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

Pull more perf updates from Ingo Molnar:
 "A second round of perf updates:

   - wide reaching kprobes sanitization and robustization, with the hope
     of fixing all 'probe this function crashes the kernel' bugs, by
     Masami Hiramatsu.

   - uprobes updates from Oleg Nesterov: tmpfs support, corner case
     fixes and robustization work.

   - perf tooling updates and fixes from Jiri Olsa, Namhyung Ki, Arnaldo
     et al:
        * Add support to accumulate hist periods (Namhyung Kim)
        * various fixes, refactorings and enhancements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (101 commits)
  perf: Differentiate exec() and non-exec() comm events
  perf: Fix perf_event_comm() vs. exec() assumption
  uprobes/x86: Rename arch_uprobe->def to ->defparam, minor comment updates
  perf/documentation: Add description for conditional branch filter
  perf/x86: Add conditional branch filtering support
  perf/tool: Add conditional branch filter 'cond' to perf record
  perf: Add new conditional branch filter 'PERF_SAMPLE_BRANCH_COND'
  uprobes: Teach copy_insn() to support tmpfs
  uprobes: Shift ->readpage check from __copy_insn() to uprobe_register()
  perf/x86: Use common PMU interrupt disabled code
  perf/ARM: Use common PMU interrupt disabled code
  perf: Disable sampled events if no PMU interrupt
  perf: Fix use after free in perf_remove_from_context()
  perf tools: Fix 'make help' message error
  perf record: Fix poll return value propagation
  perf tools: Move elide bool into perf_hpp_fmt struct
  perf tools: Remove elide setup for SORT_MODE__MEMORY mode
  perf tools: Fix "==" into "=" in ui_browser__warning assignment
  perf tools: Allow overriding sysfs and proc finding with env var
  perf tools: Consider header files outside perf directory in tags target
  ...

34 files changed, 1903 insertions, 388 deletions

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 5b5eb788996e..c1b49c36a951 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,8 +1,10 @@
 /* TODO merge/factor in debugfs.c here */
 
+#include <ctype.h>
 #include <errno.h>
 #include <stdbool.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
 #include <sys/vfs.h>
 
@@ -96,12 +98,51 @@ static bool fs__check_mounts(struct fs *fs)
 	return false;
 }
 
+static void mem_toupper(char *f, size_t len)
+{
+	while (len) {
+		*f = toupper(*f);
+		f++;
+		len--;
+	}
+}
+
+/*
+ * Check for "NAME_PATH" environment variable to override fs location (for
+ * testing). This matches the recommendation in Documentation/sysfs-rules.txt
+ * for SYSFS_PATH.
+ */
+static bool fs__env_override(struct fs *fs)
+{
+	char *override_path;
+	size_t name_len = strlen(fs->name);
+	/* name + "_PATH" + '\0' */
+	char upper_name[name_len + 5 + 1];
+	memcpy(upper_name, fs->name, name_len);
+	mem_toupper(upper_name, name_len);
+	strcpy(&upper_name[name_len], "_PATH");
+
+	override_path = getenv(upper_name);
+	if (!override_path)
+		return false;
+
+	fs->found = true;
+	strncpy(fs->path, override_path, sizeof(fs->path));
+	return true;
+}
+
 static const char *fs__get_mountpoint(struct fs *fs)
 {
+	if (fs__env_override(fs))
+		return fs->path;
+
 	if (fs__check_mounts(fs))
 		return fs->path;
 
-	return fs__read_mounts(fs) ? fs->path : NULL;
+	if (fs__read_mounts(fs))
+		return fs->path;
+
+	return NULL;
 }
 
 static const char *fs__mountpoint(int idx)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c71b0f36d9e8..d460049cae8e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -184,9 +184,10 @@ following filters are defined:
 	- in_tx: only when the target is in a hardware transaction
 	- no_tx: only when the target is not in a hardware transaction
 	- abort_tx: only when the target is a hardware transaction abort
+	- cond: conditional branches
 
 +
-The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
 The privilege levels may be omitted, in which case, the privilege levels of the associated
 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
 levels are subject to permissions.  When sampling on multiple events, branch stack sampling
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index a1b5185402d5..cefdf430d1b4 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -111,7 +111,7 @@ OPTIONS
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in -F will be appended
@@ -163,6 +163,11 @@ OPTIONS
 
 	Default: fractal,0.5,callee,function.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires callchains are recorded.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index dcfa54c851e9..180ae02137a5 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -119,7 +119,7 @@ Default is to monitor all CPUS.
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in --field will be appended
@@ -161,6 +161,12 @@ Default is to monitor all CPUS.
 	Setup and enable call-graph (stack chain/backtrace) recording,
 	implies -g.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires -g/--call-graph option
+	enabled.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 02f0a4dd1a80..ae20edfcc3f7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -400,6 +400,7 @@ LIB_OBJS += $(OUTPUT)tests/hists_common.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
 LIB_OBJS += $(OUTPUT)tests/hists_filter.o
 LIB_OBJS += $(OUTPUT)tests/hists_output.o
+LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o
 LIB_OBJS += $(OUTPUT)tests/python-use.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
@@ -788,8 +789,8 @@ help:
 	@echo ''
 	@echo 'Perf install targets:'
 	@echo '  NOTE: documentation build requires asciidoc, xmlto packages to be installed'
-	@echo '  HINT: use "make prefix=<path> <install target>" to install to a particular'
-	@echo '        path like make prefix=/usr/local install install-doc'
+	@echo '  HINT: use "prefix" or "DESTDIR" to install to a particular'
+	@echo '        path like "make prefix=/usr/local install install-doc"'
 	@echo '  install	- install compiled binaries'
 	@echo '  install-doc	- install *all* documentation'
 	@echo '  install-man	- install manpage documentation'
@@ -814,17 +815,20 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 $(DOC_TARGETS):
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
 
+TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol
+TAG_FILES= ../../include/uapi/linux/perf_event.h
+
 TAGS:
 	$(RM) TAGS
-	$(FIND) . -name '*.[hcS]' -print | xargs etags -a
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
 
 tags:
 	$(RM) tags
-	$(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
 	$(RM) cscope*
-	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
 
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index d30d2c2e2a7a..1ec429fef2be 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -65,12 +65,13 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0);
+	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
+				true);
 	if (he == NULL)
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 	return ret;
 }
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8bff543acaab..9a5a035cb426 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -315,7 +315,7 @@ static int hists__add_entry(struct hists *hists,
 			    u64 weight, u64 transaction)
 {
 	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction) != NULL)
+			       transaction, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e4c85b8f46c2..378b85b731a7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -454,7 +454,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			if (done)
 				break;
 			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
-			if (err < 0 && errno == EINTR)
+			/*
+			 * Propagate error, only if there's any. Ignore positive
+			 * number of returned events and interrupt error.
+			 */
+			if (err > 0 || (err < 0 && errno == EINTR))
 				err = 0;
 			waking++;
 		}
@@ -544,6 +548,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
 	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
 	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
 	BRANCH_END
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bc0eec1ce4be..21d830bafff3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -72,6 +72,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -85,156 +89,52 @@ static void report__inc_stats(struct report *rep, struct hist_entry *he)
 	 */
 	if (he->stat.nr_events == 1)
 		rep->nr_entries++;
-
-	/*
-	 * Only counts number of samples at this stage as it's more
-	 * natural to do it here and non-sample events are also
-	 * counted in perf_session_deliver_event().  The dump_trace
-	 * requires this info is ready before going to the output tree.
-	 */
-	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		he->hists->stats.nr_non_filtered_samples++;
 }
 
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
 
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
+	report__inc_stats(rep, he);
 
-	if (rep->hide_unresolved && !al->sym)
+	if (!ui__has_annotation())
 		return 0;
 
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
-	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
-	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
 		if (err)
 			goto out;
-	}
-
-	report__inc_stats(rep, he);
-
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
-}
-
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
 
-		err = -ENOMEM;
-
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
-			report__inc_stats(rep, he);
-		} else
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
 			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
-}
-
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
 
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
-
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
-
-	if (ui__has_annotation())
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
-	report__inc_stats(rep, he);
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
 
 out:
 	return err;
 }
 
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -243,6 +143,10 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -257,22 +161,23 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
 
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
 	return ret;
 }
 
@@ -329,6 +234,14 @@ static int report__setup_sample_type(struct report *rep)
 			}
 	}
 
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!is_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
@@ -712,6 +625,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
 		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -804,8 +719,10 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack)
+	if (branch_mode == -1 && has_br_stack) {
 		sort__mode = SORT_MODE__BRANCH;
+		symbol_conf.cumulate_callchain = false;
+	}
 
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -813,6 +730,7 @@ repeat:
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
+		symbol_conf.cumulate_callchain = false;
 	}
 
 	if (setup_sorting() < 0) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d7176830b9b2..c38d06c04775 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1428,7 +1428,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	int err = 0;
 
 	evsel->hists.stats.total_period += sample->period;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5b389ce4cd15..377971dc89a3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -196,6 +196,12 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 
 	pthread_mutex_unlock(&notes->lock);
 
+	/*
+	 * This function is now called with he->hists->lock held.
+	 * Release it before going to sleep.
+	 */
+	pthread_mutex_unlock(&he->hists->lock);
+
 	if (err == -ERANGE && !he->ms.map->erange_warned)
 		ui__warn_map_erange(he->ms.map, sym, ip);
 	else if (err == -ENOMEM) {
@@ -203,6 +209,8 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 		       sym->name);
 		sleep(1);
 	}
+
+	pthread_mutex_lock(&he->hists->lock);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -238,27 +246,6 @@ out_unlock:
 	pthread_mutex_unlock(&notes->lock);
 }
 
-static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
-						     struct addr_location *al,
-						     struct perf_sample *sample)
-{
-	struct hist_entry *he;
-
-	pthread_mutex_lock(&evsel->hists.lock);
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	pthread_mutex_unlock(&evsel->hists.lock);
-	if (he == NULL)
-		return NULL;
-
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-
-	return he;
-}
-
 static void perf_top__print_sym_table(struct perf_top *top)
 {
 	char bf[160];
@@ -662,6 +649,26 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	return 0;
 }
 
+static int hist_iter__top_callback(struct hist_entry_iter *iter,
+				   struct addr_location *al, bool single,
+				   void *arg)
+{
+	struct perf_top *top = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+
+	if (sort__has_sym && single) {
+		u64 ip = al->addr;
+
+		if (al->map)
+			ip = al->map->unmap_ip(al->map, ip);
+
+		perf_top__record_precise_ip(top, he, evsel->idx, ip);
+	}
+
+	return 0;
+}
+
 static void perf_event__process_sample(struct perf_tool *tool,
 				       const union perf_event *event,
 				       struct perf_evsel *evsel,
@@ -669,8 +676,6 @@ static void perf_event__process_sample(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
-	struct symbol *parent = NULL;
-	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 
@@ -745,25 +750,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
-		struct hist_entry *he;
+		struct hist_entry_iter iter = {
+			.add_entry_cb = hist_iter__top_callback,
+		};
 
-		err = sample__resolve_callchain(sample, &parent, evsel, &al,
-						top->max_stack);
-		if (err)
-			return;
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
 
-		he = perf_evsel__add_hist_entry(evsel, &al, sample);
-		if (he == NULL) {
-			pr_err("Problem incrementing symbol period, skipping event\n");
-			return;
-		}
+		pthread_mutex_lock(&evsel->hists.lock);
 
-		err = hist_entry__append_callchain(he, sample);
-		if (err)
-			return;
+		err = hist_entry_iter__add(&iter, &al, evsel, sample,
+					   top->max_stack, top);
+		if (err < 0)
+			pr_err("Problem incrementing symbol period, skipping event\n");
 
-		if (sort__has_sym)
-			perf_top__record_precise_ip(top, he, evsel->idx, ip);
+		pthread_mutex_unlock(&evsel->hists.lock);
 	}
 
 	return;
@@ -1001,6 +1004,10 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 
 	if (!strcmp(var, "top.call-graph"))
 		return record_parse_callchain(value, &top->record_opts);
+	if (!strcmp(var, "top.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -1095,6 +1102,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
 		     "mode[,dump_size]", record_callchain_help,
 		     &parse_callchain_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &top.max_stack,
 		    "Set the maximum stack depth when parsing the callchain. "
 		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
@@ -1200,6 +1209,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
 
+	if (!symbol_conf.use_callchain) {
+		symbol_conf.cumulate_callchain = false;
+		perf_hpp__cancel_cumulate();
+	}
+
 	symbol_conf.priv_size = sizeof(struct annotation);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 729bbdf5cec7..4f100b54ba8b 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -447,6 +447,7 @@ else
   ifneq ($(feature-libperl), 1)
     CFLAGS += -DNO_LIBPERL
     NO_LIBPERL := 1
+    msg := $(warning Missing perl devel files. Disabling perl scripting support, consider installing perl-ExtUtils-Embed);
   else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
@@ -599,7 +600,7 @@ endif
 
 # Make the path relative to DESTDIR, not to prefix
 ifndef DESTDIR
-prefix = $(HOME)
+prefix ?= $(HOME)
 endif
 bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 431798a4110d..78f7b920e548 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -481,14 +481,18 @@ int main(int argc, const char **argv)
 		fprintf(stderr, "cannot handle %s internally", cmd);
 		goto out;
 	}
-#ifdef HAVE_LIBAUDIT_SUPPORT
 	if (!prefixcmp(cmd, "trace")) {
+#ifdef HAVE_LIBAUDIT_SUPPORT
 		set_buildid_dir();
 		setup_path();
 		argv[0] = "trace";
 		return cmd_trace(argc, argv, NULL);
-	}
+#else
+		fprintf(stderr,
+			"trace command not available: missing audit-libs devel package at build time.\n");
+		goto out;
 #endif
+	}
 	/* Look for flags.. */
 	argv++;
 	argc--;
diff --git a/tools/perf/tests/builtin-test.c b/tools/p