From: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx> This patch has been added to the 4.1 stable tree. If you have any objections, please let us know. =============== [ Upstream commit 196bd485ee4f03ce4c690bfcf38138abfcd0a4bc ] 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> Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx> --- 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 +- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index e2015452177d..37496d271033 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -88,4 +88,15 @@ /* 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 */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index b4bdec3e9523..b58daa40eae9 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -184,17 +184,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); } -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; -} - #else /* !__ASSEMBLY__ */ /* Load thread_info address into "reg" */ diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index f9fd86a7fcc7..9f4ffc122d9e 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -71,7 +71,7 @@ static void call_on_stack(void *func, void *stack) 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 @@ -96,7 +96,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) /* 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); @@ -149,7 +149,7 @@ 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); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 020248f2cec4..e78c6783a2de 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -175,7 +175,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_count_sub(HARDIRQ_OFFSET); } -- 2.14.1