Mitch Williams [Fri, 15 Jan 2016 22:33:15 +0000 (14:33 -0800)]
i40e/i40evf: avoid atomics
In the case where we have a page fully used by receive data, we need to
release the page fully to the stack. Instead of calling get_page (which
increments the page count) followed by free_page (which decrements the
page count), just donate our reference to the stack. Although this
donation is not tax deductible, it does allow us to avoid two very
expensive atomic operations that reverse each other.
Change-ID: If70739792d5748995fc175ec92ac2171ed4ad8fc Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
i40e: Fix PROMISC mode for Multi-function per port (MFP) devices
This patch falls back to enabling unicast, multicast and
broadcast promiscuous mode when the driver must disable it's use
of "default port" aka defport mode (which is normally used to
provide a promiscuous mode), due to internal incompatibility
with Multiple Function per Port (aka MFP).
The situation that requires this patch is when Physical
Function 0 is the device being used, and it can support SR-IOV
when MFP is enabled, via the driver creating a VEB on an MFP
enabled adapter.
Change-ID: Ie90b00d0d58782a5dfcf2c3c9725a2eb90bd63d8 Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds a workaround for cases where we might have
interrupts that got lost but WB happened.
If that happens without this patch we will see a tx_timeout.
To work around it, this patch goes ahead and reschedules NAPI
in that situation, if NAPI is not already scheduled.
We also add a counter in ethtool to keep track of when
we detect a case of tx_lost_interrupt.
Note: napi_reschedule() can be safely called from process/service_task
context and is done in other drivers as well without an issue.
Change-ID: I00f98f1ce3774524d9421227652bef20fcbd0d20 Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Fri, 15 Jan 2016 22:33:10 +0000 (14:33 -0800)]
i40evf: support packet split receive
Support packet split receive on VFs. This is off by default but can be
enabled using ethtool private flags. Because we need to trigger a reset
from outside of i40evf_main.c, create a new function to do so, and
export it.
Also update copyright year in file headers.
Change-ID: I721aa5d70113d3d6d94102e5f31526f6fc57cbbb Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Fri, 15 Jan 2016 22:33:08 +0000 (14:33 -0800)]
i40e: get rid of magic number
We have a define for this, use it. No functional change.
Change-ID: Ic0e3ea4f562e46de63b2a8de07f291ccc10205fd Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Thu, 18 Feb 2016 04:52:12 +0000 (23:52 -0500)]
Merge branch 'vxlan-cleanups'
Jiri Benc says:
====================
vxlan: clean up rx path, consolidating extension handling
The rx path of VXLAN turned over time into kind of spaghetti code. The rx
processing is split between vxlan_udp_encap_recv and vxlan_rcv but in an
artificial way: vxlan_rcv is just called at the end of vxlan_udp_encap_recv,
continuing the rx processing where vxlan_udp_encap_recv left it. There's no
clear border between those two functions.
It makes sense to combine those functions into one; this will be actually
needed for VXLAN-GPE where we'll need to skip part of the processing which
is hard to do with the current code.
However, both functions are too long already. This patchset is shortening
them, consolidating extension handling that is spread all around together
and moving it to separate functions. (Later patchsets will do more
consolidation in other parts of the functions with the final goal of merging
vxlan_udp_encap_recv and vxlan_rcv.)
In process of consolidation of the extension handling, I needed to deal with
vni field in a generic way, as its lower 8 bits mean different things for
different extensions. While cleaning up the code to strictly distinguish
between "vni" and "vni field" (which contains vni plus an additional byte),
I also converted the code not to convert endianess back and forth.
The full picture can be seen at:
https://github.com/jbenc/linux-vxlan/commits/master
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Benc [Tue, 16 Feb 2016 20:59:03 +0000 (21:59 +0100)]
vxlan: treat vni in metadata based tunnels consistently
For metadata based tunnels, VNI is ignored when doing vxlan device lookups
(because such tunnel receives all VNIs). However, this was not honored by
vxlan_xmit_one when doing encapsulation bypass. Move the check for metadata
based tunnel to the common place where it belongs.
Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Benc [Tue, 16 Feb 2016 20:59:02 +0000 (21:59 +0100)]
vxlan: clean up rx error path
When there are unrecognized flags present in the vxlan header, it doesn't
make much sense to return the packet for further UDP processing, especially
considering that for other invalid flag combinations we drop the packet
because of previous checks.
This means we return positive value only at the beginning of the function
where tun_dst is not yet allocated. This allows us to get rid of the
bad_flags and error jump labels.
When we're dropping packet, we need to free tun_dst now.
Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Benc [Tue, 16 Feb 2016 20:58:58 +0000 (21:58 +0100)]
vxlan: keep flags and vni in network byte order
Prevent repeated conversions from and to network order in the fast path.
To achieve this, define all flag constants in big endian order and store VNI
as __be32. To prevent confusion between the actual VNI value and the VNI
field from the header (which contains additional reserved byte), strictly
distinguish between "vni" and "vni_field".
Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Benc [Tue, 16 Feb 2016 20:58:57 +0000 (21:58 +0100)]
vxlan: introduce vxlan_hdr
Currently, pointer to the vxlan header is kept in a local variable. It has
to be reloaded whenever the pskb pull operations are performed which usually
happens somewhere deep in called functions.
Create a vxlan_hdr function and use it to reference the vxlan header
instead.
Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 18 Feb 2016 04:47:32 +0000 (23:47 -0500)]
Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2016-02-17
This series contains updates to i40e/i40evf only (again).
Jesse moves sync_vsi_filters() up in the service_task because it may need
to request a reset, and we do not want to wait another round of service
task time. Refactored the enable_icr0() in order to allow it to be
decided by the caller whether the CLEARPBA (clear pending events) bit will
be set while re-enabling the interrupt. Also provides the "Don't Give Up"
patch, where the driver will keep polling trying to allocate receive buffers
until it succeeds. This should keep all receive queues running even in
the face of memory pressure. Cleans up the debugging helpers by putting
everything in hex to be consistent.
Neerav updates the DCB firmware version related checkes specific to X710
and XL710 only since the checks are not required for X722 devices.
Shannon adds the use of the new shared MAC filter bit for multicast and
broadcast filters in order to make better use of the filters available
from the device. Added a parameter to allow the driver to set the
enable/disable of statistics gathering in the hardware switch. Also the
L2 cloud filtering parameter is removed since it was never used.
Anjali refactors the force_wb and WB_ON_ITR functionality since
Force-WriteBack functionality in X710/XL710 devices has been moved out of
the clean routine and into the service task, so we need to make sure
WriteBack-On-ITR is separated out since it is still called from clean.
Catherine changes the VF driver string to reflect all the products that
are supported.
Mitch refactors the packet split receive code to properly use half-pages
for receives. Also changes the use of bitwise operators to logical
operators on clean_complete variable, while making a witty reference to
Mr. Spock. Cleans up (i.e. removes) the hsplit field in the ring
structure and use the existing macro to detect packet split enablement,
which allows debugfs dumps of the VSI to properly show which recevie
routine is in use.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 18 Feb 2016 04:08:35 +0000 (23:08 -0500)]
Merge branch 'rocker-worlds'
Jiri Pirko says:
====================
rocker: do world split
This patchset allows new rocker worlds to be easily added in future.
Two new worlds are now under development: P4 and eBPF.
The main part of the patchset is the OF-DPA carve-out. It resuts in OF-DPA
specific file. Clean cut.
Note this patchset is based on my original attempt in October 2015.
I had to rebase, included all suggestions and did lot of small changes.
Main change to go with all-port-one-world approach. Port world is set according
to what is setup in HW. Not possible to change worlds from driver.
v1->v2:
patch 12/13:
- split port_init into pre-init and init
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Tue, 16 Feb 2016 14:14:50 +0000 (15:14 +0100)]
rocker: move OF-DPA stuff into separate file
Carve out OF-DPA would specific code from the common file to the world
file. This change required struct rocker and struct rocker_port split
into world specific struct ofdpa and struct ofdpa_port. Along with this
the world specific functions and defines were renamed from prefix
"rocker_" to "ofdpa_".
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Tue, 16 Feb 2016 14:14:48 +0000 (15:14 +0100)]
rocker: remove trans parameter to rocker_cmd_exec function
The only purpose of passing this parameter is to check for
prepare phase. The only reason for a failure in that state is if
TLVs don't fit into descriptor. That is highly unlikely and if that
happens, it is a driver bug. So remove this parameter from
rocker_cmd_exec, and check for prepare phase in caller.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Tue, 16 Feb 2016 14:14:45 +0000 (15:14 +0100)]
rocker: introduce worlds infrastructure
This is another step on the way to per-world clean cut. Introduce world
ops hooks which each world can implement in world-specific way.
Also introduce world infrastructure along with OF-DPA world stub.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Tue, 16 Feb 2016 14:14:41 +0000 (15:14 +0100)]
rocker: rename rocker.c to rocker_main.c
Since "rocker.c" is going to be split into multiple files, start with
renaming original "rocker.c" file to "rocker_main.c". Multiple code
parts are going to be cut from "rocker_main.c" later on.
Fix couple of checkpatch issues on the way.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Tue, 16 Feb 2016 14:14:39 +0000 (15:14 +0100)]
rocker: remove unused rocker_port param from alloc funcs and shorten their names
No need to pass rocker_port around to alloc/free rocker functions,
since they now use switchdev_trans for memory management storage.
With the param removal, shorten the name of the functions since they now
has nothing to do with rocker port.
Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 18 Feb 2016 03:08:34 +0000 (22:08 -0500)]
Merge branch 'xgene-multiq'
Iyappan Subramanian says:
====================
Add support for Classifier and RSS
This patch set enables,
(i) Classifier engine that is used for parsing
through the packet and extracting a search string that is then used
to search a database to find associative data.
(ii) Receive Side Scaling (RSS) that does dynamic load
balancing of the CPUs by controlling the number of messages enqueued
per CPU though the help of Toeplitz Hash function of 4-tuple of
source TCP/UDP port, destination TCP/UDP port, source IPV4 address and
destination IPV4 address.
(iii) Multi queue, to make advantage of RSS
v3: Address review comments from v2
- reordered local variables from longest to shortlest line
Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Wed, 17 Feb 2016 22:35:23 +0000 (14:35 -0800)]
ixgbe: fix dates on header of ixgbe_model.h
Fixes: 9d35cf062e05 ("net: ixgbe: add minimal parser details for ixgbe") Reported-by: Mark Rustad <mark.d.rustad@intel.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Wed, 17 Feb 2016 22:34:53 +0000 (14:34 -0800)]
ixgbe: use u32 instead of __u32 in model header
I incorrectly used __u32 types where we should be using u32 types when
I added the ixgbe_model.h file.
Fixes: 9d35cf062e05 ("net: ixgbe: add minimal parser details for ixgbe") Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Mitch Williams [Thu, 14 Jan 2016 00:51:51 +0000 (16:51 -0800)]
i40e: properly show packet split status in debugfs
Get rid of the unused hsplit field in the ring struct and use the
existing macro to detect packet split enablement. This allows debugfs
dumps of the VSI to properly show which Rx routine is in use.
Change-ID: Ic4e9589e6a788ab196ed0850703f704e30c03781 Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Thu, 14 Jan 2016 00:51:50 +0000 (16:51 -0800)]
i40e/i40evf: use logical operators, not bitwise
Mr. Spock would certainly raise an eyebrow to see us using bitwise
operators, when we should clearly be relying on logic. Fascinating.
Change-ID: Ie338010c016f93e9faa2002c07c90b15134b7477 Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Thu, 14 Jan 2016 00:51:49 +0000 (16:51 -0800)]
i40e/i40evf: use pages correctly in Rx
Refactor the packet split Rx code to properly use half-pages for
receives. The previous code was doing way more mapping and unmapping
than it needed to, and wasn't properly using half-pages.
Increment the page use count each time we give a half-page to an skb,
knowing that the stack will probably process and release the page before
we need it again. Only free and reallocate pages if the count shows that
both half-pages are in use. Add counters to track reallocations and page
reuse.
Change-ID: I534b299196036b64be82b4861a0a4036310a8f22 Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jesse Brandeburg [Thu, 14 Jan 2016 00:51:48 +0000 (16:51 -0800)]
i40e/i40evf: use __GFP_NOWARN
The i40e and i40evf drivers now cleanly handle allocation
failures and can avoid kernel log spew from the memory allocator
when allocations fail, so set __GFP_NOWARN on Rx buffer alloc.
Change-ID: Ic9e1b83c495e2a3ef6b069ba7fb6e52ce134cd23 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jesse Brandeburg [Thu, 14 Jan 2016 00:51:46 +0000 (16:51 -0800)]
i40e/i40evf: try again after failure
This is the "Don't Give Up" patch. Previously the
driver could fail an allocation, and then possibly stall
a queue forever, by never coming back to continue receiving
or allocating buffers.
With this patch, the driver will keep polling trying to allocate
receive buffers until it succeeds. This should keep all receive
queues running even in the face of memory pressure.
Also update copyright year in file header.
Change-ID: I2b103d1ce95b9831288a7222c3343ffa1988b81b Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jesse Brandeburg [Thu, 14 Jan 2016 00:51:45 +0000 (16:51 -0800)]
i40e/i40evf: don't lose interrupts
While re-enabling interrupts the driver would clear all pending
causes. This meant that if an interrupt was generated while the driver
was cleaning or polling with interrupts disabled, then that interrupt
was lost. This could cause a queue to become dead, especially for
receive. Refactored the enable_icr0 function in order to allow
it to be decided by the caller whether the CLEARPBA (clear pending
events) bit will be set while re-enabling the interrupt.
Also update copyright year in file headers.
Change-ID: Ic1db100a05e13c98919057696db147a258ca365a Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
i40e: Refactor force_wb and WB_ON_ITR functionality code
Now that the Force-WriteBack functionality in X710/XL710 devices
has been moved out of the clean routine and into the service task,
we need to make sure WriteBack-On-ITR is separated out since it
is still called from clean.
In the X722 devices, Force-WriteBack implies WriteBack-On-ITR but
without the interrupt, which put the driver into a missed
interrupt scenario and a potential tx-timeout report.
With this patch, we break the two functions out, and call the
appropriate ones at the right place. This will avoid creating missed
interrupt like scenarios for X722 devices.
Also update copyright year in file headers.
Change-ID: Iacbde39f95f332f82be8736864675052c3583a40 Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Thu, 14 Jan 2016 00:51:42 +0000 (16:51 -0800)]
i40e: use new add_veb calling with VEB stats control
The new parameters for add_veb allow us to enable and disable VEB stats,
so let's use them.
Update copyright year.
Change-ID: Ie6e68c68e2d1d459e42168eda661051b56bf0a65 Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Thu, 14 Jan 2016 00:51:41 +0000 (16:51 -0800)]
i40e: add VEB stat control and remove L2 cloud filter
With the latest firmware, statistics gathering can now be enabled and
disabled in the HW switch, so we need to add a parameter to allow the
driver to set it as desired. At the same time, the L2 cloud filtering
parameter has been removed as it was never used.
Older drivers working with the newer firmware and newer drivers working
with older firmware will not run into problems with these bits as the
defaults are reasonable and there is no overlap in the bit definitions.
Also, newer drivers will be forced to update because of the change in
function call parameters, a reminder that the functionality exists.
Also update copyright year.
Change-ID: I9acb9160b892ca3146f2f11a88fdcd86be3cadcc Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Thu, 14 Jan 2016 00:51:40 +0000 (16:51 -0800)]
i40e: set shared bit for multicast filters
Add the use of the new Shared MAC filter bit for multicast and broadcast
filters in order to make better use of the filters available from the
device. The FW folks have assured me that setting this bit on older FW
will have no affect, so we don't need a version check.
Also fixed a stray indent problem nearby.
Also update copyright year.
Change-ID: I4c5826a32594382a7937a592a24d228588cee7aa Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jesse Brandeburg [Thu, 14 Jan 2016 00:51:38 +0000 (16:51 -0800)]
i40e: move sync_vsi_filters up in service_task
The sync_vsi_filters function is moved up in the service_task because
it may need to request a reset, and we don't want to wait another round
of service task time.
NOTE: Filters will be replayed by sync_vsi_filters including broadcast
and promiscuous settings.
Also, added some error handling in this space in case any of these
fail the driver will retry correctly.
Also update copyright year.
Change-ID: I23f3d552100baecea69466339f738f27614efd47 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Wed, 17 Feb 2016 21:15:47 +0000 (16:15 -0500)]
Merge branch 'inet_lro-remove'
Ben Hutchings says:
====================
Remove the inet_lro library
The old inet_lro library has been deprecated ever since GRO was
introduced, but there are still a few drivers using it. Convert
them to GRO and remove it.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Yuval Mintz [Mon, 15 Feb 2016 18:22:35 +0000 (13:22 -0500)]
qed/qede: use 8.7.3.0 FW.
This patch moves the qed* driver into utilizing the 8.7.3.0 FW.
This new FW is required for a lot of new SW features, including:
- Vlan filtering offload
- Encapsulation offload support
- HW ingress aggregations
As well as paving the way for the possibility of adding storage protocols
in the future.
V2:
- Fix kbuild test robot error/warnings.
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@qlogic.com> Signed-off-by: Manish Chopra <manish.chopra@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long [Mon, 15 Feb 2016 06:28:05 +0000 (14:28 +0800)]
sctp: remove the unused sctp_datamsg_free()
Since commit 8b570dc9f7b6 ("sctp: only drop the reference on the datamsg
after sending a msg") used sctp_datamsg_put in sctp_sendmsg, instead of
sctp_datamsg_free, this function has no use in sctp.
So we will remove it.
Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long [Mon, 15 Feb 2016 06:28:03 +0000 (14:28 +0800)]
sctp: move rcu_read_lock from __sctp_lookup_association to sctp_lookup_association
__sctp_lookup_association() is only invoked by sctp_v4_err() and
sctp_rcv(), both which run on the rx BH, and it has been protected
by rcu_read_lock [see ip_local_deliver_finish() / ipv6_rcv()].
So we can move it to sctp_lookup_association, only let
sctp_lookup_association use rcu_read_lock.
Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Rosen, Rami [Mon, 15 Feb 2016 00:39:43 +0000 (02:39 +0200)]
core: remove unneded headers for net cgroup controllers.
commit 3ed80a6 (cgroup: drop module support) made including
module.h redundant in the net cgroup controllers,
netclassid_cgroup.c and netprio_cgroup.c. This patch
removes them.
Signed-off-by: Rami Rosen <rami.rosen@intel.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Sun, 14 Feb 2016 19:56:33 +0000 (22:56 +0300)]
sh_eth: kill useless *switch* defaults
The driver often has the *default* cases doing nothing in the *switch*
statements with the integer expressions -- remove them.
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Reviewed-by: Simon Horman <horms+renesas@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Sergei Shtylyov [Sun, 14 Feb 2016 19:56:03 +0000 (22:56 +0300)]
ravb: kill useless *switch* defaults
The driver has the *default* case doing nothing in the *switch* statement
with an integer expression -- remove it.
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Reviewed-by: Simon Horman <horms+renesas@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 17 Feb 2016 20:23:53 +0000 (15:23 -0500)]
Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2016-02-17
This series contains updates to i40e/i40evf only.
Jesse cleans up a duplicate declaration in probe. Then fixes a bug where the
driver was using a offset based off a DMA handle while mapping and unmapping
using sync_single_range_for_[cpu|device], when it should be using DMA handle
(returned from alloc_coherent) and the offset of the memory to be sync'd.
Fixed an issue where sync_vsi_filter() was allocating memory in a way that
could sleep (GFP_KERNEL) which was causing a problem when called by the
team driver under rcu_read_lock().
Shannon adds a check to ensure we do not attempt to do TSO when
skb->ip_summed is not set to CHECKSUM_PARTIAL.
Kiran add functions related to port mirroring features such as add/delete
mirror rule.
Jacob assigns the i40e_pf structure directly instead of using a large
memcpy, to avoid a sparse warning and lets the compiler optimize the copy
since it know the size of the structure in advance.
Anjali enables GENEVE capability for XL710/X710 devices with firmware API
version higher than 1.4. Added flag for automatic rule eviction feature
for X722, which is disabled by default.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The following updates and fixes are included in this driver update series:
- Disable VLAN filtering in promiscuous mode
- Change from using napi_complete to napi_complete_done
- Use __napi_schedule_irqoff when running in interrupt context
- Verify ethtool speed setting is valid for the selected speedset
- Enable PFC based on the pfc_en setting
- Fix the mapping of priorities to traffic classes
- Do traffic class setup when DCB nl callbacks are invoked
- Check Rx queue fifos before stopping Rx queue DMA
- Switch from disable_irq to masking interrupts for auto-negotiation
This patch series is based on net-next.
Changes from v1:
- Removed #ifndef and #define of CRCPOLY_LE as part of the patch to
disable VLAN filtering in promiscuous mode
- Reworked changes to xgbe_setup_tc to resolve conflicts with commit 16e5cc647173 (net: rework setup_tc ndo op to consume general tc operand)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:49:28 +0000 (11:49 -0600)]
amd-xgbe: Mask auto-negotiation interrupts in ISR
Currently the auto-negotiation interrupt handling disables the irq
instead of masking off the interrupts. This was done because the phy
library was originally used to read and write the PCS registers, which
could not be performed in interrupt context. Now that the phy library is
no longer used to read and write the PCS registers the interrupts can be
masked off in the interrupt service routine eliminating the need to call
disable_irq/enable_irq. This also requires changing the protection mutex
to a spinlock.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:49:08 +0000 (11:49 -0600)]
amd-xgbe: Do traffic class setup when called through dcbnl
Currently the netdev traffic class setup is only performed when invoked
through the ndo_setup_tc interface. However, the same setup should be
performed when the dcbnl interface (ieee_setets) is invoked. Rework the
netdev traffic class setup to be invokable through either interface and
also provide the priority to traffic class mapping if available.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:48:57 +0000 (11:48 -0600)]
amd-xgbe: Fix the mapping of priorities to traffic classes
The driver is checking the pfc_en field of the ieee_pfc structure to
determine whether to associate a priority with a traffic class. This is
incorrect since the pfc_en field is for determining if PFC is enabled
for a traffic class.
The association of priority to traffic class does not depend on whether
the traffic class is enabled for PFC, so remove that check. Also, the
mapping of priorities to traffic classes should be done when configuring
the traffic classes and not the PFC support so move the priority to traffic
class association from xgbe_config_dcb_pfc to xgbe_config_dcb_tc.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:48:48 +0000 (11:48 -0600)]
amd-xgbe: Enable/disable PFC per traffic class
Currently the PFC flow control is enabled on all traffic classes if
one or more traffic classes request it. The PFC enable setting of the
traffic class should be used to determine whether to enable or disable
flow control for the traffic class.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:48:29 +0000 (11:48 -0600)]
amd-xgbe: Use __napi_schedule_irqoff
Change from calling __napi_schedule to __napi_schedule_irqoff when running
in interrupt context or when called by netpoll with interrupts already
disabled. The Tx timer function will continue to use __napi_schedule.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 17 Feb 2016 17:48:08 +0000 (11:48 -0600)]
amd-xgbe: Disable VLAN filtering when in promiscuous mode
When the hardware is placed in promiscuous mode it will still perform
VLAN filtering and therefore may not pass all packets to the driver.
Disable all VLAN filtering when entering promiscuous mode and restore
VLAN filtering upon exit from promiscuous mode. In order to avoid adding
forward declarations, move the VLAN related functions earlier in the
file.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sowmini Varadhan [Wed, 13 Jan 2016 03:32:31 +0000 (19:32 -0800)]
i40e: use eth_platform_get_mac_address()
This commit converts commit b499ffb0a22c ("i40e: Look up MAC address in
Open Firmware or IDPROM") to use eth_platform_get_mac_address()
added by commit c7f5d105495a ("net: Add eth_platform_get_mac_address()
helper.")
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Anjali Singhai [Wed, 6 Jan 2016 19:49:28 +0000 (11:49 -0800)]
i40e: Enable Geneve offload for FW API ver > 1.4 for XL710/X710 devices
This patch makes sure we check the GENEVE offload capable flag before
we attempt offload.
It also enables the Capability for XL710/X710 devices with FW API
version higher than 1.4
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Mon, 4 Jan 2016 18:33:11 +0000 (10:33 -0800)]
i40e: avoid large memcpy by assigning struct
Assign the i40e_pf structure directly instead of using a large memcpy,
which avoids a sparse warning and lets the compiler optimize the copy
since it knows the size of the structure in advance.
Change-ID: I17604e23be2616521eb760290befcb767b52b3f7 Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Driver already counted allocation errors, so print
them as part of the ethtool -S output. Useful for debugging
if your system is having trouble making memory available for
the driver.
Change-ID: I83839fa86e81e6d80f03b917c88dd3ef9a64dde0 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Mon, 4 Jan 2016 18:33:08 +0000 (10:33 -0800)]
i40e: negate PHY int mask bits
The PHY interrupt mask bits mask out the events we don't want,
so we need to negate the bitmask of events we want.
Change-ID: I273244da5a8d285b6abc84fd68a90f1e6fa0393e Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Kiran Patil [Mon, 4 Jan 2016 18:33:07 +0000 (10:33 -0800)]
i40e: APIs to Add/remove port mirroring rules
This patch implements necessary functions related to port
mirroring features such as add/delete mirror rule, function
to set promiscuous VLAN mode for VSI if mirror rule_type is
"VLAN Mirroring".
Change-ID: Iaf513fd5f188f99dcb977b48f99e73185dfddc40 Signed-off-by: Kiran Patil <kiran.patil@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The driver was being called by VLAN, bonding, teaming operations
that expected to be able to hold locks like rcu_read_lock().
This causes the driver to be held to the requirement to not sleep,
and was found by the kernel debug options for checking sleep
inside critical section, and the locking validator.
Change-ID: Ibc68c835f5ffa8ffe0638ffe910a66fc5649a7f7 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Reviewed-by: Nelson, Shannon <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The sync_vsi_filter function was allocating memory in such
a way that it could sleep (GFP_KERNEL) which was causing a problem
when called by the team driver under rcu_read_lock(), which cannot
be held while sleeping. Found with lockdep.
Change-ID: I4e59053cb5eedcf3d0ca151715be3dc42a94bdd5 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Mon, 4 Jan 2016 18:33:04 +0000 (10:33 -0800)]
i40e: do TSO only if CHECKSUM_PARTIAL is set
Don't bother trying to set up a TSO if the skb->ip_summed is not
set to CHECKSUM_PARTIAL.
Change-ID: I6495b3568e404907a2965b48cf3e2effa7c9ab55 Signed-off-by: Shannon Nelson <shannon.nelson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Driver was using an offset based off a DMA handle while mapping and
unmapping using sync_single_range_for[cpu|device], where it should
be using DMA handle (returned from alloc_coherent) and the offset of the
memory to be sync'd.
Change-ID: I208256565b1595ff0e9171ab852de06b997917c6 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Reviewed-by: Nelson, Shannon <shannon.nelson@intel.com> Reviewed-by: Williams, Mitch A <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Wed, 17 Feb 2016 14:48:50 +0000 (09:48 -0500)]
Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2016-02-16
This series contains updates to i40e/i40evf only.
Shannon adds flags to MAC allocation requests to signify that the MAC VLAN
filters should come from the shared resource pool. Added a new "set switch
config" admin queue command and the new Cisco VXLAN-GPE cloud tunnel type
for the admin queue commands. Added more detail to the NVM update debug
message in order to see the full ethtool request data. Also added a few
more bits of netdev data into the debugfs output for dump VSI.
Pandi fixes the width of two datatypes which were being declared a different
size from what they are assigned.
Anjali fixes an issue where we were not doing write-back on interrupt
throttle for legacy case in x722.
Mitch adds a counter for ARQ overflows since sometimes an ever-growing
number indicates that something bad is happening. Also added 20G speed for
Tx bandwidth calculations.
Jesse refactors the DCB function based on a community suggestion to change
the multi-level if statement into a switch statement. Cleans up VF device
IDs in the PF, since it does not need to know them.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 17 Feb 2016 14:47:37 +0000 (09:47 -0500)]
Merge branch 'tc-hw-offload'
John Fastabend says:
====================
tc offload for cls_u32 on ixgbe
This extends the setup_tc framework so it can support more than just
the mqprio offload and push other classifiers and qdiscs into the
hardware. The series here targets the u32 classifier and ixgbe
driver. I worked out the u32 classifier because it is protocol
oblivious and aligns with multiple hardware devices I have access
to. I did an initial implementation on ixgbe because (a) I have one
in my box (b) its a stable driver and (c) it is relatively simple
compared to the other devices I have here but still has enough
flexibility to exercise the features of cls_u32.
I intentionally limited the scope of this series to the basic
feature set. Specifically this uses a 'big hammer' feature bit
to do the offload or not. If the bit is set you get offloaded rules
if it is not then rules will not be offloaded. If we can agree on
this patch series there are some more patches on my queue we can
talk about to make the offload decision per rule using flags similar
to how we do l2 mac updates. Additionally the error strategy can
be improved to be hard aborting, log and continue, etc. I think
these are nice to have improvements but shouldn't block this series.
Also by adding get_parse_graph and set_parse_graph attributes as
in my previous flow_api work we can build programmable devices
and programmatically learn when rules can or can not be loaded
into the hardware. Again future work.
... v3 includes a couple style fixups suggested by Jiri and a
quick fix to ixgbe to check features flag and not dev_features
flag the latter being always set.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Wed, 17 Feb 2016 05:19:19 +0000 (21:19 -0800)]
net: ixgbe: abort with cls u32 divisor groups greater than 1
This patch ensures ixgbe will not try to offload hash tables from the
u32 module. The device class does not currently support this so until
it is enabled just abort on these tables.
Interestingly the more flexible your hardware is the less code you
need to implement to guard against these cases.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Wed, 17 Feb 2016 05:18:53 +0000 (21:18 -0800)]
net: ixgbe: add support for tc_u32 offload
This adds initial support for offloading the u32 tc classifier. This
initial implementation only implements a few base matches and actions
to illustrate the use of the infrastructure patches.
However it is an interesting subset because it handles the u32 next
hdr logic to correctly map tcp packets from ip headers using the ihl
and protocol fields. After this is accepted we can extend the match
and action fields easily by updating the model header file.
Also only the drop action is supported initially.
Here is a short test script,
#tc qdisc add dev eth4 ingress
#tc filter add dev eth4 parent ffff: protocol ip \
u32 ht 800: order 1 \
match ip dst 15.0.0.1/32 match ip src 15.0.0.2/32 action drop
<-- hardware has dst/src ip match rule installed -->
#tc filter del dev eth4 parent ffff: prio 49152
#tc filter add dev eth4 parent ffff: protocol ip prio 99 \
handle 1: u32 divisor 1
#tc filter add dev eth4 protocol ip parent ffff: prio 99 \
u32 ht 800: order 1 link 1: \
offset at 0 mask 0f00 shift 6 plus 0 eat match ip protocol 6 ff
#tc filter add dev eth4 parent ffff: protocol ip \
u32 ht 1: order 3 match tcp src 23 ffff action drop
<-- hardware has tcp src port rule installed -->
#tc qdisc del dev eth4 parent ffff:
<-- hardware cleaned up -->
Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-beck.git / log