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>
Make sure the Tx checksum encoder knows about GRE protocol and sets the
descriptor flag appropriately.
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>
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>
i40e_get_head needs to be called in multiple files in a further patch,
prepare by moving the function into a header file.
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>
When fixing the TSO support I noticed we just mask ->gso_size with the
MSSMask value and don't care about the consequences.
Provide a .ndo_features_check() method which drops the NETIF_F_TSO
feature for any skb which would exceed the maximum, and thus forces it
to be segmented by software.
Then we can stop the masking in cp_start_xmit(), and just WARN if the
maximum is exceeded, which should now never happen.
Finally, Francois Romieu noticed that we didn't even have the right
value for MSSMask anyway; it should be 0x7ff (11 bits) not 0xfff.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I fixed TSO. Hardware checksum and scatter/gather also appear to be
working correctly both on real hardware and in QEMU's emulation.
Let's enable them by default and see if anyone screams...
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/ipv4/arp.c
The net/ipv4/arp.c conflict was one commit adding a new
local variable while another commit was deleting one.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) When we run a tap on netlink sockets, we have to copy mmap'd SKBs
instead of cloning them. From Daniel Borkmann.
2) When converting classical BPF into eBPF, fix the setting of the
source reg to BPF_REG_X. From Tycho Andersen.
3) Fix igmpv3/mldv2 report parsing in the bridge multicast code, from
Linus Lussing.
4) Fix dst refcounting for ipv6 tunnels, from Martin KaFai Lau.
5) Set NLM_F_REPLACE flag properly when replacing ipv6 routes, from
Roopa Prabhu.
6) Add some new cxgb4 PCI device IDs, from Hariprasad Shenai.
7) Fix headroom tests and SKB leaks in ipv6 fragmentation code, from
Florian Westphal.
8) Check DMA mapping errors in bna driver, from Ivan Vecera.
9) Several 8139cp bug fixes (dev_kfree_skb_any in interrupt context,
misclearing of interrupt status in TX timeout handler, etc.) from
David Woodhouse.
10) In tipc, reset SKB header pointer after skb_linearize(), from Erik
Hugne.
11) Fix autobind races et al. in netlink code, from Herbert Xu with
help from Tejun Heo and others.
12) Missing SET_NETDEV_DEV in sunvnet driver, from Sowmini Varadhan.
13) Fix various races in timewait timer and reqsk_queue_hadh_req, from
Eric Dumazet.
14) Fix array overruns in mac80211, from Johannes Berg and Dan
Carpenter.
15) Fix data race in rhashtable_rehash_one(), from Dmitriy Vyukov.
16) Fix race between poll_one_napi and napi_disable, from Neil Horman.
17) Fix byte order in geneve tunnel port config, from John W Linville.
18) Fix handling of ARP replies over lightweight tunnels, from Jiri
Benc.
19) We can loop when fib rule dumps cross multiple SKBs, fix from Wilson
Kok and Roopa Prabhu.
20) Several reference count handling bug fixes in the PHY/MDIO layer
from Russel King.
21) Fix lockdep splat in ppp_dev_uninit(), from Guillaume Nault.
22) Fix crash in icmp_route_lookup(), from David Ahern.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
net: Fix panic in icmp_route_lookup
net: update docbook comment for __mdiobus_register()
ppp: fix lockdep splat in ppp_dev_uninit()
net: via/Kconfig: GENERIC_PCI_IOMAP required if PCI not selected
phy: marvell: add link partner advertised modes
net: fix net_device refcounting
phy: add phy_device_remove()
phy: fixed-phy: properly validate phy in fixed_phy_update_state()
net: fix phy refcounting in a bunch of drivers
of_mdio: fix MDIO phy device refcounting
phy: add proper phy struct device refcounting
phy: fix mdiobus module safety
net: dsa: fix of_mdio_find_bus() device refcount leak
phy: fix of_mdio_find_bus() device refcount leak
ip6_tunnel: Reduce log level in ip6_tnl_err() to debug
ip6_gre: Reduce log level in ip6gre_err() to debug
fib_rules: fix fib rule dumps across multiple skbs
bnx2x: byte swap rss_key to comply to Toeplitz specs
net: revert "net_sched: move tp->root allocation into fw_init()"
lwtunnel: remove source and destination UDP port config option
...
The builds of allmodconfig of avr32 is failing with:
drivers/net/ethernet/via/via-rhine.c:1098:2: error: implicit declaration
of function 'pci_iomap' [-Werror=implicit-function-declaration]
drivers/net/ethernet/via/via-rhine.c:1119:2: error: implicit declaration
of function 'pci_iounmap' [-Werror=implicit-function-declaration]
The generic empty pci_iomap and pci_iounmap is used only if CONFIG_PCI
is not defined and CONFIG_GENERIC_PCI_IOMAP is defined.
Add GENERIC_PCI_IOMAP in the dependency list for VIA_RHINE as we are
getting build failure when CONFIG_PCI and CONFIG_GENERIC_PCI_IOMAP both
are not defined.
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a phy_device_remove() function to complement phy_device_register(),
which undoes the effects of phy_device_register() by removing the phy
device from visibility, but not freeing it.
This allows these details to be moved out of the mdio bus code into
the phy code where this action belongs.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
of_phy_find_device() increments the phy struct device refcount, which
we need to properly balance. Add code to network drivers using this
function to ensure that the struct device refcount is correctly
balanced.
For xgene, looking back in the history, we should be able to use
of_phy_connect() with a zero flags argument for the DT case as this is
how the driver used to operate prior to de7b5b3d79 ("net: eth: xgene:
change APM X-Gene SoC platform ethernet to support ACPI").
This leaves the Cavium Thunder BGX unfixed; fixing this driver is a
complicated task, one which the maintainers need to be involved with.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Benefit from previously introduced transaction item queue infrastructure
and remove rocker specific transaction memory management.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There will be needed to have switchdev_trans available down in the call
chain, so propagate it instead of trans phase enum. This enum will be
removed anyway. Also, use prepare/commit phase check helpers to get
information about current phase of transaction.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before it disappears completely, move transaction phase enum under
transaction structure and make attr/obj structures a bit cleaner.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now, the memory allocation in prepare/commit state is done separatelly
in each driver (rocker). Introduce the similar mechanism in generic
switchdev code, in form of queue. That can be used not only for memory
allocations, but also for different items. Abort item destruction
is handled as well.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is temporary, name "trans" will be used for something else and
"trans_ph" will eventually disappear.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-09-23
This series contains updates to ixgbe only.
Mark provides all the changes in this series, first clears the destination
location for I2C data initially so that the received data will not be
corrupted by previous attempts. Then reduced the pauses/delays in the
PHY detection when no SFP is present by reducing the number of retires,
once an SFP is detected, the "normal" number of retries in PHY detection
will be used. Added support for X55EM_x SFP+ dual-speed, and fixed 1G and
10G link stability for X550EM_x by configuring the CS4227 correctly by
moving code to ixgbe_setup_mac_link_sfp_x550em(). Added functionality to
reset CS4227, since on some platforms the CS4227 does not initialize
properly. Next reduces the SFP polling rate, due to when an SFP is not
present, the I2C timeouts that result are very costly. So prevent the
SFP polling from being done more than once every two seconds. Added
support for I2C bus MUX. Fixed the setting of RDRXCTL register which
should fall through X540 and 82599, not 82598. In addition, added small
packet padding support in X550 by setting RDRXCTL.PSP when the driver is
in SRIOV mode. Fixed a known hardware issue where the PCI transactions
pending bit sticks high when there are pending transactions, so
workaround the issue by wait and then continue with our reset flow.
Added a new device ID for X550EM device with SFPs. Provided a fix with
the DCA setup, which was suggested by Alex Duyck <aduyck@mirantis.com>,
by making it so that we always set the relaxed ordering bits related to
the DCA registers even if DCA is not enbaled. Then moves the
configuration out of the ixgbe_down() and into ixgbe_configure() before
enabling the transmit and receive rings. This ensures that DCA is
configured correctly before starting the processing of packets.
Fixed VM-to-VM loopback mode which requires that FCRTH be set, but
the datasheets did not specify what the value should be. It has now
been determined that the correct value should be RXPBSIZE - (24*1024).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
After a good amount of debugging, I found bnx2x was byte swaping
the 40 bytes of rss_key.
If we byte swap the key, then bnx2x generates hashes matching
MSDN specs as documented in (Verifying the RSS Hash Calculation)
https://msdn.microsoft.com/en-us/library/windows/hardware/ff571021%
28v=vs.85%29.aspx
It is mostly a non issue, unless we want to mix different NIC
in a host, and want consistent hashing among all of them, ie
if they all use the boot time generated rss key, or if some application
is choosing specific tuple(s) so that incoming traffic lands into known
rx queue(s).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use of_property_read_u32 instead of of_get_property with return value
checks and endianness conversion.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Reviewed-by: Sören Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use of_property_read_u32 to read the "clock-frequency" property instead
of using of_get_property with return value checks.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Reviewed-by: Sören Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The device is set as wakeup capable using proper wakeup API but the
driver misuses IRQF_NO_SUSPEND to set the interrupt as wakeup source
which is incorrect.
This patch removes the use of IRQF_NO_SUSPEND flags replacing it with
enable_irq_wake instead.
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Claudiu Manoil <claudiu.manoil@freescale.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
Add new device ID for X550EM device with SFPs.
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>
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>
This patch sets RDRXCTL.PSP when the driver is in SRIOV mode which
enables padding of small packets.
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>
Setting the X550* RDRXCTL register should fall through into X540
and 82599, not 82598.
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>
The timeout path is supposed to release the semaphore, so do that.
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>
Reduce the frequency of polling for SFP modules. Because the
service task sometimes runs at high rates, we can poll for
SFPs too often. When an SFP is not present, the I2C timeouts
that result are very costly. So, prevent SFP polling from
being done more than once every two seconds. To reduce latency,
the poll time is cleared in a couple of cases to permit the
next service task execution to poll the SFP module.
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>
Since SFP+ can be used with some X550 devices, permit them to be
detected.
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>
On some hardware platforms, the CS4227 does not initialize properly.
Detect those cases and reset it appropriately.
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>
Configures the CS4227 correctly for both 1G and 10G operation,
by moving the code to ixgbe_setup_mac_link_sfp_x550em(). It
needs to be in this function because we need both the module
type and the speed, and this is the only function in the init
flow that knows the speed. In contrast,
ixgbe_setup_sfp_modules_X550em() does not know the speed, so we
can't do anything useful here. This is a fundamental difference
from the previous flow, and is due to the way the CS4227 is
implemented.
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>
This patch adds X550EM_x SFP+ dual-speed support. 82599 fiber link
code was moved from ixgbe_82599.c to ixgbe_common.c for use by
X550EM. SFP MAC link code is added to x550EM.
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>
Reduce the number of retries during PHY detection. This reduces
pauses when no SFP is present. Once an SFP is detected, the normal
retry count will be used.
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>
Clear the destination location for I2C data initially so that
the received data will not be affected by previous attempts.
This could have returned wrong data in certain retry sequences.
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>
In case the DaVinci Emac is directly connected to a
non-mdio PHY/device, it should be possible to provide
a fixed link configuration in the DT.
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-09-22
This series contains updates to e1000, e1000e, igbvf, ixgbe, ixgbevf and
fm10k.
Jacob provides several updates for fm10k, which cleans up comments and
most notably a fix for a corner case issue with the PF/VF mailbox code.
The issue being fm10k_mbx_reset_work clears various states about the
mailbox, but does not clear the Tx FIFO head/tail pointers. We also
are not able to simply clear these pointers, as we would drop
untransmitted messages without error. Also adds support for extra debug
statistics, which provides the ability to see what the PF thinks the
VF mailboxes look like.
Don adds support for SFP+ in X550 and support for SCTP flow director
filters SCTP mask.
Francois Romieu dusts off the e1000 driver and removes some dead calls
to e1000_init_eeprom_params().
Toshiaki Makita provides three patches to enable TSO for stacked VLAN's
on e1000e, igbvf and ixgbevf.
Mark provides the first of several ixgbe updates. First updates the
driver to accept SFP not present error for all devices, since an SFP
can still be inserted. Adds support for SFP insertion interrupt on
X550EM devices with SPFs. Adds I2C combined operations on X550EM
(not X550) devices. Moved the setting of lan_id to before any I2C
eeprom access. Lastly, set the bit bang mode in the hardware when
performing bit banding I2C operations on X550.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
We are seeing unexplained TX timeouts under heavy load. Let's try to get
a better idea of what's going on.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The low 16 bits of the 'opts1' field in the TX descriptor are supposed
to still contain the buffer length when the descriptor is handed back to
us. In practice, at least on my hardware, they don't. So stash the
original value of the opts1 field and get the length to unmap from
there.
There are other ways we could have worked out the length, but I actually
want a stash of the opts1 field anyway so that I can dump it alongside
the contents of the descriptor ring when we suffer a TX timeout.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We calculate the value of the opts1 descriptor field in three different
places. With two different behaviours when given an invalid packet to
be checksummed — none of them correct. Sort that out.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sending a TSO frame in multiple buffers, we were neglecting to set
the first descriptor up in TSO mode.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After a certain amount of staring at the debug output of this driver, I
realised it was lying to me.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an RX interrupt was already received but NAPI has not yet run when
the RX timeout happens, we end up in cp_tx_timeout() with RX interrupts
already disabled. Blindly re-enabling them will cause an IRQ storm.
(This is made particularly horrid by the fact that cp_interrupt() always
returns that it's handled the interrupt, even when it hasn't actually
done anything. If it didn't do that, the core IRQ code would have
detected the storm and handled it, I'd have had a clear smoking gun
backtrace instead of just a spontaneously resetting router, and I'd have
at *least* two days of my life back. Changing the return value of
cp_interrupt() will be argued about under separate cover.)
Unconditionally leave RX interrupts disabled after the reset, and
schedule NAPI to check the receive ring and re-enable them.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A deadlock trace is seen in netcp driver with lockup detector enabled.
The trace log is provided below for reference. This patch fixes the
bug by removing the usage of netcp_modules_lock within ndo_ops functions.
ndo_{open/close/ioctl)() is already called with rtnl_lock held. So there
is no need to hold another mutex for serialization across processes on
multiple cores. So remove use of netcp_modules_lock mutex from these
ndo ops functions.
ndo_set_rx_mode() shouldn't be using a mutex as it is called from atomic
context. In the case of ndo_set_rx_mode(), there can be call to this API
without rtnl_lock held from an atomic context. As the underlying modules
are expected to add address to a hardware table, it is to be protected
across concurrent updates and hence a spin lock is used to synchronize
the access. Same with ndo_vlan_rx_add_vid() & ndo_vlan_rx_kill_vid().
Probably the netcp_modules_lock is used to protect the module not being
removed as part of rmmod. Currently this is not fully implemented and
assumes the interface is brought down before doing rmmod of modules.
The support for rmmmod while interface is up is expected in a future
patch set when additional modules such as pa, qos are added. For now
all of the tests such as if up/down, reboot, iperf works fine with this
patch applied.
Deadlock trace seen with lockup detector enabled is shown below for
reference.
[ 16.863014] ======================================================
[ 16.869183] [ INFO: possible circular locking dependency detected ]
[ 16.875441] 4.1.6-01265-gfb1e101 #1 Tainted: G W
[ 16.881176] -------------------------------------------------------
[ 16.887432] ifconfig/1662 is trying to acquire lock:
[ 16.892386] (netcp_modules_lock){+.+.+.}, at: [<c03e8110>]
netcp_ndo_open+0x168/0x518
[ 16.900321]
[ 16.900321] but task is already holding lock:
[ 16.906144] (rtnl_mutex){+.+.+.}, at: [<c053a418>] devinet_ioctl+0xf8/0x7e4
[ 16.913206]
[ 16.913206] which lock already depends on the new lock.
[ 16.913206]
[ 16.921372]
[ 16.921372] the existing dependency chain (in reverse order) is:
[ 16.928844]
-> #1 (rtnl_mutex){+.+.+.}:
[ 16.932865] [<c06023f0>] mutex_lock_nested+0x68/0x4a8
[ 16.938521] [<c04c5758>] register_netdev+0xc/0x24
[ 16.943831] [<c03e65c0>] netcp_module_probe+0x214/0x2ec
[ 16.949660] [<c03e8a54>] netcp_register_module+0xd4/0x140
[ 16.955663] [<c089654c>] keystone_gbe_init+0x10/0x28
[ 16.961233] [<c000977c>] do_one_initcall+0xb8/0x1f8
[ 16.966714] [<c0867e04>] kernel_init_freeable+0x148/0x1e8
[ 16.972720] [<c05f9994>] kernel_init+0xc/0xe8
[ 16.977682] [<c0010038>] ret_from_fork+0x14/0x3c
[ 16.982905]
-> #0 (netcp_modules_lock){+.+.+.}:
[ 16.987619] [<c006eab0>] lock_acquire+0x118/0x320
[ 16.992928] [<c06023f0>] mutex_lock_nested+0x68/0x4a8
[ 16.998582] [<c03e8110>] netcp_ndo_open+0x168/0x518
[ 17.004064] [<c04c48f0>] __dev_open+0xa8/0x10c
[ 17.009112] [<c04c4b74>] __dev_change_flags+0x94/0x144
[ 17.014853] [<c04c4c3c>] dev_change_flags+0x18/0x48
[ 17.020334] [<c053a9fc>] devinet_ioctl+0x6dc/0x7e4
[ 17.025729] [<c04a59ec>] sock_ioctl+0x1d0/0x2a8
[ 17.030865] [<c0142844>] do_vfs_ioctl+0x41c/0x688
[ 17.036173] [<c0142ae4>] SyS_ioctl+0x34/0x5c
[ 17.041046] [<c000ff60>] ret_fast_syscall+0x0/0x54
[ 17.046441]
[ 17.046441] other info that might help us debug this:
[ 17.046441]
[ 17.054434] Possible unsafe locking scenario:
[ 17.054434]
[ 17.060343] CPU0 CPU1
[ 17.064862] ---- ----
[ 17.069381] lock(rtnl_mutex);
[ 17.072522] lock(netcp_modules_lock);
[ 17.078875] lock(rtnl_mutex);
[ 17.084532] lock(netcp_modules_lock);
[ 17.088366]
[ 17.088366] *** DEADLOCK ***
[ 17.088366]
[ 17.094279] 1 lock held by ifconfig/1662:
[ 17.098278] #0: (rtnl_mutex){+.+.+.}, at: [<c053a418>]
devinet_ioctl+0xf8/0x7e4
[ 17.105774]
[ 17.105774] stack backtrace:
[ 17.110124] CPU: 1 PID: 1662 Comm: ifconfig Tainted: G W
4.1.6-01265-gfb1e101 #1
[ 17.118637] Hardware name: Keystone
[ 17.122123] [<c00178e4>] (unwind_backtrace) from [<c0013cbc>]
(show_stack+0x10/0x14)
[ 17.129862] [<c0013cbc>] (show_stack) from [<c05ff450>]
(dump_stack+0x84/0xc4)
[ 17.137079] [<c05ff450>] (dump_stack) from [<c0068e34>]
(print_circular_bug+0x210/0x330)
[ 17.145161] [<c0068e34>] (print_circular_bug) from [<c006ab7c>]
(validate_chain.isra.35+0xf98/0x13ac)
[ 17.154372] [<c006ab7c>] (validate_chain.isra.35) from [<c006da60>]
(__lock_acquire+0x52c/0xcc0)
[ 17.163149] [<c006da60>] (__lock_acquire) from [<c006eab0>]
(lock_acquire+0x118/0x320)
[ 17.171058] [<c006eab0>] (lock_acquire) from [<c06023f0>]
(mutex_lock_nested+0x68/0x4a8)
[ 17.179140] [<c06023f0>] (mutex_lock_nested) from [<c03e8110>]
(netcp_ndo_open+0x168/0x518)
[ 17.187484] [<c03e8110>] (netcp_ndo_open) from [<c04c48f0>]
(__dev_open+0xa8/0x10c)
[ 17.195133] [<c04c48f0>] (__dev_open) from [<c04c4b74>]
(__dev_change_flags+0x94/0x144)
[ 17.203129] [<c04c4b74>] (__dev_change_flags) from [<c04c4c3c>]
(dev_change_flags+0x18/0x48)
[ 17.211560] [<c04c4c3c>] (dev_change_flags) from [<c053a9fc>]
(devinet_ioctl+0x6dc/0x7e4)
[ 17.219729] [<c053a9fc>] (devinet_ioctl) from [<c04a59ec>]
(sock_ioctl+0x1d0/0x2a8)
[ 17.227378] [<c04a59ec>] (sock_ioctl) from [<c0142844>]
(do_vfs_ioctl+0x41c/0x688)
[ 17.234939] [<c0142844>] (do_vfs_ioctl) from [<c0142ae4>]
(SyS_ioctl+0x34/0x5c)
[ 17.242242] [<c0142ae4>] (SyS_ioctl) from [<c000ff60>]
(ret_fast_syscall+0x0/0x54)
[ 17.258855] netcp-1.0 2620110.netcp eth0: Link is Up - 1Gbps/Full - flow
control off
[ 17.271282] BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:616
[ 17.279712] in_atomic(): 1, irqs_disabled(): 0, pid: 1662, name: ifconfig
[ 17.286500] INFO: lockdep is turned off.
[ 17.290413] Preemption disabled at:[< (null)>] (null)
[ 17.295728]
[ 17.297214] CPU: 1 PID: 1662 Comm: ifconfig Tainted: G W
4.1.6-01265-gfb1e101 #1
[ 17.305735] Hardware name: Keystone
[ 17.309223] [<c00178e4>] (unwind_backtrace) from [<c0013cbc>]
(show_stack+0x10/0x14)
[ 17.316970] [<c0013cbc>] (show_stack) from [<c05ff450>]
(dump_stack+0x84/0xc4)
[ 17.324194] [<c05ff450>] (dump_stack) from [<c06023b0>]
(mutex_lock_nested+0x28/0x4a8)
[ 17.332112] [<c06023b0>] (mutex_lock_nested) from [<c03e9840>]
(netcp_set_rx_mode+0x160/0x210)
[ 17.340724] [<c03e9840>] (netcp_set_rx_mode) from [<c04c483c>]
(dev_set_rx_mode+0x1c/0x28)
[ 17.348982] [<c04c483c>] (dev_set_rx_mode) from [<c04c490c>]
(__dev_open+0xc4/0x10c)
[ 17.356724] [<c04c490c>] (__dev_open) from [<c04c4b74>]
(__dev_change_flags+0x94/0x144)
[ 17.364729] [<c04c4b74>] (__dev_change_flags) from [<c04c4c3c>]
(dev_change_flags+0x18/0x48)
[ 17.373166] [<c04c4c3c>] (dev_change_flags) from [<c053a9fc>]
(devinet_ioctl+0x6dc/0x7e4)
[ 17.381344] [<c053a9fc>] (devinet_ioctl) from [<c04a59ec>]
(sock_ioctl+0x1d0/0x2a8)
[ 17.388994] [<c04a59ec>] (sock_ioctl) from [<c0142844>]
(do_vfs_ioctl+0x41c/0x688)
[ 17.396563] [<c0142844>] (do_vfs_ioctl) from [<c0142ae4>]
(SyS_ioctl+0x34/0x5c)
[ 17.403873] [<c0142ae4>] (SyS_ioctl) from [<c000ff60>]
(ret_fast_syscall+0x0/0x54)
[ 17.413772] IPv6: ADDRCONF(NETDEV_UP): eth0: link is not ready
udhcpc (v1.20.2) started
Sending discover...
[ 18.690666] netcp-1.0 2620110.netcp eth0: Link is Up - 1Gbps/Full - flow
control off
Sending discover...
[ 22.250972] netcp-1.0 2620110.netcp eth0: Link is Up - 1Gbps/Full - flow
control off
[ 22.258721] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
[ 22.265458] BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:616
[ 22.273896] in_atomic(): 1, irqs_disabled(): 0, pid: 342, name: kworker/1:1
[ 22.280854] INFO: lockdep is turned off.
[ 22.284767] Preemption disabled at:[< (null)>] (null)
[ 22.290074]
[ 22.291568] CPU: 1 PID: 342 Comm: kworker/1:1 Tainted: G W
4.1.6-01265-gfb1e101 #1
[ 22.300255] Hardware name: Keystone
[ 22.303750] Workqueue: ipv6_addrconf addrconf_dad_work
[ 22.308895] [<c00178e4>] (unwind_backtrace) from [<c0013cbc>]
(show_stack+0x10/0x14)
[ 22.316643] [<c0013cbc>] (show_stack) from [<c05ff450>]
(dump_stack+0x84/0xc4)
[ 22.323867] [<c05ff450>] (dump_stack) from [<c06023b0>]
(mutex_lock_nested+0x28/0x4a8)
[ 22.331786] [<c06023b0>] (mutex_lock_nested) from [<c03e9840>]
(netcp_set_rx_mode+0x160/0x210)
[ 22.340394] [<c03e9840>] (netcp_set_rx_mode) from [<c04c9d18>]
(__dev_mc_add+0x54/0x68)
[ 22.348401] [<c04c9d18>] (__dev_mc_add) from [<c05ab358>]
(igmp6_group_added+0x168/0x1b4)
[ 22.356580] [<c05ab358>] (igmp6_group_added) from [<c05ad2cc>]
(ipv6_dev_mc_inc+0x4f0/0x5a8)
[ 22.365019] [<c05ad2cc>] (ipv6_dev_mc_inc) from [<c058f0d0>]
(addrconf_dad_work+0x21c/0x33c)
[ 22.373460] [<c058f0d0>] (addrconf_dad_work) from [<c0042850>]
(process_one_work+0x214/0x8d0)
[ 22.381986] [<c0042850>] (process_one_work) from [<c0042f54>]
(worker_thread+0x48/0x4bc)
[ 22.390071] [<c0042f54>] (worker_thread) from [<c004868c>]
(kthread+0xf0/0x108)
[ 22.397381] [<c004868c>] (kthread) from [<c0010038>]
Trace related to incorrect usage of mutex inside ndo_set_rx_mode
[ 24.086066] BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:616
[ 24.094506] in_atomic(): 1, irqs_disabled(): 0, pid: 1682, name: ifconfig
[ 24.101291] INFO: lockdep is turned off.
[ 24.105203] Preemption disabled at:[< (null)>] (null)
[ 24.110511]
[ 24.112005] CPU: 2 PID: 1682 Comm: ifconfig Tainted: G W
4.1.6-01265-gfb1e101 #1
[ 24.120518] Hardware name: Keystone
[ 24.124018] [<c00178e4>] (unwind_backtrace) from [<c0013cbc>]
(show_stack+0x10/0x14)
[ 24.131772] [<c0013cbc>] (show_stack) from [<c05ff450>]
(dump_stack+0x84/0xc4)
[ 24.138989] [<c05ff450>] (dump_stack) from [<c06023b0>]
(mutex_lock_nested+0x28/0x4a8)
[ 24.146908] [<c06023b0>] (mutex_lock_nested) from [<c03e9840>]
(netcp_set_rx_mode+0x160/0x210)
[ 24.155523] [<c03e9840>] (netcp_set_rx_mode) from [<c04c483c>]
(dev_set_rx_mode+0x1c/0x28)
[ 24.163787] [<c04c483c>] (dev_set_rx_mode) from [<c04c490c>]
(__dev_open+0xc4/0x10c)
[ 24.171531] [<c04c490c>] (__dev_open) from [<c04c4b74>]
(__dev_change_flags+0x94/0x144)
[ 24.179528] [<c04c4b74>] (__dev_change_flags) from [<c04c4c3c>]
(dev_change_flags+0x18/0x48)
[ 24.187966] [<c04c4c3c>] (dev_change_flags) from [<c053a9fc>]
(devinet_ioctl+0x6dc/0x7e4)
[ 24.196145] [<c053a9fc>] (devinet_ioctl) from [<c04a59ec>]
(sock_ioctl+0x1d0/0x2a8)
[ 24.203803] [<c04a59ec>] (sock_ioctl) from [<c0142844>]
(do_vfs_ioctl+0x41c/0x688)
[ 24.211373] [<c0142844>] (do_vfs_ioctl) from [<c0142ae4>]
(SyS_ioctl+0x34/0x5c)
[ 24.218676] [<c0142ae4>] (SyS_ioctl) from [<c000ff60>]
(ret_fast_syscall+0x0/0x54)
[ 24.227156] IPv6: ADDRCONF(NETDEV_UP): eth1: link is not ready
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently netcp_rxpool_refill() that refill descriptors and attached
buffers to fdq while interrupt is enabled as part of NAPI poll. Doing
it while interrupt is disabled could be beneficial as hardware will
not be starved when CPU is busy with processing interrupt.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
