sched: Revert need_resched() to look at TIF_NEED_RESCHED

Yuanhan reported a serious throughput regression in his pigz
benchmark. Using the ftrace patch I found that several idle
paths need more TLC before we can switch the generic
need_resched() over to preempt_need_resched.

The preemption paths benefit most from preempt_need_resched and
do indeed use it; all other need_resched() users don't really
care that much so reverting need_resched() back to
tif_need_resched() is the simple and safe solution.

Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: lkp@linux.intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20130927153003.GF15690@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 5 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b09798b672f3..2ac5285db434 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2577,6 +2577,11 @@ static inline bool __must_check current_clr_polling_and_test(void)
 }
 #endif
 
+static __always_inline bool need_resched(void)
+{
+        return unlikely(tif_need_resched());
+}
+
 /*
  * Thread group CPU time accounting.
  */