74 files changed, 407 insertions, 374 deletions

diff --git a/tools/perf/lib/Build b/tools/lib/perf/Build
index 2ef9a4ec6d99..2ef9a4ec6d99 100644
--- a/tools/perf/lib/Build
+++ b/tools/lib/perf/Build
diff --git a/tools/perf/lib/Makefile b/tools/lib/perf/Makefile
index 0f233638ef1f..3718d65cffac 100644
--- a/tools/perf/lib/Makefile
+++ b/tools/lib/perf/Makefile
@@ -60,7 +60,7 @@ else
 endif
 
 INCLUDES = \
--I$(srctree)/tools/perf/lib/include \
+-I$(srctree)/tools/lib/perf/include \
 -I$(srctree)/tools/lib/ \
 -I$(srctree)/tools/include \
 -I$(srctree)/tools/arch/$(SRCARCH)/include/ \
@@ -181,7 +181,10 @@ install_pkgconfig: $(LIBPERF_PC)
 	$(call QUIET_INSTALL, $(LIBPERF_PC)) \
 		$(call do_install,$(LIBPERF_PC),$(libdir_SQ)/pkgconfig,644)
 
-install: install_lib install_headers install_pkgconfig
+install_doc:
+	$(Q)$(MAKE) -C Documentation install-man install-html install-examples
+
+install: install_lib install_headers install_pkgconfig install_doc
 
 FORCE:
 
diff --git a/tools/perf/lib/core.c b/tools/lib/perf/core.c
index 58fc894b76c5..58fc894b76c5 100644
--- a/tools/perf/lib/core.c
+++ b/tools/lib/perf/core.c
diff --git a/tools/perf/lib/cpumap.c b/tools/lib/perf/cpumap.c
index f93f4e703e4c..f93f4e703e4c 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/lib/perf/cpumap.c
diff --git a/tools/perf/lib/evlist.c b/tools/lib/perf/evlist.c
index ae9e65aa2491..5b9f2ca50591 100644
--- a/tools/perf/lib/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -164,6 +164,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
 		evlist->threads = perf_thread_map__get(threads);
 	}
 
+	if (!evlist->all_cpus && cpus)
+		evlist->all_cpus = perf_cpu_map__get(cpus);
+
 	perf_evlist__propagate_maps(evlist);
 }
 
diff --git a/tools/perf/lib/evsel.c b/tools/lib/perf/evsel.c
index 4dc06289f4c7..4dc06289f4c7 100644
--- a/tools/perf/lib/evsel.c
+++ b/tools/lib/perf/evsel.c
diff --git a/tools/perf/lib/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 840d4032587b..840d4032587b 100644
--- a/tools/perf/lib/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 74dc8c3f0b66..74dc8c3f0b66 100644
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1ffd083b235e..1ffd083b235e 100644
--- a/tools/perf/lib/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
diff --git a/tools/perf/lib/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h
index 5175d491b2d4..5175d491b2d4 100644
--- a/tools/perf/lib/include/internal/lib.h
+++ b/tools/lib/perf/include/internal/lib.h
diff --git a/tools/perf/lib/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index be7556e0a2b2..be7556e0a2b2 100644
--- a/tools/perf/lib/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
diff --git a/tools/perf/lib/include/internal/tests.h b/tools/lib/perf/include/internal/tests.h
index 2093e8868a67..2093e8868a67 100644
--- a/tools/perf/lib/include/internal/tests.h
+++ b/tools/lib/perf/include/internal/tests.h
diff --git a/tools/perf/lib/include/internal/threadmap.h b/tools/lib/perf/include/internal/threadmap.h
index df748baf9eda..df748baf9eda 100644
--- a/tools/perf/lib/include/internal/threadmap.h
+++ b/tools/lib/perf/include/internal/threadmap.h
diff --git a/tools/perf/lib/include/internal/xyarray.h b/tools/lib/perf/include/internal/xyarray.h
index 51e35d6c8ec4..51e35d6c8ec4 100644
--- a/tools/perf/lib/include/internal/xyarray.h
+++ b/tools/lib/perf/include/internal/xyarray.h
diff --git a/tools/perf/lib/include/perf/core.h b/tools/lib/perf/include/perf/core.h
index a3f6d68edad7..a3f6d68edad7 100644
--- a/tools/perf/lib/include/perf/core.h
+++ b/tools/lib/perf/include/perf/core.h
diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 6a17ad730cbc..6a17ad730cbc 100644
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
diff --git a/tools/perf/lib/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 18106899cb4e..18106899cb4e 100644
--- a/tools/perf/lib/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h
index 0a7479dc13bf..0a7479dc13bf 100644
--- a/tools/perf/lib/include/perf/evlist.h
+++ b/tools/lib/perf/include/perf/evlist.h
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index c82ec39a4ad0..c82ec39a4ad0 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
diff --git a/tools/perf/lib/include/perf/mmap.h b/tools/lib/perf/include/perf/mmap.h
index 9508ad90d8b9..9508ad90d8b9 100644
--- a/tools/perf/lib/include/perf/mmap.h
+++ b/tools/lib/perf/include/perf/mmap.h
diff --git a/tools/perf/lib/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h
index a7c50de8d010..a7c50de8d010 100644
--- a/tools/perf/lib/include/perf/threadmap.h
+++ b/tools/lib/perf/include/perf/threadmap.h
diff --git a/tools/perf/lib/internal.h b/tools/lib/perf/internal.h
index 2c27e158de6b..2c27e158de6b 100644
--- a/tools/perf/lib/internal.h
+++ b/tools/lib/perf/internal.h
diff --git a/tools/perf/lib/lib.c b/tools/lib/perf/lib.c
index 18658931fc71..18658931fc71 100644
--- a/tools/perf/lib/lib.c
+++ b/tools/lib/perf/lib.c
diff --git a/tools/perf/lib/libperf.map b/tools/lib/perf/libperf.map
index 7be1af8a546c..7be1af8a546c 100644
--- a/tools/perf/lib/libperf.map
+++ b/tools/lib/perf/libperf.map
diff --git a/tools/perf/lib/libperf.pc.template b/tools/lib/perf/libperf.pc.template
index 117e4a237b55..117e4a237b55 100644
--- a/tools/perf/lib/libperf.pc.template
+++ b/tools/lib/perf/libperf.pc.template
diff --git a/tools/perf/lib/mmap.c b/tools/lib/perf/mmap.c
index 79d5ed6c38cc..79d5ed6c38cc 100644
--- a/tools/perf/lib/mmap.c
+++ b/tools/lib/perf/mmap.c
diff --git a/tools/perf/lib/tests/Makefile b/tools/lib/perf/tests/Makefile
index a43cd08c5c03..96841775feaf 100644
--- a/tools/perf/lib/tests/Makefile
+++ b/tools/lib/perf/tests/Makefile
@@ -16,7 +16,7 @@ all:
 
 include $(srctree)/tools/scripts/Makefile.include
 
-INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/lib
+INCLUDE = -I$(srctree)/tools/lib/perf/include -I$(srctree)/tools/include -I$(srctree)/tools/lib
 
 $(TESTS_A): FORCE
 	$(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a $(LIBAPI)
diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index c8d45091e7c2..c8d45091e7c2 100644
--- a/tools/perf/lib/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index 6d8ebe0c2504..6d8ebe0c2504 100644
--- a/tools/perf/lib/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 135722ac965b..135722ac965b 100644
--- a/tools/perf/lib/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c
index 7dc4d6fbedde..7dc4d6fbedde 100644
--- a/tools/perf/lib/tests/test-threadmap.c
+++ b/tools/lib/perf/tests/test-threadmap.c
diff --git a/tools/perf/lib/threadmap.c b/tools/lib/perf/threadmap.c
index e92c368b0a6c..e92c368b0a6c 100644
--- a/tools/perf/lib/threadmap.c
+++ b/tools/lib/perf/threadmap.c
diff --git a/tools/perf/lib/xyarray.c b/tools/lib/perf/xyarray.c
index dcd901d154bb..dcd901d154bb 100644
--- a/tools/perf/lib/xyarray.c
+++ b/tools/lib/perf/xyarray.c
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index e8c972f89357..1b5042f134a8 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -112,6 +112,12 @@ OPTIONS
 --objdump=<path>::
         Path to objdump binary.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+	Remove first N entries from source file path names in executables
+	and add PREFIX. This allows to display source code compiled on systems
+	with different file system layout.
+
 --skip-missing::
 	Skip symbols that cannot be annotated.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8dbe2119686a..db61f16ffa56 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -367,6 +367,12 @@ OPTIONS
 --objdump=<path>::
         Path to objdump binary.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+	Remove first N entries from source file path names in executables
+	and add PREFIX. This allows to display source code compiled on systems
+	with different file system layout.
+
 --group::
 	Show event group information together. It forces group output also
 	if there are no groups defined in data file.
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 63f938b887dd..5fbe42bd599b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -110,6 +110,10 @@ OPTIONS for 'perf sched timehist'
 --max-stack::
 	Maximum number of functions to display in backtrace, default 5.
 
+-C=::
+--cpu=::
+	Only show events for the given CPU(s) (comma separated list).
+
 -p=::
 --pid=::
 	Only show events for given process ID (comma separated list).
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 5596129a71cf..324b6b53c86b 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -158,6 +158,12 @@ Default is to monitor all CPUS.
 -M::
 --disassembler-style=:: Set disassembler style for objdump.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+        Remove first N entries from source file path names in executables
+        and add PREFIX. This allows to display source code compiled on systems
+        with different file system layout.
+
 --source::
 	Interleave source code with assembly code. Enabled by default,
 	disable with --no-source.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 4934edb5adfd..5d7b947320fb 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -7,6 +7,7 @@ tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
 tools/lib/subcmd
+tools/lib/perf
 tools/lib/argv_split.c
 tools/lib/ctype.c
 tools/lib/hweight.c
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c90f4146e5a2..80e55e796be9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -286,7 +286,7 @@ ifeq ($(DEBUG),0)
   endif
 endif
 
-INC_FLAGS += -I$(src-perf)/lib/include
+INC_FLAGS += -I$(srctree)/tools/lib/perf/include
 INC_FLAGS += -I$(src-perf)/util/include
 INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include
 INC_FLAGS += -I$(srctree)/tools/include/
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index eae5d5e95952..3eda9d4b88e7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -230,7 +230,7 @@ LIB_DIR         = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR         = $(srctree)/tools/lib/bpf/
 SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
-LIBPERF_DIR     = $(srctree)/tools/perf/lib/
+LIBPERF_DIR     = $(srctree)/tools/lib/perf/
 
 # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
 # Without this setting the output feature dump file misses some features, for
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5898662bc8fb..ff61795a4d13 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -535,6 +535,10 @@ int cmd_annotate(int argc, const char **argv)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
@@ -574,6 +578,9 @@ int cmd_annotate(int argc, const char **argv)
 		annotate.sym_hist_filter = argv[0];
 	}
 
+	if (annotate_check_args(&annotate.opts) < 0)
+		return -EINVAL;
+
 	if (symbol_conf.show_nr_samples && annotate.use_gtk) {
 		pr_err("--show-nr-samples is not available in --gtk mode at this time\n");
 		return ret;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index e69f44941aad..246ac0b4d54f 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -595,8 +595,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 {
 	struct c2c_hist_entry *c2c_left;
 	struct c2c_hist_entry *c2c_right;
-	unsigned int tot_hitm_left;
-	unsigned int tot_hitm_right;
+	uint64_t tot_hitm_left;
+	uint64_t tot_hitm_right;
 
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
@@ -629,7 +629,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused,			\
 									\
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);	\
 	c2c_right = container_of(right, struct c2c_hist_entry, he);	\
-	return c2c_left->stats.__f - c2c_right->stats.__f;		\
+	return (uint64_t) c2c_left->stats.__f -				\
+	       (uint64_t) c2c_right->stats.__f;				\
 }
 
 #define STAT_FN(__f)		\
@@ -682,7 +683,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
 
-	return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
+	return (uint64_t) llc_miss(&c2c_left->stats) -
+	       (uint64_t) llc_miss(&c2c_right->stats);
 }
 
 static uint64_t total_records(struct c2c_stats *stats)
@@ -2384,7 +2386,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help", true);
+		key = hist_browser__run(browser, "? - help", true, 0);
 
 		switch (key) {
 		case 's':
@@ -2453,7 +2455,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help", true);
+		key = hist_browser__run(browser, "? - help", true, 0);
 
 		switch (key) {
 		case 'q':
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fb19ef63cc35..4c301466101b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,6 +62,7 @@
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
+#include <linux/bitmap.h>
 
 struct switch_output {
 	bool		 enabled;
@@ -93,7 +94,7 @@ struct record {
 	bool			timestamp_boundary;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
-	cpu_set_t		affinity_mask;
+	struct mmap_cpu_mask	affinity_mask;
 	unsigned long		output_max_size;	/* = 0: unlimited */
 };
 
@@ -961,10 +962,15 @@ static struct perf_event_header finished_round_event = {
 static void record__adjust_affinity(struct record *rec, struct mmap *map)
 {
 	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
-	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
-		CPU_ZERO(&rec->affinity_mask);
-		CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
-		sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+	    !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits,
+			  rec->affinity_mask.nbits)) {
+		bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits);
+		bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits,
+			  map->affinity_mask.bits, rec->affinity_mask.nbits);
+		sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask),
+				  (cpu_set_t *)rec->affinity_mask.bits);
+		if (verbose == 2)
+			mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread");
 	}
 }
 
@@ -2433,7 +2439,6 @@ int cmd_record(int argc, const char **argv)
 # undef REASON
 #endif
 
-	CPU_ZERO(&rec->affinity_mask);
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
@@ -2499,6 +2504,16 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
+	if (rec->opts.affinity != PERF_AFFINITY_SYS) {
+		rec->affinity_mask.nbits = cpu__max_cpu();
+		rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits);
+		if (!rec->affinity_mask.bits) {
+			pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
+			return -ENOMEM;
+		}
+		pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits);
+	}
+
 	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
@@ -2613,6 +2628,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = __cmd_record(&record, argc, argv);
 out:
+	bitmap_free(rec->affinity_mask.bits);
 	evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index de988589d99b..9483b3f0cae3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep)
 				PERF_SAMPLE_BRANCH_ANY))
 		rep->nonany_branch_mode = true;
 
-#ifndef HAVE_LIBUNWIND_SUPPORT
+#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT)
 	if (dwarf_callchain_users) {
-		ui__warning("Please install libunwind development packages "
-			    "during the perf build.\n");
+		ui__warning("Please install libunwind or libdw "
+			    "development packages during the perf build.\n");
 	}
 #endif
 
@@ -1164,7 +1164,8 @@ int cmd_report(int argc, const char **argv)
 			     report_callchain_help, &report_parse_callchain_opt,
 			     callchain_default_opt),
 	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
-		    "Accumulate callchains of children and show total overhead as well"),
+		    "Accumulate callchains of children and show total overhead as well. "
+		    "Enabled by default, use --no-children to disable."),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -1207,6 +1208,10 @@ int cmd_report(int argc, const char **argv)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set,
@@ -1286,6 +1291,9 @@ int cmd_report(int argc, const char **argv)
 		report.symbol_filter_str = argv[0];
 	}
 
+	if (annotate_check_args(&report.annotation_opts) < 0)
+		return -EINVAL;
+
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 8a12d71364c3..82fcc2c15fe4 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -51,6 +51,9 @@
 #define SYM_LEN			129
 #define MAX_PID			1024000
 
+static const char *cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
 struct sched_atom;
 
 struct task_desc {
@@ -2008,6 +2011,9 @@ static void timehist_print_sample(struct perf_sched *sched,
 	char nstr[30];
 	u64 wait_time;
 
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return;
+
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
 
@@ -2994,6 +3000,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	if (cpu_list) {
+		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (err < 0)
+			goto out;
+	}
+
 	evlist = session->evlist;
 
 	symbol__init(&session->header.env);
@@ -3429,6 +3441,7 @@ int cmd_sched(int argc, const char **argv)
 		   "analyze events only for given process id(s)"),
 	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "analyze events only for given thread id(s)"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_PARENT(sched_options)
 	};
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 795e353de095..8affcab75604 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1512,6 +1512,10 @@ int cmd_top(int argc, const char **argv)
 		    "objdump binary to use for disassembly and annotations"),
 	OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_CALLBACK(0, "percent-limit", &top, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
@@ -1582,6 +1586,9 @@ int cmd_top(int argc, const char **argv)
 	if (argc)
 		usage_with_options(top_usage, options);
 
+	if (annotate_check_args(&top.annotation_opts) < 0)
+		goto out_delete_evlist;
+
 	if (!top.evlist->core.nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index b9c203219691..65c4ff6892d9 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,11 +39,13 @@
    Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
 */
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
-int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+#define NSEC_PER_SEC	1000000000L
+
+int probe(hrtimer_nanosleep, rqtp)(void *ctx, int err, long long sec)
 {
-	return sec == 5;
+	return sec / NSEC_PER_SEC == 5ULL;
 }
 
 license(GPL);
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
index 3776d26db9e7..7d7fb0c9fe76 100644
--- a/tools/perf/examples/bpf/empty.c
+++ b/tools/perf/examples/bpf/empty.c
@@ -1,3 +1,3 @@
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 license(GPL);
diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c
index 9cd124b09392..c4481c390d23 100644
--- a/tools/perf/examples/bpf/sys_enter_openat.c
+++ b/tools/perf/examples/bpf/sys_enter_openat.c
@@ -14,7 +14,7 @@
  * the return value.
  */
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 struct syscall_enter_openat_args {
 	unsigned long long unused;
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 6e61c4bdf548..607189a315b2 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
 #ifndef _PERF_BPF_PID_FILTER_
 #define _PERF_BPF_PID_FILTER_
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #define pid_filter(name) pid_map(name, bool)
 
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 316af5b2ff35..7ca6fa5463ee 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 struct bpf_map SEC("maps") __bpf_stdout__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index ca7877f9a976..d1a35b6c649d 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
 
diff --git a/tools/perf/lib/Documentation/Makefile b/tools/perf/lib/Documentation/Makefile
deleted file mode 100644
index 586425a88795..000000000000
--- a/tools/perf/lib/Documentation/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-all:
-	rst2man man/libperf.rst > man/libperf.7
-	rst2pdf tutorial/tutorial.rst
-
-clean:
-	rm -f man/libperf.7
-	rm -f tutorial/tutorial.pdf
diff --git a/tools/perf/lib/Documentation/man/libperf.rst b/tools/perf/lib/Documentation/man/libperf.rst
deleted file mode 100644
index 09a270fccb9c..000000000000
--- a/tools/perf/lib/Documentation/man/libperf.rst
+++ /dev/null
@@ -1,100 +0,0 @@
-.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-libperf
-
-The libperf library provides an API to access the linux kernel perf
-events subsystem. It provides the following high level objects:
-
-  - struct perf_cpu_map
-  - struct perf_thread_map
-  - struct perf_evlist
-  - struct perf_evsel
-
-reference
-=========
-Function reference by header files:
-
-perf/core.h
------------
-.. code-block:: c
-
-  typedef int (\*libperf_print_fn_t)(enum libperf_print_level level,
-                                     const char \*, va_list ap);
-
-  void libperf_set_print(libperf_print_fn_t fn);
-
-perf/cpumap.h
--------------
-.. code-block:: c
-
-  struct perf_cpu_map \*perf_cpu_map__dummy_new(void);
-  struct perf_cpu_map \*perf_cpu_map__new(const char \*cpu_list);
-  struct perf_cpu_map \*perf_cpu_map__read(FILE \*file);
-  struct perf_cpu_map \*perf_cpu_map__get(struct perf_cpu_map \*map);
-  void perf_cpu_map__put(struct perf_cpu_map \*map);
-  int perf_cpu_map__cpu(const struct perf_cpu_map \*cpus, int idx);
-  int perf_cpu_map__nr(const struct perf_cpu_map \*cpus);
-  perf_cpu_map__for_each_cpu(cpu, idx, cpus)
-
-perf/threadmap.h
-----------------
-.. code-block:: c
-
-  struct perf_thread_map \*perf_thread_map__new_dummy(void);
-  void perf_thread_map__set_pid(struct perf_thread_map \*map, int thread, pid_t pid);
-  char \*perf_thread_map__comm(struct perf_thread_map \*map, int thread);
-  struct perf_thread_map \*perf_thread_map__get(struct perf_thread_map \*map);
-  void perf_thread_map__put(struct perf_thread_map \*map);
-
-perf/evlist.h
--------------
-.. code-block::
-
-  void perf_evlist__init(struct perf_evlist \*evlist);
-  void perf_evlist__add(struct perf_evlist \*evlist,
-                      struct perf_evsel \*evsel);
-  void perf_evlist__remove(struct perf_evlist \*evlist,
-                         struct perf_evsel \*evsel);
-  struct perf_evlist \*perf_evlist__new(void);
-  void perf_evlist__delete(struct perf_evlist \*evlist);
-  struct perf_evsel\* perf_evlist__next(struct perf_evlist \*evlist,
-                                     struct perf_evsel \*evsel);
-  int perf_evlist__open(struct perf_evlist \*evlist);
-  void perf_evlist__close(struct perf_evlist \*evlist);
-  void perf_evlist__enable(struct perf_evlist \*evlist);
-  void perf_evlist__disable(struct perf_evlist \*evlist);
-  perf_evlist__for_each_evsel(evlist, pos)
-  void perf_evlist__set_maps(struct perf_evlist \*evlist,
-                           struct perf_cpu_map \*cpus,
-                           struct perf_thread_map \*threads);
-
-perf/evsel.h
-------------
-.. code-block:: c
-
-  struct perf_counts_values {
-        union {
-                struct {
-                        uint64_t val;
-                        uint64_t ena;
-                        uint64_t run;
-                };
-                uint64_t values[3];
-        };
-  };
-
-  void perf_evsel__init(struct perf_evsel \*evsel,
-                      struct perf_event_attr \*attr);
-  struct perf_evsel \*perf_evsel__new(struct perf_event_attr \*attr);
-  void perf_evsel__delete(struct perf_evsel \*evsel);
-  int perf_evsel__open(struct perf_evsel \*evsel, struct perf_cpu_map \*cpus,
-                     struct perf_thread_map \*threads);
-  void perf_evsel__close(struct perf_evsel \*evsel);
-  int perf_evsel__read(struct perf_evsel \*evsel, int cpu, int thread,
-                     struct perf_counts_values \*count);
-  int perf_evsel__enable(struct perf_evsel \*evsel);
-  int perf_evsel__disable(struct perf_evsel \*evsel);
-  int perf_evsel__apply_filter(struct perf_evsel \*evsel, const char \*filter);
-  struct perf_cpu_map \*perf_evsel__cpus(struct perf_evsel \*evsel);
-  struct perf_thread_map \*perf_evsel__threads(struct perf_evsel \*evsel);
-  struct perf_event_attr \*perf_evsel__attr(struct perf_evsel \*evsel);
diff --git a/tools/perf/lib/Documentation/tutorial/tutorial.rst b/tools/perf/lib/Documentation/tutorial/tutorial.rst
deleted file mode 100644
index 7be7bc27b385..000000000000
--- a/tools/perf/lib/Documentation/tutorial/tutorial.rst
+++ /dev/null
@@ -1,123 +0,0 @@
-.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-libperf tutorial
-================
-
-Compile and install libperf from kernel sources
-===============================================
-.. code-block:: bash
-
-  git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-  cd linux/tools/perf/lib
-  make
-  sudo make install prefix=/usr
-
-Libperf object
-==============
-The libperf library provides several high level objects:
-
-struct perf_cpu_map
-  Provides a cpu list abstraction.
-
-struct perf_thread_map
-  Provides a thread list abstraction.
-
-struct perf_evsel
-  Provides an abstraction for single a perf event.
-
-struct perf_evlist
-  Gathers several struct perf_evsel object and performs functions on all of them.
-
-The exported API binds these objects together,
-for full reference see the libperf.7 man page.
-
-Examples
-========
-Examples aim to explain libperf functionality on simple use cases.
-They are based in on a checked out linux kernel git tree:
-
-.. code-block:: bash
-
-  $ cd tools/perf/lib/Documentation/tutorial/
-  $ ls -d  ex-*
-  ex-1-compile  ex-2-evsel-stat  ex-3-evlist-stat
-
-ex-1-compile example
-====================
-This example shows the basic usage of *struct perf_cpu_map*,
-how to create it and display its cpus:
-
-.. code-block:: bash
-
-  $ cd ex-1-compile/
-  $ make
-  gcc -o test test.c -lperf
-  $ ./test
-  0 1 2 3 4 5 6 7
-
-
-The full code listing is here:
-
-.. code-block:: c
-
-   1 #include <perf/cpumap.h>
-   2
-   3 int main(int argc, char **Argv)
-   4 {
-   5         struct perf_cpu_map *cpus;
-   6         int cpu, tmp;
-   7
-   8         cpus = perf_cpu_map__new(NULL);
-   9
-  10         perf_cpu_map__for_each_cpu(cpu, tmp, cpus)
-  11                 fprintf(stdout, "%d ", cpu);
-  12
-  13         fprintf(stdout, "\n");
-  14
-  15         perf_cpu_map__put(cpus);
-  16         return 0;
-  17 }
-
-
-First you need to include the proper header to have *struct perf_cpumap*
-declaration and functions:
-
-.. code-block:: c
-
-   1 #include <perf/cpumap.h>
-
-
-The *struct perf_cpumap* object is created by *perf_cpu_map__new* call.
-The *NULL* argument asks it to populate the object with the current online CPUs list:
-
-.. code-block:: c
-
-   8         cpus = perf_cpu_map__new(NULL);
-
-This is paired with a *perf_cpu_map__put*, that drops its reference at the end, possibly deleting it.
-
-.. code-block:: c
-
-  15         perf_cpu_map__put(cpus);
-
-The iteration through the *struct perf_cpumap* CPUs is done using the *perf_cpu_map__for_each_cpu*
-macro which requires 3 arguments:
-
-- cpu  - the cpu numer
-- tmp  - iteration helper variable
-- cpus - the *struct perf_cpumap* object
-
-.. code-block:: c
-
-  10         perf_cpu_map__for_each_cpu(cpu, tmp, cpus)
-  11                 fprintf(stdout, "%d ", cpu);
-
-ex-2-evsel-stat example
-=======================
-
-TBD
-
-ex-3-evlist-stat example
-========================
-
-TBD
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 415903b48578..da8ec1e8e064 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -263,20 +263,20 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused
 		if (count1 == 11)
 			pr_debug("failed: RF EFLAG recursion issue detected\n");
 		else
-			pr_debug("failed: wrong count for bp1%lld\n", count1);
+			pr_debug("failed: wrong count for bp1: %lld, expected 1\n", count1);
 	}
 
 	if (overflows != 3)
-		pr_debug("failed: wrong overflow hit\n");
+		pr_debug("failed: wrong overflow (%d) hit, expected 3\n", overflows);
 
 	if (overflows_2 != 3)
-		pr_debug("failed: wrong overflow_2 hit\n");
+		pr_debug("failed: wrong overflow_2 (%d) hit, expected 3\n", overflows_2);
 
 	if (count2 != 3)
-		pr_debug("failed: wrong count for bp2\n");
+		pr_debug("failed: wrong count for bp2 (%lld), expected 3\n", count2);
 
 	if (count3 != 2)
-		pr_debug("failed: wrong count for bp3\n");
+		pr_debug("failed: wrong count for bp3 (%lld), expected 2\n", count3);
 
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 173c8f760763..e0c13e6a5788 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -72,5 +72,5 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg
 	if (arg->augmented.args)
 		return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
 
-	return scnprintf(bf, size, "%#x", arg->val);
+	return scnprintf(bf, size, "%#lx", arg->val);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index d4d3558fdef4..f36dee499320 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -18,7 +18,9 @@
 #include "../../util/evlist.h"
 #include "../../util/header.h"
 #include "../../util/hist.h"
+#include "../../util/machine.h"
 #include "../../util/map.h"
+#include "../../util/maps.h"
 #include "../../util/symbol.h"
 #include "../../util/map_symbol.h"
 #include "../../util/branch.h"
@@ -391,6 +393,57 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 	he->init_have_children = true;
 }
 
+static bool hist_browser__selection_has_children(struct hist_browser *browser)
+{
+	struct hist_entry *he = browser->he_selection;
+	struct map_symbol *ms = browser->selection;
+
+	if (!he || !ms)
+		return false;
+
+	if (ms == &he->ms)
+	       return he->has_children;
+
+	return container_of(ms, struct callchain_list, ms)->has_children;
+}
+
+static bool hist_browser__he_selection_unfolded(struct hist_browser *browser)
+{
+	return browser->he_selection ? browser->he_selection->unfolded : false;
+}
+
+static bool hist_browser__selection_unfolded(struct hist_browser *browser)
+{
+	struct hist_entry *he = browser->he_selection;
+	struct map_symbol *ms = browser->selection;
+
+	if (!he || !ms)
+		return false;
+
+	if (ms == &he->ms)
+	       return he->unfolded;
+
+	return container_of(ms, struct callchain_list, ms)->unfolded;
+}
+
+static char *hist_browser__selection_sym_name(struct hist_browser *browser, char *bf, size_t size)
+{
+	struct hist_entry *he = browser->he_selection;
+	struct map_symbol *ms = browser->selection;
+	struct callchain_list *callchain_entry;
+
+	if (!he || !ms)
+		return NULL;
+
+	if (ms == &he->ms) {
+	       hist_entry__sym_snprintf(he, bf, size, 0);
+	       return bf + 4; // skip the level, e.g. '[k] '
+	}
+
+	callchain_entry = container_of(ms, struct callchain_list, ms);
+	return callchain_list__sym_name(callchain_entry, bf, size, browser->show_dso);
+}
+
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -624,10 +677,81 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
 	return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
+static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, int key)
+{
+	switch (key) {
+	case K_TIMER: {
+		struct hist_browser_timer *hbt = browser->hbt;
+		u64 nr_entries;
+
+		WARN_ON_ONCE(!hbt);
+
+		if (hbt)
+			hbt->timer(hbt->arg);
+
+		if (hist_browser__has_filter(browser) || symbol_conf.report_hierarchy)
+			hist_browser__update_nr_entries(browser);
+
+		nr_entries = hist_browser__nr_entries(browser);
+		ui_browser__update_nr_entries(&browser->b, nr_entries);
+
+		if (warn_lost_event &&
+		    (browser->hists->stats.nr_lost_warned !=
+		    browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
+			browser->hists->stats.nr_lost_warned =
+				browser->hists->stats.nr_events[PERF_RECORD_LOST];
+			ui_browser__warn_lost_events(&browser->b);
+		}
+
+		hist_browser__title(browser, title, sizeof(title));
+		ui_browser__show_title(&browser->b, title);
+		break;
+	}
+	case 'D': { /* Debug */
+		struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node);
+		static int seq;
+
+		ui_helpline__pop();
+		ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
+				   seq++, browser->b.nr_entries, browser->hists->nr_entries,
+				   browser->b.extra_title_lines, browser->b.rows,
+				   browser->b.index, browser->b.top_idx, h->row_offset, h->nr_rows);
+	}
+		break;
+	case 'C':
+		/* Collapse the whole world. */
+		hist_browser__set_folding(browser, false);
+		break;
+	case 'c':
+		/* Collapse the selected entry. */
+		hist_browser__set_folding_selected(browser, false);
+		break;
+	case 'E':
+		/* Expand the whole world. */
+		hist_browser__set_folding(browser, true);
+		break;
+	case 'e':
+		/* Expand the selected entry. */
+		hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser));
+		break;
+	case 'H':
+		browser->show_headers = !browser->show_headers;
+		hist_browser__update_rows(browser);
+		break;
+	case '+':
+		if (hist_browser__toggle_fold(browser))
+			break;
+		/* fall thru */
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
 int hist_browser__run(struct hist_browser *browser, const char *help,
-		      bool warn_lost_event)
+		      bool warn_lost_event, int key)
 {
-	int key;
 	char title[160];
 	struct hist_browser_timer *hbt = browser->hbt;
 	int delay_secs = hbt ? hbt->refresh : 0;
@@ -640,79 +764,14 @@ int hist_browser__run(struct hist_browser *browser, const char *help,
 	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
 
+	if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, key))
+		goto out;
+
 	while (1) {
 		key = ui_browser__run(&browser->b, delay_secs);
 
-		switch (key) {
-		case K_TIMER: {
-			u64 nr_entries;
-
-			WARN_ON_ONCE(!hbt);
-
-			if (hbt)
-				hbt->timer(hbt->arg);
-
-			if (hist_browser__has_filter(browser) ||
-			    symbol_conf.report_hierarchy)
-				hist_browser__update_nr_entries(browser);
-
-			nr_entries = hist_browser__nr_entries(browser);
-			ui_browser__update_nr_entries(&browser->b, nr_entries);
-
-			if (warn_lost_event &&
-			    (browser->hists->stats.nr_lost_warned !=
-			    browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
-				browser->hists->stats.nr_lost_warned =
-					browser->hists->stats.nr_events[PERF_RECORD_LOST];
-				ui_browser__warn_lost_events(&browser->b);
-			}
-
-			hist_browser__title(browser, title, sizeof(title));
-			ui_browser__show_title(&browser->b, title);
-			continue;
-		}
-		case 'D': { /* Debug */
-			static int seq;
-			struct hist_entry *h = rb_entry(browser->b.top,
-							struct hist_entry, rb_node);
-			ui_helpline__pop();
-			ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
-					   seq++, browser->b.nr_entries,
-					   browser->hists->nr_entries,
-					   browser->b.extra_title_lines,
-					   browser->b.rows,
-					   browser->b.index,
-					   browser->b.top_idx,
-					   h->row_offset, h->nr_rows);
-		}
-			break;
-		case 'C':
-			/* Collapse the whole world. */
-			hist_browser__set_folding(browser, false);
-			break;
-		case 'c':
-			/* Collapse the selected entry. */
-			hist_browser__set_folding_selected(browser, false);
+		if (hist_browser__handle_hotkey(browser, warn_lost_event, title, key))
 			break;
-		case 'E':
-			/* Expand the whole world. */
-			hist_browser__set_folding(browser, true);
-			break;
-		case 'e':
-			/* Expand the selected entry. */
-			hist_browser__set_folding_selected(browser, true);
-			break;
-		case 'H':
-			browser->show_headers = !browser->show_headers;
-			hist_browser__update_rows(browser);
-			break;
-		case K_ENTER:
-			if (hist_browser__toggle_fold(browser))
-				break;
-			/* fall thru */
-		default:
-			goto out;
-		}
 	}
 out:
 	ui_browser__hide(&browser->b);
@@ -2339,7 +2398,7 @@ close_file_and_continue:
 	closedir(pwd_dir);
 
 	if (nr_options) {
-		choice = ui__popup_menu(nr_options, options);
+		choice = ui__popup_menu(nr_options, options, NULL);
 		if (choice < nr_options && choice >= 0) {
 			tmp = strdup(abs_path[choice]);
 			if (tmp) {
@@ -2411,7 +2470,8 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused,
 		 struct popup_action *act, char **optstr,
 		 struct map_symbol *ms)
 {
-	if (ms->sym == NULL || ms->map->dso->annotate_warned)
+	if (ms->sym == NULL || ms->map->dso->annotate_warned ||
+	    symbol__annotation(ms->sym)->src == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Annotate %s", ms->sym->name) < 0)
@@ -2484,11 +2544,8 @@ add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 	return 1;
 }
 
-static int
-do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+static int hists_browser__zoom_map(struct hist_browser *browser, struct map *map)
 {
-	struct map *map = act->ms.map;
-
 	if (!hists__has(browser->hists, dso) || map == NULL)
 		return 0;
 
@@ -2511,13 +2568,19 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 }
 
 static int
+do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+{
+	return hists_browser__zoom_map(browser, act->ms.map);
+}
+
+static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
 	if (!hists__has(browser->hists, dso) || map == NULL)
 		return 0;
 
-	if (asprintf(optstr, "Zoom %s %s DSO",
+	if (asprintf(optstr, "Zoom %s %s DSO (use the 'k' hotkey to zoom directly into the kernel)",
 		     browser->hists->dso_filter ? "out of" : "into",
 		     __map__is_kernel(map) ? "the Kernel" : map->dso->short_name) < 0)
 		return 0;
@@ -2527,6 +2590,28 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	return 1;
 }
 
+static int do_toggle_callchain(struct hist_browser *browser, struct popup_action *act __maybe_unused)
+{
+	hist_browser__toggle_fold(browser);
+	return 0;
+}
+
+static int add_callchain_toggle_opt(struct hist_browser *browser, struct popup_action *act, char **optstr)
+{
+	char sym_name[512];
+
+        if (!hist_browser__selection_has_children(browser))
+                return 0;
+
+	if (asprintf(optstr, "%s [%s] callchain (one level, same as '+' hotkey, use 'e'/'c' for the whole main level entry)",
+		     hist_browser__selection_unfolded(browser) ? "Collapse" : "Expand",
+		     hist_browser__selection_sym_name(browser, sym_name, sizeof(sym_name))) < 0)
+		return 0;
+
+	act->fn = do_toggle_callchain;
+	return 1;
+}
+
 static int
 do_browse_map(struct hist_browser *browser __maybe_unused,
 	      struct popup_action *act)
@@ -2858,12 +2943,15 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	"For symbolic views (--sort has sym):\n\n"			\
 	"ENTER         Zoom into DSO/Threads & Annotate current symbol\n" \
 	"ESC           Zoom out\n"					\
+	"+             Expand/Collapse one callchain level\n"		\
 	"a             Annotate current symbol\n"			\
 	"C             Collapse all callchains\n"			\
 	"d             Zoom into current DSO\n"				\
+	"e             Expand/Collapse main entry callchains\n"	\
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
 	"H             Display column headers\n"			\
+	"k             Zoom into the kernel map\n"			\
 	"L             Change percent limit\n"				\
 	"m             Display context menu\n"				\
 	"S             Zoom into current Processor Socket\n"		\
@@ -2914,13 +3002,13 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	while (1) {
 		struct thread *thread = NULL;
 		struct map *map = NULL;
-		int choice = 0;
+		int choice;
 		int socked_id = -1;
 
-		nr_options = 0;
-
-		key = hist_browser__run(browser, helpline,
-					warn_lost_event);
+		key = 0; // reset key
+do_hotkey:		 // key came straight from options ui__popup_menu()
+		choice = nr_options = 0;
+		key = hist_browser__run(browser, helpline, warn_lost_event, key);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -2950,6 +3038,14 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 
+			if (symbol__annotation(browser->selection->sym)->src == NULL) {
+				ui_browser__warning(&browser->b, delay_secs * 2,
+						    "No samples for the \"%s\" symbol.\n\n"
+						    "Probably appeared just in a callchain",
+						    browser->selection->sym->name);
+				continue;
+			}
+
 			actions->ms.map = browser->selection->map;
 			actions->ms.sym = browser->selection->sym;
 			do_annotate(browser, actions);
@@ -2961,6 +3057,10 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 			actions->ms.map = map;
 			do_zoom_dso(browser, actions);
 			continue;
+		case 'k':
+			if (browser->selection != NULL)
+				hists_browser__zoom_map(browser, browser->selection->maps->machine->vmlinux_map);
+			continue;
 		case 'V':
 			verbose = (verbose + 1) % 4;
 			browser->show_dso = verbose > 0;
@@ -3062,6 +3162,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 
 				continue;
 			}
+			actions->ms.map = map;
 			top = pstack__peek(browser->pstack);
 			if (top == &browser->hists->dso_filter) {
 				/*
@@ -3135,6 +3236,7 @@ skip_annotation:
 					     &options[nr_options], thread);
 		nr_options += add_dso_opt(browser, &actions[nr_options],
 					  &options[nr_options], map);
+		nr_options += add_callchain_toggle_opt(browser, &actions[nr_options], &options[nr_options]);
 		nr_options += add_map_opt(browser, &actions[nr_options],
 					  &options[nr_options],
 					  browser->selection ?
@@ -3193,10 +3295,13 @@ skip_scripting:
 		do {
 			struct popup_action *act;
 
-			choice = ui__popup_menu(nr_options, options);
-			if (choice == -1 || choice >= nr_options)
+			choice = ui__popup_menu(nr_options, options, &key);
+			if (choice == -1)
 				break;
 
+			if (choice == nr_options)
+				goto do_hotkey;
+
 			act = &actions[choice];
 			key = act->fn(browser, act);
 		} while (key == 1);
@@ -3492,7 +3597,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	memset(&action, 0, sizeof(action));
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help", true);
+		key = hist_browser__run(browser, "? - help", true, 0);
 
 		switch (key) {
 		case 'q':
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index 078f2f2c7abd..1e938d9ffa5e 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -34,7 +34,7 @@ struct hist_browser {
 struct hist_browser *hist_browser__new(struct hists *hists);
 void hist_browser__delete(struct hist_browser *browser);
 int hist_browser__run(struct hist_browser *browser, const char *help,
-		      bool warn_lost_event);
+		      bool warn_lost_event, int key);
 void hist_browser__init(struct hist_browser *browser,
 			struct hists *hists);
 #endif /* _PERF_UI_BROWSER_HISTS_H_ */
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index 76d356a18790..7cb2d6678039 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -56,7 +56,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
 			return -1;
 		}
 	}
-	choice = ui__popup_menu(num_res, names);
+	choice = ui__popup_menu(num_res, names, NULL);
 	for (i = 0; i < num_res; i++)
 		zfree(&names[i]);
 	free(names);
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index fc733a6354d4..47d2c7a8cbe1 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -126,7 +126,7 @@ static int list_scripts(char *script_name, bool *custom,
 			SCRIPT_FULLPATH_LEN);
 	if (num < 0)
 		num = 0;
-	choice = ui__popup_menu(num + max_std, (char * const *)names);
+	choice = ui__popup_menu(num + max_std, (char * const *)names, NULL);
 	if (choice < 0) {
 		ret = -1;
 		goto out;
diff --git a/tools/perf/ui/gtk/Build b/tools/perf/ui/gtk/Build
index ec22e899a224..eef708c502f4 100644
--- a/tools/perf/ui/gtk/Build
+++ b/tools/perf/ui/gtk/Build
@@ -1,4 +1,4 @@
-CFLAGS_gtk += -fPIC $(GTK_CFLAGS)
+CFLAGS_gtk += -fPIC $(GTK_CFLAGS) -Wno-deprecated-declarations
 
 gtk-y += browser.o
 gtk-y += hists.o
@@ -7,3 +7,8 @@ gtk-y += util.o
 gtk-y += helpline.o
 gtk-y += progress.o
 gtk-y += annotate.o
+gtk-y += zalloc.o
+
+$(OUTPUT)ui/gtk/zalloc.o: ../lib/zalloc.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index b98dd0e31dc1..0f562e2cb1e8 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -23,7 +23,7 @@ static void ui_browser__argv_write(struct ui_browser *browser,
 	ui_browser__write_nstring(browser, *arg, browser->width);
 }
 
-static int popup_menu__run(struct ui_browser *menu)
+static int popup_menu__run(struct ui_browser *menu, int *keyp)
 {
 	int key;
 
@@ -45,6 +45,11 @@ static int popup_menu__run(struct ui_browser *menu)
 			key = -1;
 			break;
 		default:
+			if (keyp) {
+				*keyp = key;
+				key = menu->nr_entries;
+				break;
+			}
 			continue;
 		}
 
@@ -55,7 +60,7 @@ static int popup_menu__run(struct ui_browser *menu)
 	return key;
 }
 
-int ui__popup_menu(int argc, char * const argv[])
+int ui__popup_menu(int argc, char * const argv[], int *keyp)
 {
 	struct ui_browser menu = {
 		.entries    = (void *)argv,
@@ -64,8 +69,7 @@ int ui__popup_menu(int argc, char * const argv[])
 		.write	    = ui_browser__argv_write,
 		.nr_entries = argc,
 	};
-
-	return popup_menu__run(&menu);
+	return popup_menu__run(&menu, keyp);
 }
 
 int ui_browser__input_window(const char *title, const char *text, char *input,
diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h
index 40891942f465..e30cea807564 100644
--- a/tools/perf/ui/util.h
+++ b/tools/perf/ui/util.h
@@ -5,7 +5,7 @@
 #include <stdarg.h>
 
 int ui__getch(int delay_secs);
-int ui__popup_menu(int argc, char * const argv[]);
+int ui__popup_menu(int argc, char * const argv[], int *keyp);
 int ui__help_window(const char *text);
 int ui__dialog_yesno(const char *msg);
 void __ui__info_window(const char *title, const char *text, const char *exit_msg);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index f5e77ed237e8..ca73fb74ad03 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1966,14 +1966,20 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"$1\"",
+		 " -l -d %s %s %s %c%s%c %s%s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
-		 opts->annotate_src ? "-S" : "");
+		 opts->annotate_src ? "-S" : "",
+		 opts->prefix ? "--prefix " : "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix ?: "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix_strip ? "--prefix-strip=" : "",
+		 opts->prefix_strip ?: "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -3204,3 +3210,12 @@ out:
 	free(str1);
 	return err;
 }
+
+int annotate_check_args(struct annotation_options *args)
+{
+	if (args->prefix_strip && !args->prefix) {
+		pr_err("--prefix-strip requires --prefix\n");
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 7075d98f69d9..455403e8fede 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -94,6 +94,8 @@ struct annotation_options {
 	int  context;
 	const char *objdump_path;
 	const char *disassembler_style;
+	const char *prefix;
+	const char *prefix_strip;
 	unsigned int percent_type;
 };
 
@@ -415,4 +417,7 @@ void annotation_config__init(void);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
+
+int annotate_check_args(struct annotation_options *args);
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index fc361c3f8570..c8885dfa3667 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -71,7 +71,11 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags,
 	CompilerInstance Clang;
 	Clang.createDiagnostics();
 
+#if CLANG_VERSION_MAJOR < 9
 	Clang.setVirtualFileSystem(&*VFS);
+#else
+	Clang.createFileManager(&*VFS);
+#endif
 
 #if CLANG_VERSION_MAJOR < 4
 	IntrusiveRefCntPtr<CompilerInvocation> CI =
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index f9a20a39b64a..7d226241f1d7 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -12,7 +12,8 @@
 #define MAXIDLEN 256
 %}
 
-%pure-parser
+%define api.pure full
+
 %parse-param { double *final_val }
 %parse-param { struct parse_ctx *ctx }
 %parse-param { const char **pp }
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93ad27830e2b..4246e7447e54 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2922,7 +2922,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	if (ret == -1)
 		return -1;
 
-	stctime = st.st_ctime;
+	stctime = st.st_mtime;
 	fprintf(fp, "# captured on    : %s", ctime(&stctime));
 
 	fprintf(fp, "# header version : %u\n", header->version);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 063d1b93c53d..3b664fa673a6 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -23,6 +23,18 @@
 #include "mmap.h"
 #include "../perf.h"
 #include <internal/lib.h> /* page_size */
+#include <linux/bitmap.h>
+
+#define MASK_SIZE 1023
+void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag)
+{
+	char buf[MASK_SIZE + 1];
+	size_t len;
+
+	len = bitmap_scnprintf(mask->bits, mask->nbits, buf, MASK_SIZE);
+	buf[len] = '\0';
+	pr_debug("%p: %s mask[%zd]: %s\n", mask, tag, mask->nbits, buf);
+}
 
 size_t mmap__mmap_len(struct mmap *map)
 {
@@ -207,6 +219,8 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused)
 
 void mmap__munmap(struct mmap *map)
 {
+	bitmap_free(map->affinity_mask.bits);
+
 	perf_mmap__aio_munmap(map);
 	if (map->data != NULL) {
 		munmap(map->data, mmap__mmap_len(map));
@@ -215,7 +229,7 @@ void mmap__munmap(struct mmap *map)
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-static void build_node_mask(int node, cpu_set_t *mask)
+static void build_node_mask(int node, struct mmap_cpu_mask *mask)
 {
 	int c, cpu, nr_cpus;
 	const struct perf_cpu_map *cpu_map = NULL;
@@ -228,17 +242,23 @@ static void build_node_mask(int node, cpu_set_t *mask)
 	for (c = 0; c < nr_cpus; c++) {
 		cpu = cpu_map->map[c]; /* map c index to online cpu index */
 		if (cpu__get_node(cpu) == node)
-			CPU_SET(cpu, mask);
+			set_bit(cpu, mask->bits);
 	}
 }
 
-static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
+static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
 {
-	CPU_ZERO(&map->affinity_mask);
+	map->affinity_mask.nbits = cpu__max_cpu();
+	map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits);
+	if (!map->affinity_mask.bits)
+		return -1;
+
 	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
 		build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
 	else if (mp->affinity == PERF_AFFINITY_CPU)
-		CPU_SET(map->core.cpu, &map->affinity_mask);
+		set_bit(map->core.cpu, map->affinity_mask.bits);
+
+	return 0;
 }
 
 int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
@@ -249,7 +269,15 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 		return -1;
 	}
 
-	perf_mmap__setup_affinity_mask(map, mp);
+	if (mp->affinity != PERF_AFFINITY_SYS &&
+		perf_mmap__setup_affinity_mask(map, mp)) {
+		pr_debug2("failed to alloc mmap affinity mask, error %d\n",
+			  errno);
+		return -1;
+	}
+
+	if (verbose == 2)
+		mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap");
 
 	map->core.flush = mp->flush;
 
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index bee4e83f7109..9d5f589f02ae 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -15,6 +15,15 @@
 #include "event.h"
 
 struct aiocb;
+
+struct mmap_cpu_mask {
+	unsigned long *bits;
+	size_t nbits;
+};
+
+#define MMAP_CPU_MASK_BYTES(m) \
+	(BITS_TO_LONGS(((struct mmap_cpu_mask *)m)->nbits) * sizeof(unsigned long))
+
 /**
  * struct mmap - perf's ring buffer mmap details
  *
@@ -31,7 +40,7 @@ struct mmap {
 		int		 nr_cblocks;
 	} aio;
 #endif
-	cpu_set_t	affinity_mask;
+	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
 	int		comp_level;
 };
@@ -52,4 +61,6 @@ int perf_mmap__push(struct mmap *md, void *to,
 
 size_t mmap__mmap_len(struct mmap *map);
 
+void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag);
+
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e2eea4e601b4..94f8bcd83582 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,4 +1,4 @@
-%pure-parser
+%define api.pure full
 %parse-param {void *_parse_state}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 9fcba2872130..ab0cfd790ad0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -324,8 +324,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms,
 	return ret;
 }
 
-static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
-				    size_t size, unsigned int width)
+int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width)
 {
 	return _hist_entry__sym_snprintf(&he->ms, he->ip,
 					 he->level, bf, size, width);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5aff9542d9b7..6c862d62d052 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -164,6 +164,8 @@ static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
 	return he->callchain_size != 0;
 }
 
+int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width);
+
 static inline bool hist_entry__has_pairs(struct hist_entry *he)
 {
 	return !list_empty(&he->pairs.node);