From: Peter Zijlstra <peterz@infradead.org>
To: Oleg Nesterov <oleg@redhat.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Ingo Molnar <mingo@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [x86] BUG: unable to handle kernel paging request at 00740060
Date: Wed, 9 Oct 2013 16:33:59 +0200 [thread overview]
Message-ID: <20131009143359.GU26785@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20131009140734.GH3081@twins.programming.kicks-ass.net>
On Wed, Oct 09, 2013 at 04:07:34PM +0200, Peter Zijlstra wrote:
> Once I force a x86_64 build using the 'same' config it goes away and
> generates 'sensible' code again (although I don't see why L9 isn't
> merged with L2):
i386-SMP also generates correct code afaict; a tad stupid but not wrong.
If I remove ftrace from the .config its still broken..
If I also remove the likely/unlikely tracer its still broken and lots
smaller:
.p2align 4,,15
.globl task_work_add
.type task_work_add, @function
task_work_add:
pushl %ebp #
movl %esp, %ebp #,
pushl %edi #
pushl %esi #
pushl %ebx #
movl %eax, %esi # task, task
.p2align 4,,15
.L4:
movl 904(%esi), %ebx # task_5(D)->task_works, __old
cmpl $work_exited, %ebx #, __old
je .L5 #,
movl %ebx, (%edx) # __old, work_10(D)->next
movl %ebx, %eax # __old, __ret
#APP
# 34 "/usr/src/linux-2.6/kernel/task_work.c" 1
cmpxchgl %edx,904(%esi) # work, *__ptr_12
# 0 "" 2
#NO_APP
cmpl %eax, %ebx # __ret, __old
jne .L4 #,
testb %cl, %cl # notify
je .L6 #,
movl 4(%esi), %eax # task_5(D)->stack, task_5(D)->stack
#APP
# 208 "/usr/src/linux-2.6/arch/x86/include/asm/bitops.h" 1
bts $1, 8(%eax); jc .L2 #, MEM[(volatile long unsigned int *)_18],
# 0 "" 2
#NO_APP
.L6:
xorl %edi, %edi # D.14172
.L2:
movl %edi, %eax # D.14172,
popl %ebx #
popl %esi #
popl %edi #
popl %ebp #
ret
.L5:
movl $-3, %edi #, D.14172
jmp .L2 #
.size task_work_add, .-task_work_add
That "jc .L2" needs to be .L6 ! It looks like it fails to deal with the
empty branch.
Why this thing needs to use EDI is anybodies guess I suppose. Would've
made much more sense to have:
.L6:
xorl %eax, %eax
.L2:
popl %ebx
popl %esi
popl %ebp
ret
.L5:
movl, $-3, %eax
jmp .L2
At least its not duplicating the popl+ret bits 3 times anymore.
next prev parent reply other threads:[~2013-10-09 14:34 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-10-05 23:44 [x86] BUG: unable to handle kernel paging request at 00740060 Fengguang Wu
2013-10-05 23:47 ` [x86] BUG: unable to handle kernel paging request at 08000060 Fengguang Wu
2013-10-06 7:27 ` Mike Galbraith
2013-10-06 7:36 ` Fengguang Wu
2013-10-07 8:49 ` Peter Zijlstra
2013-10-07 9:17 ` Fengguang Wu
2013-10-07 9:36 ` Peter Zijlstra
2013-10-07 9:46 ` Fengguang Wu
2013-10-07 8:55 ` [x86] BUG: unable to handle kernel paging request at 00740060 Peter Zijlstra
2013-10-07 9:08 ` Peter Zijlstra
2013-10-07 11:32 ` Fengguang Wu
2013-10-07 9:27 ` Fengguang Wu
2013-10-07 18:47 ` Linus Torvalds
2013-10-08 7:51 ` Fengguang Wu
2013-10-08 16:21 ` Linus Torvalds
2013-10-08 17:15 ` [x86] BUG: unable to handle kernel NULL pointer dereference at (null) Fengguang Wu
2013-10-08 17:31 ` Linus Torvalds
2013-10-09 1:09 ` Fengguang Wu
2013-10-09 1:33 ` Linus Torvalds
2013-10-08 18:51 ` [x86] BUG: unable to handle kernel paging request at 00740060 Oleg Nesterov
2013-10-08 19:05 ` Jakub Jelinek
2013-10-08 19:20 ` Linus Torvalds
2013-10-08 19:34 ` Linus Torvalds
2013-10-08 19:35 ` Oleg Nesterov
2013-10-08 19:49 ` Linus Torvalds
2013-10-09 1:43 ` Mike Galbraith
2013-10-08 19:05 ` Linus Torvalds
2013-10-08 16:46 ` Oleg Nesterov
2013-10-08 14:34 ` Oleg Nesterov
2013-10-09 8:04 ` Fengguang Wu
2013-10-09 12:19 ` Fengguang Wu
2013-10-09 12:21 ` Fengguang Wu
2013-10-09 12:27 ` Peter Zijlstra
2013-10-09 12:52 ` Ingo Molnar
2013-10-09 17:18 ` Ingo Molnar
2013-10-10 2:15 ` Mike Galbraith
2013-10-09 12:56 ` Fengguang Wu
2013-10-09 12:43 ` Oleg Nesterov
2013-10-09 14:07 ` Peter Zijlstra
2013-10-09 14:17 ` Oleg Nesterov
2013-10-09 14:32 ` Ingo Molnar
2013-10-09 14:33 ` Peter Zijlstra [this message]
2013-10-09 14:46 ` Peter Zijlstra
2013-10-09 18:16 ` Jakub Jelinek
2013-10-09 18:54 ` Linus Torvalds
2013-10-09 19:02 ` Peter Zijlstra
2013-10-09 19:08 ` Jakub Jelinek
2013-10-10 6:22 ` Ingo Molnar
2013-10-10 6:51 ` Jakub Jelinek
2013-10-10 8:04 ` Jakub Jelinek
2013-10-10 8:24 ` [PATCH] gcc4: Add 'asm goto' miscompilation quirk Ingo Molnar
2013-10-10 8:31 ` Jakub Jelinek
2013-10-10 8:45 ` Ingo Molnar
2013-10-10 8:55 ` [PATCH, -v2] compiler/gcc4: Add quirk for 'asm goto' miscompilation bug Ingo Molnar
2013-10-10 11:56 ` Peter Zijlstra
2013-10-10 12:32 ` Jakub Jelinek
2013-10-10 13:10 ` Peter Zijlstra
2013-10-10 15:04 ` Ingo Molnar
2013-10-10 14:04 ` [PATCH] gcc4: Add 'asm goto' miscompilation quirk Richard Henderson
2013-10-10 14:27 ` Jakub Jelinek
2013-10-10 15:12 ` [PATCH, -v3] compiler/gcc4: Add quirk for 'asm goto' miscompilation bug Ingo Molnar
2013-10-10 16:15 ` Richard Henderson
2013-10-10 16:49 ` Ingo Molnar
2013-10-11 4:35 ` Fengguang Wu
2013-10-11 5:46 ` Ingo Molnar
2013-10-11 6:51 ` Fengguang Wu
2013-10-11 9:30 ` Fengguang Wu
2013-10-12 17:03 ` Ingo Molnar
2013-10-10 8:34 ` [PATCH] gcc4: Add 'asm goto' miscompilation quirk Ingo Molnar
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=20131009143359.GU26785@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=fengguang.wu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=torvalds@linux-foundation.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.