public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Luis Henriques <luis.henriques@canonical•com>
To: Ben Hutchings <bhutchings@solarflare•com>
Cc: Neil Horman <nhorman@tuxdriver•com>, <netdev@vger•kernel.org>,
	Jay Cliburn <jcliburn@gmail•com>,
	"David S. Miller" <davem@davemloft•net>, <stable@vger•kernel.org>
Subject: Re: [net PATCH] atl1c: Fix misuse of netdev_alloc_skb in refilling rx ring
Date: Sat, 27 Jul 2013 20:30:13 +0100	[thread overview]
Message-ID: <87k3kbdcmy.fsf@canonical.com> (raw)
In-Reply-To: <1374884670.1666.72.camel@bwh-desktop.uk.level5networks.com> (Ben Hutchings's message of "Sat, 27 Jul 2013 01:24:30 +0100")

Ben Hutchings <bhutchings@solarflare•com> writes:

> On Sat, 2013-07-27 at 01:02 +0100, Ben Hutchings wrote:
>> On Fri, 2013-07-26 at 12:47 -0400, Neil Horman wrote:
>> > atl1c uses netdev_alloc_skb to refill its rx dma ring, but that call makes no
>> > guarantees about the suitability of the memory for use in DMA.  As a result
>> > we've gotten reports of atl1c drivers occasionally hanging and needing to be
>> > reset:
>> > https://bugzilla.kernel.org/show_bug.cgi?id=54021
>> > 
>> > Fix this by modifying the call to use the internal version __netdev_alloc_skb,
>> > where you can set the gfp_mask explicitly to include GFP_DMA.
>> 
>> This is a really bad idea.  GFP_DMA means allocation from the ISA DMA
>> region (< 16 MB).  pci_map_single() takes care of allocating a bounce
>> buffer if necessary.
>> 
>> Ben.
>> 
>> > Tested by two reporters in the above bug, who have the hardware to validate it.
>> > Both report immediate cessation of the problem with this patch
> [...]
>
> So perhaps the chip somehow fails to support a full 32-bit address
> (which is the current DMA mask), though given that there are 64 address
> bits in RX descriptors this seems unlikely.  And the most likely result
> of that would be memory corruption, not a stall.
>
> Alternately, perhaps more likely, there's something wrong with the
> driver's error handling.  If atl1_alloc_rx_buffer() fails then the RX
> queue could run dry.  Depending on how the hardware is designed, that
> could result in a complete RX stall (no RX buffers available => no RX
> completions => no attempt to allocate more RX buffers).
>
> Maybe your change makes it less likely for atl1_alloc_rx_buffer() to
> fail.  On a modern PC the (ISA) DMA zone is basically unused whereas
> bounce buffers might be more contended.  Did you try adding some logging
> for failure of pci_map_single()?
>
> Ben.

Just to add a little bit more context (and hopefully not noise), I
started seeing this issue on 3.7.  Bisection resulted on the following
first bad commit:

69b08f6 net: use bigger pages in __netdev_alloc_frag

Reverting this commit (and e5e6730 "skbuff: Move definition of
NETDEV_FRAG_PAGE_MAX_SIZE") solved the problem.

Note also that I'm seeing this issue on a 32 bits system (64 bits
isn't supported).  This initially made me think the problem could be
related with this as 69b08f6 log explicitly refers to 32/64 bit
archs.  But I failed to find any obvious issue with the patch.

Cheers,
-- 
Luis

  reply	other threads:[~2013-07-27 19:30 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-26 16:47 [net PATCH] atl1c: Fix misuse of netdev_alloc_skb in refilling rx ring Neil Horman
2013-07-26 16:56 ` Luis Henriques
2013-07-26 17:02   ` Neil Horman
2013-07-26 22:56     ` David Miller
2013-07-27 16:25       ` Luis Henriques
2013-07-27  0:02 ` Ben Hutchings
2013-07-27  0:24   ` Ben Hutchings
2013-07-27 19:30     ` Luis Henriques [this message]
2013-07-27 19:49       ` Eric Dumazet
2013-07-27 21:30       ` Ben Hutchings
2013-07-27 23:59         ` Eric Dumazet
2013-07-28  3:02           ` David Miller
2013-07-28 10:44             ` Neil Horman
2013-07-28 16:15               ` Eric Dumazet
2013-07-28 18:53                 ` Neil Horman
2013-07-28 19:21                   ` Eric Dumazet
2013-07-28 20:08                     ` Eric Dumazet
2013-07-28 20:22                   ` Ben Hutchings
2013-07-28 23:01                     ` Eric Dumazet
2013-07-28 23:20                       ` Eric Dumazet
2013-07-28 23:25                         ` Eric Dumazet
2013-07-28 23:38                         ` Neil Horman
2013-07-29  0:07                         ` Ben Hutchings
2013-07-29  0:21                           ` David Miller
2013-07-29  0:26                           ` Eric Dumazet
2013-07-29  9:55                         ` Luis Henriques
2013-07-29 10:57                           ` Eric Dumazet
2013-07-29 12:09                             ` Luis Henriques
2013-07-29 15:30                               ` Eric Dumazet
2013-07-29 17:24                                 ` Eric Dumazet
2013-07-30  8:53                                   ` Luis Henriques
2013-07-31  2:11                                   ` David Miller
2013-07-31 17:48                                     ` Benjamin Poirier
2013-07-31 17:56                                       ` Eric Dumazet
2013-07-31 19:01                                       ` David Miller
2013-08-01  1:57                                         ` Eric Dumazet

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87k3kbdcmy.fsf@canonical.com \
    --to=luis.henriques@canonical$(echo .)com \
    --cc=bhutchings@solarflare$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=jcliburn@gmail$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=nhorman@tuxdriver$(echo .)com \
    --cc=stable@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox