perf report: Show branch type

index d09a9cd..69af012 100644
@@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
 	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 

@@ -198,9 +200,32 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
 	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
+		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
+/*
+ * Common flow change classification
+ */
+enum {
+	PERF_BR_NONE		= 0,	/* unknown */
+	PERF_BR_JCC		= 1,	/* conditional jump */
+	PERF_BR_JMP		= 2,	/* jump */
+	PERF_BR_IND_JMP		= 3,	/* indirect jump */
+	PERF_BR_CALL		= 4,	/* call */
+	PERF_BR_IND_CALL	= 5,	/* indirect call */
+	PERF_BR_RET		= 6,	/* return */
+	PERF_BR_SYSCALL		= 7,	/* syscall */
+	PERF_BR_SYSRET		= 8,	/* syscall return */
+	PERF_BR_IRQ		= 9,	/* hw interrupt/trap/fault */
+	PERF_BR_INT		= 10,	/* sw interrupt */
+	PERF_BR_IRET		= 11,	/* return from interrupt */
+	PERF_BR_FAR_BRANCH	= 12,	/* not generic far branch type */
+	PERF_BR_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\

@@ -999,6 +1024,7 @@ union perf_mem_data_src {
  *     in_tx: running in a hardware transaction
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
+ *      type: branch type
  */
 struct perf_branch_entry {
 	__u64	from;

@@ -1008,7 +1034,8 @@ struct perf_branch_entry {
 		in_tx:1,    /* in transaction */
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
-		reserved:44;
+		type:4,     /* branch type */
+		reserved:40;
 };
 
 #endif /* _UAPI_LINUX_PERF_EVENT_H */

index d09a9cd..69af012 100644
@@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
 	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 

@@ -198,9 +200,32 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
 	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
+		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
+/*
+ * Common flow change classification
+ */
+enum {
+	PERF_BR_NONE		= 0,	/* unknown */
+	PERF_BR_JCC		= 1,	/* conditional jump */
+	PERF_BR_JMP		= 2,	/* jump */
+	PERF_BR_IND_JMP		= 3,	/* indirect jump */
+	PERF_BR_CALL		= 4,	/* call */
+	PERF_BR_IND_CALL	= 5,	/* indirect call */
+	PERF_BR_RET		= 6,	/* return */
+	PERF_BR_SYSCALL		= 7,	/* syscall */
+	PERF_BR_SYSRET		= 8,	/* syscall return */
+	PERF_BR_IRQ		= 9,	/* hw interrupt/trap/fault */
+	PERF_BR_INT		= 10,	/* sw interrupt */
+	PERF_BR_IRET		= 11,	/* return from interrupt */
+	PERF_BR_FAR_BRANCH	= 12,	/* not generic far branch type */
+	PERF_BR_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\

@@ -999,6 +1024,7 @@ union perf_mem_data_src {
  *     in_tx: running in a hardware transaction
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
+ *      type: branch type
  */
 struct perf_branch_entry {
 	__u64	from;

@@ -1008,7 +1034,8 @@ struct perf_branch_entry {
 		in_tx:1,    /* in transaction */
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
-		reserved:44;
+		type:4,     /* branch type */
+		reserved:40;
 };
 
 #endif /* _UAPI_LINUX_PERF_EVENT_H */

index f924629..f10a7ed 100644
@@ -109,6 +109,9 @@ enum {
 	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
 	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
 	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
+
+	X86_BR_TYPE_SAVE	= 1 << 18,/* indicate to save branch type */
+
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)

@@ -510,6 +513,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].in_tx	= 0;
 		cpuc->lbr_entries[i].abort	= 0;
 		cpuc->lbr_entries[i].cycles	= 0;
+		cpuc->lbr_entries[i].type	= 0;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;

@@ -596,6 +600,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[out].in_tx	 = in_tx;
 		cpuc->lbr_entries[out].abort	 = abort;
 		cpuc->lbr_entries[out].cycles	 = cycles;
+		cpuc->lbr_entries[out].type	 = 0;
 		cpuc->lbr_entries[out].reserved	 = 0;
 		out++;
 	}

@@ -673,6 +678,10 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 
 	if (br_type & PERF_SAMPLE_BRANCH_CALL)
 		mask |= X86_BR_CALL | X86_BR_ZERO_CALL;
+
+	if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE)
+		mask |= X86_BR_TYPE_SAVE;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU

@@ -926,6 +935,44 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 	return ret;
 }
 
+#define X86_BR_TYPE_MAP_MAX	16
+
+static int
+common_branch_type(int type)
+{
+	int i, mask;
+	const int branch_map[X86_BR_TYPE_MAP_MAX] = {
+		PERF_BR_CALL,		/* X86_BR_CALL */
+		PERF_BR_RET,		/* X86_BR_RET */
+		PERF_BR_SYSCALL,	/* X86_BR_SYSCALL */
+		PERF_BR_SYSRET,		/* X86_BR_SYSRET */
+		PERF_BR_INT,		/* X86_BR_INT */
+		PERF_BR_IRET,		/* X86_BR_IRET */
+		PERF_BR_JCC,		/* X86_BR_JCC */
+		PERF_BR_JMP,		/* X86_BR_JMP */
+		PERF_BR_IRQ,		/* X86_BR_IRQ */
+		PERF_BR_IND_CALL,	/* X86_BR_IND_CALL */
+		PERF_BR_NONE,		/* X86_BR_ABORT */
+		PERF_BR_NONE,		/* X86_BR_IN_TX */
+		PERF_BR_NONE,		/* X86_BR_NO_TX */
+		PERF_BR_CALL,		/* X86_BR_ZERO_CALL */
+		PERF_BR_NONE,		/* X86_BR_CALL_STACK */
+		PERF_BR_IND_JMP,	/* X86_BR_IND_JMP */
+	};
+
+	type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */
+	mask = ~(~0 << 1);
+
+	for (i = 0; i < X86_BR_TYPE_MAP_MAX; i++) {
+		if (type & mask)
+			return branch_map[i];
+
+		type >>= 1;
+	}
+
+	return PERF_BR_NONE;
+}
+
 /*
  * implement actual branch filter based on user demand.
  * Hardware may not exactly satisfy that request, thus

@@ -942,7 +989,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	bool compress = false;
 
 	/* if sampling all branches, then nothing to filter */
-	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+	if (((br_sel & X86_BR_ALL) == X86_BR_ALL) &&
+	    ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE))
 		return;
 
 	for (i = 0; i < cpuc->lbr_stack.nr; i++) {

@@ -963,6 +1011,9 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 			cpuc->lbr_entries[i].from = 0;
 			compress = true;
 		}
+
+		if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE)
+			cpuc->lbr_entries[i].type = common_branch_type(type);
 	}
 
 	if (!compress)

index 38fd115..e71fb5f 100644
@@ -28,6 +28,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
 	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
 	BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
+	BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
 	BRANCH_END
 };
 

index 2e5eff5..8cae8a6 100644
@@ -1105,83 +1105,67 @@ int callchain_branch_counts(struct callchain_root *root,
 						  cycles_count);
 }
 
+static int count_pri64_printf(int index, const char *str, u64 value,
+	char *bf, int bfsize)
+{
+	int printed;
+
+	printed = scnprintf(bf, bfsize,
+		"%s%s:%" PRId64 "",
+		(index) ? " " : " (", str, value);
+
+	return printed;
+}
+
+static int count_float_printf(int index, const char *str, float value,
+	char *bf, int bfsize)
+{
+	int printed;
+
+	printed = scnprintf(bf, bfsize,
+		"%s%s:%.1f%%",
+		(index) ? " " : " (", str, value);
+
+	return printed;
+}
+
 static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 samples_count)
 {
-	double predicted_percent = 0.0;
-	const char *null_str = "";
-	char iter_str[32];
-	char cycle_str[32];
-	char *istr, *cstr;
 	u64 cycles;
+	int printed = 0, i = 0;
 
 	if (branch_count == 0)
 		return scnprintf(bf, bfsize, " (calltrace)");
 
 	cycles = cycles_count / branch_count;
+	if (cycles)
+		printed += count_pri64_printf(i++, "cycles",
+				cycles,
+				bf + printed, bfsize - printed);
 
-	if (iter_count && samples_count) {
-		if (cycles > 0)
-			scnprintf(iter_str, sizeof(iter_str),
-				 " iterations:%" PRId64 "",
-				 iter_count / samples_count);
-		else
-			scnprintf(iter_str, sizeof(iter_str),
-				 "iterations:%" PRId64 "",
-				 iter_count / samples_count);
-		istr = iter_str;
-	} else
-		istr = (char *)null_str;
-
-	if (cycles > 0) {
-		scnprintf(cycle_str, sizeof(cycle_str),
-			  "cycles:%" PRId64 "", cycles);
-		cstr = cycle_str;
-	} else
-		cstr = (char *)null_str;
+	if (iter_count && samples_count)
+		printed += count_pri64_printf(i++, "iterations",
+				iter_count / samples_count,
+				bf + printed, bfsize - printed);
 
-	predicted_percent = predicted_count * 100.0 / branch_count;
+	if (predicted_count < branch_count)
+		printed += count_float_printf(i++, "predicted",
+				predicted_count * 100.0 / branch_count,
+				bf + printed, bfsize - printed);
 
-	if ((predicted_count == branch_count) && (abort_count == 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
-		else
-			return scnprintf(bf, bfsize, "%s", (char *)null_str);
-	}
-
-	if ((predicted_count < branch_count) && (abort_count == 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize,
-				" (predicted:%.1f%% %s%s)",
-				predicted_percent, cstr, istr);
-		else {
-			return scnprintf(bf, bfsize,
-				" (predicted:%.1f%%)",
-				predicted_percent);
-		}
-	}
-
-	if ((predicted_count == branch_count) && (abort_count > 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize,
-				" (abort:%" PRId64 " %s%s)",
-				abort_count, cstr, istr);
-		else
-			return scnprintf(bf, bfsize,
-				" (abort:%" PRId64 ")",
-				abort_count);
-	}
+	if (abort_count)
+		printed += count_float_printf(i++, "abort",
+				abort_count * 100.0 / branch_count,
+				bf + printed, bfsize - printed);
 
-	if ((cycles > 0) || (istr != (char *)null_str))
-		return scnprintf(bf, bfsize,
-			" (predicted:%.1f%% abort:%" PRId64 " %s%s)",
-			predicted_percent, abort_count, cstr, istr);
+	if (i)
+		return scnprintf(bf + printed, bfsize - printed, ")");
 
-	return scnprintf(bf, bfsize,
-			" (predicted:%.1f%% abort:%" PRId64 ")",
-			predicted_percent, abort_count);
+	bf[0] = 0;
+	return 0;
 }
 
 static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,

63 lines not on this page · raw message

new file mode 100644
index 0000000..26c8da6
@@ -0,0 +1,23 @@
+#ifndef _PERF_BRANCH_H
+#define _PERF_BRANCH_H 1
+
+#include <stdint.h>
+#include "../perf.h"
+
+struct branch_type_stat {
+	u64 counts[PERF_BR_MAX];
+	u64 jcc_fwd;
+	u64 jcc_bwd;
+	u64 cross_4k;
+	u64 cross_2m;
+};
+
+struct branch_flags;
+
+void branch_type_count(struct branch_type_stat *stat,
+		       struct branch_flags *flags,
+		       u64 from, u64 to);
+
+const char *branch_type_name(int type);
+
+#endif /* _PERF_BRANCH_H */

index eb7a7b2..26b4c2e 100644
@@ -142,7 +142,8 @@ struct branch_flags {
 	u64 in_tx:1;
 	u64 abort:1;
 	u64 cycles:16;
-	u64 reserved:44;
+	u64 type:4;
+	u64 reserved:40;
 };
 
 struct branch_entry {

index c18158b..0050b13 100644
@@ -38,6 +38,7 @@
 #include "arch/common.h"
 #include "util/time-utils.h"
 #include "util/auxtrace.h"
+#include "util/branch.h"
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>

@@ -66,6 +67,7 @@ struct report {
 	u64			queue_size;
 	int			socket_filter;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+	struct branch_type_stat	brtype_stat;
 };
 
 static int report__config(const char *var, const char *value, void *cb)

@@ -144,6 +146,22 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	return err;
 }
 
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al __maybe_unused,
+				      bool single __maybe_unused,
+				      void *arg)
+{
+	struct hist_entry *he = iter->he;
+	struct report *rep = arg;
+	struct branch_info *bi;
+
+	bi = he->branch_info;
+	branch_type_count(&rep->brtype_stat, &bi->flags,
+			  bi->from.addr, bi->to.addr);
+
+	return 0;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,

@@ -182,6 +200,8 @@ static int process_sample_event(struct perf_tool *tool,
 		 */
 		if (!sample->branch_stack)
 			goto out_put;
+
+		iter.add_entry_cb = hist_iter__branch_callback;
 		iter.ops = &hist_iter_branch;
 	} else if (rep->mem_mode) {
 		iter.ops = &hist_iter_mem;

@@ -369,6 +389,50 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	return ret + fprintf(fp, "\n#\n");
 }
 
+static void branch_type_stat_display(FILE *fp, struct branch_type_stat *stat)
+{
+	u64 total = 0;
+	int i;
+
+	for (i = 0; i < PERF_BR_MAX; i++)
+		total += stat->counts[i];
+
+	if (total == 0)
+		return;
+
+	fprintf(fp, "\n#");
+	fprintf(fp, "\n# Branch Statistics:");
+	fprintf(fp, "\n#");
+
+	if (stat->jcc_fwd > 0)
+		fprintf(fp, "\n%12s: %5.1f%%",
+			"JCC forward",
+			100.0 * (double)stat->jcc_fwd / (double)total);
+
+	if (stat->jcc_bwd > 0)
+		fprintf(fp, "\n%12s: %5.1f%%",
+			"JCC backward",
+			100.0 * (double)stat->jcc_bwd / (double)total);
+
+	if (stat->cross_4k > 0)
+		fprintf(fp, "\n%12s: %5.1f%%",
+			"CROSS_4K",
+			100.0 * (double)stat->cross_4k / (double)total);
+
+	if (stat->cross_2m > 0)
+		fprintf(fp, "\n%12s: %5.1f%%",
+			"CROSS_2M",
+			100.0 * (double)stat->cross_2m / (double)total);
+
+	for (i = 0; i < PERF_BR_MAX; i++) {
+		if (stat->counts[i] > 0)
+			fprintf(fp, "\n%12s: %5.1f%%",
+				branch_type_name(i),
+				100.0 *
+				(double)stat->counts[i] / (double)total);
+	}
+}
+
 static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 					 struct report *rep,
 					 const char *help)

@@ -404,6 +468,9 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		perf_read_values_destroy(&rep->show_threads_values);
 	}
 
+	if (sort__mode == SORT_MODE__BRANCH)
+		branch_type_stat_display(stdout, &rep->brtype_stat);
+
 	return 0;
 }
 

@@ -936,6 +1003,8 @@ int cmd_report(int argc, const char **argv)
 	if (has_br_stack && branch_call_mode)
 		symbol_conf.show_branchflag_count = true;
 
+	memset(&report.brtype_stat, 0, sizeof(struct branch_type_stat));
+
 	/*
 	 * Branch mode is a tristate:
 	 * -1 means default, so decide based on the file having branch data.

index 61bf304..c8aee25 100644
@@ -745,12 +745,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter,
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
 			     struct addr_location *al __maybe_unused)
 {
-	/* to avoid calling callback function */
-	iter->he = NULL;
-
 	return 0;
 }
 

index 8cae8a6..0cf17ae 100644
@@ -22,6 +22,7 @@
 #include "sort.h"
 #include "machine.h"
 #include "callchain.h"
+#include "branch.h"
 
 __thread struct callchain_cursor callchain_cursor;
 

@@ -467,6 +468,11 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 			call->cycles_count = cursor_node->branch_flags.cycles;
 			call->iter_count = cursor_node->nr_loop_iter;
 			call->samples_count = cursor_node->samples;
+
+			branch_type_count(&call->brtype_stat,
+					  &cursor_node->branch_flags,
+					  cursor_node->branch_from,
+					  cursor_node->ip);
 		}
 
 		list_add_tail(&call->list, &node->val);

@@ -579,6 +585,11 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->samples_count += node->samples;
+
+			branch_type_count(&cnode->brtype_stat,
+					  &node->branch_flags,
+					  node->branch_from,
+					  node->ip);
 		}
 
 		return MATCH_EQ;

@@ -813,7 +824,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 	list_for_each_entry_safe(list, next_list, &src->val, list) {
 		callchain_cursor_append(cursor, list->ip,
 					list->ms.map, list->ms.sym,
-					false, NULL, 0, 0);
+					false, NULL, 0, 0, 0);
 		list_del(&list->list);
 		map__zput(list->ms.map);
 		free(list);

@@ -853,7 +864,7 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
 			    u64 ip, struct map *map, struct symbol *sym,
 			    bool branch, struct branch_flags *flags,
-			    int nr_loop_iter, int samples)
+			    int nr_loop_iter, int samples, u64 branch_from)
 {
 	struct callchain_cursor_node *node = *cursor->last;
 

@@ -877,6 +888,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 		memcpy(&node->branch_flags, flags,
 			sizeof(struct branch_flags));
 
+	node->branch_from = branch_from;
 	cursor->nr++;
 
 	cursor->last = &node->next;

@@ -1129,10 +1141,63 @@ static int count_float_printf(int index, const char *str, float value,
 	return printed;
 }
 
+static int count_str_printf(int index, const char *str,
+	char *bf, int bfsize)
+{
+	int printed;
+
+	printed = scnprintf(bf, bfsize,
+		"%s%s",
+		(index) ? " " : " (", str);
+
+	return printed;
+}
+
+static int branch_type_str(struct branch_type_stat *stat,
+			   char *bf, int bfsize)
+{
+	int i, j = 0, printed = 0;
+	u64 total = 0;
+
+	for (i = 0; i < PERF_BR_MAX; i++)
+		total += stat->counts[i];
+
+	if (total == 0)
+		return 0;
+
+	if (stat->jcc_fwd > 0)
+		printed += count_str_printf(j++, "JCC forward",
+				bf + printed, bfsize - printed);
+
+	if (stat->jcc_bwd > 0)
+		printed += count_str_printf(j++, "JCC backward",
+				bf + printed, bfsize - printed);
+
+	for (i = 0; i < PERF_BR_MAX; i++) {
+		if (i == PERF_BR_JCC)
+			continue;
+
+		if (stat->counts[i] > 0)
+			printed += count_str_printf(j++, branch_type_name(i),
+					bf + printed, bfsize - printed);
+	}
+
+	if (stat->cross_4k > 0)
+		printed += count_str_printf(j++, "CROSS_4K",
+				bf + printed, bfsize - printed);
+
+	if (stat->cross_2m > 0)
+		printed += count_str_printf(j++, "CROSS_2M",
+				bf + printed, bfsize - printed);
+
+	return printed;
+}
+
 static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
-			     u64 iter_count, u64 samples_count)
+			     u64 iter_count, u64 samples_count,
+			     struct branch_type_stat *brtype_stat)
 {
 	u64 cycles;
 	int printed = 0, i = 0;

@@ -1140,6 +1205,10 @@ static int counts_str_build(char *bf, int bfsize,
 	if (branch_count == 0)
 		return scnprintf(bf, bfsize, " (calltrace)");
 
+	printed = branch_type_str(brtype_stat, bf, bfsize);
+	if (printed)
+		i++;
+
 	cycles = cycles_count / branch_count;
 	if (cycles)
 		printed += count_pri64_printf(i++, "cycles",

@@ -1171,13 +1240,14 @@ static int counts_str_build(char *bf, int bfsize,
 static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
-				   u64 iter_count, u64 samples_count)
+				   u64 iter_count, u64 samples_count,
+				   struct branch_type_stat *brtype_stat)
 {
-	char str[128];
+	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, samples_count);
+			 iter_count, samples_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);

@@ -1209,7 +1279,8 @@ int callchain_list_counts__printf_value(struct callchain_node *node,
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
-				       cycles_count, iter_count, samples_count);
+				       cycles_count, iter_count, samples_count,
+				       &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)

@@ -1334,7 +1405,8 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
 		rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
 					     node->branch, &node->branch_flags,
-					     node->nr_loop_iter, node->samples);
+					     node->nr_loop_iter, node->samples,
+					     node->branch_from);
 		if (rc)
 			break;
 

index c56c23d..9773820 100644
@@ -7,6 +7,7 @@
 #include "event.h"
 #include "map.h"
 #include "symbol.h"
+#include "branch.h"
 
 #define HELP_PAD "\t\t\t\t"
 

@@ -119,6 +120,7 @@ struct callchain_list {
 	u64			cycles_count;
 	u64			iter_count;
 	u64			samples_count;
+	struct branch_type_stat brtype_stat;
 	char		       *srcline;
 	struct list_head	list;
 };

@@ -135,6 +137,7 @@ struct callchain_cursor_node {
 	struct symbol			*sym;
 	bool				branch;
 	struct branch_flags		branch_flags;
+	u64				branch_from;
 	int				nr_loop_iter;
 	int				samples;
 	struct callchain_cursor_node	*next;

@@ -198,7 +201,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
 			    struct map *map, struct symbol *sym,
 			    bool branch, struct branch_flags *flags,
-			    int nr_loop_iter, int samples);
+			    int nr_loop_iter, int samples, u64 branch_from);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)

index dfc6004..2309614 100644
@@ -1673,7 +1673,8 @@ static int add_callchain_ip(struct thread *thread,
 			    bool branch,
 			    struct branch_flags *flags,
 			    int nr_loop_iter,
-			    int samples)
+			    int samples,
+			    u64 branch_from)
 {
 	struct addr_location al;
 

@@ -1726,7 +1727,8 @@ static int add_callchain_ip(struct thread *thread,
 	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		return 0;
 	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
-				       branch, flags, nr_loop_iter, samples);
+				       branch, flags, nr_loop_iter, samples,
+				       branch_from);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,

@@ -1805,7 +1807,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = min(max_stack, (int)chain->nr), i;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	u64 ip;
+	u64 ip, branch_from = 0;
 
 	for (i = 0; i < chain_nr; i++) {
 		if (chain->ips[i] == PERF_CONTEXT_USER)

@@ -1847,6 +1849,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = lbr_stack->entries[0].to;
 					branch = true;
 					flags = &lbr_stack->entries[0].flags;
+					branch_from =
+						lbr_stack->entries[0].from;
 				}
 			} else {
 				if (j < lbr_nr) {

@@ -1861,12 +1865,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = lbr_stack->entries[0].to;
 					branch = true;
 					flags = &lbr_stack->entries[0].flags;
+					branch_from =
+						lbr_stack->entries[0].from;
 				}
 			}
 
 			err = add_callchain_ip(thread, cursor, parent,
 					       root_al, &cpumode, ip,
-					       branch, flags, 0, 0);
+					       branch, flags, 0, 0,
+					       branch_from);
 			if (err)
 				return (err < 0) ? err : 0;
 		}

@@ -1965,19 +1972,20 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 						       root_al,
 						       NULL, be[i].to,
 						       true, &be[i].flags,
-						       nr_loop_iter, 1);
+						       nr_loop_iter, 1,
+						       be[i].from);
 			else
 				err = add_callchain_ip(thread, cursor, parent,
 						       root_al,
 						       NULL, be[i].to,
 						       true, &be[i].flags,
-						       0, 0);
+						       0, 0, be[i].from);
 
 			if (!err)
 				err = add_callchain_ip(thread, cursor, parent, root_al,
 						       NULL, be[i].from,
 						       true, &be[i].flags,
-						       0, 0);
+						       0, 0, 0);
 			if (err == -EINVAL)
 				break;
 			if (err)

@@ -2007,7 +2015,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
-				       false, NULL, 0, 0);
+				       false, NULL, 0, 0, 0);
 
 		if (err)
 			return (err < 0) ? err : 0;

@@ -2024,7 +2032,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 		return 0;
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
-				       false, NULL, 0, 0);
+				       false, NULL, 0, 0, 0);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,