From f8e617f4582995f7c25ef25b4167213120ad122b Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Sat, 18 Jan 2014 17:14:44 +0100 Subject: [PATCH] sched/idle/x86: Optimize unnecessary mwait_idle() resched IPIs To fully take advantage of MWAIT, apparently the CLFLUSH instruction needs another quirk on certain CPUs: proper barriers around it on certain machines. On a Q6600 SMP system, pipe-test scheduling performance, cross core, improves significantly: 3.8.13 487.2 KHz 1.000 3.13.0-master 415.5 KHz .852 3.13.0-master+ 415.2 KHz .852 + restore mwait_idle 3.13.0-master++ 488.5 KHz 1.002 + restore mwait_idle + IPI fix Since X86_BUG_CLFLUSH_MONITOR is already a quirk, don't create a separate quirk for the extra smp_mb()s. Signed-off-by: Mike Galbraith Cc: # 3.10+ Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Ian Malone Cc: Josh Boyer Cc: Len Brown Cc: Len Brown Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1390061684.5566.4.camel@marge.simpson.net [ Ported to recent kernel, added comments about the quirk. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/process.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index da06f741d2a6..6ad8a6396b75 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -428,18 +428,22 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static void mwait_idle(void) { - if (!need_resched()) { - if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) + if (!current_set_polling_and_test()) { + if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { + smp_mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); + smp_mb(); /* quirk */ + } __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); if (!need_resched()) __sti_mwait(0, 0); else local_irq_enable(); - } else + } else { local_irq_enable(); + } + __current_clr_polling(); } void select_idle_routine(const struct cpuinfo_x86 *c) -- 2.39.5