[PATCH 5/5] perf, x86: Support Haswell v4 LBR format v2

[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

v2: Add some _
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |   56 +++++++++++++++++++++++++--
 include/linux/perf_event.h                 |    7 +++-
 include/uapi/linux/perf_event.h            |    5 ++-
 3 files changed, 61 insertions(+), 7 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..6f9b794 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -12,6 +12,16 @@ enum {
 	LBR_FORMAT_LIP		= 0x01,
 	LBR_FORMAT_EIP		= 0x02,
 	LBR_FORMAT_EIP_FLAGS	= 0x03,
+	LBR_FORMAT_EIP_FLAGS2	= 0x04,
+	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_EIP_FLAGS2,
+};
+
+static enum {
+	LBR_EIP_FLAGS		= 1,
+	LBR_TSX			= 2,
+} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = {
+	[LBR_FORMAT_EIP_FLAGS]  = LBR_EIP_FLAGS,
+	[LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX,
 };
 
 /*
@@ -56,6 +66,8 @@ enum {
 	 LBR_FAR)
 
 #define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+#define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
+#define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
 #define for_each_branch_sample_type(x) \
 	for ((x) = PERF_SAMPLE_BRANCH_USER; \
@@ -81,9 +93,13 @@ enum {
 	X86_BR_JMP      = 1 << 9, /* jump */
 	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
 	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
+	X86_BR_ABORT    = 1 << 12,/* transaction abort */
+	X86_BR_IN_TX    = 1 << 13,/* in transaction */
+	X86_BR_NO_TX    = 1 << 14,/* not in transaction */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
+#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX)
 
 #define X86_BR_ANY       \
 	(X86_BR_CALL    |\
@@ -95,6 +111,7 @@ enum {
 	 X86_BR_JCC     |\
 	 X86_BR_JMP	 |\
 	 X86_BR_IRQ	 |\
+	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -270,21 +287,31 @@ 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, in_tx = 0, abort = 0;
+		int skip = 0;
+		int lbr_flags = lbr_desc[lbr_format];
 
 		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_flags & LBR_EIP_FLAGS) {
 			mis = !!(from & LBR_FROM_FLAG_MISPRED);
 			pred = !mis;
-			from = (u64)((((s64)from) << 1) >> 1);
+			skip = 1;
+		}
+		if (lbr_flags & LBR_TSX) {
+			in_tx = !!(from & LBR_FROM_FLAG_IN_TX);
+			abort = !!(from & LBR_FROM_FLAG_ABORT);
+			skip = 3;
 		}
+		from = (u64)((((s64)from) << skip) >> skip);
 
 		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].in_tx	= in_tx;
+		cpuc->lbr_entries[i].abort	= abort;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
@@ -334,6 +361,16 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 
 	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
 		mask |= X86_BR_IND_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX)
+		mask |= X86_BR_ABORT;
+
+	if (br_type & PERF_SAMPLE_BRANCH_IN_TX)
+		mask |= X86_BR_IN_TX;
+
+	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
+		mask |= X86_BR_NO_TX;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -408,7 +445,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
  * decoded (e.g., text page not present), then X86_BR_NONE is
  * returned.
  */
-static int branch_type(unsigned long from, unsigned long to)
+static int branch_type(unsigned long from, unsigned long to, int abort)
 {
 	struct insn insn;
 	void *addr;
@@ -428,6 +465,9 @@ static int branch_type(unsigned long from, unsigned long to)
 	if (from == 0 || to == 0)
 		return X86_BR_NONE;
 
+	if (abort)
+		return X86_BR_ABORT | to_plm;
+
 	if (from_plm == X86_BR_USER) {
 		/*
 		 * can happen if measuring at the user level only
@@ -564,7 +604,13 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 		from = cpuc->lbr_entries[i].from;
 		to = cpuc->lbr_entries[i].to;
 
-		type = branch_type(from, to);
+		type = branch_type(from, to, cpuc->lbr_entries[i].abort);
+		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
+			if (cpuc->lbr_entries[i].in_tx)
+				type |= X86_BR_IN_TX;
+			else
+				type |= X86_BR_NO_TX;
+		}
 
 		/* if type does not correspond, then discard */
 		if (type == X86_BR_NONE || (br_sel & type) != type) {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e0373d2..466e378 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -73,13 +73,18 @@ struct perf_raw_record {
  *
  * support for mispred, predicted is optional. In case it
  * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: 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;
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		reserved:60;
 };
 
 /*
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index fb104e5..0b1df41 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -157,8 +157,11 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
 	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
 	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
 
-	PERF_SAMPLE_BRANCH_MAX		= 1U << 7, /* non-ABI */
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
-- 
1.7.7.6