linux-toradex.git/drivers/net/forcedeth.c, branch v2.6.31.3 Linux kernel for Apalis and Colibri modules forcedeth: Fix NAPI race. 2009-07-06T01:03:33+00:00 Eric Dumazet eric.dumazet@gmail.com 2009-07-02T04:04:45+00:00 78c29bd95bd8d2c3bcf7932cb3ab8ae01cd8f58f Eric Dumazet a écrit : > Ingo Molnar a écrit : >>> The following changes since commit 52989765629e7d182b4f146050ebba0abf2cb0b7: >>> Linus Torvalds (1): >>> Merge git://git.kernel.org/.../davem/net-2.6 >>> >>> are available in the git repository at: >>> >>> master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6.git master >> Hm, something in this lot quickly wrecked networking here - see the >> tx timeout dump below. It starts with: >> >> [ 351.004596] WARNING: at net/sched/sch_generic.c:246 dev_watchdog+0x10b/0x19c() >> [ 351.011815] Hardware name: System Product Name >> [ 351.016220] NETDEV WATCHDOG: eth0 (forcedeth): transmit queue 0 timed out >> >> Config attached. Unfortunately i've got no time to do bisection >> today. > > > > forcedeth might have a problem, in its netif_wake_queue() logic, but > I could not see why a recent patch could make this problem visible now. > > CPU0/1: AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ stepping 02 > is not a new cpu either :) > > forcedeth uses an internal tx_stop without appropriate barrier. > > Could you try following patch ? > > (random guess as I dont have much time right now) We might have a race in napi_schedule(), leaving interrupts disabled forever. I cannot test this patch, I dont have the hardware... Tested-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net> 
Eric Dumazet a écrit :
> Ingo Molnar a écrit :
>>> The following changes since commit 52989765629e7d182b4f146050ebba0abf2cb0b7:
>>>   Linus Torvalds (1):
>>>         Merge git://git.kernel.org/.../davem/net-2.6
>>>
>>> are available in the git repository at:
>>>
>>>   master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6.git master
>> Hm, something in this lot quickly wrecked networking here - see the
>> tx timeout dump below. It starts with:
>>
>> [  351.004596] WARNING: at net/sched/sch_generic.c:246 dev_watchdog+0x10b/0x19c()
>> [  351.011815] Hardware name: System Product Name
>> [  351.016220] NETDEV WATCHDOG: eth0 (forcedeth): transmit queue 0 timed out
>>
>> Config attached. Unfortunately i've got no time to do bisection
>> today.
>
>
>
> forcedeth might have a problem, in its netif_wake_queue() logic, but
> I could not see why a recent patch could make this problem visible now.
>
> CPU0/1: AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ stepping 02
> is not a new cpu either :)
>
> forcedeth uses an internal tx_stop without appropriate barrier.
>
> Could you try following patch ?
>
> (random guess as I dont have much time right now)

We might have a race in napi_schedule(), leaving interrupts disabled forever.
I cannot test this patch, I dont have the hardware...

Tested-by: Ingo Molnar <mingo@elte.hu>

Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: fix dma api mismatches 2009-06-18T07:46:13+00:00 Eric Dumazet eric.dumazet@gmail.com 2009-06-17T21:17:59+00:00 73a370795371e41f72aeca61656d47adeadf28e5 forcedeth doesnt use properly dma api in its tx completion path and in nv_loopback_test() pci_map_single() should be paired with pci_unmap_single() pci_map_page() should be paired with pci_unmap_page() forcedeth xmit path uses pci_map_single() & pci_map_page(), but tx completion path only uses pci_unmap_single() nv_loopback_test() uses pci_map_single() & pci_unmap_page() Add a dma_single field in struct nv_skb_map, and define a helper function nv_unmap_txskb Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Ayaz Abdulla <aabdulla@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
forcedeth doesnt use properly dma api in its tx completion path
and in nv_loopback_test()

pci_map_single() should be paired with pci_unmap_single()
pci_map_page() should be paired with pci_unmap_page()

forcedeth xmit path uses pci_map_single() & pci_map_page(),
but tx completion path only uses pci_unmap_single()

nv_loopback_test() uses pci_map_single() & pci_unmap_page()

Add a dma_single field in struct nv_skb_map, and
define a helper function nv_unmap_txskb

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: addition of new mcp89 device id 2009-06-07T10:52:37+00:00 Ayaz Abdulla aabdulla@nvidia.com 2009-06-03T15:05:35+00:00 3df81c4e950a7e38a8ef98f818abc3eed76b3fb2 This patch adds a new device id for mcp89 chipset. Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This patch adds a new device id for mcp89 chipset.

Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: remove device id macros 2009-06-07T10:52:37+00:00 Ayaz Abdulla aabdulla@nvidia.com 2009-06-03T15:05:17+00:00 3c2e1c11d9126d765ab40207150cb6f9869637f1 This patch removes the device id macros and instead uses the constants directly. The areas in which logic expressions where using the macros now instead use feature/workaround flags. No new functionality has been introduced in this patch, only clean up of flags and macros. Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This patch removes the device id macros and instead uses the constants
directly.

The areas in which logic expressions where using the macros now instead
use feature/workaround flags.

No new functionality has been introduced in this patch, only clean up of
flags and macros.

Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2009-06-03T09:43:41+00:00 David S. Miller davem@davemloft.net 2009-06-03T09:43:41+00:00 b2f8f7525c8aa1fdd8ad8c72c832dfb571d5f768 Conflicts: drivers/net/forcedeth.c 
Conflicts:
	drivers/net/forcedeth.c
forcedeth: add phy_power_down parameter, leave phy powered up by default (v2) 2009-06-02T07:19:52+00:00 Ed Swierk eswierk@aristanetworks.com 2009-06-02T07:19:52+00:00 5a9a8e32ebe269c71d8d3e78f9435fe7729f38e9 Add a phy_power_down parameter to forcedeth: set to 1 to power down the phy and disable the link when an interface goes down; set to 0 to always leave the phy powered up. The phy power state persists across reboots; Windows, some BIOSes, and older versions of Linux don't bother to power up the phy again, forcing users to remove all power to get the interface working (see http://bugzilla.kernel.org/show_bug.cgi?id=13072). Leaving the phy powered on is the safest default behavior. Users accustomed to seeing the link state reflect the interface state and/or wanting to minimize power consumption can set phy_power_down=1 if compatibility with other OSes is not an issue. Signed-off-by: Ed Swierk <eswierk@aristanetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Add a phy_power_down parameter to forcedeth: set to 1 to power down the
phy and disable the link when an interface goes down; set to 0 to always
leave the phy powered up.

The phy power state persists across reboots; Windows, some BIOSes, and
older versions of Linux don't bother to power up the phy again, forcing
users to remove all power to get the interface working (see
http://bugzilla.kernel.org/show_bug.cgi?id=13072).  Leaving the phy
powered on is the safest default behavior.  Users accustomed to seeing
the link state reflect the interface state and/or wanting to minimize
power consumption can set phy_power_down=1 if compatibility with other
OSes is not an issue.

Signed-off-by: Ed Swierk <eswierk@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: add clock gating feature <resend> 2009-05-01T22:30:45+00:00 Ayaz Abdulla aabdulla@nvidia.com 2009-05-01T01:41:50+00:00 88d7d8b00cdc3117150faab4c4ace6d464b71c22 This patch adds new logic to support a clock gating feature found on the latest set of chipsets. The clock gating is performed on the tx/rx engines when the link is disconnected. Clock gating helps in reducing power consumption. * modified based on comments from netdev Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This patch adds new logic to support a clock gating feature found on the
latest set of chipsets. The clock gating is performed on the tx/rx
engines when the link is disconnected. Clock gating helps in reducing
power consumption.

* modified based on comments from netdev

Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: tx timeout fix 2009-04-27T09:40:51+00:00 Ayaz Abdulla aabdulla@nvidia.com 2009-04-25T09:17:56+00:00 8f955d7f042e4ac44891a400d5000928f8db9f58 This patch fixes the tx_timeout() to properly handle the clean up of the tx ring. It also sets the tx put pointer back to the correct position to be in sync with HW. Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This patch fixes the tx_timeout() to properly handle the clean up of the
tx ring. It also sets the tx put pointer back to the correct position to
be in sync with HW.

Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
forcedeth: Use napi_complete() not __napi_complete(). 2009-04-09T08:09:33+00:00 David S. Miller davem@davemloft.net 2009-04-09T08:09:33+00:00 6c2da9c2182fe64b1443a75efc09e493923e86b0 It's not enough that forcedeth's interrupts are disabled, local cpu interrupts have to unconditionally be off when we remove the device from the poll list. Based upon a crash report from Alexander Beregalov <a.beregalov@gmail.com>: WARNING: at lib/list_debug.c:30 __list_add+0x89/0x90() Hardware name: list_add corruption. prev->next should be next (c06ea834), but was f70244c8. (prev=c06ea834). Modules linked in: w83627hf hwmon_vid i2c_nforce2 Pid: 1436, comm: portageq Not tainted 2.6.30-rc1 #1 Call Trace: [<c0129d73>] warn_slowpath+0x73/0xd0 [<c03c6008>] ? __kfree_skb+0x38/0x90 [<c03f9b06>] ? tcp_data_snd_check+0x26/0xe0 [<c03fd67f>] ? tcp_rcv_established+0x2bf/0x5e0 [<c040557a>] ? tcp_v4_rcv+0x47a/0x610 [<c014cebd>] ? print_lock_contention_bug+0x1d/0x110 [<c044a967>] ? _spin_unlock+0x27/0x50 [<c040564b>] ? tcp_v4_rcv+0x54b/0x610 [<c02d86f9>] __list_add+0x89/0x90 [<c03ccff9>] __napi_schedule+0x29/0x60 [<c036946d>] e1000_intr+0xbd/0x1a0 [<c015c5de>] handle_IRQ_event+0x3e/0x120 [<c015e190>] handle_fasteoi_irq+0x60/0xd0 [<c0104fd4>] handle_irq+0x34/0x60 [<c015f748>] ? rcu_irq_enter+0x8/0x40 [<c0104b29>] do_IRQ+0x39/0xa0 [<c03c592c>] ? skb_release_head_state+0x2c/0x60 [<c01034ee>] common_interrupt+0x2e/0x34 [<c02d8601>] ? list_del+0x21/0x90 [<c014e54b>] ? trace_hardirqs_on+0xb/0x10 [<c03cd4da>] __napi_complete+0x1a/0x30 [<c0381971>] nv_napi_poll+0xd1/0x5c0 [<c014e54b>] ? trace_hardirqs_on+0xb/0x10 [<c03cd5f6>] net_rx_action+0x106/0x1b0 [<c012e8df>] __do_softirq+0x6f/0x100 [<c044a967>] ? _spin_unlock+0x27/0x50 [<c015e1b8>] ? handle_fasteoi_irq+0x88/0xd0 [<c012e9cd>] do_softirq+0x5d/0x70 [<c012ebad>] irq_exit+0x7d/0xa0 [<c0104b32>] do_IRQ+0x42/0xa0 [<c012e9b7>] ? do_softirq+0x47/0x70 [<c01034ee>] common_interrupt+0x2e/0x34 Signed-off-by: David S. Miller <davem@davemloft.net> 
It's not enough that forcedeth's interrupts are disabled,
local cpu interrupts have to unconditionally be off
when we remove the device from the poll list.

Based upon a crash report from
Alexander Beregalov <a.beregalov@gmail.com>:

 WARNING: at lib/list_debug.c:30 __list_add+0x89/0x90()
 Hardware name:
 list_add corruption. prev->next should be next (c06ea834), but was
f70244c8. (prev=c06ea834).
 Modules linked in: w83627hf hwmon_vid i2c_nforce2
 Pid: 1436, comm: portageq Not tainted 2.6.30-rc1 #1
 Call Trace:
  [<c0129d73>] warn_slowpath+0x73/0xd0
  [<c03c6008>] ? __kfree_skb+0x38/0x90
  [<c03f9b06>] ? tcp_data_snd_check+0x26/0xe0
  [<c03fd67f>] ? tcp_rcv_established+0x2bf/0x5e0
  [<c040557a>] ? tcp_v4_rcv+0x47a/0x610
  [<c014cebd>] ? print_lock_contention_bug+0x1d/0x110
  [<c044a967>] ? _spin_unlock+0x27/0x50
  [<c040564b>] ? tcp_v4_rcv+0x54b/0x610
  [<c02d86f9>] __list_add+0x89/0x90
  [<c03ccff9>] __napi_schedule+0x29/0x60
  [<c036946d>] e1000_intr+0xbd/0x1a0
  [<c015c5de>] handle_IRQ_event+0x3e/0x120
  [<c015e190>] handle_fasteoi_irq+0x60/0xd0
  [<c0104fd4>] handle_irq+0x34/0x60
  [<c015f748>] ? rcu_irq_enter+0x8/0x40
  [<c0104b29>] do_IRQ+0x39/0xa0
  [<c03c592c>] ? skb_release_head_state+0x2c/0x60
  [<c01034ee>] common_interrupt+0x2e/0x34
  [<c02d8601>] ? list_del+0x21/0x90
  [<c014e54b>] ? trace_hardirqs_on+0xb/0x10
  [<c03cd4da>] __napi_complete+0x1a/0x30
  [<c0381971>] nv_napi_poll+0xd1/0x5c0
  [<c014e54b>] ? trace_hardirqs_on+0xb/0x10
  [<c03cd5f6>] net_rx_action+0x106/0x1b0
  [<c012e8df>] __do_softirq+0x6f/0x100
  [<c044a967>] ? _spin_unlock+0x27/0x50
  [<c015e1b8>] ? handle_fasteoi_irq+0x88/0xd0
  [<c012e9cd>] do_softirq+0x5d/0x70
  [<c012ebad>] irq_exit+0x7d/0xa0
  [<c0104b32>] do_IRQ+0x42/0xa0
  [<c012e9b7>] ? do_softirq+0x47/0x70
  [<c01034ee>] common_interrupt+0x2e/0x34

Signed-off-by: David S. Miller <davem@davemloft.net>
dma-mapping: replace all DMA_39BIT_MASK macro with DMA_BIT_MASK(39) 2009-04-07T15:31:11+00:00 Yang Hongyang yanghy@cn.fujitsu.com 2009-04-07T02:01:15+00:00 6afd142fd0dfba497246d0fab236c20a7b4bf778 Replace all DMA_39BIT_MASK macro with DMA_BIT_MASK(39) Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
Replace all DMA_39BIT_MASK macro with DMA_BIT_MASK(39)

Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>