7 files changed, 169 insertions, 144 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8ba03d6e5398..cfa8e513d0fb 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -80,15 +80,24 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min]::
+-g [type,min,order]::
 --call-graph::
-        Display call chains using type and min percent threshold.
+        Display call chains using type, min percent threshold and order.
 	type can be either:
 	- flat: single column, linear exposure of call chains.
 	- graph: use a graph tree, displaying absolute overhead rates.
 	- fractal: like graph, but displays relative rates. Each branch of
 		 the tree is considered as a new profiled object. +
-	Default: fractal,0.5.
+
+	order can be either:
+	- callee: callee based call graph.
+	- caller: inverted caller based call graph.
+
+	Default: fractal,0.5,callee.
+
+-G::
+--inverted::
+        alias for inverted caller based call graph.
 
 --pretty=<key>::
         Pretty printing style.  key: normal, raw
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 287a173523a7..5d43d0181d63 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -45,7 +45,8 @@ static struct perf_read_values	show_threads_values;
 static const char	default_pretty_printing_style[] = "normal";
 static const char	*pretty_printing_style = default_pretty_printing_style;
 
-static char		callchain_default_opt[] = "fractal,0.5";
+static char		callchain_default_opt[] = "fractal,0.5,callee";
+static bool		inverted_callchain;
 static symbol_filter_t	annotate_init;
 
 static int perf_session__add_hist_entry(struct perf_session *session,
@@ -386,13 +387,29 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	if (!tok)
 		goto setup;
 
-	tok2 = strtok(NULL, ",");
 	callchain_param.min_percent = strtod(tok, &endptr);
 	if (tok == endptr)
 		return -1;
 
-	if (tok2)
+	/* get the print limit */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+
+	if (tok2[0] != 'c') {
 		callchain_param.print_limit = strtod(tok2, &endptr);
+		tok2 = strtok(NULL, ",");
+		if (!tok2)
+			goto setup;
+	}
+
+	/* get the call chain order */
+	if (!strcmp(tok2, "caller"))
+		callchain_param.order = ORDER_CALLER;
+	else if (!strcmp(tok2, "callee"))
+		callchain_param.order = ORDER_CALLEE;
+	else
+		return -1;
 setup:
 	if (callchain_register_param(&callchain_param) < 0) {
 		fprintf(stderr, "Can't register callchain params\n");
@@ -436,9 +453,10 @@ static const struct option options[] = {
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
-		     "Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
-		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent, call_order",
+		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold and callchain order. "
+		     "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN('G', "inverted", &inverted_callchain, "alias for inverted call graph"),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
 	OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
@@ -467,6 +485,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	else if (use_tui)
 		use_browser = 1;
 
+	if (inverted_callchain)
+		callchain_param.order = ORDER_CALLER;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else
@@ -504,7 +525,14 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
 			return -1;
-		sort_parent.elide = 1;
+
+		/*
+		 * Only show the parent fields if we explicitly
+		 * sort that way. If we only use parent machinery
+		 * for filtering, we don't want it.
+		 */
+		if (!strstr(sort_order, "parent"))
+			sort_parent.elide = 1;
 	} else
 		symbol_conf.exclude_other = false;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1a79df9f739f..9b4ff16cac96 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -14,6 +14,11 @@ enum chain_mode {
 	CHAIN_GRAPH_REL
 };
 
+enum chain_order {
+	ORDER_CALLER,
+	ORDER_CALLEE
+};
+
 struct callchain_node {
 	struct callchain_node	*parent;
 	struct list_head	siblings;
@@ -41,6 +46,7 @@ struct callchain_param {
 	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
+	enum chain_order	order;
 };
 
 struct callchain_list {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 627a02e03c57..677e1da6bb3e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -14,7 +14,8 @@ enum hist_filter {
 
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
-	.min_percent = 0.5
+	.min_percent = 0.5,
+	.order  = ORDER_CALLEE
 };
 
 u16 hists__col_len(struct hists *self, enum hist_column col)
@@ -846,6 +847,9 @@ print_entries:
 	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
+		if (h->filtered)
+			continue;
+
 		if (show_displacement) {
 			if (h->pair != NULL)
 				displacement = ((long)h->pair->position -
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b723f211881c..558bcf996949 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -247,9 +247,14 @@ int perf_session__resolve_callchain(struct perf_session *self,
 	callchain_cursor_reset(&self->callchain_cursor);
 
 	for (i = 0; i < chain->nr; i++) {
-		u64 ip = chain->ips[i];
+		u64 ip;
 		struct addr_location al;
 
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
 			case PERF_CONTEXT_HV:
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f44fa541d56e..401e220566fd 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -15,95 +15,6 @@ char * field_sep;
 
 LIST_HEAD(hist_entry__sort_list);
 
-static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width);
-static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
-				     size_t size, unsigned int width);
-static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width);
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width);
-static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width);
-static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width);
-
-struct sort_entry sort_thread = {
-	.se_header	= "Command:  Pid",
-	.se_cmp		= sort__thread_cmp,
-	.se_snprintf	= hist_entry__thread_snprintf,
-	.se_width_idx	= HISTC_THREAD,
-};
-
-struct sort_entry sort_comm = {
-	.se_header	= "Command",
-	.se_cmp		= sort__comm_cmp,
-	.se_collapse	= sort__comm_collapse,
-	.se_snprintf	= hist_entry__comm_snprintf,
-	.se_width_idx	= HISTC_COMM,
-};
-
-struct sort_entry sort_dso = {
-	.se_header	= "Shared Object",
-	.se_cmp		= sort__dso_cmp,
-	.se_snprintf	= hist_entry__dso_snprintf,
-	.se_width_idx	= HISTC_DSO,
-};
-
-struct sort_entry sort_sym = {
-	.se_header	= "Symbol",
-	.se_cmp		= sort__sym_cmp,
-	.se_snprintf	= hist_entry__sym_snprintf,
-	.se_width_idx	= HISTC_SYMBOL,
-};
-
-struct sort_entry sort_parent = {
-	.se_header	= "Parent symbol",
-	.se_cmp		= sort__parent_cmp,
-	.se_snprintf	= hist_entry__parent_snprintf,
-	.se_width_idx	= HISTC_PARENT,
-};
- 
-struct sort_entry sort_cpu = {
-	.se_header      = "CPU",
-	.se_cmp	        = sort__cpu_cmp,
-	.se_snprintf    = hist_entry__cpu_snprintf,
-	.se_width_idx	= HISTC_CPU,
-};
-
-struct sort_dimension {
-	const char		*name;
-	struct sort_entry	*entry;
-	int			taken;
-};
-
-static struct sort_dimension sort_dimensions[] = {
-	{ .name = "pid",	.entry = &sort_thread,	},
-	{ .name = "comm",	.entry = &sort_comm,	},
-	{ .name = "dso",	.entry = &sort_dso,	},
-	{ .name = "symbol",	.entry = &sort_sym,	},
-	{ .name = "parent",	.entry = &sort_parent,	},
-	{ .name = "cpu",	.entry = &sort_cpu,	},
-};
-
-int64_t cmp_null(void *l, void *r)
-{
-	if (!l && !r)
-		return 0;
-	else if (!l)
-		return -1;
-	else
-		return 1;
-}
-
-/* --sort pid */
-
-int64_t
-sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	return right->thread->pid - left->thread->pid;
-}
-
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
@@ -125,6 +36,24 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 	return n;
 }
 
+static int64_t cmp_null(void *l, void *r)
+{
+	if (!l && !r)
+		return 0;
+	else if (!l)
+		return -1;
+	else
+		return 1;
+}
+
+/* --sort pid */
+
+static int64_t
+sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
 static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
 				       size_t size, unsigned int width)
 {
@@ -132,15 +61,50 @@ static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
 			      self->thread->comm ?: "", self->thread->pid);
 }
 
+struct sort_entry sort_thread = {
+	.se_header	= "Command:  Pid",
+	.se_cmp		= sort__thread_cmp,
+	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_width_idx	= HISTC_THREAD,
+};
+
+/* --sort comm */
+
+static int64_t
+sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
+static int64_t
+sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	char *comm_l = left->thread->comm;
+	char *comm_r = right->thread->comm;
+
+	if (!comm_l || !comm_r)
+		return cmp_null(comm_l, comm_r);
+
+	return strcmp(comm_l, comm_r);
+}
+
 static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
 				     size_t size, unsigned int width)
 {
 	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
+struct sort_entry sort_comm = {
+	.se_header	= "Command",
+	.se_cmp		= sort__comm_cmp,
+	.se_collapse	= sort__comm_collapse,
+	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_width_idx	= HISTC_COMM,
+};
+
 /* --sort dso */
 
-int64_t
+static int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
@@ -173,9 +137,16 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
+struct sort_entry sort_dso = {
+	.se_header	= "Shared Object",
+	.se_cmp		= sort__dso_cmp,
+	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_width_idx	= HISTC_DSO,
+};
+
 /* --sort symbol */
 
-int64_t
+static int64_t
 sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
@@ -211,29 +182,16 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 	return ret;
 }
 
-/* --sort comm */
-
-int64_t
-sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	return right->thread->pid - left->thread->pid;
-}
-
-int64_t
-sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
-{
-	char *comm_l = left->thread->comm;
-	char *comm_r = right->thread->comm;
-
-	if (!comm_l || !comm_r)
-		return cmp_null(comm_l, comm_r);
-
-	return strcmp(comm_l, comm_r);
-}
+struct sort_entry sort_sym = {
+	.se_header	= "Symbol",
+	.se_cmp		= sort__sym_cmp,
+	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_width_idx	= HISTC_SYMBOL,
+};
 
 /* --sort parent */
 
-int64_t
+static int64_t
 sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	struct symbol *sym_l = left->parent;
@@ -252,9 +210,16 @@ static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
 			      self->parent ? self->parent->name : "[other]");
 }
 
+struct sort_entry sort_parent = {
+	.se_header	= "Parent symbol",
+	.se_cmp		= sort__parent_cmp,
+	.se_snprintf	= hist_entry__parent_snprintf,
+	.se_width_idx	= HISTC_PARENT,
+};
+
 /* --sort cpu */
 
-int64_t
+static int64_t
 sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	return right->cpu - left->cpu;
@@ -266,6 +231,28 @@ static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
 	return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
 }
 
+struct sort_entry sort_cpu = {
+	.se_header      = "CPU",
+	.se_cmp	        = sort__cpu_cmp,
+	.se_snprintf    = hist_entry__cpu_snprintf,
+	.se_width_idx	= HISTC_CPU,
+};
+
+struct sort_dimension {
+	const char		*name;
+	struct sort_entry	*entry;
+	int			taken;
+};
+
+static struct sort_dimension sort_dimensions[] = {
+	{ .name = "pid",	.entry = &sort_thread,	},
+	{ .name = "comm",	.entry = &sort_comm,	},
+	{ .name = "dso",	.entry = &sort_dso,	},
+	{ .name = "symbol",	.entry = &sort_sym,	},
+	{ .name = "parent",	.entry = &sort_parent,	},
+	{ .name = "cpu",	.entry = &sort_cpu,	},
+};
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
@@ -273,15 +260,9 @@ int sort_dimension__add(const char *tok)
 	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
 		struct sort_dimension *sd = &sort_dimensions[i];
 
-		if (sd->taken)
-			continue;
-
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sd->entry->se_collapse)
-			sort__need_collapse = 1;
-
 		if (sd->entry == &sort_parent) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
@@ -294,6 +275,12 @@ int sort_dimension__add(const char *tok)
 			sort__has_parent = 1;
 		}
 
+		if (sd->taken)
+			return 0;
+
+		if (sd->entry->se_collapse)
+			sort__need_collapse = 1;
+
 		if (list_empty(&hist_entry__sort_list)) {
 			if (!strcmp(sd->name, "pid"))
 				sort__first_dimension = SORT_PID;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 0b91053a7d11..77d0388ad415 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -103,20 +103,6 @@ extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
 void setup_sorting(const char * const usagestr[], const struct option *opts);
-
-extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used);
-extern int64_t cmp_null(void *, void *);
-extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
-int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right);
-extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
 extern int sort_dimension__add(const char *);
 void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
 			     const char *list_name, FILE *fp);