Ido Schimmel [Fri, 16 Oct 2015 12:01:36 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch Port VLAN MAC Learning register definition
Since we currently do not support the offloading of 802.1D bridges, we
need to be able to let the device know it should not learn MAC addresses
on specific {Port, VID} pairs.
Add the SPVMLR register, which controls the learning enablement of
{Port, VID} pairs.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:35 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch Filtering Database Aging Time register definition
Add SFDAT which is used to control switch ageing time.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:34 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch Virtual-Port Enabling register definition
In order for a port to support {Port, VID} to FID mapping it needs to be
configured to a virtual port mode (as opposed to VLAN mode).
Add the SVPE register, which enables port virtualization.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:33 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch VID to FID Allocation register definition
An incoming packet can be classified into a filtering identifer (FID)
based on its VID or incoming port and VID ({Port, VID}).
Add the SVFA register, which controls this mapping.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:32 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch FID Management register definition
Filtering identifiers (FIDs) are unique identifers of bridge instances
in the hardware.
Add the SFMR register, which is responsible for the creation and
configuration of these FIDs.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:31 +0000 (14:01 +0200)]
mlxsw: reg: Add shared buffer configuration registers definitions
Add definitions of SBPR, SBCM, SBPM, SBMM and PBMC registers that are
used to configure shared buffers.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Elad Raz [Fri, 16 Oct 2015 12:01:30 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch Port VID and Switch Port VLAN Membership registers definitions
Add SPVID and SPVM registers responsible for default port VID
configuration and VLAN membership of a port.
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:29 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch FDB Notification register definition
Add SFN register which is used to poll for newly added and aged-out FDB
entries.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:28 +0000 (14:01 +0200)]
mlxsw: reg: Add Switch Filtering Database register definition
Add the SFD register which is responsible for filtering database
manipulation, including static and dynamic FDB entries.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:27 +0000 (14:01 +0200)]
mlxsw: item: Add MLXSW_ITEM_BUF_INDEXED helper
Add missing item helper which allows to access char bufs on multiple
offsets. This is needed by SFD and SFN register definitions.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:26 +0000 (14:01 +0200)]
mlxsw: item: Make src arg of memcpy_to helper const
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:25 +0000 (14:01 +0200)]
mlxsw: cmd: Introduce FID-offset flooding tables
Packets destined to offloaded netdevs will be classified to FIDs in the
device and flooded in case of BUM.
The flooding table used is of type FID-offset, which allows one to
create different flooding domains for different FIDs and specify the
offset in the flooding table for each FID (not necessarily equal to FID
or VID).
Add support for this flooding table type, by exposing the configuration
of the number of tables from this type and their size.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:24 +0000 (14:01 +0200)]
mlxsw: cmd: Introduce per-FID flooding tables
In the newly introduced Spectrum switch ASIC, packets destined to not
offloaded netdevs will be classified to special FIDs (vFIDs) in the
device and flooded to the CPU port.
The flooding table used is of type per-FID, which allows one to create
different flooding domains for different vFIDs.
While using a simple single-entry flood table is certainly sufficient at
this point, we do plan to offload 802.1D bridges involving VLAN
interfaces, thus making this change necessary.
Add support for this flooding table type, by exposing the configuration
of the number of tables from this type and their size.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Fri, 16 Oct 2015 12:01:23 +0000 (14:01 +0200)]
mlxsw: Enable configuration of flooding domains
As part of the introduction of L2 offloads, allow different ports to
join/leave the flooding domain, according to user configuration.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Fri, 16 Oct 2015 12:01:22 +0000 (14:01 +0200)]
net: introduce pre-change upper device notifier
This newly introduced netdevice notifier is called before actual change
upper happens. That provides a possibility for notifier handlers to
know upper change will happen and react to it, including possibility to
forbid the change. That is valuable for drivers which can check if the
upper device linkage is supported and forbid that in case it is not.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 16 Oct 2015 13:41:10 +0000 (06:41 -0700)]
Merge branch 'master' of git://git./linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-10-16
This series contains updates to e1000, e1000e, igb, igbvf, ixgbe, ixgbevf,
i40e, i40evf and fm10k.
Alex Duyck fixes the polling routine for i40e/i40evf were the NAPI budget
for receive cleanup was being rounded up to 1 but the netpoll call was
expecting no Rx to be processed as the budget passed was 0. Also cleaned
up IN_NETPOLL flag that was not adding any value due to the receive
cleanup was handled in NAPI. Added support for netpoll for i40evf as
well.
Jesse updates all of our drivers to use napi_complete_done() instead of
napi_complete(), which allows us to use
/sys/class/net/ethX/gro_flush_timeout. Added ethtool support to control
and report the new Interrupt Limit register, since the XL710 hardware
has a different interrupt moderation design that can support a limit of
total interrupts per second per vector.
Shannon cleans up startup log entries to cut down the number by putting
a couple behind debug flags and combining others into single line. Added
support to enable/disable printing VEB statistics via ethtool.
Jingjing fixes a compile issue by adding const to functions that return
strings that are not going to be modified.
Greg Rose cleans up defines that were not used and were causing customer
confusion.
Greg Bowers adds support for setting a new bit in the Set Local LLDP MIB
admin queue command Type field.
Mitch fixes an issue where vlan_features field was set to the same value
as netdev features field, but before the features were actually being
set up, leaving the vlan_features empty. Resolve the issue by setting
up the netdev features first, then mask out the VLAN feature bits when
assigning vlan_features. Fixed VF init timing, where in some instances
the VFs would fail to initialize the first time you loaded the driver.
To correct this, increased the delay time for the init task and wait
longer before giving up.
v2: fix missing space in function header comment in patch 3, based on
feedback from Sergei Shtylyov.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Catherine Sullivan [Mon, 28 Sep 2015 18:12:44 +0000 (14:12 -0400)]
i40e/i40evf: Bump i40e to 1.3.34 and i40evf to 1.3.21
Bump.
Change-ID: I7ec818a507554648675b9b245ced9e6b6bd9ed4e
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Mon, 28 Sep 2015 18:12:43 +0000 (14:12 -0400)]
i40e: increase AQ work limit
With 64 VFs, we can easily overwhelm the AQ on the PF if we have too low
a limit on the number of AQ requests. This leads to ARQ overflow errors,
and occasionally VFs that fail to initialize.
Since we really only hit this condition on initial VF driver load, the
requests that we process are lightweight, so this extra work doesn't
cause problems for the PF driver.
Change-ID: I620221520d8af987df6ace9ba938ffaf22107681
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 [Mon, 28 Sep 2015 18:12:42 +0000 (14:12 -0400)]
i40evf: relax and stagger init timing a bit
On some devices, in some systems, in some configurations, the VFs would
fail to initialize the first time you loaded the driver.
To correct this, increase the delay time for the init task slightly, and
wait longer before giving up.
If we enable VFs and load the VF driver in the same kernel as the PF
driver, we can totally overwhelm the PF driver with AQ requests because
all of the instances try to initialize at the same time.
To help alleviate this, stagger the initial scheduling of the init task
using the PCIe function as a multiplier. We mask off the function to
only three bits so no instance has to wait too long.
With these two changes, initializing 128 VFs on a single device goes
from four minutes to just a few seconds.
Change-ID: If3d8720c1c4e838ab36d8781d9ec295a62380936
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>
Catherine Sullivan [Mon, 28 Sep 2015 18:12:41 +0000 (14:12 -0400)]
i40e: Recognize 1000Base_T_Optical phy type when link is up
1000Base_T_Optical got added to the function that figures out what
is supported when link is down but not when link is up. Add it in there
too so that we display the correct information.
Change-ID: I85ebcdfa7c02d898c44c673b1500552a53c8042e
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Mon, 28 Sep 2015 18:12:40 +0000 (14:12 -0400)]
i40evf: correctly populate vlan_features
The vlan_features field was correctly being set to the same value as the
netdev features field. However, this was being done before the features
were actually being set up, leaving the vlan_features empty.
Also, after a reset, vlan_features will be incorrectly assigned the
previous netdev feature flags, which can contain VLAN feature bits. This
makes the VLAN code angry and will cause a stack dump.
To fix these issues, set up the netdev features first, then mask out the
VLAN feature bits when assigning vlan_features.
Change-ID: Ib0548869dc83cf6a841cb8697dd94c12359ba4d2
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>
Jingjing Wu [Mon, 28 Sep 2015 18:12:39 +0000 (14:12 -0400)]
i40e: reset the invalid msg counter in vf when a valid msg is received
When the number of invalid messages from a VF is exceeded, the VF
will be disabled, due to the invalid messages. This happens if
other VF drivers (like DPDK) send a message through the driver's
mailbox (aka virtchannel) interface, but the message is not
supported by the i40e pf driver, such as CONFIG_PROMISCUOUS_MODE.
This patch changes the num_invalid_msgs in struct i40e_vf to record
the continuous invalid msgs, and it will be reset when a valid msg
is received.
Change-ID: Iaec42fd3dcdd281476b3518be23261dd46fc3718
Signed-off-by: Jingjing Wu <jingjing.wu@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>
Jesse Brandeburg [Mon, 28 Sep 2015 18:12:37 +0000 (14:12 -0400)]
i40e/i40evf: moderate interrupts differently
The XL710 hardware has a different interrupt moderation design
that can support a limit of total interrupts per second per
vector, in addition to the "number of interrupts per second"
controls already established in the driver. This combination
of hardware features allows us to set very low default latency
settings but minimize the total CPU utilization by not
making too many interrupts, should the user desire.
The current driver implementation is still enabling the dynamic
moderation in the driver, and only using the rx/tx-usecs
limit in ethtool to limit the interrupt rate per second, by default.
The new code implemented in this patch
2) adds init/use of the new "Interrupt Limit" register
3) adds ethtool knob to control/report the limits above
Usage is ethtool -C ethx rx-usecs-high <value> Where <value> is number
of microseconds to create a rate of 1/N interrupts per second,
regardless of rx-usecs or tx-usecs values. Since there is a credit based
scheme in the hardware, the rx-usecs and tx-usecs can be configured for
very low latency for short bursts, but once the credit runs out the
refill rate on the credits is limited by rx-usecs-high.
Change-ID: I3a1075d3296123b0f4f50623c779b027af5b188d
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>
Greg Bowers [Mon, 28 Sep 2015 18:12:35 +0000 (14:12 -0400)]
i40e: Add support for non-willing Apps
Adds support for setting a new bit in the Set Local LLDP MIB AQ command
Type field. When set to 1, the bit indicates to FW that Apps should be
treated as non-willing. When 0, FW behaves as before.
Change-ID: I0d2101c1606c59c7188d3e6a0c7810e0f205233a
Signed-off-by: Greg Bowers <gregory.j.bowers@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Mon, 28 Sep 2015 18:12:34 +0000 (14:12 -0400)]
i40e: priv flag for controlling VEB stats
Add an ethtool priv flag to enable and disable printing
the VEB statistics.
Change-ID: I7654054a3a73b08aa8310d94ee8fce6219107dd8
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>
Greg Rose [Mon, 28 Sep 2015 18:12:33 +0000 (14:12 -0400)]
i40e: Removed unused defines
Two defines that are not used are causing customer confusion - remove
them.
Change-ID: Icef0325aca8e0f4fcdfc519e026bdd375e791200
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>
Shannon Nelson [Mon, 28 Sep 2015 18:12:32 +0000 (14:12 -0400)]
i40e: remove read/write failed messages from nvmupdate
Allow the nvmupdate application to decide when a read or write error
should be exposed to the user. Since the application needs to use
write probes to find the ReadOnly sections on a potentially unknown NVM
version in the HW and read probes to check the status of the last write,
some error messages are expected, but need not be shown to the users.
The driver doesn't know which are ignorable from real errors, so needs
to let the application make the decision.
Change-ID: I78fca8ab672bede11c10c820b83c26adfd536d03
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>
Jingjing Wu [Mon, 28 Sep 2015 18:12:31 +0000 (14:12 -0400)]
i40e/i40evf: Fix compile issue related to const string
Add const to functions that return strings that aren't going to be
modified. This addresses some reported compile complaints.
Change-ID: Ic56b1e814ab4d23a50480e7fdec652445f776ee8
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Mon, 28 Sep 2015 18:12:30 +0000 (14:12 -0400)]
i40e: generate fewer startup messages
Cut down on the number of startup log entries by putting a couple behind
debug flags and combining a couple others into a single line.
Change-ID: I708089f086308f84d43f8b6f0e8a634a02d058fb
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, 24 Sep 2015 23:35:47 +0000 (16:35 -0700)]
drivers/net/intel: use napi_complete_done()
As per Eric Dumazet's previous patches:
(see commit (
24d2e4a50737) - tg3: use napi_complete_done())
Quoting verbatim:
Using napi_complete_done() instead of napi_complete() allows
us to use /sys/class/net/ethX/gro_flush_timeout
GRO layer can aggregate more packets if the flush is delayed a bit,
without having to set too big coalescing parameters that impact
latencies.
</end quote>
Tested
configuration: low latency via ethtool -C ethx adaptive-rx off
rx-usecs 10 adaptive-tx off tx-usecs 15
workload: streaming rx using netperf TCP_MAERTS
igb:
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result: 941.48 10^6bits/s over 1.000 seconds ending at
1440193171.589
Alignment Offset Bytes Bytes Recvs Bytes Sends
Local Remote Local Remote Xfered Per Per
Recv Send Recv Send Recv (avg) Send (avg)
8 8 0 0
1176930056 1475.36 797726 16384.00 71905
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result: 941.49 10^6bits/s over 0.997 seconds ending at
1440193142.763
Alignment Offset Bytes Bytes Recvs Bytes Sends
Local Remote Local Remote Xfered Per Per
Recv Send Recv Send Recv (avg) Send (avg)
8 8 0 0
1175182320 50476.00 23282 16384.00 71816
i40e:
Hard to test because the traffic is incoming so fast (24Gb/s) that GRO
always receives 87kB, even at the highest interrupt rate.
Other drivers were only compile tested.
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>
Alexander Duyck [Thu, 24 Sep 2015 16:04:38 +0000 (09:04 -0700)]
i40evf: Add support for netpoll
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Thu, 24 Sep 2015 16:04:32 +0000 (09:04 -0700)]
i40e/i40evf: Drop useless "IN_NETPOLL" flag
The code in i40e and i40evf is using an "IN_NETPOLL" flag that has never
added any value due to the fact that the Rx clean-up is handled in NAPI.
As such the flag was set, the queue was scheduled via NAPI, and then polled
from the netpoll controller and if any Rx packets were processed the were
processed in the wrong context.
In addition the flag itself just added an unneeded conditional to the
hot-path so it can safely be dropped and save us a few instructions.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Thu, 24 Sep 2015 16:04:26 +0000 (09:04 -0700)]
i40e/i40evf: Fix handling of napi budget
The polling routine for i40e was rounding up the budget for Rx cleanup to
1. This is incorrect as the netpoll poll call is expecting no Rx to be
processed as the budget passed was 0.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David Ahern [Wed, 14 Oct 2015 23:44:00 +0000 (16:44 -0700)]
net: Fix suspicious RCU usage in fib_rebalance
This command:
ip route add 192.168.1.0/24 nexthop via 10.2.1.5 dev eth1 nexthop via 10.2.2.5 dev eth2
generated this suspicious RCU usage message:
[ 63.249262]
[ 63.249939] ===============================
[ 63.251571] [ INFO: suspicious RCU usage. ]
[ 63.253250] 4.3.0-rc3+ #298 Not tainted
[ 63.254724] -------------------------------
[ 63.256401] ../include/linux/inetdevice.h:205 suspicious rcu_dereference_check() usage!
[ 63.259450]
[ 63.259450] other info that might help us debug this:
[ 63.259450]
[ 63.262297]
[ 63.262297] rcu_scheduler_active = 1, debug_locks = 1
[ 63.264647] 1 lock held by ip/2870:
[ 63.265896] #0: (rtnl_mutex){+.+.+.}, at: [<
ffffffff813ebfb7>] rtnl_lock+0x12/0x14
[ 63.268858]
[ 63.268858] stack backtrace:
[ 63.270409] CPU: 4 PID: 2870 Comm: ip Not tainted 4.3.0-rc3+ #298
[ 63.272478] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 63.275745]
0000000000000001 ffff8800b8c9f8b8 ffffffff8125f73c ffff88013afcf301
[ 63.278185]
ffff8800bab7a380 ffff8800b8c9f8e8 ffffffff8107bf30 ffff8800bb728000
[ 63.280634]
ffff880139fe9a60 0000000000000000 ffff880139fe9a00 ffff8800b8c9f908
[ 63.283177] Call Trace:
[ 63.283959] [<
ffffffff8125f73c>] dump_stack+0x4c/0x68
[ 63.285593] [<
ffffffff8107bf30>] lockdep_rcu_suspicious+0xfa/0x103
[ 63.287500] [<
ffffffff8144d752>] __in_dev_get_rcu+0x48/0x4f
[ 63.289169] [<
ffffffff8144d797>] fib_rebalance+0x3e/0x127
[ 63.290753] [<
ffffffff8144d986>] ? rcu_read_unlock+0x3e/0x5f
[ 63.292442] [<
ffffffff8144ea45>] fib_create_info+0xaf9/0xdcc
[ 63.294093] [<
ffffffff8106c12f>] ? sched_clock_local+0x12/0x75
[ 63.295791] [<
ffffffff8145236a>] fib_table_insert+0x8c/0x451
[ 63.297493] [<
ffffffff8144bf9c>] ? fib_get_table+0x36/0x43
[ 63.299109] [<
ffffffff8144c3ca>] inet_rtm_newroute+0x43/0x51
[ 63.300709] [<
ffffffff813ef684>] rtnetlink_rcv_msg+0x182/0x195
[ 63.302334] [<
ffffffff8107d04c>] ? trace_hardirqs_on+0xd/0xf
[ 63.303888] [<
ffffffff813ebfb7>] ? rtnl_lock+0x12/0x14
[ 63.305346] [<
ffffffff813ef502>] ? __rtnl_unlock+0x12/0x12
[ 63.306878] [<
ffffffff81407c4c>] netlink_rcv_skb+0x3d/0x90
[ 63.308437] [<
ffffffff813ec00e>] rtnetlink_rcv+0x21/0x28
[ 63.309916] [<
ffffffff81407742>] netlink_unicast+0xfa/0x17f
[ 63.311447] [<
ffffffff81407a5e>] netlink_sendmsg+0x297/0x2dc
[ 63.313029] [<
ffffffff813c6cd4>] sock_sendmsg_nosec+0x12/0x1d
[ 63.314597] [<
ffffffff813c835b>] ___sys_sendmsg+0x196/0x21b
[ 63.316125] [<
ffffffff8100bf9f>] ? native_sched_clock+0x1f/0x3c
[ 63.317671] [<
ffffffff8106c12f>] ? sched_clock_local+0x12/0x75
[ 63.319185] [<
ffffffff8106c397>] ? sched_clock_cpu+0x9d/0xb6
[ 63.320693] [<
ffffffff8107e2d7>] ? __lock_is_held+0x32/0x54
[ 63.322145] [<
ffffffff81159fcb>] ? __fget_light+0x4b/0x77
[ 63.323541] [<
ffffffff813c8726>] __sys_sendmsg+0x3d/0x5b
[ 63.324947] [<
ffffffff813c8751>] SyS_sendmsg+0xd/0x19
[ 63.326274] [<
ffffffff814c8f57>] entry_SYSCALL_64_fastpath+0x12/0x6f
It looks like all of the code paths to fib_rebalance are under rtnl.
Fixes: 0e884c78ee19 ("ipv4: L3 hash-based multipath")
Cc: Peter Nørlund <pch@ordbogen.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert [Wed, 14 Oct 2015 21:40:44 +0000 (14:40 -0700)]
bpf: Need to call bpf_prog_uncharge_memlock from bpf_prog_put
Currently, is only called from __prog_put_rcu in the bpf_prog_release
path. Need this to call this from bpf_prog_put also to get correct
accounting.
Fixes: aaac3ba95e4c8b49 ("bpf: charge user for creation of BPF maps and programs")
Signed-off-by: Tom Herbert <tom@herbertland.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 16 Oct 2015 07:52:27 +0000 (00:52 -0700)]
Merge branch 'robust_listener'
Eric Dumazet says:
====================
tcp/dccp: make our listener code more robust
This patch series addresses request sockets leaks and listener dismantle
phase. This survives a stress test with listeners being added/removed
quite randomly.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 14 Oct 2015 18:16:28 +0000 (11:16 -0700)]
tcp/dccp: fix race at listener dismantle phase
Under stress, a close() on a listener can trigger the
WARN_ON(sk->sk_ack_backlog) in inet_csk_listen_stop()
We need to test if listener is still active before queueing
a child in inet_csk_reqsk_queue_add()
Create a common inet_child_forget() helper, and use it
from inet_csk_reqsk_queue_add() and inet_csk_listen_stop()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 14 Oct 2015 18:16:27 +0000 (11:16 -0700)]
tcp/dccp: add inet_csk_reqsk_queue_drop_and_put() helper
Let's reduce the confusion about inet_csk_reqsk_queue_drop() :
In many cases we also need to release reference on request socket,
so add a helper to do this, reducing code size and complexity.
Fixes: 4bdc3d66147b ("tcp/dccp: fix behavior of stale SYN_RECV request sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 14 Oct 2015 18:16:26 +0000 (11:16 -0700)]
Revert "inet: fix double request socket freeing"
This reverts commit
c69736696cf3742b37d850289dc0d7ead177bb14.
At the time of above commit, tcp_req_err() and dccp_req_err()
were dead code, as SYN_RECV request sockets were not yet in ehash table.
Real bug was fixed later in a different commit.
We need to revert to not leak a refcount on request socket.
inet_csk_reqsk_queue_drop_and_put() will be added
in following commit to make clean inet_csk_reqsk_queue_drop()
does not release the reference owned by caller.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Vecera [Thu, 15 Oct 2015 19:28:52 +0000 (21:28 +0200)]
drivers/net: get rid of unnecessary initializations in .get_drvinfo()
Many drivers initialize uselessly n_priv_flags, n_stats, testinfo_len,
eedump_len & regdump_len fields in their .get_drvinfo() ethtool op.
It's not necessary as these fields is filled in ethtool_get_drvinfo().
v2: removed unused variable
v3: removed another unused variable
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 16 Oct 2015 06:55:33 +0000 (23:55 -0700)]
Merge branch 'tipc-link-improvements'
Jon Maloy says:
====================
tipc: some link level code improvements
Extensive testing has revealed some weaknesses and non-optimal solutions
in the link level code.
This commit series addresses those issues.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:46 +0000 (14:52 -0400)]
tipc: update node FSM when peer RESET message is received
The change made in the previous commit revealed a small flaw in the way
the node FSM is updated. When the function tipc_node_link_down() is
called for the last link to a node, we should check whether this was
caused by a local reset or by a received RESET message from the peer.
In the latter case, we can directly issue a PEER_LOST_CONTACT_EVT to
the node FSM, so that it is ready to re-establish contact. If this is
not done, the peer node will sometimes have to go through a second
establish cycle before the link becomes stable.
We fix this in this commit by conditionally issuing the mentioned
event in the function tipc_node_link_down(). We also move LINK_RESET
FSM even away from the link_reset() function and into the caller
function, partially because it is easier to follow the code when state
changes are gathered at a limited number of locations, partially
because there will be cases in future commits where we don't want the
link to go RESET mode when link_reset() is called.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:45 +0000 (14:52 -0400)]
tipc: send out RESET immediately when link goes down
When a link is taken down because of a node local event, such as
disabling of a bearer or an interface, we currently leave it to the
peer node to discover the broken communication. The default time for
such failure discovery is 1.5-2 seconds.
If we instead allow the terminating link endpoint to send out a RESET
message at the moment it is reset, we can achieve the impression that
both endpoints are going down instantly. Since this is a very common
scenario, we find it worthwhile to make this small modification.
Apart from letting the link produce the said message, we also have to
ensure that the interface is able to transmit it before TIPC is
detached. We do this by performing the disabling of a bearer in three
steps:
1) Disable reception of TIPC packets from the interface in question.
2) Take down the links, while allowing them so send out a RESET message.
3) Disable transmission of TIPC packets on the interface.
Apart from this, we now have to react on the NETDEV_GOING_DOWN event,
instead of as currently the NEDEV_DOWN event, to ensure that such
transmission is possible during the teardown phase.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:44 +0000 (14:52 -0400)]
tipc: delay ESTABLISH state event when link is established
Link establishing, just like link teardown, is a non-atomic action, in
the sense that discovering that conditions are right to establish a link,
and the actual adding of the link to one of the node's send slots is done
in two different lock contexts. The link FSM is designed to help bridging
the gap between the two contexts in a safe manner.
We have now discovered a weakness in the implementaton of this FSM.
Because we directly let the link go from state LINK_ESTABLISHING to
state LINK_ESTABLISHED already in the first lock context, we are unable
to distinguish between a fully established link, i.e., a link that has
been added to its slot, and a link that has not yet reached the second
lock context. It may hence happen that a manual intervention, e.g., when
disabling an interface, causes the function tipc_node_link_down() to try
removing the link from the node slots, decrementing its active link
counter etc, although the link was never added there in the first place.
We solve this by delaying the actual state change until we reach the
second lock context, inside the function tipc_node_link_up(). This
makes it possible for potentail callers of __tipc_node_link_down() to
know if they should proceed or not, and the problem is solved.
Unforunately, the situation described above also has a second problem.
Since there by necessity is a tipc_node_link_up() call pending once
the node lock has been released, we must defuse that call by setting
the link back from LINK_ESTABLISHING to LINK_RESET state. This forces
us to make a slight modification to the link FSM, which will now look
as follows.
+------------------------------------+
|RESET_EVT |
| |
| +--------------+
| +-----------------| SYNCHING |-----------------+
| |FAILURE_EVT +--------------+ PEER_RESET_EVT|
| | A | |
| | | | |
| | | | |
| | |SYNCH_ |SYNCH_ |
| | |BEGIN_EVT |END_EVT |
| | | | |
| V | V V
| +-------------+ +--------------+ +------------+
| | RESETTING |<---------| ESTABLISHED |--------->| PEER_RESET |
| +-------------+ FAILURE_ +--------------+ PEER_ +------------+
| | EVT | A RESET_EVT |
| | | | |
| | +----------------+ | |
| RESET_EVT| |RESET_EVT | |
| | | | |
| | | |ESTABLISH_EVT |
| | | +-------------+ | |
| | | | RESET_EVT | | |
| | | | | | |
| V V V | | |
| +-------------+ +--------------+ RESET_EVT|
+--->| RESET |--------->| ESTABLISHING |<----------------+
+-------------+ PEER_ +--------------+
| A RESET_EVT |
| | |
| | |
|FAILOVER_ |FAILOVER_ |FAILOVER_
|BEGIN_EVT |END_EVT |BEGIN_EVT
| | |
V | |
+-------------+ |
| FAILINGOVER |<----------------+
+-------------+
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:43 +0000 (14:52 -0400)]
tipc: disallow packet duplicates in link deferred queue
After the previous commits, we are guaranteed that no packets
of type LINK_PROTOCOL or with illegal sequence numbers will be
attempted added to the link deferred queue. This makes it possible to
make some simplifications to the sorting algorithm in the function
tipc_skb_queue_sorted().
We also alter the function so that it will drop packets if one with
the same seqeunce number is already present in the queue. This is
necessary because we have identified weird packet sequences, involving
duplicate packets, where a legitimate in-sequence packet may advance to
the head of the queue without being detected and de-queued.
Finally, we make this function outline, since it will now be called only
in exceptional cases.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:42 +0000 (14:52 -0400)]
tipc: improve sequence number checking
The sequence number of an incoming packet is currently only checked
for less than, equality to, or bigger than the next expected number,
meaning that the receive window in practice becomes one half sequence
number cycle, or U16_MAX/2. This does not make sense, and may not even
be safe if there are extreme delays in the network. Any packet sent by
the peer during the ongoing cycle must belong inside his current send
window, or should otherwise be dropped if possible.
Since a link endpoint cannot know its peer's current send window, it
has to base this sanity check on a worst-case assumption, i.e., that
the peer is using a maximum sized window of 8191 packets. Using this
assumption, we now add a check that the sequence number is not bigger
than next_expected + TIPC_MAX_LINK_WIN. We also re-order the checks
done, so that the receive window test is performed before the gap test.
This way, we are guaranteed that no packet with illegal sequence numbers
are ever added to the deferred queue.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:41 +0000 (14:52 -0400)]
tipc: simplify tipc_link_rcv() reception loop
Currently, all packets received in tipc_link_rcv() are unconditionally
added to the packet deferred queue, whereafter that queue is walked and
all its buffers evaluated for delivery. This is both non-optimal and
and makes the queue sorting function unnecessary complex.
This commit changes the loop so that an arrived packet is evaluated
first, and added to the deferred queue only when a sequence number gap
is discovered. A non-empty deferred queue is walked until it is empty
or until its head's sequence number doesn't fit.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 15 Oct 2015 18:52:40 +0000 (14:52 -0400)]
tipc: limit usage of temporary skb list during packet reception
During packet reception, the function tipc_link_rcv() adds its accepted
packets to a temporary buffer queue, before finally splicing this queue
into the lock protected input queue that will be delivered up to the
socket layer. The purpose is to reduce potential contention on the input
queue lock. However, since the vast majority of packets arrive in
sequence, they will anyway be added one by one to the input queue, and
the use of the temporary queue becomes a sub-optimization.
The only case where this queue makes sense is when unpacking buffers
from a bundle packet; here we want to avoid dozens of small buffers
to be added individually to the lock-protected input queue in a tight
loop.
In this commit, we remove the general usage of the temporary queue,
and keep it only for the packet unbundling case.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Insu Yun [Thu, 15 Oct 2015 16:24:09 +0000 (12:24 -0400)]
mlx4: corretly check failed allocation
When allocation fails, mlx4_alloc_cmd_mailbox returns -ENOMEM.
Since there is no case that mlx4_alloc_cmd_mailbox returns NULL,
it needs to be checked by IS_ERR, not IS_ERR_OR_NULL
Signed-off-by: Insu Yun <wuninsu@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 15 Oct 2015 16:22:11 +0000 (09:22 -0700)]
bonding: support encapsulated ipv6 TSO
If using a sixtofour device on top of a bonding device,
skb segmentation of TCP traffic is done right before calling
bonding xmit, because bonding only enables TSO for IPv4.
This patch improves single flow performance by about 120 % on my hosts,
because segmentation is deferred right before calling slave xmit.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 16 Oct 2015 06:28:03 +0000 (23:28 -0700)]
Merge branch 'mlxsw-cleanups'
Jiri Pirko says:
====================
mlxsw: Driver update, cleanups
This patchset contains various cleanups and improvements in mlxsw driver.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 15 Oct 2015 15:43:29 +0000 (17:43 +0200)]
mlxsw: cmd: Update CONFIG_PROFILE command documentation
The meaning of certain parameters in the profile passed to the device
during initialization has changed, so update their documentation
accordingly.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 15 Oct 2015 15:43:28 +0000 (17:43 +0200)]
mlxsw: Add trap group for control packets
Previously, we trapped flooded and control packets using the same trap
group. This can cause flooded packets to overflow the PCI bus and
prevent control packets (e.g. STP, LACP) from getting to the CPU.
Solve this by splitting the RX trap group to RX and control, which allows
us to configure a policer on the first, thereby preventing it from
overflowing the PCI bus.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 15 Oct 2015 15:43:27 +0000 (17:43 +0200)]
mlxsw: Simplify traps creation
The Host Trap Group Table (HTGT) register configures trap groups, which
are populated with trap IDs using the Host PacKet Trap (HPKT) register.
However, a trap ID can only be present inside one trap group (the last
configured).
Instead of passing both the trap group and ID for the function that
packs HPKT, pass only the trap ID and derive from it the trap group.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:26 +0000 (17:43 +0200)]
mlxsw: Introduce mlxsw_reg_spms_vid_pack helper and use it
Introduce separate helper for packing SPMS VIDs, as it can be used for
multiple VIDs and not only for one as previous SPMS pack function
provided.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 15 Oct 2015 15:43:25 +0000 (17:43 +0200)]
mlxsw: reg: Adjust definition of enum mlxsw_reg_sfgc_type
Define max which would be needed later on.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:24 +0000 (17:43 +0200)]
mlxsw: reg: Remove extra space in SFGC ID define
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:23 +0000 (17:43 +0200)]
mlxsw: reg: Uppercase letters in register IDs
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:22 +0000 (17:43 +0200)]
mlxsw: Use dev_level_ratelimited instead of net_ratelimit & dev_level
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:21 +0000 (17:43 +0200)]
mlxsw: core: Do not use EMADs in mlxsw_emad_fini
Be symmetric with mlxsw_emad_init and don't use EMADs in mlxsw_emad_fini
cleanup function. Use command interface instead.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:20 +0000 (17:43 +0200)]
mlxsw: pci: Limit number of entries being sent in single MAP_FA cmd
Firmware accepts only limited number of mapping entries for MAP_FA
command. In order to prevent overflow, introduce a limit and in case the
number of entries is bigger, call MAP_FA multiple times.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:19 +0000 (17:43 +0200)]
mlxsw: pci: Remove MLXSW_PCI_RDQS/SDQS defines and checks
Remove strict number check of queues count as various ASICs have
different counts.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:18 +0000 (17:43 +0200)]
mlxsw: pci: Do not use MLXSW_PCI_SDQS_COUNT define
Use mlxsw_pci_sdq_count helper instead.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:17 +0000 (17:43 +0200)]
mlxsw: pci: Use MLXSW_PCI_CQS_MAX instead of MLXSW_PCI_CQS_COUNT
The count of CQs can be different for various ASICs, so just define
maximal value and check for that.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Thu, 15 Oct 2015 15:43:16 +0000 (17:43 +0200)]
mlxsw: switchx2: Use ETH_ALEN for mac address length
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 15 Oct 2015 15:43:15 +0000 (17:43 +0200)]
mlxsw: Remove multicast ID configuration
With respect to a firmware change, the Switch Multicast ID (SMID)
register is no longer needed, so the related configuration code can be
removed.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lendacky, Thomas [Wed, 14 Oct 2015 17:37:32 +0000 (12:37 -0500)]
amd-xgbe: Use system workqueue for device restart
A previous patch switched from using the system workqueue to the device
workqueue for various operations. During a device restart the device
workqueue is flushed so the restart cannot use this workqueue or else
a deadlock results. Move the device restart back to using the system
workqueue.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 15 Oct 2015 13:09:58 +0000 (06:09 -0700)]
Merge branch 'switchdev-locking'
Jiri Pirko says:
====================
switchdev: change locking
This is something which I'm currently struggling with.
Callers of attr_set and obj_add/del often hold not only RTNL, but also
spinlock (bridge). So in that case, the driver implementing the op cannot sleep.
The way rocker is dealing with this now is just to invoke driver operation
and go out, without any checking or reporting of the operation status.
Since it would be nice to at least put a warning in case the operation fails,
it makes sense to do this in delayed work directly in switchdev core
instead of implementing this in separate drivers. And that is what this patchset
is introducing.
So from now on, the locking of switchdev mod ops is consistent. Caller either
holds rtnl mutex or in case it does not, caller sets defer flag, telling
switchdev core to process the op later, in deferred queue.
Function to force to process switchdev deferred ops can be called by op
caller in appropriate location, for example after it releases
spin lock, to force switchdev core to process pending ops.
v1->v2:
- rebased on current net-next head (including Scott's ageing patchset)
v2->v3:
- fixed comment s/of/or/ typo suggested by Nik
v3->v4:
- the actual patchset is sent instead of different branch I send in v3 :/
v4->v5:
- added patch to "const" attr param
- reworked deferred ops infrastructure (mainly patch number 1 and
internal users (patch 3 and 5)) - resolves the issue pointed out
by John
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:55 +0000 (19:40 +0200)]
switchdev: assert rtnl mutex when going over lower netdevs
netdev_for_each_lower_dev has to be called with rtnl mutex held. So
better enforce it in switchdev functions.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:54 +0000 (19:40 +0200)]
rocker: remove nowait from switchdev callbacks.
No need to avoid sleeping in switchdev callbacks now, as the switchdev
core allows it.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:53 +0000 (19:40 +0200)]
bridge: defer switchdev fdb del call in fdb_del_external_learn
Since spinlock is held here, defer the switchdev operation. Also, ensure
that defered switchdev ops are processed before port master device
is unlinked.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:52 +0000 (19:40 +0200)]
switchdev: introduce possibility to defer obj_add/del
Similar to the attr usecase, the caller knows if he is holding RTNL and is
in atomic section. So let the called to decide the correct call variant.
This allows drivers to sleep inside their ops and wait for hw to get the
operation status. Then the status is propagated into switchdev core.
This avoids silent errors in drivers.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:51 +0000 (19:40 +0200)]
switchdev: remove pointers from switchdev objects
When object is used in deferred work, we cannot use pointers in
switchdev object structures because the memory they point at may be already
used by someone else. So rather do local copy of the value.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Scott Feldman <sfeldma@gmail.com>
Reviewed-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:50 +0000 (19:40 +0200)]
switchdev: allow caller to explicitly request attr_set as deferred
Caller should know if he can call attr_set directly (when holding RTNL)
or if he has to defer the att_set processing for later.
This also allows drivers to sleep inside attr_set and report operation
status back to switchdev core. Switchdev core then warns if status is
not ok, instead of silent errors happening in drivers.
Benefit from newly introduced switchdev deferred ops infrastructure.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:49 +0000 (19:40 +0200)]
switchdev: make struct switchdev_attr parameter const for attr_set calls
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Wed, 14 Oct 2015 17:40:48 +0000 (19:40 +0200)]
switchdev: introduce switchdev deferred ops infrastructure
Introduce infrastructure which will be used internally to defer ops.
Note that the deferred ops are queued up and either are processed by
scheduled work or explicitly by user calling deferred_process function.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
lipeng [Thu, 15 Oct 2015 04:40:34 +0000 (12:40 +0800)]
net: hisilicon: fixes a bug when using ethtool -S
this patch fixes a bug in hns driver. when we want to get statistic info
by using ethtool -S, it shows us there are 3 wrong counters info. because
the strings related to the registers are wrong. it needs to modify the
strings which give us wrong info.
Signed-off-by: lipeng <lipeng321@huawei.com>
Signed-off-by: yankejian <yankejian@huawei.com>
Signed-off-by: Yisen Zhuang <yisen.zhuang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 15 Oct 2015 12:56:32 +0000 (05:56 -0700)]
Merge branch 'master' of git://git./linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-10-15
This series contains updates to i40e, i40evf and ixgbe.
Emil changes the ixgbe driver to disable LRO by default in favor or GRO.
Mark provides two changes for ixgbe, first fixes a semaphore issue when
a reset never completes, it is necessary to retake the semaphore before
returning.
Jesse fixes up a missing function header comment variable reference. Then
enables ethtool priv flags to control flow director at runtime.
Neerav changes several i40e error messages to debug only since the
messages were printing when there was no functional issue and were meant
for debug only.
Catherine changes the i40e driver to make only X722 support 100M SGMII,
since it is the only device to actually support it.
Anjali modifies the i40e/i40evf driver to add writeback on ITR offload
support for X722 since the device has a way to work around the
descriptor writeback issue.
Mitch cleans up obsolete code. Also reduces the i40evf init time by
shortening up the delays in the init task to aid in performance in
load/unload tests and mitigates DMAR errors in VF enable/disable tests.
Shannon modifies i40e to allow flow director sideband when the device
is in MFP mode and only has one partition enabled, since we still have
plenty of interrupts for managing the flow director activity. Also
cleaned up flow director ATR control in debugfs since the priv flag
has been added to our ethtool interface. Makes several general code
cleanups of redundant or unnecessary code for i40e.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Mark Rustad [Wed, 9 Sep 2015 20:37:33 +0000 (13:37 -0700)]
ixgbe: Check for setup_internal_link method
Only call the internal_setup_link method when it is provided. This
check is required for newer version parts.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Catherine Sullivan [Thu, 3 Sep 2015 21:19:02 +0000 (17:19 -0400)]
i40e/i40evf: Bump i40e version to 1.3.28 and i40evf to 1.3.19
Bump.
Change-ID: I8d9a99f320af43960deba8718eee2d6de50eaf46
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mitch Williams [Thu, 3 Sep 2015 21:19:01 +0000 (17:19 -0400)]
i40evf: speed up init
Shorten up the delays in the init task, allowing the VF driver to
initialize faster. This aids performance in load/unload tests and
mitigates DMAR errors in VF enable/disable tests with absurdly short
delays. In the real world, the VF driver will come up more quickly.
The original values were set conservatively based on what we expected
from the firmware in terms of performance. Now that the driver is in use
and we know how well firmware responds to our requests, we can shorten
these delays.
Change-ID: Ibead77d34b19e8170e667c3f58bc14748bbc5bc9
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>
Shannon Nelson [Thu, 3 Sep 2015 21:19:00 +0000 (17:19 -0400)]
i40e: remove unnecessary string copy operations
Save a little stack space and remove unnecessary strncpy() with a little
string pointer.
Change-ID: Id2719d34710bfc273d3bb445fec085cd04276e88
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>
Anjali Singhai Jain [Thu, 3 Sep 2015 21:18:59 +0000 (17:18 -0400)]
i40e: X722 is on the IOSF bus and does not report the PCI bus info
X722 will report Gen 1x1 in the PCI config space as it is on
IOSF bus, so skip the PCI bus link/speed check.
Change-ID: Icd5f5751dc7fb00dccf0d5dc5a0a644948e7062e
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>
Kevin Scott [Thu, 3 Sep 2015 21:18:58 +0000 (17:18 -0400)]
i40e: Store off PHY capabilities
Store off reported PHY capabilities in link_info structure.
Change-ID: Ife0f037c26983ca985dbf79abf33f8f8791369e8
Signed-off-by: Kevin Scott <kevin.c.scott@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Shannon Nelson [Thu, 3 Sep 2015 21:18:57 +0000 (17:18 -0400)]
i40e/i40evf: remove redundant declarations of a variable and a function
Remove a variable declaration inside an if block hiding an existing
declaration at the start of the function.
Also remove a forward function declaration that is no longer needed due
to code re-organization.
Change-ID: I12954668b722718074949c93d74cd20eaacd93e4
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, 3 Sep 2015 21:18:56 +0000 (17:18 -0400)]
i40e: remove FD atr control from debugfs
Since the flow-director-atr priv flag was added to our ethtool interface,
we don't need the on/off control in debugfs.
Change-ID: Ib3b599916434ab30ccd40074e71d7a81609b5bb5
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, 3 Sep 2015 21:18:55 +0000 (17:18 -0400)]
i40e: allow FD SB if MFP mode only has 1 partition
Even though the device might be in MFP mode, if there's only one partition
enabled, then we still have plenty of interrupts for managing the Flow
Directory Sideband activity. This patch enables FD SB in this case.
This patch also reverses the sense of the conditional in order to remove
the negative logic.
Change-ID: I9edf211a6219fc8d159b4be9964f9fd7f4e00bc0
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>
Mitch Williams [Thu, 3 Sep 2015 21:18:54 +0000 (17:18 -0400)]
i40e: remove obsolete version check
This version check only applies to very, very old firmware,
that only ran on A0 hardware, which we never shipped and don't
support in this driver anyway. Remove it, before somebody
gets hurt.
Change-ID: I3752d090ff488acf98ee76b075af961e9c968ee4
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>
Anjali Singhai Jain [Thu, 3 Sep 2015 21:18:53 +0000 (17:18 -0400)]
i40e/i40evf: Add WB_ON_ITR offload support
X722 has a way to work around the descriptor WB issue,
this offload helps turn that feature on.
Change-ID: I7ffa67622426bfca5a651417b63e3afcfeb60412
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>
Catherine Sullivan [Thu, 3 Sep 2015 21:18:52 +0000 (17:18 -0400)]
i40e: Remove 100M SGMII unless hw is X722
Only the X722 device now supports 100M SGMII, and nothing supports
100M on 1000Base_T.
Change-ID: I6f44dcd818944edd40041410e6de380f4a359a0c
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
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>
Neerav Parikh [Thu, 3 Sep 2015 21:18:50 +0000 (17:18 -0400)]
i40e: Change some messages from info to debug only
There are several error messages that have been printing when there is
no functional issue. These messages should be available at debug message
level only.
Change-ID: Id91e47bf942c483563995f30d8705fa53acd5aa3
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
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, 3 Sep 2015 21:18:49 +0000 (17:18 -0400)]
i40e: use priv flags to control flow director
Some customers wish to be able to control our hardware specific
feature called flow director, at runtime. This patch enables
ethtool priv flags to control this driver/hardware specific feature.
ethtool --set-priv-flags ethX flow-director-atr off
NOTE: the ethtool ntuple interface controls the flow-director
sideband rules.
Change-ID: Iba156350b07fa2ce66f53ded51739f9a3781fe0e
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, 3 Sep 2015 21:18:48 +0000 (17:18 -0400)]
i40e: Add missing parameter comment to ndo_bridge_setlink
Add nlflags to the function comment for ndo_bridge_setlink.
Change-ID: I34c704f307f2a3f7bac3ca4b44e2a094d3d082d6
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>
Mark Rustad [Wed, 26 Aug 2015 21:10:22 +0000 (14:10 -0700)]
ixgbe: Fix CS4227-related semaphore error on reset failure
If the reset never completes, it is necessary to retake the
semaphore before returning, because the caller will release
the semaphore.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Emil Tantilov [Tue, 25 Aug 2015 01:08:31 +0000 (18:08 -0700)]
ixgbe: disable LRO by default
This patch disables LRO by default in favor of GRO.
LRO is incompatible with forwarding and is disabled when forwarding
is turned on which makes the default offloads of the driver
inconsistent. LRO can still be enabled via ethtool.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Thu, 15 Oct 2015 02:14:50 +0000 (19:14 -0700)]
Merge branch 'mlx-next'
Or Gerlitz says:
====================
Mellanox driver update, Oct 14 2015
This series contains two more patches from Eli, patch from Majd
to support PCI error handlers and a fix from Jack to mlx4 VFs
when probed without a provisioned mac address.
The patch set applied on top of net-next commit
bbb300e "Merge branch 'bridge-vlan'"
changes from V0:
- made the health flag int --> bool to address comment from Dave on patch #1
- fixed sparse warning noted by the 0-day build tests in patch #2
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jack Morgenstein [Wed, 14 Oct 2015 14:43:48 +0000 (17:43 +0300)]
net/mlx4_core: Replace VF zero mac with random mac in mlx4_core
By design, when no default MAC addresses are set in the Hypervisor for VFs,
the VFs are passed zero-macs. When such a MAC is received by the VF, it
generates a random MAC address and registers that MAC address
with the Hypervisor.
This random mac generation is currently done in the mlx4_en module.
There is a problem, though, if the mlx4_ib module is loaded by a VF before
the mlx4_en module. In this case, for RoCE, mlx4_ib will see the un-replaced
zero-mac and register that zero-mac as part of QP1 initialization.
Having a zero-mac in the port's MAC table creates problems for a
Baseboard Management Console. The BMC occasionally sends packets with a
zero-mac destination MAC. If there is a zero-mac present in the port's
MAC table, the FW will send such BMC packets to the host driver rather than
to the wire, and BMC will stop working.
To address this problem, we move the replacement of zero-mac addresses
with random-mac addresses to procedure mlx4_slave_cap(), which is part of the
driver startup for VFs, and is before activation of mlx4_ib and mlx4_en.
As a result, zero-mac addresses will never be registered in the port MAC table
by the driver.
In addition, when mlx4_en does initialize the net device, it needs to set
the NET_ADDR_RANDOM flag in the netdev structure if the address was
randomly generated. This is done so that udev on the VM does not create
a new device name after each VF probe (VM boot and such). To accomplish this,
we add a per-port flag in mlx4_dev which gets set whenever mlx4_core replaces
a zero-mac with a randomly-generated mac. This flag is examined when mlx4_en
initializes the net-device.
Fix was suggested by Matan Barak <matanb@mellanox.com>
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>
Eli Cohen [Wed, 14 Oct 2015 14:43:47 +0000 (17:43 +0300)]
net/mlx5_core: Wait for FW readiness on startup
On device initialization, wait till firmware indicates that that it is done
with initialization before proceeding to initialize the device.
Also update initialization segment layout to match driver/firmware
interface definitions.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Majd Dibbiny [Wed, 14 Oct 2015 14:43:46 +0000 (17:43 +0300)]
net/mlx5_core: Add pci error handlers to mlx5_core driver
This patch implement the pci_error_handlers for mlx5_core which allow the
driver to recover from PCI error.
Once an error is detected in the PCI, the mlx5_pci_err_detected is called
and it:
1) Marks the device to be in 'Internal Error' state.
2) Dispatches an event to the mlx5_ib to flush all the outstanding cqes
with error.
3) Returns all the on going commands with error.
4) Unloads the driver.
Afterwards, the FW is reset and mlx5_pci_slot_reset is called and it
enables the device and restore it's pci state.
If the later succeeds, mlx5_pci_resume is called, and it loads the SW
stack.
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eli Cohen [Wed, 14 Oct 2015 14:43:45 +0000 (17:43 +0300)]
net/mlx5_core: Fix internal error detection conditions
The detection of a fatal condition has been updated to take into account
the state reported by the device or by detecting an all ones read of the
firmware version which indicates that the device is not accessible.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This page took 0.050743 seconds and 5 git commands to generate.