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) <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: linux-api@vger.kernel.org
Link: http://lkml.kernel.org/r/20141105093759.GQ10501@worktop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

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 = {		\

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,

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,
 };