[tip:sched/urgent] sched/preempt: Fix preempt_count manipulations
From: tip-bot for Peter Zijlstra
Date: Tue May 17 2016 - 10:22:25 EST
Commit-ID: 2e636d5e66c35dfcbaf617aa8fa963f6847478fe
Gitweb: http://git.kernel.org/tip/2e636d5e66c35dfcbaf617aa8fa963f6847478fe
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Mon, 16 May 2016 15:01:11 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 17 May 2016 12:24:21 +0200
sched/preempt: Fix preempt_count manipulations
Vikram reported that his ARM64 compiler managed to 'optimize' away the
preempt_count manipulations in code like:
preempt_enable_no_resched();
put_user();
preempt_disable();
Irrespective of that fact that that is horrible code that should be
fixed for many reasons, it does highlight a deficiency in the generic
preempt_count manipulators. As it is never right to combine/elide
preempt_count manipulations like this.
Therefore sprinkle some volatile in the two generic accessors to
ensure the compiler is aware of the fact that the preempt_count is
observed outside of the regular program-order view and thus cannot be
optimized away like this.
x86; the only arch not using the generic code is not affected as we
do all this in asm in order to use the segment base per-cpu stuff.
Reported-by: Vikram Mulukutla <markivx@xxxxxxxxxxxxxx>
Tested-by: Vikram Mulukutla <markivx@xxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Fixes: a787870924db ("sched, arch: Create asm/preempt.h")
Link: http://lkml.kernel.org/r/20160516131751.GH3205@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
include/asm-generic/preempt.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5d8ffa3..c1cde35 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -7,10 +7,10 @@
static __always_inline int preempt_count(void)
{
- return current_thread_info()->preempt_count;
+ return READ_ONCE(current_thread_info()->preempt_count);
}
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
{
return ¤t_thread_info()->preempt_count;
}