Merge tag 'perf-core-for-mingo-4.15-20171025' of...

Merge tag 'perf-core-for-mingo-4.15-20171025' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core inline improvements from Arnaldo Carvalho de Melo:

From Milian's cover letter: (Milian Wolff)

"This series of patches completely reworks the way inline frames are
 handled.  Instead of querying for the inline nodes on-demand in the
 individual tools, we now create proper callchain nodes for inlined
 frames. The advantages this approach brings are numerous:

 - Less duplicated code in the individual browser

 - Aggregated cost for inlined frames for the --children top-down list

 - Various bug fixes that arose from querying for a srcline/symbol based on
   the IP of a sample, which will always point to the last inlined frame
   instead of the corresponding non-inlined frame

 - Overall much better support for visualizing cost for heavily-inlined C++
   code, which simply was confusing and unreliably before

 - srcline honors the global setting as to whether full paths or basenames
   should be shown

 - Caches for inlined frames and srcline information, which allow us to
   enable inline frame handling by default"
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/Documentation/perf-report.txt

@@ -434,7 +434,8 @@ include::itrace.txt[]
 
 --inline::
 	If a callgraph address belongs to an inlined function, the inline stack
-	will be printed. Each entry is function name or file/line.
+	will be printed. Each entry is function name or file/line. Enabled by
+	default, disable with --no-inline.
 
 include::callchain-overhead-calculation.txt[]
 

tools/perf/Documentation/perf-script.txt

@@ -327,7 +327,8 @@ include::itrace.txt[]
 
 --inline::
 	If a callgraph address belongs to an inlined function, the inline stack
-	will be printed. Each entry has function name and file/line.
+	will be printed. Each entry has function name and file/line. Enabled by
+	default, disable with --no-inline.
 
 SEE ALSO
 --------

tools/perf/ui/browsers/hists.c

@@ -154,57 +154,9 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
 	cl->unfolded = unfold ? cl->has_children : false;
 }
 
-static struct inline_node *inline_node__create(struct map *map, u64 ip)
-{
-	struct dso *dso;
-	struct inline_node *node;
-
-	if (map == NULL)
-		return NULL;
-
-	dso = map->dso;
-	if (dso == NULL)
-		return NULL;
-
-	node = dso__parse_addr_inlines(dso,
-				       map__rip_2objdump(map, ip));
-
-	return node;
-}
-
-static int inline__count_rows(struct inline_node *node)
-{
-	struct inline_list *ilist;
-	int i = 0;
-
-	if (node == NULL)
-		return 0;
-
-	list_for_each_entry(ilist, &node->val, list) {
-		if ((ilist->filename != NULL) || (ilist->funcname != NULL))
-			i++;
-	}
-
-	return i;
-}
-
-static int callchain_list__inline_rows(struct callchain_list *chain)
-{
-	struct inline_node *node;
-	int rows;
-
-	node = inline_node__create(chain->ms.map, chain->ip);
-	if (node == NULL)
-		return 0;
-
-	rows = inline__count_rows(node);
-	inline_node__delete(node);
-	return rows;
-}
-
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-	int n = 0, inline_rows;
+	int n = 0;
 	struct rb_node *nd;
 
 	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -215,12 +167,6 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 		list_for_each_entry(chain, &child->val, list) {
 			++n;
 
-			if (symbol_conf.inline_name) {
-				inline_rows =
-					callchain_list__inline_rows(chain);
-				n += inline_rows;
-			}
-
 			/* We need this because we may not have children */
 			folded_sign = callchain_list__folded(chain);
 			if (folded_sign == '+')
@@ -272,7 +218,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 	bool unfolded = false;
-	int n = 0, inline_rows;
+	int n = 0;
 
 	if (callchain_param.mode == CHAIN_FLAT)
 		return callchain_node__count_flat_rows(node);
@@ -281,10 +227,6 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
-		if (symbol_conf.inline_name) {
-			inline_rows = callchain_list__inline_rows(chain);
-			n += inline_rows;
-		}
 
 		unfolded = chain->unfolded;
 	}
@@ -432,19 +374,6 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 	he->init_have_children = true;
 }
 
-static void hist_entry_init_inline_node(struct hist_entry *he)
-{
-	if (he->inline_node)
-		return;
-
-	he->inline_node = inline_node__create(he->ms.map, he->ip);
-
-	if (he->inline_node == NULL)
-		return;
-
-	he->has_children = true;
-}
-
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -476,12 +405,8 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
 		if (he->unfolded) {
 			if (he->leaf)
-				if (he->inline_node)
-					he->nr_rows = inline__count_rows(
-							he->inline_node);
-				else
-					he->nr_rows = callchain__count_rows(
-							&he->sorted_chain);
+				he->nr_rows = callchain__count_rows(
+						&he->sorted_chain);
 			else
 				he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -841,71 +766,6 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_inline(struct hist_browser *browser,
-				     struct inline_node *node,
-				     unsigned short row,
-				     int offset)
-{
-	struct inline_list *ilist;
-	char buf[1024];
-	int color, width, first_row;
-
-	first_row = row;
-	width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
-	list_for_each_entry(ilist, &node->val, list) {
-		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-			color = HE_COLORSET_NORMAL;
-			if (ui_browser__is_current_entry(&browser->b, row))
-				color = HE_COLORSET_SELECTED;
-
-			if (callchain_param.key == CCKEY_ADDRESS ||
-			    callchain_param.key == CCKEY_SRCLINE) {
-				if (ilist->filename != NULL)
-					scnprintf(buf, sizeof(buf),
-						  "%s:%d (inline)",
-						  ilist->filename,
-						  ilist->line_nr);
-				else
-					scnprintf(buf, sizeof(buf), "??");
-			} else if (ilist->funcname != NULL)
-				scnprintf(buf, sizeof(buf), "%s (inline)",
-					  ilist->funcname);
-			else if (ilist->filename != NULL)
-				scnprintf(buf, sizeof(buf),
-					  "%s:%d (inline)",
-					  ilist->filename,
-					  ilist->line_nr);
-			else
-				scnprintf(buf, sizeof(buf), "??");
-
-			ui_browser__set_color(&browser->b, color);
-			hist_browser__gotorc(browser, row, 0);
-			ui_browser__write_nstring(&browser->b, " ",
-				LEVEL_OFFSET_STEP + offset);
-			ui_browser__write_nstring(&browser->b, buf, width);
-			row++;
-		}
-	}
-
-	return row - first_row;
-}
-
-static size_t show_inline_list(struct hist_browser *browser, struct map *map,
-			       u64 ip, int row, int offset)
-{
-	struct inline_node *node;
-	int ret;
-
-	node = inline_node__create(map, ip);
-	if (node == NULL)
-		return 0;
-
-	ret = hist_browser__show_inline(browser, node, row, offset);
-
-	inline_node__delete(node);
-	return ret;
-}
-
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
 					     struct callchain_node *node,
 					     struct callchain_list *chain,
@@ -917,7 +777,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	char bf[1024], *alloc_str;
 	char buf[64], *alloc_str2;
 	const char *str;
-	int inline_rows = 0, ret = 1;
+	int ret = 1;
 
 	if (arg->row_offset != 0) {
 		arg->row_offset--;
@@ -954,12 +814,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	free(alloc_str);
 	free(alloc_str2);
 
-	if (symbol_conf.inline_name) {
-		inline_rows = show_inline_list(browser, chain->ms.map,
-					       chain->ip, row + 1, offset);
-	}
-
-	return ret + inline_rows;
+	return ret;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1383,12 +1238,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		folded_sign = hist_entry__folded(entry);
 	}
 
-	if (symbol_conf.inline_name &&
-	    (!entry->has_children)) {
-		hist_entry_init_inline_node(entry);
-		folded_sign = hist_entry__folded(entry);
-	}
-
 	if (row_offset == 0) {
 		struct hpp_arg arg = {
 			.b		= &browser->b,
@@ -1420,8 +1269,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (first) {
-				if (symbol_conf.use_callchain ||
-					symbol_conf.inline_name) {
+				if (symbol_conf.use_callchain) {
 					ui_browser__printf(&browser->b, "%c ", folded_sign);
 					width -= 2;
 				}
@@ -1463,15 +1311,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
-		if (entry->inline_node)
-			printed += hist_browser__show_inline(browser,
-					entry->inline_node, row, 0);
-		else
-			printed += hist_browser__show_callchain(browser,
-					entry, 1, row,
-					hist_browser__show_callchain_entry,
-					&arg,
-					hist_browser__check_output_full);
+		printed += hist_browser__show_callchain(browser,
+				entry, 1, row,
+				hist_browser__show_callchain_entry,
+				&arg,
+				hist_browser__check_output_full);
 	}
 
 	return printed;

tools/perf/ui/stdio/hist.c

@@ -21,64 +21,6 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 	return ret;
 }
 
-static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
-			      int depth, int depth_mask, FILE *fp)
-{
-	struct dso *dso;
-	struct inline_node *node;
-	struct inline_list *ilist;
-	int ret = 0, i;
-
-	if (map == NULL)
-		return 0;
-
-	dso = map->dso;
-	if (dso == NULL)
-		return 0;
-
-	node = dso__parse_addr_inlines(dso,
-				       map__rip_2objdump(map, ip));
-	if (node == NULL)
-		return 0;
-
-	list_for_each_entry(ilist, &node->val, list) {
-		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-
-			for (i = 0; i < depth; i++) {
-				if (depth_mask & (1 << i))
-					ret += fprintf(fp, "|");
-				else
-					ret += fprintf(fp, " ");
-				ret += fprintf(fp, "          ");
-			}
-
-			if (callchain_param.key == CCKEY_ADDRESS ||
-			    callchain_param.key == CCKEY_SRCLINE) {
-				if (ilist->filename != NULL)
-					ret += fprintf(fp, "%s:%d (inline)",
-						       ilist->filename,
-						       ilist->line_nr);
-				else
-					ret += fprintf(fp, "??");
-			} else if (ilist->funcname != NULL)
-				ret += fprintf(fp, "%s (inline)",
-					       ilist->funcname);
-			else if (ilist->filename != NULL)
-				ret += fprintf(fp, "%s:%d (inline)",
-					       ilist->filename,
-					       ilist->line_nr);
-			else
-				ret += fprintf(fp, "??");
-
-			ret += fprintf(fp, "\n");
-		}
-	}
-
-	inline_node__delete(node);
-	return ret;
-}
-
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 					  int left_margin)
 {
@@ -137,9 +79,6 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
 	fputc('\n', fp);
 	free(alloc_str);
 
-	if (symbol_conf.inline_name)
-		ret += inline__fprintf(chain->ms.map, chain->ip,
-				       left_margin, depth, depth_mask, fp);
 	return ret;
 }
 
@@ -314,13 +253,6 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
 			if (++entries_printed == callchain_param.print_limit)
 				break;
-
-			if (symbol_conf.inline_name)
-				ret += inline__fprintf(chain->ms.map,
-						       chain->ip,
-						       left_margin,
-						       0, 0,
-						       fp);
 		}
 		root = &cnode->rb_root;
 	}
@@ -600,7 +532,6 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 {
 	int ret;
 	int callchain_ret = 0;
-	int inline_ret = 0;
 	struct perf_hpp hpp = {
 		.buf		= bf,
 		.size		= size,
@@ -622,13 +553,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
-	if (callchain_ret == 0 && symbol_conf.inline_name) {
-		inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
-		ret += inline_ret;
-		if (inline_ret > 0)
-			ret += fprintf(fp, "\n");
-	} else
-		ret += callchain_ret;
+	ret += callchain_ret;
 
 	return ret;
 }

tools/perf/util/callchain.c

@@ -566,6 +566,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
 		call->ms.map = map__get(cursor_node->map);
+		call->srcline = cursor_node->srcline;
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -644,103 +645,120 @@ enum match_result {
 	MATCH_GT,
 };
 
-static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
-					     struct callchain_list *cnode)
+static enum match_result match_chain_strings(const char *left,
+					     const char *right)
 {
-	char *left = NULL;
-	char *right = NULL;
 	enum match_result ret = MATCH_EQ;
 	int cmp;
 
-	if (cnode->ms.map)
-		left = get_srcline(cnode->ms.map->dso,
-				 map__rip_2objdump(cnode->ms.map, cnode->ip),
-				 cnode->ms.sym, true, false);
-	if (node->map)
-		right = get_srcline(node->map->dso,
-				  map__rip_2objdump(node->map, node->ip),
-				  node->sym, true, false);
-
 	if (left && right)
 		cmp = strcmp(left, right);
 	else if (!left && right)
 		cmp = 1;
 	else if (left && !right)
 		cmp = -1;
-	else if (cnode->ip == node->ip)
-		cmp = 0;
 	else
-		cmp = (cnode->ip < node->ip) ? -1 : 1;
+		return MATCH_ERROR;
 
 	if (cmp != 0)
 		ret = cmp < 0 ? MATCH_LT : MATCH_GT;
 
-	free_srcline(left);
-	free_srcline(right);
 	return ret;
 }
 
+/*
+ * We need to always use relative addresses because we're aggregating
+ * callchains from multiple threads, i.e. different address spaces, so
+ * comparing absolute addresses make no sense as a symbol in a DSO may end up
+ * in a different address when used in a different binary or even the same
+ * binary but with some sort of address randomization technique, thus we need
+ * to compare just relative addresses. -acme
+ */
+static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip,
+						   struct map *right_map, u64 right_ip)
+{
+	struct dso *left_dso = left_map ? left_map->dso : NULL;
+	struct dso *right_dso = right_map ? right_map->dso : NULL;
+
+	if (left_dso != right_dso)
+		return left_dso < right_dso ? MATCH_LT : MATCH_GT;
+
+	if (left_ip != right_ip)
+ 		return left_ip < right_ip ? MATCH_LT : MATCH_GT;
+
+	return MATCH_EQ;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
 				     struct callchain_list *cnode)
 {
-	struct symbol *sym = node->sym;
-	u64 left, right;
-	struct dso *left_dso = NULL;
-	struct dso *right_dso = NULL;
-
-	if (callchain_param.key == CCKEY_SRCLINE) {
-		enum match_result match = match_chain_srcline(node, cnode);
+	enum match_result match = MATCH_ERROR;
 
+	switch (callchain_param.key) {
+	case CCKEY_SRCLINE:
+		match = match_chain_strings(cnode->srcline, node->srcline);
 		if (match != MATCH_ERROR)
-			return match;
-	}
-
-	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
-		left = cnode->ms.sym->start;
-		right = sym->start;
-		left_dso = cnode->ms.map->dso;
-		right_dso = node->map->dso;
-	} else {
-		left = cnode->ip;
-		right = node->ip;
+			break;
+		/* otherwise fall-back to symbol-based comparison below */
+		__fallthrough;
+	case CCKEY_FUNCTION:
+		if (node->sym && cnode->ms.sym) {
+			/*
+			 * Compare inlined frames based on their symbol name
+			 * because different inlined frames will have the same
+			 * symbol start. Otherwise do a faster comparison based
+			 * on the symbol start address.
+			 */
+			if (cnode->ms.sym->inlined || node->sym->inlined) {
+				match = match_chain_strings(cnode->ms.sym->name,
+							    node->sym->name);
+				if (match != MATCH_ERROR)
+					break;
+			} else {
+				match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start,
+								  node->map, node->sym->start);
+				break;
+			}
+		}
+		/* otherwise fall-back to IP-based comparison below */
+		__fallthrough;
+	case CCKEY_ADDRESS:
+	default:
+		match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip);
+		break;
 	}
 
-	if (left == right && left_dso == right_dso) {
-		if (node->branch) {
-			cnode->branch_count++;
+	if (match == MATCH_EQ && node->branch) {
+		cnode->branch_count++;
 
-			if (node->branch_from) {
-				/*
-				 * It's "to" of a branch
-				 */
-				cnode->brtype_stat.branch_to = true;
+		if (node->branch_from) {
+			/*
+			 * It's "to" of a branch
+			 */
+			cnode->brtype_stat.branch_to = true;
 
-				if (node->branch_flags.predicted)
-					cnode->predicted_count++;
+			if (node->branch_flags.predicted)
+				cnode->predicted_count++;
 
-				if (node->branch_flags.abort)
-					cnode->abort_count++;
+			if (node->branch_flags.abort)
+				cnode->abort_count++;
 
-				branch_type_count(&cnode->brtype_stat,
-						  &node->branch_flags,
-						  node->branch_from,
-						  node->ip);
-			} else {
-				/*
-				 * It's "from" of a branch
-				 */
-				cnode->brtype_stat.branch_to = false;
-				cnode->cycles_count +=
-					node->branch_flags.cycles;
-				cnode->iter_count += node->nr_loop_iter;
-				cnode->iter_cycles += node->iter_cycles;
-			}
+			branch_type_count(&cnode->brtype_stat,
+					  &node->branch_flags,
+					  node->branch_from,
+					  node->ip);
+		} else {
+			/*
+			 * It's "from" of a branch
+			 */
+			cnode->brtype_stat.branch_to = false;
+			cnode->cycles_count += node->branch_flags.cycles;
+			cnode->iter_count += node->nr_loop_iter;
+			cnode->iter_cycles += node->iter_cycles;
 		}
-
-		return MATCH_EQ;
 	}
 
-	return left > right ? MATCH_GT : MATCH_LT;
+	return match;
 }
 
 /*
@@ -969,7 +987,7 @@ 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, 0);
+					false, NULL, 0, 0, 0, list->srcline);
 		list_del(&list->list);
 		map__zput(list->ms.map);
 		free(list);
@@ -1009,7 +1027,8 @@ 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, u64 iter_cycles, u64 branch_from)
+			    int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+			    const char *srcline)
 {
 	struct callchain_cursor_node *node = *cursor->last;
 
@@ -1028,6 +1047,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
 	node->iter_cycles = iter_cycles;
+	node->srcline = srcline;
 
 	if (flags)
 		memcpy(&node->branch_flags, flags,
@@ -1070,6 +1090,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 {
 	al->map = node->map;
 	al->sym = node->sym;
+	al->srcline = node->srcline;
 	if (node->map)
 		al->addr = node->map->map_ip(node->map, node->ip);
 	else
@@ -1115,16 +1136,15 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 	int printed;
 
 	if (cl->ms.sym) {
-		if (show_srcline && cl->ms.map && !cl->srcline)
-			cl->srcline = get_srcline(cl->ms.map->dso,
-						  map__rip_2objdump(cl->ms.map,
-								    cl->ip),
-						  cl->ms.sym, false, show_addr);
-		if (cl->srcline)
-			printed = scnprintf(bf, bfsize, "%s %s",
-					cl->ms.sym->name, cl->srcline);
+		const char *inlined = cl->ms.sym->inlined ? " (inlined)" : "";
+
+		if (show_srcline && cl->srcline)
+			printed = scnprintf(bf, bfsize, "%s %s%s",
+					    cl->ms.sym->name, cl->srcline,
+					    inlined);
 		else
-			printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+			printed = scnprintf(bf, bfsize, "%s%s",
+					    cl->ms.sym->name, inlined);
 	} else
 		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 
@@ -1532,7 +1552,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 					     node->branch, &node->branch_flags,
 					     node->nr_loop_iter,
 					     node->iter_cycles,
-					     node->branch_from);
+					     node->branch_from, node->srcline);
 		if (rc)
 			break;
 

tools/perf/util/callchain.h

@@ -121,7 +121,7 @@ struct callchain_list {
 	u64			iter_count;
 	u64			iter_cycles;
 	struct branch_type_stat brtype_stat;
-	char		       *srcline;
+	const char		*srcline;
 	struct list_head	list;
 };
 
@@ -135,6 +135,7 @@ struct callchain_cursor_node {
 	u64				ip;
 	struct map			*map;
 	struct symbol			*sym;
+	const char			*srcline;
 	bool				branch;
 	struct branch_flags		branch_flags;
 	u64				branch_from;
@@ -201,7 +202,8 @@ 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, u64 iter_cycles, u64 branch_from);
+			    int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+			    const char *srcline);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)

tools/perf/util/dso.c

@@ -10,6 +10,7 @@
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
@@ -1201,6 +1202,8 @@ struct dso *dso__new(const char *name)
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->data.cache = RB_ROOT;
+		dso->inlined_nodes = RB_ROOT;
+		dso->srclines = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1232,6 +1235,10 @@ void dso__delete(struct dso *dso)
 	if (!RB_EMPTY_NODE(&dso->rb_node))
 		pr_err("DSO %s is still in rbtree when being deleted!\n",
 		       dso->long_name);
+
+	/* free inlines first, as they reference symbols */
+	inlines__tree_delete(&dso->inlined_nodes);
+	srcline__tree_delete(&dso->srclines);
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
 

tools/perf/util/dso.h

@@ -141,6 +141,8 @@ struct dso {
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 inlined_nodes;
+	struct rb_root	 srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;

tools/perf/util/event.c

@@ -1604,6 +1604,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 	al->sym = NULL;
 	al->cpu = sample->cpu;
 	al->socket = -1;
+	al->srcline = NULL;
 
 	if (al->cpu >= 0) {
 		struct perf_env *env = machine->env;

tools/perf/util/evsel_fprintf.c

@@ -157,7 +157,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 				}
 			}
 
-			if (print_dso) {
+			if (print_dso && (!node->sym || !node->sym->inlined)) {
 				printed += fprintf(fp, " (");
 				printed += map__fprintf_dsoname(node->map, fp);
 				printed += fprintf(fp, ")");
@@ -166,41 +166,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (print_srcline)
 				printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
 
+			if (node->sym && node->sym->inlined)
+				printed += fprintf(fp, " (inlined)");
+
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
 
-			if (symbol_conf.inline_name && node->map) {
-				struct inline_node *inode;
-
-				addr = map__rip_2objdump(node->map, node->ip),
-				inode = dso__parse_addr_inlines(node->map->dso, addr);
-
-				if (inode) {
-					struct inline_list *ilist;
-
-					list_for_each_entry(ilist, &inode->val, list) {
-						if (print_arrow)
-							printed += fprintf(fp, " <-");
-
-						/* IP is same, just skip it */
-						if (print_ip)
-							printed += fprintf(fp, "%c%16s",
-									   s, "");
-						if (print_sym)
-							printed += fprintf(fp, " %s",
-									   ilist->funcname);
-						if (print_srcline)
-							printed += fprintf(fp, "\n  %s:%d",
-									   ilist->filename,
-									   ilist->line_nr);
-						if (!print_oneline)
-							printed += fprintf(fp, "\n");
-					}
-
-					inline_node__delete(inode);
-				}
-			}
-
 			if (symbol_conf.bt_stop_list &&
 			    node->sym &&
 			    strlist__has_entry(symbol_conf.bt_stop_list,

tools/perf/util/hist.c

@@ -596,6 +596,7 @@ __hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
+		.srcline = al->srcline ? strdup(al->srcline) : NULL,
 		.socket	 = al->socket,
 		.cpu	 = al->cpu,
 		.cpumode = al->cpumode,
@@ -950,6 +951,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			.map = al->map,
 			.sym = al->sym,
 		},
+		.srcline = al->srcline ? strdup(al->srcline) : NULL,
 		.parent = iter->parent,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
@@ -1141,11 +1143,6 @@ void hist_entry__delete(struct hist_entry *he)
 		zfree(&he->mem_info);
 	}
 
-	if (he->inline_node) {
-		inline_node__delete(he->inline_node);
-		he->inline_node = NULL;
-	}
-
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])

tools/perf/util/machine.c

@@ -1709,6 +1709,26 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	return mi;
 }
 
+static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip)
+{
+	char *srcline = NULL;
+
+	if (!map || callchain_param.key == CCKEY_FUNCTION)
+		return srcline;
+
+	srcline = srcline__tree_find(&map->dso->srclines, ip);
+	if (!srcline) {
+		bool show_sym = false;
+		bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+
+		srcline = get_srcline(map->dso, map__rip_2objdump(map, ip),
+				      sym, show_sym, show_addr);
+		srcline__tree_insert(&map->dso->srclines, ip, srcline);
+	}
+
+	return srcline;
+}
+
 struct iterations {
 	int nr_loop_iter;
 	u64 cycles;
@@ -1728,6 +1748,7 @@ static int add_callchain_ip(struct thread *thread,
 	struct addr_location al;
 	int nr_loop_iter = 0;
 	u64 iter_cycles = 0;
+	const char *srcline = NULL;
 
 	al.filtered = 0;
 	al.sym = NULL;
@@ -1783,9 +1804,10 @@ static int add_callchain_ip(struct thread *thread,
 		iter_cycles = iter->cycles;
 	}
 
+	srcline = callchain_srcline(al.map, al.sym, al.addr);
 	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
 				       branch, flags, nr_loop_iter,
-				       iter_cycles, branch_from);
+				       iter_cycles, branch_from, srcline);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -2098,15 +2120,54 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int append_inlines(struct callchain_cursor *cursor,
+			  struct map *map, struct symbol *sym, u64 ip)
+{
+	struct inline_node *inline_node;
+	struct inline_list *ilist;
+	u64 addr;
+	int ret = 1;
+
+	if (!symbol_conf.inline_name || !map || !sym)
+		return ret;
+
+	addr = map__rip_2objdump(map, ip);
+
+	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
+	if (!inline_node) {
+		inline_node = dso__parse_addr_inlines(map->dso, addr, sym);
+		if (!inline_node)
+			return ret;
+		inlines__tree_insert(&map->dso->inlined_nodes, inline_node);
+	}
+
+	list_for_each_entry(ilist, &inline_node->val, list) {
+		ret = callchain_cursor_append(cursor, ip, map,
+					      ilist->symbol, false,
+					      NULL, 0, 0, 0, ilist->srcline);
+
+		if (ret != 0)
+			return ret;
+	}
+
+	return ret;
+}
+
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
+	const char *srcline = NULL;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
+
+	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
+		return 0;
+
+	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
-				       false, NULL, 0, 0, 0);
+				       false, NULL, 0, 0, 0, srcline);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,

tools/perf/util/sort.c

@@ -225,6 +225,9 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 	if (sym_l == sym_r)
 		return 0;
 
+	if (sym_l->inlined || sym_r->inlined)
+		return strcmp(sym_l->name, sym_r->name);
+
 	if (sym_l->start != sym_r->start)
 		return (int64_t)(sym_r->start - sym_l->start);
 
@@ -283,6 +286,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
 					       width - ret,
 					       sym->name);
+			if (sym->inlined)
+				ret += repsep_snprintf(bf + ret, size - ret,
+						       " (inlined)");
 		}
 	} else {
 		size_t len = BITS_PER_LONG / 4;

tools/perf/util/sort.h

@@ -129,7 +129,6 @@ struct hist_entry {
 	};
 	char			*srcline;
 	char			*srcfile;
-	struct inline_node	*inline_node;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
 	struct hists		*hists;

tools/perf/util/srcline.h

@@ -2,6 +2,7 @@
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -14,21 +15,38 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool show_addr, bool unwind_inlines);
 void free_srcline(char *srcline);
 
+/* insert the srcline into the DSO, which will take ownership */
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+/* find previously inserted srcline */
+char *srcline__tree_find(struct rb_root *tree, u64 addr);
+/* delete all srclines within the tree */
+void srcline__tree_delete(struct rb_root *tree);
+
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
 struct inline_list {
-	char			*filename;
-	char			*funcname;
-	unsigned int		line_nr;
+	struct symbol		*symbol;
+	char			*srcline;
 	struct list_head	list;
 };
 
 struct inline_node {
 	u64			addr;
 	struct list_head	val;
+	struct rb_node		rb_node;
 };
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+/* parse inlined frames for the given address */
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+					    struct symbol *sym);
+/* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
 
+/* insert the inline node list into the DSO, which will take ownership */
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+/* find previously inserted inline node list */
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+/* delete all nodes within the tree of inline_node s */
+void inlines__tree_delete(struct rb_root *tree);
+
 #endif /* PERF_SRCLINE_H */

tools/perf/util/symbol.c

@@ -45,6 +45,7 @@ struct symbol_conf symbol_conf = {
 	.show_hist_headers	= true,
 	.symfs			= "",
 	.event_group		= true,
+	.inline_name		= true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {

tools/perf/util/symbol.h

@@ -59,6 +59,7 @@ struct symbol {
 	u8		binding;
 	u8		idle:1;
 	u8		ignore:1;
+	u8		inlined:1;
 	u8		arch_sym;
 	char		name[0];
 };
@@ -208,6 +209,7 @@ struct addr_location {
 	struct thread *thread;
 	struct map    *map;
 	struct symbol *sym;
+	const char    *srcline;
 	u64	      addr;
 	char	      level;
 	u8	      filtered;