Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel:

   - kprobes updates: use better W^X patterns for code modifications,
     improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook)

   - core fixes: event timekeeping (enabled/running times statistics)
     fixes, perf_event_read() locking fixes and cleanups, etc. (Peter
     Zijlstra)

   - Extend x86 Intel free-running PEBS support and support x86
     user-register sampling in perf record and perf script. (Andi Kleen)

  Tooling:

   - Completely rework 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. (Milian
     Wolff)

   - 'perf trace' updates (Arnaldo Carvalho de Melo)

   - Implement a way to print formatted output to per-event files in
     'perf script' to facilitate generate flamegraphs, elliminating the
     need to write scripts to do that separation (yuzhoujian, Arnaldo
     Carvalho de Melo)

   - Update vendor events JSON metrics for Intel's Broadwell, Broadwell
     Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown,
     Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi
     Kleen, Kan Liang)

   - Multithread the synthesizing of PERF_RECORD_ events for
     pre-existing threads in 'perf top', speeding up that phase, greatly
     improving the user experience in systems such as Intel's Knights
     Mill (Kan Liang)

   - Introduce the concept of weak groups in 'perf stat': try to set up
     a group, but if it's not schedulable fallback to not using a group.
     That gives us the best of both worlds: groups if they work, but
     still a usable fallback if they don't. E.g: (Andi Kleen)

   - perf sched timehist enhancements (David Ahern)

   - ... various other enhancements, updates, cleanups and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits)
  kprobes: Don't spam the build log with deprecation warnings
  arm/kprobes: Remove jprobe test case
  arm/kprobes: Fix kretprobe test to check correct counter
  perf srcline: Show correct function name for srcline of callchains
  perf srcline: Fix memory leak in addr2inlines()
  perf trace beauty kcmp: Beautify arguments
  perf trace beauty: Implement pid_fd beautifier
  tools include uapi: Grab a copy of linux/kcmp.h
  perf callchain: Fix double mapping al->addr for children without self period
  perf stat: Make --per-thread update shadow stats to show metrics
  perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
  perf tools: Add perf_data_file__write function
  perf tools: Add struct perf_data_file
  perf tools: Rename struct perf_data_file to perf_data
  perf script: Print information about per-event-dump files
  perf trace beauty prctl: Generate 'option' string table from kernel headers
  tools include uapi: Grab a copy of linux/prctl.h
  perf script: Allow creating per-event dump files
  perf evsel: Restore evsel->priv as a tool private area
  perf script: Use event_format__fprintf()
  ...

1 files changed, 98 insertions, 81 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 6031933d811c..082505d08d72 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -567,6 +567,7 @@ 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;
@@ -645,103 +646,120 @@ 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;
 }
 
 /*
@@ -970,7 +988,7 @@ 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);
@@ -1010,7 +1028,8 @@ 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;
 
@@ -1029,6 +1048,7 @@ 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,
@@ -1071,10 +1091,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 {
 	al->map = node->map;
 	al->sym = node->sym;
-	if (node->map)
-		al->addr = node->map->map_ip(node->map, node->ip);
-	else
-		al->addr = node->ip;
+	al->srcline = node->srcline;
+	al->addr = node->ip;
 
 	if (al->sym == NULL) {
 		if (hide_unresolved)
@@ -1116,16 +1134,15 @@ 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);
 
@@ -1533,7 +1550,7 @@ 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;