All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: fweisbec@gmail.com
Cc: sparclinux@vger.kernel.org, tj@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [BUG] percpu misaligned allocation
Date: Thu, 18 Mar 2010 06:26:48 +0000	[thread overview]
Message-ID: <20100317.232648.59697287.davem@davemloft.net> (raw)
In-Reply-To: <20100318044930.GC5045@nowhere>

From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 18 Mar 2010 05:49:33 +0100

> While using the lock events through perf in a sparc box, I can see
> the following message repeated many times:
> 
> 	Kernel unaligned access at TPC[49357c] perf_trace_lock_acquire+0xb4/0x180
> 
> It actually hangs the box as the messages are sent to a serial console.
> 
> When used with perf, the trace events use a per cpu buffer allocated
> in kernel/trace/trace_event_perf.c, and the allocation appears to return
> a misaligned percpu pointer. It is aligned to 4 while it seems it
> requires to be aligned to 8.

Thanks I'll take a look at this.

RAW locks (both rwlocks and spinlocks) on sparc64 are 4-bytes
in size, maybe some piece of code is assuming that locks
are cpu word sized.

Where is perf_trace_lock_acquire() I can't find it in Linus's
tree?  Does it get created by some crazy macro expansion?


WARNING: multiple messages have this Message-ID (diff)
From: David Miller <davem@davemloft.net>
To: fweisbec@gmail.com
Cc: sparclinux@vger.kernel.org, tj@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [BUG] percpu misaligned allocation
Date: Wed, 17 Mar 2010 23:26:48 -0700 (PDT)	[thread overview]
Message-ID: <20100317.232648.59697287.davem@davemloft.net> (raw)
In-Reply-To: <20100318044930.GC5045@nowhere>

From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 18 Mar 2010 05:49:33 +0100

> While using the lock events through perf in a sparc box, I can see
> the following message repeated many times:
> 
> 	Kernel unaligned access at TPC[49357c] perf_trace_lock_acquire+0xb4/0x180
> 
> It actually hangs the box as the messages are sent to a serial console.
> 
> When used with perf, the trace events use a per cpu buffer allocated
> in kernel/trace/trace_event_perf.c, and the allocation appears to return
> a misaligned percpu pointer. It is aligned to 4 while it seems it
> requires to be aligned to 8.

Thanks I'll take a look at this.

RAW locks (both rwlocks and spinlocks) on sparc64 are 4-bytes
in size, maybe some piece of code is assuming that locks
are cpu word sized.

Where is perf_trace_lock_acquire() I can't find it in Linus's
tree?  Does it get created by some crazy macro expansion?


  reply	other threads:[~2010-03-18  6:26 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-18  4:49 [BUG] percpu misaligned allocation Frederic Weisbecker
2010-03-18  4:49 ` Frederic Weisbecker
2010-03-18  6:26 ` David Miller [this message]
2010-03-18  6:26   ` David Miller
2010-03-18  6:28   ` David Miller
2010-03-18  6:28     ` David Miller
2010-03-18  6:36     ` Li Zefan
2010-03-18  6:36       ` Li Zefan
2010-03-18  6:39   ` Li Zefan
2010-03-18  6:39     ` Li Zefan
2010-03-18 16:56     ` Frederic Weisbecker
2010-03-18 16:56       ` Frederic Weisbecker
2010-03-18  9:30 ` Tejun Heo
2010-03-18  9:30   ` Tejun Heo
2010-03-18 19:50   ` Frederic Weisbecker
2010-03-18 19:50     ` Frederic Weisbecker
2010-03-19  0:54   ` David Miller
2010-03-19  0:54     ` David Miller
2010-03-19  1:31     ` Frederic Weisbecker
2010-03-19  1:31       ` Frederic Weisbecker
2010-03-19  1:51       ` Tejun Heo
2010-03-19  1:51         ` Tejun Heo
2010-03-19  1:57       ` David Miller
2010-03-19  1:57         ` David Miller
2010-03-19  2:18         ` Tejun Heo
2010-03-19  2:18           ` Tejun Heo
2010-03-19  2:30           ` Frederic Weisbecker
2010-03-19  2:30             ` Frederic Weisbecker
2010-03-19  3:02           ` David Miller
2010-03-19  3:02             ` David Miller
2010-03-19 15:48             ` Richard Kennedy
2010-03-24 20:54 ` Maciej Rutecki

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=20100317.232648.59697287.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sparclinux@vger.kernel.org \
    --cc=tj@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.