This is a note to let you know that I've just added the patch titled
x86/mm: If INVPCID is available, use it to flush global mappings
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
x86-mm-if-invpcid-is-available-use-it-to-flush-global-mappings.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From d8bced79af1db6734f66b42064cc773cada2ce99 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@xxxxxxxxxx>
Date: Fri, 29 Jan 2016 11:42:59 -0800
Subject: x86/mm: If INVPCID is available, use it to flush global mappings
From: Andy Lutomirski <luto@xxxxxxxxxx>
commit d8bced79af1db6734f66b42064cc773cada2ce99 upstream.
On my Skylake laptop, INVPCID function 2 (flush absolutely
everything) takes about 376ns, whereas saving flags, twiddling
CR4.PGE to flush global mappings, and restoring flags takes about
539ns.
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Luis R. Rodriguez <mcgrof@xxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxx>
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/ed0ef62581c0ea9c99b9bf6df726015e96d44743.1454096309.git.luto@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/include/asm/tlbflush.h | 9 +++++++++
1 file changed, 9 insertions(+)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -159,6 +159,15 @@ static inline void __native_flush_tlb_gl
{
unsigned long flags;
+ if (static_cpu_has(X86_FEATURE_INVPCID)) {
+ /*
+ * Using INVPCID is considerably faster than a pair of writes
+ * to CR4 sandwiched inside an IRQ flag save/restore.
+ */
+ invpcid_flush_all();
+ return;
+ }
+
/*
* Read-modify-write to CR4 - protect it from preemption and
* from interrupts. (Use the raw variant because this code can
Patches currently in stable-queue which might be from luto@xxxxxxxxxx are
queue-4.4/x86-mm-sched-core-uninline-switch_mm.patch
queue-4.4/x86-mm-add-a-noinvpcid-boot-option-to-turn-off-invpcid.patch
queue-4.4/x86-irq-do-not-substract-irq_tlb_count-from-irq_call_count.patch
queue-4.4/x86-mm-if-invpcid-is-available-use-it-to-flush-global-mappings.patch
queue-4.4/x86-mm-add-invpcid-helpers.patch
queue-4.4/sched-core-add-switch_mm_irqs_off-and-use-it-in-the-scheduler.patch
queue-4.4/arm-hide-finish_arch_post_lock_switch-from-modules.patch
queue-4.4/x86-mm-sched-core-turn-off-irqs-in-switch_mm.patch
queue-4.4/mm-mmu_context-sched-core-fix-mmu_context.h-assumption.patch
queue-4.4/x86-mm-build-arch-x86-mm-tlb.c-even-on-smp.patch
queue-4.4/sched-core-idle_task_exit-shouldn-t-use-switch_mm_irqs_off.patch