x86/mm, sched/core: Turn off IRQs in switch_mm()
authorAndy Lutomirski <luto@kernel.org>
Tue, 26 Apr 2016 16:39:09 +0000 (09:39 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Mon, 25 Dec 2017 13:22:09 +0000 (14:22 +0100)
commit4ead44fd2525ed97e5362a806d312a0e3b0ea445
tree6fc1b8aec9fd761e37816b5d43d91fdc29976566
parent70a39c7fd167399fde76aeac314dce026a255b49
x86/mm, sched/core: Turn off IRQs in switch_mm()

commit 078194f8e9fe3cf54c8fd8bded48a1db5bd8eb8a upstream.

Potential races between switch_mm() and TLB-flush or LDT-flush IPIs
could be very messy.  AFAICT the code is currently okay, whether by
accident or by careful design, but enabling PCID will make it
considerably more complicated and will no longer be obviously safe.

Fix it with a big hammer: run switch_mm() with IRQs off.

To avoid a performance hit in the scheduler, we take advantage of
our knowledge that the scheduler already has IRQs disabled when it
calls switch_mm().

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/f19baf759693c9dcae64bbff76189db77cb13398.1461688545.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
arch/x86/include/asm/mmu_context.h
arch/x86/mm/tlb.c