From: Dimitri Sivanich <sivanich@sgi.com>
To: linux-ia64@vger.kernel.org
Subject: [PATCH] IA64: eliminate race condition in smp_flush_tlb_mm
Date: Tue, 28 Dec 2010 19:34:42 +0000 [thread overview]
Message-ID: <20101228193442.GA28269@sgi.com> (raw)
A race condition exists within smp_call_function_many() when called from
smp_flush_tlb_mm(). On rare occasions the cpu_vm_mask can be cleared
while smp_call_function_many is executing, occasionally resulting in a
hung process.
Make a copy of the mask prior to calling smp_call_function_many().
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
---
arch/ia64/kernel/smp.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
Index: linux-2.6.36.2/arch/ia64/kernel/smp.c
=================================--- linux-2.6.36.2.orig/arch/ia64/kernel/smp.c 2010-12-28 13:13:16.261122111 -0600
+++ linux-2.6.36.2/arch/ia64/kernel/smp.c 2010-12-28 13:30:17.504590090 -0600
@@ -293,6 +293,7 @@ smp_flush_tlb_all (void)
void
smp_flush_tlb_mm (struct mm_struct *mm)
{
+ cpumask_var_t cpus;
preempt_disable();
/* this happens for the common case of a single-threaded fork(): */
if (likely(mm = current->active_mm && atomic_read(&mm->mm_users) = 1))
@@ -301,9 +302,15 @@ smp_flush_tlb_mm (struct mm_struct *mm)
preempt_enable();
return;
}
-
- smp_call_function_many(mm_cpumask(mm),
- (void (*)(void *))local_finish_flush_tlb_mm, mm, 1);
+ if (!alloc_cpumask_var(&cpus, GFP_ATOMIC)) {
+ smp_call_function((void (*)(void *))local_finish_flush_tlb_mm,
+ mm, 1);
+ } else {
+ cpumask_copy(cpus, mm_cpumask(mm));
+ smp_call_function_many(cpus,
+ (void (*)(void *))local_finish_flush_tlb_mm, mm, 1);
+ free_cpumask_var(cpus);
+ }
local_irq_disable();
local_finish_flush_tlb_mm(mm);
local_irq_enable();
reply other threads:[~2010-12-28 19:34 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20101228193442.GA28269@sgi.com \
--to=sivanich@sgi.com \
--cc=linux-ia64@vger.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox