From 2c44b1936bb3b135a3fac8b3493394d42e51cf70 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Nov 2014 10:36:45 +0100 Subject: [PATCH] perf/x86/intel: Expose LBR callstack to user space tooling With LBR call stack feature enable, there are three callchain options. Enable the 3rd callchain option (LBR callstack) to user space tooling. Signed-off-by: Peter Zijlstra (Intel) Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Andy Lutomirski Cc: Kan Liang Cc: Linus Torvalds Cc: Paul Mackerras Cc: Vince Weaver Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/20141105093759.GQ10501@worktop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.h | 8 -------- arch/x86/kernel/cpu/perf_event_intel_lbr.c | 8 ++++---- include/uapi/linux/perf_event.h | 16 ++++++++-------- 3 files changed, 12 insertions(+), 20 deletions(-) diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 69c26b396cf4..a371d27d6795 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -523,14 +523,6 @@ struct x86_perf_task_context { int lbr_stack_state; }; -enum { - PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = PERF_SAMPLE_BRANCH_MAX_SHIFT, - PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE, - - PERF_SAMPLE_BRANCH_CALL_STACK = - 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, -}; - #define x86_add_quirk(func_) \ do { \ static struct x86_pmu_quirk __quirk __initdata = { \ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 084f2eb20c8b..0473874109cb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -537,7 +537,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) u64 mask = 0, v; int i; - for (i = 0; i < PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE; i++) { + for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) { if (!(br_type & (1ULL << i))) continue; @@ -821,7 +821,7 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) /* * Map interface branch filters onto LBR filters */ -static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = { +static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, @@ -840,7 +840,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, }; -static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = { +static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, @@ -852,7 +852,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, }; -static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = { +static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e46b93279e3d..1e3cd07cf76e 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -166,6 +166,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -175,18 +177,16 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, - PERF_SAMPLE_BRANCH_ANY_CALL = - 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ANY_RETURN = - 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, - PERF_SAMPLE_BRANCH_IND_CALL = - 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ABORT_TX = - 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; -- 2.20.1