED, "I_REFERENCED"} \
)
+#define WB_WORK_REASON \
+ {WB_REASON_BACKGROUND, "background"}, \
+ {WB_REASON_TRY_TO_FREE_PAGES, "try_to_free_pages"}, \
+ {WB_REASON_SYNC, "sync"}, \
+ {WB_REASON_PERIODIC, "periodic"}, \
+ {WB_REASON_LAPTOP_TIMER, "laptop_timer"}, \
+ {WB_REASON_FREE_MORE_MEM, "free_more_memory"}, \
+ {WB_REASON_FS_FREE_SPACE, "fs_free_space"}, \
+ {WB_REASON_FORKER_THREAD, "forker_thread"}
+
struct wb_writeback_work;
DECLARE_EVENT_CLASS(writeback_work_class,
__entry->for_kupdate,
__entry->range_cyclic,
__entry->for_background,
- wb_reason_name[__entry->reason]
+ __print_symbolic(__entry->reason, WB_WORK_REASON)
)
);
#define DEFINE_WRITEBACK_WORK_EVENT(name) \
__entry->older, /* older_than_this in jiffies */
__entry->age, /* older_than_this in relative milliseconds */
__entry->moved,
- wb_reason_name[__entry->reason])
+ __print_symbolic(__entry->reason, WB_WORK_REASON)
+ )
);
TRACE_EVENT(global_dirty_state,
void (*dsi_disable_pads)(int dsi_id, unsigned lane_mask);
};
-#if defined(CONFIG_OMAP2_DSS_MODULE) || defined(CONFIG_OMAP2_DSS)
/* Init with the board info */
extern int omap_display_init(struct omap_dss_board_info *board_data);
-#else
-static inline int omap_display_init(struct omap_dss_board_info *board_data)
-{
- return 0;
-}
-#endif
struct omap_display_platform_data {
struct omap_dss_board_info *board_data;
XS_IS_DOMAIN_INTRODUCED,
XS_RESUME,
XS_SET_TARGET,
- XS_RESTRICT,
- XS_RESET_WATCHES
+ XS_RESTRICT
};
#define XS_WRITE_NONE "NONE"
static inline int xen_must_unplug_nics(void) {
#if (defined(CONFIG_XEN_NETDEV_FRONTEND) || \
defined(CONFIG_XEN_NETDEV_FRONTEND_MODULE)) && \
- (defined(CONFIG_XEN_PLATFORM_PCI) || \
- defined(CONFIG_XEN_PLATFORM_PCI_MODULE))
+ defined(CONFIG_XEN_PVHVM)
return 1;
#else
return 0;
static inline int xen_must_unplug_disks(void) {
#if (defined(CONFIG_XEN_BLKDEV_FRONTEND) || \
defined(CONFIG_XEN_BLKDEV_FRONTEND_MODULE)) && \
- (defined(CONFIG_XEN_PLATFORM_PCI) || \
- defined(CONFIG_XEN_PLATFORM_PCI_MODULE))
+ defined(CONFIG_XEN_PVHVM)
return 1;
#else
return 0;
For those who want to have the feature enabled by default should
select this option (if, for some reason, they need to disable it
then swapaccount=0 does the trick).
+config CGROUP_MEM_RES_CTLR_KMEM
+ bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
+ depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL
+ default n
+ help
+ The Kernel Memory extension for Memory Resource Controller can limit
+ the amount of memory used by kernel objects in the system. Those are
+ fundamentally different from the entities handled by the standard
+ Memory Controller, which are page-based, and can be swapped. Users of
+ the kmem extension can use it to guarantee that no group of processes
+ will ever exhaust kernel resources alone.
config CGROUP_PERF
bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
void mq_put_mnt(struct ipc_namespace *ns)
{
- mntput(ns->mq_mnt);
+ kern_unmount(ns->mq_mnt);
}
static int __init init_mqueue_fs(void)
spin_lock_init(&mq_lock);
- init_ipc_ns.mq_mnt = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
- if (IS_ERR(init_ipc_ns.mq_mnt)) {
- error = PTR_ERR(init_ipc_ns.mq_mnt);
+ error = mq_init_ns(&init_ipc_ns);
+ if (error)
goto out_filesystem;
- }
return 0;
*/
struct ipc_namespace init_ipc_ns = {
.count = ATOMIC_INIT(1),
-#ifdef CONFIG_POSIX_MQUEUE
- .mq_queues_max = DFLT_QUEUESMAX,
- .mq_msg_max = DFLT_MSGMAX,
- .mq_msgsize_max = DFLT_MSGSIZEMAX,
-#endif
.user_ns = &init_user_ns,
};
continue;
/* get old css_set pointer */
task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- /* ignore this task if it's going away */
- task_unlock(tsk);
- continue;
- }
oldcg = tsk->cgroups;
get_css_set(oldcg);
task_unlock(tsk);
kfree(cgroup_freezer(cgroup));
}
+/* task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+ return frozen(task) ||
+ (task_is_stopped_or_traced(task) && freezing(task));
+}
+
/*
* The call to cgroup_lock() in the freezer.state write method prevents
* a write to that file racing against an attach, and hence the
cgroup_iter_start(cgroup, &it);
while ((task = cgroup_iter_next(cgroup, &it))) {
ntotal++;
- if (frozen(task))
+ if (is_task_frozen_enough(task))
nfrozen++;
}
while ((task = cgroup_iter_next(cgroup, &it))) {
if (!freeze_task(task, true))
continue;
- if (frozen(task))
+ if (is_task_frozen_enough(task))
continue;
if (!freezing(task) && !freezer_should_skip(task))
num_cant_freeze_now++;
struct cpuset, css);
}
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return false;
+}
+#endif
+
+
/* bits in struct cpuset flags field */
typedef enum {
CS_CPU_EXCLUSIVE,
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
- bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+ bool need_loop;
repeat:
/*
return;
task_lock(tsk);
+ /*
+ * Determine if a loop is necessary if another thread is doing
+ * get_mems_allowed(). If at least one node remains unchanged and
+ * tsk does not have a mempolicy, then an empty nodemask will not be
+ * possible when mems_allowed is larger than a word.
+ */
+ need_loop = task_has_mempolicy(tsk) ||
+ !nodes_intersects(*newmems, tsk->mems_allowed);
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
/*
* Allocation of memory is very fast, we needn't sleep when waiting
- * for the read-side. No wait is necessary, however, if at least one
- * node remains unchanged.
+ * for the read-side.
*/
- while (masks_disjoint &&
- ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+ while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
task_unlock(tsk);
if (!task_curr(tsk))
yield();
static void update_context_time(struct perf_event_context *ctx);
static u64 perf_event_time(struct perf_event *event);
+static void ring_buffer_attach(struct perf_event *event,
+ struct ring_buffer *rb);
+
void __weak perf_event_print_debug(void) { }
extern __weak const char *perf_pmu_name(void)
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- perf_event_sched_in(cpuctx, ctx, task);
+ if (ctx->nr_events)
+ cpuctx->task_ctx = ctx;
- cpuctx->task_ctx = ctx;
+ perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
struct ring_buffer *rb;
unsigned int events = POLL_HUP;
+ /*
+ * Race between perf_event_set_output() and perf_poll(): perf_poll()
+ * grabs the rb reference but perf_event_set_output() overrides it.
+ * Here is the timeline for two threads T1, T2:
+ * t0: T1, rb = rcu_dereference(event->rb)
+ * t1: T2, old_rb = event->rb
+ * t2: T2, event->rb = new rb
+ * t3: T2, ring_buffer_detach(old_rb)
+ * t4: T1, ring_buffer_attach(rb1)
+ * t5: T1, poll_wait(event->waitq)
+ *
+ * To avoid this problem, we grab mmap_mutex in perf_poll()
+ * thereby ensuring that the assignment of the new ring buffer
+ * and the detachment of the old buffer appear atomic to perf_poll()
+ */
+ mutex_lock(&event->mmap_mutex);
+
rcu_read_lock();
rb = rcu_dereference(event->rb);
- if (rb)
+ if (rb) {
+ ring_buffer_attach(event, rb);
events = atomic_xchg(&rb->poll, 0);
+ }
rcu_read_unlock();
+ mutex_unlock(&event->mmap_mutex);
+
poll_wait(file, &event->waitq, wait);
return events;
return ret;
}
+static void ring_buffer_attach(struct perf_event *event,
+ struct ring_buffer *rb)
+{
+ unsigned long flags;
+
+ if (!list_empty(&event->rb_entry))
+ return;
+
+ spin_lock_irqsave(&rb->event_lock, flags);
+ if (!list_empty(&event->rb_entry))
+ goto unlock;
+
+ list_add(&event->rb_entry, &rb->event_list);
+unlock:
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+ struct ring_buffer *rb)
+{
+ unsigned long flags;
+
+ if (list_empty(&event->rb_entry))
+ return;
+
+ spin_lock_irqsave(&rb->event_lock, flags);
+ list_del_init(&event->rb_entry);
+ wake_up_all(&event->waitq);
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+ struct ring_buffer *rb;
+
+ rcu_read_lock();
+ rb = rcu_dereference(event->rb);
+ if (!rb)
+ goto unlock;
+
+ list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+ wake_up_all(&event->waitq);
+
+unlock:
+ rcu_read_unlock();
+}
+
static void rb_free_rcu(struct rcu_head *rcu_head)
{
struct ring_buffer *rb;
static void ring_buffer_put(struct ring_buffer *rb)
{
+ struct perf_event *event, *n;
+ unsigned long flags;
+
if (!atomic_dec_and_test(&rb->refcount))
return;
+ spin_lock_irqsave(&rb->event_lock, flags);
+ list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
+ list_del_init(&event->rb_entry);
+ wake_up_all(&event->waitq);
+ }
+ spin_unlock_irqrestore(&rb->event_lock, flags);
+
call_rcu(&rb->rcu_head, rb_free_rcu);
}
atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
vma->vm_mm->pinned_vm -= event->mmap_locked;
rcu_assign_pointer(event->rb, NULL);
+ ring_buffer_detach(event, rb);
mutex_unlock(&event->mmap_mutex);
ring_buffer_put(rb);
void perf_event_wakeup(struct perf_event *event)
{
- wake_up_all(&event->waitq);
+ ring_buffer_wakeup(event);
if (event->pending_kill) {
kill_fasync(&event->fasync, SIGIO, event->pending_kill);
INIT_LIST_HEAD(&event->group_entry);
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
+ INIT_LIST_HEAD(&event->rb_entry);
+
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
old_rb = event->rb;
rcu_assign_pointer(event->rb, rb);
+ if (old_rb)
+ ring_buffer_detach(event, old_rb);
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);
local_t lost; /* nr records lost */
long watermark; /* wakeup watermark */
+ /* poll crap */
+ spinlock_t event_lock;
+ struct list_head event_list;
struct perf_event_mmap_page *user_page;
void *data_pages[0];
rb->writable = 1;
atomic_set(&rb->refcount, 1);
+
+ INIT_LIST_HEAD(&rb->event_list);
+ spin_lock_init(&rb->event_lock);
}
#ifndef CONFIG_PERF_USE_VMALLOC
}
/* dead body doesn't have much to contribute */
- if (p->exit_state == EXIT_DEAD)
+ if (unlikely(p->exit_state == EXIT_DEAD)) {
+ /*
+ * But do not ignore this task until the tracer does
+ * wait_task_zombie()->do_notify_parent().
+ */
+ if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+ wo->notask_error = 0;
return 0;
+ }
/* slay zombie? */
if (p->exit_state == EXIT_ZOMBIE) {
void free_task(struct task_struct *tsk)
{
- prop_local_destroy_single(&tsk->dirties);
account_kernel_stack(tsk->stack, -1);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
tsk->stack = ti;
- err = prop_local_init_single(&tsk->dirties);
- if (err)
- goto out;
-
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
clear_tsk_need_resched(tsk);
#endif
lock_page(page_head);
+
+ /*
+ * If page_head->mapping is NULL, then it cannot be a PageAnon
+ * page; but it might be the ZERO_PAGE or in the gate area or
+ * in a special mapping (all cases which we are happy to fail);
+ * or it may have been a good file page when get_user_pages_fast
+ * found it, but truncated or holepunched or subjected to
+ * invalidate_complete_page2 before we got the page lock (also
+ * cases which we are happy to fail). And we hold a reference,
+ * so refcount care in invalidate_complete_page's remove_mapping
+ * prevents drop_caches from setting mapping to NULL beneath us.
+ *
+ * The case we do have to guard against is when memory pressure made
+ * shmem_writepage move it from filecache to swapcache beneath us:
+ * an unlikely race, but we do need to retry for page_head->mapping.
+ */
if (!page_head->mapping) {
+ int shmem_swizzled = PageSwapCache(page_head);
unlock_page(page_head);
put_page(page_head);
- /*
- * ZERO_PAGE pages don't have a mapping. Avoid a busy loop
- * trying to find one. RW mapping would have COW'd (and thus
- * have a mapping) so this page is RO and won't ever change.
- */
- if ((page_head == ZERO_PAGE(address)))
- return -EFAULT;
- goto again;
+ if (shmem_swizzled)
+ goto again;
+ return -EFAULT;
}
/*
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
+ struct timerqueue_node *next_timer;
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
- if (&timer->node == timerqueue_getnext(&base->active)) {
+ next_timer = timerqueue_getnext(&base->active);
+ timerqueue_del(&base->active, &timer->node);
+ if (&timer->node == next_timer) {
#ifdef CONFIG_HIGH_RES_TIMERS
/* Reprogram the clock event device. if enabled */
if (reprogram && hrtimer_hres_active()) {
}
#endif
}
- timerqueue_del(&base->active, &timer->node);
if (!timerqueue_getnext(&base->active))
base->cpu_base->active_bases &= ~(1 << base->index);
out:
/*
* Ensure the task is not frozen.
- * Also, when a freshly created task is scheduled once, changes
- * its state to TASK_UNINTERRUPTIBLE without having ever been
- * switched out once, it musn't be checked.
+ * Also, skip vfork and any other user process that freezer should skip.
*/
- if (unlikely(t->flags & PF_FROZEN || !switch_count))
+ if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP)))
+ return;
+
+ /*
+ * When a freshly created task is scheduled once, changes its state to
+ * TASK_UNINTERRUPTIBLE without having ever been switched out once, it
+ * musn't be checked.
+ */
+ if (unlikely(!switch_count))
return;
if (switch_count != t->last_switch_count) {
static int irq_wait_for_interrupt(struct irqaction *action)
{
+ set_current_state(TASK_INTERRUPTIBLE);
+
while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
return 0;
}
schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
}
+ __set_current_state(TASK_RUNNING);
return -1;
}
return -ENOMEM;
action->handler = handler;
- action->flags = IRQF_PERCPU;
+ action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
action->name = devname;
action->percpu_dev_id = dev_id;
*/
action = desc->action;
if (!action || !(action->flags & IRQF_SHARED) ||
- (action->flags & __IRQF_TIMER) || !action->next)
+ (action->flags & __IRQF_TIMER) ||
+ (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+ !action->next)
goto out;
/* Already running on another processor */
struct irq_desc *desc;
int i, ok = 0;
- if (atomic_inc_return(&irq_poll_active) == 1)
+ if (atomic_inc_return(&irq_poll_active) != 1)
goto out;
irq_poll_cpu = smp_processor_id();
return;
jump_label_lock();
- if (atomic_add_return(1, &key->enabled) == 1)
+ if (atomic_read(&key->enabled) == 0)
jump_label_update(key, JUMP_LABEL_ENABLE);
+ atomic_inc(&key->enabled);
jump_label_unlock();
}
#include <linux/stringify.h>
#include <linux/bitops.h>
#include <linux/gfp.h>
+#include <linux/kmemcheck.h>
#include <asm/sections.h>
void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
- memset(lock, 0, sizeof(*lock));
+ int i;
+
+ kmemcheck_mark_initialized(lock, sizeof(*lock));
+
+ for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+ lock->class_cache[i] = NULL;
#ifdef CONFIG_LOCK_STAT
lock->cpu = raw_smp_processor_id();
static int hibernation_mode = HIBERNATION_SHUTDOWN;
+static bool freezer_test_done;
+
static const struct platform_hibernation_ops *hibernation_ops;
/**
error = freeze_kernel_threads();
if (error)
- goto Close;
+ goto Cleanup;
+
+ if (hibernation_test(TEST_FREEZER) ||
+ hibernation_testmode(HIBERNATION_TESTPROC)) {
+
+ /*
+ * Indicate to the caller that we are returning due to a
+ * successful freezer test.
+ */
+ freezer_test_done = true;
+ goto Cleanup;
+ }
error = dpm_prepare(PMSG_FREEZE);
- if (error)
- goto Complete_devices;
+ if (error) {
+ dpm_complete(msg);
+ goto Cleanup;
+ }
suspend_console();
pm_restrict_gfp_mask();
pm_restore_gfp_mask();
resume_console();
-
- Complete_devices:
dpm_complete(msg);
Close:
Recover_platform:
platform_recover(platform_mode);
goto Resume_devices;
+
+ Cleanup:
+ swsusp_free();
+ goto Close;
}
/**
if (error)
goto Finish;
- if (hibernation_test(TEST_FREEZER))
- goto Thaw;
-
- if (hibernation_testmode(HIBERNATION_TESTPROC))
- goto Thaw;
-
error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
if (error)
goto Thaw;
+ if (freezer_test_done) {
+ freezer_test_done = false;
+ goto Thaw;
+ }
if (in_suspend) {
unsigned int flags = 0;
if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
break;
}
- if (state < PM_SUSPEND_MAX && *s)
+ if (state < PM_SUSPEND_MAX && *s) {
error = enter_state(state);
if (error) {
suspend_stats.fail++;
dpm_save_failed_errno(error);
} else
suspend_stats.success++;
+ }
#endif
Exit:
raw_spin_lock(&logbuf_lock);
if (con_start != log_end)
retry = 1;
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
if (retry && console_trylock())
goto again;
- raw_spin_unlock_irqrestore(&logbuf_lock, flags);
if (wake_klogd)
wake_up_klogd();
}
*/
if (!(child->flags & PF_EXITING) &&
(child->signal->flags & SIGNAL_STOP_STOPPED ||
- child->signal->group_stop_count))
+ child->signal->group_stop_count)) {
child->jobctl |= JOBCTL_STOP_PENDING;
+ /*
+ * This is only possible if this thread was cloned by the
+ * traced task running in the stopped group, set the signal
+ * for the future reports.
+ * FIXME: we should change ptrace_init_task() to handle this
+ * case.
+ */
+ if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
+ child->jobctl |= SIGSTOP;
+ }
+
/*
* If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
* @child in the butt. Note that @resume should be used iff @child
#include <linux/ctype.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
+#include <linux/init_task.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
*
* This waits for completion of a specific task to be signaled. It is
* interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_interruptible(struct completion *x)
{
*
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
*
* This waits to be signaled for completion of a specific task. It can be
* interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_killable(struct completion *x)
{
* This waits for either a completion of a specific task to be
* signaled or for a specified timeout to expire. It can be
* interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_killable_timeout(struct completion *x,
*/
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
}
/*
list_del_leaf_cfs_rq(cfs_rq);
}
+static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+{
+ long tg_weight;
+
+ /*
+ * Use this CPU's actual weight instead of the last load_contribution
+ * to gain a more accurate current total weight. See
+ * update_cfs_rq_load_contribution().
+ */
+ tg_weight = atomic_read(&tg->load_weight);
+ tg_weight -= cfs_rq->load_contribution;
+ tg_weight += cfs_rq->load.weight;
+
+ return tg_weight;
+}
+
static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
- long load_weight, load, shares;
+ long tg_weight, load, shares;
+ tg_weight = calc_tg_weight(tg, cfs_rq);
load = cfs_rq->load.weight;
- load_weight = atomic_read(&tg->load_weight);
- load_weight += load;
- load_weight -= cfs_rq->load_contribution;
-
shares = (tg->shares * load);
- if (load_weight)
- shares /= load_weight;
+ if (tg_weight)
+ shares /= tg_weight;
if (shares < MIN_SHARES)
shares = MIN_SHARES;
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
- if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running)
+ if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
return;
__return_cfs_rq_runtime(cfs_rq);
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
+ *
+ * Calculate the effective load difference if @wl is added (subtracted) to @tg
+ * on this @cpu and results in a total addition (subtraction) of @wg to the
+ * total group weight.
+ *
+ * Given a runqueue weight distribution (rw_i) we can compute a shares
+ * distribution (s_i) using:
+ *
+ * s_i = rw_i / \Sum rw_j (1)
+ *
+ * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
+ * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
+ * shares distribution (s_i):
+ *
+ * rw_i = { 2, 4, 1, 0 }
+ * s_i = { 2/7, 4/7, 1/7, 0 }
+ *
+ * As per wake_affine() we're interested in the load of two CPUs (the CPU the
+ * task used to run on and the CPU the waker is running on), we need to
+ * compute the effect of waking a task on either CPU and, in case of a sync
+ * wakeup, compute the effect of the current task going to sleep.
+ *
+ * So for a change of @wl to the local @cpu with an overall group weight change
+ * of @wl we can compute the new shares distribution (s'_i) using:
+ *
+ * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2)
+ *
+ * Suppose we're interested in CPUs 0 and 1, and want to compute the load
+ * differences in waking a task to CPU 0. The additional task changes the
+ * weight and shares distributions like:
+ *
+ * rw'_i = { 3, 4, 1, 0 }
+ * s'_i = { 3/8, 4/8, 1/8, 0 }
+ *
+ * We can then compute the difference in effective weight by using:
+ *
+ * dw_i = S * (s'_i - s_i) (3)
+ *
+ * Where 'S' is the group weight as seen by its parent.
+ *
+ * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
+ * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
+ * 4/7) times the weight of the group.
*/
static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
- if (!tg->parent)
+ if (!tg->parent) /* the trivial, non-cgroup case */
return wl;
for_each_sched_entity(se) {
- long lw, w;
+ long w, W;
tg = se->my_q->tg;
- w = se->my_q->load.weight;
- /* use this cpu's instantaneous contribution */
- lw = atomic_read(&tg->load_weight);
- lw -= se->my_q->load_contribution;
- lw += w + wg;
+ /*
+ * W = @wg + \Sum rw_j
+ */
+ W = wg + calc_tg_weight(tg, se->my_q);
- wl += w;
+ /*
+ * w = rw_i + @wl
+ */
+ w = se->my_q->load.weight + wl;
- if (lw > 0 && wl < lw)
- wl = (wl * tg->shares) / lw;
+ /*
+ * wl = S * s'_i; see (2)
+ */
+ if (W > 0 && w < W)
+ wl = (w * tg->shares) / W;
else
wl = tg->shares;
- /* zero point is MIN_SHARES */
+ /*
+ * Per the above, wl is the new se->load.weight value; since
+ * those are clipped to [MIN_SHARES, ...) do so now. See
+ * calc_cfs_shares().
+ */
if (wl < MIN_SHARES)
wl = MIN_SHARES;
+
+ /*
+ * wl = dw_i = S * (s'_i - s_i); see (3)
+ */
wl -= se->load.weight;
+
+ /*
+ * Recursively apply this logic to all parent groups to compute
+ * the final effective load change on the root group. Since
+ * only the @tg group gets extra weight, all parent groups can
+ * only redistribute existing shares. @wl is the shift in shares
+ * resulting from this level per the above.
+ */
wg = 0;
}
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
struct sched_domain *sd;
- int i;
+ struct sched_group *sg;
+ int i, smt = 0;
/*
* If the task is going to be woken-up on this cpu and if it is
* Otherwise, iterate the domains and find an elegible idle cpu.
*/
rcu_read_lock();
+again:
for_each_domain(target, sd) {
+ if (!smt && (sd->flags & SD_SHARE_CPUPOWER))
+ continue;
+
+ if (smt && !(sd->flags & SD_SHARE_CPUPOWER))
+ break;
+
if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
break;
- for_each_cpu_and(i, sched_domain_span(sd), tsk_cpus_allowed(p)) {
- if (idle_cpu(i)) {
- target = i;
- break;
+ sg = sd->groups;
+ do {
+ if (!cpumask_intersects(sched_group_cpus(sg),
+ tsk_cpus_allowed(p)))
+ goto next;
+
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ if (!idle_cpu(i))
+ goto next;
}
- }
- /*
- * Lets stop looking for an idle sibling when we reached
- * the domain that spans the current cpu and prev_cpu.
- */
- if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
- cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
- break;
+ target = cpumask_first_and(sched_group_cpus(sg),
+ tsk_cpus_allowed(p));
+ goto done;
+next:
+ sg = sg->next;
+ } while (sg != sd->groups);
+ }
+ if (!smt) {
+ smt = 1;
+ goto again;
}
+done:
rcu_read_unlock();
return target;
}
/**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
SCHED_FEAT(TTWU_QUEUE, 1)
SCHED_FEAT(FORCE_SD_OVERLAP, 0)
+SCHED_FEAT(RT_RUNTIME_SHARE, 1)
{
int more = 0;
+ if (!sched_feat(RT_RUNTIME_SHARE))
+ return more;
+
if (rt_rq->rt_time > rt_rq->rt_runtime) {
raw_spin_unlock(&rt_rq->rt_runtime_lock);
more = do_balance_runtime(rt_rq);
*/
if (!(sig->flags & SIGNAL_STOP_STOPPED))
sig->group_exit_code = signr;
- else
- WARN_ON_ONCE(!current->ptrace);
sig->group_stop_count = 0;
fput(file);
out_putname:
- putname(pathname);
+ __putname(pathname);
out:
return result;
}
struct alarm *alarm;
ktime_t expired = next->expires;
- if (expired.tv64 >= now.tv64)
+ if (expired.tv64 > now.tv64)
break;
alarm = container_of(next, struct alarm, node);
clocksource_resume_watchdog();
}
+/**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs: Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+ u64 ret;
+ /*
+ * We won't try to correct for more then 11% adjustments (110,000 ppm),
+ */
+ ret = (u64)cs->mult * 11;
+ do_div(ret,100);
+ return (u32)ret;
+}
+
/**
* clocksource_max_deferment - Returns max time the clocksource can be deferred
* @cs: Pointer to clocksource
/*
* Calculate the maximum number of cycles that we can pass to the
* cyc2ns function without overflowing a 64-bit signed result. The
- * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
- * is equivalent to the below.
- * max_cycles < (2^63)/cs->mult
- * max_cycles < 2^(log2((2^63)/cs->mult))
- * max_cycles < 2^(log2(2^63) - log2(cs->mult))
- * max_cycles < 2^(63 - log2(cs->mult))
- * max_cycles < 1 << (63 - log2(cs->mult))
+ * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+ * which is equivalent to the below.
+ * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+ * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+ * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+ * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+ * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
* Please note that we add 1 to the result of the log2 to account for
* any rounding errors, ensure the above inequality is satisfied and
* no overflow will occur.
*/
- max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+ max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
/*
* The actual maximum number of cycles we can defer the clocksource is
* determined by the minimum of max_cycles and cs->mask.
+ * Note: Here we subtract the maxadj to make sure we don't sleep for
+ * too long if there's a large negative adjustment.
*/
max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
- max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+ max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+ cs->shift);
/*
* To ensure that the clocksource does not wrap whilst we are idle,
* note a margin of 12.5% is used because this can be computed with
* a shift, versus say 10% which would require division.
*/
- return max_nsecs - (max_nsecs >> 5);
+ return max_nsecs - (max_nsecs >> 3);
}
#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
/**
* __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
u64 sec;
-
/*
* Calc the maximum number of seconds which we can run before
* wrapping around. For clocksources which have a mask > 32bit
* ~ 0.06ppm granularity for NTP. We apply the same 12.5%
* margin as we do in clocksource_max_deferment()
*/
- sec = (cs->mask - (cs->mask >> 5));
+ sec = (cs->mask - (cs->mask >> 3));
do_div(sec, freq);
do_div(sec, scale);
if (!sec)
clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
NSEC_PER_SEC / scale, sec * scale);
+
+ /*
+ * for clocksources that have large mults, to avoid overflow.
+ * Since mult may be adjusted by ntp, add an safety extra margin
+ *
+ */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ while ((cs->mult + cs->maxadj < cs->mult)
+ || (cs->mult - cs->maxadj > cs->mult)) {
+ cs->mult >>= 1;
+ cs->shift--;
+ cs->maxadj = clocksource_max_adjustment(cs);
+ }
+
cs->max_idle_ns = clocksource_max_deferment(cs);
}
EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
/**
* __clocksource_register_scale - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
* @scale: Scale factor multiplied against freq to get clocksource hz
* @freq: clocksource frequency (cycles per second) divided by scale
*
/**
* clocksource_register - Used to install new clocksources
- * @t: clocksource to be registered
+ * @cs: clocksource to be registered
*
* Returns -EBUSY if registration fails, zero otherwise.
*/
int clocksource_register(struct clocksource *cs)
{
+ /* calculate max adjustment for given mult/shift */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+ "Clocksource %s might overflow on 11%% adjustment\n",
+ cs->name);
+
/* calculate max idle time permitted for this clocksource */
cs->max_idle_ns = clocksource_max_deferment(cs);
/**
* clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs: clocksource to be changed
+ * @rating: new rating
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
/**
* clocksource_unregister - remove a registered clocksource
+ * @cs: clocksource to be unregistered
*/
void clocksource_unregister(struct clocksource *cs)
{
/**
* sysfs_show_current_clocksources - sysfs interface for current clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing current clocksource.
/**
* sysfs_override_clocksource - interface for manually overriding clocksource
* @dev: unused
+ * @attr: unused
* @buf: name of override clocksource
* @count: length of buffer
*
/**
* sysfs_show_available_clocksources - sysfs interface for listing clocksource
* @dev: unused
+ * @attr: unused
* @buf: char buffer to be filled with clocksource list
*
* Provides sysfs interface for listing registered clocksources
(dev->features & CLOCK_EVT_FEAT_C3STOP))
return 0;
- clockevents_exchange_device(NULL, dev);
+ clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
tick_broadcast_device.evtdev = dev;
if (!cpumask_empty(tick_get_broadcast_mask()))
tick_broadcast_start_periodic(dev);
secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
nsecs += timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
} while (read_seqretry(&xtime_lock, seq));
/*
*ts = xtime;
tomono = wall_to_monotonic;
nsecs = timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
} while (read_seqretry(&xtime_lock, seq));
s64 error, interval = timekeeper.cycle_interval;
int adj;
+ /*
+ * The point of this is to check if the error is greater then half
+ * an interval.
+ *
+ * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+ *
+ * Note we subtract one in the shift, so that error is really error*2.
+ * This "saves" dividing(shifting) intererval twice, but keeps the
+ * (error > interval) comparision as still measuring if error is
+ * larger then half an interval.
+ *
+ * Note: It does not "save" on aggrivation when reading the code.
+ */
error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
if (error > interval) {
+ /*
+ * We now divide error by 4(via shift), which checks if
+ * the error is greater then twice the interval.
+ * If it is greater, we need a bigadjust, if its smaller,
+ * we can adjust by 1.
+ */
error >>= 2;
+ /*
+ * XXX - In update_wall_time, we round up to the next
+ * nanosecond, and store the amount rounded up into
+ * the error. This causes the likely below to be unlikely.
+ *
+ * The properfix is to avoid rounding up by using
+ * the high precision timekeeper.xtime_nsec instead of
+ * xtime.tv_nsec everywhere. Fixing this will take some
+ * time.
+ */
if (likely(error <= interval))
adj = 1;
else
adj = timekeeping_bigadjust(error, &interval, &offset);
} else if (error < -interval) {
+ /* See comment above, this is just switched for the negative */
error >>= 2;
if (likely(error >= -interval)) {
adj = -1;
offset = -offset;
} else
adj = timekeeping_bigadjust(error, &interval, &offset);
- } else
+ } else /* No adjustment needed */
return;
+ WARN_ONCE(timekeeper.clock->maxadj &&
+ (timekeeper.mult + adj > timekeeper.clock->mult +
+ timekeeper.clock->maxadj),
+ "Adjusting %s more then 11%% (%ld vs %ld)\n",
+ timekeeper.clock->name, (long)timekeeper.mult + adj,
+ (long)timekeeper.clock->mult +
+ timekeeper.clock->maxadj);
+ /*
+ * So the following can be confusing.
+ *
+ * To keep things simple, lets assume adj == 1 for now.
+ *
+ * When adj != 1, remember that the interval and offset values
+ * have been appropriately scaled so the math is the same.
+ *
+ * The basic idea here is that we're increasing the multiplier
+ * by one, this causes the xtime_interval to be incremented by
+ * one cycle_interval. This is because:
+ * xtime_interval = cycle_interval * mult
+ * So if mult is being incremented by one:
+ * xtime_interval = cycle_interval * (mult + 1)
+ * Its the same as:
+ * xtime_interval = (cycle_interval * mult) + cycle_interval
+ * Which can be shortened to:
+ * xtime_interval += cycle_interval
+ *
+ * So offset stores the non-accumulated cycles. Thus the current
+ * time (in shifted nanoseconds) is:
+ * now = (offset * adj) + xtime_nsec
+ * Now, even though we're adjusting the clock frequency, we have
+ * to keep time consistent. In other words, we can't jump back
+ * in time, and we also want to avoid jumping forward in time.
+ *
+ * So given the same offset value, we need the time to be the same
+ * both before and after the freq adjustment.
+ * now = (offset * adj_1) + xtime_nsec_1
+ * now = (offset * adj_2) + xtime_nsec_2
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_2) + xtime_nsec_2
+ * And we know:
+ * adj_2 = adj_1 + 1
+ * So:
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * (adj_1+1)) + xtime_nsec_2
+ * (offset * adj_1) + xtime_nsec_1 =
+ * (offset * adj_1) + offset + xtime_nsec_2
+ * Canceling the sides:
+ * xtime_nsec_1 = offset + xtime_nsec_2
+ * Which gives us:
+ * xtime_nsec_2 = xtime_nsec_1 - offset
+ * Which simplfies to:
+ * xtime_nsec -= offset
+ *
+ * XXX - TODO: Doc ntp_error calculation.
+ */
timekeeper.mult += adj;
timekeeper.xtime_interval += interval;
timekeeper.xtime_nsec -= offset;
int pid;
rcu_read_lock();
- pid = task_tgid_vnr(current->real_parent);
+ pid = task_tgid_vnr(rcu_dereference(current->real_parent));
rcu_read_unlock();
return pid;
ftrace_pid_function = ftrace_stub;
}
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
/*
* For those archs that do not test ftrace_trace_stop in their
if (!src->count) {
free_ftrace_hash_rcu(*dst);
rcu_assign_pointer(*dst, EMPTY_HASH);
- return 0;
+ /* still need to update the function records */
+ ret = 0;
+ goto out;
}
/*
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
if (strcmp(system->name, name) == 0) {
- __get_system(system);
system->nr_events++;
return system->entry;
}
*/
err = replace_preds(call, NULL, ps, filter_string, true);
if (err)
- goto fail;
+ call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+ else
+ call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
}
list_for_each_entry(call, &ftrace_events, list) {
if (strcmp(call->class->system, system->name) != 0)
continue;
+ if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+ continue;
+
filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
if (!filter_item)
goto fail_mem;
* replace the filter for the call.
*/
filter = call->filter;
- call->filter = filter_item->filter;
+ rcu_assign_pointer(call->filter, filter_item->filter);
filter_item->filter = filter;
fail = false;
filter = call->filter;
if (!filter)
goto out_unlock;
- call->filter = NULL;
+ RCU_INIT_POINTER(call->filter, NULL);
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
* string
*/
tmp = call->filter;
- call->filter = filter;
+ rcu_assign_pointer(call->filter, filter);
if (tmp) {
/* Make sure the call is done with the filter */
synchronize_sched();
bool
depends on SMP
+config DQL
+ bool
+
#
# Netlink attribute parsing support is select'ed if needed
#
obj-$(CONFIG_CORDIC) += cordic.o
+obj-$(CONFIG_DQL) += dynamic_queue_limits.o
+
hostprogs-y := gen_crc32table
clean-files := crc32table.h
static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
{
- return ((a->dev_addr == a->dev_addr) &&
+ return ((a->dev_addr == b->dev_addr) &&
(a->dev == b->dev)) ? true : false;
}
--- /dev/null
+/*
+ * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/dynamic_queue_limits.h>
+
+#define POSDIFF(A, B) ((A) > (B) ? (A) - (B) : 0)
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+ unsigned int inprogress, prev_inprogress, limit;
+ unsigned int ovlimit, all_prev_completed, completed;
+
+ /* Can't complete more than what's in queue */
+ BUG_ON(count > dql->num_queued - dql->num_completed);
+
+ completed = dql->num_completed + count;
+ limit = dql->limit;
+ ovlimit = POSDIFF(dql->num_queued - dql->num_completed, limit);
+ inprogress = dql->num_queued - completed;
+ prev_inprogress = dql->prev_num_queued - dql->num_completed;
+ all_prev_completed = POSDIFF(completed, dql->prev_num_queued);
+
+ if ((ovlimit && !inprogress) ||
+ (dql->prev_ovlimit && all_prev_completed)) {
+ /*
+ * Queue considered starved if:
+ * - The queue was over-limit in the last interval,
+ * and there is no more data in the queue.
+ * OR
+ * - The queue was over-limit in the previous interval and
+ * when enqueuing it was possible that all queued data
+ * had been consumed. This covers the case when queue
+ * may have becomes starved between completion processing
+ * running and next time enqueue was scheduled.
+ *
+ * When queue is starved increase the limit by the amount
+ * of bytes both sent and completed in the last interval,
+ * plus any previous over-limit.
+ */
+ limit += POSDIFF(completed, dql->prev_num_queued) +
+ dql->prev_ovlimit;
+ dql->slack_start_time = jiffies;
+ dql->lowest_slack = UINT_MAX;
+ } else if (inprogress && prev_inprogress && !all_prev_completed) {
+ /*
+ * Queue was not starved, check if the limit can be decreased.
+ * A decrease is only considered if the queue has been busy in
+ * the whole interval (the check above).
+ *
+ * If there is slack, the amount of execess data queued above
+ * the the amount needed to prevent starvation, the queue limit
+ * can be decreased. To avoid hysteresis we consider the
+ * minimum amount of slack found over several iterations of the
+ * completion routine.
+ */
+ unsigned int slack, slack_last_objs;
+
+ /*
+ * Slack is the maximum of
+ * - The queue limit plus previous over-limit minus twice
+ * the number of objects completed. Note that two times
+ * number of completed bytes is a basis for an upper bound
+ * of the limit.
+ * - Portion of objects in the last queuing operation that
+ * was not part of non-zero previous over-limit. That is
+ * "round down" by non-overlimit portion of the last
+ * queueing operation.
+ */
+ slack = POSDIFF(limit + dql->prev_ovlimit,
+ 2 * (completed - dql->num_completed));
+ slack_last_objs = dql->prev_ovlimit ?
+ POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+ slack = max(slack, slack_last_objs);
+
+ if (slack < dql->lowest_slack)
+ dql->lowest_slack = slack;
+
+ if (time_after(jiffies,
+ dql->slack_start_time + dql->slack_hold_time)) {
+ limit = POSDIFF(limit, dql->lowest_slack);
+ dql->slack_start_time = jiffies;
+ dql->lowest_slack = UINT_MAX;
+ }
+ }
+
+ /* Enforce bounds on limit */
+ limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+ if (limit != dql->limit) {
+ dql->limit = limit;
+ ovlimit = 0;
+ }
+
+ dql->adj_limit = limit + completed;
+ dql->prev_ovlimit = ovlimit;
+ dql->prev_last_obj_cnt = dql->last_obj_cnt;
+ dql->num_completed = completed;
+ dql->prev_num_queued = dql->num_queued;
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+ /* Reset all dynamic values */
+ dql->limit = 0;
+ dql->num_queued = 0;
+ dql->num_completed = 0;
+ dql->last_obj_cnt = 0;
+ dql->prev_num_queued = 0;
+ dql->prev_last_obj_cnt = 0;
+ dql->prev_ovlimit = 0;
+ dql->lowest_slack = UINT_MAX;
+ dql->slack_start_time = jiffies;
+}
+EXPORT_SYMBOL(dql_reset);
+
+int dql_init(struct dql *dql, unsigned hold_time)
+{
+ dql->max_limit = DQL_MAX_LIMIT;
+ dql->min_limit = 0;
+ dql->slack_hold_time = hold_time;
+ dql_reset(dql);
+ return 0;
+}
+EXPORT_SYMBOL(dql_init);
#include <asm/div64.h>
#include <linux/reciprocal_div.h>
+#include <linux/export.h>
u32 reciprocal_value(u32 k)
{
do_div(val, k);
return (u32)val;
}
+EXPORT_SYMBOL(reciprocal_value);
return string(buf, end, uuid, spec);
}
+static
+char *netdev_feature_string(char *buf, char *end, const u8 *addr,
+ struct printf_spec spec)
+{
+ spec.flags |= SPECIAL | SMALL | ZEROPAD;
+ if (spec.field_width == -1)
+ spec.field_width = 2 + 2 * sizeof(netdev_features_t);
+ spec.base = 16;
+
+ return number(buf, end, *(const netdev_features_t *)addr, spec);
+}
+
int kptr_restrict __read_mostly;
/*
* Do not use this feature without some mechanism to verify the
* correctness of the format string and va_list arguments.
* - 'K' For a kernel pointer that should be hidden from unprivileged users
+ * - 'NF' For a netdev_features_t
*
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
has_capability_noaudit(current, CAP_SYSLOG))))
ptr = NULL;
break;
+ case 'N':
+ switch (fmt[1]) {
+ case 'F':
+ return netdev_feature_string(buf, end, ptr, spec);
+ }
+ break;
}
spec.flags |= SMALL;
if (spec.field_width == -1) {
bdi_unregister(bdi);
+ /*
+ * If bdi_unregister() had already been called earlier, the
+ * wakeup_timer could still be armed because bdi_prune_sb()
+ * can race with the bdi_wakeup_thread_delayed() calls from
+ * __mark_inode_dirty().
+ */
+ del_timer_sync(&bdi->wb.wakeup_timer);
+
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
page = __page_cache_alloc(gfp | __GFP_COLD);
if (!page)
return ERR_PTR(-ENOMEM);
- err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+ err = add_to_page_cache_lru(page, mapping, index, gfp);
if (unlikely(err)) {
page_cache_release(page);
if (err == -EEXIST)
* @gfp: the page allocator flags to use if allocating
*
* This is the same as "read_mapping_page(mapping, index, NULL)", but with
- * any new page allocations done using the specified allocation flags. Note
- * that the Radix tree operations will still use GFP_KERNEL, so you can't
- * expect to do this atomically or anything like that - but you can pass in
- * other page requirements.
+ * any new page allocations done using the specified allocation flags.
*
* If the page does not get brought uptodate, return -EIO.
*/
iov_iter_count(i));
again:
-
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
written += copied;
balance_dirty_pages_ratelimited(mapping);
-
+ if (fatal_signal_pending(current)) {
+ status = -EINTR;
+ break;
+ }
} while (iov_iter_count(i));
return written ? written : status;
static void khugepaged_alloc_sleep(void)
{
- DEFINE_WAIT(wait);
- add_wait_queue(&khugepaged_wait, &wait);
- schedule_timeout_interruptible(
- msecs_to_jiffies(
- khugepaged_alloc_sleep_millisecs));
- remove_wait_queue(&khugepaged_wait, &wait);
+ wait_event_freezable_timeout(khugepaged_wait, false,
+ msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
}
#ifndef CONFIG_NUMA
if (unlikely(kthread_should_stop()))
break;
if (khugepaged_has_work()) {
- DEFINE_WAIT(wait);
if (!khugepaged_scan_sleep_millisecs)
continue;
- add_wait_queue(&khugepaged_wait, &wait);
- schedule_timeout_interruptible(
- msecs_to_jiffies(
- khugepaged_scan_sleep_millisecs));
- remove_wait_queue(&khugepaged_wait, &wait);
+ wait_event_freezable_timeout(khugepaged_wait, false,
+ msecs_to_jiffies(khugepaged_scan_sleep_millisecs));
} else if (khugepaged_enabled())
wait_event_freezable(khugepaged_wait,
khugepaged_wait_event());
__SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
h->resv_huge_pages += delta;
ret = 0;
- spin_unlock(&hugetlb_lock);
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
if ((--needed) < 0)
VM_BUG_ON(page_count(page));
enqueue_huge_page(h, page);
}
+ spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
free:
* anon_vma prepared.
*/
if (unlikely(anon_vma_prepare(vma))) {
+ page_cache_release(new_page);
+ page_cache_release(old_page);
/* Caller expects lock to be held */
spin_lock(&mm->page_table_lock);
return VM_FAULT_OOM;
#include <linux/cpu.h>
#include <linux/oom.h>
#include "internal.h"
+#include <net/sock.h>
+#include <net/tcp_memcontrol.h>
#include <asm/uaccess.h>
*/
struct mem_cgroup_stat_cpu nocpu_base;
spinlock_t pcp_counter_lock;
+
+#ifdef CONFIG_INET
+ struct tcp_memcontrol tcp_mem;
+#endif
};
/* Stuffs for move charges at task migration. */
static void mem_cgroup_get(struct mem_cgroup *memcg);
static void mem_cgroup_put(struct mem_cgroup *memcg);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
+/* Writing them here to avoid exposing memcg's inner layout */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_INET
+#include <net/sock.h>
+#include <net/ip.h>
+
+static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
+void sock_update_memcg(struct sock *sk)
+{
+ /* A socket spends its whole life in the same cgroup */
+ if (sk->sk_cgrp) {
+ WARN_ON(1);
+ return;
+ }
+ if (static_branch(&memcg_socket_limit_enabled)) {
+ struct mem_cgroup *memcg;
+
+ BUG_ON(!sk->sk_prot->proto_cgroup);
+
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(current);
+ if (!mem_cgroup_is_root(memcg)) {
+ mem_cgroup_get(memcg);
+ sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
+ }
+ rcu_read_unlock();
+ }
+}
+EXPORT_SYMBOL(sock_update_memcg);
+
+void sock_release_memcg(struct sock *sk)
+{
+ if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+ struct mem_cgroup *memcg;
+ WARN_ON(!sk->sk_cgrp->memcg);
+ memcg = sk->sk_cgrp->memcg;
+ mem_cgroup_put(memcg);
+ }
+}
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
+{
+ if (!memcg || mem_cgroup_is_root(memcg))
+ return NULL;
+
+ return &memcg->tcp_mem.cg_proto;
+}
+EXPORT_SYMBOL(tcp_proto_cgroup);
+#endif /* CONFIG_INET */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
static void drain_all_stock_async(struct mem_cgroup *memcg);
static struct mem_cgroup_per_zone *
preempt_enable();
}
-static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
return container_of(cgroup_subsys_state(cont,
mem_cgroup_subsys_id), struct mem_cgroup,
}
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ /*
+ * Part of this would be better living in a separate allocation
+ * function, leaving us with just the cgroup tree population work.
+ * We, however, depend on state such as network's proto_list that
+ * is only initialized after cgroup creation. I found the less
+ * cumbersome way to deal with it to defer it all to populate time
+ */
+ return mem_cgroup_sockets_init(cont, ss);
+};
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ mem_cgroup_sockets_destroy(cont, ss);
+}
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ return 0;
+}
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+}
+#endif
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
/*
* Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
*/
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
if (!memcg->res.parent)
return NULL;
return mem_cgroup_from_res_counter(memcg->res.parent, res);
}
+EXPORT_SYMBOL(parent_mem_cgroup);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static void __init enable_swap_cgroup(void)
int cpu;
enable_swap_cgroup();
parent = NULL;
- root_mem_cgroup = memcg;
if (mem_cgroup_soft_limit_tree_init())
goto free_out;
+ root_mem_cgroup = memcg;
for_each_possible_cpu(cpu) {
struct memcg_stock_pcp *stock =
&per_cpu(memcg_stock, cpu);
return &memcg->css;
free_out:
__mem_cgroup_free(memcg);
- root_mem_cgroup = NULL;
return ERR_PTR(error);
}
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ kmem_cgroup_destroy(ss, cont);
+
mem_cgroup_put(memcg);
}
if (!ret)
ret = register_memsw_files(cont, ss);
+
+ if (!ret)
+ ret = register_kmem_files(cont, ss);
+
return ret;
}
struct vm_area_struct *prev;
struct vm_area_struct *vma;
int err = 0;
+ pgoff_t pgoff;
unsigned long vmstart;
unsigned long vmend;
if (!vma || vma->vm_start > start)
return -EFAULT;
+ if (start > vma->vm_start)
+ prev = vma;
+
for (; vma && vma->vm_start < end; prev = vma, vma = next) {
next = vma->vm_next;
vmstart = max(start, vma->vm_start);
vmend = min(end, vma->vm_end);
+ if (mpol_equal(vma_policy(vma), new_pol))
+ continue;
+
+ pgoff = vma->vm_pgoff +
+ ((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+ vma->anon_vma, vma->vm_file, pgoff,
new_pol);
if (prev) {
vma = prev;
if (anon_vma)
put_anon_vma(anon_vma);
-out:
unlock_page(hpage);
+out:
if (rc != -EAGAIN) {
list_del(&hpage->lru);
put_page(hpage);
* between processes, it syncs the pagetable across all
* processes.
*/
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
BUG();
return NULL;
unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
const nodemask_t *nodemask, unsigned long totalpages)
{
- int points;
+ long points;
if (oom_unkillable_task(p, mem, nodemask))
return 0;
if (!p)
return 0;
+ if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+ task_unlock(p);
+ return 0;
+ }
+
/*
* The memory controller may have a limit of 0 bytes, so avoid a divide
* by zero, if necessary.
*
*/
static struct prop_descriptor vm_completions;
-static struct prop_descriptor vm_dirties;
/*
* couple the period to the dirty_ratio:
{
int shift = calc_period_shift();
prop_change_shift(&vm_completions, shift);
- prop_change_shift(&vm_dirties, shift);
writeback_set_ratelimit();
}
}
EXPORT_SYMBOL_GPL(bdi_writeout_inc);
-void task_dirty_inc(struct task_struct *tsk)
-{
- prop_inc_single(&vm_dirties, &tsk->dirties);
-}
-
/*
* Obtain an accurate fraction of the BDI's portion.
*/
*
* Returns @bdi's dirty limit in pages. The term "dirty" in the context of
* dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
- * And the "limit" in the name is not seriously taken as hard limit in
- * balance_dirty_pages().
+ *
+ * Note that balance_dirty_pages() will only seriously take it as a hard limit
+ * when sleeping max_pause per page is not enough to keep the dirty pages under
+ * control. For example, when the device is completely stalled due to some error
+ * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * In the other normal situations, it acts more gently by throttling the tasks
+ * more (rather than completely block them) when the bdi dirty pages go high.
*
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
* - starving fast devices
*/
if (unlikely(bdi_thresh > thresh))
bdi_thresh = thresh;
+ /*
+ * It's very possible that bdi_thresh is close to 0 not because the
+ * device is slow, but that it has remained inactive for long time.
+ * Honour such devices a reasonable good (hopefully IO efficient)
+ * threshold, so that the occasional writes won't be blocked and active
+ * writes can rampup the threshold quickly.
+ */
bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
/*
* scale global setpoint to bdi's:
*
* 8 serves as the safety ratio.
*/
- if (bdi_dirty)
- t = min(t, bdi_dirty * HZ / (8 * bw + 1));
+ t = min(t, bdi_dirty * HZ / (8 * bw + 1));
/*
* The pause time will be settled within range (max_pause/4, max_pause).
pages_dirtied,
pause,
start_time);
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(TASK_KILLABLE);
io_schedule_timeout(pause);
- dirty_thresh = hard_dirty_limit(dirty_thresh);
/*
- * max-pause area. If dirty exceeded but still within this
- * area, no need to sleep for more than 200ms: (a) 8 pages per
- * 200ms is typically more than enough to curb heavy dirtiers;
- * (b) the pause time limit makes the dirtiers more responsive.
+ * This is typically equal to (nr_dirty < dirty_thresh) and can
+ * also keep "1000+ dd on a slow USB stick" under control.
*/
- if (nr_dirty < dirty_thresh)
+ if (task_ratelimit)
+ break;
+
+ /*
+ * In the case of an unresponding NFS server and the NFS dirty
+ * pages exceeds dirty_thresh, give the other good bdi's a pipe
+ * to go through, so that tasks on them still remain responsive.
+ *
+ * In theory 1 page is enough to keep the comsumer-producer
+ * pipe going: the flusher cleans 1 page => the task dirties 1
+ * more page. However bdi_dirty has accounting errors. So use
+ * the larger and more IO friendly bdi_stat_error.
+ */
+ if (bdi_dirty <= bdi_stat_error(bdi))
+ break;
+
+ if (fatal_signal_pending(current))
break;
}
shift = calc_period_shift();
prop_descriptor_init(&vm_completions, shift);
- prop_descriptor_init(&vm_dirties, shift);
}
/**
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
- task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
-
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
unsigned long block_migratetype;
int reserve;
- /* Get the start pfn, end pfn and the number of blocks to reserve */
+ /*
+ * Get the start pfn, end pfn and the number of blocks to reserve
+ * We have to be careful to be aligned to pageblock_nr_pages to
+ * make sure that we always check pfn_valid for the first page in
+ * the block.
+ */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
+ start_pfn = roundup(start_pfn, pageblock_nr_pages);
reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
if (!pages || !bitmap) {
if (may_alloc && !pages)
- pages = pcpu_mem_alloc(pages_size);
+ pages = pcpu_mem_zalloc(pages_size);
if (may_alloc && !bitmap)
- bitmap = pcpu_mem_alloc(bitmap_size);
+ bitmap = pcpu_mem_zalloc(bitmap_size);
if (!pages || !bitmap)
return NULL;
}
- memset(pages, 0, pages_size);
bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
*bitmapp = bitmap;
int page_start, int page_end)
{
flush_cache_vunmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
int page_start, int page_end)
{
flush_tlb_kernel_range(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static int __pcpu_map_pages(unsigned long addr, struct page **pages,
int page_start, int page_end)
{
flush_cache_vmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
/**
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __read_mostly;
(rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
/**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used. The returned
+ * kzalloc() is used; otherwise, vzalloc() is used. The returned
* memory is always zeroed.
*
* CONTEXT:
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
{
if (WARN_ON_ONCE(!slab_is_available()))
return NULL;
* @ptr: memory to free
* @size: size of the area
*
- * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc().
*/
static void pcpu_mem_free(void *ptr, size_t size)
{
size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
unsigned long flags;
- new = pcpu_mem_alloc(new_size);
+ new = pcpu_mem_zalloc(new_size);
if (!new)
return -ENOMEM;
{
struct pcpu_chunk *chunk;
- chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+ chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
if (!chunk)
return NULL;
- chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+ chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+ sizeof(chunk->map[0]));
if (!chunk->map) {
kfree(chunk);
return NULL;
* address. The caller is responsible for ensuring @addr stays valid
* until this function finishes.
*
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
* RETURNS:
* The physical address for @addr.
*/
{
void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
bool in_first_chunk = false;
- unsigned long first_start, first_end;
+ unsigned long first_low, first_high;
unsigned int cpu;
/*
- * The following test on first_start/end isn't strictly
+ * The following test on unit_low/high isn't strictly
* necessary but will speed up lookups of addresses which
* aren't in the first chunk.
*/
- first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
- first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
- pcpu_unit_pages);
- if ((unsigned long)addr >= first_start &&
- (unsigned long)addr < first_end) {
+ first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+ first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+ pcpu_unit_pages);
+ if ((unsigned long)addr >= first_low &&
+ (unsigned long)addr < first_high) {
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(base, cpu);
if (!is_vmalloc_addr(addr))
return __pa(addr);
else
- return page_to_phys(vmalloc_to_page(addr));
+ return page_to_phys(vmalloc_to_page(addr)) +
+ offset_in_page(addr);
} else
- return page_to_phys(pcpu_addr_to_page(addr));
+ return page_to_phys(pcpu_addr_to_page(addr)) +
+ offset_in_page(addr);
}
/**
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
unit_map[cpu] = UINT_MAX;
- pcpu_first_unit_cpu = NR_CPUS;
+
+ pcpu_low_unit_cpu = NR_CPUS;
+ pcpu_high_unit_cpu = NR_CPUS;
for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
const struct pcpu_group_info *gi = &ai->groups[group];
unit_map[cpu] = unit + i;
unit_off[cpu] = gi->base_offset + i * ai->unit_size;
- if (pcpu_first_unit_cpu == NR_CPUS)
- pcpu_first_unit_cpu = cpu;
- pcpu_last_unit_cpu = cpu;
+ /* determine low/high unit_cpu */
+ if (pcpu_low_unit_cpu == NR_CPUS ||
+ unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+ pcpu_low_unit_cpu = cpu;
+ if (pcpu_high_unit_cpu == NR_CPUS ||
+ unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+ pcpu_high_unit_cpu = cpu;
}
}
pcpu_nr_units = unit;
BUILD_BUG_ON(size > PAGE_SIZE);
- map = pcpu_mem_alloc(size);
+ map = pcpu_mem_zalloc(size);
BUG_ON(!map);
spin_lock_irqsave(&pcpu_lock, flags);
PARTIAL_AC,
PARTIAL_L3,
EARLY,
+ LATE,
FULL
} g_cpucache_up;
{
struct cache_sizes *s = malloc_sizes;
- if (g_cpucache_up != FULL)
+ if (g_cpucache_up < LATE)
return;
for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
{
struct kmem_cache *cachep;
+ g_cpucache_up = LATE;
+
/* Annotate slab for lockdep -- annotate the malloc caches */
init_lock_keys();
{
struct kmem_cache_node *n = NULL;
struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
- struct page *page;
+ struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
enum slab_modes { M_PARTIAL, M_FREE };
if (l == M_PARTIAL)
remove_partial(n, page);
else
- add_partial(n, page, 1);
+ add_partial(n, page,
+ DEACTIVATE_TO_TAIL);
l = m;
}
"unfreezing slab"));
if (m == M_FREE) {
- stat(s, DEACTIVATE_EMPTY);
- discard_slab(s, page);
- stat(s, FREE_SLAB);
+ page->next = discard_page;
+ discard_page = page;
}
}
if (n)
spin_unlock(&n->list_lock);
+
+ while (discard_page) {
+ page = discard_page;
+ discard_page = discard_page->next;
+
+ stat(s, DEACTIVATE_EMPTY);
+ discard_slab(s, page);
+ stat(s, FREE_SLAB);
+ }
}
/*
page->pobjects = pobjects;
page->next = oldpage;
- } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+ } while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
stat(s, CPU_PARTIAL_FREE);
return pobjects;
}
for_each_possible_cpu(cpu) {
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+ int node = ACCESS_ONCE(c->node);
struct page *page;
- if (!c || c->node < 0)
+ if (node < 0)
continue;
-
- if (c->page) {
- if (flags & SO_TOTAL)
- x = c->page->objects;
+ page = ACCESS_ONCE(c->page);
+ if (page) {
+ if (flags & SO_TOTAL)
+ x = page->objects;
else if (flags & SO_OBJECTS)
- x = c->page->inuse;
+ x = page->inuse;
else
x = 1;
total += x;
- nodes[c->node] += x;
+ nodes[node] += x;
}
page = c->partial;
if (page) {
x = page->pobjects;
- total += x;
- nodes[c->node] += x;
+ total += x;
+ nodes[node] += x;
}
- per_cpu[c->node]++;
+ per_cpu[node]++;
}
}
unsigned long align, unsigned long flags, unsigned long start,
unsigned long end, int node, gfp_t gfp_mask, void *caller)
{
- static struct vmap_area *va;
+ struct vmap_area *va;
struct vm_struct *area;
BUG_ON(in_interrupt());
goto fail;
addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+ if (!addr)
+ return NULL;
/*
* In this function, newly allocated vm_struct is not added
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
{
- /* apply_to_page_range() does all the hard work. */
+ pte_t ***p = data;
+
+ if (p) {
+ *(*p) = pte;
+ (*p)++;
+ }
return 0;
}
/**
* alloc_vm_area - allocate a range of kernel address space
* @size: size of the area
+ * @ptes: returns the PTEs for the address space
*
* Returns: NULL on failure, vm_struct on success
*
* This function reserves a range of kernel address space, and
* allocates pagetables to map that range. No actual mappings
- * are created. If the kernel address space is not shared
- * between processes, it syncs the pagetable across all
- * processes.
+ * are created.
+ *
+ * If @ptes is non-NULL, pointers to the PTEs (in init_mm)
+ * allocated for the VM area are returned.
*/
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
struct vm_struct *area;
* of kernel virtual address space and mapped into init_mm.
*/
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
- area->size, f, NULL)) {
+ size, f, ptes ? &ptes : NULL)) {
free_vm_area(area);
return NULL;
}
- /*
- * If the allocated address space is passed to a hypercall
- * before being used then we cannot rely on a page fault to
- * trigger an update of the page tables. So sync all the page
- * tables here.
- */
- vmalloc_sync_all();
-
return area;
}
EXPORT_SYMBOL_GPL(alloc_vm_area);
*/
void register_shrinker(struct shrinker *shrinker)
{
- shrinker->nr = 0;
+ atomic_long_set(&shrinker->nr_in_batch, 0);
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
- unsigned long total_scan;
- unsigned long max_pass;
+ long total_scan;
+ long max_pass;
int shrink_ret = 0;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
+ max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+ if (max_pass <= 0)
+ continue;
+
/*
* copy the current shrinker scan count into a local variable
* and zero it so that other concurrent shrinker invocations
* don't also do this scanning work.
*/
- do {
- nr = shrinker->nr;
- } while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+ nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
total_scan = nr;
- max_pass = do_shrinker_shrink(shrinker, shrink, 0);
delta = (4 * nr_pages_scanned) / shrinker->seeks;
delta *= max_pass;
do_div(delta, lru_pages + 1);
* manner that handles concurrent updates. If we exhausted the
* scan, there is no need to do an update.
*/
- do {
- nr = shrinker->nr;
- new_nr = total_scan + nr;
- if (total_scan <= 0)
- break;
- } while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+ if (total_scan > 0)
+ new_nr = atomic_long_add_return(total_scan,
+ &shrinker->nr_in_batch);
+ else
+ new_nr = atomic_long_read(&shrinker->nr_in_batch);
trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
}
/* End of global variables definitions. */
-static void vlan_group_free(struct vlan_group *grp)
-{
- int i;
-
- for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
- kfree(grp->vlan_devices_arrays[i]);
- kfree(grp);
-}
-
-static struct vlan_group *vlan_group_alloc(struct net_device *real_dev)
-{
- struct vlan_group *grp;
-
- grp = kzalloc(sizeof(struct vlan_group), GFP_KERNEL);
- if (!grp)
- return NULL;
-
- grp->real_dev = real_dev;
- return grp;
-}
-
static int vlan_group_prealloc_vid(struct vlan_group *vg, u16 vlan_id)
{
struct net_device **array;
return 0;
}
-static void vlan_rcu_free(struct rcu_head *rcu)
-{
- vlan_group_free(container_of(rcu, struct vlan_group, rcu));
-}
-
void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
- const struct net_device_ops *ops = real_dev->netdev_ops;
+ struct vlan_info *vlan_info;
struct vlan_group *grp;
u16 vlan_id = vlan->vlan_id;
ASSERT_RTNL();
- grp = rtnl_dereference(real_dev->vlgrp);
- BUG_ON(!grp);
+ vlan_info = rtnl_dereference(real_dev->vlan_info);
+ BUG_ON(!vlan_info);
+
+ grp = &vlan_info->grp;
/* Take it out of our own structures, but be sure to interlock with
* HW accelerating devices or SW vlan input packet processing if
* VLAN is not 0 (leave it there for 802.1p).
*/
- if (vlan_id && (real_dev->features & NETIF_F_HW_VLAN_FILTER))
- ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id);
+ if (vlan_id)
+ vlan_vid_del(real_dev, vlan_id);
- grp->nr_vlans--;
+ grp->nr_vlan_devs--;
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_leave(dev);
*/
unregister_netdevice_queue(dev, head);
- /* If the group is now empty, kill off the group. */
- if (grp->nr_vlans == 0) {
+ if (grp->nr_vlan_devs == 0)
vlan_gvrp_uninit_applicant(real_dev);
- RCU_INIT_POINTER(real_dev->vlgrp, NULL);
-
- /* Free the group, after all cpu's are done. */
- call_rcu(&grp->rcu, vlan_rcu_free);
- }
-
/* Get rid of the vlan's reference to real_dev */
dev_put(real_dev);
}
int register_vlan_dev(struct net_device *dev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
- const struct net_device_ops *ops = real_dev->netdev_ops;
u16 vlan_id = vlan->vlan_id;
- struct vlan_group *grp, *ngrp = NULL;
+ struct vlan_info *vlan_info;
+ struct vlan_group *grp;
int err;
- grp = rtnl_dereference(real_dev->vlgrp);
- if (!grp) {
- ngrp = grp = vlan_group_alloc(real_dev);
- if (!grp)
- return -ENOBUFS;
+ err = vlan_vid_add(real_dev, vlan_id);
+ if (err)
+ return err;
+
+ vlan_info = rtnl_dereference(real_dev->vlan_info);
+ /* vlan_info should be there now. vlan_vid_add took care of it */
+ BUG_ON(!vlan_info);
+
+ grp = &vlan_info->grp;
+ if (grp->nr_vlan_devs == 0) {
err = vlan_gvrp_init_applicant(real_dev);
if (err < 0)
- goto out_free_group;
+ goto out_vid_del;
}
err = vlan_group_prealloc_vid(grp, vlan_id);
if (err < 0)
goto out_uninit_applicant;
- /* Account for reference in struct vlan_dev_info */
+ /* Account for reference in struct vlan_dev_priv */
dev_hold(real_dev);
netif_stacked_transfer_operstate(real_dev, dev);
* it into our local structure.
*/
vlan_group_set_device(grp, vlan_id, dev);
- grp->nr_vlans++;
-
- if (ngrp) {
- rcu_assign_pointer(real_dev->vlgrp, ngrp);
- }
- if (real_dev->features & NETIF_F_HW_VLAN_FILTER)
- ops->ndo_vlan_rx_add_vid(real_dev, vlan_id);
+ grp->nr_vlan_devs++;
return 0;
out_uninit_applicant:
- if (ngrp)
+ if (grp->nr_vlan_devs == 0)
vlan_gvrp_uninit_applicant(real_dev);
-out_free_group:
- if (ngrp) {
- /* Free the group, after all cpu's are done. */
- call_rcu(&ngrp->rcu, vlan_rcu_free);
- }
+out_vid_del:
+ vlan_vid_del(real_dev, vlan_id);
return err;
}
snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id);
}
- new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name, vlan_setup);
+ new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, vlan_setup);
if (new_dev == NULL)
return -ENOBUFS;
*/
new_dev->mtu = real_dev->mtu;
- vlan_dev_info(new_dev)->vlan_id = vlan_id;
- vlan_dev_info(new_dev)->real_dev = real_dev;
- vlan_dev_info(new_dev)->dent = NULL;
- vlan_dev_info(new_dev)->flags = VLAN_FLAG_REORDER_HDR;
+ vlan_dev_priv(new_dev)->vlan_id = vlan_id;
+ vlan_dev_priv(new_dev)->real_dev = real_dev;
+ vlan_dev_priv(new_dev)->dent = NULL;
+ vlan_dev_priv(new_dev)->flags = VLAN_FLAG_REORDER_HDR;
new_dev->rtnl_link_ops = &vlan_link_ops;
err = register_vlan_dev(new_dev);
static void vlan_sync_address(struct net_device *dev,
struct net_device *vlandev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(vlandev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
/* May be called without an actual change */
if (!compare_ether_addr(vlan->real_dev_addr, dev->dev_addr))
{
struct net_device *dev = ptr;
struct vlan_group *grp;
+ struct vlan_info *vlan_info;
int i, flgs;
struct net_device *vlandev;
- struct vlan_dev_info *vlan;
+ struct vlan_dev_priv *vlan;
LIST_HEAD(list);
if (is_vlan_dev(dev))
__vlan_device_event(dev, event);
if ((event == NETDEV_UP) &&
- (dev->features & NETIF_F_HW_VLAN_FILTER) &&
- dev->netdev_ops->ndo_vlan_rx_add_vid) {
+ (dev->features & NETIF_F_HW_VLAN_FILTER)) {
pr_info("adding VLAN 0 to HW filter on device %s\n",
dev->name);
- dev->netdev_ops->ndo_vlan_rx_add_vid(dev, 0);
+ vlan_vid_add(dev, 0);
}
- grp = rtnl_dereference(dev->vlgrp);
- if (!grp)
+ vlan_info = rtnl_dereference(dev->vlan_info);
+ if (!vlan_info)
goto out;
+ grp = &vlan_info->grp;
/* It is OK that we do not hold the group lock right now,
* as we run under the RTNL lock.
if (!(flgs & IFF_UP))
continue;
- vlan = vlan_dev_info(vlandev);
+ vlan = vlan_dev_priv(vlandev);
if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
dev_change_flags(vlandev, flgs & ~IFF_UP);
netif_stacked_transfer_operstate(dev, vlandev);
if (flgs & IFF_UP)
continue;
- vlan = vlan_dev_info(vlandev);
+ vlan = vlan_dev_priv(vlandev);
if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
dev_change_flags(vlandev, flgs | IFF_UP);
netif_stacked_transfer_operstate(dev, vlandev);
if (!vlandev)
continue;
- /* unregistration of last vlan destroys group, abort
+ /* removal of last vid destroys vlan_info, abort
* afterwards */
- if (grp->nr_vlans == 1)
+ if (vlan_info->nr_vids == 1)
i = VLAN_N_VID;
unregister_vlan_dev(vlandev, &list);
#include <linux/if_vlan.h>
#include <linux/u64_stats_sync.h>
+#include <linux/list.h>
/**
u32 tx_dropped;
};
+struct netpoll;
+
/**
- * struct vlan_dev_info - VLAN private device data
+ * struct vlan_dev_priv - VLAN private device data
* @nr_ingress_mappings: number of ingress priority mappings
* @ingress_priority_map: ingress priority mappings
* @nr_egress_mappings: number of egress priority mappings
* @dent: proc dir entry
* @vlan_pcpu_stats: ptr to percpu rx stats
*/
-struct vlan_dev_info {
+struct vlan_dev_priv {
unsigned int nr_ingress_mappings;
u32 ingress_priority_map[8];
unsigned int nr_egress_mappings;
struct proc_dir_entry *dent;
struct vlan_pcpu_stats __percpu *vlan_pcpu_stats;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ struct netpoll *netpoll;
+#endif
};
-static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev)
+static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
{
return netdev_priv(dev);
}
+/* if this changes, algorithm will have to be reworked because this
+ * depends on completely exhausting the VLAN identifier space. Thus
+ * it gives constant time look-up, but in many cases it wastes memory.
+ */
+#define VLAN_GROUP_ARRAY_SPLIT_PARTS 8
+#define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS)
+
+struct vlan_group {
+ unsigned int nr_vlan_devs;
+ struct hlist_node hlist; /* linked list */
+ struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS];
+};
+
+struct vlan_info {
+ struct net_device *real_dev; /* The ethernet(like) device
+ * the vlan is attached to.
+ */
+ struct vlan_group grp;
+ struct list_head vid_list;
+ unsigned int nr_vids;
+ struct rcu_head rcu;
+};
+
static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
u16 vlan_id)
{
static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
u16 vlan_id)
{
- struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp);
+ struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info);
- if (grp)
- return vlan_group_get_device(grp, vlan_id);
+ if (vlan_info)
+ return vlan_group_get_device(&vlan_info->grp, vlan_id);
return NULL;
}
static inline u32 vlan_get_ingress_priority(struct net_device *dev,
u16 vlan_tci)
{
- struct vlan_dev_info *vip = vlan_dev_info(dev);
+ struct vlan_dev_priv *vip = vlan_dev_priv(dev);
return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7];
}
skb->pkt_type = PACKET_HOST;
}
- if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+ if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
unsigned int offset = skb->data - skb_mac_header(skb);
/*
skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
skb->vlan_tci = 0;
- rx_stats = this_cpu_ptr(vlan_dev_info(vlan_dev)->vlan_pcpu_stats);
+ rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->rx_packets++;
struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
u16 vlan_id)
{
- struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp);
+ struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info);
- if (grp) {
- return vlan_group_get_device(grp, vlan_id);
+ if (vlan_info) {
+ return vlan_group_get_device(&vlan_info->grp, vlan_id);
} else {
/*
* Bonding slaves do not have grp assigned to themselves.
struct net_device *vlan_dev_real_dev(const struct net_device *dev)
{
- return vlan_dev_info(dev)->real_dev;
+ return vlan_dev_priv(dev)->real_dev;
}
EXPORT_SYMBOL(vlan_dev_real_dev);
u16 vlan_dev_vlan_id(const struct net_device *dev)
{
- return vlan_dev_info(dev)->vlan_id;
+ return vlan_dev_priv(dev)->vlan_id;
}
EXPORT_SYMBOL(vlan_dev_vlan_id);
return skb;
}
-static void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr)
-{
- __be16 proto;
- unsigned char *rawp;
-
- /*
- * Was a VLAN packet, grab the encapsulated protocol, which the layer
- * three protocols care about.
- */
-
- proto = vhdr->h_vlan_encapsulated_proto;
- if (ntohs(proto) >= 1536) {
- skb->protocol = proto;
- return;
- }
-
- rawp = skb->data;
- if (*(unsigned short *) rawp == 0xFFFF)
- /*
- * This is a magic hack to spot IPX packets. Older Novell
- * breaks the protocol design and runs IPX over 802.3 without
- * an 802.2 LLC layer. We look for FFFF which isn't a used
- * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
- * but does for the rest.
- */
- skb->protocol = htons(ETH_P_802_3);
- else
- /*
- * Real 802.2 LLC
- */
- skb->protocol = htons(ETH_P_802_2);
-}
-
struct sk_buff *vlan_untag(struct sk_buff *skb)
{
struct vlan_hdr *vhdr;
kfree_skb(skb);
return NULL;
}
+
+
+/*
+ * vlan info and vid list
+ */
+
+static void vlan_group_free(struct vlan_group *grp)
+{
+ int i;
+
+ for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
+ kfree(grp->vlan_devices_arrays[i]);
+}
+
+static void vlan_info_free(struct vlan_info *vlan_info)
+{
+ vlan_group_free(&vlan_info->grp);
+ kfree(vlan_info);
+}
+
+static void vlan_info_rcu_free(struct rcu_head *rcu)
+{
+ vlan_info_free(container_of(rcu, struct vlan_info, rcu));
+}
+
+static struct vlan_info *vlan_info_alloc(struct net_device *dev)
+{
+ struct vlan_info *vlan_info;
+
+ vlan_info = kzalloc(sizeof(struct vlan_info), GFP_KERNEL);
+ if (!vlan_info)
+ return NULL;
+
+ vlan_info->real_dev = dev;
+ INIT_LIST_HEAD(&vlan_info->vid_list);
+ return vlan_info;
+}
+
+struct vlan_vid_info {
+ struct list_head list;
+ unsigned short vid;
+ int refcount;
+};
+
+static struct vlan_vid_info *vlan_vid_info_get(struct vlan_info *vlan_info,
+ unsigned short vid)
+{
+ struct vlan_vid_info *vid_info;
+
+ list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+ if (vid_info->vid == vid)
+ return vid_info;
+ }
+ return NULL;
+}
+
+static struct vlan_vid_info *vlan_vid_info_alloc(unsigned short vid)
+{
+ struct vlan_vid_info *vid_info;
+
+ vid_info = kzalloc(sizeof(struct vlan_vid_info), GFP_KERNEL);
+ if (!vid_info)
+ return NULL;
+ vid_info->vid = vid;
+
+ return vid_info;
+}
+
+static int __vlan_vid_add(struct vlan_info *vlan_info, unsigned short vid,
+ struct vlan_vid_info **pvid_info)
+{
+ struct net_device *dev = vlan_info->real_dev;
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct vlan_vid_info *vid_info;
+ int err;
+
+ vid_info = vlan_vid_info_alloc(vid);
+ if (!vid_info)
+ return -ENOMEM;
+
+ if ((dev->features & NETIF_F_HW_VLAN_FILTER) &&
+ ops->ndo_vlan_rx_add_vid) {
+ err = ops->ndo_vlan_rx_add_vid(dev, vid);
+ if (err) {
+ kfree(vid_info);
+ return err;
+ }
+ }
+ list_add(&vid_info->list, &vlan_info->vid_list);
+ vlan_info->nr_vids++;
+ *pvid_info = vid_info;
+ return 0;
+}
+
+int vlan_vid_add(struct net_device *dev, unsigned short vid)
+{
+ struct vlan_info *vlan_info;
+ struct vlan_vid_info *vid_info;
+ bool vlan_info_created = false;
+ int err;
+
+ ASSERT_RTNL();
+
+ vlan_info = rtnl_dereference(dev->vlan_info);
+ if (!vlan_info) {
+ vlan_info = vlan_info_alloc(dev);
+ if (!vlan_info)
+ return -ENOMEM;
+ vlan_info_created = true;
+ }
+ vid_info = vlan_vid_info_get(vlan_info, vid);
+ if (!vid_info) {
+ err = __vlan_vid_add(vlan_info, vid, &vid_info);
+ if (err)
+ goto out_free_vlan_info;
+ }
+ vid_info->refcount++;
+
+ if (vlan_info_created)
+ rcu_assign_pointer(dev->vlan_info, vlan_info);
+
+ return 0;
+
+out_free_vlan_info:
+ if (vlan_info_created)
+ kfree(vlan_info);
+ return err;
+}
+EXPORT_SYMBOL(vlan_vid_add);
+
+static void __vlan_vid_del(struct vlan_info *vlan_info,
+ struct vlan_vid_info *vid_info)
+{
+ struct net_device *dev = vlan_info->real_dev;
+ const struct net_device_ops *ops = dev->netdev_ops;
+ unsigned short vid = vid_info->vid;
+ int err;
+
+ if ((dev->features & NETIF_F_HW_VLAN_FILTER) &&
+ ops->ndo_vlan_rx_kill_vid) {
+ err = ops->ndo_vlan_rx_kill_vid(dev, vid);
+ if (err) {
+ pr_warn("failed to kill vid %d for device %s\n",
+ vid, dev->name);
+ }
+ }
+ list_del(&vid_info->list);
+ kfree(vid_info);
+ vlan_info->nr_vids--;
+}
+
+void vlan_vid_del(struct net_device *dev, unsigned short vid)
+{
+ struct vlan_info *vlan_info;
+ struct vlan_vid_info *vid_info;
+
+ ASSERT_RTNL();
+
+ vlan_info = rtnl_dereference(dev->vlan_info);
+ if (!vlan_info)
+ return;
+
+ vid_info = vlan_vid_info_get(vlan_info, vid);
+ if (!vid_info)
+ return;
+ vid_info->refcount--;
+ if (vid_info->refcount == 0) {
+ __vlan_vid_del(vlan_info, vid_info);
+ if (vlan_info->nr_vids == 0) {
+ RCU_INIT_POINTER(dev->vlan_info, NULL);
+ call_rcu(&vlan_info->rcu, vlan_info_rcu_free);
+ }
+ }
+}
+EXPORT_SYMBOL(vlan_vid_del);
+
+int vlan_vids_add_by_dev(struct net_device *dev,
+ const struct net_device *by_dev)
+{
+ struct vlan_vid_info *vid_info;
+ struct vlan_info *vlan_info;
+ int err;
+
+ ASSERT_RTNL();
+
+ vlan_info = rtnl_dereference(by_dev->vlan_info);
+ if (!vlan_info)
+ return 0;
+
+ list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+ err = vlan_vid_add(dev, vid_info->vid);
+ if (err)
+ goto unwind;
+ }
+ return 0;
+
+unwind:
+ list_for_each_entry_continue_reverse(vid_info,
+ &vlan_info->vid_list,
+ list) {
+ vlan_vid_del(dev, vid_info->vid);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(vlan_vids_add_by_dev);
+
+void vlan_vids_del_by_dev(struct net_device *dev,
+ const struct net_device *by_dev)
+{
+ struct vlan_vid_info *vid_info;
+ struct vlan_info *vlan_info;
+
+ ASSERT_RTNL();
+
+ vlan_info = rtnl_dereference(by_dev->vlan_info);
+ if (!vlan_info)
+ return;
+
+ list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+ vlan_vid_del(dev, vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_vids_del_by_dev);
#include "vlan.h"
#include "vlanproc.h"
#include <linux/if_vlan.h>
+#include <linux/netpoll.h>
/*
* Rebuild the Ethernet MAC header. This is called after an ARP
{
struct vlan_priority_tci_mapping *mp;
- mp = vlan_dev_info(dev)->egress_priority_map[(skb->priority & 0xF)];
+ mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)];
while (mp) {
if (mp->priority == skb->priority) {
return mp->vlan_qos; /* This should already be shifted
u16 vlan_tci = 0;
int rc;
- if (!(vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+ if (!(vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR)) {
vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
- vlan_tci = vlan_dev_info(dev)->vlan_id;
+ vlan_tci = vlan_dev_priv(dev)->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
vhdr->h_vlan_TCI = htons(vlan_tci);
saddr = dev->dev_addr;
/* Now make the underlying real hard header */
- dev = vlan_dev_info(dev)->real_dev;
+ dev = vlan_dev_priv(dev)->real_dev;
rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen);
if (rc > 0)
rc += vhdrlen;
* OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
*/
if (veth->h_vlan_proto != htons(ETH_P_8021Q) ||
- vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR) {
+ vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR) {
u16 vlan_tci;
- vlan_tci = vlan_dev_info(dev)->vlan_id;
+ vlan_tci = vlan_dev_priv(dev)->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
}
- skb_set_dev(skb, vlan_dev_info(dev)->real_dev);
+ skb_set_dev(skb, vlan_dev_priv(dev)->real_dev);
len = skb->len;
+ if (netpoll_tx_running(dev))
+ return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev);
ret = dev_queue_xmit(skb);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *stats;
- stats = this_cpu_ptr(vlan_dev_info(dev)->vlan_pcpu_stats);
+ stats = this_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += len;
u64_stats_update_end(&stats->syncp);
} else {
- this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
+ this_cpu_inc(vlan_dev_priv(dev)->vlan_pcpu_stats->tx_dropped);
}
return ret;
/* TODO: gotta make sure the underlying layer can handle it,
* maybe an IFF_VLAN_CAPABLE flag for devices?
*/
- if (vlan_dev_info(dev)->real_dev->mtu < new_mtu)
+ if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu)
return -ERANGE;
dev->mtu = new_mtu;
void vlan_dev_set_ingress_priority(const struct net_device *dev,
u32 skb_prio, u16 vlan_prio)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio)
vlan->nr_ingress_mappings--;
int vlan_dev_set_egress_priority(const struct net_device *dev,
u32 skb_prio, u16 vlan_prio)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_priority_tci_mapping *mp = NULL;
struct vlan_priority_tci_mapping *np;
u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */
int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
u32 old_flags = vlan->flags;
if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
{
- strncpy(result, vlan_dev_info(dev)->real_dev->name, 23);
+ strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
}
static int vlan_dev_open(struct net_device *dev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
int err;
static int vlan_dev_stop(struct net_device *dev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
dev_mc_unsync(real_dev, dev);
static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
struct sockaddr *addr = p;
int err;
static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
struct ifreq ifrr;
int err = -EOPNOTSUPP;
static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int err = 0;
static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = 0;
static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int len = 0;
static int vlan_dev_fcoe_enable(struct net_device *dev)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = -EINVAL;
static int vlan_dev_fcoe_disable(struct net_device *dev)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = -EINVAL;
static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = -EINVAL;
static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
int rc = 0;
static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
{
- dev_mc_sync(vlan_dev_info(vlan_dev)->real_dev, vlan_dev);
- dev_uc_sync(vlan_dev_info(vlan_dev)->real_dev, vlan_dev);
+ dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+ dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
/*
static int vlan_dev_init(struct net_device *dev)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
int subclass = 0;
netif_carrier_off(dev);
vlan_dev_set_lockdep_class(dev, subclass);
- vlan_dev_info(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
- if (!vlan_dev_info(dev)->vlan_pcpu_stats)
+ vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+ if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
return -ENOMEM;
return 0;
static void vlan_dev_uninit(struct net_device *dev)
{
struct vlan_priority_tci_mapping *pm;
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
int i;
free_percpu(vlan->vlan_pcpu_stats);
}
}
-static u32 vlan_dev_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
- struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
u32 old_features = features;
- features &= real_dev->features;
features &= real_dev->vlan_features;
+ features |= NETIF_F_RXCSUM;
+ features &= real_dev->features;
features |= old_features & NETIF_F_SOFT_FEATURES;
-
- if (dev_ethtool_get_rx_csum(real_dev))
- features |= NETIF_F_RXCSUM;
features |= NETIF_F_LLTX;
return features;
static int vlan_ethtool_get_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
- const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
return __ethtool_get_settings(vlan->real_dev, cmd);
}
static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
- if (vlan_dev_info(dev)->vlan_pcpu_stats) {
+ if (vlan_dev_priv(dev)->vlan_pcpu_stats) {
struct vlan_pcpu_stats *p;
u32 rx_errors = 0, tx_dropped = 0;
int i;
u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
unsigned int start;
- p = per_cpu_ptr(vlan_dev_info(dev)->vlan_pcpu_stats, i);
+ p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
do {
start = u64_stats_fetch_begin_bh(&p->syncp);
rxpackets = p->rx_packets;
return stats;
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void vlan_dev_poll_controller(struct net_device *dev)
+{
+ return;
+}
+
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
+{
+ struct vlan_dev_priv *info = vlan_dev_priv(dev);
+ struct net_device *real_dev = info->real_dev;
+ struct netpoll *netpoll;
+ int err = 0;
+
+ netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+ err = -ENOMEM;
+ if (!netpoll)
+ goto out;
+
+ netpoll->dev = real_dev;
+ strlcpy(netpoll->dev_name, real_dev->name, IFNAMSIZ);
+
+ err = __netpoll_setup(netpoll);
+ if (err) {
+ kfree(netpoll);
+ goto out;
+ }
+
+ info->netpoll = netpoll;
+
+out:
+ return err;
+}
+
+static void vlan_dev_netpoll_cleanup(struct net_device *dev)
+{
+ struct vlan_dev_priv *info = vlan_dev_priv(dev);
+ struct netpoll *netpoll = info->netpoll;
+
+ if (!netpoll)
+ return;
+
+ info->netpoll = NULL;
+
+ /* Wait for transmitting packets to finish before freeing. */
+ synchronize_rcu_bh();
+
+ __netpoll_cleanup(netpoll);
+ kfree(netpoll);
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
static const struct ethtool_ops vlan_ethtool_ops = {
.get_settings = vlan_ethtool_get_settings,
.get_drvinfo = vlan_ethtool_get_drvinfo,
.ndo_fcoe_disable = vlan_dev_fcoe_disable,
.ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn,
.ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target,
+#endif
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = vlan_dev_poll_controller,
+ .ndo_netpoll_setup = vlan_dev_netpoll_setup,
+ .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup,
#endif
.ndo_fix_features = vlan_dev_fix_features,
};
int vlan_gvrp_request_join(const struct net_device *dev)
{
- const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
__be16 vlan_id = htons(vlan->vlan_id);
return garp_request_join(vlan->real_dev, &vlan_gvrp_app,
void vlan_gvrp_request_leave(const struct net_device *dev)
{
- const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
__be16 vlan_id = htons(vlan->vlan_id);
garp_request_leave(vlan->real_dev, &vlan_gvrp_app,
static int vlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev;
int err;
static size_t vlan_get_size(const struct net_device *dev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
return nla_total_size(2) + /* IFLA_VLAN_ID */
sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
- struct vlan_dev_info *vlan = vlan_dev_info(dev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_priority_tci_mapping *pm;
struct ifla_vlan_flags f;
struct ifla_vlan_qos_mapping m;
struct nlattr *nest;
unsigned int i;
- NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_info(dev)->vlan_id);
+ NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_priv(dev)->vlan_id);
if (vlan->flags) {
f.flags = vlan->flags;
f.mask = ~0;
.kind = "vlan",
.maxtype = IFLA_VLAN_MAX,
.policy = vlan_policy,
- .priv_size = sizeof(struct vlan_dev_info),
+ .priv_size = sizeof(struct vlan_dev_priv),
.setup = vlan_setup,
.validate = vlan_validate,
.newlink = vlan_newlink,
int vlan_proc_add_dev(struct net_device *vlandev)
{
- struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id);
- dev_info->dent =
+ vlan->dent =
proc_create_data(vlandev->name, S_IFREG|S_IRUSR|S_IWUSR,
vn->proc_vlan_dir, &vlandev_fops, vlandev);
- if (!dev_info->dent)
+ if (!vlan->dent)
return -ENOBUFS;
return 0;
}
struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id);
/** NOTE: This will consume the memory pointed to by dent, it seems. */
- if (vlan_dev_info(vlandev)->dent) {
- remove_proc_entry(vlan_dev_info(vlandev)->dent->name,
+ if (vlan_dev_priv(vlandev)->dent) {
+ remove_proc_entry(vlan_dev_priv(vlandev)->dent->name,
vn->proc_vlan_dir);
- vlan_dev_info(vlandev)->dent = NULL;
+ vlan_dev_priv(vlandev)->dent = NULL;
}
return 0;
}
nmtype ? nmtype : "UNKNOWN");
} else {
const struct net_device *vlandev = v;
- const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+ const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
seq_printf(seq, "%-15s| %d | %s\n", vlandev->name,
- dev_info->vlan_id, dev_info->real_dev->name);
+ vlan->vlan_id, vlan->real_dev->name);
}
return 0;
}
static int vlandev_seq_show(struct seq_file *seq, void *offset)
{
struct net_device *vlandev = (struct net_device *) seq->private;
- const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+ const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
struct rtnl_link_stats64 temp;
const struct rtnl_link_stats64 *stats;
static const char fmt64[] = "%30s %12llu\n";
stats = dev_get_stats(vlandev, &temp);
seq_printf(seq,
"%s VID: %d REORDER_HDR: %i dev->priv_flags: %hx\n",
- vlandev->name, dev_info->vlan_id,
- (int)(dev_info->flags & 1), vlandev->priv_flags);
+ vlandev->name, vlan->vlan_id,
+ (int)(vlan->flags & 1), vlandev->priv_flags);
seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
seq_puts(seq, "\n");
seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
- seq_printf(seq, "Device: %s", dev_info->real_dev->name);
+ seq_printf(seq, "Device: %s", vlan->real_dev->name);
/* now show all PRIORITY mappings relating to this VLAN */
seq_printf(seq, "\nINGRESS priority mappings: "
"0:%u 1:%u 2:%u 3:%u 4:%u 5:%u 6:%u 7:%u\n",
- dev_info->ingress_priority_map[0],
- dev_info->ingress_priority_map[1],
- dev_info->ingress_priority_map[2],
- dev_info->ingress_priority_map[3],
- dev_info->ingress_priority_map[4],
- dev_info->ingress_priority_map[5],
- dev_info->ingress_priority_map[6],
- dev_info->ingress_priority_map[7]);
+ vlan->ingress_priority_map[0],
+ vlan->ingress_priority_map[1],
+ vlan->ingress_priority_map[2],
+ vlan->ingress_priority_map[3],
+ vlan->ingress_priority_map[4],
+ vlan->ingress_priority_map[5],
+ vlan->ingress_priority_map[6],
+ vlan->ingress_priority_map[7]);
seq_printf(seq, " EGRESS priority mappings: ");
for (i = 0; i < 16; i++) {
const struct vlan_priority_tci_mapping *mp
- = dev_info->egress_priority_map[i];
+ = vlan->egress_priority_map[i];
while (mp) {
seq_printf(seq, "%u:%hu ",
mp->priority, ((mp->vlan_qos >> 13) & 0x7));
source "net/dcb/Kconfig"
source "net/dns_resolver/Kconfig"
source "net/batman-adv/Kconfig"
+source "net/openvswitch/Kconfig"
config RPS
boolean
depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
default y
+config NETPRIO_CGROUP
+ tristate "Network priority cgroup"
+ depends on CGROUPS
+ ---help---
+ Cgroup subsystem for use in assigning processes to network priorities on
+ a per-interface basis
+
+config BQL
+ boolean
+ depends on SYSFS
+ select DQL
+ default y
+
config HAVE_BPF_JIT
bool
obj-$(CONFIG_CEPH_LIB) += ceph/
obj-$(CONFIG_BATMAN_ADV) += batman-adv/
obj-$(CONFIG_NFC) += nfc/
+obj-$(CONFIG_OPENVSWITCH) += openvswitch/
gfp_t gfp_flags)
{
struct sock *sk = sk_atm(vcc);
- int guess = atm_guess_pdu2truesize(pdu_size);
+ int guess = SKB_TRUESIZE(pdu_size);
atm_force_charge(vcc, guess);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
static const unsigned char ethertype_ipv6[] = { ETHERTYPE_IPV6 };
static const unsigned char llc_oui_pid_pad[] =
{ LLC, SNAP_BRIDGED, PID_ETHERNET, PAD_BRIDGED };
+static const unsigned char pad[] = { PAD_BRIDGED };
static const unsigned char llc_oui_ipv4[] = { LLC, SNAP_ROUTED, ETHERTYPE_IPV4 };
static const unsigned char llc_oui_ipv6[] = { LLC, SNAP_ROUTED, ETHERTYPE_IPV6 };
{
struct br2684_dev *brdev = BRPRIV(dev);
struct atm_vcc *atmvcc;
- int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2;
+ int minheadroom = (brvcc->encaps == e_llc) ?
+ ((brdev->payload == p_bridged) ?
+ sizeof(llc_oui_pid_pad) : sizeof(llc_oui_ipv4)) :
+ ((brdev->payload == p_bridged) ? BR2684_PAD_LEN : 0);
if (skb_headroom(skb) < minheadroom) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, minheadroom);
skb->pkt_type = PACKET_HOST;
} else { /* p_bridged */
/* first 2 chars should be 0 */
- if (*((u16 *) (skb->data)) != 0)
+ if (memcmp(skb->data, pad, BR2684_PAD_LEN) != 0)
goto error;
skb_pull(skb, BR2684_PAD_LEN);
skb->protocol = eth_type_trans(skb, net_dev);
*/
static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
{
- struct sk_buff_head queue;
- int err;
struct br2684_vcc *brvcc;
- struct sk_buff *skb, *tmp;
- struct sk_buff_head *rq;
struct br2684_dev *brdev;
struct net_device *net_dev;
struct atm_backend_br2684 be;
- unsigned long flags;
+ int err;
if (copy_from_user(&be, arg, sizeof be))
return -EFAULT;
atmvcc->push = br2684_push;
atmvcc->pop = br2684_pop;
- __skb_queue_head_init(&queue);
- rq = &sk_atm(atmvcc)->sk_receive_queue;
-
- spin_lock_irqsave(&rq->lock, flags);
- skb_queue_splice_init(rq, &queue);
- spin_unlock_irqrestore(&rq->lock, flags);
-
- skb_queue_walk_safe(&queue, skb, tmp) {
- struct net_device *dev;
-
- br2684_push(atmvcc, skb);
- dev = skb->dev;
-
- dev->stats.rx_bytes -= skb->len;
- dev->stats.rx_packets--;
- }
-
/* initialize netdev carrier state */
if (atmvcc->dev->signal == ATM_PHY_SIG_LOST)
netif_carrier_off(net_dev);
netif_carrier_on(net_dev);
__module_get(THIS_MODULE);
+
+ /* re-process everything received between connection setup and
+ backend setup */
+ vcc_process_recv_queue(atmvcc);
return 0;
error:
struct br2684_dev *brdev = BRPRIV(netdev);
ether_setup(netdev);
+ netdev->hard_header_len += sizeof(llc_oui_pid_pad); /* worst case */
brdev->net_dev = netdev;
netdev->netdev_ops = &br2684_netdev_ops;
struct br2684_dev *brdev = BRPRIV(netdev);
brdev->net_dev = netdev;
- netdev->hard_header_len = 0;
+ netdev->hard_header_len = sizeof(llc_oui_ipv4); /* worst case */
netdev->netdev_ops = &br2684_netdev_ops_routed;
netdev->addr_len = 0;
netdev->mtu = 1500;
#include <linux/slab.h>
#include <net/route.h> /* for struct rtable and routing */
#include <net/icmp.h> /* icmp_send */
+#include <net/arp.h>
#include <linux/param.h> /* for HZ */
#include <linux/uaccess.h>
#include <asm/byteorder.h> /* for htons etc. */
/* The neighbour entry n->lock is held. */
static int neigh_check_cb(struct neighbour *n)
{
- struct atmarp_entry *entry = NEIGH2ENTRY(n);
+ struct atmarp_entry *entry = neighbour_priv(n);
struct clip_vcc *cv;
for (cv = entry->vccs; cv; cv = cv->next) {
struct clip_vcc *clip_vcc = CLIP_VCC(vcc);
pr_debug("\n");
+
+ if (!clip_devs) {
+ atm_return(vcc, skb->truesize);
+ kfree_skb(skb);
+ return;
+ }
+
if (!skb) {
pr_debug("removing VCC %p\n", clip_vcc);
if (clip_vcc->entry)
static void clip_neigh_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
+ __be32 *ip = (__be32 *) neigh->primary_key;
+
pr_debug("(neigh %p, skb %p)\n", neigh, skb);
- to_atmarpd(act_need, PRIV(neigh->dev)->number, NEIGH2ENTRY(neigh)->ip);
+ to_atmarpd(act_need, PRIV(neigh->dev)->number, *ip);
}
static void clip_neigh_error(struct neighbour *neigh, struct sk_buff *skb)
static int clip_constructor(struct neighbour *neigh)
{
- struct atmarp_entry *entry = NEIGH2ENTRY(neigh);
- struct net_device *dev = neigh->dev;
- struct in_device *in_dev;
- struct neigh_parms *parms;
+ struct atmarp_entry *entry = neighbour_priv(neigh);
- pr_debug("(neigh %p, entry %p)\n", neigh, entry);
- neigh->type = inet_addr_type(&init_net, entry->ip);
- if (neigh->type != RTN_UNICAST)
+ if (neigh->tbl->family != AF_INET)
return -EINVAL;
- rcu_read_lock();
- in_dev = __in_dev_get_rcu(dev);
- if (!in_dev) {
- rcu_read_unlock();
+ if (neigh->type != RTN_UNICAST)
return -EINVAL;
- }
-
- parms = in_dev->arp_parms;
- __neigh_parms_put(neigh->parms);
- neigh->parms = neigh_parms_clone(parms);
- rcu_read_unlock();
+ neigh->nud_state = NUD_NONE;
neigh->ops = &clip_neigh_ops;
- neigh->output = neigh->nud_state & NUD_VALID ?
- neigh->ops->connected_output : neigh->ops->output;
+ neigh->output = neigh->ops->output;
entry->neigh = neigh;
entry->vccs = NULL;
entry->expires = jiffies - 1;
+
return 0;
}
-static u32 clip_hash(const void *pkey, const struct net_device *dev, __u32 rnd)
-{
- return jhash_2words(*(u32 *) pkey, dev->ifindex, rnd);
-}
-
-static struct neigh_table clip_tbl = {
- .family = AF_INET,
- .entry_size = sizeof(struct neighbour)+sizeof(struct atmarp_entry),
- .key_len = 4,
- .hash = clip_hash,
- .constructor = clip_constructor,
- .id = "clip_arp_cache",
-
- /* parameters are copied from ARP ... */
- .parms = {
- .tbl = &clip_tbl,
- .base_reachable_time = 30 * HZ,
- .retrans_time = 1 * HZ,
- .gc_staletime = 60 * HZ,
- .reachable_time = 30 * HZ,
- .delay_probe_time = 5 * HZ,
- .queue_len = 3,
- .ucast_probes = 3,
- .mcast_probes = 3,
- .anycast_delay = 1 * HZ,
- .proxy_delay = (8 * HZ) / 10,
- .proxy_qlen = 64,
- .locktime = 1 * HZ,
- },
- .gc_interval = 30 * HZ,
- .gc_thresh1 = 128,
- .gc_thresh2 = 512,
- .gc_thresh3 = 1024,
-};
-
/* @@@ copy bh locking from arp.c -- need to bh-enable atm code before */
/*
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
if (!n) {
-#if 0
- n = clip_find_neighbour(skb_dst(skb), 1);
- if (!n) {
- dev_kfree_skb(skb); /* lost that one */
- dev->stats.tx_dropped++;
- return 0;
- }
- dst_set_neighbour(dst, n);
-#endif
pr_err("NO NEIGHBOUR !\n");
dev_kfree_skb(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
- entry = NEIGH2ENTRY(n);
+ entry = neighbour_priv(n);
if (!entry->vccs) {
if (time_after(jiffies, entry->expires)) {
/* should be resolved */
entry->expires = jiffies + ATMARP_RETRY_DELAY * HZ;
- to_atmarpd(act_need, PRIV(dev)->number, entry->ip);
+ to_atmarpd(act_need, PRIV(dev)->number, *((__be32 *)n->primary_key));
}
if (entry->neigh->arp_queue.qlen < ATMARP_MAX_UNRES_PACKETS)
skb_queue_tail(&entry->neigh->arp_queue, skb);
static int clip_mkip(struct atm_vcc *vcc, int timeout)
{
- struct sk_buff_head *rq, queue;
struct clip_vcc *clip_vcc;
- struct sk_buff *skb, *tmp;
- unsigned long flags;
if (!vcc->push)
return -EBADFD;
vcc->push = clip_push;
vcc->pop = clip_pop;
- __skb_queue_head_init(&queue);
- rq = &sk_atm(vcc)->sk_receive_queue;
-
- spin_lock_irqsave(&rq->lock, flags);
- skb_queue_splice_init(rq, &queue);
- spin_unlock_irqrestore(&rq->lock, flags);
-
/* re-process everything received between connection setup and MKIP */
- skb_queue_walk_safe(&queue, skb, tmp) {
- if (!clip_devs) {
- atm_return(vcc, skb->truesize);
- kfree_skb(skb);
- } else {
- struct net_device *dev = skb->dev;
- unsigned int len = skb->len;
-
- skb_get(skb);
- clip_push(vcc, skb);
- dev->stats.rx_packets--;
- dev->stats.rx_bytes -= len;
- kfree_skb(skb);
- }
- }
+ vcc_process_recv_queue(vcc);
+
return 0;
}
rt = ip_route_output(&init_net, ip, 0, 1, 0);
if (IS_ERR(rt))
return PTR_ERR(rt);
- neigh = __neigh_lookup(&clip_tbl, &ip, rt->dst.dev, 1);
+ neigh = __neigh_lookup(&arp_tbl, &ip, rt->dst.dev, 1);
ip_rt_put(rt);
if (!neigh)
return -ENOMEM;
- entry = NEIGH2ENTRY(neigh);
+ entry = neighbour_priv(neigh);
if (entry != clip_vcc->entry) {
if (!clip_vcc->entry)
pr_debug("add\n");
}
static const struct net_device_ops clip_netdev_ops = {
- .ndo_start_xmit = clip_start_xmit,
+ .ndo_start_xmit = clip_start_xmit,
+ .ndo_neigh_construct = clip_constructor,
};
static void clip_setup(struct net_device *dev)
{
dev->netdev_ops = &clip_netdev_ops;
dev->type = ARPHRD_ATM;
+ dev->neigh_priv_len = sizeof(struct atmarp_entry);
dev->hard_header_len = RFC1483LLC_LEN;
dev->mtu = RFC1626_MTU;
dev->tx_queue_len = 100; /* "normal" queue (packets) */
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
- if (event == NETDEV_UNREGISTER) {
- neigh_ifdown(&clip_tbl, dev);
+ if (event == NETDEV_UNREGISTER)
return NOTIFY_DONE;
- }
/* ignore non-CLIP devices */
if (dev->type != ARPHRD_ATM || dev->netdev_ops != &clip_netdev_ops)
/* This means the neighbour entry has no attached VCC objects. */
#define SEQ_NO_VCC_TOKEN ((void *) 2)
-static void atmarp_info(struct seq_file *seq, struct net_device *dev,
+static void atmarp_info(struct seq_file *seq, struct neighbour *n,
struct atmarp_entry *entry, struct clip_vcc *clip_vcc)
{
+ struct net_device *dev = n->dev;
unsigned long exp;
char buf[17];
int svc, llc, off;
seq_printf(seq, "%-6s%-4s%-4s%5ld ",
dev->name, svc ? "SVC" : "PVC", llc ? "LLC" : "NULL", exp);
- off = scnprintf(buf, sizeof(buf) - 1, "%pI4",
- &entry->ip);
+ off = scnprintf(buf, sizeof(buf) - 1, "%pI4", n->primary_key);
while (off < 16)
buf[off++] = ' ';
buf[off] = '\0';
{
struct clip_seq_state *state = (struct clip_seq_state *)_state;
- return clip_seq_vcc_walk(state, NEIGH2ENTRY(n), pos);
+ if (n->dev->type != ARPHRD_ATM)
+ return NULL;
+
+ return clip_seq_vcc_walk(state, neighbour_priv(n), pos);
}
static void *clip_seq_start(struct seq_file *seq, loff_t * pos)
{
struct clip_seq_state *state = seq->private;
state->ns.neigh_sub_iter = clip_seq_sub_iter;
- return neigh_seq_start(seq, pos, &clip_tbl, NEIGH_SEQ_NEIGH_ONLY);
+ return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_NEIGH_ONLY);
}
static int clip_seq_show(struct seq_file *seq, void *v)
seq_puts(seq, atm_arp_banner);
} else {
struct clip_seq_state *state = seq->private;
- struct neighbour *n = v;
struct clip_vcc *vcc = state->vcc;
+ struct neighbour *n = v;
- atmarp_info(seq, n->dev, NEIGH2ENTRY(n), vcc);
+ atmarp_info(seq, n, neighbour_priv(n), vcc);
}
return 0;
}
static int __init atm_clip_init(void)
{
- neigh_table_init_no_netlink(&clip_tbl);
-
- clip_tbl_hook = &clip_tbl;
register_atm_ioctl(&clip_ioctl_ops);
register_netdevice_notifier(&clip_dev_notifier);
register_inetaddr_notifier(&clip_inet_notifier);
*/
del_timer_sync(&idle_timer);
- /* Next, purge the table, so that the device
- * unregister loop below does not hang due to
- * device references remaining in the table.
- */
- neigh_ifdown(&clip_tbl, NULL);
-
dev = clip_devs;
while (dev) {
next = PRIV(dev)->next;
free_netdev(dev);
dev = next;
}
-
- /* Now it is safe to fully shutdown whole table. */
- neigh_table_clear(&clip_tbl);
-
- clip_tbl_hook = NULL;
}
static void __exit atm_clip_exit(void)
}
EXPORT_SYMBOL(vcc_release_async);
+void vcc_process_recv_queue(struct atm_vcc *vcc)
+{
+ struct sk_buff_head queue, *rq;
+ struct sk_buff *skb, *tmp;
+ unsigned long flags;
+
+ __skb_queue_head_init(&queue);
+ rq = &sk_atm(vcc)->sk_receive_queue;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ skb_queue_splice_init(rq, &queue);
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ skb_queue_walk_safe(&queue, skb, tmp) {
+ __skb_unlink(skb, &queue);
+ vcc->push(vcc, skb);
+ }
+}
+EXPORT_SYMBOL(vcc_process_recv_queue);
+
void atm_dev_signal_change(struct atm_dev *dev, char signal)
{
pr_debug("%s signal=%d dev=%p number=%d dev->signal=%d\n",
if (sock->state != SS_CONNECTED)
return -ENOTCONN;
- if (flags & ~MSG_DONTWAIT) /* only handle MSG_DONTWAIT */
+
+ /* only handle MSG_DONTWAIT and MSG_PEEK */
+ if (flags & ~(MSG_DONTWAIT | MSG_PEEK))
return -EOPNOTSUPP;
+
vcc = ATM_SD(sock);
if (test_bit(ATM_VF_RELEASED, &vcc->flags) ||
test_bit(ATM_VF_CLOSE, &vcc->flags) ||
if (error)
return error;
sock_recv_ts_and_drops(msg, sk, skb);
- pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc), skb->truesize);
- atm_return(vcc, skb->truesize);
+
+ if (!(flags & MSG_PEEK)) {
+ pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc),
+ skb->truesize);
+ atm_return(vcc, skb->truesize);
+ }
+
skb_free_datagram(sk, skb);
return copied;
}
char __user *optval, unsigned int optlen);
int vcc_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen);
+void vcc_process_recv_queue(struct atm_vcc *vcc);
int atmpvc_init(void);
void atmpvc_exit(void);
atmvcc->push = pppoatm_push;
atmvcc->pop = pppoatm_pop;
__module_get(THIS_MODULE);
+
+ /* re-process everything received between connection setup and
+ backend setup */
+ vcc_process_recv_queue(atmvcc);
return 0;
}
break;
case AX25_T1:
- if (ax25_ctl.arg < 1)
+ if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ)
goto einval_put;
ax25->rtt = (ax25_ctl.arg * HZ) / 2;
ax25->t1 = ax25_ctl.arg * HZ;
break;
case AX25_T2:
- if (ax25_ctl.arg < 1)
+ if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ)
goto einval_put;
ax25->t2 = ax25_ctl.arg * HZ;
break;
break;
case AX25_T3:
+ if (ax25_ctl.arg > ULONG_MAX / HZ)
+ goto einval_put;
ax25->t3 = ax25_ctl.arg * HZ;
break;
case AX25_IDLE:
+ if (ax25_ctl.arg > ULONG_MAX / (60 * HZ))
+ goto einval_put;
+
ax25->idle = ax25_ctl.arg * 60 * HZ;
break;
ax25_cb *ax25;
struct net_device *dev;
char devname[IFNAMSIZ];
- int opt, res = 0;
+ unsigned long opt;
+ int res = 0;
if (level != SOL_AX25)
return -ENOPROTOOPT;
- if (optlen < sizeof(int))
+ if (optlen < sizeof(unsigned int))
return -EINVAL;
- if (get_user(opt, (int __user *)optval))
+ if (get_user(opt, (unsigned int __user *)optval))
return -EFAULT;
lock_sock(sk);
break;
case AX25_T1:
- if (opt < 1) {
+ if (opt < 1 || opt > ULONG_MAX / HZ) {
res = -EINVAL;
break;
}
break;
case AX25_T2:
- if (opt < 1) {
+ if (opt < 1 || opt > ULONG_MAX / HZ) {
res = -EINVAL;
break;
}
break;
case AX25_T3:
- if (opt < 1) {
+ if (opt < 1 || opt > ULONG_MAX / HZ) {
res = -EINVAL;
break;
}
break;
case AX25_IDLE:
- if (opt < 0) {
+ if (opt > ULONG_MAX / (60 * HZ)) {
res = -EINVAL;
break;
}
break;
case AX25_BACKOFF:
- if (opt < 0 || opt > 2) {
+ if (opt > 2) {
res = -EINVAL;
break;
}
unsigned long uint_val;
int ret;
- ret = strict_strtoul(buff, 10, &uint_val);
+ ret = kstrtoul(buff, 10, &uint_val);
if (ret) {
bat_info(net_dev,
"%s: Invalid parameter received: %s\n",
unsigned long val;
int ret, vis_mode_tmp = -1;
- ret = strict_strtoul(buff, 10, &val);
+ ret = kstrtoul(buff, 10, &val);
if (((count == 2) && (!ret) && (val == VIS_TYPE_CLIENT_UPDATE)) ||
(strncmp(buff, "client", 6) == 0) ||
/* sequence number is much newer, probably missed a lot of packets */
if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE)
- || (seq_num_diff < EXPECTED_SEQNO_RANGE)) {
+ && (seq_num_diff < EXPECTED_SEQNO_RANGE)) {
bat_dbg(DBG_BATMAN, bat_priv,
"We missed a lot of packets (%i) !\n",
seq_num_diff - 1);
#include "gateway_common.h"
#include "hard-interface.h"
#include "originator.h"
+#include "translation-table.h"
#include "routing.h"
#include <linux/ip.h>
#include <linux/ipv6.h>
return ret;
}
-int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb,
- struct orig_node *old_gw)
+bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
{
struct ethhdr *ethhdr;
struct iphdr *iphdr;
struct ipv6hdr *ipv6hdr;
struct udphdr *udphdr;
- struct gw_node *curr_gw;
- struct neigh_node *neigh_curr = NULL, *neigh_old = NULL;
- unsigned int header_len = 0;
- int ret = 1;
-
- if (atomic_read(&bat_priv->gw_mode) == GW_MODE_OFF)
- return 0;
/* check for ethernet header */
- if (!pskb_may_pull(skb, header_len + ETH_HLEN))
- return 0;
+ if (!pskb_may_pull(skb, *header_len + ETH_HLEN))
+ return false;
ethhdr = (struct ethhdr *)skb->data;
- header_len += ETH_HLEN;
+ *header_len += ETH_HLEN;
/* check for initial vlan header */
if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) {
- if (!pskb_may_pull(skb, header_len + VLAN_HLEN))
- return 0;
+ if (!pskb_may_pull(skb, *header_len + VLAN_HLEN))
+ return false;
ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
- header_len += VLAN_HLEN;
+ *header_len += VLAN_HLEN;
}
/* check for ip header */
switch (ntohs(ethhdr->h_proto)) {
case ETH_P_IP:
- if (!pskb_may_pull(skb, header_len + sizeof(*iphdr)))
- return 0;
- iphdr = (struct iphdr *)(skb->data + header_len);
- header_len += iphdr->ihl * 4;
+ if (!pskb_may_pull(skb, *header_len + sizeof(*iphdr)))
+ return false;
+ iphdr = (struct iphdr *)(skb->data + *header_len);
+ *header_len += iphdr->ihl * 4;
/* check for udp header */
if (iphdr->protocol != IPPROTO_UDP)
- return 0;
+ return false;
break;
case ETH_P_IPV6:
- if (!pskb_may_pull(skb, header_len + sizeof(*ipv6hdr)))
- return 0;
- ipv6hdr = (struct ipv6hdr *)(skb->data + header_len);
- header_len += sizeof(*ipv6hdr);
+ if (!pskb_may_pull(skb, *header_len + sizeof(*ipv6hdr)))
+ return false;
+ ipv6hdr = (struct ipv6hdr *)(skb->data + *header_len);
+ *header_len += sizeof(*ipv6hdr);
/* check for udp header */
if (ipv6hdr->nexthdr != IPPROTO_UDP)
- return 0;
+ return false;
break;
default:
- return 0;
+ return false;
}
- if (!pskb_may_pull(skb, header_len + sizeof(*udphdr)))
- return 0;
- udphdr = (struct udphdr *)(skb->data + header_len);
- header_len += sizeof(*udphdr);
+ if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr)))
+ return false;
+ udphdr = (struct udphdr *)(skb->data + *header_len);
+ *header_len += sizeof(*udphdr);
/* check for bootp port */
if ((ntohs(ethhdr->h_proto) == ETH_P_IP) &&
(ntohs(udphdr->dest) != 67))
- return 0;
+ return false;
if ((ntohs(ethhdr->h_proto) == ETH_P_IPV6) &&
(ntohs(udphdr->dest) != 547))
- return 0;
+ return false;
- if (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)
- return -1;
+ return true;
+}
- curr_gw = gw_get_selected_gw_node(bat_priv);
- if (!curr_gw)
- return 0;
-
- /* If old_gw != NULL then this packet is unicast.
- * So, at this point we have to check the message type: if it is a
- * DHCPREQUEST we have to decide whether to drop it or not */
- if (old_gw && curr_gw->orig_node != old_gw) {
- if (is_type_dhcprequest(skb, header_len)) {
- /* If the dhcp packet has been sent to a different gw,
- * we have to evaluate whether the old gw is still
- * reliable enough */
- neigh_curr = find_router(bat_priv, curr_gw->orig_node,
- NULL);
- neigh_old = find_router(bat_priv, old_gw, NULL);
- if (!neigh_curr || !neigh_old)
- goto free_neigh;
- if (neigh_curr->tq_avg - neigh_old->tq_avg <
- GW_THRESHOLD)
- ret = -1;
- }
+bool gw_out_of_range(struct bat_priv *bat_priv,
+ struct sk_buff *skb, struct ethhdr *ethhdr)
+{
+ struct neigh_node *neigh_curr = NULL, *neigh_old = NULL;
+ struct orig_node *orig_dst_node = NULL;
+ struct gw_node *curr_gw = NULL;
+ bool ret, out_of_range = false;
+ unsigned int header_len = 0;
+ uint8_t curr_tq_avg;
+
+ ret = gw_is_dhcp_target(skb, &header_len);
+ if (!ret)
+ goto out;
+
+ orig_dst_node = transtable_search(bat_priv, ethhdr->h_source,
+ ethhdr->h_dest);
+ if (!orig_dst_node)
+ goto out;
+
+ if (!orig_dst_node->gw_flags)
+ goto out;
+
+ ret = is_type_dhcprequest(skb, header_len);
+ if (!ret)
+ goto out;
+
+ switch (atomic_read(&bat_priv->gw_mode)) {
+ case GW_MODE_SERVER:
+ /* If we are a GW then we are our best GW. We can artificially
+ * set the tq towards ourself as the maximum value */
+ curr_tq_avg = TQ_MAX_VALUE;
+ break;
+ case GW_MODE_CLIENT:
+ curr_gw = gw_get_selected_gw_node(bat_priv);
+ if (!curr_gw)
+ goto out;
+
+ /* packet is going to our gateway */
+ if (curr_gw->orig_node == orig_dst_node)
+ goto out;
+
+ /* If the dhcp packet has been sent to a different gw,
+ * we have to evaluate whether the old gw is still
+ * reliable enough */
+ neigh_curr = find_router(bat_priv, curr_gw->orig_node, NULL);
+ if (!neigh_curr)
+ goto out;
+
+ curr_tq_avg = neigh_curr->tq_avg;
+ break;
+ case GW_MODE_OFF:
+ default:
+ goto out;
}
-free_neigh:
+
+ neigh_old = find_router(bat_priv, orig_dst_node, NULL);
+ if (!neigh_old)
+ goto out;
+
+ if (curr_tq_avg - neigh_old->tq_avg > GW_THRESHOLD)
+ out_of_range = true;
+
+out:
+ if (orig_dst_node)
+ orig_node_free_ref(orig_dst_node);
+ if (curr_gw)
+ gw_node_free_ref(curr_gw);
if (neigh_old)
neigh_node_free_ref(neigh_old);
if (neigh_curr)
neigh_node_free_ref(neigh_curr);
- if (curr_gw)
- gw_node_free_ref(curr_gw);
- return ret;
+ return out_of_range;
}
void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node);
void gw_node_purge(struct bat_priv *bat_priv);
int gw_client_seq_print_text(struct seq_file *seq, void *offset);
-int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb,
- struct orig_node *old_gw);
+bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len);
+bool gw_out_of_range(struct bat_priv *bat_priv,
+ struct sk_buff *skb, struct ethhdr *ethhdr);
#endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */
*tmp_ptr = '\0';
}
- ret = strict_strtol(buff, 10, &ldown);
+ ret = kstrtol(buff, 10, &ldown);
if (ret) {
bat_err(net_dev,
"Download speed of gateway mode invalid: %s\n",
*tmp_ptr = '\0';
}
- ret = strict_strtol(slash_ptr + 1, 10, &lup);
+ ret = kstrtol(slash_ptr + 1, 10, &lup);
if (ret) {
bat_err(net_dev,
"Upload speed of gateway mode invalid: "
/* clears the hash */
static void hash_init(struct hashtable_t *hash)
{
- int i;
+ uint32_t i;
for (i = 0 ; i < hash->size; i++) {
INIT_HLIST_HEAD(&hash->table[i]);
}
/* allocates and clears the hash */
-struct hashtable_t *hash_new(int size)
+struct hashtable_t *hash_new(uint32_t size)
{
struct hashtable_t *hash;
/* the hashfunction, should return an index
* based on the key in the data of the first
* argument and the size the second */
-typedef int (*hashdata_choose_cb)(const void *, int);
+typedef uint32_t (*hashdata_choose_cb)(const void *, uint32_t);
typedef void (*hashdata_free_cb)(struct hlist_node *, void *);
struct hashtable_t {
struct hlist_head *table; /* the hashtable itself with the buckets */
spinlock_t *list_locks; /* spinlock for each hash list entry */
- int size; /* size of hashtable */
+ uint32_t size; /* size of hashtable */
};
/* allocates and clears the hash */
-struct hashtable_t *hash_new(int size);
+struct hashtable_t *hash_new(uint32_t size);
/* free only the hashtable and the hash itself. */
void hash_destroy(struct hashtable_t *hash);
struct hlist_head *head;
struct hlist_node *node, *node_tmp;
spinlock_t *list_lock; /* spinlock to protect write access */
- int i;
+ uint32_t i;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
hashdata_choose_cb choose,
const void *data, struct hlist_node *data_node)
{
- int index, ret = -1;
+ uint32_t index;
+ int ret = -1;
struct hlist_head *head;
struct hlist_node *node;
spinlock_t *list_lock; /* spinlock to protect write access */
hashdata_compare_cb compare,
hashdata_choose_cb choose, void *data)
{
- size_t index;
+ uint32_t index;
struct hlist_node *node;
struct hlist_head *head;
void *data_save = NULL;
spin_unlock_bh(&socket_client->lock);
- error = __copy_to_user(buf, &socket_packet->icmp_packet,
- socket_packet->icmp_len);
+ packet_len = min(count, socket_packet->icmp_len);
+ error = copy_to_user(buf, &socket_packet->icmp_packet, packet_len);
- packet_len = socket_packet->icmp_len;
kfree(socket_packet);
if (error)
skb_reserve(skb, sizeof(struct ethhdr));
icmp_packet = (struct icmp_packet_rr *)skb_put(skb, packet_len);
- if (!access_ok(VERIFY_READ, buff, packet_len)) {
- len = -EFAULT;
- goto free_skb;
- }
-
- if (__copy_from_user(icmp_packet, buff, packet_len)) {
+ if (copy_from_user(icmp_packet, buff, packet_len)) {
len = -EFAULT;
goto free_skb;
}
if (icmp_packet->version != COMPAT_VERSION) {
icmp_packet->msg_type = PARAMETER_PROBLEM;
- icmp_packet->ttl = COMPAT_VERSION;
+ icmp_packet->version = COMPAT_VERSION;
bat_socket_add_packet(socket_client, icmp_packet, packet_len);
goto free_skb;
}
#define DRIVER_DEVICE "batman-adv"
#ifndef SOURCE_VERSION
-#define SOURCE_VERSION "2011.4.0"
+#define SOURCE_VERSION "2012.0.0"
#endif
/* B.A.T.M.A.N. parameters */
struct hlist_head *head;
spinlock_t *list_lock; /* spinlock to protect write access */
struct orig_node *orig_node;
- int i;
+ uint32_t i;
if (!hash)
return;
struct hlist_head *head;
spinlock_t *list_lock; /* spinlock to protect write access */
struct orig_node *orig_node;
- int i;
+ uint32_t i;
if (!hash)
return;
int batman_count = 0;
int last_seen_secs;
int last_seen_msecs;
- int i, ret = 0;
+ uint32_t i;
+ int ret = 0;
primary_if = primary_if_get_selected(bat_priv);
struct hlist_node *node;
struct hlist_head *head;
struct orig_node *orig_node;
- int i, ret;
+ uint32_t i;
+ int ret;
/* resize all orig nodes because orig_node->bcast_own(_sum) depend on
* if_num */
struct hlist_head *head;
struct hard_iface *hard_iface_tmp;
struct orig_node *orig_node;
- int i, ret;
+ uint32_t i;
+ int ret;
/* resize all orig nodes because orig_node->bcast_own(_sum) depend on
* if_num */
/* hashfunction to choose an entry in a hash table of given size */
/* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */
-static inline int choose_orig(const void *data, int32_t size)
+static inline uint32_t choose_orig(const void *data, uint32_t size)
{
const unsigned char *key = data;
uint32_t hash = 0;
struct hlist_head *head;
struct orig_node *orig_node;
unsigned long *word;
- int i;
+ uint32_t i;
size_t word_index;
for (i = 0; i < hash->size; i++) {
{
struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface);
struct tt_query_packet *tt_query;
+ uint16_t tt_len;
struct ethhdr *ethhdr;
/* drop packet if it has not necessary minimum size */
}
break;
case TT_RESPONSE:
- /* packet needs to be linearized to access the TT changes */
- if (skb_linearize(skb) < 0)
- goto out;
+ if (is_my_mac(tt_query->dst)) {
+ /* packet needs to be linearized to access the TT
+ * changes */
+ if (skb_linearize(skb) < 0)
+ goto out;
+
+ tt_len = tt_query->tt_data * sizeof(struct tt_change);
+
+ /* Ensure we have all the claimed data */
+ if (unlikely(skb_headlen(skb) <
+ sizeof(struct tt_query_packet) + tt_len))
+ goto out;
- if (is_my_mac(tt_query->dst))
handle_tt_response(bat_priv, tt_query);
- else {
+ } else {
bat_dbg(DBG_TT, bat_priv,
"Routing TT_RESPONSE to %pM [%c]\n",
tt_query->dst,
struct bcast_packet *bcast_packet;
struct vlan_ethhdr *vhdr;
struct softif_neigh *curr_softif_neigh = NULL;
- struct orig_node *orig_node = NULL;
+ unsigned int header_len = 0;
int data_len = skb->len, ret;
short vid = -1;
- bool do_bcast;
+ bool do_bcast = false;
if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE)
goto dropped;
/* Register the client MAC in the transtable */
tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif);
- orig_node = transtable_search(bat_priv, ethhdr->h_source,
- ethhdr->h_dest);
- do_bcast = is_multicast_ether_addr(ethhdr->h_dest);
- if (do_bcast || (orig_node && orig_node->gw_flags)) {
- ret = gw_is_target(bat_priv, skb, orig_node);
+ if (is_multicast_ether_addr(ethhdr->h_dest)) {
+ do_bcast = true;
- if (ret < 0)
- goto dropped;
-
- if (ret)
- do_bcast = false;
+ switch (atomic_read(&bat_priv->gw_mode)) {
+ case GW_MODE_SERVER:
+ /* gateway servers should not send dhcp
+ * requests into the mesh */
+ ret = gw_is_dhcp_target(skb, &header_len);
+ if (ret)
+ goto dropped;
+ break;
+ case GW_MODE_CLIENT:
+ /* gateway clients should send dhcp requests
+ * via unicast to their gateway */
+ ret = gw_is_dhcp_target(skb, &header_len);
+ if (ret)
+ do_bcast = false;
+ break;
+ case GW_MODE_OFF:
+ default:
+ break;
+ }
}
/* ethernet packet should be broadcasted */
/* unicast packet */
} else {
+ if (atomic_read(&bat_priv->gw_mode) != GW_MODE_OFF) {
+ ret = gw_out_of_range(bat_priv, skb, ethhdr);
+ if (ret)
+ goto dropped;
+ }
+
ret = unicast_send_skb(skb, bat_priv);
if (ret != 0)
goto dropped_freed;
softif_neigh_free_ref(curr_softif_neigh);
if (primary_if)
hardif_free_ref(primary_if);
- if (orig_node)
- orig_node_free_ref(orig_node);
return NETDEV_TX_OK;
}
unreg_sysfs:
sysfs_del_meshif(soft_iface);
unreg_soft_iface:
- unregister_netdev(soft_iface);
+ unregister_netdevice(soft_iface);
return NULL;
free_soft_iface:
static void tt_purge(struct work_struct *work);
/* returns 1 if they are the same mac addr */
-static int compare_ltt(const struct hlist_node *node, const void *data2)
+static int compare_tt(const struct hlist_node *node, const void *data2)
{
- const void *data1 = container_of(node, struct tt_local_entry,
- hash_entry);
-
- return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
-}
-
-/* returns 1 if they are the same mac addr */
-static int compare_gtt(const struct hlist_node *node, const void *data2)
-{
- const void *data1 = container_of(node, struct tt_global_entry,
+ const void *data1 = container_of(node, struct tt_common_entry,
hash_entry);
return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
msecs_to_jiffies(5000));
}
-static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv,
- const void *data)
+static struct tt_common_entry *tt_hash_find(struct hashtable_t *hash,
+ const void *data)
{
- struct hashtable_t *hash = bat_priv->tt_local_hash;
struct hlist_head *head;
struct hlist_node *node;
- struct tt_local_entry *tt_local_entry, *tt_local_entry_tmp = NULL;
- int index;
+ struct tt_common_entry *tt_common_entry, *tt_common_entry_tmp = NULL;
+ uint32_t index;
if (!hash)
return NULL;
head = &hash->table[index];
rcu_read_lock();
- hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) {
- if (!compare_eth(tt_local_entry, data))
+ hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) {
+ if (!compare_eth(tt_common_entry, data))
continue;
- if (!atomic_inc_not_zero(&tt_local_entry->refcount))
+ if (!atomic_inc_not_zero(&tt_common_entry->refcount))
continue;
- tt_local_entry_tmp = tt_local_entry;
+ tt_common_entry_tmp = tt_common_entry;
break;
}
rcu_read_unlock();
- return tt_local_entry_tmp;
+ return tt_common_entry_tmp;
}
-static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv,
- const void *data)
+static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv,
+ const void *data)
{
- struct hashtable_t *hash = bat_priv->tt_global_hash;
- struct hlist_head *head;
- struct hlist_node *node;
- struct tt_global_entry *tt_global_entry;
- struct tt_global_entry *tt_global_entry_tmp = NULL;
- int index;
-
- if (!hash)
- return NULL;
-
- index = choose_orig(data, hash->size);
- head = &hash->table[index];
+ struct tt_common_entry *tt_common_entry;
+ struct tt_local_entry *tt_local_entry = NULL;
- rcu_read_lock();
- hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) {
- if (!compare_eth(tt_global_entry, data))
- continue;
+ tt_common_entry = tt_hash_find(bat_priv->tt_local_hash, data);
+ if (tt_common_entry)
+ tt_local_entry = container_of(tt_common_entry,
+ struct tt_local_entry, common);
+ return tt_local_entry;
+}
- if (!atomic_inc_not_zero(&tt_global_entry->refcount))
- continue;
+static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv,
+ const void *data)
+{
+ struct tt_common_entry *tt_common_entry;
+ struct tt_global_entry *tt_global_entry = NULL;
- tt_global_entry_tmp = tt_global_entry;
- break;
- }
- rcu_read_unlock();
+ tt_common_entry = tt_hash_find(bat_priv->tt_global_hash, data);
+ if (tt_common_entry)
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry, common);
+ return tt_global_entry;
- return tt_global_entry_tmp;
}
static bool is_out_of_time(unsigned long starting_time, unsigned long timeout)
static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry)
{
- if (atomic_dec_and_test(&tt_local_entry->refcount))
- kfree_rcu(tt_local_entry, rcu);
+ if (atomic_dec_and_test(&tt_local_entry->common.refcount))
+ kfree_rcu(tt_local_entry, common.rcu);
}
static void tt_global_entry_free_rcu(struct rcu_head *rcu)
{
+ struct tt_common_entry *tt_common_entry;
struct tt_global_entry *tt_global_entry;
- tt_global_entry = container_of(rcu, struct tt_global_entry, rcu);
+ tt_common_entry = container_of(rcu, struct tt_common_entry, rcu);
+ tt_global_entry = container_of(tt_common_entry, struct tt_global_entry,
+ common);
if (tt_global_entry->orig_node)
orig_node_free_ref(tt_global_entry->orig_node);
static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry)
{
- if (atomic_dec_and_test(&tt_global_entry->refcount))
- call_rcu(&tt_global_entry->rcu, tt_global_entry_free_rcu);
+ if (atomic_dec_and_test(&tt_global_entry->common.refcount))
+ call_rcu(&tt_global_entry->common.rcu,
+ tt_global_entry_free_rcu);
}
static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr,
struct bat_priv *bat_priv = netdev_priv(soft_iface);
struct tt_local_entry *tt_local_entry = NULL;
struct tt_global_entry *tt_global_entry = NULL;
+ int hash_added;
tt_local_entry = tt_local_hash_find(bat_priv, addr);
"Creating new local tt entry: %pM (ttvn: %d)\n", addr,
(uint8_t)atomic_read(&bat_priv->ttvn));
- memcpy(tt_local_entry->addr, addr, ETH_ALEN);
- tt_local_entry->last_seen = jiffies;
- tt_local_entry->flags = NO_FLAGS;
+ memcpy(tt_local_entry->common.addr, addr, ETH_ALEN);
+ tt_local_entry->common.flags = NO_FLAGS;
if (is_wifi_iface(ifindex))
- tt_local_entry->flags |= TT_CLIENT_WIFI;
- atomic_set(&tt_local_entry->refcount, 2);
+ tt_local_entry->common.flags |= TT_CLIENT_WIFI;
+ atomic_set(&tt_local_entry->common.refcount, 2);
+ tt_local_entry->last_seen = jiffies;
/* the batman interface mac address should never be purged */
if (compare_eth(addr, soft_iface->dev_addr))
- tt_local_entry->flags |= TT_CLIENT_NOPURGE;
+ tt_local_entry->common.flags |= TT_CLIENT_NOPURGE;
- tt_local_event(bat_priv, addr, tt_local_entry->flags);
+ hash_added = hash_add(bat_priv->tt_local_hash, compare_tt, choose_orig,
+ &tt_local_entry->common,
+ &tt_local_entry->common.hash_entry);
+
+ if (unlikely(hash_added != 0)) {
+ /* remove the reference for the hash */
+ tt_local_entry_free_ref(tt_local_entry);
+ goto out;
+ }
+
+ tt_local_event(bat_priv, addr, tt_local_entry->common.flags);
/* The local entry has to be marked as NEW to avoid to send it in
* a full table response going out before the next ttvn increment
* (consistency check) */
- tt_local_entry->flags |= TT_CLIENT_NEW;
-
- hash_add(bat_priv->tt_local_hash, compare_ltt, choose_orig,
- tt_local_entry, &tt_local_entry->hash_entry);
+ tt_local_entry->common.flags |= TT_CLIENT_NEW;
/* remove address from global hash if present */
tt_global_entry = tt_global_hash_find(bat_priv, addr);
if (tt_global_entry) {
/* This node is probably going to update its tt table */
tt_global_entry->orig_node->tt_poss_change = true;
- /* The global entry has to be marked as PENDING and has to be
+ /* The global entry has to be marked as ROAMING and has to be
* kept for consistency purpose */
- tt_global_entry->flags |= TT_CLIENT_PENDING;
- send_roam_adv(bat_priv, tt_global_entry->addr,
+ tt_global_entry->common.flags |= TT_CLIENT_ROAM;
+ tt_global_entry->roam_at = jiffies;
+ send_roam_adv(bat_priv, tt_global_entry->common.addr,
tt_global_entry->orig_node);
}
out:
struct net_device *net_dev = (struct net_device *)seq->private;
struct bat_priv *bat_priv = netdev_priv(net_dev);
struct hashtable_t *hash = bat_priv->tt_local_hash;
- struct tt_local_entry *tt_local_entry;
+ struct tt_common_entry *tt_common_entry;
struct hard_iface *primary_if;
struct hlist_node *node;
struct hlist_head *head;
- size_t buf_size, pos;
- char *buff;
- int i, ret = 0;
+ uint32_t i;
+ int ret = 0;
primary_if = primary_if_get_selected(bat_priv);
if (!primary_if) {
"announced via TT (TTVN: %u):\n",
net_dev->name, (uint8_t)atomic_read(&bat_priv->ttvn));
- buf_size = 1;
- /* Estimate length for: " * xx:xx:xx:xx:xx:xx\n" */
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
rcu_read_lock();
- __hlist_for_each_rcu(node, head)
- buf_size += 29;
- rcu_read_unlock();
- }
-
- buff = kmalloc(buf_size, GFP_ATOMIC);
- if (!buff) {
- ret = -ENOMEM;
- goto out;
- }
-
- buff[0] = '\0';
- pos = 0;
-
- for (i = 0; i < hash->size; i++) {
- head = &hash->table[i];
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(tt_local_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
- pos += snprintf(buff + pos, 30, " * %pM "
- "[%c%c%c%c%c]\n",
- tt_local_entry->addr,
- (tt_local_entry->flags &
+ seq_printf(seq, " * %pM [%c%c%c%c%c]\n",
+ tt_common_entry->addr,
+ (tt_common_entry->flags &
TT_CLIENT_ROAM ? 'R' : '.'),
- (tt_local_entry->flags &
+ (tt_common_entry->flags &
TT_CLIENT_NOPURGE ? 'P' : '.'),
- (tt_local_entry->flags &
+ (tt_common_entry->flags &
TT_CLIENT_NEW ? 'N' : '.'),
- (tt_local_entry->flags &
+ (tt_common_entry->flags &
TT_CLIENT_PENDING ? 'X' : '.'),
- (tt_local_entry->flags &
+ (tt_common_entry->flags &
TT_CLIENT_WIFI ? 'W' : '.'));
}
rcu_read_unlock();
}
-
- seq_printf(seq, "%s", buff);
- kfree(buff);
out:
if (primary_if)
hardif_free_ref(primary_if);
struct tt_local_entry *tt_local_entry,
uint16_t flags)
{
- tt_local_event(bat_priv, tt_local_entry->addr,
- tt_local_entry->flags | flags);
+ tt_local_event(bat_priv, tt_local_entry->common.addr,
+ tt_local_entry->common.flags | flags);
/* The local client has to be marked as "pending to be removed" but has
* to be kept in the table in order to send it in a full table
* response issued before the net ttvn increment (consistency check) */
- tt_local_entry->flags |= TT_CLIENT_PENDING;
+ tt_local_entry->common.flags |= TT_CLIENT_PENDING;
}
void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr,
(roaming ? TT_CLIENT_ROAM : NO_FLAGS));
bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) pending to be removed: "
- "%s\n", tt_local_entry->addr, message);
+ "%s\n", tt_local_entry->common.addr, message);
out:
if (tt_local_entry)
tt_local_entry_free_ref(tt_local_entry);
{
struct hashtable_t *hash = bat_priv->tt_local_hash;
struct tt_local_entry *tt_local_entry;
+ struct tt_common_entry *tt_common_entry;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
spinlock_t *list_lock; /* protects write access to the hash lists */
- int i;
+ uint32_t i;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+ hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
head, hash_entry) {
- if (tt_local_entry->flags & TT_CLIENT_NOPURGE)
+ tt_local_entry = container_of(tt_common_entry,
+ struct tt_local_entry,
+ common);
+ if (tt_local_entry->common.flags & TT_CLIENT_NOPURGE)
continue;
/* entry already marked for deletion */
- if (tt_local_entry->flags & TT_CLIENT_PENDING)
+ if (tt_local_entry->common.flags & TT_CLIENT_PENDING)
continue;
if (!is_out_of_time(tt_local_entry->last_seen,
TT_CLIENT_DEL);
bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) "
"pending to be removed: timed out\n",
- tt_local_entry->addr);
+ tt_local_entry->common.addr);
}
spin_unlock_bh(list_lock);
}
{
struct hashtable_t *hash;
spinlock_t *list_lock; /* protects write access to the hash lists */
+ struct tt_common_entry *tt_common_entry;
struct tt_local_entry *tt_local_entry;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
- int i;
+ uint32_t i;
if (!bat_priv->tt_local_hash)
return;
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+ hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
head, hash_entry) {
hlist_del_rcu(node);
+ tt_local_entry = container_of(tt_common_entry,
+ struct tt_local_entry,
+ common);
tt_local_entry_free_ref(tt_local_entry);
}
spin_unlock_bh(list_lock);
struct tt_global_entry *tt_global_entry;
struct orig_node *orig_node_tmp;
int ret = 0;
+ int hash_added;
tt_global_entry = tt_global_hash_find(bat_priv, tt_addr);
if (!tt_global_entry)
goto out;
- memcpy(tt_global_entry->addr, tt_addr, ETH_ALEN);
+ memcpy(tt_global_entry->common.addr, tt_addr, ETH_ALEN);
+ tt_global_entry->common.flags = NO_FLAGS;
+ atomic_set(&tt_global_entry->common.refcount, 2);
/* Assign the new orig_node */
atomic_inc(&orig_node->refcount);
tt_global_entry->orig_node = orig_node;
tt_global_entry->ttvn = ttvn;
- tt_global_entry->flags = NO_FLAGS;
tt_global_entry->roam_at = 0;
- atomic_set(&tt_global_entry->refcount, 2);
- hash_add(bat_priv->tt_global_hash, compare_gtt,
- choose_orig, tt_global_entry,
- &tt_global_entry->hash_entry);
+ hash_added = hash_add(bat_priv->tt_global_hash, compare_tt,
+ choose_orig, &tt_global_entry->common,
+ &tt_global_entry->common.hash_entry);
+
+ if (unlikely(hash_added != 0)) {
+ /* remove the reference for the hash */
+ tt_global_entry_free_ref(tt_global_entry);
+ goto out_remove;
+ }
atomic_inc(&orig_node->tt_size);
} else {
if (tt_global_entry->orig_node != orig_node) {
orig_node_free_ref(orig_node_tmp);
atomic_inc(&orig_node->tt_size);
}
+ tt_global_entry->common.flags = NO_FLAGS;
tt_global_entry->ttvn = ttvn;
- tt_global_entry->flags = NO_FLAGS;
tt_global_entry->roam_at = 0;
}
if (wifi)
- tt_global_entry->flags |= TT_CLIENT_WIFI;
+ tt_global_entry->common.flags |= TT_CLIENT_WIFI;
bat_dbg(DBG_TT, bat_priv,
"Creating new global tt entry: %pM (via %pM)\n",
- tt_global_entry->addr, orig_node->orig);
+ tt_global_entry->common.addr, orig_node->orig);
+out_remove:
/* remove address from local hash if present */
- tt_local_remove(bat_priv, tt_global_entry->addr,
+ tt_local_remove(bat_priv, tt_global_entry->common.addr,
"global tt received", roaming);
ret = 1;
out:
struct net_device *net_dev = (struct net_device *)seq->private;
struct bat_priv *bat_priv = netdev_priv(net_dev);
struct hashtable_t *hash = bat_priv->tt_global_hash;
+ struct tt_common_entry *tt_common_entry;
struct tt_global_entry *tt_global_entry;
struct hard_iface *primary_if;
struct hlist_node *node;
struct hlist_head *head;
- size_t buf_size, pos;
- char *buff;
- int i, ret = 0;
+ uint32_t i;
+ int ret = 0;
primary_if = primary_if_get_selected(bat_priv);
if (!primary_if) {
seq_printf(seq, " %-13s %s %-15s %s %s\n",
"Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags");
- buf_size = 1;
- /* Estimate length for: " * xx:xx:xx:xx:xx:xx (ttvn) via
- * xx:xx:xx:xx:xx:xx (cur_ttvn)\n"*/
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
rcu_read_lock();
- __hlist_for_each_rcu(node, head)
- buf_size += 67;
- rcu_read_unlock();
- }
-
- buff = kmalloc(buf_size, GFP_ATOMIC);
- if (!buff) {
- ret = -ENOMEM;
- goto out;
- }
-
- buff[0] = '\0';
- pos = 0;
-
- for (i = 0; i < hash->size; i++) {
- head = &hash->table[i];
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(tt_global_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
- pos += snprintf(buff + pos, 69,
- " * %pM (%3u) via %pM (%3u) "
- "[%c%c%c]\n", tt_global_entry->addr,
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry,
+ common);
+ seq_printf(seq, " * %pM (%3u) via %pM (%3u) "
+ "[%c%c%c]\n",
+ tt_global_entry->common.addr,
tt_global_entry->ttvn,
tt_global_entry->orig_node->orig,
(uint8_t) atomic_read(
&tt_global_entry->orig_node->
last_ttvn),
- (tt_global_entry->flags &
+ (tt_global_entry->common.flags &
TT_CLIENT_ROAM ? 'R' : '.'),
- (tt_global_entry->flags &
+ (tt_global_entry->common.flags &
TT_CLIENT_PENDING ? 'X' : '.'),
- (tt_global_entry->flags &
+ (tt_global_entry->common.flags &
TT_CLIENT_WIFI ? 'W' : '.'));
}
rcu_read_unlock();
}
-
- seq_printf(seq, "%s", buff);
- kfree(buff);
out:
if (primary_if)
hardif_free_ref(primary_if);
bat_dbg(DBG_TT, bat_priv,
"Deleting global tt entry %pM (via %pM): %s\n",
- tt_global_entry->addr, tt_global_entry->orig_node->orig,
+ tt_global_entry->common.addr, tt_global_entry->orig_node->orig,
message);
atomic_dec(&tt_global_entry->orig_node->tt_size);
- hash_remove(bat_priv->tt_global_hash, compare_gtt, choose_orig,
- tt_global_entry->addr);
+ hash_remove(bat_priv->tt_global_hash, compare_tt, choose_orig,
+ tt_global_entry->common.addr);
out:
if (tt_global_entry)
tt_global_entry_free_ref(tt_global_entry);
const char *message, bool roaming)
{
struct tt_global_entry *tt_global_entry = NULL;
+ struct tt_local_entry *tt_local_entry = NULL;
tt_global_entry = tt_global_hash_find(bat_priv, addr);
if (!tt_global_entry)
if (tt_global_entry->orig_node == orig_node) {
if (roaming) {
- tt_global_entry->flags |= TT_CLIENT_ROAM;
- tt_global_entry->roam_at = jiffies;
- goto out;
+ /* if we are deleting a global entry due to a roam
+ * event, there are two possibilities:
+ * 1) the client roamed from node A to node B => we mark
+ * it with TT_CLIENT_ROAM, we start a timer and we
+ * wait for node B to claim it. In case of timeout
+ * the entry is purged.
+ * 2) the client roamed to us => we can directly delete
+ * the global entry, since it is useless now. */
+ tt_local_entry = tt_local_hash_find(bat_priv,
+ tt_global_entry->common.addr);
+ if (!tt_local_entry) {
+ tt_global_entry->common.flags |= TT_CLIENT_ROAM;
+ tt_global_entry->roam_at = jiffies;
+ goto out;
+ }
}
_tt_global_del(bat_priv, tt_global_entry, message);
}
out:
if (tt_global_entry)
tt_global_entry_free_ref(tt_global_entry);
+ if (tt_local_entry)
+ tt_local_entry_free_ref(tt_local_entry);
}
void tt_global_del_orig(struct bat_priv *bat_priv,
struct orig_node *orig_node, const char *message)
{
struct tt_global_entry *tt_global_entry;
- int i;
+ struct tt_common_entry *tt_common_entry;
+ uint32_t i;
struct hashtable_t *hash = bat_priv->tt_global_hash;
struct hlist_node *node, *safe;
struct hlist_head *head;
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_global_entry, node, safe,
+ hlist_for_each_entry_safe(tt_common_entry, node, safe,
head, hash_entry) {
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry,
+ common);
if (tt_global_entry->orig_node == orig_node) {
bat_dbg(DBG_TT, bat_priv,
"Deleting global tt entry %pM "
- "(via %pM): originator time out\n",
- tt_global_entry->addr,
- tt_global_entry->orig_node->orig);
+ "(via %pM): %s\n",
+ tt_global_entry->common.addr,
+ tt_global_entry->orig_node->orig,
+ message);
hlist_del_rcu(node);
tt_global_entry_free_ref(tt_global_entry);
}
static void tt_global_roam_purge(struct bat_priv *bat_priv)
{
struct hashtable_t *hash = bat_priv->tt_global_hash;
+ struct tt_common_entry *tt_common_entry;
struct tt_global_entry *tt_global_entry;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
spinlock_t *list_lock; /* protects write access to the hash lists */
- int i;
+ uint32_t i;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_global_entry, node, node_tmp,
+ hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
head, hash_entry) {
- if (!(tt_global_entry->flags & TT_CLIENT_ROAM))
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry,
+ common);
+ if (!(tt_global_entry->common.flags & TT_CLIENT_ROAM))
continue;
if (!is_out_of_time(tt_global_entry->roam_at,
TT_CLIENT_ROAM_TIMEOUT * 1000))
bat_dbg(DBG_TT, bat_priv, "Deleting global "
"tt entry (%pM): Roaming timeout\n",
- tt_global_entry->addr);
+ tt_global_entry->common.addr);
atomic_dec(&tt_global_entry->orig_node->tt_size);
hlist_del_rcu(node);
tt_global_entry_free_ref(tt_global_entry);
{
struct hashtable_t *hash;
spinlock_t *list_lock; /* protects write access to the hash lists */
+ struct tt_common_entry *tt_common_entry;
struct tt_global_entry *tt_global_entry;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
- int i;
+ uint32_t i;
if (!bat_priv->tt_global_hash)
return;
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_global_entry, node, node_tmp,
+ hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
head, hash_entry) {
hlist_del_rcu(node);
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry,
+ common);
tt_global_entry_free_ref(tt_global_entry);
}
spin_unlock_bh(list_lock);
{
bool ret = false;
- if (tt_local_entry->flags & TT_CLIENT_WIFI &&
- tt_global_entry->flags & TT_CLIENT_WIFI)
+ if (tt_local_entry->common.flags & TT_CLIENT_WIFI &&
+ tt_global_entry->common.flags & TT_CLIENT_WIFI)
ret = true;
return ret;
/* A global client marked as PENDING has already moved from that
* originator */
- if (tt_global_entry->flags & TT_CLIENT_PENDING)
+ if (tt_global_entry->common.flags & TT_CLIENT_PENDING)
goto out;
orig_node = tt_global_entry->orig_node;
{
uint16_t total = 0, total_one;
struct hashtable_t *hash = bat_priv->tt_global_hash;
+ struct tt_common_entry *tt_common_entry;
struct tt_global_entry *tt_global_entry;
struct hlist_node *node;
struct hlist_head *head;
- int i, j;
+ uint32_t i;
+ int j;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
rcu_read_lock();
- hlist_for_each_entry_rcu(tt_global_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
+ tt_global_entry = container_of(tt_common_entry,
+ struct tt_global_entry,
+ common);
if (compare_eth(tt_global_entry->orig_node,
orig_node)) {
/* Roaming clients are in the global table for
* consistency only. They don't have to be
* taken into account while computing the
* global crc */
- if (tt_global_entry->flags & TT_CLIENT_ROAM)
+ if (tt_common_entry->flags & TT_CLIENT_ROAM)
continue;
total_one = 0;
for (j = 0; j < ETH_ALEN; j++)
total_one = crc16_byte(total_one,
- tt_global_entry->addr[j]);
+ tt_common_entry->addr[j]);
total ^= total_one;
}
}
{
uint16_t total = 0, total_one;
struct hashtable_t *hash = bat_priv->tt_local_hash;
- struct tt_local_entry *tt_local_entry;
+ struct tt_common_entry *tt_common_entry;
struct hlist_node *node;
struct hlist_head *head;
- int i, j;
+ uint32_t i;
+ int j;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
rcu_read_lock();
- hlist_for_each_entry_rcu(tt_local_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
/* not yet committed clients have not to be taken into
* account while computing the CRC */
- if (tt_local_entry->flags & TT_CLIENT_NEW)
+ if (tt_common_entry->flags & TT_CLIENT_NEW)
continue;
total_one = 0;
for (j = 0; j < ETH_ALEN; j++)
total_one = crc16_byte(total_one,
- tt_local_entry->addr[j]);
+ tt_common_entry->addr[j]);
total ^= total_one;
}
rcu_read_unlock();
/* data_ptr is useless here, but has to be kept to respect the prototype */
static int tt_local_valid_entry(const void *entry_ptr, const void *data_ptr)
{
- const struct tt_local_entry *tt_local_entry = entry_ptr;
+ const struct tt_common_entry *tt_common_entry = entry_ptr;
- if (tt_local_entry->flags & TT_CLIENT_NEW)
+ if (tt_common_entry->flags & TT_CLIENT_NEW)
return 0;
return 1;
}
static int tt_global_valid_entry(const void *entry_ptr, const void *data_ptr)
{
- const struct tt_global_entry *tt_global_entry = entry_ptr;
+ const struct tt_common_entry *tt_common_entry = entry_ptr;
+ const struct tt_global_entry *tt_global_entry;
const struct orig_node *orig_node = data_ptr;
- if (tt_global_entry->flags & TT_CLIENT_ROAM)
+ if (tt_common_entry->flags & TT_CLIENT_ROAM)
return 0;
+ tt_global_entry = container_of(tt_common_entry, struct tt_global_entry,
+ common);
+
return (tt_global_entry->orig_node == orig_node);
}
const void *),
void *cb_data)
{
- struct tt_local_entry *tt_local_entry;
+ struct tt_common_entry *tt_common_entry;
struct tt_query_packet *tt_response;
struct tt_change *tt_change;
struct hlist_node *node;
struct sk_buff *skb = NULL;
uint16_t tt_tot, tt_count;
ssize_t tt_query_size = sizeof(struct tt_query_packet);
- int i;
+ uint32_t i;
if (tt_query_size + tt_len > primary_if->soft_iface->mtu) {
tt_len = primary_if->soft_iface->mtu - tt_query_size;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
- hlist_for_each_entry_rcu(tt_local_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
if (tt_count == tt_tot)
break;
- if ((valid_cb) && (!valid_cb(tt_local_entry, cb_data)))
+ if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
continue;
- memcpy(tt_change->addr, tt_local_entry->addr, ETH_ALEN);
+ memcpy(tt_change->addr, tt_common_entry->addr,
+ ETH_ALEN);
tt_change->flags = NO_FLAGS;
tt_count++;
(tt_request->flags & TT_FULL_TABLE ? 'F' : '.'));
/* Let's get the orig node of the REAL destination */
- req_dst_orig_node = get_orig_node(bat_priv, tt_request->dst);
+ req_dst_orig_node = orig_hash_find(bat_priv, tt_request->dst);
if (!req_dst_orig_node)
goto out;
- res_dst_orig_node = get_orig_node(bat_priv, tt_request->src);
+ res_dst_orig_node = orig_hash_find(bat_priv, tt_request->src);
if (!res_dst_orig_node)
goto out;
my_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn);
req_ttvn = tt_request->ttvn;
- orig_node = get_orig_node(bat_priv, tt_request->src);
+ orig_node = orig_hash_find(bat_priv, tt_request->src);
if (!orig_node)
goto out;
goto out;
/* Check if the client has been logically deleted (but is kept for
* consistency purpose) */
- if (tt_local_entry->flags & TT_CLIENT_PENDING)
+ if (tt_local_entry->common.flags & TT_CLIENT_PENDING)
goto out;
ret = true;
out:
kfree(bat_priv->tt_buff);
}
-/* This function will reset the specified flags from all the entries in
- * the given hash table and will increment num_local_tt for each involved
- * entry */
-static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags)
+/* This function will enable or disable the specified flags for all the entries
+ * in the given hash table and returns the number of modified entries */
+static uint16_t tt_set_flags(struct hashtable_t *hash, uint16_t flags,
+ bool enable)
{
- int i;
- struct hashtable_t *hash = bat_priv->tt_local_hash;
+ uint32_t i;
+ uint16_t changed_num = 0;
struct hlist_head *head;
struct hlist_node *node;
- struct tt_local_entry *tt_local_entry;
+ struct tt_common_entry *tt_common_entry;
if (!hash)
- return;
+ goto out;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
rcu_read_lock();
- hlist_for_each_entry_rcu(tt_local_entry, node,
+ hlist_for_each_entry_rcu(tt_common_entry, node,
head, hash_entry) {
- if (!(tt_local_entry->flags & flags))
- continue;
- tt_local_entry->flags &= ~flags;
- atomic_inc(&bat_priv->num_local_tt);
+ if (enable) {
+ if ((tt_common_entry->flags & flags) == flags)
+ continue;
+ tt_common_entry->flags |= flags;
+ } else {
+ if (!(tt_common_entry->flags & flags))
+ continue;
+ tt_common_entry->flags &= ~flags;
+ }
+ changed_num++;
}
rcu_read_unlock();
}
-
+out:
+ return changed_num;
}
/* Purge out all the tt local entries marked with TT_CLIENT_PENDING */
static void tt_local_purge_pending_clients(struct bat_priv *bat_priv)
{
struct hashtable_t *hash = bat_priv->tt_local_hash;
+ struct tt_common_entry *tt_common_entry;
struct tt_local_entry *tt_local_entry;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
spinlock_t *list_lock; /* protects write access to the hash lists */
- int i;
+ uint32_t i;
if (!hash)
return;
list_lock = &hash->list_locks[i];
spin_lock_bh(list_lock);
- hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+ hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
head, hash_entry) {
- if (!(tt_local_entry->flags & TT_CLIENT_PENDING))
+ if (!(tt_common_entry->flags & TT_CLIENT_PENDING))
continue;
bat_dbg(DBG_TT, bat_priv, "Deleting local tt entry "
- "(%pM): pending\n", tt_local_entry->addr);
+ "(%pM): pending\n", tt_common_entry->addr);
atomic_dec(&bat_priv->num_local_tt);
hlist_del_rcu(node);
+ tt_local_entry = container_of(tt_common_entry,
+ struct tt_local_entry,
+ common);
tt_local_entry_free_ref(tt_local_entry);
}
spin_unlock_bh(list_lock);
void tt_commit_changes(struct bat_priv *bat_priv)
{
- tt_local_reset_flags(bat_priv, TT_CLIENT_NEW);
+ uint16_t changed_num = tt_set_flags(bat_priv->tt_local_hash,
+ TT_CLIENT_NEW, false);
+ /* all the reset entries have now to be effectively counted as local
+ * entries */
+ atomic_add(changed_num, &bat_priv->num_local_tt);
tt_local_purge_pending_clients(bat_priv);
/* Increment the TTVN only once per OGM interval */
struct icmp_packet_rr icmp_packet;
};
-struct tt_local_entry {
+struct tt_common_entry {
uint8_t addr[ETH_ALEN];
struct hlist_node hash_entry;
- unsigned long last_seen;
uint16_t flags;
atomic_t refcount;
struct rcu_head rcu;
};
+struct tt_local_entry {
+ struct tt_common_entry common;
+ unsigned long last_seen;
+};
+
struct tt_global_entry {
- uint8_t addr[ETH_ALEN];
- struct hlist_node hash_entry; /* entry in the global table */
+ struct tt_common_entry common;
struct orig_node *orig_node;
uint8_t ttvn;
- uint16_t flags; /* only TT_GLOBAL_ROAM is used */
unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */
- atomic_t refcount;
- struct rcu_head rcu;
};
struct tt_change_node {
/* hash function to choose an entry in a hash table of given size */
/* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */
-static int vis_info_choose(const void *data, int size)
+static uint32_t vis_info_choose(const void *data, uint32_t size)
{
const struct vis_info *vis_info = data;
const struct vis_packet *packet;
struct hlist_head *head;
struct hlist_node *node;
struct vis_info *vis_info, *vis_info_tmp = NULL;
- int index;
+ uint32_t index;
if (!hash)
return NULL;
HLIST_HEAD(vis_if_list);
struct if_list_entry *entry;
struct hlist_node *pos, *n;
- int i, j, ret = 0;
+ uint32_t i;
+ int j, ret = 0;
int vis_server = atomic_read(&bat_priv->vis_mode);
size_t buff_pos, buf_size;
char *buff;
struct hlist_head *head;
struct orig_node *orig_node;
struct vis_packet *packet;
- int best_tq = -1, i;
+ int best_tq = -1;
+ uint32_t i;
packet = (struct vis_packet *)info->skb_packet->data;
struct vis_info *info = bat_priv->my_vis_info;
struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data;
struct vis_info_entry *entry;
- struct tt_local_entry *tt_local_entry;
- int best_tq = -1, i;
+ struct tt_common_entry *tt_common_entry;
+ int best_tq = -1;
+ uint32_t i;
info->first_seen = jiffies;
packet->vis_type = atomic_read(&bat_priv->vis_mode);
head = &hash->table[i];
rcu_read_lock();
- hlist_for_each_entry_rcu(tt_local_entry, node, head,
+ hlist_for_each_entry_rcu(tt_common_entry, node, head,
hash_entry) {
entry = (struct vis_info_entry *)
skb_put(info->skb_packet,
sizeof(*entry));
memset(entry->src, 0, ETH_ALEN);
- memcpy(entry->dest, tt_local_entry->addr, ETH_ALEN);
+ memcpy(entry->dest, tt_common_entry->addr, ETH_ALEN);
entry->quality = 0; /* 0 means TT */
packet->entries++;
* held */
static void purge_vis_packets(struct bat_priv *bat_priv)
{
- int i;
+ uint32_t i;
struct hashtable_t *hash = bat_priv->vis_hash;
struct hlist_node *node, *node_tmp;
struct hlist_head *head;
struct sk_buff *skb;
struct hard_iface *hard_iface;
uint8_t dstaddr[ETH_ALEN];
- int i;
+ uint32_t i;
packet = (struct vis_packet *)info->skb_packet->data;
#define VERSION "1.3"
-static int compress_src = 1;
-static int compress_dst = 1;
+static bool compress_src = true;
+static bool compress_dst = true;
static LIST_HEAD(bnep_session_list);
static DECLARE_RWSEM(bnep_session_sem);
if (!test_bit(HCI_RAW, &hdev->flags)) {
set_bit(HCI_INIT, &hdev->flags);
__hci_request(hdev, hci_reset_req, 0,
- msecs_to_jiffies(HCI_INIT_TIMEOUT));
+ msecs_to_jiffies(250));
clear_bit(HCI_INIT, &hdev->flags);
}
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
-static int enable_le;
+static bool enable_le;
/* Handle HCI Event packets */
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
-static int enable_mgmt;
+static bool enable_mgmt;
/* ----- HCI socket interface ----- */
#include <net/bluetooth/l2cap.h>
#include <net/bluetooth/smp.h>
-int disable_ertm;
+bool disable_ertm;
static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN;
static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP, };
#define VERSION "1.11"
-static int disable_cfc;
-static int l2cap_ertm;
+static bool disable_cfc;
+static bool l2cap_ertm;
static int channel_mtu = -1;
static unsigned int l2cap_mtu = RFCOMM_MAX_L2CAP_MTU;
#include <net/bluetooth/hci_core.h>
#include <net/bluetooth/sco.h>
-static int disable_esco;
+static bool disable_esco;
static const struct proto_ops sco_sock_ops;
brioctl_set(br_ioctl_deviceless_stub);
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
br_fdb_test_addr_hook = br_fdb_test_addr;
#endif
rcu_barrier(); /* Wait for completion of call_rcu()'s */
br_netfilter_fini();
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
br_fdb_test_addr_hook = NULL;
#endif
return -EINVAL;
spin_lock_bh(&br->lock);
- memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
- br_stp_change_bridge_id(br, addr->sa_data);
+ if (compare_ether_addr(dev->dev_addr, addr->sa_data)) {
+ memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+ br_fdb_change_mac_address(br, addr->sa_data);
+ br_stp_change_bridge_id(br, addr->sa_data);
+ }
br->flags |= BR_SET_MAC_ADDR;
spin_unlock_bh(&br->lock);
strcpy(info->bus_info, "N/A");
}
-static u32 br_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t br_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
struct net_bridge *br = netdev_priv(dev);
dev->priv_flags = IFF_EBRIDGE;
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
- NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX |
+ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX |
NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_TX;
dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
- NETIF_F_GSO_MASK | NETIF_F_NO_CSUM |
+ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
NETIF_F_HW_VLAN_TX;
br->dev = dev;
static struct kmem_cache *br_fdb_cache __read_mostly;
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr);
-static void fdb_notify(const struct net_bridge_fdb_entry *, int);
+static void fdb_notify(struct net_bridge *br,
+ const struct net_bridge_fdb_entry *, int);
static u32 fdb_salt __read_mostly;
kmem_cache_free(br_fdb_cache, ent);
}
-static inline void fdb_delete(struct net_bridge_fdb_entry *f)
+static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
{
- fdb_notify(f, RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
+ fdb_notify(br, f, RTM_DELNEIGH);
call_rcu(&f->rcu, fdb_rcu_free);
}
}
/* delete old one */
- fdb_delete(f);
+ fdb_delete(br, f);
goto insert;
}
}
spin_unlock_bh(&br->hash_lock);
}
+void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
+{
+ struct net_bridge_fdb_entry *f;
+
+ /* If old entry was unassociated with any port, then delete it. */
+ f = __br_fdb_get(br, br->dev->dev_addr);
+ if (f && f->is_local && !f->dst)
+ fdb_delete(br, f);
+
+ fdb_insert(br, NULL, newaddr);
+}
+
void br_fdb_cleanup(unsigned long _data)
{
struct net_bridge *br = (struct net_bridge *)_data;
continue;
this_timer = f->updated + delay;
if (time_before_eq(this_timer, jiffies))
- fdb_delete(f);
+ fdb_delete(br, f);
else if (time_before(this_timer, next_timer))
next_timer = this_timer;
}
struct hlist_node *h, *n;
hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) {
if (!f->is_static)
- fdb_delete(f);
+ fdb_delete(br, f);
}
}
spin_unlock_bh(&br->hash_lock);
}
}
- fdb_delete(f);
+ fdb_delete(br, f);
skip_delete: ;
}
}
return NULL;
}
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
/* Interface used by ATM LANE hook to test
* if an addr is on some other bridge port */
int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
ret = 0;
else {
fdb = __br_fdb_get(port->br, addr);
- ret = fdb && fdb->dst->dev != dev &&
+ ret = fdb && fdb->dst && fdb->dst->dev != dev &&
fdb->dst->state == BR_STATE_FORWARDING;
}
rcu_read_unlock();
if (has_expired(br, f))
continue;
+ /* ignore pseudo entry for local MAC address */
+ if (!f->dst)
+ continue;
+
if (skip) {
--skip;
continue;
fdb->is_static = 0;
fdb->updated = fdb->used = jiffies;
hlist_add_head_rcu(&fdb->hlist, head);
- fdb_notify(fdb, RTM_NEWNEIGH);
}
return fdb;
}
br_warn(br, "adding interface %s with same address "
"as a received packet\n",
source->dev->name);
- fdb_delete(fdb);
+ fdb_delete(br, fdb);
}
fdb = fdb_create(head, source, addr);
return -ENOMEM;
fdb->is_local = fdb->is_static = 1;
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
return 0;
}
}
} else {
spin_lock(&br->hash_lock);
- if (likely(!fdb_find(head, addr)))
- fdb_create(head, source, addr);
-
+ if (likely(!fdb_find(head, addr))) {
+ fdb = fdb_create(head, source, addr);
+ if (fdb)
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
+ }
/* else we lose race and someone else inserts
* it first, don't bother updating
*/
return NUD_REACHABLE;
}
-static int fdb_fill_info(struct sk_buff *skb,
+static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb,
u32 pid, u32 seq, int type, unsigned int flags)
{
if (nlh == NULL)
return -EMSGSIZE;
-
ndm = nlmsg_data(nlh);
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_pad1 = 0;
ndm->ndm_pad2 = 0;
ndm->ndm_flags = 0;
ndm->ndm_type = 0;
- ndm->ndm_ifindex = fdb->dst->dev->ifindex;
+ ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
ndm->ndm_state = fdb_to_nud(fdb);
NLA_PUT(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr);
+ nla_total_size(sizeof(struct nda_cacheinfo));
}
-static void fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
+static void fdb_notify(struct net_bridge *br,
+ const struct net_bridge_fdb_entry *fdb, int type)
{
- struct net *net = dev_net(fdb->dst->dev);
+ struct net *net = dev_net(br->dev);
struct sk_buff *skb;
int err = -ENOBUFS;
if (skb == NULL)
goto errout;
- err = fdb_fill_info(skb, fdb, 0, 0, type, 0);
+ err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in fdb_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
if (idx < cb->args[0])
goto skip;
- if (fdb_fill_info(skb, f,
+ if (fdb_fill_info(skb, br, f,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
return skb->len;
}
-/* Create new static fdb entry */
+/* Update (create or replace) forwarding database entry */
static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
__u16 state, __u16 flags)
{
fdb = fdb_create(head, source, addr);
if (!fdb)
return -ENOMEM;
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
} else {
if (flags & NLM_F_EXCL)
return -EEXIST;
+ }
+
+ if (fdb_to_nud(fdb) != state) {
+ if (state & NUD_PERMANENT)
+ fdb->is_local = fdb->is_static = 1;
+ else if (state & NUD_NOARP) {
+ fdb->is_local = 0;
+ fdb->is_static = 1;
+ } else
+ fdb->is_local = fdb->is_static = 0;
- if (flags & NLM_F_REPLACE)
- fdb->updated = fdb->used = jiffies;
- fdb->is_local = fdb->is_static = 0;
+ fdb->updated = fdb->used = jiffies;
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
}
- if (state & NUD_PERMANENT)
- fdb->is_local = fdb->is_static = 1;
- else if (state & NUD_NOARP)
- fdb->is_static = 1;
return 0;
}
return -EINVAL;
}
+ if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
+ pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
+ return -EINVAL;
+ }
+
p = br_port_get_rtnl(dev);
if (p == NULL) {
pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
return -EINVAL;
}
- spin_lock_bh(&p->br->hash_lock);
- err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags);
- spin_unlock_bh(&p->br->hash_lock);
+ if (ndm->ndm_flags & NTF_USE) {
+ rcu_read_lock();
+ br_fdb_update(p->br, p, addr);
+ rcu_read_unlock();
+ } else {
+ spin_lock_bh(&p->br->hash_lock);
+ err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags);
+ spin_unlock_bh(&p->br->hash_lock);
+ }
return err;
}
if (!fdb)
return -ENOENT;
- fdb_delete(fdb);
+ fdb_delete(p->br, fdb);
return 0;
}
/* called with rcu_read_lock */
void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
- if (should_deliver(to, skb)) {
+ if (to && should_deliver(to, skb)) {
__br_deliver(to, skb);
return;
}
/*
* Recomputes features using slave's features
*/
-u32 br_features_recompute(struct net_bridge *br, u32 features)
+netdev_features_t br_features_recompute(struct net_bridge *br,
+ netdev_features_t features)
{
struct net_bridge_port *p;
- u32 mask;
+ netdev_features_t mask;
if (list_empty(&br->port_list))
return features;
#include <linux/slab.h>
#include <linux/timer.h>
#include <net/ip.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/mld.h>
#include <net/addrconf.h>
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
{
if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
switch (a->proto) {
case htons(ETH_P_IP):
return a->u.ip4 == b->u.ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
#endif
return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
const struct in6_addr *ip)
{
switch (ip->proto) {
case htons(ETH_P_IP):
return __br_ip4_hash(mdb, ip->u.ip4);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return __br_ip6_hash(mdb, &ip->u.ip6);
#endif
return br_mdb_ip_get(mdb, &br_dst);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static struct net_bridge_mdb_entry *br_mdb_ip6_get(
struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst)
{
struct br_ip br_dst;
- ipv6_addr_copy(&br_dst.u.ip6, dst);
+ br_dst.u.ip6 = *dst;
br_dst.proto = htons(ETH_P_IPV6);
return br_mdb_ip_get(mdb, &br_dst);
case htons(ETH_P_IP):
ip.u.ip4 = ip_hdr(skb)->daddr;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
- ipv6_addr_copy(&ip.u.ip6, &ipv6_hdr(skb)->daddr);
+ ip.u.ip6 = ipv6_hdr(skb)->daddr;
break;
#endif
default:
return skb;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
const struct in6_addr *group)
{
mldq->mld_cksum = 0;
mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
mldq->mld_reserved = 0;
- ipv6_addr_copy(&mldq->mld_mca, group);
+ mldq->mld_mca = *group;
/* checksum */
mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
switch (addr->proto) {
case htons(ETH_P_IP):
return br_ip4_multicast_alloc_query(br, addr->u.ip4);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
#endif
return br_multicast_add_group(br, port, &br_group);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
const struct in6_addr *group)
if (!ipv6_is_transient_multicast(group))
return 0;
- ipv6_addr_copy(&br_group.u.ip6, group);
+ br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
return br_multicast_add_group(br, port, &br_group);
br_group.proto = htons(ETH_P_IP);
__br_multicast_send_query(br, port, &br_group);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
br_group.proto = htons(ETH_P_IPV6);
__br_multicast_send_query(br, port, &br_group);
#endif
return err;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_mld2_report(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
return err;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int br_ip6_multicast_query(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
br_multicast_leave_group(br, port, &br_group);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static void br_ip6_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
const struct in6_addr *group)
if (!ipv6_is_transient_multicast(group))
return;
- ipv6_addr_copy(&br_group.u.ip6, group);
+ br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_multicast_leave_group(br, port, &br_group);
return err;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int br_multicast_ipv6_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
const struct ipv6hdr *ip6h;
u8 icmp6_type;
u8 nexthdr;
+ __be16 frag_off;
unsigned len;
int offset;
int err;
return -EINVAL;
nexthdr = ip6h->nexthdr;
- offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr);
+ offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
return 0;
__skb_pull(skb2, offset);
skb_reset_transport_header(skb2);
+ skb_postpull_rcsum(skb2, skb_network_header(skb2),
+ skb_network_header_len(skb2));
icmp6_type = icmp6_hdr(skb2)->icmp6_type;
switch (skb->protocol) {
case htons(ETH_P_IP):
return br_multicast_ipv4_rcv(br, port, skb);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return br_multicast_ipv6_rcv(br, port, skb);
#endif
int err = 0;
struct net_bridge_mdb_htable *mdb;
- spin_lock(&br->multicast_lock);
+ spin_lock_bh(&br->multicast_lock);
if (br->multicast_disabled == !val)
goto unlock;
}
unlock:
- spin_unlock(&br->multicast_lock);
+ spin_unlock_bh(&br->multicast_lock);
return err;
}
return NULL;
}
+static unsigned int fake_mtu(const struct dst_entry *dst)
+{
+ return dst->dev->mtu;
+}
+
static struct dst_ops fake_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.update_pmtu = fake_update_pmtu,
.cow_metrics = fake_cow_metrics,
.neigh_lookup = fake_neigh_lookup,
+ .mtu = fake_mtu,
};
/*
rt->dst.dev = br->dev;
rt->dst.path = &rt->dst;
dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
- rt->dst.flags = DST_NOXFRM;
+ rt->dst.flags = DST_NOXFRM | DST_NOPEER;
rt->dst.ops = &fake_dst_ops;
}
if (!skb->dev)
goto free_skb;
dst = skb_dst(skb);
- neigh = dst_get_neighbour(dst);
+ neigh = dst_get_neighbour_noref(dst);
if (neigh->hh.hh_len) {
neigh_hh_bridge(&neigh->hh, skb);
skb->dev = nf_bridge->physindev;
return NF_STOLEN;
}
-#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
static int br_nf_dev_queue_xmit(struct sk_buff *skb)
{
int ret;
#include <net/sock.h>
#include "br_private.h"
+#include "br_private_stp.h"
static inline size_t br_nlmsg_size(void)
{
p->state = new_state;
br_log_state(p);
+
+ spin_lock_bh(&p->br->lock);
+ br_port_state_selection(p->br);
+ spin_unlock_bh(&p->br->lock);
+
br_ifinfo_notify(RTM_NEWLINK, p);
return 0;
{
union {
__be32 ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
} u;
extern void br_fdb_flush(struct net_bridge *br);
extern void br_fdb_changeaddr(struct net_bridge_port *p,
const unsigned char *newaddr);
+extern void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
extern void br_fdb_cleanup(unsigned long arg);
extern void br_fdb_delete_by_port(struct net_bridge *br,
const struct net_bridge_port *p, int do_all);
extern int br_del_if(struct net_bridge *br,
struct net_device *dev);
extern int br_min_mtu(const struct net_bridge *br);
-extern u32 br_features_recompute(struct net_bridge *br, u32 features);
+extern netdev_features_t br_features_recompute(struct net_bridge *br,
+ netdev_features_t features);
/* br_input.c */
extern int br_handle_frame_finish(struct sk_buff *skb);
extern unsigned long br_timer_value(const struct timer_list *timer);
/* br.c */
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr);
#endif
struct net_bridge_port *p;
unsigned int liveports = 0;
- /* Don't change port states if userspace is handling STP */
- if (br->stp_enabled == BR_USER_STP)
- return;
-
list_for_each_entry(p, &br->port_list, list) {
if (p->state == BR_STATE_DISABLED)
continue;
- if (p->port_no == br->root_port) {
- p->config_pending = 0;
- p->topology_change_ack = 0;
- br_make_forwarding(p);
- } else if (br_is_designated_port(p)) {
- del_timer(&p->message_age_timer);
- br_make_forwarding(p);
- } else {
- p->config_pending = 0;
- p->topology_change_ack = 0;
- br_make_blocking(p);
+ /* Don't change port states if userspace is handling STP */
+ if (br->stp_enabled != BR_USER_STP) {
+ if (p->port_no == br->root_port) {
+ p->config_pending = 0;
+ p->topology_change_ack = 0;
+ br_make_forwarding(p);
+ } else if (br_is_designated_port(p)) {
+ del_timer(&p->message_age_timer);
+ br_make_forwarding(p);
+ } else {
+ p->config_pending = 0;
+ p->topology_change_ack = 0;
+ br_make_blocking(p);
+ }
}
if (p->state == BR_STATE_FORWARDING)
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
+ __be16 frag_off;
int offset_ph;
- offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
+ offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
if (offset_ph == -1)
return false;
if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
goto out;
}
-#if defined(CONFIG_BRIDGE_EBT_IP6) || defined(CONFIG_BRIDGE_EBT_IP6_MODULE)
+#if IS_ENABLED(CONFIG_BRIDGE_EBT_IP6)
if ((bitmask & EBT_LOG_IP6) && eth_hdr(skb)->h_proto ==
htons(ETH_P_IPV6)) {
const struct ipv6hdr *ih;
struct ipv6hdr _iph;
uint8_t nexthdr;
+ __be16 frag_off;
int offset_ph;
ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
&ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
nexthdr = ih->nexthdr;
- offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr);
+ offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
if (offset_ph == -1)
goto out;
print_ports(skb, nexthdr, offset_ph);
If you select to build it as a built-in then the main CAIF device must
also be a built-in.
If unsure say Y.
+
+config CAIF_USB
+ tristate "CAIF USB support"
+ depends on CAIF
+ default n
+ ---help---
+ Say Y if you are using CAIF over USB CDC NCM.
+ This can be either built-in or a loadable module,
+ If you select to build it as a built-in then the main CAIF device must
+ also be a built-in.
+ If unsure say N.
obj-$(CONFIG_CAIF) += caif.o
obj-$(CONFIG_CAIF_NETDEV) += chnl_net.o
obj-$(CONFIG_CAIF) += caif_socket.o
+obj-$(CONFIG_CAIF_USB) += caif_usb.o
export-y := caif.o
#include <linux/netdevice.h>
#include <linux/mutex.h>
#include <linux/module.h>
+#include <linux/spinlock.h>
#include <net/netns/generic.h>
#include <net/net_namespace.h>
#include <net/pkt_sched.h>
#include <net/caif/caif_layer.h>
#include <net/caif/cfpkt.h>
#include <net/caif/cfcnfg.h>
+#include <net/caif/cfserl.h>
MODULE_LICENSE("GPL");
struct list_head list;
struct net_device *netdev;
int __percpu *pcpu_refcnt;
+ spinlock_t flow_lock;
+ struct sk_buff *xoff_skb;
+ void (*xoff_skb_dtor)(struct sk_buff *skb);
+ bool xoff;
};
struct caif_device_entry_list {
};
static int caif_net_id;
+static int q_high = 50; /* Percent */
struct cfcnfg *get_cfcnfg(struct net *net)
{
struct caif_net *caifn;
- BUG_ON(!net);
caifn = net_generic(net, caif_net_id);
- BUG_ON(!caifn);
+ if (!caifn)
+ return NULL;
return caifn->cfg;
}
EXPORT_SYMBOL(get_cfcnfg);
static struct caif_device_entry_list *caif_device_list(struct net *net)
{
struct caif_net *caifn;
- BUG_ON(!net);
caifn = net_generic(net, caif_net_id);
- BUG_ON(!caifn);
+ if (!caifn)
+ return NULL;
return &caifn->caifdevs;
}
struct caif_device_entry *caifd;
caifdevs = caif_device_list(dev_net(dev));
- BUG_ON(!caifdevs);
+ if (!caifdevs)
+ return NULL;
caifd = kzalloc(sizeof(*caifd), GFP_KERNEL);
if (!caifd)
struct caif_device_entry_list *caifdevs =
caif_device_list(dev_net(dev));
struct caif_device_entry *caifd;
- BUG_ON(!caifdevs);
+ if (!caifdevs)
+ return NULL;
+
list_for_each_entry_rcu(caifd, &caifdevs->list, list) {
if (caifd->netdev == dev)
return caifd;
return NULL;
}
+void caif_flow_cb(struct sk_buff *skb)
+{
+ struct caif_device_entry *caifd;
+ void (*dtor)(struct sk_buff *skb) = NULL;
+ bool send_xoff;
+
+ WARN_ON(skb->dev == NULL);
+
+ rcu_read_lock();
+ caifd = caif_get(skb->dev);
+ caifd_hold(caifd);
+ rcu_read_unlock();
+
+ spin_lock_bh(&caifd->flow_lock);
+ send_xoff = caifd->xoff;
+ caifd->xoff = 0;
+ if (!WARN_ON(caifd->xoff_skb_dtor == NULL)) {
+ WARN_ON(caifd->xoff_skb != skb);
+ dtor = caifd->xoff_skb_dtor;
+ caifd->xoff_skb = NULL;
+ caifd->xoff_skb_dtor = NULL;
+ }
+ spin_unlock_bh(&caifd->flow_lock);
+
+ if (dtor)
+ dtor(skb);
+
+ if (send_xoff)
+ caifd->layer.up->
+ ctrlcmd(caifd->layer.up,
+ _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND,
+ caifd->layer.id);
+ caifd_put(caifd);
+}
+
static int transmit(struct cflayer *layer, struct cfpkt *pkt)
{
- int err;
+ int err, high = 0, qlen = 0;
+ struct caif_dev_common *caifdev;
struct caif_device_entry *caifd =
container_of(layer, struct caif_device_entry, layer);
struct sk_buff *skb;
+ struct netdev_queue *txq;
+
+ rcu_read_lock_bh();
skb = cfpkt_tonative(pkt);
skb->dev = caifd->netdev;
+ skb_reset_network_header(skb);
+ skb->protocol = htons(ETH_P_CAIF);
+ caifdev = netdev_priv(caifd->netdev);
+
+ /* Check if we need to handle xoff */
+ if (likely(caifd->netdev->tx_queue_len == 0))
+ goto noxoff;
+
+ if (unlikely(caifd->xoff))
+ goto noxoff;
+
+ if (likely(!netif_queue_stopped(caifd->netdev))) {
+ /* If we run with a TX queue, check if the queue is too long*/
+ txq = netdev_get_tx_queue(skb->dev, 0);
+ qlen = qdisc_qlen(rcu_dereference_bh(txq->qdisc));
+
+ if (likely(qlen == 0))
+ goto noxoff;
+
+ high = (caifd->netdev->tx_queue_len * q_high) / 100;
+ if (likely(qlen < high))
+ goto noxoff;
+ }
+
+ /* Hold lock while accessing xoff */
+ spin_lock_bh(&caifd->flow_lock);
+ if (caifd->xoff) {
+ spin_unlock_bh(&caifd->flow_lock);
+ goto noxoff;
+ }
+
+ /*
+ * Handle flow off, we do this by temporary hi-jacking this
+ * skb's destructor function, and replace it with our own
+ * flow-on callback. The callback will set flow-on and call
+ * the original destructor.
+ */
+
+ pr_debug("queue has stopped(%d) or is full (%d > %d)\n",
+ netif_queue_stopped(caifd->netdev),
+ qlen, high);
+ caifd->xoff = 1;
+ caifd->xoff_skb = skb;
+ caifd->xoff_skb_dtor = skb->destructor;
+ skb->destructor = caif_flow_cb;
+ spin_unlock_bh(&caifd->flow_lock);
+
+ caifd->layer.up->ctrlcmd(caifd->layer.up,
+ _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND,
+ caifd->layer.id);
+noxoff:
+ rcu_read_unlock_bh();
err = dev_queue_xmit(skb);
if (err > 0)
/* Release reference to stack upwards */
caifd_put(caifd);
- return 0;
+
+ if (err != 0)
+ err = NET_RX_DROP;
+ return err;
}
static struct packet_type caif_packet_type __read_mostly = {
caifd_put(caifd);
}
+void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+ struct cflayer *link_support, int head_room,
+ struct cflayer **layer, int (**rcv_func)(
+ struct sk_buff *, struct net_device *,
+ struct packet_type *, struct net_device *))
+{
+ struct caif_device_entry *caifd;
+ enum cfcnfg_phy_preference pref;
+ struct cfcnfg *cfg = get_cfcnfg(dev_net(dev));
+ struct caif_device_entry_list *caifdevs;
+
+ caifdevs = caif_device_list(dev_net(dev));
+ if (!cfg || !caifdevs)
+ return;
+ caifd = caif_device_alloc(dev);
+ if (!caifd)
+ return;
+ *layer = &caifd->layer;
+ spin_lock_init(&caifd->flow_lock);
+
+ switch (caifdev->link_select) {
+ case CAIF_LINK_HIGH_BANDW:
+ pref = CFPHYPREF_HIGH_BW;
+ break;
+ case CAIF_LINK_LOW_LATENCY:
+ pref = CFPHYPREF_LOW_LAT;
+ break;
+ default:
+ pref = CFPHYPREF_HIGH_BW;
+ break;
+ }
+ mutex_lock(&caifdevs->lock);
+ list_add_rcu(&caifd->list, &caifdevs->list);
+
+ strncpy(caifd->layer.name, dev->name,
+ sizeof(caifd->layer.name) - 1);
+ caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0;
+ caifd->layer.transmit = transmit;
+ cfcnfg_add_phy_layer(cfg,
+ dev,
+ &caifd->layer,
+ pref,
+ link_support,
+ caifdev->use_fcs,
+ head_room);
+ mutex_unlock(&caifdevs->lock);
+ if (rcv_func)
+ *rcv_func = receive;
+}
+EXPORT_SYMBOL(caif_enroll_dev);
+
/* notify Caif of device events */
static int caif_device_notify(struct notifier_block *me, unsigned long what,
void *arg)
struct net_device *dev = arg;
struct caif_device_entry *caifd = NULL;
struct caif_dev_common *caifdev;
- enum cfcnfg_phy_preference pref;
- enum cfcnfg_phy_type phy_type;
struct cfcnfg *cfg;
+ struct cflayer *layer, *link_support;
+ int head_room = 0;
struct caif_device_entry_list *caifdevs;
- if (dev->type != ARPHRD_CAIF)
- return 0;
-
cfg = get_cfcnfg(dev_net(dev));
- if (cfg == NULL)
+ caifdevs = caif_device_list(dev_net(dev));
+ if (!cfg || !caifdevs)
return 0;
- caifdevs = caif_device_list(dev_net(dev));
+ caifd = caif_get(dev);
+ if (caifd == NULL && dev->type != ARPHRD_CAIF)
+ return 0;
switch (what) {
case NETDEV_REGISTER:
- caifd = caif_device_alloc(dev);
- if (!caifd)
- return 0;
+ if (caifd != NULL)
+ break;
caifdev = netdev_priv(dev);
- caifdev->flowctrl = dev_flowctrl;
- caifd->layer.transmit = transmit;
-
- if (caifdev->use_frag)
- phy_type = CFPHYTYPE_FRAG;
- else
- phy_type = CFPHYTYPE_CAIF;
-
- switch (caifdev->link_select) {
- case CAIF_LINK_HIGH_BANDW:
- pref = CFPHYPREF_HIGH_BW;
- break;
- case CAIF_LINK_LOW_LATENCY:
- pref = CFPHYPREF_LOW_LAT;
- break;
- default:
- pref = CFPHYPREF_HIGH_BW;
- break;
+ link_support = NULL;
+ if (caifdev->use_frag) {
+ head_room = 1;
+ link_support = cfserl_create(dev->ifindex,
+ caifdev->use_stx);
+ if (!link_support) {
+ pr_warn("Out of memory\n");
+ break;
+ }
}
- strncpy(caifd->layer.name, dev->name,
- sizeof(caifd->layer.name) - 1);
- caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0;
-
- mutex_lock(&caifdevs->lock);
- list_add_rcu(&caifd->list, &caifdevs->list);
-
- cfcnfg_add_phy_layer(cfg,
- phy_type,
- dev,
- &caifd->layer,
- pref,
- caifdev->use_fcs,
- caifdev->use_stx);
- mutex_unlock(&caifdevs->lock);
+ caif_enroll_dev(dev, caifdev, link_support, head_room,
+ &layer, NULL);
+ caifdev->flowctrl = dev_flowctrl;
break;
case NETDEV_UP:
break;
}
+ caifd->xoff = 0;
cfcnfg_set_phy_state(cfg, &caifd->layer, true);
rcu_read_unlock();
caifd->layer.up->ctrlcmd(caifd->layer.up,
_CAIF_CTRLCMD_PHYIF_DOWN_IND,
caifd->layer.id);
+
+ spin_lock_bh(&caifd->flow_lock);
+
+ /*
+ * Replace our xoff-destructor with original destructor.
+ * We trust that skb->destructor *always* is called before
+ * the skb reference is invalid. The hijacked SKB destructor
+ * takes the flow_lock so manipulating the skb->destructor here
+ * should be safe.
+ */
+ if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL)
+ caifd->xoff_skb->destructor = caifd->xoff_skb_dtor;
+
+ caifd->xoff = 0;
+ caifd->xoff_skb_dtor = NULL;
+ caifd->xoff_skb = NULL;
+
+ spin_unlock_bh(&caifd->flow_lock);
caifd_put(caifd);
break;
static int caif_init_net(struct net *net)
{
struct caif_net *caifn = net_generic(net, caif_net_id);
- BUG_ON(!caifn);
+ if (WARN_ON(!caifn))
+ return -EINVAL;
+
INIT_LIST_HEAD(&caifn->caifdevs.list);
mutex_init(&caifn->caifdevs.lock);
caifn->cfg = cfcnfg_create();
- if (!caifn->cfg) {
- pr_warn("can't create cfcnfg\n");
+ if (!caifn->cfg)
return -ENOMEM;
- }
return 0;
}
struct caif_device_entry *caifd, *tmp;
struct caif_device_entry_list *caifdevs =
caif_device_list(net);
- struct cfcnfg *cfg;
+ struct cfcnfg *cfg = get_cfcnfg(net);
+
+ if (!cfg || !caifdevs)
+ return;
rtnl_lock();
mutex_lock(&caifdevs->lock);
- cfg = get_cfcnfg(net);
- if (cfg == NULL) {
- mutex_unlock(&caifdevs->lock);
- return;
- }
-
list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) {
int i = 0;
list_del_rcu(&caifd->list);
--- /dev/null
+/*
+ * CAIF USB handler
+ * Copyright (C) ST-Ericsson AB 2011
+ * Author: Sjur Brendeland/sjur.brandeland@stericsson.com
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/usbnet.h>
+#include <net/netns/generic.h>
+#include <net/caif/caif_dev.h>
+#include <net/caif/caif_layer.h>
+#include <net/caif/cfpkt.h>
+#include <net/caif/cfcnfg.h>
+
+MODULE_LICENSE("GPL");
+
+#define CFUSB_PAD_DESCR_SZ 1 /* Alignment descriptor length */
+#define CFUSB_ALIGNMENT 4 /* Number of bytes to align. */
+#define CFUSB_MAX_HEADLEN (CFUSB_PAD_DESCR_SZ + CFUSB_ALIGNMENT-1)
+#define STE_USB_VID 0x04cc /* USB Product ID for ST-Ericsson */
+#define STE_USB_PID_CAIF 0x2306 /* Product id for CAIF Modems */
+
+struct cfusbl {
+ struct cflayer layer;
+ u8 tx_eth_hdr[ETH_HLEN];
+};
+
+static bool pack_added;
+
+static int cfusbl_receive(struct cflayer *layr, struct cfpkt *pkt)
+{
+ u8 hpad;
+
+ /* Remove padding. */
+ cfpkt_extr_head(pkt, &hpad, 1);
+ cfpkt_extr_head(pkt, NULL, hpad);
+ return layr->up->receive(layr->up, pkt);
+}
+
+static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt)
+{
+ struct caif_payload_info *info;
+ u8 hpad;
+ u8 zeros[CFUSB_ALIGNMENT];
+ struct sk_buff *skb;
+ struct cfusbl *usbl = container_of(layr, struct cfusbl, layer);
+
+ skb = cfpkt_tonative(pkt);
+
+ skb_reset_network_header(skb);
+ skb->protocol = htons(ETH_P_IP);
+
+ info = cfpkt_info(pkt);
+ hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1);
+
+ if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) {
+ pr_warn("Headroom to small\n");
+ kfree_skb(skb);
+ return -EIO;
+ }
+ memset(zeros, 0, hpad);
+
+ cfpkt_add_head(pkt, zeros, hpad);
+ cfpkt_add_head(pkt, &hpad, 1);
+ cfpkt_add_head(pkt, usbl->tx_eth_hdr, sizeof(usbl->tx_eth_hdr));
+ return layr->dn->transmit(layr->dn, pkt);
+}
+
+static void cfusbl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
+ int phyid)
+{
+ if (layr->up && layr->up->ctrlcmd)
+ layr->up->ctrlcmd(layr->up, ctrl, layr->id);
+}
+
+struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN],
+ u8 braddr[ETH_ALEN])
+{
+ struct cfusbl *this = kmalloc(sizeof(struct cfusbl), GFP_ATOMIC);
+
+ if (!this) {
+ pr_warn("Out of memory\n");
+ return NULL;
+ }
+ caif_assert(offsetof(struct cfusbl, layer) == 0);
+
+ memset(this, 0, sizeof(struct cflayer));
+ this->layer.receive = cfusbl_receive;
+ this->layer.transmit = cfusbl_transmit;
+ this->layer.ctrlcmd = cfusbl_ctrlcmd;
+ snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "usb%d", phyid);
+ this->layer.id = phyid;
+
+ /*
+ * Construct TX ethernet header:
+ * 0-5 destination address
+ * 5-11 source address
+ * 12-13 protocol type
+ */
+ memcpy(&this->tx_eth_hdr[ETH_ALEN], braddr, ETH_ALEN);
+ memcpy(&this->tx_eth_hdr[ETH_ALEN], ethaddr, ETH_ALEN);
+ this->tx_eth_hdr[12] = cpu_to_be16(ETH_P_802_EX1) & 0xff;
+ this->tx_eth_hdr[13] = (cpu_to_be16(ETH_P_802_EX1) >> 8) & 0xff;
+ pr_debug("caif ethernet TX-header dst:%pM src:%pM type:%02x%02x\n",
+ this->tx_eth_hdr, this->tx_eth_hdr + ETH_ALEN,
+ this->tx_eth_hdr[12], this->tx_eth_hdr[13]);
+
+ return (struct cflayer *) this;
+}
+
+static struct packet_type caif_usb_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_802_EX1),
+};
+
+static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
+ void *arg)
+{
+ struct net_device *dev = arg;
+ struct caif_dev_common common;
+ struct cflayer *layer, *link_support;
+ struct usbnet *usbnet = netdev_priv(dev);
+ struct usb_device *usbdev = usbnet->udev;
+ struct ethtool_drvinfo drvinfo;
+
+ /*
+ * Quirks: High-jack ethtool to find if we have a NCM device,
+ * and find it's VID/PID.
+ */
+ if (dev->ethtool_ops == NULL || dev->ethtool_ops->get_drvinfo == NULL)
+ return 0;
+
+ dev->ethtool_ops->get_drvinfo(dev, &drvinfo);
+ if (strncmp(drvinfo.driver, "cdc_ncm", 7) != 0)
+ return 0;
+
+ pr_debug("USB CDC NCM device VID:0x%4x PID:0x%4x\n",
+ le16_to_cpu(usbdev->descriptor.idVendor),
+ le16_to_cpu(usbdev->descriptor.idProduct));
+
+ /* Check for VID/PID that supports CAIF */
+ if (!(le16_to_cpu(usbdev->descriptor.idVendor) == STE_USB_VID &&
+ le16_to_cpu(usbdev->descriptor.idProduct) == STE_USB_PID_CAIF))
+ return 0;
+
+ if (what == NETDEV_UNREGISTER)
+ module_put(THIS_MODULE);
+
+ if (what != NETDEV_REGISTER)
+ return 0;
+
+ __module_get(THIS_MODULE);
+
+ memset(&common, 0, sizeof(common));
+ common.use_frag = false;
+ common.use_fcs = false;
+ common.use_stx = false;
+ common.link_select = CAIF_LINK_HIGH_BANDW;
+ common.flowctrl = NULL;
+
+ link_support = cfusbl_create(dev->ifindex, dev->dev_addr,
+ dev->broadcast);
+
+ if (!link_support)
+ return -ENOMEM;
+
+ if (dev->num_tx_queues > 1)
+ pr_warn("USB device uses more than one tx queue\n");
+
+ caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN,
+ &layer, &caif_usb_type.func);
+ if (!pack_added)
+ dev_add_pack(&caif_usb_type);
+ pack_added = true;
+
+ strncpy(layer->name, dev->name,
+ sizeof(layer->name) - 1);
+ layer->name[sizeof(layer->name) - 1] = 0;
+
+ return 0;
+}
+
+static struct notifier_block caif_device_notifier = {
+ .notifier_call = cfusbl_device_notify,
+ .priority = 0,
+};
+
+static int __init cfusbl_init(void)
+{
+ return register_netdevice_notifier(&caif_device_notifier);
+}
+
+static void __exit cfusbl_exit(void)
+{
+ unregister_netdevice_notifier(&caif_device_notifier);
+ dev_remove_pack(&caif_usb_type);
+}
+
+module_init(cfusbl_init);
+module_exit(cfusbl_exit);
/* Interface index */
int ifindex;
- /* Use Start of frame extension */
- bool use_stx;
+ /* Protocol head room added for CAIF link layer */
+ int head_room;
/* Use Start of frame checksum */
bool use_fcs;
if (channel_id != 0) {
struct cflayer *servl;
servl = cfmuxl_remove_uplayer(cfg->mux, channel_id);
+ cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer);
if (servl != NULL)
layer_set_up(servl, NULL);
} else
pr_debug("nothing to disconnect\n");
- cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer);
/* Do RCU sync before initiating cleanup */
synchronize_rcu();
*ifindex = phy->ifindex;
*proto_tail = 2;
- *proto_head =
-
- protohead[param.linktype] + (phy->use_stx ? 1 : 0);
+ *proto_head = protohead[param.linktype] + phy->head_room;
rcu_read_unlock();
}
void
-cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type,
+cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
struct net_device *dev, struct cflayer *phy_layer,
enum cfcnfg_phy_preference pref,
- bool fcs, bool stx)
+ struct cflayer *link_support,
+ bool fcs, int head_room)
{
struct cflayer *frml;
- struct cflayer *phy_driver = NULL;
struct cfcnfg_phyinfo *phyinfo = NULL;
int i;
u8 phyid;
goto got_phyid;
}
pr_warn("Too many CAIF Link Layers (max 6)\n");
- goto out_err;
+ goto out;
got_phyid:
phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC);
if (!phyinfo)
goto out_err;
- switch (phy_type) {
- case CFPHYTYPE_FRAG:
- phy_driver =
- cfserl_create(CFPHYTYPE_FRAG, phyid, stx);
- if (!phy_driver)
- goto out_err;
- break;
- case CFPHYTYPE_CAIF:
- phy_driver = NULL;
- break;
- default:
- goto out_err;
- }
phy_layer->id = phyid;
phyinfo->pref = pref;
phyinfo->id = phyid;
phyinfo->dev_info.dev = dev;
phyinfo->phy_layer = phy_layer;
phyinfo->ifindex = dev->ifindex;
- phyinfo->use_stx = stx;
+ phyinfo->head_room = head_room;
phyinfo->use_fcs = fcs;
frml = cffrml_create(phyid, fcs);
phyinfo->frm_layer = frml;
layer_set_up(frml, cnfg->mux);
- if (phy_driver != NULL) {
- phy_driver->id = phyid;
- layer_set_dn(frml, phy_driver);
- layer_set_up(phy_driver, frml);
- layer_set_dn(phy_driver, phy_layer);
- layer_set_up(phy_layer, phy_driver);
+ if (link_support != NULL) {
+ link_support->id = phyid;
+ layer_set_dn(frml, link_support);
+ layer_set_up(link_support, frml);
+ layer_set_dn(link_support, phy_layer);
+ layer_set_up(phy_layer, link_support);
} else {
layer_set_dn(frml, phy_layer);
layer_set_up(phy_layer, frml);
}
list_add_rcu(&phyinfo->node, &cnfg->phys);
+out:
mutex_unlock(&cnfg->lock);
return;
out_err:
- kfree(phy_driver);
kfree(phyinfo);
mutex_unlock(&cnfg->lock);
}
static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt)
{
- int tmp;
u16 chks;
u16 len;
+ __le16 data;
+
struct cffrml *this = container_obj(layr);
if (this->dofcs) {
chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff);
- tmp = cpu_to_le16(chks);
- cfpkt_add_trail(pkt, &tmp, 2);
+ data = cpu_to_le16(chks);
+ cfpkt_add_trail(pkt, &data, 2);
} else {
cfpkt_pad_trail(pkt, 2);
}
len = cfpkt_getlen(pkt);
- tmp = cpu_to_le16(len);
- cfpkt_add_head(pkt, &tmp, 2);
+ data = cpu_to_le16(len);
+ cfpkt_add_head(pkt, &data, 2);
cfpkt_info(pkt)->hdr_len += 2;
if (cfpkt_erroneous(pkt)) {
pr_err("Packet is erroneous!\n");
return (struct cfpkt *) skb;
}
-
struct cfpkt *cfpkt_fromnative(enum caif_direction dir, void *nativepkt)
{
struct cfpkt *pkt = skb_to_pkt(nativepkt);
kfree_skb(skb);
}
-
inline bool cfpkt_more(struct cfpkt *pkt)
{
struct sk_buff *skb = pkt_to_skb(pkt);
return skb->len > 0;
}
-
int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len)
{
struct sk_buff *skb = pkt_to_skb(pkt);
}
from = skb_pull(skb, len);
from -= len;
- memcpy(data, from, len);
+ if (data)
+ memcpy(data, from, len);
return 0;
}
+EXPORT_SYMBOL(cfpkt_extr_head);
int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len)
{
return 0;
}
-
int cfpkt_pad_trail(struct cfpkt *pkt, u16 len)
{
return cfpkt_add_body(pkt, NULL, len);
}
-
int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len)
{
struct sk_buff *skb = pkt_to_skb(pkt);
memcpy(to, data, len);
return 0;
}
-
+EXPORT_SYMBOL(cfpkt_add_head);
inline int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len)
{
return cfpkt_add_body(pkt, data, len);
}
-
inline u16 cfpkt_getlen(struct cfpkt *pkt)
{
struct sk_buff *skb = pkt_to_skb(pkt);
return skb->len;
}
-
inline u16 cfpkt_iterate(struct cfpkt *pkt,
u16 (*iter_func)(u16, void *, u16),
u16 data)
return iter_func(data, pkt->skb.data, cfpkt_getlen(pkt));
}
-
int cfpkt_setlen(struct cfpkt *pkt, u16 len)
{
struct sk_buff *skb = pkt_to_skb(pkt);
{
return (struct caif_payload_info *)&pkt_to_skb(pkt)->cb;
}
+EXPORT_SYMBOL(cfpkt_info);
static int cfrfml_transmit_segment(struct cfrfml *rfml, struct cfpkt *pkt)
{
- caif_assert(cfpkt_getlen(pkt) < rfml->fragment_size);
+ caif_assert(cfpkt_getlen(pkt) < rfml->fragment_size + RFM_HEAD_SIZE);
/* Add info for MUX-layer to route the packet out. */
cfpkt_info(pkt)->channel_id = rfml->serv.layer.id;
static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
int phyid);
-struct cflayer *cfserl_create(int type, int instance, bool use_stx)
+struct cflayer *cfserl_create(int instance, bool use_stx)
{
struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC);
if (!this)
this->layer.receive = cfserl_receive;
this->layer.transmit = cfserl_transmit;
this->layer.ctrlcmd = cfserl_ctrlcmd;
- this->layer.type = type;
this->usestx = use_stx;
spin_lock_init(&this->sync);
snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "ser1");
int i, j;
int numrep;
int firstn;
- int rc = -1;
BUG_ON(ruleno >= map->max_rules);
* that this may or may not correspond to the specific types
* referenced by the crush rule.
*/
- if (force >= 0) {
- if (force >= map->max_devices ||
- map->device_parents[force] == 0) {
- /*dprintk("CRUSH: forcefed device dne\n");*/
- rc = -1; /* force fed device dne */
- goto out;
- }
- if (!is_out(map, weight, force, x)) {
- while (1) {
- force_context[++force_pos] = force;
- if (force >= 0)
- force = map->device_parents[force];
- else
- force = map->bucket_parents[-1-force];
- if (force == 0)
- break;
- }
+ if (force >= 0 &&
+ force < map->max_devices &&
+ map->device_parents[force] != 0 &&
+ !is_out(map, weight, force, x)) {
+ while (1) {
+ force_context[++force_pos] = force;
+ if (force >= 0)
+ force = map->device_parents[force];
+ else
+ force = map->bucket_parents[-1-force];
+ if (force == 0)
+ break;
}
}
BUG_ON(1);
}
}
- rc = result_len;
-
-out:
- return rc;
+ return result_len;
}
ceph_pagelist_init(req->r_trail);
}
/* create request message; allow space for oid */
- msg_size += 40;
+ msg_size += MAX_OBJ_NAME_SIZE;
if (snapc)
msg_size += sizeof(u64) * snapc->num_snaps;
if (use_mempool)
#
obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
- gen_stats.o gen_estimator.o net_namespace.o secure_seq.o
+ gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
- neighbour.o rtnetlink.o utils.o link_watch.o filter.o
+ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
+ sock_diag.o
obj-$(CONFIG_XFRM) += flow.o
obj-y += net-sysfs.o
obj-$(CONFIG_TRACEPOINTS) += net-traces.o
obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
-#include <linux/if_tunnel.h>
-#include <linux/if_pppox.h>
-#include <linux/ppp_defs.h>
#include <linux/net_tstamp.h>
+#include <linux/jump_label.h>
+#include <net/flow_keys.h>
#include "net-sysfs.h"
*/
void dev_disable_lro(struct net_device *dev)
{
- u32 flags;
-
/*
* If we're trying to disable lro on a vlan device
* use the underlying physical device instead
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
- if (dev->ethtool_ops && dev->ethtool_ops->get_flags)
- flags = dev->ethtool_ops->get_flags(dev);
- else
- flags = ethtool_op_get_flags(dev);
+ dev->wanted_features &= ~NETIF_F_LRO;
+ netdev_update_features(dev);
- if (!(flags & ETH_FLAG_LRO))
- return;
-
- __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO);
if (unlikely(dev->features & NETIF_F_LRO))
netdev_WARN(dev, "failed to disable LRO!\n");
}
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev == last)
- break;
+ goto outroll;
if (dev->flags & IFF_UP) {
nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
}
}
+outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
}
EXPORT_SYMBOL(call_netdevice_notifiers);
-/* When > 0 there are consumers of rx skb time stamps */
-static atomic_t netstamp_needed = ATOMIC_INIT(0);
+static struct jump_label_key netstamp_needed __read_mostly;
+#ifdef HAVE_JUMP_LABEL
+/* We are not allowed to call jump_label_dec() from irq context
+ * If net_disable_timestamp() is called from irq context, defer the
+ * jump_label_dec() calls.
+ */
+static atomic_t netstamp_needed_deferred;
+#endif
void net_enable_timestamp(void)
{
- atomic_inc(&netstamp_needed);
+#ifdef HAVE_JUMP_LABEL
+ int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+
+ if (deferred) {
+ while (--deferred)
+ jump_label_dec(&netstamp_needed);
+ return;
+ }
+#endif
+ WARN_ON(in_interrupt());
+ jump_label_inc(&netstamp_needed);
}
EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
- atomic_dec(&netstamp_needed);
+#ifdef HAVE_JUMP_LABEL
+ if (in_interrupt()) {
+ atomic_inc(&netstamp_needed_deferred);
+ return;
+ }
+#endif
+ jump_label_dec(&netstamp_needed);
}
EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp_set(struct sk_buff *skb)
{
- if (atomic_read(&netstamp_needed))
+ skb->tstamp.tv64 = 0;
+ if (static_branch(&netstamp_needed))
__net_timestamp(skb);
- else
- skb->tstamp.tv64 = 0;
}
-static inline void net_timestamp_check(struct sk_buff *skb)
-{
- if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed))
- __net_timestamp(skb);
-}
+#define net_timestamp_check(COND, SKB) \
+ if (static_branch(&netstamp_needed)) { \
+ if ((COND) && !(SKB)->tstamp.tv64) \
+ __net_timestamp(SKB); \
+ } \
static int net_hwtstamp_validate(struct ifreq *ifr)
{
* It may return NULL if the skb requires no segmentation. This is
* only possible when GSO is used for verifying header integrity.
*/
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *skb_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_type *ptype;
if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo)
dev->ethtool_ops->get_drvinfo(dev, &info);
- WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n",
- info.driver, dev ? dev->features : 0L,
- skb->sk ? skb->sk->sk_route_caps : 0L,
+ WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d ip_summed=%d\n",
+ info.driver, dev ? &dev->features : NULL,
+ skb->sk ? &skb->sk->sk_route_caps : NULL,
skb->len, skb->data_len, skb->ip_summed);
if (skb_header_cloned(skb) &&
* This function segments the given skb and stores the list of segments
* in skb->next.
*/
-static int dev_gso_segment(struct sk_buff *skb, int features)
+static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
struct sk_buff *segs;
}
}
-static bool can_checksum_protocol(unsigned long features, __be16 protocol)
+static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
{
return ((features & NETIF_F_GEN_CSUM) ||
((features & NETIF_F_V4_CSUM) &&
protocol == htons(ETH_P_FCOE)));
}
-static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
+static netdev_features_t harmonize_features(struct sk_buff *skb,
+ __be16 protocol, netdev_features_t features)
{
if (!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
return features;
}
-u32 netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
- u32 features = skb->dev->features;
+ netdev_features_t features = skb->dev->features;
if (protocol == htons(ETH_P_8021Q)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
unsigned int skb_len;
if (likely(!skb->next)) {
- u32 features;
+ netdev_features_t features;
/*
* If device doesn't need skb->dst, release it right now while
return rc;
}
txq_trans_update(txq);
- if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
+ if (unlikely(netif_xmit_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
return rc;
}
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+static void skb_update_prio(struct sk_buff *skb)
+{
+ struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
+
+ if ((!skb->priority) && (skb->sk) && map)
+ skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+}
+#else
+#define skb_update_prio(skb)
+#endif
+
static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 10
*/
rcu_read_lock_bh();
+ skb_update_prio(skb);
+
txq = dev_pick_tx(dev, skb);
q = rcu_dereference_bh(txq->qdisc);
HARD_TX_LOCK(dev, txq, cpu);
- if (!netif_tx_queue_stopped(txq)) {
+ if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
rc = dev_hard_start_xmit(skb, dev, txq);
__this_cpu_dec(xmit_recursion);
*/
void __skb_get_rxhash(struct sk_buff *skb)
{
- int nhoff, hash = 0, poff;
- const struct ipv6hdr *ip6;
- const struct iphdr *ip;
- const struct vlan_hdr *vlan;
- u8 ip_proto;
- u32 addr1, addr2;
- u16 proto;
- union {
- u32 v32;
- u16 v16[2];
- } ports;
-
- nhoff = skb_network_offset(skb);
- proto = skb->protocol;
-
-again:
- switch (proto) {
- case __constant_htons(ETH_P_IP):
-ip:
- if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
- goto done;
-
- ip = (const struct iphdr *) (skb->data + nhoff);
- if (ip_is_fragment(ip))
- ip_proto = 0;
- else
- ip_proto = ip->protocol;
- addr1 = (__force u32) ip->saddr;
- addr2 = (__force u32) ip->daddr;
- nhoff += ip->ihl * 4;
- break;
- case __constant_htons(ETH_P_IPV6):
-ipv6:
- if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
- goto done;
-
- ip6 = (const struct ipv6hdr *) (skb->data + nhoff);
- ip_proto = ip6->nexthdr;
- addr1 = (__force u32) ip6->saddr.s6_addr32[3];
- addr2 = (__force u32) ip6->daddr.s6_addr32[3];
- nhoff += 40;
- break;
- case __constant_htons(ETH_P_8021Q):
- if (!pskb_may_pull(skb, sizeof(*vlan) + nhoff))
- goto done;
- vlan = (const struct vlan_hdr *) (skb->data + nhoff);
- proto = vlan->h_vlan_encapsulated_proto;
- nhoff += sizeof(*vlan);
- goto again;
- case __constant_htons(ETH_P_PPP_SES):
- if (!pskb_may_pull(skb, PPPOE_SES_HLEN + nhoff))
- goto done;
- proto = *((__be16 *) (skb->data + nhoff +
- sizeof(struct pppoe_hdr)));
- nhoff += PPPOE_SES_HLEN;
- switch (proto) {
- case __constant_htons(PPP_IP):
- goto ip;
- case __constant_htons(PPP_IPV6):
- goto ipv6;
- default:
- goto done;
- }
- default:
- goto done;
- }
-
- switch (ip_proto) {
- case IPPROTO_GRE:
- if (pskb_may_pull(skb, nhoff + 16)) {
- u8 *h = skb->data + nhoff;
- __be16 flags = *(__be16 *)h;
+ struct flow_keys keys;
+ u32 hash;
- /*
- * Only look inside GRE if version zero and no
- * routing
- */
- if (!(flags & (GRE_VERSION|GRE_ROUTING))) {
- proto = *(__be16 *)(h + 2);
- nhoff += 4;
- if (flags & GRE_CSUM)
- nhoff += 4;
- if (flags & GRE_KEY)
- nhoff += 4;
- if (flags & GRE_SEQ)
- nhoff += 4;
- goto again;
- }
- }
- break;
- case IPPROTO_IPIP:
- goto again;
- default:
- break;
- }
+ if (!skb_flow_dissect(skb, &keys))
+ return;
- ports.v32 = 0;
- poff = proto_ports_offset(ip_proto);
- if (poff >= 0) {
- nhoff += poff;
- if (pskb_may_pull(skb, nhoff + 4)) {
- ports.v32 = * (__force u32 *) (skb->data + nhoff);
- if (ports.v16[1] < ports.v16[0])
- swap(ports.v16[0], ports.v16[1]);
- skb->l4_rxhash = 1;
- }
+ if (keys.ports) {
+ if ((__force u16)keys.port16[1] < (__force u16)keys.port16[0])
+ swap(keys.port16[0], keys.port16[1]);
+ skb->l4_rxhash = 1;
}
/* get a consistent hash (same value on both flow directions) */
- if (addr2 < addr1)
- swap(addr1, addr2);
+ if ((__force u32)keys.dst < (__force u32)keys.src)
+ swap(keys.dst, keys.src);
- hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
+ hash = jhash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports, hashrnd);
if (!hash)
hash = 1;
-done:
skb->rxhash = hash;
}
EXPORT_SYMBOL(__skb_get_rxhash);
struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);
+struct jump_label_key rps_needed __read_mostly;
+
static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
if (netpoll_rx(skb))
return NET_RX_DROP;
- if (netdev_tstamp_prequeue)
- net_timestamp_check(skb);
+ net_timestamp_check(netdev_tstamp_prequeue, skb);
trace_netif_rx(skb);
#ifdef CONFIG_RPS
- {
+ if (static_branch(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
rcu_read_unlock();
preempt_enable();
- }
-#else
+ } else
+#endif
{
unsigned int qtail;
ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
put_cpu();
}
-#endif
return ret;
}
EXPORT_SYMBOL(netif_rx);
int ret = NET_RX_DROP;
__be16 type;
- if (!netdev_tstamp_prequeue)
- net_timestamp_check(skb);
+ net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
*/
int netif_receive_skb(struct sk_buff *skb)
{
- if (netdev_tstamp_prequeue)
- net_timestamp_check(skb);
+ net_timestamp_check(netdev_tstamp_prequeue, skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
#ifdef CONFIG_RPS
- {
+ if (static_branch(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu, ret;
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
- } else {
- rcu_read_unlock();
- ret = __netif_receive_skb(skb);
+ return ret;
}
-
- return ret;
+ rcu_read_unlock();
}
-#else
- return __netif_receive_skb(skb);
#endif
+ return __netif_receive_skb(skb);
}
EXPORT_SYMBOL(netif_receive_skb);
sizeof(struct dev_iter_state));
}
+int dev_seq_open_ops(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
+{
+ return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+}
+
static const struct file_operations dev_seq_fops = {
.owner = THIS_MODULE,
.open = dev_seq_open,
static int __dev_set_promiscuity(struct net_device *dev, int inc)
{
- unsigned short old_flags = dev->flags;
+ unsigned int old_flags = dev->flags;
uid_t uid;
gid_t gid;
*/
int dev_set_promiscuity(struct net_device *dev, int inc)
{
- unsigned short old_flags = dev->flags;
+ unsigned int old_flags = dev->flags;
int err;
err = __dev_set_promiscuity(dev, inc);
int dev_set_allmulti(struct net_device *dev, int inc)
{
- unsigned short old_flags = dev->flags;
+ unsigned int old_flags = dev->flags;
ASSERT_RTNL();
int __dev_change_flags(struct net_device *dev, unsigned int flags)
{
- int old_flags = dev->flags;
+ unsigned int old_flags = dev->flags;
int ret;
ASSERT_RTNL();
* Change settings on device based state flags. The flags are
* in the userspace exported format.
*/
-int dev_change_flags(struct net_device *dev, unsigned flags)
+int dev_change_flags(struct net_device *dev, unsigned int flags)
{
- int ret, changes;
- int old_flags = dev->flags;
+ int ret;
+ unsigned int changes, old_flags = dev->flags;
ret = __dev_change_flags(dev, flags);
if (ret < 0)
list_del(&single);
}
-static u32 netdev_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t netdev_fix_features(struct net_device *dev,
+ netdev_features_t features)
{
/* Fix illegal checksum combinations */
if ((features & NETIF_F_HW_CSUM) &&
features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
- if ((features & NETIF_F_NO_CSUM) &&
- (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
- netdev_warn(dev, "mixed no checksumming and other settings.\n");
- features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
- }
-
/* Fix illegal SG+CSUM combinations. */
if ((features & NETIF_F_SG) &&
!(features & NETIF_F_ALL_CSUM)) {
int __netdev_update_features(struct net_device *dev)
{
- u32 features;
+ netdev_features_t features;
int err = 0;
ASSERT_RTNL();
if (dev->features == features)
return 0;
- netdev_dbg(dev, "Features changed: 0x%08x -> 0x%08x\n",
- dev->features, features);
+ netdev_dbg(dev, "Features changed: %pNF -> %pNF\n",
+ &dev->features, &features);
if (dev->netdev_ops->ndo_set_features)
err = dev->netdev_ops->ndo_set_features(dev, features);
if (unlikely(err < 0)) {
netdev_err(dev,
- "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
- err, features, dev->features);
+ "set_features() failed (%d); wanted %pNF, left %pNF\n",
+ err, &features, &dev->features);
return -1;
}
queue->xmit_lock_owner = -1;
netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
queue->dev = dev;
+#ifdef CONFIG_BQL
+ dql_init(&queue->dql, HZ);
+#endif
}
static int netif_alloc_netdev_queues(struct net_device *dev)
dev->wanted_features = dev->features & dev->hw_features;
/* Turn on no cache copy if HW is doing checksum */
- dev->hw_features |= NETIF_F_NOCACHE_COPY;
- if ((dev->features & NETIF_F_ALL_CSUM) &&
- !(dev->features & NETIF_F_NO_CSUM)) {
- dev->wanted_features |= NETIF_F_NOCACHE_COPY;
- dev->features |= NETIF_F_NOCACHE_COPY;
+ if (!(dev->flags & IFF_LOOPBACK)) {
+ dev->hw_features |= NETIF_F_NOCACHE_COPY;
+ if (dev->features & NETIF_F_ALL_CSUM) {
+ dev->wanted_features |= NETIF_F_NOCACHE_COPY;
+ dev->features |= NETIF_F_NOCACHE_COPY;
+ }
}
/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
* @one to the master device with current feature set @all. Will not
* enable anything that is off in @mask. Returns the new feature set.
*/
-u32 netdev_increment_features(u32 all, u32 one, u32 mask)
+netdev_features_t netdev_increment_features(netdev_features_t all,
+ netdev_features_t one, netdev_features_t mask)
{
if (mask & NETIF_F_GEN_CSUM)
mask |= NETIF_F_ALL_CSUM;
all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask;
all &= one | ~NETIF_F_ALL_FOR_ALL;
- /* If device needs checksumming, downgrade to it. */
- if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM))
- all &= ~NETIF_F_NO_CSUM;
-
/* If one device supports hw checksumming, set for all. */
if (all & NETIF_F_GEN_CSUM)
all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
static int dev_mc_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &dev_mc_seq_ops,
- sizeof(struct seq_net_private));
+ return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
}
static const struct file_operations dev_mc_seq_fops = {
dev_hold(dst->dev);
dev_put(dev);
rcu_read_lock();
- neigh = dst_get_neighbour(dst);
+ neigh = dst_get_neighbour_noref(dst);
if (neigh && neigh->dev == dev) {
neigh->dev = dst->dev;
dev_hold(dst->dev);
}
EXPORT_SYMBOL(ethtool_op_get_link);
-u32 ethtool_op_get_tx_csum(struct net_device *dev)
-{
- return (dev->features & NETIF_F_ALL_CSUM) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_tx_csum);
-
-int ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_IP_CSUM;
- else
- dev->features &= ~NETIF_F_IP_CSUM;
-
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_csum);
-
-int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_HW_CSUM;
- else
- dev->features &= ~NETIF_F_HW_CSUM;
-
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum);
-
-int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- else
- dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
-
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum);
-
-u32 ethtool_op_get_sg(struct net_device *dev)
-{
- return (dev->features & NETIF_F_SG) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_sg);
-
-int ethtool_op_set_sg(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_SG;
- else
- dev->features &= ~NETIF_F_SG;
-
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_sg);
-
-u32 ethtool_op_get_tso(struct net_device *dev)
-{
- return (dev->features & NETIF_F_TSO) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_tso);
-
-int ethtool_op_set_tso(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_TSO;
- else
- dev->features &= ~NETIF_F_TSO;
-
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tso);
-
-u32 ethtool_op_get_ufo(struct net_device *dev)
-{
- return (dev->features & NETIF_F_UFO) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_ufo);
-
-int ethtool_op_set_ufo(struct net_device *dev, u32 data)
-{
- if (data)
- dev->features |= NETIF_F_UFO;
- else
- dev->features &= ~NETIF_F_UFO;
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_ufo);
-
-/* the following list of flags are the same as their associated
- * NETIF_F_xxx values in include/linux/netdevice.h
- */
-static const u32 flags_dup_features =
- (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE |
- ETH_FLAG_RXHASH);
-
-u32 ethtool_op_get_flags(struct net_device *dev)
-{
- /* in the future, this function will probably contain additional
- * handling for flags which are not so easily handled
- * by a simple masking operation
- */
-
- return dev->features & flags_dup_features;
-}
-EXPORT_SYMBOL(ethtool_op_get_flags);
-
-/* Check if device can enable (or disable) particular feature coded in "data"
- * argument. Flags "supported" describe features that can be toggled by device.
- * If feature can not be toggled, it state (enabled or disabled) must match
- * hardcoded device features state, otherwise flags are marked as invalid.
- */
-bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported)
-{
- u32 features = dev->features & flags_dup_features;
- /* "data" can contain only flags_dup_features bits,
- * see __ethtool_set_flags */
-
- return (features & ~supported) != (data & ~supported);
-}
-EXPORT_SYMBOL(ethtool_invalid_flags);
-
-int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported)
-{
- if (ethtool_invalid_flags(dev, data, supported))
- return -EINVAL;
-
- dev->features = ((dev->features & ~flags_dup_features) |
- (data & flags_dup_features));
- return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_flags);
-
/* Handlers for each ethtool command */
-#define ETHTOOL_DEV_FEATURE_WORDS 1
-
-static void ethtool_get_features_compat(struct net_device *dev,
- struct ethtool_get_features_block *features)
-{
- if (!dev->ethtool_ops)
- return;
-
- /* getting RX checksum */
- if (dev->ethtool_ops->get_rx_csum)
- if (dev->ethtool_ops->get_rx_csum(dev))
- features[0].active |= NETIF_F_RXCSUM;
-
- /* mark legacy-changeable features */
- if (dev->ethtool_ops->set_sg)
- features[0].available |= NETIF_F_SG;
- if (dev->ethtool_ops->set_tx_csum)
- features[0].available |= NETIF_F_ALL_CSUM;
- if (dev->ethtool_ops->set_tso)
- features[0].available |= NETIF_F_ALL_TSO;
- if (dev->ethtool_ops->set_rx_csum)
- features[0].available |= NETIF_F_RXCSUM;
- if (dev->ethtool_ops->set_flags)
- features[0].available |= flags_dup_features;
-}
-
-static int ethtool_set_feature_compat(struct net_device *dev,
- int (*legacy_set)(struct net_device *, u32),
- struct ethtool_set_features_block *features, u32 mask)
-{
- u32 do_set;
-
- if (!legacy_set)
- return 0;
-
- if (!(features[0].valid & mask))
- return 0;
-
- features[0].valid &= ~mask;
-
- do_set = !!(features[0].requested & mask);
-
- if (legacy_set(dev, do_set) < 0)
- netdev_info(dev,
- "Legacy feature change (%s) failed for 0x%08x\n",
- do_set ? "set" : "clear", mask);
-
- return 1;
-}
-
-static int ethtool_set_flags_compat(struct net_device *dev,
- int (*legacy_set)(struct net_device *, u32),
- struct ethtool_set_features_block *features, u32 mask)
-{
- u32 value;
-
- if (!legacy_set)
- return 0;
-
- if (!(features[0].valid & mask))
- return 0;
-
- value = dev->features & ~features[0].valid;
- value |= features[0].requested;
-
- features[0].valid &= ~mask;
-
- if (legacy_set(dev, value & mask) < 0)
- netdev_info(dev, "Legacy flags change failed\n");
-
- return 1;
-}
-
-static int ethtool_set_features_compat(struct net_device *dev,
- struct ethtool_set_features_block *features)
-{
- int compat;
-
- if (!dev->ethtool_ops)
- return 0;
-
- compat = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg,
- features, NETIF_F_SG);
- compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum,
- features, NETIF_F_ALL_CSUM);
- compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso,
- features, NETIF_F_ALL_TSO);
- compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum,
- features, NETIF_F_RXCSUM);
- compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags,
- features, flags_dup_features);
-
- return compat;
-}
+#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32)
+
+static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
+ [NETIF_F_SG_BIT] = "tx-scatter-gather",
+ [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4",
+ [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic",
+ [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6",
+ [NETIF_F_HIGHDMA_BIT] = "highdma",
+ [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist",
+ [NETIF_F_HW_VLAN_TX_BIT] = "tx-vlan-hw-insert",
+
+ [NETIF_F_HW_VLAN_RX_BIT] = "rx-vlan-hw-parse",
+ [NETIF_F_HW_VLAN_FILTER_BIT] = "rx-vlan-filter",
+ [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged",
+ [NETIF_F_GSO_BIT] = "tx-generic-segmentation",
+ [NETIF_F_LLTX_BIT] = "tx-lockless",
+ [NETIF_F_NETNS_LOCAL_BIT] = "netns-local",
+ [NETIF_F_GRO_BIT] = "rx-gro",
+ [NETIF_F_LRO_BIT] = "rx-lro",
+
+ [NETIF_F_TSO_BIT] = "tx-tcp-segmentation",
+ [NETIF_F_UFO_BIT] = "tx-udp-fragmentation",
+ [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust",
+ [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation",
+ [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation",
+ [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
+
+ [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
+ [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
+ [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu",
+ [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter",
+ [NETIF_F_RXHASH_BIT] = "rx-hashing",
+ [NETIF_F_RXCSUM_BIT] = "rx-checksum",
+ [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy",
+ [NETIF_F_LOOPBACK_BIT] = "loopback",
+};
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
{
.cmd = ETHTOOL_GFEATURES,
.size = ETHTOOL_DEV_FEATURE_WORDS,
};
- struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = {
- {
- .available = dev->hw_features,
- .requested = dev->wanted_features,
- .active = dev->features,
- .never_changed = NETIF_F_NEVER_CHANGE,
- },
- };
+ struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
u32 __user *sizeaddr;
u32 copy_size;
+ int i;
- ethtool_get_features_compat(dev, features);
+ /* in case feature bits run out again */
+ BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t));
+
+ for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
+ features[i].available = (u32)(dev->hw_features >> (32 * i));
+ features[i].requested = (u32)(dev->wanted_features >> (32 * i));
+ features[i].active = (u32)(dev->features >> (32 * i));
+ features[i].never_changed =
+ (u32)(NETIF_F_NEVER_CHANGE >> (32 * i));
+ }
sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
if (get_user(copy_size, sizeaddr))
{
struct ethtool_sfeatures cmd;
struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
- int ret = 0;
+ netdev_features_t wanted = 0, valid = 0;
+ int i, ret = 0;
if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
return -EFAULT;
if (copy_from_user(features, useraddr, sizeof(features)))
return -EFAULT;
- if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
- return -EINVAL;
+ for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
+ valid |= (netdev_features_t)features[i].valid << (32 * i);
+ wanted |= (netdev_features_t)features[i].requested << (32 * i);
+ }
- if (ethtool_set_features_compat(dev, features))
- ret |= ETHTOOL_F_COMPAT;
+ if (valid & ~NETIF_F_ETHTOOL_BITS)
+ return -EINVAL;
- if (features[0].valid & ~dev->hw_features) {
- features[0].valid &= dev->hw_features;
+ if (valid & ~dev->hw_features) {
+ valid &= dev->hw_features;
ret |= ETHTOOL_F_UNSUPPORTED;
}
- dev->wanted_features &= ~features[0].valid;
- dev->wanted_features |= features[0].valid & features[0].requested;
+ dev->wanted_features &= ~valid;
+ dev->wanted_features |= wanted & valid;
__netdev_update_features(dev);
- if ((dev->wanted_features ^ dev->features) & features[0].valid)
+ if ((dev->wanted_features ^ dev->features) & valid)
ret |= ETHTOOL_F_WISH;
return ret;
}
-static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = {
- /* NETIF_F_SG */ "tx-scatter-gather",
- /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4",
- /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded",
- /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic",
- /* NETIF_F_IPV6_CSUM */ "tx-checksum-ipv6",
- /* NETIF_F_HIGHDMA */ "highdma",
- /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist",
- /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert",
-
- /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse",
- /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter",
- /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged",
- /* NETIF_F_GSO */ "tx-generic-segmentation",
- /* NETIF_F_LLTX */ "tx-lockless",
- /* NETIF_F_NETNS_LOCAL */ "netns-local",
- /* NETIF_F_GRO */ "rx-gro",
- /* NETIF_F_LRO */ "rx-lro",
-
- /* NETIF_F_TSO */ "tx-tcp-segmentation",
- /* NETIF_F_UFO */ "tx-udp-fragmentation",
- /* NETIF_F_GSO_ROBUST */ "tx-gso-robust",
- /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation",
- /* NETIF_F_TSO6 */ "tx-tcp6-segmentation",
- /* NETIF_F_FSO */ "tx-fcoe-segmentation",
- "",
- "",
-
- /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc",
- /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp",
- /* NETIF_F_FCOE_MTU */ "fcoe-mtu",
- /* NETIF_F_NTUPLE */ "rx-ntuple-filter",
- /* NETIF_F_RXHASH */ "rx-hashing",
- /* NETIF_F_RXCSUM */ "rx-checksum",
- /* NETIF_F_NOCACHE_COPY */ "tx-nocache-copy",
- /* NETIF_F_LOOPBACK */ "loopback",
-};
-
static int __ethtool_get_sset_count(struct net_device *dev, int sset)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
ops->get_strings(dev, stringset, data);
}
-static u32 ethtool_get_feature_mask(u32 eth_cmd)
+static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd)
{
/* feature masks of legacy discrete ethtool ops */
}
}
-static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
-{
- const struct ethtool_ops *ops = dev->ethtool_ops;
-
- if (!ops)
- return NULL;
-
- switch (ethcmd) {
- case ETHTOOL_GTXCSUM:
- return ops->get_tx_csum;
- case ETHTOOL_GRXCSUM:
- return ops->get_rx_csum;
- case ETHTOOL_SSG:
- return ops->get_sg;
- case ETHTOOL_STSO:
- return ops->get_tso;
- case ETHTOOL_SUFO:
- return ops->get_ufo;
- default:
- return NULL;
- }
-}
-
-static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev)
-{
- return !!(dev->features & NETIF_F_ALL_CSUM);
-}
-
static int ethtool_get_one_feature(struct net_device *dev,
char __user *useraddr, u32 ethcmd)
{
- u32 mask = ethtool_get_feature_mask(ethcmd);
+ netdev_features_t mask = ethtool_get_feature_mask(ethcmd);
struct ethtool_value edata = {
.cmd = ethcmd,
.data = !!(dev->features & mask),
};
- /* compatibility with discrete get_ ops */
- if (!(dev->hw_features & mask)) {
- u32 (*actor)(struct net_device *);
-
- actor = __ethtool_get_one_feature_actor(dev, ethcmd);
-
- /* bug compatibility with old get_rx_csum */
- if (ethcmd == ETHTOOL_GRXCSUM && !actor)
- actor = __ethtool_get_rx_csum_oldbug;
-
- if (actor)
- edata.data = actor(dev);
- }
-
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
return 0;
}
-static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
-static int __ethtool_set_rx_csum(struct net_device *dev, u32 data);
-static int __ethtool_set_sg(struct net_device *dev, u32 data);
-static int __ethtool_set_tso(struct net_device *dev, u32 data);
-static int __ethtool_set_ufo(struct net_device *dev, u32 data);
-
static int ethtool_set_one_feature(struct net_device *dev,
void __user *useraddr, u32 ethcmd)
{
struct ethtool_value edata;
- u32 mask;
+ netdev_features_t mask;
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
mask = ethtool_get_feature_mask(ethcmd);
mask &= dev->hw_features;
- if (mask) {
- if (edata.data)
- dev->wanted_features |= mask;
- else
- dev->wanted_features &= ~mask;
+ if (!mask)
+ return -EOPNOTSUPP;
- __netdev_update_features(dev);
- return 0;
- }
+ if (edata.data)
+ dev->wanted_features |= mask;
+ else
+ dev->wanted_features &= ~mask;
- /* Driver is not converted to ndo_fix_features or does not
- * support changing this offload. In the latter case it won't
- * have corresponding ethtool_ops field set.
- *
- * Following part is to be removed after all drivers advertise
- * their changeable features in netdev->hw_features and stop
- * using discrete offload setting ops.
- */
+ __netdev_update_features(dev);
- switch (ethcmd) {
- case ETHTOOL_STXCSUM:
- return __ethtool_set_tx_csum(dev, edata.data);
- case ETHTOOL_SRXCSUM:
- return __ethtool_set_rx_csum(dev, edata.data);
- case ETHTOOL_SSG:
- return __ethtool_set_sg(dev, edata.data);
- case ETHTOOL_STSO:
- return __ethtool_set_tso(dev, edata.data);
- case ETHTOOL_SUFO:
- return __ethtool_set_ufo(dev, edata.data);
- default:
- return -EOPNOTSUPP;
- }
+ return 0;
+}
+
+#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \
+ ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH)
+#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_RX | \
+ NETIF_F_HW_VLAN_TX | NETIF_F_NTUPLE | NETIF_F_RXHASH)
+
+static u32 __ethtool_get_flags(struct net_device *dev)
+{
+ u32 flags = 0;
+
+ if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO;
+ if (dev->features & NETIF_F_HW_VLAN_RX) flags |= ETH_FLAG_RXVLAN;
+ if (dev->features & NETIF_F_HW_VLAN_TX) flags |= ETH_FLAG_TXVLAN;
+ if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE;
+ if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH;
+
+ return flags;
}
-int __ethtool_set_flags(struct net_device *dev, u32 data)
+static int __ethtool_set_flags(struct net_device *dev, u32 data)
{
- u32 changed;
+ netdev_features_t features = 0, changed;
- if (data & ~flags_dup_features)
+ if (data & ~ETH_ALL_FLAGS)
return -EINVAL;
- /* legacy set_flags() op */
- if (dev->ethtool_ops->set_flags) {
- if (unlikely(dev->hw_features & flags_dup_features))
- netdev_warn(dev,
- "driver BUG: mixed hw_features and set_flags()\n");
- return dev->ethtool_ops->set_flags(dev, data);
- }
+ if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO;
+ if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_RX;
+ if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_TX;
+ if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE;
+ if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH;
/* allow changing only bits set in hw_features */
- changed = (data ^ dev->features) & flags_dup_features;
+ changed = (features ^ dev->features) & ETH_ALL_FEATURES;
if (changed & ~dev->hw_features)
return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP;
dev->wanted_features =
- (dev->wanted_features & ~changed) | (data & dev->hw_features);
+ (dev->wanted_features & ~changed) | (features & changed);
__netdev_update_features(dev);
{
struct ethtool_rxnfc info;
size_t info_size = sizeof(info);
+ int rc;
if (!dev->ethtool_ops->set_rxnfc)
return -EOPNOTSUPP;
if (copy_from_user(&info, useraddr, info_size))
return -EFAULT;
- return dev->ethtool_ops->set_rxnfc(dev, &info);
+ rc = dev->ethtool_ops->set_rxnfc(dev, &info);
+ if (rc)
+ return rc;
+
+ if (cmd == ETHTOOL_SRXCLSRLINS &&
+ copy_to_user(useraddr, &info, info_size))
+ return -EFAULT;
+
+ return 0;
}
static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
void __user *useraddr)
{
- struct ethtool_rxfh_indir *indir;
- u32 table_size;
- size_t full_size;
+ u32 user_size, dev_size;
+ u32 *indir;
int ret;
- if (!dev->ethtool_ops->get_rxfh_indir)
+ if (!dev->ethtool_ops->get_rxfh_indir_size ||
+ !dev->ethtool_ops->get_rxfh_indir)
+ return -EOPNOTSUPP;
+ dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+ if (dev_size == 0)
return -EOPNOTSUPP;
- if (copy_from_user(&table_size,
+ if (copy_from_user(&user_size,
useraddr + offsetof(struct ethtool_rxfh_indir, size),
- sizeof(table_size)))
+ sizeof(user_size)))
return -EFAULT;
- if (table_size >
- (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index))
- return -ENOMEM;
- full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size;
- indir = kzalloc(full_size, GFP_USER);
+ if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size),
+ &dev_size, sizeof(dev_size)))
+ return -EFAULT;
+
+ /* If the user buffer size is 0, this is just a query for the
+ * device table size. Otherwise, if it's smaller than the
+ * device table size it's an error.
+ */
+ if (user_size < dev_size)
+ return user_size == 0 ? 0 : -EINVAL;
+
+ indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
if (!indir)
return -ENOMEM;
- indir->cmd = ETHTOOL_GRXFHINDIR;
- indir->size = table_size;
ret = dev->ethtool_ops->get_rxfh_indir(dev, indir);
if (ret)
goto out;
- if (copy_to_user(useraddr, indir, full_size))
+ if (copy_to_user(useraddr +
+ offsetof(struct ethtool_rxfh_indir, ring_index[0]),
+ indir, dev_size * sizeof(indir[0])))
ret = -EFAULT;
out:
static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
void __user *useraddr)
{
- struct ethtool_rxfh_indir *indir;
- u32 table_size;
- size_t full_size;
+ struct ethtool_rxnfc rx_rings;
+ u32 user_size, dev_size, i;
+ u32 *indir;
int ret;
- if (!dev->ethtool_ops->set_rxfh_indir)
+ if (!dev->ethtool_ops->get_rxfh_indir_size ||
+ !dev->ethtool_ops->set_rxfh_indir ||
+ !dev->ethtool_ops->get_rxnfc)
+ return -EOPNOTSUPP;
+ dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+ if (dev_size == 0)
return -EOPNOTSUPP;
- if (copy_from_user(&table_size,
+ if (copy_from_user(&user_size,
useraddr + offsetof(struct ethtool_rxfh_indir, size),
- sizeof(table_size)))
+ sizeof(user_size)))
return -EFAULT;
- if (table_size >
- (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index))
- return -ENOMEM;
- full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size;
- indir = kmalloc(full_size, GFP_USER);
+ if (user_size != 0 && user_size != dev_size)
+ return -EINVAL;
+
+ indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
if (!indir)
return -ENOMEM;
- if (copy_from_user(indir, useraddr, full_size)) {
- ret = -EFAULT;
+ rx_rings.cmd = ETHTOOL_GRXRINGS;
+ ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL);
+ if (ret)
goto out;
+
+ if (user_size == 0) {
+ for (i = 0; i < dev_size; i++)
+ indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+ } else {
+ if (copy_from_user(indir,
+ useraddr +
+ offsetof(struct ethtool_rxfh_indir,
+ ring_index[0]),
+ dev_size * sizeof(indir[0]))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ /* Validate ring indices */
+ for (i = 0; i < dev_size; i++) {
+ if (indir[i] >= rx_rings.data) {
+ ret = -EINVAL;
+ goto out;
+ }
+ }
}
ret = dev->ethtool_ops->set_rxfh_indir(dev, indir);
return ret;
}
-/*
- * ethtool does not (or did not) set masks for flow parameters that are
- * not specified, so if both value and mask are 0 then this must be
- * treated as equivalent to a mask with all bits set. Implement that
- * here rather than in drivers.
- */
-static void rx_ntuple_fix_masks(struct ethtool_rx_ntuple_flow_spec *fs)
-{
- struct ethtool_tcpip4_spec *entry = &fs->h_u.tcp_ip4_spec;
- struct ethtool_tcpip4_spec *mask = &fs->m_u.tcp_ip4_spec;
-
- if (fs->flow_type != TCP_V4_FLOW &&
- fs->flow_type != UDP_V4_FLOW &&
- fs->flow_type != SCTP_V4_FLOW)
- return;
-
- if (!(entry->ip4src | mask->ip4src))
- mask->ip4src = htonl(0xffffffff);
- if (!(entry->ip4dst | mask->ip4dst))
- mask->ip4dst = htonl(0xffffffff);
- if (!(entry->psrc | mask->psrc))
- mask->psrc = htons(0xffff);
- if (!(entry->pdst | mask->pdst))
- mask->pdst = htons(0xffff);
- if (!(entry->tos | mask->tos))
- mask->tos = 0xff;
- if (!(fs->vlan_tag | fs->vlan_tag_mask))
- fs->vlan_tag_mask = 0xffff;
- if (!(fs->data | fs->data_mask))
- fs->data_mask = 0xffffffffffffffffULL;
-}
-
-static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev,
- void __user *useraddr)
-{
- struct ethtool_rx_ntuple cmd;
- const struct ethtool_ops *ops = dev->ethtool_ops;
-
- if (!ops->set_rx_ntuple)
- return -EOPNOTSUPP;
-
- if (!(dev->features & NETIF_F_NTUPLE))
- return -EINVAL;
-
- if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
- return -EFAULT;
-
- rx_ntuple_fix_masks(&cmd.fs);
-
- return ops->set_rx_ntuple(dev, &cmd);
-}
-
static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
{
struct ethtool_regs regs;
return dev->ethtool_ops->set_pauseparam(dev, &pauseparam);
}
-static int __ethtool_set_sg(struct net_device *dev, u32 data)
-{
- int err;
-
- if (!dev->ethtool_ops->set_sg)
- return -EOPNOTSUPP;
-
- if (data && !(dev->features & NETIF_F_ALL_CSUM))
- return -EINVAL;
-
- if (!data && dev->ethtool_ops->set_tso) {
- err = dev->ethtool_ops->set_tso(dev, 0);
- if (err)
- return err;
- }
-
- if (!data && dev->ethtool_ops->set_ufo) {
- err = dev->ethtool_ops->set_ufo(dev, 0);
- if (err)
- return err;
- }
- return dev->ethtool_ops->set_sg(dev, data);
-}
-
-static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
-{
- int err;
-
- if (!dev->ethtool_ops->set_tx_csum)
- return -EOPNOTSUPP;
-
- if (!data && dev->ethtool_ops->set_sg) {
- err = __ethtool_set_sg(dev, 0);
- if (err)
- return err;
- }
-
- return dev->ethtool_ops->set_tx_csum(dev, data);
-}
-
-static int __ethtool_set_rx_csum(struct net_device *dev, u32 data)
-{
- if (!dev->ethtool_ops->set_rx_csum)
- return -EOPNOTSUPP;
-
- if (!data)
- dev->features &= ~NETIF_F_GRO;
-
- return dev->ethtool_ops->set_rx_csum(dev, data);
-}
-
-static int __ethtool_set_tso(struct net_device *dev, u32 data)
-{
- if (!dev->ethtool_ops->set_tso)
- return -EOPNOTSUPP;
-
- if (data && !(dev->features & NETIF_F_SG))
- return -EINVAL;
-
- return dev->ethtool_ops->set_tso(dev, data);
-}
-
-static int __ethtool_set_ufo(struct net_device *dev, u32 data)
-{
- if (!dev->ethtool_ops->set_ufo)
- return -EOPNOTSUPP;
- if (data && !(dev->features & NETIF_F_SG))
- return -EINVAL;
- if (data && !((dev->features & NETIF_F_GEN_CSUM) ||
- (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
- == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)))
- return -EINVAL;
- return dev->ethtool_ops->set_ufo(dev, data);
-}
-
static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
{
struct ethtool_test test;
break;
case ETHTOOL_GFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_flags ?
- dev->ethtool_ops->get_flags :
- ethtool_op_get_flags));
+ __ethtool_get_flags);
break;
case ETHTOOL_SFLAGS:
rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags);
case ETHTOOL_RESET:
rc = ethtool_reset(dev, useraddr);
break;
- case ETHTOOL_SRXNTUPLE:
- rc = ethtool_set_rx_ntuple(dev, useraddr);
- break;
case ETHTOOL_GSSET_INFO:
rc = ethtool_get_sset_info(dev, useraddr);
break;
put_online_cpus();
}
+static void flow_cache_flush_task(struct work_struct *work)
+{
+ flow_cache_flush();
+}
+
+static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+
+void flow_cache_flush_deferred(void)
+{
+ schedule_work(&flow_cache_flush_work);
+}
+
static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
{
struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
--- /dev/null
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <net/flow_keys.h>
+
+/* copy saddr & daddr, possibly using 64bit load/store
+ * Equivalent to : flow->src = iph->saddr;
+ * flow->dst = iph->daddr;
+ */
+static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+{
+ BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
+ offsetof(typeof(*flow), src) + sizeof(flow->src));
+ memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+}
+
+bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+{
+ int poff, nhoff = skb_network_offset(skb);
+ u8 ip_proto;
+ __be16 proto = skb->protocol;
+
+ memset(flow, 0, sizeof(*flow));
+
+again:
+ switch (proto) {
+ case __constant_htons(ETH_P_IP): {
+ const struct iphdr *iph;
+ struct iphdr _iph;
+ip:
+ iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ if (!iph)
+ return false;
+
+ if (ip_is_fragment(iph))
+ ip_proto = 0;
+ else
+ ip_proto = iph->protocol;
+ iph_to_flow_copy_addrs(flow, iph);
+ nhoff += iph->ihl * 4;
+ break;
+ }
+ case __constant_htons(ETH_P_IPV6): {
+ const struct ipv6hdr *iph;
+ struct ipv6hdr _iph;
+ipv6:
+ iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ if (!iph)
+ return false;
+
+ ip_proto = iph->nexthdr;
+ flow->src = iph->saddr.s6_addr32[3];
+ flow->dst = iph->daddr.s6_addr32[3];
+ nhoff += sizeof(struct ipv6hdr);
+ break;
+ }
+ case __constant_htons(ETH_P_8021Q): {
+ const struct vlan_hdr *vlan;
+ struct vlan_hdr _vlan;
+
+ vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan);
+ if (!vlan)
+ return false;
+
+ proto = vlan->h_vlan_encapsulated_proto;
+ nhoff += sizeof(*vlan);
+ goto again;
+ }
+ case __constant_htons(ETH_P_PPP_SES): {
+ struct {
+ struct pppoe_hdr hdr;
+ __be16 proto;
+ } *hdr, _hdr;
+ hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ if (!hdr)
+ return false;
+ proto = hdr->proto;
+ nhoff += PPPOE_SES_HLEN;
+ switch (proto) {
+ case __constant_htons(PPP_IP):
+ goto ip;
+ case __constant_htons(PPP_IPV6):
+ goto ipv6;
+ default:
+ return false;
+ }
+ }
+ default:
+ return false;
+ }
+
+ switch (ip_proto) {
+ case IPPROTO_GRE: {
+ struct gre_hdr {
+ __be16 flags;
+ __be16 proto;
+ } *hdr, _hdr;
+
+ hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ if (!hdr)
+ return false;
+ /*
+ * Only look inside GRE if version zero and no
+ * routing
+ */
+ if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
+ proto = hdr->proto;
+ nhoff += 4;
+ if (hdr->flags & GRE_CSUM)
+ nhoff += 4;
+ if (hdr->flags & GRE_KEY)
+ nhoff += 4;
+ if (hdr->flags & GRE_SEQ)
+ nhoff += 4;
+ goto again;
+ }
+ break;
+ }
+ case IPPROTO_IPIP:
+ goto again;
+ default:
+ break;
+ }
+
+ flow->ip_proto = ip_proto;
+ poff = proto_ports_offset(ip_proto);
+ if (poff >= 0) {
+ __be32 *ports, _ports;
+
+ nhoff += poff;
+ ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
+ if (ports)
+ flow->ports = *ports;
+ }
+
+ return true;
+}
+EXPORT_SYMBOL(skb_flow_dissect);
it to safe state.
*/
skb_queue_purge(&n->arp_queue);
+ n->arp_queue_len_bytes = 0;
n->output = neigh_blackhole;
if (n->nud_state & NUD_VALID)
n->nud_state = NUD_NOARP;
}
EXPORT_SYMBOL(neigh_ifdown);
-static struct neighbour *neigh_alloc(struct neigh_table *tbl)
+static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev)
{
struct neighbour *n = NULL;
unsigned long now = jiffies;
goto out_entries;
}
- n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC);
+ if (tbl->entry_size)
+ n = kzalloc(tbl->entry_size, GFP_ATOMIC);
+ else {
+ int sz = sizeof(*n) + tbl->key_len;
+
+ sz = ALIGN(sz, NEIGH_PRIV_ALIGN);
+ sz += dev->neigh_priv_len;
+ n = kzalloc(sz, GFP_ATOMIC);
+ }
if (!n)
goto out_entries;
goto out;
}
+static void neigh_get_hash_rnd(u32 *x)
+{
+ get_random_bytes(x, sizeof(*x));
+ *x |= 1;
+}
+
static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
{
size_t size = (1 << shift) * sizeof(struct neighbour *);
struct neigh_hash_table *ret;
struct neighbour __rcu **buckets;
+ int i;
ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
if (!ret)
}
ret->hash_buckets = buckets;
ret->hash_shift = shift;
- get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd));
- ret->hash_rnd |= 1;
+ for (i = 0; i < NEIGH_NUM_HASH_RND; i++)
+ neigh_get_hash_rnd(&ret->hash_rnd[i]);
return ret;
}
u32 hash_val;
int key_len = tbl->key_len;
int error;
- struct neighbour *n1, *rc, *n = neigh_alloc(tbl);
+ struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
struct neigh_hash_table *nht;
if (!n) {
goto out_neigh_release;
}
+ if (dev->netdev_ops->ndo_neigh_construct) {
+ error = dev->netdev_ops->ndo_neigh_construct(n);
+ if (error < 0) {
+ rc = ERR_PTR(error);
+ goto out_neigh_release;
+ }
+ }
+
/* Device specific setup. */
if (n->parms->neigh_setup &&
(error = n->parms->neigh_setup(n)) < 0) {
neigh_parms_destroy(parms);
}
-static void neigh_destroy_rcu(struct rcu_head *head)
-{
- struct neighbour *neigh = container_of(head, struct neighbour, rcu);
-
- kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
-}
/*
* neighbour must already be out of the table;
*
*/
void neigh_destroy(struct neighbour *neigh)
{
+ struct net_device *dev = neigh->dev;
+
NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);
if (!neigh->dead) {
printk(KERN_WARNING "Impossible event.\n");
skb_queue_purge(&neigh->arp_queue);
+ neigh->arp_queue_len_bytes = 0;
- dev_put(neigh->dev);
+ if (dev->netdev_ops->ndo_neigh_destroy)
+ dev->netdev_ops->ndo_neigh_destroy(neigh);
+
+ dev_put(dev);
neigh_parms_put(neigh->parms);
NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);
atomic_dec(&neigh->tbl->entries);
- call_rcu(&neigh->rcu, neigh_destroy_rcu);
+ kfree_rcu(neigh, rcu);
}
EXPORT_SYMBOL(neigh_destroy);
write_lock(&neigh->lock);
}
skb_queue_purge(&neigh->arp_queue);
+ neigh->arp_queue_len_bytes = 0;
}
static void neigh_probe(struct neighbour *neigh)
if (neigh->nud_state == NUD_INCOMPLETE) {
if (skb) {
- if (skb_queue_len(&neigh->arp_queue) >=
- neigh->parms->queue_len) {
+ while (neigh->arp_queue_len_bytes + skb->truesize >
+ neigh->parms->queue_len_bytes) {
struct sk_buff *buff;
+
buff = __skb_dequeue(&neigh->arp_queue);
+ if (!buff)
+ break;
+ neigh->arp_queue_len_bytes -= buff->truesize;
kfree_skb(buff);
NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
}
skb_dst_force(skb);
__skb_queue_tail(&neigh->arp_queue, skb);
+ neigh->arp_queue_len_bytes += skb->truesize;
}
rc = 1;
}
rcu_read_lock();
/* On shaper/eql skb->dst->neighbour != neigh :( */
- if (dst && (n2 = dst_get_neighbour(dst)) != NULL)
+ if (dst && (n2 = dst_get_neighbour_noref(dst)) != NULL)
n1 = n2;
n1->output(n1, skb);
rcu_read_unlock();
write_lock_bh(&neigh->lock);
}
skb_queue_purge(&neigh->arp_queue);
+ neigh->arp_queue_len_bytes = 0;
}
out:
if (update_isrouter) {
tbl->parms.reachable_time =
neigh_rand_reach_time(tbl->parms.base_reachable_time);
- if (!tbl->kmem_cachep)
- tbl->kmem_cachep =
- kmem_cache_create(tbl->id, tbl->entry_size, 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC,
- NULL);
tbl->stats = alloc_percpu(struct neigh_statistics);
if (!tbl->stats)
panic("cannot create neighbour cache statistics");
free_percpu(tbl->stats);
tbl->stats = NULL;
- kmem_cache_destroy(tbl->kmem_cachep);
- tbl->kmem_cachep = NULL;
-
return 0;
}
EXPORT_SYMBOL(neigh_table_clear);
NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);
NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
- NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
+ NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes);
+ /* approximative value for deprecated QUEUE_LEN (in packets) */
+ NLA_PUT_U32(skb, NDTPA_QUEUE_LEN,
+ DIV_ROUND_UP(parms->queue_len_bytes,
+ SKB_TRUESIZE(ETH_FRAME_LEN)));
NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- ndc.ndtc_hash_rnd = nht->hash_rnd;
+ ndc.ndtc_hash_rnd = nht->hash_rnd[0];
ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1);
rcu_read_unlock_bh();
switch (i) {
case NDTPA_QUEUE_LEN:
- p->queue_len = nla_get_u32(tbp[i]);
+ p->queue_len_bytes = nla_get_u32(tbp[i]) *
+ SKB_TRUESIZE(ETH_FRAME_LEN);
+ break;
+ case NDTPA_QUEUE_LENBYTES:
+ p->queue_len_bytes = nla_get_u32(tbp[i]);
break;
case NDTPA_PROXY_QLEN:
p->proxy_qlen = nla_get_u32(tbp[i]);
struct net *net = seq_file_net(seq);
struct neigh_table *tbl = state->tbl;
- pn = pn->next;
+ do {
+ pn = pn->next;
+ } while (pn && !net_eq(pneigh_net(pn), net));
+
while (!pn) {
if (++state->bucket > PNEIGH_HASHMASK)
break;
#ifdef CONFIG_SYSCTL
-#define NEIGH_VARS_MAX 19
+static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int size, ret;
+ ctl_table tmp = *ctl;
+
+ tmp.data = &size;
+ size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN));
+ ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret)
+ *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN);
+ return ret;
+}
+
+enum {
+ NEIGH_VAR_MCAST_PROBE,
+ NEIGH_VAR_UCAST_PROBE,
+ NEIGH_VAR_APP_PROBE,
+ NEIGH_VAR_RETRANS_TIME,
+ NEIGH_VAR_BASE_REACHABLE_TIME,
+ NEIGH_VAR_DELAY_PROBE_TIME,
+ NEIGH_VAR_GC_STALETIME,
+ NEIGH_VAR_QUEUE_LEN,
+ NEIGH_VAR_QUEUE_LEN_BYTES,
+ NEIGH_VAR_PROXY_QLEN,
+ NEIGH_VAR_ANYCAST_DELAY,
+ NEIGH_VAR_PROXY_DELAY,
+ NEIGH_VAR_LOCKTIME,
+ NEIGH_VAR_RETRANS_TIME_MS,
+ NEIGH_VAR_BASE_REACHABLE_TIME_MS,
+ NEIGH_VAR_GC_INTERVAL,
+ NEIGH_VAR_GC_THRESH1,
+ NEIGH_VAR_GC_THRESH2,
+ NEIGH_VAR_GC_THRESH3,
+ NEIGH_VAR_MAX
+};
static struct neigh_sysctl_table {
struct ctl_table_header *sysctl_header;
- struct ctl_table neigh_vars[NEIGH_VARS_MAX];
+ struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1];
char *dev_name;
} neigh_sysctl_template __read_mostly = {
.neigh_vars = {
- {
+ [NEIGH_VAR_MCAST_PROBE] = {
.procname = "mcast_solicit",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_UCAST_PROBE] = {
.procname = "ucast_solicit",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_APP_PROBE] = {
.procname = "app_solicit",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_RETRANS_TIME] = {
.procname = "retrans_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_userhz_jiffies,
},
- {
+ [NEIGH_VAR_BASE_REACHABLE_TIME] = {
.procname = "base_reachable_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {
+ [NEIGH_VAR_DELAY_PROBE_TIME] = {
.procname = "delay_first_probe_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {
+ [NEIGH_VAR_GC_STALETIME] = {
.procname = "gc_stale_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {
+ [NEIGH_VAR_QUEUE_LEN] = {
.procname = "unres_qlen",
.maxlen = sizeof(int),
.mode = 0644,
+ .proc_handler = proc_unres_qlen,
+ },
+ [NEIGH_VAR_QUEUE_LEN_BYTES] = {
+ .procname = "unres_qlen_bytes",
+ .maxlen = sizeof(int),
+ .mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_PROXY_QLEN] = {
.procname = "proxy_qlen",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_ANYCAST_DELAY] = {
.procname = "anycast_delay",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_userhz_jiffies,
},
- {
+ [NEIGH_VAR_PROXY_DELAY] = {
.procname = "proxy_delay",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_userhz_jiffies,
},
- {
+ [NEIGH_VAR_LOCKTIME] = {
.procname = "locktime",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_userhz_jiffies,
},
- {
+ [NEIGH_VAR_RETRANS_TIME_MS] = {
.procname = "retrans_time_ms",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
- {
+ [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = {
.procname = "base_reachable_time_ms",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
- {
+ [NEIGH_VAR_GC_INTERVAL] = {
.procname = "gc_interval",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {
+ [NEIGH_VAR_GC_THRESH1] = {
.procname = "gc_thresh1",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_GC_THRESH2] = {
.procname = "gc_thresh2",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
+ [NEIGH_VAR_GC_THRESH3] = {
.procname = "gc_thresh3",
.maxlen = sizeof(int),
.mode = 0644,
if (!t)
goto err;
- t->neigh_vars[0].data = &p->mcast_probes;
- t->neigh_vars[1].data = &p->ucast_probes;
- t->neigh_vars[2].data = &p->app_probes;
- t->neigh_vars[3].data = &p->retrans_time;
- t->neigh_vars[4].data = &p->base_reachable_time;
- t->neigh_vars[5].data = &p->delay_probe_time;
- t->neigh_vars[6].data = &p->gc_staletime;
- t->neigh_vars[7].data = &p->queue_len;
- t->neigh_vars[8].data = &p->proxy_qlen;
- t->neigh_vars[9].data = &p->anycast_delay;
- t->neigh_vars[10].data = &p->proxy_delay;
- t->neigh_vars[11].data = &p->locktime;
- t->neigh_vars[12].data = &p->retrans_time;
- t->neigh_vars[13].data = &p->base_reachable_time;
+ t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes;
+ t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes;
+ t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time;
+ t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time;
+ t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime;
+ t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes;
+ t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes;
+ t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen;
+ t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay;
+ t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay;
+ t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time;
if (dev) {
dev_name_source = dev->name;
/* Terminate the table early */
- memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14]));
+ memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
+ sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
} else {
dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname;
- t->neigh_vars[14].data = (int *)(p + 1);
- t->neigh_vars[15].data = (int *)(p + 1) + 1;
- t->neigh_vars[16].data = (int *)(p + 1) + 2;
- t->neigh_vars[17].data = (int *)(p + 1) + 3;
+ t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
+ t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
+ t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
+ t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
}
if (handler) {
/* RetransTime */
- t->neigh_vars[3].proc_handler = handler;
- t->neigh_vars[3].extra1 = dev;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev;
/* ReachableTime */
- t->neigh_vars[4].proc_handler = handler;
- t->neigh_vars[4].extra1 = dev;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev;
/* RetransTime (in milliseconds)*/
- t->neigh_vars[12].proc_handler = handler;
- t->neigh_vars[12].extra1 = dev;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
+ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev;
/* ReachableTime (in milliseconds) */
- t->neigh_vars[13].proc_handler = handler;
- t->neigh_vars[13].extra1 = dev;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
+ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev;
}
t->dev_name = kstrdup(dev_name_source, GFP_KERNEL);
#include <linux/wireless.h>
#include <linux/vmalloc.h>
#include <linux/export.h>
+#include <linux/jiffies.h>
#include <net/wext.h>
#include "net-sysfs.h"
rcu_assign_pointer(queue->rps_map, map);
spin_unlock(&rps_map_lock);
- if (old_map)
+ if (map)
+ jump_label_inc(&rps_needed);
+ if (old_map) {
kfree_rcu(old_map, rcu);
-
+ jump_label_dec(&rps_needed);
+ }
free_cpumask_var(mask);
return len;
}
char *buf)
{
struct rps_dev_flow_table *flow_table;
- unsigned int val = 0;
+ unsigned long val = 0;
rcu_read_lock();
flow_table = rcu_dereference(queue->rps_flow_table);
if (flow_table)
- val = flow_table->mask + 1;
+ val = (unsigned long)flow_table->mask + 1;
rcu_read_unlock();
- return sprintf(buf, "%u\n", val);
+ return sprintf(buf, "%lu\n", val);
}
static void rps_dev_flow_table_release_work(struct work_struct *work)
struct rx_queue_attribute *attr,
const char *buf, size_t len)
{
- unsigned int count;
- char *endp;
+ unsigned long mask, count;
struct rps_dev_flow_table *table, *old_table;
static DEFINE_SPINLOCK(rps_dev_flow_lock);
+ int rc;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- count = simple_strtoul(buf, &endp, 0);
- if (endp == buf)
- return -EINVAL;
+ rc = kstrtoul(buf, 0, &count);
+ if (rc < 0)
+ return rc;
if (count) {
- int i;
-
- if (count > 1<<30) {
+ mask = count - 1;
+ /* mask = roundup_pow_of_two(count) - 1;
+ * without overflows...
+ */
+ while ((mask | (mask >> 1)) != mask)
+ mask |= (mask >> 1);
+ /* On 64 bit arches, must check mask fits in table->mask (u32),
+ * and on 32bit arches, must check RPS_DEV_FLOW_TABLE_SIZE(mask + 1)
+ * doesnt overflow.
+ */
+#if BITS_PER_LONG > 32
+ if (mask > (unsigned long)(u32)mask)
+ return -EINVAL;
+#else
+ if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1))
+ / sizeof(struct rps_dev_flow)) {
/* Enforce a limit to prevent overflow */
return -EINVAL;
}
- count = roundup_pow_of_two(count);
- table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
+#endif
+ table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1));
if (!table)
return -ENOMEM;
- table->mask = count - 1;
- for (i = 0; i < count; i++)
- table->flows[i].cpu = RPS_NO_CPU;
+ table->mask = mask;
+ for (count = 0; count <= mask; count++)
+ table->flows[count].cpu = RPS_NO_CPU;
} else
table = NULL;
#endif
}
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SYSFS
/*
* netdev_queue sysfs structures and functions.
*/
.store = netdev_queue_attr_store,
};
+static ssize_t show_trans_timeout(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ char *buf)
+{
+ unsigned long trans_timeout;
+
+ spin_lock_irq(&queue->_xmit_lock);
+ trans_timeout = queue->trans_timeout;
+ spin_unlock_irq(&queue->_xmit_lock);
+
+ return sprintf(buf, "%lu", trans_timeout);
+}
+
+static struct netdev_queue_attribute queue_trans_timeout =
+ __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
+
+#ifdef CONFIG_BQL
+/*
+ * Byte queue limits sysfs structures and functions.
+ */
+static ssize_t bql_show(char *buf, unsigned int value)
+{
+ return sprintf(buf, "%u\n", value);
+}
+
+static ssize_t bql_set(const char *buf, const size_t count,
+ unsigned int *pvalue)
+{
+ unsigned int value;
+ int err;
+
+ if (!strcmp(buf, "max") || !strcmp(buf, "max\n"))
+ value = DQL_MAX_LIMIT;
+ else {
+ err = kstrtouint(buf, 10, &value);
+ if (err < 0)
+ return err;
+ if (value > DQL_MAX_LIMIT)
+ return -EINVAL;
+ }
+
+ *pvalue = value;
+
+ return count;
+}
+
+static ssize_t bql_show_hold_time(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attr,
+ char *buf)
+{
+ struct dql *dql = &queue->dql;
+
+ return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time));
+}
+
+static ssize_t bql_set_hold_time(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ const char *buf, size_t len)
+{
+ struct dql *dql = &queue->dql;
+ unsigned value;
+ int err;
+
+ err = kstrtouint(buf, 10, &value);
+ if (err < 0)
+ return err;
+
+ dql->slack_hold_time = msecs_to_jiffies(value);
+
+ return len;
+}
+
+static struct netdev_queue_attribute bql_hold_time_attribute =
+ __ATTR(hold_time, S_IRUGO | S_IWUSR, bql_show_hold_time,
+ bql_set_hold_time);
+
+static ssize_t bql_show_inflight(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attr,
+ char *buf)
+{
+ struct dql *dql = &queue->dql;
+
+ return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed);
+}
+
+static struct netdev_queue_attribute bql_inflight_attribute =
+ __ATTR(inflight, S_IRUGO | S_IWUSR, bql_show_inflight, NULL);
+
+#define BQL_ATTR(NAME, FIELD) \
+static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \
+ struct netdev_queue_attribute *attr, \
+ char *buf) \
+{ \
+ return bql_show(buf, queue->dql.FIELD); \
+} \
+ \
+static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \
+ struct netdev_queue_attribute *attr, \
+ const char *buf, size_t len) \
+{ \
+ return bql_set(buf, len, &queue->dql.FIELD); \
+} \
+ \
+static struct netdev_queue_attribute bql_ ## NAME ## _attribute = \
+ __ATTR(NAME, S_IRUGO | S_IWUSR, bql_show_ ## NAME, \
+ bql_set_ ## NAME);
+
+BQL_ATTR(limit, limit)
+BQL_ATTR(limit_max, max_limit)
+BQL_ATTR(limit_min, min_limit)
+
+static struct attribute *dql_attrs[] = {
+ &bql_limit_attribute.attr,
+ &bql_limit_max_attribute.attr,
+ &bql_limit_min_attribute.attr,
+ &bql_hold_time_attribute.attr,
+ &bql_inflight_attribute.attr,
+ NULL
+};
+
+static struct attribute_group dql_group = {
+ .name = "byte_queue_limits",
+ .attrs = dql_attrs,
+};
+#endif /* CONFIG_BQL */
+
+#ifdef CONFIG_XPS
static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
+static void xps_queue_release(struct netdev_queue *queue)
+{
+ struct net_device *dev = queue->dev;
+ struct xps_dev_maps *dev_maps;
+ struct xps_map *map;
+ unsigned long index;
+ int i, pos, nonempty = 0;
+
+ index = get_netdev_queue_index(queue);
+
+ mutex_lock(&xps_map_mutex);
+ dev_maps = xmap_dereference(dev->xps_maps);
+
+ if (dev_maps) {
+ for_each_possible_cpu(i) {
+ map = xmap_dereference(dev_maps->cpu_map[i]);
+ if (!map)
+ continue;
+
+ for (pos = 0; pos < map->len; pos++)
+ if (map->queues[pos] == index)
+ break;
+
+ if (pos < map->len) {
+ if (map->len > 1)
+ map->queues[pos] =
+ map->queues[--map->len];
+ else {
+ RCU_INIT_POINTER(dev_maps->cpu_map[i],
+ NULL);
+ kfree_rcu(map, rcu);
+ map = NULL;
+ }
+ }
+ if (map)
+ nonempty = 1;
+ }
+
+ if (!nonempty) {
+ RCU_INIT_POINTER(dev->xps_maps, NULL);
+ kfree_rcu(dev_maps, rcu);
+ }
+ }
+ mutex_unlock(&xps_map_mutex);
+}
+
static ssize_t store_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute,
const char *buf, size_t len)
struct xps_map *map, *new_map;
struct xps_dev_maps *dev_maps, *new_dev_maps;
int nonempty = 0;
- int numa_node = -2;
+ int numa_node_id = -2;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu);
#ifdef CONFIG_NUMA
if (need_set) {
- if (numa_node == -2)
- numa_node = cpu_to_node(cpu);
- else if (numa_node != cpu_to_node(cpu))
- numa_node = -1;
+ if (numa_node_id == -2)
+ numa_node_id = cpu_to_node(cpu);
+ else if (numa_node_id != cpu_to_node(cpu))
+ numa_node_id = -1;
}
#endif
if (need_set && pos >= map_len) {
if (dev_maps)
kfree_rcu(dev_maps, rcu);
- netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node :
+ netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id :
NUMA_NO_NODE);
mutex_unlock(&xps_map_mutex);
static struct netdev_queue_attribute xps_cpus_attribute =
__ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map);
+#endif /* CONFIG_XPS */
static struct attribute *netdev_queue_default_attrs[] = {
+ &queue_trans_timeout.attr,
+#ifdef CONFIG_XPS
&xps_cpus_attribute.attr,
+#endif
NULL
};
static void netdev_queue_release(struct kobject *kobj)
{
struct netdev_queue *queue = to_netdev_queue(kobj);
- struct net_device *dev = queue->dev;
- struct xps_dev_maps *dev_maps;
- struct xps_map *map;
- unsigned long index;
- int i, pos, nonempty = 0;
-
- index = get_netdev_queue_index(queue);
-
- mutex_lock(&xps_map_mutex);
- dev_maps = xmap_dereference(dev->xps_maps);
-
- if (dev_maps) {
- for_each_possible_cpu(i) {
- map = xmap_dereference(dev_maps->cpu_map[i]);
- if (!map)
- continue;
- for (pos = 0; pos < map->len; pos++)
- if (map->queues[pos] == index)
- break;
-
- if (pos < map->len) {
- if (map->len > 1)
- map->queues[pos] =
- map->queues[--map->len];
- else {
- RCU_INIT_POINTER(dev_maps->cpu_map[i],
- NULL);
- kfree_rcu(map, rcu);
- map = NULL;
- }
- }
- if (map)
- nonempty = 1;
- }
-
- if (!nonempty) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
- kfree_rcu(dev_maps, rcu);
- }
- }
-
- mutex_unlock(&xps_map_mutex);
+#ifdef CONFIG_XPS
+ xps_queue_release(queue);
+#endif
memset(kobj, 0, sizeof(*kobj));
dev_put(queue->dev);
kobj->kset = net->queues_kset;
error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
"tx-%u", index);
- if (error) {
- kobject_put(kobj);
- return error;
- }
+ if (error)
+ goto exit;
+
+#ifdef CONFIG_BQL
+ error = sysfs_create_group(kobj, &dql_group);
+ if (error)
+ goto exit;
+#endif
kobject_uevent(kobj, KOBJ_ADD);
dev_hold(queue->dev);
+ return 0;
+exit:
+ kobject_put(kobj);
return error;
}
-#endif /* CONFIG_XPS */
+#endif /* CONFIG_SYSFS */
int
netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
{
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SYSFS
int i;
int error = 0;
}
}
- while (--i >= new_num)
- kobject_put(&net->_tx[i].kobj);
+ while (--i >= new_num) {
+ struct netdev_queue *queue = net->_tx + i;
+
+#ifdef CONFIG_BQL
+ sysfs_remove_group(&queue->kobj, &dql_group);
+#endif
+ kobject_put(&queue->kobj);
+ }
return error;
#else
return 0;
-#endif
+#endif /* CONFIG_SYSFS */
}
static int register_queue_kobjects(struct net_device *net)
{
int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0;
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
net->queues_kset = kset_create_and_add("queues",
NULL, &net->dev.kobj);
if (!net->queues_kset)
net_rx_queue_update_kobjects(net, real_rx, 0);
netdev_queue_update_kobjects(net, real_tx, 0);
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
kset_unregister(net->queues_kset);
#endif
}
local_irq_save(flags);
__netif_tx_lock(txq, smp_processor_id());
- if (netif_tx_queue_frozen_or_stopped(txq) ||
+ if (netif_xmit_frozen_or_stopped(txq) ||
ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
__netif_tx_unlock(txq);
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
if (__netif_tx_trylock(txq)) {
- if (!netif_tx_queue_stopped(txq)) {
+ if (!netif_xmit_stopped(txq)) {
status = ops->ndo_start_xmit(skb, dev);
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
struct sk_buff *send_skb;
struct netpoll *np, *tmp;
unsigned long flags;
+ int hlen, tlen;
int hits = 0;
if (list_empty(&npinfo->rx_np))
if (tip != np->local_ip)
continue;
- send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
- LL_RESERVED_SPACE(np->dev));
+ hlen = LL_RESERVED_SPACE(np->dev);
+ tlen = np->dev->needed_tailroom;
+ send_skb = find_skb(np, size + hlen + tlen, hlen);
if (!send_skb)
continue;
--- /dev/null
+/*
+ * net/core/netprio_cgroup.c Priority Control Group
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/cgroup.h>
+#include <linux/rcupdate.h>
+#include <linux/atomic.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+#include <net/netprio_cgroup.h>
+
+static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
+ struct cgroup *cgrp);
+static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
+static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp);
+
+struct cgroup_subsys net_prio_subsys = {
+ .name = "net_prio",
+ .create = cgrp_create,
+ .destroy = cgrp_destroy,
+ .populate = cgrp_populate,
+#ifdef CONFIG_NETPRIO_CGROUP
+ .subsys_id = net_prio_subsys_id,
+#endif
+ .module = THIS_MODULE
+};
+
+#define PRIOIDX_SZ 128
+
+static unsigned long prioidx_map[PRIOIDX_SZ];
+static DEFINE_SPINLOCK(prioidx_map_lock);
+static atomic_t max_prioidx = ATOMIC_INIT(0);
+
+static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
+{
+ return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id),
+ struct cgroup_netprio_state, css);
+}
+
+static int get_prioidx(u32 *prio)
+{
+ unsigned long flags;
+ u32 prioidx;
+
+ spin_lock_irqsave(&prioidx_map_lock, flags);
+ prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
+ set_bit(prioidx, prioidx_map);
+ spin_unlock_irqrestore(&prioidx_map_lock, flags);
+ if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ)
+ return -ENOSPC;
+
+ atomic_set(&max_prioidx, prioidx);
+ *prio = prioidx;
+ return 0;
+}
+
+static void put_prioidx(u32 idx)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&prioidx_map_lock, flags);
+ clear_bit(idx, prioidx_map);
+ spin_unlock_irqrestore(&prioidx_map_lock, flags);
+}
+
+static void extend_netdev_table(struct net_device *dev, u32 new_len)
+{
+ size_t new_size = sizeof(struct netprio_map) +
+ ((sizeof(u32) * new_len));
+ struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
+ struct netprio_map *old_priomap;
+ int i;
+
+ old_priomap = rtnl_dereference(dev->priomap);
+
+ if (!new_priomap) {
+ printk(KERN_WARNING "Unable to alloc new priomap!\n");
+ return;
+ }
+
+ for (i = 0;
+ old_priomap && (i < old_priomap->priomap_len);
+ i++)
+ new_priomap->priomap[i] = old_priomap->priomap[i];
+
+ new_priomap->priomap_len = new_len;
+
+ rcu_assign_pointer(dev->priomap, new_priomap);
+ if (old_priomap)
+ kfree_rcu(old_priomap, rcu);
+}
+
+static void update_netdev_tables(void)
+{
+ struct net_device *dev;
+ u32 max_len = atomic_read(&max_prioidx);
+ struct netprio_map *map;
+
+ rtnl_lock();
+ for_each_netdev(&init_net, dev) {
+ map = rtnl_dereference(dev->priomap);
+ if ((!map) ||
+ (map->priomap_len < max_len))
+ extend_netdev_table(dev, max_len);
+ }
+ rtnl_unlock();
+}
+
+static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
+ struct cgroup *cgrp)
+{
+ struct cgroup_netprio_state *cs;
+ int ret;
+
+ cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+ if (!cs)
+ return ERR_PTR(-ENOMEM);
+
+ if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
+ kfree(cs);
+ return ERR_PTR(-EINVAL);
+ }
+
+ ret = get_prioidx(&cs->prioidx);
+ if (ret != 0) {
+ printk(KERN_WARNING "No space in priority index array\n");
+ kfree(cs);
+ return ERR_PTR(ret);
+ }
+
+ return &cs->css;
+}
+
+static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ struct cgroup_netprio_state *cs;
+ struct net_device *dev;
+ struct netprio_map *map;
+
+ cs = cgrp_netprio_state(cgrp);
+ rtnl_lock();
+ for_each_netdev(&init_net, dev) {
+ map = rtnl_dereference(dev->priomap);
+ if (map)
+ map->priomap[cs->prioidx] = 0;
+ }
+ rtnl_unlock();
+ put_prioidx(cs->prioidx);
+ kfree(cs);
+}
+
+static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
+{
+ return (u64)cgrp_netprio_state(cgrp)->prioidx;
+}
+
+static int read_priomap(struct cgroup *cont, struct cftype *cft,
+ struct cgroup_map_cb *cb)
+{
+ struct net_device *dev;
+ u32 prioidx = cgrp_netprio_state(cont)->prioidx;
+ u32 priority;
+ struct netprio_map *map;
+
+ rcu_read_lock();
+ for_each_netdev_rcu(&init_net, dev) {
+ map = rcu_dereference(dev->priomap);
+ priority = map ? map->priomap[prioidx] : 0;
+ cb->fill(cb, dev->name, priority);
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ char *devname = kstrdup(buffer, GFP_KERNEL);
+ int ret = -EINVAL;
+ u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
+ unsigned long priority;
+ char *priostr;
+ struct net_device *dev;
+ struct netprio_map *map;
+
+ if (!devname)
+ return -ENOMEM;
+
+ /*
+ * Minimally sized valid priomap string
+ */
+ if (strlen(devname) < 3)
+ goto out_free_devname;
+
+ priostr = strstr(devname, " ");
+ if (!priostr)
+ goto out_free_devname;
+
+ /*
+ *Separate the devname from the associated priority
+ *and advance the priostr poitner to the priority value
+ */
+ *priostr = '\0';
+ priostr++;
+
+ /*
+ * If the priostr points to NULL, we're at the end of the passed
+ * in string, and its not a valid write
+ */
+ if (*priostr == '\0')
+ goto out_free_devname;
+
+ ret = kstrtoul(priostr, 10, &priority);
+ if (ret < 0)
+ goto out_free_devname;
+
+ ret = -ENODEV;
+
+ dev = dev_get_by_name(&init_net, devname);
+ if (!dev)
+ goto out_free_devname;
+
+ update_netdev_tables();
+ ret = 0;
+ rcu_read_lock();
+ map = rcu_dereference(dev->priomap);
+ if (map)
+ map->priomap[prioidx] = priority;
+ rcu_read_unlock();
+ dev_put(dev);
+
+out_free_devname:
+ kfree(devname);
+ return ret;
+}
+
+static struct cftype ss_files[] = {
+ {
+ .name = "prioidx",
+ .read_u64 = read_prioidx,
+ },
+ {
+ .name = "ifpriomap",
+ .read_map = read_priomap,
+ .write_string = write_priomap,
+ },
+};
+
+static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
+}
+
+static int netprio_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = ptr;
+ struct netprio_map *old;
+ u32 max_len = atomic_read(&max_prioidx);
+
+ /*
+ * Note this is called with rtnl_lock held so we have update side
+ * protection on our rcu assignments
+ */
+
+ switch (event) {
+
+ case NETDEV_REGISTER:
+ if (max_len)
+ extend_netdev_table(dev, max_len);
+ break;
+ case NETDEV_UNREGISTER:
+ old = rtnl_dereference(dev->priomap);
+ RCU_INIT_POINTER(dev->priomap, NULL);
+ if (old)
+ kfree_rcu(old, rcu);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block netprio_device_notifier = {
+ .notifier_call = netprio_device_event
+};
+
+static int __init init_cgroup_netprio(void)
+{
+ int ret;
+
+ ret = cgroup_load_subsys(&net_prio_subsys);
+ if (ret)
+ goto out;
+#ifndef CONFIG_NETPRIO_CGROUP
+ smp_wmb();
+ net_prio_subsys_id = net_prio_subsys.subsys_id;
+#endif
+
+ register_netdevice_notifier(&netprio_device_notifier);
+
+out:
+ return ret;
+}
+
+static void __exit exit_cgroup_netprio(void)
+{
+ struct netprio_map *old;
+ struct net_device *dev;
+
+ unregister_netdevice_notifier(&netprio_device_notifier);
+
+ cgroup_unload_subsys(&net_prio_subsys);
+
+#ifndef CONFIG_NETPRIO_CGROUP
+ net_prio_subsys_id = -1;
+ synchronize_rcu();
+#endif
+
+ rtnl_lock();
+ for_each_netdev(&init_net, dev) {
+ old = rtnl_dereference(dev->priomap);
+ RCU_INIT_POINTER(dev->priomap, NULL);
+ if (old)
+ kfree_rcu(old, rcu);
+ }
+ rtnl_unlock();
+}
+
+module_init(init_cgroup_netprio);
+module_exit(exit_cgroup_netprio);
+MODULE_LICENSE("GPL v2");
scan_ip6(buf, pkt_dev->in6_daddr.s6_addr);
snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr);
- ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr);
+ pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr;
if (debug)
printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf);
scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr);
snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr);
- ipv6_addr_copy(&pkt_dev->cur_in6_daddr,
- &pkt_dev->min_in6_daddr);
+ pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr;
if (debug)
printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf);
scan_ip6(buf, pkt_dev->in6_saddr.s6_addr);
snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr);
- ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr);
+ pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr;
if (debug)
printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf);
ifp = ifp->if_next) {
if (ifp->scope == IFA_LINK &&
!(ifp->flags & IFA_F_TENTATIVE)) {
- ipv6_addr_copy(&pkt_dev->
- cur_in6_saddr,
- &ifp->addr);
+ pkt_dev->cur_in6_saddr = ifp->addr;
err = 0;
break;
}
iph->payload_len = htons(sizeof(struct udphdr) + datalen);
iph->nexthdr = IPPROTO_UDP;
- ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr);
- ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr);
+ iph->daddr = pkt_dev->cur_in6_daddr;
+ iph->saddr = pkt_dev->cur_in6_saddr;
skb->mac_header = (skb->network_header - ETH_HLEN -
pkt_dev->pkt_overhead);
__netif_tx_lock_bh(txq);
- if (unlikely(netif_tx_queue_frozen_or_stopped(txq))) {
+ if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
ret = NETDEV_TX_BUSY;
pkt_dev->last_ok = 0;
goto unlock;
* but then some measure against one socket starving all other sockets
* would be needed.
*
- * It was 128 by default. Experiments with real servers show, that
+ * The minimum value of it is 128. Experiments with real servers show that
* it is absolutely not enough even at 100conn/sec. 256 cures most
- * of problems. This value is adjusted to 128 for very small machines
- * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb).
+ * of problems.
+ * This value is adjusted to 128 for low memory machines,
+ * and it will increase in proportion to the memory of machine.
* Note : Dont forget somaxconn that may limit backlog too.
*/
int sysctl_max_syn_backlog = 256;
static LIST_HEAD(link_ops);
+static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
+{
+ const struct rtnl_link_ops *ops;
+
+ list_for_each_entry(ops, &link_ops, list) {
+ if (!strcmp(ops->kind, kind))
+ return ops;
+ }
+ return NULL;
+}
+
/**
* __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
* @ops: struct rtnl_link_ops * to register
*/
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
+ if (rtnl_link_ops_get(ops->kind))
+ return -EEXIST;
+
if (!ops->dellink)
ops->dellink = unregister_netdevice_queue;
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
-static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
-{
- const struct rtnl_link_ops *ops;
-
- list_for_each_entry(ops, &link_ops, list) {
- if (!strcmp(ops->kind, kind))
- return ops;
- }
- return NULL;
-}
-
static size_t rtnl_link_get_size(const struct net_device *dev)
{
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
}
late_initcall(net_secret_init);
+#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
{
/*
*/
return seq + (ktime_to_ns(ktime_get_real()) >> 6);
}
+#endif
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
__be16 sport, __be16 dport)
{
EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
#endif
-#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
+#if IS_ENABLED(CONFIG_IP_DCCP)
u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport)
{
}
EXPORT_SYMBOL(secure_dccp_sequence_number);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
__be16 sport, __be16 dport)
{
}
EXPORT_SYMBOL(__alloc_skb);
+/**
+ * build_skb - build a network buffer
+ * @data: data buffer provided by caller
+ *
+ * Allocate a new &sk_buff. Caller provides space holding head and
+ * skb_shared_info. @data must have been allocated by kmalloc()
+ * The return is the new skb buffer.
+ * On a failure the return is %NULL, and @data is not freed.
+ * Notes :
+ * Before IO, driver allocates only data buffer where NIC put incoming frame
+ * Driver should add room at head (NET_SKB_PAD) and
+ * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info))
+ * After IO, driver calls build_skb(), to allocate sk_buff and populate it
+ * before giving packet to stack.
+ * RX rings only contains data buffers, not full skbs.
+ */
+struct sk_buff *build_skb(void *data)
+{
+ struct skb_shared_info *shinfo;
+ struct sk_buff *skb;
+ unsigned int size;
+
+ skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ memset(skb, 0, offsetof(struct sk_buff, tail));
+ skb->truesize = SKB_TRUESIZE(size);
+ atomic_set(&skb->users, 1);
+ skb->head = data;
+ skb->data = data;
+ skb_reset_tail_pointer(skb);
+ skb->end = skb->tail + size;
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ skb->mac_header = ~0U;
+#endif
+
+ /* make sure we initialize shinfo sequentially */
+ shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+ atomic_set(&shinfo->dataref, 1);
+ kmemcheck_annotate_variable(shinfo->destructor_arg);
+
+ return skb;
+}
+EXPORT_SYMBOL(build_skb);
+
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
WARN_ON(in_irq());
skb->destructor(skb);
}
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb->nfct);
#endif
#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
new->ip_summed = old->ip_summed;
skb_copy_queue_mapping(new, old);
new->priority = old->priority;
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+#if IS_ENABLED(CONFIG_IP_VS)
new->ipvs_property = old->ipvs_property;
#endif
new->protocol = old->protocol;
new->mark = old->mark;
new->skb_iif = old->skb_iif;
__nf_copy(new, old);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
new->nf_trace = old->nf_trace;
#endif
#ifdef CONFIG_NET_SCHED
EXPORT_SYMBOL(skb_copy);
/**
- * pskb_copy - create copy of an sk_buff with private head.
+ * __pskb_copy - create copy of an sk_buff with private head.
* @skb: buffer to copy
+ * @headroom: headroom of new skb
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and part of its data, located
* The returned buffer has a reference count of 1.
*/
-struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
+struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
{
- unsigned int size = skb_end_pointer(skb) - skb->head;
+ unsigned int size = skb_headlen(skb) + headroom;
struct sk_buff *n = alloc_skb(size, gfp_mask);
if (!n)
goto out;
/* Set the data pointer */
- skb_reserve(n, skb_headroom(skb));
+ skb_reserve(n, headroom);
/* Set the tail pointer and length */
skb_put(n, skb_headlen(skb));
/* Copy the bytes */
out:
return n;
}
-EXPORT_SYMBOL(pskb_copy);
+EXPORT_SYMBOL(__pskb_copy);
/**
* pskb_expand_head - reallocate header of &sk_buff
* @shiftlen: shift up to this many bytes
*
* Attempts to shift up to shiftlen worth of bytes, which may be less than
- * the length of the skb, from tgt to skb. Returns number bytes shifted.
+ * the length of the skb, from skb to tgt. Returns number bytes shifted.
* It's up to caller to free skb if everything was shifted.
*
* If @tgt runs out of frags, the whole operation is aborted.
* a pointer to the first in a list of new skbs for the segments.
* In case of error it returns ERR_PTR(err).
*/
-struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
{
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
+#include <linux/jump_label.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
#include <net/cls_cgroup.h>
+#include <net/netprio_cgroup.h>
#include <linux/filter.h>
#include <net/tcp.h>
#endif
+static DEFINE_MUTEX(proto_list_mutex);
+static LIST_HEAD(proto_list);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct proto *proto;
+ int ret = 0;
+
+ mutex_lock(&proto_list_mutex);
+ list_for_each_entry(proto, &proto_list, node) {
+ if (proto->init_cgroup) {
+ ret = proto->init_cgroup(cgrp, ss);
+ if (ret)
+ goto out;
+ }
+ }
+
+ mutex_unlock(&proto_list_mutex);
+ return ret;
+out:
+ list_for_each_entry_continue_reverse(proto, &proto_list, node)
+ if (proto->destroy_cgroup)
+ proto->destroy_cgroup(cgrp, ss);
+ mutex_unlock(&proto_list_mutex);
+ return ret;
+}
+
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct proto *proto;
+
+ mutex_lock(&proto_list_mutex);
+ list_for_each_entry_reverse(proto, &proto_list, node)
+ if (proto->destroy_cgroup)
+ proto->destroy_cgroup(cgrp, ss);
+ mutex_unlock(&proto_list_mutex);
+}
+#endif
+
/*
* Each address family might have different locking rules, so we have
* one slock key per address family:
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
+struct jump_label_key memcg_socket_limit_enabled;
+EXPORT_SYMBOL(memcg_socket_limit_enabled);
+
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
-#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+#if defined(CONFIG_CGROUPS)
+#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
EXPORT_SYMBOL_GPL(net_cls_subsys_id);
#endif
+#if !defined(CONFIG_NETPRIO_CGROUP)
+int net_prio_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_prio_subsys_id);
+#endif
+#endif
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
}
}
-static void sock_disable_timestamp(struct sock *sk, int flag)
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
+static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
- if (sock_flag(sk, flag)) {
- sock_reset_flag(sk, flag);
- if (!sock_flag(sk, SOCK_TIMESTAMP) &&
- !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) {
+ if (sk->sk_flags & flags) {
+ sk->sk_flags &= ~flags;
+ if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
net_disable_timestamp();
- }
}
}
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
- /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces
- number of warnings when compiling with -W --ANK
- */
- if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned)sk->sk_rcvbuf) {
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
SOCK_TIMESTAMPING_RX_SOFTWARE);
else
sock_disable_timestamp(sk,
- SOCK_TIMESTAMPING_RX_SOFTWARE);
+ (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE,
val & SOF_TIMESTAMPING_SOFTWARE);
sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE,
sk->sk_classid = classid;
}
EXPORT_SYMBOL(sock_update_classid);
+
+void sock_update_netprioidx(struct sock *sk)
+{
+ struct cgroup_netprio_state *state;
+ if (in_interrupt())
+ return;
+ rcu_read_lock();
+ state = task_netprio_state(current);
+ sk->sk_cgrp_prioidx = state ? state->prioidx : 0;
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(sock_update_netprioidx);
#endif
/**
atomic_set(&sk->sk_wmem_alloc, 1);
sock_update_classid(sk);
+ sock_update_netprioidx(sk);
}
return sk;
RCU_INIT_POINTER(sk->sk_filter, NULL);
}
- sock_disable_timestamp(sk, SOCK_TIMESTAMP);
- sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
+ sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
if (atomic_read(&sk->sk_omem_alloc))
printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
}
EXPORT_SYMBOL(sk_release_kernel);
-struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
+/**
+ * sk_clone_lock - clone a socket, and lock its clone
+ * @sk: the socket to clone
+ * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ * Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
{
struct sock *newsk;
newsk->sk_wq = NULL;
if (newsk->sk_prot->sockets_allocated)
- percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+ sk_sockets_allocated_inc(newsk);
- if (sock_flag(newsk, SOCK_TIMESTAMP) ||
- sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))
+ if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
net_enable_timestamp();
}
out:
return newsk;
}
-EXPORT_SYMBOL_GPL(sk_clone);
+EXPORT_SYMBOL_GPL(sk_clone_lock);
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
struct proto *prot = sk->sk_prot;
int amt = sk_mem_pages(size);
long allocated;
+ int parent_status = UNDER_LIMIT;
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
- allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+ allocated = sk_memory_allocated_add(sk, amt, &parent_status);
/* Under limit. */
- if (allocated <= prot->sysctl_mem[0]) {
- if (prot->memory_pressure && *prot->memory_pressure)
- *prot->memory_pressure = 0;
+ if (parent_status == UNDER_LIMIT &&
+ allocated <= sk_prot_mem_limits(sk, 0)) {
+ sk_leave_memory_pressure(sk);
return 1;
}
- /* Under pressure. */
- if (allocated > prot->sysctl_mem[1])
- if (prot->enter_memory_pressure)
- prot->enter_memory_pressure(sk);
+ /* Under pressure. (we or our parents) */
+ if ((parent_status > SOFT_LIMIT) ||
+ allocated > sk_prot_mem_limits(sk, 1))
+ sk_enter_memory_pressure(sk);
- /* Over hard limit. */
- if (allocated > prot->sysctl_mem[2])
+ /* Over hard limit (we or our parents) */
+ if ((parent_status == OVER_LIMIT) ||
+ (allocated > sk_prot_mem_limits(sk, 2)))
goto suppress_allocation;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
return 1;
+
} else { /* SK_MEM_SEND */
if (sk->sk_type == SOCK_STREAM) {
if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
return 1;
}
- if (prot->memory_pressure) {
+ if (sk_has_memory_pressure(sk)) {
int alloc;
- if (!*prot->memory_pressure)
+ if (!sk_under_memory_pressure(sk))
return 1;
- alloc = percpu_counter_read_positive(prot->sockets_allocated);
- if (prot->sysctl_mem[2] > alloc *
+ alloc = sk_sockets_allocated_read_positive(sk);
+ if (sk_prot_mem_limits(sk, 2) > alloc *
sk_mem_pages(sk->sk_wmem_queued +
atomic_read(&sk->sk_rmem_alloc) +
sk->sk_forward_alloc))
/* Alas. Undo changes. */
sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
- atomic_long_sub(amt, prot->memory_allocated);
+
+ sk_memory_allocated_sub(sk, amt, parent_status);
+
return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);
*/
void __sk_mem_reclaim(struct sock *sk)
{
- struct proto *prot = sk->sk_prot;
-
- atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
- prot->memory_allocated);
+ sk_memory_allocated_sub(sk,
+ sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0);
sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
- if (prot->memory_pressure && *prot->memory_pressure &&
- (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
- *prot->memory_pressure = 0;
+ if (sk_under_memory_pressure(sk) &&
+ (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
+ sk_leave_memory_pressure(sk);
}
EXPORT_SYMBOL(__sk_mem_reclaim);
void sock_enable_timestamp(struct sock *sk, int flag)
{
if (!sock_flag(sk, flag)) {
+ unsigned long previous_flags = sk->sk_flags;
+
sock_set_flag(sk, flag);
/*
* we just set one of the two flags which require net
* time stamping, but time stamping might have been on
* already because of the other one
*/
- if (!sock_flag(sk,
- flag == SOCK_TIMESTAMP ?
- SOCK_TIMESTAMPING_RX_SOFTWARE :
- SOCK_TIMESTAMP))
+ if (!(previous_flags & SK_FLAGS_TIMESTAMP))
net_enable_timestamp();
}
}
}
EXPORT_SYMBOL(sk_common_release);
-static DEFINE_RWLOCK(proto_list_lock);
-static LIST_HEAD(proto_list);
-
#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR 64 /* should be enough for the first time */
struct prot_inuse {
}
}
- write_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
list_add(&prot->node, &proto_list);
assign_proto_idx(prot);
- write_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
return 0;
out_free_timewait_sock_slab_name:
void proto_unregister(struct proto *prot)
{
- write_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
release_proto_idx(prot);
list_del(&prot->node);
- write_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
if (prot->slab != NULL) {
kmem_cache_destroy(prot->slab);
#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(proto_list_lock)
+ __acquires(proto_list_mutex)
{
- read_lock(&proto_list_lock);
+ mutex_lock(&proto_list_mutex);
return seq_list_start_head(&proto_list, *pos);
}
}
static void proto_seq_stop(struct seq_file *seq, void *v)
- __releases(proto_list_lock)
+ __releases(proto_list_mutex)
{
- read_unlock(&proto_list_lock);
+ mutex_unlock(&proto_list_mutex);
}
static char proto_method_implemented(const void *method)
{
return method == NULL ? 'n' : 'y';
}
+static long sock_prot_memory_allocated(struct proto *proto)
+{
+ return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+}
+
+static char *sock_prot_memory_pressure(struct proto *proto)
+{
+ return proto->memory_pressure != NULL ?
+ proto_memory_pressure(proto) ? "yes" : "no" : "NI";
+}
static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
+
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
- proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
- proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
+ sock_prot_memory_allocated(proto),
+ sock_prot_memory_pressure(proto),
proto->max_header,
proto->slab == NULL ? "no" : "yes",
module_name(proto->owner),
--- /dev/null
+#include <linux/mutex.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <linux/module.h>
+#include <linux/rtnetlink.h>
+#include <net/sock.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+static struct sock_diag_handler *sock_diag_handlers[AF_MAX];
+static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
+static DEFINE_MUTEX(sock_diag_table_mutex);
+
+int sock_diag_check_cookie(void *sk, __u32 *cookie)
+{
+ if ((cookie[0] != INET_DIAG_NOCOOKIE ||
+ cookie[1] != INET_DIAG_NOCOOKIE) &&
+ ((u32)(unsigned long)sk != cookie[0] ||
+ (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1]))
+ return -ESTALE;
+ else
+ return 0;
+}
+EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
+
+void sock_diag_save_cookie(void *sk, __u32 *cookie)
+{
+ cookie[0] = (u32)(unsigned long)sk;
+ cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+}
+EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
+
+int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
+{
+ __u32 *mem;
+
+ mem = RTA_DATA(__RTA_PUT(skb, attrtype, SK_MEMINFO_VARS * sizeof(__u32)));
+
+ mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+ mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+ mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+ mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+ mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+ mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+ mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
+
+void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+ mutex_lock(&sock_diag_table_mutex);
+ inet_rcv_compat = fn;
+ mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
+
+void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+ mutex_lock(&sock_diag_table_mutex);
+ inet_rcv_compat = NULL;
+ mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
+
+int sock_diag_register(struct sock_diag_handler *hndl)
+{
+ int err = 0;
+
+ if (hndl->family >= AF_MAX)
+ return -EINVAL;
+
+ mutex_lock(&sock_diag_table_mutex);
+ if (sock_diag_handlers[hndl->family])
+ err = -EBUSY;
+ else
+ sock_diag_handlers[hndl->family] = hndl;
+ mutex_unlock(&sock_diag_table_mutex);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sock_diag_register);
+
+void sock_diag_unregister(struct sock_diag_handler *hnld)
+{
+ int family = hnld->family;
+
+ if (family >= AF_MAX)
+ return;
+
+ mutex_lock(&sock_diag_table_mutex);
+ BUG_ON(sock_diag_handlers[family] != hnld);
+ sock_diag_handlers[family] = NULL;
+ mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister);
+
+static inline struct sock_diag_handler *sock_diag_lock_handler(int family)
+{
+ if (sock_diag_handlers[family] == NULL)
+ request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, family);
+
+ mutex_lock(&sock_diag_table_mutex);
+ return sock_diag_handlers[family];
+}
+
+static inline void sock_diag_unlock_handler(struct sock_diag_handler *h)
+{
+ mutex_unlock(&sock_diag_table_mutex);
+}
+
+static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+ int err;
+ struct sock_diag_req *req = NLMSG_DATA(nlh);
+ struct sock_diag_handler *hndl;
+
+ if (nlmsg_len(nlh) < sizeof(*req))
+ return -EINVAL;
+
+ hndl = sock_diag_lock_handler(req->sdiag_family);
+ if (hndl == NULL)
+ err = -ENOENT;
+ else
+ err = hndl->dump(skb, nlh);
+ sock_diag_unlock_handler(hndl);
+
+ return err;
+}
+
+static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+ int ret;
+
+ switch (nlh->nlmsg_type) {
+ case TCPDIAG_GETSOCK:
+ case DCCPDIAG_GETSOCK:
+ if (inet_rcv_compat == NULL)
+ request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, AF_INET);
+
+ mutex_lock(&sock_diag_table_mutex);
+ if (inet_rcv_compat != NULL)
+ ret = inet_rcv_compat(skb, nlh);
+ else
+ ret = -EOPNOTSUPP;
+ mutex_unlock(&sock_diag_table_mutex);
+
+ return ret;
+ case SOCK_DIAG_BY_FAMILY:
+ return __sock_diag_rcv_msg(skb, nlh);
+ default:
+ return -EINVAL;
+ }
+}
+
+static DEFINE_MUTEX(sock_diag_mutex);
+
+static void sock_diag_rcv(struct sk_buff *skb)
+{
+ mutex_lock(&sock_diag_mutex);
+ netlink_rcv_skb(skb, &sock_diag_rcv_msg);
+ mutex_unlock(&sock_diag_mutex);
+}
+
+struct sock *sock_diag_nlsk;
+EXPORT_SYMBOL_GPL(sock_diag_nlsk);
+
+static int __init sock_diag_init(void)
+{
+ sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0,
+ sock_diag_rcv, NULL, THIS_MODULE);
+ return sock_diag_nlsk == NULL ? -ENOMEM : 0;
+}
+
+static void __exit sock_diag_exit(void)
+{
+ netlink_kernel_release(sock_diag_nlsk);
+}
+
+module_init(sock_diag_init);
+module_exit(sock_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);
if (sock_table != orig_sock_table) {
rcu_assign_pointer(rps_sock_flow_table, sock_table);
- synchronize_rcu();
- vfree(orig_sock_table);
+ if (sock_table)
+ jump_label_inc(&rps_needed);
+ if (orig_sock_table) {
+ jump_label_dec(&rps_needed);
+ synchronize_rcu();
+ vfree(orig_sock_table);
+ }
}
}
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
-static int ccid2_debug;
+static bool ccid2_debug;
#define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a)
#else
#define ccid2_pr_debug(format, a...)
/*
* Congestion window validation (RFC 2861).
*/
-static int ccid2_do_cwv = 1;
+static bool ccid2_do_cwv = true;
module_param(ccid2_do_cwv, bool, 0644);
MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation");
#include <asm/unaligned.h>
#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
-static int ccid3_debug;
+static bool ccid3_debug;
#define ccid3_pr_debug(format, a...) DCCP_PR_DEBUG(ccid3_debug, format, ##a)
#else
#define ccid3_pr_debug(format, a...)
#include "tfrc.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-int tfrc_debug;
+bool tfrc_debug;
module_param(tfrc_debug, bool, 0644);
MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages");
#endif
#include "packet_history.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-extern int tfrc_debug;
+extern bool tfrc_debug;
#define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a)
#else
#define tfrc_pr_debug(format, a...)
"%s: " fmt, __func__, ##a)
#ifdef CONFIG_IP_DCCP_DEBUG
-extern int dccp_debug;
+extern bool dccp_debug;
#define dccp_pr_debug(format, a...) DCCP_PR_DEBUG(dccp_debug, format, ##a)
#define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a)
#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
struct dccp_skb_cb {
union {
struct inet_skb_parm h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header;
dccp_get_info(sk, _info);
}
+static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc);
+}
+
+static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+ struct inet_diag_req *req)
+{
+ return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req);
+}
+
static const struct inet_diag_handler dccp_diag_handler = {
- .idiag_hashinfo = &dccp_hashinfo,
+ .dump = dccp_diag_dump,
+ .dump_one = dccp_diag_dump_one,
.idiag_get_info = dccp_diag_get_info,
- .idiag_type = DCCPDIAG_GETSOCK,
- .idiag_info_size = sizeof(struct tcp_info),
+ .idiag_type = IPPROTO_DCCP,
};
static int __init dccp_diag_init(void)
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
MODULE_DESCRIPTION("DCCP inet_diag handler");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, DCCPDIAG_GETSOCK);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-33 /* AF_INET - IPPROTO_DCCP */);
new->feat_num = feat;
new->is_local = local;
new->state = FEAT_INITIALISING;
- new->needs_confirm = 0;
- new->empty_confirm = 0;
+ new->needs_confirm = false;
+ new->empty_confirm = false;
new->val = *fval;
new->needs_mandatory = mandatory;
new->feat_num = feat;
new->is_local = local;
new->state = FEAT_STABLE; /* transition in 6.6.2 */
- new->needs_confirm = 1;
+ new->needs_confirm = true;
new->empty_confirm = (fval == NULL);
new->val.nn = 0; /* zeroes the whole structure */
if (!new->empty_confirm)
new->val = *fval;
- new->needs_mandatory = 0;
+ new->needs_mandatory = false;
return 0;
}
}
if (dccp_feat_reconcile(&entry->val, val, len, server, true)) {
- entry->empty_confirm = 0;
+ entry->empty_confirm = false;
} else if (is_mandatory) {
return DCCP_RESET_CODE_MANDATORY_ERROR;
} else if (entry->state == FEAT_INITIALISING) {
defval = dccp_feat_default_value(feat);
if (!dccp_feat_reconcile(&entry->val, &defval, 1, server, true))
return DCCP_RESET_CODE_OPTION_ERROR;
- entry->empty_confirm = 1;
+ entry->empty_confirm = true;
}
- entry->needs_confirm = 1;
- entry->needs_mandatory = 0;
+ entry->needs_confirm = true;
+ entry->needs_mandatory = false;
entry->state = FEAT_STABLE;
return 0;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
rt = NULL;
goto failure;
}
struct sk_buff *skb)
{
struct rtable *rt;
+ const struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.flowi4_oif = skb_rtable(skb)->rt_iif,
- .daddr = ip_hdr(skb)->saddr,
- .saddr = ip_hdr(skb)->daddr,
+ .daddr = iph->saddr,
+ .saddr = iph->daddr,
.flowi4_tos = RT_CONN_FLAGS(sk),
.flowi4_proto = sk->sk_protocol,
.fl4_sport = dccp_hdr(skb)->dccph_dport,
*/
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
- ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
- ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+ fl6.daddr = ireq6->rmt_addr;
+ fl6.saddr = ireq6->loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = ireq6->iif;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
dh->dccph_checksum = dccp_v6_csum_finish(skb,
&ireq6->loc_addr,
&ireq6->rmt_addr);
- ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+ fl6.daddr = ireq6->rmt_addr;
err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
err = net_xmit_eval(err);
}
&rxip6h->daddr);
memset(&fl6, 0, sizeof(fl6));
- ipv6_addr_copy(&fl6.daddr, &rxip6h->saddr);
- ipv6_addr_copy(&fl6.saddr, &rxip6h->daddr);
+ fl6.daddr = rxip6h->saddr;
+ fl6.saddr = rxip6h->daddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.flowi6_oif = inet6_iif(rxskb);
goto drop_and_free;
ireq6 = inet6_rsk(req);
- ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
- ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+ ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq6->loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
- ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
+ newnp->rcv_saddr = newnp->saddr;
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
- ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+ fl6.daddr = ireq6->rmt_addr;
final_p = fl6_update_dst(&fl6, opt, &final);
- ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+ fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_rsk(req)->loc_port;
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr);
- ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr);
- ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr);
+ newnp->daddr = ireq6->rmt_addr;
+ newnp->saddr = ireq6->loc_addr;
+ newnp->rcv_saddr = ireq6->loc_addr;
newsk->sk_bound_dev_if = ireq6->iif;
/* Now IPv6 options...
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
- ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+ usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
return -EINVAL;
}
- ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
+ np->daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, saddr ? saddr : &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
if (saddr == NULL) {
saddr = &fl6.saddr;
- ipv6_addr_copy(&np->rcv_saddr, saddr);
+ np->rcv_saddr = *saddr;
}
/* set the source address */
- ipv6_addr_copy(&np->saddr, saddr);
+ np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
if (tw != NULL) {
const struct inet_connection_sock *icsk = inet_csk(sk);
const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
const struct ipv6_pinfo *np = inet6_sk(sk);
struct inet6_timewait_sock *tw6;
tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
tw6 = inet6_twsk((struct sock *)tw);
- ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
- ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
+ tw6->tw_v6_daddr = np->daddr;
+ tw6->tw_v6_rcv_saddr = np->rcv_saddr;
tw->tw_ipv6only = np->ipv6only;
}
#endif
* (* Generate a new socket and switch to that socket *)
* Set S := new socket for this port pair
*/
- struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+ struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
if (newsk != NULL) {
struct dccp_request_sock *dreq = dccp_rsk(req);
}
if (unlikely(val == NULL || len == 0))
- len = repeat_first = 0;
+ len = repeat_first = false;
tot_len = 3 + repeat_first + len;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) {
.llseek = noop_llseek,
};
+static __init int setup_jprobe(void)
+{
+ int ret = register_jprobe(&dccp_send_probe);
+
+ if (ret) {
+ request_module("dccp");
+ ret = register_jprobe(&dccp_send_probe);
+ }
+ return ret;
+}
+
static __init int dccpprobe_init(void)
{
int ret = -ENOMEM;
if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops))
goto err0;
- try_then_request_module((ret = register_jprobe(&dccp_send_probe)) == 0,
- "dccp");
+ ret = setup_jprobe();
if (ret)
goto err1;
MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");
#ifdef CONFIG_IP_DCCP_DEBUG
-int dccp_debug;
+bool dccp_debug;
module_param(dccp_debug, bool, 0644);
MODULE_PARM_DESC(dccp_debug, "Enable debug messages");
static u32 dn_neigh_hash(const void *pkey,
const struct net_device *dev,
- __u32 hash_rnd)
+ __u32 *hash_rnd)
{
- return jhash_2words(*(__u16 *)pkey, 0, hash_rnd);
+ return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]);
}
struct neigh_table dn_neigh_table = {
.gc_staletime = 60 * HZ,
.reachable_time = 30 * HZ,
.delay_probe_time = 5 * HZ,
- .queue_len = 3,
+ .queue_len_bytes = 64*1024,
.ucast_probes = 0,
.app_probes = 0,
.mcast_probes = 0,
{
struct dst_entry *dst = skb_dst(skb);
struct dn_route *rt = (struct dn_route *)dst;
- struct neighbour *neigh = dst_get_neighbour(dst);
+ struct neighbour *neigh = dst_get_neighbour_noref(dst);
struct net_device *dev = neigh->dev;
char mac_addr[ETH_ALEN];
static int dn_dst_gc(struct dst_ops *ops);
static struct dst_entry *dn_dst_check(struct dst_entry *, __u32);
static unsigned int dn_dst_default_advmss(const struct dst_entry *dst);
-static unsigned int dn_dst_default_mtu(const struct dst_entry *dst);
+static unsigned int dn_dst_mtu(const struct dst_entry *dst);
static void dn_dst_destroy(struct dst_entry *);
static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
static void dn_dst_link_failure(struct sk_buff *);
.gc = dn_dst_gc,
.check = dn_dst_check,
.default_advmss = dn_dst_default_advmss,
- .default_mtu = dn_dst_default_mtu,
+ .mtu = dn_dst_mtu,
.cow_metrics = dst_cow_metrics_generic,
.destroy = dn_dst_destroy,
.negative_advice = dn_dst_negative_advice,
*/
static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
{
- struct neighbour *n = dst_get_neighbour(dst);
+ struct neighbour *n = dst_get_neighbour_noref(dst);
u32 min_mtu = 230;
struct dn_dev *dn;
static int dn_to_neigh_output(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- struct neighbour *n = dst_get_neighbour(dst);
+ struct neighbour *n = dst_get_neighbour_noref(dst);
return n->output(n, skb);
}
int err = -EINVAL;
- if ((neigh = dst_get_neighbour(dst)) == NULL)
+ if ((neigh = dst_get_neighbour_noref(dst)) == NULL)
goto error;
skb->dev = dev;
return dn_mss_from_pmtu(dst->dev, dst_mtu(dst));
}
-static unsigned int dn_dst_default_mtu(const struct dst_entry *dst)
+static unsigned int dn_dst_mtu(const struct dst_entry *dst)
{
- return dst->dev->mtu;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst->dev->mtu;
}
static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
}
rt->rt_type = res->type;
- if (dev != NULL && dst_get_neighbour(&rt->dst) == NULL) {
+ if (dev != NULL && dst_get_neighbour_noref(&rt->dst) == NULL) {
n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev);
if (IS_ERR(n))
return PTR_ERR(n);
void dn_start_slow_timer(struct sock *sk)
{
- sk->sk_timer.expires = jiffies + SLOW_INTERVAL;
- sk->sk_timer.function = dn_slow_timer;
- sk->sk_timer.data = (unsigned long)sk;
-
- add_timer(&sk->sk_timer);
+ setup_timer(&sk->sk_timer, dn_slow_timer, (unsigned long)sk);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL);
}
void dn_stop_slow_timer(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
static void dn_slow_timer(unsigned long arg)
struct sock *sk = (struct sock *)arg;
struct dn_scp *scp = DN_SK(sk);
- sock_hold(sk);
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
- sk->sk_timer.expires = jiffies + HZ / 10;
- add_timer(&sk->sk_timer);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10);
goto out;
}
scp->keepalive_fxn(sk);
}
- sk->sk_timer.expires = jiffies + SLOW_INTERVAL;
-
- add_timer(&sk->sk_timer);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL);
out:
bh_unlock_sock(sk);
sock_put(sk);
-menuconfig NET_DSA
- bool "Distributed Switch Architecture support"
+config NET_DSA
+ tristate "Distributed Switch Architecture support"
default n
depends on EXPERIMENTAL && NETDEVICES && !S390
select PHYLIB
bool
default n
-
-# switch drivers
-config NET_DSA_MV88E6XXX
- bool
- default n
-
-config NET_DSA_MV88E6060
- bool "Marvell 88E6060 ethernet switch chip support"
- select NET_DSA_TAG_TRAILER
- ---help---
- This enables support for the Marvell 88E6060 ethernet switch
- chip.
-
-config NET_DSA_MV88E6XXX_NEED_PPU
- bool
- default n
-
-config NET_DSA_MV88E6131
- bool "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support"
- select NET_DSA_MV88E6XXX
- select NET_DSA_MV88E6XXX_NEED_PPU
- select NET_DSA_TAG_DSA
- ---help---
- This enables support for the Marvell 88E6085/6095/6095F/6131
- ethernet switch chips.
-
-config NET_DSA_MV88E6123_61_65
- bool "Marvell 88E6123/6161/6165 ethernet switch chip support"
- select NET_DSA_MV88E6XXX
- select NET_DSA_TAG_EDSA
- ---help---
- This enables support for the Marvell 88E6123/6161/6165
- ethernet switch chips.
-
endif
-# tagging formats
-obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
-obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
-obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
-
-# switch drivers
-obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
-obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
-obj-$(CONFIG_NET_DSA_MV88E6123_61_65) += mv88e6123_61_65.o
-obj-$(CONFIG_NET_DSA_MV88E6131) += mv88e6131.o
-
# the core
-obj-$(CONFIG_NET_DSA) += dsa.o slave.o
+obj-$(CONFIG_NET_DSA) += dsa_core.o
+dsa_core-y += dsa.o slave.o
+
+# tagging formats
+dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
+dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
+dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
list_add_tail(&drv->list, &dsa_switch_drivers);
mutex_unlock(&dsa_switch_drivers_mutex);
}
+EXPORT_SYMBOL_GPL(register_switch_driver);
void unregister_switch_driver(struct dsa_switch_driver *drv)
{
list_del_init(&drv->list);
mutex_unlock(&dsa_switch_drivers_mutex);
}
+EXPORT_SYMBOL_GPL(unregister_switch_driver);
static struct dsa_switch_driver *
dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
}
-/* hooks for ethertype-less tagging formats *********************************/
-/*
- * The original DSA tag format and some other tag formats have no
- * ethertype, which means that we need to add a little hack to the
- * networking receive path to make sure that received frames get
- * the right ->protocol assigned to them when one of those tag
- * formats is in use.
- */
-bool dsa_uses_dsa_tags(void *dsa_ptr)
-{
- struct dsa_switch_tree *dst = dsa_ptr;
-
- return !!(dst->tag_protocol == htons(ETH_P_DSA));
-}
-
-bool dsa_uses_trailer_tags(void *dsa_ptr)
-{
- struct dsa_switch_tree *dst = dsa_ptr;
-
- return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
-}
-
-
/* link polling *************************************************************/
static void dsa_link_poll_work(struct work_struct *ugly)
{
static int __init dsa_init_module(void)
{
- return platform_driver_register(&dsa_driver);
+ int rc;
+
+ rc = platform_driver_register(&dsa_driver);
+ if (rc)
+ return rc;
+
+#ifdef CONFIG_NET_DSA_TAG_DSA
+ dev_add_pack(&dsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+ dev_add_pack(&edsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+ dev_add_pack(&trailer_packet_type);
+#endif
+ return 0;
}
module_init(dsa_init_module);
static void __exit dsa_cleanup_module(void)
{
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+ dev_remove_pack(&trailer_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+ dev_remove_pack(&edsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_DSA
+ dev_remove_pack(&dsa_packet_type);
+#endif
platform_driver_unregister(&dsa_driver);
}
module_exit(dsa_cleanup_module);
#ifndef __DSA_PRIV_H
#define __DSA_PRIV_H
-#include <linux/list.h>
#include <linux/phy.h>
-#include <linux/timer.h>
-#include <linux/workqueue.h>
#include <net/dsa.h>
-struct dsa_switch {
- /*
- * Parent switch tree, and switch index.
- */
- struct dsa_switch_tree *dst;
- int index;
-
- /*
- * Configuration data for this switch.
- */
- struct dsa_chip_data *pd;
-
- /*
- * The used switch driver.
- */
- struct dsa_switch_driver *drv;
-
- /*
- * Reference to mii bus to use.
- */
- struct mii_bus *master_mii_bus;
-
- /*
- * Slave mii_bus and devices for the individual ports.
- */
- u32 dsa_port_mask;
- u32 phys_port_mask;
- struct mii_bus *slave_mii_bus;
- struct net_device *ports[DSA_MAX_PORTS];
-};
-
-struct dsa_switch_tree {
- /*
- * Configuration data for the platform device that owns
- * this dsa switch tree instance.
- */
- struct dsa_platform_data *pd;
-
- /*
- * Reference to network device to use, and which tagging
- * protocol to use.
- */
- struct net_device *master_netdev;
- __be16 tag_protocol;
-
- /*
- * The switch and port to which the CPU is attached.
- */
- s8 cpu_switch;
- s8 cpu_port;
-
- /*
- * Link state polling.
- */
- int link_poll_needed;
- struct work_struct link_poll_work;
- struct timer_list link_poll_timer;
-
- /*
- * Data for the individual switch chips.
- */
- struct dsa_switch *ds[DSA_MAX_SWITCHES];
-};
-
-static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
-{
- return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
-}
-
-static inline u8 dsa_upstream_port(struct dsa_switch *ds)
-{
- struct dsa_switch_tree *dst = ds->dst;
-
- /*
- * If this is the root switch (i.e. the switch that connects
- * to the CPU), return the cpu port number on this switch.
- * Else return the (DSA) port number that connects to the
- * switch that is one hop closer to the cpu.
- */
- if (dst->cpu_switch == ds->index)
- return dst->cpu_port;
- else
- return ds->pd->rtable[dst->cpu_switch];
-}
-
struct dsa_slave_priv {
/*
* The linux network interface corresponding to this
struct phy_device *phy;
};
-struct dsa_switch_driver {
- struct list_head list;
-
- __be16 tag_protocol;
- int priv_size;
-
- /*
- * Probing and setup.
- */
- char *(*probe)(struct mii_bus *bus, int sw_addr);
- int (*setup)(struct dsa_switch *ds);
- int (*set_addr)(struct dsa_switch *ds, u8 *addr);
-
- /*
- * Access to the switch's PHY registers.
- */
- int (*phy_read)(struct dsa_switch *ds, int port, int regnum);
- int (*phy_write)(struct dsa_switch *ds, int port,
- int regnum, u16 val);
-
- /*
- * Link state polling and IRQ handling.
- */
- void (*poll_link)(struct dsa_switch *ds);
-
- /*
- * ethtool hardware statistics.
- */
- void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
- void (*get_ethtool_stats)(struct dsa_switch *ds,
- int port, uint64_t *data);
- int (*get_sset_count)(struct dsa_switch *ds);
-};
-
/* dsa.c */
extern char dsa_driver_version[];
-void register_switch_driver(struct dsa_switch_driver *type);
-void unregister_switch_driver(struct dsa_switch_driver *type);
/* slave.c */
void dsa_slave_mii_bus_init(struct dsa_switch *ds);
/* tag_dsa.c */
netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type dsa_packet_type;
/* tag_edsa.c */
netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type edsa_packet_type;
/* tag_trailer.c */
netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type trailer_packet_type;
#endif
return 0;
}
-static struct packet_type dsa_packet_type __read_mostly = {
+struct packet_type dsa_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_DSA),
.func = dsa_rcv,
};
-
-static int __init dsa_init_module(void)
-{
- dev_add_pack(&dsa_packet_type);
- return 0;
-}
-module_init(dsa_init_module);
-
-static void __exit dsa_cleanup_module(void)
-{
- dev_remove_pack(&dsa_packet_type);
-}
-module_exit(dsa_cleanup_module);
return 0;
}
-static struct packet_type edsa_packet_type __read_mostly = {
+struct packet_type edsa_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_EDSA),
.func = edsa_rcv,
};
-
-static int __init edsa_init_module(void)
-{
- dev_add_pack(&edsa_packet_type);
- return 0;
-}
-module_init(edsa_init_module);
-
-static void __exit edsa_cleanup_module(void)
-{
- dev_remove_pack(&edsa_packet_type);
-}
-module_exit(edsa_cleanup_module);
return 0;
}
-static struct packet_type trailer_packet_type __read_mostly = {
+struct packet_type trailer_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_TRAILER),
.func = trailer_rcv,
};
-
-static int __init trailer_init_module(void)
-{
- dev_add_pack(&trailer_packet_type);
- return 0;
-}
-module_init(trailer_init_module);
-
-static void __exit trailer_cleanup_module(void)
-{
- dev_remove_pack(&trailer_packet_type);
-}
-module_exit(trailer_cleanup_module);
/* Real hardware Econet. We're not worthy etc. */
#ifdef CONFIG_ECONET_NATIVE
unsigned short proto = 0;
+ int hlen, tlen;
int res;
if (len + 15 > dev->mtu) {
dev_hold(dev);
- skb = sock_alloc_send_skb(sk, len + LL_ALLOCATED_SPACE(dev),
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = sock_alloc_send_skb(sk, len + hlen + tlen,
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out_unlock;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
eb = (struct ec_cb *)&skb->cb;
* SUCH DAMAGE.
*/
-#define DEBUG
-
#include <linux/bitops.h>
#include <linux/if_arp.h>
#include <linux/module.h>
struct list_head list;
};
+struct lowpan_fragment {
+ struct sk_buff *skb; /* skb to be assembled */
+ spinlock_t lock; /* concurency lock */
+ u16 length; /* length to be assemled */
+ u32 bytes_rcv; /* bytes received */
+ u16 tag; /* current fragment tag */
+ struct timer_list timer; /* assembling timer */
+ struct list_head list; /* fragments list */
+};
+
+static unsigned short fragment_tag;
+static LIST_HEAD(lowpan_fragments);
+spinlock_t flist_lock;
+
static inline struct
lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
{
return 0;
}
+static void
+lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+
+ pr_debug("(%s): UDP header compression\n", __func__);
+
+ if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) ==
+ LOWPAN_NHC_UDP_4BIT_PORT) &&
+ ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) ==
+ LOWPAN_NHC_UDP_4BIT_PORT)) {
+ pr_debug("(%s): both ports compression to 4 bits\n", __func__);
+ **hc06_ptr = LOWPAN_NHC_UDP_CS_P_11;
+ **(hc06_ptr + 1) = /* subtraction is faster */
+ (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) +
+ ((uh->source & LOWPAN_NHC_UDP_4BIT_PORT) << 4));
+ *hc06_ptr += 2;
+ } else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) ==
+ LOWPAN_NHC_UDP_8BIT_PORT) {
+ pr_debug("(%s): remove 8 bits of dest\n", __func__);
+ **hc06_ptr = LOWPAN_NHC_UDP_CS_P_01;
+ memcpy(*hc06_ptr + 1, &uh->source, 2);
+ **(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT);
+ *hc06_ptr += 4;
+ } else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) ==
+ LOWPAN_NHC_UDP_8BIT_PORT) {
+ pr_debug("(%s): remove 8 bits of source\n", __func__);
+ **hc06_ptr = LOWPAN_NHC_UDP_CS_P_10;
+ memcpy(*hc06_ptr + 1, &uh->dest, 2);
+ **(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT);
+ *hc06_ptr += 4;
+ } else {
+ pr_debug("(%s): can't compress header\n", __func__);
+ **hc06_ptr = LOWPAN_NHC_UDP_CS_P_00;
+ memcpy(*hc06_ptr + 1, &uh->source, 2);
+ memcpy(*hc06_ptr + 3, &uh->dest, 2);
+ *hc06_ptr += 5;
+ }
+
+ /* checksum is always inline */
+ memcpy(*hc06_ptr, &uh->check, 2);
+ *hc06_ptr += 2;
+}
+
static u8 lowpan_fetch_skb_u8(struct sk_buff *skb)
{
u8 ret;
return ret;
}
+static u16 lowpan_fetch_skb_u16(struct sk_buff *skb)
+{
+ u16 ret;
+
+ BUG_ON(!pskb_may_pull(skb, 2));
+
+ ret = skb->data[0] | (skb->data[1] << 8);
+ skb_pull(skb, 2);
+ return ret;
+}
+
+static int
+lowpan_uncompress_udp_header(struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+ u8 tmp;
+
+ tmp = lowpan_fetch_skb_u8(skb);
+
+ if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) {
+ pr_debug("(%s): UDP header uncompression\n", __func__);
+ switch (tmp & LOWPAN_NHC_UDP_CS_P_11) {
+ case LOWPAN_NHC_UDP_CS_P_00:
+ memcpy(&uh->source, &skb->data[0], 2);
+ memcpy(&uh->dest, &skb->data[2], 2);
+ skb_pull(skb, 4);
+ break;
+ case LOWPAN_NHC_UDP_CS_P_01:
+ memcpy(&uh->source, &skb->data[0], 2);
+ uh->dest =
+ skb->data[2] + LOWPAN_NHC_UDP_8BIT_PORT;
+ skb_pull(skb, 3);
+ break;
+ case LOWPAN_NHC_UDP_CS_P_10:
+ uh->source = skb->data[0] + LOWPAN_NHC_UDP_8BIT_PORT;
+ memcpy(&uh->dest, &skb->data[1], 2);
+ skb_pull(skb, 3);
+ break;
+ case LOWPAN_NHC_UDP_CS_P_11:
+ uh->source =
+ LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] >> 4);
+ uh->dest =
+ LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] & 0x0f);
+ skb_pull(skb, 1);
+ break;
+ default:
+ pr_debug("(%s) ERROR: unknown UDP format\n", __func__);
+ goto err;
+ break;
+ }
+
+ pr_debug("(%s): uncompressed UDP ports: src = %d, dst = %d\n",
+ __func__, uh->source, uh->dest);
+
+ /* copy checksum */
+ memcpy(&uh->check, &skb->data[0], 2);
+ skb_pull(skb, 2);
+ } else {
+ pr_debug("(%s): ERROR: unsupported NH format\n", __func__);
+ goto err;
+ }
+
+ return 0;
+err:
+ return -EINVAL;
+}
+
static int lowpan_header_create(struct sk_buff *skb,
struct net_device *dev,
unsigned short type, const void *_daddr,
if (hdr->nexthdr == UIP_PROTO_UDP)
iphc0 |= LOWPAN_IPHC_NH_C;
-/* TODO: next header compression */
-
if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
*hc06_ptr = hdr->nexthdr;
hc06_ptr += 1;
}
}
- /* TODO: UDP header compression */
- /* TODO: Next Header compression */
+ /* UDP header compression */
+ if (hdr->nexthdr == UIP_PROTO_UDP)
+ lowpan_compress_udp_header(&hc06_ptr, skb);
head[0] = iphc0;
head[1] = iphc1;
memcpy(&(sa.hwaddr), saddr, 8);
mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
+
return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
type, (void *)&da, (void *)&sa, skb->len);
}
return stat;
}
+static void lowpan_fragment_timer_expired(unsigned long entry_addr)
+{
+ struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr;
+
+ pr_debug("%s: timer expired for frame with tag %d\n", __func__,
+ entry->tag);
+
+ spin_lock(&flist_lock);
+ list_del(&entry->list);
+ spin_unlock(&flist_lock);
+
+ dev_kfree_skb(entry->skb);
+ kfree(entry);
+}
+
static int
lowpan_process_data(struct sk_buff *skb)
{
if (skb->len < 2)
goto drop;
iphc0 = lowpan_fetch_skb_u8(skb);
+
+ /* fragments assembling */
+ switch (iphc0 & LOWPAN_DISPATCH_MASK) {
+ case LOWPAN_DISPATCH_FRAG1:
+ case LOWPAN_DISPATCH_FRAGN:
+ {
+ struct lowpan_fragment *frame;
+ u8 len, offset;
+ u16 tag;
+ bool found = false;
+
+ len = lowpan_fetch_skb_u8(skb); /* frame length */
+ tag = lowpan_fetch_skb_u16(skb);
+
+ /*
+ * check if frame assembling with the same tag is
+ * already in progress
+ */
+ spin_lock(&flist_lock);
+
+ list_for_each_entry(frame, &lowpan_fragments, list)
+ if (frame->tag == tag) {
+ found = true;
+ break;
+ }
+
+ /* alloc new frame structure */
+ if (!found) {
+ frame = kzalloc(sizeof(struct lowpan_fragment),
+ GFP_ATOMIC);
+ if (!frame)
+ goto unlock_and_drop;
+
+ INIT_LIST_HEAD(&frame->list);
+
+ frame->length = (iphc0 & 7) | (len << 3);
+ frame->tag = tag;
+
+ /* allocate buffer for frame assembling */
+ frame->skb = alloc_skb(frame->length +
+ sizeof(struct ipv6hdr), GFP_ATOMIC);
+
+ if (!frame->skb) {
+ kfree(frame);
+ goto unlock_and_drop;
+ }
+
+ frame->skb->priority = skb->priority;
+ frame->skb->dev = skb->dev;
+
+ /* reserve headroom for uncompressed ipv6 header */
+ skb_reserve(frame->skb, sizeof(struct ipv6hdr));
+ skb_put(frame->skb, frame->length);
+
+ init_timer(&frame->timer);
+ /* time out is the same as for ipv6 - 60 sec */
+ frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT;
+ frame->timer.data = (unsigned long)frame;
+ frame->timer.function = lowpan_fragment_timer_expired;
+
+ add_timer(&frame->timer);
+
+ list_add_tail(&frame->list, &lowpan_fragments);
+ }
+
+ if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1)
+ goto unlock_and_drop;
+
+ offset = lowpan_fetch_skb_u8(skb); /* fetch offset */
+
+ /* if payload fits buffer, copy it */
+ if (likely((offset * 8 + skb->len) <= frame->length))
+ skb_copy_to_linear_data_offset(frame->skb, offset * 8,
+ skb->data, skb->len);
+ else
+ goto unlock_and_drop;
+
+ frame->bytes_rcv += skb->len;
+
+ /* frame assembling complete */
+ if ((frame->bytes_rcv == frame->length) &&
+ frame->timer.expires > jiffies) {
+ /* if timer haven't expired - first of all delete it */
+ del_timer(&frame->timer);
+ list_del(&frame->list);
+ spin_unlock(&flist_lock);
+
+ dev_kfree_skb(skb);
+ skb = frame->skb;
+ kfree(frame);
+ iphc0 = lowpan_fetch_skb_u8(skb);
+ break;
+ }
+ spin_unlock(&flist_lock);
+
+ return kfree_skb(skb), 0;
+ }
+ default:
+ break;
+ }
+
iphc1 = lowpan_fetch_skb_u8(skb);
_saddr = mac_cb(skb)->sa.hwaddr;
goto drop;
}
- /* TODO: UDP header parse */
+ /* UDP data uncompression */
+ if (iphc0 & LOWPAN_IPHC_NH_C)
+ if (lowpan_uncompress_udp_header(skb))
+ goto drop;
/* Not fragmented package */
hdr.payload_len = htons(skb->len);
lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr,
sizeof(hdr));
return lowpan_skb_deliver(skb, &hdr);
+
+unlock_and_drop:
+ spin_unlock(&flist_lock);
drop:
kfree_skb(skb);
return -EINVAL;
return 0;
}
+static int lowpan_get_mac_header_length(struct sk_buff *skb)
+{
+ /*
+ * Currently long addressing mode is supported only, so the overall
+ * header size is 21:
+ * FC SeqNum DPAN DA SA Sec
+ * 2 + 1 + 2 + 8 + 8 + 0 = 21
+ */
+ return 21;
+}
+
+static int
+lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
+ int mlen, int plen, int offset)
+{
+ struct sk_buff *frag;
+ int hlen, ret;
+
+ /* if payload length is zero, therefore it's a first fragment */
+ hlen = (plen == 0 ? LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE);
+
+ lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen);
+
+ frag = dev_alloc_skb(hlen + mlen + plen + IEEE802154_MFR_SIZE);
+ if (!frag)
+ return -ENOMEM;
+
+ frag->priority = skb->priority;
+ frag->dev = skb->dev;
+
+ /* copy header, MFR and payload */
+ memcpy(skb_put(frag, mlen), skb->data, mlen);
+ memcpy(skb_put(frag, hlen), head, hlen);
+
+ if (plen)
+ skb_copy_from_linear_data_offset(skb, offset + mlen,
+ skb_put(frag, plen), plen);
+
+ lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data,
+ frag->len);
+
+ ret = dev_queue_xmit(frag);
+
+ return ret;
+}
+
+static int
+lowpan_skb_fragmentation(struct sk_buff *skb)
+{
+ int err, header_length, payload_length, tag, offset = 0;
+ u8 head[5];
+
+ header_length = lowpan_get_mac_header_length(skb);
+ payload_length = skb->len - header_length;
+ tag = fragment_tag++;
+
+ /* first fragment header */
+ head[0] = LOWPAN_DISPATCH_FRAG1 | (payload_length & 0x7);
+ head[1] = (payload_length >> 3) & 0xff;
+ head[2] = tag & 0xff;
+ head[3] = tag >> 8;
+
+ err = lowpan_fragment_xmit(skb, head, header_length, 0, 0);
+
+ /* next fragment header */
+ head[0] &= ~LOWPAN_DISPATCH_FRAG1;
+ head[0] |= LOWPAN_DISPATCH_FRAGN;
+
+ while ((payload_length - offset > 0) && (err >= 0)) {
+ int len = LOWPAN_FRAG_SIZE;
+
+ head[4] = offset / 8;
+
+ if (payload_length - offset < len)
+ len = payload_length - offset;
+
+ err = lowpan_fragment_xmit(skb, head, header_length,
+ len, offset);
+ offset += len;
+ }
+
+ return err;
+}
+
static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
{
- int err = 0;
+ int err = -1;
pr_debug("(%s): package xmit\n", __func__);
skb->dev = lowpan_dev_info(dev)->real_dev;
if (skb->dev == NULL) {
pr_debug("(%s) ERROR: no real wpan device found\n", __func__);
- dev_kfree_skb(skb);
- } else
+ goto error;
+ }
+
+ if (skb->len <= IEEE802154_MTU) {
err = dev_queue_xmit(skb);
+ goto out;
+ }
+
+ pr_debug("(%s): frame is too big, fragmentation is needed\n",
+ __func__);
+ err = lowpan_skb_fragmentation(skb);
+error:
+ dev_kfree_skb(skb);
+out:
+ if (err < 0)
+ pr_debug("(%s): ERROR: xmit failed\n", __func__);
return (err < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK);
}
dev->addr_len = IEEE802154_ADDR_LEN;
memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
dev->type = ARPHRD_IEEE802154;
- dev->features = NETIF_F_NO_CSUM;
/* Frame Control + Sequence Number + Address fields + Security Header */
dev->hard_header_len = 2 + 1 + 20 + 14;
dev->needed_tailroom = 2; /* FCS */
dev->mtu = 1281;
dev->tx_queue_len = 0;
- dev->flags = IFF_NOARP | IFF_BROADCAST;
+ dev->flags = IFF_BROADCAST | IFF_MULTICAST;
dev->watchdog_timeo = 0;
dev->netdev_ops = &lowpan_netdev_ops;
goto drop;
/* check that it's our buffer */
- if ((skb->data[0] & 0xe0) == 0x60)
+ switch (skb->data[0] & 0xe0) {
+ case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */
+ case LOWPAN_DISPATCH_FRAG1: /* first fragment header */
+ case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */
lowpan_process_data(skb);
+ break;
+ default:
+ break;
+ }
return NET_RX_SUCCESS;
#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */
#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */
+#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */
+
+#define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */
+
+#define LOWPAN_FRAG1_HEAD_SIZE 0x4
+#define LOWPAN_FRAGN_HEAD_SIZE 0x5
+
+/*
+ * According IEEE802.15.4 standard:
+ * - MTU is 127 octets
+ * - maximum MHR size is 37 octets
+ * - MFR size is 2 octets
+ *
+ * so minimal payload size that we may guarantee is:
+ * MTU - MHR - MFR = 88 octets
+ */
+#define LOWPAN_FRAG_SIZE 88
+
/*
* Values of fields within the IPHC encoding first byte
* (C stands for compressed and I for inline)
#define LOWPAN_NHC_UDP_CHECKSUMC 0x04
#define LOWPAN_NHC_UDP_CHECKSUMI 0x00
+#define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0
+#define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0
+#define LOWPAN_NHC_UDP_8BIT_PORT 0xF000
+#define LOWPAN_NHC_UDP_8BIT_MASK 0xFF00
+
/* values for port compression, _with checksum_ ie bit 5 set to 0 */
#define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */
#define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline,
unsigned mtu;
struct sk_buff *skb;
struct dgram_sock *ro = dgram_sk(sk);
+ int hlen, tlen;
int err;
if (msg->msg_flags & MSG_OOB) {
mtu = dev->mtu;
pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
- skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size,
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = sock_alloc_send_skb(sk, hlen + tlen + size,
msg->msg_flags & MSG_DONTWAIT,
&err);
if (!skb)
goto out_dev;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
struct net_device *dev;
unsigned mtu;
struct sk_buff *skb;
+ int hlen, tlen;
int err;
if (msg->msg_flags & MSG_OOB) {
goto out_dev;
}
- skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size,
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = sock_alloc_send_skb(sk, hlen + tlen + size,
msg->msg_flags & MSG_DONTWAIT, &err);
if (!skb)
goto out_dev;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
depends on INET_DIAG
def_tristate INET_DIAG
+config INET_UDP_DIAG
+ depends on INET_DIAG
+ def_tristate INET_DIAG && IPV6
+
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/
obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
+obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
return err;
}
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct iphdr *iph;
sizeof(struct icmp_mib),
__alignof__(struct icmp_mib)) < 0)
goto err_icmp_mib;
- if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
- sizeof(struct icmpmsg_mib),
- __alignof__(struct icmpmsg_mib)) < 0)
+ net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
+ GFP_KERNEL);
+ if (!net->mib.icmpmsg_statistics)
goto err_icmpmsg_mib;
tcp_mib_init(net);
static __net_exit void ipv4_mib_exit_net(struct net *net)
{
- snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
+ kfree(net->mib.icmpmsg_statistics);
snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
snmp_mib_free((void __percpu **)net->mib.udp_statistics);
ip_static_sysctl_init();
#endif
+ tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
/*
* Add all the base protocols.
*/
memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
}
- err = ah->nexthdr;
-
kfree(AH_SKB_CB(skb)->tmp);
xfrm_output_resume(skb, err);
}
if (err)
goto out;
+ err = ah->nexthdr;
+
skb->network_header += ah_hlen;
memcpy(skb_network_header(skb), work_iph, ihl);
__skb_pull(skb, ah_hlen + ihl);
skb_set_transport_header(skb, -ihl);
-
- err = ah->nexthdr;
out:
kfree(AH_SKB_CB(skb)->tmp);
xfrm_input_resume(skb, err);
if (err == -EINPROGRESS)
goto out;
- if (err == -EBUSY)
- err = NET_XMIT_DROP;
goto out_free;
}
#include <net/arp.h>
#include <net/ax25.h>
#include <net/netrom.h>
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
-#include <net/atmclip.h>
-struct neigh_table *clip_tbl_hook;
-EXPORT_SYMBOL(clip_tbl_hook);
-#endif
#include <asm/system.h>
#include <linux/uaccess.h>
/*
* Interface to generic neighbour cache.
*/
-static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 rnd);
+static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd);
static int arp_constructor(struct neighbour *neigh);
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
struct neigh_table arp_tbl = {
.family = AF_INET,
- .entry_size = sizeof(struct neighbour) + 4,
.key_len = 4,
.hash = arp_hash,
.constructor = arp_constructor,
.gc_staletime = 60 * HZ,
.reachable_time = 30 * HZ,
.delay_probe_time = 5 * HZ,
- .queue_len = 3,
+ .queue_len_bytes = 64*1024,
.ucast_probes = 3,
.mcast_probes = 3,
.anycast_delay = 1 * HZ,
static u32 arp_hash(const void *pkey,
const struct net_device *dev,
- __u32 hash_rnd)
+ __u32 *hash_rnd)
{
- return arp_hashfn(*(u32 *)pkey, dev, hash_rnd);
+ return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd);
}
static int arp_constructor(struct neighbour *neigh)
default:
break;
case ARPHRD_ROSE:
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
case ARPHRD_AX25:
-#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE)
+#if IS_ENABLED(CONFIG_NETROM)
case ARPHRD_NETROM:
#endif
neigh->ops = &arp_broken_ops;
struct sk_buff *skb;
struct arphdr *arp;
unsigned char *arp_ptr;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
/*
* Allocate a buffer
*/
- skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC);
if (skb == NULL)
return NULL;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev));
skb->dev = dev;
arp->ar_pro = htons(ETH_P_IP);
break;
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
case ARPHRD_AX25:
arp->ar_hrd = htons(ARPHRD_AX25);
arp->ar_pro = htons(AX25_P_IP);
break;
-#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE)
+#if IS_ENABLED(CONFIG_NETROM)
case ARPHRD_NETROM:
arp->ar_hrd = htons(ARPHRD_NETROM);
arp->ar_pro = htons(AX25_P_IP);
#endif
#endif
-#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
+#if IS_ENABLED(CONFIG_FDDI)
case ARPHRD_FDDI:
arp->ar_hrd = htons(ARPHRD_ETHER);
arp->ar_pro = htons(ETH_P_IP);
break;
#endif
-#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
+#if IS_ENABLED(CONFIG_TR)
case ARPHRD_IEEE802_TR:
arp->ar_hrd = htons(ARPHRD_IEEE802);
arp->ar_pro = htons(ETH_P_IP);
return -EINVAL;
}
switch (dev->type) {
-#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
+#if IS_ENABLED(CONFIG_FDDI)
case ARPHRD_FDDI:
/*
* According to RFC 1390, FDDI devices should accept ARP
}
#ifdef CONFIG_PROC_FS
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
/* ------------------------------------------------------------------------ */
/*
read_lock(&n->lock);
/* Convert hardware address to XX:XX:XX:XX ... form. */
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM)
ax2asc2((ax25_address *)n->ha, hbuffer);
else {
if (k != 0)
--k;
hbuffer[k] = 0;
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
}
#endif
sprintf(tbuf, "%pI4", n->primary_key);
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ int old_value = *(int *)ctl->data;
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
if (write) {
struct ipv4_devconf *cnf = ctl->extra1;
if (cnf == net->ipv4.devconf_dflt)
devinet_copy_dflt_conf(net, i);
+ if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1)
+ if ((new_value == 0) && (old_value != 0))
+ rt_cache_flush(net, 0);
}
return ret;
return err;
}
+EXPORT_SYMBOL_GPL(fib_lookup);
static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
rcu_read_unlock();
return ret;
}
+EXPORT_SYMBOL_GPL(fib_table_lookup);
/*
* Remove the leaf and return parent.
struct igmpv3_report *pig;
struct net *net = dev_net(dev);
struct flowi4 fl4;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
while (1) {
- skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev),
+ skb = alloc_skb(size + hlen + tlen,
GFP_ATOMIC | __GFP_NOWARN);
if (skb)
break;
skb_dst_set(skb, &rt->dst);
skb->dev = dev;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
pip = ip_hdr(skb);
__be32 group = pmc ? pmc->multiaddr : 0;
struct flowi4 fl4;
__be32 dst;
+ int hlen, tlen;
if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
return igmpv3_send_report(in_dev, pmc);
if (IS_ERR(rt))
return -1;
- skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC);
if (skb == NULL) {
ip_rt_put(rt);
return -1;
skb_dst_set(skb, &rt->dst);
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
iph = ip_hdr(skb);
* Add multicast single-source filter to the interface list
*/
static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode,
- __be32 *psfsrc, int delta)
+ __be32 *psfsrc)
{
struct ip_sf_list *psf, *psf_prev;
pmc->sfcount[sfmode]++;
err = 0;
for (i=0; i<sfcount; i++) {
- err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i], delta);
+ err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]);
if (err)
break;
}
if (err) {
int j;
- pmc->sfcount[sfmode]--;
+ if (!delta)
+ pmc->sfcount[sfmode]--;
for (j=0; j<i; j++)
(void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]);
} else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) {
return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define AF_INET_FAMILY(fam) 1
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
-struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
- const gfp_t priority)
+/**
+ * inet_csk_clone_lock - clone an inet socket, and lock its clone
+ * @sk: the socket to clone
+ * @req: request_sock
+ * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ * Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *inet_csk_clone_lock(const struct sock *sk,
+ const struct request_sock *req,
+ const gfp_t priority)
{
- struct sock *newsk = sk_clone(sk, priority);
+ struct sock *newsk = sk_clone_lock(sk, priority);
if (newsk != NULL) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
}
return newsk;
}
-EXPORT_SYMBOL_GPL(inet_csk_clone);
+EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
/*
* At this point, there should be no process reference to this
#include <linux/stddef.h>
#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
static const struct inet_diag_handler **inet_diag_table;
u16 userlocks;
};
-static struct sock *idiagnl;
-
#define INET_DIAG_PUT(skb, attrtype, attrlen) \
RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
static DEFINE_MUTEX(inet_diag_table_mutex);
-static const struct inet_diag_handler *inet_diag_lock_handler(int type)
+static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
{
- if (!inet_diag_table[type])
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_INET_DIAG, type);
+ if (!inet_diag_table[proto])
+ request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, AF_INET, proto);
mutex_lock(&inet_diag_table_mutex);
- if (!inet_diag_table[type])
+ if (!inet_diag_table[proto])
return ERR_PTR(-ENOENT);
- return inet_diag_table[type];
+ return inet_diag_table[proto];
}
static inline void inet_diag_unlock_handler(
mutex_unlock(&inet_diag_table_mutex);
}
-static int inet_csk_diag_fill(struct sock *sk,
- struct sk_buff *skb,
- int ext, u32 pid, u32 seq, u16 nlmsg_flags,
+int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
+ struct sk_buff *skb, struct inet_diag_req *req,
+ u32 pid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
const struct inet_sock *inet = inet_sk(sk);
- const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
void *info = NULL;
struct inet_diag_meminfo *minfo = NULL;
unsigned char *b = skb_tail_pointer(skb);
const struct inet_diag_handler *handler;
+ int ext = req->idiag_ext;
- handler = inet_diag_table[unlh->nlmsg_type];
+ handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(handler == NULL);
nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
if (ext & (1 << (INET_DIAG_MEMINFO - 1)))
minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo));
- if (ext & (1 << (INET_DIAG_INFO - 1)))
- info = INET_DIAG_PUT(skb, INET_DIAG_INFO,
- handler->idiag_info_size);
-
- if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
- const size_t len = strlen(icsk->icsk_ca_ops->name);
-
- strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
- icsk->icsk_ca_ops->name);
- }
-
- if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6))
- RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
-
r->idiag_family = sk->sk_family;
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->id.idiag_if = sk->sk_bound_dev_if;
- r->id.idiag_cookie[0] = (u32)(unsigned long)sk;
- r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+ sock_diag_save_cookie(sk, r->id.idiag_cookie);
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = inet->inet_dport;
r->id.idiag_src[0] = inet->inet_rcv_saddr;
r->id.idiag_dst[0] = inet->inet_daddr;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+ /* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
+ * hence this needs to be included regardless of socket family.
+ */
+ if (ext & (1 << (INET_DIAG_TOS - 1)))
+ RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
+
+#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
const struct ipv6_pinfo *np = inet6_sk(sk);
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
- &np->rcv_saddr);
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
- &np->daddr);
- if (ext & (1 << (INET_DIAG_TOS - 1)))
- RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass);
+ *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
+ *(struct in6_addr *)r->id.idiag_dst = np->daddr;
+ if (ext & (1 << (INET_DIAG_TCLASS - 1)))
+ RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass);
}
#endif
+ r->idiag_uid = sock_i_uid(sk);
+ r->idiag_inode = sock_i_ino(sk);
+
+ if (minfo) {
+ minfo->idiag_rmem = sk_rmem_alloc_get(sk);
+ minfo->idiag_wmem = sk->sk_wmem_queued;
+ minfo->idiag_fmem = sk->sk_forward_alloc;
+ minfo->idiag_tmem = sk_wmem_alloc_get(sk);
+ }
+
+ if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
+ if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
+ goto rtattr_failure;
+
+ if (icsk == NULL) {
+ r->idiag_rqueue = r->idiag_wqueue = 0;
+ goto out;
+ }
+
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
}
#undef EXPIRES_IN_MS
- r->idiag_uid = sock_i_uid(sk);
- r->idiag_inode = sock_i_ino(sk);
+ if (ext & (1 << (INET_DIAG_INFO - 1)))
+ info = INET_DIAG_PUT(skb, INET_DIAG_INFO, sizeof(struct tcp_info));
- if (minfo) {
- minfo->idiag_rmem = sk_rmem_alloc_get(sk);
- minfo->idiag_wmem = sk->sk_wmem_queued;
- minfo->idiag_fmem = sk->sk_forward_alloc;
- minfo->idiag_tmem = sk_wmem_alloc_get(sk);
+ if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
+ const size_t len = strlen(icsk->icsk_ca_ops->name);
+
+ strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
+ icsk->icsk_ca_ops->name);
}
handler->idiag_get_info(sk, r, info);
icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
icsk->icsk_ca_ops->get_info(sk, ext, skb);
+out:
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
nlmsg_trim(skb, b);
return -EMSGSIZE;
}
+EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
+
+static int inet_csk_diag_fill(struct sock *sk,
+ struct sk_buff *skb, struct inet_diag_req *req,
+ u32 pid, u32 seq, u16 nlmsg_flags,
+ const struct nlmsghdr *unlh)
+{
+ return inet_sk_diag_fill(sk, inet_csk(sk),
+ skb, req, pid, seq, nlmsg_flags, unlh);
+}
static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
- struct sk_buff *skb, int ext, u32 pid,
- u32 seq, u16 nlmsg_flags,
+ struct sk_buff *skb, struct inet_diag_req *req,
+ u32 pid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
long tmo;
r->idiag_family = tw->tw_family;
r->idiag_retrans = 0;
r->id.idiag_if = tw->tw_bound_dev_if;
- r->id.idiag_cookie[0] = (u32)(unsigned long)tw;
- r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1);
+ sock_diag_save_cookie(tw, r->id.idiag_cookie);
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == AF_INET6) {
const struct inet6_timewait_sock *tw6 =
inet6_twsk((struct sock *)tw);
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
- &tw6->tw_v6_rcv_saddr);
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
- &tw6->tw_v6_daddr);
+ *(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
+ *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
}
#endif
nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
- int ext, u32 pid, u32 seq, u16 nlmsg_flags,
+ struct inet_diag_req *r, u32 pid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
- skb, ext, pid, seq, nlmsg_flags,
+ skb, r, pid, seq, nlmsg_flags,
unlh);
- return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh);
+ return inet_csk_diag_fill(sk, skb, r, pid, seq, nlmsg_flags, unlh);
}
-static int inet_diag_get_exact(struct sk_buff *in_skb,
- const struct nlmsghdr *nlh)
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh, struct inet_diag_req *req)
{
int err;
struct sock *sk;
- struct inet_diag_req *req = NLMSG_DATA(nlh);
struct sk_buff *rep;
- struct inet_hashinfo *hashinfo;
- const struct inet_diag_handler *handler;
-
- handler = inet_diag_lock_handler(nlh->nlmsg_type);
- if (IS_ERR(handler)) {
- err = PTR_ERR(handler);
- goto unlock;
- }
- hashinfo = handler->idiag_hashinfo;
err = -EINVAL;
-
- if (req->idiag_family == AF_INET) {
+ if (req->sdiag_family == AF_INET) {
sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
}
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
- else if (req->idiag_family == AF_INET6) {
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (req->sdiag_family == AF_INET6) {
sk = inet6_lookup(&init_net, hashinfo,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
}
#endif
else {
- goto unlock;
+ goto out_nosk;
}
err = -ENOENT;
if (sk == NULL)
- goto unlock;
+ goto out_nosk;
- err = -ESTALE;
- if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE ||
- req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) &&
- ((u32)(unsigned long)sk != req->id.idiag_cookie[0] ||
- (u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1]))
+ err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
+ if (err)
goto out;
err = -ENOMEM;
rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
sizeof(struct inet_diag_meminfo) +
- handler->idiag_info_size + 64)),
+ sizeof(struct tcp_info) + 64)),
GFP_KERNEL);
if (!rep)
goto out;
- err = sk_diag_fill(sk, rep, req->idiag_ext,
+ err = sk_diag_fill(sk, rep, req,
NETLINK_CB(in_skb).pid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid,
+ err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
else
sock_put(sk);
}
-unlock:
+out_nosk:
+ return err;
+}
+EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
+
+static int inet_diag_get_exact(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct inet_diag_req *req)
+{
+ const struct inet_diag_handler *handler;
+ int err;
+
+ handler = inet_diag_lock_handler(req->sdiag_protocol);
+ if (IS_ERR(handler))
+ err = PTR_ERR(handler);
+ else
+ err = handler->dump_one(in_skb, nlh, req);
inet_diag_unlock_handler(handler);
+
return err;
}
}
-static int inet_diag_bc_run(const void *bc, int len,
- const struct inet_diag_entry *entry)
+static int inet_diag_bc_run(const struct nlattr *_bc,
+ const struct inet_diag_entry *entry)
{
+ const void *bc = nla_data(_bc);
+ int len = nla_len(_bc);
+
while (len > 0) {
int yes = 1;
const struct inet_diag_bc_op *op = bc;
return len == 0;
}
+int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
+{
+ struct inet_diag_entry entry;
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (bc == NULL)
+ return 1;
+
+ entry.family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (entry.family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ entry.saddr = np->rcv_saddr.s6_addr32;
+ entry.daddr = np->daddr.s6_addr32;
+ } else
+#endif
+ {
+ entry.saddr = &inet->inet_rcv_saddr;
+ entry.daddr = &inet->inet_daddr;
+ }
+ entry.sport = inet->inet_num;
+ entry.dport = ntohs(inet->inet_dport);
+ entry.userlocks = sk->sk_userlocks;
+
+ return inet_diag_bc_run(bc, &entry);
+}
+EXPORT_SYMBOL_GPL(inet_diag_bc_sk);
+
static int valid_cc(const void *bc, int len, int cc)
{
while (len >= 0) {
static int inet_csk_diag_dump(struct sock *sk,
struct sk_buff *skb,
- struct netlink_callback *cb)
+ struct netlink_callback *cb,
+ struct inet_diag_req *r,
+ const struct nlattr *bc)
{
- struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
-
- if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
- struct inet_diag_entry entry;
- const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
- sizeof(*r),
- INET_DIAG_REQ_BYTECODE);
- struct inet_sock *inet = inet_sk(sk);
-
- entry.family = sk->sk_family;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
- if (entry.family == AF_INET6) {
- struct ipv6_pinfo *np = inet6_sk(sk);
-
- entry.saddr = np->rcv_saddr.s6_addr32;
- entry.daddr = np->daddr.s6_addr32;
- } else
-#endif
- {
- entry.saddr = &inet->inet_rcv_saddr;
- entry.daddr = &inet->inet_daddr;
- }
- entry.sport = inet->inet_num;
- entry.dport = ntohs(inet->inet_dport);
- entry.userlocks = sk->sk_userlocks;
+ if (!inet_diag_bc_sk(bc, sk))
+ return 0;
- if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
- return 0;
- }
-
- return inet_csk_diag_fill(sk, skb, r->idiag_ext,
+ return inet_csk_diag_fill(sk, skb, r,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
struct sk_buff *skb,
- struct netlink_callback *cb)
+ struct netlink_callback *cb,
+ struct inet_diag_req *r,
+ const struct nlattr *bc)
{
- struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
-
- if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
+ if (bc != NULL) {
struct inet_diag_entry entry;
- const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
- sizeof(*r),
- INET_DIAG_REQ_BYTECODE);
entry.family = tw->tw_family;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == AF_INET6) {
struct inet6_timewait_sock *tw6 =
inet6_twsk((struct sock *)tw);
entry.dport = ntohs(tw->tw_dport);
entry.userlocks = 0;
- if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
+ if (!inet_diag_bc_run(bc, &entry))
return 0;
}
- return inet_twsk_diag_fill(tw, skb, r->idiag_ext,
+ return inet_twsk_diag_fill(tw, skb, r,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
r->idiag_retrans = req->retrans;
r->id.idiag_if = sk->sk_bound_dev_if;
- r->id.idiag_cookie[0] = (u32)(unsigned long)req;
- r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1);
+ sock_diag_save_cookie(req, r->id.idiag_cookie);
tmo = req->expires - jiffies;
if (tmo < 0)
r->idiag_wqueue = 0;
r->idiag_uid = sock_i_uid(sk);
r->idiag_inode = 0;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
- &inet6_rsk(req)->loc_addr);
- ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
- &inet6_rsk(req)->rmt_addr);
+ *(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr;
+ *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr;
}
#endif
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
}
static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
- struct netlink_callback *cb)
+ struct netlink_callback *cb,
+ struct inet_diag_req *r,
+ const struct nlattr *bc)
{
struct inet_diag_entry entry;
- struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt;
- const struct nlattr *bc = NULL;
struct inet_sock *inet = inet_sk(sk);
int j, s_j;
int reqnum, s_reqnum;
if (!lopt || !lopt->qlen)
goto out;
- if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
- bc = nlmsg_find_attr(cb->nlh, sizeof(*r),
- INET_DIAG_REQ_BYTECODE);
+ if (bc != NULL) {
entry.sport = inet->inet_num;
entry.userlocks = sk->sk_userlocks;
}
if (bc) {
entry.saddr =
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
(entry.family == AF_INET6) ?
inet6_rsk(req)->loc_addr.s6_addr32 :
#endif
&ireq->loc_addr;
entry.daddr =
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
(entry.family == AF_INET6) ?
inet6_rsk(req)->rmt_addr.s6_addr32 :
#endif
&ireq->rmt_addr;
entry.dport = ntohs(ireq->rmt_port);
- if (!inet_diag_bc_run(nla_data(bc),
- nla_len(bc), &entry))
+ if (!inet_diag_bc_run(bc, &entry))
continue;
}
return err;
}
-static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
+ struct netlink_callback *cb, struct inet_diag_req *r, struct nlattr *bc)
{
int i, num;
int s_i, s_num;
- struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
- const struct inet_diag_handler *handler;
- struct inet_hashinfo *hashinfo;
-
- handler = inet_diag_lock_handler(cb->nlh->nlmsg_type);
- if (IS_ERR(handler))
- goto unlock;
-
- hashinfo = handler->idiag_hashinfo;
s_i = cb->args[1];
s_num = num = cb->args[2];
continue;
}
+ if (r->sdiag_family != AF_UNSPEC &&
+ sk->sk_family != r->sdiag_family)
+ goto next_listen;
+
if (r->id.idiag_sport != inet->inet_sport &&
r->id.idiag_sport)
goto next_listen;
cb->args[3] > 0)
goto syn_recv;
- if (inet_csk_diag_dump(sk, skb, cb) < 0) {
+ if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
spin_unlock_bh(&ilb->lock);
goto done;
}
if (!(r->idiag_states & TCPF_SYN_RECV))
goto next_listen;
- if (inet_diag_dump_reqs(skb, sk, cb) < 0) {
+ if (inet_diag_dump_reqs(skb, sk, cb, r, bc) < 0) {
spin_unlock_bh(&ilb->lock);
goto done;
}
}
if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV)))
- goto unlock;
+ goto out;
for (i = s_i; i <= hashinfo->ehash_mask; i++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[i];
goto next_normal;
if (!(r->idiag_states & (1 << sk->sk_state)))
goto next_normal;
+ if (r->sdiag_family != AF_UNSPEC &&
+ sk->sk_family != r->sdiag_family)
+ goto next_normal;
if (r->id.idiag_sport != inet->inet_sport &&
r->id.idiag_sport)
goto next_normal;
if (r->id.idiag_dport != inet->inet_dport &&
r->id.idiag_dport)
goto next_normal;
- if (inet_csk_diag_dump(sk, skb, cb) < 0) {
+ if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
spin_unlock_bh(lock);
goto done;
}
if (num < s_num)
goto next_dying;
+ if (r->sdiag_family != AF_UNSPEC &&
+ tw->tw_family != r->sdiag_family)
+ goto next_dying;
if (r->id.idiag_sport != tw->tw_sport &&
r->id.idiag_sport)
goto next_dying;
if (r->id.idiag_dport != tw->tw_dport &&
r->id.idiag_dport)
goto next_dying;
- if (inet_twsk_diag_dump(tw, skb, cb) < 0) {
+ if (inet_twsk_diag_dump(tw, skb, cb, r, bc) < 0) {
spin_unlock_bh(lock);
goto done;
}
done:
cb->args[1] = i;
cb->args[2] = num;
-unlock:
+out:
+ ;
+}
+EXPORT_SYMBOL_GPL(inet_diag_dump_icsk);
+
+static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ const struct inet_diag_handler *handler;
+
+ handler = inet_diag_lock_handler(r->sdiag_protocol);
+ if (!IS_ERR(handler))
+ handler->dump(skb, cb, r, bc);
inet_diag_unlock_handler(handler);
+
return skb->len;
}
-static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct nlattr *bc = NULL;
int hdrlen = sizeof(struct inet_diag_req);
+ if (nlmsg_attrlen(cb->nlh, hdrlen))
+ bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
+
+ return __inet_diag_dump(skb, cb, (struct inet_diag_req *)NLMSG_DATA(cb->nlh), bc);
+}
+
+static inline int inet_diag_type2proto(int type)
+{
+ switch (type) {
+ case TCPDIAG_GETSOCK:
+ return IPPROTO_TCP;
+ case DCCPDIAG_GETSOCK:
+ return IPPROTO_DCCP;
+ default:
+ return 0;
+ }
+}
+
+static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct inet_diag_req_compat *rc = NLMSG_DATA(cb->nlh);
+ struct inet_diag_req req;
+ struct nlattr *bc = NULL;
+ int hdrlen = sizeof(struct inet_diag_req_compat);
+
+ req.sdiag_family = AF_UNSPEC; /* compatibility */
+ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type);
+ req.idiag_ext = rc->idiag_ext;
+ req.idiag_states = rc->idiag_states;
+ req.id = rc->id;
+
+ if (nlmsg_attrlen(cb->nlh, hdrlen))
+ bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
+
+ return __inet_diag_dump(skb, cb, &req, bc);
+}
+
+static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh)
+{
+ struct inet_diag_req_compat *rc = NLMSG_DATA(nlh);
+ struct inet_diag_req req;
+
+ req.sdiag_family = rc->idiag_family;
+ req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type);
+ req.idiag_ext = rc->idiag_ext;
+ req.idiag_states = rc->idiag_states;
+ req.id = rc->id;
+
+ return inet_diag_get_exact(in_skb, nlh, &req);
+}
+
+static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+ int hdrlen = sizeof(struct inet_diag_req_compat);
+
if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
nlmsg_len(nlh) < hdrlen)
return -EINVAL;
return -EINVAL;
}
- return netlink_dump_start(idiagnl, skb, nlh,
- inet_diag_dump, NULL, 0);
+ return netlink_dump_start(sock_diag_nlsk, skb, nlh,
+ inet_diag_dump_compat, NULL, 0);
}
- return inet_diag_get_exact(skb, nlh);
+ return inet_diag_get_exact_compat(skb, nlh);
}
-static DEFINE_MUTEX(inet_diag_mutex);
-
-static void inet_diag_rcv(struct sk_buff *skb)
+static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
{
- mutex_lock(&inet_diag_mutex);
- netlink_rcv_skb(skb, &inet_diag_rcv_msg);
- mutex_unlock(&inet_diag_mutex);
+ int hdrlen = sizeof(struct inet_diag_req);
+
+ if (nlmsg_len(h) < hdrlen)
+ return -EINVAL;
+
+ if (h->nlmsg_flags & NLM_F_DUMP) {
+ if (nlmsg_attrlen(h, hdrlen)) {
+ struct nlattr *attr;
+ attr = nlmsg_find_attr(h, hdrlen,
+ INET_DIAG_REQ_BYTECODE);
+ if (attr == NULL ||
+ nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
+ inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
+ return -EINVAL;
+ }
+
+ return netlink_dump_start(sock_diag_nlsk, skb, h,
+ inet_diag_dump, NULL, 0);
+ }
+
+ return inet_diag_get_exact(skb, h, (struct inet_diag_req *)NLMSG_DATA(h));
}
+static struct sock_diag_handler inet_diag_handler = {
+ .family = AF_INET,
+ .dump = inet_diag_handler_dump,
+};
+
+static struct sock_diag_handler inet6_diag_handler = {
+ .family = AF_INET6,
+ .dump = inet_diag_handler_dump,
+};
+
int inet_diag_register(const struct inet_diag_handler *h)
{
const __u16 type = h->idiag_type;
int err = -EINVAL;
- if (type >= INET_DIAG_GETSOCK_MAX)
+ if (type >= IPPROTO_MAX)
goto out;
mutex_lock(&inet_diag_table_mutex);
{
const __u16 type = h->idiag_type;
- if (type >= INET_DIAG_GETSOCK_MAX)
+ if (type >= IPPROTO_MAX)
return;
mutex_lock(&inet_diag_table_mutex);
static int __init inet_diag_init(void)
{
- const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX *
+ const int inet_diag_table_size = (IPPROTO_MAX *
sizeof(struct inet_diag_handler *));
int err = -ENOMEM;
if (!inet_diag_table)
goto out;
- idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0,
- inet_diag_rcv, NULL, THIS_MODULE);
- if (idiagnl == NULL)
- goto out_free_table;
- err = 0;
+ err = sock_diag_register(&inet_diag_handler);
+ if (err)
+ goto out_free_nl;
+
+ err = sock_diag_register(&inet6_diag_handler);
+ if (err)
+ goto out_free_inet;
+
+ sock_diag_register_inet_compat(inet_diag_rcv_msg_compat);
out:
return err;
-out_free_table:
+
+out_free_inet:
+ sock_diag_unregister(&inet_diag_handler);
+out_free_nl:
kfree(inet_diag_table);
goto out;
}
static void __exit inet_diag_exit(void)
{
- netlink_kernel_release(idiagnl);
+ sock_diag_unregister(&inet6_diag_handler);
+ sock_diag_unregister(&inet_diag_handler);
+ sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat);
kfree(inet_diag_table);
}
module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);
rt = skb_rtable(skb);
- if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway)
+ if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
#include <net/rtnetlink.h>
#include <net/gre.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ipgre_get_stats(struct net_device *dev)
{
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct neighbour *neigh = dst_get_neighbour(skb_dst(skb));
+ struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb));
const struct in6_addr *addr6;
int addr_type;
goto tx_error;
}
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+ if (max_headroom > dev->needed_headroom)
+ dev->needed_headroom = max_headroom;
if (!new_skb) {
ip_rt_put(rt);
dev->stats.tx_dropped++;
if ((iph->ttl = tiph->ttl) == 0) {
if (skb->protocol == htons(ETH_P_IP))
iph->ttl = old_iph->ttl;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
#endif
) {
if (srrptr + 3 > srrspace)
break;
- if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0)
+ if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
break;
}
if (srrptr + 3 <= srrspace) {
opt->is_changed = 1;
ip_rt_get_source(&optptr[srrptr-1], skb, rt);
+ ip_hdr(skb)->daddr = opt->nexthop;
optptr[2] = srrptr+4;
} else if (net_ratelimit())
printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n");
}
if (srrptr <= srrspace) {
opt->srr_is_hit = 1;
+ opt->nexthop = nexthop;
opt->is_changed = 1;
}
return 0;
}
rcu_read_lock();
- neigh = dst_get_neighbour(dst);
+ neigh = dst_get_neighbour_noref(dst);
if (neigh) {
int res = neigh_output(neigh, skb);
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
+/*
+ * copy saddr and daddr, possibly using 64bit load/stores
+ * Equivalent to :
+ * iph->saddr = fl4->saddr;
+ * iph->daddr = fl4->daddr;
+ */
+static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
+{
+ BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
+ offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
+ memcpy(&iph->saddr, &fl4->saddr,
+ sizeof(fl4->saddr) + sizeof(fl4->daddr));
+}
+
int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
{
struct sock *sk = skb->sk;
iph->frag_off = 0;
iph->ttl = ip_select_ttl(inet, &rt->dst);
iph->protocol = sk->sk_protocol;
- iph->saddr = fl4->saddr;
- iph->daddr = fl4->daddr;
+ ip_copy_addrs(iph, fl4);
+
/* Transport layer set skb->h.foo itself. */
if (inet_opt && inet_opt->opt.optlen) {
ip_select_ident(iph, &rt->dst, sk);
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
- iph->saddr = fl4->saddr;
- iph->daddr = fl4->daddr;
+ ip_copy_addrs(iph, fl4);
if (opt) {
iph->ihl += opt->optlen>>2;
#include <net/route.h>
#include <net/xfrm.h>
#include <net/compat.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <net/transp_v6.h>
#endif
/*
* SOL_IP control messages.
*/
+#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb))
static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
- struct in_pktinfo info;
- struct rtable *rt = skb_rtable(skb);
+ struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
- if (rt) {
- info.ipi_ifindex = rt->rt_iif;
- info.ipi_spec_dst.s_addr = rt->rt_spec_dst;
- } else {
- info.ipi_ifindex = 0;
- info.ipi_spec_dst.s_addr = 0;
- }
put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
sock_owned_by_user(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
}
#endif
}
}
/**
- * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * ipv4_pktinfo_prepare - transfert some info from rtable to skb
* @sk: socket
* @skb: buffer
*
- * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
- * is not set, we drop skb dst entry now, while dst cache line is hot.
+ * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst
+ * in skb->cb[] before dst drop.
+ * This way, receiver doesnt make cache line misses to read rtable.
*/
-int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(struct sk_buff *skb)
{
- if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
- skb_dst_drop(skb);
- return sock_queue_rcv_skb(sk, skb);
+ struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+ const struct rtable *rt = skb_rtable(skb);
+
+ if (rt) {
+ pktinfo->ipi_ifindex = rt->rt_iif;
+ pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst;
+ } else {
+ pktinfo->ipi_ifindex = 0;
+ pktinfo->ipi_spec_dst.s_addr = 0;
+ }
+ skb_dst_drop(skb);
}
-EXPORT_SYMBOL(ip_queue_rcv_skb);
int ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
}
}
+ /* no point in waiting if we could not bring up at least one device */
+ if (!ic_first_dev)
+ goto have_carrier;
+
/* wait for a carrier on at least one device */
start = jiffies;
while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) {
struct sk_buff *skb;
struct bootp_pkt *b;
struct iphdr *h;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
/* Allocate packet */
- skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15,
+ skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15,
GFP_KERNEL);
if (!skb)
return;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt));
memset(b, 0, sizeof(struct bootp_pkt));
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
if (dev_hard_header(skb, dev, ntohs(skb->protocol),
- dev->broadcast, dev->dev_addr, skb->len) < 0 ||
- dev_queue_xmit(skb) < 0)
+ dev->broadcast, dev->dev_addr, skb->len) < 0) {
+ kfree_skb(skb);
+ printk("E");
+ return;
+ }
+
+ if (dev_queue_xmit(skb) < 0)
printk("E");
}
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ipip_get_stats(struct net_device *dev)
{
if (register_netdevice(dev) < 0)
goto failed_free;
+ strcpy(nt->parms.name, dev->name);
+
dev_hold(dev);
ipip_tunnel_link(ipn, nt);
return nt;
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
static int __net_init ipip_init_net(struct net *net)
{
struct ipip_net *ipn = net_generic(net, ipip_net_id);
+ struct ip_tunnel *t;
int err;
ipn->tunnels[0] = ipn->tunnels_wc;
if ((err = register_netdev(ipn->fb_tunnel_dev)))
goto err_reg_dev;
+ t = netdev_priv(ipn->fb_tunnel_dev);
+
+ strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
struct mr_table *mrt;
struct vif_device *v;
int ct;
- LIST_HEAD(list);
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
v = &mrt->vif_table[0];
for (ct = 0; ct < mrt->maxvif; ct++, v++) {
if (v->dev == dev)
- vif_delete(mrt, ct, 1, &list);
+ vif_delete(mrt, ct, 1, NULL);
}
}
- unregister_netdevice_many(&list);
return NOTIFY_DONE;
}
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
- pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
+ pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
+ 0, GFP_ATOMIC))
return -1;
return 0;
config NF_CONNTRACK_PROC_COMPAT
bool "proc/sysctl compatibility with old connection tracking"
- depends on NF_CONNTRACK_IPV4
+ depends on NF_CONNTRACK_PROCFS && NF_CONNTRACK_IPV4
default y
help
This option enables /proc and sysctl compatibility with the old
config IP_NF_MATCH_ECN
tristate '"ecn" match support'
depends on NETFILTER_ADVANCED
- help
- This option adds a `ECN' match, which allows you to match against
- the IPv4 and TCP header ECN fields.
+ select NETFILTER_XT_MATCH_ECN
+ ---help---
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects
+ CONFIG_NETFILTER_XT_MATCH_ECN.
+
+config IP_NF_MATCH_RPFILTER
+ tristate '"rpfilter" reverse path filter match support'
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option allows you to match packets whose replies would
+ go out via the interface the packet came in.
To compile it as a module, choose M here. If unsure, say N.
+ The module will be called ipt_rpfilter.
config IP_NF_MATCH_TTL
tristate '"ttl" match support'
# raw + specific targets
config IP_NF_RAW
tristate 'raw table support (required for NOTRACK/TRACE)'
- depends on NETFILTER_ADVANCED
help
This option adds a `raw' table to iptables. This table is the very
first in the netfilter framework and hooks in at the PREROUTING
# matches
obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o
-obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o
+obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
int status, type, pid, flags;
unsigned int nlmsglen, skblen;
struct nlmsghdr *nlh;
+ bool enable_timestamp = false;
skblen = skb->len;
if (skblen < sizeof(*nlh))
RCV_SKB_FAIL(-EBUSY);
}
} else {
- net_enable_timestamp();
+ enable_timestamp = true;
peer_pid = pid;
}
spin_unlock_bh(&queue_lock);
-
+ if (enable_timestamp)
+ net_enable_timestamp();
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
if (status < 0)
/* FIXME: Multiple targets. --RR */
static int masquerade_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) {
+ if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
struct nf_conn *ct;
struct nf_conn_nat *nat;
enum ip_conntrack_info ctinfo;
- struct nf_nat_range newrange;
- const struct nf_nat_multi_range_compat *mr;
+ struct nf_nat_ipv4_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr;
const struct rtable *rt;
__be32 newsrc;
nat->masq_index = par->out->ifindex;
/* Transfer from original range. */
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
newsrc, newsrc,
mr->range[0].min, mr->range[0].max });
/* Hand modified range to generic setup. */
- return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_SRC);
+ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
}
static int
.name = "MASQUERADE",
.family = NFPROTO_IPV4,
.target = masquerade_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = 1 << NF_INET_POST_ROUTING,
.checkentry = masquerade_tg_check,
static int netmap_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) {
+ if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
__be32 new_ip, netmask;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
+ struct nf_nat_ipv4_range newrange;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_POST_ROUTING ||
new_ip = ip_hdr(skb)->saddr & ~netmask;
new_ip |= mr->range[0].min_ip & netmask;
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
new_ip, new_ip,
mr->range[0].min, mr->range[0].max });
.name = "NETMAP",
.family = NFPROTO_IPV4,
.target = netmap_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
/* FIXME: Take multiple ranges --RR */
static int redirect_tg_check(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) {
+ if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) {
pr_debug("bad MAP_IPS.\n");
return -EINVAL;
}
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
__be32 newdst;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range newrange;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
+ struct nf_nat_ipv4_range newrange;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_OUT);
}
/* Transfer from original range. */
- newrange = ((struct nf_nat_range)
- { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS,
+ newrange = ((struct nf_nat_ipv4_range)
+ { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
newdst, newdst,
mr->range[0].min, mr->range[0].max });
/* Hand modified range to generic setup. */
- return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_DST);
+ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
}
static struct xt_target redirect_tg_reg __read_mostly = {
.name = "REDIRECT",
.family = NFPROTO_IPV4,
.target = redirect_tg,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
.checkentry = redirect_tg_check,
module_param(flushtimeout, uint, 0600);
MODULE_PARM_DESC(flushtimeout, "buffer flush timeout (hundredths of a second)");
-static int nflog = 1;
+static bool nflog = true;
module_param(nflog, bool, 0400);
MODULE_PARM_DESC(nflog, "register as internal netfilter logging module");
+++ /dev/null
-/* IP tables module for matching the value of the IPv4 and TCP ECN bits
- *
- * (C) 2002 by Harald Welte <laforge@gnumonks.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <net/ip.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/tcp.h>
-
-#include <linux/netfilter/x_tables.h>
-#include <linux/netfilter_ipv4/ip_tables.h>
-#include <linux/netfilter_ipv4/ipt_ecn.h>
-
-MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
-MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag match for IPv4");
-MODULE_LICENSE("GPL");
-
-static inline bool match_ip(const struct sk_buff *skb,
- const struct ipt_ecn_info *einfo)
-{
- return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^
- !!(einfo->invert & IPT_ECN_OP_MATCH_IP);
-}
-
-static inline bool match_tcp(const struct sk_buff *skb,
- const struct ipt_ecn_info *einfo,
- bool *hotdrop)
-{
- struct tcphdr _tcph;
- const struct tcphdr *th;
-
- /* In practice, TCP match does this, so can't fail. But let's
- * be good citizens.
- */
- th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph);
- if (th == NULL) {
- *hotdrop = false;
- return false;
- }
-
- if (einfo->operation & IPT_ECN_OP_MATCH_ECE) {
- if (einfo->invert & IPT_ECN_OP_MATCH_ECE) {
- if (th->ece == 1)
- return false;
- } else {
- if (th->ece == 0)
- return false;
- }
- }
-
- if (einfo->operation & IPT_ECN_OP_MATCH_CWR) {
- if (einfo->invert & IPT_ECN_OP_MATCH_CWR) {
- if (th->cwr == 1)
- return false;
- } else {
- if (th->cwr == 0)
- return false;
- }
- }
-
- return true;
-}
-
-static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par)
-{
- const struct ipt_ecn_info *info = par->matchinfo;
-
- if (info->operation & IPT_ECN_OP_MATCH_IP)
- if (!match_ip(skb, info))
- return false;
-
- if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) {
- if (!match_tcp(skb, info, &par->hotdrop))
- return false;
- }
-
- return true;
-}
-
-static int ecn_mt_check(const struct xt_mtchk_param *par)
-{
- const struct ipt_ecn_info *info = par->matchinfo;
- const struct ipt_ip *ip = par->entryinfo;
-
- if (info->operation & IPT_ECN_OP_MATCH_MASK)
- return -EINVAL;
-
- if (info->invert & IPT_ECN_OP_MATCH_MASK)
- return -EINVAL;
-
- if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) &&
- (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) {
- pr_info("cannot match TCP bits in rule for non-tcp packets\n");
- return -EINVAL;
- }
-
- return 0;
-}
-
-static struct xt_match ecn_mt_reg __read_mostly = {
- .name = "ecn",
- .family = NFPROTO_IPV4,
- .match = ecn_mt,
- .matchsize = sizeof(struct ipt_ecn_info),
- .checkentry = ecn_mt_check,
- .me = THIS_MODULE,
-};
-
-static int __init ecn_mt_init(void)
-{
- return xt_register_match(&ecn_mt_reg);
-}
-
-static void __exit ecn_mt_exit(void)
-{
- xt_unregister_match(&ecn_mt_reg);
-}
-
-module_init(ecn_mt_init);
-module_exit(ecn_mt_exit);
--- /dev/null
+/*
+ * Copyright (c) 2011 Florian Westphal <fw@strlen.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * based on fib_frontend.c; Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <net/ip_fib.h>
+#include <net/route.h>
+
+#include <linux/netfilter/xt_rpfilter.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("iptables: ipv4 reverse path filter match");
+
+/* don't try to find route from mcast/bcast/zeronet */
+static __be32 rpfilter_get_saddr(__be32 addr)
+{
+ if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) ||
+ ipv4_is_zeronet(addr))
+ return 0;
+ return addr;
+}
+
+static bool rpfilter_lookup_reverse(struct flowi4 *fl4,
+ const struct net_device *dev, u8 flags)
+{
+ struct fib_result res;
+ bool dev_match;
+ struct net *net = dev_net(dev);
+ int ret __maybe_unused;
+
+ if (fib_lookup(net, fl4, &res))
+ return false;
+
+ if (res.type != RTN_UNICAST) {
+ if (res.type != RTN_LOCAL || !(flags & XT_RPFILTER_ACCEPT_LOCAL))
+ return false;
+ }
+ dev_match = false;
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ for (ret = 0; ret < res.fi->fib_nhs; ret++) {
+ struct fib_nh *nh = &res.fi->fib_nh[ret];
+
+ if (nh->nh_dev == dev) {
+ dev_match = true;
+ break;
+ }
+ }
+#else
+ if (FIB_RES_DEV(res) == dev)
+ dev_match = true;
+#endif
+ if (dev_match || flags & XT_RPFILTER_LOOSE)
+ return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST;
+ return dev_match;
+}
+
+static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_rpfilter_info *info;
+ const struct iphdr *iph;
+ struct flowi4 flow;
+ bool invert;
+
+ info = par->matchinfo;
+ invert = info->flags & XT_RPFILTER_INVERT;
+
+ if (par->in->flags & IFF_LOOPBACK)
+ return true ^ invert;
+
+ iph = ip_hdr(skb);
+ if (ipv4_is_multicast(iph->daddr)) {
+ if (ipv4_is_zeronet(iph->saddr))
+ return ipv4_is_local_multicast(iph->daddr) ^ invert;
+ flow.flowi4_iif = 0;
+ } else {
+ flow.flowi4_iif = dev_net(par->in)->loopback_dev->ifindex;
+ }
+
+ flow.daddr = iph->saddr;
+ flow.saddr = rpfilter_get_saddr(iph->daddr);
+ flow.flowi4_oif = 0;
+ flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
+ flow.flowi4_tos = RT_TOS(iph->tos);
+ flow.flowi4_scope = RT_SCOPE_UNIVERSE;
+
+ return rpfilter_lookup_reverse(&flow, par->in, info->flags) ^ invert;
+}
+
+static int rpfilter_check(const struct xt_mtchk_param *par)
+{
+ const struct xt_rpfilter_info *info = par->matchinfo;
+ unsigned int options = ~XT_RPFILTER_OPTION_MASK;
+ if (info->flags & options) {
+ pr_info("unknown options encountered");
+ return -EINVAL;
+ }
+
+ if (strcmp(par->table, "mangle") != 0 &&
+ strcmp(par->table, "raw") != 0) {
+ pr_info("match only valid in the \'raw\' "
+ "or \'mangle\' tables, not \'%s\'.\n", par->table);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match rpfilter_mt_reg __read_mostly = {
+ .name = "rpfilter",
+ .family = NFPROTO_IPV4,
+ .checkentry = rpfilter_check,
+ .match = rpfilter_mt,
+ .matchsize = sizeof(struct xt_rpfilter_info),
+ .hooks = (1 << NF_INET_PRE_ROUTING),
+ .me = THIS_MODULE
+};
+
+static int __init rpfilter_mt_init(void)
+{
+ return xt_register_match(&rpfilter_mt_reg);
+}
+
+static void __exit rpfilter_mt_exit(void)
+{
+ xt_unregister_match(&rpfilter_mt_reg);
+}
+
+module_init(rpfilter_mt_init);
+module_exit(rpfilter_mt_exit);
static struct nf_hook_ops *filter_ops __read_mostly;
/* Default to forward because I got too much mail already. */
-static int forward = NF_ACCEPT;
+static bool forward = NF_ACCEPT;
module_param(forward, bool, 0000);
static int __net_init iptable_filter_net_init(struct net *net)
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_zones.h>
static DEFINE_SPINLOCK(nf_nat_lock);
/* Original src, to ensure we map it consistently if poss. */
hash = jhash_3words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->src.u.all ^ zone,
- tuple->dst.protonum, 0);
+ tuple->dst.protonum, nf_conntrack_hash_rnd);
return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
}
* that meet the constraints of range. */
static int
in_range(const struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range)
+ const struct nf_nat_ipv4_range *range)
{
const struct nf_nat_protocol *proto;
int ret = 0;
/* If we are supposed to map IPs, then we must be in the
range specified, otherwise let this drag us onto a new src IP. */
- if (range->flags & IP_NAT_RANGE_MAP_IPS) {
+ if (range->flags & NF_NAT_RANGE_MAP_IPS) {
if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) ||
ntohl(tuple->src.u3.ip) > ntohl(range->max_ip))
return 0;
rcu_read_lock();
proto = __nf_nat_proto_find(tuple->dst.protonum);
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
- proto->in_range(tuple, IP_NAT_MANIP_SRC,
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
+ proto->in_range(tuple, NF_NAT_MANIP_SRC,
&range->min, &range->max))
ret = 1;
rcu_read_unlock();
find_appropriate_src(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
- const struct nf_nat_range *range)
+ const struct nf_nat_ipv4_range *range)
{
unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn_nat *nat;
*/
static void
find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
u_int32_t minip, maxip, j;
/* No IP mapping? Do nothing. */
- if (!(range->flags & IP_NAT_RANGE_MAP_IPS))
+ if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
return;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
var_ipp = &tuple->src.u3.ip;
else
var_ipp = &tuple->dst.u3.ip;
minip = ntohl(range->min_ip);
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
- range->flags & IP_NAT_RANGE_PERSISTENT ?
+ range->flags & NF_NAT_RANGE_PERSISTENT ?
0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
j = ((u64)j * (maxip - minip + 1)) >> 32;
*var_ipp = htonl(minip + j);
static void
get_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_tuple *orig_tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
This is only required for source (ie. NAT/masq) mappings.
So far, we don't do local source mappings, so multiple
manips not an issue. */
- if (maniptype == IP_NAT_MANIP_SRC &&
- !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
+ if (maniptype == NF_NAT_MANIP_SRC &&
+ !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
/* try the original tuple first */
if (in_range(orig_tuple, range)) {
if (!nf_nat_used_tuple(orig_tuple, ct)) {
proto = __nf_nat_proto_find(orig_tuple->dst.protonum);
/* Only bother mapping if it's not already in range and unique */
- if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
- if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+ if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
if (proto->in_range(tuple, maniptype, &range->min,
&range->max) &&
(range->min.all == range->max.all ||
unsigned int
nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype)
{
struct net *net = nf_ct_net(ct);
}
}
- NF_CT_ASSERT(maniptype == IP_NAT_MANIP_SRC ||
- maniptype == IP_NAT_MANIP_DST);
+ NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
+ maniptype == NF_NAT_MANIP_DST);
BUG_ON(nf_nat_initialized(ct, maniptype));
/* What we've got will look like inverse of reply. Normally
nf_conntrack_alter_reply(ct, &reply);
/* Non-atomic: we own this at the moment. */
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
ct->status |= IPS_SRC_NAT;
else
ct->status |= IPS_DST_NAT;
}
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
unsigned int srchash;
srchash = hash_by_src(net, nf_ct_zone(ct),
}
/* It's done. */
- if (maniptype == IP_NAT_MANIP_DST)
+ if (maniptype == NF_NAT_MANIP_DST)
ct->status |= IPS_DST_NAT_DONE;
else
ct->status |= IPS_SRC_NAT_DONE;
iph = (void *)skb->data + iphdroff;
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
iph->saddr = target->src.u3.ip;
} else {
unsigned long statusbit;
enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum);
- if (mtype == IP_NAT_MANIP_SRC)
+ if (mtype == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
struct icmphdr icmp;
struct iphdr ip;
} *inside;
- const struct nf_conntrack_l4proto *l4proto;
- struct nf_conntrack_tuple inner, target;
+ struct nf_conntrack_tuple target;
int hdrlen = ip_hdrlen(skb);
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
unsigned long statusbit;
return 0;
}
- if (manip == IP_NAT_MANIP_SRC)
+ if (manip == NF_NAT_MANIP_SRC)
statusbit = IPS_SRC_NAT;
else
statusbit = IPS_DST_NAT;
"dir %s\n", skb, manip,
dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY");
- /* rcu_read_lock()ed by nf_hook_slow */
- l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol);
-
- if (!nf_ct_get_tuple(skb, hdrlen + sizeof(struct icmphdr),
- (hdrlen +
- sizeof(struct icmphdr) + inside->ip.ihl * 4),
- (u_int16_t)AF_INET, inside->ip.protocol,
- &inner, l3proto, l4proto))
- return 0;
-
/* Change inner back to look like incoming packet. We do the
opposite manip on this hook to normal, because it might not
pass all hooks (locally-generated ICMP). Consider incoming
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
-static const struct nf_nat_protocol *
-nf_nat_proto_find_get(u_int8_t protonum)
-{
- const struct nf_nat_protocol *p;
-
- rcu_read_lock();
- p = __nf_nat_proto_find(protonum);
- if (!try_module_get(p->me))
- p = &nf_nat_unknown_protocol;
- rcu_read_unlock();
-
- return p;
-}
-
-static void
-nf_nat_proto_put(const struct nf_nat_protocol *p)
-{
- module_put(p->me);
-}
-
static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
[CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 },
[CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 },
static int nfnetlink_parse_nat_proto(struct nlattr *attr,
const struct nf_conn *ct,
- struct nf_nat_range *range)
+ struct nf_nat_ipv4_range *range)
{
struct nlattr *tb[CTA_PROTONAT_MAX+1];
const struct nf_nat_protocol *npt;
if (err < 0)
return err;
- npt = nf_nat_proto_find_get(nf_ct_protonum(ct));
+ rcu_read_lock();
+ npt = __nf_nat_proto_find(nf_ct_protonum(ct));
if (npt->nlattr_to_range)
err = npt->nlattr_to_range(tb, range);
- nf_nat_proto_put(npt);
+ rcu_read_unlock();
return err;
}
static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
[CTA_NAT_MINIP] = { .type = NLA_U32 },
[CTA_NAT_MAXIP] = { .type = NLA_U32 },
+ [CTA_NAT_PROTO] = { .type = NLA_NESTED },
};
static int
nfnetlink_parse_nat(const struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range)
+ const struct nf_conn *ct, struct nf_nat_ipv4_range *range)
{
struct nlattr *tb[CTA_NAT_MAX+1];
int err;
range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]);
if (range->min_ip)
- range->flags |= IP_NAT_RANGE_MAP_IPS;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
if (!tb[CTA_NAT_PROTO])
return 0;
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
if (nfnetlink_parse_nat(attr, ct, &range) < 0)
return -EINVAL;
static void ip_nat_q931_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */
nf_nat_follow_master(new, this);
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = this->saved_proto;
range.min_ip = range.max_ip =
new->master->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
static void ip_nat_callforwarding_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(new->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = this->saved_proto;
range.min_ip = range.max_ip = this->saved_ip;
- nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST);
}
/****************************************************************************/
struct udphdr *udph;
int datalen, oldlen;
- /* UDP helpers might accidentally mangle the wrong packet */
- iph = ip_hdr(skb);
- if (skb->len < iph->ihl*4 + sizeof(*udph) +
- match_offset + match_len)
- return 0;
-
if (!skb_make_writable(skb, skb->len))
return 0;
void nf_nat_follow_master(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = exp->saved_proto;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.src.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
}
EXPORT_SYMBOL(nf_nat_follow_master);
struct nf_conntrack_tuple t;
const struct nf_ct_pptp_master *ct_pptp_info;
const struct nf_nat_pptp *nat_pptp_info;
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
ct_pptp_info = &nfct_help(master)->help.ct_pptp_info;
nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info;
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* Change src to where master sends to */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
if (exp->dir == IP_CT_DIR_ORIGINAL) {
- range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min = range.max = exp->saved_proto;
}
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
/* For DST manip, map port here to where it's expected. */
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.src.u3.ip;
if (exp->dir == IP_CT_DIR_REPLY) {
- range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range.min = range.max = exp->saved_proto;
}
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
}
/* outbound packets == from PNS to PAC */
{
__be16 port;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
port = tuple->src.u.all;
else
port = tuple->dst.u.all;
EXPORT_SYMBOL_GPL(nf_nat_proto_in_range);
void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u_int16_t *rover)
__be16 *portptr;
u_int16_t off;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
portptr = &tuple->src.u.all;
else
portptr = &tuple->dst.u.all;
/* If no range specified... */
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
/* If it's dst rewrite, can't change port */
- if (maniptype == IP_NAT_MANIP_DST)
+ if (maniptype == NF_NAT_MANIP_DST)
return;
if (ntohs(*portptr) < 1024) {
range_size = ntohs(range->max.all) - min + 1;
}
- if (range->flags & IP_NAT_RANGE_PROTO_RANDOM)
+ if (range->flags & NF_NAT_RANGE_PROTO_RANDOM)
off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip,
- maniptype == IP_NAT_MANIP_SRC
+ maniptype == NF_NAT_MANIP_SRC
? tuple->dst.u.all
: tuple->src.u.all);
else
*portptr = htons(min + off % range_size);
if (++i != range_size && nf_nat_used_tuple(tuple, ct))
continue;
- if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM))
+ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM))
*rover = off;
return;
}
EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple);
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
-int nf_nat_proto_range_to_nlattr(struct sk_buff *skb,
- const struct nf_nat_range *range)
-{
- NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MIN, range->min.all);
- NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MAX, range->max.all);
- return 0;
-
-nla_put_failure:
- return -1;
-}
-EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range);
-
int nf_nat_proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range)
+ struct nf_nat_ipv4_range *range)
{
if (tb[CTA_PROTONAT_PORT_MIN]) {
range->min.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
range->max.all = range->min.tcp.port;
- range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
if (tb[CTA_PROTONAT_PORT_MAX]) {
range->max.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]);
- range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
return 0;
}
-EXPORT_SYMBOL_GPL(nf_nat_proto_range_to_nlattr);
+EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range);
#endif
static void
dccp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct dccp_hdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.dccp.port;
static const struct nf_nat_protocol nf_nat_protocol_dccp = {
.protonum = IPPROTO_DCCP,
- .me = THIS_MODULE,
.manip_pkt = dccp_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = dccp_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
/* generate unique tuple ... */
static void
gre_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
if (!ct->master)
return;
- if (maniptype == IP_NAT_MANIP_SRC)
+ if (maniptype == NF_NAT_MANIP_SRC)
keyptr = &tuple->src.u.gre.key;
else
keyptr = &tuple->dst.u.gre.key;
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
pr_debug("%p: NATing GRE PPTP\n", ct);
min = 1;
range_size = 0xffff;
/* we only have destination manip of a packet, since 'source key'
* is not present in the packet itself */
- if (maniptype != IP_NAT_MANIP_DST)
+ if (maniptype != NF_NAT_MANIP_DST)
return true;
switch (greh->version) {
case GRE_VERSION_1701:
static const struct nf_nat_protocol gre = {
.protonum = IPPROTO_GRE,
- .me = THIS_MODULE,
.manip_pkt = gre_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = gre_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
static void
icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1;
/* If no range specified... */
- if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED))
+ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
range_size = 0xFFFF;
for (i = 0; ; ++id) {
const struct nf_nat_protocol nf_nat_protocol_icmp = {
.protonum = IPPROTO_ICMP,
- .me = THIS_MODULE,
.manip_pkt = icmp_manip_pkt,
.in_range = icmp_in_range,
.unique_tuple = icmp_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
static void
sctp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct sctphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
static const struct nf_nat_protocol nf_nat_protocol_sctp = {
.protonum = IPPROTO_SCTP,
- .me = THIS_MODULE,
.manip_pkt = sctp_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = sctp_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
static void
tcp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct tcphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
const struct nf_nat_protocol nf_nat_protocol_tcp = {
.protonum = IPPROTO_TCP,
- .me = THIS_MODULE,
.manip_pkt = tcp_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = tcp_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
static void
udp_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct udphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
const struct nf_nat_protocol nf_nat_protocol_udp = {
.protonum = IPPROTO_UDP,
- .me = THIS_MODULE,
.manip_pkt = udp_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = udp_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
static void
udplite_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct udphdr *)(skb->data + hdroff);
- if (maniptype == IP_NAT_MANIP_SRC) {
+ if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
static const struct nf_nat_protocol nf_nat_protocol_udplite = {
.protonum = IPPROTO_UDPLITE,
- .me = THIS_MODULE,
.manip_pkt = udplite_manip_pkt,
.in_range = nf_nat_proto_in_range,
.unique_tuple = udplite_unique_tuple,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .range_to_nlattr = nf_nat_proto_range_to_nlattr,
.nlattr_to_range = nf_nat_proto_nlattr_to_range,
#endif
};
}
static void unknown_unique_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_ipv4_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
}
const struct nf_nat_protocol nf_nat_unknown_protocol = {
- /* .me isn't set: getting a ref to this cannot fail. */
.manip_pkt = unknown_manip_pkt,
.in_range = unknown_in_range,
.unique_tuple = unknown_unique_tuple,
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING ||
par->hooknum == NF_INET_LOCAL_IN);
ctinfo == IP_CT_RELATED_REPLY));
NF_CT_ASSERT(par->out != NULL);
- return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
+ return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_SRC);
}
static unsigned int
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_OUT);
/* Connection must be valid and new. */
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
- return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_DST);
+ return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST);
}
static int ipt_snat_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
/* Must be a valid range */
if (mr->rangesize != 1) {
static int ipt_dnat_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_multi_range_compat *mr = par->targinfo;
+ const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
/* Must be a valid range */
if (mr->rangesize != 1) {
alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* Force range to this IP; let proto decide mapping for
- per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
+ per-proto parts (hence not NF_NAT_RANGE_PROTO_SPECIFIED).
*/
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
range.flags = 0;
pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
- HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ?
+ HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
static struct xt_target ipt_snat_reg __read_mostly = {
.name = "SNAT",
.target = ipt_snat_target,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN),
.checkentry = ipt_snat_checkentry,
static struct xt_target ipt_dnat_reg __read_mostly = {
.name = "DNAT",
.target = ipt_dnat_target,
- .targetsize = sizeof(struct nf_nat_multi_range_compat),
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
.checkentry = ipt_dnat_checkentry,
static void ip_nat_sip_expected(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_ipv4_range range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
/* For DST manip, map port here to where it's expected. */
- range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED);
+ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
range.min = range.max = exp->saved_proto;
range.min_ip = range.max_ip = exp->saved_ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
/* Change src to where master sends to, but only if the connection
* actually came from the same source. */
if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip ==
ct->master->tuplehash[exp->dir].tuple.src.u3.ip) {
- range.flags = IP_NAT_RANGE_MAP_IPS;
+ range.flags = NF_NAT_RANGE_MAP_IPS;
range.min_ip = range.max_ip
= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
+ nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
}
}
return ret;
} else
pr_debug("Already setup manip %s for ct %p\n",
- maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST",
+ maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
ntohs(icmph->un.echo.id), skb->dev->ifindex);
if (sk == NULL) {
- ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
pr_debug("no socket, dropping\n");
return; /* No socket for error */
}
pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
inet_sk(sk), inet_sk(sk)->inet_num, skb);
if (sock_queue_rcv_skb(sk, skb) < 0) {
- ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS);
kfree_skb(skb);
pr_debug("ping_queue_rcv_skb -> failed\n");
return -1;
local_bh_disable();
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
- sockets = percpu_counter_sum_positive(&tcp_sockets_allocated);
+ sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
local_bh_enable();
socket_seq_show(seq);
seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
sock_prot_inuse_get(net, &tcp_prot), orphans,
tcp_death_row.tw_count, sockets,
- atomic_long_read(&tcp_memory_allocated));
+ proto_memory_allocated(&tcp_prot));
seq_printf(seq, "UDP: inuse %d mem %ld\n",
sock_prot_inuse_get(net, &udp_prot),
- atomic_long_read(&udp_memory_allocated));
+ proto_memory_allocated(&udp_prot));
seq_printf(seq, "UDPLITE: inuse %d\n",
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
count = 0;
for (i = 0; i < ICMPMSG_MIB_MAX; i++) {
- val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i);
+ val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]);
if (val) {
type[count] = i;
vals[count++] = val;
{
int i;
struct net *net = seq->private;
+ atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
seq_puts(seq, "\nIcmp: InMsgs InErrors");
for (i=0; icmpmibmap[i].name != NULL; i++)
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS));
for (i=0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
- snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
- icmpmibmap[i].index));
+ atomic_long_read(ptr + icmpmibmap[i].index));
seq_printf(seq, " %lu %lu",
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
for (i=0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
- snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
- icmpmibmap[i].index | 0x100));
+ atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
}
/*
{
/* Charge it to the socket. */
- if (ip_queue_rcv_skb(sk, skb) < 0) {
+ ipv4_pktinfo_prepare(skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
+ int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
if (flags&MSG_PROBE)
goto out;
+ hlen = LL_RESERVED_SPACE(rt->dst.dev);
+ tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
- length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+ length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
- skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+ skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
+#include <linux/prefetch.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
-#include <net/atmclip.h>
#include <net/secure_seq.h>
#define RT_FL_TOS(oldflp4) \
- ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
#define IP_MAX_MTU 0xFFF0
static int ip_rt_max_size;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+static int ip_rt_gc_interval __read_mostly = 60 * HZ;
static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
+static int redirect_genid;
+
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
/*
* Interface to generic destination cache.
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int ipv4_mtu(const struct dst_entry *dst);
static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
- .default_mtu = ipv4_default_mtu,
+ .mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
else {
struct rtable *r = v;
struct neighbour *n;
- int len;
+ int len, HHUptod;
+
+ rcu_read_lock();
+ n = dst_get_neighbour_noref(&r->dst);
+ HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+ rcu_read_unlock();
- n = dst_get_neighbour(&r->dst);
seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
"%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
r->dst.dev ? r->dst.dev->name : "*",
dst_metric(&r->dst, RTAX_RTTVAR)),
r->rt_key_tos,
-1,
- (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+ HHUptod,
r->rt_spec_dst, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
return ONE;
}
+static void rt_check_expire(void)
+{
+ static unsigned int rover;
+ unsigned int i = rover, goal;
+ struct rtable *rth;
+ struct rtable __rcu **rthp;
+ unsigned long samples = 0;
+ unsigned long sum = 0, sum2 = 0;
+ unsigned long delta;
+ u64 mult;
+
+ delta = jiffies - expires_ljiffies;
+ expires_ljiffies = jiffies;
+ mult = ((u64)delta) << rt_hash_log;
+ if (ip_rt_gc_timeout > 1)
+ do_div(mult, ip_rt_gc_timeout);
+ goal = (unsigned int)mult;
+ if (goal > rt_hash_mask)
+ goal = rt_hash_mask + 1;
+ for (; goal > 0; goal--) {
+ unsigned long tmo = ip_rt_gc_timeout;
+ unsigned long length;
+
+ i = (i + 1) & rt_hash_mask;
+ rthp = &rt_hash_table[i].chain;
+
+ if (need_resched())
+ cond_resched();
+
+ samples++;
+
+ if (rcu_dereference_raw(*rthp) == NULL)
+ continue;
+ length = 0;
+ spin_lock_bh(rt_hash_lock_addr(i));
+ while ((rth = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+ prefetch(rth->dst.rt_next);
+ if (rt_is_expired(rth)) {
+ *rthp = rth->dst.rt_next;
+ rt_free(rth);
+ continue;
+ }
+ if (rth->dst.expires) {
+ /* Entry is expired even if it is in use */
+ if (time_before_eq(jiffies, rth->dst.expires)) {
+nofree:
+ tmo >>= 1;
+ rthp = &rth->dst.rt_next;
+ /*
+ * We only count entries on
+ * a chain with equal hash inputs once
+ * so that entries for different QOS
+ * levels, and other non-hash input
+ * attributes don't unfairly skew
+ * the length computation
+ */
+ length += has_noalias(rt_hash_table[i].chain, rth);
+ continue;
+ }
+ } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+ goto nofree;
+
+ /* Cleanup aged off entries. */
+ *rthp = rth->dst.rt_next;
+ rt_free(rth);
+ }
+ spin_unlock_bh(rt_hash_lock_addr(i));
+ sum += length;
+ sum2 += length*length;
+ }
+ if (samples) {
+ unsigned long avg = sum / samples;
+ unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
+ rt_chain_length_max = max_t(unsigned long,
+ ip_rt_gc_elasticity,
+ (avg + 4*sd) >> FRACT_BITS);
+ }
+ rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+ rt_check_expire();
+ schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+ redirect_genid++;
}
/*
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
{
- struct neigh_table *tbl = &arp_tbl;
static const __be32 inaddr_any = 0;
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
struct neighbour *n;
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
- if (dev->type == ARPHRD_ATM)
- tbl = clip_tbl_hook;
-#endif
if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
pkey = &inaddr_any;
- n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey);
+ n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey);
if (n)
return n;
- return neigh_create(tbl, pkey, dev);
+ return neigh_create(&arp_tbl, pkey, dev);
}
static int rt_bind_neighbour(struct rtable *rt)
{
struct rtable *rt = (struct rtable *) dst;
- if (rt) {
+ if (rt && !(rt->dst.flags & DST_NOPEER)) {
if (rt->peer == NULL)
rt_bind_peer(rt, rt->rt_dst, 1);
iph->id = htons(inet_getid(rt->peer, more));
return;
}
- } else
+ } else if (!rt)
printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
__builtin_return_address(0));
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+ struct rtable *rt = (struct rtable *) dst;
+ __be32 orig_gw = rt->rt_gateway;
+ struct neighbour *n, *old_n;
+
+ dst_confirm(&rt->dst);
+
+ rt->rt_gateway = peer->redirect_learned.a4;
+
+ n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+ if (IS_ERR(n)) {
+ rt->rt_gateway = orig_gw;
+ return;
+ }
+ old_n = xchg(&rt->dst._neighbour, n);
+ if (old_n)
+ neigh_release(old_n);
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_event_send(n, NULL);
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+ }
+}
+
/* called in rcu_read_lock() section */
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 saddr, struct net_device *dev)
{
int s, i;
struct in_device *in_dev = __in_dev_get_rcu(dev);
- struct rtable *rt;
__be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
- struct flowi4 fl4;
struct inet_peer *peer;
struct net *net;
goto reject_redirect;
}
- memset(&fl4, 0, sizeof(fl4));
- fl4.daddr = daddr;
for (s = 0; s < 2; s++) {
for (i = 0; i < 2; i++) {
- fl4.flowi4_oif = ikeys[i];
- fl4.saddr = skeys[s];
- rt = __ip_route_output_key(net, &fl4);
- if (IS_ERR(rt))
- continue;
-
- if (rt->dst.error || rt->dst.dev != dev ||
- rt->rt_gateway != old_gw) {
- ip_rt_put(rt);
- continue;
- }
-
- if (!rt->peer)
- rt_bind_peer(rt, rt->rt_dst, 1);
+ unsigned int hash;
+ struct rtable __rcu **rthp;
+ struct rtable *rt;
+
+ hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+ rthp = &rt_hash_table[hash].chain;
+
+ while ((rt = rcu_dereference(*rthp)) != NULL) {
+ rthp = &rt->dst.rt_next;
+
+ if (rt->rt_key_dst != daddr ||
+ rt->rt_key_src != skeys[s] ||
+ rt->rt_oif != ikeys[i] ||
+ rt_is_input_route(rt) ||
+ rt_is_expired(rt) ||
+ !net_eq(dev_net(rt->dst.dev), net) ||
+ rt->dst.error ||
+ rt->dst.dev != dev ||
+ rt->rt_gateway != old_gw)
+ continue;
- peer = rt->peer;
- if (peer) {
- peer->redirect_learned.a4 = new_gw;
- atomic_inc(&__rt_peer_genid);
+ if (!rt->peer)
+ rt_bind_peer(rt, rt->rt_dst, 1);
+
+ peer = rt->peer;
+ if (peer) {
+ if (peer->redirect_learned.a4 != new_gw ||
+ peer->redirect_genid != redirect_genid) {
+ peer->redirect_learned.a4 = new_gw;
+ peer->redirect_genid = redirect_genid;
+ atomic_inc(&__rt_peer_genid);
+ }
+ check_peer_redir(&rt->dst, peer);
+ }
}
-
- ip_rt_put(rt);
- return;
}
}
return;
}
}
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
- struct rtable *rt = (struct rtable *) dst;
- __be32 orig_gw = rt->rt_gateway;
- struct neighbour *n, *old_n;
-
- dst_confirm(&rt->dst);
-
- rt->rt_gateway = peer->redirect_learned.a4;
-
- n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
- if (IS_ERR(n))
- return PTR_ERR(n);
- old_n = xchg(&rt->dst._neighbour, n);
- if (old_n)
- neigh_release(old_n);
- if (!n || !(n->nud_state & NUD_VALID)) {
- if (n)
- neigh_event_send(n, NULL);
- rt->rt_gateway = orig_gw;
- return -EAGAIN;
- } else {
- rt->rt_flags |= RTCF_REDIRECTED;
- call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
- }
- return 0;
-}
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
{
- struct rtable *rt = (struct rtable *) dst;
-
- if (rt_is_expired(rt))
- return NULL;
if (rt->rt_peer_genid != rt_peer_genid()) {
struct inet_peer *peer;
peer = rt->peer;
if (peer) {
- check_peer_pmtu(dst, peer);
+ check_peer_pmtu(&rt->dst, peer);
+ if (peer->redirect_genid != redirect_genid)
+ peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
- peer->redirect_learned.a4 != rt->rt_gateway) {
- if (check_peer_redir(dst, peer))
- return NULL;
- }
+ peer->redirect_learned.a4 != rt->rt_gateway)
+ check_peer_redir(&rt->dst, peer);
}
rt->rt_peer_genid = rt_peer_genid();
}
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (rt_is_expired(rt))
+ return NULL;
+ ipv4_validate_peer(rt);
return dst;
}
return advmss;
}
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
{
- unsigned int mtu = dst->dev->mtu;
+ const struct rtable *rt = (const struct rtable *) dst;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ if (mtu && rt_is_output_route(rt))
+ return mtu;
+
+ mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- const struct rtable *rt = (const struct rtable *) dst;
if (rt->rt_gateway != rt->rt_dst && mtu > 576)
mtu = 576;
dst_init_metrics(&rt->dst, peer->metrics, false);
check_peer_pmtu(&rt->dst, peer);
+ if (peer->redirect_genid != redirect_genid)
+ peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway) {
rt->rt_gateway = peer->redirect_learned.a4;
rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
+ ipv4_validate_peer(rth);
if (noref) {
dst_use_noref(&rth->dst, jiffies);
skb_dst_set_noref(skb, &rth->dst);
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4,
__be32 orig_daddr, __be32 orig_saddr,
- int orig_oif, struct net_device *dev_out,
+ int orig_oif, __u8 orig_rtos,
+ struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
- u32 tos = RT_FL_TOS(fl4);
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
- rth->rt_key_tos = tos;
+ rth->rt_key_tos = orig_rtos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
{
struct net_device *dev_out = NULL;
- u32 tos = RT_FL_TOS(fl4);
+ __u8 tos = RT_FL_TOS(fl4);
unsigned int flags = 0;
struct fib_result res;
struct rtable *rth;
make_route:
rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
- dev_out, flags);
+ tos, dev_out, flags);
if (!IS_ERR(rth)) {
unsigned int hash;
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
+ ipv4_validate_peer(rth);
dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
return NULL;
}
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
{
- return 0;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst->dev->mtu;
}
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
- .default_mtu = ipv4_blackhole_default_mtu,
+ .mtu = ipv4_blackhole_mtu,
.default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.cow_metrics = ipv4_rt_blackhole_cow_metrics,
struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
struct nlmsghdr *nlh;
- long expires = 0;
+ unsigned long expires = 0;
const struct inet_peer *peer = rt->peer;
u32 id = 0, ts = 0, tsage = 0, error;
tsage = get_seconds() - peer->tcp_ts_stamp;
}
expires = ACCESS_ONCE(peer->pmtu_expires);
- if (expires)
- expires -= jiffies;
+ if (expires) {
+ if (time_before(jiffies, expires))
+ expires -= jiffies;
+ else
+ expires = 0;
+ }
}
if (rt_is_input_route(rt)) {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "gc_interval",
+ .data = &ip_rt_gc_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{
.procname = "redirect_load",
.data = &ip_rt_redirect_load,
devinet_init();
ip_fib_init();
+ INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
+ expires_ljiffies = jiffies;
+ schedule_delayed_work(&expires_work,
+ net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
+
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
if (!sysctl_tcp_timestamps)
return false;
- tcp_opt->sack_ok = (options >> 4) & 0x1;
+ tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0;
*ecn_ok = (options >> 5) & 1;
if (*ecn_ok && !sysctl_tcp_ecn)
return false;
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
+#include <linux/swap.h>
#include <net/snmp.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
#include <net/ping.h>
+#include <net/tcp_memcontrol.h>
static int zero;
static int tcp_retr1_max = 255;
}
-void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high)
+static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high)
{
gid_t *data = table->data;
unsigned seq;
}
/* Update system visible IP port range */
-static void set_ping_group_range(struct ctl_table *table, int range[2])
+static void set_ping_group_range(struct ctl_table *table, gid_t range[2])
{
gid_t *data = table->data;
write_seqlock(&sysctl_local_ports.lock);
return ret;
}
+static int ipv4_tcp_mem(ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ unsigned long vec[3];
+ struct net *net = current->nsproxy->net_ns;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ struct mem_cgroup *memcg;
+#endif
+
+ ctl_table tmp = {
+ .data = &vec,
+ .maxlen = sizeof(vec),
+ .mode = ctl->mode,
+ };
+
+ if (!write) {
+ ctl->data = &net->ipv4.sysctl_tcp_mem;
+ return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
+ }
+
+ ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(current);
+
+ tcp_prot_mem(memcg, vec[0], 0);
+ tcp_prot_mem(memcg, vec[1], 1);
+ tcp_prot_mem(memcg, vec[2], 2);
+ rcu_read_unlock();
+#endif
+
+ net->ipv4.sysctl_tcp_mem[0] = vec[0];
+ net->ipv4.sysctl_tcp_mem[1] = vec[1];
+ net->ipv4.sysctl_tcp_mem[2] = vec[2];
+
+ return 0;
+}
+
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_timestamps",
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
- .procname = "tcp_mem",
- .data = &sysctl_tcp_mem,
- .maxlen = sizeof(sysctl_tcp_mem),
- .mode = 0644,
- .proc_handler = proc_doulongvec_minmax
- },
{
.procname = "tcp_wmem",
.data = &sysctl_tcp_wmem,
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
},
+ {
+ .procname = "tcp_mem",
+ .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
+ .mode = 0644,
+ .proc_handler = ipv4_tcp_mem,
+ },
{ }
};
static __net_init int ipv4_sysctl_init_net(struct net *net)
{
struct ctl_table *table;
+ unsigned long limit;
table = ipv4_net_table;
if (!net_eq(net, &init_net)) {
net->ipv4.sysctl_rt_cache_rebuild_count = 4;
+ limit = nr_free_buffer_pages() / 8;
+ limit = max(limit, 128UL);
+ net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+ net->ipv4.sysctl_tcp_mem[1] = limit;
+ net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+
net->ipv4.ipv4_hdr = register_net_sysctl_table(net,
net_ipv4_ctl_path, table);
if (net->ipv4.ipv4_hdr == NULL)
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
-long sysctl_tcp_mem[3] __read_mostly;
int sysctl_tcp_wmem[3] __read_mostly;
int sysctl_tcp_rmem[3] __read_mostly;
-EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
EXPORT_SYMBOL(sysctl_tcp_wmem);
}
EXPORT_SYMBOL(tcp_sendpage);
-#define TCP_PAGE(sk) (sk->sk_sndmsg_page)
-#define TCP_OFF(sk) (sk->sk_sndmsg_off)
-
-static inline int select_size(const struct sock *sk, int sg)
+static inline int select_size(const struct sock *sk, bool sg)
{
const struct tcp_sock *tp = tcp_sk(sk);
int tmp = tp->mss_cache;
if (sg) {
- if (sk_can_gso(sk))
- tmp = 0;
- else {
+ if (sk_can_gso(sk)) {
+ /* Small frames wont use a full page:
+ * Payload will immediately follow tcp header.
+ */
+ tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+ } else {
int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
if (tmp >= pgbreak &&
struct iovec *iov;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int iovlen, flags;
+ int iovlen, flags, err, copied;
int mss_now, size_goal;
- int sg, err, copied;
+ bool sg;
long timeo;
lock_sock(sk);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto out_err;
- sg = sk->sk_route_caps & NETIF_F_SG;
+ sg = !!(sk->sk_route_caps & NETIF_F_SG);
while (--iovlen >= 0) {
size_t seglen = iov->iov_len;
} else {
int merge = 0;
int i = skb_shinfo(skb)->nr_frags;
- struct page *page = TCP_PAGE(sk);
- int off = TCP_OFF(sk);
+ struct page *page = sk->sk_sndmsg_page;
+ int off;
+
+ if (page && page_count(page) == 1)
+ sk->sk_sndmsg_off = 0;
+
+ off = sk->sk_sndmsg_off;
if (skb_can_coalesce(skb, i, page, off) &&
off != PAGE_SIZE) {
} else if (page) {
if (off == PAGE_SIZE) {
put_page(page);
- TCP_PAGE(sk) = page = NULL;
+ sk->sk_sndmsg_page = page = NULL;
off = 0;
}
} else
/* If this page was new, give it to the
* socket so it does not get leaked.
*/
- if (!TCP_PAGE(sk)) {
- TCP_PAGE(sk) = page;
- TCP_OFF(sk) = 0;
+ if (!sk->sk_sndmsg_page) {
+ sk->sk_sndmsg_page = page;
+ sk->sk_sndmsg_off = 0;
}
goto do_error;
}
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
} else {
skb_fill_page_desc(skb, i, page, off, copy);
- if (TCP_PAGE(sk)) {
+ if (sk->sk_sndmsg_page) {
get_page(page);
} else if (off + copy < PAGE_SIZE) {
get_page(page);
- TCP_PAGE(sk) = page;
+ sk->sk_sndmsg_page = page;
}
}
- TCP_OFF(sk) = off + copy;
+ sk->sk_sndmsg_off = off + copy;
}
if (!copied)
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct tcphdr *th;
sysctl_tcp_max_orphans = cnt / 2;
sysctl_max_syn_backlog = max(128, cnt / 256);
- limit = nr_free_buffer_pages() / 8;
- limit = max(limit, 128UL);
- sysctl_tcp_mem[0] = limit / 4 * 3;
- sysctl_tcp_mem[1] = limit;
- sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
-
/* Set per-socket limits to no more than 1/128 the pressure threshold */
- limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+ limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
+ << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
left * tp->mss_cache < sk->sk_gso_max_size)
return 1;
- return left <= tcp_max_burst(tp);
+ return left <= tcp_max_tso_deferred_mss(tp);
}
EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
tcp_get_info(sk, info);
}
+static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
+}
+
+static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+ struct inet_diag_req *req)
+{
+ return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
+}
+
static const struct inet_diag_handler tcp_diag_handler = {
- .idiag_hashinfo = &tcp_hashinfo,
+ .dump = tcp_diag_dump,
+ .dump_one = tcp_diag_dump_one,
.idiag_get_info = tcp_diag_get_info,
- .idiag_type = TCPDIAG_GETSOCK,
- .idiag_info_size = sizeof(struct tcp_info),
+ .idiag_type = IPPROTO_TCP,
};
static int __init tcp_diag_init(void)
module_init(tcp_diag_init);
module_exit(tcp_diag_exit);
MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, TCPDIAG_GETSOCK);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_memory_pressure) {
+ !sk_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
- !tcp_memory_pressure &&
- atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+ !sk_under_memory_pressure(sk) &&
+ sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
}
/* RFC3517 uses different metric in lost marker => reset on change */
if (tcp_is_fack(tp))
tp->lost_skb_hint = NULL;
- tp->rx_opt.sack_ok &= ~2;
+ tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED;
}
/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
- tp->rx_opt.sack_ok |= 4;
+ tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
}
/* Initialize metrics on socket. */
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
struct tcp_sock *tp = tcp_sk(sk);
int state = TCP_CA_Open;
- if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
+ if (tcp_left_out(tp) || tcp_any_retrans_done(sk))
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
- tcp_moderate_cwnd(tp);
+ if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+ tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_down(sk, flag);
}
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int newly_acked_sacked, int flag)
+ int newly_acked_sacked, bool is_dupack,
+ int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
int fast_rexmit = 0, mib_idx;
}
break;
- case TCP_CA_Disorder:
- tcp_try_undo_dsack(sk);
- if (!tp->undo_marker ||
- /* For SACK case do not Open to allow to undo
- * catching for all duplicate ACKs. */
- tcp_is_reno(tp) || tp->snd_una != tp->high_seq) {
- tp->undo_marker = 0;
- tcp_set_ca_state(sk, TCP_CA_Open);
- }
- break;
-
case TCP_CA_Recovery:
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
tcp_add_reno_sack(sk);
}
- if (icsk->icsk_ca_state == TCP_CA_Disorder)
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk)) {
u32 prior_snd_una = tp->snd_una;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
+ bool is_dupack = false;
u32 prior_in_flight;
u32 prior_fackets;
int prior_packets;
int prior_sacked = tp->sacked_out;
+ int pkts_acked = 0;
int newly_acked_sacked = 0;
int frto_cwnd = 0;
/* See if we can take anything off of the retransmit queue. */
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
+ pkts_acked = prior_packets - tp->packets_out;
newly_acked_sacked = (prior_packets - prior_sacked) -
(tp->packets_out - tp->sacked_out);
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
- tcp_fastretrans_alert(sk, prior_packets - tp->packets_out,
- newly_acked_sacked, flag);
+ is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
tcp_cong_avoid(sk, ack, prior_in_flight);
return 1;
no_queue:
+ /* If data was DSACKed, see if we can undo a cwnd reduction. */
+ if (flag & FLAG_DSACKING_ACK)
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
return -1;
old_ack:
+ /* If data was SACKed, tag it and see if we should send more data.
+ * If data was DSACKed, see if we can undo a cwnd reduction.
+ */
if (TCP_SKB_CB(skb)->sacked) {
- tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- if (icsk->icsk_ca_state == TCP_CA_Open)
- tcp_try_keep_open(sk);
+ flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ newly_acked_sacked = tp->sacked_out - prior_sacked;
+ tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ is_dupack, flag);
}
SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
!estab && sysctl_tcp_sack) {
- opt_rx->sack_ok = 1;
+ opt_rx->sack_ok = TCP_SACK_SEEN;
tcp_sack_reset(opt_rx);
}
break;
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
tcp_clamp_window(sk);
- else if (tcp_memory_pressure)
+ else if (sk_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tcp_collapse_ofo_queue(sk);
return 0;
/* If we are under global TCP memory pressure, do not expand. */
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
return 0;
/* If we are under soft global TCP memory pressure, do not expand. */
- if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+ if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
return 0;
/* If we filled the congestion window, do not expand. */
goto discard;
if (th->syn) {
+ if (th->fin)
+ goto discard;
if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
return 1;
#include <net/xfrm.h>
#include <net/netdma.h>
#include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
+ tcp_clear_xmit_timers(newsk);
+ tcp_cleanup_congestion_control(newsk);
bh_unlock_sock(newsk);
sock_put(newsk);
goto exit;
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- percpu_counter_inc(&tcp_sockets_allocated);
+ sock_update_memcg(sk);
+ sk_sockets_allocated_inc(sk);
local_bh_enable();
return 0;
tp->cookie_values = NULL;
}
- percpu_counter_dec(&tcp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
+ sock_release_memcg(sk);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
- .sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ .init_cgroup = tcp_init_cgroup,
+ .destroy_cgroup = tcp_destroy_cgroup,
+ .proto_cgroup = tcp_proto_cgroup,
+#endif
};
EXPORT_SYMBOL(tcp_prot);
-
static int __net_init tcp_sk_init(struct net *net)
{
return inet_ctl_sock_create(&net->ipv4.tcp_sock,
--- /dev/null
+#include <net/tcp.h>
+#include <net/tcp_memcontrol.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <linux/nsproxy.h>
+#include <linux/memcontrol.h>
+#include <linux/module.h>
+
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+ const char *buffer);
+static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event);
+
+static struct cftype tcp_files[] = {
+ {
+ .name = "kmem.tcp.limit_in_bytes",
+ .write_string = tcp_cgroup_write,
+ .read_u64 = tcp_cgroup_read,
+ .private = RES_LIMIT,
+ },
+ {
+ .name = "kmem.tcp.usage_in_bytes",
+ .read_u64 = tcp_cgroup_read,
+ .private = RES_USAGE,
+ },
+ {
+ .name = "kmem.tcp.failcnt",
+ .private = RES_FAILCNT,
+ .trigger = tcp_cgroup_reset,
+ .read_u64 = tcp_cgroup_read,
+ },
+ {
+ .name = "kmem.tcp.max_usage_in_bytes",
+ .private = RES_MAX_USAGE,
+ .trigger = tcp_cgroup_reset,
+ .read_u64 = tcp_cgroup_read,
+ },
+};
+
+static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
+{
+ return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
+}
+
+static void memcg_tcp_enter_memory_pressure(struct sock *sk)
+{
+ if (sk->sk_cgrp->memory_pressure)
+ *sk->sk_cgrp->memory_pressure = 1;
+}
+EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
+
+int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ /*
+ * The root cgroup does not use res_counters, but rather,
+ * rely on the data already collected by the network
+ * subsystem
+ */
+ struct res_counter *res_parent = NULL;
+ struct cg_proto *cg_proto, *parent_cg;
+ struct tcp_memcontrol *tcp;
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+ struct net *net = current->nsproxy->net_ns;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ goto create_files;
+
+ tcp = tcp_from_cgproto(cg_proto);
+
+ tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
+ tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
+ tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
+ tcp->tcp_memory_pressure = 0;
+
+ parent_cg = tcp_prot.proto_cgroup(parent);
+ if (parent_cg)
+ res_parent = parent_cg->memory_allocated;
+
+ res_counter_init(&tcp->tcp_memory_allocated, res_parent);
+ percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
+
+ cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
+ cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
+ cg_proto->sysctl_mem = tcp->tcp_prot_mem;
+ cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
+ cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
+ cg_proto->memcg = memcg;
+
+create_files:
+ return cgroup_add_files(cgrp, ss, tcp_files,
+ ARRAY_SIZE(tcp_files));
+}
+EXPORT_SYMBOL(tcp_init_cgroup);
+
+void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct cg_proto *cg_proto;
+ struct tcp_memcontrol *tcp;
+ u64 val;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return;
+
+ tcp = tcp_from_cgproto(cg_proto);
+ percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+
+ val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+
+ if (val != RESOURCE_MAX)
+ jump_label_dec(&memcg_socket_limit_enabled);
+}
+EXPORT_SYMBOL(tcp_destroy_cgroup);
+
+static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+ u64 old_lim;
+ int i;
+ int ret;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return -EINVAL;
+
+ if (val > RESOURCE_MAX)
+ val = RESOURCE_MAX;
+
+ tcp = tcp_from_cgproto(cg_proto);
+
+ old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+ ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < 3; i++)
+ tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
+ net->ipv4.sysctl_tcp_mem[i]);
+
+ if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
+ jump_label_dec(&memcg_socket_limit_enabled);
+ else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
+ jump_label_inc(&memcg_socket_limit_enabled);
+
+ return 0;
+}
+
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+ const char *buffer)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ unsigned long long val;
+ int ret = 0;
+
+ switch (cft->private) {
+ case RES_LIMIT:
+ /* see memcontrol.c */
+ ret = res_counter_memparse_write_strategy(buffer, &val);
+ if (ret)
+ break;
+ ret = tcp_update_limit(memcg, val);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ return ret;
+}
+
+static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
+{
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return default_val;
+
+ tcp = tcp_from_cgproto(cg_proto);
+ return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
+}
+
+static u64 tcp_read_usage(struct mem_cgroup *memcg)
+{
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
+
+ tcp = tcp_from_cgproto(cg_proto);
+ return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+}
+
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ u64 val;
+
+ switch (cft->private) {
+ case RES_LIMIT:
+ val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
+ break;
+ case RES_USAGE:
+ val = tcp_read_usage(memcg);
+ break;
+ case RES_FAILCNT:
+ case RES_MAX_USAGE:
+ val = tcp_read_stat(memcg, cft->private, 0);
+ break;
+ default:
+ BUG();
+ }
+ return val;
+}
+
+static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event)
+{
+ struct mem_cgroup *memcg;
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+
+ memcg = mem_cgroup_from_cont(cont);
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return 0;
+ tcp = tcp_from_cgproto(cg_proto);
+
+ switch (event) {
+ case RES_MAX_USAGE:
+ res_counter_reset_max(&tcp->tcp_memory_allocated);
+ break;
+ case RES_FAILCNT:
+ res_counter_reset_failcnt(&tcp->tcp_memory_allocated);
+ break;
+ }
+
+ return 0;
+}
+
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
+{
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+
+ cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
+ if (!cg_proto)
+ return 0;
+
+ tcp = tcp_from_cgproto(cg_proto);
+ return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+}
+
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
+{
+ struct tcp_memcontrol *tcp;
+ struct cg_proto *cg_proto;
+
+ cg_proto = tcp_prot.proto_cgroup(memcg);
+ if (!cg_proto)
+ return;
+
+ tcp = tcp_from_cgproto(cg_proto);
+
+ tcp->tcp_prot_mem[idx] = val;
+}
tcptw->tw_ts_recent = tp->rx_opt.ts_recent;
tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet6_timewait_sock *tw6;
tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
tw6 = inet6_twsk((struct sock *)tw);
- ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
- ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
+ tw6->tw_v6_daddr = np->daddr;
+ tw6->tw_v6_rcv_saddr = np->rcv_saddr;
tw->tw_tclass = np->tclass;
tw->tw_ipv6only = np->ipv6only;
}
*/
struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
{
- struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+ struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
if (newsk != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
newtp->frto_counter = 0;
newtp->frto_highmark = 0;
- newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
+ !try_module_get(newicsk->icsk_ca_ops->owner))
+ newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
{
int i, k, eat;
+ eat = min_t(int, len, skb_headlen(skb));
+ if (eat) {
+ __skb_pull(skb, eat);
+ len -= eat;
+ if (!len)
+ return;
+ }
eat = len;
k = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return -ENOMEM;
- /* If len == headlen, we avoid __skb_pull to preserve alignment. */
- if (unlikely(len < skb_headlen(skb)))
- __skb_pull(skb, len);
- else
- __pskb_trim_head(skb, len - skb_headlen(skb));
+ __pskb_trim_head(skb, len);
TCP_SKB_CB(skb)->seq += len;
skb->ip_summed = CHECKSUM_PARTIAL;
/* Return 0, if packet can be sent now without violation Nagle's rules:
* 1. It is full sized.
* 2. Or it contains FIN. (already checked by caller)
- * 3. Or TCP_NODELAY was set.
+ * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
* 4. Or TCP_CORK is not set, and all sent packets are ACKed.
* With Minshall's modification: all sent small packets are ACKed.
*/
* frame, so if we have space for more than 3 frames
* then send now.
*/
- if (limit > tcp_max_burst(tp) * tp->mss_cache)
+ if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache)
goto send_now;
}
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh,
4U * tp->advmss);
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ /* make sure skb->data is aligned on arches that require it */
+ if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+ struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
+ GFP_ATOMIC);
+ err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+ -ENOBUFS;
+ } else {
+ err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ }
if (err == 0) {
/* Update global TCP statistics. */
{
struct inet_connection_sock *icsk = inet_csk(sk);
int retry_until;
- bool do_reset, syn_set = 0;
+ bool do_reset, syn_set = false;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
- syn_set = 1;
+ syn_set = true;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
/* Black hole detection */
}
out:
- if (tcp_memory_pressure)
+ if (sk_under_memory_pressure(sk))
sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
&inet->inet_daddr, ntohs(inet->inet_dport),
inet->inet_num, tp->snd_una, tp->snd_nxt);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
return 0;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int tunnel64_rcv(struct sk_buff *skb)
{
struct xfrm_tunnel *handler;
break;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static void tunnel64_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
.netns_ok = 1,
};
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static const struct net_protocol tunnel64_protocol = {
.handler = tunnel64_rcv,
.err_handler = tunnel64_err,
printk(KERN_ERR "tunnel4 init: can't add protocol\n");
return -EAGAIN;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) {
printk(KERN_ERR "tunnel64 init: can't add protocol\n");
inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
static void __exit tunnel4_fini(void)
{
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6))
printk(KERN_ERR "tunnel64 close: can't remove protocol\n");
#endif
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
-static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
+struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
__be16 sport, __be32 daddr, __be16 dport,
int dif, struct udp_table *udptable)
{
rcu_read_unlock();
return result;
}
+EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
struct sk_buff *skb;
- unsigned int ulen;
+ unsigned int ulen, copied;
int peeked;
int err;
int is_udplite = IS_UDPLITE(sk);
goto out;
ulen = skb->len - sizeof(struct udphdr);
- if (len > ulen)
- len = ulen;
- else if (len < ulen)
+ copied = len;
+ if (copied > ulen)
+ copied = ulen;
+ else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
/*
* coverage checksum (UDP-Lite), do it before the copy.
*/
- if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
+ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
if (udp_lib_checksum_complete(skb))
goto csum_copy_err;
}
if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
- msg->msg_iov, len);
+ msg->msg_iov, copied);
else {
err = skb_copy_and_csum_datagram_iovec(skb,
sizeof(struct udphdr),
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
- err = len;
+ err = copied;
if (flags & MSG_TRUNC)
err = ulen;
if (inet_sk(sk)->inet_daddr)
sock_rps_save_rxhash(sk, skb);
- rc = ip_queue_rcv_skb(sk, skb);
+ rc = sock_queue_rcv_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
rc = 0;
+ ipv4_pktinfo_prepare(skb);
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
rc = __udp_queue_rcv_skb(sk, skb);
return 0;
}
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features)
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
--- /dev/null
+/*
+ * udp_diag.c Module for monitoring UDP transport protocols sockets.
+ *
+ * Authors: Pavel Emelyanov, <xemul@parallels.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/module.h>
+#include <linux/inet_diag.h>
+#include <linux/udp.h>
+#include <net/udp.h>
+#include <net/udplite.h>
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
+ struct netlink_callback *cb, struct inet_diag_req *req,
+ struct nlattr *bc)
+{
+ if (!inet_diag_bc_sk(bc, sk))
+ return 0;
+
+ return inet_sk_diag_fill(sk, NULL, skb, req, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
+}
+
+static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh, struct inet_diag_req *req)
+{
+ int err = -EINVAL;
+ struct sock *sk;
+ struct sk_buff *rep;
+
+ if (req->sdiag_family == AF_INET)
+ sk = __udp4_lib_lookup(&init_net,
+ req->id.idiag_src[0], req->id.idiag_sport,
+ req->id.idiag_dst[0], req->id.idiag_dport,
+ req->id.idiag_if, tbl);
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (req->sdiag_family == AF_INET6)
+ sk = __udp6_lib_lookup(&init_net,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ req->id.idiag_if, tbl);
+#endif
+ else
+ goto out_nosk;
+
+ err = -ENOENT;
+ if (sk == NULL)
+ goto out_nosk;
+
+ err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
+ if (err)
+ goto out;
+
+ err = -ENOMEM;
+ rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
+ sizeof(struct inet_diag_meminfo) +
+ 64)), GFP_KERNEL);
+ if (!rep)
+ goto out;
+
+ err = inet_sk_diag_fill(sk, NULL, rep, req,
+ NETLINK_CB(in_skb).pid,
+ nlh->nlmsg_seq, 0, nlh);
+ if (err < 0) {
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(rep);
+ goto out;
+ }
+ err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+out:
+ if (sk)
+ sock_put(sk);
+out_nosk:
+ return err;
+}
+
+static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ int num, s_num, slot, s_slot;
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+ struct sock *sk;
+ struct hlist_nulls_node *node;
+ struct udp_hslot *hslot = &table->hash[slot];
+
+ if (hlist_nulls_empty(&hslot->head))
+ continue;
+
+ spin_lock_bh(&hslot->lock);
+ sk_nulls_for_each(sk, node, &hslot->head) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (num < s_num)
+ goto next;
+ if (!(r->idiag_states & (1 << sk->sk_state)))
+ goto next;
+ if (r->sdiag_family != AF_UNSPEC &&
+ sk->sk_family != r->sdiag_family)
+ goto next;
+ if (r->id.idiag_sport != inet->inet_sport &&
+ r->id.idiag_sport)
+ goto next;
+ if (r->id.idiag_dport != inet->inet_dport &&
+ r->id.idiag_dport)
+ goto next;
+
+ if (sk_diag_dump(sk, skb, cb, r, bc) < 0) {
+ spin_unlock_bh(&hslot->lock);
+ goto done;
+ }
+next:
+ num++;
+ }
+ spin_unlock_bh(&hslot->lock);
+ }
+done:
+ cb->args[0] = slot;
+ cb->args[1] = num;
+}
+
+static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ udp_dump(&udp_table, skb, cb, r, bc);
+}
+
+static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+ struct inet_diag_req *req)
+{
+ return udp_dump_one(&udp_table, in_skb, nlh, req);
+}
+
+static const struct inet_diag_handler udp_diag_handler = {
+ .dump = udp_diag_dump,
+ .dump_one = udp_diag_dump_one,
+ .idiag_type = IPPROTO_UDP,
+};
+
+static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req *r, struct nlattr *bc)
+{
+ udp_dump(&udplite_table, skb, cb, r, bc);
+}
+
+static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+ struct inet_diag_req *req)
+{
+ return udp_dump_one(&udplite_table, in_skb, nlh, req);
+}
+
+static const struct inet_diag_handler udplite_diag_handler = {
+ .dump = udplite_diag_dump,
+ .dump_one = udplite_diag_dump_one,
+ .idiag_type = IPPROTO_UDPLITE,
+};
+
+static int __init udp_diag_init(void)
+{
+ int err;
+
+ err = inet_diag_register(&udp_diag_handler);
+ if (err)
+ goto out;
+ err = inet_diag_register(&udplite_diag_handler);
+ if (err)
+ goto out_lite;
+out:
+ return err;
+out_lite:
+ inet_diag_unregister(&udp_diag_handler);
+ goto out;
+}
+
+static void __exit udp_diag_exit(void)
+{
+ inet_diag_unregister(&udplite_diag_handler);
+ inet_diag_unregister(&udp_diag_handler);
+}
+
+module_init(udp_diag_init);
+module_exit(udp_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */);
.priority = 2,
};
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
xfrm_unregister_type(&ipip_type, AF_INET);
return -EAGAIN;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (xfrm4_tunnel_register(&xfrm64_tunnel_handler, AF_INET6)) {
printk(KERN_INFO "ipip init: can't add xfrm handler for AF_INET6\n");
xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET);
static void __exit ipip_fini(void)
{
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
if (xfrm4_tunnel_deregister(&xfrm64_tunnel_handler, AF_INET6))
printk(KERN_INFO "ipip close: can't remove xfrm handler for AF_INET6\n");
#endif
goto out;
}
- rt = addrconf_dst_alloc(idev, addr, 0);
+ rt = addrconf_dst_alloc(idev, addr, false);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto out;
}
- ipv6_addr_copy(&ifa->addr, addr);
+ ifa->addr = *addr;
spin_lock_init(&ifa->lock);
spin_lock_init(&ifa->state_lock);
ifa->rt = rt;
- /*
- * part one of RFC 4429, section 3.3
- * We should not configure an address as
- * optimistic if we do not yet know the link
- * layer address of our nexhop router
- */
-
- if (dst_get_neighbour_raw(&rt->dst) == NULL)
- ifa->flags &= ~IFA_F_OPTIMISTIC;
-
ifa->idev = idev;
in6_dev_hold(idev);
/* For caller */
ip6_del_rt(rt);
rt = NULL;
} else if (!(rt->rt6i_flags & RTF_EXPIRES)) {
- rt->rt6i_expires = expires;
+ rt->dst.expires = expires;
rt->rt6i_flags |= RTF_EXPIRES;
}
}
if (!hiscore->ifa)
return -EADDRNOTAVAIL;
- ipv6_addr_copy(saddr, &hiscore->ifa->addr);
+ *saddr = hiscore->ifa->addr;
in6_ifa_put(hiscore->ifa);
return 0;
}
list_for_each_entry(ifp, &idev->addr_list, if_list) {
if (ifp->scope == IFA_LINK &&
!(ifp->flags & banned_flags)) {
- ipv6_addr_copy(addr, &ifp->addr);
+ *addr = ifp->addr;
err = 0;
break;
}
.fc_protocol = RTPROT_KERNEL,
};
- ipv6_addr_copy(&cfg.fc_dst, pfx);
+ cfg.fc_dst = *pfx;
/* Prevent useless cloning on PtP SIT.
This thing is done here expecting that the whole
if (!fn)
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_dev->ifindex != dev->ifindex)
+ if (rt->dst.dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & flags) != flags)
continue;
return ERR_PTR(-EACCES);
/* Add default multicast route */
- addrconf_add_mroute(dev);
+ if (!(dev->flags & IFF_LOOPBACK))
+ addrconf_add_mroute(dev);
/* Add link local route */
addrconf_add_lroute(dev);
return idev;
}
-void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
+void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
{
struct prefix_info *pinfo;
__u32 valid_lft;
rt = NULL;
} else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
- rt->rt6i_expires = jiffies + rt_expires;
+ rt->dst.expires = jiffies + rt_expires;
rt->rt6i_flags |= RTF_EXPIRES;
} else {
rt->rt6i_flags &= ~RTF_EXPIRES;
- rt->rt6i_expires = 0;
+ rt->dst.expires = 0;
}
} else if (valid_lft) {
clock_t expires = 0;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
if (in6_dev->cnf.optimistic_dad &&
- !net->ipv6.devconf_all->forwarding)
+ !net->ipv6.devconf_all->forwarding && sllao)
addr_flags = IFA_F_OPTIMISTIC;
#endif
struct if6_iter_state {
struct seq_net_private p;
int bucket;
+ int offset;
};
-static struct inet6_ifaddr *if6_get_first(struct seq_file *seq)
+static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
{
struct inet6_ifaddr *ifa = NULL;
struct if6_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
+ int p = 0;
+
+ /* initial bucket if pos is 0 */
+ if (pos == 0) {
+ state->bucket = 0;
+ state->offset = 0;
+ }
- for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
+ for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
struct hlist_node *n;
hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket],
- addr_lst)
+ addr_lst) {
+ /* sync with offset */
+ if (p < state->offset) {
+ p++;
+ continue;
+ }
+ state->offset++;
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
+ }
+
+ /* prepare for next bucket */
+ state->offset = 0;
+ p = 0;
}
return NULL;
}
struct net *net = seq_file_net(seq);
struct hlist_node *n = &ifa->addr_lst;
- hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst)
+ hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) {
+ state->offset++;
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
+ }
while (++state->bucket < IN6_ADDR_HSIZE) {
+ state->offset = 0;
hlist_for_each_entry_rcu_bh(ifa, n,
&inet6_addr_lst[state->bucket], addr_lst) {
+ state->offset++;
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
}
return NULL;
}
-static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos)
-{
- struct inet6_ifaddr *ifa = if6_get_first(seq);
-
- if (ifa)
- while (pos && (ifa = if6_get_next(seq, ifa)) != NULL)
- --pos;
- return pos ? NULL : ifa;
-}
-
static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(rcu_bh)
{
rcu_read_lock_bh();
- return if6_get_idx(seq, *pos);
+ return if6_get_first(seq, *pos);
}
static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
*/
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST)) {
- if (!inet->transparent &&
+ if (!(inet->freebind || inet->transparent) &&
!ipv6_chk_addr(net, &addr->sin6_addr,
dev, 0)) {
err = -EADDRNOTAVAIL;
inet->inet_rcv_saddr = v4addr;
inet->inet_saddr = v4addr;
- ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+ np->rcv_saddr = addr->sin6_addr;
if (!(addr_type & IPV6_ADDR_MULTICAST))
- ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+ np->saddr = addr->sin6_addr;
/* Make sure we are allowed to bind here. */
if (sk->sk_prot->get_port(sk, snum)) {
peer == 1)
return -ENOTCONN;
sin->sin6_port = inet->inet_dport;
- ipv6_addr_copy(&sin->sin6_addr, &np->daddr);
+ sin->sin6_addr = np->daddr;
if (np->sndflow)
sin->sin6_flowinfo = np->flow_label;
} else {
if (ipv6_addr_any(&np->rcv_saddr))
- ipv6_addr_copy(&sin->sin6_addr, &np->saddr);
+ sin->sin6_addr = np->saddr;
else
- ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr);
+ sin->sin6_addr = np->rcv_saddr;
sin->sin6_port = inet->inet_sport;
}
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = sk->sk_protocol;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = np->saddr;
fl6.flowlabel = np->flow_label;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
return err;
}
-static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features)
+static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct ipv6hdr *ipv6h;
sizeof(struct icmpv6_mib),
__alignof__(struct icmpv6_mib)) < 0)
goto err_icmp_mib;
- if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics,
- sizeof(struct icmpv6msg_mib),
- __alignof__(struct icmpv6msg_mib)) < 0)
+ net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib),
+ GFP_KERNEL);
+ if (!net->mib.icmpv6msg_statistics)
goto err_icmpmsg_mib;
return 0;
snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
- snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics);
+ kfree(net->mib.icmpv6msg_statistics);
}
static int __net_init inet6_net_init(struct net *net)
if (err)
goto static_sysctl_fail;
#endif
+ tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
/*
* ipngwg API draft makes clear that the correct semantics
* for TCP and UDP is to consider one TCP and UDP instance
printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length);
goto bad;
}
- ipv6_addr_copy(&final_addr, &hao->addr);
- ipv6_addr_copy(&hao->addr, &iph->saddr);
- ipv6_addr_copy(&iph->saddr, &final_addr);
+ final_addr = hao->addr;
+ hao->addr = iph->saddr;
+ iph->saddr = final_addr;
}
break;
}
segments = rthdr->hdrlen >> 1;
addrs = ((struct rt0_hdr *)rthdr)->addr;
- ipv6_addr_copy(&final_addr, addrs + segments - 1);
+ final_addr = addrs[segments - 1];
addrs += segments - segments_left;
memmove(addrs + 1, addrs, (segments_left - 1) * sizeof(*addrs));
- ipv6_addr_copy(addrs, &iph->daddr);
- ipv6_addr_copy(&iph->daddr, &final_addr);
+ addrs[0] = iph->daddr;
+ iph->daddr = final_addr;
}
static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
#endif
}
- err = ah->nexthdr;
-
kfree(AH_SKB_CB(skb)->tmp);
xfrm_output_resume(skb, err);
}
if (err)
goto out;
+ err = ah->nexthdr;
+
skb->network_header += ah_hlen;
memcpy(skb_network_header(skb), work_iph, hdr_len);
__skb_pull(skb, ah_hlen + hdr_len);
skb_set_transport_header(skb, -hdr_len);
-
- err = ah->nexthdr;
out:
kfree(AH_SKB_CB(skb)->tmp);
xfrm_input_resume(skb, err);
if (err == -EINPROGRESS)
goto out;
- if (err == -EBUSY)
- err = NET_XMIT_DROP;
goto out_free;
}
if (pac == NULL)
return -ENOMEM;
pac->acl_next = NULL;
- ipv6_addr_copy(&pac->acl_addr, addr);
+ pac->acl_addr = *addr;
rcu_read_lock();
if (ifindex == 0) {
rt = rt6_lookup(net, addr, NULL, 0, 0);
if (rt) {
- dev = rt->rt6i_dev;
+ dev = rt->dst.dev;
dst_release(&rt->dst);
} else if (ishost) {
err = -EADDRNOTAVAIL;
goto out;
}
- rt = addrconf_dst_alloc(idev, addr, 1);
+ rt = addrconf_dst_alloc(idev, addr, true);
if (IS_ERR(rt)) {
kfree(aca);
err = PTR_ERR(rt);
goto out;
}
- ipv6_addr_copy(&aca->aca_addr, addr);
+ aca->aca_addr = *addr;
aca->aca_idev = idev;
aca->aca_rt = rt;
aca->aca_users = 1;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
- ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+ usin->sin6_addr = flowlabel->dst;
}
}
}
}
- ipv6_addr_copy(&np->daddr, daddr);
+ np->daddr = *daddr;
np->flow_label = fl6.flowlabel;
inet->inet_dport = usin->sin6_port;
*/
fl6.flowi6_proto = sk->sk_protocol;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
/* source address lookup done in ip6_dst_lookup */
if (ipv6_addr_any(&np->saddr))
- ipv6_addr_copy(&np->saddr, &fl6.saddr);
+ np->saddr = fl6.saddr;
if (ipv6_addr_any(&np->rcv_saddr)) {
- ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr);
+ np->rcv_saddr = fl6.saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
- ipv6_addr_copy(&iph->daddr, &fl6->daddr);
+ iph->daddr = fl6->daddr;
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
- ipv6_addr_copy(&iph->daddr, &fl6->daddr);
+ iph->daddr = fl6->daddr;
mtu_info = IP6CBMTU(skb);
mtu_info->ip6m_addr.sin6_port = 0;
mtu_info->ip6m_addr.sin6_flowinfo = 0;
mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif;
- ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+ mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
sin->sin6_port = serr->port;
sin->sin6_scope_id = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
- ipv6_addr_copy(&sin->sin6_addr,
- (struct in6_addr *)(nh + serr->addr_offset));
+ sin->sin6_addr =
+ *(struct in6_addr *)(nh + serr->addr_offset);
if (np->sndflow)
sin->sin6_flowinfo =
(*(__be32 *)(nh + serr->addr_offset - 24) &
sin->sin6_flowinfo = 0;
sin->sin6_scope_id = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
- ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr);
+ sin->sin6_addr = ipv6_hdr(skb)->saddr;
if (np->rxopt.all)
datagram_recv_ctl(sk, msg, skb);
if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin->sin6_flowinfo = 0;
sin->sin6_port = 0;
sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
- ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+ sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
}
put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = opt->iif;
- ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr);
+ src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = opt->iif;
- ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr);
+ src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
*/
sin6.sin6_family = AF_INET6;
- ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr);
+ sin6.sin6_addr = ipv6_hdr(skb)->daddr;
sin6.sin6_port = ports[1];
sin6.sin6_flowinfo = 0;
sin6.sin6_scope_id = 0;
if (addr_type != IPV6_ADDR_ANY) {
int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
- if (!inet_sk(sk)->transparent &&
+ if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
!ipv6_chk_addr(net, &src_info->ipi6_addr,
strict ? dev : NULL, 0))
err = -EINVAL;
else
- ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr);
+ fl6->saddr = src_info->ipi6_addr;
}
rcu_read_unlock();
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
- ipv6_addr_copy(&tmp_addr, &ipv6h->saddr);
- ipv6_addr_copy(&ipv6h->saddr, &hao->addr);
- ipv6_addr_copy(&hao->addr, &tmp_addr);
+ tmp_addr = ipv6h->saddr;
+ ipv6h->saddr = hao->addr;
+ hao->addr = tmp_addr;
if (skb->tstamp.tv64 == 0)
__net_timestamp(skb);
return -1;
}
- ipv6_addr_copy(&daddr, addr);
- ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr);
- ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr);
+ daddr = *addr;
+ *addr = ipv6_hdr(skb)->daddr;
+ ipv6_hdr(skb)->daddr = daddr;
skb_dst_drop(skb);
ip6_route_input(skb);
memcpy(phdr->addr, ihdr->addr + 1,
(hops - 1) * sizeof(struct in6_addr));
- ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p);
+ phdr->addr[hops - 1] = **addr_p;
*addr_p = ihdr->addr;
phdr->rt_hdr.nexthdr = *proto;
if (!opt || !opt->srcrt)
return NULL;
- ipv6_addr_copy(orig, &fl6->daddr);
- ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr);
+ *orig = fl6->daddr;
+ fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
return orig;
}
* it returns NULL.
* - First fragment header is skipped, not-first ones
* are considered as unparsable.
+ * - Reports the offset field of the final fragment header so it is
+ * possible to tell whether this is a first fragment, later fragment,
+ * or not fragmented.
* - ESP is unparsable for now and considered like
* normal payload protocol.
* - Note also special handling of AUTH header. Thanks to IPsec wizards.
* --ANK (980726)
*/
-int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp)
+int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
+ __be16 *frag_offp)
{
u8 nexthdr = *nexthdrp;
+ *frag_offp = 0;
+
while (ipv6_ext_hdr(nexthdr)) {
struct ipv6_opt_hdr _hdr, *hp;
int hdrlen;
if (fp == NULL)
return -1;
- if (ntohs(*fp) & ~0x7)
+ *frag_offp = *fp;
+ if (ntohs(*frag_offp) & ~0x7)
break;
hdrlen = 8;
} else if (nexthdr == NEXTHDR_AUTH)
if (!ipv6_prefix_equal(&saddr, &r->src.addr,
r->src.plen))
goto again;
- ipv6_addr_copy(&flp6->saddr, &saddr);
+ flp6->saddr = saddr;
}
goto out;
}
int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
int len = skb->len - ptr;
__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+ __be16 frag_off;
if (len < 0)
return 1;
- ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
+ ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
if (ptr < 0)
return 0;
if (nexthdr == IPPROTO_ICMPV6) {
if (likely(off >= 0)) {
hao = (struct ipv6_destopt_hao *)
(skb_network_header(skb) + off);
- ipv6_addr_copy(&tmp, &iph->saddr);
- ipv6_addr_copy(&iph->saddr, &hao->addr);
- ipv6_addr_copy(&hao->addr, &tmp);
+ tmp = iph->saddr;
+ iph->saddr = hao->addr;
+ hao->addr = tmp;
}
}
}
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
- ipv6_addr_copy(&fl6.daddr, &hdr->saddr);
+ fl6.daddr = hdr->saddr;
if (saddr)
- ipv6_addr_copy(&fl6.saddr, saddr);
+ fl6.saddr = *saddr;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
- ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
+ fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
- ipv6_addr_copy(&fl6.saddr, saddr);
+ fl6.saddr = *saddr;
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
int inner_offset;
int hash;
u8 nexthdr;
+ __be16 frag_off;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
return;
nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
if (ipv6_ext_hdr(nexthdr)) {
/* now skip over extension headers */
- inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+ inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+ &nexthdr, &frag_off);
if (inner_offset<0)
return;
} else {
int oif)
{
memset(fl6, 0, sizeof(*fl6));
- ipv6_addr_copy(&fl6->saddr, saddr);
- ipv6_addr_copy(&fl6->daddr, daddr);
+ fl6->saddr = *saddr;
+ fl6->daddr = *daddr;
fl6->flowi6_proto = IPPROTO_ICMPV6;
fl6->fl6_icmp_type = type;
fl6->fl6_icmp_code = 0;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+ fl6.daddr = treq->rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
- ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+ fl6.saddr = treq->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
* request_sock (formerly open request) hash tables.
*/
static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport,
- const u32 rnd, const u16 synq_hsize)
+ const u32 rnd, const u32 synq_hsize)
{
u32 c;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
sin6->sin6_family = AF_INET6;
- ipv6_addr_copy(&sin6->sin6_addr, &np->daddr);
+ sin6->sin6_addr = np->daddr;
sin6->sin6_port = inet_sk(sk)->inet_dport;
/* We do not store received flowlabel for TCP */
sin6->sin6_flowinfo = 0;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = sk->sk_protocol;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = np->saddr;
fl6.flowlabel = np->flow_label;
IP6_ECN_flow_xmit(sk, fl6.flowlabel);
fl6.flowi6_oif = sk->sk_bound_dev_if;
skb_dst_set_noref(skb, dst);
/* Restore final destination back after routing done */
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
+ fl6.daddr = np->daddr;
res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
rcu_read_unlock();
struct fib6_table *table;
table = kzalloc(sizeof(*table), GFP_ATOMIC);
- if (table != NULL) {
+ if (table) {
table->tb6_id = id;
table->tb6_root.leaf = net->ipv6.ip6_null_entry;
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
return tb;
tb = fib6_alloc_table(net, id);
- if (tb != NULL)
+ if (tb)
fib6_link_table(net, tb);
return tb;
s_e = cb->args[1];
w = (void *)cb->args[2];
- if (w == NULL) {
+ if (!w) {
/* New dump:
*
* 1. hook callback destructor.
* 2. allocate and initialize walker.
*/
w = kzalloc(sizeof(*w), GFP_ATOMIC);
- if (w == NULL)
+ if (!w)
return -ENOMEM;
w->func = fib6_dump_node;
cb->args[2] = (long)w;
static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
int addrlen, int plen,
- int offset)
+ int offset, int allow_create,
+ int replace_required)
{
struct fib6_node *fn, *in, *ln;
struct fib6_node *pn = NULL;
* Prefix match
*/
if (plen < fn->fn_bit ||
- !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
+ !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) {
+ if (!allow_create) {
+ if (replace_required) {
+ pr_warn("IPv6: Can't replace route, "
+ "no match found\n");
+ return ERR_PTR(-ENOENT);
+ }
+ pr_warn("IPv6: NLM_F_CREATE should be set "
+ "when creating new route\n");
+ }
goto insert_above;
+ }
/*
* Exact match ?
if (plen == fn->fn_bit) {
/* clean up an intermediate node */
- if ((fn->fn_flags & RTN_RTINFO) == 0) {
+ if (!(fn->fn_flags & RTN_RTINFO)) {
rt6_release(fn->leaf);
fn->leaf = NULL;
}
fn = dir ? fn->right: fn->left;
} while (fn);
+ if (!allow_create) {
+ /* We should not create new node because
+ * NLM_F_REPLACE was specified without NLM_F_CREATE
+ * I assume it is safe to require NLM_F_CREATE when
+ * REPLACE flag is used! Later we may want to remove the
+ * check for replace_required, because according
+ * to netlink specification, NLM_F_CREATE
+ * MUST be specified if new route is created.
+ * That would keep IPv6 consistent with IPv4
+ */
+ if (replace_required) {
+ pr_warn("IPv6: Can't replace route, no match found\n");
+ return ERR_PTR(-ENOENT);
+ }
+ pr_warn("IPv6: NLM_F_CREATE should be set "
+ "when creating new route\n");
+ }
/*
* We walked to the bottom of tree.
* Create new leaf node without children.
ln = node_alloc();
- if (ln == NULL)
+ if (!ln)
return NULL;
ln->fn_bit = plen;
in = node_alloc();
ln = node_alloc();
- if (in == NULL || ln == NULL) {
+ if (!in || !ln) {
if (in)
node_free(in);
if (ln)
ln = node_alloc();
- if (ln == NULL)
+ if (!ln)
return NULL;
ln->fn_bit = plen;
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
+ int replace = (info->nlh &&
+ (info->nlh->nlmsg_flags & NLM_F_REPLACE));
+ int add = (!info->nlh ||
+ (info->nlh->nlmsg_flags & NLM_F_CREATE));
+ int found = 0;
ins = &fn->leaf;
- for (iter = fn->leaf; iter; iter=iter->dst.rt6_next) {
+ for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
/*
* Search for duplicates
*/
/*
* Same priority level
*/
+ if (info->nlh &&
+ (info->nlh->nlmsg_flags & NLM_F_EXCL))
+ return -EEXIST;
+ if (replace) {
+ found++;
+ break;
+ }
- if (iter->rt6i_dev == rt->rt6i_dev &&
+ if (iter->dst.dev == rt->dst.dev &&
iter->rt6i_idev == rt->rt6i_idev &&
ipv6_addr_equal(&iter->rt6i_gateway,
&rt->rt6i_gateway)) {
- if (!(iter->rt6i_flags&RTF_EXPIRES))
+ if (!(iter->rt6i_flags & RTF_EXPIRES))
return -EEXIST;
- iter->rt6i_expires = rt->rt6i_expires;
- if (!(rt->rt6i_flags&RTF_EXPIRES)) {
+ iter->dst.expires = rt->dst.expires;
+ if (!(rt->rt6i_flags & RTF_EXPIRES)) {
iter->rt6i_flags &= ~RTF_EXPIRES;
- iter->rt6i_expires = 0;
+ iter->dst.expires = 0;
}
return -EEXIST;
}
/*
* insert node
*/
+ if (!replace) {
+ if (!add)
+ pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n");
+
+add:
+ rt->dst.rt6_next = iter;
+ *ins = rt;
+ rt->rt6i_node = fn;
+ atomic_inc(&rt->rt6i_ref);
+ inet6_rt_notify(RTM_NEWROUTE, rt, info);
+ info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
+
+ if (!(fn->fn_flags & RTN_RTINFO)) {
+ info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
+ fn->fn_flags |= RTN_RTINFO;
+ }
- rt->dst.rt6_next = iter;
- *ins = rt;
- rt->rt6i_node = fn;
- atomic_inc(&rt->rt6i_ref);
- inet6_rt_notify(RTM_NEWROUTE, rt, info);
- info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
-
- if ((fn->fn_flags & RTN_RTINFO) == 0) {
- info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
- fn->fn_flags |= RTN_RTINFO;
+ } else {
+ if (!found) {
+ if (add)
+ goto add;
+ pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n");
+ return -ENOENT;
+ }
+ *ins = rt;
+ rt->rt6i_node = fn;
+ rt->dst.rt6_next = iter->dst.rt6_next;
+ atomic_inc(&rt->rt6i_ref);
+ inet6_rt_notify(RTM_NEWROUTE, rt, info);
+ rt6_release(iter);
+ if (!(fn->fn_flags & RTN_RTINFO)) {
+ info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
+ fn->fn_flags |= RTN_RTINFO;
+ }
}
return 0;
static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
- (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE)))
+ (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
{
struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
+ int allow_create = 1;
+ int replace_required = 0;
+
+ if (info->nlh) {
+ if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
+ allow_create = 0;
+ if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
+ replace_required = 1;
+ }
+ if (!allow_create && !replace_required)
+ pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
- rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst));
+ rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst),
+ allow_create, replace_required);
+
+ if (IS_ERR(fn)) {
+ err = PTR_ERR(fn);
+ fn = NULL;
+ }
- if (fn == NULL)
+ if (!fn)
goto out;
pn = fn;
if (rt->rt6i_src.plen) {
struct fib6_node *sn;
- if (fn->subtree == NULL) {
+ if (!fn->subtree) {
struct fib6_node *sfn;
/*
/* Create subtree root node */
sfn = node_alloc();
- if (sfn == NULL)
+ if (!sfn)
goto st_failure;
sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
sizeof(struct in6_addr), rt->rt6i_src.plen,
- offsetof(struct rt6_info, rt6i_src));
+ offsetof(struct rt6_info, rt6i_src),
+ allow_create, replace_required);
- if (sn == NULL) {
+ if (!sn) {
/* If it is failed, discard just allocated
root, and then (in st_failure) stale node
in main tree.
} else {
sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
sizeof(struct in6_addr), rt->rt6i_src.plen,
- offsetof(struct rt6_info, rt6i_src));
+ offsetof(struct rt6_info, rt6i_src),
+ allow_create, replace_required);
- if (sn == NULL)
+ if (IS_ERR(sn)) {
+ err = PTR_ERR(sn);
+ sn = NULL;
+ }
+ if (!sn)
goto st_failure;
}
- if (fn->leaf == NULL) {
+ if (!fn->leaf) {
fn->leaf = rt;
atomic_inc(&rt->rt6i_ref);
}
#endif
err = fib6_add_rt2node(fn, rt, info);
-
- if (err == 0) {
+ if (!err) {
fib6_start_gc(info->nl_net, rt);
- if (!(rt->rt6i_flags&RTF_CACHE))
+ if (!(rt->rt6i_flags & RTF_CACHE))
fib6_prune_clones(info->nl_net, pn, rt);
}
*/
struct lookup_args {
- int offset; /* key offset on rt6_info */
+ int offset; /* key offset on rt6_info */
const struct in6_addr *addr; /* search key */
};
fn = next;
continue;
}
-
break;
}
- while(fn) {
+ while (fn) {
if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
struct rt6key *key;
};
fn = fib6_lookup_1(root, daddr ? args : args + 1);
-
- if (fn == NULL || fn->fn_flags & RTN_TL_ROOT)
+ if (!fn || fn->fn_flags & RTN_TL_ROOT)
fn = root;
return fn;
}
#endif
- if (fn && fn->fn_flags&RTN_RTINFO)
+ if (fn && fn->fn_flags & RTN_RTINFO)
return fn;
return NULL;
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
{
- if (fn->fn_flags&RTN_ROOT)
+ if (fn->fn_flags & RTN_ROOT)
return net->ipv6.ip6_null_entry;
- while(fn) {
- if(fn->left)
+ while (fn) {
+ if (fn->left)
return fn->left->leaf;
-
- if(fn->right)
+ if (fn->right)
return fn->right->leaf;
fn = FIB6_SUBTREE(fn);
if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
/* Subtree root (i.e. fn) may have one child */
- || (children && fn->fn_flags&RTN_ROOT)
+ || (children && fn->fn_flags & RTN_ROOT)
#endif
) {
fn->leaf = fib6_find_prefix(net, fn);
#if RT6_DEBUG >= 2
- if (fn->leaf==NULL) {
+ if (!fn->leaf) {
WARN_ON(!fn->leaf);
fn->leaf = net->ipv6.ip6_null_entry;
}
read_lock(&fib6_walker_lock);
FOR_WALKERS(w) {
- if (child == NULL) {
+ if (!child) {
if (w->root == fn) {
w->root = w->node = NULL;
RT6_TRACE("W %p adjusted by delroot 1\n", w);
read_unlock(&fib6_walker_lock);
node_free(fn);
- if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn))
+ if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
return pn;
rt6_release(pn->leaf);
if (w->state == FWS_C && w->leaf == rt) {
RT6_TRACE("walker %p adjusted by delroute\n", w);
w->leaf = rt->dst.rt6_next;
- if (w->leaf == NULL)
+ if (!w->leaf)
w->state = FWS_U;
}
}
rt->dst.rt6_next = NULL;
/* If it was last route, expunge its radix tree node */
- if (fn->leaf == NULL) {
+ if (!fn->leaf) {
fn->fn_flags &= ~RTN_RTINFO;
net->ipv6.rt6_stats->fib_route_nodes--;
fn = fib6_repair_tree(net, fn);
* to still alive ones.
*/
while (fn) {
- if (!(fn->fn_flags&RTN_RTINFO) && fn->leaf == rt) {
+ if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
fn->leaf = fib6_find_prefix(net, fn);
atomic_inc(&fn->leaf->rt6i_ref);
rt6_release(rt);
return -ENOENT;
}
#endif
- if (fn == NULL || rt == net->ipv6.ip6_null_entry)
+ if (!fn || rt == net->ipv6.ip6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
- if (!(rt->rt6i_flags&RTF_CACHE)) {
+ if (!(rt->rt6i_flags & RTF_CACHE)) {
struct fib6_node *pn = fn;
#ifdef CONFIG_IPV6_SUBTREES
/* clones of this route might be in another subtree */
if (rt->rt6i_src.plen) {
- while (!(pn->fn_flags&RTN_ROOT))
+ while (!(pn->fn_flags & RTN_ROOT))
pn = pn->parent;
pn = pn->parent;
}
for (;;) {
fn = w->node;
- if (fn == NULL)
+ if (!fn)
return 0;
if (w->prune && fn != w->root &&
- fn->fn_flags&RTN_RTINFO && w->state < FWS_C) {
+ fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
w->state = FWS_C;
w->leaf = fn->leaf;
}
w->state = FWS_C;
w->leaf = fn->leaf;
case FWS_C:
- if (w->leaf && fn->fn_flags&RTN_RTINFO) {
+ if (w->leaf && fn->fn_flags & RTN_RTINFO) {
int err;
if (w->count < w->skip) {
fib6_walk(&c.w);
}
+void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
+ int prune, void *arg)
+{
+ struct fib6_table *table;
+ struct hlist_node *node;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
+ read_lock_bh(&table->tb6_lock);
+ fib6_clean_tree(net, &table->tb6_root,
+ func, prune, arg);
+ read_unlock_bh(&table->tb6_lock);
+ }
+ }
+ rcu_read_unlock();
+}
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
* only if they are not in use now.
*/
- if (rt->rt6i_flags&RTF_EXPIRES && rt->rt6i_expires) {
- if (time_after(now, rt->rt6i_expires)) {
+ if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
+ if (time_after(now, rt->dst.expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
}
RT6_TRACE("aging clone %p\n", rt);
return -1;
} else if ((rt->rt6i_flags & RTF_GATEWAY) &&
- (!(dst_get_neighbour_raw(&rt->dst)->flags & NTF_ROUTER))) {
+ (!(dst_get_neighbour_noref_raw(&rt->dst)->flags & NTF_ROUTER))) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
return -1;
err = -EINVAL;
goto done;
}
- ipv6_addr_copy(&fl->dst, &freq->flr_dst);
+ fl->dst = freq->flr_dst;
atomic_set(&fl->users, 1);
switch (fl->share) {
case IPV6_FL_S_EXCL:
ipv6_addr_loopback(&hdr->daddr))
goto err;
+ /*
+ * RFC4291 2.7
+ * Multicast addresses must not be used as source addresses in IPv6
+ * packets or appear in any Routing header.
+ */
+ if (ipv6_addr_is_multicast(&hdr->saddr))
+ goto err;
+
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
u8 *ptr = skb_network_header(skb) + opt->ra;
struct icmp6hdr *icmp6;
u8 nexthdr = hdr->nexthdr;
+ __be16 frag_off;
int offset;
/* Check if the value of Router Alert
goto out;
}
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
- &nexthdr);
+ &nexthdr, &frag_off);
if (offset < 0)
goto out;
}
rcu_read_lock();
- neigh = dst_get_neighbour(dst);
+ neigh = dst_get_neighbour_noref(dst);
if (neigh) {
int res = neigh_output(neigh, skb);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
- ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
- ipv6_addr_copy(&hdr->daddr, first_hop);
+ hdr->saddr = fl6->saddr;
+ hdr->daddr = *first_hop;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
hdr->nexthdr = proto;
hdr->hop_limit = np->hop_limit;
- ipv6_addr_copy(&hdr->saddr, saddr);
- ipv6_addr_copy(&hdr->daddr, daddr);
+ hdr->saddr = *saddr;
+ hdr->daddr = *daddr;
return 0;
}
{
struct ipv6hdr *hdr = ipv6_hdr(skb);
u8 nexthdr = hdr->nexthdr;
+ __be16 frag_off;
int offset;
if (ipv6_ext_hdr(nexthdr)) {
- offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
+ offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off);
if (offset < 0)
return 0;
} else
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
- n = dst_get_neighbour(dst);
+ n = dst_get_neighbour_noref(dst);
if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct rt6_info *rt;
static atomic_t ipv6_fragmentation_id;
int old, new;
- if (rt) {
+ if (rt && !(rt->dst.flags & DST_NOPEER)) {
struct inet_peer *peer;
if (!rt->rt6i_peer)
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
+ int hroom, troom;
__be32 frag_id = 0;
int ptr, offset = 0, err=0;
u8 *prevhdr, nexthdr = 0;
*/
*prevhdr = NEXTHDR_FRAGMENT;
+ hroom = LL_RESERVED_SPACE(rt->dst.dev);
+ troom = rt->dst.dev->needed_tailroom;
/*
* Keep copying data until we run out.
* Allocate buffer.
*/
- if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) {
+ if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
+ hroom + troom, GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
*/
ip6_copy_metadata(frag, skb);
- skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev));
+ skb_reserve(frag, hroom);
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
skb_reset_network_header(frag);
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
* dst entry of the nexthop router
*/
rcu_read_lock();
- n = dst_get_neighbour(*dst);
+ n = dst_get_neighbour_noref(*dst);
if (n && !(n->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
if (err)
return ERR_PTR(err);
if (final_dst)
- ipv6_addr_copy(&fl6->daddr, final_dst);
+ fl6->daddr = *final_dst;
if (can_sleep)
fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
if (err)
return ERR_PTR(err);
if (final_dst)
- ipv6_addr_copy(&fl6->daddr, final_dst);
+ fl6->daddr = *final_dst;
if (can_sleep)
fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
if (np->pmtudisc < IPV6_PMTUDISC_DO)
skb->local_df = 1;
- ipv6_addr_copy(final_dst, &fl6->daddr);
+ *final_dst = fl6->daddr;
__skb_pull(skb, skb_network_header_len(skb));
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
- ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
- ipv6_addr_copy(&hdr->daddr, final_dst);
+ hdr->saddr = fl6->saddr;
+ hdr->daddr = *final_dst;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ip6_get_stats(struct net_device *dev)
{
if ((err = register_netdevice(dev)) < 0)
goto failed_free;
+ strcpy(t->parms.name, dev->name);
+
dev_hold(dev);
ip6_tnl_link(ip6n, t);
return t;
rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr,
NULL, 0, 0);
- if (rt && rt->rt6i_dev)
- skb2->dev = rt->rt6i_dev;
+ if (rt && rt->dst.dev)
+ skb2->dev = rt->dst.dev;
icmpv6_send(skb2, rel_type, rel_code, rel_info);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
- ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr);
- ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr);
+ ipv6h->saddr = fl6->saddr;
+ ipv6h->daddr = fl6->daddr;
nf_reset(skb);
pkt_len = skb->len;
err = ip6_local_out(skb);
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
/* Set up flowi template */
- ipv6_addr_copy(&fl6->saddr, &p->laddr);
- ipv6_addr_copy(&fl6->daddr, &p->raddr);
+ fl6->saddr = p->laddr;
+ fl6->daddr = p->raddr;
fl6->flowi6_oif = p->link;
fl6->flowlabel = 0;
if (rt == NULL)
return;
- if (rt->rt6i_dev) {
- dev->hard_header_len = rt->rt6i_dev->hard_header_len +
+ if (rt->dst.dev) {
+ dev->hard_header_len = rt->dst.dev->hard_header_len +
sizeof (struct ipv6hdr);
- dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr);
+ dev->mtu = rt->dst.dev->mtu - sizeof (struct ipv6hdr);
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu-=8;
static int
ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
{
- ipv6_addr_copy(&t->parms.laddr, &p->laddr);
- ipv6_addr_copy(&t->parms.raddr, &p->raddr);
+ t->parms.laddr = p->laddr;
+ t->parms.raddr = p->raddr;
t->parms.flags = p->flags;
t->parms.hop_limit = p->hop_limit;
t->parms.encap_limit = p->encap_limit;
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
- strcpy(t->parms.name, dev->name);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
static int __net_init ip6_tnl_init_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ struct ip6_tnl *t = NULL;
int err;
ip6n->tnls[0] = ip6n->tnls_wc;
err = register_netdev(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
+
+ t = netdev_priv(ip6n->fb_tnl_dev);
+
+ strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
return 0;
err_register:
msg->im6_msgtype = MRT6MSG_WHOLEPKT;
msg->im6_mif = mrt->mroute_reg_vif_num;
msg->im6_pad = 0;
- ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
- ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
+ msg->im6_src = ipv6_hdr(pkt)->saddr;
+ msg->im6_dst = ipv6_hdr(pkt)->daddr;
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else
msg->im6_msgtype = assert;
msg->im6_mif = mifi;
msg->im6_pad = 0;
- ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
- ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
+ msg->im6_src = ipv6_hdr(pkt)->saddr;
+ msg->im6_dst = ipv6_hdr(pkt)->daddr;
skb_dst_set(skb, dst_clone(skb_dst(pkt)));
skb->ip_summed = CHECKSUM_UNNECESSARY;
iph->payload_len = 0;
iph->nexthdr = IPPROTO_NONE;
iph->hop_limit = 0;
- ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr);
- ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr);
+ iph->saddr = rt->rt6i_src.addr;
+ iph->daddr = rt->rt6i_dst.addr;
err = ip6mr_cache_unresolved(mrt, vif, skb2);
read_unlock(&mrt_lock);
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
- ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr);
+ np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
- np->mcast_hops = val;
+ np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
retv = 0;
break;
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
- np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
- ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
+ src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
- np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
- ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
+ src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
return -ENOMEM;
mc_lst->next = NULL;
- ipv6_addr_copy(&mc_lst->addr, addr);
+ mc_lst->addr = *addr;
rcu_read_lock();
if (ifindex == 0) {
struct rt6_info *rt;
rt = rt6_lookup(net, addr, NULL, 0, 0);
if (rt) {
- dev = rt->rt6i_dev;
+ dev = rt->dst.dev;
dst_release(&rt->dst);
}
} else
struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0);
if (rt) {
- dev = rt->rt6i_dev;
+ dev = rt->dst.dev;
dev_hold(dev);
dst_release(&rt->dst);
}
setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc);
- ipv6_addr_copy(&mc->mca_addr, addr);
+ mc->mca_addr = *addr;
mc->idev = idev; /* (reference taken) */
mc->mca_users = 1;
/* mca_stamp should be updated upon changes */
struct mld2_report *pmr;
struct in6_addr addr_buf;
const struct in6_addr *saddr;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
int err;
u8 ra[8] = { IPPROTO_ICMPV6, 0,
IPV6_TLV_ROUTERALERT, 2, 0, 0,
IPV6_TLV_PADN, 0 };
/* we assume size > sizeof(ra) here */
- size += LL_ALLOCATED_SPACE(dev);
+ size += hlen + tlen;
/* limit our allocations to order-0 page */
size = min_t(int, size, SKB_MAX_ORDER(0, 0));
skb = sock_alloc_send_skb(sk, size, 1, &err);
if (!skb)
return NULL;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
/* <draft-ietf-magma-mld-source-05.txt>:
csum_partial(skb_transport_header(skb),
mldlen, 0));
- dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
-
- if (!dst) {
- err = -ENOMEM;
- goto err_out;
- }
-
icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
skb->dev->ifindex);
+ dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
- dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
err = 0;
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
struct mld_msg *hdr;
const struct in6_addr *snd_addr, *saddr;
struct in6_addr addr_buf;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
int err, len, payload_len, full_len;
u8 ra[8] = { IPPROTO_ICMPV6, 0,
IPV6_TLV_ROUTERALERT, 2, 0, 0,
IPSTATS_MIB_OUT, full_len);
rcu_read_unlock();
- skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + full_len, 1, &err);
+ skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err);
if (skb == NULL) {
rcu_read_lock();
return;
}
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
/* <draft-ietf-magma-mld-source-05.txt>:
hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg));
memset(hdr, 0, sizeof(struct mld_msg));
hdr->mld_type = type;
- ipv6_addr_copy(&hdr->mld_mca, addr);
+ hdr->mld_mca = *addr;
hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len,
IPPROTO_ICMPV6,
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
- dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
- if (!dst) {
- err = -ENOMEM;
- goto err_out;
- }
-
icmpv6_flow_init(sk, &fl6, type,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
skb->dev->ifindex);
-
- dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+ dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err_out;
* Add multicast single-source filter to the interface list
*/
static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode,
- const struct in6_addr *psfsrc, int delta)
+ const struct in6_addr *psfsrc)
{
struct ip6_sf_list *psf, *psf_prev;
pmc->mca_sfcount[sfmode]++;
err = 0;
for (i=0; i<sfcount; i++) {
- err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i], delta);
+ err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]);
if (err)
break;
}
mip6_report_rl.stamp.tv_sec = stamp->tv_sec;
mip6_report_rl.stamp.tv_usec = stamp->tv_usec;
mip6_report_rl.iif = iif;
- ipv6_addr_copy(&mip6_report_rl.src, src);
- ipv6_addr_copy(&mip6_report_rl.dst, dst);
+ mip6_report_rl.src = *src;
+ mip6_report_rl.dst = *dst;
allow = 1;
}
spin_unlock_bh(&mip6_report_rl.lock);
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
- __u32 rnd);
+ __u32 *hash_rnd);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
struct neigh_table nd_tbl = {
.family = AF_INET6,
- .entry_size = sizeof(struct neighbour) + sizeof(struct in6_addr),
.key_len = sizeof(struct in6_addr),
.hash = ndisc_hash,
.constructor = ndisc_constructor,
.gc_staletime = 60 * HZ,
.reachable_time = ND_REACHABLE_TIME,
.delay_probe_time = 5 * HZ,
- .queue_len = 3,
+ .queue_len_bytes = 64*1024,
.ucast_probes = 3,
.mcast_probes = 3,
.anycast_delay = 1 * HZ,
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
- __u32 hash_rnd)
+ __u32 *hash_rnd)
{
- const u32 *p32 = pkey;
- u32 addr_hash, i;
-
- addr_hash = 0;
- for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++)
- addr_hash ^= *p32++;
-
- return jhash_2words(addr_hash, dev->ifindex, hash_rnd);
+ return ndisc_hashfn(pkey, dev, hash_rnd);
}
static int ndisc_constructor(struct neighbour *neigh)
struct sock *sk = net->ipv6.ndisc_sk;
struct sk_buff *skb;
struct icmp6hdr *hdr;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
int len;
int err;
u8 *opt;
skb = sock_alloc_send_skb(sk,
(MAX_HEADER + sizeof(struct ipv6hdr) +
- len + LL_ALLOCATED_SPACE(dev)),
+ len + hlen + tlen),
1, &err);
if (!skb) {
ND_PRINTK0(KERN_ERR
return NULL;
}
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);
skb->transport_header = skb->tail;
opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
if (target) {
- ipv6_addr_copy((struct in6_addr *)opt, target);
+ *(struct in6_addr *)opt = *target;
opt += sizeof(*target);
}
type = icmp6h->icmp6_type;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
-
- dst = icmp6_dst_alloc(dev, neigh, daddr);
- if (!dst) {
- kfree_skb(skb);
- return;
- }
-
- dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+ dst = icmp6_dst_alloc(dev, neigh, &fl6);
if (IS_ERR(dst)) {
kfree_skb(skb);
return;
rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
if (rt)
- neigh = dst_get_neighbour(&rt->dst);
+ neigh = dst_get_neighbour_noref(&rt->dst);
if (rt && lifetime == 0) {
neigh_clone(neigh);
return;
}
- neigh = dst_get_neighbour(&rt->dst);
+ neigh = dst_get_neighbour_noref(&rt->dst);
if (neigh == NULL) {
ND_PRINTK0(KERN_ERR
"ICMPv6 RA: %s() got default router without neighbour.\n",
}
if (rt)
- rt->rt6i_expires = jiffies + (HZ * lifetime);
+ rt->dst.expires = jiffies + (HZ * lifetime);
if (ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
for (p = ndopts.nd_opts_pi;
p;
p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) {
- addrconf_prefix_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3);
+ addrconf_prefix_rcv(skb->dev, (u8 *)p,
+ (p->nd_opt_len) << 3,
+ ndopts.nd_opts_src_lladdr != NULL);
}
}
struct inet6_dev *idev;
struct flowi6 fl6;
u8 *opt;
+ int hlen, tlen;
int rd_len;
int err;
u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
}
if (!rt->rt6i_peer)
rt6_bind_peer(rt, 1);
- if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
+ if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
goto release;
if (dev->addr_len) {
rd_len &= ~0x7;
len += rd_len;
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
buff = sock_alloc_send_skb(sk,
(MAX_HEADER + sizeof(struct ipv6hdr) +
- len + LL_ALLOCATED_SPACE(dev)),
+ len + hlen + tlen),
1, &err);
if (buff == NULL) {
ND_PRINTK0(KERN_ERR
goto release;
}
- skb_reserve(buff, LL_RESERVED_SPACE(dev));
+ skb_reserve(buff, hlen);
ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr,
IPPROTO_ICMPV6, len);
*/
addrp = (struct in6_addr *)(icmph + 1);
- ipv6_addr_copy(addrp, target);
+ *addrp = *target;
addrp++;
- ipv6_addr_copy(addrp, &ipv6_hdr(skb)->daddr);
+ *addrp = ipv6_hdr(skb)->daddr;
opt = (u8*) (addrp + 1);
To compile it as a module, choose M here. If unsure, say N.
+config IP6_NF_MATCH_RPFILTER
+ tristate '"rpfilter" reverse path filter match support'
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option allows you to match packets whose replies would
+ go out via the interface the packet came in.
+
+ To compile it as a module, choose M here. If unsure, say N.
+ The module will be called ip6t_rpfilter.
+
config IP6_NF_MATCH_RT
tristate '"rt" Routing header match support'
depends on NETFILTER_ADVANCED
config IP6_NF_RAW
tristate 'raw table support (required for TRACE)'
- depends on NETFILTER_ADVANCED
help
This option adds a `raw' table to ip6tables. This table is the very
first in the netfilter framework and hooks in at the PREROUTING
obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o
obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o
obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o
+obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o
obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
# targets
int status, type, pid, flags;
unsigned int nlmsglen, skblen;
struct nlmsghdr *nlh;
+ bool enable_timestamp = false;
skblen = skb->len;
if (skblen < sizeof(*nlh))
RCV_SKB_FAIL(-EBUSY);
}
} else {
- net_enable_timestamp();
+ enable_timestamp = true;
peer_pid = pid;
}
spin_unlock_bh(&queue_lock);
+ if (enable_timestamp)
+ net_enable_timestamp();
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
const __u8 tclass = DEFAULT_TOS_VALUE;
struct dst_entry *dst = NULL;
u8 proto;
+ __be16 frag_off;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
}
proto = oip6h->nexthdr;
- tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);
+ tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
pr_debug("Cannot get TCP header.\n");
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.saddr, &oip6h->daddr);
- ipv6_addr_copy(&fl6.daddr, &oip6h->saddr);
+ fl6.saddr = oip6h->daddr;
+ fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph.dest;
fl6.fl6_dport = otcph.source;
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
*(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20));
ip6h->hop_limit = ip6_dst_hoplimit(dst);
ip6h->nexthdr = IPPROTO_TCP;
- ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr);
- ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr);
+ ip6h->saddr = oip6h->daddr;
+ ip6h->daddr = oip6h->saddr;
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
/* Truncate to length (no data) */
--- /dev/null
+/*
+ * Copyright (c) 2011 Florian Westphal <fw@strlen.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/route.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+
+#include <linux/netfilter/xt_rpfilter.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("Xtables: IPv6 reverse path filter match");
+
+static bool rpfilter_addr_unicast(const struct in6_addr *addr)
+{
+ int addr_type = ipv6_addr_type(addr);
+ return addr_type & IPV6_ADDR_UNICAST;
+}
+
+static bool rpfilter_lookup_reverse6(const struct sk_buff *skb,
+ const struct net_device *dev, u8 flags)
+{
+ struct rt6_info *rt;
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ bool ret = false;
+ struct flowi6 fl6 = {
+ .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
+ .flowi6_proto = iph->nexthdr,
+ .daddr = iph->saddr,
+ };
+ int lookup_flags;
+
+ if (rpfilter_addr_unicast(&iph->daddr)) {
+ memcpy(&fl6.saddr, &iph->daddr, sizeof(struct in6_addr));
+ lookup_flags = RT6_LOOKUP_F_HAS_SADDR;
+ } else {
+ lookup_flags = 0;
+ }
+
+ fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
+ if ((flags & XT_RPFILTER_LOOSE) == 0) {
+ fl6.flowi6_oif = dev->ifindex;
+ lookup_flags |= RT6_LOOKUP_F_IFACE;
+ }
+
+ rt = (void *) ip6_route_lookup(dev_net(dev), &fl6, lookup_flags);
+ if (rt->dst.error)
+ goto out;
+
+ if (rt->rt6i_flags & (RTF_REJECT|RTF_ANYCAST))
+ goto out;
+
+ if (rt->rt6i_flags & RTF_LOCAL) {
+ ret = flags & XT_RPFILTER_ACCEPT_LOCAL;
+ goto out;
+ }
+
+ if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+ ret = true;
+ out:
+ dst_release(&rt->dst);
+ return ret;
+}
+
+static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_rpfilter_info *info = par->matchinfo;
+ int saddrtype;
+ struct ipv6hdr *iph;
+ bool invert = info->flags & XT_RPFILTER_INVERT;
+
+ if (par->in->flags & IFF_LOOPBACK)
+ return true ^ invert;
+
+ iph = ipv6_hdr(skb);
+ saddrtype = ipv6_addr_type(&iph->saddr);
+ if (unlikely(saddrtype == IPV6_ADDR_ANY))
+ return true ^ invert; /* not routable: forward path will drop it */
+
+ return rpfilter_lookup_reverse6(skb, par->in, info->flags) ^ invert;
+}
+
+static int rpfilter_check(const struct xt_mtchk_param *par)
+{
+ const struct xt_rpfilter_info *info = par->matchinfo;
+ unsigned int options = ~XT_RPFILTER_OPTION_MASK;
+
+ if (info->flags & options) {
+ pr_info("unknown options encountered");
+ return -EINVAL;
+ }
+
+ if (strcmp(par->table, "mangle") != 0 &&
+ strcmp(par->table, "raw") != 0) {
+ pr_info("match only valid in the \'raw\' "
+ "or \'mangle\' tables, not \'%s\'.\n", par->table);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match rpfilter_mt_reg __read_mostly = {
+ .name = "rpfilter",
+ .family = NFPROTO_IPV6,
+ .checkentry = rpfilter_check,
+ .match = rpfilter_mt,
+ .matchsize = sizeof(struct xt_rpfilter_info),
+ .hooks = (1 << NF_INET_PRE_ROUTING),
+ .me = THIS_MODULE
+};
+
+static int __init rpfilter_mt_init(void)
+{
+ return xt_register_match(&rpfilter_mt_reg);
+}
+
+static void __exit rpfilter_mt_exit(void)
+{
+ xt_unregister_match(&rpfilter_mt_reg);
+}
+
+module_init(rpfilter_mt_init);
+module_exit(rpfilter_mt_exit);
static struct nf_hook_ops *filter_ops __read_mostly;
/* Default to forward because I got too much mail already. */
-static int forward = NF_ACCEPT;
+static bool forward = NF_ACCEPT;
module_param(forward, bool, 0000);
static int __net_init ip6table_filter_net_init(struct net *net)
SNMP_MIB_SENTINEL
};
-/* can be called either with percpu mib (pcpumib != NULL),
- * or shared one (smib != NULL)
- */
-static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib,
- atomic_long_t *smib)
+static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib)
{
char name[32];
int i;
snprintf(name, sizeof(name), "Icmp6%s%s",
i & 0x100 ? "Out" : "In", p);
seq_printf(seq, "%-32s\t%lu\n", name,
- pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i));
+ atomic_long_read(smib + i));
}
/* print by number (nonzero only) - ICMPMsgStat format */
for (i = 0; i < ICMP6MSG_MIB_MAX; i++) {
unsigned long val;
- val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i);
+ val = atomic_long_read(smib + i);
if (!val)
continue;
snprintf(name, sizeof(name), "Icmp6%sType%u",
snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
NULL, snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq,
- (void __percpu **)net->mib.icmpv6msg_statistics, NULL);
+ snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs);
snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
NULL, snmp6_udp6_list);
snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
snmp6_ipstats_list);
snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs,
snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs);
+ snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs);
return 0;
}
}
inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
- ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+ np->rcv_saddr = addr->sin6_addr;
if (!(addr_type & IPV6_ADDR_MULTICAST))
- ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+ np->saddr = addr->sin6_addr;
err = 0;
out_unlock:
rcu_read_unlock();
}
/* Charge it to the socket. */
- if (ip_queue_rcv_skb(sk, skb) < 0) {
+ skb_dst_drop(skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
if (sin6) {
sin6->sin6_family = AF_INET6;
sin6->sin6_port = 0;
- ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
+ sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = 0;
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
struct sk_buff *skb;
int err;
struct rt6_info *rt = (struct rt6_info *)*dstp;
+ int hlen = LL_RESERVED_SPACE(rt->dst.dev);
+ int tlen = rt->dst.dev->needed_tailroom;
if (length > rt->dst.dev->mtu) {
ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
goto out;
skb = sock_alloc_send_skb(sk,
- length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+ length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
- skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+ skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
goto out;
if (!ipv6_addr_any(daddr))
- ipv6_addr_copy(&fl6.daddr, daddr);
+ fl6.daddr = *daddr;
else
fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.saddr = np->saddr;
final_p = fl6_update_dst(&fl6, opt, &final);
fq->id = arg->id;
fq->user = arg->user;
- ipv6_addr_copy(&fq->saddr, arg->src);
- ipv6_addr_copy(&fq->daddr, arg->dst);
+ fq->saddr = *arg->src;
+ fq->daddr = *arg->dst;
}
EXPORT_SYMBOL(ip6_frag_init);
#include <linux/sysctl.h>
#endif
-/* Set to 3 to get tracing. */
-#define RT6_DEBUG 2
-
-#if RT6_DEBUG >= 3
-#define RDBG(x) printk x
-#define RT6_TRACE(x...) printk(KERN_DEBUG x)
-#else
-#define RDBG(x)
-#define RT6_TRACE(x...) do { ; } while (0)
-#endif
-
static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
const struct in6_addr *dest);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
-static unsigned int ip6_default_mtu(const struct dst_entry *dst);
+static unsigned int ip6_mtu(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr)
{
- return __neigh_lookup_errno(&nd_tbl, daddr, dst->dev);
+ struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr);
+ if (n)
+ return n;
+ return neigh_create(&nd_tbl, daddr, dst->dev);
+}
+
+static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev)
+{
+ struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway);
+ if (!n) {
+ n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev);
+ if (IS_ERR(n))
+ return PTR_ERR(n);
+ }
+ dst_set_neighbour(&rt->dst, n);
+
+ return 0;
}
static struct dst_ops ip6_dst_ops_template = {
.gc_thresh = 1024,
.check = ip6_dst_check,
.default_advmss = ip6_default_advmss,
- .default_mtu = ip6_default_mtu,
+ .mtu = ip6_mtu,
.cow_metrics = ipv6_cow_metrics,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.neigh_lookup = ip6_neigh_lookup,
};
-static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
{
- return 0;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst->dev->mtu;
}
static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
.protocol = cpu_to_be16(ETH_P_IPV6),
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
- .default_mtu = ip6_blackhole_default_mtu,
+ .mtu = ip6_blackhole_mtu,
.default_advmss = ip6_default_advmss,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
.cow_metrics = ip6_rt_blackhole_cow_metrics,
{
struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
- if (rt != NULL)
+ if (rt)
memset(&rt->rt6i_table, 0,
- sizeof(*rt) - sizeof(struct dst_entry));
+ sizeof(*rt) - sizeof(struct dst_entry));
return rt;
}
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
- if (idev != NULL) {
+ if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
struct net_device *loopback_dev =
dev_net(dev)->loopback_dev;
- if (dev != loopback_dev && idev != NULL && idev->dev == dev) {
+ if (dev != loopback_dev && idev && idev->dev == dev) {
struct inet6_dev *loopback_idev =
in6_dev_get(loopback_dev);
- if (loopback_idev != NULL) {
+ if (loopback_idev) {
rt->rt6i_idev = loopback_idev;
in6_dev_put(idev);
}
static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
return (rt->rt6i_flags & RTF_EXPIRES) &&
- time_after(jiffies, rt->rt6i_expires);
+ time_after(jiffies, rt->dst.expires);
}
static inline int rt6_need_strict(const struct in6_addr *daddr)
goto out;
for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) {
- struct net_device *dev = sprt->rt6i_dev;
+ struct net_device *dev = sprt->dst.dev;
if (oif) {
if (dev->ifindex == oif)
return sprt;
if (dev->flags & IFF_LOOPBACK) {
- if (sprt->rt6i_idev == NULL ||
+ if (!sprt->rt6i_idev ||
sprt->rt6i_idev->dev->ifindex != oif) {
if (flags & RT6_LOOKUP_F_IFACE && oif)
continue;
* to no more than one per minute.
*/
rcu_read_lock();
- neigh = rt ? dst_get_neighbour(&rt->dst) : NULL;
+ neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL;
if (!neigh || (neigh->nud_state & NUD_VALID))
goto out;
read_lock_bh(&neigh->lock);
target = (struct in6_addr *)&neigh->primary_key;
addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
+ ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
} else {
read_unlock_bh(&neigh->lock);
}
*/
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
- struct net_device *dev = rt->rt6i_dev;
+ struct net_device *dev = rt->dst.dev;
if (!oif || dev->ifindex == oif)
return 2;
if ((dev->flags & IFF_LOOPBACK) &&
int m;
rcu_read_lock();
- neigh = dst_get_neighbour(&rt->dst);
+ neigh = dst_get_neighbour_noref(&rt->dst);
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
m = 1;
struct rt6_info *match, *rt0;
struct net *net;
- RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
- __func__, fn->leaf, oif);
-
rt0 = fn->rr_ptr;
if (!rt0)
fn->rr_ptr = rt0 = fn->leaf;
fn->rr_ptr = next;
}
- RT6_TRACE("%s() => %p\n",
- __func__, match);
-
- net = dev_net(rt0->rt6i_dev);
+ net = dev_net(rt0->dst.dev);
return match ? match : net->ipv6.ip6_null_entry;
}
if (!addrconf_finite_timeout(lifetime)) {
rt->rt6i_flags &= ~RTF_EXPIRES;
} else {
- rt->rt6i_expires = jiffies + HZ * lifetime;
+ rt->dst.expires = jiffies + HZ * lifetime;
rt->rt6i_flags |= RTF_EXPIRES;
}
dst_release(&rt->dst);
goto restart; \
} \
} \
-} while(0)
+} while (0)
static struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
}
+struct dst_entry * ip6_route_lookup(struct net *net, struct flowi6 *fl6,
+ int flags)
+{
+ return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup);
+}
+EXPORT_SYMBOL_GPL(ip6_route_lookup);
+
struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
const struct in6_addr *saddr, int oif, int strict)
{
int ip6_ins_rt(struct rt6_info *rt)
{
struct nl_info info = {
- .nl_net = dev_net(rt->rt6i_dev),
+ .nl_net = dev_net(rt->dst.dev),
};
return __ip6_ins_rt(rt, &info);
}
rt = ip6_rt_copy(ort, daddr);
if (rt) {
- struct neighbour *neigh;
int attempts = !in_softirq();
- if (!(rt->rt6i_flags&RTF_GATEWAY)) {
- if (rt->rt6i_dst.plen != 128 &&
+ if (!(rt->rt6i_flags & RTF_GATEWAY)) {
+ if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
- ipv6_addr_copy(&rt->rt6i_gateway, daddr);
+ rt->rt6i_gateway = *daddr;
}
rt->rt6i_flags |= RTF_CACHE;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
- ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
+ rt->rt6i_src.addr = *saddr;
rt->rt6i_src.plen = 128;
}
#endif
retry:
- neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
- if (IS_ERR(neigh)) {
- struct net *net = dev_net(rt->rt6i_dev);
+ if (rt6_bind_neighbour(rt, rt->dst.dev)) {
+ struct net *net = dev_net(rt->dst.dev);
int saved_rt_min_interval =
net->ipv6.sysctl.ip6_rt_gc_min_interval;
int saved_rt_elasticity =
dst_free(&rt->dst);
return NULL;
}
- dst_set_neighbour(&rt->dst, neigh);
-
}
return rt;
if (rt) {
rt->rt6i_flags |= RTF_CACHE;
- dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst)));
+ dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst)));
}
return rt;
}
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+ if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
.flowi6_iif = skb->dev->ifindex,
.daddr = iph->daddr,
.saddr = iph->saddr,
- .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
+ .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
};
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
- rt->rt6i_expires = 0;
+ rt->dst.expires = 0;
- ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
+ rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
rt->rt6i_metric = 0;
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
- if (rt->rt6i_flags&RTF_CACHE) {
+ if (rt->rt6i_flags & RTF_CACHE) {
dst_set_expires(&rt->dst, 0);
rt->rt6i_flags |= RTF_EXPIRES;
} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
return mtu;
}
-static unsigned int ip6_default_mtu(const struct dst_entry *dst)
+static unsigned int ip6_mtu(const struct dst_entry *dst)
{
- unsigned int mtu = IPV6_MIN_MTU;
struct inet6_dev *idev;
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ if (mtu)
+ return mtu;
+
+ mtu = IPV6_MIN_MTU;
rcu_read_lock();
idev = __in6_dev_get(dst->dev);
struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct neighbour *neigh,
- const struct in6_addr *addr)
+ struct flowi6 *fl6)
{
+ struct dst_entry *dst;
struct rt6_info *rt;
struct inet6_dev *idev = in6_dev_get(dev);
struct net *net = dev_net(dev);
- if (unlikely(idev == NULL))
+ if (unlikely(!idev))
return NULL;
rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
- if (unlikely(rt == NULL)) {
+ if (unlikely(!rt)) {
in6_dev_put(idev);
+ dst = ERR_PTR(-ENOMEM);
goto out;
}
if (neigh)
neigh_hold(neigh);
else {
- neigh = ndisc_get_neigh(dev, addr);
- if (IS_ERR(neigh))
- neigh = NULL;
+ neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr);
+ if (IS_ERR(neigh)) {
+ dst_free(&rt->dst);
+ return ERR_CAST(neigh);
+ }
}
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
dst_set_neighbour(&rt->dst, neigh);
atomic_set(&rt->dst.__refcnt, 1);
- ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
+ rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
rt->rt6i_idev = idev;
dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
fib6_force_start_gc(net);
+ dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
+
out:
- return &rt->dst;
+ return dst;
}
int icmp6_dst_gc(void)
if (cfg->fc_metric == 0)
cfg->fc_metric = IP6_RT_PRIO_USER;
- table = fib6_new_table(net, cfg->fc_table);
- if (table == NULL) {
- err = -ENOBUFS;
- goto out;
+ err = -ENOBUFS;
+ if (cfg->fc_nlinfo.nlh &&
+ !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
+ table = fib6_get_table(net, cfg->fc_table);
+ if (!table) {
+ printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n");
+ table = fib6_new_table(net, cfg->fc_table);
+ }
+ } else {
+ table = fib6_new_table(net, cfg->fc_table);
}
+ if (!table)
+ goto out;
+
rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
- if (rt == NULL) {
+ if (!rt) {
err = -ENOMEM;
goto out;
}
rt->dst.obsolete = -1;
- rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ?
+ rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ?
jiffies + clock_t_to_jiffies(cfg->fc_expires) :
0;
they would result in kernel looping; promote them to reject routes
*/
if ((cfg->fc_flags & RTF_REJECT) ||
- (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK)
- && !(cfg->fc_flags&RTF_LOCAL))) {
+ (dev && (dev->flags & IFF_LOOPBACK) &&
+ !(addr_type & IPV6_ADDR_LOOPBACK) &&
+ !(cfg->fc_flags & RTF_LOCAL))) {
/* hold loopback dev/idev if we haven't done so. */
if (dev != net->loopback_dev) {
if (dev) {
int gwa_type;
gw_addr = &cfg->fc_gateway;
- ipv6_addr_copy(&rt->rt6i_gateway, gw_addr);
+ rt->rt6i_gateway = *gw_addr;
gwa_type = ipv6_addr_type(gw_addr);
if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
some exceptions. --ANK
*/
err = -EINVAL;
- if (!(gwa_type&IPV6_ADDR_UNICAST))
+ if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
err = -EHOSTUNREACH;
- if (grt == NULL)
+ if (!grt)
goto out;
if (dev) {
- if (dev != grt->rt6i_dev) {
+ if (dev != grt->dst.dev) {
dst_release(&grt->dst);
goto out;
}
} else {
- dev = grt->rt6i_dev;
+ dev = grt->dst.dev;
idev = grt->rt6i_idev;
dev_hold(dev);
in6_dev_hold(grt->rt6i_idev);
}
- if (!(grt->rt6i_flags&RTF_GATEWAY))
+ if (!(grt->rt6i_flags & RTF_GATEWAY))
err = 0;
dst_release(&grt->dst);
goto out;
}
err = -EINVAL;
- if (dev == NULL || (dev->flags&IFF_LOOPBACK))
+ if (!dev || (dev->flags & IFF_LOOPBACK))
goto out;
}
err = -ENODEV;
- if (dev == NULL)
+ if (!dev)
goto out;
if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
err = -EINVAL;
goto out;
}
- ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc);
+ rt->rt6i_prefsrc.addr = cfg->fc_prefsrc;
rt->rt6i_prefsrc.plen = 128;
} else
rt->rt6i_prefsrc.plen = 0;
if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
- struct neighbour *n = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
- if (IS_ERR(n)) {
- err = PTR_ERR(n);
+ err = rt6_bind_neighbour(rt, dev);
+ if (err)
goto out;
- }
- dst_set_neighbour(&rt->dst, n);
}
rt->rt6i_flags = cfg->fc_flags;
{
int err;
struct fib6_table *table;
- struct net *net = dev_net(rt->rt6i_dev);
+ struct net *net = dev_net(rt->dst.dev);
if (rt == net->ipv6.ip6_null_entry)
return -ENOENT;
int ip6_del_rt(struct rt6_info *rt)
{
struct nl_info info = {
- .nl_net = dev_net(rt->rt6i_dev),
+ .nl_net = dev_net(rt->dst.dev),
};
return __ip6_del_rt(rt, &info);
}
int err = -ESRCH;
table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
- if (table == NULL)
+ if (!table)
return err;
read_lock_bh(&table->tb6_lock);
if (fn) {
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
if (cfg->fc_ifindex &&
- (rt->rt6i_dev == NULL ||
- rt->rt6i_dev->ifindex != cfg->fc_ifindex))
+ (!rt->dst.dev ||
+ rt->dst.dev->ifindex != cfg->fc_ifindex))
continue;
if (cfg->fc_flags & RTF_GATEWAY &&
!ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
continue;
if (!(rt->rt6i_flags & RTF_GATEWAY))
continue;
- if (fl6->flowi6_oif != rt->rt6i_dev->ifindex)
+ if (fl6->flowi6_oif != rt->dst.dev->ifindex)
continue;
if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
continue;
},
};
- ipv6_addr_copy(&rdfl.gateway, gateway);
+ rdfl.gateway = *gateway;
if (rt6_need_strict(dest))
flags |= RT6_LOOKUP_F_IFACE;
dst_confirm(&rt->dst);
/* Duplicate redirect: silently ignore. */
- if (neigh == dst_get_neighbour_raw(&rt->dst))
+ if (neigh == dst_get_neighbour_noref_raw(&rt->dst))
goto out;
nrt = ip6_rt_copy(rt, dest);
- if (nrt == NULL)
+ if (!nrt)
goto out;
nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
if (on_link)
nrt->rt6i_flags &= ~RTF_GATEWAY;
- ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
+ nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
if (ip6_ins_rt(nrt))
netevent.new = &nrt->dst;
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
- if (rt->rt6i_flags&RTF_CACHE) {
+ if (rt->rt6i_flags & RTF_CACHE) {
ip6_del_rt(rt);
return;
}
int allfrag = 0;
again:
rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
- if (rt == NULL)
+ if (!rt)
return;
if (rt6_check_expired(rt)) {
1. It is connected route. Action: COW
2. It is gatewayed route or NONEXTHOP route. Action: clone it.
*/
- if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+ if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, daddr, saddr);
else
nrt = rt6_alloc_clone(rt, daddr);
static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
const struct in6_addr *dest)
{
- struct net *net = dev_net(ort->rt6i_dev);
+ struct net *net = dev_net(ort->dst.dev);
struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
ort->dst.dev, 0);
rt->dst.output = ort->dst.output;
rt->dst.flags |= DST_HOST;
- ipv6_addr_copy(&rt->rt6i_dst.addr, dest);
+ rt->rt6i_dst.addr = *dest;
rt->rt6i_dst.plen = 128;
dst_copy_metrics(&rt->dst, &ort->dst);
rt->dst.error = ort->dst.error;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->rt6i_expires = 0;
+ rt->dst.expires = 0;
- ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
+ rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
rt->rt6i_metric = 0;
struct fib6_table *table;
table = fib6_get_table(net, RT6_TABLE_INFO);
- if (table == NULL)
+ if (!table)
return NULL;
write_lock_bh(&table->tb6_lock);
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_dev->ifindex != ifindex)
+ if (rt->dst.dev->ifindex != ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
.fc_nlinfo.nl_net = net,
};
- ipv6_addr_copy(&cfg.fc_dst, prefix);
- ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
+ cfg.fc_dst = *prefix;
+ cfg.fc_gateway = *gwaddr;
/* We should treat it as a default route if prefix length is 0. */
if (!prefixlen)
struct fib6_table *table;
table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
- if (table == NULL)
+ if (!table)
return NULL;
write_lock_bh(&table->tb6_lock);
for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
- if (dev == rt->rt6i_dev &&
+ if (dev == rt->dst.dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
ipv6_addr_equal(&rt->rt6i_gateway, addr))
break;
.fc_nlinfo.nl_net = dev_net(dev),
};
- ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
+ cfg.fc_gateway = *gwaddr;
ip6_route_add(&cfg);
/* NOTE: Keep consistent with rt6_get_dflt_router */
table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (table == NULL)
+ if (!table)
return;
restart:
cfg->fc_nlinfo.nl_net = net;
- ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
- ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
- ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
+ cfg->fc_dst = rtmsg->rtmsg_dst;
+ cfg->fc_src = rtmsg->rtmsg_src;
+ cfg->fc_gateway = rtmsg->rtmsg_gateway;
}
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr,
- int anycast)
+ bool anycast)
{
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
net->loopback_dev, 0);
- struct neighbour *neigh;
+ int err;
- if (rt == NULL) {
+ if (!rt) {
if (net_ratelimit())
pr_warning("IPv6: Maximum number of routes reached,"
" consider increasing route/max_size.\n");
rt->rt6i_flags |= RTF_ANYCAST;
else
rt->rt6i_flags |= RTF_LOCAL;
- neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
- if (IS_ERR(neigh)) {
+ err = rt6_bind_neighbour(rt, rt->dst.dev);
+ if (err) {
dst_free(&rt->dst);
-
- return ERR_CAST(neigh);
+ return ERR_PTR(err);
}
- dst_set_neighbour(&rt->dst, neigh);
- ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
+ rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
int err = 0;
if (rt->rt6i_prefsrc.plen)
- ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr);
+ *saddr = rt->rt6i_prefsrc.addr;
else
err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
daddr, prefs, saddr);
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
- if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
+ if (((void *)rt->dst.dev == dev || !dev) &&
rt != net->ipv6.ip6_null_entry &&
ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
/* remove prefsrc entry */
const struct arg_dev_net *adn = arg;
const struct net_device *dev = adn->dev;
- if ((rt->rt6i_dev == dev || dev == NULL) &&
- rt != adn->net->ipv6.ip6_null_entry) {
- RT6_TRACE("deleted by ifdown %p\n", rt);
+ if ((rt->dst.dev == dev || !dev) &&
+ rt != adn->net->ipv6.ip6_null_entry)
return -1;
- }
+
return 0;
}
*/
idev = __in6_dev_get(arg->dev);
- if (idev == NULL)
+ if (!idev)
return 0;
/* For administrative MTU increase, there is no way to discover
also have the lowest MTU, TOO BIG MESSAGE will be lead to
PMTU discouvery.
*/
- if (rt->rt6i_dev == arg->dev &&
+ if (rt->dst.dev == arg->dev &&
!dst_metric_locked(&rt->dst, RTAX_MTU) &&
(dst_mtu(&rt->dst) >= arg->mtu ||
(dst_mtu(&rt->dst) < arg->mtu &&
int iif, int type, u32 pid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
+ const struct inet_peer *peer;
struct rtmsg *rtm;
struct nlmsghdr *nlh;
long expires;
u32 table;
struct neighbour *n;
+ u32 ts, tsage;
if (prefix) { /* user wants prefix routes only */
if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
}
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
- if (nlh == NULL)
+ if (!nlh)
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
table = RT6_TABLE_UNSPEC;
rtm->rtm_table = table;
NLA_PUT_U32(skb, RTA_TABLE, table);
- if (rt->rt6i_flags&RTF_REJECT)
+ if (rt->rt6i_flags & RTF_REJECT)
rtm->rtm_type = RTN_UNREACHABLE;
- else if (rt->rt6i_flags&RTF_LOCAL)
+ else if (rt->rt6i_flags & RTF_LOCAL)
rtm->rtm_type = RTN_LOCAL;
- else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
+ else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
rtm->rtm_type = RTN_LOCAL;
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = 0;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
- if (rt->rt6i_flags&RTF_DYNAMIC)
+ if (rt->rt6i_flags & RTF_DYNAMIC)
rtm->rtm_protocol = RTPROT_REDIRECT;
else if (rt->rt6i_flags & RTF_ADDRCONF)
rtm->rtm_protocol = RTPROT_KERNEL;
- else if (rt->rt6i_flags&RTF_DEFAULT)
+ else if (rt->rt6i_flags & RTF_DEFAULT)
rtm->rtm_protocol = RTPROT_RA;
- if (rt->rt6i_flags&RTF_CACHE)
+ if (rt->rt6i_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
if (dst) {
if (rt->rt6i_prefsrc.plen) {
struct in6_addr saddr_buf;
- ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr);
+ saddr_buf = rt->rt6i_prefsrc.addr;
NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
}
goto nla_put_failure;
rcu_read_lock();
- n = dst_get_neighbour(&rt->dst);
+ n = dst_get_neighbour_noref(&rt->dst);
if (n)
NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key);
rcu_read_unlock();
if (rt->dst.dev)
- NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);
+ NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);
if (!(rt->rt6i_flags & RTF_EXPIRES))
expires = 0;
- else if (rt->rt6i_expires - jiffies < INT_MAX)
- expires = rt->rt6i_expires - jiffies;
+ else if (rt->dst.expires - jiffies < INT_MAX)
+ expires = rt->dst.expires - jiffies;
else
expires = INT_MAX;
- if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0,
+ peer = rt->rt6i_peer;
+ ts = tsage = 0;
+ if (peer && peer->tcp_ts_stamp) {
+ ts = peer->tcp_ts;
+ tsage = get_seconds() - peer->tcp_ts_stamp;
+ }
+
+ if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage,
expires, rt->dst.error) < 0)
goto nla_put_failure;
if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
goto errout;
- ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC]));
+ fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]);
}
if (tb[RTA_DST]) {
if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
goto errout;
- ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST]));
+ fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]);
}
if (tb[RTA_IIF])
}
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (skb == NULL) {
+ if (!skb) {
err = -ENOBUFS;
goto errout;
}
int err;
err = -ENOBUFS;
- seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0;
+ seq = info->nlh ? info->nlh->nlmsg_seq : 0;
skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
- if (skb == NULL)
+ if (!skb)
goto errout;
err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
seq_puts(m, "00000000000000000000000000000000 00 ");
#endif
rcu_read_lock();
- n = dst_get_neighbour(&rt->dst);
+ n = dst_get_neighbour_noref(&rt->dst);
if (n) {
seq_printf(m, "%pi6", n->primary_key);
} else {
seq_printf(m, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,
- rt->rt6i_dev ? rt->rt6i_dev->name : "");
+ rt->dst.dev ? rt->dst.dev->name : "");
return 0;
}
static int ipv6_route_show(struct seq_file *m, void *v)
{
struct net *net = (struct net *)m->private;
- fib6_clean_all(net, rt6_info_route, 0, m);
+ fib6_clean_all_ro(net, rt6_info_route, 0, m);
return 0;
}
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ipip6_get_stats(struct net_device *dev)
{
if (register_netdevice(dev) < 0)
goto failed_free;
+ strcpy(nt->parms.name, dev->name);
+
dev_hold(dev);
ipip6_tunnel_link(sitn, nt);
struct neighbour *neigh = NULL;
if (skb_dst(skb))
- neigh = dst_get_neighbour(skb_dst(skb));
+ neigh = dst_get_neighbour_noref(skb_dst(skb));
if (neigh == NULL) {
if (net_ratelimit())
struct neighbour *neigh = NULL;
if (skb_dst(skb))
- neigh = dst_get_neighbour(skb_dst(skb));
+ neigh = dst_get_neighbour_noref(skb_dst(skb));
if (neigh == NULL) {
if (net_ratelimit())
goto done;
#ifdef CONFIG_IPV6_SIT_6RD
} else {
- ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix);
+ ip6rd.prefix = t->ip6rd.prefix;
ip6rd.relay_prefix = t->ip6rd.relay_prefix;
ip6rd.prefixlen = t->ip6rd.prefixlen;
ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
if (relay_prefix != ip6rd.relay_prefix)
goto done;
- ipv6_addr_copy(&t->ip6rd.prefix, &prefix);
+ t->ip6rd.prefix = prefix;
t->ip6rd.relay_prefix = relay_prefix;
t->ip6rd.prefixlen = ip6rd.prefixlen;
t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
static int __net_init sit_init_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
+ struct ip_tunnel *t;
int err;
sitn->tunnels[0] = sitn->tunnels_wc;
if ((err = register_netdev(sitn->fb_tunnel_dev)))
goto err_reg_dev;
+ t = netdev_priv(sitn->fb_tunnel_dev);
+
+ strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
req->mss = mss;
ireq->rmt_port = th->source;
ireq->loc_port = th->dest;
- ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
- ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+ ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq6->loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+ fl6.daddr = ireq6->rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
- ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+ fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
#include <net/netdma.h>
#include <net/inet_common.h>
#include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
#include <asm/uaccess.h>
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
- ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+ usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
tp->write_seq = 0;
}
- ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
+ np->daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr,
- (saddr ? saddr : &np->saddr));
+ fl6.daddr = np->daddr;
+ fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
if (saddr == NULL) {
saddr = &fl6.saddr;
- ipv6_addr_copy(&np->rcv_saddr, saddr);
+ np->rcv_saddr = *saddr;
}
/* set the source address */
- ipv6_addr_copy(&np->saddr, saddr);
+ np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
*/
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.daddr, &np->daddr);
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.daddr = np->daddr;
+ fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
- ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+ fl6.daddr = treq->rmt_addr;
+ fl6.saddr = treq->loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = treq->iif;
fl6.flowi6_mark = sk->sk_mark;
if (skb) {
__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
- ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+ fl6.daddr = treq->rmt_addr;
err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
err = net_xmit_eval(err);
}
tp->md5sig_info->alloced6++;
}
- ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr,
- peer);
+ tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer;
tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey;
tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen;
bp = &hp->md5_blk.ip6;
/* 1. TCP pseudo-header (RFC2460) */
- ipv6_addr_copy(&bp->saddr, saddr);
- ipv6_addr_copy(&bp->daddr, daddr);
+ bp->saddr = *saddr;
+ bp->daddr = *daddr;
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
#endif
memset(&fl6, 0, sizeof(fl6));
- ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
- ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr);
+ fl6.daddr = ipv6_hdr(skb)->saddr;
+ fl6.saddr = ipv6_hdr(skb)->daddr;
buff->ip_summed = CHECKSUM_PARTIAL;
buff->csum = 0;
tcp_openreq_init(req, &tmp_opt, skb);
treq = inet6_rsk(req);
- ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
- ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
+ treq->rmt_addr = ipv6_hdr(skb)->saddr;
+ treq->loc_addr = ipv6_hdr(skb)->daddr;
if (!want_cookie || tmp_opt.tstamp_ok)
TCP_ECN_create_request(req, tcp_hdr(skb));
+ treq->iif = sk->sk_bound_dev_if;
+
+ /* So that link locals have meaning */
+ if (!sk->sk_bound_dev_if &&
+ ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ treq->iif = inet6_iif(skb);
+
if (!isn) {
struct inet_peer *peer = NULL;
atomic_inc(&skb->users);
treq->pktopts = skb;
}
- treq->iif = sk->sk_bound_dev_if;
-
- /* So that link locals have meaning */
- if (!sk->sk_bound_dev_if &&
- ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
- treq->iif = inet6_iif(skb);
if (want_cookie) {
isn = cookie_v6_init_sequence(sk, skb, &req->mss);
ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
- ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
+ newnp->rcv_saddr = newnp->saddr;
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr);
- ipv6_addr_copy(&newnp->saddr, &treq->loc_addr);
- ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
+ newnp->daddr = treq->rmt_addr;
+ newnp->saddr = treq->loc_addr;
+ newnp->rcv_saddr = treq->loc_addr;
newsk->sk_bound_dev_if = treq->iif;
/* Now IPv6 options...
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- percpu_counter_inc(&tcp_sockets_allocated);
+ sock_update_memcg(sk);
+ sk_sockets_allocated_inc(sk);
local_bh_enable();
return 0;
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.orphan_count = &tcp_orphan_count,
- .sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ .proto_cgroup = tcp_proto_cgroup,
+#endif
};
static const struct inet6_protocol tcpv6_protocol = {
return result;
}
-static struct sock *__udp6_lib_lookup(struct net *net,
+struct sock *__udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif, struct udp_table *udptable)
rcu_read_unlock();
return result;
}
+EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
- unsigned int ulen;
+ unsigned int ulen, copied;
int peeked;
int err;
int is_udplite = IS_UDPLITE(sk);
goto out;
ulen = skb->len - sizeof(struct udphdr);
- if (len > ulen)
- len = ulen;
- else if (len < ulen)
+ copied = len;
+ if (copied > ulen)
+ copied = ulen;
+ else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
* coverage checksum (UDP-Lite), do it before the copy.
*/
- if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
+ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
if (udp_lib_checksum_complete(skb))
goto csum_copy_err;
}
if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
- msg->msg_iov,len);
+ msg->msg_iov, copied );
else {
err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
if (err == -EINVAL)
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin6->sin6_addr);
else {
- ipv6_addr_copy(&sin6->sin6_addr,
- &ipv6_hdr(skb)->saddr);
+ sin6->sin6_addr = ipv6_hdr(skb)->saddr;
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin6->sin6_scope_id = IP6CB(skb)->iif;
}
datagram_recv_ctl(sk, msg, skb);
}
- err = len;
+ err = copied;
if (flags & MSG_TRUNC)
err = ulen;
goto drop;
}
- if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) {
+ skb_dst_drop(skb);
+ rc = sock_queue_rcv_skb(sk, skb);
+ if (rc < 0) {
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
UDP6_INC_STATS_BH(sock_net(sk),
fl6.flowi6_proto = sk->sk_protocol;
if (!ipv6_addr_any(daddr))
- ipv6_addr_copy(&fl6.daddr, daddr);
+ fl6.daddr = *daddr;
else
fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
- ipv6_addr_copy(&fl6.saddr, &np->saddr);
+ fl6.saddr = np->saddr;
fl6.fl6_sport = inet->inet_sport;
final_p = fl6_update_dst(&fl6, opt, &final);
return 0;
}
-static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
top_iph->nexthdr = IPPROTO_BEETPH;
}
- ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
- ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+ top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+ top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
return 0;
}
ip6h = ipv6_hdr(skb);
ip6h->payload_len = htons(skb->len - size);
- ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6);
- ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6);
+ ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6;
+ ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6;
err = 0;
out:
return err;
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
- ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr);
- ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr);
+ top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+ top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
return 0;
}
struct sock *sk = skb->sk;
fl6.flowi6_oif = sk->sk_bound_dev_if;
- ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr);
+ fl6.daddr = ipv6_hdr(skb)->daddr;
ipv6_local_rxpmtu(sk, &fl6, mtu);
}
struct sock *sk = skb->sk;
fl6.fl6_dport = inet_sk(sk)->inet_dport;
- ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr);
+ fl6.daddr = ipv6_hdr(skb)->daddr;
ipv6_local_error(sk, EMSGSIZE, &fl6, mtu);
}
memset(fl6, 0, sizeof(struct flowi6));
fl6->flowi6_mark = skb->mark;
- ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr);
- ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr);
+ fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+ fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
while (nh + offset + 1 < skb->data ||
pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
/* Initialize temporary selector matching only
* to current session. */
- ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr);
- ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr);
+ *(struct in6_addr *)&sel->daddr = fl6->daddr;
+ *(struct in6_addr *)&sel->saddr = fl6->saddr;
sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
sel->dport_mask = htons(0xffff);
sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
self->errno = 0;
setup_timer(&self->watchdog, irda_discovery_timeout,
(unsigned long)self);
- self->watchdog.expires = jiffies + (val * HZ/1000);
- add_timer(&(self->watchdog));
+ mod_timer(&self->watchdog,
+ jiffies + msecs_to_jiffies(val));
/* Wait for IR-LMP to call us back */
__wait_event_interruptible(self->query_wait,
static void *skey;
/* Module parameters */
-static int eth; /* Use "eth" or "irlan" name for devices */
+static bool eth; /* Use "eth" or "irlan" name for devices */
static int access = ACCESS_PEER; /* PEER, DIRECT or HOSTED */
#ifdef CONFIG_PROC_FS
}
/* Allocate a new instance */
- new = kmalloc(sizeof(struct tsap_cb), GFP_ATOMIC);
+ new = kmemdup(orig, sizeof(struct tsap_cb), GFP_ATOMIC);
if (!new) {
IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
return NULL;
}
- /* Dup */
- memcpy(new, orig, sizeof(struct tsap_cb));
spin_lock_init(&new->lock);
/* We don't need the old instance any more */
memcpy(&dst[8], src, 8);
}
+static void iucv_skb_queue_purge(struct sk_buff_head *list)
+{
+ struct sk_buff *skb;
+
+ while ((skb = skb_dequeue(list)) != NULL) {
+ if (skb->dev)
+ dev_put(skb->dev);
+ kfree_skb(skb);
+ }
+}
+
static int afiucv_pm_prepare(struct device *dev)
{
#ifdef CONFIG_PM_DEBUG
read_lock(&iucv_sk_list.lock);
sk_for_each(sk, node, &iucv_sk_list.head) {
iucv = iucv_sk(sk);
- skb_queue_purge(&iucv->send_skb_q);
+ iucv_skb_queue_purge(&iucv->send_skb_q);
skb_queue_purge(&iucv->backlog_skb_q);
switch (sk->sk_state) {
- case IUCV_SEVERED:
case IUCV_DISCONN:
case IUCV_CLOSING:
case IUCV_CONNECTED:
sk->sk_state_change(sk);
break;
case IUCV_DISCONN:
- case IUCV_SEVERED:
case IUCV_CLOSING:
case IUCV_LISTEN:
case IUCV_BOUND:
if (imsg)
memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message));
- rcu_read_lock();
- skb->dev = dev_get_by_index_rcu(net, sock->sk_bound_dev_if);
- rcu_read_unlock();
+ skb->dev = dev_get_by_index(net, sock->sk_bound_dev_if);
if (!skb->dev)
return -ENODEV;
if (!(skb->dev->flags & IFF_UP))
err = dev_queue_xmit(skb);
if (err) {
skb_unlink(nskb, &iucv->send_skb_q);
+ dev_put(nskb->dev);
kfree_skb(nskb);
} else {
atomic_sub(confirm_recv, &iucv->msg_recv);
return err;
}
-/* Timers */
-static void iucv_sock_timeout(unsigned long arg)
-{
- struct sock *sk = (struct sock *)arg;
-
- bh_lock_sock(sk);
- sk->sk_err = ETIMEDOUT;
- sk->sk_state_change(sk);
- bh_unlock_sock(sk);
-
- iucv_sock_kill(sk);
- sock_put(sk);
-}
-
-static void iucv_sock_clear_timer(struct sock *sk)
-{
- sk_stop_timer(sk, &sk->sk_timer);
-}
-
static struct sock *__iucv_get_sock_by_name(char *nm)
{
struct sock *sk;
int err, blen;
struct sk_buff *skb;
- iucv_sock_clear_timer(sk);
lock_sock(sk);
switch (sk->sk_state) {
blen = sizeof(struct af_iucv_trans_hdr) + ETH_HLEN;
skb = sock_alloc_send_skb(sk, blen, 1, &err);
if (skb) {
- skb_reserve(skb,
- sizeof(struct af_iucv_trans_hdr) +
- ETH_HLEN);
+ skb_reserve(skb, blen);
err = afiucv_hs_send(NULL, sk, skb,
AF_IUCV_FLAG_FIN);
}
sk->sk_state = IUCV_DISCONN;
sk->sk_state_change(sk);
}
- case IUCV_DISCONN:
+ case IUCV_DISCONN: /* fall through */
sk->sk_state = IUCV_CLOSING;
sk->sk_state_change(sk);
sk->sk_err = ECONNRESET;
sk->sk_state_change(sk);
- skb_queue_purge(&iucv->send_skb_q);
+ iucv_skb_queue_purge(&iucv->send_skb_q);
skb_queue_purge(&iucv->backlog_skb_q);
break;
sk->sk_protocol = proto;
sk->sk_state = IUCV_OPEN;
- setup_timer(&sk->sk_timer, iucv_sock_timeout, (unsigned long)sk);
-
iucv_sock_link(&iucv_sk_list, sk);
return sk;
}
}
if (sk->sk_state == IUCV_CONNECTED ||
- sk->sk_state == IUCV_SEVERED ||
- sk->sk_state == IUCV_DISCONN || /* due to PM restore */
+ sk->sk_state == IUCV_DISCONN ||
!newsock) {
iucv_accept_unlink(sk);
if (newsock)
sock_graft(sk, newsock);
- if (sk->sk_state == IUCV_SEVERED)
- sk->sk_state = IUCV_DISCONN;
-
release_sock(sk);
return sk;
}
if (!memcmp(dev->perm_addr, uid, 8)) {
memcpy(iucv->src_name, sa->siucv_name, 8);
memcpy(iucv->src_user_id, sa->siucv_user_id, 8);
- sock->sk->sk_bound_dev_if = dev->ifindex;
+ sk->sk_bound_dev_if = dev->ifindex;
sk->sk_state = IUCV_BOUND;
iucv->transport = AF_IUCV_TRANS_HIPER;
if (!iucv->msglimit)
static int iucv_sock_autobind(struct sock *sk)
{
struct iucv_sock *iucv = iucv_sk(sk);
- char query_buffer[80];
char name[12];
int err = 0;
- /* Set the userid and name */
- cpcmd("QUERY USERID", query_buffer, sizeof(query_buffer), &err);
- if (unlikely(err))
+ if (unlikely(!pr_iucv))
return -EPROTO;
- memcpy(iucv->src_user_id, query_buffer, 8);
+ memcpy(iucv->src_user_id, iucv_userid, 8);
write_lock_bh(&iucv_sk_list.lock);
return len;
fail:
+ if (skb->dev)
+ dev_put(skb->dev);
kfree_skb(skb);
out:
release_sock(sk);
int blen;
int err = 0;
- if ((sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_SEVERED) &&
+ if ((sk->sk_state == IUCV_DISCONN) &&
skb_queue_empty(&iucv->backlog_skb_q) &&
skb_queue_empty(&sk->sk_receive_queue) &&
list_empty(&iucv->message_q.list))
ETH_HLEN;
sskb = sock_alloc_send_skb(sk, blen, 1, &err);
if (sskb) {
- skb_reserve(sskb,
- sizeof(struct af_iucv_trans_hdr)
- + ETH_HLEN);
+ skb_reserve(sskb, blen);
err = afiucv_hs_send(NULL, sk, sskb,
AF_IUCV_FLAG_WIN);
}
if (sk->sk_state == IUCV_CLOSED)
mask |= POLLHUP;
- if (sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_SEVERED)
+ if (sk->sk_state == IUCV_DISCONN)
mask |= POLLIN;
if (sock_writeable(sk))
switch (sk->sk_state) {
case IUCV_DISCONN:
case IUCV_CLOSING:
- case IUCV_SEVERED:
case IUCV_CLOSED:
err = -ENOTCONN;
goto fail;
{
struct sock *sk = path->private;
- if (!list_empty(&iucv_sk(sk)->accept_q))
- sk->sk_state = IUCV_SEVERED;
- else
- sk->sk_state = IUCV_DISCONN;
+ sk->sk_state = IUCV_DISCONN;
sk->sk_state_change(sk);
}
/* other end of connection closed */
if (iucv) {
bh_lock_sock(sk);
- if (!list_empty(&iucv->accept_q))
- sk->sk_state = IUCV_SEVERED;
- else
- sk->sk_state = IUCV_DISCONN;
+ sk->sk_state = IUCV_DISCONN;
sk->sk_state_change(sk);
bh_unlock_sock(sk);
}
break;
case 0:
/* plain data frame */
+ memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class,
+ CB_TRGCLS_LEN);
err = afiucv_hs_callback_rx(sk, skb);
break;
default:
case TX_NOTIFY_OK:
__skb_unlink(this, list);
iucv_sock_wake_msglim(sk);
+ dev_put(this->dev);
kfree_skb(this);
break;
case TX_NOTIFY_PENDING:
atomic_dec(&iucv->pendings);
if (atomic_read(&iucv->pendings) <= 0)
iucv_sock_wake_msglim(sk);
+ dev_put(this->dev);
kfree_skb(this);
break;
case TX_NOTIFY_UNREACHABLE:
case TX_NOTIFY_GENERALERROR:
case TX_NOTIFY_DELAYED_GENERALERROR:
__skb_unlink(this, list);
+ dev_put(this->dev);
kfree_skb(this);
- if (!list_empty(&iucv->accept_q))
- sk->sk_state = IUCV_SEVERED;
- else
- sk->sk_state = IUCV_DISCONN;
+ sk->sk_state = IUCV_DISCONN;
sk->sk_state_change(sk);
break;
}
}
spin_unlock_irqrestore(&list->lock, flags);
+ if (sk->sk_state == IUCV_CLOSING) {
+ if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) {
+ sk->sk_state = IUCV_CLOSED;
+ sk->sk_state_change(sk);
+ }
+ }
+
out_unlock:
bh_unlock_sock(sk);
}
const struct sadb_address *sp = p;
const struct sockaddr *addr = (const struct sockaddr *)(sp + 1);
const struct sockaddr_in *sin;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
const struct sockaddr_in6 *sin6;
#endif
int len;
sp->sadb_address_prefixlen > 32)
return -EINVAL;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t));
if (sp->sadb_address_len != len ||
if (s_addr->sa_family != d_addr->sa_family)
return 0;
if (s_addr->sa_family != AF_INET
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
&& s_addr->sa_family != AF_INET6
#endif
)
switch (family) {
case AF_INET:
return sizeof(struct sockaddr_in);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return sizeof(struct sockaddr_in6);
#endif
xaddr->a4 =
((struct sockaddr_in *)sa)->sin_addr.s_addr;
return AF_INET;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
memcpy(xaddr->a6,
&((struct sockaddr_in6 *)sa)->sin6_addr,
case AF_INET:
xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr;
break;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
return 32;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
{
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
sin6->sin6_family = AF_INET6;
sin6->sin6_port = port;
sin6->sin6_flowinfo = 0;
- ipv6_addr_copy(&sin6->sin6_addr, (const struct in6_addr *)xaddr->a6);
+ sin6->sin6_addr = *(struct in6_addr *)xaddr->a6;
sin6->sin6_scope_id = 0;
return 128;
}
xdaddr = (xfrm_address_t *)&((struct sockaddr_in *)(daddr + 1))->sin_addr.s_addr;
xsaddr = (xfrm_address_t *)&((struct sockaddr_in *)(saddr + 1))->sin_addr.s_addr;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
xdaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(daddr + 1))->sin6_addr;
xsaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(saddr + 1))->sin6_addr;
return NULL;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
if (opt != IPV6_IPSEC_POLICY) {
*dir = -EOPNOTSUPP;
goto error;
}
- /* Point to L2TP header */
- optr = ptr = skb->data;
-
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
offset = 0;
do {
- printk(" %02X", ptr[offset]);
+ printk(" %02X", skb->data[offset]);
} while (++offset < length);
printk("\n");
}
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
/* Get L2TP header flags */
hdrflags = ntohs(*(__be16 *) ptr);
/* Get routing info from the tunnel socket */
skb_dst_drop(skb);
- skb_dst_set(skb, dst_clone(__sk_dst_get(sk)));
+ skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0)));
inet = inet_sk(sk);
fl = &inet->cork.fl;
copied += used;
len -= used;
+ /* For non stream protcols we get one packet per recvmsg call */
+ if (sk->sk_type != SOCK_STREAM)
+ goto copy_uaddr;
+
if (!(flags & MSG_PEEK)) {
sk_eat_skb(sk, skb, 0);
*seq = 0;
}
- /* For non stream protcols we get one packet per recvmsg call */
- if (sk->sk_type != SOCK_STREAM)
- goto copy_uaddr;
-
/* Partial read */
if (used + offset < skb->len)
continue;
}
if (llc_sk(sk)->cmsg_flags)
llc_cmsg_rcv(msg, skb);
+
+ if (!(flags & MSG_PEEK)) {
+ sk_eat_skb(sk, skb, 0);
+ *seq = 0;
+ }
+
goto out;
}
rinfo[i].diff = i * pinfo->norm_offset;
}
for (i = 1; i < sband->n_bitrates; i++) {
- s = 0;
+ s = false;
for (j = 0; j < sband->n_bitrates - i; j++)
if (unlikely(sband->bitrates[rinfo[j].index].bitrate >
sband->bitrates[rinfo[j + 1].index].bitrate)) {
rinfo[j + 1].index = tmp;
rinfo[rinfo[j].index].rev_index = j;
rinfo[rinfo[j + 1].index].rev_index = j + 1;
- s = 1;
+ s = true;
}
if (!s)
break;
/* save the ERP value so that it is available at association time */
if (elems->erp_info && elems->erp_info_len >= 1) {
bss->erp_value = elems->erp_info[0];
- bss->has_erp_value = 1;
+ bss->has_erp_value = true;
}
if (elems->tim) {
config NETFILTER_NETLINK
tristate
+config NETFILTER_NETLINK_ACCT
+tristate "Netfilter NFACCT over NFNETLINK interface"
+ depends on NETFILTER_ADVANCED
+ select NETFILTER_NETLINK
+ help
+ If this option is enabled, the kernel will include support
+ for extended accounting via NFNETLINK.
+
config NETFILTER_NETLINK_QUEUE
tristate "Netfilter NFQUEUE over NFNETLINK interface"
depends on NETFILTER_ADVANCED
If unsure, say `N'.
+config NF_CONNTRACK_PROCFS
+ bool "Supply CT list in procfs (OBSOLETE)"
+ default y
+ depends on PROC_FS
+ ---help---
+ This option enables for the list of known conntrack entries
+ to be shown in procfs under net/netfilter/nf_conntrack. This
+ is considered obsolete in favor of using the conntrack(8)
+ tool which uses Netlink.
+
config NF_CONNTRACK_EVENTS
bool "Connection tracking events"
depends on NETFILTER_ADVANCED
config NF_CONNTRACK_NETBIOS_NS
tristate "NetBIOS name service protocol support"
- depends on NETFILTER_ADVANCED
select NF_CONNTRACK_BROADCAST
help
NetBIOS name service requests are sent as broadcast messages from an
tristate '"NOTRACK" target support'
depends on IP_NF_RAW || IP6_NF_RAW
depends on NF_CONNTRACK
- depends on NETFILTER_ADVANCED
help
The NOTRACK target allows a select rule to specify
which packets *not* to enter the conntrack/NAT
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_ECN
+ tristate '"ecn" match support'
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option adds an "ECN" match, which allows you to match against
+ the IPv4 and TCP header ECN fields.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_ESP
tristate '"esp" match support'
depends on NETFILTER_ADVANCED
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_NFACCT
+ tristate '"nfacct" match support'
+ depends on NETFILTER_ADVANCED
+ select NETFILTER_NETLINK_ACCT
+ help
+ This option allows you to use the extended accounting through
+ nfnetlink_acct.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_OSF
tristate '"osf" Passive OS fingerprint match'
depends on NETFILTER_ADVANCED && NETFILTER_NETLINK
obj-$(CONFIG_NETFILTER) = netfilter.o
obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
+obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_DEVGROUP) += xt_devgroup.o
obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_ECN) += xt_ecn.o
obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
EXPORT_SYMBOL(nf_hooks);
+
+#if defined(CONFIG_JUMP_LABEL)
+struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+EXPORT_SYMBOL(nf_hooks_needed);
+#endif
+
static DEFINE_MUTEX(nf_hook_mutex);
int nf_register_hook(struct nf_hook_ops *reg)
}
list_add_rcu(®->list, elem->list.prev);
mutex_unlock(&nf_hook_mutex);
+#if defined(CONFIG_JUMP_LABEL)
+ jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
+#endif
return 0;
}
EXPORT_SYMBOL(nf_register_hook);
mutex_lock(&nf_hook_mutex);
list_del_rcu(®->list);
mutex_unlock(&nf_hook_mutex);
-
+#if defined(CONFIG_JUMP_LABEL)
+ jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
+#endif
synchronize_net();
}
EXPORT_SYMBOL(nf_unregister_hook);
}
EXPORT_SYMBOL(skb_make_writable);
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* This does not belong here, but locally generated errors need it if connection
tracking in use: without this, connection may not be in hash table, and hence
manufactured ICMP or RST packets will not be associated with it. */
}
EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
bool
ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
__be16 *port, u8 *proto)
{
int protoff;
u8 nexthdr;
+ __be16 frag_off;
nexthdr = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+ protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+ &frag_off);
if (protoff < 0)
return false;
static inline void
hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src)
{
- ipv6_addr_copy(&dst->ip.in6, &src->ip.in6);
+ dst->ip.in6 = src->ip.in6;
}
static inline void
const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem data = { };
- u32 ip, ip_to, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to;
u32 timeout = h->timeout;
bool with_ports = false;
int ret;
const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem data = { };
- u32 ip, ip_to, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to;
u32 timeout = h->timeout;
bool with_ports = false;
int ret;
const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem data = { .cidr = HOST_MASK };
- u32 ip, ip_to, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to;
u32 ip2_from = 0, ip2_to, ip2_last, ip2;
u32 timeout = h->timeout;
bool with_ports = false;
hash_net6_data_copy(struct hash_net6_elem *dst,
const struct hash_net6_elem *src)
{
- ipv6_addr_copy(&dst->ip.in6, &src->ip.in6);
+ dst->ip.in6 = src->ip.in6;
dst->cidr = src->cidr;
}
If you want to compile it in kernel, say Y. To compile it as a
module, choose M here. If unsure, say N.
+comment 'IPVS SH scheduler'
+
+config IP_VS_SH_TAB_BITS
+ int "IPVS source hashing table size (the Nth power of 2)"
+ range 4 20
+ default 8
+ ---help---
+ The source hashing scheduler maps source IPs to destinations
+ stored in a hash table. This table is tiled by each destination
+ until all slots in the table are filled. When using weights to
+ allow destinations to receive more connections, the table is
+ tiled an amount proportional to the weights specified. The table
+ needs to be large enough to effectively fit all the destinations
+ multiplied by their respective weights.
+
comment 'IPVS application helper'
config IP_VS_FTP
if ((cp) && (!cp->dest)) {
dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
cp->dport, &cp->vaddr, cp->vport,
- cp->protocol, cp->fwmark);
+ cp->protocol, cp->fwmark, cp->flags);
ip_vs_bind_dest(cp, dest);
return dest;
} else
if (!cp)
return NF_ACCEPT;
- ipv6_addr_copy(&snet.in6, &iph->saddr);
+ snet.in6 = iph->saddr;
return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp,
pp, offset, sizeof(struct ipv6hdr));
}
};
rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
- if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK))
+ if (rt && rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
return 1;
return 0;
const union nf_inet_addr *daddr,
__be16 dport,
const union nf_inet_addr *vaddr,
- __be16 vport, __u16 protocol, __u32 fwmark)
+ __be16 vport, __u16 protocol, __u32 fwmark,
+ __u32 flags)
{
struct ip_vs_dest *dest;
struct ip_vs_service *svc;
+ __be16 port = dport;
svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport);
if (!svc)
return NULL;
- dest = ip_vs_lookup_dest(svc, daddr, dport);
+ if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
+ port = 0;
+ dest = ip_vs_lookup_dest(svc, daddr, port);
+ if (!dest)
+ dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
if (dest)
atomic_inc(&dest->refcnt);
ip_vs_service_put(svc);
struct ip_vs_conn *ct)
{
- bool ret = 0;
+ bool ret = false;
if (ct->af == p->af &&
ip_vs_addr_equal(p->af, p->caddr, &ct->caddr) &&
ct->protocol == p->protocol &&
ct->pe_data && ct->pe_data_len == p->pe_data_len &&
!memcmp(ct->pe_data, p->pe_data, p->pe_data_len))
- ret = 1;
+ ret = true;
IP_VS_DBG_BUF(9, "SIP template match %s %s->%s:%d %s\n",
ip_vs_proto_name(p->protocol),
* server is dead or overloaded, the load balancer can bypass the cache
* server and send requests to the original server directly.
*
+ * The weight destination attribute can be used to control the
+ * distribution of connections to the destinations in servernode. The
+ * greater the weight, the more connections the destination
+ * will receive.
+ *
*/
#define KMSG_COMPONENT "IPVS"
struct ip_vs_sh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
+ int d_count;
b = tbl;
p = &svc->destinations;
+ d_count = 0;
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
if (list_empty(p)) {
b->dest = NULL;
atomic_inc(&dest->refcnt);
b->dest = dest;
- p = p->next;
+ IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
+ i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
+ atomic_read(&dest->weight));
+
+ /* Don't move to next dest until filling weight */
+ if (++d_count >= atomic_read(&dest->weight)) {
+ p = p->next;
+ d_count = 0;
+ }
+
}
b++;
}
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6) {
p += sizeof(struct ip_vs_sync_v6);
- ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6);
- ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6);
- ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6);
+ s->v6.caddr = cp->caddr.in6;
+ s->v6.vaddr = cp->vaddr.in6;
+ s->v6.daddr = cp->daddr.in6;
} else
#endif
{
* but still handled.
*/
dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
- param->vport, protocol, fwmark);
+ param->vport, protocol, fwmark, flags);
/* Set the approprite ativity flag */
if (protocol == IPPROTO_TCP) {
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
- return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
+ return rt->dst.dev && rt->dst.dev->flags & IFF_LOOPBACK;
}
static struct dst_entry *
goto out_err;
}
}
- ipv6_addr_copy(ret_saddr, &fl6.saddr);
+ *ret_saddr = fl6.saddr;
return dst;
out_err:
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
- ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6);
+ *ret_saddr = dest->dst_saddr.in6;
spin_unlock(&dest->dst_lock);
} else {
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error;
- ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6);
+ ipv6_hdr(skb)->daddr = cp->daddr.in6;
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
iph->priority = old_iph->priority;
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
- ipv6_addr_copy(&iph->daddr, &cp->daddr.in6);
- ipv6_addr_copy(&iph->saddr, &saddr);
+ iph->daddr = cp->daddr.in6;
+ iph->saddr = saddr;
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
-static int nf_ct_acct __read_mostly;
+static bool nf_ct_acct __read_mostly;
module_param_named(acct, nf_ct_acct, bool, 0644);
MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting.");
return 0;
return seq_printf(s, "packets=%llu bytes=%llu ",
- (unsigned long long)acct[dir].packets,
- (unsigned long long)acct[dir].bytes);
+ (unsigned long long)atomic64_read(&acct[dir].packets),
+ (unsigned long long)atomic64_read(&acct[dir].bytes));
};
EXPORT_SYMBOL_GPL(seq_print_acct);
EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
unsigned int nf_conntrack_hash_rnd __read_mostly;
+EXPORT_SYMBOL_GPL(nf_conntrack_hash_rnd);
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone)
{
acct = nf_conn_acct_find(ct);
if (acct) {
- spin_lock_bh(&ct->lock);
- acct[CTINFO2DIR(ctinfo)].packets++;
- acct[CTINFO2DIR(ctinfo)].bytes += skb->len;
- spin_unlock_bh(&ct->lock);
+ atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
+ atomic64_add(skb->len, &acct[CTINFO2DIR(ctinfo)].bytes);
}
}
}
acct = nf_conn_acct_find(ct);
if (acct) {
- spin_lock_bh(&ct->lock);
- acct[CTINFO2DIR(ctinfo)].packets++;
- acct[CTINFO2DIR(ctinfo)].bytes +=
- skb->len - skb_network_offset(skb);
- spin_unlock_bh(&ct->lock);
+ atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
+ atomic64_add(skb->len - skb_network_offset(skb),
+ &acct[CTINFO2DIR(ctinfo)].bytes);
}
}
};
#endif
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
get_order(sz));
if (!hash) {
printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
- hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
- PAGE_KERNEL);
+ hash = vzalloc(sz);
}
if (hash && nulls)
static DEFINE_MUTEX(nf_ct_ecache_mutex);
-struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
-
-struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_expect_event_cb);
-
/* deliver cached events and clear cache entry - must be called with locally
* disabled softirqs */
void nf_ct_deliver_cached_events(struct nf_conn *ct)
{
+ struct net *net = nf_ct_net(ct);
unsigned long events;
struct nf_ct_event_notifier *notify;
struct nf_conntrack_ecache *e;
rcu_read_lock();
- notify = rcu_dereference(nf_conntrack_event_cb);
+ notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
if (notify == NULL)
goto out_unlock;
}
EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events);
-int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new)
+int nf_conntrack_register_notifier(struct net *net,
+ struct nf_ct_event_notifier *new)
{
int ret = 0;
struct nf_ct_event_notifier *notify;
mutex_lock(&nf_ct_ecache_mutex);
- notify = rcu_dereference_protected(nf_conntrack_event_cb,
+ notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
lockdep_is_held(&nf_ct_ecache_mutex));
if (notify != NULL) {
ret = -EBUSY;
goto out_unlock;
}
- RCU_INIT_POINTER(nf_conntrack_event_cb, new);
+ RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new);
mutex_unlock(&nf_ct_ecache_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
-void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new)
+void nf_conntrack_unregister_notifier(struct net *net,
+ struct nf_ct_event_notifier *new)
{
struct nf_ct_event_notifier *notify;
mutex_lock(&nf_ct_ecache_mutex);
- notify = rcu_dereference_protected(nf_conntrack_event_cb,
+ notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
lockdep_is_held(&nf_ct_ecache_mutex));
BUG_ON(notify != new);
- RCU_INIT_POINTER(nf_conntrack_event_cb, NULL);
+ RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
}
EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
-int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new)
+int nf_ct_expect_register_notifier(struct net *net,
+ struct nf_exp_event_notifier *new)
{
int ret = 0;
struct nf_exp_event_notifier *notify;
mutex_lock(&nf_ct_ecache_mutex);
- notify = rcu_dereference_protected(nf_expect_event_cb,
+ notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
lockdep_is_held(&nf_ct_ecache_mutex));
if (notify != NULL) {
ret = -EBUSY;
goto out_unlock;
}
- RCU_INIT_POINTER(nf_expect_event_cb, new);
+ RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new);
mutex_unlock(&nf_ct_ecache_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier);
-void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new)
+void nf_ct_expect_unregister_notifier(struct net *net,
+ struct nf_exp_event_notifier *new)
{
struct nf_exp_event_notifier *notify;
mutex_lock(&nf_ct_ecache_mutex);
- notify = rcu_dereference_protected(nf_expect_event_cb,
+ notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
lockdep_is_held(&nf_ct_ecache_mutex));
BUG_ON(notify != new);
- RCU_INIT_POINTER(nf_expect_event_cb, NULL);
+ RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
-static HLIST_HEAD(nf_ct_userspace_expect_list);
-
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
u32 pid, int report)
struct nf_conn_help *master_help = nfct_help(exp->master);
struct net *net = nf_ct_exp_net(exp);
+ NF_CT_ASSERT(master_help);
NF_CT_ASSERT(!timer_pending(&exp->timeout));
hlist_del_rcu(&exp->hnode);
net->ct.expect_count--;
hlist_del(&exp->lnode);
- if (!(exp->flags & NF_CT_EXPECT_USERSPACE))
- master_help->expecting[exp->class]--;
+ master_help->expecting[exp->class]--;
nf_ct_expect_event_report(IPEXP_DESTROY, exp, pid, report);
nf_ct_expect_put(exp);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_put);
-static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
+static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
{
struct nf_conn_help *master_help = nfct_help(exp->master);
+ struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(exp);
- const struct nf_conntrack_expect_policy *p;
unsigned int h = nf_ct_expect_dst_hash(&exp->tuple);
/* two references : one for hash insert, one for the timer */
atomic_add(2, &exp->use);
- if (master_help) {
- hlist_add_head(&exp->lnode, &master_help->expectations);
- master_help->expecting[exp->class]++;
- } else if (exp->flags & NF_CT_EXPECT_USERSPACE)
- hlist_add_head(&exp->lnode, &nf_ct_userspace_expect_list);
+ hlist_add_head(&exp->lnode, &master_help->expectations);
+ master_help->expecting[exp->class]++;
hlist_add_head_rcu(&exp->hnode, &net->ct.expect_hash[h]);
net->ct.expect_count++;
setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
(unsigned long)exp);
- if (master_help) {
- p = &rcu_dereference_protected(
- master_help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- )->expect_policy[exp->class];
- exp->timeout.expires = jiffies + p->timeout * HZ;
+ helper = rcu_dereference_protected(master_help->helper,
+ lockdep_is_held(&nf_conntrack_lock));
+ if (helper) {
+ exp->timeout.expires = jiffies +
+ helper->expect_policy[exp->class].timeout * HZ;
}
add_timer(&exp->timeout);
NF_CT_STAT_INC(net, expect_create);
+ return 0;
}
/* Race with expectations being used means we could have none to find; OK. */
struct nf_conntrack_expect *i;
struct nf_conn *master = expect->master;
struct nf_conn_help *master_help = nfct_help(master);
+ struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(expect);
struct hlist_node *n;
unsigned int h;
int ret = 1;
- /* Don't allow expectations created from kernel-space with no helper */
- if (!(expect->flags & NF_CT_EXPECT_USERSPACE) &&
- (!master_help || (master_help && !master_help->helper))) {
+ if (!master_help) {
ret = -ESHUTDOWN;
goto out;
}
}
}
/* Will be over limit? */
- if (master_help) {
- p = &rcu_dereference_protected(
- master_help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- )->expect_policy[expect->class];
+ helper = rcu_dereference_protected(master_help->helper,
+ lockdep_is_held(&nf_conntrack_lock));
+ if (helper) {
+ p = &helper->expect_policy[expect->class];
if (p->max_expected &&
master_help->expecting[expect->class] >= p->max_expected) {
evict_oldest_expect(master, expect);
if (ret <= 0)
goto out;
- ret = 0;
- nf_ct_expect_insert(expect);
+ ret = nf_ct_expect_insert(expect);
+ if (ret < 0)
+ goto out;
spin_unlock_bh(&nf_conntrack_lock);
nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
-void nf_ct_remove_userspace_expectations(void)
-{
- struct nf_conntrack_expect *exp;
- struct hlist_node *n, *next;
-
- hlist_for_each_entry_safe(exp, n, next,
- &nf_ct_userspace_expect_list, lnode) {
- if (del_timer(&exp->timeout)) {
- nf_ct_unlink_expect(exp);
- nf_ct_expect_put(exp);
- }
- }
-}
-EXPORT_SYMBOL_GPL(nf_ct_remove_userspace_expectations);
-
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct ct_expect_iter_state {
struct seq_net_private p;
unsigned int bucket;
.llseek = seq_lseek,
.release = seq_release_net,
};
-#endif /* CONFIG_PROC_FS */
+#endif /* CONFIG_NF_CONNTRACK_PROCFS */
static int exp_proc_init(struct net *net)
{
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct proc_dir_entry *proc;
proc = proc_net_fops_create(net, "nf_conntrack_expect", 0440, &exp_file_ops);
if (!proc)
return -ENOMEM;
-#endif /* CONFIG_PROC_FS */
+#endif /* CONFIG_NF_CONNTRACK_PROCFS */
return 0;
}
static void exp_proc_remove(struct net *net)
{
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_NF_CONNTRACK_PROCFS
proc_net_remove(net, "nf_conntrack_expect");
-#endif /* CONFIG_PROC_FS */
+#endif /* CONFIG_NF_CONNTRACK_PROCFS */
}
module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);
static unsigned int ports_c;
module_param_array(ports, ushort, &ports_c, 0400);
-static int loose;
+static bool loose;
module_param(loose, bool, 0600);
unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb,
module_param(gkrouted_only, int, 0600);
MODULE_PARM_DESC(gkrouted_only, "only accept calls from gatekeeper");
-static int callforward_filter __read_mostly = 1;
+static bool callforward_filter __read_mostly = true;
module_param(callforward_filter, bool, 0600);
MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations "
"if both endpoints are on different sides "
}
break;
}
-#if defined(CONFIG_NF_CONNTRACK_IPV6) || \
- defined(CONFIG_NF_CONNTRACK_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
case AF_INET6: {
struct flowi6 fl1, fl2;
struct rt6_info *rt1, *rt2;
memset(&fl1, 0, sizeof(fl1));
- ipv6_addr_copy(&fl1.daddr, &src->in6);
+ fl1.daddr = src->in6;
memset(&fl2, 0, sizeof(fl2));
- ipv6_addr_copy(&fl2.daddr, &dst->in6);
+ fl2.daddr = dst->in6;
if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
int ret = 0;
if (tmpl != NULL) {
+ /* we've got a userspace helper. */
+ if (tmpl->status & IPS_USERSPACE_HELPER) {
+ help = nf_ct_helper_ext_add(ct, flags);
+ if (help == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ rcu_assign_pointer(help->helper, NULL);
+ __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status);
+ ret = 0;
+ goto out;
+ }
help = nfct_help(tmpl);
if (help != NULL)
helper = help->helper;
* (C) 2001 by Jay Schulist <jschlst@samba.org>
* (C) 2002-2006 by Harald Welte <laforge@gnumonks.org>
* (C) 2003 by Patrick Mchardy <kaber@trash.net>
- * (C) 2005-20
08 by Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2005-20
11 by Pablo Neira Ayuso <pablo@netfilter.org>
*
* Initial connection tracking via netlink development funded and
* generally made possible by Network Robots, Inc. (www.networkrobots.com)
static inline int
ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct)
{
- long timeout = (ct->timeout.expires - jiffies) / HZ;
+ long timeout = ((long)ct->timeout.expires - (long)jiffies) / HZ;
if (timeout < 0)
timeout = 0;
}
static int
-ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
- enum ip_conntrack_dir dir)
+dump_counters(struct sk_buff *skb, u64 pkts, u64 bytes,
+ enum ip_conntrack_dir dir)
{
enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
struct nlattr *nest_count;
- const struct nf_conn_counter *acct;
-
- acct = nf_conn_acct_find(ct);
- if (!acct)
- return 0;
nest_count = nla_nest_start(skb, type | NLA_F_NESTED);
if (!nest_count)
goto nla_put_failure;
- NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS,
- cpu_to_be64(acct[dir].packets));
- NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES,
- cpu_to_be64(acct[dir].bytes));
+ NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts));
+ NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes));
nla_nest_end(skb, nest_count);
return -1;
}
+static int
+ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
+ enum ip_conntrack_dir dir, int type)
+{
+ struct nf_conn_counter *acct;
+ u64 pkts, bytes;
+
+ acct = nf_conn_acct_find(ct);
+ if (!acct)
+ return 0;
+
+ if (type == IPCTNL_MSG_CT_GET_CTRZERO) {
+ pkts = atomic64_xchg(&acct[dir].packets, 0);
+ bytes = atomic64_xchg(&acct[dir].bytes, 0);
+ } else {
+ pkts = atomic64_read(&acct[dir].packets);
+ bytes = atomic64_read(&acct[dir].bytes);
+ }
+ return dump_counters(skb, pkts, bytes, dir);
+}
+
static int
ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct)
{
}
static int
-ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
- int event, struct nf_conn *ct)
+ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
+ struct nf_conn *ct)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
- unsigned int flags = pid ? NLM_F_MULTI : 0;
+ unsigned int flags = pid ? NLM_F_MULTI : 0, event;
- event |= NFNL_SUBSYS_CTNETLINK << 8;
+ event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_NEW);
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
if (nlh == NULL)
goto nlmsg_failure;
if (ctnetlink_dump_status(skb, ct) < 0 ||
ctnetlink_dump_timeout(skb, ct) < 0 ||
- ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
- ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+ ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL, type) < 0 ||
+ ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY, type) < 0 ||
ctnetlink_dump_timestamp(skb, ct) < 0 ||
ctnetlink_dump_protoinfo(skb, ct) < 0 ||
ctnetlink_dump_helpinfo(skb, ct) < 0 ||
goto nla_put_failure;
if (events & (1 << IPCT_DESTROY)) {
- if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
- ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+ if (ctnetlink_dump_counters(skb, ct,
+ IP_CT_DIR_ORIGINAL, type) < 0 ||
+ ctnetlink_dump_counters(skb, ct,
+ IP_CT_DIR_REPLY, type) < 0 ||
ctnetlink_dump_timestamp(skb, ct) < 0)
goto nla_put_failure;
} else {
}
if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
- IPCTNL_MSG_CT_NEW, ct) < 0) {
+ NFNL_MSG_TYPE(
+ cb->nlh->nlmsg_type),
+ ct) < 0) {
nf_conntrack_get(&ct->ct_general);
cb->args[1] = (unsigned long)ct;
goto out;
}
-
- if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) ==
- IPCTNL_MSG_CT_GET_CTRZERO) {
- struct nf_conn_counter *acct;
-
- acct = nf_conn_acct_find(ct);
- if (acct)
- memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]));
- }
}
if (cb->args[1]) {
cb->args[1] = 0;
rcu_read_lock();
err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq,
- IPCTNL_MSG_CT_NEW, ct);
+ NFNL_MSG_TYPE(nlh->nlmsg_type), ct);
rcu_read_unlock();
nf_ct_put(ct);
if (err <= 0)
if (cda[CTA_NAT_DST]) {
ret = ctnetlink_parse_nat_setup(ct,
- IP_NAT_MANIP_DST,
+ NF_NAT_MANIP_DST,
cda[CTA_NAT_DST]);
if (ret < 0)
return ret;
}
if (cda[CTA_NAT_SRC]) {
ret = ctnetlink_parse_nat_setup(ct,
- IP_NAT_MANIP_SRC,
+ NF_NAT_MANIP_SRC,
cda[CTA_NAT_SRC]);
if (ret < 0)
return ret;
nf_ct_protonum(ct));
if (helper == NULL) {
rcu_read_unlock();
+ spin_unlock_bh(&nf_conntrack_lock);
#ifdef CONFIG_MODULES
if (request_module("nfct-helper-%s", helpname) < 0) {
+ spin_lock_bh(&nf_conntrack_lock);
err = -EOPNOTSUPP;
goto err1;
}
+ spin_lock_bh(&nf_conntrack_lock);
rcu_read_lock();
helper = __nf_conntrack_helper_find(helpname,
nf_ct_l3num(ct),
const struct nf_conntrack_expect *exp)
{
struct nf_conn *master = exp->master;
- long timeout = (exp->timeout.expires - jiffies) / HZ;
+ long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
struct nf_conn_help *help;
if (timeout < 0)
if (err < 0)
return err;
- if (cda[CTA_EXPECT_MASTER])
+ if (cda[CTA_EXPECT_TUPLE])
+ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
+ else if (cda[CTA_EXPECT_MASTER])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3);
else
return -EINVAL;
err = -ENOMEM;
skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (skb2 == NULL)
+ if (skb2 == NULL) {
+ nf_ct_expect_put(exp);
goto out;
+ }
rcu_read_lock();
err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid,
nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp);
rcu_read_unlock();
+ nf_ct_expect_put(exp);
if (err <= 0)
goto free;
- nf_ct_expect_put(exp);
+ err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT);
+ if (err < 0)
+ goto out;
- return netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT);
+ return 0;
free:
kfree_skb(skb2);
out:
- nf_ct_expect_put(exp);
- return err;
+ /* this avoids a loop in nfnetlink. */
+ return err == -EAGAIN ? -ENOBUFS : err;
}
static int
}
help = nfct_help(ct);
if (!help) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+ if (test_bit(IPS_USERSPACE_HELPER_BIT, &ct->status)) {
if (!cda[CTA_EXPECT_TIMEOUT]) {
err = -EINVAL;
goto out;
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK);
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP);
+static int __net_init ctnetlink_net_init(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+ int ret;
+
+ ret = nf_conntrack_register_notifier(net, &ctnl_notifier);
+ if (ret < 0) {
+ pr_err("ctnetlink_init: cannot register notifier.\n");
+ goto err_out;
+ }
+
+ ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp);
+ if (ret < 0) {
+ pr_err("ctnetlink_init: cannot expect register notifier.\n");
+ goto err_unreg_notifier;
+ }
+#endif
+ return 0;
+
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+err_unreg_notifier:
+ nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+err_out:
+ return ret;
+#endif
+}
+
+static void ctnetlink_net_exit(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+ nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp);
+ nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+#endif
+}
+
+static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
+{
+ struct net *net;
+
+ list_for_each_entry(net, net_exit_list, exit_list)
+ ctnetlink_net_exit(net);
+}
+
+static struct pernet_operations ctnetlink_net_ops = {
+ .init = ctnetlink_net_init,
+ .exit_batch = ctnetlink_net_exit_batch,
+};
+
static int __init ctnetlink_init(void)
{
int ret;
goto err_unreg_subsys;
}
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
- ret = nf_conntrack_register_notifier(&ctnl_notifier);
- if (ret < 0) {
- pr_err("ctnetlink_init: cannot register notifier.\n");
+ if (register_pernet_subsys(&ctnetlink_net_ops)) {
+ pr_err("ctnetlink_init: cannot register pernet operations\n");
goto err_unreg_exp_subsys;
}
- ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp);
- if (ret < 0) {
- pr_err("ctnetlink_init: cannot expect register notifier.\n");
- goto err_unreg_notifier;
- }
-#endif
-
return 0;
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-err_unreg_notifier:
- nf_conntrack_unregister_notifier(&ctnl_notifier);
err_unreg_exp_subsys:
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
-#endif
err_unreg_subsys:
nfnetlink_subsys_unregister(&ctnl_subsys);
err_out:
{
pr_info("ctnetlink: unregistering from nfnetlink.\n");
- nf_ct_remove_userspace_expectations();
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
- nf_ct_expect_unregister_notifier(&ctnl_notifier_exp);
- nf_conntrack_unregister_notifier(&ctnl_notifier);
-#endif
-
+ unregister_pernet_subsys(&ctnetlink_net_ops);
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
nfnetlink_subsys_unregister(&ctnl_subsys);
}
return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
}
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
struct nf_conn *ct)
{
.error = dccp_error,
.print_tuple = dccp_print_tuple,
.print_conntrack = dccp_print_conntrack,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = dccp_to_nlattr,
.nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.error = dccp_error,
.print_tuple = dccp_print_tuple,
.print_conntrack = dccp_print_conntrack,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = dccp_to_nlattr,
.nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.new = gre_new,
.destroy = gre_destroy,
.me = THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
return true;
}
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
.packet = sctp_packet,
.new = sctp_new,
.me = THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = sctp_to_nlattr,
.nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
.packet = sctp_packet,
.new = sctp_new,
.me = THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = sctp_to_nlattr,
.nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
return true;
}
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
.packet = tcp_packet,
.new = tcp_new,
.error = tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = tcp_to_nlattr,
.nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.packet = tcp_packet,
.new = tcp_new,
.error = tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = tcp_to_nlattr,
.nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.packet = udp_packet,
.new = udp_new,
.error = udp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.packet = udp_packet,
.new = udp_new,
.error = udp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.packet = udplite_packet,
.new = udplite_new,
.error = udplite_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.packet = udplite_packet,
.new = udplite_new,
.error = udplite_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
MODULE_LICENSE("GPL");
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_NF_CONNTRACK_PROCFS
int
print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_l3proto *l3proto,
static void nf_conntrack_standalone_fini_proc(struct net *net)
{
}
-#endif /* CONFIG_PROC_FS */
+#endif /* CONFIG_NF_CONNTRACK_PROCFS */
/* Sysctl support */
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
-static int nf_ct_tstamp __read_mostly;
+static bool nf_ct_tstamp __read_mostly;
module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
--- /dev/null
+/*
+ * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2011 Intra2net AG <http://www.intra2net.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation (or any later at your option).
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <net/netlink.h>
+#include <net/sock.h>
+#include <asm/atomic.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_acct.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("nfacct: Extended Netfilter accounting infrastructure");
+
+static LIST_HEAD(nfnl_acct_list);
+
+struct nf_acct {
+ atomic64_t pkts;
+ atomic64_t bytes;
+ struct list_head head;
+ atomic_t refcnt;
+ char name[NFACCT_NAME_MAX];
+ struct rcu_head rcu_head;
+};
+
+static int
+nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ struct nf_acct *nfacct, *matching = NULL;
+ char *acct_name;
+
+ if (!tb[NFACCT_NAME])
+ return -EINVAL;
+
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(nfacct, &nfnl_acct_list, head) {
+ if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0)
+ continue;
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+
+ matching = nfacct;
+ break;
+ }
+
+ if (matching) {
+ if (nlh->nlmsg_flags & NLM_F_REPLACE) {
+ /* reset counters if you request a replacement. */
+ atomic64_set(&matching->pkts, 0);
+ atomic64_set(&matching->bytes, 0);
+ return 0;
+ }
+ return -EBUSY;
+ }
+
+ nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL);
+ if (nfacct == NULL)
+ return -ENOMEM;
+
+ strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
+
+ if (tb[NFACCT_BYTES]) {
+ atomic64_set(&nfacct->bytes,
+ be64_to_cpu(nla_get_u64(tb[NFACCT_BYTES])));
+ }
+ if (tb[NFACCT_PKTS]) {
+ atomic64_set(&nfacct->pkts,
+ be64_to_cpu(nla_get_u64(tb[NFACCT_PKTS])));
+ }
+ atomic_set(&nfacct->refcnt, 1);
+ list_add_tail_rcu(&nfacct->head, &nfnl_acct_list);
+ return 0;
+}
+
+static int
+nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
+ int event, struct nf_acct *acct)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+ unsigned int flags = pid ? NLM_F_MULTI : 0;
+ u64 pkts, bytes;
+
+ event |= NFNL_SUBSYS_ACCT << 8;
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = AF_UNSPEC;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ NLA_PUT_STRING(skb, NFACCT_NAME, acct->name);
+
+ if (type == NFNL_MSG_ACCT_GET_CTRZERO) {
+ pkts = atomic64_xchg(&acct->pkts, 0);
+ bytes = atomic64_xchg(&acct->bytes, 0);
+ } else {
+ pkts = atomic64_read(&acct->pkts);
+ bytes = atomic64_read(&acct->bytes);
+ }
+ NLA_PUT_BE64(skb, NFACCT_PKTS, cpu_to_be64(pkts));
+ NLA_PUT_BE64(skb, NFACCT_BYTES, cpu_to_be64(bytes));
+ NLA_PUT_BE32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)));
+
+ nlmsg_end(skb, nlh);
+ return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -1;
+}
+
+static int
+nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct nf_acct *cur, *last;
+
+ if (cb->args[2])
+ return 0;
+
+ last = (struct nf_acct *)cb->args[1];
+ if (cb->args[1])
+ cb->args[1] = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(cur, &nfnl_acct_list, head) {
+ if (last && cur != last)
+ continue;
+
+ if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+ NFNL_MSG_ACCT_NEW, cur) < 0) {
+ cb->args[1] = (unsigned long)cur;
+ break;
+ }
+ }
+ if (!cb->args[1])
+ cb->args[2] = 1;
+ rcu_read_unlock();
+ return skb->len;
+}
+
+static int
+nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ int ret = -ENOENT;
+ struct nf_acct *cur;
+ char *acct_name;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ return netlink_dump_start(nfnl, skb, nlh, nfnl_acct_dump,
+ NULL, 0);
+ }
+
+ if (!tb[NFACCT_NAME])
+ return -EINVAL;
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(cur, &nfnl_acct_list, head) {
+ struct sk_buff *skb2;
+
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
+ continue;
+
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).pid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_ACCT_NEW, cur);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ break;
+ }
+ ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid,
+ MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
+
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
+ }
+ return ret;
+}
+
+/* try to delete object, fail if it is still in use. */
+static int nfnl_acct_try_del(struct nf_acct *cur)
+{
+ int ret = 0;
+
+ /* we want to avoid races with nfnl_acct_find_get. */
+ if (atomic_dec_and_test(&cur->refcnt)) {
+ /* We are protected by nfnl mutex. */
+ list_del_rcu(&cur->head);
+ kfree_rcu(cur, rcu_head);
+ } else {
+ /* still in use, restore reference counter. */
+ atomic_inc(&cur->refcnt);
+ ret = -EBUSY;
+ }
+ return ret;
+}
+
+static int
+nfnl_acct_del(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ char *acct_name;
+ struct nf_acct *cur;
+ int ret = -ENOENT;
+
+ if (!tb[NFACCT_NAME]) {
+ list_for_each_entry(cur, &nfnl_acct_list, head)
+ nfnl_acct_try_del(cur);
+
+ return 0;
+ }
+ acct_name = nla_data(tb[NFACCT_NAME]);
+
+ list_for_each_entry(cur, &nfnl_acct_list, head) {
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX) != 0)
+ continue;
+
+ ret = nfnl_acct_try_del(cur);
+ if (ret < 0)
+ return ret;
+
+ break;
+ }
+ return ret;
+}
+
+static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
+ [NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 },
+ [NFACCT_BYTES] = { .type = NLA_U64 },
+ [NFACCT_PKTS] = { .type = NLA_U64 },
+};
+
+static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
+ [NFNL_MSG_ACCT_NEW] = { .call = nfnl_acct_new,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_GET] = { .call = nfnl_acct_get,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_GET_CTRZERO] = { .call = nfnl_acct_get,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+ [NFNL_MSG_ACCT_DEL] = { .call = nfnl_acct_del,
+ .attr_count = NFACCT_MAX,
+ .policy = nfnl_acct_policy },
+};
+
+static const struct nfnetlink_subsystem nfnl_acct_subsys = {
+ .name = "acct",
+ .subsys_id = NFNL_SUBSYS_ACCT,
+ .cb_count = NFNL_MSG_ACCT_MAX,
+ .cb = nfnl_acct_cb,
+};
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ACCT);
+
+struct nf_acct *nfnl_acct_find_get(const char *acct_name)
+{
+ struct nf_acct *cur, *acct = NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(cur, &nfnl_acct_list, head) {
+ if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
+ continue;
+
+ if (!try_module_get(THIS_MODULE))
+ goto err;
+
+ if (!atomic_inc_not_zero(&cur->refcnt)) {
+ module_put(THIS_MODULE);
+ goto err;
+ }
+
+ acct = cur;
+ break;
+ }
+err:
+ rcu_read_unlock();
+ return acct;
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_find_get);
+
+void nfnl_acct_put(struct nf_acct *acct)
+{
+ atomic_dec(&acct->refcnt);
+ module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_put);
+
+void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct)
+{
+ atomic64_inc(&nfacct->pkts);
+ atomic64_add(skb->len, &nfacct->bytes);
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_update);
+
+static int __init nfnl_acct_init(void)
+{
+ int ret;
+
+ pr_info("nfnl_acct: registering with nfnetlink.\n");
+ ret = nfnetlink_subsys_register(&nfnl_acct_subsys);
+ if (ret < 0) {
+ pr_err("nfnl_acct_init: cannot register with nfnetlink.\n");
+ goto err_out;
+ }
+ return 0;
+err_out:
+ return ret;
+}
+
+static void __exit nfnl_acct_exit(void)
+{
+ struct nf_acct *cur, *tmp;
+
+ pr_info("nfnl_acct: unregistering from nfnetlink.\n");
+ nfnetlink_subsys_unregister(&nfnl_acct_subsys);
+
+ list_for_each_entry_safe(cur, tmp, &nfnl_acct_list, head) {
+ list_del_rcu(&cur->head);
+ /* We are sure that our objects have no clients at this point,
+ * it's safe to release them all without checking refcnt. */
+ kfree_rcu(cur, rcu_head);
+ }
+}
+
+module_init(nfnl_acct_init);
+module_exit(nfnl_acct_exit);
struct ipv6hdr _ip6h;
const struct ipv6hdr *ih;
u8 nexthdr;
+ __be16 frag_off;
int offset;
ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
nexthdr = ih->nexthdr;
offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
- &nexthdr);
+ &nexthdr, &frag_off);
audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
&ih->saddr, &ih->daddr, nexthdr);
int ret = 0;
u8 proto;
- if (info->flags & ~XT_CT_NOTRACK)
- return -EINVAL;
+ if (info->flags & ~(XT_CT_NOTRACK | XT_CT_USERSPACE_HELPER))
+ return -EOPNOTSUPP;
if (info->flags & XT_CT_NOTRACK) {
ct = nf_ct_untracked_get();
GFP_KERNEL))
goto err3;
- if (info->helper[0]) {
+ if (info->flags & XT_CT_USERSPACE_HELPER) {
+ __set_bit(IPS_USERSPACE_HELPER_BIT, &ct->status);
+ } else if (info->helper[0]) {
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto) {
return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval);
}
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static u32 hash_v6(const struct sk_buff *skb)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
if (par->family == NFPROTO_IPV4)
queue = (((u64) hash_v4(skb) * info->queues_total) >>
32) + queue;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
else if (par->family == NFPROTO_IPV6)
queue = (((u64) hash_v6(skb) * info->queues_total) >>
32) + queue;
struct flowi6 *fl6 = &fl.u.ip6;
memset(fl6, 0, sizeof(*fl6));
- ipv6_addr_copy(&fl6->daddr, &ipv6_hdr(skb)->saddr);
+ fl6->daddr = ipv6_hdr(skb)->saddr;
}
rcu_read_lock();
ai = nf_get_afinfo(family);
return XT_CONTINUE;
}
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static unsigned int
tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
u8 nexthdr;
+ __be16 frag_off;
int tcphoff;
int ret;
nexthdr = ipv6h->nexthdr;
- tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+ tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
if (tcphoff < 0)
return NF_DROP;
ret = tcpmss_mangle_packet(skb, par->targinfo,
return -EINVAL;
}
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static int tcpmss_tg6_check(const struct xt_tgchk_param *par)
{
const struct xt_tcpmss_info *info = par->targinfo;
.proto = IPPROTO_TCP,
.me = THIS_MODULE,
},
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.family = NFPROTO_IPV6,
.name = "TCPMSS",
sizeof(struct iphdr) + sizeof(struct tcphdr));
}
-#if defined(CONFIG_IP6_NF_MANGLE) || defined(CONFIG_IP6_NF_MANGLE_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_MANGLE)
static unsigned int
tcpoptstrip_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
int tcphoff;
u_int8_t nexthdr;
+ __be16 frag_off;
nexthdr = ipv6h->nexthdr;
- tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+ tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
if (tcphoff < 0)
return NF_DROP;
.targetsize = sizeof(struct xt_tcpoptstrip_target_info),
.me = THIS_MODULE,
},
-#if defined(CONFIG_IP6_NF_MANGLE) || defined(CONFIG_IP6_NF_MANGLE_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_MANGLE)
{
.name = "TCPOPTSTRIP",
.family = NFPROTO_IPV6,
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_TEE.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
# define WITH_CONNTRACK 1
# include <net/netfilter/nf_conntrack.h>
#endif
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-# define WITH_IPV6 1
-#endif
struct xt_tee_priv {
struct notifier_block notifier;
return XT_CONTINUE;
}
-#ifdef WITH_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
static bool
tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
{
}
return XT_CONTINUE;
}
-#endif /* WITH_IPV6 */
+#endif
static int tee_netdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
.destroy = tee_tg_destroy,
.me = THIS_MODULE,
},
-#ifdef WITH_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
{
.name = "TEE",
.revision = 1,
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#define XT_TPROXY_HAVE_IPV6 1
#include <net/if_inet6.h>
#include <net/addrconf.h>
#include <linux/ip.h>
#include <net/route.h>
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/ip6_fib.h>
MODULE_ALIAS("ipt_addrtype");
MODULE_ALIAS("ip6t_addrtype");
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
const struct in6_addr *addr)
{
int route_err;
memset(&flow, 0, sizeof(flow));
- ipv6_addr_copy(&flow.daddr, addr);
+ flow.daddr = *addr;
if (dev)
flow.flowi6_oif = dev->ifindex;
else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT)
dev = par->out;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
if (par->family == NFPROTO_IPV6)
return addrtype_mt6(net, dev, skb, info);
#endif
return -EINVAL;
}
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
if (par->family == NFPROTO_IPV6) {
if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) {
pr_err("ipv6 BLACKHOLE matching not supported\n");
case XT_CONNBYTES_PKTS:
switch (sinfo->direction) {
case XT_CONNBYTES_DIR_ORIGINAL:
- what = counters[IP_CT_DIR_ORIGINAL].packets;
+ what = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].packets);
break;
case XT_CONNBYTES_DIR_REPLY:
- what = counters[IP_CT_DIR_REPLY].packets;
+ what = atomic64_read(&counters[IP_CT_DIR_REPLY].packets);
break;
case XT_CONNBYTES_DIR_BOTH:
- what = counters[IP_CT_DIR_ORIGINAL].packets;
- what += counters[IP_CT_DIR_REPLY].packets;
+ what = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].packets);
+ what += atomic64_read(&counters[IP_CT_DIR_REPLY].packets);
break;
}
break;
case XT_CONNBYTES_BYTES:
switch (sinfo->direction) {
case XT_CONNBYTES_DIR_ORIGINAL:
- what = counters[IP_CT_DIR_ORIGINAL].bytes;
+ what = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].bytes);
break;
case XT_CONNBYTES_DIR_REPLY:
- what = counters[IP_CT_DIR_REPLY].bytes;
+ what = atomic64_read(&counters[IP_CT_DIR_REPLY].bytes);
break;
case XT_CONNBYTES_DIR_BOTH:
- what = counters[IP_CT_DIR_ORIGINAL].bytes;
- what += counters[IP_CT_DIR_REPLY].bytes;
+ what = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].bytes);
+ what += atomic64_read(&counters[IP_CT_DIR_REPLY].bytes);
break;
}
break;
case XT_CONNBYTES_AVGPKT:
switch (sinfo->direction) {
case XT_CONNBYTES_DIR_ORIGINAL:
- bytes = counters[IP_CT_DIR_ORIGINAL].bytes;
- pkts = counters[IP_CT_DIR_ORIGINAL].packets;
+ bytes = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].bytes);
+ pkts = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].packets);
break;
case XT_CONNBYTES_DIR_REPLY:
- bytes = counters[IP_CT_DIR_REPLY].bytes;
- pkts = counters[IP_CT_DIR_REPLY].packets;
+ bytes = atomic64_read(&counters[IP_CT_DIR_REPLY].bytes);
+ pkts = atomic64_read(&counters[IP_CT_DIR_REPLY].packets);
break;
case XT_CONNBYTES_DIR_BOTH:
- bytes = counters[IP_CT_DIR_ORIGINAL].bytes +
- counters[IP_CT_DIR_REPLY].bytes;
- pkts = counters[IP_CT_DIR_ORIGINAL].packets +
- counters[IP_CT_DIR_REPLY].packets;
+ bytes = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].bytes) +
+ atomic64_read(&counters[IP_CT_DIR_REPLY].bytes);
+ pkts = atomic64_read(&counters[IP_CT_DIR_ORIGINAL].packets) +
+ atomic64_read(&counters[IP_CT_DIR_REPLY].packets);
break;
}
if (pkts != 0)
break;
}
- if (sinfo->count.to)
+ if (sinfo->count.to >= sinfo->count.from)
return what <= sinfo->count.to && what >= sinfo->count.from;
- else
- return what >= sinfo->count.from;
+ else /* inverted */
+ return what < sinfo->count.to || what > sinfo->count.from;
}
static int connbytes_mt_check(const struct xt_mtchk_param *par)
--- /dev/null
+/*
+ * Xtables module for matching the value of the IPv4/IPv6 and TCP ECN bits
+ *
+ * (C) 2002 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_ecn.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
+MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag match");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_ecn");
+MODULE_ALIAS("ip6t_ecn");
+
+static bool match_tcp(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ecn_info *einfo = par->matchinfo;
+ struct tcphdr _tcph;
+ const struct tcphdr *th;
+
+ /* In practice, TCP match does this, so can't fail. But let's
+ * be good citizens.
+ */
+ th = skb_header_pointer(skb, par->thoff, sizeof(_tcph), &_tcph);
+ if (th == NULL)
+ return false;
+
+ if (einfo->operation & XT_ECN_OP_MATCH_ECE) {
+ if (einfo->invert & XT_ECN_OP_MATCH_ECE) {
+ if (th->ece == 1)
+ return false;
+ } else {
+ if (th->ece == 0)
+ return false;
+ }
+ }
+
+ if (einfo->operation & XT_ECN_OP_MATCH_CWR) {
+ if (einfo->invert & XT_ECN_OP_MATCH_CWR) {
+ if (th->cwr == 1)
+ return false;
+ } else {
+ if (th->cwr == 0)
+ return false;
+ }
+ }
+
+ return true;
+}
+
+static inline bool match_ip(const struct sk_buff *skb,
+ const struct xt_ecn_info *einfo)
+{
+ return ((ip_hdr(skb)->tos & XT_ECN_IP_MASK) == einfo->ip_ect) ^
+ !!(einfo->invert & XT_ECN_OP_MATCH_IP);
+}
+
+static bool ecn_mt4(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ecn_info *info = par->matchinfo;
+
+ if (info->operation & XT_ECN_OP_MATCH_IP && !match_ip(skb, info))
+ return false;
+
+ if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) &&
+ !match_tcp(skb, par))
+ return false;
+
+ return true;
+}
+
+static int ecn_mt_check4(const struct xt_mtchk_param *par)
+{
+ const struct xt_ecn_info *info = par->matchinfo;
+ const struct ipt_ip *ip = par->entryinfo;
+
+ if (info->operation & XT_ECN_OP_MATCH_MASK)
+ return -EINVAL;
+
+ if (info->invert & XT_ECN_OP_MATCH_MASK)
+ return -EINVAL;
+
+ if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) &&
+ (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) {
+ pr_info("cannot match TCP bits in rule for non-tcp packets\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static inline bool match_ipv6(const struct sk_buff *skb,
+ const struct xt_ecn_info *einfo)
+{
+ return (((ipv6_hdr(skb)->flow_lbl[0] >> 4) & XT_ECN_IP_MASK) ==
+ einfo->ip_ect) ^
+ !!(einfo->invert & XT_ECN_OP_MATCH_IP);
+}
+
+static bool ecn_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ecn_info *info = par->matchinfo;
+
+ if (info->operation & XT_ECN_OP_MATCH_IP && !match_ipv6(skb, info))
+ return false;
+
+ if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) &&
+ !match_tcp(skb, par))
+ return false;
+
+ return true;
+}
+
+static int ecn_mt_check6(const struct xt_mtchk_param *par)
+{
+ const struct xt_ecn_info *info = par->matchinfo;
+ const struct ip6t_ip6 *ip = par->entryinfo;
+
+ if (info->operation & XT_ECN_OP_MATCH_MASK)
+ return -EINVAL;
+
+ if (info->invert & XT_ECN_OP_MATCH_MASK)
+ return -EINVAL;
+
+ if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) &&
+ (ip->proto != IPPROTO_TCP || ip->invflags & IP6T_INV_PROTO)) {
+ pr_info("cannot match TCP bits in rule for non-tcp packets\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match ecn_mt_reg[] __read_mostly = {
+ {
+ .name = "ecn",
+ .family = NFPROTO_IPV4,
+ .match = ecn_mt4,
+ .matchsize = sizeof(struct xt_ecn_info),
+ .checkentry = ecn_mt_check4,
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "ecn",
+ .family = NFPROTO_IPV6,
+ .match = ecn_mt6,
+ .matchsize = sizeof(struct xt_ecn_info),
+ .checkentry = ecn_mt_check6,
+ .me = THIS_MODULE,
+ },
+};
+
+static int __init ecn_mt_init(void)
+{
+ return xt_register_matches(ecn_mt_reg, ARRAY_SIZE(ecn_mt_reg));
+}
+
+static void __exit ecn_mt_exit(void)
+{
+ xt_unregister_matches(ecn_mt_reg, ARRAY_SIZE(ecn_mt_reg));
+}
+
+module_init(ecn_mt_init);
+module_exit(ecn_mt_exit);
#include <linux/mm.h>
#include <linux/in.h>
#include <linux/ip.h>
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#include <linux/ipv6.h>
#include <net/ipv6.h>
#endif
__be32 src;
__be32 dst;
} ip;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
struct {
__be32 src[4];
__be32 dst[4];
return l ? htonl(ntohl(a) & ~0 << (32 - l)) : 0;
}
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static void hashlimit_ipv6_mask(__be32 *i, unsigned int p)
{
switch (p) {
{
__be16 _ports[2], *ports;
u8 nexthdr;
+ __be16 frag_off;
int poff;
memset(dst, 0, sizeof(*dst));
return 0;
nexthdr = ip_hdr(skb)->protocol;
break;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
case NFPROTO_IPV6:
if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) {
memcpy(&dst->ip6.dst, &ipv6_hdr(skb)->daddr,
(XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT)))
return 0;
nexthdr = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+ protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off);
if ((int)protoff < 0)
return -1;
break;
.destroy = hashlimit_mt_destroy,
.me = THIS_MODULE,
},
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.name = "hashlimit",
.revision = 1,
ent->rateinfo.credit, ent->rateinfo.credit_cap,
ent->rateinfo.cost);
break;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
case NFPROTO_IPV6:
res = seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n",
(long)(ent->expires - jiffies)/HZ,
hashlimit_net->ipt_hashlimit = proc_mkdir("ipt_hashlimit", net->proc_net);
if (!hashlimit_net->ipt_hashlimit)
return -ENOMEM;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net);
if (!hashlimit_net->ip6t_hashlimit) {
proc_net_remove(net, "ipt_hashlimit");
static void __net_exit hashlimit_proc_net_exit(struct net *net)
{
proc_net_remove(net, "ipt_hashlimit");
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
proc_net_remove(net, "ip6t_hashlimit");
#endif
}
--- /dev/null
+/*
+ * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2011 Intra2net AG <http://www.intra2net.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 (or any
+ * later at your option) as published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/nfnetlink_acct.h>
+#include <linux/netfilter/xt_nfacct.h>
+
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("Xtables: match for the extended accounting infrastructure");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_nfacct");
+MODULE_ALIAS("ip6t_nfacct");
+
+static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_nfacct_match_info *info = par->targinfo;
+
+ nfnl_acct_update(skb, info->nfacct);
+
+ return true;
+}
+
+static int
+nfacct_mt_checkentry(const struct xt_mtchk_param *par)
+{
+ struct xt_nfacct_match_info *info = par->matchinfo;
+ struct nf_acct *nfacct;
+
+ nfacct = nfnl_acct_find_get(info->name);
+ if (nfacct == NULL) {
+ pr_info("xt_nfacct: accounting object with name `%s' "
+ "does not exists\n", info->name);
+ return -ENOENT;
+ }
+ info->nfacct = nfacct;
+ return 0;
+}
+
+static void
+nfacct_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_nfacct_match_info *info = par->matchinfo;
+
+ nfnl_acct_put(info->nfacct);
+}
+
+static struct xt_match nfacct_mt_reg __read_mostly = {
+ .name = "nfacct",
+ .family = NFPROTO_UNSPEC,
+ .checkentry = nfacct_mt_checkentry,
+ .match = nfacct_mt,
+ .destroy = nfacct_mt_destroy,
+ .matchsize = sizeof(struct xt_nfacct_match_info),
+ .me = THIS_MODULE,
+};
+
+static int __init nfacct_mt_init(void)
+{
+ return xt_register_match(&nfacct_mt_reg);
+}
+
+static void __exit nfacct_mt_exit(void)
+{
+ xt_unregister_match(&nfacct_mt_reg);
+}
+
+module_init(nfacct_mt_init);
+module_exit(nfacct_mt_exit);
#include <net/netfilter/nf_tproxy_core.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
#define XT_SOCKET_HAVE_IPV6 1
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <linux/netfilter/xt_socket.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#define XT_SOCKET_HAVE_CONNTRACK 1
#include <net/netfilter/nf_conntrack.h>
#endif
struct icmp6hdr *icmph, _icmph;
__be16 *ports, _ports[2];
u8 inside_nexthdr;
+ __be16 inside_fragoff;
int inside_hdrlen;
icmph = skb_header_pointer(skb, outside_hdrlen,
return 1;
inside_nexthdr = inside_iph->nexthdr;
- inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), &inside_nexthdr);
+ inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph),
+ &inside_nexthdr, &inside_fragoff);
if (inside_hdrlen < 0)
return 1; /* hjm: Packet has no/incomplete transport layer headers. */
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_af6list_search - Search for a matching IPv6 address entry
* @addr: IPv6 address
return 0;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_af6list_add - Add a new IPv6 address entry to a list
* @entry: address entry
return entry;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_af6list_remove_entry - Remove an IPv6 address entry
* @entry: address entry
}
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_af6list_audit_addr - Audit an IPv6 address
* @audit_buf: audit buffer
}
#endif
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#define __af6list_entry(ptr) container_of(ptr, struct netlbl_af6list, list)
struct netlbl_dom_map *ptr;
struct netlbl_af4list *iter4;
struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
struct netlbl_af6list *tmp6;
#endif /* IPv6 */
netlbl_af4list_remove_entry(iter4);
kfree(netlbl_domhsh_addr4_entry(iter4));
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_safe(iter6, tmp6,
&ptr->type_def.addrsel->list6) {
netlbl_af6list_remove_entry(iter6);
cipsov4 = map4->type_def.cipsov4;
netlbl_af4list_audit_addr(audit_buf, 0, NULL,
addr4->addr, addr4->mask);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
} else if (addr6 != NULL) {
struct netlbl_domaddr6_map *map6;
map6 = netlbl_domhsh_addr6_entry(addr6);
struct netlbl_dom_map *entry_old;
struct netlbl_af4list *iter4;
struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
struct netlbl_af6list *tmp6;
#endif /* IPv6 */
&entry->type_def.addrsel->list4)
netlbl_domhsh_audit_add(entry, iter4, NULL,
ret_val, audit_info);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(iter6,
&entry->type_def.addrsel->list6)
netlbl_domhsh_audit_add(entry, NULL, iter6,
ret_val = -EEXIST;
goto add_return;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(iter6,
&entry->type_def.addrsel->list6)
if (netlbl_af6list_search_exact(&iter6->addr,
if (ret_val != 0)
goto add_return;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_safe(iter6, tmp6,
&entry->type_def.addrsel->list6) {
netlbl_af6list_remove_entry(iter6);
struct netlbl_dom_map *entry_map;
struct netlbl_af4list *entry_addr;
struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
#endif /* IPv6 */
struct netlbl_domaddr4_map *entry;
goto remove_af4_failure;
netlbl_af4list_foreach_rcu(iter4, &entry_map->type_def.addrsel->list4)
goto remove_af4_single_addr;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(iter6, &entry_map->type_def.addrsel->list6)
goto remove_af4_single_addr;
#endif /* IPv6 */
return netlbl_domhsh_addr4_entry(addr_iter);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_domhsh_getentry_af6 - Get an entry from the domain hash table
* @domain: the domain name to search for
int (*callback) (struct netlbl_dom_map *entry, void *arg),
void *cb_arg);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain,
const struct in6_addr *addr);
#endif /* IPv6 */
struct netlbl_domaddr_map *addrmap = NULL;
struct netlbl_domaddr4_map *map4 = NULL;
struct netlbl_domaddr6_map *map6 = NULL;
- const struct in_addr *addr4, *mask4;
- const struct in6_addr *addr6, *mask6;
entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
if (entry == NULL)
INIT_LIST_HEAD(&addrmap->list6);
switch (family) {
- case AF_INET:
- addr4 = addr;
- mask4 = mask;
+ case AF_INET: {
+ const struct in_addr *addr4 = addr;
+ const struct in_addr *mask4 = mask;
map4 = kzalloc(sizeof(*map4), GFP_ATOMIC);
if (map4 == NULL)
goto cfg_unlbl_map_add_failure;
if (ret_val != 0)
goto cfg_unlbl_map_add_failure;
break;
- case AF_INET6:
- addr6 = addr;
- mask6 = mask;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6: {
+ const struct in6_addr *addr6 = addr;
+ const struct in6_addr *mask6 = mask;
map6 = kzalloc(sizeof(*map6), GFP_ATOMIC);
if (map6 == NULL)
goto cfg_unlbl_map_add_failure;
map6->type = NETLBL_NLTYPE_UNLABELED;
- ipv6_addr_copy(&map6->list.addr, addr6);
+ map6->list.addr = *addr6;
map6->list.addr.s6_addr32[0] &= mask6->s6_addr32[0];
map6->list.addr.s6_addr32[1] &= mask6->s6_addr32[1];
map6->list.addr.s6_addr32[2] &= mask6->s6_addr32[2];
map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3];
- ipv6_addr_copy(&map6->list.mask, mask6);
+ map6->list.mask = *mask6;
map6->list.valid = 1;
- ret_val = netlbl_af4list_add(&map4->list,
- &addrmap->list4);
+ ret_val = netlbl_af6list_add(&map6->list,
+ &addrmap->list6);
if (ret_val != 0)
goto cfg_unlbl_map_add_failure;
break;
+ }
+#endif /* IPv6 */
default:
goto cfg_unlbl_map_add_failure;
break;
case AF_INET:
addr_len = sizeof(struct in_addr);
break;
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
addr_len = sizeof(struct in6_addr);
break;
+#endif /* IPv6 */
default:
return -EPFNOSUPPORT;
}
case AF_INET:
addr_len = sizeof(struct in_addr);
break;
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
addr_len = sizeof(struct in6_addr);
break;
+#endif /* IPv6 */
default:
return -EPFNOSUPPORT;
}
ret_val = -ENOENT;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
/* since we don't support any IPv6 labeling protocols right
* now we can optimize everything away until we do */
case AF_INET:
ret_val = cipso_v4_sock_getattr(sk, secattr);
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
ret_val = -ENOMSG;
break;
ret_val = -ENOENT;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
/* since we don't support any IPv6 labeling protocols right
* now we can optimize everything away until we do */
ret_val = -ENOENT;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
/* since we don't support any IPv6 labeling protocols right
* now we can optimize everything away until we do */
ret_val = -ENOENT;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
/* since we don't support any IPv6 labeling protocols right
* now we can optimize everything away until we do */
cipso_v4_skbuff_getattr(skb, secattr) == 0)
return 0;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
break;
#endif /* IPv6 */
entry->type = NETLBL_NLTYPE_ADDRSELECT;
entry->type_def.addrsel = addrmap;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
} else if (info->attrs[NLBL_MGMT_A_IPV6ADDR]) {
struct in6_addr *addr;
struct in6_addr *mask;
ret_val = -ENOMEM;
goto add_failure;
}
- ipv6_addr_copy(&map->list.addr, addr);
+ map->list.addr = *addr;
map->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
map->list.addr.s6_addr32[1] &= mask->s6_addr32[1];
map->list.addr.s6_addr32[2] &= mask->s6_addr32[2];
map->list.addr.s6_addr32[3] &= mask->s6_addr32[3];
- ipv6_addr_copy(&map->list.mask, mask);
+ map->list.mask = *mask;
map->list.valid = 1;
map->type = entry->type;
struct nlattr *nla_a;
struct nlattr *nla_b;
struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
#endif
nla_nest_end(skb, nla_b);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(iter6,
&entry->type_def.addrsel->list6) {
struct netlbl_domaddr6_map *map6;
struct netlbl_unlhsh_iface *iface;
struct netlbl_af4list *iter4;
struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
struct netlbl_af6list *tmp6;
#endif /* IPv6 */
netlbl_af4list_remove_entry(iter4);
kfree(netlbl_unlhsh_addr4_entry(iter4));
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_safe(iter6, tmp6, &iface->addr6_list) {
netlbl_af6list_remove_entry(iter6);
kfree(netlbl_unlhsh_addr6_entry(iter6));
return ret_val;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_unlhsh_add_addr6 - Add a new IPv6 address entry to the hash table
* @iface: the associated interface entry
if (entry == NULL)
return -ENOMEM;
- ipv6_addr_copy(&entry->list.addr, addr);
+ entry->list.addr = *addr;
entry->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
entry->list.addr.s6_addr32[1] &= mask->s6_addr32[1];
entry->list.addr.s6_addr32[2] &= mask->s6_addr32[2];
entry->list.addr.s6_addr32[3] &= mask->s6_addr32[3];
- ipv6_addr_copy(&entry->list.mask, mask);
+ entry->list.mask = *mask;
entry->list.valid = 1;
entry->secid = secid;
mask4->s_addr);
break;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case sizeof(struct in6_addr): {
const struct in6_addr *addr6 = addr;
const struct in6_addr *mask6 = mask;
return 0;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/**
* netlbl_unlhsh_remove_addr6 - Remove an IPv6 address entry
* @net: network namespace
static void netlbl_unlhsh_condremove_iface(struct netlbl_unlhsh_iface *iface)
{
struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *iter6;
#endif /* IPv6 */
spin_lock(&netlbl_unlhsh_lock);
netlbl_af4list_foreach_rcu(iter4, &iface->addr4_list)
goto unlhsh_condremove_failure;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(iter6, &iface->addr6_list)
goto unlhsh_condremove_failure;
#endif /* IPv6 */
iface, addr, mask,
audit_info);
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case sizeof(struct in6_addr):
ret_val = netlbl_unlhsh_remove_addr6(net,
iface, addr, mask,
struct netlbl_unlhsh_iface *iface;
struct list_head *iter_list;
struct netlbl_af4list *addr4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct netlbl_af6list *addr6;
#endif
goto unlabel_staticlist_return;
}
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(addr6,
&iface->addr6_list) {
if (iter_addr6++ < skip_addr6)
u32 skip_addr6 = cb->args[1];
u32 iter_addr4 = 0;
struct netlbl_af4list *addr4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
u32 iter_addr6 = 0;
struct netlbl_af6list *addr6;
#endif
goto unlabel_staticlistdef_return;
}
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) {
if (iter_addr6++ < skip_addr6)
continue;
secattr->attr.secid = netlbl_unlhsh_addr4_entry(addr4)->secid;
break;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6: {
struct ipv6hdr *hdr6;
struct netlbl_af6list *addr6;
static ATOMIC_NOTIFIER_HEAD(netlink_chain);
-static u32 netlink_group_mask(u32 group)
+static inline u32 netlink_group_mask(u32 group)
{
return group ? 1 << (group - 1) : 0;
}
-static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
+static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
{
return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
}
wake_up(&nl_table_wait);
}
-static inline struct sock *netlink_lookup(struct net *net, int protocol,
- u32 pid)
+static struct sock *netlink_lookup(struct net *net, int protocol, u32 pid)
{
struct nl_pid_hash *hash = &nl_table[protocol].hash;
struct hlist_head *head;
return sk;
}
-static inline struct hlist_head *nl_pid_hash_zalloc(size_t size)
+static struct hlist_head *nl_pid_hash_zalloc(size_t size)
{
if (size <= PAGE_SIZE)
return kzalloc(size, GFP_ATOMIC);
get_order(size));
}
-static inline void nl_pid_hash_free(struct hlist_head *table, size_t size)
+static void nl_pid_hash_free(struct hlist_head *table, size_t size)
{
if (size <= PAGE_SIZE)
kfree(table);
return err;
}
-static inline int netlink_capable(struct socket *sock, unsigned int flag)
+static inline int netlink_capable(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) ||
capable(CAP_NET_ADMIN);
sock_put(sk);
}
-static inline struct sk_buff *netlink_trim(struct sk_buff *skb,
- gfp_t allocation)
+static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
{
int delta;
return skb;
}
-static inline void netlink_rcv_wake(struct sock *sk)
+static void netlink_rcv_wake(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
wake_up_interruptible(&nlk->wait);
}
-static inline int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
+static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
{
int ret;
struct netlink_sock *nlk = nlk_sk(sk);
}
EXPORT_SYMBOL_GPL(netlink_has_listeners);
-static inline int netlink_broadcast_deliver(struct sock *sk,
- struct sk_buff *skb)
+static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
skb_set_owner_r(skb, sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, skb->len);
- return atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf;
+ return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
}
return -1;
}
void *tx_data;
};
-static inline int do_one_broadcast(struct sock *sk,
+static int do_one_broadcast(struct sock *sk,
struct netlink_broadcast_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
int code;
};
-static inline int do_one_set_err(struct sock *sk,
- struct netlink_set_err_data *p)
+static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
int ret = 0;
}
EXPORT_SYMBOL(genl_unlock);
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_genl_is_held(void)
+{
+ return lockdep_is_held(&genl_mutex);
+}
+EXPORT_SYMBOL(lockdep_genl_is_held);
+#endif
+
#define GENL_FAM_TAB_SIZE 16
#define GENL_FAM_TAB_MASK (GENL_FAM_TAB_SIZE - 1)
/* Of course we are going to have problems once we hit
* 2^16 alive types, but that can only happen by year 2K
*/
-static inline u16 genl_generate_id(void)
+static u16 genl_generate_id(void)
{
static u16 id_gen_idx = GENL_MIN_ID;
int i;
name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]);
res = genl_family_find_byname(name);
+#ifdef CONFIG_MODULES
+ if (res == NULL) {
+ genl_unlock();
+ request_module("net-pf-%d-proto-%d-type-%s",
+ PF_NETLINK, NETLINK_GENERIC, name);
+ genl_lock();
+ res = genl_family_find_byname(name);
+ }
+#endif
err = -ENOENT;
}
return genlmsg_mcast(skb, pid, group, flags);
}
EXPORT_SYMBOL(genlmsg_multicast_allns);
+
+void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
+ struct nlmsghdr *nlh, gfp_t flags)
+{
+ struct sock *sk = net->genl_sock;
+ int report = 0;
+
+ if (nlh)
+ report = nlmsg_report(nlh);
+
+ nlmsg_notify(sk, skb, pid, group, report, flags);
+}
+EXPORT_SYMBOL(genl_notify);
{
struct sock *sk = sock->sk;
struct nr_sock *nr = nr_sk(sk);
- int opt;
+ unsigned long opt;
if (level != SOL_NETROM)
return -ENOPROTOOPT;
- if (optlen < sizeof(int))
+ if (optlen < sizeof(unsigned int))
return -EINVAL;
- if (get_user(opt, (int __user *)optval))
+ if (get_user(opt, (unsigned int __user *)optval))
return -EFAULT;
switch (optname) {
case NETROM_T1:
- if (opt < 1)
+ if (opt < 1 || opt > ULONG_MAX / HZ)
return -EINVAL;
nr->t1 = opt * HZ;
return 0;
case NETROM_T2:
- if (opt < 1)
+ if (opt < 1 || opt > ULONG_MAX / HZ)
return -EINVAL;
nr->t2 = opt * HZ;
return 0;
return 0;
case NETROM_T4:
- if (opt < 1)
+ if (opt < 1 || opt > ULONG_MAX / HZ)
return -EINVAL;
nr->t4 = opt * HZ;
return 0;
case NETROM_IDLE:
- if (opt < 0)
+ if (opt > ULONG_MAX / (60 * HZ))
return -EINVAL;
nr->idle = opt * 60 * HZ;
return 0;
case SIOCADDRT:
case SIOCDELRT:
case SIOCNRDECOBS:
- if (!capable(CAP_NET_ADMIN)) return -EPERM;
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
return nr_rt_ioctl(cmd, argp);
default:
case SIOCADDRT:
if (copy_from_user(&nr_route, arg, sizeof(struct nr_route_struct)))
return -EFAULT;
- if ((dev = nr_ax25_dev_get(nr_route.device)) == NULL)
+ if (nr_route.ndigis > AX25_MAX_DIGIS)
return -EINVAL;
- if (nr_route.ndigis < 0 || nr_route.ndigis > AX25_MAX_DIGIS) {
- dev_put(dev);
+ if ((dev = nr_ax25_dev_get(nr_route.device)) == NULL)
return -EINVAL;
- }
switch (nr_route.type) {
case NETROM_NODE:
+ if (strnlen(nr_route.mnemonic, 7) == 7) {
+ ret = -EINVAL;
+ break;
+ }
+
ret = nr_add_node(&nr_route.callsign,
nr_route.mnemonic,
&nr_route.neighbour,
--- /dev/null
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+ tristate "Open vSwitch"
+ ---help---
+ Open vSwitch is a multilayer Ethernet switch targeted at virtualized
+ environments. In addition to supporting a variety of features
+ expected in a traditional hardware switch, it enables fine-grained
+ programmatic extension and flow-based control of the network. This
+ control is useful in a wide variety of applications but is
+ particularly important in multi-server virtualization deployments,
+ which are often characterized by highly dynamic endpoints and the
+ need to maintain logical abstractions for multiple tenants.
+
+ The Open vSwitch datapath provides an in-kernel fast path for packet
+ forwarding. It is complemented by a userspace daemon, ovs-vswitchd,
+ which is able to accept configuration from a variety of sources and
+ translate it into packet processing rules.
+
+ See http://openvswitch.org for more information and userspace
+ utilities.
+
+ To compile this code as a module, choose M here: the module will be
+ called openvswitch.
+
+ If unsure, say N.
--- /dev/null
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+ actions.o \
+ datapath.o \
+ dp_notify.o \
+ flow.o \
+ vport.o \
+ vport-internal_dev.o \
+ vport-netdev.o \
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/openvswitch.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/in6.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr, int len, bool keep_skb);
+
+static int make_writable(struct sk_buff *skb, int write_len)
+{
+ if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+ return 0;
+
+ return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
+/* remove VLAN header from packet and update csum accrodingly. */
+static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
+{
+ struct vlan_hdr *vhdr;
+ int err;
+
+ err = make_writable(skb, VLAN_ETH_HLEN);
+ if (unlikely(err))
+ return err;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+ + ETH_HLEN, VLAN_HLEN, 0));
+
+ vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+ *current_tci = vhdr->h_vlan_TCI;
+
+ memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+ __skb_pull(skb, VLAN_HLEN);
+
+ vlan_set_encap_proto(skb, vhdr);
+ skb->mac_header += VLAN_HLEN;
+ skb_reset_mac_len(skb);
+
+ return 0;
+}
+
+static int pop_vlan(struct sk_buff *skb)
+{
+ __be16 tci;
+ int err;
+
+ if (likely(vlan_tx_tag_present(skb))) {
+ skb->vlan_tci = 0;
+ } else {
+ if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
+ skb->len < VLAN_ETH_HLEN))
+ return 0;
+
+ err = __pop_vlan_tci(skb, &tci);
+ if (err)
+ return err;
+ }
+ /* move next vlan tag to hw accel tag */
+ if (likely(skb->protocol != htons(ETH_P_8021Q) ||
+ skb->len < VLAN_ETH_HLEN))
+ return 0;
+
+ err = __pop_vlan_tci(skb, &tci);
+ if (unlikely(err))
+ return err;
+
+ __vlan_hwaccel_put_tag(skb, ntohs(tci));
+ return 0;
+}
+
+static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+{
+ if (unlikely(vlan_tx_tag_present(skb))) {
+ u16 current_tag;
+
+ /* push down current VLAN tag */
+ current_tag = vlan_tx_tag_get(skb);
+
+ if (!__vlan_put_tag(skb, current_tag))
+ return -ENOMEM;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_add(skb->csum, csum_partial(skb->data
+ + ETH_HLEN, VLAN_HLEN, 0));
+
+ }
+ __vlan_hwaccel_put_tag(skb, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+ return 0;
+}
+
+static int set_eth_addr(struct sk_buff *skb,
+ const struct ovs_key_ethernet *eth_key)
+{
+ int err;
+ err = make_writable(skb, ETH_HLEN);
+ if (unlikely(err))
+ return err;
+
+ memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
+ memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+
+ return 0;
+}
+
+static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
+ __be32 *addr, __be32 new_addr)
+{
+ int transport_len = skb->len - skb_transport_offset(skb);
+
+ if (nh->protocol == IPPROTO_TCP) {
+ if (likely(transport_len >= sizeof(struct tcphdr)))
+ inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
+ *addr, new_addr, 1);
+ } else if (nh->protocol == IPPROTO_UDP) {
+ if (likely(transport_len >= sizeof(struct udphdr)))
+ inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
+ *addr, new_addr, 1);
+ }
+
+ csum_replace4(&nh->check, *addr, new_addr);
+ skb->rxhash = 0;
+ *addr = new_addr;
+}
+
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
+{
+ csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
+ nh->ttl = new_ttl;
+}
+
+static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+{
+ struct iphdr *nh;
+ int err;
+
+ err = make_writable(skb, skb_network_offset(skb) +
+ sizeof(struct iphdr));
+ if (unlikely(err))
+ return err;
+
+ nh = ip_hdr(skb);
+
+ if (ipv4_key->ipv4_src != nh->saddr)
+ set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
+
+ if (ipv4_key->ipv4_dst != nh->daddr)
+ set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+
+ if (ipv4_key->ipv4_tos != nh->tos)
+ ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+
+ if (ipv4_key->ipv4_ttl != nh->ttl)
+ set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+
+ return 0;
+}
+
+/* Must follow make_writable() since that can move the skb data. */
+static void set_tp_port(struct sk_buff *skb, __be16 *port,
+ __be16 new_port, __sum16 *check)
+{
+ inet_proto_csum_replace2(check, skb, *port, new_port, 0);
+ *port = new_port;
+ skb->rxhash = 0;
+}
+
+static int set_udp_port(struct sk_buff *skb,
+ const struct ovs_key_udp *udp_port_key)
+{
+ struct udphdr *uh;
+ int err;
+
+ err = make_writable(skb, skb_transport_offset(skb) +
+ sizeof(struct udphdr));
+ if (unlikely(err))
+ return err;
+
+ uh = udp_hdr(skb);
+ if (udp_port_key->udp_src != uh->source)
+ set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+
+ if (udp_port_key->udp_dst != uh->dest)
+ set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+
+ return 0;
+}
+
+static int set_tcp_port(struct sk_buff *skb,
+ const struct ovs_key_tcp *tcp_port_key)
+{
+ struct tcphdr *th;
+ int err;
+
+ err = make_writable(skb, skb_transport_offset(skb) +
+ sizeof(struct tcphdr));
+ if (unlikely(err))
+ return err;
+
+ th = tcp_hdr(skb);
+ if (tcp_port_key->tcp_src != th->source)
+ set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
+
+ if (tcp_port_key->tcp_dst != th->dest)
+ set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+
+ return 0;
+}
+
+static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+{
+ struct vport *vport;
+
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ vport = rcu_dereference(dp->ports[out_port]);
+ if (unlikely(!vport)) {
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+
+ ovs_vport_send(vport, skb);
+ return 0;
+}
+
+static int output_userspace(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr)
+{
+ struct dp_upcall_info upcall;
+ const struct nlattr *a;
+ int rem;
+
+ upcall.cmd = OVS_PACKET_CMD_ACTION;
+ upcall.key = &OVS_CB(skb)->flow->key;
+ upcall.userdata = NULL;
+ upcall.pid = 0;
+
+ for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+ a = nla_next(a, &rem)) {
+ switch (nla_type(a)) {
+ case OVS_USERSPACE_ATTR_USERDATA:
+ upcall.userdata = a;
+ break;
+
+ case OVS_USERSPACE_ATTR_PID:
+ upcall.pid = nla_get_u32(a);
+ break;
+ }
+ }
+
+ return ovs_dp_upcall(dp, skb, &upcall);
+}
+
+static int sample(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr)
+{
+ const struct nlattr *acts_list = NULL;
+ const struct nlattr *a;
+ int rem;
+
+ for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+ a = nla_next(a, &rem)) {
+ switch (nla_type(a)) {
+ case OVS_SAMPLE_ATTR_PROBABILITY:
+ if (net_random() >= nla_get_u32(a))
+ return 0;
+ break;
+
+ case OVS_SAMPLE_ATTR_ACTIONS:
+ acts_list = a;
+ break;
+ }
+ }
+
+ return do_execute_actions(dp, skb, nla_data(acts_list),
+ nla_len(acts_list), true);
+}
+
+static int execute_set_action(struct sk_buff *skb,
+ const struct nlattr *nested_attr)
+{
+ int err = 0;
+
+ switch (nla_type(nested_attr)) {
+ case OVS_KEY_ATTR_PRIORITY:
+ skb->priority = nla_get_u32(nested_attr);
+ break;
+
+ case OVS_KEY_ATTR_ETHERNET:
+ err = set_eth_addr(skb, nla_data(nested_attr));
+ break;
+
+ case OVS_KEY_ATTR_IPV4:
+ err = set_ipv4(skb, nla_data(nested_attr));
+ break;
+
+ case OVS_KEY_ATTR_TCP:
+ err = set_tcp_port(skb, nla_data(nested_attr));
+ break;
+
+ case OVS_KEY_ATTR_UDP:
+ err = set_udp_port(skb, nla_data(nested_attr));
+ break;
+ }
+
+ return err;
+}
+
+/* Execute a list of actions against 'skb'. */
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr, int len, bool keep_skb)
+{
+ /* Every output action needs a separate clone of 'skb', but the common
+ * case is just a single output action, so that doing a clone and
+ * then freeing the original skbuff is wasteful. So the following code
+ * is slightly obscure just to avoid that. */
+ int prev_port = -1;
+ const struct nlattr *a;
+ int rem;
+
+ for (a = attr, rem = len; rem > 0;
+ a = nla_next(a, &rem)) {
+ int err = 0;
+
+ if (prev_port != -1) {
+ do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+ prev_port = -1;
+ }
+
+ switch (nla_type(a)) {
+ case OVS_ACTION_ATTR_OUTPUT:
+ prev_port = nla_get_u32(a);
+ break;
+
+ case OVS_ACTION_ATTR_USERSPACE:
+ output_userspace(dp, skb, a);
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_VLAN:
+ err = push_vlan(skb, nla_data(a));
+ if (unlikely(err)) /* skb already freed. */
+ return err;
+ break;
+
+ case OVS_ACTION_ATTR_POP_VLAN:
+ err = pop_vlan(skb);
+ break;
+
+ case OVS_ACTION_ATTR_SET:
+ err = execute_set_action(skb, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_SAMPLE:
+ err = sample(dp, skb, a);
+ break;
+ }
+
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return err;
+ }
+ }
+
+ if (prev_port != -1) {
+ if (keep_skb)
+ skb = skb_clone(skb, GFP_ATOMIC);
+
+ do_output(dp, skb, prev_port);
+ } else if (!keep_skb)
+ consume_skb(skb);
+
+ return 0;
+}
+
+/* Execute a list of actions against 'skb'. */
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
+{
+ struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+ return do_execute_actions(dp, skb, acts->actions,
+ acts->actions_len, false);
+}
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/jhash.h>
+#include <linux/delay.h>
+#include <linux/time.h>
+#include <linux/etherdevice.h>
+#include <linux/genetlink.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/version.h>
+#include <linux/ethtool.h>
+#include <linux/wait.h>
+#include <asm/system.h>
+#include <asm/div64.h>
+#include <linux/highmem.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/inetdevice.h>
+#include <linux/list.h>
+#include <linux/openvswitch.h>
+#include <linux/rculist.h>
+#include <linux/dmi.h>
+#include <linux/workqueue.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "flow.h"
+#include "vport-internal_dev.h"
+
+/**
+ * DOC: Locking:
+ *
+ * Writes to device state (add/remove datapath, port, set operations on vports,
+ * etc.) are protected by RTNL.
+ *
+ * Writes to other state (flow table modifications, set miscellaneous datapath
+ * parameters, etc.) are protected by genl_mutex. The RTNL lock nests inside
+ * genl_mutex.
+ *
+ * Reads are protected by RCU.
+ *
+ * There are a few special cases (mostly stats) that have their own
+ * synchronization but they nest under all of above and don't interact with
+ * each other.
+ */
+
+/* Global list of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ */
+static LIST_HEAD(dps);
+
+#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
+static void rehash_flow_table(struct work_struct *work);
+static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);
+
+static struct vport *new_vport(const struct vport_parms *);
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *,
+ const struct dp_upcall_info *);
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *,
+ const struct dp_upcall_info *);
+
+/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */
+static struct datapath *get_dp(int dp_ifindex)
+{
+ struct datapath *dp = NULL;
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(&init_net, dp_ifindex);
+ if (dev) {
+ struct vport *vport = ovs_internal_dev_get_vport(dev);
+ if (vport)
+ dp = vport->dp;
+ }
+ rcu_read_unlock();
+
+ return dp;
+}
+
+/* Must be called with rcu_read_lock or RTNL lock. */
+const char *ovs_dp_name(const struct datapath *dp)
+{
+ struct vport *vport = rcu_dereference_rtnl(dp->ports[OVSP_LOCAL]);
+ return vport->ops->get_name(vport);
+}
+
+static int get_dpifindex(struct datapath *dp)
+{
+ struct vport *local;
+ int ifindex;
+
+ rcu_read_lock();
+
+ local = rcu_dereference(dp->ports[OVSP_LOCAL]);
+ if (local)
+ ifindex = local->ops->get_ifindex(local);
+ else
+ ifindex = 0;
+
+ rcu_read_unlock();
+
+ return ifindex;
+}
+
+static void destroy_dp_rcu(struct rcu_head *rcu)
+{
+ struct datapath *dp = container_of(rcu, struct datapath, rcu);
+
+ ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
+ free_percpu(dp->stats_percpu);
+ kfree(dp);
+}
+
+/* Called with RTNL lock and genl_lock. */
+static struct vport *new_vport(const struct vport_parms *parms)
+{
+ struct vport *vport;
+
+ vport = ovs_vport_add(parms);
+ if (!IS_ERR(vport)) {
+ struct datapath *dp = parms->dp;
+
+ rcu_assign_pointer(dp->ports[parms->port_no], vport);
+ list_add(&vport->node, &dp->port_list);
+ }
+
+ return vport;
+}
+
+/* Called with RTNL lock. */
+void ovs_dp_detach_port(struct vport *p)
+{
+ ASSERT_RTNL();
+
+ /* First drop references to device. */
+ list_del(&p->node);
+ rcu_assign_pointer(p->dp->ports[p->port_no], NULL);
+
+ /* Then destroy it. */
+ ovs_vport_del(p);
+}
+
+/* Must be called with rcu_read_lock. */
+void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
+{
+ struct datapath *dp = p->dp;
+ struct sw_flow *flow;
+ struct dp_stats_percpu *stats;
+ struct sw_flow_key key;
+ u64 *stats_counter;
+ int error;
+ int key_len;
+
+ stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+ /* Extract flow from 'skb' into 'key'. */
+ error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
+ if (unlikely(error)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ /* Look up flow. */
+ flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table), &key, key_len);
+ if (unlikely(!flow)) {
+ struct dp_upcall_info upcall;
+
+ upcall.cmd = OVS_PACKET_CMD_MISS;
+ upcall.key = &key;
+ upcall.userdata = NULL;
+ upcall.pid = p->upcall_pid;
+ ovs_dp_upcall(dp, skb, &upcall);
+ consume_skb(skb);
+ stats_counter = &stats->n_missed;
+ goto out;
+ }
+
+ OVS_CB(skb)->flow = flow;
+
+ stats_counter = &stats->n_hit;
+ ovs_flow_used(OVS_CB(skb)->flow, skb);
+ ovs_execute_actions(dp, skb);
+
+out:
+ /* Update datapath statistics. */
+ u64_stats_update_begin(&stats->sync);
+ (*stats_counter)++;
+ u64_stats_update_end(&stats->sync);
+}
+
+static struct genl_family dp_packet_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_PACKET_FAMILY,
+ .version = OVS_PACKET_VERSION,
+ .maxattr = OVS_PACKET_ATTR_MAX
+};
+
+int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
+ const struct dp_upcall_info *upcall_info)
+{
+ struct dp_stats_percpu *stats;
+ int dp_ifindex;
+ int err;
+
+ if (upcall_info->pid == 0) {
+ err = -ENOTCONN;
+ goto err;
+ }
+
+ dp_ifindex = get_dpifindex(dp);
+ if (!dp_ifindex) {
+ err = -ENODEV;
+ goto err;
+ }
+
+ if (!skb_is_gso(skb))
+ err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+ else
+ err = queue_gso_packets(dp_ifindex, skb, upcall_info);
+ if (err)
+ goto err;
+
+ return 0;
+
+err:
+ stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+ u64_stats_update_begin(&stats->sync);
+ stats->n_lost++;
+ u64_stats_update_end(&stats->sync);
+
+ return err;
+}
+
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb,
+ const struct dp_upcall_info *upcall_info)
+{
+ struct dp_upcall_info later_info;
+ struct sw_flow_key later_key;
+ struct sk_buff *segs, *nskb;
+ int err;
+
+ segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
+
+ /* Queue all of the segments. */
+ skb = segs;
+ do {
+ err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+ if (err)
+ break;
+
+ if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) {
+ /* The initial flow key extracted by ovs_flow_extract()
+ * in this case is for a first fragment, so we need to
+ * properly mark later fragments.
+ */
+ later_key = *upcall_info->key;
+ later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+
+ later_info = *upcall_info;
+ later_info.key = &later_key;
+ upcall_info = &later_info;
+ }
+ } while ((skb = skb->next));
+
+ /* Free all of the segments. */
+ skb = segs;
+ do {
+ nskb = skb->next;
+ if (err)
+ kfree_skb(skb);
+ else
+ consume_skb(skb);
+ } while ((skb = nskb));
+ return err;
+}
+
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb,
+ const struct dp_upcall_info *upcall_info)
+{
+ struct ovs_header *upcall;
+ struct sk_buff *nskb = NULL;
+ struct sk_buff *user_skb; /* to be queued to userspace */
+ struct nlattr *nla;
+ unsigned int len;
+ int err;
+
+ if (vlan_tx_tag_present(skb)) {
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return -ENOMEM;
+
+ nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb));
+ if (!skb)
+ return -ENOMEM;
+
+ nskb->vlan_tci = 0;
+ skb = nskb;
+ }
+
+ if (nla_attr_size(skb->len) > USHRT_MAX) {
+ err = -EFBIG;
+ goto out;
+ }
+
+ len = sizeof(struct ovs_header);
+ len += nla_total_size(skb->len);
+ len += nla_total_size(FLOW_BUFSIZE);
+ if (upcall_info->cmd == OVS_PACKET_CMD_ACTION)
+ len += nla_total_size(8);
+
+ user_skb = genlmsg_new(len, GFP_ATOMIC);
+ if (!user_skb) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family,
+ 0, upcall_info->cmd);
+ upcall->dp_ifindex = dp_ifindex;
+
+ nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
+ ovs_flow_to_nlattrs(upcall_info->key, user_skb);
+ nla_nest_end(user_skb, nla);
+
+ if (upcall_info->userdata)
+ nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA,
+ nla_get_u64(upcall_info->userdata));
+
+ nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
+
+ skb_copy_and_csum_dev(skb, nla_data(nla));
+
+ err = genlmsg_unicast(&init_net, user_skb, upcall_info->pid);
+
+out:
+ kfree_skb(nskb);
+ return err;
+}
+
+/* Called with genl_mutex. */
+static int flush_flows(int dp_ifindex)
+{
+ struct flow_table *old_table;
+ struct flow_table *new_table;
+ struct datapath *dp;
+
+ dp = get_dp(dp_ifindex);
+ if (!dp)
+ return -ENODEV;
+
+ old_table = genl_dereference(dp->table);
+ new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS);
+ if (!new_table)
+ return -ENOMEM;
+
+ rcu_assign_pointer(dp->table, new_table);
+
+ ovs_flow_tbl_deferred_destroy(old_table);
+ return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+ const struct sw_flow_key *key, int depth);
+
+static int validate_sample(const struct nlattr *attr,
+ const struct sw_flow_key *key, int depth)
+{
+ const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
+ const struct nlattr *probability, *actions;
+ const struct nlattr *a;
+ int rem;
+
+ memset(attrs, 0, sizeof(attrs));
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
+ if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
+ return -EINVAL;
+ attrs[type] = a;
+ }
+ if (rem)
+ return -EINVAL;
+
+ probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
+ if (!probability || nla_len(probability) != sizeof(u32))
+ return -EINVAL;
+
+ actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
+ if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
+ return -EINVAL;
+ return validate_actions(actions, key, depth + 1);
+}
+
+static int validate_set(const struct nlattr *a,
+ const struct sw_flow_key *flow_key)
+{
+ const struct nlattr *ovs_key = nla_data(a);
+ int key_type = nla_type(ovs_key);
+
+ /* There can be only one key in a action */
+ if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
+ return -EINVAL;
+
+ if (key_type > OVS_KEY_ATTR_MAX ||
+ nla_len(ovs_key) != ovs_key_lens[key_type])
+ return -EINVAL;
+
+ switch (key_type) {
+ const struct ovs_key_ipv4 *ipv4_key;
+
+ case OVS_KEY_ATTR_PRIORITY:
+ case OVS_KEY_ATTR_ETHERNET:
+ break;
+
+ case OVS_KEY_ATTR_IPV4:
+ if (flow_key->eth.type != htons(ETH_P_IP))
+ return -EINVAL;
+
+ if (!flow_key->ipv4.addr.src || !flow_key->ipv4.addr.dst)
+ return -EINVAL;
+
+ ipv4_key = nla_data(ovs_key);
+ if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+ return -EINVAL;
+
+ if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+ return -EINVAL;
+
+ break;
+
+ case OVS_KEY_ATTR_TCP:
+ if (flow_key->ip.proto != IPPROTO_TCP)
+ return -EINVAL;
+
+ if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+ return -EINVAL;
+
+ break;
+
+ case OVS_KEY_ATTR_UDP:
+ if (flow_key->ip.proto != IPPROTO_UDP)
+ return -EINVAL;
+
+ if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+ return -EINVAL;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int validate_userspace(const struct nlattr *attr)
+{
+ static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
+ [OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
+ [OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 },
+ };
+ struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
+ int error;
+
+ error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
+ attr, userspace_policy);
+ if (error)
+ return error;
+
+ if (!a[OVS_USERSPACE_ATTR_PID] ||
+ !nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+ const struct sw_flow_key *key, int depth)
+{
+ const struct nlattr *a;
+ int rem, err;
+
+ if (depth >= SAMPLE_ACTION_DEPTH)
+ return -EOVERFLOW;
+
+ nla_for_each_nested(a, attr, rem) {
+ /* Expected argument lengths, (u32)-1 for variable length. */
+ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
+ [OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
+ [OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+ [OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
+ [OVS_ACTION_ATTR_POP_VLAN] = 0,
+ [OVS_ACTION_ATTR_SET] = (u32)-1,
+ [OVS_ACTION_ATTR_SAMPLE] = (u32)-1
+ };
+ const struct ovs_action_push_vlan *vlan;
+ int type = nla_type(a);
+
+ if (type > OVS_ACTION_ATTR_MAX ||
+ (action_lens[type] != nla_len(a) &&
+ action_lens[type] != (u32)-1))
+ return -EINVAL;
+
+ switch (type) {
+ case OVS_ACTION_ATTR_UNSPEC:
+ return -EINVAL;
+
+ case OVS_ACTION_ATTR_USERSPACE:
+ err = validate_userspace(a);
+ if (err)
+ return err;
+ break;
+
+ case OVS_ACTION_ATTR_OUTPUT:
+ if (nla_get_u32(a) >= DP_MAX_PORTS)
+ return -EINVAL;
+ break;
+
+
+ case OVS_ACTION_ATTR_POP_VLAN:
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_VLAN:
+ vlan = nla_data(a);
+ if (vlan->vlan_tpid != htons(ETH_P_8021Q))
+ return -EINVAL;
+ if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
+ return -EINVAL;
+ break;
+
+ case OVS_ACTION_ATTR_SET:
+ err = validate_set(a, key);
+ if (err)
+ return err;
+ break;
+
+ case OVS_ACTION_ATTR_SAMPLE:
+ err = validate_sample(a, key, depth);
+ if (err)
+ return err;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ }
+
+ if (rem > 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static void clear_stats(struct sw_flow *flow)
+{
+ flow->used = 0;
+ flow->tcp_flags = 0;
+ flow->packet_count = 0;
+ flow->byte_count = 0;
+}
+
+static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
+{
+ struct ovs_header *ovs_header = info->userhdr;
+ struct nlattr **a = info->attrs;
+ struct sw_flow_actions *acts;
+ struct sk_buff *packet;
+ struct sw_flow *flow;
+ struct datapath *dp;
+ struct ethhdr *eth;
+ int len;
+ int err;
+ int key_len;
+
+ err = -EINVAL;
+ if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
+ !a[OVS_PACKET_ATTR_ACTIONS] ||
+ nla_len(a[OVS_PACKET_ATTR_PACKET]) < ETH_HLEN)
+ goto err;
+
+ len = nla_len(a[OVS_PACKET_ATTR_PACKET]);
+ packet = __dev_alloc_skb(NET_IP_ALIGN + len, GFP_KERNEL);
+ err = -ENOMEM;
+ if (!packet)
+ goto err;
+ skb_reserve(packet, NET_IP_ALIGN);
+
+ memcpy(__skb_put(packet, len), nla_data(a[OVS_PACKET_ATTR_PACKET]), len);
+
+ skb_reset_mac_header(packet);
+ eth = eth_hdr(packet);
+
+ /* Normally, setting the skb 'protocol' field would be handled by a
+ * call to eth_type_trans(), but it assumes there's a sending
+ * device, which we may not have. */
+ if (ntohs(eth->h_proto) >= 1536)
+ packet->protocol = eth->h_proto;
+ else
+ packet->protocol = htons(ETH_P_802_2);
+
+ /* Build an sw_flow for sending this packet. */
+ flow = ovs_flow_alloc();
+ err = PTR_ERR(flow);
+ if (IS_ERR(flow))
+ goto err_kfree_skb;
+
+ err = ovs_flow_extract(packet, -1, &flow->key, &key_len);
+ if (err)
+ goto err_flow_free;
+
+ err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority,
+ &flow->key.phy.in_port,
+ a[OVS_PACKET_ATTR_KEY]);
+ if (err)
+ goto err_flow_free;
+
+ err = validate_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0);
+ if (err)
+ goto err_flow_free;
+
+ flow->hash = ovs_flow_hash(&flow->key, key_len);
+
+ acts = ovs_flow_actions_alloc(a[OVS_PACKET_ATTR_ACTIONS]);
+ err = PTR_ERR(acts);
+ if (IS_ERR(acts))
+ goto err_flow_free;
+ rcu_assign_pointer(flow->sf_acts, acts);
+
+ OVS_CB(packet)->flow = flow;
+ packet->priority = flow->key.phy.priority;
+
+ rcu_read_lock();
+ dp = get_dp(ovs_header->dp_ifindex);
+ err = -ENODEV;
+ if (!dp)
+ goto err_unlock;
+
+ local_bh_disable();
+ err = ovs_execute_actions(dp, packet);
+ local_bh_enable();
+ rcu_read_unlock();
+
+ ovs_flow_free(flow);
+ return err;
+
+err_unlock:
+ rcu_read_unlock();
+err_flow_free:
+ ovs_flow_free(flow);
+err_kfree_skb:
+ kfree_skb(packet);
+err:
+ return err;
+}
+
+static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
+ [OVS_PACKET_ATTR_PACKET] = { .type = NLA_UNSPEC },
+ [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
+ [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_ops dp_packet_genl_ops[] = {
+ { .cmd = OVS_PACKET_CMD_EXECUTE,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = packet_policy,
+ .doit = ovs_packet_cmd_execute
+ }
+};
+
+static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
+{
+ int i;
+ struct flow_table *table = genl_dereference(dp->table);
+
+ stats->n_flows = ovs_flow_tbl_count(table);
+
+ stats->n_hit = stats->n_missed = stats->n_lost = 0;
+ for_each_possible_cpu(i) {
+ const struct dp_stats_percpu *percpu_stats;
+ struct dp_stats_percpu local_stats;
+ unsigned int start;
+
+ percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
+
+ do {
+ start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+ local_stats = *percpu_stats;
+ } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+
+ stats->n_hit += local_stats.n_hit;
+ stats->n_missed += local_stats.n_missed;
+ stats->n_lost += local_stats.n_lost;
+ }
+}
+
+static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
+ [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+ [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
+ [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+};
+
+static struct genl_family dp_flow_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_FLOW_FAMILY,
+ .version = OVS_FLOW_VERSION,
+ .maxattr = OVS_FLOW_ATTR_MAX
+};
+
+static struct genl_multicast_group ovs_dp_flow_multicast_group = {
+ .name = OVS_FLOW_MCGROUP
+};
+
+/* Called with genl_lock. */
+static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
+ struct sk_buff *skb, u32 pid,
+ u32 seq, u32 flags, u8 cmd)
+{
+ const int skb_orig_len = skb->len;
+ const struct sw_flow_actions *sf_acts;
+ struct ovs_flow_stats stats;
+ struct ovs_header *ovs_header;
+ struct nlattr *nla;
+ unsigned long used;
+ u8 tcp_flags;
+ int err;
+
+ sf_acts = rcu_dereference_protected(flow->sf_acts,
+ lockdep_genl_is_held());
+
+ ovs_header = genlmsg_put(skb, pid, seq, &dp_flow_genl_family, flags, cmd);
+ if (!ovs_header)
+ return -EMSGSIZE;
+
+ ovs_header->dp_ifindex = get_dpifindex(dp);
+
+ nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
+ if (!nla)
+ goto nla_put_failure;
+ err = ovs_flow_to_nlattrs(&flow->key, skb);
+ if (err)
+ goto error;
+ nla_nest_end(skb, nla);
+
+ spin_lock_bh(&flow->lock);
+ used = flow->used;
+ stats.n_packets = flow->packet_count;
+ stats.n_bytes = flow->byte_count;
+ tcp_flags = flow->tcp_flags;
+ spin_unlock_bh(&flow->lock);
+
+ if (used)
+ NLA_PUT_U64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used));
+
+ if (stats.n_packets)
+ NLA_PUT(skb, OVS_FLOW_ATTR_STATS,
+ sizeof(struct ovs_flow_stats), &stats);
+
+ if (tcp_flags)
+ NLA_PUT_U8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags);
+
+ /* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
+ * this is the first flow to be dumped into 'skb'. This is unusual for
+ * Netlink but individual action lists can be longer than
+ * NLMSG_GOODSIZE and thus entirely undumpable if we didn't do this.
+ * The userspace caller can always fetch the actions separately if it
+ * really wants them. (Most userspace callers in fact don't care.)
+ *
+ * This can only fail for dump operations because the skb is always
+ * properly sized for single flows.
+ */
+ err = nla_put(skb, OVS_FLOW_ATTR_ACTIONS, sf_acts->actions_len,
+ sf_acts->actions);
+ if (err < 0 && skb_orig_len)
+ goto error;
+
+ return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+ err = -EMSGSIZE;
+error:
+ genlmsg_cancel(skb, ovs_header);
+ return err;
+}
+
+static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+{
+ const struct sw_flow_actions *sf_acts;
+ int len;
+
+ sf_acts = rcu_dereference_protected(flow->sf_acts,
+ lockdep_genl_is_held());
+
+ /* OVS_FLOW_ATTR_KEY */
+ len = nla_total_size(FLOW_BUFSIZE);
+ /* OVS_FLOW_ATTR_ACTIONS */
+ len += nla_total_size(sf_acts->actions_len);
+ /* OVS_FLOW_ATTR_STATS */
+ len += nla_total_size(sizeof(struct ovs_flow_stats));
+ /* OVS_FLOW_ATTR_TCP_FLAGS */
+ len += nla_total_size(1);
+ /* OVS_FLOW_ATTR_USED */
+ len += nla_total_size(8);
+
+ len += NLMSG_ALIGN(sizeof(struct ovs_header));
+
+ return genlmsg_new(len, GFP_KERNEL);
+}
+
+static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
+ struct datapath *dp,
+ u32 pid, u32 seq, u8 cmd)
+{
+ struct sk_buff *skb;
+ int retval;
+
+ skb = ovs_flow_cmd_alloc_info(flow);
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
+
+ retval = ovs_flow_cmd_fill_info(flow, dp, skb, pid, seq, 0, cmd);
+ BUG_ON(retval < 0);
+ return skb;
+}
+
+static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct sw_flow_key key;
+ struct sw_flow *flow;
+ struct sk_buff *reply;
+ struct datapath *dp;
+ struct flow_table *table;
+ int error;
+ int key_len;
+
+ /* Extract key. */
+ error = -EINVAL;
+ if (!a[OVS_FLOW_ATTR_KEY])
+ goto error;
+ error = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+ if (error)
+ goto error;
+
+ /* Validate actions. */
+ if (a[OVS_FLOW_ATTR_ACTIONS]) {
+ error = validate_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, 0);
+ if (error)
+ goto error;
+ } else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
+ error = -EINVAL;
+ goto error;
+ }
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ error = -ENODEV;
+ if (!dp)
+ goto error;
+
+ table = genl_dereference(dp->table);
+ flow = ovs_flow_tbl_lookup(table, &key, key_len);
+ if (!flow) {
+ struct sw_flow_actions *acts;
+
+ /* Bail out if we're not allowed to create a new flow. */
+ error = -ENOENT;
+ if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
+ goto error;
+
+ /* Expand table, if necessary, to make room. */
+ if (ovs_flow_tbl_need_to_expand(table)) {
+ struct flow_table *new_table;
+
+ new_table = ovs_flow_tbl_expand(table);
+ if (!IS_ERR(new_table)) {
+ rcu_assign_pointer(dp->table, new_table);
+ ovs_flow_tbl_deferred_destroy(table);
+ table = genl_dereference(dp->table);
+ }
+ }
+
+ /* Allocate flow. */
+ flow = ovs_flow_alloc();
+ if (IS_ERR(flow)) {
+ error = PTR_ERR(flow);
+ goto error;
+ }
+ flow->key = key;
+ clear_stats(flow);
+
+ /* Obtain actions. */
+ acts = ovs_flow_actions_alloc(a[OVS_FLOW_ATTR_ACTIONS]);
+ error = PTR_ERR(acts);
+ if (IS_ERR(acts))
+ goto error_free_flow;
+ rcu_assign_pointer(flow->sf_acts, acts);
+
+ /* Put flow in bucket. */
+ flow->hash = ovs_flow_hash(&key, key_len);
+ ovs_flow_tbl_insert(table, flow);
+
+ reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+ info->snd_seq,
+ OVS_FLOW_CMD_NEW);
+ } else {
+ /* We found a matching flow. */
+ struct sw_flow_actions *old_acts;
+ struct nlattr *acts_attrs;
+
+ /* Bail out if we're not allowed to modify an existing flow.
+ * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL
+ * because Generic Netlink treats the latter as a dump
+ * request. We also accept NLM_F_EXCL in case that bug ever
+ * gets fixed.
+ */
+ error = -EEXIST;
+ if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
+ info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
+ goto error;
+
+ /* Update actions. */
+ old_acts = rcu_dereference_protected(flow->sf_acts,
+ lockdep_genl_is_held());
+ acts_attrs = a[OVS_FLOW_ATTR_ACTIONS];
+ if (acts_attrs &&
+ (old_acts->actions_len != nla_len(acts_attrs) ||
+ memcmp(old_acts->actions, nla_data(acts_attrs),
+ old_acts->actions_len))) {
+ struct sw_flow_actions *new_acts;
+
+ new_acts = ovs_flow_actions_alloc(acts_attrs);
+ error = PTR_ERR(new_acts);
+ if (IS_ERR(new_acts))
+ goto error;
+
+ rcu_assign_pointer(flow->sf_acts, new_acts);
+ ovs_flow_deferred_free_acts(old_acts);
+ }
+
+ reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+ info->snd_seq, OVS_FLOW_CMD_NEW);
+
+ /* Clear stats. */
+ if (a[OVS_FLOW_ATTR_CLEAR]) {
+ spin_lock_bh(&flow->lock);
+ clear_stats(flow);
+ spin_unlock_bh(&flow->lock);
+ }
+ }
+
+ if (!IS_ERR(reply))
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_flow_multicast_group.id, info->nlhdr,
+ GFP_KERNEL);
+ else
+ netlink_set_err(init_net.genl_sock, 0,
+ ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
+ return 0;
+
+error_free_flow:
+ ovs_flow_free(flow);
+error:
+ return error;
+}
+
+static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct sw_flow_key key;
+ struct sk_buff *reply;
+ struct sw_flow *flow;
+ struct datapath *dp;
+ struct flow_table *table;
+ int err;
+ int key_len;
+
+ if (!a[OVS_FLOW_ATTR_KEY])
+ return -EINVAL;
+ err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+ if (err)
+ return err;
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ if (!dp)
+ return -ENODEV;
+
+ table = genl_dereference(dp->table);
+ flow = ovs_flow_tbl_lookup(table, &key, key_len);
+ if (!flow)
+ return -ENOENT;
+
+ reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+ info->snd_seq, OVS_FLOW_CMD_NEW);
+ if (IS_ERR(reply))
+ return PTR_ERR(reply);
+
+ return genlmsg_reply(reply, info);
+}
+
+static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct sw_flow_key key;
+ struct sk_buff *reply;
+ struct sw_flow *flow;
+ struct datapath *dp;
+ struct flow_table *table;
+ int err;
+ int key_len;
+
+ if (!a[OVS_FLOW_ATTR_KEY])
+ return flush_flows(ovs_header->dp_ifindex);
+ err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+ if (err)
+ return err;
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ if (!dp)
+ return -ENODEV;
+
+ table = genl_dereference(dp->table);
+ flow = ovs_flow_tbl_lookup(table, &key, key_len);
+ if (!flow)
+ return -ENOENT;
+
+ reply = ovs_flow_cmd_alloc_info(flow);
+ if (!reply)
+ return -ENOMEM;
+
+ ovs_flow_tbl_remove(table, flow);
+
+ err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_pid,
+ info->snd_seq, 0, OVS_FLOW_CMD_DEL);
+ BUG_ON(err < 0);
+
+ ovs_flow_deferred_free(flow);
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL);
+ return 0;
+}
+
+static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
+ struct datapath *dp;
+ struct flow_table *table;
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ if (!dp)
+ return -ENODEV;
+
+ table = genl_dereference(dp->table);
+
+ for (;;) {
+ struct sw_flow *flow;
+ u32 bucket, obj;
+
+ bucket = cb->args[0];
+ obj = cb->args[1];
+ flow = ovs_flow_tbl_next(table, &bucket, &obj);
+ if (!flow)
+ break;
+
+ if (ovs_flow_cmd_fill_info(flow, dp, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ OVS_FLOW_CMD_NEW) < 0)
+ break;
+
+ cb->args[0] = bucket;
+ cb->args[1] = obj;
+ }
+ return skb->len;
+}
+
+static struct genl_ops dp_flow_genl_ops[] = {
+ { .cmd = OVS_FLOW_CMD_NEW,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = flow_policy,
+ .doit = ovs_flow_cmd_new_or_set
+ },
+ { .cmd = OVS_FLOW_CMD_DEL,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = flow_policy,
+ .doit = ovs_flow_cmd_del
+ },
+ { .cmd = OVS_FLOW_CMD_GET,
+ .flags = 0, /* OK for unprivileged users. */
+ .policy = flow_policy,
+ .doit = ovs_flow_cmd_get,
+ .dumpit = ovs_flow_cmd_dump
+ },
+ { .cmd = OVS_FLOW_CMD_SET,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = flow_policy,
+ .doit = ovs_flow_cmd_new_or_set,
+ },
+};
+
+static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
+ [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+ [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+};
+
+static struct genl_family dp_datapath_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_DATAPATH_FAMILY,
+ .version = OVS_DATAPATH_VERSION,
+ .maxattr = OVS_DP_ATTR_MAX
+};
+
+static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+ .name = OVS_DATAPATH_MCGROUP
+};
+
+static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
+ u32 pid, u32 seq, u32 flags, u8 cmd)
+{
+ struct ovs_header *ovs_header;
+ struct ovs_dp_stats dp_stats;
+ int err;
+
+ ovs_header = genlmsg_put(skb, pid, seq, &dp_datapath_genl_family,
+ flags, cmd);
+ if (!ovs_header)
+ goto error;
+
+ ovs_header->dp_ifindex = get_dpifindex(dp);
+
+ rcu_read_lock();
+ err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
+ rcu_read_unlock();
+ if (err)
+ goto nla_put_failure;
+
+ get_dp_stats(dp, &dp_stats);
+ NLA_PUT(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats);
+
+ return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+ genlmsg_cancel(skb, ovs_header);
+error:
+ return -EMSGSIZE;
+}
+
+static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid,
+ u32 seq, u8 cmd)
+{
+ struct sk_buff *skb;
+ int retval;
+
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
+
+ retval = ovs_dp_cmd_fill_info(dp, skb, pid, seq, 0, cmd);
+ if (retval < 0) {
+ kfree_skb(skb);
+ return ERR_PTR(retval);
+ }
+ return skb;
+}
+
+/* Called with genl_mutex and optionally with RTNL lock also. */
+static struct datapath *lookup_datapath(struct ovs_header *ovs_header,
+ struct nlattr *a[OVS_DP_ATTR_MAX + 1])
+{
+ struct datapath *dp;
+
+ if (!a[OVS_DP_ATTR_NAME])
+ dp = get_dp(ovs_header->dp_ifindex);
+ else {
+ struct vport *vport;
+
+ rcu_read_lock();
+ vport = ovs_vport_locate(nla_data(a[OVS_DP_ATTR_NAME]));
+ dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL;
+ rcu_read_unlock();
+ }
+ return dp ? dp : ERR_PTR(-ENODEV);
+}
+
+static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct vport_parms parms;
+ struct sk_buff *reply;
+ struct datapath *dp;
+ struct vport *vport;
+ int err;
+
+ err = -EINVAL;
+ if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
+ goto err;
+
+ rtnl_lock();
+ err = -ENODEV;
+ if (!try_module_get(THIS_MODULE))
+ goto err_unlock_rtnl;
+
+ err = -ENOMEM;
+ dp = kzalloc(sizeof(*dp), GFP_KERNEL);
+ if (dp == NULL)
+ goto err_put_module;
+ INIT_LIST_HEAD(&dp->port_list);
+
+ /* Allocate table. */
+ err = -ENOMEM;
+ rcu_assign_pointer(dp->table, ovs_flow_tbl_alloc(TBL_MIN_BUCKETS));
+ if (!dp->table)
+ goto err_free_dp;
+
+ dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+ if (!dp->stats_percpu) {
+ err = -ENOMEM;
+ goto err_destroy_table;
+ }
+
+ /* Set up our datapath device. */
+ parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
+ parms.type = OVS_VPORT_TYPE_INTERNAL;
+ parms.options = NULL;
+ parms.dp = dp;
+ parms.port_no = OVSP_LOCAL;
+ parms.upcall_pid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
+
+ vport = new_vport(&parms);
+ if (IS_ERR(vport)) {
+ err = PTR_ERR(vport);
+ if (err == -EBUSY)
+ err = -EEXIST;
+
+ goto err_destroy_percpu;
+ }
+
+ reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+ info->snd_seq, OVS_DP_CMD_NEW);
+ err = PTR_ERR(reply);
+ if (IS_ERR(reply))
+ goto err_destroy_local_port;
+
+ list_add_tail(&dp->list_node, &dps);
+ rtnl_unlock();
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_datapath_multicast_group.id, info->nlhdr,
+ GFP_KERNEL);
+ return 0;
+
+err_destroy_local_port:
+ ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+err_destroy_percpu:
+ free_percpu(dp->stats_percpu);
+err_destroy_table:
+ ovs_flow_tbl_destroy(genl_dereference(dp->table));
+err_free_dp:
+ kfree(dp);
+err_put_module:
+ module_put(THIS_MODULE);
+err_unlock_rtnl:
+ rtnl_unlock();
+err:
+ return err;
+}
+
+static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+ struct vport *vport, *next_vport;
+ struct sk_buff *reply;
+ struct datapath *dp;
+ int err;
+
+ rtnl_lock();
+ dp = lookup_datapath(info->userhdr, info->attrs);
+ err = PTR_ERR(dp);
+ if (IS_ERR(dp))
+ goto exit_unlock;
+
+ reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+ info->snd_seq, OVS_DP_CMD_DEL);
+ err = PTR_ERR(reply);
+ if (IS_ERR(reply))
+ goto exit_unlock;
+
+ list_for_each_entry_safe(vport, next_vport, &dp->port_list, node)
+ if (vport->port_no != OVSP_LOCAL)
+ ovs_dp_detach_port(vport);
+
+ list_del(&dp->list_node);
+ ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+
+ /* rtnl_unlock() will wait until all the references to devices that
+ * are pending unregistration have been dropped. We do it here to
+ * ensure that any internal devices (which contain DP pointers) are
+ * fully destroyed before freeing the datapath.
+ */
+ rtnl_unlock();
+
+ call_rcu(&dp->rcu, destroy_dp_rcu);
+ module_put(THIS_MODULE);
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_datapath_multicast_group.id, info->nlhdr,
+ GFP_KERNEL);
+
+ return 0;
+
+exit_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+ struct sk_buff *reply;
+ struct datapath *dp;
+ int err;
+
+ dp = lookup_datapath(info->userhdr, info->attrs);
+ if (IS_ERR(dp))
+ return PTR_ERR(dp);
+
+ reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+ info->snd_seq, OVS_DP_CMD_NEW);
+ if (IS_ERR(reply)) {
+ err = PTR_ERR(reply);
+ netlink_set_err(init_net.genl_sock, 0,
+ ovs_dp_datapath_multicast_group.id, err);
+ return 0;
+ }
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_datapath_multicast_group.id, info->nlhdr,
+ GFP_KERNEL);
+
+ return 0;
+}
+
+static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct sk_buff *reply;
+ struct datapath *dp;
+
+ dp = lookup_datapath(info->userhdr, info->attrs);
+ if (IS_ERR(dp))
+ return PTR_ERR(dp);
+
+ reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+ info->snd_seq, OVS_DP_CMD_NEW);
+ if (IS_ERR(reply))
+ return PTR_ERR(reply);
+
+ return genlmsg_reply(reply, info);
+}
+
+static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct datapath *dp;
+ int skip = cb->args[0];
+ int i = 0;
+
+ list_for_each_entry(dp, &dps, list_node) {
+ if (i < skip)
+ continue;
+ if (ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ OVS_DP_CMD_NEW) < 0)
+ break;
+ i++;
+ }
+
+ cb->args[0] = i;
+
+ return skb->len;
+}
+
+static struct genl_ops dp_datapath_genl_ops[] = {
+ { .cmd = OVS_DP_CMD_NEW,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = datapath_policy,
+ .doit = ovs_dp_cmd_new
+ },
+ { .cmd = OVS_DP_CMD_DEL,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = datapath_policy,
+ .doit = ovs_dp_cmd_del
+ },
+ { .cmd = OVS_DP_CMD_GET,
+ .flags = 0, /* OK for unprivileged users. */
+ .policy = datapath_policy,
+ .doit = ovs_dp_cmd_get,
+ .dumpit = ovs_dp_cmd_dump
+ },
+ { .cmd = OVS_DP_CMD_SET,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = datapath_policy,
+ .doit = ovs_dp_cmd_set,
+ },
+};
+
+static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
+ [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+ [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
+ [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_family dp_vport_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_VPORT_FAMILY,
+ .version = OVS_VPORT_VERSION,
+ .maxattr = OVS_VPORT_ATTR_MAX
+};
+
+struct genl_multicast_group ovs_dp_vport_multicast_group = {
+ .name = OVS_VPORT_MCGROUP
+};
+
+/* Called with RTNL lock or RCU read lock. */
+static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
+ u32 pid, u32 seq, u32 flags, u8 cmd)
+{
+ struct ovs_header *ovs_header;
+ struct ovs_vport_stats vport_stats;
+ int err;
+
+ ovs_header = genlmsg_put(skb, pid, seq, &dp_vport_genl_family,
+ flags, cmd);
+ if (!ovs_header)
+ return -EMSGSIZE;
+
+ ovs_header->dp_ifindex = get_dpifindex(vport->dp);
+
+ NLA_PUT_U32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no);
+ NLA_PUT_U32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type);
+ NLA_PUT_STRING(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport));
+ NLA_PUT_U32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid);
+
+ ovs_vport_get_stats(vport, &vport_stats);
+ NLA_PUT(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats),
+ &vport_stats);
+
+ err = ovs_vport_get_options(vport, skb);
+ if (err == -EMSGSIZE)
+ goto error;
+
+ return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+ err = -EMSGSIZE;
+error:
+ genlmsg_cancel(skb, ovs_header);
+ return err;
+}
+
+/* Called with RTNL lock or RCU read lock. */
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid,
+ u32 seq, u8 cmd)
+{
+ struct sk_buff *skb;
+ int retval;
+
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
+
+ retval = ovs_vport_cmd_fill_info(vport, skb, pid, seq, 0, cmd);
+ if (retval < 0) {
+ kfree_skb(skb);
+ return ERR_PTR(retval);
+ }
+ return skb;
+}
+
+/* Called with RTNL lock or RCU read lock. */
+static struct vport *lookup_vport(struct ovs_header *ovs_header,
+ struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
+{
+ struct datapath *dp;
+ struct vport *vport;
+
+ if (a[OVS_VPORT_ATTR_NAME]) {
+ vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME]));
+ if (!vport)
+ return ERR_PTR(-ENODEV);
+ return vport;
+ } else if (a[OVS_VPORT_ATTR_PORT_NO]) {
+ u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
+
+ if (port_no >= DP_MAX_PORTS)
+ return ERR_PTR(-EFBIG);
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ if (!dp)
+ return ERR_PTR(-ENODEV);
+
+ vport = rcu_dereference_rtnl(dp->ports[port_no]);
+ if (!vport)
+ return ERR_PTR(-ENOENT);
+ return vport;
+ } else
+ return ERR_PTR(-EINVAL);
+}
+
+static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct vport_parms parms;
+ struct sk_buff *reply;
+ struct vport *vport;
+ struct datapath *dp;
+ u32 port_no;
+ int err;
+
+ err = -EINVAL;
+ if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
+ !a[OVS_VPORT_ATTR_UPCALL_PID])
+ goto exit;
+
+ rtnl_lock();
+ dp = get_dp(ovs_header->dp_ifindex);
+ err = -ENODEV;
+ if (!dp)
+ goto exit_unlock;
+
+ if (a[OVS_VPORT_ATTR_PORT_NO]) {
+ port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
+
+ err = -EFBIG;
+ if (port_no >= DP_MAX_PORTS)
+ goto exit_unlock;
+
+ vport = rtnl_dereference(dp->ports[port_no]);
+ err = -EBUSY;
+ if (vport)
+ goto exit_unlock;
+ } else {
+ for (port_no = 1; ; port_no++) {
+ if (port_no >= DP_MAX_PORTS) {
+ err = -EFBIG;
+ goto exit_unlock;
+ }
+ vport = rtnl_dereference(dp->ports[port_no]);
+ if (!vport)
+ break;
+ }
+ }
+
+ parms.name = nla_data(a[OVS_VPORT_ATTR_NAME]);
+ parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
+ parms.options = a[OVS_VPORT_ATTR_OPTIONS];
+ parms.dp = dp;
+ parms.port_no = port_no;
+ parms.upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+
+ vport = new_vport(&parms);
+ err = PTR_ERR(vport);
+ if (IS_ERR(vport))
+ goto exit_unlock;
+
+ reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+ OVS_VPORT_CMD_NEW);
+ if (IS_ERR(reply)) {
+ err = PTR_ERR(reply);
+ ovs_dp_detach_port(vport);
+ goto exit_unlock;
+ }
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+ rtnl_unlock();
+exit:
+ return err;
+}
+
+static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct sk_buff *reply;
+ struct vport *vport;
+ int err;
+
+ rtnl_lock();
+ vport = lookup_vport(info->userhdr, a);
+ err = PTR_ERR(vport);
+ if (IS_ERR(vport))
+ goto exit_unlock;
+
+ err = 0;
+ if (a[OVS_VPORT_ATTR_TYPE] &&
+ nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type)
+ err = -EINVAL;
+
+ if (!err && a[OVS_VPORT_ATTR_OPTIONS])
+ err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
+ if (!err && a[OVS_VPORT_ATTR_UPCALL_PID])
+ vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+
+ reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+ OVS_VPORT_CMD_NEW);
+ if (IS_ERR(reply)) {
+ err = PTR_ERR(reply);
+ netlink_set_err(init_net.genl_sock, 0,
+ ovs_dp_vport_multicast_group.id, err);
+ return 0;
+ }
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct sk_buff *reply;
+ struct vport *vport;
+ int err;
+
+ rtnl_lock();
+ vport = lookup_vport(info->userhdr, a);
+ err = PTR_ERR(vport);
+ if (IS_ERR(vport))
+ goto exit_unlock;
+
+ if (vport->port_no == OVSP_LOCAL) {
+ err = -EINVAL;
+ goto exit_unlock;
+ }
+
+ reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+ OVS_VPORT_CMD_DEL);
+ err = PTR_ERR(reply);
+ if (IS_ERR(reply))
+ goto exit_unlock;
+
+ ovs_dp_detach_port(vport);
+
+ genl_notify(reply, genl_info_net(info), info->snd_pid,
+ ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct sk_buff *reply;
+ struct vport *vport;
+ int err;
+
+ rcu_read_lock();
+ vport = lookup_vport(ovs_header, a);
+ err = PTR_ERR(vport);
+ if (IS_ERR(vport))
+ goto exit_unlock;
+
+ reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+ OVS_VPORT_CMD_NEW);
+ err = PTR_ERR(reply);
+ if (IS_ERR(reply))
+ goto exit_unlock;
+
+ rcu_read_unlock();
+
+ return genlmsg_reply(reply, info);
+
+exit_unlock:
+ rcu_read_unlock();
+ return err;
+}
+
+static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
+ struct datapath *dp;
+ u32 port_no;
+ int retval;
+
+ dp = get_dp(ovs_header->dp_ifindex);
+ if (!dp)
+ return -ENODEV;
+
+ rcu_read_lock();
+ for (port_no = cb->args[0]; port_no < DP_MAX_PORTS; port_no++) {
+ struct vport *vport;
+
+ vport = rcu_dereference(dp->ports[port_no]);
+ if (!vport)
+ continue;
+
+ if (ovs_vport_cmd_fill_info(vport, skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ OVS_VPORT_CMD_NEW) < 0)
+ break;
+ }
+ rcu_read_unlock();
+
+ cb->args[0] = port_no;
+ retval = skb->len;
+
+ return retval;
+}
+
+static void rehash_flow_table(struct work_struct *work)
+{
+ struct datapath *dp;
+
+ genl_lock();
+
+ list_for_each_entry(dp, &dps, list_node) {
+ struct flow_table *old_table = genl_dereference(dp->table);
+ struct flow_table *new_table;
+
+ new_table = ovs_flow_tbl_rehash(old_table);
+ if (!IS_ERR(new_table)) {
+ rcu_assign_pointer(dp->table, new_table);
+ ovs_flow_tbl_deferred_destroy(old_table);
+ }
+ }
+
+ genl_unlock();
+
+ schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
+}
+
+static struct genl_ops dp_vport_genl_ops[] = {
+ { .cmd = OVS_VPORT_CMD_NEW,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = vport_policy,
+ .doit = ovs_vport_cmd_new
+ },
+ { .cmd = OVS_VPORT_CMD_DEL,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = vport_policy,
+ .doit = ovs_vport_cmd_del
+ },
+ { .cmd = OVS_VPORT_CMD_GET,
+ .flags = 0, /* OK for unprivileged users. */
+ .policy = vport_policy,
+ .doit = ovs_vport_cmd_get,
+ .dumpit = ovs_vport_cmd_dump
+ },
+ { .cmd = OVS_VPORT_CMD_SET,
+ .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+ .policy = vport_policy,
+ .doit = ovs_vport_cmd_set,
+ },
+};
+
+struct genl_family_and_ops {
+ struct genl_family *family;
+ struct genl_ops *ops;
+ int n_ops;
+ struct genl_multicast_group *group;
+};
+
+static const struct genl_family_and_ops dp_genl_families[] = {
+ { &dp_datapath_genl_family,
+ dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops),
+ &ovs_dp_datapath_multicast_group },
+ { &dp_vport_genl_family,
+ dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops),
+ &ovs_dp_vport_multicast_group },
+ { &dp_flow_genl_family,
+ dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops),
+ &ovs_dp_flow_multicast_group },
+ { &dp_packet_genl_family,
+ dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops),
+ NULL },
+};
+
+static void dp_unregister_genl(int n_families)
+{
+ int i;
+
+ for (i = 0; i < n_families; i++)
+ genl_unregister_family(dp_genl_families[i].family);
+}
+
+static int dp_register_genl(void)
+{
+ int n_registered;
+ int err;
+ int i;
+
+ n_registered = 0;
+ for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
+ const struct genl_family_and_ops *f = &dp_genl_families[i];
+
+ err = genl_register_family_with_ops(f->family, f->ops,
+ f->n_ops);
+ if (err)
+ goto error;
+ n_registered++;
+
+ if (f->group) {
+ err = genl_register_mc_group(f->family, f->group);
+ if (err)
+ goto error;
+ }
+ }
+
+ return 0;
+
+error:
+ dp_unregister_genl(n_registered);
+ return err;
+}
+
+static int __init dp_init(void)
+{
+ struct sk_buff *dummy_skb;
+ int err;
+
+ BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb));
+
+ pr_info("Open vSwitch switching datapath\n");
+
+ err = ovs_flow_init();
+ if (err)
+ goto error;
+
+ err = ovs_vport_init();
+ if (err)
+ goto error_flow_exit;
+
+ err = register_netdevice_notifier(&ovs_dp_device_notifier);
+ if (err)
+ goto error_vport_exit;
+
+ err = dp_register_genl();
+ if (err < 0)
+ goto error_unreg_notifier;
+
+ schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
+
+ return 0;
+
+error_unreg_notifier:
+ unregister_netdevice_notifier(&ovs_dp_device_notifier);
+error_vport_exit:
+ ovs_vport_exit();
+error_flow_exit:
+ ovs_flow_exit();
+error:
+ return err;
+}
+
+static void dp_cleanup(void)
+{
+ cancel_delayed_work_sync(&rehash_flow_wq);
+ rcu_barrier();
+ dp_unregister_genl(ARRAY_SIZE(dp_genl_families));
+ unregister_netdevice_notifier(&ovs_dp_device_notifier);
+ ovs_vport_exit();
+ ovs_flow_exit();
+}
+
+module_init(dp_init);
+module_exit(dp_cleanup);
+
+MODULE_DESCRIPTION("Open vSwitch switching datapath");
+MODULE_LICENSE("GPL");
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef DATAPATH_H
+#define DATAPATH_H 1
+
+#include <asm/page.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/version.h>
+
+#include "flow.h"
+
+struct vport;
+
+#define DP_MAX_PORTS 1024
+#define SAMPLE_ACTION_DEPTH 3
+
+/**
+ * struct dp_stats_percpu - per-cpu packet processing statistics for a given
+ * datapath.
+ * @n_hit: Number of received packets for which a matching flow was found in
+ * the flow table.
+ * @n_miss: Number of received packets that had no matching flow in the flow
+ * table. The sum of @n_hit and @n_miss is the number of packets that have
+ * been received by the datapath.
+ * @n_lost: Number of received packets that had no matching flow in the flow
+ * table that could not be sent to userspace (normally due to an overflow in
+ * one of the datapath's queues).
+ */
+struct dp_stats_percpu {
+ u64 n_hit;
+ u64 n_missed;
+ u64 n_lost;
+ struct u64_stats_sync sync;
+};
+
+/**
+ * struct datapath - datapath for flow-based packet switching
+ * @rcu: RCU callback head for deferred destruction.
+ * @list_node: Element in global 'dps' list.
+ * @n_flows: Number of flows currently in flow table.
+ * @table: Current flow table. Protected by genl_lock and RCU.
+ * @ports: Map from port number to &struct vport. %OVSP_LOCAL port
+ * always exists, other ports may be %NULL. Protected by RTNL and RCU.
+ * @port_list: List of all ports in @ports in arbitrary order. RTNL required
+ * to iterate or modify.
+ * @stats_percpu: Per-CPU datapath statistics.
+ *
+ * Context: See the comment on locking at the top of datapath.c for additional
+ * locking information.
+ */
+struct datapath {
+ struct rcu_head rcu;
+ struct list_head list_node;
+
+ /* Flow table. */
+ struct flow_table __rcu *table;
+
+ /* Switch ports. */
+ struct vport __rcu *ports[DP_MAX_PORTS];
+ struct list_head port_list;
+
+ /* Stats. */
+ struct dp_stats_percpu __percpu *stats_percpu;
+};
+
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @flow: The flow associated with this packet. May be %NULL if no flow.
+ */
+struct ovs_skb_cb {
+ struct sw_flow *flow;
+};
+#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
+
+/**
+ * struct dp_upcall - metadata to include with a packet to send to userspace
+ * @cmd: One of %OVS_PACKET_CMD_*.
+ * @key: Becomes %OVS_PACKET_ATTR_KEY. Must be nonnull.
+ * @userdata: If nonnull, its u64 value is extracted and passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @pid: Netlink PID to which packet should be sent. If @pid is 0 then no
+ * packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ */
+struct dp_upcall_info {
+ u8 cmd;
+ const struct sw_flow_key *key;
+ const struct nlattr *userdata;
+ u32 pid;
+};
+
+extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_multicast_group ovs_dp_vport_multicast_group;
+
+void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
+void ovs_dp_detach_port(struct vport *);
+int ovs_dp_upcall(struct datapath *, struct sk_buff *,
+ const struct dp_upcall_info *);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
+ u8 cmd);
+
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
+#endif /* datapath.h */
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static int dp_device_event(struct notifier_block *unused, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = ptr;
+ struct vport *vport;
+
+ if (ovs_is_internal_dev(dev))
+ vport = ovs_internal_dev_get_vport(dev);
+ else
+ vport = ovs_netdev_get_vport(dev);
+
+ if (!vport)
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UNREGISTER:
+ if (!ovs_is_internal_dev(dev)) {
+ struct sk_buff *notify;
+
+ notify = ovs_vport_cmd_build_info(vport, 0, 0,
+ OVS_VPORT_CMD_DEL);
+ ovs_dp_detach_port(vport);
+ if (IS_ERR(notify)) {
+ netlink_set_err(init_net.genl_sock, 0,
+ ovs_dp_vport_multicast_group.id,
+ PTR_ERR(notify));
+ break;
+ }
+
+ genlmsg_multicast(notify, 0, ovs_dp_vport_multicast_group.id,
+ GFP_KERNEL);
+ }
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+struct notifier_block ovs_dp_device_notifier = {
+ .notifier_call = dp_device_event
+};
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include "flow.h"
+#include "datapath.h"
+#include <linux/uaccess.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/llc_pdu.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/rculist.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+
+static struct kmem_cache *flow_cache;
+
+static int check_header(struct sk_buff *skb, int len)
+{
+ if (unlikely(skb->len < len))
+ return -EINVAL;
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return -ENOMEM;
+ return 0;
+}
+
+static bool arphdr_ok(struct sk_buff *skb)
+{
+ return pskb_may_pull(skb, skb_network_offset(skb) +
+ sizeof(struct arp_eth_header));
+}
+
+static int check_iphdr(struct sk_buff *skb)
+{
+ unsigned int nh_ofs = skb_network_offset(skb);
+ unsigned int ip_len;
+ int err;
+
+ err = check_header(skb, nh_ofs + sizeof(struct iphdr));
+ if (unlikely(err))
+ return err;
+
+ ip_len = ip_hdrlen(skb);
+ if (unlikely(ip_len < sizeof(struct iphdr) ||
+ skb->len < nh_ofs + ip_len))
+ return -EINVAL;
+
+ skb_set_transport_header(skb, nh_ofs + ip_len);
+ return 0;
+}
+
+static bool tcphdr_ok(struct sk_buff *skb)
+{
+ int th_ofs = skb_transport_offset(skb);
+ int tcp_len;
+
+ if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr))))
+ return false;
+
+ tcp_len = tcp_hdrlen(skb);
+ if (unlikely(tcp_len < sizeof(struct tcphdr) ||
+ skb->len < th_ofs + tcp_len))
+ return false;
+
+ return true;
+}
+
+static bool udphdr_ok(struct sk_buff *skb)
+{
+ return pskb_may_pull(skb, skb_transport_offset(skb) +
+ sizeof(struct udphdr));
+}
+
+static bool icmphdr_ok(struct sk_buff *skb)
+{
+ return pskb_may_pull(skb, skb_transport_offset(skb) +
+ sizeof(struct icmphdr));
+}
+
+u64 ovs_flow_used_time(unsigned long flow_jiffies)
+{
+ struct timespec cur_ts;
+ u64 cur_ms, idle_ms;
+
+ ktime_get_ts(&cur_ts);
+ idle_ms = jiffies_to_msecs(jiffies - flow_jiffies);
+ cur_ms = (u64)cur_ts.tv_sec * MSEC_PER_SEC +
+ cur_ts.tv_nsec / NSEC_PER_MSEC;
+
+ return cur_ms - idle_ms;
+}
+
+#define SW_FLOW_KEY_OFFSET(field) \
+ (offsetof(struct sw_flow_key, field) + \
+ FIELD_SIZEOF(struct sw_flow_key, field))
+
+static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key,
+ int *key_lenp)
+{
+ unsigned int nh_ofs = skb_network_offset(skb);
+ unsigned int nh_len;
+ int payload_ofs;
+ struct ipv6hdr *nh;
+ uint8_t nexthdr;
+ __be16 frag_off;
+ int err;
+
+ *key_lenp = SW_FLOW_KEY_OFFSET(ipv6.label);
+
+ err = check_header(skb, nh_ofs + sizeof(*nh));
+ if (unlikely(err))
+ return err;
+
+ nh = ipv6_hdr(skb);
+ nexthdr = nh->nexthdr;
+ payload_ofs = (u8 *)(nh + 1) - skb->data;
+
+ key->ip.proto = NEXTHDR_NONE;
+ key->ip.tos = ipv6_get_dsfield(nh);
+ key->ip.ttl = nh->hop_limit;
+ key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+ key->ipv6.addr.src = nh->saddr;
+ key->ipv6.addr.dst = nh->daddr;
+
+ payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off);
+ if (unlikely(payload_ofs < 0))
+ return -EINVAL;
+
+ if (frag_off) {
+ if (frag_off & htons(~0x7))
+ key->ip.frag = OVS_FRAG_TYPE_LATER;
+ else
+ key->ip.frag = OVS_FRAG_TYPE_FIRST;
+ }
+
+ nh_len = payload_ofs - nh_ofs;
+ skb_set_transport_header(skb, nh_ofs + nh_len);
+ key->ip.proto = nexthdr;
+ return nh_len;
+}
+
+static bool icmp6hdr_ok(struct sk_buff *skb)
+{
+ return pskb_may_pull(skb, skb_transport_offset(skb) +
+ sizeof(struct icmp6hdr));
+}
+
+#define TCP_FLAGS_OFFSET 13
+#define TCP_FLAG_MASK 0x3f
+
+void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
+{
+ u8 tcp_flags = 0;
+
+ if (flow->key.eth.type == htons(ETH_P_IP) &&
+ flow->key.ip.proto == IPPROTO_TCP) {
+ u8 *tcp = (u8 *)tcp_hdr(skb);
+ tcp_flags = *(tcp + TCP_FLAGS_OFFSET) & TCP_FLAG_MASK;
+ }
+
+ spin_lock(&flow->lock);
+ flow->used = jiffies;
+ flow->packet_count++;
+ flow->byte_count += skb->len;
+ flow->tcp_flags |= tcp_flags;
+ spin_unlock(&flow->lock);
+}
+
+struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *actions)
+{
+ int actions_len = nla_len(actions);
+ struct sw_flow_actions *sfa;
+
+ /* At least DP_MAX_PORTS actions are required to be able to flood a
+ * packet to every port. Factor of 2 allows for setting VLAN tags,
+ * etc. */
+ if (actions_len > 2 * DP_MAX_PORTS * nla_total_size(4))
+ return ERR_PTR(-EINVAL);
+
+ sfa = kmalloc(sizeof(*sfa) + actions_len, GFP_KERNEL);
+ if (!sfa)
+ return ERR_PTR(-ENOMEM);
+
+ sfa->actions_len = actions_len;
+ memcpy(sfa->actions, nla_data(actions), actions_len);
+ return sfa;
+}
+
+struct sw_flow *ovs_flow_alloc(void)
+{
+ struct sw_flow *flow;
+
+ flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+ if (!flow)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock_init(&flow->lock);
+ flow->sf_acts = NULL;
+
+ return flow;
+}
+
+static struct hlist_head *find_bucket(struct flow_table *table, u32 hash)
+{
+ hash = jhash_1word(hash, table->hash_seed);
+ return flex_array_get(table->buckets,
+ (hash & (table->n_buckets - 1)));
+}
+
+static struct flex_array *alloc_buckets(unsigned int n_buckets)
+{
+ struct flex_array *buckets;
+ int i, err;
+
+ buckets = flex_array_alloc(sizeof(struct hlist_head *),
+ n_buckets, GFP_KERNEL);
+ if (!buckets)
+ return NULL;
+
+ err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
+ if (err) {
+ flex_array_free(buckets);
+ return NULL;
+ }
+
+ for (i = 0; i < n_buckets; i++)
+ INIT_HLIST_HEAD((struct hlist_head *)
+ flex_array_get(buckets, i));
+
+ return buckets;
+}
+
+static void free_buckets(struct flex_array *buckets)
+{
+ flex_array_free(buckets);
+}
+
+struct flow_table *ovs_flow_tbl_alloc(int new_size)
+{
+ struct flow_table *table = kmalloc(sizeof(*table), GFP_KERNEL);
+
+ if (!table)
+ return NULL;
+
+ table->buckets = alloc_buckets(new_size);
+
+ if (!table->buckets) {
+ kfree(table);
+ return NULL;
+ }
+ table->n_buckets = new_size;
+ table->count = 0;
+ table->node_ver = 0;
+ table->keep_flows = false;
+ get_random_bytes(&table->hash_seed, sizeof(u32));
+
+ return table;
+}
+
+void ovs_flow_tbl_destroy(struct flow_table *table)
+{
+ int i;
+
+ if (!table)
+ return;
+
+ if (table->keep_flows)
+ goto skip_flows;
+
+ for (i = 0; i < table->n_buckets; i++) {
+ struct sw_flow *flow;
+ struct hlist_head *head = flex_array_get(table->buckets, i);
+ struct hlist_node *node, *n;
+ int ver = table->node_ver;
+
+ hlist_for_each_entry_safe(flow, node, n, head, hash_node[ver]) {
+ hlist_del_rcu(&flow->hash_node[ver]);
+ ovs_flow_free(flow);
+ }
+ }
+
+skip_flows:
+ free_buckets(table->buckets);
+ kfree(table);
+}
+
+static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
+{
+ struct flow_table *table = container_of(rcu, struct flow_table, rcu);
+
+ ovs_flow_tbl_destroy(table);
+}
+
+void ovs_flow_tbl_deferred_destroy(struct flow_table *table)
+{
+ if (!table)
+ return;
+
+ call_rcu(&table->rcu, flow_tbl_destroy_rcu_cb);
+}
+
+struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *last)
+{
+ struct sw_flow *flow;
+ struct hlist_head *head;
+ struct hlist_node *n;
+ int ver;
+ int i;
+
+ ver = table->node_ver;
+ while (*bucket < table->n_buckets) {
+ i = 0;
+ head = flex_array_get(table->buckets, *bucket);
+ hlist_for_each_entry_rcu(flow, n, head, hash_node[ver]) {
+ if (i < *last) {
+ i++;
+ continue;
+ }
+ *last = i + 1;
+ return flow;
+ }
+ (*bucket)++;
+ *last = 0;
+ }
+
+ return NULL;
+}
+
+static void flow_table_copy_flows(struct flow_table *old, struct flow_table *new)
+{
+ int old_ver;
+ int i;
+
+ old_ver = old->node_ver;
+ new->node_ver = !old_ver;
+
+ /* Insert in new table. */
+ for (i = 0; i < old->n_buckets; i++) {
+ struct sw_flow *flow;
+ struct hlist_head *head;
+ struct hlist_node *n;
+
+ head = flex_array_get(old->buckets, i);
+
+ hlist_for_each_entry(flow, n, head, hash_node[old_ver])
+ ovs_flow_tbl_insert(new, flow);
+ }
+ old->keep_flows = true;
+}
+
+static struct flow_table *__flow_tbl_rehash(struct flow_table *table, int n_buckets)
+{
+ struct flow_table *new_table;
+
+ new_table = ovs_flow_tbl_alloc(n_buckets);
+ if (!new_table)
+ return ERR_PTR(-ENOMEM);
+
+ flow_table_copy_flows(table, new_table);
+
+ return new_table;
+}
+
+struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table)
+{
+ return __flow_tbl_rehash(table, table->n_buckets);
+}
+
+struct flow_table *ovs_flow_tbl_expand(struct flow_table *table)
+{
+ return __flow_tbl_rehash(table, table->n_buckets * 2);
+}
+
+void ovs_flow_free(struct sw_flow *flow)
+{
+ if (unlikely(!flow))
+ return;
+
+ kfree((struct sf_flow_acts __force *)flow->sf_acts);
+ kmem_cache_free(flow_cache, flow);
+}
+
+/* RCU callback used by ovs_flow_deferred_free. */
+static void rcu_free_flow_callback(struct rcu_head *rcu)
+{
+ struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);
+
+ ovs_flow_free(flow);
+}
+
+/* Schedules 'flow' to be freed after the next RCU grace period.
+ * The caller must hold rcu_read_lock for this to be sensible. */
+void ovs_flow_deferred_free(struct sw_flow *flow)
+{
+ call_rcu(&flow->rcu, rcu_free_flow_callback);
+}
+
+/* RCU callback used by ovs_flow_deferred_free_acts. */
+static void rcu_free_acts_callback(struct rcu_head *rcu)
+{
+ struct sw_flow_actions *sf_acts = container_of(rcu,
+ struct sw_flow_actions, rcu);
+ kfree(sf_acts);
+}
+
+/* Schedules 'sf_acts' to be freed after the next RCU grace period.
+ * The caller must hold rcu_read_lock for this to be sensible. */
+void ovs_flow_deferred_free_acts(struct sw_flow_actions *sf_acts)
+{
+ call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ struct qtag_prefix {
+ __be16 eth_type; /* ETH_P_8021Q */
+ __be16 tci;
+ };
+ struct qtag_prefix *qp;
+
+ if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16)))
+ return 0;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
+ sizeof(__be16))))
+ return -ENOMEM;
+
+ qp = (struct qtag_prefix *) skb->data;
+ key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT);
+ __skb_pull(skb, sizeof(struct qtag_prefix));
+
+ return 0;
+}
+
+static __be16 parse_ethertype(struct sk_buff *skb)
+{
+ struct llc_snap_hdr {
+ u8 dsap; /* Always 0xAA */
+ u8 ssap; /* Always 0xAA */
+ u8 ctrl;
+ u8 oui[3];
+ __be16 ethertype;
+ };
+ struct llc_snap_hdr *llc;
+ __be16 proto;
+
+ proto = *(__be16 *) skb->data;
+ __skb_pull(skb, sizeof(__be16));
+
+ if (ntohs(proto) >= 1536)
+ return proto;
+
+ if (skb->len < sizeof(struct llc_snap_hdr))
+ return htons(ETH_P_802_2);
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr))))
+ return htons(0);
+
+ llc = (struct llc_snap_hdr *) skb->data;
+ if (llc->dsap != LLC_SAP_SNAP ||
+ llc->ssap != LLC_SAP_SNAP ||
+ (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0)
+ return htons(ETH_P_802_2);
+
+ __skb_pull(skb, sizeof(struct llc_snap_hdr));
+ return llc->ethertype;
+}
+
+static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
+ int *key_lenp, int nh_len)
+{
+ struct icmp6hdr *icmp = icmp6_hdr(skb);
+ int error = 0;
+ int key_len;
+
+ /* The ICMPv6 type and code fields use the 16-bit transport port
+ * fields, so we need to store them in 16-bit network byte order.
+ */
+ key->ipv6.tp.src = htons(icmp->icmp6_type);
+ key->ipv6.tp.dst = htons(icmp->icmp6_code);
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+
+ if (icmp->icmp6_code == 0 &&
+ (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+ icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+ int icmp_len = skb->len - skb_transport_offset(skb);
+ struct nd_msg *nd;
+ int offset;
+
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+
+ /* In order to process neighbor discovery options, we need the
+ * entire packet.
+ */
+ if (unlikely(icmp_len < sizeof(*nd)))
+ goto out;
+ if (unlikely(skb_linearize(skb))) {
+ error = -ENOMEM;
+ goto out;
+ }
+
+ nd = (struct nd_msg *)skb_transport_header(skb);
+ key->ipv6.nd.target = nd->target;
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+
+ icmp_len -= sizeof(*nd);
+ offset = 0;
+ while (icmp_len >= 8) {
+ struct nd_opt_hdr *nd_opt =
+ (struct nd_opt_hdr *)(nd->opt + offset);
+ int opt_len = nd_opt->nd_opt_len * 8;
+
+ if (unlikely(!opt_len || opt_len > icmp_len))
+ goto invalid;
+
+ /* Store the link layer address if the appropriate
+ * option is provided. It is considered an error if
+ * the same link layer option is specified twice.
+ */
+ if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR
+ && opt_len == 8) {
+ if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
+ goto invalid;
+ memcpy(key->ipv6.nd.sll,
+ &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+ } else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
+ && opt_len == 8) {
+ if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
+ goto invalid;
+ memcpy(key->ipv6.nd.tll,
+ &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+ }
+
+ icmp_len -= opt_len;
+ offset += opt_len;
+ }
+ }
+
+ goto out;
+
+invalid:
+ memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target));
+ memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll));
+ memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll));
+
+out:
+ *key_lenp = key_len;
+ return error;
+}
+
+/**
+ * ovs_flow_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @in_port: port number on which @skb was received.
+ * @key: output flow key
+ * @key_lenp: length of output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Returns 0 if successful, otherwise a negative errno value.
+ *
+ * Initializes @skb header pointers as follows:
+ *
+ * - skb->mac_header: the Ethernet header.
+ *
+ * - skb->network_header: just past the Ethernet header, or just past the
+ * VLAN header, to the first byte of the Ethernet payload.
+ *
+ * - skb->transport_header: If key->dl_type is ETH_P_IP or ETH_P_IPV6
+ * on output, then just past the IP header, if one is present and
+ * of a correct length, otherwise the same as skb->network_header.
+ * For other key->dl_type values it is left untouched.
+ */
+int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key,
+ int *key_lenp)
+{
+ int error = 0;
+ int key_len = SW_FLOW_KEY_OFFSET(eth);
+ struct ethhdr *eth;
+
+ memset(key, 0, sizeof(*key));
+
+ key->phy.priority = skb->priority;
+ key->phy.in_port = in_port;
+
+ skb_reset_mac_header(skb);
+
+ /* Link layer. We are guaranteed to have at least the 14 byte Ethernet
+ * header in the linear data area.
+ */
+ eth = eth_hdr(skb);
+ memcpy(key->eth.src, eth->h_source, ETH_ALEN);
+ memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+
+ __skb_pull(skb, 2 * ETH_ALEN);
+
+ if (vlan_tx_tag_present(skb))
+ key->eth.tci = htons(skb->vlan_tci);
+ else if (eth->h_proto == htons(ETH_P_8021Q))
+ if (unlikely(parse_vlan(skb, key)))
+ return -ENOMEM;
+
+ key->eth.type = parse_ethertype(skb);
+ if (unlikely(key->eth.type == htons(0)))
+ return -ENOMEM;
+
+ skb_reset_network_header(skb);
+ __skb_push(skb, skb->data - skb_mac_header(skb));
+
+ /* Network layer. */
+ if (key->eth.type == htons(ETH_P_IP)) {
+ struct iphdr *nh;
+ __be16 offset;
+
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);
+
+ error = check_iphdr(skb);
+ if (unlikely(error)) {
+ if (error == -EINVAL) {
+ skb->transport_header = skb->network_header;
+ error = 0;
+ }
+ goto out;
+ }
+
+ nh = ip_hdr(skb);
+ key->ipv4.addr.src = nh->saddr;
+ key->ipv4.addr.dst = nh->daddr;
+
+ key->ip.proto = nh->protocol;
+ key->ip.tos = nh->tos;
+ key->ip.ttl = nh->ttl;
+
+ offset = nh->frag_off & htons(IP_OFFSET);
+ if (offset) {
+ key->ip.frag = OVS_FRAG_TYPE_LATER;
+ goto out;
+ }
+ if (nh->frag_off & htons(IP_MF) ||
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
+ /* Transport layer. */
+ if (key->ip.proto == IPPROTO_TCP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ if (tcphdr_ok(skb)) {
+ struct tcphdr *tcp = tcp_hdr(skb);
+ key->ipv4.tp.src = tcp->source;
+ key->ipv4.tp.dst = tcp->dest;
+ }
+ } else if (key->ip.proto == IPPROTO_UDP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ if (udphdr_ok(skb)) {
+ struct udphdr *udp = udp_hdr(skb);
+ key->ipv4.tp.src = udp->source;
+ key->ipv4.tp.dst = udp->dest;
+ }
+ } else if (key->ip.proto == IPPROTO_ICMP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ if (icmphdr_ok(skb)) {
+ struct icmphdr *icmp = icmp_hdr(skb);
+ /* The ICMP type and code fields use the 16-bit
+ * transport port fields, so we need to store
+ * them in 16-bit network byte order. */
+ key->ipv4.tp.src = htons(icmp->type);
+ key->ipv4.tp.dst = htons(icmp->code);
+ }
+ }
+
+ } else if (key->eth.type == htons(ETH_P_ARP) && arphdr_ok(skb)) {
+ struct arp_eth_header *arp;
+
+ arp = (struct arp_eth_header *)skb_network_header(skb);
+
+ if (arp->ar_hrd == htons(ARPHRD_ETHER)
+ && arp->ar_pro == htons(ETH_P_IP)
+ && arp->ar_hln == ETH_ALEN
+ && arp->ar_pln == 4) {
+
+ /* We only match on the lower 8 bits of the opcode. */
+ if (ntohs(arp->ar_op) <= 0xff)
+ key->ip.proto = ntohs(arp->ar_op);
+
+ if (key->ip.proto == ARPOP_REQUEST
+ || key->ip.proto == ARPOP_REPLY) {
+ memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
+ memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
+ memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
+ memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
+ }
+ }
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
+ int nh_len; /* IPv6 Header + Extensions */
+
+ nh_len = parse_ipv6hdr(skb, key, &key_len);
+ if (unlikely(nh_len < 0)) {
+ if (nh_len == -EINVAL)
+ skb->transport_header = skb->network_header;
+ else
+ error = nh_len;
+ goto out;
+ }
+
+ if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+ goto out;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
+ /* Transport layer. */
+ if (key->ip.proto == NEXTHDR_TCP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ if (tcphdr_ok(skb)) {
+ struct tcphdr *tcp = tcp_hdr(skb);
+ key->ipv6.tp.src = tcp->source;
+ key->ipv6.tp.dst = tcp->dest;
+ }
+ } else if (key->ip.proto == NEXTHDR_UDP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ if (udphdr_ok(skb)) {
+ struct udphdr *udp = udp_hdr(skb);
+ key->ipv6.tp.src = udp->source;
+ key->ipv6.tp.dst = udp->dest;
+ }
+ } else if (key->ip.proto == NEXTHDR_ICMP) {
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ if (icmp6hdr_ok(skb)) {
+ error = parse_icmpv6(skb, key, &key_len, nh_len);
+ if (error < 0)
+ goto out;
+ }
+ }
+ }
+
+out:
+ *key_lenp = key_len;
+ return error;
+}
+
+u32 ovs_flow_hash(const struct sw_flow_key *key, int key_len)
+{
+ return jhash2((u32 *)key, DIV_ROUND_UP(key_len, sizeof(u32)), 0);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
+ struct sw_flow_key *key, int key_len)
+{
+ struct sw_flow *flow;
+ struct hlist_node *n;
+ struct hlist_head *head;
+ u32 hash;
+
+ hash = ovs_flow_hash(key, key_len);
+
+ head = find_bucket(table, hash);
+ hlist_for_each_entry_rcu(flow, n, head, hash_node[table->node_ver]) {
+
+ if (flow->hash == hash &&
+ !memcmp(&flow->key, key, key_len)) {
+ return flow;
+ }
+ }
+ return NULL;
+}
+
+void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow)
+{
+ struct hlist_head *head;
+
+ head = find_bucket(table, flow->hash);
+ hlist_add_head_rcu(&flow->hash_node[table->node_ver], head);
+ table->count++;
+}
+
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
+{
+ hlist_del_rcu(&flow->hash_node[table->node_ver]);
+ table->count--;
+ BUG_ON(table->count < 0);
+}
+
+/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
+const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
+ [OVS_KEY_ATTR_ENCAP] = -1,
+ [OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
+ [OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
+ [OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
+ [OVS_KEY_ATTR_VLAN] = sizeof(__be16),
+ [OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
+ [OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
+ [OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
+ [OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
+ [OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
+ [OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
+ [OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
+ [OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
+ [OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
+};
+
+static int ipv4_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
+ const struct nlattr *a[], u32 *attrs)
+{
+ const struct ovs_key_icmp *icmp_key;
+ const struct ovs_key_tcp *tcp_key;
+ const struct ovs_key_udp *udp_key;
+
+ switch (swkey->ip.proto) {
+ case IPPROTO_TCP:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_TCP);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
+ swkey->ipv4.tp.src = tcp_key->tcp_src;
+ swkey->ipv4.tp.dst = tcp_key->tcp_dst;
+ break;
+
+ case IPPROTO_UDP:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_UDP);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
+ swkey->ipv4.tp.src = udp_key->udp_src;
+ swkey->ipv4.tp.dst = udp_key->udp_dst;
+ break;
+
+ case IPPROTO_ICMP:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_ICMP)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+ icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
+ swkey->ipv4.tp.src = htons(icmp_key->icmp_type);
+ swkey->ipv4.tp.dst = htons(icmp_key->icmp_code);
+ break;
+ }
+
+ return 0;
+}
+
+static int ipv6_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
+ const struct nlattr *a[], u32 *attrs)
+{
+ const struct ovs_key_icmpv6 *icmpv6_key;
+ const struct ovs_key_tcp *tcp_key;
+ const struct ovs_key_udp *udp_key;
+
+ switch (swkey->ip.proto) {
+ case IPPROTO_TCP:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_TCP);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
+ swkey->ipv6.tp.src = tcp_key->tcp_src;
+ swkey->ipv6.tp.dst = tcp_key->tcp_dst;
+ break;
+
+ case IPPROTO_UDP:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_UDP);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
+ swkey->ipv6.tp.src = udp_key->udp_src;
+ swkey->ipv6.tp.dst = udp_key->udp_dst;
+ break;
+
+ case IPPROTO_ICMPV6:
+ if (!(*attrs & (1 << OVS_KEY_ATTR_ICMPV6)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+ icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
+ swkey->ipv6.tp.src = htons(icmpv6_key->icmpv6_type);
+ swkey->ipv6.tp.dst = htons(icmpv6_key->icmpv6_code);
+
+ if (swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+ swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+ const struct ovs_key_nd *nd_key;
+
+ if (!(*attrs & (1 << OVS_KEY_ATTR_ND)))
+ return -EINVAL;
+ *attrs &= ~(1 << OVS_KEY_ATTR_ND);
+
+ *key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+ nd_key = nla_data(a[OVS_KEY_ATTR_ND]);
+ memcpy(&swkey->ipv6.nd.target, nd_key->nd_target,
+ sizeof(swkey->ipv6.nd.target));
+ memcpy(swkey->ipv6.nd.sll, nd_key->nd_sll, ETH_ALEN);
+ memcpy(swkey->ipv6.nd.tll, nd_key->nd_tll, ETH_ALEN);
+ }
+ break;
+ }
+
+ return 0;
+}
+
+static int parse_flow_nlattrs(const struct nlattr *attr,
+ const struct nlattr *a[], u32 *attrsp)
+{
+ const struct nlattr *nla;
+ u32 attrs;
+ int rem;
+
+ attrs = 0;
+ nla_for_each_nested(nla, attr, rem) {
+ u16 type = nla_type(nla);
+ int expected_len;
+
+ if (type > OVS_KEY_ATTR_MAX || attrs & (1 << type))
+ return -EINVAL;
+
+ expected_len = ovs_key_lens[type];
+ if (nla_len(nla) != expected_len && expected_len != -1)
+ return -EINVAL;
+
+ attrs |= 1 << type;
+ a[type] = nla;
+ }
+ if (rem)
+ return -EINVAL;
+
+ *attrsp = attrs;
+ return 0;
+}
+
+/**
+ * ovs_flow_from_nlattrs - parses Netlink attributes into a flow key.
+ * @swkey: receives the extracted flow key.
+ * @key_lenp: number of bytes used in @swkey.
+ * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
+ * sequence.
+ */
+int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
+ const struct nlattr *attr)
+{
+ const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
+ const struct ovs_key_ethernet *eth_key;
+ int key_len;
+ u32 attrs;
+ int err;
+
+ memset(swkey, 0, sizeof(struct sw_flow_key));
+ key_len = SW_FLOW_KEY_OFFSET(eth);
+
+ err = parse_flow_nlattrs(attr, a, &attrs);
+ if (err)
+ return err;
+
+ /* Metadata attributes. */
+ if (attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
+ swkey->phy.priority = nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]);
+ attrs &= ~(1 << OVS_KEY_ATTR_PRIORITY);
+ }
+ if (attrs & (1 << OVS_KEY_ATTR_IN_PORT)) {
+ u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);
+ if (in_port >= DP_MAX_PORTS)
+ return -EINVAL;
+ swkey->phy.in_port = in_port;
+ attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT);
+ } else {
+ swkey->phy.in_port = USHRT_MAX;
+ }
+
+ /* Data attributes. */
+ if (!(attrs & (1 << OVS_KEY_ATTR_ETHERNET)))
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);
+
+ eth_key = nla_data(a[OVS_KEY_ATTR_ETHERNET]);
+ memcpy(swkey->eth.src, eth_key->eth_src, ETH_ALEN);
+ memcpy(swkey->eth.dst, eth_key->eth_dst, ETH_ALEN);
+
+ if (attrs & (1u << OVS_KEY_ATTR_ETHERTYPE) &&
+ nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q)) {
+ const struct nlattr *encap;
+ __be16 tci;
+
+ if (attrs != ((1 << OVS_KEY_ATTR_VLAN) |
+ (1 << OVS_KEY_ATTR_ETHERTYPE) |
+ (1 << OVS_KEY_ATTR_ENCAP)))
+ return -EINVAL;
+
+ encap = a[OVS_KEY_ATTR_ENCAP];
+ tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
+ if (tci & htons(VLAN_TAG_PRESENT)) {
+ swkey->eth.tci = tci;
+
+ err = parse_flow_nlattrs(encap, a, &attrs);
+ if (err)
+ return err;
+ } else if (!tci) {
+ /* Corner case for truncated 802.1Q header. */
+ if (nla_len(encap))
+ return -EINVAL;
+
+ swkey->eth.type = htons(ETH_P_8021Q);
+ *key_lenp = key_len;
+ return 0;
+ } else {
+ return -EINVAL;
+ }
+ }
+
+ if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
+ swkey->eth.type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+ if (ntohs(swkey->eth.type) < 1536)
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+ } else {
+ swkey->eth.type = htons(ETH_P_802_2);
+ }
+
+ if (swkey->eth.type == htons(ETH_P_IP)) {
+ const struct ovs_key_ipv4 *ipv4_key;
+
+ if (!(attrs & (1 << OVS_KEY_ATTR_IPV4)))
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
+
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);
+ ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
+ if (ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX)
+ return -EINVAL;
+ swkey->ip.proto = ipv4_key->ipv4_proto;
+ swkey->ip.tos = ipv4_key->ipv4_tos;
+ swkey->ip.ttl = ipv4_key->ipv4_ttl;
+ swkey->ip.frag = ipv4_key->ipv4_frag;
+ swkey->ipv4.addr.src = ipv4_key->ipv4_src;
+ swkey->ipv4.addr.dst = ipv4_key->ipv4_dst;
+
+ if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+ err = ipv4_flow_from_nlattrs(swkey, &key_len, a, &attrs);
+ if (err)
+ return err;
+ }
+ } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+ const struct ovs_key_ipv6 *ipv6_key;
+
+ if (!(attrs & (1 << OVS_KEY_ATTR_IPV6)))
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
+
+ key_len = SW_FLOW_KEY_OFFSET(ipv6.label);
+ ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
+ if (ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX)
+ return -EINVAL;
+ swkey->ipv6.label = ipv6_key->ipv6_label;
+ swkey->ip.proto = ipv6_key->ipv6_proto;
+ swkey->ip.tos = ipv6_key->ipv6_tclass;
+ swkey->ip.ttl = ipv6_key->ipv6_hlimit;
+ swkey->ip.frag = ipv6_key->ipv6_frag;
+ memcpy(&swkey->ipv6.addr.src, ipv6_key->ipv6_src,
+ sizeof(swkey->ipv6.addr.src));
+ memcpy(&swkey->ipv6.addr.dst, ipv6_key->ipv6_dst,
+ sizeof(swkey->ipv6.addr.dst));
+
+ if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+ err = ipv6_flow_from_nlattrs(swkey, &key_len, a, &attrs);
+ if (err)
+ return err;
+ }
+ } else if (swkey->eth.type == htons(ETH_P_ARP)) {
+ const struct ovs_key_arp *arp_key;
+
+ if (!(attrs & (1 << OVS_KEY_ATTR_ARP)))
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_ARP);
+
+ key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
+ arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
+ swkey->ipv4.addr.src = arp_key->arp_sip;
+ swkey->ipv4.addr.dst = arp_key->arp_tip;
+ if (arp_key->arp_op & htons(0xff00))
+ return -EINVAL;
+ swkey->ip.proto = ntohs(arp_key->arp_op);
+ memcpy(swkey->ipv4.arp.sha, arp_key->arp_sha, ETH_ALEN);
+ memcpy(swkey->ipv4.arp.tha, arp_key->arp_tha, ETH_ALEN);
+ }
+
+ if (attrs)
+ return -EINVAL;
+ *key_lenp = key_len;
+
+ return 0;
+}
+
+/**
+ * ovs_flow_metadata_from_nlattrs - parses Netlink attributes into a flow key.
+ * @in_port: receives the extracted input port.
+ * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
+ * sequence.
+ *
+ * This parses a series of Netlink attributes that form a flow key, which must
+ * take the same form accepted by flow_from_nlattrs(), but only enough of it to
+ * get the metadata, that is, the parts of the flow key that cannot be
+ * extracted from the packet itself.
+ */
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+ const struct nlattr *attr)
+{
+ const struct nlattr *nla;
+ int rem;
+
+ *in_port = USHRT_MAX;
+ *priority = 0;
+
+ nla_for_each_nested(nla, attr, rem) {
+ int type = nla_type(nla);
+
+ if (type <= OVS_KEY_ATTR_MAX && ovs_key_lens[type] > 0) {
+ if (nla_len(nla) != ovs_key_lens[type])
+ return -EINVAL;
+
+ switch (type) {
+ case OVS_KEY_ATTR_PRIORITY:
+ *priority = nla_get_u32(nla);
+ break;
+
+ case OVS_KEY_ATTR_IN_PORT:
+ if (nla_get_u32(nla) >= DP_MAX_PORTS)
+ return -EINVAL;
+ *in_port = nla_get_u32(nla);
+ break;
+ }
+ }
+ }
+ if (rem)
+ return -EINVAL;
+ return 0;
+}
+
+int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb)
+{
+ struct ovs_key_ethernet *eth_key;
+ struct nlattr *nla, *encap;
+
+ if (swkey->phy.priority)
+ NLA_PUT_U32(skb, OVS_KEY_ATTR_PRIORITY, swkey->phy.priority);
+
+ if (swkey->phy.in_port != USHRT_MAX)
+ NLA_PUT_U32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port);
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
+ if (!nla)
+ goto nla_put_failure;
+ eth_key = nla_data(nla);
+ memcpy(eth_key->eth_src, swkey->eth.src, ETH_ALEN);
+ memcpy(eth_key->eth_dst, swkey->eth.dst, ETH_ALEN);
+
+ if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
+ NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, htons(ETH_P_8021Q));
+ NLA_PUT_BE16(skb, OVS_KEY_ATTR_VLAN, swkey->eth.tci);
+ encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.tci)
+ goto unencap;
+ } else {
+ encap = NULL;
+ }
+
+ if (swkey->eth.type == htons(ETH_P_802_2))
+ goto unencap;
+
+ NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, swkey->eth.type);
+
+ if (swkey->eth.type == htons(ETH_P_IP)) {
+ struct ovs_key_ipv4 *ipv4_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_IPV4, sizeof(*ipv4_key));
+ if (!nla)
+ goto nla_put_failure;
+ ipv4_key = nla_data(nla);
+ ipv4_key->ipv4_src = swkey->ipv4.addr.src;
+ ipv4_key->ipv4_dst = swkey->ipv4.addr.dst;
+ ipv4_key->ipv4_proto = swkey->ip.proto;
+ ipv4_key->ipv4_tos = swkey->ip.tos;
+ ipv4_key->ipv4_ttl = swkey->ip.ttl;
+ ipv4_key->ipv4_frag = swkey->ip.frag;
+ } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+ struct ovs_key_ipv6 *ipv6_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
+ if (!nla)
+ goto nla_put_failure;
+ ipv6_key = nla_data(nla);
+ memcpy(ipv6_key->ipv6_src, &swkey->ipv6.addr.src,
+ sizeof(ipv6_key->ipv6_src));
+ memcpy(ipv6_key->ipv6_dst, &swkey->ipv6.addr.dst,
+ sizeof(ipv6_key->ipv6_dst));
+ ipv6_key->ipv6_label = swkey->ipv6.label;
+ ipv6_key->ipv6_proto = swkey->ip.proto;
+ ipv6_key->ipv6_tclass = swkey->ip.tos;
+ ipv6_key->ipv6_hlimit = swkey->ip.ttl;
+ ipv6_key->ipv6_frag = swkey->ip.frag;
+ } else if (swkey->eth.type == htons(ETH_P_ARP)) {
+ struct ovs_key_arp *arp_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key));
+ if (!nla)
+ goto nla_put_failure;
+ arp_key = nla_data(nla);
+ memset(arp_key, 0, sizeof(struct ovs_key_arp));
+ arp_key->arp_sip = swkey->ipv4.addr.src;
+ arp_key->arp_tip = swkey->ipv4.addr.dst;
+ arp_key->arp_op = htons(swkey->ip.proto);
+ memcpy(arp_key->arp_sha, swkey->ipv4.arp.sha, ETH_ALEN);
+ memcpy(arp_key->arp_tha, swkey->ipv4.arp.tha, ETH_ALEN);
+ }
+
+ if ((swkey->eth.type == htons(ETH_P_IP) ||
+ swkey->eth.type == htons(ETH_P_IPV6)) &&
+ swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+
+ if (swkey->ip.proto == IPPROTO_TCP) {
+ struct ovs_key_tcp *tcp_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_TCP, sizeof(*tcp_key));
+ if (!nla)
+ goto nla_put_failure;
+ tcp_key = nla_data(nla);
+ if (swkey->eth.type == htons(ETH_P_IP)) {
+ tcp_key->tcp_src = swkey->ipv4.tp.src;
+ tcp_key->tcp_dst = swkey->ipv4.tp.dst;
+ } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+ tcp_key->tcp_src = swkey->ipv6.tp.src;
+ tcp_key->tcp_dst = swkey->ipv6.tp.dst;
+ }
+ } else if (swkey->ip.proto == IPPROTO_UDP) {
+ struct ovs_key_udp *udp_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_UDP, sizeof(*udp_key));
+ if (!nla)
+ goto nla_put_failure;
+ udp_key = nla_data(nla);
+ if (swkey->eth.type == htons(ETH_P_IP)) {
+ udp_key->udp_src = swkey->ipv4.tp.src;
+ udp_key->udp_dst = swkey->ipv4.tp.dst;
+ } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+ udp_key->udp_src = swkey->ipv6.tp.src;
+ udp_key->udp_dst = swkey->ipv6.tp.dst;
+ }
+ } else if (swkey->eth.type == htons(ETH_P_IP) &&
+ swkey->ip.proto == IPPROTO_ICMP) {
+ struct ovs_key_icmp *icmp_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ICMP, sizeof(*icmp_key));
+ if (!nla)
+ goto nla_put_failure;
+ icmp_key = nla_data(nla);
+ icmp_key->icmp_type = ntohs(swkey->ipv4.tp.src);
+ icmp_key->icmp_code = ntohs(swkey->ipv4.tp.dst);
+ } else if (swkey->eth.type == htons(ETH_P_IPV6) &&
+ swkey->ip.proto == IPPROTO_ICMPV6) {
+ struct ovs_key_icmpv6 *icmpv6_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ICMPV6,
+ sizeof(*icmpv6_key));
+ if (!nla)
+ goto nla_put_failure;
+ icmpv6_key = nla_data(nla);
+ icmpv6_key->icmpv6_type = ntohs(swkey->ipv6.tp.src);
+ icmpv6_key->icmpv6_code = ntohs(swkey->ipv6.tp.dst);
+
+ if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+ icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
+ struct ovs_key_nd *nd_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
+ if (!nla)
+ goto nla_put_failure;
+ nd_key = nla_data(nla);
+ memcpy(nd_key->nd_target, &swkey->ipv6.nd.target,
+ sizeof(nd_key->nd_target));
+ memcpy(nd_key->nd_sll, swkey->ipv6.nd.sll, ETH_ALEN);
+ memcpy(nd_key->nd_tll, swkey->ipv6.nd.tll, ETH_ALEN);
+ }
+ }
+ }
+
+unencap:
+ if (encap)
+ nla_nest_end(skb, encap);
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+/* Initializes the flow module.
+ * Returns zero if successful or a negative error code. */
+int ovs_flow_init(void)
+{
+ flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
+ 0, NULL);
+ if (flow_cache == NULL)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/* Uninitializes the flow module. */
+void ovs_flow_exit(void)
+{
+ kmem_cache_destroy(flow_cache);
+}
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef FLOW_H
+#define FLOW_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+#include <net/inet_ecn.h>
+
+struct sk_buff;
+
+struct sw_flow_actions {
+ struct rcu_head rcu;
+ u32 actions_len;
+ struct nlattr actions[];
+};
+
+struct sw_flow_key {
+ struct {
+ u32 priority; /* Packet QoS priority. */
+ u16 in_port; /* Input switch port (or USHRT_MAX). */
+ } phy;
+ struct {
+ u8 src[ETH_ALEN]; /* Ethernet source address. */
+ u8 dst[ETH_ALEN]; /* Ethernet destination address. */
+ __be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
+ __be16 type; /* Ethernet frame type. */
+ } eth;
+ struct {
+ u8 proto; /* IP protocol or lower 8 bits of ARP opcode. */
+ u8 tos; /* IP ToS. */
+ u8 ttl; /* IP TTL/hop limit. */
+ u8 frag; /* One of OVS_FRAG_TYPE_*. */
+ } ip;
+ union {
+ struct {
+ struct {
+ __be32 src; /* IP source address. */
+ __be32 dst; /* IP destination address. */
+ } addr;
+ union {
+ struct {
+ __be16 src; /* TCP/UDP source port. */
+ __be16 dst; /* TCP/UDP destination port. */
+ } tp;
+ struct {
+ u8 sha[ETH_ALEN]; /* ARP source hardware address. */
+ u8 tha[ETH_ALEN]; /* ARP target hardware address. */
+ } arp;
+ };
+ } ipv4;
+ struct {
+ struct {
+ struct in6_addr src; /* IPv6 source address. */
+ struct in6_addr dst; /* IPv6 destination address. */
+ } addr;
+ __be32 label; /* IPv6 flow label. */
+ struct {
+ __be16 src; /* TCP/UDP source port. */
+ __be16 dst; /* TCP/UDP destination port. */
+ } tp;
+ struct {
+ struct in6_addr target; /* ND target address. */
+ u8 sll[ETH_ALEN]; /* ND source link layer address. */
+ u8 tll[ETH_ALEN]; /* ND target link layer address. */
+ } nd;
+ } ipv6;
+ };
+};
+
+struct sw_flow {
+ struct rcu_head rcu;
+ struct hlist_node hash_node[2];
+ u32 hash;
+
+ struct sw_flow_key key;
+ struct sw_flow_actions __rcu *sf_acts;
+
+ spinlock_t lock; /* Lock for values below. */
+ unsigned long used; /* Last used time (in jiffies). */
+ u64 packet_count; /* Number of packets matched. */
+ u64 byte_count; /* Number of bytes matched. */
+ u8 tcp_flags; /* Union of seen TCP flags. */
+};
+
+struct arp_eth_header {
+ __be16 ar_hrd; /* format of hardware address */
+ __be16 ar_pro; /* format of protocol address */
+ unsigned char ar_hln; /* length of hardware address */
+ unsigned char ar_pln; /* length of protocol address */
+ __be16 ar_op; /* ARP opcode (command) */
+
+ /* Ethernet+IPv4 specific members. */
+ unsigned char ar_sha[ETH_ALEN]; /* sender hardware address */
+ unsigned char ar_sip[4]; /* sender IP address */
+ unsigned char ar_tha[ETH_ALEN]; /* target hardware address */
+ unsigned char ar_tip[4]; /* target IP address */
+} __packed;
+
+int ovs_flow_init(void);
+void ovs_flow_exit(void);
+
+struct sw_flow *ovs_flow_alloc(void);
+void ovs_flow_deferred_free(struct sw_flow *);
+void ovs_flow_free(struct sw_flow *flow);
+
+struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *);
+void ovs_flow_deferred_free_acts(struct sw_flow_actions *);
+
+int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *,
+ int *key_lenp);
+void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+u64 ovs_flow_used_time(unsigned long flow_jiffies);
+
+/* Upper bound on the length of a nlattr-formatted flow key. The longest
+ * nlattr-formatted flow key would be:
+ *
+ * struct pad nl hdr total
+ * ------ --- ------ -----
+ * OVS_KEY_ATTR_PRIORITY 4 -- 4 8
+ * OVS_KEY_ATTR_IN_PORT 4 -- 4 8
+ * OVS_KEY_ATTR_ETHERNET 12 -- 4 16
+ * OVS_KEY_ATTR_8021Q 4 -- 4 8
+ * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8
+ * OVS_KEY_ATTR_IPV6 40 -- 4 44
+ * OVS_KEY_ATTR_ICMPV6 2 2 4 8
+ * OVS_KEY_ATTR_ND 28 -- 4 32
+ * -------------------------------------------------
+ * total 132
+ */
+#define FLOW_BUFSIZE 132
+
+int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *);
+int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
+ const struct nlattr *);
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+ const struct nlattr *);
+
+#define TBL_MIN_BUCKETS 1024
+
+struct flow_table {
+ struct flex_array *buckets;
+ unsigned int count, n_buckets;
+ struct rcu_head rcu;
+ int node_ver;
+ u32 hash_seed;
+ bool keep_flows;
+};
+
+static inline int ovs_flow_tbl_count(struct flow_table *table)
+{
+ return table->count;
+}
+
+static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table)
+{
+ return (table->count > table->n_buckets);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
+ struct sw_flow_key *key, int len);
+void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_deferred_destroy(struct flow_table *table);
+struct flow_table *ovs_flow_tbl_alloc(int new_size);
+struct flow_table *ovs_flow_tbl_expand(struct flow_table *table);
+struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table);
+void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow);
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+u32 ovs_flow_hash(const struct sw_flow_key *key, int key_len);
+
+struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *idx);
+extern const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1];
+
+#endif /* flow.h */
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/hardirq.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/skbuff.h>
+#include <linux/version.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+struct internal_dev {
+ struct vport *vport;
+};
+
+static struct internal_dev *internal_dev_priv(struct net_device *netdev)
+{
+ return netdev_priv(netdev);
+}
+
+/* This function is only called by the kernel network layer.*/
+static struct rtnl_link_stats64 *internal_dev_get_stats(struct net_device *netdev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct vport *vport = ovs_internal_dev_get_vport(netdev);
+ struct ovs_vport_stats vport_stats;
+
+ ovs_vport_get_stats(vport, &vport_stats);
+
+ /* The tx and rx stats need to be swapped because the
+ * switch and host OS have opposite perspectives. */
+ stats->rx_packets = vport_stats.tx_packets;
+ stats->tx_packets = vport_stats.rx_packets;
+ stats->rx_bytes = vport_stats.tx_bytes;
+ stats->tx_bytes = vport_stats.rx_bytes;
+ stats->rx_errors = vport_stats.tx_errors;
+ stats->tx_errors = vport_stats.rx_errors;
+ stats->rx_dropped = vport_stats.tx_dropped;
+ stats->tx_dropped = vport_stats.rx_dropped;
+
+ return stats;
+}
+
+static int internal_dev_mac_addr(struct net_device *dev, void *p)
+{
+ struct sockaddr *addr = p;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+ memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+ return 0;
+}
+
+/* Called with rcu_read_lock_bh. */
+static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+ rcu_read_lock();
+ ovs_vport_receive(internal_dev_priv(netdev)->vport, skb);
+ rcu_read_unlock();
+ return 0;
+}
+
+static int internal_dev_open(struct net_device *netdev)
+{
+ netif_start_queue(netdev);
+ return 0;
+}
+
+static int internal_dev_stop(struct net_device *netdev)
+{
+ netif_stop_queue(netdev);
+ return 0;
+}
+
+static void internal_dev_getinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *info)
+{
+ strcpy(info->driver, "openvswitch");
+}
+
+static const struct ethtool_ops internal_dev_ethtool_ops = {
+ .get_drvinfo = internal_dev_getinfo,
+ .get_link = ethtool_op_get_link,
+};
+
+static int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ if (new_mtu < 68)
+ return -EINVAL;
+
+ netdev->mtu = new_mtu;
+ return 0;
+}
+
+static void internal_dev_destructor(struct net_device *dev)
+{
+ struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+ ovs_vport_free(vport);
+ free_netdev(dev);
+}
+
+static const struct net_device_ops internal_dev_netdev_ops = {
+ .ndo_open = internal_dev_open,
+ .ndo_stop = internal_dev_stop,
+ .ndo_start_xmit = internal_dev_xmit,
+ .ndo_set_mac_address = internal_dev_mac_addr,
+ .ndo_change_mtu = internal_dev_change_mtu,
+ .ndo_get_stats64 = internal_dev_get_stats,
+};
+
+static void do_setup(struct net_device *netdev)
+{
+ ether_setup(netdev);
+
+ netdev->netdev_ops = &internal_dev_netdev_ops;
+
+ netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ netdev->destructor = internal_dev_destructor;
+ SET_ETHTOOL_OPS(netdev, &internal_dev_ethtool_ops);
+ netdev->tx_queue_len = 0;
+
+ netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
+ NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_TSO;
+
+ netdev->vlan_features = netdev->features;
+ netdev->features |= NETIF_F_HW_VLAN_TX;
+ netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
+ random_ether_addr(netdev->dev_addr);
+}
+
+static struct vport *internal_dev_create(const struct vport_parms *parms)
+{
+ struct vport *vport;
+ struct netdev_vport *netdev_vport;
+ struct internal_dev *internal_dev;
+ int err;
+
+ vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+ &ovs_internal_vport_ops, parms);
+ if (IS_ERR(vport)) {
+ err = PTR_ERR(vport);
+ goto error;
+ }
+
+ netdev_vport = netdev_vport_priv(vport);
+
+ netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev),
+ parms->name, do_setup);
+ if (!netdev_vport->dev) {
+ err = -ENOMEM;
+ goto error_free_vport;
+ }
+
+ internal_dev = internal_dev_priv(netdev_vport->dev);
+ internal_dev->vport = vport;
+
+ err = register_netdevice(netdev_vport->dev);
+ if (err)
+ goto error_free_netdev;
+
+ dev_set_promiscuity(netdev_vport->dev, 1);
+ netif_start_queue(netdev_vport->dev);
+
+ return vport;
+
+error_free_netdev:
+ free_netdev(netdev_vport->dev);
+error_free_vport:
+ ovs_vport_free(vport);
+error:
+ return ERR_PTR(err);
+}
+
+static void internal_dev_destroy(struct vport *vport)
+{
+ struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+ netif_stop_queue(netdev_vport->dev);
+ dev_set_promiscuity(netdev_vport->dev, -1);
+
+ /* unregister_netdevice() waits for an RCU grace period. */
+ unregister_netdevice(netdev_vport->dev);
+}
+
+static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
+{
+ struct net_device *netdev = netdev_vport_priv(vport)->dev;
+ int len;
+
+ len = skb->len;
+ skb->dev = netdev;
+ skb->pkt_type = PACKET_HOST;
+ skb->protocol = eth_type_trans(skb, netdev);
+
+ netif_rx(skb);
+
+ return len;
+}
+
+const struct vport_ops ovs_internal_vport_ops = {
+ .type = OVS_VPORT_TYPE_INTERNAL,
+ .create = internal_dev_create,
+ .destroy = internal_dev_destroy,
+ .get_name = ovs_netdev_get_name,
+ .get_ifindex = ovs_netdev_get_ifindex,
+ .send = internal_dev_recv,
+};
+
+int ovs_is_internal_dev(const struct net_device *netdev)
+{
+ return netdev->netdev_ops == &internal_dev_netdev_ops;
+}
+
+struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
+{
+ if (!ovs_is_internal_dev(netdev))
+ return NULL;
+
+ return internal_dev_priv(netdev)->vport;
+}
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_INTERNAL_DEV_H
+#define VPORT_INTERNAL_DEV_H 1
+
+#include "datapath.h"
+#include "vport.h"
+
+int ovs_is_internal_dev(const struct net_device *);
+struct vport *ovs_internal_dev_get_vport(struct net_device *);
+
+#endif /* vport-internal_dev.h */
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if_arp.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/llc.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+
+#include <net/llc.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+/* Must be called with rcu_read_lock. */
+static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
+{
+ if (unlikely(!vport)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ /* Make our own copy of the packet. Otherwise we will mangle the
+ * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
+ * (No one comes after us, since we tell handle_bridge() that we took
+ * the packet.) */
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ return;
+
+ skb_push(skb, ETH_HLEN);
+ ovs_vport_receive(vport, skb);
+}
+
+/* Called with rcu_read_lock and bottom-halves disabled. */
+static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct vport *vport;
+
+ if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+ return RX_HANDLER_PASS;
+
+ vport = ovs_netdev_get_vport(skb->dev);
+
+ netdev_port_receive(vport, skb);
+
+ return RX_HANDLER_CONSUMED;
+}
+
+static struct vport *netdev_create(const struct vport_parms *parms)
+{
+ struct vport *vport;
+ struct netdev_vport *netdev_vport;
+ int err;
+
+ vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+ &ovs_netdev_vport_ops, parms);
+ if (IS_ERR(vport)) {
+ err = PTR_ERR(vport);
+ goto error;
+ }
+
+ netdev_vport = netdev_vport_priv(vport);
+
+ netdev_vport->dev = dev_get_by_name(&init_net, parms->name);
+ if (!netdev_vport->dev) {
+ err = -ENODEV;
+ goto error_free_vport;
+ }
+
+ if (netdev_vport->dev->flags & IFF_LOOPBACK ||
+ netdev_vport->dev->type != ARPHRD_ETHER ||
+ ovs_is_internal_dev(netdev_vport->dev)) {
+ err = -EINVAL;
+ goto error_put;
+ }
+
+ err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook,
+ vport);
+ if (err)
+ goto error_put;
+
+ dev_set_promiscuity(netdev_vport->dev, 1);
+ netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
+
+ return vport;
+
+error_put:
+ dev_put(netdev_vport->dev);
+error_free_vport:
+ ovs_vport_free(vport);
+error:
+ return ERR_PTR(err);
+}
+
+static void netdev_destroy(struct vport *vport)
+{
+ struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+ netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
+ netdev_rx_handler_unregister(netdev_vport->dev);
+ dev_set_promiscuity(netdev_vport->dev, -1);
+
+ synchronize_rcu();
+
+ dev_put(netdev_vport->dev);
+ ovs_vport_free(vport);
+}
+
+const char *ovs_netdev_get_name(const struct vport *vport)
+{
+ const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+ return netdev_vport->dev->name;
+}
+
+int ovs_netdev_get_ifindex(const struct vport *vport)
+{
+ const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+ return netdev_vport->dev->ifindex;
+}
+
+static unsigned packet_length(const struct sk_buff *skb)
+{
+ unsigned length = skb->len - ETH_HLEN;
+
+ if (skb->protocol == htons(ETH_P_8021Q))
+ length -= VLAN_HLEN;
+
+ return length;
+}
+
+static int netdev_send(struct vport *vport, struct sk_buff *skb)
+{
+ struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+ int mtu = netdev_vport->dev->mtu;
+ int len;
+
+ if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+ if (net_ratelimit())
+ pr_warn("%s: dropped over-mtu packet: %d > %d\n",
+ ovs_dp_name(vport->dp), packet_length(skb), mtu);
+ goto error;
+ }
+
+ if (unlikely(skb_warn_if_lro(skb)))
+ goto error;
+
+ skb->dev = netdev_vport->dev;
+ len = skb->len;
+ dev_queue_xmit(skb);
+
+ return len;
+
+error:
+ kfree_skb(skb);
+ ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
+ return 0;
+}
+
+/* Returns null if this device is not attached to a datapath. */
+struct vport *ovs_netdev_get_vport(struct net_device *dev)
+{
+ if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
+ return (struct vport *)
+ rcu_dereference_rtnl(dev->rx_handler_data);
+ else
+ return NULL;
+}
+
+const struct vport_ops ovs_netdev_vport_ops = {
+ .type = OVS_VPORT_TYPE_NETDEV,
+ .create = netdev_create,
+ .destroy = netdev_destroy,
+ .get_name = ovs_netdev_get_name,
+ .get_ifindex = ovs_netdev_get_ifindex,
+ .send = netdev_send,
+};
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_NETDEV_H
+#define VPORT_NETDEV_H 1
+
+#include <linux/netdevice.h>
+
+#include "vport.h"
+
+struct vport *ovs_netdev_get_vport(struct net_device *dev);
+
+struct netdev_vport {
+ struct net_device *dev;
+};
+
+static inline struct netdev_vport *
+netdev_vport_priv(const struct vport *vport)
+{
+ return vport_priv(vport);
+}
+
+const char *ovs_netdev_get_name(const struct vport *);
+const char *ovs_netdev_get_config(const struct vport *);
+int ovs_netdev_get_ifindex(const struct vport *);
+
+#endif /* vport_netdev.h */
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/dcache.h>
+#include <linux/etherdevice.h>
+#include <linux/if.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+#include <linux/compat.h>
+#include <linux/version.h>
+
+#include "vport.h"
+#include "vport-internal_dev.h"
+
+/* List of statically compiled vport implementations. Don't forget to also
+ * add yours to the list at the bottom of vport.h. */
+static const struct vport_ops *vport_ops_list[] = {
+ &ovs_netdev_vport_ops,
+ &ovs_internal_vport_ops,
+};
+
+/* Protected by RCU read lock for reading, RTNL lock for writing. */
+static struct hlist_head *dev_table;
+#define VPORT_HASH_BUCKETS 1024
+
+/**
+ * ovs_vport_init - initialize vport subsystem
+ *
+ * Called at module load time to initialize the vport subsystem.
+ */
+int ovs_vport_init(void)
+{
+ dev_table = kzalloc(VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
+ GFP_KERNEL);
+ if (!dev_table)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * ovs_vport_exit - shutdown vport subsystem
+ *
+ * Called at module exit time to shutdown the vport subsystem.
+ */
+void ovs_vport_exit(void)
+{
+ kfree(dev_table);
+}
+
+static struct hlist_head *hash_bucket(const char *name)
+{
+ unsigned int hash = full_name_hash(name, strlen(name));
+ return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
+}
+
+/**
+ * ovs_vport_locate - find a port that has already been created
+ *
+ * @name: name of port to find
+ *
+ * Must be called with RTNL or RCU read lock.
+ */
+struct vport *ovs_vport_locate(const char *name)
+{
+ struct hlist_head *bucket = hash_bucket(name);
+ struct vport *vport;
+ struct hlist_node *node;
+
+ hlist_for_each_entry_rcu(vport, node, bucket, hash_node)
+ if (!strcmp(name, vport->ops->get_name(vport)))
+ return vport;
+
+ return NULL;
+}
+
+/**
+ * ovs_vport_alloc - allocate and initialize new vport
+ *
+ * @priv_size: Size of private data area to allocate.
+ * @ops: vport device ops
+ *
+ * Allocate and initialize a new vport defined by @ops. The vport will contain
+ * a private data area of size @priv_size that can be accessed using
+ * vport_priv(). vports that are no longer needed should be released with
+ * vport_free().
+ */
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
+ const struct vport_parms *parms)
+{
+ struct vport *vport;
+ size_t alloc_size;
+
+ alloc_size = sizeof(struct vport);
+ if (priv_size) {
+ alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
+ alloc_size += priv_size;
+ }
+
+ vport = kzalloc(alloc_size, GFP_KERNEL);
+ if (!vport)
+ return ERR_PTR(-ENOMEM);
+
+ vport->dp = parms->dp;
+ vport->port_no = parms->port_no;
+ vport->upcall_pid = parms->upcall_pid;
+ vport->ops = ops;
+
+ vport->percpu_stats = alloc_percpu(struct vport_percpu_stats);
+ if (!vport->percpu_stats) {
+ kfree(vport);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ spin_lock_init(&vport->stats_lock);
+
+ return vport;
+}
+
+/**
+ * ovs_vport_free - uninitialize and free vport
+ *
+ * @vport: vport to free
+ *
+ * Frees a vport allocated with vport_alloc() when it is no longer needed.
+ *
+ * The caller must ensure that an RCU grace period has passed since the last
+ * time @vport was in a datapath.
+ */
+void ovs_vport_free(struct vport *vport)
+{
+ free_percpu(vport->percpu_stats);
+ kfree(vport);
+}
+
+/**
+ * ovs_vport_add - add vport device (for kernel callers)
+ *
+ * @parms: Information about new vport.
+ *
+ * Creates a new vport with the specified configuration (which is dependent on
+ * device type). RTNL lock must be held.
+ */
+struct vport *ovs_vport_add(const struct vport_parms *parms)
+{
+ struct vport *vport;
+ int err = 0;
+ int i;
+
+ ASSERT_RTNL();
+
+ for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
+ if (vport_ops_list[i]->type == parms->type) {
+ vport = vport_ops_list[i]->create(parms);
+ if (IS_ERR(vport)) {
+ err = PTR_ERR(vport);
+ goto out;
+ }
+
+ hlist_add_head_rcu(&vport->hash_node,
+ hash_bucket(vport->ops->get_name(vport)));
+ return vport;
+ }
+ }
+
+ err = -EAFNOSUPPORT;
+
+out:
+ return ERR_PTR(err);
+}
+
+/**
+ * ovs_vport_set_options - modify existing vport device (for kernel callers)
+ *
+ * @vport: vport to modify.
+ * @port: New configuration.
+ *
+ * Modifies an existing device with the specified configuration (which is
+ * dependent on device type). RTNL lock must be held.
+ */
+int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
+{
+ ASSERT_RTNL();
+
+ if (!vport->ops->set_options)
+ return -EOPNOTSUPP;
+ return vport->ops->set_options(vport, options);
+}
+
+/**
+ * ovs_vport_del - delete existing vport device
+ *
+ * @vport: vport to delete.
+ *
+ * Detaches @vport from its datapath and destroys it. It is possible to fail
+ * for reasons such as lack of memory. RTNL lock must be held.
+ */
+void ovs_vport_del(struct vport *vport)
+{
+ ASSERT_RTNL();
+
+ hlist_del_rcu(&vport->hash_node);
+
+ vport->ops->destroy(vport);
+}
+
+/**
+ * ovs_vport_get_stats - retrieve device stats
+ *
+ * @vport: vport from which to retrieve the stats
+ * @stats: location to store stats
+ *
+ * Retrieves transmit, receive, and error stats for the given device.
+ *
+ * Must be called with RTNL lock or rcu_read_lock.
+ */
+void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
+{
+ int i;
+
+ memset(stats, 0, sizeof(*stats));
+
+ /* We potentially have 2 sources of stats that need to be combined:
+ * those we have collected (split into err_stats and percpu_stats) from
+ * set_stats() and device error stats from netdev->get_stats() (for
+ * errors that happen downstream and therefore aren't reported through
+ * our vport_record_error() function).
+ * Stats from first source are reported by ovs (OVS_VPORT_ATTR_STATS).
+ * netdev-stats can be directly read over netlink-ioctl.
+ */
+
+ spin_lock_bh(&vport->stats_lock);
+
+ stats->rx_errors = vport->err_stats.rx_errors;
+ stats->tx_errors = vport->err_stats.tx_errors;
+ stats->tx_dropped = vport->err_stats.tx_dropped;
+ stats->rx_dropped = vport->err_stats.rx_dropped;
+
+ spin_unlock_bh(&vport->stats_lock);
+
+ for_each_possible_cpu(i) {
+ const struct vport_percpu_stats *percpu_stats;
+ struct vport_percpu_stats local_stats;
+ unsigned int start;
+
+ percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
+
+ do {
+ start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+ local_stats = *percpu_stats;
+ } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+
+ stats->rx_bytes += local_stats.rx_bytes;
+ stats->rx_packets += local_stats.rx_packets;
+ stats->tx_bytes += local_stats.tx_bytes;
+ stats->tx_packets += local_stats.tx_packets;
+ }
+}
+
+/**
+ * ovs_vport_get_options - retrieve device options
+ *
+ * @vport: vport from which to retrieve the options.
+ * @skb: sk_buff where options should be appended.
+ *
+ * Retrieves the configuration of the given device, appending an
+ * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
+ * vport-specific attributes to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
+ * negative error code if a real error occurred. If an error occurs, @skb is
+ * left unmodified.
+ *
+ * Must be called with RTNL lock or rcu_read_lock.
+ */
+int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+ struct nlattr *nla;
+
+ nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
+ if (!nla)
+ return -EMSGSIZE;
+
+ if (vport->ops->get_options) {
+ int err = vport->ops->get_options(vport, skb);
+ if (err) {
+ nla_nest_cancel(skb, nla);
+ return err;
+ }
+ }
+
+ nla_nest_end(skb, nla);
+ return 0;
+}
+
+/**
+ * ovs_vport_receive - pass up received packet to the datapath for processing
+ *
+ * @vport: vport that received the packet
+ * @skb: skb that was received
+ *
+ * Must be called with rcu_read_lock. The packet cannot be shared and
+ * skb->data should point to the Ethernet header. The caller must have already
+ * called compute_ip_summed() to initialize the checksumming fields.
+ */
+void ovs_vport_receive(struct vport *vport, struct sk_buff *skb)
+{
+ struct vport_percpu_stats *stats;
+
+ stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
+
+ u64_stats_update_begin(&stats->sync);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->sync);
+
+ ovs_dp_process_received_packet(vport, skb);
+}
+
+/**
+ * ovs_vport_send - send a packet on a device
+ *
+ * @vport: vport on which to send the packet
+ * @skb: skb to send
+ *
+ * Sends the given packet and returns the length of data sent. Either RTNL
+ * lock or rcu_read_lock must be held.
+ */
+int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+{
+ int sent = vport->ops->send(vport, skb);
+
+ if (likely(sent)) {
+ struct vport_percpu_stats *stats;
+
+ stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
+
+ u64_stats_update_begin(&stats->sync);
+ stats->tx_packets++;
+ stats->tx_bytes += sent;
+ u64_stats_update_end(&stats->sync);
+ }
+ return sent;
+}
+
+/**
+ * ovs_vport_record_error - indicate device error to generic stats layer
+ *
+ * @vport: vport that encountered the error
+ * @err_type: one of enum vport_err_type types to indicate the error type
+ *
+ * If using the vport generic stats layer indicate that an error of the given
+ * type has occured.
+ */
+void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
+{
+ spin_lock(&vport->stats_lock);
+
+ switch (err_type) {
+ case VPORT_E_RX_DROPPED:
+ vport->err_stats.rx_dropped++;
+ break;
+
+ case VPORT_E_RX_ERROR:
+ vport->err_stats.rx_errors++;
+ break;
+
+ case VPORT_E_TX_DROPPED:
+ vport->err_stats.tx_dropped++;
+ break;
+
+ case VPORT_E_TX_ERROR:
+ vport->err_stats.tx_errors++;
+ break;
+ };
+
+ spin_unlock(&vport->stats_lock);
+}
--- /dev/null
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_H
+#define VPORT_H 1
+
+#include <linux/list.h>
+#include <linux/openvswitch.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/u64_stats_sync.h>
+
+#include "datapath.h"
+
+struct vport;
+struct vport_parms;
+
+/* The following definitions are for users of the vport subsytem: */
+
+int ovs_vport_init(void);
+void ovs_vport_exit(void);
+
+struct vport *ovs_vport_add(const struct vport_parms *);
+void ovs_vport_del(struct vport *);
+
+struct vport *ovs_vport_locate(const char *name);
+
+void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
+
+int ovs_vport_set_options(struct vport *, struct nlattr *options);
+int ovs_vport_get_options(const struct vport *, struct sk_buff *);
+
+int ovs_vport_send(struct vport *, struct sk_buff *);
+
+/* The following definitions are for implementers of vport devices: */
+
+struct vport_percpu_stats {
+ u64 rx_bytes;
+ u64 rx_packets;
+ u64 tx_bytes;
+ u64 tx_packets;
+ struct u64_stats_sync sync;
+};
+
+struct vport_err_stats {
+ u64 rx_dropped;
+ u64 rx_errors;
+ u64 tx_dropped;
+ u64 tx_errors;
+};
+
+/**
+ * struct vport - one port within a datapath
+ * @rcu: RCU callback head for deferred destruction.
+ * @port_no: Index into @dp's @ports array.
+ * @dp: Datapath to which this port belongs.
+ * @node: Element in @dp's @port_list.
+ * @upcall_pid: The Netlink port to use for packets received on this port that
+ * miss the flow table.
+ * @hash_node: Element in @dev_table hash table in vport.c.
+ * @ops: Class structure.
+ * @percpu_stats: Points to per-CPU statistics used and maintained by vport
+ * @stats_lock: Protects @err_stats;
+ * @err_stats: Points to error statistics used and maintained by vport
+ */
+struct vport {
+ struct rcu_head rcu;
+ u16 port_no;
+ struct datapath *dp;
+ struct list_head node;
+ u32 upcall_pid;
+
+ struct hlist_node hash_node;
+ const struct vport_ops *ops;
+
+ struct vport_percpu_stats __percpu *percpu_stats;
+
+ spinlock_t stats_lock;
+ struct vport_err_stats err_stats;
+};
+
+/**
+ * struct vport_parms - parameters for creating a new vport
+ *
+ * @name: New vport's name.
+ * @type: New vport's type.
+ * @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
+ * none was supplied.
+ * @dp: New vport's datapath.
+ * @port_no: New vport's port number.
+ */
+struct vport_parms {
+ const char *name;
+ enum ovs_vport_type type;
+ struct nlattr *options;
+
+ /* For ovs_vport_alloc(). */
+ struct datapath *dp;
+ u16 port_no;
+ u32 upcall_pid;
+};
+
+/**
+ * struct vport_ops - definition of a type of virtual port
+ *
+ * @type: %OVS_VPORT_TYPE_* value for this type of virtual port.
+ * @create: Create a new vport configured as specified. On success returns
+ * a new vport allocated with ovs_vport_alloc(), otherwise an ERR_PTR() value.
+ * @destroy: Destroys a vport. Must call vport_free() on the vport but not
+ * before an RCU grace period has elapsed.
+ * @set_options: Modify the configuration of an existing vport. May be %NULL
+ * if modification is not supported.
+ * @get_options: Appends vport-specific attributes for the configuration of an
+ * existing vport to a &struct sk_buff. May be %NULL for a vport that does not
+ * have any configuration.
+ * @get_name: Get the device's name.
+ * @get_config: Get the device's configuration.
+ * @get_ifindex: Get the system interface index associated with the device.
+ * May be null if the device does not have an ifindex.
+ * @send: Send a packet on the device. Returns the length of the packet sent.
+ */
+struct vport_ops {
+ enum ovs_vport_type type;
+
+ /* Called with RTNL lock. */
+ struct vport *(*create)(const struct vport_parms *);
+ void (*destroy)(struct vport *);
+
+ int (*set_options)(struct vport *, struct nlattr *);
+ int (*get_options)(const struct vport *, struct sk_buff *);
+
+ /* Called with rcu_read_lock or RTNL lock. */
+ const char *(*get_name)(const struct vport *);
+ void (*get_config)(const struct vport *, void *);
+ int (*get_ifindex)(const struct vport *);
+
+ int (*send)(struct vport *, struct sk_buff *);
+};
+
+enum vport_err_type {
+ VPORT_E_RX_DROPPED,
+ VPORT_E_RX_ERROR,
+ VPORT_E_TX_DROPPED,
+ VPORT_E_TX_ERROR,
+};
+
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
+ const struct vport_parms *);
+void ovs_vport_free(struct vport *);
+
+#define VPORT_ALIGN 8
+
+/**
+ * vport_priv - access private data area of vport
+ *
+ * @vport: vport to access
+ *
+ * If a nonzero size was passed in priv_size of vport_alloc() a private data
+ * area was allocated on creation. This allows that area to be accessed and
+ * used for any purpose needed by the vport implementer.
+ */
+static inline void *vport_priv(const struct vport *vport)
+{
+ return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+}
+
+/**
+ * vport_from_priv - lookup vport from private data pointer
+ *
+ * @priv: Start of private data area.
+ *
+ * It is sometimes useful to translate from a pointer to the private data
+ * area to the vport, such as in the case where the private data pointer is
+ * the result of a hash table lookup. @priv must point to the start of the
+ * private data area.
+ */
+static inline struct vport *vport_from_priv(const void *priv)
+{
+ return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+}
+
+void ovs_vport_receive(struct vport *, struct sk_buff *);
+void ovs_vport_record_error(struct vport *, enum vport_err_type err_type);
+
+/* List of statically compiled vport implementations. Don't forget to also
+ * add yours to the list at the top of vport.c. */
+extern const struct vport_ops ovs_netdev_vport_ops;
+extern const struct vport_ops ovs_internal_vport_ops;
+
+#endif /* vport.h */
if (!skb) {
size_t reserved = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
rcu_read_unlock();
- skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL);
+ skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL);
if (skb == NULL)
return -ENOBUFS;
/* FIXME: Save some space for broken drivers that write a hard
if (snaplen > res)
snaplen = res;
- if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned)sk->sk_rcvbuf)
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto drop_n_acct;
if (skb_shared(skb)) {
if (po->tp_version <= TPACKET_V2) {
if (macoff + snaplen > po->rx_ring.frame_size) {
if (po->copy_thresh &&
- atomic_read(&sk->sk_rmem_alloc) + skb->truesize
- < (unsigned)sk->sk_rcvbuf) {
+ atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
if (skb_shared(skb)) {
copy_skb = skb_clone(skb, GFP_ATOMIC);
} else {
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
void *frame, struct net_device *dev, int size_max,
- __be16 proto, unsigned char *addr)
+ __be16 proto, unsigned char *addr, int hlen)
{
union {
struct tpacket_hdr *h1;
return -EMSGSIZE;
}
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
unsigned char *addr;
int len_sum = 0;
int status = 0;
+ int hlen, tlen;
mutex_lock(&po->pg_vec_lock);
}
status = TP_STATUS_SEND_REQUEST;
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
skb = sock_alloc_send_skb(&po->sk,
- LL_ALLOCATED_SPACE(dev)
- + sizeof(struct sockaddr_ll),
+ hlen + tlen + sizeof(struct sockaddr_ll),
0, &err);
if (unlikely(skb == NULL))
goto out_status;
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
- addr);
+ addr, hlen);
if (unlikely(tp_len < 0)) {
if (po->tp_loss) {
int vnet_hdr_len;
struct packet_sock *po = pkt_sk(sk);
unsigned short gso_type = 0;
+ int hlen, tlen;
/*
* Get and verify the address.
goto out_unlock;
err = -ENOBUFS;
- skb = packet_alloc_skb(sk, LL_ALLOCATED_SPACE(dev),
- LL_RESERVED_SPACE(dev), len, vnet_hdr.hdr_len,
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, vnet_hdr.hdr_len,
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out_unlock;
{
struct packet_sock *po = pkt_sk(sk);
- if (po->fanout)
+ if (po->fanout) {
+ if (dev)
+ dev_put(dev);
+
return -EINVAL;
+ }
lock_sock(sk);
return pipe_handler_send_created_ind(sk);
}
+static int pep_enableresp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ struct pnpipehdr *hdr = pnp_hdr(skb);
+
+ if (hdr->error_code != PN_PIPE_NO_ERROR)
+ return -ECONNREFUSED;
+
+ return pep_indicate(sk, PNS_PIPE_ENABLED_IND, 0 /* sub-blocks */,
+ NULL, 0, GFP_ATOMIC);
+
+}
+
+static void pipe_start_flow_control(struct sock *sk)
+{
+ struct pep_sock *pn = pep_sk(sk);
+
+ if (!pn_flow_safe(pn->tx_fc)) {
+ atomic_set(&pn->tx_credits, 1);
+ sk->sk_write_space(sk);
+ }
+ pipe_grant_credits(sk, GFP_ATOMIC);
+}
+
/* Queue an skb to an actively connected sock.
* Socket lock must be held. */
static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
sk->sk_state = TCP_CLOSE_WAIT;
break;
}
+ if (pn->init_enable == PN_PIPE_DISABLE)
+ sk->sk_state = TCP_SYN_RECV;
+ else {
+ sk->sk_state = TCP_ESTABLISHED;
+ pipe_start_flow_control(sk);
+ }
+ break;
- sk->sk_state = TCP_ESTABLISHED;
- if (!pn_flow_safe(pn->tx_fc)) {
- atomic_set(&pn->tx_credits, 1);
- sk->sk_write_space(sk);
+ case PNS_PEP_ENABLE_RESP:
+ if (sk->sk_state != TCP_SYN_SENT)
+ break;
+
+ if (pep_enableresp_rcv(sk, skb)) {
+ sk->sk_state = TCP_CLOSE_WAIT;
+ break;
}
- pipe_grant_credits(sk, GFP_ATOMIC);
+
+ sk->sk_state = TCP_ESTABLISHED;
+ pipe_start_flow_control(sk);
break;
case PNS_PEP_DISCONNECT_RESP:
int err;
u8 data[4] = { 0 /* sub-blocks */, PAD, PAD, PAD };
- pn->pipe_handle = 1; /* anything but INVALID_HANDLE */
+ if (pn->pipe_handle == PN_PIPE_INVALID_HANDLE)
+ pn->pipe_handle = 1; /* anything but INVALID_HANDLE */
+
err = pipe_handler_request(sk, PNS_PEP_CONNECT_REQ,
- PN_PIPE_ENABLE, data, 4);
+ pn->init_enable, data, 4);
if (err) {
pn->pipe_handle = PN_PIPE_INVALID_HANDLE;
return err;
}
+
sk->sk_state = TCP_SYN_SENT;
+
+ return 0;
+}
+
+static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len)
+{
+ int err;
+
+ err = pipe_handler_request(sk, PNS_PEP_ENABLE_REQ, PAD,
+ NULL, 0);
+ if (err)
+ return err;
+
+ sk->sk_state = TCP_SYN_SENT;
+
return 0;
}
{
struct pep_sock *pn = pep_sk(sk);
int answ;
+ int ret = -ENOIOCTLCMD;
switch (cmd) {
case SIOCINQ:
- if (sk->sk_state == TCP_LISTEN)
- return -EINVAL;
+ if (sk->sk_state == TCP_LISTEN) {
+ ret = -EINVAL;
+ break;
+ }
lock_sock(sk);
if (sock_flag(sk, SOCK_URGINLINE) &&
else
answ = 0;
release_sock(sk);
- return put_user(answ, (int __user *)arg);
+ ret = put_user(answ, (int __user *)arg);
+ break;
+
+ case SIOCPNENABLEPIPE:
+ lock_sock(sk);
+ if (sk->sk_state == TCP_SYN_SENT)
+ ret = -EBUSY;
+ else if (sk->sk_state == TCP_ESTABLISHED)
+ ret = -EISCONN;
+ else
+ ret = pep_sock_enable(sk, NULL, 0);
+ release_sock(sk);
+ break;
}
- return -ENOIOCTLCMD;
+ return ret;
}
static int pep_init(struct sock *sk)
}
goto out_norel;
+ case PNPIPE_HANDLE:
+ if ((sk->sk_state == TCP_CLOSE) &&
+ (val >= 0) && (val < PN_PIPE_INVALID_HANDLE))
+ pn->pipe_handle = val;
+ else
+ err = -EINVAL;
+ break;
+
+ case PNPIPE_INITSTATE:
+ pn->init_enable = !!val;
+ break;
+
default:
err = -ENOPROTOOPT;
}
return -EINVAL;
break;
+ case PNPIPE_INITSTATE:
+ val = pn->init_enable;
+ break;
+
default:
return -ENOPROTOOPT;
}
config RDS_RDMA
tristate "RDS over Infiniband and iWARP"
- select LLIST
depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS
---help---
Allow RDS to use Infiniband and iWARP as a transport.
if (blocked) {
if (rfkill_data->reg_enabled) {
regulator_disable(rfkill_data->vcc);
- rfkill_data->reg_enabled = 0;
+ rfkill_data->reg_enabled = false;
}
} else {
if (!rfkill_data->reg_enabled) {
regulator_enable(rfkill_data->vcc);
- rfkill_data->reg_enabled = 1;
+ rfkill_data->reg_enabled = true;
}
}
if (regulator_is_enabled(vcc)) {
dev_dbg(&pdev->dev, "Regulator already enabled\n");
- rfkill_data->reg_enabled = 1;
+ rfkill_data->reg_enabled = true;
}
rfkill_data->vcc = vcc;
rfkill_data->rf_kill = rf_kill;
sp = rxrpc_skb(txb);
if (sp->need_resend) {
- sp->need_resend = 0;
+ sp->need_resend = false;
/* each Tx packet has a new serial number */
sp->hdr.serial =
}
if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = 1;
+ sp->need_resend = true;
resend |= 1;
} else if (resend & 2) {
if (time_before(sp->resend_at, resend_at))
if (sp->need_resend) {
;
} else if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = 1;
+ sp->need_resend = true;
resend |= 1;
} else if (resend & 2) {
if (time_before(sp->resend_at, resend_at))
switch (sacks[loop]) {
case RXRPC_ACK_TYPE_ACK:
- sp->need_resend = 0;
+ sp->need_resend = false;
*p_txb |= 1;
break;
case RXRPC_ACK_TYPE_NACK:
- sp->need_resend = 1;
+ sp->need_resend = true;
*p_txb &= ~1;
resend = 1;
break;
if (*p_txb & 1) {
/* packet must have been discarded */
- sp->need_resend = 1;
+ sp->need_resend = true;
*p_txb &= ~1;
resend |= 1;
} else if (sp->need_resend) {
;
} else if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = 1;
+ sp->need_resend = true;
resend |= 1;
} else if (resend & 2) {
if (time_before(sp->resend_at, resend_at))
td->data_len = len;
if (len > 0) {
- td->data = kmalloc(len, GFP_KERNEL);
+ td->data = kmemdup(xdr, len, GFP_KERNEL);
if (!td->data)
return -ENOMEM;
- memcpy(td->data, xdr, len);
len = (len + 3) & ~3;
toklen -= len;
xdr += len >> 2;
_debug("ticket len %u", len);
if (len > 0) {
- *_ticket = kmalloc(len, GFP_KERNEL);
+ *_ticket = kmemdup(xdr, len, GFP_KERNEL);
if (!*_ticket)
return -ENOMEM;
- memcpy(*_ticket, xdr, len);
len = (len + 3) & ~3;
toklen -= len;
xdr += len >> 2;
_proto("Tx DATA %%%u { #%u }",
ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
- sp->need_resend = 0;
+ sp->need_resend = false;
sp->resend_at = jiffies + rxrpc_resend_timeout * HZ;
if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) {
_debug("run timer");
if (ret < 0) {
_debug("need instant resend %d", ret);
- sp->need_resend = 1;
+ sp->need_resend = true;
rxrpc_instant_resend(call);
}
#include <net/pkt_cls.h>
#include <net/ip.h>
#include <net/route.h>
+#include <net/flow_keys.h>
+
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netfilter/nf_conntrack.h>
#endif
return (a & 0xFFFFFFFF) ^ (BITS_PER_LONG > 32 ? a >> 32 : 0);
}
-static u32 flow_get_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
- __be32 *data = NULL, hdata;
-
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct iphdr,
- saddr),
- 4, &hdata);
- break;
- case htons(ETH_P_IPV6):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct ipv6hdr,
- saddr.s6_addr32[3]),
- 4, &hdata);
- break;
- }
-
- if (data)
- return ntohl(*data);
+ if (flow->src)
+ return ntohl(flow->src);
return addr_fold(skb->sk);
}
-static u32 flow_get_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
- __be32 *data = NULL, hdata;
-
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct iphdr,
- daddr),
- 4, &hdata);
- break;
- case htons(ETH_P_IPV6):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct ipv6hdr,
- daddr.s6_addr32[3]),
- 4, &hdata);
- break;
- }
-
- if (data)
- return ntohl(*data);
+ if (flow->dst)
+ return ntohl(flow->dst);
return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
}
-static u32 flow_get_proto(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
{
- __u8 *data = NULL, hdata;
-
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct iphdr,
- protocol),
- 1, &hdata);
- break;
- case htons(ETH_P_IPV6):
- data = skb_header_pointer(skb,
- nhoff + offsetof(struct ipv6hdr,
- nexthdr),
- 1, &hdata);
- break;
- }
- if (data)
- return *data;
- return 0;
+ return flow->ip_proto;
}
-/* helper function to get either src or dst port */
-static __be16 *flow_get_proto_common(const struct sk_buff *skb, int nhoff,
- __be16 *_port, int dst)
+static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
- __be16 *port = NULL;
- int poff;
-
- switch (skb->protocol) {
- case htons(ETH_P_IP): {
- struct iphdr *iph, _iph;
-
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
- break;
- if (ip_is_fragment(iph))
- break;
- poff = proto_ports_offset(iph->protocol);
- if (poff >= 0)
- port = skb_header_pointer(skb,
- nhoff + iph->ihl * 4 + poff + dst,
- sizeof(*_port), _port);
- break;
- }
- case htons(ETH_P_IPV6): {
- struct ipv6hdr *iph, _iph;
-
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
- break;
- poff = proto_ports_offset(iph->nexthdr);
- if (poff >= 0)
- port = skb_header_pointer(skb,
- nhoff + sizeof(*iph) + poff + dst,
- sizeof(*_port), _port);
- break;
- }
- }
-
- return port;
-}
-
-static u32 flow_get_proto_src(const struct sk_buff *skb, int nhoff)
-{
- __be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 0);
-
- if (port)
- return ntohs(*port);
+ if (flow->ports)
+ return ntohs(flow->port16[0]);
return addr_fold(skb->sk);
}
-static u32 flow_get_proto_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
- __be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 2);
-
- if (port)
- return ntohs(*port);
+ if (flow->ports)
+ return ntohs(flow->port16[1]);
return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
}
})
#endif
-static u32 flow_get_nfct_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
switch (skb->protocol) {
case htons(ETH_P_IP):
return ntohl(CTTUPLE(skb, src.u3.ip6[3]));
}
fallback:
- return flow_get_src(skb, nhoff);
+ return flow_get_src(skb, flow);
}
-static u32 flow_get_nfct_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
switch (skb->protocol) {
case htons(ETH_P_IP):
return ntohl(CTTUPLE(skb, dst.u3.ip6[3]));
}
fallback:
- return flow_get_dst(skb, nhoff);
+ return flow_get_dst(skb, flow);
}
-static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
return ntohs(CTTUPLE(skb, src.u.all));
fallback:
- return flow_get_proto_src(skb, nhoff);
+ return flow_get_proto_src(skb, flow);
}
-static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
return ntohs(CTTUPLE(skb, dst.u.all));
fallback:
- return flow_get_proto_dst(skb, nhoff);
+ return flow_get_proto_dst(skb, flow);
}
static u32 flow_get_rtclassid(const struct sk_buff *skb)
return skb_get_rxhash(skb);
}
-static u32 flow_key_get(struct sk_buff *skb, int key)
+static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow)
{
- int nhoff = skb_network_offset(skb);
-
switch (key) {
case FLOW_KEY_SRC:
- return flow_get_src(skb, nhoff);
+ return flow_get_src(skb, flow);
case FLOW_KEY_DST:
- return flow_get_dst(skb, nhoff);
+ return flow_get_dst(skb, flow);
case FLOW_KEY_PROTO:
- return flow_get_proto(skb, nhoff);
+ return flow_get_proto(skb, flow);
case FLOW_KEY_PROTO_SRC:
- return flow_get_proto_src(skb, nhoff);
+ return flow_get_proto_src(skb, flow);
case FLOW_KEY_PROTO_DST:
- return flow_get_proto_dst(skb, nhoff);
+ return flow_get_proto_dst(skb, flow);
case FLOW_KEY_IIF:
return flow_get_iif(skb);
case FLOW_KEY_PRIORITY:
case FLOW_KEY_NFCT:
return flow_get_nfct(skb);
case FLOW_KEY_NFCT_SRC:
- return flow_get_nfct_src(skb, nhoff);
+ return flow_get_nfct_src(skb, flow);
case FLOW_KEY_NFCT_DST:
- return flow_get_nfct_dst(skb, nhoff);
+ return flow_get_nfct_dst(skb, flow);
case FLOW_KEY_NFCT_PROTO_SRC:
- return flow_get_nfct_proto_src(skb, nhoff);
+ return flow_get_nfct_proto_src(skb, flow);
case FLOW_KEY_NFCT_PROTO_DST:
- return flow_get_nfct_proto_dst(skb, nhoff);
+ return flow_get_nfct_proto_dst(skb, flow);
case FLOW_KEY_RTCLASSID:
return flow_get_rtclassid(skb);
case FLOW_KEY_SKUID:
}
}
+#define FLOW_KEYS_NEEDED ((1 << FLOW_KEY_SRC) | \
+ (1 << FLOW_KEY_DST) | \
+ (1 << FLOW_KEY_PROTO) | \
+ (1 << FLOW_KEY_PROTO_SRC) | \
+ (1 << FLOW_KEY_PROTO_DST) | \
+ (1 << FLOW_KEY_NFCT_SRC) | \
+ (1 << FLOW_KEY_NFCT_DST) | \
+ (1 << FLOW_KEY_NFCT_PROTO_SRC) | \
+ (1 << FLOW_KEY_NFCT_PROTO_DST))
+
static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
int r;
list_for_each_entry(f, &head->filters, list) {
- u32 keys[f->nkeys];
+ u32 keys[FLOW_KEY_MAX + 1];
+ struct flow_keys flow_keys;
if (!tcf_em_tree_match(skb, &f->ematches, NULL))
continue;
keymask = f->keymask;
+ if (keymask & FLOW_KEYS_NEEDED)
+ skb_flow_dissect(skb, &flow_keys);
for (n = 0; n < f->nkeys; n++) {
key = ffs(keymask) - 1;
keymask &= ~(1 << key);
- keys[n] = flow_key_get(skb, key);
+ keys[n] = flow_key_get(skb, key, &flow_keys);
}
if (f->mode == FLOW_MODE_HASH)
}
EXPORT_SYMBOL(qdisc_class_hash_remove);
-/* Allocate an unique handle from space managed by kernel */
-
+/* Allocate an unique handle from space managed by kernel
+ * Possible range is [8000-FFFF]:0000 (0x8000 values)
+ */
static u32 qdisc_alloc_handle(struct net_device *dev)
{
- int i = 0x10000;
+ int i = 0x8000;
static u32 autohandle = TC_H_MAKE(0x80000000U, 0);
do {
autohandle += TC_H_MAKE(0x10000U, 0);
if (autohandle == TC_H_MAKE(TC_H_ROOT, 0))
autohandle = TC_H_MAKE(0x80000000U, 0);
- } while (qdisc_lookup(dev, autohandle) && --i > 0);
+ if (!qdisc_lookup(dev, autohandle))
+ return autohandle;
+ cond_resched();
+ } while (--i > 0);
- return i > 0 ? autohandle : 0;
+ return 0;
}
void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
#include <net/red.h>
-#include <linux/ip.h>
-#include <net/ip.h>
-#include <linux/ipv6.h>
-#include <net/ipv6.h>
+#include <net/flow_keys.h>
/*
CHOKe stateless AQM for fair bandwidth allocation
--sch->q.qlen;
}
-/*
- * Compare flow of two packets
- * Returns true only if source and destination address and port match.
- * false for special cases
- */
-static bool choke_match_flow(struct sk_buff *skb1,
- struct sk_buff *skb2)
-{
- int off1, off2, poff;
- const u32 *ports1, *ports2;
- u8 ip_proto;
- __u32 hash1;
-
- if (skb1->protocol != skb2->protocol)
- return false;
-
- /* Use hash value as quick check
- * Assumes that __skb_get_rxhash makes IP header and ports linear
- */
- hash1 = skb_get_rxhash(skb1);
- if (!hash1 || hash1 != skb_get_rxhash(skb2))
- return false;
-
- /* Probably match, but be sure to avoid hash collisions */
- off1 = skb_network_offset(skb1);
- off2 = skb_network_offset(skb2);
-
- switch (skb1->protocol) {
- case __constant_htons(ETH_P_IP): {
- const struct iphdr *ip1, *ip2;
-
- ip1 = (const struct iphdr *) (skb1->data + off1);
- ip2 = (const struct iphdr *) (skb2->data + off2);
-
- ip_proto = ip1->protocol;
- if (ip_proto != ip2->protocol ||
- ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr)
- return false;
-
- if (ip_is_fragment(ip1) | ip_is_fragment(ip2))
- ip_proto = 0;
- off1 += ip1->ihl * 4;
- off2 += ip2->ihl * 4;
- break;
- }
-
- case __constant_htons(ETH_P_IPV6): {
- const struct ipv6hdr *ip1, *ip2;
-
- ip1 = (const struct ipv6hdr *) (skb1->data + off1);
- ip2 = (const struct ipv6hdr *) (skb2->data + off2);
-
- ip_proto = ip1->nexthdr;
- if (ip_proto != ip2->nexthdr ||
- ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) ||
- ipv6_addr_cmp(&ip1->daddr, &ip2->daddr))
- return false;
- off1 += 40;
- off2 += 40;
- }
-
- default: /* Maybe compare MAC header here? */
- return false;
- }
-
- poff = proto_ports_offset(ip_proto);
- if (poff < 0)
- return true;
-
- off1 += poff;
- off2 += poff;
-
- ports1 = (__force u32 *)(skb1->data + off1);
- ports2 = (__force u32 *)(skb2->data + off2);
- return *ports1 == *ports2;
-}
-
struct choke_skb_cb {
- u16 classid;
+ u16 classid;
+ u8 keys_valid;
+ struct flow_keys keys;
};
static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
return choke_skb_cb(skb)->classid;
}
+/*
+ * Compare flow of two packets
+ * Returns true only if source and destination address and port match.
+ * false for special cases
+ */
+static bool choke_match_flow(struct sk_buff *skb1,
+ struct sk_buff *skb2)
+{
+ if (skb1->protocol != skb2->protocol)
+ return false;
+
+ if (!choke_skb_cb(skb1)->keys_valid) {
+ choke_skb_cb(skb1)->keys_valid = 1;
+ skb_flow_dissect(skb1, &choke_skb_cb(skb1)->keys);
+ }
+
+ if (!choke_skb_cb(skb2)->keys_valid) {
+ choke_skb_cb(skb2)->keys_valid = 1;
+ skb_flow_dissect(skb2, &choke_skb_cb(skb2)->keys);
+ }
+
+ return !memcmp(&choke_skb_cb(skb1)->keys,
+ &choke_skb_cb(skb2)->keys,
+ sizeof(struct flow_keys));
+}
+
/*
* Classify flow using either:
* 1. pre-existing classification result in skb
goto other_drop; /* Packet was eaten by filter */
}
+ choke_skb_cb(skb)->keys_valid = 0;
/* Compute average queue usage (see RED) */
p->qavg = red_calc_qavg(p, sch->q.qlen);
if (red_is_idling(p))
static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
[TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) },
[TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE },
+ [TCA_CHOKE_MAX_P] = { .type = NLA_U32 },
};
int err;
struct sk_buff **old = NULL;
unsigned int mask;
+ u32 max_P;
if (opt == NULL)
return -EINVAL;
tb[TCA_CHOKE_STAB] == NULL)
return -EINVAL;
+ max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
+
ctl = nla_data(tb[TCA_CHOKE_PARMS]);
if (ctl->limit > CHOKE_MAX_QUEUE)
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
ctl->Plog, ctl->Scell_log,
- nla_data(tb[TCA_CHOKE_STAB]));
+ nla_data(tb[TCA_CHOKE_STAB]),
+ max_P);
if (q->head == q->tail)
red_end_of_idle_period(&q->parms);
goto nla_put_failure;
NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt);
+ NLA_PUT_U32(skb, TCA_CHOKE_MAX_P, q->parms.max_P);
return nla_nest_end(skb, opts);
nla_put_failure:
/* check the reason of requeuing without tx lock first */
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
- if (!netif_tx_queue_frozen_or_stopped(txq)) {
+ if (!netif_xmit_frozen_or_stopped(txq)) {
q->gso_skb = NULL;
q->q.qlen--;
} else
spin_unlock(root_lock);
HARD_TX_LOCK(dev, txq, smp_processor_id());
- if (!netif_tx_queue_frozen_or_stopped(txq))
+ if (!netif_xmit_frozen_or_stopped(txq))
ret = dev_hard_start_xmit(skb, dev, txq);
HARD_TX_UNLOCK(dev, txq);
ret = dev_requeue_skb(skb, q);
}
- if (ret && netif_tx_queue_frozen_or_stopped(txq))
+ if (ret && netif_xmit_frozen_or_stopped(txq))
ret = 0;
return ret;
* old device drivers set dev->trans_start
*/
trans_start = txq->trans_start ? : dev->trans_start;
- if (netif_tx_queue_stopped(txq) &&
+ if (netif_xmit_stopped(txq) &&
time_after(jiffies, (trans_start +
dev->watchdog_timeo))) {
some_queue_timedout = 1;
+ txq->trans_timeout++;
break;
}
}
struct gred_sched_data {
u32 limit; /* HARD maximal queue length */
- u32 DP; /* the drop pramaters */
+ u32 DP; /* the drop parameters */
u32 bytesin; /* bytes seen on virtualQ so far*/
u32 packetsin; /* packets seen on virtualQ so far*/
u32 backlog; /* bytes on the virtualQ */
}
static inline int gred_change_vq(struct Qdisc *sch, int dp,
- struct tc_gred_qopt *ctl, int prio, u8 *stab)
+ struct tc_gred_qopt *ctl, int prio,
+ u8 *stab, u32 max_P,
+ struct gred_sched_data **prealloc)
{
struct gred_sched *table = qdisc_priv(sch);
- struct gred_sched_data *q;
+ struct gred_sched_data *q = table->tab[dp];
- if (table->tab[dp] == NULL) {
- table->tab[dp] = kzalloc(sizeof(*q), GFP_KERNEL);
- if (table->tab[dp] == NULL)
+ if (!q) {
+ table->tab[dp] = q = *prealloc;
+ *prealloc = NULL;
+ if (!q)
return -ENOMEM;
}
- q = table->tab[dp];
q->DP = dp;
q->prio = prio;
q->limit = ctl->limit;
red_set_parms(&q->parms,
ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog,
- ctl->Scell_log, stab);
+ ctl->Scell_log, stab, max_P);
return 0;
}
[TCA_GRED_PARMS] = { .len = sizeof(struct tc_gred_qopt) },
[TCA_GRED_STAB] = { .len = 256 },
[TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) },
+ [TCA_GRED_MAX_P] = { .type = NLA_U32 },
};
static int gred_change(struct Qdisc *sch, struct nlattr *opt)
struct nlattr *tb[TCA_GRED_MAX + 1];
int err, prio = GRED_DEF_PRIO;
u8 *stab;
+ u32 max_P;
+ struct gred_sched_data *prealloc;
if (opt == NULL)
return -EINVAL;
tb[TCA_GRED_STAB] == NULL)
return -EINVAL;
+ max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0;
+
err = -EINVAL;
ctl = nla_data(tb[TCA_GRED_PARMS]);
stab = nla_data(tb[TCA_GRED_STAB]);
prio = ctl->prio;
}
+ prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
sch_tree_lock(sch);
- err = gred_change_vq(sch, ctl->DP, ctl, prio, stab);
+ err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc);
if (err < 0)
goto errout_locked;
errout_locked:
sch_tree_unlock(sch);
+ kfree(prealloc);
errout:
return err;
}
struct gred_sched *table = qdisc_priv(sch);
struct nlattr *parms, *opts = NULL;
int i;
+ u32 max_p[MAX_DPs];
struct tc_gred_sopt sopt = {
.DPs = table->DPs,
.def_DP = table->def,
if (opts == NULL)
goto nla_put_failure;
NLA_PUT(skb, TCA_GRED_DPS, sizeof(sopt), &sopt);
+
+ for (i = 0; i < MAX_DPs; i++) {
+ struct gred_sched_data *q = table->tab[i];
+
+ max_p[i] = q ? q->parms.max_P : 0;
+ }
+ NLA_PUT(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p);
+
parms = nla_nest_start(skb, TCA_GRED_PARMS);
if (parms == NULL)
goto nla_put_failure;
struct tc_hfsc_stats xstats;
cl->qstats.qlen = cl->qdisc->q.qlen;
+ cl->qstats.backlog = cl->qdisc->qstats.backlog;
xstats.level = cl->level;
xstats.period = cl->cl_vtperiod;
xstats.work = cl->cl_total;
struct hfsc_sched *q = qdisc_priv(sch);
unsigned char *b = skb_tail_pointer(skb);
struct tc_hfsc_qopt qopt;
+ struct hfsc_class *cl;
+ struct hlist_node *n;
+ unsigned int i;
+
+ sch->qstats.backlog = 0;
+ for (i = 0; i < q->clhash.hashsize; i++) {
+ hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode)
+ sch->qstats.backlog += cl->qdisc->qstats.backlog;
+ }
qopt.defcls = q->defcls;
NLA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt);
if (!netif_is_multiqueue(dev))
return -EOPNOTSUPP;
- if (nla_len(opt) < sizeof(*qopt))
+ if (!opt || nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
/* Check that target subqueue is available before
* pulling an skb to avoid head-of-line blocking.
*/
- if (!__netif_subqueue_stopped(qdisc_dev(sch), q->curband)) {
+ if (!netif_xmit_stopped(
+ netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
qdisc = q->queues[q->curband];
skb = qdisc->dequeue(qdisc);
if (skb) {
/* Check that target subqueue is available before
* pulling an skb to avoid head-of-line blocking.
*/
- if (!__netif_subqueue_stopped(qdisc_dev(sch), curband)) {
+ if (!netif_xmit_stopped(
+ netdev_get_tx_queue(qdisc_dev(sch), curband))) {
qdisc = q->queues[curband];
skb = qdisc->ops->peek(qdisc);
if (skb)
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
+#include <linux/reciprocal_div.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
*/
struct netem_sched_data {
+ /* internal t(ime)fifo qdisc uses sch->q and sch->limit */
+
+ /* optional qdisc for classful handling (NULL at netem init) */
struct Qdisc *qdisc;
+
struct qdisc_watchdog watchdog;
psched_tdiff_t latency;
u32 duplicate;
u32 reorder;
u32 corrupt;
+ u32 rate;
+ s32 packet_overhead;
+ u32 cell_size;
+ u32 cell_size_reciprocal;
+ s32 cell_overhead;
struct crndstate {
u32 last;
};
-/* Time stamp put into socket buffer control block */
+/* Time stamp put into socket buffer control block
+ * Only valid when skbs are in our internal t(ime)fifo queue.
+ */
struct netem_skb_cb {
psched_time_t time_to_send;
};
return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu;
}
+static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q)
+{
+ u64 ticks;
+
+ len += q->packet_overhead;
+
+ if (q->cell_size) {
+ u32 cells = reciprocal_divide(len, q->cell_size_reciprocal);
+
+ if (len > cells * q->cell_size) /* extra cell needed for remainder */
+ cells++;
+ len = cells * (q->cell_size + q->cell_overhead);
+ }
+
+ ticks = (u64)len * NSEC_PER_SEC;
+
+ do_div(ticks, q->rate);
+ return PSCHED_NS2TICKS(ticks);
+}
+
+static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
+{
+ struct sk_buff_head *list = &sch->q;
+ psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
+ struct sk_buff *skb;
+
+ if (likely(skb_queue_len(list) < sch->limit)) {
+ skb = skb_peek_tail(list);
+ /* Optimize for add at tail */
+ if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send))
+ return qdisc_enqueue_tail(nskb, sch);
+
+ skb_queue_reverse_walk(list, skb) {
+ if (tnext >= netem_skb_cb(skb)->time_to_send)
+ break;
+ }
+
+ __skb_queue_after(list, skb, nskb);
+ sch->qstats.backlog += qdisc_pkt_len(nskb);
+ return NET_XMIT_SUCCESS;
+ }
+
+ return qdisc_reshape_fail(nskb, sch);
+}
+
/*
* Insert one skb into qdisc.
* Note: parent depends on return value to account for queue length.
&q->delay_cor, q->delay_dist);
now = psched_get_time();
+
+ if (q->rate) {
+ struct sk_buff_head *list = &sch->q;
+
+ delay += packet_len_2_sched_time(skb->len, q);
+
+ if (!skb_queue_empty(list)) {
+ /*
+ * Last packet in queue is reference point (now).
+ * First packet in queue is already in flight,
+ * calculate this time bonus and substract
+ * from delay.
+ */
+ delay -= now - netem_skb_cb(skb_peek(list))->time_to_send;
+ now = netem_skb_cb(skb_peek_tail(list))->time_to_send;
+ }
+ }
+
cb->time_to_send = now + delay;
++q->counter;
- ret = qdisc_enqueue(skb, q->qdisc);
+ ret = tfifo_enqueue(skb, sch);
} else {
/*
* Do re-ordering by putting one out of N packets at the front
cb->time_to_send = psched_get_time();
q->counter = 0;
- __skb_queue_head(&q->qdisc->q, skb);
+ __skb_queue_head(&sch->q, skb);
q->qdisc->qstats.backlog += qdisc_pkt_len(skb);
q->qdisc->qstats.requeues++;
ret = NET_XMIT_SUCCESS;
}
}
- sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
static unsigned int netem_drop(struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
- unsigned int len = 0;
+ unsigned int len;
- if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
- sch->q.qlen--;
+ len = qdisc_queue_drop(sch);
+ if (!len && q->qdisc && q->qdisc->ops->drop)
+ len = q->qdisc->ops->drop(q->qdisc);
+ if (len)
sch->qstats.drops++;
- }
+
return len;
}
if (qdisc_is_throttled(sch))
return NULL;
- skb = q->qdisc->ops->peek(q->qdisc);
+tfifo_dequeue:
+ skb = qdisc_peek_head(sch);
if (skb) {
const struct netem_skb_cb *cb = netem_skb_cb(skb);
- psched_time_t now = psched_get_time();
/* if more time remaining? */
- if (cb->time_to_send <= now) {
- skb = qdisc_dequeue_peeked(q->qdisc);
+ if (cb->time_to_send <= psched_get_time()) {
+ skb = qdisc_dequeue_tail(sch);
if (unlikely(!skb))
- return NULL;
+ goto qdisc_dequeue;
#ifdef CONFIG_NET_CLS_ACT
/*
skb->tstamp.tv64 = 0;
#endif
- sch->q.qlen--;
+ if (q->qdisc) {
+ int err = qdisc_enqueue(skb, q->qdisc);
+
+ if (unlikely(err != NET_XMIT_SUCCESS)) {
+ if (net_xmit_drop_count(err)) {
+ sch->qstats.drops++;
+ qdisc_tree_decrease_qlen(sch, 1);
+ }
+ }
+ goto tfifo_dequeue;
+ }
+deliver:
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
return skb;
}
+ if (q->qdisc) {
+ skb = q->qdisc->ops->dequeue(q->qdisc);
+ if (skb)
+ goto deliver;
+ }
qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send);
}
+qdisc_dequeue:
+ if (q->qdisc) {
+ skb = q->qdisc->ops->dequeue(q->qdisc);
+ if (skb)
+ goto deliver;
+ }
return NULL;
}
{
struct netem_sched_data *q = qdisc_priv(sch);
- qdisc_reset(q->qdisc);
- sch->q.qlen = 0;
+ qdisc_reset_queue(sch);
+ if (q->qdisc)
+ qdisc_reset(q->qdisc);
qdisc_watchdog_cancel(&q->watchdog);
}
return -EINVAL;
s = sizeof(struct disttable) + n * sizeof(s16);
- d = kmalloc(s, GFP_KERNEL);
+ d = kmalloc(s, GFP_KERNEL | __GFP_NOWARN);
if (!d)
d = vmalloc(s);
if (!d)
root_lock = qdisc_root_sleeping_lock(sch);
spin_lock_bh(root_lock);
- dist_free(q->delay_dist);
- q->delay_dist = d;
+ swap(q->delay_dist, d);
spin_unlock_bh(root_lock);
+
+ dist_free(d);
return 0;
}
init_crandom(&q->corrupt_cor, r->correlation);
}
+static void get_rate(struct Qdisc *sch, const struct nlattr *attr)
+{
+ struct netem_sched_data *q = qdisc_priv(sch);
+ const struct tc_netem_rate *r = nla_data(attr);
+
+ q->rate = r->rate;
+ q->packet_overhead = r->packet_overhead;
+ q->cell_size = r->cell_size;
+ if (q->cell_size)
+ q->cell_size_reciprocal = reciprocal_value(q->cell_size);
+ q->cell_overhead = r->cell_overhead;
+}
+
static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
{
struct netem_sched_data *q = qdisc_priv(sch);
case NETEM_LOSS_GI: {
const struct tc_netem_gimodel *gi = nla_data(la);
- if (nla_len(la) != sizeof(struct tc_netem_gimodel)) {
+ if (nla_len(la) < sizeof(struct tc_netem_gimodel)) {
pr_info("netem: incorrect gi model size\n");
return -EINVAL;
}
case NETEM_LOSS_GE: {
const struct tc_netem_gemodel *ge = nla_data(la);
- if (nla_len(la) != sizeof(struct tc_netem_gemodel)) {
- pr_info("netem: incorrect gi model size\n");
+ if (nla_len(la) < sizeof(struct tc_netem_gemodel)) {
+ pr_info("netem: incorrect ge model size\n");
return -EINVAL;
}
[TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) },
[TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) },
[TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) },
+ [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) },
[TCA_NETEM_LOSS] = { .type = NLA_NESTED },
};
if (ret < 0)
return ret;
- ret = fifo_set_limit(q->qdisc, qopt->limit);
- if (ret) {
- pr_info("netem: can't set fifo limit\n");
- return ret;
- }
+ sch->limit = qopt->limit;
q->latency = qopt->latency;
q->jitter = qopt->jitter;
if (tb[TCA_NETEM_CORRUPT])
get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
+ if (tb[TCA_NETEM_RATE])
+ get_rate(sch, tb[TCA_NETEM_RATE]);
+
q->loss_model = CLG_RANDOM;
if (tb[TCA_NETEM_LOSS])
ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
return ret;
}
-/*
- * Special case version of FIFO queue for use by netem.
- * It queues in order based on timestamps in skb's
- */
-struct fifo_sched_data {
- u32 limit;
- psched_time_t oldest;
-};
-
-static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
-{
- struct fifo_sched_data *q = qdisc_priv(sch);
- struct sk_buff_head *list = &sch->q;
- psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
- struct sk_buff *skb;
-
- if (likely(skb_queue_len(list) < q->limit)) {
- /* Optimize for add at tail */
- if (likely(skb_queue_empty(list) || tnext >= q->oldest)) {
- q->oldest = tnext;
- return qdisc_enqueue_tail(nskb, sch);
- }
-
- skb_queue_reverse_walk(list, skb) {
- const struct netem_skb_cb *cb = netem_skb_cb(skb);
-
- if (tnext >= cb->time_to_send)
- break;
- }
-
- __skb_queue_after(list, skb, nskb);
-
- sch->qstats.backlog += qdisc_pkt_len(nskb);
-
- return NET_XMIT_SUCCESS;
- }
-
- return qdisc_reshape_fail(nskb, sch);
-}
-
-static int tfifo_init(struct Qdisc *sch, struct nlattr *opt)
-{
- struct fifo_sched_data *q = qdisc_priv(sch);
-
- if (opt) {
- struct tc_fifo_qopt *ctl = nla_data(opt);
- if (nla_len(opt) < sizeof(*ctl))
- return -EINVAL;
-
- q->limit = ctl->limit;
- } else
- q->limit = max_t(u32, qdisc_dev(sch)->tx_queue_len, 1);
-
- q->oldest = PSCHED_PASTPERFECT;
- return 0;
-}
-
-static int tfifo_dump(struct Qdisc *sch, struct sk_buff *skb)
-{
- struct fifo_sched_data *q = qdisc_priv(sch);
- struct tc_fifo_qopt opt = { .limit = q->limit };
-
- NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
- return skb->len;
-
-nla_put_failure:
- return -1;
-}
-
-static struct Qdisc_ops tfifo_qdisc_ops __read_mostly = {
- .id = "tfifo",
- .priv_size = sizeof(struct fifo_sched_data),
- .enqueue = tfifo_enqueue,
- .dequeue = qdisc_dequeue_head,
- .peek = qdisc_peek_head,
- .drop = qdisc_queue_drop,
- .init = tfifo_init,
- .reset = qdisc_reset_queue,
- .change = tfifo_init,
- .dump = tfifo_dump,
-};
-
static int netem_init(struct Qdisc *sch, struct nlattr *opt)
{
struct netem_sched_data *q = qdisc_priv(sch);
qdisc_watchdog_init(&q->watchdog, sch);
q->loss_model = CLG_RANDOM;
- q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops,
- TC_H_MAKE(sch->handle, 1));
- if (!q->qdisc) {
- pr_notice("netem: qdisc create tfifo qdisc failed\n");
- return -ENOMEM;
- }
-
ret = netem_change(sch, opt);
- if (ret) {
+ if (ret)
pr_info("netem: change failed\n");
- qdisc_destroy(q->qdisc);
- }
return ret;
}
struct netem_sched_data *q = qdisc_priv(sch);
qdisc_watchdog_cancel(&q->watchdog);
- qdisc_destroy(q->qdisc);
+ if (q->qdisc)
+ qdisc_destroy(q->qdisc);
dist_free(q->delay_dist);
}
struct tc_netem_corr cor;
struct tc_netem_reorder reorder;
struct tc_netem_corrupt corrupt;
+ struct tc_netem_rate rate;
qopt.latency = q->latency;
qopt.jitter = q->jitter;
corrupt.correlation = q->corrupt_cor.rho;
NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt);
+ rate.rate = q->rate;
+ rate.packet_overhead = q->packet_overhead;
+ rate.cell_size = q->cell_size;
+ rate.cell_overhead = q->cell_overhead;
+ NLA_PUT(skb, TCA_NETEM_RATE, sizeof(rate), &rate);
+
if (dump_loss_model(q, skb) != 0)
goto nla_put_failure;
{
struct netem_sched_data *q = qdisc_priv(sch);
- if (cl != 1) /* only one class */
+ if (cl != 1 || !q->qdisc) /* only one class */
return -ENOENT;
tcm->tcm_handle |= TC_H_MIN(1);
{
struct netem_sched_data *q = qdisc_priv(sch);
- if (new == NULL)
- new = &noop_qdisc;
-
sch_tree_lock(sch);
*old = q->qdisc;
q->qdisc = new;
- qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
- qdisc_reset(*old);
+ if (*old) {
+ qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
+ qdisc_reset(*old);
+ }
sch_tree_unlock(sch);
return 0;
struct nlattr *tb[TCA_QFQ_MAX + 1];
u32 weight, lmax, inv_w;
int i, err;
+ int delta_w;
if (tca[TCA_OPTIONS] == NULL) {
pr_notice("qfq: no options\n");
inv_w = ONE_FP / weight;
weight = ONE_FP / inv_w;
- if (q->wsum + weight > QFQ_MAX_WSUM) {
+ delta_w = weight - (cl ? ONE_FP / cl->inv_w : 0);
+ if (q->wsum + delta_w > QFQ_MAX_WSUM) {
pr_notice("qfq: total weight out of range (%u + %u)\n",
- weight, q->wsum);
+ delta_w, q->wsum);
return -EINVAL;
}
return err;
}
- sch_tree_lock(sch);
- if (tb[TCA_QFQ_WEIGHT]) {
- q->wsum = weight - ONE_FP / cl->inv_w;
+ if (inv_w != cl->inv_w) {
+ sch_tree_lock(sch);
+ q->wsum += delta_w;
cl->inv_w = inv_w;
+ sch_tree_unlock(sch);
}
- sch_tree_unlock(sch);
-
return 0;
}
i = qfq_calc_index(cl->inv_w, cl->lmax);
cl->grp = &q->groups[i];
- q->wsum += weight;
cl->qdisc = qdisc_create_dflt(sch->dev_queue,
&pfifo_qdisc_ops, classid);
return err;
}
}
+ q->wsum += weight;
sch_tree_lock(sch);
qdisc_class_hash_insert(&q->clhash, &cl->common);
static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl)
{
unsigned long mask;
- uint32_t limit, roundedF;
+ u64 limit, roundedF;
int slot_shift = cl->grp->slot_shift;
roundedF = qfq_round_down(cl->F, slot_shift);
- limit = qfq_round_down(q->V, slot_shift) + (1UL << slot_shift);
+ limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift);
if (!qfq_gt(cl->F, q->V) || qfq_gt(roundedF, limit)) {
/* timestamp was stale */
struct red_sched_data {
u32 limit; /* HARD maximal queue length */
unsigned char flags;
+ struct timer_list adapt_timer;
struct red_parms parms;
struct red_stats stats;
struct Qdisc *qdisc;
static void red_destroy(struct Qdisc *sch)
{
struct red_sched_data *q = qdisc_priv(sch);
+
+ del_timer_sync(&q->adapt_timer);
qdisc_destroy(q->qdisc);
}
static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
[TCA_RED_PARMS] = { .len = sizeof(struct tc_red_qopt) },
[TCA_RED_STAB] = { .len = RED_STAB_SIZE },
+ [TCA_RED_MAX_P] = { .type = NLA_U32 },
};
static int red_change(struct Qdisc *sch, struct nlattr *opt)
struct tc_red_qopt *ctl;
struct Qdisc *child = NULL;
int err;
+ u32 max_P;
if (opt == NULL)
return -EINVAL;
tb[TCA_RED_STAB] == NULL)
return -EINVAL;
+ max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
+
ctl = nla_data(tb[TCA_RED_PARMS]);
if (ctl->limit > 0) {
}
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
- ctl->Plog, ctl->Scell_log,
- nla_data(tb[TCA_RED_STAB]));
+ ctl->Plog, ctl->Scell_log,
+ nla_data(tb[TCA_RED_STAB]),
+ max_P);
- if (skb_queue_empty(&sch->q))
- red_end_of_idle_period(&q->parms);
+ del_timer(&q->adapt_timer);
+ if (ctl->flags & TC_RED_ADAPTATIVE)
+ mod_timer(&q->adapt_timer, jiffies + HZ/2);
+
+ if (!q->qdisc->q.qlen)
+ red_start_of_idle_period(&q->parms);
sch_tree_unlock(sch);
return 0;
}
+static inline void red_adaptative_timer(unsigned long arg)
+{
+ struct Qdisc *sch = (struct Qdisc *)arg;
+ struct red_sched_data *q = qdisc_priv(sch);
+ spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+
+ spin_lock(root_lock);
+ red_adaptative_algo(&q->parms);
+ mod_timer(&q->adapt_timer, jiffies + HZ/2);
+ spin_unlock(root_lock);
+}
+
static int red_init(struct Qdisc *sch, struct nlattr *opt)
{
struct red_sched_data *q = qdisc_priv(sch);
q->qdisc = &noop_qdisc;
+ setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch);
return red_change(sch, opt);
}
if (opts == NULL)
goto nla_put_failure;
NLA_PUT(skb, TCA_RED_PARMS, sizeof(opt), &opt);
+ NLA_PUT_U32(skb, TCA_RED_MAX_P, q->parms.max_P);
return nla_nest_end(skb, opts);
nla_put_failure:
#include <net/ip.h>
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
+#include <net/flow_keys.h>
/*
* SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level)
u32 minqlen = ~0;
u32 r, slot, salt, sfbhash;
int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+ struct flow_keys keys;
if (unlikely(sch->q.qlen >= q->limit)) {
sch->qstats.overlimits++;
/* If using external classifiers, get result and record it. */
if (!sfb_classify(skb, q, &ret, &salt))
goto other_drop;
+ keys.src = salt;
+ keys.dst = 0;
+ keys.ports = 0;
} else {
- salt = skb_get_rxhash(skb);
+ skb_flow_dissect(skb, &keys);
}
slot = q->slot;
- sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+ sfbhash = jhash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports,
+ q->bins[slot].perturbation);
if (!sfbhash)
sfbhash = 1;
sfb_skb_cb(skb)->hashes[slot] = sfbhash;
if (unlikely(p_min >= SFB_MAX_PROB)) {
/* Inelastic flow */
if (q->double_buffering) {
- sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+ sfbhash = jhash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports,
+ q->bins[slot].perturbation);
if (!sfbhash)
sfbhash = 1;
sfb_skb_cb(skb)->hashes[slot] = sfbhash;
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/init.h>
-#include <linux/ipv6.h>
#include <linux/skbuff.h>
#include <linux/jhash.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/flow_keys.h>
/* Stochastic Fairness Queuing algorithm.
return &q->dep[val - SFQ_SLOTS];
}
-static unsigned int sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
+/*
+ * In order to be able to quickly rehash our queue when timer changes
+ * q->perturbation, we store flow_keys in skb->cb[]
+ */
+struct sfq_skb_cb {
+ struct flow_keys keys;
+};
+
+static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb)
{
- return jhash_2words(h, h1, q->perturbation) & (q->divisor - 1);
+ BUILD_BUG_ON(sizeof(skb->cb) <
+ sizeof(struct qdisc_skb_cb) + sizeof(struct sfq_skb_cb));
+ return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data;
}
-static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
+static unsigned int sfq_hash(const struct sfq_sched_data *q,
+ const struct sk_buff *skb)
{
- u32 h, h2;
-
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- {
- const struct iphdr *iph;
- int poff;
-
- if (!pskb_network_may_pull(skb, sizeof(*iph)))
- goto err;
- iph = ip_hdr(skb);
- h = (__force u32)iph->daddr;
- h2 = (__force u32)iph->saddr ^ iph->protocol;
- if (ip_is_fragment(iph))
- break;
- poff = proto_ports_offset(iph->protocol);
- if (poff >= 0 &&
- pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) {
- iph = ip_hdr(skb);
- h2 ^= *(u32 *)((void *)iph + iph->ihl * 4 + poff);
- }
- break;
- }
- case htons(ETH_P_IPV6):
- {
- const struct ipv6hdr *iph;
- int poff;
-
- if (!pskb_network_may_pull(skb, sizeof(*iph)))
- goto err;
- iph = ipv6_hdr(skb);
- h = (__force u32)iph->daddr.s6_addr32[3];
- h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr;
- poff = proto_ports_offset(iph->nexthdr);
- if (poff >= 0 &&
- pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) {
- iph = ipv6_hdr(skb);
- h2 ^= *(u32 *)((void *)iph + sizeof(*iph) + poff);
- }
- break;
- }
- default:
-err:
- h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol;
- h2 = (unsigned long)skb->sk;
- }
+ const struct flow_keys *keys = &sfq_skb_cb(skb)->keys;
+ unsigned int hash;
- return sfq_fold_hash(q, h, h2);
+ hash = jhash_3words((__force u32)keys->dst,
+ (__force u32)keys->src ^ keys->ip_proto,
+ (__force u32)keys->ports, q->perturbation);
+ return hash & (q->divisor - 1);
}
static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
TC_H_MIN(skb->priority) <= q->divisor)
return TC_H_MIN(skb->priority);
- if (!q->filter_list)
+ if (!q->filter_list) {
+ skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys);
return sfq_hash(q, skb) + 1;
+ }
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
result = tc_classify(skb, q->filter_list, &res);
if (slot->qlen == 1) { /* The flow is new */
if (q->tail == NULL) { /* It is the first flow */
slot->next = x;
+ q->tail = slot;
} else {
slot->next = q->tail->next;
q->tail->next = x;
}
- q->tail = slot;
slot->allot = q->scaled_quantum;
}
if (++sch->q.qlen <= q->limit)
kfree_skb(skb);
}
+/*
+ * When q->perturbation is changed, we rehash all queued skbs
+ * to avoid OOO (Out Of Order) effects.
+ * We dont use sfq_dequeue()/sfq_enqueue() because we dont want to change
+ * counters.
+ */
+static void sfq_rehash(struct sfq_sched_data *q)
+{
+ struct sk_buff *skb;
+ int i;
+ struct sfq_slot *slot;
+ struct sk_buff_head list;
+
+ __skb_queue_head_init(&list);
+
+ for (i = 0; i < SFQ_SLOTS; i++) {
+ slot = &q->slots[i];
+ if (!slot->qlen)
+ continue;
+ while (slot->qlen) {
+ skb = slot_dequeue_head(slot);
+ sfq_dec(q, i);
+ __skb_queue_tail(&list, skb);
+ }
+ q->ht[slot->hash] = SFQ_EMPTY_SLOT;
+ }
+ q->tail = NULL;
+
+ while ((skb = __skb_dequeue(&list)) != NULL) {
+ unsigned int hash = sfq_hash(q, skb);
+ sfq_index x = q->ht[hash];
+
+ slot = &q->slots[x];
+ if (x == SFQ_EMPTY_SLOT) {
+ x = q->dep[0].next; /* get a free slot */
+ q->ht[hash] = x;
+ slot = &q->slots[x];
+ slot->hash = hash;
+ }
+ slot_queue_add(slot, skb);
+ sfq_inc(q, x);
+ if (slot->qlen == 1) { /* The flow is new */
+ if (q->tail == NULL) { /* It is the first flow */
+ slot->next = x;
+ } else {
+ slot->next = q->tail->next;
+ q->tail->next = x;
+ }
+ q->tail = slot;
+ slot->allot = q->scaled_quantum;
+ }
+ }
+}
+
static void sfq_perturbation(unsigned long arg)
{
struct Qdisc *sch = (struct Qdisc *)arg;
struct sfq_sched_data *q = qdisc_priv(sch);
+ spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+ spin_lock(root_lock);
q->perturbation = net_random();
+ if (!q->filter_list && q->tail)
+ sfq_rehash(q);
+ spin_unlock(root_lock);
if (q->perturb_period)
mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
return 0;
}
+static void *sfq_alloc(size_t sz)
+{
+ void *ptr = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN);
+
+ if (!ptr)
+ ptr = vmalloc(sz);
+ return ptr;
+}
+
+static void sfq_free(void *addr)
+{
+ if (addr) {
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+ }
+}
+
+static void sfq_destroy(struct Qdisc *sch)
+{
+ struct sfq_sched_data *q = qdisc_priv(sch);
+
+ tcf_destroy_chain(&q->filter_list);
+ q->perturb_period = 0;
+ del_timer_sync(&q->perturb_timer);
+ sfq_free(q->ht);
+}
+
static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
{
struct sfq_sched_data *q = qdisc_priv(sch);
- size_t sz;
int i;
q->perturb_timer.function = sfq_perturbation;
q->cur_depth = 0;
q->tail = NULL;
q->divisor = SFQ_DEFAULT_HASH_DIVISOR;
- if (opt == NULL) {
- q->quantum = psched_mtu(qdisc_dev(sch));
- q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
- q->perturb_period = 0;
- q->perturbation = net_random();
- } else {
+ q->quantum = psched_mtu(qdisc_dev(sch));
+ q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
+ q->perturb_period = 0;
+ q->perturbation = net_random();
+
+ if (opt) {
int err = sfq_change(sch, opt);
if (err)
return err;
}
- sz = sizeof(q->ht[0]) * q->divisor;
- q->ht = kmalloc(sz, GFP_KERNEL);
- if (!q->ht && sz > PAGE_SIZE)
- q->ht = vmalloc(sz);
- if (!q->ht)
+ q->ht = sfq_alloc(sizeof(q->ht[0]) * q->divisor);
+ if (!q->ht) {
+ sfq_destroy(sch);
return -ENOMEM;
+ }
for (i = 0; i < q->divisor; i++)
q->ht[i] = SFQ_EMPTY_SLOT;
return 0;
}
-static void sfq_destroy(struct Qdisc *sch)
-{
- struct sfq_sched_data *q = qdisc_priv(sch);
-
- tcf_destroy_chain(&q->filter_list);
- q->perturb_period = 0;
- del_timer_sync(&q->perturb_timer);
- if (is_vmalloc_addr(q->ht))
- vfree(q->ht);
- else
- kfree(q->ht);
-}
-
static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct nlattr *nest;
struct tc_tbf_qopt opt;
+ sch->qstats.backlog = q->qdisc->qstats.backlog;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
static int
-__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev)
+__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
+ struct net_device *dev, struct netdev_queue *txq,
+ struct neighbour *mn)
{
- struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0);
- struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc);
- struct neighbour *mn = dst_get_neighbour(skb_dst(skb));
+ struct teql_sched_data *q = qdisc_priv(txq->qdisc);
struct neighbour *n = q->ncache;
if (mn->tbl == NULL)
}
static inline int teql_resolve(struct sk_buff *skb,
- struct sk_buff *skb_res, struct net_device *dev)
+ struct sk_buff *skb_res,
+ struct net_device *dev,
+ struct netdev_queue *txq)
{
- struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
+ struct dst_entry *dst = skb_dst(skb);
+ struct neighbour *mn;
+ int res;
+
if (txq->qdisc == &noop_qdisc)
return -ENODEV;
- if (dev->header_ops == NULL ||
- skb_dst(skb) == NULL ||
- dst_get_neighbour(skb_dst(skb)) == NULL)
+ if (!dev->header_ops || !dst)
return 0;
- return __teql_resolve(skb, skb_res, dev);
+
+ rcu_read_lock();
+ mn = dst_get_neighbour_noref(dst);
+ res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0;
+ rcu_read_unlock();
+
+ return res;
}
static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
if (slave_txq->qdisc_sleeping != q)
continue;
- if (__netif_subqueue_stopped(slave, subq) ||
+ if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) ||
!netif_running(slave)) {
busy = 1;
continue;
}
- switch (teql_resolve(skb, skb_res, slave)) {
+ switch (teql_resolve(skb, skb_res, slave, slave_txq)) {
case 0:
if (__netif_tx_trylock(slave_txq)) {
unsigned int length = qdisc_pkt_len(skb);
- if (!netif_tx_queue_frozen_or_stopped(slave_txq) &&
+ if (!netif_xmit_frozen_or_stopped(slave_txq) &&
slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
txq_trans_update(slave_txq);
__netif_tx_unlock(slave_txq);
}
__netif_tx_unlock(slave_txq);
}
- if (netif_queue_stopped(dev))
+ if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)))
busy = 1;
break;
case 1:
asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0;
asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay;
asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
- (unsigned long)sp->autoclose * HZ;
+ min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ;
/* Initializes the timers */
for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)
struct sctp_auth_bytes *key;
/* Verify that we are not going to overflow INT_MAX */
- if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes))
+ if (key_len > (INT_MAX - sizeof(struct sctp_auth_bytes)))
return NULL;
/* Allocate the shared key */
struct sctp_input_cb {
union {
struct inet_skb_parm h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct inet6_skb_parm h6;
#endif
} header;
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
addr->a.v6.sin6_port = 0;
- ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifa->addr);
+ addr->a.v6.sin6_addr = ifa->addr;
addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
addr->valid = 1;
spin_lock_bh(&sctp_local_addr_lock);
/* Fill in the dest address from the route entry passed with the skb
* and the source address from the transport.
*/
- ipv6_addr_copy(&fl6.daddr, &transport->ipaddr.v6.sin6_addr);
- ipv6_addr_copy(&fl6.saddr, &transport->saddr.v6.sin6_addr);
+ fl6.daddr = transport->ipaddr.v6.sin6_addr;
+ fl6.saddr = transport->saddr.v6.sin6_addr;
fl6.flowlabel = np->flow_label;
IP6_ECN_flow_xmit(sk, fl6.flowlabel);
if (np->opt && np->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
- ipv6_addr_copy(&fl6.daddr, rt0->addr);
+ fl6.daddr = *rt0->addr;
}
SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n",
sctp_scope_t scope;
memset(fl6, 0, sizeof(struct flowi6));
- ipv6_addr_copy(&fl6->daddr, &daddr->v6.sin6_addr);
+ fl6->daddr = daddr->v6.sin6_addr;
fl6->fl6_dport = daddr->v6.sin6_port;
fl6->flowi6_proto = IPPROTO_SCTP;
if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
fl6->fl6_sport = htons(asoc->base.bind_addr.port);
if (saddr) {
- ipv6_addr_copy(&fl6->saddr, &saddr->v6.sin6_addr);
+ fl6->saddr = saddr->v6.sin6_addr;
fl6->fl6_sport = saddr->v6.sin6_port;
SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr);
}
}
rcu_read_unlock();
if (baddr) {
- ipv6_addr_copy(&fl6->saddr, &baddr->v6.sin6_addr);
+ fl6->saddr = baddr->v6.sin6_addr;
fl6->fl6_sport = baddr->v6.sin6_port;
dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
}
if (t->dst) {
saddr->v6.sin6_family = AF_INET6;
- ipv6_addr_copy(&saddr->v6.sin6_addr, &fl6->saddr);
+ saddr->v6.sin6_addr = fl6->saddr;
}
}
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
addr->a.v6.sin6_port = 0;
- ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifp->addr);
+ addr->a.v6.sin6_addr = ifp->addr;
addr->a.v6.sin6_scope_id = dev->ifindex;
addr->valid = 1;
INIT_LIST_HEAD(&addr->list);
static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
int is_saddr)
{
- void *from;
__be16 *port;
struct sctphdr *sh;
sh = sctp_hdr(skb);
if (is_saddr) {
*port = sh->source;
- from = &ipv6_hdr(skb)->saddr;
+ addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
} else {
*port = sh->dest;
- from = &ipv6_hdr(skb)->daddr;
+ addr->v6.sin6_addr = ipv6_hdr(skb)->daddr;
}
- ipv6_addr_copy(&addr->v6.sin6_addr, from);
}
/* Initialize an sctp_addr from a socket. */
{
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = 0;
- ipv6_addr_copy(&addr->v6.sin6_addr, &inet6_sk(sk)->rcv_saddr);
+ addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr;
}
/* Initialize sk->sk_rcv_saddr from sctp_addr. */
inet6_sk(sk)->rcv_saddr.s6_addr32[3] =
addr->v4.sin_addr.s_addr;
} else {
- ipv6_addr_copy(&inet6_sk(sk)->rcv_saddr, &addr->v6.sin6_addr);
+ inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr;
}
}
inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff);
inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
} else {
- ipv6_addr_copy(&inet6_sk(sk)->daddr, &addr->v6.sin6_addr);
+ inet6_sk(sk)->daddr = addr->v6.sin6_addr;
}
}
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_port = port;
addr->v6.sin6_flowinfo = 0; /* BUG */
- ipv6_addr_copy(&addr->v6.sin6_addr, ¶m->v6.addr);
+ addr->v6.sin6_addr = param->v6.addr;
addr->v6.sin6_scope_id = iif;
}
param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS;
param->v6.param_hdr.length = htons(length);
- ipv6_addr_copy(¶m->v6.addr, &addr->v6.sin6_addr);
+ param->v6.addr = addr->v6.sin6_addr;
return length;
}
{
addr->sa.sa_family = AF_INET6;
addr->v6.sin6_port = port;
- ipv6_addr_copy(&addr->v6.sin6_addr, saddr);
+ addr->v6.sin6_addr = *saddr;
}
/* Compare addresses exactly.
}
sin6from = &asoc->peer.primary_addr.v6;
- ipv6_addr_copy(&sin6->sin6_addr, &sin6from->sin6_addr);
+ sin6->sin6_addr = sin6from->sin6_addr;
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin6->sin6_scope_id = sin6from->sin6_scope_id;
}
}
/* Otherwise, just copy the v6 address. */
- ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
+ sin6->sin6_addr = ipv6_hdr(skb)->saddr;
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) {
struct sctp_ulpevent *ev = sctp_skb2event(skb);
sin6->sin6_scope_id = ev->iif;
/* Keep track of how many bytes are in flight to the receiver. */
asoc->outqueue.outstanding_bytes += datasize;
- /* Update our view of the receiver's rwnd. Include sk_buff overhead
- * while updating peer.rwnd so that it reduces the chances of a
- * receiver running out of receive buffer space even when receive
- * window is still open. This can happen when a sender is sending
- * sending small messages.
- */
- datasize += sizeof(struct sk_buff);
+ /* Update our view of the receiver's rwnd. */
if (datasize < rwnd)
rwnd -= datasize;
else
chunk->transport->flight_size -=
sctp_data_size(chunk);
q->outstanding_bytes -= sctp_data_size(chunk);
- q->asoc->peer.rwnd += (sctp_data_size(chunk) +
- sizeof(struct sk_buff));
+ q->asoc->peer.rwnd += sctp_data_size(chunk);
}
continue;
}
* (Section 7.2.4)), add the data size of those
* chunks to the rwnd.
*/
- q->asoc->peer.rwnd += (sctp_data_size(chunk) +
- sizeof(struct sk_buff));
+ q->asoc->peer.rwnd += sctp_data_size(chunk);
q->outstanding_bytes -= sctp_data_size(chunk);
if (chunk->transport)
transport->flight_size -= sctp_data_size(chunk);
" for cmd %d at entry %p\n", &sctp_addr_waitq, &addrw->a, addrw->state,
addrw);
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/* Now we send an ASCONF for each association */
/* Note. we currently don't handle link local IPv6 addressees */
if (addrw->a.sa.sa_family == AF_INET6) {
sctp_max_instreams = SCTP_DEFAULT_INSTREAMS;
sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS;
+ /* Initialize maximum autoclose timeout. */
+ sctp_max_autoclose = INT_MAX / HZ;
+
/* Initialize handle used for association ids. */
idr_init(&sctp_assocs_id);
asconf_len -= length;
}
- if (no_err && asoc->src_out_of_asoc_ok)
+ if (no_err && asoc->src_out_of_asoc_ok) {
asoc->src_out_of_asoc_ok = 0;
+ sctp_transport_immediate_rtx(asoc->peer.primary_path);
+ }
/* Free the cached last sent asconf chunk. */
list_del_init(&asconf->transmitted_list);
struct sctp_chunk *chunk)
{
sctp_sender_hb_info_t *hbinfo;
+ int was_unconfirmed = 0;
/* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the
* HEARTBEAT should clear the error counter of the destination
/* Mark the destination transport address as active if it is not so
* marked.
*/
- if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED))
+ if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED)) {
+ was_unconfirmed = 1;
sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP,
SCTP_HEARTBEAT_SUCCESS);
+ }
/* The receiver of the HEARTBEAT ACK should also perform an
* RTT measurement for that destination transport address
/* Update the heartbeat timer. */
if (!mod_timer(&t->hb_timer, sctp_transport_timeout(t)))
sctp_transport_hold(t);
+
+ if (was_unconfirmed && asoc->peer.transport_count == 1)
+ sctp_transport_immediate_rtx(t);
}
struct sockaddr_in6 *sin6;
sin6 = (struct sockaddr_in6 *)addrs;
- ipv6_addr_copy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr);
+ asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr;
}
SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ",
" at %p\n", asoc, asoc->asconf_addr_del_pending,
return -EINVAL;
if (copy_from_user(&sp->autoclose, optval, optlen))
return -EFAULT;
- /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */
- sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ);
return 0;
}
.sockets_allocated = &sctp_sockets_allocated,
};
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct proto sctpv6_prot = {
.name = "SCTPv6",
.memory_allocated = &sctp_memory_allocated,
.sockets_allocated = &sctp_sockets_allocated,
};
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
static int sack_timer_max = 500;
static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
static int rwnd_scale_max = 16;
+static unsigned long max_autoclose_min = 0;
+static unsigned long max_autoclose_max =
+ (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
+ ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
extern long sysctl_sctp_mem[3];
extern int sysctl_sctp_rmem[3];
.extra1 = &one,
.extra2 = &rwnd_scale_max,
},
+ {
+ .procname = "max_autoclose",
+ .data = &sctp_max_autoclose,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = &proc_doulongvec_minmax,
+ .extra1 = &max_autoclose_min,
+ .extra2 = &max_autoclose_max,
+ },
{ /* sentinel */ }
};
t->cacc.next_tsn_at_change = 0;
t->cacc.cacc_saw_newack = 0;
}
+
+/* Schedule retransmission on the given transport */
+void sctp_transport_immediate_rtx(struct sctp_transport *t)
+{
+ /* Stop pending T3_rtx_timer */
+ if (timer_pending(&t->T3_rtx_timer)) {
+ (void)del_timer(&t->T3_rtx_timer);
+ sctp_transport_put(t);
+ }
+ sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX);
+ if (!timer_pending(&t->T3_rtx_timer)) {
+ if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto))
+ sctp_transport_hold(t);
+ }
+ return;
+}
sock_update_classid(sock->sk);
+ sock_update_netprioidx(sock->sk);
+
si->sock = sock;
si->scm = NULL;
si->msg = msg;
case ETHTOOL_GRXRINGS:
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
+ case ETHTOOL_SRXCLSRLINS:
convert_out = true;
/* fall through */
case ETHTOOL_SRXCLSRLDEL:
- case ETHTOOL_SRXCLSRLINS:
buf_size += sizeof(struct ethtool_rxnfc);
convert_in = true;
break;
#include <linux/slab.h>
#include <linux/export.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
char *buf, const int buflen)
return len;
}
-#else /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+#else /* !IS_ENABLED(CONFIG_IPV6) */
static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
char *buf, const int buflen)
return 0;
}
-#endif /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+#endif /* !IS_ENABLED(CONFIG_IPV6) */
static int rpc_ntop4(const struct sockaddr *sap,
char *buf, const size_t buflen)
return sizeof(struct sockaddr_in);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static int rpc_parse_scope_id(const char *buf, const size_t buflen,
const char *delim, struct sockaddr_in6 *sin6)
{
task->tk_ops->rpc_call_prepare(task, task->tk_calldata);
}
+static void
+rpc_init_task_statistics(struct rpc_task *task)
+{
+ /* Initialize retry counters */
+ task->tk_garb_retry = 2;
+ task->tk_cred_retry = 2;
+ task->tk_rebind_retry = 2;
+
+ /* starting timestamp */
+ task->tk_start = ktime_get();
+}
+
+static void
+rpc_reset_task_statistics(struct rpc_task *task)
+{
+ task->tk_timeouts = 0;
+ task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_KILLED|RPC_TASK_SENT);
+
+ rpc_init_task_statistics(task);
+}
+
/*
* Helper that calls task->tk_ops->rpc_call_done if it exists
*/
WARN_ON(RPC_ASSASSINATED(task));
/* Always release the RPC slot and buffer memory */
xprt_release(task);
+ rpc_reset_task_statistics(task);
}
}
}
task->tk_calldata = task_setup_data->callback_data;
INIT_LIST_HEAD(&task->tk_task);
- /* Initialize retry counters */
- task->tk_garb_retry = 2;
- task->tk_cred_retry = 2;
- task->tk_rebind_retry = 2;
-
task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW;
task->tk_owner = current->tgid;
if (task->tk_ops->rpc_call_prepare != NULL)
task->tk_action = rpc_prepare_task;
- /* starting timestamp */
- task->tk_start = ktime_get();
+ rpc_init_task_statistics(task);
dprintk("RPC: new task initialized, procpid %u\n",
task_pid_nr(current));
return error;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/*
* Register an "inet6" protocol family netid with the local
* rpcbind daemon via an rpcbind v4 SET request.
return error;
}
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
/*
* Register a kernel RPC service via rpcbind version 4.
error = __svc_rpcb_register4(program, version,
protocol, port);
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
error = __svc_rpcb_register6(program, version,
protocol, port);
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
}
if (error < 0)
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
struct sockaddr_in6 sin6 = {
.sin6_family = AF_INET6,
.sin6_addr = IN6ADDR_ANY_INIT,
.sin6_port = htons(port),
};
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
struct sockaddr *sap;
size_t len;
sap = (struct sockaddr *)&sin;
len = sizeof(sin);
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
sap = (struct sockaddr *)&sin6;
len = sizeof(sin6);
break;
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
default:
return ERR_PTR(-EAFNOSUPPORT);
}
struct ip_map *item = container_of(citem, struct ip_map, h);
strcpy(new->m_class, item->m_class);
- ipv6_addr_copy(&new->m_addr, &item->m_addr);
+ new->m_addr = item->m_addr;
}
static void update(struct cache_head *cnew, struct cache_head *citem)
{
ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr,
&sin6.sin6_addr);
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
memcpy(&sin6, &address.s6, sizeof(sin6));
break;
}
im = container_of(h, struct ip_map, h);
/* class addr domain */
- ipv6_addr_copy(&addr, &im->m_addr);
+ addr = im->m_addr;
if (test_bit(CACHE_VALID, &h->flags) &&
!test_bit(CACHE_NEGATIVE, &h->flags))
struct cache_head *ch;
strcpy(ip.m_class, class);
- ipv6_addr_copy(&ip.m_addr, addr);
+ ip.m_addr = *addr;
ch = sunrpc_cache_lookup(cd, &ip.h,
hash_str(class, IP_HASHBITS) ^
hash_ip6(*addr));
cmh->cmsg_level = SOL_IPV6;
cmh->cmsg_type = IPV6_PKTINFO;
pki->ipi6_ifindex = daddr->sin6_scope_id;
- ipv6_addr_copy(&pki->ipi6_addr, &daddr->sin6_addr);
+ pki->ipi6_addr = daddr->sin6_addr;
cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
}
break;
return 0;
daddr->sin6_family = AF_INET6;
- ipv6_addr_copy(&daddr->sin6_addr, &pki->ipi6_addr);
+ daddr->sin6_addr = pki->ipi6_addr;
daddr->sin6_scope_id = pki->ipi6_ifindex;
return 1;
}
static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
- if (xprt_dynamic_free_slot(xprt, req))
- return;
-
- memset(req, 0, sizeof(*req)); /* mark unused */
-
spin_lock(&xprt->reserve_lock);
- list_add(&req->rq_list, &xprt->free);
+ if (!xprt_dynamic_free_slot(xprt, req)) {
+ memset(req, 0, sizeof(*req)); /* mark unused */
+ list_add(&req->rq_list, &xprt->free);
+ }
rpc_wake_up_next(&xprt->backlog);
spin_unlock(&xprt->reserve_lock);
}
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
- int ret = 0;
+ int ret = -EAGAIN;
dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
task->tk_pid, req->rq_slen - req->rq_bytes_sent,
/* Don't race with disconnect */
if (xprt_connected(xprt)) {
if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
- ret = -EAGAIN;
/*
* Notify TCP that we're limited by the application
* window size
int err;
err = xs_init_anyaddr(args->dstaddr->sa_family,
(struct sockaddr *)&new->srcaddr);
- if (err != 0)
+ if (err != 0) {
+ xprt_free(xprt);
return ERR_PTR(err);
+ }
}
return xprt;
#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */
/**
- * struct bcbearer_pair - a pair of bearers used by broadcast link
+ * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link
* @primary: pointer to primary bearer
* @secondary: pointer to secondary bearer
*
* to be paired.
*/
-struct bcbearer_pair {
+struct tipc_bcbearer_pair {
struct tipc_bearer *primary;
struct tipc_bearer *secondary;
};
/**
- * struct bcbearer - bearer used by broadcast link
+ * struct tipc_bcbearer - bearer used by broadcast link
* @bearer: (non-standard) broadcast bearer structure
* @media: (non-standard) broadcast media structure
* @bpairs: array of bearer pairs
* prevented through use of the spinlock "bc_lock".
*/
-struct bcbearer {
+struct tipc_bcbearer {
struct tipc_bearer bearer;
- struct media media;
- struct bcbearer_pair bpairs[MAX_BEARERS];
- struct bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1];
+ struct tipc_media media;
+ struct tipc_bcbearer_pair bpairs[MAX_BEARERS];
+ struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1];
struct tipc_node_map remains;
struct tipc_node_map remains_new;
};
/**
- * struct bclink - link used for broadcast messages
+ * struct tipc_bclink - link used for broadcast messages
* @link: (non-standard) broadcast link structure
* @node: (non-standard) node structure representing b'cast link's peer node
+ * @bcast_nodes: map of broadcast-capable nodes
* @retransmit_to: node that most recently requested a retransmit
*
* Handles sequence numbering, fragmentation, bundling, etc.
*/
-struct bclink {
- struct link link;
+struct tipc_bclink {
+ struct tipc_link link;
struct tipc_node node;
+ struct tipc_node_map bcast_nodes;
struct tipc_node *retransmit_to;
};
+static struct tipc_bcbearer bcast_bearer;
+static struct tipc_bclink bcast_link;
-static struct bcbearer *bcbearer;
-static struct bclink *bclink;
-static struct link *bcl;
-static DEFINE_SPINLOCK(bc_lock);
+static struct tipc_bcbearer *bcbearer = &bcast_bearer;
+static struct tipc_bclink *bclink = &bcast_link;
+static struct tipc_link *bcl = &bcast_link.link;
-/* broadcast-capable node map */
-struct tipc_node_map tipc_bcast_nmap;
+static DEFINE_SPINLOCK(bc_lock);
const char tipc_bclink_name[] = "broadcast-link";
struct tipc_node_map *nm_b,
struct tipc_node_map *nm_diff);
-static u32 buf_seqno(struct sk_buff *buf)
-{
- return msg_seqno(buf_msg(buf));
-}
-
static u32 bcbuf_acks(struct sk_buff *buf)
{
return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle;
bcbuf_set_acks(buf, bcbuf_acks(buf) - 1);
}
+void tipc_bclink_add_node(u32 addr)
+{
+ spin_lock_bh(&bc_lock);
+ tipc_nmap_add(&bclink->bcast_nodes, addr);
+ spin_unlock_bh(&bc_lock);
+}
+
+void tipc_bclink_remove_node(u32 addr)
+{
+ spin_lock_bh(&bc_lock);
+ tipc_nmap_remove(&bclink->bcast_nodes, addr);
+ spin_unlock_bh(&bc_lock);
+}
static void bclink_set_last_sent(void)
{
struct sk_buff *next;
unsigned int released = 0;
- if (less_eq(acked, n_ptr->bclink.acked))
- return;
-
spin_lock_bh(&bc_lock);
- /* Skip over packets that node has previously acknowledged */
-
+ /* Bail out if tx queue is empty (no clean up is required) */
crs = bcl->first_out;
+ if (!crs)
+ goto exit;
+
+ /* Determine which messages need to be acknowledged */
+ if (acked == INVALID_LINK_SEQ) {
+ /*
+ * Contact with specified node has been lost, so need to
+ * acknowledge sent messages only (if other nodes still exist)
+ * or both sent and unsent messages (otherwise)
+ */
+ if (bclink->bcast_nodes.count)
+ acked = bcl->fsm_msg_cnt;
+ else
+ acked = bcl->next_out_no;
+ } else {
+ /*
+ * Bail out if specified sequence number does not correspond
+ * to a message that has been sent and not yet acknowledged
+ */
+ if (less(acked, buf_seqno(crs)) ||
+ less(bcl->fsm_msg_cnt, acked) ||
+ less_eq(acked, n_ptr->bclink.acked))
+ goto exit;
+ }
+
+ /* Skip over packets that node has previously acknowledged */
while (crs && less_eq(buf_seqno(crs), n_ptr->bclink.acked))
crs = crs->next;
while (crs && less_eq(buf_seqno(crs), acked)) {
next = crs->next;
- bcbuf_decr_acks(crs);
+
+ if (crs != bcl->next_out)
+ bcbuf_decr_acks(crs);
+ else {
+ bcbuf_set_acks(crs, 0);
+ bcl->next_out = next;
+ bclink_set_last_sent();
+ }
+
if (bcbuf_acks(crs) == 0) {
bcl->first_out = next;
bcl->out_queue_size--;
}
if (unlikely(released && !list_empty(&bcl->waiting_ports)))
tipc_link_wakeup_ports(bcl, 0);
+exit:
spin_unlock_bh(&bc_lock);
}
static void bclink_send_ack(struct tipc_node *n_ptr)
{
- struct link *l_ptr = n_ptr->active_links[n_ptr->addr & 1];
+ struct tipc_link *l_ptr = n_ptr->active_links[n_ptr->addr & 1];
if (l_ptr != NULL)
tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
spin_lock_bh(&bc_lock);
+ if (!bclink->bcast_nodes.count) {
+ res = msg_data_sz(buf_msg(buf));
+ buf_discard(buf);
+ goto exit;
+ }
+
res = tipc_link_send_buf(bcl, buf);
- if (likely(res > 0))
+ if (likely(res >= 0)) {
bclink_set_last_sent();
-
- bcl->stats.queue_sz_counts++;
- bcl->stats.accu_queue_sz += bcl->out_queue_size;
-
+ bcl->stats.queue_sz_counts++;
+ bcl->stats.accu_queue_sz += bcl->out_queue_size;
+ }
+exit:
spin_unlock_bh(&bc_lock);
return res;
}
if (likely(!msg_non_seq(buf_msg(buf)))) {
struct tipc_msg *msg;
- bcbuf_set_acks(buf, tipc_bcast_nmap.count);
+ bcbuf_set_acks(buf, bclink->bcast_nodes.count);
msg = buf_msg(buf);
msg_set_non_seq(msg, 1);
msg_set_mc_netid(msg, tipc_net_id);
bcl->stats.sent_info++;
- if (WARN_ON(!tipc_bcast_nmap.count)) {
+ if (WARN_ON(!bclink->bcast_nodes.count)) {
dump_stack();
return 0;
}
/* Send buffer over bearers until all targets reached */
- bcbearer->remains = tipc_bcast_nmap;
+ bcbearer->remains = bclink->bcast_nodes;
for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) {
struct tipc_bearer *p = bcbearer->bpairs[bp_index].primary;
void tipc_bcbearer_sort(void)
{
- struct bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
- struct bcbearer_pair *bp_curr;
+ struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
+ struct tipc_bcbearer_pair *bp_curr;
int b_index;
int pri;
return 0;
}
-int tipc_bclink_init(void)
+void tipc_bclink_init(void)
{
- bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC);
- bclink = kzalloc(sizeof(*bclink), GFP_ATOMIC);
- if (!bcbearer || !bclink) {
- warn("Broadcast link creation failed, no memory\n");
- kfree(bcbearer);
- bcbearer = NULL;
- kfree(bclink);
- bclink = NULL;
- return -ENOMEM;
- }
-
INIT_LIST_HEAD(&bcbearer->bearer.cong_links);
bcbearer->bearer.media = &bcbearer->media;
bcbearer->media.send_msg = tipc_bcbearer_send;
sprintf(bcbearer->media.name, "tipc-broadcast");
- bcl = &bclink->link;
INIT_LIST_HEAD(&bcl->waiting_ports);
bcl->next_out_no = 1;
spin_lock_init(&bclink->node.lock);
bcl->b_ptr = &bcbearer->bearer;
bcl->state = WORKING_WORKING;
strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
-
- return 0;
}
void tipc_bclink_stop(void)
{
spin_lock_bh(&bc_lock);
- if (bcbearer) {
- tipc_link_stop(bcl);
- bcl = NULL;
- kfree(bclink);
- bclink = NULL;
- kfree(bcbearer);
- bcbearer = NULL;
- }
+ tipc_link_stop(bcl);
spin_unlock_bh(&bc_lock);
+
+ memset(bclink, 0, sizeof(*bclink));
+ memset(bcbearer, 0, sizeof(*bcbearer));
}
* tipc_port_list_add - add a port to a port list, ensuring no duplicates
*/
-void tipc_port_list_add(struct port_list *pl_ptr, u32 port)
+void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port)
{
- struct port_list *item = pl_ptr;
+ struct tipc_port_list *item = pl_ptr;
int i;
int item_sz = PLSIZE;
int cnt = pl_ptr->count;
*
*/
-void tipc_port_list_free(struct port_list *pl_ptr)
+void tipc_port_list_free(struct tipc_port_list *pl_ptr)
{
- struct port_list *item;
- struct port_list *next;
+ struct tipc_port_list *item;
+ struct tipc_port_list *next;
for (item = pl_ptr->next; item; item = next) {
next = item->next;
u32 map[MAX_NODES / WSIZE];
};
-extern struct tipc_node_map tipc_bcast_nmap;
-
#define PLSIZE 32
/**
- * struct port_list - set of node local destination ports
+ * struct tipc_port_list - set of node local destination ports
* @count: # of ports in set (only valid for first entry in list)
* @next: pointer to next entry in list
* @ports: array of port references
*/
-struct port_list {
+struct tipc_port_list {
int count;
- struct port_list *next;
+ struct tipc_port_list *next;
u32 ports[PLSIZE];
};
return !memcmp(nm_a, nm_b, sizeof(*nm_a));
}
-void tipc_port_list_add(struct port_list *pl_ptr, u32 port);
-void tipc_port_list_free(struct port_list *pl_ptr);
+void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port);
+void tipc_port_list_free(struct tipc_port_list *pl_ptr);
-int tipc_bclink_init(void);
+void tipc_bclink_init(void);
void tipc_bclink_stop(void);
+void tipc_bclink_add_node(u32 addr);
+void tipc_bclink_remove_node(u32 addr);
struct tipc_node *tipc_bclink_retransmit_to(void);
void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked);
int tipc_bclink_send_msg(struct sk_buff *buf);
#define MAX_ADDR_STR 32
-static struct media media_list[MAX_MEDIA];
+static struct tipc_media *media_list[MAX_MEDIA];
static u32 media_count;
struct tipc_bearer tipc_bearers[MAX_BEARERS];
}
/**
- * media_find - locates specified media object by name
+ * tipc_media_find - locates specified media object by name
*/
-static struct media *media_find(const char *name)
+struct tipc_media *tipc_media_find(const char *name)
{
- struct media *m_ptr;
u32 i;
- for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) {
- if (!strcmp(m_ptr->name, name))
- return m_ptr;
+ for (i = 0; i < media_count; i++) {
+ if (!strcmp(media_list[i]->name, name))
+ return media_list[i];
+ }
+ return NULL;
+}
+
+/**
+ * media_find_id - locates specified media object by type identifier
+ */
+
+static struct tipc_media *media_find_id(u8 type)
+{
+ u32 i;
+
+ for (i = 0; i < media_count; i++) {
+ if (media_list[i]->type_id == type)
+ return media_list[i];
}
return NULL;
}
* Bearers for this media type must be activated separately at a later stage.
*/
-int tipc_register_media(u32 media_type,
- char *name,
- int (*enable)(struct tipc_bearer *),
- void (*disable)(struct tipc_bearer *),
- int (*send_msg)(struct sk_buff *,
- struct tipc_bearer *,
- struct tipc_media_addr *),
- char *(*addr2str)(struct tipc_media_addr *a,
- char *str_buf, int str_size),
- struct tipc_media_addr *bcast_addr,
- const u32 bearer_priority,
- const u32 link_tolerance, /* [ms] */
- const u32 send_window_limit)
+int tipc_register_media(struct tipc_media *m_ptr)
{
- struct media *m_ptr;
- u32 media_id;
- u32 i;
int res = -EINVAL;
write_lock_bh(&tipc_net_lock);
- if (tipc_mode != TIPC_NET_MODE) {
- warn("Media <%s> rejected, not in networked mode yet\n", name);
+ if (!media_name_valid(m_ptr->name))
goto exit;
- }
- if (!media_name_valid(name)) {
- warn("Media <%s> rejected, illegal name\n", name);
+ if ((m_ptr->bcast_addr.media_id != m_ptr->type_id) ||
+ !m_ptr->bcast_addr.broadcast)
goto exit;
- }
- if (!bcast_addr) {
- warn("Media <%s> rejected, no broadcast address\n", name);
+ if (m_ptr->priority > TIPC_MAX_LINK_PRI)
goto exit;
- }
- if ((bearer_priority < TIPC_MIN_LINK_PRI) ||
- (bearer_priority > TIPC_MAX_LINK_PRI)) {
- warn("Media <%s> rejected, illegal priority (%u)\n", name,
- bearer_priority);
+ if ((m_ptr->tolerance < TIPC_MIN_LINK_TOL) ||
+ (m_ptr->tolerance > TIPC_MAX_LINK_TOL))
goto exit;
- }
- if ((link_tolerance < TIPC_MIN_LINK_TOL) ||
- (link_tolerance > TIPC_MAX_LINK_TOL)) {
- warn("Media <%s> rejected, illegal tolerance (%u)\n", name,
- link_tolerance);
+ if (media_count >= MAX_MEDIA)
goto exit;
- }
-
- media_id = media_count++;
- if (media_id >= MAX_MEDIA) {
- warn("Media <%s> rejected, media limit reached (%u)\n", name,
- MAX_MEDIA);
- media_count--;
+ if (tipc_media_find(m_ptr->name) || media_find_id(m_ptr->type_id))
goto exit;
- }
- for (i = 0; i < media_id; i++) {
- if (media_list[i].type_id == media_type) {
- warn("Media <%s> rejected, duplicate type (%u)\n", name,
- media_type);
- media_count--;
- goto exit;
- }
- if (!strcmp(name, media_list[i].name)) {
- warn("Media <%s> rejected, duplicate name\n", name);
- media_count--;
- goto exit;
- }
- }
- m_ptr = &media_list[media_id];
- m_ptr->type_id = media_type;
- m_ptr->send_msg = send_msg;
- m_ptr->enable_bearer = enable;
- m_ptr->disable_bearer = disable;
- m_ptr->addr2str = addr2str;
- memcpy(&m_ptr->bcast_addr, bcast_addr, sizeof(*bcast_addr));
- strcpy(m_ptr->name, name);
- m_ptr->priority = bearer_priority;
- m_ptr->tolerance = link_tolerance;
- m_ptr->window = send_window_limit;
+ media_list[media_count] = m_ptr;
+ media_count++;
res = 0;
exit:
write_unlock_bh(&tipc_net_lock);
+ if (res)
+ warn("Media <%s> registration error\n", m_ptr->name);
return res;
}
void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a)
{
- struct media *m_ptr;
- u32 media_type;
- u32 i;
+ char addr_str[MAX_ADDR_STR];
+ struct tipc_media *m_ptr;
- media_type = ntohl(a->type);
- for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) {
- if (m_ptr->type_id == media_type)
- break;
- }
-
- if ((i < media_count) && (m_ptr->addr2str != NULL)) {
- char addr_str[MAX_ADDR_STR];
+ m_ptr = media_find_id(a->media_id);
- tipc_printf(pb, "%s(%s)", m_ptr->name,
- m_ptr->addr2str(a, addr_str, sizeof(addr_str)));
- } else {
- unchar *addr = (unchar *)&a->dev_addr;
+ if (m_ptr && !m_ptr->addr2str(a, addr_str, sizeof(addr_str)))
+ tipc_printf(pb, "%s(%s)", m_ptr->name, addr_str);
+ else {
+ u32 i;
- tipc_printf(pb, "UNKNOWN(%u)", media_type);
- for (i = 0; i < (sizeof(*a) - sizeof(a->type)); i++)
- tipc_printf(pb, "-%02x", addr[i]);
+ tipc_printf(pb, "UNKNOWN(%u)", a->media_id);
+ for (i = 0; i < sizeof(a->value); i++)
+ tipc_printf(pb, "-%02x", a->value[i]);
}
}
struct sk_buff *tipc_media_get_names(void)
{
struct sk_buff *buf;
- struct media *m_ptr;
int i;
buf = tipc_cfg_reply_alloc(MAX_MEDIA * TLV_SPACE(TIPC_MAX_MEDIA_NAME));
return NULL;
read_lock_bh(&tipc_net_lock);
- for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) {
- tipc_cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME, m_ptr->name,
- strlen(m_ptr->name) + 1);
+ for (i = 0; i < media_count; i++) {
+ tipc_cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME,
+ media_list[i]->name,
+ strlen(media_list[i]->name) + 1);
}
read_unlock_bh(&tipc_net_lock);
return buf;
*/
static int bearer_name_validate(const char *name,
- struct bearer_name *name_parts)
+ struct tipc_bearer_names *name_parts)
{
char name_copy[TIPC_MAX_BEARER_NAME];
char *media_name;
}
/**
- * bearer_find - locates bearer object with matching bearer name
+ * tipc_bearer_find - locates bearer object with matching bearer name
*/
-static struct tipc_bearer *bearer_find(const char *name)
+struct tipc_bearer *tipc_bearer_find(const char *name)
{
struct tipc_bearer *b_ptr;
u32 i;
struct sk_buff *tipc_bearer_get_names(void)
{
struct sk_buff *buf;
- struct media *m_ptr;
struct tipc_bearer *b_ptr;
int i, j;
return NULL;
read_lock_bh(&tipc_net_lock);
- for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) {
+ for (i = 0; i < media_count; i++) {
for (j = 0; j < MAX_BEARERS; j++) {
b_ptr = &tipc_bearers[j];
- if (b_ptr->active && (b_ptr->media == m_ptr)) {
+ if (b_ptr->active && (b_ptr->media == media_list[i])) {
tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME,
b_ptr->name,
strlen(b_ptr->name) + 1);
static int bearer_push(struct tipc_bearer *b_ptr)
{
u32 res = 0;
- struct link *ln, *tln;
+ struct tipc_link *ln, *tln;
if (b_ptr->blocked)
return 0;
* bearer.lock is busy
*/
-static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr, struct link *l_ptr)
+static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr,
+ struct tipc_link *l_ptr)
{
list_move_tail(&l_ptr->link_list, &b_ptr->cong_links);
}
* bearer.lock is free
*/
-void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct link *l_ptr)
+void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr)
{
spin_lock_bh(&b_ptr->lock);
tipc_bearer_schedule_unlocked(b_ptr, l_ptr);
* and if there is, try to resolve it before returning.
* 'tipc_net_lock' is read_locked when this function is called
*/
-int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, struct link *l_ptr)
+int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr,
+ struct tipc_link *l_ptr)
{
int res = 1;
* tipc_bearer_congested - determines if bearer is currently congested
*/
-int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct link *l_ptr)
+int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr)
{
if (unlikely(b_ptr->blocked))
return 1;
int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
{
struct tipc_bearer *b_ptr;
- struct media *m_ptr;
- struct bearer_name b_name;
+ struct tipc_media *m_ptr;
+ struct tipc_bearer_names b_names;
char addr_string[16];
u32 bearer_id;
u32 with_this_prio;
name);
return -ENOPROTOOPT;
}
- if (!bearer_name_validate(name, &b_name)) {
+ if (!bearer_name_validate(name, &b_names)) {
warn("Bearer <%s> rejected, illegal name\n", name);
return -EINVAL;
}
write_lock_bh(&tipc_net_lock);
- m_ptr = media_find(b_name.media_name);
+ m_ptr = tipc_media_find(b_names.media_name);
if (!m_ptr) {
warn("Bearer <%s> rejected, media <%s> not registered\n", name,
- b_name.media_name);
+ b_names.media_name);
goto exit;
}
b_ptr->identity = bearer_id;
b_ptr->media = m_ptr;
+ b_ptr->tolerance = m_ptr->tolerance;
+ b_ptr->window = m_ptr->window;
b_ptr->net_plane = bearer_id + 'A';
b_ptr->active = 1;
b_ptr->priority = priority;
int tipc_block_bearer(const char *name)
{
struct tipc_bearer *b_ptr = NULL;
- struct link *l_ptr;
- struct link *temp_l_ptr;
+ struct tipc_link *l_ptr;
+ struct tipc_link *temp_l_ptr;
read_lock_bh(&tipc_net_lock);
- b_ptr = bearer_find(name);
+ b_ptr = tipc_bearer_find(name);
if (!b_ptr) {
warn("Attempt to block unknown bearer <%s>\n", name);
read_unlock_bh(&tipc_net_lock);
static void bearer_disable(struct tipc_bearer *b_ptr)
{
- struct link *l_ptr;
- struct link *temp_l_ptr;
+ struct tipc_link *l_ptr;
+ struct tipc_link *temp_l_ptr;
info("Disabling bearer <%s>\n", b_ptr->name);
spin_lock_bh(&b_ptr->lock);
int res;
write_lock_bh(&tipc_net_lock);
- b_ptr = bearer_find(name);
+ b_ptr = tipc_bearer_find(name);
if (b_ptr == NULL) {
warn("Attempt to disable unknown bearer <%s>\n", name);
res = -EINVAL;
#define MAX_BEARERS 2
#define MAX_MEDIA 2
+/*
+ * Identifiers associated with TIPC message header media address info
+ *
+ * - address info field is 20 bytes long
+ * - media type identifier located at offset 3
+ * - remaining bytes vary according to media type
+ */
+
+#define TIPC_MEDIA_ADDR_SIZE 20
+#define TIPC_MEDIA_TYPE_OFFSET 3
+
/*
* Identifiers of supported TIPC media types
*/
#define TIPC_MEDIA_TYPE_ETH 1
/*
- * Destination address structure used by TIPC bearers when sending messages
- *
- * IMPORTANT: The fields of this structure MUST be stored using the specified
- * byte order indicated below, as the structure is exchanged between nodes
- * as part of a link setup process.
+ * struct tipc_media_addr - destination address used by TIPC bearers
+ * @value: address info (format defined by media)
+ * @media_id: TIPC media type identifier
+ * @broadcast: non-zero if address is a broadcast address
*/
+
struct tipc_media_addr {
- __be32 type; /* bearer type (network byte order) */
- union {
- __u8 eth_addr[6]; /* 48 bit Ethernet addr (byte array) */
- } dev_addr;
+ u8 value[TIPC_MEDIA_ADDR_SIZE];
+ u8 media_id;
+ u8 broadcast;
};
struct tipc_bearer;
/**
- * struct media - TIPC media information available to internal users
+ * struct tipc_media - TIPC media information available to internal users
* @send_msg: routine which handles buffer transmission
* @enable_bearer: routine which enables a bearer
* @disable_bearer: routine which disables a bearer
- * @addr2str: routine which converts bearer's address to string form
+ * @addr2str: routine which converts media address to string
+ * @str2addr: routine which converts media address from string
+ * @addr2msg: routine which converts media address to protocol message area
+ * @msg2addr: routine which converts media address from protocol message area
* @bcast_addr: media address used in broadcasting
* @priority: default link (and bearer) priority
* @tolerance: default time (in ms) before declaring link failure
* @name: media name
*/
-struct media {
+struct tipc_media {
int (*send_msg)(struct sk_buff *buf,
struct tipc_bearer *b_ptr,
struct tipc_media_addr *dest);
int (*enable_bearer)(struct tipc_bearer *b_ptr);
void (*disable_bearer)(struct tipc_bearer *b_ptr);
- char *(*addr2str)(struct tipc_media_addr *a,
- char *str_buf, int str_size);
+ int (*addr2str)(struct tipc_media_addr *a, char *str_buf, int str_size);
+ int (*str2addr)(struct tipc_media_addr *a, char *str_buf);
+ int (*addr2msg)(struct tipc_media_addr *a, char *msg_area);
+ int (*msg2addr)(struct tipc_media_addr *a, char *msg_area);
struct tipc_media_addr bcast_addr;
u32 priority;
u32 tolerance;
* @name: bearer name (format = media:interface)
* @media: ptr to media structure associated with bearer
* @priority: default link priority for bearer
+ * @window: default window size for bearer
+ * @tolerance: default link tolerance for bearer
* @identity: array index of this bearer within TIPC bearer array
* @link_req: ptr to (optional) structure making periodic link setup requests
* @links: list of non-congested links associated with bearer
struct tipc_media_addr addr; /* initalized by media */
char name[TIPC_MAX_BEARER_NAME];
spinlock_t lock;
- struct media *media;
+ struct tipc_media *media;
u32 priority;
+ u32 window;
+ u32 tolerance;
u32 identity;
- struct link_req *link_req;
+ struct tipc_link_req *link_req;
struct list_head links;
struct list_head cong_links;
int active;
struct tipc_node_map nodes;
};
-struct bearer_name {
+struct tipc_bearer_names {
char media_name[TIPC_MAX_MEDIA_NAME];
char if_name[TIPC_MAX_IF_NAME];
};
-struct link;
+struct tipc_link;
extern struct tipc_bearer tipc_bearers[];
/*
* TIPC routines available to supported media types
*/
-int tipc_register_media(u32 media_type,
- char *media_name, int (*enable)(struct tipc_bearer *),
- void (*disable)(struct tipc_bearer *),
- int (*send_msg)(struct sk_buff *,
- struct tipc_bearer *, struct tipc_media_addr *),
- char *(*addr2str)(struct tipc_media_addr *a,
- char *str_buf, int str_size),
- struct tipc_media_addr *bcast_addr, const u32 bearer_priority,
- const u32 link_tolerance, /* [ms] */
- const u32 send_window_limit);
+int tipc_register_media(struct tipc_media *m_ptr);
void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr);
int tipc_eth_media_start(void);
void tipc_eth_media_stop(void);
+int tipc_media_set_priority(const char *name, u32 new_value);
+int tipc_media_set_window(const char *name, u32 new_value);
void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a);
struct sk_buff *tipc_media_get_names(void);
struct sk_buff *tipc_bearer_get_names(void);
void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest);
void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest);
-void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct link *l_ptr);
+void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr);
+struct tipc_bearer *tipc_bearer_find(const char *name);
struct tipc_bearer *tipc_bearer_find_interface(const char *if_name);
-int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, struct link *l_ptr);
-int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct link *l_ptr);
+struct tipc_media *tipc_media_find(const char *name);
+int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr,
+ struct tipc_link *l_ptr);
+int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr);
void tipc_bearer_stop(void);
void tipc_bearer_lock_push(struct tipc_bearer *b_ptr);
" (cannot change node address once assigned)");
/*
- * Must release all spinlocks before calling start_net() because
- * Linux version of TIPC calls eth_media_start() which calls
- * register_netdevice_notifier() which may block!
- *
- * Temporarily releasing the lock should be harmless for non-Linux TIPC,
- * but Linux version of eth_media_start() should really be reworked
- * so that it can be called with spinlocks held.
+ * Must temporarily release configuration spinlock while switching into
+ * networking mode as it calls tipc_eth_media_start(), which may sleep.
+ * Releasing the lock is harmless as other locally-issued configuration
+ * commands won't occur until this one completes, and remotely-issued
+ * configuration commands can't be received until a local configuration
+ * command to enable the first bearer is received and processed.
*/
spin_unlock_bh(&config_lock);
static void tipc_core_stop_net(void)
{
- tipc_eth_media_stop();
tipc_net_stop();
+ tipc_eth_media_stop();
}
/**
/**
- * struct link_req - information about an ongoing link setup request
+ * struct tipc_link_req - information about an ongoing link setup request
* @bearer: bearer issuing requests
* @dest: destination address for request messages
* @domain: network domain to which links can be established
* @timer: timer governing period between requests
* @timer_intv: current interval between requests (in ms)
*/
-struct link_req {
+struct tipc_link_req {
struct tipc_bearer *bearer;
struct tipc_media_addr dest;
u32 domain;
msg_set_non_seq(msg, 1);
msg_set_dest_domain(msg, dest_domain);
msg_set_bc_netid(msg, tipc_net_id);
- msg_set_media_addr(msg, &b_ptr->addr);
+ b_ptr->media->addr2msg(&b_ptr->addr, msg_media_addr(msg));
}
return buf;
}
void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr)
{
struct tipc_node *n_ptr;
- struct link *link;
+ struct tipc_link *link;
struct tipc_media_addr media_addr, *addr;
struct sk_buff *rbuf;
struct tipc_msg *msg = buf_msg(buf);
u32 type = msg_type(msg);
int link_fully_up;
- msg_get_media_addr(msg, &media_addr);
+ media_addr.broadcast = 1;
+ b_ptr->media->msg2addr(&media_addr, msg_media_addr(msg));
buf_discard(buf);
/* Validate discovery message from requesting node */
if (net_id != tipc_net_id)
return;
+ if (media_addr.broadcast)
+ return;
if (!tipc_addr_domain_valid(dest))
return;
if (!tipc_addr_node_valid(orig))
* and is either not currently searching or is searching at a slow rate
*/
-static void disc_update(struct link_req *req)
+static void disc_update(struct tipc_link_req *req)
{
if (!req->num_nodes) {
if ((req->timer_intv == TIPC_LINK_REQ_INACTIVE) ||
* @req: ptr to link request structure
*/
-void tipc_disc_add_dest(struct link_req *req)
+void tipc_disc_add_dest(struct tipc_link_req *req)
{
req->num_nodes++;
}
* @req: ptr to link request structure
*/
-void tipc_disc_remove_dest(struct link_req *req)
+void tipc_disc_remove_dest(struct tipc_link_req *req)
{
req->num_nodes--;
disc_update(req);
* @req: ptr to link request structure
*/
-static void disc_send_msg(struct link_req *req)
+static void disc_send_msg(struct tipc_link_req *req)
{
if (!req->bearer->blocked)
tipc_bearer_send(req->bearer, req->buf, &req->dest);
* Called whenever a link setup request timer associated with a bearer expires.
*/
-static void disc_timeout(struct link_req *req)
+static void disc_timeout(struct tipc_link_req *req)
{
int max_delay;
int tipc_disc_create(struct tipc_bearer *b_ptr,
struct tipc_media_addr *dest, u32 dest_domain)
{
- struct link_req *req;
+ struct tipc_link_req *req;
req = kmalloc(sizeof(*req), GFP_ATOMIC);
if (!req)
* @req: ptr to link request structure
*/
-void tipc_disc_delete(struct link_req *req)
+void tipc_disc_delete(struct tipc_link_req *req)
{
k_cancel_timer(&req->timer);
k_term_timer(&req->timer);
#ifndef _TIPC_DISCOVER_H
#define _TIPC_DISCOVER_H
-struct link_req;
+struct tipc_link_req;
int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
u32 dest_domain);
-void tipc_disc_delete(struct link_req *req);
-void tipc_disc_add_dest(struct link_req *req);
-void tipc_disc_remove_dest(struct link_req *req);
+void tipc_disc_delete(struct tipc_link_req *req);
+void tipc_disc_add_dest(struct tipc_link_req *req);
+void tipc_disc_remove_dest(struct tipc_link_req *req);
void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr);
#endif
#include "bearer.h"
#define MAX_ETH_BEARERS MAX_BEARERS
-#define ETH_LINK_PRIORITY TIPC_DEF_LINK_PRI
-#define ETH_LINK_TOLERANCE TIPC_DEF_LINK_TOL
-#define ETH_LINK_WINDOW TIPC_DEF_LINK_WIN
+
+#define ETH_ADDR_OFFSET 4 /* message header offset of MAC address */
/**
* struct eth_bearer - Ethernet bearer data structure
* @bearer: ptr to associated "generic" bearer structure
* @dev: ptr to associated Ethernet network device
* @tipc_packet_type: used in binding TIPC to Ethernet driver
+ * @cleanup: work item used when disabling bearer
*/
struct eth_bearer {
struct tipc_bearer *bearer;
struct net_device *dev;
struct packet_type tipc_packet_type;
+ struct work_struct cleanup;
};
+static struct tipc_media eth_media_info;
static struct eth_bearer eth_bearers[MAX_ETH_BEARERS];
static int eth_started;
static struct notifier_block notifier;
+/**
+ * eth_media_addr_set - initialize Ethernet media address structure
+ *
+ * Media-dependent "value" field stores MAC address in first 6 bytes
+ * and zeroes out the remaining bytes.
+ */
+
+static void eth_media_addr_set(struct tipc_media_addr *a, char *mac)
+{
+ memcpy(a->value, mac, ETH_ALEN);
+ memset(a->value + ETH_ALEN, 0, sizeof(a->value) - ETH_ALEN);
+ a->media_id = TIPC_MEDIA_TYPE_ETH;
+ a->broadcast = !memcmp(mac, eth_media_info.bcast_addr.value, ETH_ALEN);
+}
+
/**
* send_msg - send a TIPC message out over an Ethernet interface
*/
skb_reset_network_header(clone);
clone->dev = dev;
- dev_hard_header(clone, dev, ETH_P_TIPC, &dest->dev_addr.eth_addr,
+ dev_hard_header(clone, dev, ETH_P_TIPC, dest->value,
dev->dev_addr, clone->len);
dev_queue_xmit(clone);
return 0;
tb_ptr->usr_handle = (void *)eb_ptr;
tb_ptr->mtu = dev->mtu;
tb_ptr->blocked = 0;
- tb_ptr->addr.type = htonl(TIPC_MEDIA_TYPE_ETH);
- memcpy(&tb_ptr->addr.dev_addr, dev->dev_addr, ETH_ALEN);
+ eth_media_addr_set(&tb_ptr->addr, (char *)dev->dev_addr);
return 0;
}
+/**
+ * cleanup_bearer - break association between Ethernet bearer and interface
+ *
+ * This routine must be invoked from a work queue because it can sleep.
+ */
+
+static void cleanup_bearer(struct work_struct *work)
+{
+ struct eth_bearer *eb_ptr =
+ container_of(work, struct eth_bearer, cleanup);
+
+ dev_remove_pack(&eb_ptr->tipc_packet_type);
+ dev_put(eb_ptr->dev);
+ eb_ptr->dev = NULL;
+}
+
/**
* disable_bearer - detach TIPC bearer from an Ethernet interface
*
- * We really should do dev_remove_pack() here, but this function can not be
- * called at tasklet level. => Use eth_bearer->bearer as a flag to throw away
- * incoming buffers, & postpone dev_remove_pack() to eth_media_stop() on exit.
+ * Mark Ethernet bearer as inactive so that incoming buffers are thrown away,
+ * then get worker thread to complete bearer cleanup. (Can't do cleanup
+ * here because cleanup code needs to sleep and caller holds spinlocks.)
*/
static void disable_bearer(struct tipc_bearer *tb_ptr)
{
- ((struct eth_bearer *)tb_ptr->usr_handle)->bearer = NULL;
+ struct eth_bearer *eb_ptr = (struct eth_bearer *)tb_ptr->usr_handle;
+
+ eb_ptr->bearer = NULL;
+ INIT_WORK(&eb_ptr->cleanup, cleanup_bearer);
+ schedule_work(&eb_ptr->cleanup);
}
/**
* eth_addr2str - convert Ethernet address to string
*/
-static char *eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size)
+static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size)
+{
+ if (str_size < 18) /* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
+ return 1;
+
+ sprintf(str_buf, "%pM", a->value);
+ return 0;
+}
+
+/**
+ * eth_str2addr - convert string to Ethernet address
+ */
+
+static int eth_str2addr(struct tipc_media_addr *a, char *str_buf)
+{
+ char mac[ETH_ALEN];
+ int r;
+
+ r = sscanf(str_buf, "%02x:%02x:%02x:%02x:%02x:%02x",
+ (u32 *)&mac[0], (u32 *)&mac[1], (u32 *)&mac[2],
+ (u32 *)&mac[3], (u32 *)&mac[4], (u32 *)&mac[5]);
+
+ if (r != ETH_ALEN)
+ return 1;
+
+ eth_media_addr_set(a, mac);
+ return 0;
+}
+
+/**
+ * eth_str2addr - convert Ethernet address format to message header format
+ */
+
+static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area)
{
- unchar *addr = (unchar *)&a->dev_addr;
+ memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE);
+ msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
+ memcpy(msg_area + ETH_ADDR_OFFSET, a->value, ETH_ALEN);
+ return 0;
+}
- if (str_size < 18)
- *str_buf = '\0';
- else
- sprintf(str_buf, "%pM", addr);
- return str_buf;
+/**
+ * eth_str2addr - convert message header address format to Ethernet format
+ */
+
+static int eth_msg2addr(struct tipc_media_addr *a, char *msg_area)
+{
+ if (msg_area[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_ETH)
+ return 1;
+
+ eth_media_addr_set(a, msg_area + ETH_ADDR_OFFSET);
+ return 0;
}
+/*
+ * Ethernet media registration info
+ */
+
+static struct tipc_media eth_media_info = {
+ .send_msg = send_msg,
+ .enable_bearer = enable_bearer,
+ .disable_bearer = disable_bearer,
+ .addr2str = eth_addr2str,
+ .str2addr = eth_str2addr,
+ .addr2msg = eth_addr2msg,
+ .msg2addr = eth_msg2addr,
+ .bcast_addr = { { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+ TIPC_MEDIA_TYPE_ETH, 1 },
+ .priority = TIPC_DEF_LINK_PRI,
+ .tolerance = TIPC_DEF_LINK_TOL,
+ .window = TIPC_DEF_LINK_WIN,
+ .type_id = TIPC_MEDIA_TYPE_ETH,
+ .name = "eth"
+};
+
/**
* tipc_eth_media_start - activate Ethernet bearer support
*
int tipc_eth_media_start(void)
{
- struct tipc_media_addr bcast_addr;
int res;
if (eth_started)
return -EINVAL;
- bcast_addr.type = htonl(TIPC_MEDIA_TYPE_ETH);
- memset(&bcast_addr.dev_addr, 0xff, ETH_ALEN);
-
- memset(eth_bearers, 0, sizeof(eth_bearers));
-
- res = tipc_register_media(TIPC_MEDIA_TYPE_ETH, "eth",
- enable_bearer, disable_bearer, send_msg,
- eth_addr2str, &bcast_addr, ETH_LINK_PRIORITY,
- ETH_LINK_TOLERANCE, ETH_LINK_WINDOW);
+ res = tipc_register_media(ð_media_info);
if (res)
return res;
void tipc_eth_media_stop(void)
{
- int i;
-
if (!eth_started)
return;
+ flush_scheduled_work();
unregister_netdevice_notifier(¬ifier);
- for (i = 0; i < MAX_ETH_BEARERS ; i++) {
- if (eth_bearers[i].bearer) {
- eth_bearers[i].bearer->blocked = 1;
- eth_bearers[i].bearer = NULL;
- }
- if (eth_bearers[i].dev) {
- dev_remove_pack(ð_bearers[i].tipc_packet_type);
- dev_put(eth_bearers[i].dev);
- }
- }
- memset(ð_bearers, 0, sizeof(eth_bearers));
eth_started = 0;
}
#define START_CHANGEOVER 100000u
/**
- * struct link_name - deconstructed link name
+ * struct tipc_link_name - deconstructed link name
* @addr_local: network address of node at this end
* @if_local: name of interface at this end
* @addr_peer: network address of node at far end
* @if_peer: name of interface at far end
*/
-struct link_name {
+struct tipc_link_name {
u32 addr_local;
char if_local[TIPC_MAX_IF_NAME];
u32 addr_peer;
char if_peer[TIPC_MAX_IF_NAME];
};
-static void link_handle_out_of_seq_msg(struct link *l_ptr,
+static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
struct sk_buff *buf);
-static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf);
-static int link_recv_changeover_msg(struct link **l_ptr, struct sk_buff **buf);
-static void link_set_supervision_props(struct link *l_ptr, u32 tolerance);
+static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf);
+static int link_recv_changeover_msg(struct tipc_link **l_ptr,
+ struct sk_buff **buf);
+static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance);
static int link_send_sections_long(struct tipc_port *sender,
struct iovec const *msg_sect,
u32 num_sect, unsigned int total_len,
u32 destnode);
-static void link_check_defragm_bufs(struct link *l_ptr);
-static void link_state_event(struct link *l_ptr, u32 event);
-static void link_reset_statistics(struct link *l_ptr);
-static void link_print(struct link *l_ptr, const char *str);
-static void link_start(struct link *l_ptr);
-static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf);
+static void link_check_defragm_bufs(struct tipc_link *l_ptr);
+static void link_state_event(struct tipc_link *l_ptr, u32 event);
+static void link_reset_statistics(struct tipc_link *l_ptr);
+static void link_print(struct tipc_link *l_ptr, const char *str);
+static void link_start(struct tipc_link *l_ptr);
+static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
/*
* Simple link routines
return (i + 3) & ~3u;
}
-static void link_init_max_pkt(struct link *l_ptr)
+static void link_init_max_pkt(struct tipc_link *l_ptr)
{
u32 max_pkt;
l_ptr->max_pkt_probes = 0;
}
-static u32 link_next_sent(struct link *l_ptr)
+static u32 link_next_sent(struct tipc_link *l_ptr)
{
if (l_ptr->next_out)
- return msg_seqno(buf_msg(l_ptr->next_out));
+ return buf_seqno(l_ptr->next_out);
return mod(l_ptr->next_out_no);
}
-static u32 link_last_sent(struct link *l_ptr)
+static u32 link_last_sent(struct tipc_link *l_ptr)
{
return mod(link_next_sent(l_ptr) - 1);
}
* Simple non-static link routines (i.e. referenced outside this file)
*/
-int tipc_link_is_up(struct link *l_ptr)
+int tipc_link_is_up(struct tipc_link *l_ptr)
{
if (!l_ptr)
return 0;
return link_working_working(l_ptr) || link_working_unknown(l_ptr);
}
-int tipc_link_is_active(struct link *l_ptr)
+int tipc_link_is_active(struct tipc_link *l_ptr)
{
return (l_ptr->owner->active_links[0] == l_ptr) ||
(l_ptr->owner->active_links[1] == l_ptr);
}
/**
- * link_name_validate - validate & (optionally) deconstruct link name
+ * link_name_validate - validate & (optionally) deconstruct tipc_link name
* @name - ptr to link name string
* @name_parts - ptr to area for link name components (or NULL if not needed)
*
* Returns 1 if link name is valid, otherwise 0.
*/
-static int link_name_validate(const char *name, struct link_name *name_parts)
+static int link_name_validate(const char *name,
+ struct tipc_link_name *name_parts)
{
char name_copy[TIPC_MAX_LINK_NAME];
char *addr_local;
* tipc_node_delete() is called.)
*/
-static void link_timeout(struct link *l_ptr)
+static void link_timeout(struct tipc_link *l_ptr)
{
tipc_node_lock(l_ptr->owner);
tipc_node_unlock(l_ptr->owner);
}
-static void link_set_timer(struct link *l_ptr, u32 time)
+static void link_set_timer(struct tipc_link *l_ptr, u32 time)
{
k_start_timer(&l_ptr->timer, time);
}
* Returns pointer to link.
*/
-struct link *tipc_link_create(struct tipc_node *n_ptr,
+struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
struct tipc_bearer *b_ptr,
const struct tipc_media_addr *media_addr)
{
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_msg *msg;
char *if_name;
char addr_string[16];
l_ptr->checkpoint = 1;
l_ptr->peer_session = INVALID_SESSION;
l_ptr->b_ptr = b_ptr;
- link_set_supervision_props(l_ptr, b_ptr->media->tolerance);
+ link_set_supervision_props(l_ptr, b_ptr->tolerance);
l_ptr->state = RESET_UNKNOWN;
l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg;
strcpy((char *)msg_data(msg), if_name);
l_ptr->priority = b_ptr->priority;
- tipc_link_set_queue_limits(l_ptr, b_ptr->media->window);
+ tipc_link_set_queue_limits(l_ptr, b_ptr->window);
link_init_max_pkt(l_ptr);
* to avoid a potential deadlock situation.
*/
-void tipc_link_delete(struct link *l_ptr)
+void tipc_link_delete(struct tipc_link *l_ptr)
{
if (!l_ptr) {
err("Attempt to delete non-existent link\n");
kfree(l_ptr);
}
-static void link_start(struct link *l_ptr)
+static void link_start(struct tipc_link *l_ptr)
{
tipc_node_lock(l_ptr->owner);
link_state_event(l_ptr, STARTING_EVT);
* has abated.
*/
-static int link_schedule_port(struct link *l_ptr, u32 origport, u32 sz)
+static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz)
{
struct tipc_port *p_ptr;
return -ELINKCONG;
}
-void tipc_link_wakeup_ports(struct link *l_ptr, int all)
+void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all)
{
struct tipc_port *p_ptr;
struct tipc_port *temp_p_ptr;
* @l_ptr: pointer to link
*/
-static void link_release_outqueue(struct link *l_ptr)
+static void link_release_outqueue(struct tipc_link *l_ptr)
{
struct sk_buff *buf = l_ptr->first_out;
struct sk_buff *next;
* @l_ptr: pointer to link
*/
-void tipc_link_reset_fragments(struct link *l_ptr)
+void tipc_link_reset_fragments(struct tipc_link *l_ptr)
{
struct sk_buff *buf = l_ptr->defragm_buf;
struct sk_buff *next;
* @l_ptr: pointer to link
*/
-void tipc_link_stop(struct link *l_ptr)
+void tipc_link_stop(struct tipc_link *l_ptr)
{
struct sk_buff *buf;
struct sk_buff *next;
l_ptr->proto_msg_queue = NULL;
}
-void tipc_link_reset(struct link *l_ptr)
+void tipc_link_reset(struct tipc_link *l_ptr)
{
struct sk_buff *buf;
u32 prev_state = l_ptr->state;
}
-static void link_activate(struct link *l_ptr)
+static void link_activate(struct tipc_link *l_ptr)
{
l_ptr->next_in_no = l_ptr->stats.recv_info = 1;
tipc_node_link_up(l_ptr->owner, l_ptr);
* @event: state machine event to process
*/
-static void link_state_event(struct link *l_ptr, unsigned event)
+static void link_state_event(struct tipc_link *l_ptr, unsigned event)
{
- struct link *other;
+ struct tipc_link *other;
u32 cont_intv = l_ptr->continuity_interval;
if (!l_ptr->started && (event != STARTING_EVT))
* the tail of an existing one.
*/
-static int link_bundle_buf(struct link *l_ptr,
+static int link_bundle_buf(struct tipc_link *l_ptr,
struct sk_buff *bundler,
struct sk_buff *buf)
{
return 1;
}
-static void link_add_to_outqueue(struct link *l_ptr,
+static void link_add_to_outqueue(struct tipc_link *l_ptr,
struct sk_buff *buf,
struct tipc_msg *msg)
{
l_ptr->stats.max_queue_sz = l_ptr->out_queue_size;
}
-static void link_add_chain_to_outqueue(struct link *l_ptr,
+static void link_add_chain_to_outqueue(struct tipc_link *l_ptr,
struct sk_buff *buf_chain,
u32 long_msgno)
{
* has failed, and from link_send()
*/
-int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf)
+int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
u32 size = msg_size(msg);
int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector)
{
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_node *n_ptr;
int res = -ELINKCONG;
void tipc_link_send_names(struct list_head *message_list, u32 dest)
{
struct tipc_node *n_ptr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct sk_buff *buf;
struct sk_buff *temp_buf;
* Link is locked. Returns user data length.
*/
-static int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf,
+static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
u32 *used_max_pkt)
{
struct tipc_msg *msg = buf_msg(buf);
*/
int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode)
{
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_node *n_ptr;
int res;
u32 selector = msg_origport(buf_msg(buf)) & 1;
u32 destaddr)
{
struct tipc_msg *hdr = &sender->phdr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct sk_buff *buf;
struct tipc_node *node;
int res;
unsigned int total_len,
u32 destaddr)
{
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_node *node;
struct tipc_msg *hdr = &sender->phdr;
u32 dsz = total_len;
/*
* tipc_link_push_packet: Push one unsent packet to the media
*/
-u32 tipc_link_push_packet(struct link *l_ptr)
+u32 tipc_link_push_packet(struct tipc_link *l_ptr)
{
struct sk_buff *buf = l_ptr->first_out;
u32 r_q_size = l_ptr->retransm_queue_size;
if (r_q_size && buf) {
u32 last = lesser(mod(r_q_head + r_q_size),
link_last_sent(l_ptr));
- u32 first = msg_seqno(buf_msg(buf));
+ u32 first = buf_seqno(buf);
while (buf && less(first, r_q_head)) {
first = mod(first + 1);
if (buf) {
struct tipc_msg *msg = buf_msg(buf);
u32 next = msg_seqno(msg);
- u32 first = msg_seqno(buf_msg(l_ptr->first_out));
+ u32 first = buf_seqno(l_ptr->first_out);
if (mod(next - first) < l_ptr->queue_limit[0]) {
msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
* push_queue(): push out the unsent messages of a link where
* congestion has abated. Node is locked
*/
-void tipc_link_push_queue(struct link *l_ptr)
+void tipc_link_push_queue(struct tipc_link *l_ptr)
{
u32 res;
read_unlock_bh(&tipc_net_lock);
}
-static void link_retransmit_failure(struct link *l_ptr, struct sk_buff *buf)
+static void link_retransmit_failure(struct tipc_link *l_ptr,
+ struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
}
}
-void tipc_link_retransmit(struct link *l_ptr, struct sk_buff *buf,
+void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf,
u32 retransmits)
{
struct tipc_msg *msg;
} else {
tipc_bearer_schedule(l_ptr->b_ptr, l_ptr);
l_ptr->stats.bearer_congs++;
- l_ptr->retransm_queue_head = msg_seqno(buf_msg(buf));
+ l_ptr->retransm_queue_head = buf_seqno(buf);
l_ptr->retransm_queue_size = retransmits;
return;
}
* link_insert_deferred_queue - insert deferred messages back into receive chain
*/
-static struct sk_buff *link_insert_deferred_queue(struct link *l_ptr,
+static struct sk_buff *link_insert_deferred_queue(struct tipc_link *l_ptr,
struct sk_buff *buf)
{
u32 seq_no;
if (l_ptr->oldest_deferred_in == NULL)
return buf;
- seq_no = msg_seqno(buf_msg(l_ptr->oldest_deferred_in));
+ seq_no = buf_seqno(l_ptr->oldest_deferred_in);
if (seq_no == mod(l_ptr->next_in_no)) {
l_ptr->newest_deferred_in->next = buf;
buf = l_ptr->oldest_deferred_in;
read_lock_bh(&tipc_net_lock);
while (head) {
struct tipc_node *n_ptr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct sk_buff *crs;
struct sk_buff *buf = head;
struct tipc_msg *msg;
/* Release acked messages */
- if (less(n_ptr->bclink.acked, msg_bcast_ack(msg))) {
- if (tipc_node_is_up(n_ptr) && n_ptr->bclink.supported)
- tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg));
- }
+ if (tipc_node_is_up(n_ptr) && n_ptr->bclink.supported)
+ tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg));
crs = l_ptr->first_out;
while ((crs != l_ptr->next_out) &&
- less_eq(msg_seqno(buf_msg(crs)), ackd)) {
+ less_eq(buf_seqno(crs), ackd)) {
struct sk_buff *next = crs->next;
buf_discard(crs);
{
struct sk_buff *prev = NULL;
struct sk_buff *crs = *head;
- u32 seq_no = msg_seqno(buf_msg(buf));
+ u32 seq_no = buf_seqno(buf);
buf->next = NULL;
}
/* Last ? */
- if (less(msg_seqno(buf_msg(*tail)), seq_no)) {
+ if (less(buf_seqno(*tail), seq_no)) {
(*tail)->next = buf;
*tail = buf;
return 1;
* link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet
*/
-static void link_handle_out_of_seq_msg(struct link *l_ptr,
+static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
struct sk_buff *buf)
{
- u32 seq_no = msg_seqno(buf_msg(buf));
+ u32 seq_no = buf_seqno(buf);
if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) {
link_recv_proto_msg(l_ptr, buf);
/*
* Send protocol message to the other endpoint.
*/
-void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg,
- u32 gap, u32 tolerance, u32 priority, u32 ack_mtu)
+void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
+ int probe_msg, u32 gap, u32 tolerance,
+ u32 priority, u32 ack_mtu)
{
struct sk_buff *buf = NULL;
struct tipc_msg *msg = l_ptr->pmsg;
if (!tipc_link_is_up(l_ptr))
return;
if (l_ptr->next_out)
- next_sent = msg_seqno(buf_msg(l_ptr->next_out));
+ next_sent = buf_seqno(l_ptr->next_out);
msg_set_next_sent(msg, next_sent);
if (l_ptr->oldest_deferred_in) {
- u32 rec = msg_seqno(buf_msg(l_ptr->oldest_deferred_in));
+ u32 rec = buf_seqno(l_ptr->oldest_deferred_in);
gap = mod(rec - mod(l_ptr->next_in_no));
}
msg_set_seq_gap(msg, gap);
* change at any time. The node with lowest address rules
*/
-static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf)
+static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
{
u32 rec_gap = 0;
u32 max_pkt_info;
* tipc_link_tunnel(): Send one message via a link belonging to
* another bearer. Owner node is locked.
*/
-static void tipc_link_tunnel(struct link *l_ptr,
+static void tipc_link_tunnel(struct tipc_link *l_ptr,
struct tipc_msg *tunnel_hdr,
struct tipc_msg *msg,
u32 selector)
{
- struct link *tunnel;
+ struct tipc_link *tunnel;
struct sk_buff *buf;
u32 length = msg_size(msg);
* Owner node is locked.
*/
-void tipc_link_changeover(struct link *l_ptr)
+void tipc_link_changeover(struct tipc_link *l_ptr)
{
u32 msgcount = l_ptr->out_queue_size;
struct sk_buff *crs = l_ptr->first_out;
- struct link *tunnel = l_ptr->owner->active_links[0];
+ struct tipc_link *tunnel = l_ptr->owner->active_links[0];
struct tipc_msg tunnel_hdr;
int split_bundles;
}
}
-void tipc_link_send_duplicate(struct link *l_ptr, struct link *tunnel)
+void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel)
{
struct sk_buff *iter;
struct tipc_msg tunnel_hdr;
* via other link. Node is locked. Return extracted buffer.
*/
-static int link_recv_changeover_msg(struct link **l_ptr,
+static int link_recv_changeover_msg(struct tipc_link **l_ptr,
struct sk_buff **buf)
{
struct sk_buff *tunnel_buf = *buf;
- struct link *dest_link;
+ struct tipc_link *dest_link;
struct tipc_msg *msg;
struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf);
u32 msg_typ = msg_type(tunnel_msg);
* The buffer is complete, inclusive total message length.
* Returns user data length.
*/
-static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf)
+static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
{
struct sk_buff *buf_chain = NULL;
struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain;
/* Is there an incomplete message waiting for this fragment? */
- while (pbuf && ((msg_seqno(buf_msg(pbuf)) != long_msg_seq_no) ||
+ while (pbuf && ((buf_seqno(pbuf) != long_msg_seq_no) ||
(msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) {
prev = pbuf;
pbuf = pbuf->next;
* @l_ptr: pointer to link
*/
-static void link_check_defragm_bufs(struct link *l_ptr)
+static void link_check_defragm_bufs(struct tipc_link *l_ptr)
{
struct sk_buff *prev = NULL;
struct sk_buff *next = NULL;
-static void link_set_supervision_props(struct link *l_ptr, u32 tolerance)
+static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance)
{
if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL))
return;
}
-void tipc_link_set_queue_limits(struct link *l_ptr, u32 window)
+void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window)
{
/* Data messages from this node, inclusive FIRST_FRAGM */
l_ptr->queue_limit[TIPC_LOW_IMPORTANCE] = window;
* Returns pointer to link (or 0 if invalid link name).
*/
-static struct link *link_find_link(const char *name, struct tipc_node **node)
+static struct tipc_link *link_find_link(const char *name,
+ struct tipc_node **node)
{
- struct link_name link_name_parts;
+ struct tipc_link_name link_name_parts;
struct tipc_bearer *b_ptr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
if (!link_name_validate(name, &link_name_parts))
return NULL;
return l_ptr;
}
+/**
+ * link_value_is_valid -- validate proposed link tolerance/priority/window
+ *
+ * @cmd - value type (TIPC_CMD_SET_LINK_*)
+ * @new_value - the new value
+ *
+ * Returns 1 if value is within range, 0 if not.
+ */
+
+static int link_value_is_valid(u16 cmd, u32 new_value)
+{
+ switch (cmd) {
+ case TIPC_CMD_SET_LINK_TOL:
+ return (new_value >= TIPC_MIN_LINK_TOL) &&
+ (new_value <= TIPC_MAX_LINK_TOL);
+ case TIPC_CMD_SET_LINK_PRI:
+ return (new_value <= TIPC_MAX_LINK_PRI);
+ case TIPC_CMD_SET_LINK_WINDOW:
+ return (new_value >= TIPC_MIN_LINK_WIN) &&
+ (new_value <= TIPC_MAX_LINK_WIN);
+ }
+ return 0;
+}
+
+
+/**
+ * link_cmd_set_value - change priority/tolerance/window for link/bearer/media
+ * @name - ptr to link, bearer, or media name
+ * @new_value - new value of link, bearer, or media setting
+ * @cmd - which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*)
+ *
+ * Caller must hold 'tipc_net_lock' to ensure link/bearer/media is not deleted.
+ *
+ * Returns 0 if value updated and negative value on error.
+ */
+
+static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd)
+{
+ struct tipc_node *node;
+ struct tipc_link *l_ptr;
+ struct tipc_bearer *b_ptr;
+ struct tipc_media *m_ptr;
+
+ l_ptr = link_find_link(name, &node);
+ if (l_ptr) {
+ /*
+ * acquire node lock for tipc_link_send_proto_msg().
+ * see "TIPC locking policy" in net.c.
+ */
+ tipc_node_lock(node);
+ switch (cmd) {
+ case TIPC_CMD_SET_LINK_TOL:
+ link_set_supervision_props(l_ptr, new_value);
+ tipc_link_send_proto_msg(l_ptr,
+ STATE_MSG, 0, 0, new_value, 0, 0);
+ break;
+ case TIPC_CMD_SET_LINK_PRI:
+ l_ptr->priority = new_value;
+ tipc_link_send_proto_msg(l_ptr,
+ STATE_MSG, 0, 0, 0, new_value, 0);
+ break;
+ case TIPC_CMD_SET_LINK_WINDOW:
+ tipc_link_set_queue_limits(l_ptr, new_value);
+ break;
+ }
+ tipc_node_unlock(node);
+ return 0;
+ }
+
+ b_ptr = tipc_bearer_find(name);
+ if (b_ptr) {
+ switch (cmd) {
+ case TIPC_CMD_SET_LINK_TOL:
+ b_ptr->tolerance = new_value;
+ return 0;
+ case TIPC_CMD_SET_LINK_PRI:
+ b_ptr->priority = new_value;
+ return 0;
+ case TIPC_CMD_SET_LINK_WINDOW:
+ b_ptr->window = new_value;
+ return 0;
+ }
+ return -EINVAL;
+ }
+
+ m_ptr = tipc_media_find(name);
+ if (!m_ptr)
+ return -ENODEV;
+ switch (cmd) {
+ case TIPC_CMD_SET_LINK_TOL:
+ m_ptr->tolerance = new_value;
+ return 0;
+ case TIPC_CMD_SET_LINK_PRI:
+ m_ptr->priority = new_value;
+ return 0;
+ case TIPC_CMD_SET_LINK_WINDOW:
+ m_ptr->window = new_value;
+ return 0;
+ }
+ return -EINVAL;
+}
+
struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space,
u16 cmd)
{
struct tipc_link_config *args;
u32 new_value;
- struct link *l_ptr;
- struct tipc_node *node;
int res;
if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_CONFIG))
args = (struct tipc_link_config *)TLV_DATA(req_tlv_area);
new_value = ntohl(args->value);
+ if (!link_value_is_valid(cmd, new_value))
+ return tipc_cfg_reply_error_string(
+ "cannot change, value invalid");
+
if (!strcmp(args->name, tipc_bclink_name)) {
if ((cmd == TIPC_CMD_SET_LINK_WINDOW) &&
(tipc_bclink_set_queue_limits(new_value) == 0))
}
read_lock_bh(&tipc_net_lock);
- l_ptr = link_find_link(args->name, &node);
- if (!l_ptr) {
- read_unlock_bh(&tipc_net_lock);
- return tipc_cfg_reply_error_string("link not found");
- }
-
- tipc_node_lock(node);
- res = -EINVAL;
- switch (cmd) {
- case TIPC_CMD_SET_LINK_TOL:
- if ((new_value >= TIPC_MIN_LINK_TOL) &&
- (new_value <= TIPC_MAX_LINK_TOL)) {
- link_set_supervision_props(l_ptr, new_value);
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 0, 0, new_value, 0, 0);
- res = 0;
- }
- break;
- case TIPC_CMD_SET_LINK_PRI:
- if ((new_value >= TIPC_MIN_LINK_PRI) &&
- (new_value <= TIPC_MAX_LINK_PRI)) {
- l_ptr->priority = new_value;
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 0, 0, 0, new_value, 0);
- res = 0;
- }
- break;
- case TIPC_CMD_SET_LINK_WINDOW:
- if ((new_value >= TIPC_MIN_LINK_WIN) &&
- (new_value <= TIPC_MAX_LINK_WIN)) {
- tipc_link_set_queue_limits(l_ptr, new_value);
- res = 0;
- }
- break;
- }
- tipc_node_unlock(node);
-
+ res = link_cmd_set_value(args->name, new_value, cmd);
read_unlock_bh(&tipc_net_lock);
if (res)
return tipc_cfg_reply_error_string("cannot change link setting");
* @l_ptr: pointer to link
*/
-static void link_reset_statistics(struct link *l_ptr)
+static void link_reset_statistics(struct tipc_link *l_ptr)
{
memset(&l_ptr->stats, 0, sizeof(l_ptr->stats));
l_ptr->stats.sent_info = l_ptr->next_out_no;
struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space)
{
char *link_name;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_node *node;
if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
{
struct print_buf pb;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct tipc_node *node;
char *status;
u32 profile_total = 0;
u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
{
struct tipc_node *n_ptr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
u32 res = MAX_PKT_DEFAULT;
if (dest == tipc_own_addr)
return res;
}
-static void link_print(struct link *l_ptr, const char *str)
+static void link_print(struct tipc_link *l_ptr, const char *str)
{
char print_area[256];
struct print_buf pb;
tipc_printf(buf, "NXI(%u):", mod(l_ptr->next_in_no));
tipc_printf(buf, "SQUE");
if (l_ptr->first_out) {
- tipc_printf(buf, "[%u..", msg_seqno(buf_msg(l_ptr->first_out)));
+ tipc_printf(buf, "[%u..", buf_seqno(l_ptr->first_out));
if (l_ptr->next_out)
- tipc_printf(buf, "%u..",
- msg_seqno(buf_msg(l_ptr->next_out)));
- tipc_printf(buf, "%u]", msg_seqno(buf_msg(l_ptr->last_out)));
- if ((mod(msg_seqno(buf_msg(l_ptr->last_out)) -
- msg_seqno(buf_msg(l_ptr->first_out)))
+ tipc_printf(buf, "%u..", buf_seqno(l_ptr->next_out));
+ tipc_printf(buf, "%u]", buf_seqno(l_ptr->last_out));
+ if ((mod(buf_seqno(l_ptr->last_out) -
+ buf_seqno(l_ptr->first_out))
!= (l_ptr->out_queue_size - 1)) ||
(l_ptr->last_out->next != NULL)) {
tipc_printf(buf, "\nSend queue inconsistency\n");
tipc_printf(buf, "[]");
tipc_printf(buf, "SQSIZ(%u)", l_ptr->out_queue_size);
if (l_ptr->oldest_deferred_in) {
- u32 o = msg_seqno(buf_msg(l_ptr->oldest_deferred_in));
- u32 n = msg_seqno(buf_msg(l_ptr->newest_deferred_in));
+ u32 o = buf_seqno(l_ptr->oldest_deferred_in);
+ u32 n = buf_seqno(l_ptr->newest_deferred_in);
tipc_printf(buf, ":RQUE[%u..%u]", o, n);
if (l_ptr->deferred_inqueue_sz != mod((n + 1) - o)) {
tipc_printf(buf, ":RQSIZ(%u)",
#define PUSH_FAILED 1
#define PUSH_FINISHED 2
+/*
+ * Out-of-range value for link sequence numbers
+ */
+
+#define INVALID_LINK_SEQ 0x10000
+
/*
* Link states
*/
#define MAX_PKT_DEFAULT 1500
/**
- * struct link - TIPC link data structure
+ * struct tipc_link - TIPC link data structure
* @addr: network address of link's peer node
* @name: link name character string
* @media_addr: media address to use when sending messages over link
* @stats: collects statistics regarding link activity
*/
-struct link {
+struct tipc_link {
u32 addr;
char name[TIPC_MAX_LINK_NAME];
struct tipc_media_addr media_addr;
struct tipc_port;
-struct link *tipc_link_create(struct tipc_node *n_ptr,
+struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
struct tipc_bearer *b_ptr,
const struct tipc_media_addr *media_addr);
-void tipc_link_delete(struct link *l_ptr);
-void tipc_link_changeover(struct link *l_ptr);
-void tipc_link_send_duplicate(struct link *l_ptr, struct link *dest);
-void tipc_link_reset_fragments(struct link *l_ptr);
-int tipc_link_is_up(struct link *l_ptr);
-int tipc_link_is_active(struct link *l_ptr);
-u32 tipc_link_push_packet(struct link *l_ptr);
-void tipc_link_stop(struct link *l_ptr);
+void tipc_link_delete(struct tipc_link *l_ptr);
+void tipc_link_changeover(struct tipc_link *l_ptr);
+void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *dest);
+void tipc_link_reset_fragments(struct tipc_link *l_ptr);
+int tipc_link_is_up(struct tipc_link *l_ptr);
+int tipc_link_is_active(struct tipc_link *l_ptr);
+u32 tipc_link_push_packet(struct tipc_link *l_ptr);
+void tipc_link_stop(struct tipc_link *l_ptr);
struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, u16 cmd);
struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space);
struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space);
-void tipc_link_reset(struct link *l_ptr);
+void tipc_link_reset(struct tipc_link *l_ptr);
int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector);
void tipc_link_send_names(struct list_head *message_list, u32 dest);
-int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf);
+int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
u32 tipc_link_get_max_pkt(u32 dest, u32 selector);
int tipc_link_send_sections_fast(struct tipc_port *sender,
struct iovec const *msg_sect,
int tipc_link_recv_fragment(struct sk_buff **pending,
struct sk_buff **fb,
struct tipc_msg **msg);
-void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int prob, u32 gap,
- u32 tolerance, u32 priority, u32 acked_mtu);
-void tipc_link_push_queue(struct link *l_ptr);
+void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob,
+ u32 gap, u32 tolerance, u32 priority,
+ u32 acked_mtu);
+void tipc_link_push_queue(struct tipc_link *l_ptr);
u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
struct sk_buff *buf);
-void tipc_link_wakeup_ports(struct link *l_ptr, int all);
-void tipc_link_set_queue_limits(struct link *l_ptr, u32 window);
-void tipc_link_retransmit(struct link *l_ptr, struct sk_buff *start, u32 retransmits);
+void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all);
+void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
+void tipc_link_retransmit(struct tipc_link *l_ptr,
+ struct sk_buff *start, u32 retransmits);
/*
* Link sequence number manipulation routines (uses modulo 2**16 arithmetic)
*/
+static inline u32 buf_seqno(struct sk_buff *buf)
+{
+ return msg_seqno(buf_msg(buf));
+}
+
static inline u32 mod(u32 x)
{
return x & 0xffffu;
* Link status checking routines
*/
-static inline int link_working_working(struct link *l_ptr)
+static inline int link_working_working(struct tipc_link *l_ptr)
{
return l_ptr->state == WORKING_WORKING;
}
-static inline int link_working_unknown(struct link *l_ptr)
+static inline int link_working_unknown(struct tipc_link *l_ptr)
{
return l_ptr->state == WORKING_UNKNOWN;
}
-static inline int link_reset_unknown(struct link *l_ptr)
+static inline int link_reset_unknown(struct tipc_link *l_ptr)
{
return l_ptr->state == RESET_UNKNOWN;
}
-static inline int link_reset_reset(struct link *l_ptr)
+static inline int link_reset_reset(struct tipc_link *l_ptr)
{
return l_ptr->state == RESET_RESET;
}
-static inline int link_blocked(struct link *l_ptr)
+static inline int link_blocked(struct tipc_link *l_ptr)
{
return l_ptr->exp_msg_count || l_ptr->blocked;
}
-static inline int link_congested(struct link *l_ptr)
+static inline int link_congested(struct tipc_link *l_ptr)
{
return l_ptr->out_queue_size >= l_ptr->queue_limit[0];
}
}
if (msg_user(msg) == LINK_CONFIG) {
- u32 *raw = (u32 *)msg;
- struct tipc_media_addr *orig = (struct tipc_media_addr *)&raw[5];
+ struct tipc_media_addr orig;
+
tipc_printf(buf, ":DDOM(%x):", msg_dest_domain(msg));
tipc_printf(buf, ":NETID(%u):", msg_bc_netid(msg));
- tipc_media_addr_printf(buf, orig);
+ memcpy(orig.value, msg_media_addr(msg), sizeof(orig.value));
+ orig.media_id = 0;
+ orig.broadcast = 0;
+ tipc_media_addr_printf(buf, &orig);
}
if (msg_user(msg) == BCAST_PROTOCOL) {
tipc_printf(buf, "BCNACK:AFTER(%u):", msg_bcgap_after(msg));
#define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE)
+#define TIPC_MEDIA_ADDR_OFFSET 5
+
struct tipc_msg {
__be32 hdr[15];
msg_set_bits(m, 5, 12, 0x1, r);
}
+static inline char *msg_media_addr(struct tipc_msg *m)
+{
+ return (char *)&m->hdr[TIPC_MEDIA_ADDR_OFFSET];
+}
/*
* Word 9
u32 num_sect, unsigned int total_len,
int max_size, int usrmem, struct sk_buff **buf);
-static inline void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr *a)
-{
- memcpy(&((int *)m)[5], a, sizeof(*a));
-}
-
-static inline void msg_get_media_addr(struct tipc_msg *m, struct tipc_media_addr *a)
-{
- memcpy(a, &((int *)m)[5], sizeof(*a));
-}
-
#endif
void tipc_named_node_up(unsigned long nodearg)
{
struct tipc_node *n_ptr;
- struct link *l_ptr;
+ struct tipc_link *l_ptr;
struct publication *publ;
struct distr_item *item = NULL;
struct sk_buff *buf = NULL;
/**
* tipc_named_reinit - re-initialize local publication list
*
- * This routine is called whenever TIPC networking is (re)enabled.
+ * This routine is called whenever TIPC networking is enabled.
* All existing publications by this node that have "cluster" or "zone" scope
- * are updated to reflect the node's current network address.
- * (If the node's address is unchanged, the update loop terminates immediately.)
+ * are updated to reflect the node's new network address.
*/
void tipc_named_reinit(void)
struct publication *publ;
write_lock_bh(&tipc_nametbl_lock);
- list_for_each_entry(publ, &publ_root, local_list) {
- if (publ->node == tipc_own_addr)
- break;
+
+ list_for_each_entry(publ, &publ_root, local_list)
publ->node = tipc_own_addr;
- }
+
write_unlock_bh(&tipc_nametbl_lock);
}
u32 type, u32 lower, u32 upper,
u32 scope, u32 node, u32 port, u32 key)
{
- struct subscription *s;
- struct subscription *st;
+ struct tipc_subscription *s;
+ struct tipc_subscription *st;
struct publication *publ;
struct sub_seq *sseq;
struct name_info *info;
struct sub_seq *sseq = nameseq_find_subseq(nseq, inst);
struct name_info *info;
struct sub_seq *free;
- struct subscription *s, *st;
+ struct tipc_subscription *s, *st;
int removed_subseq = 0;
if (!sseq)
* sequence overlapping with the requested sequence
*/
-static void tipc_nameseq_subscribe(struct name_seq *nseq, struct subscription *s)
+static void tipc_nameseq_subscribe(struct name_seq *nseq,
+ struct tipc_subscription *s)
{
struct sub_seq *sseq = nseq->sseqs;
*/
int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
- struct port_list *dports)
+ struct tipc_port_list *dports)
{
struct name_seq *seq;
struct sub_seq *sseq;
* tipc_nametbl_subscribe - add a subscription object to the name table
*/
-void tipc_nametbl_subscribe(struct subscription *s)
+void tipc_nametbl_subscribe(struct tipc_subscription *s)
{
u32 type = s->seq.type;
struct name_seq *seq;
* tipc_nametbl_unsubscribe - remove a subscription object from name table
*/
-void tipc_nametbl_unsubscribe(struct subscription *s)
+void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
{
struct name_seq *seq;
#include "node_subscr.h"
-struct subscription;
-struct port_list;
+struct tipc_subscription;
+struct tipc_port_list;
/*
* TIPC name types reserved for internal TIPC use (both current and planned)
struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space);
u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *node);
int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
- struct port_list *dports);
+ struct tipc_port_list *dports);
int tipc_nametbl_publish_rsv(u32 ref, unsigned int scope,
struct tipc_name_seq const *seq);
struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
u32 scope, u32 node, u32 ref, u32 key);
struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower,
u32 node, u32 ref, u32 key);
-void tipc_nametbl_subscribe(struct subscription *s);
-void tipc_nametbl_unsubscribe(struct subscription *s);
+void tipc_nametbl_subscribe(struct tipc_subscription *s);
+void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
int tipc_nametbl_init(void);
void tipc_nametbl_stop(void);
int tipc_net_start(u32 addr)
{
char addr_string[16];
- int res;
if (tipc_mode != TIPC_NODE_MODE)
return -ENOPROTOOPT;
tipc_named_reinit();
tipc_port_reinit();
- res = tipc_bclink_init();
- if (res)
- return res;
+ tipc_bclink_init();
tipc_k_signal((Handler)tipc_subscr_start, 0);
tipc_k_signal((Handler)tipc_cfg_init, 0);
if (tipc_mode != TIPC_NET_MODE)
return;
write_lock_bh(&tipc_net_lock);
- tipc_bearer_stop();
tipc_mode = TIPC_NODE_MODE;
+ tipc_bearer_stop();
tipc_bclink_stop();
list_for_each_entry_safe(node, t_node, &tipc_node_list, list)
tipc_node_delete(node);
* Link becomes active (alone or shared) or standby, depending on its priority.
*/
-void tipc_node_link_up(struct tipc_node *n_ptr, struct link *l_ptr)
+void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
- struct link **active = &n_ptr->active_links[0];
+ struct tipc_link **active = &n_ptr->active_links[0];
n_ptr->working_links++;
static void node_select_active_links(struct tipc_node *n_ptr)
{
- struct link **active = &n_ptr->active_links[0];
+ struct tipc_link **active = &n_ptr->active_links[0];
u32 i;
u32 highest_prio = 0;
active[0] = active[1] = NULL;
for (i = 0; i < MAX_BEARERS; i++) {
- struct link *l_ptr = n_ptr->links[i];
+ struct tipc_link *l_ptr = n_ptr->links[i];
if (!l_ptr || !tipc_link_is_up(l_ptr) ||
(l_ptr->priority < highest_prio))
* tipc_node_link_down - handle loss of link
*/
-void tipc_node_link_down(struct tipc_node *n_ptr, struct link *l_ptr)
+void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
- struct link **active;
+ struct tipc_link **active;
n_ptr->working_links--;
return tipc_node_active_links(n_ptr);
}
-void tipc_node_attach_link(struct tipc_node *n_ptr, struct link *l_ptr)
+void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
n_ptr->links[l_ptr->b_ptr->identity] = l_ptr;
atomic_inc(&tipc_num_links);
n_ptr->link_cnt++;
}
-void tipc_node_detach_link(struct tipc_node *n_ptr, struct link *l_ptr)
+void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
n_ptr->links[l_ptr->b_ptr->identity] = NULL;
atomic_dec(&tipc_num_links);
n_ptr->bclink.acked = tipc_bclink_get_last_sent();
if (n_ptr->bclink.supported) {
- tipc_nmap_add(&tipc_bcast_nmap, n_ptr->addr);
+ tipc_bclink_add_node(n_ptr->addr);
if (n_ptr->addr < tipc_own_addr)
tipc_own_tag++;
}
n_ptr->bclink.defragm = NULL;
}
- tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr);
- tipc_bclink_acknowledge(n_ptr,
- mod(n_ptr->bclink.acked + 10000));
+ tipc_bclink_remove_node(n_ptr->addr);
+ tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ);
if (n_ptr->addr < tipc_own_addr)
tipc_own_tag--;
/* Abort link changeover */
for (i = 0; i < MAX_BEARERS; i++) {
- struct link *l_ptr = n_ptr->links[i];
+ struct tipc_link *l_ptr = n_ptr->links[i];
if (!l_ptr)
continue;
l_ptr->reset_checkpoint = l_ptr->next_in_no;
struct hlist_node hash;
struct list_head list;
struct list_head nsub;
- struct link *active_links[2];
- struct link *links[MAX_BEARERS];
+ struct tipc_link *active_links[2];
+ struct tipc_link *links[MAX_BEARERS];
int link_cnt;
int working_links;
int block_setup;
struct tipc_node *tipc_node_find(u32 addr);
struct tipc_node *tipc_node_create(u32 addr);
void tipc_node_delete(struct tipc_node *n_ptr);
-void tipc_node_attach_link(struct tipc_node *n_ptr, struct link *l_ptr);
-void tipc_node_detach_link(struct tipc_node *n_ptr, struct link *l_ptr);
-void tipc_node_link_down(struct tipc_node *n_ptr, struct link *l_ptr);
-void tipc_node_link_up(struct tipc_node *n_ptr, struct link *l_ptr);
+void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
+void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
+void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
+void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
int tipc_node_active_links(struct tipc_node *n_ptr);
int tipc_node_redundant_links(struct tipc_node *n_ptr);
int tipc_node_is_up(struct tipc_node *n_ptr);
struct tipc_msg *hdr;
struct sk_buff *buf;
struct sk_buff *ibuf = NULL;
- struct port_list dports = {0, NULL, };
+ struct tipc_port_list dports = {0, NULL, };
struct tipc_port *oport = tipc_port_deref(ref);
int ext_targets;
int res;
* If there is no port list, perform a lookup to create one
*/
-void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp)
+void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp)
{
struct tipc_msg *msg;
- struct port_list dports = {0, NULL, };
- struct port_list *item = dp;
+ struct tipc_port_list dports = {0, NULL, };
+ struct tipc_port_list *item = dp;
int cnt = 0;
msg = buf_msg(buf);
};
extern spinlock_t tipc_port_list_lock;
-struct port_list;
+struct tipc_port_list;
/*
* TIPC port manipulation routines
unsigned int total_len, int err);
struct sk_buff *tipc_port_get_ports(void);
void tipc_port_recv_proto_msg(struct sk_buff *buf);
-void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp);
+void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp);
void tipc_port_reinit(void);
/**
/* allocate table & mark all entries as uninitialized */
- table = __vmalloc(actual_size * sizeof(struct reference),
- GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+ table = vzalloc(actual_size * sizeof(struct reference));
if (table == NULL)
return -ENOMEM;
/* Validate arguments */
- if (!net_eq(net, &init_net))
- return -EAFNOSUPPORT;
-
if (unlikely(protocol != 0))
return -EPROTONOSUPPORT;
#include "subscr.h"
/**
- * struct subscriber - TIPC network topology subscriber
+ * struct tipc_subscriber - TIPC network topology subscriber
* @port_ref: object reference to server port connecting to subscriber
* @lock: pointer to spinlock controlling access to subscriber's server port
* @subscriber_list: adjacent subscribers in top. server's list of subscribers
* @subscription_list: list of subscription objects for this subscriber
*/
-struct subscriber {
+struct tipc_subscriber {
u32 port_ref;
spinlock_t *lock;
struct list_head subscriber_list;
* try to take the lock if the message is rejected and returned!
*/
-static void subscr_send_event(struct subscription *sub,
+static void subscr_send_event(struct tipc_subscription *sub,
u32 found_lower,
u32 found_upper,
u32 event,
* Returns 1 if there is overlap, otherwise 0.
*/
-int tipc_subscr_overlap(struct subscription *sub,
+int tipc_subscr_overlap(struct tipc_subscription *sub,
u32 found_lower,
u32 found_upper)
* Protected by nameseq.lock in name_table.c
*/
-void tipc_subscr_report_overlap(struct subscription *sub,
+void tipc_subscr_report_overlap(struct tipc_subscription *sub,
u32 found_lower,
u32 found_upper,
u32 event,
* subscr_timeout - subscription timeout has occurred
*/
-static void subscr_timeout(struct subscription *sub)
+static void subscr_timeout(struct tipc_subscription *sub)
{
struct tipc_port *server_port;
* Called with subscriber port locked.
*/
-static void subscr_del(struct subscription *sub)
+static void subscr_del(struct tipc_subscription *sub)
{
tipc_nametbl_unsubscribe(sub);
list_del(&sub->subscription_list);
* simply wait for it to be released, then claim it.)
*/
-static void subscr_terminate(struct subscriber *subscriber)
+static void subscr_terminate(struct tipc_subscriber *subscriber)
{
u32 port_ref;
- struct subscription *sub;
- struct subscription *sub_temp;
+ struct tipc_subscription *sub;
+ struct tipc_subscription *sub_temp;
/* Invalidate subscriber reference */
*/
static void subscr_cancel(struct tipc_subscr *s,
- struct subscriber *subscriber)
+ struct tipc_subscriber *subscriber)
{
- struct subscription *sub;
- struct subscription *sub_temp;
+ struct tipc_subscription *sub;
+ struct tipc_subscription *sub_temp;
int found = 0;
/* Find first matching subscription, exit if not found */
* Called with subscriber port locked.
*/
-static struct subscription *subscr_subscribe(struct tipc_subscr *s,
- struct subscriber *subscriber)
+static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
+ struct tipc_subscriber *subscriber)
{
- struct subscription *sub;
+ struct tipc_subscription *sub;
int swap;
/* Determine subscriber's endianness */
unsigned int size,
int reason)
{
- struct subscriber *subscriber = usr_handle;
+ struct tipc_subscriber *subscriber = usr_handle;
spinlock_t *subscriber_lock;
if (tipc_port_lock(port_ref) == NULL)
const unchar *data,
u32 size)
{
- struct subscriber *subscriber = usr_handle;
+ struct tipc_subscriber *subscriber = usr_handle;
spinlock_t *subscriber_lock;
- struct subscription *sub;
+ struct tipc_subscription *sub;
/*
* Lock subscriber's server port (& make a local copy of lock pointer,
struct tipc_portid const *orig,
struct tipc_name_seq const *dest)
{
- struct subscriber *subscriber;
+ struct tipc_subscriber *subscriber;
u32 server_port_ref;
/* Create subscriber object */
- subscriber = kzalloc(sizeof(struct subscriber), GFP_ATOMIC);
+ subscriber = kzalloc(sizeof(struct tipc_subscriber), GFP_ATOMIC);
if (subscriber == NULL) {
warn("Subscriber rejected, no memory\n");
return;
void tipc_subscr_stop(void)
{
- struct subscriber *subscriber;
- struct subscriber *subscriber_temp;
+ struct tipc_subscriber *subscriber;
+ struct tipc_subscriber *subscriber_temp;
spinlock_t *subscriber_lock;
if (topsrv.setup_port) {
#ifndef _TIPC_SUBSCR_H
#define _TIPC_SUBSCR_H
-struct subscription;
+struct tipc_subscription;
/**
- * struct subscription - TIPC network topology subscription object
+ * struct tipc_subscription - TIPC network topology subscription object
* @seq: name sequence associated with subscription
* @timeout: duration of subscription (in ms)
* @filter: event filtering to be done for subscription
* @evt: template for events generated by subscription
*/
-struct subscription {
+struct tipc_subscription {
struct tipc_name_seq seq;
u32 timeout;
u32 filter;
struct tipc_event evt;
};
-int tipc_subscr_overlap(struct subscription *sub,
+int tipc_subscr_overlap(struct tipc_subscription *sub,
u32 found_lower,
u32 found_upper);
-void tipc_subscr_report_overlap(struct subscription *sub,
+void tipc_subscr_report_overlap(struct tipc_subscription *sub,
u32 found_lower,
u32 found_upper,
u32 event,
Say Y unless you know what you are doing.
+config UNIX_DIAG
+ tristate "UNIX: socket monitoring interface"
+ depends on UNIX
+ default UNIX
+ ---help---
+ Support for UNIX socket monitoring interface used by the ss tool.
+ If unsure, say Y.
unix-y := af_unix.o garbage.o
unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o
+
+obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
+unix_diag-y := diag.o
#include <net/checksum.h>
#include <linux/security.h>
-static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
-static DEFINE_SPINLOCK(unix_table_lock);
+struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
+EXPORT_SYMBOL_GPL(unix_socket_table);
+DEFINE_SPINLOCK(unix_table_lock);
+EXPORT_SYMBOL_GPL(unix_table_lock);
static atomic_long_t unix_nr_socks;
#define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE])
return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
}
-static struct sock *unix_peer_get(struct sock *s)
+struct sock *unix_peer_get(struct sock *s)
{
struct sock *peer;
unix_state_unlock(s);
return peer;
}
+EXPORT_SYMBOL_GPL(unix_peer_get);
static inline void unix_release_addr(struct unix_address *addr)
{
if ((UNIXCB(skb).pid != siocb->scm->pid) ||
(UNIXCB(skb).cred != siocb->scm->cred)) {
skb_queue_head(&sk->sk_receive_queue, skb);
+ sk->sk_data_ready(sk, skb->len);
break;
}
} else {
chunk = min_t(unsigned int, skb->len, size);
if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
skb_queue_head(&sk->sk_receive_queue, skb);
+ sk->sk_data_ready(sk, skb->len);
if (copied == 0)
copied = -EFAULT;
break;
/* put the skb back if we didn't use it up.. */
if (skb->len) {
skb_queue_head(&sk->sk_receive_queue, skb);
+ sk->sk_data_ready(sk, skb->len);
break;
}
/* put message back and return */
skb_queue_head(&sk->sk_receive_queue, skb);
+ sk->sk_data_ready(sk, skb->len);
break;
}
} while (size);
return 0;
}
+long unix_inq_len(struct sock *sk)
+{
+ struct sk_buff *skb;
+ long amount = 0;
+
+ if (sk->sk_state == TCP_LISTEN)
+ return -EINVAL;
+
+ spin_lock(&sk->sk_receive_queue.lock);
+ if (sk->sk_type == SOCK_STREAM ||
+ sk->sk_type == SOCK_SEQPACKET) {
+ skb_queue_walk(&sk->sk_receive_queue, skb)
+ amount += skb->len;
+ } else {
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb)
+ amount = skb->len;
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+
+ return amount;
+}
+EXPORT_SYMBOL_GPL(unix_inq_len);
+
+long unix_outq_len(struct sock *sk)
+{
+ return sk_wmem_alloc_get(sk);
+}
+EXPORT_SYMBOL_GPL(unix_outq_len);
+
static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
switch (cmd) {
case SIOCOUTQ:
- amount = sk_wmem_alloc_get(sk);
+ amount = unix_outq_len(sk);
err = put_user(amount, (int __user *)arg);
break;
case SIOCINQ:
- {
- struct sk_buff *skb;
-
- if (sk->sk_state == TCP_LISTEN) {
- err = -EINVAL;
- break;
- }
-
- spin_lock(&sk->sk_receive_queue.lock);
- if (sk->sk_type == SOCK_STREAM ||
- sk->sk_type == SOCK_SEQPACKET) {
- skb_queue_walk(&sk->sk_receive_queue, skb)
- amount += skb->len;
- } else {
- skb = skb_peek(&sk->sk_receive_queue);
- if (skb)
- amount = skb->len;
- }
- spin_unlock(&sk->sk_receive_queue.lock);
+ amount = unix_inq_len(sk);
+ if (amount < 0)
+ err = amount;
+ else
err = put_user(amount, (int __user *)arg);
- break;
- }
-
+ break;
default:
err = -ENOIOCTLCMD;
break;
--- /dev/null
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+#include <linux/skbuff.h>
+#include <linux/module.h>
+#include <net/netlink.h>
+#include <net/af_unix.h>
+#include <net/tcp_states.h>
+
+#define UNIX_DIAG_PUT(skb, attrtype, attrlen) \
+ RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
+
+static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct unix_address *addr = unix_sk(sk)->addr;
+ char *s;
+
+ if (addr) {
+ s = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short));
+ memcpy(s, addr->name->sun_path, addr->len - sizeof(short));
+ }
+
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
+static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct dentry *dentry = unix_sk(sk)->dentry;
+ struct unix_diag_vfs *uv;
+
+ if (dentry) {
+ uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv));
+ uv->udiag_vfs_ino = dentry->d_inode->i_ino;
+ uv->udiag_vfs_dev = dentry->d_sb->s_dev;
+ }
+
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
+static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sock *peer;
+ int ino;
+
+ peer = unix_peer_get(sk);
+ if (peer) {
+ unix_state_lock(peer);
+ ino = sock_i_ino(peer);
+ unix_state_unlock(peer);
+ sock_put(peer);
+
+ RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino);
+ }
+
+ return 0;
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
+static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sk_buff *skb;
+ u32 *buf;
+ int i;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ spin_lock(&sk->sk_receive_queue.lock);
+ buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS,
+ sk->sk_receive_queue.qlen * sizeof(u32));
+ i = 0;
+ skb_queue_walk(&sk->sk_receive_queue, skb) {
+ struct sock *req, *peer;
+
+ req = skb->sk;
+ /*
+ * The state lock is outer for the same sk's
+ * queue lock. With the other's queue locked it's
+ * OK to lock the state.
+ */
+ unix_state_lock_nested(req);
+ peer = unix_sk(req)->peer;
+ buf[i++] = (peer ? sock_i_ino(peer) : 0);
+ unix_state_unlock(req);
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+ }
+
+ return 0;
+
+rtattr_failure:
+ spin_unlock(&sk->sk_receive_queue.lock);
+ return -EMSGSIZE;
+}
+
+static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct unix_diag_rqlen *rql;
+
+ rql = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_RQLEN, sizeof(*rql));
+
+ if (sk->sk_state == TCP_LISTEN) {
+ rql->udiag_rqueue = sk->sk_receive_queue.qlen;
+ rql->udiag_wqueue = sk->sk_max_ack_backlog;
+ } else {
+ rql->udiag_rqueue = (__u32)unix_inq_len(sk);
+ rql->udiag_wqueue = (__u32)unix_outq_len(sk);
+ }
+
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+ u32 pid, u32 seq, u32 flags, int sk_ino)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct nlmsghdr *nlh;
+ struct unix_diag_msg *rep;
+
+ nlh = NLMSG_PUT(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep));
+ nlh->nlmsg_flags = flags;
+
+ rep = NLMSG_DATA(nlh);
+
+ rep->udiag_family = AF_UNIX;
+ rep->udiag_type = sk->sk_type;
+ rep->udiag_state = sk->sk_state;
+ rep->udiag_ino = sk_ino;
+ sock_diag_save_cookie(sk, rep->udiag_cookie);
+
+ if ((req->udiag_show & UDIAG_SHOW_NAME) &&
+ sk_diag_dump_name(sk, skb))
+ goto nlmsg_failure;
+
+ if ((req->udiag_show & UDIAG_SHOW_VFS) &&
+ sk_diag_dump_vfs(sk, skb))
+ goto nlmsg_failure;
+
+ if ((req->udiag_show & UDIAG_SHOW_PEER) &&
+ sk_diag_dump_peer(sk, skb))
+ goto nlmsg_failure;
+
+ if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
+ sk_diag_dump_icons(sk, skb))
+ goto nlmsg_failure;
+
+ if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
+ sk_diag_show_rqlen(sk, skb))
+ goto nlmsg_failure;
+
+ if ((req->udiag_show & UDIAG_SHOW_MEMINFO) &&
+ sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
+ goto nlmsg_failure;
+
+ nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+ return skb->len;
+
+nlmsg_failure:
+ nlmsg_trim(skb, b);
+ return -EMSGSIZE;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+ u32 pid, u32 seq, u32 flags)
+{
+ int sk_ino;
+
+ unix_state_lock(sk);
+ sk_ino = sock_i_ino(sk);
+ unix_state_unlock(sk);
+
+ if (!sk_ino)
+ return 0;
+
+ return sk_diag_fill(sk, skb, req, pid, seq, flags, sk_ino);
+}
+
+static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct unix_diag_req *req;
+ int num, s_num, slot, s_slot;
+
+ req = NLMSG_DATA(cb->nlh);
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ spin_lock(&unix_table_lock);
+ for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) {
+ struct sock *sk;
+ struct hlist_node *node;
+
+ num = 0;
+ sk_for_each(sk, node, &unix_socket_table[slot]) {
+ if (num < s_num)
+ goto next;
+ if (!(req->udiag_states & (1 << sk->sk_state)))
+ goto next;
+ if (sk_diag_dump(sk, skb, req,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI) < 0)
+ goto done;
+next:
+ num++;
+ }
+ }
+done:
+ spin_unlock(&unix_table_lock);
+ cb->args[0] = slot;
+ cb->args[1] = num;
+
+ return skb->len;
+}
+
+static struct sock *unix_lookup_by_ino(int ino)
+{
+ int i;
+ struct sock *sk;
+
+ spin_lock(&unix_table_lock);
+ for (i = 0; i <= UNIX_HASH_SIZE; i++) {
+ struct hlist_node *node;
+
+ sk_for_each(sk, node, &unix_socket_table[i])
+ if (ino == sock_i_ino(sk)) {
+ sock_hold(sk);
+ spin_unlock(&unix_table_lock);
+
+ return sk;
+ }
+ }
+
+ spin_unlock(&unix_table_lock);
+ return NULL;
+}
+
+static int unix_diag_get_exact(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct unix_diag_req *req)
+{
+ int err = -EINVAL;
+ struct sock *sk;
+ struct sk_buff *rep;
+ unsigned int extra_len;
+
+ if (req->udiag_ino == 0)
+ goto out_nosk;
+
+ sk = unix_lookup_by_ino(req->udiag_ino);
+ err = -ENOENT;
+ if (sk == NULL)
+ goto out_nosk;
+
+ err = sock_diag_check_cookie(sk, req->udiag_cookie);
+ if (err)
+ goto out;
+
+ extra_len = 256;
+again:
+ err = -ENOMEM;
+ rep = alloc_skb(NLMSG_SPACE((sizeof(struct unix_diag_msg) + extra_len)),
+ GFP_KERNEL);
+ if (!rep)
+ goto out;
+
+ err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid,
+ nlh->nlmsg_seq, 0, req->udiag_ino);
+ if (err < 0) {
+ kfree_skb(rep);
+ extra_len += 256;
+ if (extra_len >= PAGE_SIZE)
+ goto out;
+
+ goto again;
+ }
+ err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+out:
+ if (sk)
+ sock_put(sk);
+out_nosk:
+ return err;
+}
+
+static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+ int hdrlen = sizeof(struct unix_diag_req);
+
+ if (nlmsg_len(h) < hdrlen)
+ return -EINVAL;
+
+ if (h->nlmsg_flags & NLM_F_DUMP)
+ return netlink_dump_start(sock_diag_nlsk, skb, h,
+ unix_diag_dump, NULL, 0);
+ else
+ return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h));
+}
+
+static struct sock_diag_handler unix_diag_handler = {
+ .family = AF_UNIX,
+ .dump = unix_diag_handler_dump,
+};
+
+static int __init unix_diag_init(void)
+{
+ return sock_diag_register(&unix_diag_handler);
+}
+
+static void __exit unix_diag_exit(void)
+{
+ sock_diag_unregister(&unix_diag_handler);
+}
+
+module_init(unix_diag_init);
+module_exit(unix_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);
return NOTIFY_DONE;
if (dev->type == ARPHRD_X25
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
|| dev->type == ARPHRD_ETHER
#endif
) {
*ptr = X25_IFACE_CONNECT;
break;
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
case ARPHRD_ETHER:
return;
#endif
struct sk_buff *skb;
unsigned char *ptr;
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
if (nb->dev->type == ARPHRD_ETHER)
return;
#endif
*dptr = X25_IFACE_DATA;
break;
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
case ARPHRD_ETHER:
kfree_skb(skb);
return;
if (dev &&
(!(dev->flags & IFF_UP) || (dev->type != ARPHRD_X25
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
&& dev->type != ARPHRD_ETHER
#endif
))){
{
const struct flowi4 *fl4 = &fl->u.ip4;
- return addr_match(&fl4->daddr, &sel->daddr, sel->prefixlen_d) &&
- addr_match(&fl4->saddr, &sel->saddr, sel->prefixlen_s) &&
+ return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
+ addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
!((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
!((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
(fl4->flowi4_proto == sel->proto || !sel->proto) &&
case AF_INET:
dst_ops = &net->xfrm.xfrm4_dst_ops;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
dst_ops = &net->xfrm.xfrm6_dst_ops;
break;
goto free_dst;
/* Copy neighbour for reachability confirmation */
- dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour(dst)));
+ dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour_noref(dst)));
xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len);
xfrm_init_pmtu(dst_prev);
{
struct dst_entry *head, *next;
- flow_cache_flush();
-
spin_lock_bh(&xfrm_policy_sk_bundle_lock);
head = xfrm_policy_sk_bundles;
xfrm_policy_sk_bundles = NULL;
}
}
+static void xfrm_garbage_collect(struct net *net)
+{
+ flow_cache_flush();
+ __xfrm_garbage_collect(net);
+}
+
+static void xfrm_garbage_collect_deferred(struct net *net)
+{
+ flow_cache_flush_deferred();
+ __xfrm_garbage_collect(net);
+}
+
static void xfrm_init_pmtu(struct dst_entry *dst)
{
do {
return dst_metric_advmss(dst->path);
}
-static unsigned int xfrm_default_mtu(const struct dst_entry *dst)
+static unsigned int xfrm_mtu(const struct dst_entry *dst)
{
- return dst_mtu(dst->path);
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst_mtu(dst->path);
}
static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr)
dst_ops->check = xfrm_dst_check;
if (likely(dst_ops->default_advmss == NULL))
dst_ops->default_advmss = xfrm_default_advmss;
- if (likely(dst_ops->default_mtu == NULL))
- dst_ops->default_mtu = xfrm_default_mtu;
+ if (likely(dst_ops->mtu == NULL))
+ dst_ops->mtu = xfrm_mtu;
if (likely(dst_ops->negative_advice == NULL))
dst_ops->negative_advice = xfrm_negative_advice;
if (likely(dst_ops->link_failure == NULL))
if (likely(dst_ops->neigh_lookup == NULL))
dst_ops->neigh_lookup = xfrm_neigh_lookup;
if (likely(afinfo->garbage_collect == NULL))
- afinfo->garbage_collect = __xfrm_garbage_collect;
+ afinfo->garbage_collect = xfrm_garbage_collect_deferred;
xfrm_policy_afinfo[afinfo->family] = afinfo;
}
write_unlock_bh(&xfrm_policy_afinfo_lock);
case AF_INET:
xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
break;
afinfo = xfrm_policy_afinfo[AF_INET];
if (afinfo)
net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
afinfo = xfrm_policy_afinfo[AF_INET6];
if (afinfo)
net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
switch (event) {
case NETDEV_DOWN:
- __xfrm_garbage_collect(dev_net(dev));
+ xfrm_garbage_collect(dev_net(dev));
}
return NOTIFY_DONE;
}
break;
case AF_INET6:
- ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6,
- (const struct in6_addr *)daddr);
- ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6,
- (const struct in6_addr *)saddr);
+ *(struct in6_addr *)x->sel.daddr.a6 = *(struct in6_addr *)daddr;
+ *(struct in6_addr *)x->sel.saddr.a6 = *(struct in6_addr *)saddr;
x->sel.prefixlen_d = 128;
x->sel.prefixlen_s = 128;
- ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6,
- (const struct in6_addr *)saddr);
- ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6,
- (const struct in6_addr *)daddr);
+ *(struct in6_addr *)x->props.saddr.a6 = *(struct in6_addr *)saddr;
+ *(struct in6_addr *)x->id.daddr.a6 = *(struct in6_addr *)daddr;
break;
}
#include <net/netlink.h>
#include <net/ah.h>
#include <asm/uaccess.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
#include <linux/in6.h>
#endif
break;
case AF_INET6:
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
break;
#else
err = -EAFNOSUPPORT;
goto out;
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case IPPROTO_DSTOPTS:
case IPPROTO_ROUTING:
if (attrs[XFRMA_ALG_COMP] ||
break;
case AF_INET6:
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
break;
#else
return -EAFNOSUPPORT;
switch (ut[i].family) {
case AF_INET:
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
break;
#endif
return NULL;
}
break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
if (opt != IPV6_XFRM_POLICY) {
*dir = -EOPNOTSUPP;
--directory=$(srctree) --directory=$(objtree) \
--output $(obj)/config.pot
$(Q)sed -i s/CHARSET/UTF-8/ $(obj)/config.pot
- $(Q)ln -fs Kconfig.x86 arch/um/Kconfig
- $(Q)(for i in `ls $(srctree)/arch/*/Kconfig`; \
+ $(Q)(for i in `ls $(srctree)/arch/*/Kconfig \
+ $(srctree)/arch/*/um/Kconfig`; \
do \
echo " GEN $$i"; \
$(obj)/kxgettext $$i \
done )
$(Q)msguniq --sort-by-file --to-code=UTF-8 $(obj)/config.pot \
--output $(obj)/linux.pot
- $(Q)rm -f $(srctree)/arch/um/Kconfig
$(Q)rm -f $(obj)/config.pot
PHONY += allnoconfig allyesconfig allmodconfig alldefconfig randconfig
static int d_namespace_path(struct path *path, char *buf, int buflen,
char **name, int flags)
{
- struct path root, tmp;
char *res;
- int connected, error = 0;
+ int error = 0;
+ int connected = 1;
+
+ if (path->mnt->mnt_flags & MNT_INTERNAL) {
+ /* it's not mounted anywhere */
+ res = dentry_path(path->dentry, buf, buflen);
+ *name = res;
+ if (IS_ERR(res)) {
+ *name = buf;
+ return PTR_ERR(res);
+ }
+ if (path->dentry->d_sb->s_magic == PROC_SUPER_MAGIC &&
+ strncmp(*name, "/sys/", 5) == 0) {
+ /* TODO: convert over to using a per namespace
+ * control instead of hard coded /proc
+ */
+ return prepend(name, *name - buf, "/proc", 5);
+ }
+ return 0;
+ }
- /* Get the root we want to resolve too, released below */
+ /* resolve paths relative to chroot?*/
if (flags & PATH_CHROOT_REL) {
- /* resolve paths relative to chroot */
+ struct path root;
get_fs_root(current->fs, &root);
- } else {
- /* resolve paths relative to namespace */
- root.mnt = current->nsproxy->mnt_ns->root;
- root.dentry = root.mnt->mnt_root;
- path_get(&root);
+ res = __d_path(path, &root, buf, buflen);
+ if (res && !IS_ERR(res)) {
+ /* everything's fine */
+ *name = res;
+ path_put(&root);
+ goto ok;
+ }
+ path_put(&root);
+ connected = 0;
}
- tmp = root;
- res = __d_path(path, &tmp, buf, buflen);
+ res = d_absolute_path(path, buf, buflen);
*name = res;
/* handle error conditions - and still allow a partial path to
*name = buf;
goto out;
}
+ if (!our_mnt(path->mnt))
+ connected = 0;
+ok:
/* Handle two cases:
* 1. A deleted dentry && profile is not allowing mediation of deleted
* 2. On some filesystems, newly allocated dentries appear to the
goto out;
}
- /* Determine if the path is connected to the expected root */
- connected = tmp.dentry == root.dentry && tmp.mnt == root.mnt;
-
- /* If the path is not connected,
+ /* If the path is not connected to the expected root,
* check if it is a sysctl and handle specially else remove any
* leading / that __d_path may have returned.
* Unless
* namespace root.
*/
if (!connected) {
- /* is the disconnect path a sysctl? */
- if (tmp.dentry->d_sb->s_magic == PROC_SUPER_MAGIC &&
- strncmp(*name, "/sys/", 5) == 0) {
- /* TODO: convert over to using a per namespace
- * control instead of hard coded /proc
- */
- error = prepend(name, *name - buf, "/proc", 5);
- } else if (!(flags & PATH_CONNECT_PATH) &&
+ if (!(flags & PATH_CONNECT_PATH) &&
!(((flags & CHROOT_NSCONNECT) == CHROOT_NSCONNECT) &&
- (tmp.mnt == current->nsproxy->mnt_ns->root &&
- tmp.dentry == tmp.mnt->mnt_root))) {
+ our_mnt(path->mnt))) {
/* disconnected path, don't return pathname starting
* with '/'
*/
}
out:
- path_put(&root);
-
return error;
}
struct crypto_shash *hmac_tfm;
+static DEFINE_MUTEX(mutex);
+
static struct shash_desc *init_desc(void)
{
int rc;
struct shash_desc *desc;
if (hmac_tfm == NULL) {
+ mutex_lock(&mutex);
+ if (hmac_tfm)
+ goto out;
hmac_tfm = crypto_alloc_shash(evm_hmac, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(hmac_tfm)) {
pr_err("Can not allocate %s (reason: %ld)\n",
evm_hmac, PTR_ERR(hmac_tfm));
rc = PTR_ERR(hmac_tfm);
hmac_tfm = NULL;
+ mutex_unlock(&mutex);
+ return ERR_PTR(rc);
+ }
+ rc = crypto_shash_setkey(hmac_tfm, evmkey, evmkey_len);
+ if (rc) {
+ crypto_free_shash(hmac_tfm);
+ hmac_tfm = NULL;
+ mutex_unlock(&mutex);
return ERR_PTR(rc);
}
+out:
+ mutex_unlock(&mutex);
}
desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac_tfm),
desc->tfm = hmac_tfm;
desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- rc = crypto_shash_setkey(hmac_tfm, evmkey, evmkey_len);
- if (rc)
- goto out;
rc = crypto_shash_init(desc);
-out:
if (rc) {
kfree(desc);
return ERR_PTR(rc);
# Makefile for encrypted keys
#
-obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted.o ecryptfs_format.o
-obj-$(CONFIG_TRUSTED_KEYS) += masterkey_trusted.o
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys.o
+
+encrypted-keys-y := encrypted.o ecryptfs_format.o
+masterkey-$(CONFIG_TRUSTED_KEYS) := masterkey_trusted.o
+masterkey-$(CONFIG_TRUSTED_KEYS)-$(CONFIG_ENCRYPTED_KEYS) := masterkey_trusted.o
+encrypted-keys-y += $(masterkey-y) $(masterkey-m-m)
goto out;
if (IS_ERR(mkey)) {
- int ret = PTR_ERR(epayload);
+ int ret = PTR_ERR(mkey);
if (ret == -ENOTSUPP)
pr_info("encrypted_key: key %s not supported",
#define __ENCRYPTED_KEY_H
#define ENCRYPTED_DEBUG 0
-#ifdef CONFIG_TRUSTED_KEYS
+#if defined(CONFIG_TRUSTED_KEYS) || \
+ (defined(CONFIG_TRUSTED_KEYS_MODULE) && defined(CONFIG_ENCRYPTED_KEYS_MODULE))
extern struct key *request_trusted_key(const char *trusted_desc,
u8 **master_key, size_t *master_keylen);
#else
key->expiry = 0;
}
- kfree_rcu(zap, rcu);
+ if (zap)
+ kfree_rcu(zap, rcu);
error:
return ret;
int offset, ret = 0;
struct ipv6hdr *ip6;
u8 nexthdr;
+ __be16 frag_off;
ip6 = ipv6_hdr(skb);
if (ip6 == NULL)
return -EINVAL;
- ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
- ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+ ad->u.net.v6info.saddr = ip6->saddr;
+ ad->u.net.v6info.daddr = ip6->daddr;
ret = 0;
/* IPv6 can have several extension header before the Transport header
* skip them */
offset = skb_network_offset(skb);
offset += sizeof(*ip6);
nexthdr = ip6->nexthdr;
- offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+ offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
if (offset < 0)
return 0;
if (proto)
void **value, size_t *len)
{
if (unlikely(IS_PRIVATE(inode)))
- return 0;
+ return -EOPNOTSUPP;
return security_ops->inode_init_security(inode, dir, qstr, name, value,
len);
}
return SECCLASS_NETLINK_ROUTE_SOCKET;
case NETLINK_FIREWALL:
return SECCLASS_NETLINK_FIREWALL_SOCKET;
- case NETLINK_INET_DIAG:
+ case NETLINK_SOCK_DIAG:
return SECCLASS_NETLINK_TCPDIAG_SOCKET;
case NETLINK_NFLOG:
return SECCLASS_NETLINK_NFLOG_SOCKET;
u8 nexthdr;
int ret = -EINVAL, offset;
struct ipv6hdr _ipv6h, *ip6;
+ __be16 frag_off;
offset = skb_network_offset(skb);
ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
if (ip6 == NULL)
goto out;
- ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
- ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+ ad->u.net.v6info.saddr = ip6->saddr;
+ ad->u.net.v6info.daddr = ip6->daddr;
ret = 0;
nexthdr = ip6->nexthdr;
offset += sizeof(_ipv6h);
- offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+ offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
if (offset < 0)
goto out;
if (family == PF_INET)
ad.u.net.v4info.saddr = addr4->sin_addr.s_addr;
else
- ipv6_addr_copy(&ad.u.net.v6info.saddr, &addr6->sin6_addr);
+ ad.u.net.v6info.saddr = addr6->sin6_addr;
err = avc_has_perm(sksec->sid, sid,
sksec->sclass, node_perm, &ad);
case PF_INET6:
ret = security_node_sid(PF_INET6,
addr, sizeof(struct in6_addr), sid);
- ipv6_addr_copy(&new->nsec.addr.ipv6, addr);
+ new->nsec.addr.ipv6 = *(struct in6_addr *)addr;
break;
default:
BUG();
if (sel_netport_hash[idx].size == SEL_NETPORT_HASH_BKT_LIMIT) {
struct sel_netport *tail;
tail = list_entry(
- rcu_dereference(sel_netport_hash[idx].list.prev),
+ rcu_dereference_protected(
+ sel_netport_hash[idx].list.prev,
+ lockdep_is_held(&sel_netport_lock)),
struct sel_netport, list);
list_del_rcu(&tail->list);
kfree_rcu(tail, rcu);
const char *smack_cipso_option = SMACK_CIPSO_OPTION;
-
-#define SEQ_READ_FINISHED ((loff_t)-1)
-
/*
* Values for parsing cipso rules
* SMK_DIGITLEN: Length of a digit field in a rule.
rc = count;
/*
+ * If this is "load" as opposed to "load-self" and a new rule
+ * it needs to get added for reporting.
* smk_set_access returns true if there was already a rule
* for the subject/object pair, and false if it was new.
*/
- if (!smk_set_access(rule, rule_list, rule_lock)) {
+ if (load && !smk_set_access(rule, rule_list, rule_lock)) {
smlp = kzalloc(sizeof(*smlp), GFP_KERNEL);
if (smlp != NULL) {
smlp->smk_rule = rule;
return rc;
}
-
/*
- * Seq_file read operations for /smack/load
+ * Core logic for smackfs seq list operations.
*/
-static void *load_seq_start(struct seq_file *s, loff_t *pos)
+static void *smk_seq_start(struct seq_file *s, loff_t *pos,
+ struct list_head *head)
{
struct list_head *list;
* This is 0 the first time through.
*/
if (s->index == 0)
- s->private = &smack_rule_list;
+ s->private = head;
if (s->private == NULL)
return NULL;
return list;
}
-static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
+static void *smk_seq_next(struct seq_file *s, void *v, loff_t *pos,
+ struct list_head *head)
{
struct list_head *list = v;
- if (list_is_last(list, &smack_rule_list)) {
+ if (list_is_last(list, head)) {
s->private = NULL;
return NULL;
}
return list->next;
}
+static void smk_seq_stop(struct seq_file *s, void *v)
+{
+ /* No-op */
+}
+
+/*
+ * Seq_file read operations for /smack/load
+ */
+
+static void *load_seq_start(struct seq_file *s, loff_t *pos)
+{
+ return smk_seq_start(s, pos, &smack_rule_list);
+}
+
+static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+ return smk_seq_next(s, v, pos, &smack_rule_list);
+}
+
static int load_seq_show(struct seq_file *s, void *v)
{
struct list_head *list = v;
return 0;
}
-static void load_seq_stop(struct seq_file *s, void *v)
-{
- /* No-op */
-}
-
static const struct seq_operations load_seq_ops = {
.start = load_seq_start,
.next = load_seq_next,
.show = load_seq_show,
- .stop = load_seq_stop,
+ .stop = smk_seq_stop,
};
/**
static void *cipso_seq_start(struct seq_file *s, loff_t *pos)
{
- if (*pos == SEQ_READ_FINISHED)
- return NULL;
- if (list_empty(&smack_known_list))
- return NULL;
-
- return smack_known_list.next;
+ return smk_seq_start(s, pos, &smack_known_list);
}
static void *cipso_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct list_head *list = v;
-
- /*
- * labels with no associated cipso value wont be printed
- * in cipso_seq_show
- */
- if (list_is_last(list, &smack_known_list)) {
- *pos = SEQ_READ_FINISHED;
- return NULL;
- }
-
- return list->next;
+ return smk_seq_next(s, v, pos, &smack_known_list);
}
/*
return 0;
}
-static void cipso_seq_stop(struct seq_file *s, void *v)
-{
- /* No-op */
-}
-
static const struct seq_operations cipso_seq_ops = {
.start = cipso_seq_start,
- .stop = cipso_seq_stop,
.next = cipso_seq_next,
.show = cipso_seq_show,
+ .stop = smk_seq_stop,
};
/**
static void *netlbladdr_seq_start(struct seq_file *s, loff_t *pos)
{
- if (*pos == SEQ_READ_FINISHED)
- return NULL;
- if (list_empty(&smk_netlbladdr_list))
- return NULL;
- return smk_netlbladdr_list.next;
+ return smk_seq_start(s, pos, &smk_netlbladdr_list);
}
static void *netlbladdr_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct list_head *list = v;
-
- if (list_is_last(list, &smk_netlbladdr_list)) {
- *pos = SEQ_READ_FINISHED;
- return NULL;
- }
-
- return list->next;
+ return smk_seq_next(s, v, pos, &smk_netlbladdr_list);
}
#define BEBITS (sizeof(__be32) * 8)
return 0;
}
-static void netlbladdr_seq_stop(struct seq_file *s, void *v)
-{
- /* No-op */
-}
-
static const struct seq_operations netlbladdr_seq_ops = {
.start = netlbladdr_seq_start,
- .stop = netlbladdr_seq_stop,
.next = netlbladdr_seq_next,
.show = netlbladdr_seq_show,
+ .stop = smk_seq_stop,
};
/**
{
struct task_smack *tsp = current_security();
- if (*pos == SEQ_READ_FINISHED)
- return NULL;
- if (list_empty(&tsp->smk_rules))
- return NULL;
- return tsp->smk_rules.next;
+ return smk_seq_start(s, pos, &tsp->smk_rules);
}
static void *load_self_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
struct task_smack *tsp = current_security();
- struct list_head *list = v;
- if (list_is_last(list, &tsp->smk_rules)) {
- *pos = SEQ_READ_FINISHED;
- return NULL;
- }
- return list->next;
+ return smk_seq_next(s, v, pos, &tsp->smk_rules);
}
static int load_self_seq_show(struct seq_file *s, void *v)
return 0;
}
-static void load_self_seq_stop(struct seq_file *s, void *v)
-{
- /* No-op */
-}
-
static const struct seq_operations load_self_seq_ops = {
.start = load_self_seq_start,
.next = load_self_seq_next,
.show = load_self_seq_show,
- .stop = load_self_seq_stop,
+ .stop = smk_seq_stop,
};
{
char *pos = ERR_PTR(-ENOMEM);
if (buflen >= 256) {
- struct path ns_root = { };
/* go to whatever namespace root we are under */
- pos = __d_path(path, &ns_root, buffer, buflen - 1);
+ pos = d_absolute_path(path, buffer, buflen - 1);
if (!IS_ERR(pos) && *pos == '/' && pos[1]) {
struct inode *inode = path->dentry->d_inode;
if (inode && S_ISDIR(inode->i_mode)) {
pos = tomoyo_get_local_path(path->dentry, buf,
buf_len - 1);
/* Get absolute name for the rest. */
- else
+ else {
pos = tomoyo_get_absolute_path(path, buf, buf_len - 1);
+ /*
+ * Fall back to local name if absolute name is not
+ * available.
+ */
+ if (pos == ERR_PTR(-EINVAL))
+ pos = tomoyo_get_local_path(path->dentry, buf,
+ buf_len - 1);
+ }
encode:
if (IS_ERR(pos))
continue;
/* AC97 v2.2 specifications says minimum 1 us. */
udelay(2);
gpio_set_value(chip->reset_pin, 1);
+ } else {
+ ac97c_writel(chip, MR, AC97C_MR_WRST | AC97C_MR_ENA);
+ udelay(2);
+ ac97c_writel(chip, MR, AC97C_MR_ENA);
}
}
struct cs5535audio_dma_desc *desc =
&((struct cs5535audio_dma_desc *) dma->desc_buf.area)[i];
desc->addr = cpu_to_le32(addr);
- desc->size = cpu_to_le32(period_bytes);
+ desc->size = cpu_to_le16(period_bytes);
desc->ctlreserved = cpu_to_le16(PRD_EOP);
desc_addr += sizeof(struct cs5535audio_dma_desc);
addr += period_bytes;
/* Search for codec ID */
for (q = tbl; q->subvendor; q++) {
- unsigned long vendorid = (q->subdevice) | (q->subvendor << 16);
-
- if (vendorid == codec->subsystem_id)
+ unsigned int mask = 0xffff0000 | q->subdevice_mask;
+ unsigned int id = (q->subdevice | (q->subvendor << 16)) & mask;
+ if ((codec->subsystem_id & mask) == id)
break;
}
buf + ELD_FIXED_BYTES + mnl + 3 * i);
}
+ /*
+ * HDMI sink's ELD info cannot always be retrieved for now, e.g.
+ * in console or for audio devices. Assume the highest speakers
+ * configuration, to _not_ prohibit multi-channel audio playback.
+ */
+ if (!e->spk_alloc)
+ e->spk_alloc = 0xffff;
+
+ e->eld_valid = true;
return 0;
out_fail:
- e->eld_ver = 0;
return -EINVAL;
}
* ELD is valid, actual eld_size is assigned in hdmi_update_eld()
*/
- if (!eld->eld_valid)
- return -ENOENT;
-
size = snd_hdmi_get_eld_size(codec, nid);
if (size == 0) {
/* wfg: workaround for ASUS P5E-VM HDMI board */
for (i = 0; i < size; i++) {
unsigned int val = hdmi_get_eld_data(codec, nid, i);
+ /*
+ * Graphics driver might be writing to ELD buffer right now.
+ * Just abort. The caller will repoll after a while.
+ */
if (!(val & AC_ELDD_ELD_VALID)) {
- if (!i) {
- snd_printd(KERN_INFO
- "HDMI: invalid ELD data\n");
- ret = -EINVAL;
- goto error;
- }
snd_printd(KERN_INFO
"HDMI: invalid ELD data byte %d\n", i);
- val = 0;
- } else
- val &= AC_ELDD_ELD_DATA;
+ ret = -EINVAL;
+ goto error;
+ }
+ val &= AC_ELDD_ELD_DATA;
+ /*
+ * The first byte cannot be zero. This can happen on some DVI
+ * connections. Some Intel chips may also need some 250ms delay
+ * to return non-zero ELD data, even when the graphics driver
+ * correctly writes ELD content before setting ELD_valid bit.
+ */
+ if (!val && !i) {
+ snd_printdd(KERN_INFO "HDMI: 0 ELD data\n");
+ ret = -EINVAL;
+ goto error;
+ }
buf[i] = val;
}
SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB),
+ SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS 1101HA", POS_FIX_LPIB),
SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB),
- SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1297, 0x3166, "Shuttle", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1458, 0xa022, "ga-ma770-ud3", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1462, 0x1002, "MSI Wind U115", POS_FIX_LPIB),
/* SCH */
{ PCI_DEVICE(0x8086, 0x811b),
.driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP |
- AZX_DCAPS_BUFSIZE},
+ AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Poulsbo */
+ /* ICH */
{ PCI_DEVICE(0x8086, 0x2668),
.driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC |
AZX_DCAPS_BUFSIZE }, /* ICH6 */
int spk_alloc;
int sad_count;
struct cea_sad sad[ELD_MAX_SAD];
+ /*
+ * all fields above eld_buffer will be cleared before updating ELD
+ */
char eld_buffer[ELD_MAX_SIZE];
#ifdef CONFIG_PROC_FS
struct snd_info_entry *proc_entry;
unsigned int gpio_mask;
unsigned int gpio_dir;
unsigned int gpio_data;
+ unsigned int gpio_eapd_hp; /* EAPD GPIO bit for headphones */
+ unsigned int gpio_eapd_speaker; /* EAPD GPIO bit for speakers */
struct hda_pcm pcm_rec[2]; /* PCM information */
CS420X_MBP53,
CS420X_MBP55,
CS420X_IMAC27,
+ CS420X_APPLE,
CS420X_AUTO,
CS420X_MODELS
};
return snd_hda_multi_out_dig_cleanup(codec, &spec->multiout);
}
+static void cs_update_input_select(struct hda_codec *codec)
+{
+ struct cs_spec *spec = codec->spec;
+ if (spec->cur_adc)
+ snd_hda_codec_write(codec, spec->cur_adc, 0,
+ AC_VERB_SET_CONNECT_SEL,
+ spec->adc_idx[spec->cur_input]);
+}
+
/*
* Analog capture
*/
spec->cur_adc = spec->adc_nid[spec->cur_input];
spec->cur_adc_stream_tag = stream_tag;
spec->cur_adc_format = format;
+ cs_update_input_select(codec);
snd_hda_codec_setup_stream(codec, spec->cur_adc, stream_tag, 0, format);
return 0;
}
spec->cur_adc_stream_tag, 0,
spec->cur_adc_format);
}
- snd_hda_codec_write(codec, spec->cur_adc, 0,
- AC_VERB_SET_CONNECT_SEL,
- spec->adc_idx[idx]);
spec->cur_input = idx;
+ cs_update_input_select(codec);
return 1;
}
spdif_present ? 0 : PIN_OUT);
}
}
- if (spec->board_config == CS420X_MBP53 ||
- spec->board_config == CS420X_MBP55 ||
- spec->board_config == CS420X_IMAC27) {
- unsigned int gpio = hp_present ? 0x02 : 0x08;
+ if (spec->gpio_eapd_hp) {
+ unsigned int gpio = hp_present ?
+ spec->gpio_eapd_hp : spec->gpio_eapd_speaker;
snd_hda_codec_write(codec, 0x01, 0,
AC_VERB_SET_GPIO_DATA, gpio);
}
} else {
spec->cur_input = spec->last_input;
}
-
- snd_hda_codec_write_cache(codec, spec->cur_adc, 0,
- AC_VERB_SET_CONNECT_SEL,
- spec->adc_idx[spec->cur_input]);
+ cs_update_input_select(codec);
} else {
if (present)
change_cur_input(codec, spec->automic_idx, 0);
cs_automic(codec);
else {
spec->cur_adc = spec->adc_nid[spec->cur_input];
- snd_hda_codec_write(codec, spec->cur_adc, 0,
- AC_VERB_SET_CONNECT_SEL,
- spec->adc_idx[spec->cur_input]);
+ cs_update_input_select(codec);
}
} else {
change_cur_input(codec, spec->cur_input, 1);
[CS420X_MBP53] = "mbp53",
[CS420X_MBP55] = "mbp55",
[CS420X_IMAC27] = "imac27",
+ [CS420X_APPLE] = "apple",
[CS420X_AUTO] = "auto",
};
SND_PCI_QUIRK(0x10de, 0x0d94, "MacBookAir 3,1(2)", CS420X_MBP55),
SND_PCI_QUIRK(0x10de, 0xcb79, "MacBookPro 5,5", CS420X_MBP55),
SND_PCI_QUIRK(0x10de, 0xcb89, "MacBookPro 7,1", CS420X_MBP55),
- SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),
+ /* this conflicts with too many other models */
+ /*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/
+ {} /* terminator */
+};
+
+static const struct snd_pci_quirk cs420x_codec_cfg_tbl[] = {
+ SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE),
{} /* terminator */
};
spec->board_config =
snd_hda_check_board_config(codec, CS420X_MODELS,
cs420x_models, cs420x_cfg_tbl);
+ if (spec->board_config < 0)
+ spec->board_config =
+ snd_hda_check_board_codec_sid_config(codec,
+ CS420X_MODELS, NULL, cs420x_codec_cfg_tbl);
if (spec->board_config >= 0)
fix_pincfg(codec, spec->board_config, cs_pincfgs);
case CS420X_IMAC27:
case CS420X_MBP53:
case CS420X_MBP55:
- /* GPIO1 = headphones */
- /* GPIO3 = speakers */
- spec->gpio_mask = 0x0a;
- spec->gpio_dir = 0x0a;
+ case CS420X_APPLE:
+ spec->gpio_eapd_hp = 2; /* GPIO1 = headphones */
+ spec->gpio_eapd_speaker = 8; /* GPIO3 = speakers */
+ spec->gpio_mask = spec->gpio_dir =
+ spec->gpio_eapd_hp | spec->gpio_eapd_speaker;
break;
}
hda_nid_t pin_nid;
int num_mux_nids;
hda_nid_t mux_nids[HDA_MAX_CONNECTIONS];
+
+ struct hda_codec *codec;
struct hdmi_eld sink_eld;
+ struct delayed_work work;
+ int repoll_count;
};
struct hdmi_spec {
* Unsolicited events
*/
-static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
- struct hdmi_eld *eld);
+static void hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll);
static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
{
int pd = !!(res & AC_UNSOL_RES_PD);
int eldv = !!(res & AC_UNSOL_RES_ELDV);
int pin_idx;
- struct hdmi_eld *eld;
printk(KERN_INFO
"HDMI hot plug event: Codec=%d Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
pin_idx = pin_nid_to_pin_index(spec, pin_nid);
if (pin_idx < 0)
return;
- eld = &spec->pins[pin_idx].sink_eld;
-
- hdmi_present_sense(codec, pin_nid, eld);
- /*
- * HDMI sink's ELD info cannot always be retrieved for now, e.g.
- * in console or for audio devices. Assume the highest speakers
- * configuration, to _not_ prohibit multi-channel audio playback.
- */
- if (!eld->spk_alloc)
- eld->spk_alloc = 0xffff;
+ hdmi_present_sense(&spec->pins[pin_idx], 1);
}
static void hdmi_non_intrinsic_event(struct hda_codec *codec, unsigned int res)
return 0;
}
-static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
- struct hdmi_eld *eld)
+static void hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
{
+ struct hda_codec *codec = per_pin->codec;
+ struct hdmi_eld *eld = &per_pin->sink_eld;
+ hda_nid_t pin_nid = per_pin->pin_nid;
/*
* Always execute a GetPinSense verb here, even when called from
* hdmi_intrinsic_event; for some NVIDIA HW, the unsolicited
* the unsolicited response to avoid custom WARs.
*/
int present = snd_hda_pin_sense(codec, pin_nid);
+ bool eld_valid = false;
- memset(eld, 0, sizeof(*eld));
+ memset(eld, 0, offsetof(struct hdmi_eld, eld_buffer));
eld->monitor_present = !!(present & AC_PINSENSE_PRESENCE);
if (eld->monitor_present)
- eld->eld_valid = !!(present & AC_PINSENSE_ELDV);
- else
- eld->eld_valid = 0;
+ eld_valid = !!(present & AC_PINSENSE_ELDV);
printk(KERN_INFO
"HDMI status: Codec=%d Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
- codec->addr, pin_nid, eld->monitor_present, eld->eld_valid);
+ codec->addr, pin_nid, eld->monitor_present, eld_valid);
- if (eld->eld_valid)
+ if (eld_valid) {
if (!snd_hdmi_get_eld(eld, codec, pin_nid))
snd_hdmi_show_eld(eld);
+ else if (repoll) {
+ queue_delayed_work(codec->bus->workq,
+ &per_pin->work,
+ msecs_to_jiffies(300));
+ }
+ }
snd_hda_input_jack_report(codec, pin_nid);
}
+static void hdmi_repoll_eld(struct work_struct *work)
+{
+ struct hdmi_spec_per_pin *per_pin =
+ container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
+
+ if (per_pin->repoll_count++ > 6)
+ per_pin->repoll_count = 0;
+
+ hdmi_present_sense(per_pin, per_pin->repoll_count);
+}
+
static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
{
struct hdmi_spec *spec = codec->spec;
if (err < 0)
return err;
- hdmi_present_sense(codec, per_pin->pin_nid, &per_pin->sink_eld);
+ hdmi_present_sense(per_pin, 0);
return 0;
}
AC_VERB_SET_UNSOLICITED_ENABLE,
AC_USRSP_EN | pin_nid);
+ per_pin->codec = codec;
+ INIT_DELAYED_WORK(&per_pin->work, hdmi_repoll_eld);
snd_hda_eld_proc_new(codec, eld, pin_idx);
}
return 0;
struct hdmi_spec_per_pin *per_pin = &spec->pins[pin_idx];
struct hdmi_eld *eld = &per_pin->sink_eld;
+ cancel_delayed_work(&per_pin->work);
snd_hda_eld_proc_free(codec, eld);
}
snd_hda_input_jack_free(codec);
+ flush_workqueue(codec->bus->workq);
kfree(spec);
}
return false;
}
+static inline hda_nid_t get_capsrc(struct alc_spec *spec, int idx)
+{
+ return spec->capsrc_nids ?
+ spec->capsrc_nids[idx] : spec->adc_nids[idx];
+}
+
/* select the given imux item; either unmute exclusively or select the route */
static int alc_mux_select(struct hda_codec *codec, unsigned int adc_idx,
unsigned int idx, bool force)
imux = &spec->input_mux[mux_idx];
if (!imux->num_items && mux_idx > 0)
imux = &spec->input_mux[0];
+ if (!imux->num_items)
+ return 0;
if (idx >= imux->num_items)
idx = imux->num_items - 1;
adc_idx = spec->dyn_adc_idx[idx];
}
- nid = spec->capsrc_nids ?
- spec->capsrc_nids[adc_idx] : spec->adc_nids[adc_idx];
+ nid = get_capsrc(spec, adc_idx);
/* no selection? */
num_conns = snd_hda_get_conn_list(codec, nid, NULL);
spec->imux_pins[2] = spec->dock_mic_pin;
for (i = 0; i < 3; i++) {
strcpy(imux->items[i].label, texts[i]);
- if (spec->imux_pins[i])
+ if (spec->imux_pins[i]) {
+ hda_nid_t pin = spec->imux_pins[i];
+ int c;
+ for (c = 0; c < spec->num_adc_nids; c++) {
+ hda_nid_t cap = get_capsrc(spec, c);
+ int idx = get_connection_index(codec, cap, pin);
+ if (idx >= 0) {
+ imux->items[i].index = idx;
+ break;
+ }
+ }
imux->num_items = i + 1;
+ }
}
spec->num_mux_defs = 1;
spec->input_mux = imux;
switch (fix->type) {
case ALC_FIXUP_SKU:
if (action != ALC_FIXUP_ACT_PRE_PROBE || !fix->v.sku)
- break;;
+ break;
snd_printdd(KERN_INFO "hda_codec: %s: "
"Apply sku override for %s\n",
codec->chip_name, modelname);
if (!kctl)
kctl = snd_hda_find_mixer_ctl(codec, "Input Source");
for (i = 0; kctl && i < kctl->count; i++) {
- const hda_nid_t *nids = spec->capsrc_nids;
- if (!nids)
- nids = spec->adc_nids;
- err = snd_hda_add_nid(codec, kctl, i, nids[i]);
+ err = snd_hda_add_nid(codec, kctl, i,
+ get_capsrc(spec, i));
if (err < 0)
return err;
}
case AUTO_PIN_SPEAKER_OUT:
if (cfg->line_outs == 1)
return "Speaker";
+ if (cfg->line_outs == 2)
+ return ch ? "Bass Speaker" : "Speaker";
break;
case AUTO_PIN_HP_OUT:
/* for multi-io case, only the primary out */
}
for (c = 0; c < num_adcs; c++) {
- hda_nid_t cap = spec->capsrc_nids ?
- spec->capsrc_nids[c] : spec->adc_nids[c];
+ hda_nid_t cap = get_capsrc(spec, c);
idx = get_connection_index(codec, cap, pin);
if (idx >= 0) {
spec->imux_pins[imux->num_items] = pin;
if (!nid)
continue;
if (found_in_nid_list(nid, spec->multiout.dac_nids,
- spec->multiout.num_dacs))
+ ARRAY_SIZE(spec->private_dac_nids)))
continue;
if (found_in_nid_list(nid, spec->multiout.hp_out_nid,
ARRAY_SIZE(spec->multiout.hp_out_nid)))
return 0;
}
+/* return 0 if no possible DAC is found, 1 if one or more found */
static int alc_auto_fill_extra_dacs(struct hda_codec *codec, int num_outs,
const hda_nid_t *pins, hda_nid_t *dacs)
{
if (!dacs[i])
dacs[i] = alc_auto_look_for_dac(codec, pins[i]);
}
- return 0;
+ return 1;
}
static int alc_auto_fill_multi_ios(struct hda_codec *codec,
static int alc_auto_fill_dac_nids(struct hda_codec *codec)
{
struct alc_spec *spec = codec->spec;
- const struct auto_pin_cfg *cfg = &spec->autocfg;
+ struct auto_pin_cfg *cfg = &spec->autocfg;
bool redone = false;
int i;
spec->multiout.extra_out_nid[0] = 0;
memset(spec->private_dac_nids, 0, sizeof(spec->private_dac_nids));
spec->multiout.dac_nids = spec->private_dac_nids;
+ spec->multi_ios = 0;
/* fill hard-wired DACs first */
if (!redone) {
for (i = 0; i < cfg->line_outs; i++) {
if (spec->private_dac_nids[i])
spec->multiout.num_dacs++;
- else
+ else {
memmove(spec->private_dac_nids + i,
spec->private_dac_nids + i + 1,
sizeof(hda_nid_t) * (cfg->line_outs - i - 1));
+ spec->private_dac_nids[cfg->line_outs - 1] = 0;
+ }
}
if (cfg->line_outs == 1 && cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) {
if (cfg->line_out_type != AUTO_PIN_HP_OUT)
alc_auto_fill_extra_dacs(codec, cfg->hp_outs, cfg->hp_pins,
spec->multiout.hp_out_nid);
- if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT)
- alc_auto_fill_extra_dacs(codec, cfg->speaker_outs, cfg->speaker_pins,
- spec->multiout.extra_out_nid);
+ if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) {
+ int err = alc_auto_fill_extra_dacs(codec, cfg->speaker_outs,
+ cfg->speaker_pins,
+ spec->multiout.extra_out_nid);
+ /* if no speaker volume is assigned, try again as the primary
+ * output
+ */
+ if (!err && cfg->speaker_outs > 0 &&
+ cfg->line_out_type == AUTO_PIN_HP_OUT) {
+ cfg->hp_outs = cfg->line_outs;
+ memcpy(cfg->hp_pins, cfg->line_out_pins,
+ sizeof(cfg->hp_pins));
+ cfg->line_outs = cfg->speaker_outs;
+ memcpy(cfg->line_out_pins, cfg->speaker_pins,
+ sizeof(cfg->speaker_pins));
+ cfg->speaker_outs = 0;
+ memset(cfg->speaker_pins, 0, sizeof(cfg->speaker_pins));
+ cfg->line_out_type = AUTO_PIN_SPEAKER_OUT;
+ redone = false;
+ goto again;
+ }
+ }
return 0;
}
}
static int alc_auto_create_extra_out(struct hda_codec *codec, hda_nid_t pin,
- hda_nid_t dac, const char *pfx)
+ hda_nid_t dac, const char *pfx,
+ int cidx)
{
struct alc_spec *spec = codec->spec;
hda_nid_t sw, vol;
if (is_ctl_used(spec->sw_ctls, val))
return 0; /* already created */
mark_ctl_usage(spec->sw_ctls, val);
- return add_pb_sw_ctrl(spec, ALC_CTL_WIDGET_MUTE, pfx, val);
+ return __add_pb_sw_ctrl(spec, ALC_CTL_WIDGET_MUTE, pfx, cidx, val);
}
sw = alc_look_for_out_mute_nid(codec, pin, dac);
vol = alc_look_for_out_vol_nid(codec, pin, dac);
- err = alc_auto_add_stereo_vol(codec, pfx, 0, vol);
+ err = alc_auto_add_stereo_vol(codec, pfx, cidx, vol);
if (err < 0)
return err;
- err = alc_auto_add_stereo_sw(codec, pfx, 0, sw);
+ err = alc_auto_add_stereo_sw(codec, pfx, cidx, sw);
if (err < 0)
return err;
return 0;
hda_nid_t dac = *dacs;
if (!dac)
dac = spec->multiout.dac_nids[0];
- return alc_auto_create_extra_out(codec, *pins, dac, pfx);
+ return alc_auto_create_extra_out(codec, *pins, dac, pfx, 0);
}
if (dacs[num_pins - 1]) {
/* OK, we have a multi-output system with individual volumes */
for (i = 0; i < num_pins; i++) {
- snprintf(name, sizeof(name), "%s %s",
- pfx, channel_name[i]);
- err = alc_auto_create_extra_out(codec, pins[i], dacs[i],
- name);
+ if (num_pins >= 3) {
+ snprintf(name, sizeof(name), "%s %s",
+ pfx, channel_name[i]);
+ err = alc_auto_create_extra_out(codec, pins[i], dacs[i],
+ name, 0);
+ } else {
+ err = alc_auto_create_extra_out(codec, pins[i], dacs[i],
+ pfx, i);
+ }
if (err < 0)
return err;
}
if (!pin)
return 0;
for (i = 0; i < spec->num_adc_nids; i++) {
- hda_nid_t cap = spec->capsrc_nids ?
- spec->capsrc_nids[i] : spec->adc_nids[i];
+ hda_nid_t cap = get_capsrc(spec, i);
int idx;
idx = get_connection_index(codec, cap, pin);
unsigned int gpio_mute;
unsigned int gpio_led;
unsigned int gpio_led_polarity;
+ unsigned int vref_mute_led_nid; /* pin NID for mute-LED vref control */
unsigned int vref_led;
/* stream */
/* power management */
unsigned int num_pwrs;
- const unsigned int *pwr_mapping;
const hda_nid_t *pwr_nids;
const hda_nid_t *dac_list;
#define STAC92HD83_DAC_COUNT 3
-static const hda_nid_t stac92hd83xxx_pwr_nids[4] = {
- 0xa, 0xb, 0xd, 0xe,
+static const hda_nid_t stac92hd83xxx_pwr_nids[7] = {
+ 0x0a, 0x0b, 0x0c, 0xd, 0x0e,
+ 0x0f, 0x10
};
static const hda_nid_t stac92hd83xxx_slave_dig_outs[2] = {
0x1e, 0,
};
-static const unsigned int stac92hd83xxx_pwr_mapping[4] = {
- 0x03, 0x0c, 0x20, 0x40,
-};
-
static const hda_nid_t stac92hd83xxx_dmic_nids[] = {
0x11, 0x20,
};
"Alienware M17x", STAC_ALIENWARE_M17X),
SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x043a,
"Alienware M17x", STAC_ALIENWARE_M17X),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
+ "Alienware M17x", STAC_ALIENWARE_M17X),
{} /* terminator */
};
spec->eapd_switch = val;
get_int_hint(codec, "gpio_led_polarity", &spec->gpio_led_polarity);
if (get_int_hint(codec, "gpio_led", &spec->gpio_led)) {
- if (spec->gpio_led <= 8) {
- spec->gpio_mask |= spec->gpio_led;
- spec->gpio_dir |= spec->gpio_led;
- if (spec->gpio_led_polarity)
- spec->gpio_data |= spec->gpio_led;
- }
+ spec->gpio_mask |= spec->gpio_led;
+ spec->gpio_dir |= spec->gpio_led;
+ if (spec->gpio_led_polarity)
+ spec->gpio_data |= spec->gpio_led;
}
}
int pinctl, def_conf;
/* power on when no jack detection is available */
- if (!spec->hp_detect) {
+ /* or when the VREF is used for controlling LED */
+ if (!spec->hp_detect ||
+ spec->vref_mute_led_nid == nid) {
stac_toggle_power_map(codec, nid, 1);
continue;
}
stac_toggle_power_map(codec, nid, 1);
continue;
}
- if (enable_pin_detect(codec, nid, STAC_PWR_EVENT))
+ if (enable_pin_detect(codec, nid, STAC_PWR_EVENT)) {
stac_issue_unsol_event(codec, nid);
+ continue;
+ }
+ /* none of the above, turn the port OFF */
+ stac_toggle_power_map(codec, nid, 0);
}
/* sync mute LED */
if (idx >= spec->num_pwrs)
return;
- /* several codecs have two power down bits */
- if (spec->pwr_mapping)
- idx = spec->pwr_mapping[idx];
- else
- idx = 1 << idx;
+ idx = 1 << idx;
val = snd_hda_codec_read(codec, codec->afg, 0, 0x0fec, 0x0) & 0xff;
if (enable)
if (sscanf(dev->name, "HP_Mute_LED_%d_%x",
&spec->gpio_led_polarity,
&spec->gpio_led) == 2) {
- if (spec->gpio_led < 4)
+ unsigned int max_gpio;
+ max_gpio = snd_hda_param_read(codec, codec->afg,
+ AC_PAR_GPIO_CAP);
+ max_gpio &= AC_GPIO_IO_COUNT;
+ if (spec->gpio_led < max_gpio)
spec->gpio_led = 1 << spec->gpio_led;
+ else
+ spec->vref_mute_led_nid = spec->gpio_led;
return 1;
}
if (sscanf(dev->name, "HP_Mute_LED_%d",
set_hp_led_gpio(codec);
return 1;
}
+ /* BIOS bug: unfilled OEM string */
+ if (strstr(dev->name, "HP_Mute_LED_P_G")) {
+ set_hp_led_gpio(codec);
+ spec->gpio_led_polarity = 1;
+ return 1;
+ }
}
/*
struct sigmatel_spec *spec = codec->spec;
/* sync mute LED */
- if (spec->gpio_led) {
- if (spec->gpio_led <= 8) {
- stac_gpio_set(codec, spec->gpio_mask,
- spec->gpio_dir, spec->gpio_data);
- } else {
- stac_vrefout_set(codec,
- spec->gpio_led, spec->vref_led);
- }
- }
- return 0;
-}
-
-static int stac92xx_post_suspend(struct hda_codec *codec)
-{
- struct sigmatel_spec *spec = codec->spec;
- if (spec->gpio_led > 8) {
- /* with vref-out pin used for mute led control
- * codec AFG is prevented from D3 state, but on
- * system suspend it can (and should) be used
- */
- snd_hda_codec_read(codec, codec->afg, 0,
- AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
- }
+ if (spec->vref_mute_led_nid)
+ stac_vrefout_set(codec, spec->vref_mute_led_nid,
+ spec->vref_led);
+ else if (spec->gpio_led)
+ stac_gpio_set(codec, spec->gpio_mask,
+ spec->gpio_dir, spec->gpio_data);
return 0;
}
struct sigmatel_spec *spec = codec->spec;
if (power_state == AC_PWRST_D3) {
- if (spec->gpio_led > 8) {
+ if (spec->vref_mute_led_nid) {
/* with vref-out pin used for mute led control
* codec AFG is prevented from D3 state
*/
}
}
/*polarity defines *not* muted state level*/
- if (spec->gpio_led <= 8) {
+ if (!spec->vref_mute_led_nid) {
if (muted)
spec->gpio_data &= ~spec->gpio_led; /* orange */
else
muted_lvl = spec->gpio_led_polarity ?
AC_PINCTL_VREF_GRD : AC_PINCTL_VREF_HIZ;
spec->vref_led = muted ? muted_lvl : notmtd_lvl;
- stac_vrefout_set(codec, spec->gpio_led, spec->vref_led);
+ stac_vrefout_set(codec, spec->vref_mute_led_nid,
+ spec->vref_led);
}
return 0;
}
snd_hda_codec_set_pincfg(codec, 0xf, 0x2181205e);
}
- /* reset pin power-down; Windows may leave these bits after reboot */
- snd_hda_codec_write_cache(codec, codec->afg, 0, 0x7EC, 0);
- snd_hda_codec_write_cache(codec, codec->afg, 0, 0x7ED, 0);
codec->no_trigger_sense = 1;
codec->spec = spec;
codec->slave_dig_outs = stac92hd83xxx_slave_dig_outs;
spec->digbeep_nid = 0x21;
spec->pwr_nids = stac92hd83xxx_pwr_nids;
- spec->pwr_mapping = stac92hd83xxx_pwr_mapping;
spec->num_pwrs = ARRAY_SIZE(stac92hd83xxx_pwr_nids);
spec->multiout.dac_nids = spec->dac_nids;
spec->init = stac92hd83xxx_core_init;
stac92xx_set_config_regs(codec,
stac92hd83xxx_brd_tbl[spec->board_config]);
- if (spec->board_config != STAC_92HD83XXX_PWR_REF)
- spec->num_pwrs = 0;
-
codec->patch_ops = stac92xx_patch_ops;
if (find_mute_led_gpio(codec, 0))
#ifdef CONFIG_SND_HDA_POWER_SAVE
if (spec->gpio_led) {
- if (spec->gpio_led <= 8) {
+ if (!spec->vref_mute_led_nid) {
spec->gpio_mask |= spec->gpio_led;
spec->gpio_dir |= spec->gpio_led;
spec->gpio_data |= spec->gpio_led;
} else {
codec->patch_ops.set_power_state =
stac92xx_set_power_state;
- codec->patch_ops.post_suspend =
- stac92xx_post_suspend;
}
codec->patch_ops.pre_resume = stac92xx_pre_resume;
codec->patch_ops.check_power_status =
(codec->revision_id & 0xf) == 1)
spec->stream_delay = 40; /* 40 milliseconds */
- /* no output amps */
- spec->num_pwrs = 0;
/* disable VSW */
spec->init = stac92hd71bxx_core_init;
unmute_init++;
if ((codec->revision_id & 0xf) == 1)
spec->stream_delay = 40; /* 40 milliseconds */
- /* no output amps */
- spec->num_pwrs = 0;
/* fallthru */
default:
spec->init = stac92hd71bxx_core_init;
#ifdef CONFIG_SND_HDA_POWER_SAVE
if (spec->gpio_led) {
- if (spec->gpio_led <= 8) {
+ if (!spec->vref_mute_led_nid) {
spec->gpio_mask |= spec->gpio_led;
spec->gpio_dir |= spec->gpio_led;
spec->gpio_data |= spec->gpio_led;
} else {
codec->patch_ops.set_power_state =
stac92xx_set_power_state;
- codec->patch_ops.post_suspend =
- stac92xx_post_suspend;
}
codec->patch_ops.pre_resume = stac92xx_pre_resume;
codec->patch_ops.check_power_status =
/* work to check hp jack state */
struct hda_codec *codec;
struct delayed_work vt1708_hp_work;
+ int hp_work_active;
int vt1708_jack_detect;
int vt1708_hp_present;
static void analog_low_current_mode(struct hda_codec *codec);
static bool is_aa_path_mute(struct hda_codec *codec);
-static void vt1708_start_hp_work(struct via_spec *spec)
+#define hp_detect_with_aa(codec) \
+ (snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1 && \
+ !is_aa_path_mute(codec))
+
+static void vt1708_stop_hp_work(struct via_spec *spec)
{
if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
return;
- snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
- !spec->vt1708_jack_detect);
- if (!delayed_work_pending(&spec->vt1708_hp_work))
- schedule_delayed_work(&spec->vt1708_hp_work,
- msecs_to_jiffies(100));
+ if (spec->hp_work_active) {
+ snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 1);
+ cancel_delayed_work_sync(&spec->vt1708_hp_work);
+ spec->hp_work_active = 0;
+ }
}
-static void vt1708_stop_hp_work(struct via_spec *spec)
+static void vt1708_update_hp_work(struct via_spec *spec)
{
if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
return;
- if (snd_hda_get_bool_hint(spec->codec, "analog_loopback_hp_detect") == 1
- && !is_aa_path_mute(spec->codec))
- return;
- snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
- !spec->vt1708_jack_detect);
- cancel_delayed_work_sync(&spec->vt1708_hp_work);
+ if (spec->vt1708_jack_detect &&
+ (spec->active_streams || hp_detect_with_aa(spec->codec))) {
+ if (!spec->hp_work_active) {
+ snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 0);
+ schedule_delayed_work(&spec->vt1708_hp_work,
+ msecs_to_jiffies(100));
+ spec->hp_work_active = 1;
+ }
+ } else if (!hp_detect_with_aa(spec->codec))
+ vt1708_stop_hp_work(spec);
}
static void set_widgets_power_state(struct hda_codec *codec)
set_widgets_power_state(codec);
analog_low_current_mode(snd_kcontrol_chip(kcontrol));
- if (snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1) {
- if (is_aa_path_mute(codec))
- vt1708_start_hp_work(codec->spec);
- else
- vt1708_stop_hp_work(codec->spec);
- }
+ vt1708_update_hp_work(codec->spec);
return change;
}
spec->cur_dac_stream_tag = stream_tag;
spec->cur_dac_format = format;
mutex_unlock(&spec->config_mutex);
- vt1708_start_hp_work(spec);
+ vt1708_update_hp_work(spec);
return 0;
}
spec->cur_hp_stream_tag = stream_tag;
spec->cur_hp_format = format;
mutex_unlock(&spec->config_mutex);
- vt1708_start_hp_work(spec);
+ vt1708_update_hp_work(spec);
return 0;
}
snd_hda_multi_out_analog_cleanup(codec, &spec->multiout);
spec->active_streams &= ~STREAM_MULTI_OUT;
mutex_unlock(&spec->config_mutex);
- vt1708_stop_hp_work(spec);
+ vt1708_update_hp_work(spec);
return 0;
}
snd_hda_codec_setup_stream(codec, spec->hp_dac_nid, 0, 0, 0);
spec->active_streams &= ~STREAM_INDEP_HP;
mutex_unlock(&spec->config_mutex);
- vt1708_stop_hp_work(spec);
+ vt1708_update_hp_work(spec);
return 0;
}
int nums;
struct via_spec *spec = codec->spec;
- if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0])
+ if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0] &&
+ (spec->codec_type != VT1708 || spec->vt1708_jack_detect))
present = snd_hda_jack_detect(codec, spec->autocfg.hp_pins[0]);
if (spec->smart51_enabled)
if (spec->codec_type != VT1708)
return 0;
- spec->vt1708_jack_detect =
- !((snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8) & 0x1);
ucontrol->value.integer.value[0] = spec->vt1708_jack_detect;
return 0;
}
{
struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
struct via_spec *spec = codec->spec;
- int change;
+ int val;
if (spec->codec_type != VT1708)
return 0;
- spec->vt1708_jack_detect = ucontrol->value.integer.value[0];
- change = (0x1 & (snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8))
- == !spec->vt1708_jack_detect;
- if (spec->vt1708_jack_detect) {
+ val = !!ucontrol->value.integer.value[0];
+ if (spec->vt1708_jack_detect == val)
+ return 0;
+ spec->vt1708_jack_detect = val;
+ if (spec->vt1708_jack_detect &&
+ snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") != 1) {
mute_aa_path(codec, 1);
notify_aa_path_ctls(codec);
}
- return change;
+ via_hp_automute(codec);
+ vt1708_update_hp_work(spec);
+ return 1;
}
static const struct snd_kcontrol_new vt1708_jack_detect_ctl = {
via_auto_init_unsol_event(codec);
via_hp_automute(codec);
+ vt1708_update_hp_work(spec);
return 0;
}
spec->vt1708_hp_present ^= 1;
via_hp_automute(spec->codec);
}
- vt1708_start_hp_work(spec);
+ if (spec->vt1708_jack_detect)
+ schedule_delayed_work(&spec->vt1708_hp_work,
+ msecs_to_jiffies(100));
}
static int get_mux_nids(struct hda_codec *codec)
return ioread32(address);
}
-void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data, u32 len)
+static void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data,
+ u32 len)
{
- void __iomem *address = lx_dsp_register(chip, port);
- memcpy_fromio(data, address, len*sizeof(u32));
+ u32 __iomem *address = lx_dsp_register(chip, port);
+ int i;
+
+ /* we cannot use memcpy_fromio */
+ for (i = 0; i != len; ++i)
+ data[i] = ioread32(address + i);
}
iowrite32(data, address);
}
-void lx_dsp_reg_writebuf(struct lx6464es *chip, int port, const u32 *data,
- u32 len)
+static void lx_dsp_reg_writebuf(struct lx6464es *chip, int port,
+ const u32 *data, u32 len)
{
- void __iomem *address = lx_dsp_register(chip, port);
- memcpy_toio(address, data, len*sizeof(u32));
+ u32 __iomem *address = lx_dsp_register(chip, port);
+ int i;
+
+ /* we cannot use memcpy_to */
+ for (i = 0; i != len; ++i)
+ iowrite32(data[i], address + i);
}
};
unsigned long lx_dsp_reg_read(struct lx6464es *chip, int port);
-void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data, u32 len);
void lx_dsp_reg_write(struct lx6464es *chip, int port, unsigned data);
-void lx_dsp_reg_writebuf(struct lx6464es *chip, int port, const u32 *data,
- u32 len);
/* plx register access */
enum {
hdspm->io_type = AES32;
hdspm->card_name = "RME AES32";
hdspm->midiPorts = 2;
- } else if ((hdspm->firmware_rev == 0xd5) ||
+ } else if ((hdspm->firmware_rev == 0xd2) ||
((hdspm->firmware_rev >= 0xc8) &&
(hdspm->firmware_rev <= 0xcf))) {
hdspm->io_type = MADI;
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
static int enable = 1;
+static int codecs = 1;
module_param(index, int, 0444);
MODULE_PARM_DESC(index, "Index value for SiS7019 Audio Accelerator.");
MODULE_PARM_DESC(id, "ID string for SiS7019 Audio Accelerator.");
module_param(enable, bool, 0444);
MODULE_PARM_DESC(enable, "Enable SiS7019 Audio Accelerator.");
+module_param(codecs, int, 0444);
+MODULE_PARM_DESC(codecs, "Set bit to indicate that codec number is expected to be present (default 1)");
static DEFINE_PCI_DEVICE_TABLE(snd_sis7019_ids) = {
{ PCI_DEVICE(PCI_VENDOR_ID_SI, 0x7019) },
dma_addr_t silence_dma_addr;
};
+/* These values are also used by the module param 'codecs' to indicate
+ * which codecs should be present.
+ */
#define SIS_PRIMARY_CODEC_PRESENT 0x0001
#define SIS_SECONDARY_CODEC_PRESENT 0x0002
#define SIS_TERTIARY_CODEC_PRESENT 0x0004
{
unsigned long io = sis->ioport;
void __iomem *ioaddr = sis->ioaddr;
+ unsigned long timeout;
u16 status;
int count;
int i;
while ((inw(io + SIS_AC97_STATUS) & SIS_AC97_STATUS_BUSY) && --count)
udelay(1);
+ /* Command complete, we can let go of the semaphore now.
+ */
+ outl(SIS_AC97_SEMA_RELEASE, io + SIS_AC97_SEMA);
+ if (!count)
+ return -EIO;
+
/* Now that we've finished the reset, find out what's attached.
+ * There are some codec/board combinations that take an extremely
+ * long time to come up. 350+ ms has been observed in the field,
+ * so we'll give them up to 500ms.
*/
- status = inl(io + SIS_AC97_STATUS);
- if (status & SIS_AC97_STATUS_CODEC_READY)
- sis->codecs_present |= SIS_PRIMARY_CODEC_PRESENT;
- if (status & SIS_AC97_STATUS_CODEC2_READY)
- sis->codecs_present |= SIS_SECONDARY_CODEC_PRESENT;
- if (status & SIS_AC97_STATUS_CODEC3_READY)
- sis->codecs_present |= SIS_TERTIARY_CODEC_PRESENT;
-
- /* All done, let go of the semaphore, and check for errors
+ sis->codecs_present = 0;
+ timeout = msecs_to_jiffies(500) + jiffies;
+ while (time_before_eq(jiffies, timeout)) {
+ status = inl(io + SIS_AC97_STATUS);
+ if (status & SIS_AC97_STATUS_CODEC_READY)
+ sis->codecs_present |= SIS_PRIMARY_CODEC_PRESENT;
+ if (status & SIS_AC97_STATUS_CODEC2_READY)
+ sis->codecs_present |= SIS_SECONDARY_CODEC_PRESENT;
+ if (status & SIS_AC97_STATUS_CODEC3_READY)
+ sis->codecs_present |= SIS_TERTIARY_CODEC_PRESENT;
+
+ if (sis->codecs_present == codecs)
+ break;
+
+ msleep(1);
+ }
+
+ /* All done, check for errors.
*/
- outl(SIS_AC97_SEMA_RELEASE, io + SIS_AC97_SEMA);
- if (!sis->codecs_present || !count)
+ if (!sis->codecs_present) {
+ printk(KERN_ERR "sis7019: could not find any codecs\n");
return -EIO;
+ }
+
+ if (sis->codecs_present != codecs) {
+ printk(KERN_WARNING "sis7019: missing codecs, found %0x, expected %0x\n",
+ sis->codecs_present, codecs);
+ }
/* Let the hardware know that the audio driver is alive,
* and enable PCM slots on the AC-link for L/R playback (3 & 4) and
if (!enable)
goto error_out;
+ /* The user can specify which codecs should be present so that we
+ * can wait for them to show up if they are slow to recover from
+ * the AC97 cold reset. We default to a single codec, the primary.
+ *
+ * We assume that SIS_PRIMARY_*_PRESENT matches bits 0-2.
+ */
+ codecs &= SIS_PRIMARY_CODEC_PRESENT | SIS_SECONDARY_CODEC_PRESENT |
+ SIS_TERTIARY_CODEC_PRESENT;
+ if (!codecs)
+ codecs = SIS_PRIMARY_CODEC_PRESENT;
+
rc = snd_card_create(index, id, THIS_MODULE, sizeof(*sis), &card);
if (rc < 0)
goto error_out;
config SND_ATMEL_SOC
tristate "SoC Audio for the Atmel System-on-Chip"
- depends on ARCH_AT91 || AVR32
+ depends on ARCH_AT91
help
Say Y or M if you want to add support for codecs attached to
the ATMEL SSC interface. You will also need
Say Y if you want to add support for SoC audio on WM8731-based
AT91sam9g20 evaluation board.
-config SND_AT32_SOC_PLAYPAQ
- tristate "SoC Audio support for PlayPaq with WM8510"
- depends on SND_ATMEL_SOC && BOARD_PLAYPAQ && AT91_PROGRAMMABLE_CLOCKS
- select SND_ATMEL_SOC_SSC
- select SND_SOC_WM8510
- help
- Say Y or M here if you want to add support for SoC audio
- on the LRS PlayPaq.
-
-config SND_AT32_SOC_PLAYPAQ_SLAVE
- bool "Run CODEC on PlayPaq in slave mode"
- depends on SND_AT32_SOC_PLAYPAQ
- default n
- help
- Say Y if you want to run with the AT32 SSC generating the BCLK
- and FRAME signals on the PlayPaq. Unless you want to play
- with the AT32 as the SSC master, you probably want to say N here,
- as this will give you better sound quality.
-
config SND_AT91_SOC_AFEB9260
tristate "SoC Audio support for AFEB9260 board"
depends on ARCH_AT91 && MACH_AFEB9260 && SND_ATMEL_SOC
# AT91 Machine Support
snd-soc-sam9g20-wm8731-objs := sam9g20_wm8731.o
-# AT32 Machine Support
-snd-soc-playpaq-objs := playpaq_wm8510.o
-
obj-$(CONFIG_SND_AT91_SOC_SAM9G20_WM8731) += snd-soc-sam9g20-wm8731.o
-obj-$(CONFIG_SND_AT32_SOC_PLAYPAQ) += snd-soc-playpaq.o
obj-$(CONFIG_SND_AT91_SOC_AFEB9260) += snd-soc-afeb9260.o
+++ /dev/null
-/* sound/soc/at32/playpaq_wm8510.c
- * ASoC machine driver for PlayPaq using WM8510 codec
- *
- * Copyright (C) 2008 Long Range Systems
- * Geoffrey Wossum <gwossum@acm.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This code is largely inspired by sound/soc/at91/eti_b1_wm8731.c
- *
- * NOTE: If you don't have the AT32 enhanced portmux configured (which
- * isn't currently in the mainline or Atmel patched kernel), you will
- * need to set the MCLK pin (PA30) to peripheral A in your board initialization
- * code. Something like:
- * at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0);
- *
- */
-
-/* #define DEBUG */
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/timer.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-
-#include <sound/core.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/soc.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/portmux.h>
-
-#include "../codecs/wm8510.h"
-#include "atmel-pcm.h"
-#include "atmel_ssc_dai.h"
-
-
-/*-------------------------------------------------------------------------*\
- * constants
-\*-------------------------------------------------------------------------*/
-#define MCLK_PIN GPIO_PIN_PA(30)
-#define MCLK_PERIPH GPIO_PERIPH_A
-
-
-/*-------------------------------------------------------------------------*\
- * data types
-\*-------------------------------------------------------------------------*/
-/* SSC clocking data */
-struct ssc_clock_data {
- /* CMR div */
- unsigned int cmr_div;
-
- /* Frame period (as needed by xCMR.PERIOD) */
- unsigned int period;
-
- /* The SSC clock rate these settings where calculated for */
- unsigned long ssc_rate;
-};
-
-
-/*-------------------------------------------------------------------------*\
- * module data
-\*-------------------------------------------------------------------------*/
-static struct clk *_gclk0;
-static struct clk *_pll0;
-
-#define CODEC_CLK (_gclk0)
-
-
-/*-------------------------------------------------------------------------*\
- * Sound SOC operations
-\*-------------------------------------------------------------------------*/
-#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
-static struct ssc_clock_data playpaq_wm8510_calc_ssc_clock(
- struct snd_pcm_hw_params *params,
- struct snd_soc_dai *cpu_dai)
-{
- struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai);
- struct ssc_device *ssc = ssc_p->ssc;
- struct ssc_clock_data cd;
- unsigned int rate, width_bits, channels;
- unsigned int bitrate, ssc_div;
- unsigned actual_rate;
-
-
- /*
- * Figure out required bitrate
- */
- rate = params_rate(params);
- channels = params_channels(params);
- width_bits = snd_pcm_format_physical_width(params_format(params));
- bitrate = rate * width_bits * channels;
-
-
- /*
- * Figure out required SSC divider and period for required bitrate
- */
- cd.ssc_rate = clk_get_rate(ssc->clk);
- ssc_div = cd.ssc_rate / bitrate;
- cd.cmr_div = ssc_div / 2;
- if (ssc_div & 1) {
- /* round cmr_div up */
- cd.cmr_div++;
- }
- cd.period = width_bits - 1;
-
-
- /*
- * Find actual rate, compare to requested rate
- */
- actual_rate = (cd.ssc_rate / (cd.cmr_div * 2)) / (2 * (cd.period + 1));
- pr_debug("playpaq_wm8510: Request rate = %u, actual rate = %u\n",
- rate, actual_rate);
-
-
- return cd;
-}
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
-
-static int playpaq_wm8510_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *codec_dai = rtd->codec_dai;
- struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
- struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai);
- struct ssc_device *ssc = ssc_p->ssc;
- unsigned int pll_out = 0, bclk = 0, mclk_div = 0;
- int ret;
-
-
- /* Due to difficulties with getting the correct clocks from the AT32's
- * PLL0, we're going to let the CODEC be in charge of all the clocks
- */
-#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
- const unsigned int fmt = (SND_SOC_DAIFMT_I2S |
- SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBM_CFM);
-#else
- struct ssc_clock_data cd;
- const unsigned int fmt = (SND_SOC_DAIFMT_I2S |
- SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBS_CFS);
-#endif
-
- if (ssc == NULL) {
- pr_warning("playpaq_wm8510_hw_params: ssc is NULL!\n");
- return -EINVAL;
- }
-
-
- /*
- * Figure out PLL and BCLK dividers for WM8510
- */
- switch (params_rate(params)) {
- case 48000:
- pll_out = 24576000;
- mclk_div = WM8510_MCLKDIV_2;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- case 44100:
- pll_out = 22579200;
- mclk_div = WM8510_MCLKDIV_2;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- case 22050:
- pll_out = 22579200;
- mclk_div = WM8510_MCLKDIV_4;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- case 16000:
- pll_out = 24576000;
- mclk_div = WM8510_MCLKDIV_6;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- case 11025:
- pll_out = 22579200;
- mclk_div = WM8510_MCLKDIV_8;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- case 8000:
- pll_out = 24576000;
- mclk_div = WM8510_MCLKDIV_12;
- bclk = WM8510_BCLKDIV_8;
- break;
-
- default:
- pr_warning("playpaq_wm8510: Unsupported sample rate %d\n",
- params_rate(params));
- return -EINVAL;
- }
-
-
- /*
- * set CPU and CODEC DAI configuration
- */
- ret = snd_soc_dai_set_fmt(codec_dai, fmt);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: "
- "Failed to set CODEC DAI format (%d)\n",
- ret);
- return ret;
- }
- ret = snd_soc_dai_set_fmt(cpu_dai, fmt);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: "
- "Failed to set CPU DAI format (%d)\n",
- ret);
- return ret;
- }
-
-
- /*
- * Set CPU clock configuration
- */
-#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
- cd = playpaq_wm8510_calc_ssc_clock(params, cpu_dai);
- pr_debug("playpaq_wm8510: cmr_div = %d, period = %d\n",
- cd.cmr_div, cd.period);
- ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_CMR_DIV, cd.cmr_div);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: Failed to set CPU CMR_DIV (%d)\n",
- ret);
- return ret;
- }
- ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_TCMR_PERIOD,
- cd.period);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: "
- "Failed to set CPU transmit period (%d)\n",
- ret);
- return ret;
- }
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
- /*
- * Set CODEC clock configuration
- */
- pr_debug("playpaq_wm8510: "
- "pll_in = %ld, pll_out = %u, bclk = %x, mclk = %x\n",
- clk_get_rate(CODEC_CLK), pll_out, bclk, mclk_div);
-
-
-#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
- ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_BCLKDIV, bclk);
- if (ret < 0) {
- pr_warning
- ("playpaq_wm8510: Failed to set CODEC DAI BCLKDIV (%d)\n",
- ret);
- return ret;
- }
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
- ret = snd_soc_dai_set_pll(codec_dai, 0, 0,
- clk_get_rate(CODEC_CLK), pll_out);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: Failed to set CODEC DAI PLL (%d)\n",
- ret);
- return ret;
- }
-
-
- ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_MCLKDIV, mclk_div);
- if (ret < 0) {
- pr_warning("playpaq_wm8510: Failed to set CODEC MCLKDIV (%d)\n",
- ret);
- return ret;
- }
-
-
- return 0;
-}
-
-
-
-static struct snd_soc_ops playpaq_wm8510_ops = {
- .hw_params = playpaq_wm8510_hw_params,
-};
-
-
-
-static const struct snd_soc_dapm_widget playpaq_dapm_widgets[] = {
- SND_SOC_DAPM_MIC("Int Mic", NULL),
- SND_SOC_DAPM_SPK("Ext Spk", NULL),
-};
-
-
-
-static const struct snd_soc_dapm_route intercon[] = {
- /* speaker connected to SPKOUT */
- {"Ext Spk", NULL, "SPKOUTP"},
- {"Ext Spk", NULL, "SPKOUTN"},
-
- {"Mic Bias", NULL, "Int Mic"},
- {"MICN", NULL, "Mic Bias"},
- {"MICP", NULL, "Mic Bias"},
-};
-
-
-
-static int playpaq_wm8510_init(struct snd_soc_pcm_runtime *rtd)
-{
- struct snd_soc_codec *codec = rtd->codec;
- struct snd_soc_dapm_context *dapm = &codec->dapm;
- int i;
-
- /*
- * Add DAPM widgets
- */
- for (i = 0; i < ARRAY_SIZE(playpaq_dapm_widgets); i++)
- snd_soc_dapm_new_control(dapm, &playpaq_dapm_widgets[i]);
-
-
-
- /*
- * Setup audio path interconnects
- */
- snd_soc_dapm_add_routes(dapm, intercon, ARRAY_SIZE(intercon));
-
-
-
- /* always connected pins */
- snd_soc_dapm_enable_pin(dapm, "Int Mic");
- snd_soc_dapm_enable_pin(dapm, "Ext Spk");
-
-
-
- /* Make CSB show PLL rate */
- snd_soc_dai_set_clkdiv(rtd->codec_dai, WM8510_OPCLKDIV,
- WM8510_OPCLKDIV_1 | 4);
-
- return 0;
-}
-
-
-
-static struct snd_soc_dai_link playpaq_wm8510_dai = {
- .name = "WM8510",
- .stream_name = "WM8510 PCM",
- .cpu_dai_name= "atmel-ssc-dai.0",
- .platform_name = "atmel-pcm-audio",
- .codec_name = "wm8510-codec.0-0x1a",
- .codec_dai_name = "wm8510-hifi",
- .init = playpaq_wm8510_init,
- .ops = &playpaq_wm8510_ops,
-};
-
-
-
-static struct snd_soc_card snd_soc_playpaq = {
- .name = "LRS_PlayPaq_WM8510",
- .dai_link = &playpaq_wm8510_dai,
- .num_links = 1,
-};
-
-static struct platform_device *playpaq_snd_device;
-
-
-static int __init playpaq_asoc_init(void)
-{
- int ret = 0;
-
- /*
- * Configure MCLK for WM8510
- */
- _gclk0 = clk_get(NULL, "gclk0");
- if (IS_ERR(_gclk0)) {
- _gclk0 = NULL;
- ret = PTR_ERR(_gclk0);
- goto err_gclk0;
- }
- _pll0 = clk_get(NULL, "pll0");
- if (IS_ERR(_pll0)) {
- _pll0 = NULL;
- ret = PTR_ERR(_pll0);
- goto err_pll0;
- }
- ret = clk_set_parent(_gclk0, _pll0);
- if (ret) {
- pr_warning("snd-soc-playpaq: "
- "Failed to set PLL0 as parent for DAC clock\n");
- goto err_set_clk;
- }
- clk_set_rate(CODEC_CLK, 12000000);
- clk_enable(CODEC_CLK);
-
-#if defined CONFIG_AT32_ENHANCED_PORTMUX
- at32_select_periph(MCLK_PIN, MCLK_PERIPH, 0);
-#endif
-
-
- /*
- * Create and register platform device
- */
- playpaq_snd_device = platform_device_alloc("soc-audio", 0);
- if (playpaq_snd_device == NULL) {
- ret = -ENOMEM;
- goto err_device_alloc;
- }
-
- platform_set_drvdata(playpaq_snd_device, &snd_soc_playpaq);
-
- ret = platform_device_add(playpaq_snd_device);
- if (ret) {
- pr_warning("playpaq_wm8510: platform_device_add failed (%d)\n",
- ret);
- goto err_device_add;
- }
-
- return 0;
-
-
-err_device_add:
- if (playpaq_snd_device != NULL) {
- platform_device_put(playpaq_snd_device);
- playpaq_snd_device = NULL;
- }
-err_device_alloc:
-err_set_clk:
- if (_pll0 != NULL) {
- clk_put(_pll0);
- _pll0 = NULL;
- }
-err_pll0:
- if (_gclk0 != NULL) {
- clk_put(_gclk0);
- _gclk0 = NULL;
- }
- return ret;
-}
-
-
-static void __exit playpaq_asoc_exit(void)
-{
- if (_gclk0 != NULL) {
- clk_put(_gclk0);
- _gclk0 = NULL;
- }
- if (_pll0 != NULL) {
- clk_put(_pll0);
- _pll0 = NULL;
- }
-
-#if defined CONFIG_AT32_ENHANCED_PORTMUX
- at32_free_pin(MCLK_PIN);
-#endif
-
- platform_device_unregister(playpaq_snd_device);
- playpaq_snd_device = NULL;
-}
-
-module_init(playpaq_asoc_init);
-module_exit(playpaq_asoc_exit);
-
-MODULE_AUTHOR("Geoffrey Wossum <gwossum@acm.org>");
-MODULE_DESCRIPTION("ASoC machine driver for LRS PlayPaq");
-MODULE_LICENSE("GPL");
select SND_SOC_CX20442
select SND_SOC_DA7210 if I2C
select SND_SOC_DFBMCS320
- select SND_SOC_JZ4740_CODEC if SOC_JZ4740
+ select SND_SOC_JZ4740_CODEC
select SND_SOC_LM4857 if I2C
select SND_SOC_MAX98088 if I2C
select SND_SOC_MAX98095 if I2C
#define AD1836_ADC_CTRL2 13
#define AD1836_ADC_WORD_LEN_MASK 0x30
-#define AD1836_ADC_WORD_OFFSET 5
+#define AD1836_ADC_WORD_OFFSET 4
#define AD1836_ADC_SERFMT_MASK (7 << 6)
#define AD1836_ADC_SERFMT_PCK256 (0x4 << 6)
#define AD1836_ADC_SERFMT_PCK128 (0x5 << 6)
};
static const unsigned int adau1373_bass_tlv[] = {
- TLV_DB_RANGE_HEAD(4),
+ TLV_DB_RANGE_HEAD(3),
0, 2, TLV_DB_SCALE_ITEM(-600, 600, 1),
3, 4, TLV_DB_SCALE_ITEM(950, 250, 0),
5, 7, TLV_DB_SCALE_ITEM(1400, 150, 0),
static int cs4270_soc_resume(struct snd_soc_codec *codec)
{
struct cs4270_private *cs4270 = snd_soc_codec_get_drvdata(codec);
- struct i2c_client *i2c_client = to_i2c_client(codec->dev);
int reg;
regulator_bulk_enable(ARRAY_SIZE(cs4270->supplies),
ndelay(500);
/* first restore the entire register cache ... */
- for (reg = CS4270_FIRSTREG; reg <= CS4270_LASTREG; reg++) {
- u8 val = snd_soc_read(codec, reg);
-
- if (i2c_smbus_write_byte_data(i2c_client, reg, val)) {
- dev_err(codec->dev, "i2c write failed\n");
- return -EIO;
- }
- }
+ snd_soc_cache_sync(codec);
/* ... then disable the power-down bits */
reg = snd_soc_read(codec, CS4270_PWRCTL);
{
int ret;
/* Set power-down bit */
- ret = snd_soc_update_bits(codec, CS4271_MODE2, 0, CS4271_MODE2_PDN);
+ ret = snd_soc_update_bits(codec, CS4271_MODE2, CS4271_MODE2_PDN,
+ CS4271_MODE2_PDN);
if (ret < 0)
return ret;
return 0;
return ret;
}
- ret = snd_soc_update_bits(codec, CS4271_MODE2, 0,
- CS4271_MODE2_PDN | CS4271_MODE2_CPEN);
+ ret = snd_soc_update_bits(codec, CS4271_MODE2,
+ CS4271_MODE2_PDN | CS4271_MODE2_CPEN,
+ CS4271_MODE2_PDN | CS4271_MODE2_CPEN);
if (ret < 0)
return ret;
ret = snd_soc_update_bits(codec, CS4271_MODE2, CS4271_MODE2_PDN, 0);
static struct snd_soc_codec_driver soc_codec_device_cs42l51 = {
.probe = cs42l51_probe,
- .reg_cache_size = CS42L51_NUMREGS,
+ .reg_cache_size = CS42L51_NUMREGS + 1,
.reg_word_size = sizeof(u8),
};
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/io.h>
#include <linux/delay.h>
unsigned int mask = mc->max;
unsigned int val = (ucontrol->value.integer.value[0] & mask);
unsigned int val2 = (ucontrol->value.integer.value[1] & mask);
- unsigned int change = 1;
+ unsigned int change = 0;
- if (((max9877_regs[reg] >> shift) & mask) == val)
- change = 0;
+ if (((max9877_regs[reg] >> shift) & mask) != val)
+ change = 1;
- if (((max9877_regs[reg2] >> shift) & mask) == val2)
- change = 0;
+ if (((max9877_regs[reg2] >> shift) & mask) != val2)
+ change = 1;
if (change) {
max9877_regs[reg] &= ~(mask << shift);
static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
/* {0, +20, +24, +30, +35, +40, +44, +50, +52}dB */
static unsigned int mic_bst_tlv[] = {
- TLV_DB_RANGE_HEAD(6),
+ TLV_DB_RANGE_HEAD(7),
0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0),
2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0),
/* tlv for mic gain, 0db 20db 30db 40db */
static const unsigned int mic_gain_tlv[] = {
- TLV_DB_RANGE_HEAD(4),
+ TLV_DB_RANGE_HEAD(2),
0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
1, 3, TLV_DB_SCALE_ITEM(2000, 1000, 0),
};
unsigned int mclk;
unsigned int format;
+
+ u32 coef_shadow[STA32X_COEF_COUNT];
};
static const DECLARE_TLV_DB_SCALE(mvol_tlv, -12700, 50, 1);
struct snd_ctl_elem_value *ucontrol)
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
+ struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
int numcoef = kcontrol->private_value >> 16;
int index = kcontrol->private_value & 0xffff;
unsigned int cfud;
snd_soc_write(codec, STA32X_CFUD, cfud);
snd_soc_write(codec, STA32X_CFADDR2, index);
+ for (i = 0; i < numcoef && (index + i < STA32X_COEF_COUNT); i++)
+ sta32x->coef_shadow[index + i] =
+ (ucontrol->value.bytes.data[3 * i] << 16)
+ | (ucontrol->value.bytes.data[3 * i + 1] << 8)
+ | (ucontrol->value.bytes.data[3 * i + 2]);
for (i = 0; i < 3 * numcoef; i++)
snd_soc_write(codec, STA32X_B1CF1 + i,
ucontrol->value.bytes.data[i]);
return 0;
}
+int sta32x_sync_coef_shadow(struct snd_soc_codec *codec)
+{
+ struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
+ unsigned int cfud;
+ int i;
+
+ /* preserve reserved bits in STA32X_CFUD */
+ cfud = snd_soc_read(codec, STA32X_CFUD) & 0xf0;
+
+ for (i = 0; i < STA32X_COEF_COUNT; i++) {
+ snd_soc_write(codec, STA32X_CFADDR2, i);
+ snd_soc_write(codec, STA32X_B1CF1,
+ (sta32x->coef_shadow[i] >> 16) & 0xff);
+ snd_soc_write(codec, STA32X_B1CF2,
+ (sta32x->coef_shadow[i] >> 8) & 0xff);
+ snd_soc_write(codec, STA32X_B1CF3,
+ (sta32x->coef_shadow[i]) & 0xff);
+ /* chip documentation does not say if the bits are
+ * self-clearing, so do it explicitly */
+ snd_soc_write(codec, STA32X_CFUD, cfud);
+ snd_soc_write(codec, STA32X_CFUD, cfud | 0x01);
+ }
+ return 0;
+}
+
+int sta32x_cache_sync(struct snd_soc_codec *codec)
+{
+ unsigned int mute;
+ int rc;
+
+ if (!codec->cache_sync)
+ return 0;
+
+ /* mute during register sync */
+ mute = snd_soc_read(codec, STA32X_MMUTE);
+ snd_soc_write(codec, STA32X_MMUTE, mute | STA32X_MMUTE_MMUTE);
+ sta32x_sync_coef_shadow(codec);
+ rc = snd_soc_cache_sync(codec);
+ snd_soc_write(codec, STA32X_MMUTE, mute);
+ return rc;
+}
+
#define SINGLE_COEF(xname, index) \
{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
.info = sta32x_coefficient_info, \
return ret;
}
- snd_soc_cache_sync(codec);
+ sta32x_cache_sync(codec);
}
/* Power up to mute */
STA32X_CxCFG_OM_MASK,
2 << STA32X_CxCFG_OM_SHIFT);
+ /* initialize coefficient shadow RAM with reset values */
+ for (i = 4; i <= 49; i += 5)
+ sta32x->coef_shadow[i] = 0x400000;
+ for (i = 50; i <= 54; i++)
+ sta32x->coef_shadow[i] = 0x7fffff;
+ sta32x->coef_shadow[55] = 0x5a9df7;
+ sta32x->coef_shadow[56] = 0x7fffff;
+ sta32x->coef_shadow[59] = 0x7fffff;
+ sta32x->coef_shadow[60] = 0x400000;
+ sta32x->coef_shadow[61] = 0x400000;
+
sta32x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
/* Bias level configuration will have done an extra enable */
regulator_bulk_disable(ARRAY_SIZE(sta32x->supplies), sta32x->supplies);
/* STA326 register addresses */
#define STA32X_REGISTER_COUNT 0x2d
+#define STA32X_COEF_COUNT 62
#define STA32X_CONFA 0x00
#define STA32X_CONFB 0x01
static int __init uda1380_modinit(void)
{
- int ret;
+ int ret = 0;
#if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE)
ret = i2c_add_driver(&uda1380_i2c_driver);
if (ret != 0)
pr_err("Failed to register UDA1380 I2C driver: %d\n", ret);
#endif
- return 0;
+ return ret;
}
module_init(uda1380_modinit);
snd_soc_write(codec, WM8731_PWR, 0xffff);
regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies),
wm8731->supplies);
+ codec->cache_sync = 1;
break;
}
codec->dapm.bias_level = level;
struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec);
u16 ioctl;
+ if (wm8753->dai_func == ucontrol->value.integer.value[0])
+ return 0;
+
if (codec->active)
return -EBUSY;
switch (snd_pcm_format_width(params_format(params))) {
case 16:
iface = 0;
+ break;
case 20:
iface = 0x10;
break;
}
if (memcmp(fw->data, "WMFW", 4) != 0) {
+ memcpy(&data32, fw->data, sizeof(data32));
+ data32 = be32_to_cpu(data32);
dev_err(codec->dev, "%s: firmware has bad file magic %08x\n",
name, data32);
goto err;
static const DECLARE_TLV_DB_SCALE(inpga_tlv, -2325, 75, 0);
static const DECLARE_TLV_DB_SCALE(mixin_tlv, -1500, 300, 0);
static const unsigned int mixinpga_tlv[] = {
- TLV_DB_RANGE_HEAD(7),
+ TLV_DB_RANGE_HEAD(5),
0, 1, TLV_DB_SCALE_ITEM(0, 600, 0),
2, 2, TLV_DB_SCALE_ITEM(1300, 1300, 0),
3, 4, TLV_DB_SCALE_ITEM(1800, 200, 0),
static const DECLARE_TLV_DB_SCALE(out_tlv, -12100, 100, 1);
static const DECLARE_TLV_DB_SCALE(hp_tlv, -700, 100, 0);
static const unsigned int classd_tlv[] = {
- TLV_DB_RANGE_HEAD(7),
+ TLV_DB_RANGE_HEAD(2),
0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
};
static const DECLARE_TLV_DB_SCALE(drc_comp_amp, -2250, 75, 0);
static const DECLARE_TLV_DB_SCALE(drc_min_tlv, -1800, 600, 0);
static const unsigned int drc_max_tlv[] = {
- TLV_DB_RANGE_HEAD(4),
+ TLV_DB_RANGE_HEAD(2),
0, 2, TLV_DB_SCALE_ITEM(1200, 600, 0),
3, 3, TLV_DB_SCALE_ITEM(3600, 0, 0),
};
};
static const struct snd_soc_dapm_widget wm8994_adc_revd_widgets[] = {
-SND_SOC_DAPM_MUX_E("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux,
- adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
-SND_SOC_DAPM_MUX_E("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux,
- adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_VIRT_MUX_E("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux,
+ adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_VIRT_MUX_E("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux,
+ adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
};
static const struct snd_soc_dapm_widget wm8994_adc_widgets[] = {
-SND_SOC_DAPM_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux),
-SND_SOC_DAPM_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux),
+SND_SOC_DAPM_VIRT_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux),
+SND_SOC_DAPM_VIRT_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux),
};
static const struct snd_soc_dapm_widget wm8994_dapm_widgets[] = {
bclk |= best << WM8994_AIF1_BCLK_DIV_SHIFT;
lrclk = bclk_rate / params_rate(params);
+ if (!lrclk) {
+ dev_err(dai->dev, "Unable to generate LRCLK from %dHz BCLK\n",
+ bclk_rate);
+ return -EINVAL;
+ }
dev_dbg(dai->dev, "Using LRCLK rate %d for actual LRCLK %dHz\n",
lrclk, bclk_rate / lrclk);
switch (wm8994->revision) {
case 0:
case 1:
+ case 2:
+ case 3:
wm8994->hubs.dcs_codes_l = -9;
wm8994->hubs.dcs_codes_r = -5;
break;
break;
case 24576000:
ratediv = WM8996_SYSCLK_DIV;
+ wm8996->sysclk /= 2;
case 12288000:
snd_soc_update_bits(codec, WM8996_AIF_RATE,
WM8996_SYSCLK_RATE, WM8996_SYSCLK_RATE);
mdelay(100);
/* Normal bias enable & soft start off */
- reg |= WM9081_BIAS_ENA;
reg &= ~WM9081_VMID_RAMP;
snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
}
/* VMID 2*240k */
- reg = snd_soc_read(codec, WM9081_BIAS_CONTROL_1);
+ reg = snd_soc_read(codec, WM9081_VMID_CONTROL);
reg &= ~WM9081_VMID_SEL_MASK;
reg |= 0x04;
snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
break;
case SND_SOC_BIAS_OFF:
- /* Startup bias source */
+ /* Startup bias source and disable bias */
reg = snd_soc_read(codec, WM9081_BIAS_CONTROL_1);
reg |= WM9081_BIAS_SRC;
+ reg &= ~WM9081_BIAS_ENA;
snd_soc_write(codec, WM9081_BIAS_CONTROL_1, reg);
- /* Disable VMID and biases with soft ramping */
+ /* Disable VMID with soft ramping */
reg = snd_soc_read(codec, WM9081_VMID_CONTROL);
- reg &= ~(WM9081_VMID_SEL_MASK | WM9081_BIAS_ENA);
+ reg &= ~WM9081_VMID_SEL_MASK;
reg |= WM9081_VMID_RAMP;
snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
}
static const unsigned int in_tlv[] = {
- TLV_DB_RANGE_HEAD(6),
+ TLV_DB_RANGE_HEAD(3),
0, 0, TLV_DB_SCALE_ITEM(-600, 0, 0),
1, 3, TLV_DB_SCALE_ITEM(-350, 350, 0),
4, 6, TLV_DB_SCALE_ITEM(600, 600, 0),
};
static const unsigned int mix_tlv[] = {
- TLV_DB_RANGE_HEAD(4),
+ TLV_DB_RANGE_HEAD(2),
0, 2, TLV_DB_SCALE_ITEM(-1200, 300, 0),
3, 3, TLV_DB_SCALE_ITEM(0, 0, 0),
};
static const DECLARE_TLV_DB_SCALE(out_tlv, -5700, 100, 0);
static const unsigned int spkboost_tlv[] = {
- TLV_DB_RANGE_HEAD(7),
+ TLV_DB_RANGE_HEAD(2),
0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
};
static const DECLARE_TLV_DB_SCALE(spkmixout_tlv, -1800, 600, 1);
static const DECLARE_TLV_DB_SCALE(outpga_tlv, -5700, 100, 0);
static const unsigned int spkboost_tlv[] = {
- TLV_DB_RANGE_HEAD(7),
+ TLV_DB_RANGE_HEAD(2),
0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
};
/* Initialize the the device_attribute structure */
dev_attr = &ssi_private->dev_attr;
+ sysfs_attr_init(&dev_attr->attr);
dev_attr->attr.name = "statistics";
dev_attr->attr.mode = S_IRUGO;
dev_attr->show = fsl_sysfs_ssi_show;
}
if (strcasecmp(sprop, "i2s-slave") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_I2S;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
}
machine_data->clk_frequency = be32_to_cpup(iprop);
} else if (strcasecmp(sprop, "i2s-master") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_I2S;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "lj-slave") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "lj-master") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "rj-slave") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "rj-master") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "ac97-slave") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_AC97;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "ac97-master") == 0) {
- machine_data->dai_format = SND_SOC_DAIFMT_AC97;
+ machine_data->dai_format =
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else {
config SND_SOC_MX27VIS_AIC32X4
tristate "SoC audio support for Visstrim M10 boards"
- depends on MACH_IMX27_VISSTRIM_M10
+ depends on MACH_IMX27_VISSTRIM_M10 && I2C
select SND_SOC_TLV320AIC32X4
select SND_MXC_SOC_MX2
help
config SND_KIRKWOOD_SOC_OPENRD
tristate "SoC Audio support for Kirkwood Openrd Client"
depends on SND_KIRKWOOD_SOC && (MACH_OPENRD_CLIENT || MACH_OPENRD_ULTIMATE)
+ depends on I2C
select SND_KIRKWOOD_SOC_I2S
select SND_SOC_CS42L51
help
config SND_KIRKWOOD_SOC_T5325
tristate "SoC Audio support for HP t5325"
- depends on SND_KIRKWOOD_SOC && MACH_T5325
+ depends on SND_KIRKWOOD_SOC && MACH_T5325 && I2C
select SND_KIRKWOOD_SOC_I2S
select SND_SOC_ALC5623
help
platform_driver_unregister(&mxs_pcm_driver);
}
module_exit(snd_mxs_pcm_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mxs-pcm-audio");
MODULE_AUTHOR("Freescale Semiconductor, Inc.");
MODULE_DESCRIPTION("MXS ALSA SoC Machine driver");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mxs-sgtl5000");
if (ret)
goto out3;
- mfp_set_groupg(nuc900_audio->dev); /* enbale ac97 multifunction pin*/
+ /* enbale ac97 multifunction pin */
+ mfp_set_groupg(nuc900_audio->dev, "nuc900-audio");
return 0;
config SND_SOC_RAUMFELD
tristate "SoC Audio support Raumfeld audio adapter"
depends on SND_PXA2XX_SOC && (MACH_RAUMFELD_SPEAKER || MACH_RAUMFELD_CONNECTOR)
+ depends on I2C && SPI_MASTER
select SND_PXA_SOC_SSP
select SND_SOC_CS4270
select SND_SOC_AK4104
config SND_PXA2XX_SOC_HX4700
tristate "SoC Audio support for HP iPAQ hx4700"
- depends on SND_PXA2XX_SOC && MACH_H4700
+ depends on SND_PXA2XX_SOC && MACH_H4700 && I2C
select SND_PXA2XX_SOC_I2S
select SND_SOC_AK4641
help
snd_soc_card_hx4700.dev = &pdev->dev;
ret = snd_soc_register_card(&snd_soc_card_hx4700);
if (ret)
- return ret;
+ gpio_free_array(hx4700_audio_gpios,
+ ARRAY_SIZE(hx4700_audio_gpios));
- return 0;
+ return ret;
}
static int __devexit hx4700_audio_remove(struct platform_device *pdev)
{
struct snd_soc_codec *codec = rtd->codec;
struct snd_soc_dapm_context *dapm = &codec->dapm;
- int err;
/* These endpoints are not being used. */
snd_soc_dapm_nc_pin(dapm, "LINPUT2");
.dai_link = &jive_dai,
.num_links = 1,
- .dapm_widgtets = wm8750_dapm_widgets,
+ .dapm_widgets = wm8750_dapm_widgets,
.num_dapm_widgets = ARRAY_SIZE(wm8750_dapm_widgets),
.dapm_routes = audio_map,
.num_dapm_routes = ARRAY_SIZE(audio_map),
*
*/
+#include <linux/module.h>
#include <sound/soc.h>
static struct snd_soc_card smdk2443;
#include "../codecs/wm8994.h"
#include <sound/pcm_params.h>
+#include <linux/module.h>
/*
* Default CFG switch settings to use this driver:
snd_soc_dapm_ignore_suspend(&card->dapm, "Headset Mic");
snd_soc_dapm_ignore_suspend(&card->dapm, "Main AMIC");
snd_soc_dapm_ignore_suspend(&card->dapm, "Main DMIC");
- snd_soc_dapm_ignore_suspend(&card->dapm, "Speaker");
+ snd_soc_dapm_ignore_suspend(&card->dapm, "Main Speaker");
snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Output");
snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Input");
struct snd_soc_card *card = dev_get_drvdata(dev);
int i, ac97_control = 0;
+ /* If the initialization of this soc device failed, there is no codec
+ * associated with it. Just bail out in this case.
+ */
+ if (list_empty(&card->codec_dev_list))
+ return 0;
+
/* AC97 devices might have other drivers hanging off them so
* need to resume immediately. Other drivers don't have that
* problem and may take a substantial amount of time to resume
}
EXPORT_SYMBOL_GPL(snd_soc_params_to_bclk);
-static struct snd_soc_platform_driver dummy_platform;
+static const struct snd_pcm_hardware dummy_dma_hardware = {
+ .formats = 0xffffffff,
+ .channels_min = 1,
+ .channels_max = UINT_MAX,
+
+ /* Random values to keep userspace happy when checking constraints */
+ .info = SNDRV_PCM_INFO_INTERLEAVED |
+ SNDRV_PCM_INFO_BLOCK_TRANSFER,
+ .buffer_bytes_max = 128*1024,
+ .period_bytes_min = PAGE_SIZE,
+ .period_bytes_max = PAGE_SIZE*2,
+ .periods_min = 2,
+ .periods_max = 128,
+};
+
+static int dummy_dma_open(struct snd_pcm_substream *substream)
+{
+ snd_soc_set_runtime_hwparams(substream, &dummy_dma_hardware);
+
+ return 0;
+}
+
+static struct snd_pcm_ops dummy_dma_ops = {
+ .open = dummy_dma_open,
+ .ioctl = snd_pcm_lib_ioctl,
+};
+
+static struct snd_soc_platform_driver dummy_platform = {
+ .ops = &dummy_dma_ops,
+};
static __devinit int snd_soc_dummy_probe(struct platform_device *pdev)
{
}
}
},
+{
+ /* Roland GAIA SH-01 */
+ USB_DEVICE(0x0582, 0x0111),
+ .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+ .vendor_name = "Roland",
+ .product_name = "GAIA",
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = (const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 0,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 1,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 2,
+ .type = QUIRK_MIDI_FIXED_ENDPOINT,
+ .data = &(const struct snd_usb_midi_endpoint_info) {
+ .out_cables = 0x0003,
+ .in_cables = 0x0003
+ }
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
{
USB_DEVICE(0x0582, 0x0113),
.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
list_for_each_entry(counter, &evsel_list->entries, node) {
if (create_perf_stat_counter(counter, first) < 0) {
- if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
+ if (errno == EINVAL || errno == ENOSYS ||
+ errno == ENOENT || errno == EOPNOTSUPP) {
if (verbose)
ui__warning("%s event is not supported by the kernel.\n",
event_name(counter));
return size;
}
+static void hists__init(struct hists *hists)
+{
+ memset(hists, 0, sizeof(*hists));
+ hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+ hists->entries_in = &hists->entries_in_array[0];
+ hists->entries_collapsed = RB_ROOT;
+ hists->entries = RB_ROOT;
+ pthread_mutex_init(&hists->lock, NULL);
+}
+
void perf_evsel__init(struct perf_evsel *evsel,
struct perf_event_attr *attr, int idx)
{
/*
* write event string as passed on cmdline
*/
- ret = do_write_string(fd, attr->name);
+ ret = do_write_string(fd, event_name(attr));
if (ret < 0)
return ret;
/*
return ret;
}
-
-void hists__init(struct hists *hists)
-{
- memset(hists, 0, sizeof(*hists));
- hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
- hists->entries_in = &hists->entries_in_array[0];
- hists->entries_collapsed = RB_ROOT;
- hists->entries = RB_ROOT;
- pthread_mutex_init(&hists->lock, NULL);
-}
struct callchain_cursor callchain_cursor;
};
-void hists__init(struct hists *hists);
-
struct hist_entry *__hists__add_entry(struct hists *self,
struct addr_location *al,
struct symbol *parent, u64 period);
}
map = cpu_map__new(cpu_list);
+ if (map == NULL) {
+ pr_err("Invalid cpu_list\n");
+ return -1;
+ }
for (i = 0; i < map->nr; i++) {
int cpu = map->map[i];
field = malloc_or_die(sizeof(*field));
type = process_arg(event, field, &token);
+ while (type == EVENT_OP)
+ type = process_op(event, field, &token);
if (test_type_token(type, token, EVENT_DELIM, ","))
goto out_free;
# Add space to evaluate the character before $
$option = " $option";
my $retval = "";
+ my $repeated = 0;
+ my $parent = 0;
+
+ foreach my $test (keys %repeat_tests) {
+ if ($i >= $test &&
+ $i < $test + $repeat_tests{$test}) {
+
+ $repeated = 1;
+ $parent = $test;
+ last;
+ }
+ }
while ($option =~ /(.*?[^\\])\$\{(.*?)\}(.*)/) {
my $start = $1;
# otherwise see if the default OPT (without [$i]) exists.
my $o = "$var\[$i\]";
+ my $parento = "$var\[$parent\]";
if (defined($opt{$o})) {
$o = $opt{$o};
$retval = "$retval$o";
+ } elsif ($repeated && defined($opt{$parento})) {
+ $o = $opt{$parento};
+ $retval = "$retval$o";
} elsif (defined($opt{$var})) {
$o = $opt{$var};
$retval = "$retval$o";
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
#include "irq.h"
static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
return r;
}
+/*
+ * We want to test whether the caller has been granted permissions to
+ * use this device. To be able to configure and control the device,
+ * the user needs access to PCI configuration space and BAR resources.
+ * These are accessed through PCI sysfs. PCI config space is often
+ * passed to the process calling this ioctl via file descriptor, so we
+ * can't rely on access to that file. We can check for permissions
+ * on each of the BAR resource files, which is a pretty clear
+ * indicator that the user has been granted access to the device.
+ */
+static int probe_sysfs_permissions(struct pci_dev *dev)
+{
+#ifdef CONFIG_SYSFS
+ int i;
+ bool bar_found = false;
+
+ for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
+ char *kpath, *syspath;
+ struct path path;
+ struct inode *inode;
+ int r;
+
+ if (!pci_resource_len(dev, i))
+ continue;
+
+ kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
+ if (!kpath)
+ return -ENOMEM;
+
+ /* Per sysfs-rules, sysfs is always at /sys */
+ syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
+ kfree(kpath);
+ if (!syspath)
+ return -ENOMEM;
+
+ r = kern_path(syspath, LOOKUP_FOLLOW, &path);
+ kfree(syspath);
+ if (r)
+ return r;
+
+ inode = path.dentry->d_inode;
+
+ r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
+ path_put(&path);
+ if (r)
+ return r;
+
+ bar_found = true;
+ }
+
+ /* If no resources, probably something special */
+ if (!bar_found)
+ return -EPERM;
+
+ return 0;
+#else
+ return -EINVAL; /* No way to control the device without sysfs */
+#endif
+}
+
static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
struct kvm_assigned_pci_dev *assigned_dev)
{
int r = 0, idx;
struct kvm_assigned_dev_kernel *match;
struct pci_dev *dev;
+ u8 header_type;
+
+ if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
+ return -EINVAL;
mutex_lock(&kvm->lock);
idx = srcu_read_lock(&kvm->srcu);
r = -EINVAL;
goto out_free;
}
+
+ /* Don't allow bridges to be assigned */
+ pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+ if ((header_type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) {
+ r = -EPERM;
+ goto out_put;
+ }
+
+ r = probe_sysfs_permissions(dev);
+ if (r)
+ goto out_put;
+
if (pci_enable_device(dev)) {
printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
r = -EBUSY;
list_add(&match->list, &kvm->arch.assigned_dev_head);
- if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
- if (!kvm->arch.iommu_domain) {
- r = kvm_iommu_map_guest(kvm);
- if (r)
- goto out_list_del;
- }
- r = kvm_assign_device(kvm, match);
+ if (!kvm->arch.iommu_domain) {
+ r = kvm_iommu_map_guest(kvm);
if (r)
goto out_list_del;
}
+ r = kvm_assign_device(kvm, match);
+ if (r)
+ goto out_list_del;
out:
srcu_read_unlock(&kvm->srcu, idx);
goto out;
}
- if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
- kvm_deassign_device(kvm, match);
+ kvm_deassign_device(kvm, match);
kvm_free_assigned_device(kvm, match);
projects / mv-sheeva.git / commitdiff