[PATCH 5/5] perf, x86: Support Haswell v4 LBR format

[Andi Kleen <andi@firstfloor.org>]

From: Andi Kleen <ak@linux.intel.com>

Haswell has two additional LBR from flags for TSX: intx and abort, implemented
as a new v4 version of the LBR format.

Handle those in and adjust the sign extension code to still correctly extend.
The flags are exported similarly in the LBR record to the existing misprediction
flag

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |   18 +++++++++++++++---
 include/linux/perf_event.h                 |    7 ++++++-
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index da02e9c..2af6695b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -12,6 +12,7 @@ enum {
 	LBR_FORMAT_LIP		= 0x01,
 	LBR_FORMAT_EIP		= 0x02,
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
+	LBR_FORMAT_EIP_FLAGS2	= 0x04,
 };
 
 /*
@@ -56,6 +57,8 @@ enum {
 	 LBR_FAR)
 
 #define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+#define LBR_FROM_FLAG_INTX     (1ULL << 62)
+#define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
 #define for_each_branch_sample_type(x) \
 	for ((x) = PERF_SAMPLE_BRANCH_USER; \
@@ -270,21 +273,30 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
-		u64 from, to, mis = 0, pred = 0;
+		u64 from, to, mis = 0, pred = 0, intx = 0, abort = 0;
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
-		if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
+		if (lbr_format == LBR_FORMAT_EIP_FLAGS ||
+		    lbr_format == LBR_FORMAT_EIP_FLAGS2) {
 			mis = !!(from & LBR_FROM_FLAG_MISPRED);
 			pred = !mis;
-			from = (u64)((((s64)from) << 1) >> 1);
+			if (lbr_format == LBR_FORMAT_EIP_FLAGS)
+				from = (u64)((((s64)from) << 1) >> 1);
+			else if (lbr_format == LBR_FORMAT_EIP_FLAGS2) {
+				intx = !!(from & LBR_FROM_FLAG_INTX);
+				abort = !!(from & LBR_FROM_FLAG_ABORT);
+				from = (u64)((((s64)from) << 3) >> 3);
+			}
 		}
 
 		cpuc->lbr_entries[i].from	= from;
 		cpuc->lbr_entries[i].to		= to;
 		cpuc->lbr_entries[i].mispred	= mis;
 		cpuc->lbr_entries[i].predicted	= pred;
+		cpuc->lbr_entries[i].intx	= intx;
+		cpuc->lbr_entries[i].abort	= abort;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1d795df..e1b975a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -74,13 +74,18 @@ struct perf_raw_record {
  *
  * support for mispred, predicted is optional. In case it
  * is not supported mispred = predicted = 0.
+ *
+ *     intx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
  */
 struct perf_branch_entry {
 	__u64	from;
 	__u64	to;
 	__u64	mispred:1,  /* target mispredicted */
 		predicted:1,/* target predicted */
-		reserved:62;
+		intx:1,	    /* in transaction */
+		abort:1,    /* transaction abort */
+		reserved:60;
 };
 
 /*
-- 
1.7.7.6