Johannes Berg [Sat, 29 Jun 2013 17:23:13 +0000 (19:23 +0200)]
alx: treat flow control correctly in alx_set_pauseparam()
Even when alx_setup_speed_duplex() is called, we still
need to call alx_cfg_mac_flowcontrol() and set hw->flowctrl
if flow control changed.
This was a bug I accidentally introduced while simplifying
the original driver.
Reported-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Rony Efraim [Thu, 27 Jun 2013 16:05:22 +0000 (19:05 +0300)]
net/mlx4_core: Add HW enforcement to VF link state
When the firmware supports the UPDATE_QP command, if the VF link is disabled,
block all QPs opened by the VF, by programming the UPDATE_QP command to drop
all RX & TX traffic to/from these QPs. Operates only in VST mode.
Signed-off-by: Rony Efraim <ronye@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jack Morgenstein [Thu, 27 Jun 2013 16:05:21 +0000 (19:05 +0300)]
net/mlx4_core: Dynamic VST to VST vlan/qos changes
Within VST mode, enable modifying the vlan and/or qos
for a VF without requiring unbind/rebind.
This requires firmware which supports the UPDATE_QP command.
(If the command is not available, we fall back to requiring
unbind/bind to activate these changes).
To avoid race conditions with modify-qp on QPs that are affected
by update-qp, this operation is performed on the comm_wq.
If the update operation succeeds for all the necessary QPs, a
vlan_unregister is performed for the abandoned vlan id.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 1 Jul 2013 00:35:13 +0000 (17:35 -0700)]
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:
====================
The following batch contains Netfilter/IPVS updates for net-next,
they are:
* Enforce policy to several nfnetlink subsystem, from Daniel
Borkmann.
* Use xt_socket to match the third packet (to perform simplistic
socket-based stateful filtering), from Eric Dumazet.
* Avoid large timeout for picked up from the middle TCP flows,
from Florian Westphal.
* Exclude IPVS from struct net if IPVS is disabled and removal
of unnecessary included header file, from JunweiZhang.
* Release SCTP connection immediately under load, to mimic current
TCP behaviour, from Julian Anastasov.
* Replace and enhance SCTP state machine, from Julian Anastasov.
* Add tweak to reduce sync traffic in the presence of persistence,
also from Julian Anastasov.
* Add tweak for the IPVS SH scheduler not to reject connections
directed to a server, choose a new one instead, from Alexander
Frolkin.
* Add support for sloppy TCP and SCTP modes, that creates state
information on any packet, not only initial handshake packets,
from Alexander Frolkin.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Westphal [Sat, 29 Jun 2013 12:15:47 +0000 (14:15 +0200)]
netfilter: nf_queue: add NFQA_SKB_CSUM_NOTVERIFIED info flag
The common case is that TCP/IP checksums have already been
verified, e.g. by hardware (rx checksum offload), or conntrack.
Userspace can use this flag to determine when the checksum
has not been validated yet.
If the flag is set, this doesn't necessarily mean that the packet has
an invalid checksum, e.g. if NIC doesn't support rx checksum.
Userspace that sucessfully enabled NFQA_CFG_F_GSO queue feature flag can
infer that IP/TCP checksum has already been validated if either the
SKB_INFO attribute is not present or the NFQA_SKB_CSUM_NOTVERIFIED
flag is unset.
Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
David S. Miller [Sat, 29 Jun 2013 05:13:14 +0000 (22:13 -0700)]
Merge branch 'for-davem' of git://gitorious.org/linux-can/linux-can-next
Marc Kleine-Budde says:
====================
this is a pull-request for net-next/master. It consists of three
patches by Fabio Estevam and me, which convert the flexcan transceiver
switching to DT[1] and a patch by Sachin Kamat, which cleans up the
at91_can driver a bit.
[1] These patches touch arch/arm/mach-imx, so I collected Acked-bys
from Shawn Guo and Sascha Hauer.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Yijing Wang [Thu, 27 Jun 2013 13:00:11 +0000 (21:00 +0800)]
ssb/trivial: replace numeric with standard PM state macros
Use standard PM state macros PCI_Dx instead of numeric 0/1/2..
Signed-off-by: Yijing Wang <wangyijing@huawei.com> Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
Yijing Wang [Thu, 27 Jun 2013 12:53:42 +0000 (20:53 +0800)]
net/trivial: replace numeric with standard PM state macros
Use standard PM state macros PCI_Dx instead of numeric 0/1/2..
Signed-off-by: Yijing Wang <wangyijing@huawei.com> Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Thu, 27 Jun 2013 11:44:26 +0000 (13:44 +0200)]
nlmon: fix comparison in nlmon_is_valid_mtu
This patch fixes the following warning introduced in e4fc408e0e99
("packet: nlmon: virtual netlink monitoring device for packet
sockets") reported by Dan Carpenter:
Thus, we should simply remove the test against INT_MAX. Next to that
we also need to explicitly cast the sizeof() case as the comparison
is type promoted to unsigned long so negative values are then
valid instead of invalid. While at it, this also adds a comment about
Netlink and MTUs.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David Chang [Thu, 27 Jun 2013 09:16:43 +0000 (17:16 +0800)]
usbnet: ax88179_178a: add .reset_resume hook
I tested with the AX88179 usb dongle, if without .reset_resume hook,
after S3/S4 resume you have to enable network interface or reload the
dirver module manually otherwise the network interface can not work.
Signed-off-by: David Chang <dchang@suse.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Timo Teräs [Thu, 27 Jun 2013 07:27:05 +0000 (10:27 +0300)]
ipv4: use next hop exceptions also for input routes
Commit d2d68ba9 (ipv4: Cache input routes in fib_info nexthops)
assmued that "locally destined, and routed packets, never trigger
PMTU events or redirects that will be processed by us".
However, it seems that tunnel devices do trigger PMTU events in certain
cases. At least ip_gre, ip6_gre, sit, and ipip do use the inner flow's
skb_dst(skb)->ops->update_pmtu to propage mtu information from the
outer flows. These can cause the inner flow mtu to be decreased. If
next hop exceptions are not consulted for pmtu, IP fragmentation will
not be done properly for these routes.
It also seems that we really need to have the PMTU information always
for netfilter TCPMSS clamp-to-pmtu feature to work properly.
So for the time being, cache separate copies of input routes for
each next hop exception.
Signed-off-by: Timo Teräs <timo.teras@iki.fi> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6: resend MLD report if a link-local address completes DAD
RFC3590/RFC3810 specifies we should resend MLD reports as soon as a
valid link-local address is available.
We now use the valid_ll_addr_cnt to check if it is necessary to resend
a new report.
Changes since Flavio Leitner's version:
a) adapt for valid_ll_addr_cnt
b) resend first reports directly in the path and just arm the timer for
mc_qrv-1 resends.
Reported-by: Flavio Leitner <fleitner@redhat.com> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: David Stevens <dlstevens@us.ibm.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Flavio Leitner <fbl@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6: introduce per-interface counter for dad-completed ipv6 addresses
To reduce the number of unnecessary router solicitations, MLDv2 and IGMPv3
messages we need to track the number of valid (as in non-optimistic,
no-dad-failed and non-tentative) link-local addresses. Therefore, this
patch implements a valid_ll_addr_cnt in struct inet6_dev.
We now only emit router solicitations if the first link-local address
finishes duplicate address detection.
The changes for MLDv2 and IGMPv3 are in a follow-up patch.
While there, also simplify one if statement(one minor nit I made in one
of my previous patches):
if (!...)
do();
else
return;
<<into>>
if (...)
return;
do();
Cc: Flavio Leitner <fbl@redhat.com> Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Cc: David Stevens <dlstevens@us.ibm.com> Suggested-by: David Stevens <dlstevens@us.ibm.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Flavio Leitner <fbl@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
A simple semantic change, when a slave's MAC is cloned by the bond
master then set addr_assign_type to NET_ADDR_STOLEN instead of
NET_ADDR_SET. Also use bond_set_dev_addr() in BOND_FOM_ACTIVE mode
to change the bond's MAC address because the assign_type has to be
set properly.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
bonding: remove unnecessary dev_addr_from_first member
In struct bonding there's a member called dev_addr_from_first which is
used to denote when the bond dev should clone the first slave's MAC
address but since we have netdev's addr_assign_type variable that is not
necessary. We clone the first slave's MAC each time we have a random MAC
set to the bond device. This has the nice side-effect of also fixing an
inconsistency - when the MAC address of the bond dev is set after its
creation, but prior to having slaves, it's not kept and the first slave's
MAC is cloned. The only way to keep the MAC was to create the bond device
with the MAC address set (e.g. through ip link). In all cases if the
bond device is left without any slaves - its MAC gets reset to a random
one as before.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
We have a member called setup_by_slave in struct bonding to denote if the
bond dev has different type than ARPHRD_ETHER, but that is already denoted
in bond's netdev type variable if it was setup by the slave, so use that
instead of the member.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1) introducing a new netlink_skb_clone function that is used in nl_fib_input,
that sets our special skb->destructor in the cloned skb. Moreover, handle
the release of the large cloned skb head area in the destructor path.
2) not allowing large skbuffs in the netlink broadcast path. I cannot find
any reasonable use of the large data transfer using netlink in that path,
moreover this helps to skip extra skb_clone handling.
I found two more netlink clients that are cloning the skbs, but they are
not in the sendmsg path. Therefore, the sole client cloning that I found
seems to be the fib frontend.
Thanks to Eric Dumazet for helping to address this issue.
Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Nicolas Dichtel [Wed, 26 Jun 2013 14:11:28 +0000 (16:11 +0200)]
sit: add support of x-netns
This patch allows to switch the netns when packet is encapsulated or
decapsulated. In other word, the encapsulated packet is received in a netns,
where the lookup is done to find the tunnel. Once the tunnel is found, the
packet is decapsulated and injecting into the corresponding interface which
stands to another netns.
When one of the two netns is removed, the tunnel is destroyed.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Fabio Estevam [Tue, 11 Jun 2013 02:12:57 +0000 (23:12 -0300)]
can: flexcan: Use a regulator to control the CAN transceiver
Instead of using a GPIO to turn on/off the CAN transceiver, it is better to
use a regulator as some systems may use a PMIC to power the CAN transceiver.
ipv6: rearm router solicitaion timer when setting new tokenized address
When a new tokenized address gets installed we send out just one
router solicition. We should send out `rtr_solicits' in case one router
advertisment got lost.
So, rearm the timer as we do in addrconf_dad_complete.
Cc: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Nicolas Dichtel [Wed, 26 Jun 2013 15:40:33 +0000 (17:40 +0200)]
sit: fix 4in4 + IPsec scenario
Since commit 32b8a8e59c9c "sit: add IPv4 over IPv4 support",
tunnel->parms.iph.protocol is 0 when both 4in4 and 6in4 are setup, but
xfrm_lookup() is called only when proto is != 0, thus we need to pass the real
value.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
By default the SH scheduler rejects connections that are hashed onto a
realserver of weight 0. This patch adds a flag to make SH choose a
different realserver in this case, instead of rejecting the connection.
The patch also adds a flag to make SH include the source port (TCP, UDP,
SCTP) in the hash as well as the source address. This basically allows
for deterministic round-robin load balancing (i.e., where any director
in a cluster of directors with identical config will send the same
packet the same way).
The flags are service flags (IP_VS_SVC_F_SCHED*) so that these options
can be set per service. They are set using a new option to ipvsadm.
Signed-off-by: Alexander Frolkin <avf@eldamar.org.uk> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Simon Horman <horms@verge.net.au>
Julian Anastasov [Tue, 18 Jun 2013 07:08:08 +0000 (10:08 +0300)]
ipvs: drop SCTP connections depending on state
Drop SCTP connections under load (dropentry context) depending
on the protocol state, just like for TCP: INIT conns are
dropped immediately, established are dropped randomly while
connections in progress or shutdown are skipped.
Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Simon Horman <horms@verge.net.au>
Julian Anastasov [Tue, 18 Jun 2013 07:08:07 +0000 (10:08 +0300)]
ipvs: replace the SCTP state machine
Convert the SCTP state table, so that it is more readable.
Change the states to be according to the diagram in RFC 2960
and add more states suitable for middle box. Still, such
change in states adds incompatibility if systems in sync
setup include this change and others do not include it.
With this change we also have proper transitions in INPUT-ONLY
mode (DR/TUN) where we see packets only from client. Now
we should not switch to 10-second CLOSED state at a time
when we should stay in ESTABLISHED state.
The short names for states are because we have 16-char space
in ipvsadm and 11-char limit for the connection list format.
It is a sequence of the TCP implementation where the longest
state name is ESTABLISHED.
Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Simon Horman <horms@verge.net.au>
This adds support for sloppy TCP and SCTP modes to IPVS.
When enabled (sysctls net.ipv4.vs.sloppy_tcp and
net.ipv4.vs.sloppy_sctp), allows IPVS to create connection state on any
packet, not just a TCP SYN (or SCTP INIT).
This allows connections to fail over from one IPVS director to another
mid-flight.
Signed-off-by: Alexander Frolkin <avf@eldamar.org.uk> Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Simon Horman <horms@verge.net.au>
Julian Anastasov [Sun, 16 Jun 2013 06:09:36 +0000 (09:09 +0300)]
ipvs: provide iph to schedulers
Before now the schedulers needed access only to IP
addresses and it was easy to get them from skb by
using ip_vs_fill_iph_addr_only.
New changes for the SH scheduler will need the protocol
and ports which is difficult to get from skb for the
IPv6 case. As we have all the data in the iph structure,
to avoid the same slow lookups provide the iph to schedulers.
Signed-off-by: Julian Anastasov <ja@ssi.bg> Acked-by: Hans Schillstrom <hans@schillstrom.com> Signed-off-by: Simon Horman <horms@verge.net.au>
Alexey Brodkin [Wed, 26 Jun 2013 07:49:26 +0000 (11:49 +0400)]
arc_emac: fix compile-time errors & warnings on PPC64
As reported by "kbuild test robot" there were some errors and warnings
on attempt to build kernel with "make ARCH=powerpc allmodconfig".
And this patch addresses both errors and warnings.
Below is a list of introduced changes:
1. Fix compile-time errors (misspellings in "dma_unmap_single") on PPC.
2. Use DMA address instead of "skb->data" as a pointer to data buffer.
This fixed warnings on pointer to int conversion on 64-bit systems.
3. Re-implemented initial allocation of Rx buffers in "arc_emac_open" in
the same way they're re-allocated during operation (receiving packets).
So once again DMA address could be used instead of "skb->data".
4. Explicitly use EMAC_BUFFER_SIZE for Rx buffers allocation.
Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com> Cc: netdev@vger.kernel.org Cc: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Francois Romieu <romieu@fr.zoreil.com> Cc: Joe Perches <joe@perches.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Mischa Jonker <mjonker@synopsys.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Grant Likely <grant.likely@linaro.org> Cc: Rob Herring <rob.herring@calxeda.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: linux-kernel@vger.kernel.org Cc: devicetree-discuss@lists.ozlabs.org Cc: Florian Fainelli <florian@openwrt.org> Cc: David Laight <david.laight@aculab.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Veaceslav Falico [Mon, 24 Jun 2013 09:49:34 +0000 (11:49 +0200)]
bonding: add an option to fail when any of arp_ip_target is inaccessible
Currently, we fail only when all of the ips in arp_ip_target are gone.
However, in some situations we might need to fail if even one host from
arp_ip_target becomes unavailable.
All situations, obviously, rely on the idea that we need *completely*
functional network, with all interfaces/addresses working correctly.
One real world example might be:
vlans on top on bond (hybrid port). If bond and vlans have ips assigned
and we have their peers monitored via arp_ip_target - in case of switch
misconfiguration (trunk/access port), slave driver malfunction or
tagged/untagged traffic dropped on the way - we will be able to switch
to another slave.
Though any other configuration needs that if we need to have access to all
arp_ip_targets.
This patch adds this possibility by adding a new parameter -
arp_all_targets (both as a module parameter and as a sysfs knob). It can be
set to:
0 or any (the default) - which works exactly as it's working now -
the slave is up if any of the arp_ip_targets are up.
1 or all - the slave is up if all of the arp_ip_targets are up.
This parameter can be changed on the fly (via sysfs), and requires the mode
to be active-backup and arp_validate to be enabled (it obeys the
arp_validate config on which slaves to validate).
Internally it's done through:
1) Add target_last_arp_rx[BOND_MAX_ARP_TARGETS] array to slave struct. It's
an array of jiffies, meaning that slave->target_last_arp_rx[i] is the
last time we've received arp from bond->params.arp_targets[i] on this
slave.
2) If we successfully validate an arp from bond->params.arp_targets[i] in
bond_validate_arp() - update the slave->target_last_arp_rx[i] with the
current jiffies value.
3) When getting slave's last_rx via slave_last_rx(), we return the oldest
time when we've received an arp from any address in
bond->params.arp_targets[].
If the value of arp_all_targets == 0 - we still work the same way as
before.
Also, update the documentation to reflect the new parameter.
v3->v4:
Kill the forgotten rtnl_unlock(), rephrase the documentation part to be
more clear, don't fail setting arp_all_targets if arp_validate is not set -
it has no effect anyway but can be easier to set up. Also, print a warning
if the last arp_ip_target is removed while the arp_interval is on, but not
the arp_validate.
v2->v3:
Use _bh spinlock, remove useless rtnl_lock() and use jiffies for new
arp_ip_target last arp, instead of slave_last_rx(). On bond_enslave(),
use the same initialization value for target_last_arp_rx[] as is used
for the default last_arp_rx, to avoid useless interface flaps.
Also, instead of failing to remove the last arp_ip_target just print a
warning - otherwise it might break existing scripts.
v1->v2:
Correctly handle adding/removing hosts in arp_ip_target - we need to
shift/initialize all slave's target_last_arp_rx. Also, don't fail module
loading on arp_all_targets misconfiguration, just disable it, and some
minor style fixes.
Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Veaceslav Falico [Mon, 24 Jun 2013 09:49:32 +0000 (11:49 +0200)]
bonding: don't trust arp requests unless active slave really works
Currently, if we receive any arp packet on a backup slave in active-backup
mode and arp_validate enabled, we suppose that it's an arp request, swap
source/target ip and try to validate it. This optimization gives us
virtually no downtime in the most common situation (active and backup
slaves are in the same broadcast domain and the active slave failed).
However, if we can't reach the arp_ip_target(s), we end up in an endless
loop of reselecting slaves, because we receive our arp requests, sent by
the active slave, and think that backup slaves are up, thus selecting them
as active and, again, sending arp requests, which fool our backup slaves.
Fix this by not validating the swapped arp packets if the current active
slave didn't receive any arp reply after it was selected as active. This
way we will only accept arp requests if we know that the current active
slave can actually reach arp_ip_target.
v3->v4:
Obey 80 lines and make checkpatch.pl happy, per Sergei's suggestion.
v1->v3:
No change.
Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Veaceslav Falico [Mon, 24 Jun 2013 09:49:31 +0000 (11:49 +0200)]
bonding: don't validate arp if we don't have to
Currently, we validate all the incoming arps if arp_validate not 0.
However, we don't have to validate backup slaves if arp_validate == active
and vice versa, so return early in bond_arp_rcv() in these cases.
It works correctly now because we verify arp_validate in slave_last_rx(),
however we're just doing useless work in bond_arp_rcv().
Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Veaceslav Falico [Mon, 24 Jun 2013 09:49:29 +0000 (11:49 +0200)]
bonding: add helper function bond_get_targets_ip(targets, ip)
Add function bond_get_targets_ip(targets, ip) which searches through
targets array of ips (arp_targets) and returns the position of first
match. If ip == 0, returns the first free slot. On failure to find the
ip or free slot, return -1.
Use it to verify if the arp we've received is valid and in sysfs.
v1->v2:
Fix "[2/6] bonding: add helper function bond_get_targets_ip(targets, ip)",
per Nikolay's advice, to verify if source ip != 0.0.0.0, otherwise we might
update 'null' arp_ip_targets' last_rx. Also, address style.
Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Cong Wang [Mon, 24 Jun 2013 11:46:54 +0000 (19:46 +0800)]
doc: fix some syntax errors in netlink mmap sample code
Cc: Patrick McHardy <kaber@trash.net> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Tue, 25 Jun 2013 20:04:22 +0000 (16:04 -0400)]
macvtap: Perform GSO on forwarding path.
When macvtap forwards skb to its tap, it needs to check
if GSO needs to be performed. This is sometimes necessary
when the HW device performed GRO, but the guest reading
from the tap does not support it (ex: Windows 7).
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Tue, 25 Jun 2013 20:04:21 +0000 (16:04 -0400)]
macvtap: Let TUNSETOFFLOAD actually controll offload features.
When the user issues TUNSETOFFLOAD ioctl, macvtap does not do
anything other then to verify arguments. This patch adds
functionality to allow users to actually control offload features.
NETIF_F_GSO and NETIF_F_GRO are always on, but the rest of the
features can be controlled.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Tue, 25 Jun 2013 20:04:20 +0000 (16:04 -0400)]
macvtap: Consistently use rcu functions
Currently macvtap uses rcu_bh functions in its
user facing fuction macvtap_get_user() and macvtap_put_user().
However, its packet handlers use normal rcu as the rcu_read_lock()
is taken in netif_receive_skb(). We can safely discontinue
the usage or rcu with bh disabled.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Tue, 25 Jun 2013 20:04:19 +0000 (16:04 -0400)]
macvtap: Convert to using rtnl lock
Macvtap uses a private lock to protect the relationship between
macvtap_queue and macvlan_dev. The private lock is not needed
since the relationship is managed by user via open(), release(),
and dellink() calls. dellink() already happens under rtnl, so
we can safely convert open() and release(), and use it in ioctl()
as well.
Suggested by Eric Dumazet.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eliezer Tamir [Mon, 24 Jun 2013 07:28:03 +0000 (10:28 +0300)]
net: poll/select low latency socket support
select/poll busy-poll support.
Split sysctl value into two separate ones, one for read and one for poll.
updated Documentation/sysctl/net.txt
Add a new poll flag POLL_LL. When this flag is set, sock_poll will call
sk_poll_ll if possible. sock_poll sets this flag in its return value
to indicate to select/poll when a socket that can busy poll is found.
When poll/select have nothing to report, call the low-level
sock_poll again until we are out of time or we find something.
Once the system call finds something, it stops setting POLL_LL, so it can
return the result to the user ASAP.
Signed-off-by: Eliezer Tamir <eliezer.tamir@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 25 Jun 2013 16:17:30 +0000 (18:17 +0200)]
net: sctp: simplify sctp_get_port
No need to have an extra ret variable when we directly can return
the value of sctp_get_port_local().
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 25 Jun 2013 16:17:29 +0000 (18:17 +0200)]
net: sctp: decouple cleaning some socket data from endpoint
Rather instead of having the endpoint clean the garbage from the
socket, use a sk_destruct handler sctp_destruct_sock(), that does
the job for that when there are no more references on the socket.
At least do this for our crypto transform through crypto_free_hash()
that is allocated when in listening state.
Also, perform sctp_put_port() only when sk is valid. At a later
point in time we can still determine if there's an option of
placing this into sk_prot->unhash() or sctp_endpoint_free() without
any races. For now, leave it in sctp_endpoint_destroy() though.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
A trailing newline has been forgotten to add into the WARN().
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 25 Jun 2013 16:17:27 +0000 (18:17 +0200)]
net: sctp: migrate cookie life from timeval to ktime
Currently, SCTP code defines its own timeval functions (since timeval
is rarely used inside the kernel by others), namely tv_lt() and
TIMEVAL_ADD() macros, that operate on SCTP cookie expiration.
We might as well remove all those, and operate directly on ktime
structures for a couple of reasons: ktime is available on all archs;
complexity of ktime calculations depending on the arch is less than
(reduces to a simple arithmetic operations on archs with
BITS_PER_LONG == 64 or CONFIG_KTIME_SCALAR) or equal to timeval
functions (other archs); code becomes more readable; macros can be
thrown out.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 25 Jun 2013 16:17:26 +0000 (18:17 +0200)]
ktime: add ms_to_ktime() and ktime_add_ms() helpers
Add two ktime helper functions that i) convert a given msec value to
a ktime structure and ii) that adds a msec value to a ktime structure.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Tue, 25 Jun 2013 16:17:25 +0000 (18:17 +0200)]
net: sctp: remove TEST_FRAME ifdef
We do neither ship a test_frame.h, nor will this be compatible with
the 2.5 out-of-tree lksctp kernel test suite anyway. So remove this
artefact.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jack Morgenstein [Tue, 25 Jun 2013 09:09:38 +0000 (12:09 +0300)]
net/mlx4_core: Fail device init if num_vfs is negative
Should not allow negative num_vfs
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.com> Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Dotan Barak [Tue, 25 Jun 2013 09:09:37 +0000 (12:09 +0300)]
net/mlx4_core: Add warning in case of command timeouts
Warning prints when there are command timeout to help debugging future
failures.
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Dotan Barak [Tue, 25 Jun 2013 09:09:36 +0000 (12:09 +0300)]
net/mlx4_core: Replace sscanf() with kstrtoint()
It is not safe to use sscanf.
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.com> Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Dotan Barak [Tue, 25 Jun 2013 09:09:35 +0000 (12:09 +0300)]
net/mlx4_en: Remove an unnecessary test
Since this variable is now part of a structure and not allocated dynamically,
this test is irrelevant now.
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Yevgeny Petrilin [Tue, 25 Jun 2013 09:09:34 +0000 (12:09 +0300)]
net/mlx4_en: Add prints when TX timeout occurs
Print a warning when a TX timeout is detected
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com> Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx4_en: Fix a race between napi poll function and RX ring cleanup
The RX rings were cleaned while there was still possible RX traffic completion
handling.
Change the sequance of events so that the port is closed and the QPs are being
stopped before RX cleanup.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net/mlx4_en: Move register_netdev() to the end of initialization function
To avoid a race between the open function and everything that happens after
register_netdev() move it to be the last operation called.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jack Morgenstein [Tue, 25 Jun 2013 09:09:30 +0000 (12:09 +0300)]
net/mlx4_en: Do not query stats when device port is down
There are no counters allocated to the eth device when the port is down, so
this query is meaningless at that time.
It also leads to querying incorrect counters (since the counter_index is not
valid when the device port is down).
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Dotan Barak [Tue, 25 Jun 2013 09:09:29 +0000 (12:09 +0300)]
net/mlx4_en: Fix resource leak in error flow
Wrong condition was used when calling iounmap.
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6: remove old token ipv6 address as soon as possible
If the tokenized ip address is re-set on an interface we depend on the
arrival of a new router advertisment to call addrconf_verify to clean
up the old address (which valid_lft is now set to 0). Old addresses can
linger around for a longer time if e.g. the source of router advertisments
vanishes.
So, call addrconf_verify immediately after setting the new tokenized
address to get rid of the old tokenized addresses.
Cc: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6: don't disable interface if last ipv6 address is removed
The reason behind this change is that as soon as we delete
the last ipv6 address of an interface we also lose the
/proc/sys/net/ipv6/conf/<interface> directory. This seems to be a
usability problem for me.
I don't see any reason why we should shutdown ipv6 on that interface in
such cases.
Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6: split duplicate address detection and router solicitation timer
This patch splits the timers for duplicate address detection and router
solicitations apart. The router solicitations timer goes into inet6_dev
and the dad timer stays in inet6_ifaddr.
The reason behind this patch is to reduce the number of unneeded router
solicitations send out by the host if additional link-local addresses
are created. Currently we send out RS for every link-local address on
an interface.
If the RS timer fires we pick a source address with ipv6_get_lladdr. This
change could hurt people adding additional link-local addresses and
specifying these addresses in the radvd clients section because we
no longer guarantee that we use every ll address as source address in
router solicitations.
Cc: Flavio Leitner <fleitner@redhat.com> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: David Stevens <dlstevens@us.ibm.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Reviewed-by: Flavio Leitner <fbl@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Sun, 23 Jun 2013 15:17:56 +0000 (08:17 -0700)]
mlx4: allow order-0 memory allocations in RX path
Signed-off-by: Eric Dumazet <edumazet@google.com>
mlx4 exclusively uses order-2 allocations in RX path, which are
likely to fail under memory pressure.
We therefore drop frames more than needed.
This patch tries order-3, order-2, order-1 and finally order-0
allocations to keep good performance, yet allow allocations if/when
memory gets fragmented.
By using larger pages, and avoiding unnecessary get_page()/put_page()
on compound pages, this patch improves performance as well, lowering
false sharing on struct page.
Also use GFP_KERNEL allocations in initialization path, as allocating 12
MB (390 order-3 pages) can easily fail with GFP_ATOMIC.
Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Amir Vadai <amirv@mellanox.com> Acked-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 25 Jun 2013 23:11:41 +0000 (16:11 -0700)]
Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next
Ben Hutchings says:
====================
1. Make EEH recovery work when using legacy interrupts, from Alexandre
Rames.
2. Enable accelerated RFS for VLAN-tagged flows, from Andy Lutomirski.
3. Improve performance for non-TCP (and particularly UDP) traffic, which
regressed in 3.10 when we switched to always allocating paged RX
buffers. Partly by Jon Cooper.
4. Some minor bug fixes to IOMMU detection, timestamping capabilities,
and IRQ cleanup on the probe failure path.
I've dropped the RX skb cache, which improved some benchmarks but
perhaps needs some reworking to be more generally useful.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Sebastian Ott [Mon, 24 Jun 2013 11:21:52 +0000 (13:21 +0200)]
qeth: use default napi weight
Since commit 82dc3c63c692b1e1d59378ecee948ac88e034aad
"net: introduce NAPI_POLL_WEIGHT" network drivers receive a warning
when they use napi weight higher than NAPI_POLL_WEIGHT. This patch
reduces QETH_NAPI_WEIGHT from 128 to 64 (NAPI_POLL_WEIGHT).
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Stefan Raspl [Mon, 24 Jun 2013 11:21:51 +0000 (13:21 +0200)]
qeth: Fix crash on initial MTU size change
When the initial MTU size is changed prior to any activity on the device
(e.g. by attaching a z/VM vNIC already configured in Linux to a guestLAN),
we call dev_kfree_skb_irq(NULL) which results in a kernel panic.
Adding a proper check for NULL pointers to address this issue.
Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com> Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com> Reviewed-by: Ursula Braun <braunu@de.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ursula Braun [Mon, 24 Jun 2013 11:21:50 +0000 (13:21 +0200)]
qeth: change default standard blkt settings for OSA
blkt settings (or LAN idle settings) for an OSA Express card
determine when and how often an OSA Express card tells the
operating system about new incoming packets. The semantic of
these settings has changed starting with OSA Express3. Currently
the qeth standard settings apply to OSA Express2 and older
generations of OSA Express cards, while new generations of OSA
Express cards require extra coding of their reasonable default.
To cover future OSA Express generations the qeth default standard
blkt setting is now the desired setting for OSA generations
starting with OSA Express3, while the fixed set of older OSA
Express cards receives its blkt settings explicitly.
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com> Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com> Reviewed-by: Stefan Raspl <raspl@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Stefan Raspl [Mon, 24 Jun 2013 11:21:49 +0000 (13:21 +0200)]
qeth: Increase default MTU for OSA devices
Increase the default MTU for real OSA devices in layer 2 mode
to 1500 Bytes for increased compatibility.
Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com> Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com> Reviewed-by: Ursula Braun <ursula.braun@de.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Andy Shevchenko [Mon, 24 Jun 2013 11:21:48 +0000 (13:21 +0200)]
netiucv: remove unused macro
If someone is interested to dump something they may consider to use
print_hex_dump() or print_hex_dump_bytes() kernel helpers.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com> Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Tue, 25 Jun 2013 08:30:11 +0000 (01:30 -0700)]
ipv6: add include file to suppress sparse warnings
commit f88c91ddba95 ("ipv6: statically link
register_inet6addr_notifier()" added following sparse warnings :
net/ipv6/addrconf_core.c:83:5: warning: symbol
'register_inet6addr_notifier' was not declared. Should it be static?
net/ipv6/addrconf_core.c:89:5: warning: symbol
'unregister_inet6addr_notifier' was not declared. Should it be static?
net/ipv6/addrconf_core.c:95:5: warning: symbol
'inet6addr_notifier_call_chain' was not declared. Should it be static?
Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Tue, 25 Jun 2013 08:21:06 +0000 (01:21 -0700)]
tcp: remove invalid __rcu annotation
struct tcp_fastopen_context has a field named tfm, which is a pointer
to a crypto_cipher structure.
It currently has a __rcu annotation, which is not needed at all.
tcp_fastopen_ctx is the pointer fetched by rcu_dereference(), but once
we have a pointer to current tcp_fastopen_context, we do not use/need
rcu_dereference() to access tfm.
This fixes a lot of sparse errors like the following :
Daniel Borkmann [Fri, 21 Jun 2013 17:38:08 +0000 (19:38 +0200)]
packet: nlmon: virtual netlink monitoring device for packet sockets
Currently, there is no good possibility to debug netlink traffic that
is being exchanged between kernel and user space. Therefore, this patch
implements a netlink virtual device, so that netlink messages will be
made visible to PF_PACKET sockets. Once there was an approach with a
similar idea [1], but it got forgotten somehow.
I think it makes most sense to accept the "overhead" of an extra netlink
net device over implementing the same functionality from PF_PACKET
sockets once again into netlink sockets. We have BPF filters that can
already be easily applied which even have netlink extensions, we have
RX_RING zero-copy between kernel- and user space that can be reused,
and much more features. So instead of re-implementing all of this, we
simply pass the skb to a given PF_PACKET socket for further analysis.
Another nice benefit that comes from that is that no code needs to be
changed in user space packet analyzers (maybe adding a dissector, but
not more), thus out of the box, we can already capture pcap files of
netlink traffic to debug/troubleshoot netlink problems.
Also thanks goes to Thomas Graf, Flavio Leitner, Jesper Dangaard Brouer.
Daniel Borkmann [Fri, 21 Jun 2013 17:38:07 +0000 (19:38 +0200)]
net: netlink: virtual tap device management
Similarly to the networking receive path with ptype_all taps, we add
the possibility to register netdevices that are for ARPHRD_NETLINK to
the netlink subsystem, so that those can be used for netlink analyzers
resp. debuggers. We do not offer a direct callback function as out-of-tree
modules could do crap with it. Instead, a netdevice must be registered
properly and only receives a clone, managed by the netlink layer. Symbols
are exported as GPL-only.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Fri, 21 Jun 2013 17:38:06 +0000 (19:38 +0200)]
net: if_arp: add ARPHRD_NETLINK type
This small patch adds the definition of ARPHRD_NETLINK which can for
example be used by netlink monitoring devices as device type. So that
sockaddr_ll can pick it up and based on that choose the correct packet
dissector.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
which initially accidently went into 'net', were
reverted there, and then properly placed into 'net-next'.
But the next net --> net-next merge accidently wiped them
out again.
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ben Hutchings [Wed, 12 Jun 2013 17:09:08 +0000 (18:09 +0100)]
sfc: Improve test for IOMMU in use
The device::iommu_group field may be set even if no IOMMU is in use.
iommu_present() is still a better indicator, although it doesn't tell
us whether *our* device is affected.
Reported-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Ben Hutchings [Wed, 22 May 2013 17:03:35 +0000 (18:03 +0100)]
sfc: Fix IRQ cleanup in case of a probe failure
The lifetime of an irq_cpu_rmap is odd: we have to allocate it before
installing IRQ handlers and free it before removing the IRQ handlers.
As a result of this asymmetry, it was omitted from some failure paths.
On another failure path, we could try to remove IRQ handlers we
had not yet installed.
Move the irq_cpu_rmap allocation and freeing alongside IRQ handler
installation and removal, in efx_nic_{init,fini}_interrupts().
Count the number of IRQ handlers successfully installed and only
remove those on the failure path.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Ben Hutchings [Thu, 16 May 2013 17:38:13 +0000 (18:38 +0100)]
sfc: Do not pass non-TCP packets into GRO code
GRO can handle non-TCP packets and pass them up without coalescing,
but it has to do some extra work to parse the packet which we can
bypass using the hardware parse result. (This condition yields a
false negative for TCP/IPv6 packets received by Falcon, but its
performance is already poor in that case due to lack of checksum
offload.)
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Alexandre Rames [Thu, 21 Mar 2013 16:41:43 +0000 (16:41 +0000)]
sfc: Fix EEH with legacy interrupts.
PCI legacy interrupts are level-triggered, and we cannot mask them up
on an isolated device. Instead, disable the IRQ at the controller
until we have recovered.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
projects / linux-beck.git / log