diff options
| author | Thomas Gleixner <tglx@linutronix.de> | 2022-09-15 14:11:30 +0300 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2022-10-17 17:41:16 +0300 |
| commit | f5c1bb2afe93396d41c5cbdcb909b08a75b8dde4 (patch) | |
| tree | ea7d2c0ffd9a4c54bb865b0b3fdccbfb21f4189a /arch/x86/include/asm/nospec-branch.h | |
| parent | bbaceb189a21d7245e8063701fe10985396028f9 (diff) | |
| download | linux-f5c1bb2afe93396d41c5cbdcb909b08a75b8dde4.tar.xz | |
x86/calldepth: Add ret/call counting for debug
Add a debuigfs mechanism to validate the accounting, e.g. vs. call/ret
balance and to gather statistics about the stuffing to call ratio.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111148.204285506@infradead.org
Diffstat (limited to 'arch/x86/include/asm/nospec-branch.h')
| -rw-r--r-- | arch/x86/include/asm/nospec-branch.h | 36 |
1 files changed, 32 insertions, 4 deletions
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 06ba7caa0cad..4771147c7c5a 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -57,6 +57,22 @@ #define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL #define RET_DEPTH_CREDIT 0xffffffffffffffffULL +#ifdef CONFIG_CALL_THUNKS_DEBUG +# define CALL_THUNKS_DEBUG_INC_CALLS \ + incq %gs:__x86_call_count; +# define CALL_THUNKS_DEBUG_INC_RETS \ + incq %gs:__x86_ret_count; +# define CALL_THUNKS_DEBUG_INC_STUFFS \ + incq %gs:__x86_stuffs_count; +# define CALL_THUNKS_DEBUG_INC_CTXSW \ + incq %gs:__x86_ctxsw_count; +#else +# define CALL_THUNKS_DEBUG_INC_CALLS +# define CALL_THUNKS_DEBUG_INC_RETS +# define CALL_THUNKS_DEBUG_INC_STUFFS +# define CALL_THUNKS_DEBUG_INC_CTXSW +#endif + #if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> @@ -75,18 +91,23 @@ #define RESET_CALL_DEPTH_FROM_CALL \ mov $0xfc, %rax; \ shl $56, %rax; \ - movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); + movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ - sarq $5, %gs:pcpu_hot + X86_call_depth; + sarq $5, %gs:pcpu_hot + X86_call_depth; \ + CALL_THUNKS_DEBUG_INC_CALLS #define ASM_INCREMENT_CALL_DEPTH \ - sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); + sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH +#define ASM_CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH #define INCREMENT_CALL_DEPTH +#define ASM_INCREMENT_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL #endif @@ -137,7 +158,8 @@ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ - ASM_CREDIT_CALL_DEPTH + ASM_CREDIT_CALL_DEPTH \ + CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't @@ -321,6 +343,12 @@ static inline void x86_set_skl_return_thunk(void) { x86_return_thunk = &__x86_return_skl; } +#ifdef CONFIG_CALL_THUNKS_DEBUG +DECLARE_PER_CPU(u64, __x86_call_count); +DECLARE_PER_CPU(u64, __x86_ret_count); +DECLARE_PER_CPU(u64, __x86_stuffs_count); +DECLARE_PER_CPU(u64, __x86_ctxsw_count); +#endif #else static inline void x86_set_skl_return_thunk(void) {} #endif |