[PATCH 4.9 84/96] x86/asm: Use register variable to get stack pointer value

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>

commit 196bd485ee4f03ce4c690bfcf38138abfcd0a4bc upstream.

Currently we use current_stack_pointer() function to get the value
of the stack pointer register. Since commit:

  f5caf621ee35 ("x86/asm: Fix inline asm call constraints for Clang")

... we have a stack register variable declared. It can be used instead of
current_stack_pointer() function which allows to optimize away some
excessive "mov %rsp, %<dst>" instructions:

 -mov    %rsp,%rdx
 -sub    %rdx,%rax
 -cmp    $0x3fff,%rax
 -ja     ffffffff810722fd <ist_begin_non_atomic+0x2d>

 +sub    %rsp,%rax
 +cmp    $0x3fff,%rax
 +ja     ffffffff810722fa <ist_begin_non_atomic+0x2a>

Remove current_stack_pointer(), rename __asm_call_sp to current_stack_pointer
and use it instead of the removed function.

Signed-off-by: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Reviewed-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
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/20170929141537.29167-1-aryabinin@xxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
[dwmw2: We want ASM_CALL_CONSTRAINT for retpoline]
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/asm.h         |   11 +++++++++++
 arch/x86/include/asm/thread_info.h |   11 -----------
 arch/x86/kernel/irq_32.c           |    6 +++---
 arch/x86/kernel/traps.c            |    2 +-
 arch/x86/mm/tlb.c                  |    2 +-
 5 files changed, 16 insertions(+), 16 deletions(-)

--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -125,4 +125,15 @@
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
+#ifndef __ASSEMBLY__
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction.  Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function.  If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif
+
 #endif /* _ASM_X86_ASM_H */
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -152,17 +152,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 /*
  * Walks up the stack frames to make sure that the specified object is
  * entirely contained by a single stack frame.
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -64,7 +64,7 @@ static void call_on_stack(void *func, vo
 
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(i
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -139,7 +139,7 @@ void do_softirq_own_stack(void)
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -153,7 +153,7 @@ void ist_begin_non_atomic(struct pt_regs
 	 * from double_fault.
 	 */
 	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer()) >= THREAD_SIZE);
+			       current_stack_pointer) >= THREAD_SIZE);
 
 	preempt_enable_no_resched();
 }
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -110,7 +110,7 @@ void switch_mm_irqs_off(struct mm_struct
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
+			unsigned int stack_pgd_index = pgd_index(current_stack_pointer);
 
 			pgd_t *pgd = next->pgd + stack_pgd_index;