perf branch: Extend branch type classification

This updates the perf tool with generic branch type classification with new
ABI extender place holder i.e PERF_BR_EXTEND_ABI, the new 4 bit branch type
field i.e perf_branch_entry.new_type, new generic page fault related branch
types and some arch specific branch types as added earlier in the kernel.

Committer note:

Add an extra entry to the branch_type_name array to cope with
PERF_BR_EXTEND_ABI, to address build warnings on some compiler/systems,
like:

  75     8.89 ubuntu:20.04-x-powerpc64el    : FAIL gcc version 10.3.0 (Ubuntu 10.3.0-1ubuntu1~20.04)
        inlined from 'branch_type_stat_display' at util/branch.c:152:4:
    /usr/powerpc64le-linux-gnu/include/bits/stdio2.h💯10: error: '%8s' directive argument is null [-Werror=format-overflow=]
      100 |   return __fprintf_chk (__stream, __USE_FORTIFY_LEVEL - 1, __fmt,
          |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      101 |    __va_arg_pack ());
          |    ~~~~~~~~~~~~~~~~~

Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20220824044822.70230-7-anshuman.khandual@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/include/uapi/linux/perf_event.h

@@ -255,9 +255,22 @@ enum {
 	PERF_BR_IRQ		= 12,	/* irq */
 	PERF_BR_SERROR		= 13,	/* system error */
 	PERF_BR_NO_TX		= 14,	/* not in transaction */
+	PERF_BR_EXTEND_ABI	= 15,	/* extend ABI */
 	PERF_BR_MAX,
 };
 
+enum {
+	PERF_BR_NEW_FAULT_ALGN		= 0,    /* Alignment fault */
+	PERF_BR_NEW_FAULT_DATA		= 1,    /* Data fault */
+	PERF_BR_NEW_FAULT_INST		= 2,    /* Inst fault */
+	PERF_BR_NEW_ARCH_1		= 3,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_2		= 4,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_3		= 5,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_4		= 6,    /* Architecture specific */
+	PERF_BR_NEW_ARCH_5		= 7,    /* Architecture specific */
+	PERF_BR_NEW_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\
@@ -1375,7 +1388,8 @@ struct perf_branch_entry {
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
 		type:4,     /* branch type */
-		reserved:40;
+		new_type:4, /* additional branch type */
+		reserved:36;
 };
 
 union perf_sample_weight {

tools/perf/builtin-script.c

@@ -882,7 +882,7 @@ static int print_bstack_flags(FILE *fp, struct branch_entry *br)
 		       br->flags.in_tx ? 'X' : '-',
 		       br->flags.abort ? 'A' : '-',
 		       br->flags.cycles,
-		       br->flags.type ? branch_type_name(br->flags.type) : "-");
+		       get_branch_type(br));
 }
 
 static int perf_sample__fprintf_brstack(struct perf_sample *sample,

tools/perf/util/branch.c

@@ -21,7 +21,10 @@ void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 	if (flags->type == PERF_BR_UNKNOWN || from == 0)
 		return;
 
-	st->counts[flags->type]++;
+	if (flags->type == PERF_BR_EXTEND_ABI)
+		st->new_counts[flags->new_type]++;
+	else
+		st->counts[flags->type]++;
 
 	if (flags->type == PERF_BR_COND) {
 		if (to > from)
@@ -36,6 +39,25 @@ void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 		st->cross_4k++;
 }
 
+const char *branch_new_type_name(int new_type)
+{
+	const char *branch_new_names[PERF_BR_NEW_MAX] = {
+		"FAULT_ALGN",
+		"FAULT_DATA",
+		"FAULT_INST",
+		"ARCH_1",
+		"ARCH_2",
+		"ARCH_3",
+		"ARCH_4",
+		"ARCH_5"
+	};
+
+	if (new_type >= 0 && new_type < PERF_BR_NEW_MAX)
+		return branch_new_names[new_type];
+
+	return NULL;
+}
+
 const char *branch_type_name(int type)
 {
 	const char *branch_names[PERF_BR_MAX] = {
@@ -53,7 +75,8 @@ const char *branch_type_name(int type)
 		"ERET",
 		"IRQ",
 		"SERROR",
-		"NO_TX"
+		"NO_TX",
+		"", // Needed for PERF_BR_EXTEND_ABI that ends up triggering some compiler warnings about NULL deref
 	};
 
 	if (type >= 0 && type < PERF_BR_MAX)
@@ -62,6 +85,17 @@ const char *branch_type_name(int type)
 	return NULL;
 }
 
+const char *get_branch_type(struct branch_entry *e)
+{
+	if (e->flags.type == PERF_BR_UNKNOWN)
+		return "";
+
+	if (e->flags.type == PERF_BR_EXTEND_ABI)
+		return branch_new_type_name(e->flags.new_type);
+
+	return branch_type_name(e->flags.type);
+}
+
 void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
 {
 	u64 total = 0;
@@ -108,6 +142,15 @@ void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
 				100.0 *
 				(double)st->counts[i] / (double)total);
 	}
+
+	for (i = 0; i < PERF_BR_NEW_MAX; i++) {
+		if (st->new_counts[i] > 0)
+			fprintf(fp, "\n%8s: %5.1f%%",
+				branch_new_type_name(i),
+				100.0 *
+				(double)st->new_counts[i] / (double)total);
+	}
+
 }
 
 static int count_str_scnprintf(int idx, const char *str, char *bf, int size)
@@ -123,6 +166,9 @@ int branch_type_str(struct branch_type_stat *st, char *bf, int size)
 	for (i = 0; i < PERF_BR_MAX; i++)
 		total += st->counts[i];
 
+	for (i = 0; i < PERF_BR_NEW_MAX; i++)
+		total += st->new_counts[i];
+
 	if (total == 0)
 		return 0;
 
@@ -140,6 +186,11 @@ int branch_type_str(struct branch_type_stat *st, char *bf, int size)
 			printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed);
 	}
 
+	for (i = 0; i < PERF_BR_NEW_MAX; i++) {
+		if (st->new_counts[i] > 0)
+			printed += count_str_scnprintf(j++, branch_new_type_name(i), bf + printed, size - printed);
+	}
+
 	if (st->cross_4k > 0)
 		printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed);
 

tools/perf/util/branch.h

@@ -24,7 +24,8 @@ struct branch_flags {
 			u64 abort:1;
 			u64 cycles:16;
 			u64 type:4;
-			u64 reserved:40;
+			u64 new_type:4;
+			u64 reserved:36;
 		};
 	};
 };
@@ -72,6 +73,7 @@ static inline struct branch_entry *perf_sample__branch_entries(struct perf_sampl
 struct branch_type_stat {
 	bool	branch_to;
 	u64	counts[PERF_BR_MAX];
+	u64	new_counts[PERF_BR_NEW_MAX];
 	u64	cond_fwd;
 	u64	cond_bwd;
 	u64	cross_4k;
@@ -82,6 +84,8 @@ void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 		       u64 from, u64 to);
 
 const char *branch_type_name(int type);
+const char *branch_new_type_name(int new_type);
+const char *get_branch_type(struct branch_entry *e);
 void branch_type_stat_display(FILE *fp, struct branch_type_stat *st);
 int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize);
 

tools/perf/util/session.c

@@ -1180,7 +1180,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 				e->flags.abort ? "A" : " ",
 				e->flags.in_tx ? "T" : " ",
 				(unsigned)e->flags.reserved,
-				e->flags.type ? branch_type_name(e->flags.type) : "");
+				get_branch_type(e));
 		} else {
 			if (i == 0) {
 				printf("..... %2"PRIu64": %016" PRIx64 "\n"