Explicitly stop the rings belonging to each VF when disabling SR-IOV.
Even though the VFs were gone, and the associated VSIs were removed, the
rings were not stopped, and in some circumstances the hardware would
continue to access the memory formerly used by the rings, causing memory
corruption or DMAR errors, both of which would lead to general malaise
of the kernel.
To relieve this condition, explicitly stop all the rings associated with
each VF before releasing its resources.
Change-ID: I78c05d562c66e7b594b7e48d67860f49b3e5b6ec
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>
The driver was disabling Wake-on-LAN by default and waiting for the user
to expressly turn it on. This patch has the driver turning on WoL from
the start if enabled in the hardware config, which matches the behavior
of our other drivers.
Change-ID: I43faedb907f8ba4d1a61b72a7c86072b97af12b1
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>
In some rare cases the reset can take longer to complete so increase the
amount of time we wait.
Change-ID: Ib5628ec54b526a811ee33d1214fe763226406671
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The standard way to check if the AQ is enabled is to look at the
count field. So we should only set this field after we have
successfully allocated memory. To do otherwise is to incite
panic among the populace.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-10-03
This series contains updates to i40e and i40evf, some of which are to
resolve more Red Hat bugzilla issues.
Jiang Liu updates the i40e and i40evf drivers to use numa_mem_id()
instead of numa_node_id() to get the nearest node with memory which
better supports memoryless nodes.
Anjali fixes an issue from Dan Carpenter <dan.carpenter@oracle.com>,
to resolve a memory leak in X722 RSS configuration path, where we should
free the memory allocated before exiting.
Shannon modifies the drivers to ensure we have the spinlocks before we
clear the ARQ and ASQ management registers. In addition, we widen the
locked portion insert a sanity check to ensure we are working with safe
register values.
Mitch fixes an issue where under certain circumstances, we can get an
extra VF_RESOURCES message from the PF driver at runtime. When this
occurs, we need to parse it because our VSI may have changed and that
will affect the relationship with the PF driver. But this parsing also
blows away our current MAC address, so resolve the issue by restoring
the current MAC address from the netdev struct after we parse the
resource message.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver still was not offloading TSO on GRE tunnels because
it forgot to set the GSO_GRE flag, causing lots of retransmits.
This fixes generic GRE traffic (like a tunnel added like below)
whereas before it would get 1Gb/s or less, now on a 10G adapter
it gets 8.7Gb/s.
ip ad ad 11.1.0.2/24 dev ens2f0
ip l set ens2f0 up
ip link add gre2 type gretap remote 11.1.0.1 local 11.1.0.2 dev ens2f0
ip l set gre2 up
ip ad ad 192.168.124.2/24 dev gre2
ping 192.168.124.1
netperf -H 192.168.124.1
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to deprecate the use of 'struct timespec' on 32-bit
architectures, as it is will overflow in 2038. The igb
driver uses it to read the current time, and can simply
be changed to use ktime_get_real_ts64() instead.
Because of hardware limitations, there is still an overflow
in year 2106, which we cannot really avoid, but this documents
the overflow.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Reviewed-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Under certain circumstances, we can get an extra VF_RESOURCES message
from the PF driver at runtime. When this happens, we need to parse it
because our VSI may have changed out from underneath us, and that will
affect our relationship with the PF driver.
However, parsing the resources message also blows away our current MAC
address in the hardware struct, usually with all zeros. When this
happens, the next time the interface is opened, it will have no MAC
address and will a) not work and b) complain.
Fix this issue by restoring the current MAC address from the netdev
struct after we parse the resource message.
Change-ID: I6cd1b624fc20432f81dc901166c8de195b8e0e65
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>
Make sure we have the spinlocks before we clear the ARQ and ASQ management
registers. Also, widen the locked portion and make a sanity check earlier
in the send function to be sure we're working with safe register values.
Change-ID: I34b56044b33461ed780f3d2de8d62826cdf933f9
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>
Function i40e_clean_rx_irq() tries to reuse memory pages allocated
from the nearest node. To better support memoryless node, use
numa_mem_id() instead of numa_node_id() to get the nearest node with
memory.
This change should only affect performance.
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Function i40e_clean_rx_irq() tries to reuse memory pages allocated
from the nearest node. To better support memoryless node, use
numa_mem_id() instead of numa_node_id() to get the nearest node with
memory.
This change should only affect performance.
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-09-30
This series contains updates to i40e and i40evf only.
Vasily Averin provides a couple of rtnl lock/unlock fixes for both i40e
and i40evf.
Shannon provides several updates and fixes, first fixes up a type clash
in i40e_aq_rc_to_posix(), where the error codes are signed values, so we
need to treat them as such. Then fixes up a padding issue where an
extra byte is added in i40e_aqc_get_cee_dcb_cfg_v1_resp to directly
acknowledge the padding. Updated i40e to keep debugfs register read
and writes from accessing outside of the io-remapped space. Added
support and device id for another 20 GbE device.
Jesse fixes the transmit hand workaround code for ARM that was causing
Tx hangs to still occur occasionally when there really was no hang. Then
fixed the receive dropped counter to show up in netstat interface.
Refactor the interrupt enable function since it was always making the
caller add the base_vector from the VSI struct which is already passed
to the function. Fix kbuild warnings found in 0day build infrastructure
by adding a harmless cast to a dev_info(), also fix 32 bit build
warnings found by sparse.
Greg fixed a configuration error that results if a port VLAN is set
for a VF before the VF driver is loaded, so that when the VF driver is
loaded the port VLAN is ignored.
Mitch fixes the use of QOS field consistently in
i40e_ndo_set_vf_port_vlan(). Modified the init timing of the driver
to increase stability on load/unload and SR-IOV enable/disable cycles.
Anjali updates i40e to not collect VEB stats if they are disabled in the
hardware for performance reasons.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Sparse found some issues with 32 bit compilation, which probably should
at least work without warning. Not only that, but the code was wrong.
Thanks sparse!!
And thanks to the kbuild robot zero day testing for finding this issue.
$ make ARCH=i386 M=drivers/net/ethernet/intel/i40e C=2 CF="-D__CHECK_ENDIAN__"
CHECK drivers/net/ethernet/intel/i40e/i40e_main.c
include/linux/etherdevice.h:79:32: warning: restricted __be16 degrades to integer
drivers/net/ethernet/intel/i40e/i40e_main.c:7565:17: warning: shift too big (32) for type unsigned long
drivers/net/ethernet/intel/i40e/i40e_main.c:7565:17: warning: shift too big (42) for type unsigned long
drivers/net/ethernet/intel/i40e/i40e_main.c:7565:17: warning: shift too big (39) for type unsigned long
drivers/net/ethernet/intel/i40e/i40e_main.c:7565:17: warning: shift too big (40) for type unsigned long
CC: kbuild-all@01.org
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch tweaks the init timing of the driver just a little bit to
increase stability on load/unload and SR-IOV enable/disable cycles.
First, run the init_task loop a little quicker in order to reduce
overall init time.
Second, stagger the start of the init task based on the device's
PCIe function ID. This lessens the impact on the firmware when a
whole bunch of VFs are initialized simultaneously, e.g. enabling
SR-IOV without the VF driver blacklisted. For single VFs assigned
to VMs this will have no effect as the function ID will always be 0.
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>
Down was requesting queue disables, but then exited immediately without
waiting for the queues to actually disable. This could allow any
function called after i40evf_down to run immediately, including
i40evf_up, and causes a memory leak.
This issue has been fixed in a recent refactor of the reset code, but
add a couple WARN_ONs in the slow path to help us recognize if we
reintroduce this issue or if we missed any cases.
Change-ID: I27b6b5c9a79c1892f0ba453129f116bc32647dd0
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
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>
The interrupt enable function was always making the caller add
the base_vector from the VSI struct which is already passed to
the function. Just collapse the math into the helper function.
Change-ID: I54ef33aa7ceebc3231c3cc48f7b39fd0c3ff5806
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>
Due to performance reasons, VEB stats have been disabled in the hw. This
patch adds code to check for that condition before accumulating these
stats.
Change-ID: I7d805669476fedabb073790403703798ae5d878e
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>
Don't let the debugfs register read and write commands try to access
outside of the ioremapped space. While we're at it, remove the use of
a misleading constant.
Change-ID: Ifce2893e232c65c7a76c23532c658f298218a81b
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>
In i40e_ndo_set_vf_port_vlan, we were using the QOS value
inconsistently, sometimes shifting it, sometimes not. Do the shift-and-
or operation correctly, once, and use the result consistently everywhere
in the function.
Change-ID: I46f062f3edc90a8a017ecec9137f4d1ab0ab9e41
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>
The i40e rx_dropped counter was not showing up in netstat -i.
Add the right counter to be updated with the stats.
Change-ID: I4dd552e9995836099184f9d9a08e90edb591155f
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>
The arm writeback (arm_wb) code is used for kicking the Tx ring to
make sure any pending work is completed even if interrupts are
disabled. It was running when it didn't need to, and not clearing
the ring->arm_wb state after it was set. This caused Tx hangs
to still occur occasionally when there really was no hang.
Fix this by resetting the variable right after it was used.
Change-ID: I7bf75d552ba9c4bd203d40615213861a24bb5594
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>
The struct i40e_aqc_get_cee_dcb_cfg_v1_resp was originally defined with
word boundary layout issues, which most compilers deal with by silently
adding padding, making the actual struct larger than designed.
This patch adds an extra byte in fields reserved3 and reserved4 to directly
acknowledge that padding.
Because the struct doesn't actually change in size or layout, this doesn't
constitute a change in the API.
Change-ID: I53fa4741b73fa255621232a85fba000b0e223015
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>
If a port VLAN is set for a given virtual function (VF) before the VF
driver is loaded then a configuration error results in which the port
VLAN is ignored when the VF driver is subsequently loaded. This causes
the VF's MAC/VLAN filters to not use the correct VLAN filter. This
patch ensures that the port VLAN filter is considered at the right time
during configuration of the VF's MAC/VLAN filters.
Change-ID: I28f404cbc21a4c6d70a7980b87c77f13f06685a4
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
It's possible that while we are waiting for the spinlock, another
entity (that owns the spinlock) has shut down the admin queue.
If we then attempt to use the queue, we will panic.
Add a check for this condition on the receive side. This matches
an existing check on the send queue side.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously to this patch, the hardware was removing
VLAN tags from the inner header of VXLAN packets. The
hardware configuration can be changed to leave the
packet alone since that is what the linux stack
expects for this type of VLAN in VXLAN packet.
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>
Signed-off-by: David S. Miller <davem@davemloft.net>
In igb_sw_init() the sequence of calls was changed from
igb_init_queue_configuration()
igb_init_interrupt_scheme()
igb_probe_vfs()
to
igb_probe_vfs()
igb_init_queue_configuration()
igb_init_interrupt_scheme()
This results in adapter->flags not having the IGB_FLAG_HAS_MSIX bit set
during igb_probe_vfs()->igb_enable_sriov(). Therefore SR-IOV does not
get enabled properly and we run into a NULL pointer if the max_vfs
module parameter is specified (adapter->vf_data does not get allocated,
crash on accessing the structure).
[ 7.419348] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048
[ 7.419367] IP: [<ffffffffa02161c6>] igb_reset+0xe6/0x5d0 [igb]
[ 7.419370] PGD 0
[ 7.419373] Oops: 0002 [#1] SMP
[ 7.419381] Modules linked in: ahci(+) libahci igb(+) i40e(+) vxlan ip6_udp_tunnel udp_tunnel megaraid_sas(+) ixgbe(+) mdio
[ 7.419385] CPU: 0 PID: 4 Comm: kworker/0:0 Not tainted 4.2.0+ #153
[ 7.419387] Hardware name: Dell Inc. PowerEdge R720/0C4Y3R, BIOS 1.6.0 03/07/2013
[...]
[ 7.419431] Call Trace:
[ 7.419442] [<ffffffffa0217236>] igb_probe+0x8b6/0x1340 [igb]
[ 7.419447] [<ffffffff814c7f15>] local_pci_probe+0x45/0xa0
Prevent this by setting the IGB_FLAG_HAS_MSIX bit before calling
igb_probe_vfs(). The real interrupt capabilities will be checked during
igb_init_interrupt_scheme() so this is safe to do.
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The sync_vsi_filters function can be called directly under RTNL
or through the timer subtask without one. This was causing a deadlock.
If sync_vsi_filters is called from a thread which held the lock,
and in another thread the PROMISC setting got changed we would
be executing the PROMISC change in the thread which already held
the lock alongside the other filter update. The PROMISC change
requires a reset if we are on a VEB, which requires it to be called
under RTNL.
Earlier the driver would call reset for PROMISC change without
checking if we were already under RTNL and would try to grab it
causing a deadlock. This patch changes the flow to see if we are
already under RTNL before trying to grab it.
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch fixes the issue of forcing WB too often causing us to not
benefit from NAPI.
Without this patch we were forcing WB/arming interrupt too often taking
away the benefits of NAPI and causing a performance impact.
With this patch we disable force WB in the clean routine for X710
and XL710 adapters. X722 adapters do not enable interrupt to force
a WB and benefit from WB_ON_ITR and hence force WB is left enabled
for those adapters.
For XL710 and X710 adapters if we have less than 4 packets pending
a software Interrupt triggered from service task will force a WB.
This patch also changes the conditions for setting RS bit as described
in code comments. This optimizes when the HW does a tail bump and when
it does a WB. It also optimizes when we do a wmb.
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 modifies the driver timeout logic by issuing a writeback
request via a software interrupt to the hardware the first time the
driver detects a hang. The driver was too aggressive in resetting a hung
queue, so back that off by removing logic to down the netdevice after
too many hangs, and move the function to the service task.
Change-ID: Ife100b9d124cd08cbdb81ab659008c1b9abbedea
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
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>
With the addition of X550em_x SFP+ support, the driver is now
functionally equivalent to what will be the 4.2.1 driver when
released, so change the version to match.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The X540 thermal interrupt (IXGBE_EIMS_TS) is not an SDP, so it
doesn't need to be enabled in ixgbe_setup_gpie(). In fact the
value is simply not for the GPIE register at all.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The 82599 and X540 datasheets require that FCRTH be "set" for Tx
switching (VM-to-VM loopback) but it did not previously specify what
the value should be set to. It has now been determined that
the correct value is RXPBSIZE - (24*1024).
This setting is also required for later devices.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
A logic error here results in the adapter_stopped flag only being
cleared when ixgbe_setup_fc returns an error. Correct the logic.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This change does two things. First, it makes it so that we always
set the relaxed ordering bits related to the DCA registers even if
DCA is not enabled. Second, it moves the configuration out of the
ixgbe_down function and into the ixgbe_configure function before
enabling the Rx and Tx rings. This ensures that DCA is configured
correctly before starting to process packets.
Thanks to Alex Duyck for this fix.
CC: Alex Duyck <aduyck@mirantis.com>
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch skips the PCI transactions pending check in
ixgbe_disable_pcie_master. This is done to addresses a known HW
issue where the PCI transactions pending bit sticks high when there
are pending transactions. HW engineering instructed to workaround
this issue by wait and then continue with our reset flow.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Take control of an I2C mux that selects which SFP is attached to
the I2C bus. The control of the mux is captured in the taking and
releasing of the related semaphore. Because only port 1 can control
the mux, port 1 always leaves the mux set to select port 0.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
