perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK

This patch adds:

 - ability to parse samples with PERF_SAMPLE_BRANCH_STACK
 - sort on branches (dso_from, symbol_from, dso_to, symbol_to, mispredict)
 - build histograms on branches
Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: acme@redhat.com
Cc: robert.richter@amd.com
Cc: ming.m.lin@intel.com
Cc: andi@firstfloor.org
Cc: asharma@fb.com
Cc: vweaver1@eecs.utk.edu
Cc: khandual@linux.vnet.ibm.com
Cc: dsahern@gmail.com
Link: http://lkml.kernel.org/r/1328826068-11713-12-git-send-email-eranian@google.comSigned-off-by: Ingo Molnar <mingo@elte.hu>

tools/perf/perf.h

@@ -179,6 +179,23 @@ struct ip_callchain {
 	u64 ips[0];
 };
 
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 reserved:62;
+};
+
+struct branch_entry {
+	u64				from;
+	u64				to;
+	struct branch_flags flags;
+};
+
+struct branch_stack {
+	u64				nr;
+	struct branch_entry	entries[0];
+};
+
 extern bool perf_host, perf_guest;
 extern const char perf_version_string[];
 

tools/perf/util/event.h

@@ -81,6 +81,7 @@ struct perf_sample {
 	u32 raw_size;
 	void *raw_data;
 	struct ip_callchain *callchain;
+	struct branch_stack *branch_stack;
 };
 
 #define BUILD_ID_SIZE 20

tools/perf/util/evsel.c

@@ -576,6 +576,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 		data->raw_data = (void *) pdata;
 	}
 
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 sz;
+
+		data->branch_stack = (struct branch_stack *)array;
+		array++; /* nr */
+
+		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		sz /= sizeof(u64);
+		array += sz;
+	}
 	return 0;
 }
 

tools/perf/util/hist.c

@@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists)
 		hists__set_col_len(hists, col, 0);
 }
 
-static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
+static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
 {
-	u16 len;
-
-	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
-	else {
 	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
 
-		if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
+	if (hists__col_len(hists, dso) < unresolved_col_width &&
 	    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
 	    !symbol_conf.dso_list)
-			hists__set_col_len(hists, HISTC_DSO,
-					   unresolved_col_width);
-	}
+		hists__set_col_len(hists, dso, unresolved_col_width);
+}
+
+static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+	u16 len;
+
+	if (h->ms.sym)
+		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+	else
+		hists__set_unres_dso_col_len(hists, HISTC_DSO);
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		len = dso__name_len(h->ms.map->dso);
 		hists__new_col_len(hists, HISTC_DSO, len);
 	}
+
+	if (h->branch_info) {
+		int symlen;
+		/*
+		 * +4 accounts for '[x] ' priv level info
+		 * +2 account of 0x prefix on raw addresses
+		 */
+		if (h->branch_info->from.sym) {
+			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+
+			symlen = dso__name_len(h->branch_info->from.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
+		}
+
+		if (h->branch_info->to.sym) {
+			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+
+			symlen = dso__name_len(h->branch_info->to.map->dso);
+			hists__new_col_len(hists, HISTC_DSO_TO, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
+		}
+	}
 }
 
 static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
+static struct hist_entry *add_hist_entry(struct hists *hists,
+				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      u64 period)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= al->map,
-			.sym	= al->sym,
-		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
-		.period	= period,
-		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-	};
 	int cmp;
 
 	pthread_mutex_lock(&hists->lock);
@@ -225,7 +248,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		parent = *p;
 		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(&entry, he);
+		cmp = hist_entry__cmp(entry, he);
 
 		if (!cmp) {
 			he->period += period;
@@ -239,7 +262,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(&entry);
+	he = hist_entry__new(entry);
 	if (!he)
 		goto out_unlock;
 
@@ -252,6 +275,51 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 	return he;
 }
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= bi->to.map,
+			.sym	= bi->to.sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= bi->to.addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+		.branch_info = bi,
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *sym_parent, u64 period)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
+		.cpu	= al->cpu,
+		.ip	= al->addr,
+		.level	= al->level,
+		.period	= period,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+	};
+
+	return add_hist_entry(self, &entry, al, period);
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {

tools/perf/util/hist.h

@@ -42,6 +42,11 @@ enum hist_column {
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_MISPREDICT,
+	HISTC_SYMBOL_FROM,
+	HISTC_SYMBOL_TO,
+	HISTC_DSO_FROM,
+	HISTC_DSO_TO,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -74,6 +79,12 @@ int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
 			 struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+					     struct addr_location *al,
+					     struct symbol *sym_parent,
+					     struct branch_info *bi,
+					     u64 period);
+
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);

tools/perf/util/session.c

@@ -229,6 +229,63 @@ static bool symbol__match_parent_regex(struct symbol *sym)
 	return 0;
 }
 
+static const u8 cpumodes[] = {
+	PERF_RECORD_MISC_USER,
+	PERF_RECORD_MISC_KERNEL,
+	PERF_RECORD_MISC_GUEST_USER,
+	PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *self, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+	size_t i;
+	u8 m;
+
+	memset(&al, 0, sizeof(al));
+
+	for (i = 0; i < NCPUMODES; i++) {
+		m = cpumodes[i];
+		/*
+		 * We cannot use the header.misc hint to determine whether a
+		 * branch stack address is user, kernel, guest, hypervisor.
+		 * Branches may straddle the kernel/user/hypervisor boundaries.
+		 * Thus, we have to try consecutively until we find a match
+		 * or else, the symbol is unknown
+		 */
+		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
+				ip, &al, NULL);
+		if (al.sym)
+			goto found;
+	}
+found:
+	ams->addr = ip;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thr,
+					    struct branch_stack *bs)
+{
+	struct branch_info *bi;
+	unsigned int i;
+
+	bi = calloc(bs->nr, sizeof(struct branch_info));
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
 int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct ip_callchain *chain,
@@ -697,6 +754,18 @@ static void callchain__printf(struct perf_sample *sample)
 		       i, sample->callchain->ips[i]);
 }
 
+static void branch_stack__printf(struct perf_sample *sample)
+{
+	uint64_t i;
+
+	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+
+	for (i = 0; i < sample->branch_stack->nr; i++)
+		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
+			i, sample->branch_stack->entries[i].from,
+			sample->branch_stack->entries[i].to);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
@@ -744,6 +813,9 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 
 	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
+
+	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample);
 }
 
 static struct machine *

tools/perf/util/session.h

@@ -73,6 +73,10 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel
 				    struct ip_callchain *chain,
 				    struct symbol **parent);
 
+struct branch_info *machine__resolve_bstack(struct machine *self,
+					    struct thread *thread,
+					    struct branch_stack *bs);
+
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);

tools/perf/util/sort.h

@@ -31,11 +31,14 @@ extern const char *parent_pattern;
 extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
+extern bool sort__branch_mode;
 extern char *field_sep;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
 extern struct sort_entry sort_parent;
+extern struct sort_entry sort_lbr_dso;
+extern struct sort_entry sort_lbr_sym;
 extern enum sort_type sort__first_dimension;
 
 /**
@@ -72,6 +75,7 @@ struct hist_entry {
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct branch_info	*branch_info;
 	struct callchain_root	callchain[0];
 };
 
@@ -82,6 +86,11 @@ enum sort_type {
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
+	SORT_DSO_FROM,
+	SORT_DSO_TO,
+	SORT_SYM_FROM,
+	SORT_SYM_TO,
+	SORT_MISPREDICT,
 };
 
 /*

tools/perf/util/symbol.h

@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include "map.h"
+#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
@@ -120,6 +121,18 @@ struct map_symbol {
 	bool	      has_children;
 };
 
+struct addr_map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+};
+
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags flags;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;