diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c39c05e029a7f357cb872ffa982d6ca2381fddb..799bb352d99f9dfd4c199b0c4f39b3122118d010 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6640,6 +6640,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	struct perf_namespaces_event *namespaces_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u16 header_size = namespaces_event->event_id.header.size;
 	int ret;
 
 	if (!perf_event_namespaces_match(event))
@@ -6650,7 +6651,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	ret = perf_output_begin(&handle, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
-		return;
+		goto out;
 
 	namespaces_event->event_id.pid = perf_event_pid(event,
 							namespaces_event->task);
@@ -6662,6 +6663,8 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	perf_event__output_id_sample(event, &handle, &sample);
 
 	perf_output_end(&handle);
+out:
+	namespaces_event->event_id.header.size = header_size;
 }
 
 static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
index 481e103da78ed42a5a76447e836ee8374541d7c7..ef130501092531b23148898efc08b0e521f3354c 100644
--- a/tools/include/uapi/linux/kcmp.h
+++ b/tools/include/uapi/linux/kcmp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_KCMP_H
 #define _UAPI_LINUX_KCMP_H
 
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index a8d0759a9e400c5d472fe37d13a924bc9e9777a6..b640071421f709e783f839b3d4c17344d8c86dac 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 84681007f80f4aae6ec031e416edf1c3e866d304..73c2650bd0db565b6bd1fe695bb2504a294f0470 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -24,6 +24,9 @@ OPTIONS
 -a::
 --add=::
         Add specified file to the cache.
+-f::
+--force::
+	Don't complain, do it.
 -k::
 --kcore::
         Add specified kcore file to the cache. For the current host that is
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 6f7200fb85cf2e509d8d17bc5c3ff7ed6d7a7331..c0a66400a960d68cbf73690f608867f648d79797 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -20,6 +20,10 @@ OPTIONS
 --input=::
         Input file name. (default: perf.data unless stdin is a fifo)
 
+-f::
+--force::
+	Don't complain, do it.
+
 -F::
 --freq=::
 	Show just the sample frequency used for each event.
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 87b2588d1cbdee6060a304be4f79015cb5889171..a64d6588470e605845e1eb4589e8e9a7a8a6f049 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -60,6 +60,10 @@ include::itrace.txt[]
 	found in the jitdumps files captured in the input perf.data file. Use this option
 	if you are monitoring environment using JIT runtimes, such as Java, DART or V8.
 
+-f::
+--force::
+	Don't complain, do it.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index ab25be28c9dcaab31adb1822195afab571308910..74d7745921968b3a7286311f740d3f5aab0315e2 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -42,6 +42,10 @@ COMMON OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
+-f::
+--force::
+	Don't complan, do it.
+
 REPORT OPTIONS
 --------------
 
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 55b67338548e1d116f8dc80555b30f9798c96bfc..c7e50f26388733eb6c559c70d869e9fc9091992b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -74,6 +74,10 @@ OPTIONS
 --dump-raw-trace=::
         Display verbose dump of the sched data.
 
+-f::
+--force::
+	Don't complain, do it.
+
 OPTIONS for 'perf sched map'
 ----------------------------
 
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index df98d1c82688a4efb6a59d28d254bdbda229ad60..ef0c7565bd5c61416fd4897f497d9f5dfad50eac 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -50,7 +50,9 @@ TIMECHART OPTIONS
 -p::
 --process::
         Select the processes to display, by name or PID
-
+-f::
+--force::
+	Don't complain, do it.
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
 -n::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 4353262bc462b05cc3c4008c1a39e06ee76b758b..8a32cc77bead37463b8d2517bf3d9a5c42ce8673 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -268,6 +268,12 @@ INTERACTIVE PROMPTING KEYS
 [S]::
 	Stop annotation, return to full profile display.
 
+[K]::
+	Hide kernel symbols.
+
+[U]::
+	Hide user symbols.
+
 [z]::
 	Toggle event count zeroing across display updates.
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index d53bea6bd5710561834eb576fbf81dd1006cee9f..6909cf1e0eea293669432685009e94b9d6166355 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -86,18 +86,18 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-
 In per-thread mode with inheritance mode on (default), Events are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
---duration:
+--duration::
 	Show only events that had a duration greater than N.M ms.
 
---sched:
+--sched::
 	Accrue thread runtime and provide a summary at the end of the session.
 
--i
---input
+-i::
+--input::
 	Process events from a given perf data file.
 
--T
---time
+-T::
+--time::
 	Print full timestamp rather time relative to first sample.
 
 --comm::
@@ -117,6 +117,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	Show tool stats such as number of times fd->pathname was discovered thru
 	hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
 
+-f::
+--force::
+	Don't complain, do it.
+
 -F=[all|min|maj]::
 --pf=[all|min|maj]::
 	Trace pagefaults. Optionally, you can specify whether you want minor,
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index e90c59c6d8157052341847fd02ad50a38b356a3e..15e8b48077ba30f6fa04bd5e12a31d8082fcc42e 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -238,6 +238,29 @@ struct auxtrace_index {
 	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
 };
 
+	HEADER_STAT = 19,
+
+This is merely a flag signifying that the data section contains data
+recorded from perf stat record.
+
+	HEADER_CACHE = 20,
+
+Description of the cache hierarchy. Based on the Linux sysfs format
+in /sys/devices/system/cpu/cpu*/cache/
+
+	u32 version	Currently always 1
+	u32 number_of_cache_levels
+
+struct {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	struct perf_header_string type;
+	struct perf_header_string size;
+	struct perf_header_string map;
+}[number_of_cache_levels];
+
 	other bits are reserved and should ignored for now
 	HEADER_FEAT_BITS	= 256,
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 63f534a0902f29e5682570d70751ccb6035d13bb..f6786fa2419fed0a54a4c24625885a3f4505f739 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -579,7 +579,7 @@ else
   PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
   PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-  PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+  PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
   ifneq ($(feature-libperl), 1)
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 3d354ba6e9c59884ebed61b2ba512b42e0d9359a..41db2cba77eb96d4620982e1754e0b182b175e13 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -325,8 +325,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		   "file", "kcore file to add"),
 	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
 		    "file(s) to remove"),
-	OPT_STRING('p', "purge", &purge_name_list_str, "path list",
-		    "path(s) to remove (remove old caches too)"),
+	OPT_STRING('p', "purge", &purge_name_list_str, "file list",
+		    "file(s) to remove (remove old caches too)"),
 	OPT_STRING('M', "missing", &missing_filename, "file",
 		   "to find missing build ids in the cache"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 17855c4626a08b7d4add1b5c9922653a5be39ad4..f1da9b0833c077fde4d78c1d6528caee1847c820 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2224,9 +2224,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	struct hist_browser *browser;
 	int key = -1;
 	const char help[] =
-	" ENTER         Togle callchains (if present) \n"
-	" n             Togle Node details info \n"
-	" s             Togle full lenght of symbol and source line columns \n"
+	" ENTER         Toggle callchains (if present) \n"
+	" n             Toggle Node details info \n"
+	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
 	/* Display compact version first. */
@@ -2303,7 +2303,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 	int key = -1;
 	const char help[] =
 	" d             Display cacheline details \n"
-	" ENTER         Togle callchains (if present) \n"
+	" ENTER         Toggle callchains (if present) \n"
 	" q             Quit \n";
 
 	browser = perf_c2c_browser__new(hists);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index bd1fedef3d1c5d67a8ab6954467c24da622f2a27..a0f7ed2b869b0304408483e5660efa9167794a0e 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 		add_man_viewer(value);
 		return 0;
 	}
-	if (!strstarts(var, "man."))
+	if (strstarts(var, "man."))
 		return add_man_viewer_info(var, value);
 
 	return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
 	if (!perf_cmd)
 		return "perf";
-	else if (!strstarts(perf_cmd, "perf"))
+	else if (strstarts(perf_cmd, "perf"))
 		return perf_cmd;
 
 	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0c36f2ac6a0e0419a61306be7161ea9462b3aead..597c7de9bec9401a4bc05ea64e004403a64d9b20 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -741,20 +741,20 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 				   u64 *mmap_time)
 {
 	union perf_event *event;
-	struct perf_sample sample;
+	u64 timestamp;
 	s64 n = 0;
 	int err;
 
 	*mmap_time = ULLONG_MAX;
 	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
-		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
+		err = perf_evlist__parse_sample_timestamp(kvm->evlist, event, &timestamp);
 		if (err) {
 			perf_evlist__mmap_consume(kvm->evlist, idx);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}
 
-		err = perf_session__queue_event(kvm->session, event, &sample, 0);
+		err = perf_session__queue_event(kvm->session, event, timestamp, 0);
 		/*
 		 * FIXME: Here we can't consume the event, as perf_session__queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
@@ -768,7 +768,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 
 		/* save time stamp of our first sample for this mmap */
 		if (n == 0)
-			*mmap_time = sample.time;
+			*mmap_time = timestamp;
 
 		/* limit events per mmap handled all at once */
 		n++;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3d7f33e19df28d90c7e33dcc37ea823197de6731..003255910c05df9104eafd2c012267c96523118b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -339,6 +339,22 @@ static int record__open(struct record *rec)
 	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
+	/*
+	 * For initial_delay we need to add a dummy event so that we can track
+	 * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+	 * real events, the ones asked by the user.
+	 */
+	if (opts->initial_delay) {
+		if (perf_evlist__add_dummy(evlist))
+			return -ENOMEM;
+
+		pos = perf_evlist__first(evlist);
+		pos->tracking = 0;
+		pos = perf_evlist__last(evlist);
+		pos->tracking = 1;
+		pos->attr.enable_on_exec = 1;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -749,17 +765,19 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/modules permission or run as root.\n");
+	if (!perf_evlist__exclude_kernel(rec->evlist)) {
+		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+							 machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/kallsyms permission or run as root.\n");
+
+		err = perf_event__synthesize_modules(tool, process_synthesized_event,
+						     machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/modules permission or run as root.\n");
+	}
 
 	if (perf_guest) {
 		machines__process_guests(&session->machines,
@@ -1693,7 +1711,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict)
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1394cd8d96f7bb8d132e2a5cf892090690a19920..af5dd038195e3f6e3a6877d5884efda263e46843 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
 	struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+	if (perf_evlist__exclude_kernel(rep->session->evlist))
+		return;
+
 	if (kernel_map == NULL ||
 	    (kernel_map->dso->hit &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 68f36dc0344f2bb7d07a1bcdb05f8af4419d1d88..ee7c7aaaae72eafaba07125df31037a4bd0f5609 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -423,11 +423,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
-	if (PRINT_FIELD(PERIOD) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_PERIOD, "PERIOD",
-					PERF_OUTPUT_PERIOD))
-		return -EINVAL;
-
 	if (PRINT_FIELD(IREGS) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS",
 					PERF_OUTPUT_IREGS))
@@ -1955,6 +1950,16 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 	struct perf_evsel *evsel;
 
 	evlist__for_each_entry(script->session->evlist, evsel) {
+		/*
+		 * Already setup? I.e. we may be called twice in cases like
+		 * Intel PT, one for the intel_pt// and dummy events, then
+		 * for the evsels syntheized from the auxtrace info.
+		 *
+		 * Ses perf_script__process_auxtrace_info.
+		 */
+		if (evsel->priv != NULL)
+			continue;
+
 		evsel->priv = perf_evsel_script__new(evsel, script->session->data);
 		if (evsel->priv == NULL)
 			goto out_err_fclose;
@@ -2838,6 +2843,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+					      union perf_event *event,
+					      struct perf_session *session)
+{
+	int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+	if (ret == 0) {
+		struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+		ret = perf_script__setup_per_event_dump(script);
+	}
+
+	return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -2866,7 +2890,7 @@ int cmd_script(int argc, const char **argv)
 			.feature	 = perf_event__process_feature,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
-			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace_info	 = perf_script__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
 			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.stat		 = perf_event__process_stat_event,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 477a8699f0b501e3c71a711fd6a5a336645a1c46..0077724fb24fe70cd1d20feb3995273da13b5228 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,17 +86,20 @@ static void perf_top__update_print_entries(struct perf_top *top)
 	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-				siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-	struct perf_top *top = arg;
+	resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
 	get_term_dimensions(&top->winsize);
 	perf_top__update_print_entries(top);
 }
 
 static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 {
+	struct perf_evsel *evsel = hists_to_evsel(he->hists);
 	struct symbol *sym;
 	struct annotation *notes;
 	struct map *map;
@@ -134,7 +138,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__disassemble(sym, map, NULL, 0, NULL, NULL);
+	err = symbol__annotate(sym, map, evsel, 0, NULL, NULL);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;
@@ -226,6 +230,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 static void perf_top__show_details(struct perf_top *top)
 {
 	struct hist_entry *he = top->sym_filter_entry;
+	struct perf_evsel *evsel = hists_to_evsel(he->hists);
 	struct annotation *notes;
 	struct symbol *symbol;
 	int more;
@@ -238,6 +243,8 @@ static void perf_top__show_details(struct perf_top *top)
 
 	pthread_mutex_lock(&notes->lock);
 
+	symbol__calc_percent(symbol, evsel);
+
 	if (notes->src == NULL)
 		goto out_unlock;
 
@@ -409,7 +416,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
 	fprintf(stdout, "\t[S]     stop annotation.\n");
 
 	fprintf(stdout,
-		"\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
+		"\t[K]     hide kernel symbols.             \t(%s)\n",
 		top->hide_kernel_symbols ? "yes" : "no");
 	fprintf(stdout,
 		"\t[U]     hide user symbols.               \t(%s)\n",
@@ -473,12 +480,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 		case 'e':
 			prompt_integer(&top->print_entries, "Enter display entries (lines)");
 			if (top->print_entries == 0) {
-				struct sigaction act = {
-					.sa_sigaction = perf_top__sig_winch,
-					.sa_flags     = SA_SIGINFO,
-				};
-				perf_top__sig_winch(SIGWINCH, NULL, top);
-				sigaction(SIGWINCH, &act, NULL);
+				perf_top__resize(top);
+				signal(SIGWINCH, winch_sig);
 			} else {
 				signal(SIGWINCH, SIG_DFL);
 			}
@@ -732,14 +735,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
-		ui__warning(
+		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
 			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
-		if (use_browser <= 0)
-			sleep(5);
+			if (use_browser <= 0)
+				sleep(5);
+		}
 		machine->kptr_restrict_warned = true;
 	}
 
@@ -1030,6 +1035,11 @@ static int __cmd_top(struct perf_top *top)
 
 		if (hits == top->samples)
 			ret = perf_evlist__poll(top->evlist, 100);
+
+		if (resize) {
+			perf_top__resize(top);
+			resize = 0;
+		}
 	}
 
 	ret = 0;
@@ -1352,12 +1362,8 @@ int cmd_top(int argc, const char **argv)
 
 	get_term_dimensions(&top.winsize);
 	if (top.print_entries == 0) {
-		struct sigaction act = {
-			.sa_sigaction = perf_top__sig_winch,
-			.sa_flags     = SA_SIGINFO,
-		};
 		perf_top__update_print_entries(&top);
-		sigaction(SIGWINCH, &act, NULL);
+		signal(SIGWINCH, winch_sig);
 	}
 
 	status = __cmd_top(&top);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f2757d38c7d7054d4dcef7d7e90f25efc115a8f7..84debdbad32717ce3f5a00cf646d778527cc6302 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1152,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-		return -errno;
+	err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+	if (err < 0)
+		goto out;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout, 1);
+out:
 	if (err)
 		symbol__exit();
 
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
index 18f6645f28975be1d428c9efe8c861563f982930..7945c5196c43975a06230374f311fd3e33fa8fce 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
@@ -124,11 +124,6 @@
     "EventName": "PM_CMPLU_STALL_LARX",
     "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied"
   },
-  {,
-    "EventCode": "0x3006C",
-    "EventName": "PM_RUN_CYC_SMT2_MODE",
-    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode"
-  },
   {,
     "EventCode": "0x1C058",
     "EventName": "PM_DTLB_MISS_16G",
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
index c63a919eda981bbc972e08d55a03a35ab4208645..bd8361b5fd6a66c31e68cd6d57ce020e405f7d0b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -1,9 +1,4 @@
 [
-  {,
-    "EventCode": "0x3E15C",
-    "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER",
-    "BriefDescription": "TM marked store abort for this thread"
-  },
   {,
     "EventCode": "0x25044",
     "EventName": "PM_IPTEG_FROM_L31_MOD",
@@ -369,4 +364,4 @@
     "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
index b9df54fb37e3690171f09c46f1d96d95d6e99684..22f9f32060a8765bdc91cb9b9e5430289f5dcfe0 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
@@ -1,9 +1,4 @@
 [
-  {,
-    "EventCode": "0x3C052",
-    "EventName": "PM_DATA_SYS_PUMP_MPRED",
-    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
-  },
   {,
     "EventCode": "0x3013E",
     "EventName": "PM_MRK_STALL_CMPLU_CYC",
@@ -254,6 +249,11 @@
     "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3",
     "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache"
   },
+  {,
+    "EventCode": "0x3C052",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
+  },
   {,
     "EventCode": "0x4D142",
     "EventName": "PM_MRK_DATA_FROM_L3",
@@ -434,21 +434,6 @@
     "EventName": "PM_ITLB_MISS",
     "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed"
   },
-  {,
-    "EventCode": "0x2D024",
-    "EventName": "PM_RADIX_PWC_L2_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache."
-  },
-  {,
-    "EventCode": "0x3F056",
-    "EventName": "PM_RADIX_PWC_L3_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache."
-  },
-  {,
-    "EventCode": "0x4E014",
-    "EventName": "PM_TM_TX_PASS_RUN_INST",
-    "BriefDescription": "Run instructions spent in successful transactions"
-  },
   {,
     "EventCode": "0x1E044",
     "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT",
@@ -644,4 +629,4 @@
     "EventName": "PM_MRK_BR_MPRED_CMPL",
     "BriefDescription": "Marked Branch Mispredicted"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
index 54cc3be00fc2d84903ce127eb9554ec7054dd9ed..5ce312973f1ece20a0982e6e1441b7e678f1d072 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -79,6 +79,11 @@
     "EventName": "PM_RADIX_PWC_MISS",
     "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache."
   },
+  {,
+    "EventCode": "0x26882",
+    "EventName": "PM_L2_DC_INV",
+    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
+  },
   {,
     "EventCode": "0x24048",
     "EventName": "PM_INST_FROM_LMEM",
@@ -94,11 +99,6 @@
     "EventName": "PM_TM_PASSED",
     "BriefDescription": "Number of TM transactions that passed"
   },
-  {,
-    "EventCode": "0xD1A0",
-    "EventName": "PM_MRK_LSU_FLUSH_LHS",
-    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
-  },
   {,
     "EventCode": "0xF088",
     "EventName": "PM_LSU0_STORE_REJECT",
@@ -127,7 +127,7 @@
   {,
     "EventCode": "0xD08C",
     "EventName": "PM_LSU2_LDMX_FIN",
-    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])"
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
   },
   {,
     "EventCode": "0x300F8",
@@ -204,11 +204,6 @@
     "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD_CYC",
     "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
   },
-  {,
-    "EventCode": "0xF0B4",
-    "EventName": "PM_DC_PREF_CONS_ALLOC",
-    "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch"
-  },
   {,
     "EventCode": "0xF894",
     "EventName": "PM_LSU3_L1_CAM_CANCEL",
@@ -219,21 +214,11 @@
     "EventName": "PM_FLUSH_DISP_TLBIE",
     "BriefDescription": "Dispatch Flush: TLBIE"
   },
-  {,
-    "EventCode": "0xD1A4",
-    "EventName": "PM_MRK_LSU_FLUSH_SAO",
-    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
-  },
   {,
     "EventCode": "0x4E11E",
     "EventName": "PM_MRK_DATA_FROM_DMEM_CYC",
     "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load"
   },
-  {,
-    "EventCode": "0x5894",
-    "EventName": "PM_LWSYNC",
-    "BriefDescription": "Lwsync instruction decoded and transferred"
-  },
   {,
     "EventCode": "0x14156",
     "EventName": "PM_MRK_DATA_FROM_L2_CYC",
@@ -244,11 +229,6 @@
     "EventName": "PM_RD_CLEARING_SC",
     "BriefDescription": "Read clearing SC"
   },
-  {,
-    "EventCode": "0x50A0",
-    "EventName": "PM_HWSYNC",
-    "BriefDescription": "Hwsync instruction decoded and transferred"
-  },
   {,
     "EventCode": "0x168B0",
     "EventName": "PM_L3_P1_NODE_PUMP",
@@ -264,6 +244,11 @@
     "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST",
     "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load"
   },
+  {,
+    "EventCode": "0x468AE",
+    "EventName": "PM_L3_P3_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 3 (memory only), every retry counted"
+  },
   {,
     "EventCode": "0x460A8",
     "EventName": "PM_SN_HIT",
@@ -279,11 +264,6 @@
     "EventName": "PM_DC_PREF_HW_ALLOC",
     "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism"
   },
-  {,
-    "EventCode": "0xF0BC",
-    "EventName": "PM_LS2_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
   {,
     "EventCode": "0xD0AC",
     "EventName": "PM_SRQ_SYNC_CYC",
@@ -379,26 +359,11 @@
     "EventName": "PM_RUN_CYC_SMT4_MODE",
     "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode"
   },
-  {,
-    "EventCode": "0x5088",
-    "EventName": "PM_DECODE_FUSION_OP_PRESERV",
-    "BriefDescription": "Destructive op operand preservation"
-  },
   {,
     "EventCode": "0x1D14E",
     "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC",
     "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
   },
-  {,
-    "EventCode": "0x509C",
-    "EventName": "PM_FORCED_NOP",
-    "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time"
-  },
-  {,
-    "EventCode": "0xC098",
-    "EventName": "PM_LS2_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
   {,
     "EventCode": "0x20058",
     "EventName": "PM_DARQ1_10_12_ENTRIES",
@@ -434,11 +399,6 @@
     "EventName": "PM_LSU1_STORE_REJECT",
     "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
   },
-  {,
-    "EventCode": "0x4505E",
-    "EventName": "PM_FLOP_CMPL",
-    "BriefDescription": "Floating Point Operation Finished"
-  },
   {,
     "EventCode": "0x1D144",
     "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT",
@@ -480,14 +440,9 @@
     "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT.  The EAT forces a mispredict in this case since there is no predicated target to validate.  This is a rare case that may occur when the EAT is full and a branch is issued"
   },
   {,
-    "EventCode": "0xC094",
-    "EventName": "PM_LS0_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
-    "EventCode": "0xF8BC",
-    "EventName": "PM_LS3_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+    "EventCode": "0x460AE",
+    "EventName": "PM_L3_P2_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 2 (memory only), every retry counted"
   },
   {,
     "EventCode": "0x58B0",
@@ -504,11 +459,6 @@
     "EventName": "PM_TM_ST_CONF",
     "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)"
   },
-  {,
-    "EventCode": "0xD998",
-    "EventName": "PM_MRK_LSU_FLUSH_EMSH",
-    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
-  },
   {,
     "EventCode": "0xF8A0",
     "EventName": "PM_NON_DATA_STORE",
@@ -524,11 +474,6 @@
     "EventName": "PM_BR_UNCOND",
     "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve."
   },
-  {,
-    "EventCode": "0x1F056",
-    "EventName": "PM_RADIX_PWC_L1_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit."
-  },
   {,
     "EventCode": "0xF8A8",
     "EventName": "PM_DC_PREF_FUZZY_CONF",
@@ -544,6 +489,11 @@
     "EventName": "PM_LSU2_TM_L1_MISS",
     "BriefDescription": "Load tm L1 miss"
   },
+  {,
+    "EventCode": "0xC880",
+    "EventName": "PM_LS1_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
   {,
     "EventCode": "0x2894",
     "EventName": "PM_TM_OUTER_TEND",
@@ -564,21 +514,11 @@
     "EventName": "PM_MRK_LSU_DERAT_MISS",
     "BriefDescription": "Marked derat reload (miss) for any page size"
   },
-  {,
-    "EventCode": "0x160A0",
-    "EventName": "PM_L3_PF_MISS_L3",
-    "BriefDescription": "L3 PF missed in L3"
-  },
   {,
     "EventCode": "0x1C04A",
     "EventName": "PM_DATA_FROM_RL2L3_SHR",
     "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
   },
-  {,
-    "EventCode": "0xD99C",
-    "EventName": "PM_MRK_LSU_FLUSH_UE",
-    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
-  },
   {,
     "EventCode": "0x268B0",
     "EventName": "PM_L3_P1_GRP_PUMP",
@@ -629,11 +569,6 @@
     "EventName": "PM_TMA_REQ_L2",
     "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding"
   },
-  {,
-    "EventCode": "0x5884",
-    "EventName": "PM_DECODE_LANES_NOT_AVAIL",
-    "BriefDescription": "Decode has something to transmit but dispatch lanes are not available"
-  },
   {,
     "EventCode": "0x3C042",
     "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT",
@@ -690,9 +625,9 @@
     "BriefDescription": "False LHS match detected"
   },
   {,
-    "EventCode": "0xD9A4",
-    "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX",
-    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+    "EventCode": "0xF0B0",
+    "EventName": "PM_L3_LD_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
   },
   {,
     "EventCode": "0x4D012",
@@ -715,9 +650,9 @@
     "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
   },
   {,
-    "EventCode": "0xF8B8",
-    "EventName": "PM_LS1_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+    "EventCode": "0x160A0",
+    "EventName": "PM_L3_PF_MISS_L3",
+    "BriefDescription": "L3 PF missed in L3"
   },
   {,
     "EventCode": "0x408C",
@@ -764,11 +699,6 @@
     "EventName": "PM_TM_NESTED_TEND",
     "BriefDescription": "Completion time nested tend"
   },
-  {,
-    "EventCode": "0x36084",
-    "EventName": "PM_L2_RCST_DISP",
-    "BriefDescription": "All D-side store dispatch attempts for this thread"
-  },
   {,
     "EventCode": "0x368A0",
     "EventName": "PM_L3_PF_OFF_CHIP_CACHE",
@@ -829,11 +759,6 @@
     "EventName": "PM_L3_SN_USAGE",
     "BriefDescription": "Rotating sample of 16 snoop valids"
   },
-  {,
-    "EventCode": "0x16084",
-    "EventName": "PM_L2_RCLD_DISP",
-    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
-  },
   {,
     "EventCode": "0x1608C",
     "EventName": "PM_RC0_BUSY",
@@ -842,7 +767,7 @@
   {,
     "EventCode": "0x36082",
     "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)"
   },
   {,
     "EventCode": "0xF8B0",
@@ -904,11 +829,6 @@
     "EventName": "PM_IC_PREF_REQ",
     "BriefDescription": "Instruction prefetch requests"
   },
-  {,
-    "EventCode": "0xC898",
-    "EventName": "PM_LS3_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
   {,
     "EventCode": "0x488C",
     "EventName": "PM_IC_PREF_WRITE",
@@ -1017,7 +937,7 @@
   {,
     "EventCode": "0x3E05E",
     "EventName": "PM_L3_CO_MEPF",
-    "BriefDescription": "L3 castouts in Mepf state for this thread"
+    "BriefDescription": "L3 CO of line in Mep state (includes casthrough to memory).  The Mepf state indicates that a line was brought in to satisfy an L3 prefetch request"
   },
   {,
     "EventCode": "0x460A2",
@@ -1204,11 +1124,6 @@
     "EventName": "PM_TM_FAIL_NON_TX_CONFLICT",
     "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR"
   },
-  {,
-    "EventCode": "0xD198",
-    "EventName": "PM_MRK_LSU_FLUSH_ATOMIC",
-    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
-  },
   {,
     "EventCode": "0x201E0",
     "EventName": "PM_MRK_DATA_FROM_MEMORY",
@@ -1294,11 +1209,6 @@
     "EventName": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL",
     "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
   },
-  {,
-    "EventCode": "0xC894",
-    "EventName": "PM_LS1_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
   {,
     "EventCode": "0x360A2",
     "EventName": "PM_L3_L2_CO_HIT",
@@ -1324,11 +1234,6 @@
     "EventName": "PM_L2_CASTOUT_SHR",
     "BriefDescription": "L2 Castouts - Shared (Tx,Sx)"
   },
-  {,
-    "EventCode": "0xD884",
-    "EventName": "PM_LSU3_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
   {,
     "EventCode": "0x26092",
     "EventName": "PM_L2_LD_MISS_64B",
@@ -1362,12 +1267,12 @@
   {,
     "EventCode": "0xD8A8",
     "EventName": "PM_ISLB_MISS",
-    "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
+    "BriefDescription": "Instruction SLB Miss - Total of all segment sizes"
   },
   {,
-    "EventCode": "0xD19C",
-    "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS",
-    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+    "EventCode": "0x368AE",
+    "EventName": "PM_L3_P1_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
   },
   {,
     "EventCode": "0x260A2",
@@ -1384,6 +1289,11 @@
     "EventName": "PM_CMPLU_STALL_NESTED_TBEGIN",
     "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT"
   },
+  {,
+    "EventCode": "0xC084",
+    "EventName": "PM_LS2_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
   {,
     "EventCode": "0x1608E",
     "EventName": "PM_ST_CAUSED_FAIL",
@@ -1409,11 +1319,6 @@
     "EventName": "PM_CO_USAGE",
     "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
   },
-  {,
-    "EventCode": "0xD084",
-    "EventName": "PM_LSU2_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
   {,
     "EventCode": "0x48B8",
     "EventName": "PM_BR_MPRED_TAKEN_TA",
@@ -1449,30 +1354,25 @@
     "EventName": "PM_DC_PREF_STRIDED_CONF",
     "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
   },
+  {,
+    "EventCode": "0x36084",
+    "EventName": "PM_L2_RCST_DISP",
+    "BriefDescription": "All D-side store dispatch attempts for this thread"
+  },
   {,
     "EventCode": "0x45054",
     "EventName": "PM_FMA_CMPL",
     "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. "
   },
-  {,
-    "EventCode": "0x5090",
-    "EventName": "PM_SHL_ST_DISABLE",
-    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)"
-  },
   {,
     "EventCode": "0x201E8",
     "EventName": "PM_THRESH_EXC_512",
     "BriefDescription": "Threshold counter exceeded a value of 512"
   },
-  {,
-    "EventCode": "0x5084",
-    "EventName": "PM_DECODE_FUSION_EXT_ADD",
-    "BriefDescription": "32-bit extended addition"
-  },
   {,
     "EventCode": "0x36080",
     "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
+    "BriefDescription": "All successful I-side dispatches for this thread   (excludes i_l2mru_tch reqs)"
   },
   {,
     "EventCode": "0x3504C",
@@ -1554,21 +1454,11 @@
     "EventName": "PM_MEM_RWITM",
     "BriefDescription": "Memory Read With Intent to Modify for this thread"
   },
-  {,
-    "EventCode": "0x26882",
-    "EventName": "PM_L2_DC_INV",
-    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
-  },
   {,
     "EventCode": "0xC090",
     "EventName": "PM_LSU_STCX",
     "BriefDescription": "STCX sent to nest, i.e. total"
   },
-  {,
-    "EventCode": "0xD080",
-    "EventName": "PM_LSU0_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
   {,
     "EventCode": "0x2C120",
     "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT",
@@ -1609,11 +1499,6 @@
     "EventName": "PM_IPTEG_FROM_L2_NO_CONFLICT",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request"
   },
-  {,
-    "EventCode": "0xD9A0",
-    "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL",
-    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
-  },
   {,
     "EventCode": "0x35042",
     "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT",
@@ -1692,7 +1577,7 @@
   {,
     "EventCode": "0x2001A",
     "EventName": "PM_NTC_ALL_FIN",
-    "BriefDescription": "Cycles after all instructions have finished to group completed"
+    "BriefDescription": "Cycles after instruction finished to instruction completed."
   },
   {,
     "EventCode": "0x3005A",
@@ -1709,6 +1594,11 @@
     "EventName": "PM_LSU1_L1_CAM_CANCEL",
     "BriefDescription": "ls1 l1 tm cam cancel"
   },
+  {,
+    "EventCode": "0x268AE",
+    "EventName": "PM_L3_P3_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 3, every retry counted"
+  },
   {,
     "EventCode": "0xE884",
     "EventName": "PM_LS1_ERAT_MISS_PREF",
@@ -1742,7 +1632,7 @@
   {,
     "EventCode": "0x160B6",
     "EventName": "PM_L3_WI0_BUSY",
-    "BriefDescription": "Rotating sample of 8 WI valid"
+    "BriefDescription": "Rotating sample of 8 WI valid (duplicate)"
   },
   {,
     "EventCode": "0x368AC",
@@ -1790,9 +1680,9 @@
     "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)"
   },
   {,
-    "EventCode": "0x589C",
-    "EventName": "PM_PTESYNC",
-    "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted"
+    "EventCode": "0x260AE",
+    "EventName": "PM_L3_P2_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 2, every retry counted"
   },
   {,
     "EventCode": "0x26086",
@@ -1824,6 +1714,11 @@
     "EventName": "PM_SHL_ST_DEP_CREATED",
     "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled"
   },
+  {,
+    "EventCode": "0x46882",
+    "EventName": "PM_L2_ST_HIT",
+    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+  },
   {,
     "EventCode": "0x360AC",
     "EventName": "PM_L3_SN0_BUSY",
@@ -1844,11 +1739,6 @@
     "EventName": "PM_L2_ST_MISS",
     "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread"
   },
-  {,
-    "EventCode": "0xF8B4",
-    "EventName": "PM_DC_PREF_XCONS_ALLOC",
-    "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch"
-  },
   {,
     "EventCode": "0x35048",
     "EventName": "PM_IPTEG_FROM_DL2L3_SHR",
@@ -1969,11 +1859,6 @@
     "EventName": "PM_THRD_PRIO_2_3_CYC",
     "BriefDescription": "Cycles thread running at priority level 2 or 3"
   },
-  {,
-    "EventCode": "0x10134",
-    "EventName": "PM_MRK_ST_DONE_L2",
-    "BriefDescription": "marked store completed in L2 ( RC machine done)"
-  },
   {,
     "EventCode": "0x368B2",
     "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
@@ -2004,11 +1889,6 @@
     "EventName": "PM_L2_GRP_GUESS_WRONG",
     "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)"
   },
-  {,
-    "EventCode": "0x368AE",
-    "EventName": "PM_L3_P1_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
-  },
   {,
     "EventCode": "0xC0AC",
     "EventName": "PM_LSU_FLUSH_EMSH",
@@ -2034,11 +1914,6 @@
     "EventName": "PM_L2_GROUP_PUMP",
     "BriefDescription": "RC requests that were on group (aka nodel) pump attempts"
   },
-  {,
-    "EventCode": "0xF0B0",
-    "EventName": "PM_L3_LD_PREF",
-    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
-  },
   {,
     "EventCode": "0x16080",
     "EventName": "PM_L2_LD",
@@ -2049,6 +1924,11 @@
     "EventName": "PM_MATH_FLOP_CMPL",
     "BriefDescription": "Math flop instruction completed"
   },
+  {,
+    "EventCode": "0xC080",
+    "EventName": "PM_LS0_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
   {,
     "EventCode": "0x368B0",
     "EventName": "PM_L3_P1_SYS_PUMP",
@@ -2119,11 +1999,6 @@
     "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL",
     "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
   },
-  {,
-    "EventCode": "0xF0B8",
-    "EventName": "PM_LS0_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
   {,
     "EventCode": "0x20132",
     "EventName": "PM_MRK_DFU_FIN",
@@ -2139,6 +2014,11 @@
     "EventName": "PM_LSU_FLUSH_LHS",
     "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
   },
+  {,
+    "EventCode": "0x16084",
+    "EventName": "PM_L2_RCLD_DISP",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
   {,
     "EventCode": "0x3F150",
     "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC",
@@ -2224,11 +2104,6 @@
     "EventName": "PM_IC_PREF_CANCEL_PAGE",
     "BriefDescription": "Prefetch Canceled due to page boundary"
   },
-  {,
-    "EventCode": "0xF09C",
-    "EventName": "PM_SLB_TABLEWALK_CYC",
-    "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table"
-  },
   {,
     "EventCode": "0x460AA",
     "EventName": "PM_L3_P0_CO_L31",
@@ -2247,10 +2122,10 @@
   {,
     "EventCode": "0x46082",
     "EventName": "PM_L2_ST_DISP",
-    "BriefDescription": "All successful D-side store dispatches for this thread "
+    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
   },
   {,
-    "EventCode": "0x4609E",
+    "EventCode": "0x36880",
     "EventName": "PM_L2_INST_MISS",
     "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
   },
@@ -2340,9 +2215,9 @@
     "BriefDescription": "All ISU rejects"
   },
   {,
-    "EventCode": "0x46882",
-    "EventName": "PM_L2_ST_HIT",
-    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+    "EventCode": "0xC884",
+    "EventName": "PM_LS3_LD_VECTOR_FIN",
+    "BriefDescription": ""
   },
   {,
     "EventCode": "0x360A8",
@@ -2359,11 +2234,6 @@
     "EventName": "PM_LSU_NCST",
     "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1"
   },
-  {,
-    "EventCode": "0xD880",
-    "EventName": "PM_LSU1_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
   {,
     "EventCode": "0xD0B8",
     "EventName": "PM_LSU_LMQ_FULL_CYC",
@@ -2389,4 +2259,4 @@
     "EventName": "PM_L3_PF_USAGE",
     "BriefDescription": "Rotating sample of 32 PF actives"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
index bc2db636dabf1612c7c698fb3555319f763755c7..5af1abbe82c48b1943893798216b871baac7a157 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -124,6 +124,11 @@
     "EventName": "PM_PMC5_OVERFLOW",
     "BriefDescription": "Overflow from counter 5"
   },
+  {,
+    "EventCode": "0x4505E",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operation Finished"
+  },
   {,
     "EventCode": "0x2C018",
     "EventName": "PM_CMPLU_STALL_DMISS_L21_L31",
@@ -389,11 +394,6 @@
     "EventName": "PM_ICT_NOSLOT_BR_MPRED",
     "BriefDescription": "Ict empty for this thread due to branch mispred"
   },
-  {,
-    "EventCode": "0x3405E",
-    "EventName": "PM_IFETCH_THROTTLE",
-    "BriefDescription": "Cycles in which Instruction fetch throttle was active."
-  },
   {,
     "EventCode": "0x1F148",
     "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE",
@@ -422,7 +422,7 @@
   {,
     "EventCode": "0xD0A8",
     "EventName": "PM_DSLB_MISS",
-    "BriefDescription": "Data SLB Miss - Total of all segment sizes"
+    "BriefDescription": "gate_and(sd_pc_c0_comp_valid AND sd_pc_c0_comp_thread(0:1)=tid,sd_pc_c0_comp_ppc_count(0:3)) + gate_and(sd_pc_c1_comp_valid AND sd_pc_c1_comp_thread(0:1)=tid,sd_pc_c1_comp_ppc_count(0:3))"
   },
   {,
     "EventCode": "0x4C058",
@@ -549,4 +549,4 @@
     "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC",
     "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
index 3ef8a10aac8638965391ffef28052f5f2bc59ac5..d0b89f93056758b1dceccc56de9edc0e749d3f98 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -119,4 +119,4 @@
     "EventName": "PM_1FLOP_CMPL",
     "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
index 8c0f12024afaf78ea0cc85bb71204a4c1e23dd38..bc8e03d7a6b0370fcc9445d7bf0ae9551c353074 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
@@ -89,11 +89,6 @@
     "EventName": "PM_STCX_FAIL",
     "BriefDescription": "stcx failed"
   },
-  {,
-    "EventCode": "0x20112",
-    "EventName": "PM_MRK_NTF_FIN",
-    "BriefDescription": "Marked next to finish instruction finished"
-  },
   {,
     "EventCode": "0x300F0",
     "EventName": "PM_ST_MISS_L1",
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0e1367f90af5355576a49e3693474f91686b5a7c..97f64ad7fa08e236a3bde6923900e25f8b84bc1f 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -124,6 +124,12 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	WRITE_ASS(exclude_guest,  "d");
 	WRITE_ASS(exclude_callchain_kernel, "d");
 	WRITE_ASS(exclude_callchain_user, "d");
+	WRITE_ASS(mmap2,	  "d");
+	WRITE_ASS(comm_exec,	  "d");
+	WRITE_ASS(context_switch, "d");
+	WRITE_ASS(write_backward, "d");
+	WRITE_ASS(namespaces,	  "d");
+	WRITE_ASS(use_clockid,    "d");
 	WRITE_ASS(wakeup_events, PRIu32);
 	WRITE_ASS(bp_type, PRIu32);
 	WRITE_ASS(config1, "llu");
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 71b9a0b613d2b2fcedee056de59d9ea56ec78516..43a8c6ac4070e3b50868b39d3de0fdd38cbcfa5c 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 	int err;
 	char sbuf[STRERR_BUFSIZE];
 
-	err = perf_evlist__mmap(evlist, mmap_pages, true);
+	err = perf_evlist__mmap(evlist, mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5a8bf318f8a7ed4d832b4119da75927c2536903b..91f10d6d9ae2f17c599b6c597f7e0658d1c83abf 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		expected_nr_events[i] = 1 + rand() % 127;
 	}
 
-	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+	if (perf_evlist__mmap(evlist, 128, false) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 7a84d73324e3c1209781296dcc54260745150b53..8b3da21a08f19a110a3e9c2519495460da2eb310 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
 	idx=0
@@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() {
 	done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2e68c5f120da87250a87b5067793e2ca75ced60c..2a9ef080efd028a1038ab214c05012f7d9186aa7 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	perf trace -e open touch $file 2>&1 | \
-	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
+
+	perf trace -e ${svc:-open} touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 725a196991a88447cf0f80adf5b05bb47ad1f39e..c6937ed12e6bc6364c91bba77b85ff943719836e 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		goto out_delete_evlist;
 	}
 
-	err = perf_evlist__mmap(evlist, 128, true);
+	err = perf_evlist__mmap(evlist, 128, false);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a7344e274255141e54e8ec28f47a0d12e6819..98c098475e71dd49dc4d3a0f2028a0448acd9712 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -97,7 +97,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		goto out_delete_evlist;
 	}
 
-	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+	if (perf_evlist__mmap(evlist, 128, false) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 8f7f59d1a2b5913c2a3027a89384011dab86c9e5..03b7363a49c9ae646ac731078fe3fc52a8c5450f 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -25,16 +25,10 @@ struct disasm_line_samples {
 #define IPC_WIDTH 6
 #define CYCLES_WIDTH 6
 
-struct browser_disasm_line {
-	struct rb_node			rb_node;
-	u32				idx;
-	int				idx_asm;
-	int				jump_sources;
-	/*
-	 * actual length of this array is saved on the nr_events field
-	 * of the struct annotate_browser
-	 */
-	struct disasm_line_samples	samples[1];
+struct browser_line {
+	u32	idx;
+	int	idx_asm;
+	int	jump_sources;
 };
 
 static struct annotate_browser_opt {
@@ -53,39 +47,43 @@ static struct annotate_browser_opt {
 struct arch;
 
 struct annotate_browser {
-	struct ui_browser b;
-	struct rb_root	  entries;
-	struct rb_node	  *curr_hot;
-	struct disasm_line  *selection;
-	struct disasm_line  **offsets;
-	struct arch	    *arch;
-	int		    nr_events;
-	u64		    start;
-	int		    nr_asm_entries;
-	int		    nr_entries;
-	int		    max_jump_sources;
-	int		    nr_jumps;
-	bool		    searching_backwards;
-	bool		    have_cycles;
-	u8		    addr_width;
-	u8		    jumps_width;
-	u8		    target_width;
-	u8		    min_addr_width;
-	u8		    max_addr_width;
-	char		    search_bf[128];
+	struct ui_browser	    b;
+	struct rb_root		    entries;
+	struct rb_node		   *curr_hot;
+	struct annotation_line	   *selection;
+	struct annotation_line	  **offsets;
+	struct arch		   *arch;
+	int			    nr_events;
+	u64			    start;
+	int			    nr_asm_entries;
+	int			    nr_entries;
+	int			    max_jump_sources;
+	int			    nr_jumps;
+	bool			    searching_backwards;
+	bool			    have_cycles;
+	u8			    addr_width;
+	u8			    jumps_width;
+	u8			    target_width;
+	u8			    min_addr_width;
+	u8			    max_addr_width;
+	char			    search_bf[128];
 };
 
-static inline struct browser_disasm_line *disasm_line__browser(struct disasm_line *dl)
+static inline struct browser_line *browser_line(struct annotation_line *al)
 {
-	return (struct browser_disasm_line *)(dl + 1);
+	void *ptr = al;
+
+	ptr = container_of(al, struct disasm_line, al);
+	return ptr - sizeof(struct browser_line);
 }
 
 static bool disasm_line__filter(struct ui_browser *browser __maybe_unused,
 				void *entry)
 {
 	if (annotate_browser__opts.hide_src_code) {
-		struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
-		return dl->offset == -1;
+		struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+
+		return al->offset == -1;
 	}
 
 	return false;
@@ -120,11 +118,37 @@ static int annotate_browser__cycles_width(struct annotate_browser *ab)
 	return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0;
 }
 
+static void disasm_line__write(struct disasm_line *dl, struct ui_browser *browser,
+			       char *bf, size_t size)
+{
+	if (dl->ins.ops && dl->ins.ops->scnprintf) {
+		if (ins__is_jump(&dl->ins)) {
+			bool fwd = dl->ops.target.offset > dl->al.offset;
+
+			ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
+							    SLSMG_UARROW_CHAR);
+			SLsmg_write_char(' ');
+		} else if (ins__is_call(&dl->ins)) {
+			ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
+			SLsmg_write_char(' ');
+		} else if (ins__is_ret(&dl->ins)) {
+			ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+			SLsmg_write_char(' ');
+		} else {
+			ui_browser__write_nstring(browser, " ", 2);
+		}
+	} else {
+		ui_browser__write_nstring(browser, " ", 2);
+	}
+
+	disasm_line__scnprintf(dl, bf, size, !annotate_browser__opts.use_offset);
+}
+
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
-	struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
-	struct browser_disasm_line *bdl = disasm_line__browser(dl);
+	struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+	struct browser_line *bl = browser_line(al);
 	bool current_entry = ui_browser__is_current_entry(browser, row);
 	bool change_color = (!annotate_browser__opts.hide_src_code &&
 			     (!current_entry || (browser->use_navkeypressed &&
@@ -137,32 +161,32 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	bool show_title = false;
 
 	for (i = 0; i < ab->nr_events; i++) {
-		if (bdl->samples[i].percent > percent_max)
-			percent_max = bdl->samples[i].percent;
+		if (al->samples[i].percent > percent_max)
+			percent_max = al->samples[i].percent;
 	}
 
-	if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) {
+	if ((row == 0) && (al->offset == -1 || percent_max == 0.0)) {
 		if (ab->have_cycles) {
-			if (dl->ipc == 0.0 && dl->cycles == 0)
+			if (al->ipc == 0.0 && al->cycles == 0)
 				show_title = true;
 		} else
 			show_title = true;
 	}
 
-	if (dl->offset != -1 && percent_max != 0.0) {
+	if (al->offset != -1 && percent_max != 0.0) {
 		for (i = 0; i < ab->nr_events; i++) {
 			ui_browser__set_percent_color(browser,
-						bdl->samples[i].percent,
+						al->samples[i].percent,
 						current_entry);
 			if (annotate_browser__opts.show_total_period) {
 				ui_browser__printf(browser, "%11" PRIu64 " ",
-						   bdl->samples[i].he.period);
+						   al->samples[i].he.period);
 			} else if (annotate_browser__opts.show_nr_samples) {
 				ui_browser__printf(browser, "%6" PRIu64 " ",
-						   bdl->samples[i].he.nr_samples);
+						   al->samples[i].he.nr_samples);
 			} else {
 				ui_browser__printf(browser, "%6.2f ",
-						   bdl->samples[i].percent);
+						   al->samples[i].percent);
 			}
 		}
 	} else {
@@ -177,16 +201,16 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		}
 	}
 	if (ab->have_cycles) {
-		if (dl->ipc)
-			ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc);
+		if (al->ipc)
+			ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, al->ipc);
 		else if (!show_title)
 			ui_browser__write_nstring(browser, " ", IPC_WIDTH);
 		else
 			ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC");
 
-		if (dl->cycles)
+		if (al->cycles)
 			ui_browser__printf(browser, "%*" PRIu64 " ",
-					   CYCLES_WIDTH - 1, dl->cycles);
+					   CYCLES_WIDTH - 1, al->cycles);
 		else if (!show_title)
 			ui_browser__write_nstring(browser, " ", CYCLES_WIDTH);
 		else
@@ -199,19 +223,19 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	if (!browser->navkeypressed)
 		width += 1;
 
-	if (!*dl->line)
+	if (!*al->line)
 		ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width);
-	else if (dl->offset == -1) {
-		if (dl->line_nr && annotate_browser__opts.show_linenr)
+	else if (al->offset == -1) {
+		if (al->line_nr && annotate_browser__opts.show_linenr)
 			printed = scnprintf(bf, sizeof(bf), "%-*d ",
-					ab->addr_width + 1, dl->line_nr);
+					ab->addr_width + 1, al->line_nr);
 		else
 			printed = scnprintf(bf, sizeof(bf), "%*s  ",
 				    ab->addr_width, " ");
 		ui_browser__write_nstring(browser, bf, printed);
-		ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width - cycles_width + 1);
+		ui_browser__write_nstring(browser, al->line, width - printed - pcnt_width - cycles_width + 1);
 	} else {
-		u64 addr = dl->offset;
+		u64 addr = al->offset;
 		int color = -1;
 
 		if (!annotate_browser__opts.use_offset)
@@ -220,13 +244,13 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		if (!annotate_browser__opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
-			if (bdl->jump_sources) {
+			if (bl->jump_sources) {
 				if (annotate_browser__opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
 							    ab->jumps_width,
-							    bdl->jump_sources);
-					prev = annotate_browser__set_jumps_percent_color(ab, bdl->jump_sources,
+							    bl->jump_sources);
+					prev = annotate_browser__set_jumps_percent_color(ab, bl->jump_sources,
 											 current_entry);
 					ui_browser__write_nstring(browser, bf, printed);
 					ui_browser__set_color(browser, prev);
@@ -245,32 +269,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		ui_browser__write_nstring(browser, bf, printed);
 		if (change_color)
 			ui_browser__set_color(browser, color);
-		if (dl->ins.ops && dl->ins.ops->scnprintf) {
-			if (ins__is_jump(&dl->ins)) {
-				bool fwd = dl->ops.target.offset > dl->offset;
-
-				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
-								    SLSMG_UARROW_CHAR);
-				SLsmg_write_char(' ');
-			} else if (ins__is_call(&dl->ins)) {
-				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
-				SLsmg_write_char(' ');
-			} else if (ins__is_ret(&dl->ins)) {
-				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-				SLsmg_write_char(' ');
-			} else {
-				ui_browser__write_nstring(browser, " ", 2);
-			}
-		} else {
-			ui_browser__write_nstring(browser, " ", 2);
-		}
 
-		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
+		disasm_line__write(disasm_line(al), browser, bf, sizeof(bf));
+
 		ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed);
 	}
 
 	if (current_entry)
-		ab->selection = dl;
+		ab->selection = al;
 }
 
 static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
@@ -286,7 +292,7 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
 
 static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 {
-	struct disasm_line *pos = list_prev_entry(cursor, node);
+	struct disasm_line *pos = list_prev_entry(cursor, al.node);
 	const char *name;
 
 	if (!pos)
@@ -306,8 +312,9 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
-	struct disasm_line *cursor = ab->selection, *target;
-	struct browser_disasm_line *btarget, *bcursor;
+	struct disasm_line *cursor = disasm_line(ab->selection);
+	struct annotation_line *target;
+	struct browser_line *btarget, *bcursor;
 	unsigned int from, to;
 	struct map_symbol *ms = ab->b.priv;
 	struct symbol *sym = ms->sym;
@@ -321,11 +328,9 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		return;
 
 	target = ab->offsets[cursor->ops.target.offset];
-	if (!target)
-		return;
 
-	bcursor = disasm_line__browser(cursor);
-	btarget = disasm_line__browser(target);
+	bcursor = browser_line(&cursor->al);
+	btarget = browser_line(target);
 
 	if (annotate_browser__opts.hide_src_code) {
 		from = bcursor->idx_asm;
@@ -361,12 +366,11 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 	return ret;
 }
 
-static int disasm__cmp(struct browser_disasm_line *a,
-		       struct browser_disasm_line *b, int nr_pcnt)
+static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
 {
 	int i;
 
-	for (i = 0; i < nr_pcnt; i++) {
+	for (i = 0; i < a->samples_nr; i++) {
 		if (a->samples[i].percent == b->samples[i].percent)
 			continue;
 		return a->samples[i].percent < b->samples[i].percent;
@@ -374,28 +378,27 @@ static int disasm__cmp(struct browser_disasm_line *a,
 	return 0;
 }
 
-static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl,
-				   int nr_events)
+static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
-	struct browser_disasm_line *l;
+	struct annotation_line *l;
 
 	while (*p != NULL) {
 		parent = *p;
-		l = rb_entry(parent, struct browser_disasm_line, rb_node);
+		l = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (disasm__cmp(bdl, l, nr_events))
+		if (disasm__cmp(al, l))
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
 	}
-	rb_link_node(&bdl->rb_node, parent, p);
-	rb_insert_color(&bdl->rb_node, root);
+	rb_link_node(&al->rb_node, parent, p);
+	rb_insert_color(&al->rb_node, root);
 }
 
 static void annotate_browser__set_top(struct annotate_browser *browser,
-				      struct disasm_line *pos, u32 idx)
+				      struct annotation_line *pos, u32 idx)
 {
 	unsigned back;
 
@@ -404,7 +407,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 	browser->b.top_idx = browser->b.index = idx;
 
 	while (browser->b.top_idx != 0 && back != 0) {
-		pos = list_entry(pos->node.prev, struct disasm_line, node);
+		pos = list_entry(pos->node.prev, struct annotation_line, node);
 
 		if (disasm_line__filter(&browser->b, &pos->node))
 			continue;
@@ -420,12 +423,13 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 					 struct rb_node *nd)
 {
-	struct browser_disasm_line *bpos;
-	struct disasm_line *pos;
+	struct browser_line *bpos;
+	struct annotation_line *pos;
 	u32 idx;
 
-	bpos = rb_entry(nd, struct browser_disasm_line, rb_node);
-	pos = ((struct disasm_line *)bpos) - 1;
+	pos = rb_entry(nd, struct annotation_line, rb_node);
+	bpos = browser_line(pos);
+
 	idx = bpos->idx;
 	if (annotate_browser__opts.hide_src_code)
 		idx = bpos->idx_asm;
@@ -439,46 +443,35 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *pos, *next;
-	s64 len = symbol__size(sym);
+	struct disasm_line *pos;
 
 	browser->entries = RB_ROOT;
 
 	pthread_mutex_lock(&notes->lock);
 
-	list_for_each_entry(pos, &notes->src->source, node) {
-		struct browser_disasm_line *bpos = disasm_line__browser(pos);
-		const char *path = NULL;
+	symbol__calc_percent(sym, evsel);
+
+	list_for_each_entry(pos, &notes->src->source, al.node) {
 		double max_percent = 0.0;
 		int i;
 
-		if (pos->offset == -1) {
-			RB_CLEAR_NODE(&bpos->rb_node);
+		if (pos->al.offset == -1) {
+			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
 
-		next = disasm__get_next_ip_line(&notes->src->source, pos);
-
-		for (i = 0; i < browser->nr_events; i++) {
-			struct sym_hist_entry sample;
-
-			bpos->samples[i].percent = disasm__calc_percent(notes,
-						evsel->idx + i,
-						pos->offset,
-						next ? next->offset : len,
-						&path, &sample);
-			bpos->samples[i].he = sample;
+		for (i = 0; i < pos->al.samples_nr; i++) {
+			struct annotation_data *sample = &pos->al.samples[i];
 
-			if (max_percent < bpos->samples[i].percent)
-				max_percent = bpos->samples[i].percent;
+			if (max_percent < sample->percent)
+				max_percent = sample->percent;
 		}
 
-		if (max_percent < 0.01 && pos->ipc == 0) {
-			RB_CLEAR_NODE(&bpos->rb_node);
+		if (max_percent < 0.01 && pos->al.ipc == 0) {
+			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
-		disasm_rb_tree__insert(&browser->entries, bpos,
-				       browser->nr_events);
+		disasm_rb_tree__insert(&browser->entries, &pos->al);
 	}
 	pthread_mutex_unlock(&notes->lock);
 
@@ -487,38 +480,38 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 
 static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 {
-	struct disasm_line *dl;
-	struct browser_disasm_line *bdl;
+	struct annotation_line *al;
+	struct browser_line *bl;
 	off_t offset = browser->b.index - browser->b.top_idx;
 
 	browser->b.seek(&browser->b, offset, SEEK_CUR);
-	dl = list_entry(browser->b.top, struct disasm_line, node);
-	bdl = disasm_line__browser(dl);
+	al = list_entry(browser->b.top, struct annotation_line, node);
+	bl = browser_line(al);
 
 	if (annotate_browser__opts.hide_src_code) {
-		if (bdl->idx_asm < offset)
-			offset = bdl->idx;
+		if (bl->idx_asm < offset)
+			offset = bl->idx;
 
 		browser->b.nr_entries = browser->nr_entries;
 		annotate_browser__opts.hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
-		browser->b.top_idx = bdl->idx - offset;
-		browser->b.index = bdl->idx;
+		browser->b.top_idx = bl->idx - offset;
+		browser->b.index = bl->idx;
 	} else {
-		if (bdl->idx_asm < 0) {
+		if (bl->idx_asm < 0) {
 			ui_helpline__puts("Only available for assembly lines.");
 			browser->b.seek(&browser->b, -offset, SEEK_CUR);
 			return false;
 		}
 
-		if (bdl->idx_asm < offset)
-			offset = bdl->idx_asm;
+		if (bl->idx_asm < offset)
+			offset = bl->idx_asm;
 
 		browser->b.nr_entries = browser->nr_asm_entries;
 		annotate_browser__opts.hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
-		browser->b.top_idx = bdl->idx_asm - offset;
-		browser->b.index = bdl->idx_asm;
+		browser->b.top_idx = bl->idx_asm - offset;
+		browser->b.index = bl->idx_asm;
 	}
 
 	return true;
@@ -543,7 +536,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 				    struct hist_browser_timer *hbt)
 {
 	struct map_symbol *ms = browser->b.priv;
-	struct disasm_line *dl = browser->selection;
+	struct disasm_line *dl = disasm_line(browser->selection);
 	struct annotation *notes;
 	struct addr_map_symbol target = {
 		.map = ms->map,
@@ -589,10 +582,10 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 	struct disasm_line *pos;
 
 	*idx = 0;
-	list_for_each_entry(pos, &notes->src->source, node) {
-		if (pos->offset == offset)
+	list_for_each_entry(pos, &notes->src->source, al.node) {
+		if (pos->al.offset == offset)
 			return pos;
-		if (!disasm_line__filter(&browser->b, &pos->node))
+		if (!disasm_line__filter(&browser->b, &pos->al.node))
 			++*idx;
 	}
 
@@ -601,7 +594,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 
 static bool annotate_browser__jump(struct annotate_browser *browser)
 {
-	struct disasm_line *dl = browser->selection;
+	struct disasm_line *dl = disasm_line(browser->selection);
 	u64 offset;
 	s64 idx;
 
@@ -615,29 +608,29 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
 		return true;
 	}
 
-	annotate_browser__set_top(browser, dl, idx);
+	annotate_browser__set_top(browser, &dl->al, idx);
 
 	return true;
 }
 
 static
-struct disasm_line *annotate_browser__find_string(struct annotate_browser *browser,
+struct annotation_line *annotate_browser__find_string(struct annotate_browser *browser,
 					  char *s, s64 *idx)
 {
 	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *pos = browser->selection;
+	struct annotation_line *al = browser->selection;
 
 	*idx = browser->b.index;
-	list_for_each_entry_continue(pos, &notes->src->source, node) {
-		if (disasm_line__filter(&browser->b, &pos->node))
+	list_for_each_entry_continue(al, &notes->src->source, node) {
+		if (disasm_line__filter(&browser->b, &al->node))
 			continue;
 
 		++*idx;
 
-		if (pos->line && strstr(pos->line, s) != NULL)
-			return pos;
+		if (al->line && strstr(al->line, s) != NULL)
+			return al;
 	}
 
 	return NULL;
@@ -645,38 +638,38 @@ struct disasm_line *annotate_browser__find_string(struct annotate_browser *brows
 
 static bool __annotate_browser__search(struct annotate_browser *browser)
 {
-	struct disasm_line *dl;
+	struct annotation_line *al;
 	s64 idx;
 
-	dl = annotate_browser__find_string(browser, browser->search_bf, &idx);
-	if (dl == NULL) {
+	al = annotate_browser__find_string(browser, browser->search_bf, &idx);
+	if (al == NULL) {
 		ui_helpline__puts("String not found!");
 		return false;
 	}
 
-	annotate_browser__set_top(browser, dl, idx);
+	annotate_browser__set_top(browser, al, idx);
 	browser->searching_backwards = false;
 	return true;
 }
 
 static
-struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
+struct annotation_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
 						  char *s, s64 *idx)
 {
 	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *pos = browser->selection;
+	struct annotation_line *al = browser->selection;
 
 	*idx = browser->b.index;
-	list_for_each_entry_continue_reverse(pos, &notes->src->source, node) {
-		if (disasm_line__filter(&browser->b, &pos->node))
+	list_for_each_entry_continue_reverse(al, &notes->src->source, node) {
+		if (disasm_line__filter(&browser->b, &al->node))
 			continue;
 
 		--*idx;
 
-		if (pos->line && strstr(pos->line, s) != NULL)
-			return pos;
+		if (al->line && strstr(al->line, s) != NULL)
+			return al;
 	}
 
 	return NULL;
@@ -684,16 +677,16 @@ struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browse
 
 static bool __annotate_browser__search_reverse(struct annotate_browser *browser)
 {
-	struct disasm_line *dl;
+	struct annotation_line *al;
 	s64 idx;
 
-	dl = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
-	if (dl == NULL) {
+	al = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
+	if (al == NULL) {
 		ui_helpline__puts("String not found!");
 		return false;
 	}
 
-	annotate_browser__set_top(browser, dl, idx);
+	annotate_browser__set_top(browser, al, idx);
 	browser->searching_backwards = true;
 	return true;
 }
@@ -899,13 +892,16 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
+		{
+			struct disasm_line *dl = disasm_line(browser->selection);
+
 			if (browser->selection == NULL)
 				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
 			else if (browser->selection->offset == -1)
 				ui_helpline__puts("Actions are only available for assembly lines.");
-			else if (!browser->selection->ins.ops)
+			else if (!dl->ins.ops)
 				goto show_sup_ins;
-			else if (ins__is_ret(&browser->selection->ins))
+			else if (ins__is_ret(&dl->ins))
 				goto out;
 			else if (!(annotate_browser__jump(browser) ||
 				     annotate_browser__callq(browser, evsel, hbt))) {
@@ -913,6 +909,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
 			}
 			continue;
+		}
 		case 't':
 			if (annotate_browser__opts.show_total_period) {
 				annotate_browser__opts.show_total_period = false;
@@ -990,10 +987,10 @@ static void count_and_fill(struct annotate_browser *browser, u64 start, u64 end,
 			return;
 
 		for (offset = start; offset <= end; offset++) {
-			struct disasm_line *dl = browser->offsets[offset];
+			struct annotation_line *al = browser->offsets[offset];
 
-			if (dl)
-				dl->ipc = ipc;
+			if (al)
+				al->ipc = ipc;
 		}
 	}
 }
@@ -1018,13 +1015,13 @@ static void annotate__compute_ipc(struct annotate_browser *browser, size_t size,
 
 		ch = &notes->src->cycles_hist[offset];
 		if (ch && ch->cycles) {
-			struct disasm_line *dl;
+			struct annotation_line *al;
 
 			if (ch->have_start)
 				count_and_fill(browser, ch->start, offset, ch);
-			dl = browser->offsets[offset];
-			if (dl && ch->num_aggr)
-				dl->cycles = ch->cycles_aggr / ch->num_aggr;
+			al = browser->offsets[offset];
+			if (al && ch->num_aggr)
+				al->cycles = ch->cycles_aggr / ch->num_aggr;
 			browser->have_cycles = true;
 		}
 	}
@@ -1043,23 +1040,27 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser
 		return;
 
 	for (offset = 0; offset < size; ++offset) {
-		struct disasm_line *dl = browser->offsets[offset], *dlt;
-		struct browser_disasm_line *bdlt;
+		struct annotation_line *al = browser->offsets[offset];
+		struct disasm_line *dl;
+		struct browser_line *blt;
+
+		dl = disasm_line(al);
 
 		if (!disasm_line__is_valid_jump(dl, sym))
 			continue;
 
-		dlt = browser->offsets[dl->ops.target.offset];
+		al = browser->offsets[dl->ops.target.offset];
+
 		/*
  		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
  		 * have to adjust to the previous offset?
  		 */
-		if (dlt == NULL)
+		if (al == NULL)
 			continue;
 
-		bdlt = disasm_line__browser(dlt);
-		if (++bdlt->jump_sources > browser->max_jump_sources)
-			browser->max_jump_sources = bdlt->jump_sources;
+		blt = browser_line(al);
+		if (++blt->jump_sources > browser->max_jump_sources)
+			browser->max_jump_sources = blt->jump_sources;
 
 		++browser->nr_jumps;
 	}
@@ -1078,7 +1079,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt)
 {
-	struct disasm_line *pos, *n;
+	struct annotation_line *al;
 	struct annotation *notes;
 	size_t size;
 	struct map_symbol ms = {
@@ -1097,7 +1098,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	};
 	int ret = -1, err;
 	int nr_pcnt = 1;
-	size_t sizeof_bdl = sizeof(struct browser_disasm_line);
 
 	if (sym == NULL)
 		return -1;
@@ -1107,21 +1107,18 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	browser.offsets = zalloc(size * sizeof(struct disasm_line *));
+	browser.offsets = zalloc(size * sizeof(struct annotation_line *));
 	if (browser.offsets == NULL) {
 		ui__error("Not enough memory!");
 		return -1;
 	}
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->nr_members;
-		sizeof_bdl += sizeof(struct disasm_line_samples) *
-		  (nr_pcnt - 1);
-	}
 
-	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				  sizeof_bdl, &browser.arch,
-				  perf_evsel__env_cpuid(evsel));
+	err = symbol__annotate(sym, map, evsel,
+			       sizeof(struct browser_line), &browser.arch,
+			       perf_evsel__env_cpuid(evsel));
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -1129,20 +1126,22 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		goto out_free_offsets;
 	}
 
+	symbol__calc_percent(sym, evsel);
+
 	ui_helpline__push("Press ESC to exit");
 
 	notes = symbol__annotation(sym);
 	browser.start = map__rip_2objdump(map, sym->start);
 
-	list_for_each_entry(pos, &notes->src->source, node) {
-		struct browser_disasm_line *bpos;
-		size_t line_len = strlen(pos->line);
+	list_for_each_entry(al, &notes->src->source, node) {
+		struct browser_line *bpos;
+		size_t line_len = strlen(al->line);
 
 		if (browser.b.width < line_len)
 			browser.b.width = line_len;
-		bpos = disasm_line__browser(pos);
+		bpos = browser_line(al);
 		bpos->idx = browser.nr_entries++;
-		if (pos->offset != -1) {
+		if (al->offset != -1) {
 			bpos->idx_asm = browser.nr_asm_entries++;
 			/*
 			 * FIXME: short term bandaid to cope with assembly
@@ -1151,8 +1150,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 *
 			 * E.g. copy_user_generic_unrolled
  			 */
-			if (pos->offset < (s64)size)
-				browser.offsets[pos->offset] = pos;
+			if (al->offset < (s64)size)
+				browser.offsets[al->offset] = al;
 		} else
 			bpos->idx_asm = -1;
 	}
@@ -1174,10 +1173,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	annotate_browser__update_addr_width(&browser);
 
 	ret = annotate_browser__run(&browser, evsel, hbt);
-	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
-		list_del(&pos->node);
-		disasm_line__free(pos);
-	}
+
+	annotated_source__purge(notes->src);
 
 out_free_offsets:
 	free(browser.offsets);
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index fc7a2e105bfdff149d966c526dfa0d23ef082397..cdb5ecf91666b354348a6cecc9e960c899ded5ae 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -31,14 +31,14 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
 
 	strcpy(buf, "");
 
-	if (dl->offset == (s64) -1)
+	if (dl->al.offset == (s64) -1)
 		return 0;
 
 	symhist = annotation__histogram(symbol__annotation(sym), evidx);
-	if (!symbol_conf.event_group && !symhist->addr[dl->offset].nr_samples)
+	if (!symbol_conf.event_group && !symhist->addr[dl->al.offset].nr_samples)
 		return 0;
 
-	percent = 100.0 * symhist->addr[dl->offset].nr_samples / symhist->nr_samples;
+	percent = 100.0 * symhist->addr[dl->al.offset].nr_samples / symhist->nr_samples;
 
 	markup = perf_gtk__get_percent_color(percent);
 	if (markup)
@@ -57,16 +57,16 @@ static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym,
 
 	strcpy(buf, "");
 
-	if (dl->offset == (s64) -1)
+	if (dl->al.offset == (s64) -1)
 		return 0;
 
-	return scnprintf(buf, size, "%"PRIx64, start + dl->offset);
+	return scnprintf(buf, size, "%"PRIx64, start + dl->al.offset);
 }
 
 static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
 {
 	int ret = 0;
-	char *line = g_markup_escape_text(dl->line, -1);
+	char *line = g_markup_escape_text(dl->al.line, -1);
 	const char *markup = "<span fgcolor='gray'>";
 
 	strcpy(buf, "");
@@ -74,7 +74,7 @@ static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
 	if (!line)
 		return 0;
 
-	if (dl->offset != (s64) -1)
+	if (dl->al.offset != (s64) -1)
 		markup = NULL;
 
 	if (markup)
@@ -119,7 +119,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
 	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
 	g_object_unref(GTK_TREE_MODEL(store));
 
-	list_for_each_entry(pos, &notes->src->source, node) {
+	list_for_each_entry(pos, &notes->src->source, al.node) {
 		GtkTreeIter iter;
 		int ret = 0;
 
@@ -148,8 +148,8 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
 
 	gtk_container_add(GTK_CONTAINER(window), view);
 
-	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
-		list_del(&pos->node);
+	list_for_each_entry_safe(pos, n, &notes->src->source, al.node) {
+		list_del(&pos->al.node);
 		disasm_line__free(pos);
 	}
 
@@ -169,8 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				  0, NULL, NULL);
+	err = symbol__annotate(sym, map, evsel, 0, NULL, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -178,6 +177,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 		return -1;
 	}
 
+	symbol__calc_percent(sym, evsel);
+
 	if (perf_gtk__is_active_context(pgctx)) {
 		window = pgctx->main_window;
 		notebook = pgctx->notebook;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index da1c4c4a0dd842a279283f8b2b52bef10c5fda3d..22ea7936d92f4c7068868a337ceade1cde987d7e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -165,7 +165,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
 			      struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -230,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
 	if (ops->target.addr == 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -299,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -372,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 	if (ops->locked.ins.ops == NULL)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+	printed = scnprintf(bf, size, "%-6s ", ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
 					size - printed, ops->locked.ops);
 }
@@ -448,7 +448,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -488,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name,
+	return scnprintf(bf, size, "%-6s %s", ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -500,7 +500,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
 			  struct ins_operands *ops __maybe_unused)
 {
-	return scnprintf(bf, size, "%-6.6s", "nop");
+	return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -878,32 +878,99 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 	return -1;
 }
 
-static struct disasm_line *disasm_line__new(s64 offset, char *line,
-					    size_t privsize, int line_nr,
-					    struct arch *arch,
-					    struct map *map)
+struct annotate_args {
+	size_t			 privsize;
+	struct arch		*arch;
+	struct map		*map;
+	struct perf_evsel	*evsel;
+	s64			 offset;
+	char			*line;
+	int			 line_nr;
+};
+
+static void annotation_line__delete(struct annotation_line *al)
 {
-	struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
+	void *ptr = (void *) al - al->privsize;
+
+	free_srcline(al->path);
+	zfree(&al->line);
+	free(ptr);
+}
 
-	if (dl != NULL) {
-		dl->offset = offset;
-		dl->line = strdup(line);
-		dl->line_nr = line_nr;
-		if (dl->line == NULL)
+/*
+ * Allocating the annotation line data with following
+ * structure:
+ *
+ *    --------------------------------------
+ *    private space | struct annotation_line
+ *    --------------------------------------
+ *
+ * Size of the private space is stored in 'struct annotation_line'.
+ *
+ */
+static struct annotation_line *
+annotation_line__new(struct annotate_args *args, size_t privsize)
+{
+	struct annotation_line *al;
+	struct perf_evsel *evsel = args->evsel;
+	size_t size = privsize + sizeof(*al);
+	int nr = 1;
+
+	if (perf_evsel__is_group_event(evsel))
+		nr = evsel->nr_members;
+
+	size += sizeof(al->samples[0]) * nr;
+
+	al = zalloc(size);
+	if (al) {
+		al = (void *) al + privsize;
+		al->privsize   = privsize;
+		al->offset     = args->offset;
+		al->line       = strdup(args->line);
+		al->line_nr    = args->line_nr;
+		al->samples_nr = nr;
+	}
+
+	return al;
+}
+
+/*
+ * Allocating the disasm annotation line data with
+ * following structure:
+ *
+ *    ------------------------------------------------------------
+ *    privsize space | struct disasm_line | struct annotation_line
+ *    ------------------------------------------------------------
+ *
+ * We have 'struct annotation_line' member as last member
+ * of 'struct disasm_line' to have an easy access.
+ *
+ */
+static struct disasm_line *disasm_line__new(struct annotate_args *args)
+{
+	struct disasm_line *dl = NULL;
+	struct annotation_line *al;
+	size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+
+	al = annotation_line__new(args, privsize);
+	if (al != NULL) {
+		dl = disasm_line(al);
+
+		if (dl->al.line == NULL)
 			goto out_delete;
 
-		if (offset != -1) {
-			if (disasm_line__parse(dl->line, &dl->ins.name, &dl->ops.raw) < 0)
+		if (args->offset != -1) {
+			if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
 				goto out_free_line;
 
-			disasm_line__init_ins(dl, arch, map);
+			disasm_line__init_ins(dl, args->arch, args->map);
 		}
 	}
 
 	return dl;
 
 out_free_line:
-	zfree(&dl->line);
+	zfree(&dl->al.line);
 out_delete:
 	free(dl);
 	return NULL;
@@ -911,30 +978,30 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line,
 
 void disasm_line__free(struct disasm_line *dl)
 {
-	zfree(&dl->line);
 	if (dl->ins.ops && dl->ins.ops->free)
 		dl->ins.ops->free(&dl->ops);
 	else
 		ins__delete(&dl->ops);
 	free((void *)dl->ins.name);
 	dl->ins.name = NULL;
-	free(dl);
+	annotation_line__delete(&dl->al);
 }
 
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
 	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }
 
-static void disasm__add(struct list_head *head, struct disasm_line *line)
+static void annotation_line__add(struct annotation_line *al, struct list_head *head)
 {
-	list_add_tail(&line->node, head);
+	list_add_tail(&al->node, head);
 }
 
-struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos)
+struct annotation_line *
+annotation_line__next(struct annotation_line *pos, struct list_head *head)
 {
 	list_for_each_entry_continue(pos, head, node)
 		if (pos->offset >= 0)
@@ -943,50 +1010,6 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 	return NULL;
 }
 
-double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path, struct sym_hist_entry *sample)
-{
-	struct source_line *src_line = notes->src->lines;
-	double percent = 0.0;
-
-	sample->nr_samples = sample->period = 0;
-
-	if (src_line) {
-		size_t sizeof_src_line = sizeof(*src_line) +
-				sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
-
-		while (offset < end) {
-			src_line = (void *)notes->src->lines +
-					(sizeof_src_line * offset);
-
-			if (*path == NULL)
-				*path = src_line->path;
-
-			percent += src_line->samples[evidx].percent;
-			sample->nr_samples += src_line->samples[evidx].nr;
-			offset++;
-		}
-	} else {
-		struct sym_hist *h = annotation__histogram(notes, evidx);
-		unsigned int hits = 0;
-		u64 period = 0;
-
-		while (offset < end) {
-			hits   += h->addr[offset].nr_samples;
-			period += h->addr[offset].period;
-			++offset;
-		}
-
-		if (h->nr_samples) {
-			sample->period	   = period;
-			sample->nr_samples = hits;
-			percent = 100.0 * hits / h->nr_samples;
-		}
-	}
-
-	return percent;
-}
-
 static const char *annotate__address_color(struct block_range *br)
 {
 	double cov = block_range__coverage(br);
@@ -1069,50 +1092,39 @@ static void annotate__branch_printf(struct block_range *br, u64 addr)
 	}
 }
 
+static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_width)
+{
+	s64 offset = dl->al.offset;
+	const u64 addr = start + offset;
+	struct block_range *br;
+
+	br = block_range__find(addr);
+	color_fprintf(stdout, annotate__address_color(br), "  %*" PRIx64 ":", addr_fmt_width, addr);
+	color_fprintf(stdout, annotate__asm_color(br), "%s", dl->al.line);
+	annotate__branch_printf(br, addr);
+	return 0;
+}
 
-static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
-		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
-		      int max_lines, struct disasm_line *queue)
+static int
+annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start,
+		       struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
+		       int max_lines, struct annotation_line *queue, int addr_fmt_width)
 {
+	struct disasm_line *dl = container_of(al, struct disasm_line, al);
 	static const char *prev_line;
 	static const char *prev_color;
 
-	if (dl->offset != -1) {
-		const char *path = NULL;
-		double percent, max_percent = 0.0;
-		double *ppercents = &percent;
-		struct sym_hist_entry sample;
-		struct sym_hist_entry *psamples = &sample;
+	if (al->offset != -1) {
+		double max_percent = 0.0;
 		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
-		s64 offset = dl->offset;
-		const u64 addr = start + offset;
-		struct disasm_line *next;
-		struct block_range *br;
-
-		next = disasm__get_next_ip_line(&notes->src->source, dl);
-
-		if (perf_evsel__is_group_event(evsel)) {
-			nr_percent = evsel->nr_members;
-			ppercents = calloc(nr_percent, sizeof(double));
-			psamples = calloc(nr_percent, sizeof(struct sym_hist_entry));
-			if (ppercents == NULL || psamples == NULL) {
-				return -1;
-			}
-		}
 
-		for (i = 0; i < nr_percent; i++) {
-			percent = disasm__calc_percent(notes,
-					notes->src->lines ? i : evsel->idx + i,
-					offset,
-					next ? next->offset : (s64) len,
-					&path, &sample);
-
-			ppercents[i] = percent;
-			psamples[i] = sample;
-			if (percent > max_percent)
-				max_percent = percent;
+		for (i = 0; i < al->samples_nr; i++) {
+			struct annotation_data *sample = &al->samples[i];
+
+			if (sample->percent > max_percent)
+				max_percent = sample->percent;
 		}
 
 		if (max_percent < min_pcnt)
@@ -1123,10 +1135,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 		if (queue != NULL) {
 			list_for_each_entry_from(queue, &notes->src->source, node) {
-				if (queue == dl)
+				if (queue == al)
 					break;
-				disasm_line__print(queue, sym, start, evsel, len,
-						    0, 0, 1, NULL);
+				annotation_line__print(queue, sym, start, evsel, len,
+						       0, 0, 1, NULL, addr_fmt_width);
 			}
 		}
 
@@ -1137,44 +1149,34 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		 * the same color than the percentage. Don't print it
 		 * twice for close colored addr with the same filename:line
 		 */
-		if (path) {
-			if (!prev_line || strcmp(prev_line, path)
+		if (al->path) {
+			if (!prev_line || strcmp(prev_line, al->path)
 				       || color != prev_color) {
-				color_fprintf(stdout, color, " %s", path);
-				prev_line = path;
+				color_fprintf(stdout, color, " %s", al->path);
+				prev_line = al->path;
 				prev_color = color;
 			}
 		}
 
 		for (i = 0; i < nr_percent; i++) {
-			percent = ppercents[i];
-			sample = psamples[i];
-			color = get_percent_color(percent);
+			struct annotation_data *sample = &al->samples[i];
+
+			color = get_percent_color(sample->percent);
 
 			if (symbol_conf.show_total_period)
 				color_fprintf(stdout, color, " %11" PRIu64,
-					      sample.period);
+					      sample->he.period);
 			else if (symbol_conf.show_nr_samples)
 				color_fprintf(stdout, color, " %7" PRIu64,
-					      sample.nr_samples);
+					      sample->he.nr_samples);
 			else
-				color_fprintf(stdout, color, " %7.2f", percent);
+				color_fprintf(stdout, color, " %7.2f", sample->percent);
 		}
 
-		printf(" :	");
+		printf(" : ");
 
-		br = block_range__find(addr);
-		color_fprintf(stdout, annotate__address_color(br), "  %" PRIx64 ":", addr);
-		color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line);
-		annotate__branch_printf(br, addr);
+		disasm_line__print(dl, start, addr_fmt_width);
 		printf("\n");
-
-		if (ppercents != &percent)
-			free(ppercents);
-
-		if (psamples != &sample)
-			free(psamples);
-
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
@@ -1186,10 +1188,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (perf_evsel__is_group_event(evsel))
 			width *= evsel->nr_members;
 
-		if (!*dl->line)
+		if (!*al->line)
 			printf(" %*s:\n", width, " ");
 		else
-			printf(" %*s:	%s\n", width, " ", dl->line);
+			printf(" %*s:     %*s %s\n", width, " ", addr_fmt_width, " ", al->line);
 	}
 
 	return 0;
@@ -1215,11 +1217,11 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
  * means that it's not a disassembly line so should be treated differently.
  * The ops.raw part will be parsed further according to type of the instruction.
  */
-static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
-				      struct arch *arch,
-				      FILE *file, size_t privsize,
+static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
+				      struct annotate_args *args,
 				      int *line_nr)
 {
+	struct map *map = args->map;
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
 	char *line = NULL, *parsed_line, *tmp, *tmp2;
@@ -1263,7 +1265,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			parsed_line = tmp2 + 1;
 	}
 
-	dl = disasm_line__new(offset, parsed_line, privsize, *line_nr, arch, map);
+	args->offset  = offset;
+	args->line    = parsed_line;
+	args->line_nr = *line_nr;
+
+	dl = disasm_line__new(args);
 	free(line);
 	(*line_nr)++;
 
@@ -1288,7 +1294,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			dl->ops.target.name = strdup(target.sym->name);
 	}
 
-	disasm__add(&notes->src->source, dl);
+	annotation_line__add(&dl->al, &notes->src->source);
 
 	return 0;
 }
@@ -1305,19 +1311,19 @@ static void delete_last_nop(struct symbol *sym)
 	struct disasm_line *dl;
 
 	while (!list_empty(list)) {
-		dl = list_entry(list->prev, struct disasm_line, node);
+		dl = list_entry(list->prev, struct disasm_line, al.node);
 
 		if (dl->ins.ops) {
 			if (dl->ins.ops != &nop_ops)
 				return;
 		} else {
-			if (!strstr(dl->line, " nop ") &&
-			    !strstr(dl->line, " nopl ") &&
-			    !strstr(dl->line, " nopw "))
+			if (!strstr(dl->al.line, " nop ") &&
+			    !strstr(dl->al.line, " nopl ") &&
+			    !strstr(dl->al.line, " nopw "))
 				return;
 		}
 
-		list_del(&dl->node);
+		list_del(&dl->al.node);
 		disasm_line__free(dl);
 	}
 }
@@ -1424,13 +1430,11 @@ static const char *annotate__norm_arch(const char *arch_name)
 	return normalize_arch((char *)arch_name);
 }
 
-int symbol__disassemble(struct symbol *sym, struct map *map,
-			const char *arch_name, size_t privsize,
-			struct arch **parch, char *cpuid)
+static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
+	struct map *map = args->map;
 	struct dso *dso = map->dso;
 	char command[PATH_MAX * 2];
-	struct arch *arch = NULL;
 	FILE *file;
 	char symfs_filename[PATH_MAX];
 	struct kcore_extract kce;
@@ -1444,25 +1448,6 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 	if (err)
 		return err;
 
-	arch_name = annotate__norm_arch(arch_name);
-	if (!arch_name)
-		return -1;
-
-	arch = arch__find(arch_name);
-	if (arch == NULL)
-		return -ENOTSUP;
-
-	if (parch)
-		*parch = arch;
-
-	if (arch->init) {
-		err = arch->init(arch, cpuid);
-		if (err) {
-			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
-			return err;
-		}
-	}
-
 	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
 		 symfs_filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
@@ -1546,8 +1531,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 		 * can associate it with the instructions till the next one.
 		 * See disasm_line__new() and struct disasm_line::line_nr.
 		 */
-		if (symbol__parse_objdump_line(sym, map, arch, file, privsize,
-			    &lineno) < 0)
+		if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0)
 			break;
 		nline++;
 	}
@@ -1580,21 +1564,113 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 	goto out_remove_tmp;
 }
 
-static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+static void calc_percent(struct sym_hist *hist,
+			 struct annotation_data *sample,
+			 s64 offset, s64 end)
+{
+	unsigned int hits = 0;
+	u64 period = 0;
+
+	while (offset < end) {
+		hits   += hist->addr[offset].nr_samples;
+		period += hist->addr[offset].period;
+		++offset;
+	}
+
+	if (hist->nr_samples) {
+		sample->he.period     = period;
+		sample->he.nr_samples = hits;
+		sample->percent = 100.0 * hits / hist->nr_samples;
+	}
+}
+
+static void annotation__calc_percent(struct annotation *notes,
+				     struct perf_evsel *evsel, s64 len)
+{
+	struct annotation_line *al, *next;
+
+	list_for_each_entry(al, &notes->src->source, node) {
+		s64 end;
+		int i;
+
+		if (al->offset == -1)
+			continue;
+
+		next = annotation_line__next(al, &notes->src->source);
+		end  = next ? next->offset : len;
+
+		for (i = 0; i < al->samples_nr; i++) {
+			struct annotation_data *sample;
+			struct sym_hist *hist;
+
+			hist   = annotation__histogram(notes, evsel->idx + i);
+			sample = &al->samples[i];
+
+			calc_percent(hist, sample, al->offset, end);
+		}
+	}
+}
+
+void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	annotation__calc_percent(notes, evsel, symbol__size(sym));
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map,
+		     struct perf_evsel *evsel, size_t privsize,
+		     struct arch **parch, char *cpuid)
+{
+	struct annotate_args args = {
+		.privsize	= privsize,
+		.map		= map,
+		.evsel		= evsel,
+	};
+	const char *arch_name = NULL;
+	struct arch *arch;
+	int err;
+
+	if (evsel)
+		arch_name = perf_evsel__env_arch(evsel);
+
+	arch_name = annotate__norm_arch(arch_name);
+	if (!arch_name)
+		return -1;
+
+	args.arch = arch = arch__find(arch_name);
+	if (arch == NULL)
+		return -ENOTSUP;
+
+	if (parch)
+		*parch = arch;
+
+	if (arch->init) {
+		err = arch->init(arch, cpuid);
+		if (err) {
+			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
+			return err;
+		}
+	}
+
+	return symbol__disassemble(sym, &args);
+}
+
+static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 {
-	struct source_line *iter;
+	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	int i, ret;
 
 	while (*p != NULL) {
 		parent = *p;
-		iter = rb_entry(parent, struct source_line, node);
+		iter = rb_entry(parent, struct annotation_line, rb_node);
 
-		ret = strcmp(iter->path, src_line->path);
+		ret = strcmp(iter->path, al->path);
 		if (ret == 0) {
-			for (i = 0; i < src_line->nr_pcnt; i++)
-				iter->samples[i].percent_sum += src_line->samples[i].percent;
+			for (i = 0; i < al->samples_nr; i++)
+				iter->samples[i].percent_sum += al->samples[i].percent;
 			return;
 		}
 
@@ -1604,18 +1680,18 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 			p = &(*p)->rb_right;
 	}
 
-	for (i = 0; i < src_line->nr_pcnt; i++)
-		src_line->samples[i].percent_sum = src_line->samples[i].percent;
+	for (i = 0; i < al->samples_nr; i++)
+		al->samples[i].percent_sum = al->samples[i].percent;
 
-	rb_link_node(&src_line->node, parent, p);
-	rb_insert_color(&src_line->node, root);
+	rb_link_node(&al->rb_node, parent, p);
+	rb_insert_color(&al->rb_node, root);
 }
 
-static int cmp_source_line(struct source_line *a, struct source_line *b)
+static int cmp_source_line(struct annotation_line *a, struct annotation_line *b)
 {
 	int i;
 
-	for (i = 0; i < a->nr_pcnt; i++) {
+	for (i = 0; i < a->samples_nr; i++) {
 		if (a->samples[i].percent_sum == b->samples[i].percent_sum)
 			continue;
 		return a->samples[i].percent_sum > b->samples[i].percent_sum;
@@ -1624,135 +1700,47 @@ static int cmp_source_line(struct source_line *a, struct source_line *b)
 	return 0;
 }
 
-static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
+static void __resort_source_line(struct rb_root *root, struct annotation_line *al)
 {
-	struct source_line *iter;
+	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 
 	while (*p != NULL) {
 		parent = *p;
-		iter = rb_entry(parent, struct source_line, node);
+		iter = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (cmp_source_line(src_line, iter))
+		if (cmp_source_line(al, iter))
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
 	}
 
-	rb_link_node(&src_line->node, parent, p);
-	rb_insert_color(&src_line->node, root);
+	rb_link_node(&al->rb_node, parent, p);
+	rb_insert_color(&al->rb_node, root);
 }
 
 static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root)
 {
-	struct source_line *src_line;
+	struct annotation_line *al;
 	struct rb_node *node;
 
 	node = rb_first(src_root);
 	while (node) {
 		struct rb_node *next;
 
-		src_line = rb_entry(node, struct source_line, node);
+		al = rb_entry(node, struct annotation_line, rb_node);
 		next = rb_next(node);
 		rb_erase(node, src_root);
 
-		__resort_source_line(dest_root, src_line);
+		__resort_source_line(dest_root, al);
 		node = next;
 	}
 }
 
-static void symbol__free_source_line(struct symbol *sym, int len)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct source_line *src_line = notes->src->lines;
-	size_t sizeof_src_line;
-	int i;
-
-	sizeof_src_line = sizeof(*src_line) +
-			  (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
-
-	for (i = 0; i < len; i++) {
-		free_srcline(src_line->path);
-		src_line = (void *)src_line + sizeof_src_line;
-	}
-
-	zfree(&notes->src->lines);
-}
-
-/* Get the filename:line for the colored entries */
-static int symbol__get_source_line(struct symbol *sym, struct map *map,
-				   struct perf_evsel *evsel,
-				   struct rb_root *root, int len)
-{
-	u64 start;
-	int i, k;
-	int evidx = evsel->idx;
-	struct source_line *src_line;
-	struct annotation *notes = symbol__annotation(sym);
-	struct sym_hist *h = annotation__histogram(notes, evidx);
-	struct rb_root tmp_root = RB_ROOT;
-	int nr_pcnt = 1;
-	u64 nr_samples = h->nr_samples;
-	size_t sizeof_src_line = sizeof(struct source_line);
-
-	if (perf_evsel__is_group_event(evsel)) {
-		for (i = 1; i < evsel->nr_members; i++) {
-			h = annotation__histogram(notes, evidx + i);
-			nr_samples += h->nr_samples;
-		}
-		nr_pcnt = evsel->nr_members;
-		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
-	}
-
-	if (!nr_samples)
-		return 0;
-
-	src_line = notes->src->lines = calloc(len, sizeof_src_line);
-	if (!notes->src->lines)
-		return -1;
-
-	start = map__rip_2objdump(map, sym->start);
-
-	for (i = 0; i < len; i++) {
-		u64 offset;
-		double percent_max = 0.0;
-
-		src_line->nr_pcnt = nr_pcnt;
-
-		for (k = 0; k < nr_pcnt; k++) {
-			double percent = 0.0;
-
-			h = annotation__histogram(notes, evidx + k);
-			nr_samples = h->addr[i].nr_samples;
-			if (h->nr_samples)
-				percent = 100.0 * nr_samples / h->nr_samples;
-
-			if (percent > percent_max)
-				percent_max = percent;
-			src_line->samples[k].percent = percent;
-			src_line->samples[k].nr = nr_samples;
-		}
-
-		if (percent_max <= 0.5)
-			goto next;
-
-		offset = start + i;
-		src_line->path = get_srcline(map->dso, offset, NULL,
-					     false, true);
-		insert_source_line(&tmp_root, src_line);
-
-	next:
-		src_line = (void *)src_line + sizeof_src_line;
-	}
-
-	resort_source_line(root, &tmp_root);
-	return 0;
-}
-
 static void print_summary(struct rb_root *root, const char *filename)
 {
-	struct source_line *src_line;
+	struct annotation_line *al;
 	struct rb_node *node;
 
 	printf("\nSorted summary for file %s\n", filename);
@@ -1770,9 +1758,9 @@ static void print_summary(struct rb_root *root, const char *filename)
 		char *path;
 		int i;
 
-		src_line = rb_entry(node, struct source_line, node);
-		for (i = 0; i < src_line->nr_pcnt; i++) {
-			percent = src_line->samples[i].percent_sum;
+		al = rb_entry(node, struct annotation_line, rb_node);
+		for (i = 0; i < al->samples_nr; i++) {
+			percent = al->samples[i].percent_sum;
 			color = get_percent_color(percent);
 			color_fprintf(stdout, color, " %7.2f", percent);
 
@@ -1780,7 +1768,7 @@ static void print_summary(struct rb_root *root, const char *filename)
 				percent_max = percent;
 		}
 
-		path = src_line->path;
+		path = al->path;
 		color = get_percent_color(percent_max);
 		color_fprintf(stdout, color, " %s\n", path);
 
@@ -1801,6 +1789,19 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
 	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
 }
 
+static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
+{
+	char bf[32];
+	struct annotation_line *line;
+
+	list_for_each_entry_reverse(line, lines, node) {
+		if (line->offset != -1)
+			return scnprintf(bf, sizeof(bf), "%" PRIx64, start + line->offset);
+	}
+
+	return 0;
+}
+
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context)
@@ -1811,9 +1812,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	const char *evsel_name = perf_evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
-	struct disasm_line *pos, *queue = NULL;
+	struct annotation_line *pos, *queue = NULL;
 	u64 start = map__rip_2objdump(map, sym->start);
-	int printed = 2, queue_len = 0;
+	int printed = 2, queue_len = 0, addr_fmt_width;
 	int more = 0;
 	u64 len;
 	int width = symbol_conf.show_total_period ? 12 : 8;
@@ -1844,15 +1845,21 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	if (verbose > 0)
 		symbol__annotate_hits(sym, evsel);
 
+	addr_fmt_width = annotated_source__addr_fmt_width(&notes->src->source, start);
+
 	list_for_each_entry(pos, &notes->src->source, node) {
+		int err;
+
 		if (context && queue == NULL) {
 			queue = pos;
 			queue_len = 0;
 		}
 
-		switch (disasm_line__print(pos, sym, start, evsel, len,
-					    min_pcnt, printed, max_lines,
-					    queue)) {
+		err = annotation_line__print(pos, sym, start, evsel, len,
+					     min_pcnt, printed, max_lines,
+					     queue, addr_fmt_width);
+
+		switch (err) {
 		case 0:
 			++printed;
 			if (context) {
@@ -1907,13 +1914,13 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
 	}
 }
 
-void disasm__purge(struct list_head *head)
+void annotated_source__purge(struct annotated_source *as)
 {
-	struct disasm_line *pos, *n;
+	struct annotation_line *al, *n;
 
-	list_for_each_entry_safe(pos, n, head, node) {
-		list_del(&pos->node);
-		disasm_line__free(pos);
+	list_for_each_entry_safe(al, n, &as->source, node) {
+		list_del(&al->node);
+		disasm_line__free(disasm_line(al));
 	}
 }
 
@@ -1921,10 +1928,10 @@ static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp)
 {
 	size_t printed;
 
-	if (dl->offset == -1)
-		return fprintf(fp, "%s\n", dl->line);
+	if (dl->al.offset == -1)
+		return fprintf(fp, "%s\n", dl->al.line);
 
-	printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->ins.name);
+	printed = fprintf(fp, "%#" PRIx64 " %s", dl->al.offset, dl->ins.name);
 
 	if (dl->ops.raw[0] != '\0') {
 		printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ",
@@ -1939,38 +1946,72 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp)
 	struct disasm_line *pos;
 	size_t printed = 0;
 
-	list_for_each_entry(pos, head, node)
+	list_for_each_entry(pos, head, al.node)
 		printed += disasm_line__fprintf(pos, fp);
 
 	return printed;
 }
 
+static void annotation__calc_lines(struct annotation *notes, struct map *map,
+				  struct rb_root *root, u64 start)
+{
+	struct annotation_line *al;
+	struct rb_root tmp_root = RB_ROOT;
+
+	list_for_each_entry(al, &notes->src->source, node) {
+		double percent_max = 0.0;
+		int i;
+
+		for (i = 0; i < al->samples_nr; i++) {
+			struct annotation_data *sample;
+
+			sample = &al->samples[i];
+
+			if (sample->percent > percent_max)
+				percent_max = sample->percent;
+		}
+
+		if (percent_max <= 0.5)
+			continue;
+
+		al->path = get_srcline(map->dso, start + al->offset, NULL, false, true);
+		insert_source_line(&tmp_root, al);
+	}
+
+	resort_source_line(root, &tmp_root);
+}
+
+static void symbol__calc_lines(struct symbol *sym, struct map *map,
+			      struct rb_root *root)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	u64 start = map__rip_2objdump(map, sym->start);
+
+	annotation__calc_lines(notes, map, root, start);
+}
+
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines)
 {
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
-	u64 len;
 
-	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				0, NULL, NULL) < 0)
+	if (symbol__annotate(sym, map, evsel, 0, NULL, NULL) < 0)
 		return -1;
 
-	len = symbol__size(sym);
+	symbol__calc_percent(sym, evsel);
 
 	if (print_lines) {
 		srcline_full_filename = full_paths;
-		symbol__get_source_line(sym, map, evsel, &source_line, len);
+		symbol__calc_lines(sym, map, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
 	symbol__annotate_printf(sym, map, evsel, full_paths,
 				min_pcnt, max_lines, 0);
-	if (print_lines)
-		symbol__free_source_line(sym, len);
 
-	disasm__purge(&symbol__annotation(sym)->src->source);
+	annotated_source__purge(symbol__annotation(sym)->src);
 
 	return 0;
 }
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f6ba3560de5ea55481703ff9728907ede11f247a..6d7289e88fa3779abcec72812f4049d82ef1bd25 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -59,33 +59,55 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 struct annotation;
 
+struct sym_hist_entry {
+	u64		nr_samples;
+	u64		period;
+};
+
+struct annotation_data {
+	double			 percent;
+	double			 percent_sum;
+	struct sym_hist_entry	 he;
+};
+
+struct annotation_line {
+	struct list_head	 node;
+	struct rb_node		 rb_node;
+	s64			 offset;
+	char			*line;
+	int			 line_nr;
+	float			 ipc;
+	u64			 cycles;
+	size_t			 privsize;
+	char			*path;
+	int			 samples_nr;
+	struct annotation_data	 samples[0];
+};
+
 struct disasm_line {
-	struct list_head    node;
-	s64		    offset;
-	char		    *line;
-	struct ins	    ins;
-	int		    line_nr;
-	float		    ipc;
-	u64		    cycles;
-	struct ins_operands ops;
+	struct ins		 ins;
+	struct ins_operands	 ops;
+
+	/* This needs to be at the end. */
+	struct annotation_line	 al;
 };
 
+static inline struct disasm_line *disasm_line(struct annotation_line *al)
+{
+	return al ? container_of(al, struct disasm_line, al) : NULL;
+}
+
 static inline bool disasm_line__has_offset(const struct disasm_line *dl)
 {
 	return dl->ops.target.offset_avail;
 }
 
-struct sym_hist_entry {
-	u64		nr_samples;
-	u64		period;
-};
-
 void disasm_line__free(struct disasm_line *dl);
-struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
+struct annotation_line *
+annotation_line__next(struct annotation_line *pos, struct list_head *head);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
-double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path, struct sym_hist_entry *sample);
+void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
 
 struct sym_hist {
 	u64		      nr_samples;
@@ -104,19 +126,6 @@ struct cyc_hist {
 	u16	reset;
 };
 
-struct source_line_samples {
-	double		percent;
-	double		percent_sum;
-	u64		nr;
-};
-
-struct source_line {
-	struct rb_node	node;
-	char		*path;
-	int		nr_pcnt;
-	struct source_line_samples samples[1];
-};
-
 /** struct annotated_source - symbols with hits have this attached as in sannotation
  *
  * @histogram: Array of addr hit histograms per event being monitored
@@ -132,7 +141,6 @@ struct source_line {
  */
 struct annotated_source {
 	struct list_head   source;
-	struct source_line *lines;
 	int    		   nr_histograms;
 	size_t		   sizeof_sym_hist;
 	struct cyc_hist	   *cycles_hist;
@@ -169,9 +177,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__disassemble(struct symbol *sym, struct map *map,
-			const char *arch_name, size_t privsize,
-			struct arch **parch, char *cpuid);
+int symbol__annotate(struct symbol *sym, struct map *map,
+		     struct perf_evsel *evsel, size_t privsize,
+		     struct arch **parch, char *cpuid);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
@@ -198,7 +206,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    int min_pcnt, int max_lines, int context);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
-void disasm__purge(struct list_head *head);
+void annotated_source__purge(struct annotated_source *as);
 
 bool ui__has_annotation(void);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e154a63c67971c04512c0b576d5bf43087..199bb82efbcdf8ebf028e31dbdd0b598eb708aea 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -257,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct perf_evsel *evsel = perf_evsel__new(&attr);
+	struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
 	if (evsel == NULL)
 		return -ENOMEM;
@@ -1582,6 +1582,17 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even
 	return perf_evsel__parse_sample(evsel, event, sample);
 }
 
+int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+					union perf_event *event,
+					u64 *timestamp)
+{
+	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+	if (!evsel)
+		return -EFAULT;
+	return perf_evsel__parse_sample_timestamp(evsel, event, timestamp);
+}
+
 size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 {
 	struct perf_evsel *evsel;
@@ -1786,3 +1797,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
 	return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel->attr.exclude_kernel)
+			return false;
+	}
+
+	return true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e72ae64c11acb5214d82996d9c21498b1d34547e..4e8131dacbd7d4d66c8a2d1109252ad336b571b8 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -205,6 +205,10 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
 			      struct perf_sample *sample);
 
+int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+					union perf_event *event,
+					u64 *timestamp);
+
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
@@ -312,4 +316,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f894893c203d13e00259d356414a8b781066fa5a..95853c51c0ca45293200e0fea7aba4b8d33a89bd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	list_for_each_entry(term, config_terms, list) {
 		switch (term->type) {
 		case PERF_EVSEL__CONFIG_TERM_PERIOD:
-			attr->sample_period = term->val.period;
-			attr->freq = 0;
+			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
+				attr->sample_period = term->val.period;
+				attr->freq = 0;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
-			attr->sample_freq = term->val.freq;
-			attr->freq = 1;
+			if (!(term->weak && opts->user_freq != UINT_MAX)) {
+				attr->sample_freq = term->val.freq;
+				attr->freq = 1;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
 			if (term->val.time)
@@ -775,6 +779,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
 			attr->write_backward = term->val.overwrite ? 1 : 0;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
+			BUG_ON(1);
 		default:
 			break;
 		}
@@ -1371,7 +1377,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-	struct perf_stat_evsel *ps = leader->priv;
+	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->attr.read_format;
 	int size = perf_evsel__read_size(leader);
 	u64 *data = ps->group_data;
@@ -1956,6 +1962,20 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset,
 #define OVERFLOW_CHECK_u64(offset) \
 	OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
 
+static int
+perf_event__check_size(union perf_event *event, unsigned int sample_size)
+{
+	/*
+	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
+	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
+	 * check the format does not go past the end of the event.
+	 */
+	if (sample_size + sizeof(event->header) > event->header.size)
+		return -EFAULT;
+
+	return 0;
+}
+
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
@@ -1977,6 +1997,8 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = evsel->attr.sample_period;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	data->id = -1ULL;
+	data->data_src = PERF_MEM_DATA_SRC_NONE;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
@@ -1986,15 +2008,9 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	array = event->sample.array;
 
-	/*
-	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
-	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
-	 * check the format does not go past the end of the event.
-	 */
-	if (evsel->sample_size + sizeof(event->header) > event->header.size)
+	if (perf_event__check_size(event, evsel->sample_size))
 		return -EFAULT;
 
-	data->id = -1ULL;
 	if (type & PERF_SAMPLE_IDENTIFIER) {
 		data->id = *array;
 		array++;
@@ -2024,7 +2040,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
-	data->addr = 0;
 	if (type & PERF_SAMPLE_ADDR) {
 		data->addr = *array;
 		array++;
@@ -2188,14 +2203,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
-	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	if (type & PERF_SAMPLE_DATA_SRC) {
 		OVERFLOW_CHECK_u64(array);
 		data->data_src = *array;
 		array++;
 	}
 
-	data->transaction = 0;
 	if (type & PERF_SAMPLE_TRANSACTION) {
 		OVERFLOW_CHECK_u64(array);
 		data->transaction = *array;
@@ -2228,6 +2241,50 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	return 0;
 }
 
+int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+				       union perf_event *event,
+				       u64 *timestamp)
+{
+	u64 type = evsel->attr.sample_type;
+	const u64 *array;
+
+	if (!(type & PERF_SAMPLE_TIME))
+		return -1;
+
+	if (event->header.type != PERF_RECORD_SAMPLE) {
+		struct perf_sample data = {
+			.time = -1ULL,
+		};
+
+		if (!evsel->attr.sample_id_all)
+			return -1;
+		if (perf_evsel__parse_id_sample(evsel, event, &data))
+			return -1;
+
+		*timestamp = data.time;
+		return 0;
+	}
+
+	array = event->sample.array;
+
+	if (perf_event__check_size(event, evsel->sample_size))
+		return -EFAULT;
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		array++;
+
+	if (type & PERF_SAMPLE_IP)
+		array++;
+
+	if (type & PERF_SAMPLE_TID)
+		array++;
+
+	if (type & PERF_SAMPLE_TIME)
+		*timestamp = *array;
+
+	return 0;
+}
+
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 				     u64 read_format)
 {
@@ -2739,8 +2796,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 		break;
 	case EOPNOTSUPP:
 		if (evsel->attr.sample_period != 0)
-			return scnprintf(msg, size, "%s",
-	"PMU Hardware doesn't support sampling/overflow-interrupts.");
+			return scnprintf(msg, size,
+	"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
+					 perf_evsel__name(evsel));
 		if (evsel->attr.precise_ip)
 			return scnprintf(msg, size, "%s",
 	"\'precise\' request may not be supported. Try removing 'p' modifier.");
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9277df96ffdad90a4899e922b574156bb708ef86..c3663a70c9b9b13537df7b8e582d4e02bef9d599 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -38,7 +38,7 @@ struct cgroup_sel;
  * It is allocated within event parsing and attached to
  * perf_evsel::config_terms list head.
 */
-enum {
+enum term_type {
 	PERF_EVSEL__CONFIG_TERM_PERIOD,
 	PERF_EVSEL__CONFIG_TERM_FREQ,
 	PERF_EVSEL__CONFIG_TERM_TIME,
@@ -49,12 +49,11 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
-	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
 struct perf_evsel_config_term {
 	struct list_head	list;
-	int	type;
+	enum term_type	type;
 	union {
 		u64	period;
 		u64	freq;
@@ -67,6 +66,7 @@ struct perf_evsel_config_term {
 		bool	overwrite;
 		char	*branch;
 	} val;
+	bool weak;
 };
 
 struct perf_stat_evsel;
@@ -338,6 +338,10 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 
+int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+				       union perf_event *event,
+				       u64 *timestamp);
+
 static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 {
 	return list_entry(evsel->node.next, struct perf_evsel, node);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6a8d03c3d9b7095961b07a4d648eadc6f857e868..64d255f6a5374c8ee730d759d409c789782b690a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -172,6 +172,9 @@ void machine__exit(struct machine *machine)
 {
 	int i;
 
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
@@ -2201,7 +2204,7 @@ int thread__resolve_callchain(struct thread *thread,
 {
 	int ret = 0;
 
-	callchain_cursor_reset(&callchain_cursor);
+	callchain_cursor_reset(cursor);
 
 	if (callchain_param.order == ORDER_CALLEE) {
 		ret = thread__resolve_callchain_sample(thread, cursor,
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 8e09fd2d842f492c9b47342deaab725ccfcdf01e..bad9e0296e9ab5dafa4c237fe2c0f1760b57fda1 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -157,9 +157,8 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 }
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-			  struct perf_sample *sample, u64 file_offset)
+			  u64 timestamp, u64 file_offset)
 {
-	u64 timestamp = sample->time;
 	struct ordered_event *oevent;
 
 	if (!timestamp || timestamp == ~0ULL)
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 96e5292d88e2584ba0d78abd3b23a3f3b5237073..8c7a2948593e96a8c297559ae30f694fafeee21f 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -45,7 +45,7 @@ struct ordered_events {
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-			  struct perf_sample *sample, u64 file_offset);
+			  u64 timestamp, u64 file_offset);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
 void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a7fcd95961ef0776f07c6968088a7b6cf7836924..170316795a1845c7e013d84ee17ba663da200d6d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1116,6 +1116,7 @@ do {								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
 	__t->val.__name = __val;				\
+	__t->weak	= term->weak;				\
 	list_add_tail(&__t->list, head_terms);			\
 } while (0)
 
@@ -2410,6 +2411,7 @@ static int new_term(struct parse_events_term **_term,
 
 	*term = *temp;
 	INIT_LIST_HEAD(&term->list);
+	term->weak = false;
 
 	switch (term->type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index be337c266697a718d3ad595a166f8f3e3602cb93..88108cd11b4c80132d7b9b80f1b53d727d2bac1b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -101,6 +101,9 @@ struct parse_events_term {
 	/* error string indexes for within parsed string */
 	int err_term;
 	int err_val;
+
+	/* Coming from implicit alias */
+	bool weak;
 };
 
 struct parse_events_error {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 07cb2ac041d7a63b53298b4205fd0b4cd629c349..80fb1593913a9227a742a1a2ed56330c877facad 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -405,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 			parse_events_terms__purge(&list);
 			return ret;
 		}
+		/*
+		 * Weak terms don't override command line options,
+		 * which we don't want for implicit terms in aliases.
+		 */
+		cloned->weak = true;
 		list_add_tail(&cloned->list, &list);
 	}
 	list_splice(&list, terms);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5c412310f26644236844dd59e114cc770e04b0d0..df28571379082a4414335d7a0a395e3d12a98ba5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -27,7 +27,6 @@
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
-				       struct perf_sample *sample,
 				       struct perf_tool *tool,
 				       u64 file_offset);
 
@@ -107,17 +106,10 @@ static void perf_session__set_comm_exec(struct perf_session *session)
 static int ordered_events__deliver_event(struct ordered_events *oe,
 					 struct ordered_event *event)
 {
-	struct perf_sample sample;
 	struct perf_session *session = container_of(oe, struct perf_session,
 						    ordered_events);
-	int ret = perf_evlist__parse_sample(session->evlist, event->event, &sample);
-
-	if (ret) {
-		pr_err("Can't parse sample, err = %d\n", ret);
-		return ret;
-	}
 
-	return perf_session__deliver_event(session, event->event, &sample,
+	return perf_session__deliver_event(session, event->event,
 					   session->tool, event->file_offset);
 }
 
@@ -873,9 +865,9 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 }
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      struct perf_sample *sample, u64 file_offset)
+			      u64 timestamp, u64 file_offset)
 {
-	return ordered_events__queue(&s->ordered_events, event, sample, file_offset);
+	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -1328,20 +1320,26 @@ static int machines__deliver_event(struct machines *machines,
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
-				       struct perf_sample *sample,
 				       struct perf_tool *tool,
 				       u64 file_offset)
 {
+	struct perf_sample sample;
 	int ret;
 
-	ret = auxtrace__process_event(session, event, sample, tool);
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
+	if (ret) {
+		pr_err("Can't parse sample, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = auxtrace__process_event(session, event, &sample, tool);
 	if (ret < 0)
 		return ret;
 	if (ret > 0)
 		return 0;
 
 	return machines__deliver_event(&session->machines, session->evlist,
-				       event, sample, tool, file_offset);
+				       event, &sample, tool, file_offset);
 }
 
 static s64 perf_session__process_user_event(struct perf_session *session,
@@ -1495,7 +1493,6 @@ static s64 perf_session__process_event(struct perf_session *session,
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct perf_tool *tool = session->tool;
-	struct perf_sample sample;
 	int ret;
 
 	if (session->header.needs_swap)
@@ -1509,21 +1506,19 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
 		return perf_session__process_user_event(session, event, file_offset);
 
-	/*
-	 * For all kernel events we get the sample data
-	 */
-	ret = perf_evlist__parse_sample(evlist, event, &sample);
-	if (ret)
-		return ret;
-
 	if (tool->ordered_events) {
-		ret = perf_session__queue_event(session, event, &sample, file_offset);
+		u64 timestamp;
+
+		ret = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
+		if (ret)
+			return ret;
+
+		ret = perf_session__queue_event(session, event, timestamp, file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session__deliver_event(session, event, &sample, tool,
-					   file_offset);
+	return perf_session__deliver_event(session, event, tool, file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da1434a7c120d5682c02f1d5b0c24fc11d583886..da40b4b380ca9c4cfa10516182e890c206210d92 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -53,7 +53,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 int perf_session__process_events(struct perf_session *session);
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      struct perf_sample *sample, u64 file_offset);
+			      u64 timestamp, u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);