[PATCH 3.16.y-ckt 047/104] x86/nmi/64: Fix a paravirt stack-clobbering bug in the NMI code
From: Luis Henriques
Date: Mon Oct 26 2015 - 10:17:14 EST
3.16.7-ckt19 -stable review patch. If anyone has any objections, please let me know.
From: Andy Lutomirski <luto@xxxxxxxxxx>
commit 83c133cf11fb0e68a51681447e372489f052d40e upstream.
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
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@xxxxxxxxxx>
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
[ luis: backported to 3.16:
- file rename: arch/x86/entry/entry_64.S -> arch/x86/kernel/entry_64.S
- adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@xxxxxxxxxxxxx>
arch/x86/kernel/entry_64.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 47b8deb372f9..701db48562b1 100644
@@ -1489,9 +1489,12 @@ 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.
movq %rsp, %rdx
movq PER_CPU_VAR(kernel_stack), %rsp
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/