[PATCH] x86/entry/64: Fix native_load_gs_index() SWAPGS handling with IRQ state tracing enabled

[Ingo Molnar]

Jarkko Nikula reported a S2R resume hang regression and bisected it back to:

  ca37e57bbe0c ("x86/entry/64: Add missing irqflags tracing to native_load_gs_index()")

Turns out the GS handling of that patch is wrong: when IRQ state tracing is
enabled it calls a kernel function (as part of the TRACE_IRQS_*() functionality),
but we have not switched to the kernel GS yet ...

Fix the SWAPGS handling and also annotate every affected SWAPGS
instance to document the intended state of GS.

Reported-by: Jarkko Nikula <jarkko.nikula@xxxxxxxxxxxxxxx>
Bisected-by: Jarkko Nikula <jarkko.nikula@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/0fede9f9-88b0-a6e7-1027-dfb2019b8ef2@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/entry/entry_64.S | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f81d50d7ceac..c0b52df8ee4f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -945,16 +945,16 @@ idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
 	 */
 ENTRY(native_load_gs_index)
 	FRAME_BEGIN
+	SWAPGS					/* switch from user GS to kernel GS */
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	TRACE_IRQS_OFF
-	SWAPGS
 .Lgs_change:
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
-	SWAPGS
 	TRACE_IRQS_FLAGS (%rsp)
 	popfq
+	SWAPGS					/* switch from kernel GS to user GS */
 	FRAME_END
 	ret
 ENDPROC(native_load_gs_index)
@@ -964,7 +964,7 @@ EXPORT_SYMBOL(native_load_gs_index)
 	.section .fixup, "ax"
 	/* running with kernelgs */
 bad_gs:
-	SWAPGS					/* switch back to user gs */
+	SWAPGS					/* switch back to user GS, to modify GS */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */
 	movl $__USER_DS, %eax
@@ -973,6 +973,7 @@ EXPORT_SYMBOL(native_load_gs_index)
 	ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG
 	xorl	%eax, %eax
 	movl	%eax, %gs
+	SWAPGS					/* switch to kernel GS again before continuing */
 	jmp	2b
 	.previous