+++ /dev/null
-From f8e617f4582995f7c25ef25b4167213120ad122b Mon Sep 17 00:00:00 2001
-From: Mike Galbraith <bitbucket@online.de>
-Date: Sat, 18 Jan 2014 17:14:44 +0100
-Subject: sched/idle/x86: Optimize unnecessary mwait_idle() resched IPIs
-
-From: Mike Galbraith <bitbucket@online.de>
-
-commit f8e617f4582995f7c25ef25b4167213120ad122b upstream.
-
-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 <bitbucket@online.de>
-Cc: Borislav Petkov <bp@alien8.de>
-Cc: H. Peter Anvin <hpa@zytor.com>
-Cc: Ian Malone <ibmalone@gmail.com>
-Cc: Josh Boyer <jwboyer@redhat.com>
-Cc: Len Brown <len.brown@intel.com>
-Cc: Len Brown <lenb@kernel.org>
-Cc: Linus Torvalds <torvalds@linux-foundation.org>
-Cc: Mike Galbraith <efault@gmx.de>
-Cc: Peter Zijlstra <peterz@infradead.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-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 <mingo@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
----
- arch/x86/kernel/process.c | 12 ++++++++----
- 1 file changed, 8 insertions(+), 4 deletions(-)
-
---- a/arch/x86/kernel/process.c
-+++ b/arch/x86/kernel/process.c
-@@ -428,18 +428,22 @@ static int prefer_mwait_c1_over_halt(con
-
- 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)
Tested-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Len Brown <len.brown@intel.com>
Acked-by: Mike Galbraith <bitbucket@online.de>
+Cc: <stable@vger.kernel.org> # 3.9+
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ian Malone <ibmalone@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/345254a551eb5a6a866e048d7ab570fd2193aca4.1389763084.git.len.brown@intel.com
[ Ported to recent kernels. ]
+[ Mike: 3.10 backport ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
- arch/x86/include/asm/mwait.h | 8 +++++++
- arch/x86/kernel/process.c | 47 +++++++++++++++++++++++++++++++++++++++++++
- 2 files changed, 55 insertions(+)
+ arch/x86/include/asm/mwait.h | 8 ++++++
+ arch/x86/kernel/process.c | 50 +++++++++++++++++++++++++++++++++++++++++++
+ 2 files changed, 58 insertions(+)
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
* which can obviate IPI to trigger checking of need_resched.
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
-@@ -24,6 +24,7 @@
- #include <asm/syscalls.h>
- #include <asm/idle.h>
- #include <asm/uaccess.h>
-+#include <asm/mwait.h>
- #include <asm/i387.h>
+@@ -28,6 +28,7 @@
#include <asm/fpu-internal.h>
#include <asm/debugreg.h>
-@@ -398,6 +399,49 @@ static void amd_e400_idle(void)
+ #include <asm/nmi.h>
++#include <asm/mwait.h>
+
+ /*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+@@ -398,6 +399,52 @@ static void amd_e400_idle(void)
default_idle();
}
+
+static void mwait_idle(void)
+{
-+ if (!need_resched()) {
-+ if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR))
++ if (!current_set_polling_and_test()) {
++ if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) {
++ mb();
+ clflush((void *)¤t_thread_info()->flags);
++ mb();
++ }
+
+ __monitor((void *)¤t_thread_info()->flags, 0, 0);
-+ smp_mb();
+ if (!need_resched())
+ __sti_mwait(0, 0);
+ else
+ local_irq_enable();
+ } else
+ local_irq_enable();
++ current_clr_polling();
+}
+
void select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
-@@ -411,6 +455,9 @@ void select_idle_routine(const struct cp
+@@ -411,6 +458,9 @@ void select_idle_routine(const struct cp
/* E400: APIC timer interrupt does not wake up CPU from C1e */
pr_info("using AMD E400 aware idle routine\n");
x86_idle = amd_e400_idle;
tcp-avoid-looping-in-tcp_send_fin.patch
net-do-not-deplete-pfmemalloc-reserve.patch
net-fix-crash-in-build_skb.patch
-sched-idle-x86-restore-mwait_idle-to-fix-boot-hangs-to-improve-power-savings-and-to-improve-performance.patch
-sched-idle-x86-optimize-unnecessary-mwait_idle-resched-ipis.patch
btrfs-fix-log-tree-corruption-when-fs-mounted-with-o-discard.patch
btrfs-don-t-accept-bare-namespace-as-a-valid-xattr.patch
btrfs-fix-inode-eviction-infinite-loop-after-cloning-into-it.patch
btrfs-fix-inode-eviction-infinite-loop-after-extent_same-ioctl.patch
+sched-idle-x86-restore-mwait_idle-to-fix-boot-hangs-to-improve-power-savings-and-to-improve-performance.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
