x86/nmi/64: Fix a paravirt stack-clobbering bug in the NMI code

The NMI entry code that switches to the normal kernel stack needs to
be very careful not to clobber any extra stack slots on the NMI
stack.  The code is fine under the assumption that SWAPGS is just a
normal instruction, but that assumption isn't really true.  Use
SWAPGS_UNSAFE_STACK instead.

This is part of a fix for some random crashes that Sasha saw.

Fixes: 9b6e6a8334d5 ("x86/nmi/64: Switch stacks on userspace NMI entry")
Reported-and-tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/974bc40edffdb5c2950a5c4977f821a446b76178.1442791737.git.luto@kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 4 insertions, 1 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 404ca97c4715..055a01de7c8d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1190,9 +1190,12 @@ ENTRY(nmi)
          * we don't want to enable interrupts, because then we'll end
          * up in an awkward situation in which IRQs are on but NMIs
          * are off.
+         *
+         * We also must not push anything to the stack before switching
+         * stacks lest we corrupt the "NMI executing" variable.
          */
 
-        SWAPGS
+        SWAPGS_UNSAFE_STACK
         cld
         movq    %rsp, %rdx
         movq    PER_CPU_VAR(cpu_current_top_of_stack), %rsp