Merge tag 'perf-core-for-mingo-4.18-20180606' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf stat:

 - Display user and system time for workload targets (Jiri Olsa)

perf record:

 - Enable arbitrary event names thru name= modifier (Alexey Budankov)

PowerPC:

 - Add a python script for hypervisor call statistics (Ravi Bangoria)

Intel PT: (Adrian Hunter)

 - Fix sync_switch INTEL_PT_SS_NOT_TRACING

 - Fix decoding to accept CBR between FUP and corresponding TIP

 - Fix MTC timing after overflow

 - Fix "Unexpected indirect branch" error

perf test:

 - record+probe_libc_inet_pton:

  -  To get the symbol table for dynamic
     shared objects on ubuntu we need to pass the -D/--dynamic command line
     option, unlike with the fedora distros (Arnaldo Carvalho de Melo)

 - code-reading:

  - Fix perf_env setup for PTI entry trampolines (Adrian Hunter)

 - kmod-path:

  - Add tests for vdso32 and vdsox32 (Adrian Hunter)

 - Use header file util/debug.h (Thomas Richter)

perf annotate:

 - Make the various UI backends (stdio, TUI, gtk) use more consistently
  structs with annotation options as specified by the user (Arnaldo Carvalho de Melo)

 - Move annotation specific knobs from the symbol_conf global kitchen
  sink to the annotation option structs (Arnaldo Carvalho de Melo)

perf script:

 - Add more PMU fields to python scripts event handler dict (Jin Yao)

Core:

 - Fix misleading error for some unparsable events mentioning PMUs when
  those are not involved in the problem (Jiri Olsa)

 - Consider BSS symbols when processing /proc/kallsyms ('B' and 'b')
  (Arnaldo Carvalho de Melo)

- Be more robust when trying to use per-symbol histograms, checking for
  unlikely but possible cases where the space for the histograms wasn't
  allocated, print a debug message for such cases (Arnaldo Carvalho de Melo)

- Fix symbol and object code resolution for vdso32 and vdsox32 (Adrian Hunter)

 - No need to check for null when passing pointers to foo__get() style
  refcount grabbing helpers, just like in the kernel and with free(),
  its safe to pass a NULL pointer to avoid having to check it before
  each and every foo__get() call (Arnaldo Carvalho de Melo)

 - Remove some dead code (quote.[ch]) (Arnaldo Carvalho de Melo)

 - Remove some needless globals, making them local (Arnaldo Carvalho de Melo)

 - Reduce usage of symbol_conf.use_callchain, using other means of
  finding out if callchains are in use or available for specific events,
  as we evolved this codebase to allow requesting callchains for just
  a subset of the monitored events. In time it will help polish
  recording and showing mixed sets accross the various tools:

    perf record -e cycles/call-graph=fp/,cache-misses/call-graph=dwarf/,instructions'

  (Arnaldo Carvalho de Melo)

 - Consider PTI entry trampolines in map__rip_2objdump() (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

27 files changed, 556 insertions, 289 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5d4c45b76895..b604ef334dc9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -24,7 +24,6 @@ libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
 libperf-y += smt.o
-libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
 libperf-y += strlist.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 71897689dacf..f91775b4bc3c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -21,6 +21,7 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include "evlist.h"
 #include "block-range.h"
 #include "string2.h"
 #include "arch/common.h"
@@ -46,11 +47,10 @@
 struct annotation_options annotation__default_options = {
 	.use_offset     = true,
 	.jump_arrows    = true,
+	.annotate_src	= true,
 	.offset_level	= ANNOTATION__OFFSET_JUMP_TARGETS,
 };
 
-const char 	*disassembler_style;
-const char	*objdump_path;
 static regex_t	 file_lineno;
 
 static struct ins_ops *ins__find(struct arch *arch, const char *name);
@@ -678,10 +678,28 @@ static struct arch *arch__find(const char *name)
 	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
 }
 
-int symbol__alloc_hist(struct symbol *sym)
+static struct annotated_source *annotated_source__new(void)
+{
+	struct annotated_source *src = zalloc(sizeof(*src));
+
+	if (src != NULL)
+		INIT_LIST_HEAD(&src->source);
+
+	return src;
+}
+
+static __maybe_unused void annotated_source__delete(struct annotated_source *src)
+{
+	if (src == NULL)
+		return;
+	zfree(&src->histograms);
+	zfree(&src->cycles_hist);
+	free(src);
+}
+
+static int annotated_source__alloc_histograms(struct annotated_source *src,
+					      size_t size, int nr_hists)
 {
-	struct annotation *notes = symbol__annotation(sym);
-	size_t size = symbol__size(sym);
 	size_t sizeof_sym_hist;
 
 	/*
@@ -701,17 +719,13 @@ int symbol__alloc_hist(struct symbol *sym)
 	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry));
 
 	/* Check for overflow in zalloc argument */
-	if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
-				/ symbol_conf.nr_events)
+	if (sizeof_sym_hist > SIZE_MAX / nr_hists)
 		return -1;
 
-	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
-	if (notes->src == NULL)
-		return -1;
-	notes->src->sizeof_sym_hist = sizeof_sym_hist;
-	notes->src->nr_histograms   = symbol_conf.nr_events;
-	INIT_LIST_HEAD(&notes->src->source);
-	return 0;
+	src->sizeof_sym_hist = sizeof_sym_hist;
+	src->nr_histograms   = nr_hists;
+	src->histograms	     = calloc(nr_hists, sizeof_sym_hist) ;
+	return src->histograms ? 0 : -1;
 }
 
 /* The cycles histogram is lazily allocated. */
@@ -741,14 +755,11 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	pthread_mutex_unlock(&notes->lock);
 }
 
-static int __symbol__account_cycles(struct annotation *notes,
+static int __symbol__account_cycles(struct cyc_hist *ch,
 				    u64 start,
 				    unsigned offset, unsigned cycles,
 				    unsigned have_start)
 {
-	struct cyc_hist *ch;
-
-	ch = notes->src->cycles_hist;
 	/*
 	 * For now we can only account one basic block per
 	 * final jump. But multiple could be overlapping.
@@ -791,7 +802,7 @@ static int __symbol__account_cycles(struct annotation *notes,
 }
 
 static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-				      struct annotation *notes, int evidx, u64 addr,
+				      struct annotated_source *src, int evidx, u64 addr,
 				      struct perf_sample *sample)
 {
 	unsigned offset;
@@ -807,7 +818,12 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	}
 
 	offset = addr - sym->start;
-	h = annotation__histogram(notes, evidx);
+	h = annotated_source__histogram(src, evidx);
+	if (h == NULL) {
+		pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n",
+			 __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC);
+		return -ENOMEM;
+	}
 	h->nr_samples++;
 	h->addr[offset].nr_samples++;
 	h->period += sample->period;
@@ -820,45 +836,69 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
-static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles)
+static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
 
 	if (notes->src == NULL) {
-		if (symbol__alloc_hist(sym) < 0)
+		notes->src = annotated_source__new();
+		if (notes->src == NULL)
 			return NULL;
+		goto alloc_cycles_hist;
+	}
+
+	if (!notes->src->cycles_hist) {
+alloc_cycles_hist:
+		symbol__alloc_hist_cycles(sym);
 	}
-	if (!notes->src->cycles_hist && cycles) {
-		if (symbol__alloc_hist_cycles(sym) < 0)
+
+	return notes->src->cycles_hist;
+}
+
+struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	if (notes->src == NULL) {
+		notes->src = annotated_source__new();
+		if (notes->src == NULL)
 			return NULL;
+		goto alloc_histograms;
 	}
-	return notes;
+
+	if (notes->src->histograms == NULL) {
+alloc_histograms:
+		annotated_source__alloc_histograms(notes->src, symbol__size(sym),
+						   nr_hists);
+	}
+
+	return notes->src;
 }
 
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-				    int evidx, u64 addr,
+				    struct perf_evsel *evsel, u64 addr,
 				    struct perf_sample *sample)
 {
-	struct annotation *notes;
+	struct annotated_source *src;
 
 	if (sym == NULL)
 		return 0;
-	notes = symbol__get_annotation(sym, false);
-	if (notes == NULL)
+	src = symbol__hists(sym, evsel->evlist->nr_entries);
+	if (src == NULL)
 		return -ENOMEM;
-	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample);
+	return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample);
 }
 
 static int symbol__account_cycles(u64 addr, u64 start,
 				  struct symbol *sym, unsigned cycles)
 {
-	struct annotation *notes;
+	struct cyc_hist *cycles_hist;
 	unsigned offset;
 
 	if (sym == NULL)
 		return 0;
-	notes = symbol__get_annotation(sym, true);
-	if (notes == NULL)
+	cycles_hist = symbol__cycles_hist(sym);
+	if (cycles_hist == NULL)
 		return -ENOMEM;
 	if (addr < sym->start || addr >= sym->end)
 		return -ERANGE;
@@ -870,7 +910,7 @@ static int symbol__account_cycles(u64 addr, u64 start,
 			start = 0;
 	}
 	offset = addr - sym->start;
-	return __symbol__account_cycles(notes,
+	return __symbol__account_cycles(cycles_hist,
 					start ? start - sym->start : 0,
 					offset, cycles,
 					!!start);
@@ -974,15 +1014,15 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
-				 int evidx)
+				 struct perf_evsel *evsel)
 {
-	return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample);
+	return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample);
 }
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
-				 int evidx, u64 ip)
+				 struct perf_evsel *evsel, u64 ip)
 {
-	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample);
+	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample);
 }
 
 static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
@@ -1031,6 +1071,7 @@ struct annotate_args {
 	struct arch		*arch;
 	struct map_symbol	 ms;
 	struct perf_evsel	*evsel;
+	struct annotation_options *options;
 	s64			 offset;
 	char			*line;
 	int			 line_nr;
@@ -1572,6 +1613,7 @@ fallback:
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
+	struct annotation_options *opts = args->options;
 	struct map *map = args->ms.map;
 	struct dso *dso = map->dso;
 	char *command;
@@ -1619,13 +1661,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
 		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
-		 objdump_path ? objdump_path : "objdump",
-		 disassembler_style ? "-M " : "",
-		 disassembler_style ? disassembler_style : "",
+		 opts->objdump_path ?: "objdump",
+		 opts->disassembler_style ? "-M " : "",
+		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
-		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
-		 symbol_conf.annotate_src ? "-S" : "",
+		 opts->show_asm_raw ? "" : "--no-show-raw",
+		 opts->annotate_src ? "-S" : "",
 		 symfs_filename, symfs_filename);
 
 	if (err < 0) {
@@ -1767,11 +1809,13 @@ void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel)
 
 int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct perf_evsel *evsel, size_t privsize,
+		     struct annotation_options *options,
 		     struct arch **parch)
 {
 	struct annotate_args args = {
 		.privsize	= privsize,
 		.evsel		= evsel,
+		.options	= options,
 	};
 	struct perf_env *env = perf_evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
@@ -1949,8 +1993,8 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
 }
 
 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)
+			    struct perf_evsel *evsel,
+			    struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
 	char *filename;
@@ -1962,6 +2006,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0, addr_fmt_width;
 	int more = 0;
+	bool context = opts->context;
 	u64 len;
 	int width = symbol_conf.show_total_period ? 12 : 8;
 	int graph_dotted_len;
@@ -1971,7 +2016,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	if (!filename)
 		return -ENOMEM;
 
-	if (full_paths)
+	if (opts->full_path)
 		d_filename = filename;
 	else
 		d_filename = basename(filename);
@@ -2006,7 +2051,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 		}
 
 		err = annotation_line__print(pos, sym, start, evsel, len,
-					     min_pcnt, printed, max_lines,
+					     opts->min_pcnt, printed, opts->max_lines,
 					     queue, addr_fmt_width);
 
 		switch (err) {
@@ -2339,20 +2384,19 @@ static void symbol__calc_lines(struct symbol *sym, struct map *map,
 }
 
 int symbol__tty_annotate2(struct symbol *sym, struct map *map,
-			  struct perf_evsel *evsel, bool print_lines,
-			  bool full_paths)
+			  struct perf_evsel *evsel,
+			  struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
-	struct annotation_options opts = annotation__default_options;
 	struct annotation *notes = symbol__annotation(sym);
 	char buf[1024];
 
-	if (symbol__annotate2(sym, map, evsel, &opts, NULL) < 0)
+	if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0)
 		return -1;
 
-	if (print_lines) {
-		srcline_full_filename = full_paths;
+	if (opts->print_lines) {
+		srcline_full_filename = opts->full_path;
 		symbol__calc_lines(sym, map, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
@@ -2367,25 +2411,24 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map,
 }
 
 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 perf_evsel *evsel,
+			 struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
 
-	if (symbol__annotate(sym, map, evsel, 0, NULL) < 0)
+	if (symbol__annotate(sym, map, evsel, 0, opts, NULL) < 0)
 		return -1;
 
 	symbol__calc_percent(sym, evsel);
 
-	if (print_lines) {
-		srcline_full_filename = full_paths;
+	if (opts->print_lines) {
+		srcline_full_filename = opts->full_path;
 		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);
+	symbol__annotate_printf(sym, map, evsel, opts);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
@@ -2620,7 +2663,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->nr_members;
 
-	err = symbol__annotate(sym, map, evsel, 0, parch);
+	err = symbol__annotate(sym, map, evsel, 0, options, parch);
 	if (err)
 		goto out_free_offsets;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 5080b6dd98b8..a4c0d91907e6 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -67,12 +67,21 @@ struct annotation_options {
 	bool hide_src_code,
 	     use_offset,
 	     jump_arrows,
+	     print_lines,
+	     full_path,
 	     show_linenr,
 	     show_nr_jumps,
 	     show_nr_samples,
 	     show_total_period,
-	     show_minmax_cycle;
+	     show_minmax_cycle,
+	     show_asm_raw,
+	     annotate_src;
 	u8   offset_level;
+	int  min_pcnt;
+	int  max_lines;
+	int  context;
+	const char *objdump_path;
+	const char *disassembler_style;
 };
 
 enum {
@@ -201,7 +210,11 @@ struct cyc_hist {
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
  *
- * @histogram: Array of addr hit histograms per event being monitored
+ * @histograms: Array of addr hit histograms per event being monitored
+ * nr_histograms: This may not be the same as evsel->evlist->nr_entries if
+ * 		  we have more than a group in a evlist, where we will want
+ * 		  to see each group separately, that is why symbol__annotate2()
+ * 		  sets src->nr_histograms to evsel->nr_members.
  * @lines: If 'print_lines' is specified, per source code line percentages
  * @source: source parsed from a disassembler like objdump -dS
  * @cyc_hist: Average cycles per basic block
@@ -217,7 +230,7 @@ struct annotated_source {
 	int    		   nr_histograms;
 	size_t		   sizeof_sym_hist;
 	struct cyc_hist	   *cycles_hist;
-	struct sym_hist	   histograms[0];
+	struct sym_hist	   *histograms;
 };
 
 struct annotation {
@@ -267,10 +280,14 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 void annotation__update_column_widths(struct annotation *notes);
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
 
+static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx)
+{
+	return ((void *)src->histograms) + (src->sizeof_sym_hist * idx);
+}
+
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
-	return (((void *)&notes->src->histograms) +
-	 	(notes->src->sizeof_sym_hist * idx));
+	return annotated_source__histogram(notes->src, idx);
 }
 
 static inline struct annotation *symbol__annotation(struct symbol *sym)
@@ -279,20 +296,21 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
-				 int evidx);
+				 struct perf_evsel *evsel);
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
 				    unsigned cycles);
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
-				 int evidx, u64 addr);
+				 struct perf_evsel *evsel, u64 addr);
 
-int symbol__alloc_hist(struct symbol *sym);
+struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct perf_evsel *evsel, size_t privsize,
+		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct symbol *sym, struct map *map,
 		      struct perf_evsel *evsel,
@@ -320,8 +338,8 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
 				 int errnum, char *buf, size_t buflen);
 
 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);
+			    struct perf_evsel *evsel,
+			    struct annotation_options *options);
 int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
@@ -332,30 +350,27 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel)
 bool ui__has_annotation(void);
 
 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 perf_evsel *evsel, struct annotation_options *opts);
 
 int symbol__tty_annotate2(struct symbol *sym, struct map *map,
-			  struct perf_evsel *evsel, bool print_lines,
-			  bool full_paths);
+			  struct perf_evsel *evsel, struct annotation_options *opts);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
-			 struct hist_browser_timer *hbt);
+			 struct hist_browser_timer *hbt,
+			 struct annotation_options *opts);
 #else
 static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
 				struct map *map __maybe_unused,
 				struct perf_evsel *evsel  __maybe_unused,
-				struct hist_browser_timer *hbt
-				__maybe_unused)
+				struct hist_browser_timer *hbt __maybe_unused,
+				struct annotation_options *opts __maybe_unused)
 {
 	return 0;
 }
 #endif
 
-extern const char	*disassembler_style;
-
 void annotation_config__init(void);
 
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index decb91f9da82..ccd02634a616 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -93,20 +93,17 @@ static int open_cgroup(const char *name)
 static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup *cgrp = NULL;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
 	evlist__for_each_entry(evlist, counter) {
 		if (!counter->cgrp)
 			continue;
-		if (!strcmp(counter->cgrp->name, str)) {
-			cgrp = cgroup__get(counter->cgrp);
-			break;
-		}
+		if (!strcmp(counter->cgrp->name, str))
+			return cgroup__get(counter->cgrp);
 	}
 
-	return cgrp;
+	return NULL;
 }
 
 static struct cgroup *cgroup__new(const char *name)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index cdfc2e5f55f5..51cf82cf1882 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -354,6 +354,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
 		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
 		    (strncmp(name, "[vdso]", 6) == 0) ||
+		    (strncmp(name, "[vdso32]", 8) == 0) ||
+		    (strncmp(name, "[vdsox32]", 9) == 0) ||
 		    (strncmp(name, "[vsyscall]", 10) == 0)) {
 			m->kmod = false;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 150db5ed7400..94fce4f537e9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2197,7 +2197,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		}
 	}
 
-	if (type & PERF_SAMPLE_CALLCHAIN) {
+	if (evsel__has_callchain(evsel)) {
 		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
 		OVERFLOW_CHECK_u64(array);
@@ -2857,7 +2857,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			 "Hint: Try again after reducing the number of events.\n"
 			 "Hint: Try increasing the limit with 'ulimit -n <limit>'");
 	case ENOMEM:
-		if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 &&
+		if (evsel__has_callchain(evsel) &&
 		    access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0)
 			return scnprintf(msg, size,
 					 "Not enough memory to setup event with callchain.\n"
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b13f5f234c8f..d277930b19a1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -459,6 +459,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evs
 	return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
+static inline bool evsel__has_callchain(const struct perf_evsel *evsel)
+{
+	return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
+}
+
 typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a8bff2178fbc..540cd2dcd3e7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1459,8 +1459,24 @@ static void print_cmdline(struct feat_fd *ff, FILE *fp)
 
 	fprintf(fp, "# cmdline : ");
 
-	for (i = 0; i < nr; i++)
-		fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]);
+	for (i = 0; i < nr; i++) {
+		char *argv_i = strdup(ff->ph->env.cmdline_argv[i]);
+		if (!argv_i) {
+			fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]);
+		} else {
+			char *mem = argv_i;
+			do {
+				char *quote = strchr(argv_i, '\'');
+				if (!quote)
+					break;
+				*quote++ = '\0';
+				fprintf(fp, "%s\\\'", argv_i);
+				argv_i = quote;
+			} while (1);
+			fprintf(fp, "%s ", argv_i);
+			free(mem);
+		}
+	}
 	fputc('\n', fp);
 }
 
@@ -3312,8 +3328,6 @@ int perf_session__read_header(struct perf_session *session)
 		lseek(fd, tmp, SEEK_SET);
 	}
 
-	symbol_conf.nr_events = nr_attrs;
-
 	perf_header__process_sections(header, fd, &session->tevent,
 				      perf_file_section__process);
 
@@ -3739,8 +3753,6 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 		perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
 	}
 
-	symbol_conf.nr_events = evlist->nr_entries;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4d602fba40b2..52e8fda93a47 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -410,7 +410,7 @@ static int hist_entry__init(struct hist_entry *he,
 		map__get(he->mem_info->daddr.map);
 	}
 
-	if (symbol_conf.use_callchain)
+	if (hist_entry__has_callchains(he) && symbol_conf.use_callchain)
 		callchain_init(he->callchain);
 
 	if (he->raw_data) {
@@ -492,7 +492,7 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 
 static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
 {
-	if (!symbol_conf.use_callchain)
+	if (!hist_entry__has_callchains(he) || !symbol_conf.use_callchain)
 		return;
 
 	he->hists->callchain_period += period;
@@ -986,7 +986,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	if (symbol_conf.use_callchain)
+	if (hist_entry__has_callchains(he) && symbol_conf.use_callchain)
 		callchain_append(he->callchain, &cursor, sample->period);
 	return 0;
 }
@@ -1039,7 +1039,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	int err, err2;
 	struct map *alm = NULL;
 
-	if (al && al->map)
+	if (al)
 		alm = map__get(al->map);
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
@@ -1373,7 +1373,8 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 	if (new_he) {
 		new_he->leaf = true;
 
-		if (symbol_conf.use_callchain) {
+		if (hist_entry__has_callchains(new_he) &&
+		    symbol_conf.use_callchain) {
 			callchain_cursor_reset(&callchain_cursor);
 			if (callchain_merge(&callchain_cursor,
 					    new_he->callchain,
@@ -1414,7 +1415,7 @@ static int hists__collapse_insert_entry(struct hists *hists,
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
-			if (symbol_conf.use_callchain) {
+			if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
 				if (callchain_merge(&callchain_cursor,
 						    iter->callchain,
@@ -1757,7 +1758,7 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
 	bool use_callchain;
 
 	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
-		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
+		use_callchain = evsel__has_callchain(evsel);
 	else
 		use_callchain = symbol_conf.use_callchain;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index fbabfd8a215d..06607c434949 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -220,6 +220,12 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 	return &hevsel->hists;
 }
 
+static __pure inline bool hists__has_callchains(struct hists *hists)
+{
+	const struct perf_evsel *evsel = hists_to_evsel(hists);
+	return evsel__has_callchain(evsel);
+}
+
 int hists__init(void);
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
@@ -419,19 +425,24 @@ struct hist_browser_timer {
 	int refresh;
 };
 
+struct annotation_options;
+
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
-			     struct hist_browser_timer *hbt);
+			     struct hist_browser_timer *hbt,
+			     struct annotation_options *annotation_opts);
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
-			     struct hist_browser_timer *hbt);
+			     struct hist_browser_timer *hbt,
+			     struct annotation_options *annotation_opts);
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  float min_pcnt,
 				  struct perf_env *env,
-				  bool warn_lost_event);
+				  bool warn_lost_event,
+				  struct annotation_options *annotation_options);
 int script_browse(const char *script_opt);
 #else
 static inline
@@ -440,20 +451,23 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 				  struct hist_browser_timer *hbt __maybe_unused,
 				  float min_pcnt __maybe_unused,
 				  struct perf_env *env __maybe_unused,
-				  bool warn_lost_event __maybe_unused)
+				  bool warn_lost_event __maybe_unused,
+				  struct annotation_options *annotation_options __maybe_unused)
 {
 	return 0;
 }
 static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 					   struct perf_evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused,
+					   struct annotation_options *annotation_options __maybe_unused)
 {
 	return 0;
 }
 
 static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
 					   struct perf_evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused,
+					   struct annotation_options *annotation_opts __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index f9157aed1289..d404bed7003a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -113,6 +113,7 @@ struct intel_pt_decoder {
 	bool have_cyc;
 	bool fixup_last_mtc;
 	bool have_last_ip;
+	enum intel_pt_param_flags flags;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;
@@ -226,6 +227,8 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->return_compression = params->return_compression;
 	decoder->branch_enable      = params->branch_enable;
 
+	decoder->flags              = params->flags;
+
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
 
@@ -1097,6 +1100,15 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 	return ret;
 }
 
+static inline bool intel_pt_fup_with_nlip(struct intel_pt_decoder *decoder,
+					  struct intel_pt_insn *intel_pt_insn,
+					  uint64_t ip, int err)
+{
+	return decoder->flags & INTEL_PT_FUP_WITH_NLIP && !err &&
+	       intel_pt_insn->branch == INTEL_PT_BR_INDIRECT &&
+	       ip == decoder->ip + intel_pt_insn->length;
+}
+
 static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 {
 	struct intel_pt_insn intel_pt_insn;
@@ -1109,10 +1121,11 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 		err = intel_pt_walk_insn(decoder, &intel_pt_insn, ip);
 		if (err == INTEL_PT_RETURN)
 			return 0;
-		if (err == -EAGAIN) {
+		if (err == -EAGAIN ||
+		    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
 			if (intel_pt_fup_event(decoder))
 				return 0;
-			return err;
+			return -EAGAIN;
 		}
 		decoder->set_fup_tx_flags = false;
 		if (err)
@@ -1376,7 +1389,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 {
 	intel_pt_log("ERROR: Buffer overflow\n");
 	intel_pt_clear_tx_flags(decoder);
-	decoder->have_tma = false;
 	decoder->cbr = 0;
 	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
@@ -1604,7 +1616,6 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PSB:
 		case INTEL_PT_TSC:
 		case INTEL_PT_TMA:
-		case INTEL_PT_CBR:
 		case INTEL_PT_MODE_TSX:
 		case INTEL_PT_BAD:
 		case INTEL_PT_PSBEND:
@@ -1620,6 +1631,10 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_step = 0;
 			return -ENOENT;
 
+		case INTEL_PT_CBR:
+			intel_pt_calc_cbr(decoder);
+			break;
+
 		case INTEL_PT_OVF:
 			return intel_pt_overflow(decoder);
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index fc1752d50019..51c18d67f4ca 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -60,6 +60,14 @@ enum {
 	INTEL_PT_ERR_MAX,
 };
 
+enum intel_pt_param_flags {
+	/*
+	 * FUP packet can contain next linear instruction pointer instead of
+	 * current linear instruction pointer.
+	 */
+	INTEL_PT_FUP_WITH_NLIP	= 1 << 0,
+};
+
 struct intel_pt_state {
 	enum intel_pt_sample_type type;
 	int err;
@@ -106,6 +114,7 @@ struct intel_pt_params {
 	unsigned int mtc_period;
 	uint32_t tsc_ctc_ratio_n;
 	uint32_t tsc_ctc_ratio_d;
+	enum intel_pt_param_flags flags;
 };
 
 struct intel_pt_decoder;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 492986a25ef6..aec68908d604 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -749,6 +749,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 						   unsigned int queue_nr)
 {
 	struct intel_pt_params params = { .get_trace = 0, };
+	struct perf_env *env = pt->machine->env;
 	struct intel_pt_queue *ptq;
 
 	ptq = zalloc(sizeof(struct intel_pt_queue));
@@ -830,6 +831,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 		}
 	}
 
+	if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18))
+		params.flags |= INTEL_PT_FUP_WITH_NLIP;
+
 	ptq->decoder = intel_pt_decoder_new(&params);
 	if (!ptq->decoder)
 		goto out_free;
@@ -1521,6 +1525,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
 		switch (ptq->switch_state) {
+		case INTEL_PT_SS_NOT_TRACING:
 		case INTEL_PT_SS_UNKNOWN:
 		case INTEL_PT_SS_EXPECTING_SWITCH_IP:
 			err = intel_pt_next_tid(pt, ptq);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6ae97eda370b..89ac5b5dc218 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -415,16 +415,20 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 	return fprintf(fp, "%s", dsoname);
 }
 
+char *map__srcline(struct map *map, u64 addr, struct symbol *sym)
+{
+	if (map == NULL)
+		return SRCLINE_UNKNOWN;
+	return get_srcline(map->dso, map__rip_2objdump(map, addr), sym, true, true, addr);
+}
+
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp)
 {
-	char *srcline;
 	int ret = 0;
 
 	if (map && map->dso) {
-		srcline = get_srcline(map->dso,
-				      map__rip_2objdump(map, addr), NULL,
-				      true, true, addr);
+		char *srcline = map__srcline(map, addr, NULL);
 		if (srcline != SRCLINE_UNKNOWN)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
@@ -445,6 +449,20 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
  */
 u64 map__rip_2objdump(struct map *map, u64 rip)
 {
+	struct kmap *kmap = __map__kmap(map);
+
+	/*
+	 * vmlinux does not have program headers for PTI entry trampolines and
+	 * kcore may not either. However the trampoline object code is on the
+	 * main kernel map, so just use that instead.
+	 */
+	if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps && kmap->kmaps->machine) {
+		struct map *kernel_map = machine__kernel_map(kmap->kmaps->machine);
+
+		if (kernel_map)
+			map = kernel_map;
+	}
+
 	if (!map->dso->adjust_symbols)
 		return rip;
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 97e2a063bd65..4cb90f242bed 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -169,6 +169,7 @@ static inline void __map__zput(struct map **map)
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index a1a01b1ac8b8..5f761f3ed0f3 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -53,7 +53,21 @@ static int str(yyscan_t scanner, int token)
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
 
-	yylval->str = strdup(text);
+	if (text[0] != '\'') {
+		yylval->str = strdup(text);
+	} else {
+		/*
+		 * If a text tag specified on the command line
+		 * contains opening single quite ' then it is
+		 * expected that the tag ends with single quote
+		 * as well, like this:
+		 *     name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\'
+		 * quotes need to be escaped to bypass shell
+		 * processing.
+		 */
+		yylval->str = strndup(&text[1], strlen(text) - 2);
+	}
+
 	return token;
 }
 
@@ -176,6 +190,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
+name_tag	[\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
@@ -344,6 +359,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {bpf_object}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
 {bpf_source}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
+{name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e37608a87dba..155d2570274f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -73,6 +73,7 @@ static void inc_group_count(struct list_head *list,
 %type <num> value_sym
 %type <head> event_config
 %type <head> opt_event_config
+%type <head> opt_pmu_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -224,7 +225,7 @@ event_def: event_pmu |
 	   event_bpf_file
 
 event_pmu:
-PE_NAME opt_event_config
+PE_NAME opt_pmu_config
 {
 	struct list_head *list, *orig_terms, *terms;
 
@@ -496,6 +497,17 @@ opt_event_config:
 	$$ = NULL;
 }
 
+opt_pmu_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+'/' '/'
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_state *parse_state = _parse_state;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 3094f11e7d81..f119eb628dbb 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -165,8 +165,7 @@ static struct map *kernel_get_module_map(const char *module)
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0 &&
 		    module[pos->dso->short_name_len - 2] == '\0') {
-			map__get(pos);
-			return pos;
+			return map__get(pos);
 		}
 	}
 	return NULL;
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
deleted file mode 100644
index 22eaa201aa27..000000000000
--- a/tools/perf/util/quote.c
+++ /dev/null
@@ -1,62 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <errno.h>
-#include <stdlib.h>
-#include "strbuf.h"
-#include "quote.h"
-#include "util.h"
-
-/* Help to copy the thing properly quoted for the shell safety.
- * any single quote is replaced with '\'', any exclamation point
- * is replaced with '\!', and the whole thing is enclosed in a
- *
- * E.g.
- *  original     sq_quote     result
- *  name     ==> name      ==> 'name'
- *  a b      ==> a b       ==> 'a b'
- *  a'b      ==> a'\''b    ==> 'a'\''b'
- *  a!b      ==> a'\!'b    ==> 'a'\!'b'
- */
-static inline int need_bs_quote(char c)
-{
-	return (c == '\'' || c == '!');
-}
-
-static int sq_quote_buf(struct strbuf *dst, const char *src)
-{
-	char *to_free = NULL;
-	int ret;
-
-	if (dst->buf == src)
-		to_free = strbuf_detach(dst, NULL);
-
-	ret = strbuf_addch(dst, '\'');
-	while (!ret && *src) {
-		size_t len = strcspn(src, "'!");
-		ret = strbuf_add(dst, src, len);
-		src += len;
-		while (!ret && need_bs_quote(*src))
-			ret = strbuf_addf(dst, "'\\%c\'", *src++);
-	}
-	if (!ret)
-		ret = strbuf_addch(dst, '\'');
-	free(to_free);
-
-	return ret;
-}
-
-int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen)
-{
-	int i, ret;
-
-	/* Copy into destination buffer. */
-	ret = strbuf_grow(dst, 255);
-	for (i = 0; !ret && argv[i]; ++i) {
-		ret = strbuf_addch(dst, ' ');
-		if (ret)
-			break;
-		ret = sq_quote_buf(dst, argv[i]);
-		if (maxlen && dst->len > maxlen)
-			return -ENOSPC;
-	}
-	return ret;
-}
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
deleted file mode 100644
index 274bf26d3511..000000000000
--- a/tools/perf/util/quote.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PERF_QUOTE_H
-#define __PERF_QUOTE_H
-
-#include <stddef.h>
-
-/* Help to copy the thing properly quoted for the shell safety.
- * any single quote is replaced with '\'', any exclamation point
- * is replaced with '\!', and the whole thing is enclosed in a
- * single quote pair.
- *
- * For example, if you are passing the result to system() as an
- * argument:
- *
- * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1))
- *
- * would be appropriate.  If the system() is going to call ssh to
- * run the command on the other side:
- *
- * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1));
- * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd));
- *
- * Note that the above examples leak memory!  Remember to free result from
- * sq_quote() in a real application.
- */
-
-struct strbuf;
-
-int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
-
-#endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7f8afacd08ee..46e9e19ab1ac 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -48,6 +48,7 @@
 #include "cpumap.h"
 #include "print_binary.h"
 #include "stat.h"
+#include "mem-events.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
@@ -372,6 +373,19 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 	return obj;
 }
 
+static const char *get_dsoname(struct map *map)
+{
+	const char *dsoname = "[unknown]";
+
+	if (map && map->dso) {
+		if (symbol_conf.show_kernel_path && map->dso->long_name)
+			dsoname = map->dso->long_name;
+		else
+			dsoname = map->dso->name;
+	}
+
+	return dsoname;
+}
 
 static PyObject *python_process_callchain(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
@@ -427,14 +441,8 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 		}
 
 		if (node->map) {
-			struct map *map = node->map;
-			const char *dsoname = "[unknown]";
-			if (map && map->dso) {
-				if (symbol_conf.show_kernel_path && map->dso->long_name)
-					dsoname = map->dso->long_name;
-				else
-					dsoname = map->dso->name;
-			}
+			const char *dsoname = get_dsoname(node->map);
+
 			pydict_set_item_string_decref(pyelem, "dso",
 					_PyUnicode_FromString(dsoname));
 		}
@@ -448,6 +456,166 @@ exit:
 	return pylist;
 }
 
+static PyObject *python_process_brstack(struct perf_sample *sample,
+					struct thread *thread)
+{
+	struct branch_stack *br = sample->branch_stack;
+	PyObject *pylist;
+	u64 i;
+
+	pylist = PyList_New(0);
+	if (!pylist)
+		Py_FatalError("couldn't create Python list");
+
+	if (!(br && br->nr))
+		goto exit;
+
+	for (i = 0; i < br->nr; i++) {
+		PyObject *pyelem;
+		struct addr_location al;
+		const char *dsoname;
+
+		pyelem = PyDict_New();
+		if (!pyelem)
+			Py_FatalError("couldn't create Python dictionary");
+
+		pydict_set_item_string_decref(pyelem, "from",
+		    PyLong_FromUnsignedLongLong(br->entries[i].from));
+		pydict_set_item_string_decref(pyelem, "to",
+		    PyLong_FromUnsignedLongLong(br->entries[i].to));
+		pydict_set_item_string_decref(pyelem, "mispred",
+		    PyBool_FromLong(br->entries[i].flags.mispred));
+		pydict_set_item_string_decref(pyelem, "predicted",
+		    PyBool_FromLong(br->entries[i].flags.predicted));
+		pydict_set_item_string_decref(pyelem, "in_tx",
+		    PyBool_FromLong(br->entries[i].flags.in_tx));
+		pydict_set_item_string_decref(pyelem, "abort",
+		    PyBool_FromLong(br->entries[i].flags.abort));
+		pydict_set_item_string_decref(pyelem, "cycles",
+		    PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+
+		thread__find_map(thread, sample->cpumode,
+				 br->entries[i].from, &al);
+		dsoname = get_dsoname(al.map);
+		pydict_set_item_string_decref(pyelem, "from_dsoname",
+					      _PyUnicode_FromString(dsoname));
+
+		thread__find_map(thread, sample->cpumode,
+				 br->entries[i].to, &al);
+		dsoname = get_dsoname(al.map);
+		pydict_set_item_string_decref(pyelem, "to_dsoname",
+					      _PyUnicode_FromString(dsoname));
+
+		PyList_Append(pylist, pyelem);
+		Py_DECREF(pyelem);
+	}
+
+exit:
+	return pylist;
+}
+
+static unsigned long get_offset(struct symbol *sym, struct addr_location *al)
+{
+	unsigned long offset;
+
+	if (al->addr < sym->end)
+		offset = al->addr - sym->start;
+	else
+		offset = al->addr - al->map->start - sym->start;
+
+	return offset;
+}
+
+static int get_symoff(struct symbol *sym, struct addr_location *al,
+		      bool print_off, char *bf, int size)
+{
+	unsigned long offset;
+
+	if (!sym || !sym->name[0])
+		return scnprintf(bf, size, "%s", "[unknown]");
+
+	if (!print_off)
+		return scnprintf(bf, size, "%s", sym->name);
+
+	offset = get_offset(sym, al);
+
+	return scnprintf(bf, size, "%s+0x%x", sym->name, offset);
+}
+
+static int get_br_mspred(struct branch_flags *flags, char *bf, int size)
+{
+	if (!flags->mispred  && !flags->predicted)
+		return scnprintf(bf, size, "%s", "-");
+
+	if (flags->mispred)
+		return scnprintf(bf, size, "%s", "M");
+
+	return scnprintf(bf, size, "%s", "P");
+}
+
+static PyObject *python_process_brstacksym(struct perf_sample *sample,
+					   struct thread *thread)
+{
+	struct branch_stack *br = sample->branch_stack;
+	PyObject *pylist;
+	u64 i;
+	char bf[512];
+	struct addr_location al;
+
+	pylist = PyList_New(0);
+	if (!pylist)
+		Py_FatalError("couldn't create Python list");
+
+	if (!(br && br->nr))
+		goto exit;
+
+	for (i = 0; i < br->nr; i++) {
+		PyObject *pyelem;
+
+		pyelem = PyDict_New();
+		if (!pyelem)
+			Py_FatalError("couldn't create Python dictionary");
+
+		thread__find_symbol(thread, sample->cpumode,
+				    br->entries[i].from, &al);
+		get_symoff(al.sym, &al, true, bf, sizeof(bf));
+		pydict_set_item_string_decref(pyelem, "from",
+					      _PyUnicode_FromString(bf));
+
+		thread__find_symbol(thread, sample->cpumode,
+				    br->entries[i].to, &al);
+		get_symoff(al.sym, &al, true, bf, sizeof(bf));
+		pydict_set_item_string_decref(pyelem, "to",
+					      _PyUnicode_FromString(bf));
+
+		get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+		pydict_set_item_string_decref(pyelem, "pred",
+					      _PyUnicode_FromString(bf));
+
+		if (br->entries[i].flags.in_tx) {
+			pydict_set_item_string_decref(pyelem, "in_tx",
+					      _PyUnicode_FromString("X"));
+		} else {
+			pydict_set_item_string_decref(pyelem, "in_tx",
+					      _PyUnicode_FromString("-"));
+		}
+
+		if (br->entries[i].flags.abort) {
+			pydict_set_item_string_decref(pyelem, "abort",
+					      _PyUnicode_FromString("A"));
+		} else {
+			pydict_set_item_string_decref(pyelem, "abort",
+					      _PyUnicode_FromString("-"));
+		}
+
+		PyList_Append(pylist, pyelem);
+		Py_DECREF(pyelem);
+	}
+
+exit:
+	return pylist;
+}
+
 static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
 {
 	PyObject *t;
@@ -498,12 +666,63 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
 	pydict_set_item_string_decref(dict_sample, "values", values);
 }
 
+static void set_sample_datasrc_in_dict(PyObject *dict,
+				       struct perf_sample *sample)
+{
+	struct mem_info mi = { .data_src.val = sample->data_src };
+	char decode[100];
+
+	pydict_set_item_string_decref(dict, "datasrc",
+			PyLong_FromUnsignedLongLong(sample->data_src));
+
+	perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+	pydict_set_item_string_decref(dict, "datasrc_decode",
+			_PyUnicode_FromString(decode));
+}
+
+static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
+{
+	unsigned int i = 0, r;
+	int printed = 0;
+
+	bf[0] = 0;
+
+	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs->regs[i++];
+
+		printed += scnprintf(bf + printed, size - printed,
+				     "%5s:0x%" PRIx64 " ",
+				     perf_reg_name(r), val);
+	}
+
+	return printed;
+}
+
+static void set_regs_in_dict(PyObject *dict,
+			     struct perf_sample *sample,
+			     struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	char bf[512];
+
+	regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
+
+	pydict_set_item_string_decref(dict, "iregs",
+			_PyUnicode_FromString(bf));
+
+	regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf));
+
+	pydict_set_item_string_decref(dict, "uregs",
+			_PyUnicode_FromString(bf));
+}
+
 static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct addr_location *al,
 					 PyObject *callchain)
 {
-	PyObject *dict, *dict_sample;
+	PyObject *dict, *dict_sample, *brstack, *brstacksym;
 
 	dict = PyDict_New();
 	if (!dict)
@@ -534,6 +753,11 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict_sample, "addr",
 			PyLong_FromUnsignedLongLong(sample->addr));
 	set_sample_read_in_dict(dict_sample, sample, evsel);
+	pydict_set_item_string_decref(dict_sample, "weight",
+			PyLong_FromUnsignedLongLong(sample->weight));
+	pydict_set_item_string_decref(dict_sample, "transaction",
+			PyLong_FromUnsignedLongLong(sample->transaction));
+	set_sample_datasrc_in_dict(dict_sample, sample);
 	pydict_set_item_string_decref(dict, "sample", dict_sample);
 
 	pydict_set_item_string_decref(dict, "raw_buf", _PyBytes_FromStringAndSize(
@@ -551,6 +775,14 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 
 	pydict_set_item_string_decref(dict, "callchain", callchain);
 
+	brstack = python_process_brstack(sample, al->thread);
+	pydict_set_item_string_decref(dict, "brstack", brstack);
+
+	brstacksym = python_process_brstacksym(sample, al->thread);
+	pydict_set_item_string_decref(dict, "brstacksym", brstacksym);
+
+	set_regs_in_dict(dict, sample, evsel);
+
 	return dict;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b998bb475589..8b9369303561 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1094,7 +1094,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	sample_type = evsel->attr.sample_type;
 
-	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
 	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4058ade352a5..fed2952ab45a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -331,24 +331,18 @@ struct sort_entry sort_sym = {
 
 /* --sort srcline */
 
-char *hist_entry__get_srcline(struct hist_entry *he)
+char *hist_entry__srcline(struct hist_entry *he)
 {
-	struct map *map = he->ms.map;
-
-	if (!map)
-		return SRCLINE_UNKNOWN;
-
-	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
-			   he->ms.sym, true, true, he->ip);
+	return map__srcline(he->ms.map, he->ip, he->ms.sym);
 }
 
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	if (!left->srcline)
-		left->srcline = hist_entry__get_srcline(left);
+		left->srcline = hist_entry__srcline(left);
 	if (!right->srcline)
-		right->srcline = hist_entry__get_srcline(right);
+		right->srcline = hist_entry__srcline(right);
 
 	return strcmp(right->srcline, left->srcline);
 }
@@ -357,7 +351,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
 	if (!he->srcline)
-		he->srcline = hist_entry__get_srcline(he);
+		he->srcline = hist_entry__srcline(he);
 
 	return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
@@ -371,33 +365,20 @@ struct sort_entry sort_srcline = {
 
 /* --sort srcline_from */
 
+static char *addr_map_symbol__srcline(struct addr_map_symbol *ams)
+{
+	return map__srcline(ams->map, ams->al_addr, ams->sym);
+}
+
 static int64_t
 sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->branch_info->srcline_from) {
-		struct map *map = left->branch_info->from.map;
-		if (!map)
-			left->branch_info->srcline_from = SRCLINE_UNKNOWN;
-		else
-			left->branch_info->srcline_from = get_srcline(map->dso,
-					   map__rip_2objdump(map,
-							     left->branch_info->from.al_addr),
-							 left->branch_info->from.sym,
-							 true, true,
-							 left->branch_info->from.al_addr);
-	}
-	if (!right->branch_info->srcline_from) {
-		struct map *map = right->branch_info->from.map;
-		if (!map)
-			right->branch_info->srcline_from = SRCLINE_UNKNOWN;
-		else
-			right->branch_info->srcline_from = get_srcline(map->dso,
-					     map__rip_2objdump(map,
-							       right->branch_info->from.al_addr),
-						     right->branch_info->from.sym,
-						     true, true,
-						     right->branch_info->from.al_addr);
-	}
+	if (!left->branch_info->srcline_from)
+		left->branch_info->srcline_from = addr_map_symbol__srcline(&left->branch_info->from);
+
+	if (!right->branch_info->srcline_from)
+		right->branch_info->srcline_from = addr_map_symbol__srcline(&right->branch_info->from);
+
 	return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
 }
 
@@ -419,30 +400,12 @@ struct sort_entry sort_srcline_from = {
 static int64_t
 sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->branch_info->srcline_to) {
-		struct map *map = left->branch_info->to.map;
-		if (!map)
-			left->branch_info->srcline_to = SRCLINE_UNKNOWN;
-		else
-			left->branch_info->srcline_to = get_srcline(map->dso,
-					   map__rip_2objdump(map,
-							     left->branch_info->to.al_addr),
-							 left->branch_info->from.sym,
-							 true, true,
-							 left->branch_info->to.al_addr);
-	}
-	if (!right->branch_info->srcline_to) {
-		struct map *map = right->branch_info->to.map;
-		if (!map)
-			right->branch_info->srcline_to = SRCLINE_UNKNOWN;
-		else
-			right->branch_info->srcline_to = get_srcline(map->dso,
-					     map__rip_2objdump(map,
-							       right->branch_info->to.al_addr),
-						     right->branch_info->to.sym,
-						     true, true,
-						     right->branch_info->to.al_addr);
-	}
+	if (!left->branch_info->srcline_to)
+		left->branch_info->srcline_to = addr_map_symbol__srcline(&left->branch_info->to);
+
+	if (!right->branch_info->srcline_to)
+		right->branch_info->srcline_to = addr_map_symbol__srcline(&right->branch_info->to);
+
 	return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
 }
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 9e6896293bbd..7cf2d5cc038e 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -151,6 +151,11 @@ struct hist_entry {
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
+static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
+{
+	return hists__has_callchains(he->hists);
+}
+
 static inline bool hist_entry__has_pairs(struct hist_entry *he)
 {
 	return !list_empty(&he->pairs.node);
@@ -292,5 +297,5 @@ int64_t
 sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
-char *hist_entry__get_srcline(struct hist_entry *he);
+char *hist_entry__srcline(struct hist_entry *he);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8c84437f2a10..d188b7588152 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -40,7 +40,6 @@ char **vmlinux_path;
 struct symbol_conf symbol_conf = {
 	.use_modules		= true,
 	.try_vmlinux_path	= true,
-	.annotate_src		= true,
 	.demangle		= true,
 	.demangle_kernel	= false,
 	.cumulate_callchain	= true,
@@ -74,7 +73,7 @@ static enum dso_binary_type binary_type_symtab[] = {
 static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
-	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D';
+	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B';
 }
 
 static int prefix_underscores_count(const char *str)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 1a16438eb3ce..f25fae4b5743 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -90,7 +90,6 @@ struct intlist;
 
 struct symbol_conf {
 	unsigned short	priv_size;
-	unsigned short	nr_events;
 	bool		try_vmlinux_path,
 			init_annotation,
 			force,
@@ -109,8 +108,6 @@ struct symbol_conf {
 			show_cpu_utilization,
 			initialized,
 			kptr_restrict,
-			annotate_asm_raw,
-			annotate_src,
 			event_group,
 			demangle,
 			demangle_kernel,
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 9892323cdd7c..9add1f72ce95 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -3,6 +3,7 @@
 #define __PERF_TOP_H 1
 
 #include "tool.h"
+#include "annotate.h"
 #include <linux/types.h>
 #include <stddef.h>
 #include <stdbool.h>
@@ -16,6 +17,7 @@ struct perf_top {
 	struct perf_tool   tool;
 	struct perf_evlist *evlist;
 	struct record_opts record_opts;
+	struct annotation_options annotation_opts;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.
@@ -35,7 +37,6 @@ struct perf_top {
 	struct perf_session *session;
 	struct winsize	   winsize;
 	int		   realtime_prio;
-	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
 	float		   min_percent;
 	unsigned int	   nr_threads_synthesize;