sched: Remove PREEMPT_NEED_RESCHED from generic code

While hunting a preemption issue with Alexander, Ben noticed that the
currently generic PREEMPT_NEED_RESCHED stuff is horribly broken for
load-store architectures.

We currently rely on the IPI to fold TIF_NEED_RESCHED into
PREEMPT_NEED_RESCHED, but when this IPI lands while we already have
a load for the preempt-count but before the store, the store will erase
the PREEMPT_NEED_RESCHED change.

The current preempt-count only works on load-store archs because
interrupts are assumed to be completely balanced wrt their preempt_count
fiddling; the previous preempt_count load will match the preempt_count
state after the interrupt and therefore nothing gets lost.

This patch removes the PREEMPT_NEED_RESCHED usage from generic code and
pushes it into x86 arch code; the generic code goes back to relying on
TIF_NEED_RESCHED.

Boot tested on x86_64 and compile tested on ppc64.

Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reported-and-Tested-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131128132641.GP10022@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2013-11-28 14:26:41 +01:00 committed by Ingo Molnar
parent 8e8339a3a1
commit ba1f14fbe7
3 changed files with 22 additions and 26 deletions

View File

@ -7,6 +7,12 @@
DECLARE_PER_CPU(int, __preempt_count);
/*
* We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
* that a decrement hitting 0 means we can and should reschedule.
*/
#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
/*
* We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
* that think a non-zero value indicates we cannot preempt.
@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
__this_cpu_add_4(__preempt_count, -val);
}
/*
* Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
* a decrement which hits zero means we have no preempt_count and should
* reschedule.
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");

View File

@ -3,13 +3,11 @@
#include <linux/thread_info.h>
/*
* We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
* that think a non-zero value indicates we cannot preempt.
*/
#define PREEMPT_ENABLED (0)
static __always_inline int preempt_count(void)
{
return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
return current_thread_info()->preempt_count;
}
static __always_inline int *preempt_count_ptr(void)
@ -17,11 +15,6 @@ static __always_inline int *preempt_count_ptr(void)
return &current_thread_info()->preempt_count;
}
/*
* We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
* alternative is loosing a reschedule. Better schedule too often -- also this
* should be a very rare operation.
*/
static __always_inline void preempt_count_set(int pc)
{
*preempt_count_ptr() = pc;
@ -41,28 +34,17 @@ static __always_inline void preempt_count_set(int pc)
task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
} while (0)
/*
* We fold the NEED_RESCHED bit into the preempt count such that
* preempt_enable() can decrement and test for needing to reschedule with a
* single instruction.
*
* We invert the actual bit, so that when the decrement hits 0 we know we both
* need to resched (the bit is cleared) and can resched (no preempt count).
*/
static __always_inline void set_preempt_need_resched(void)
{
*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
}
static __always_inline void clear_preempt_need_resched(void)
{
*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
}
static __always_inline bool test_preempt_need_resched(void)
{
return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
return false;
}
/*
@ -81,7 +63,12 @@ static __always_inline void __preempt_count_sub(int val)
static __always_inline bool __preempt_count_dec_and_test(void)
{
return !--*preempt_count_ptr();
/*
* Because of load-store architectures cannot do per-cpu atomic
* operations; we cannot use PREEMPT_NEED_RESCHED because it might get
* lost.
*/
return !--*preempt_count_ptr() && tif_need_resched();
}
/*
@ -89,7 +76,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
*/
static __always_inline bool should_resched(void)
{
return unlikely(!*preempt_count_ptr());
return unlikely(!preempt_count() && tif_need_resched());
}
#ifdef CONFIG_PREEMPT

View File

@ -440,8 +440,6 @@ struct task_cputime {
.sum_exec_runtime = 0, \
}
#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED)
#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED)
#else