diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 1d6092c460dd..73496320fca3 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -56,6 +56,9 @@ OPTIONS
 --all-user::
 	Configure all used events to run in user space.
 
+--ldload::
+	Specify desired latency for loads event.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 3a8a9ba2b041..947db6fe512c 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -109,6 +109,10 @@ OPTIONS
 	Dry run. With this option, --add and --del doesn't execute actual
 	adding and removal operations.
 
+--cache::
+	Cache the probes (with --add option). Any events which successfully added
+	are also stored in the cache file.
+
 --max-probes=NUM::
 	Set the maximum number of probe points for an event. Default is 128.
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f7645a42708e..7f628f9c2fb4 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -666,7 +666,8 @@ static void hists__process(struct hists *hists)
 	hists__precompute(hists);
 	hists__output_resort(hists, NULL);
 
-	hists__fprintf(hists, true, 0, 0, 0, stdout);
+	hists__fprintf(hists, true, 0, 0, 0, stdout,
+		       symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
@@ -1044,7 +1045,7 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 }
 
 static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		       struct perf_evsel *evsel __maybe_unused)
+		       struct hists *hists __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
@@ -1055,7 +1056,7 @@ static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int hpp__width(struct perf_hpp_fmt *fmt,
 		      struct perf_hpp *hpp __maybe_unused,
-		      struct perf_evsel *evsel __maybe_unused)
+		      struct hists *hists __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 1dc140c5481d..d608a2c9e48c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -67,6 +67,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
 		     parse_record_events),
+	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 9af859b28b15..6d7ab4316449 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -512,6 +512,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
+	OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a87cb338bdf1..9f36b236f0f9 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -370,7 +370,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 			continue;
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
-		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
+		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+			       symbol_conf.use_callchain);
 		fprintf(stdout, "\n\n");
 	}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2a6cc254ad0c..81dba80a42b5 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -295,7 +295,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout);
+		       top->min_percent, stdout, symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 098874b99981..80018feb99c0 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -365,6 +365,7 @@ ifndef NO_LIBUNWIND
     $(call detected,CONFIG_LIBUNWIND_X86)
     CFLAGS += -DHAVE_LIBUNWIND_X86_SUPPORT
     LDFLAGS += -lunwind-x86
+    EXTLIBS_LIBUNWIND += -lunwind-x86
     have_libunwind = 1
   endif
 
@@ -372,6 +373,7 @@ ifndef NO_LIBUNWIND
     $(call detected,CONFIG_LIBUNWIND_AARCH64)
     CFLAGS += -DHAVE_LIBUNWIND_AARCH64_SUPPORT
     LDFLAGS += -lunwind-aarch64
+    EXTLIBS_LIBUNWIND += -lunwind-aarch64
     have_libunwind = 1
     $(call feature_check,libunwind-debug-frame-aarch64)
     ifneq ($(feature-libunwind-debug-frame-aarch64), 1)
@@ -449,6 +451,7 @@ ifndef NO_LIBUNWIND
   CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
   CFLAGS  += $(LIBUNWIND_CFLAGS)
   LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  EXTLIBS += $(EXTLIBS_LIBUNWIND)
 endif
 
 ifndef NO_LIBAUDIT
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 538bae880bfe..b1b60544a545 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1470,7 +1470,7 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
 		    column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+		ret = fmt->width(fmt, NULL, browser->hists);
 
 		if (first) {
 			/* for folded sign */
@@ -1531,7 +1531,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret = fmt->header(fmt, &dummy_hpp, hists);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1568,7 +1568,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret = fmt->header(fmt, &dummy_hpp, hists);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1605,7 +1605,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			ret = fmt->header(fmt, &dummy_hpp, hists);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = trim(dummy_hpp.buf);
@@ -1622,21 +1622,38 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	return ret;
 }
 
-static void hist_browser__show_headers(struct hist_browser *browser)
+static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 {
 	char headers[1024];
 
-	if (symbol_conf.report_hierarchy)
-		hists_browser__scnprintf_hierarchy_headers(browser, headers,
-							   sizeof(headers));
-	else
-		hists_browser__scnprintf_headers(browser, headers,
-						 sizeof(headers));
+	hists_browser__scnprintf_hierarchy_headers(browser, headers,
+						   sizeof(headers));
+
 	ui_browser__gotorc(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }
 
+static void hists_browser__headers(struct hist_browser *browser)
+{
+	char headers[1024];
+
+	hists_browser__scnprintf_headers(browser, headers,
+					 sizeof(headers));
+
+	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+}
+
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+	if (symbol_conf.report_hierarchy)
+		hists_browser__hierarchy_headers(browser);
+	else
+		hists_browser__headers(browser);
+}
+
 static void ui_browser__hists_init_top(struct ui_browser *browser)
 {
 	if (browser->top == NULL) {
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 932adfaa05af..e5c1325b0340 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				strcat(buf, "+");
 			first_col = false;
 
-			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			fmt->header(fmt, &hpp, hists);
 			strcat(buf, ltrim(rtrim(hpp.buf)));
 		}
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index af07ffb129ca..6940745aa77c 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -215,9 +215,10 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 
 static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 			 struct perf_hpp *hpp __maybe_unused,
-			 struct perf_evsel *evsel)
+			 struct hists *hists)
 {
 	int len = fmt->user_len ?: fmt->len;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 
 	if (symbol_conf.event_group)
 		len = max(len, evsel->nr_members * fmt->len);
@@ -229,9 +230,9 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct perf_evsel *evsel)
+			  struct hists *hists)
 {
-	int len = hpp__width_fn(fmt, hpp, evsel);
+	int len = hpp__width_fn(fmt, hpp, hists);
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
@@ -632,7 +633,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 		else
 			ret += 2;
 
-		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret += fmt->width(fmt, &dummy_hpp, hists);
 	}
 
 	if (verbose && hists__has(hists, sym)) /* Addr + origin */
@@ -657,7 +658,7 @@ unsigned int hists__overhead_width(struct hists *hists)
 		else
 			ret += 2;
 
-		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret += fmt->width(fmt, &dummy_hpp, hists);
 	}
 
 	return ret;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 560eb47d56f9..f04a63112079 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -492,14 +492,15 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
-			       struct hists *hists,
-			       char *bf, size_t bfsz, FILE *fp)
+			       char *bf, size_t bfsz, FILE *fp,
+			       bool use_callchain)
 {
 	int ret;
 	struct perf_hpp hpp = {
 		.buf		= bf,
 		.size		= size,
 	};
+	struct hists *hists = he->hists;
 	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
@@ -512,7 +513,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (symbol_conf.use_callchain)
+	if (use_callchain)
 		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
@@ -548,7 +549,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				    struct perf_hpp_list_node, list);
 
 	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists_to_evsel(hists));
+		fmt->header(fmt, hpp, hists);
 		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
@@ -568,7 +569,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				header_width += fprintf(fp, "+");
 			first_col = false;
 
-			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			fmt->header(fmt, hpp, hists);
 
 			header_width += fprintf(fp, "%s", trim(hpp->buf));
 		}
@@ -589,7 +590,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 			fprintf(fp, "%s", sep ?: "..");
 		first_col = false;
 
-		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		width = fmt->width(fmt, hpp, hists);
 		fprintf(fp, "%.*s", width, dots);
 	}
 
@@ -606,7 +607,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				width++;  /* for '+' sign between column header */
 			first_col = false;
 
-			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+			width += fmt->width(fmt, hpp, hists);
 		}
 
 		if (width > header_width)
@@ -622,47 +623,31 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	return 2;
 }
 
-size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-		      int max_cols, float min_pcnt, FILE *fp)
+static int
+hists__fprintf_hierarchy_headers(struct hists *hists,
+				 struct perf_hpp *hpp,
+				 FILE *fp)
+{
+	struct perf_hpp_list_node *fmt_node;
+	struct perf_hpp_fmt *fmt;
+
+	list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+			perf_hpp__reset_width(fmt, hists);
+	}
+
+	return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
+}
+
+static int
+hists__fprintf_standard_headers(struct hists *hists,
+				struct perf_hpp *hpp,
+				FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
-	struct perf_hpp_list_node *fmt_node;
-	struct rb_node *nd;
-	size_t ret = 0;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
-	int nr_rows = 0;
-	char bf[96];
-	struct perf_hpp dummy_hpp = {
-		.buf	= bf,
-		.size	= sizeof(bf),
-	};
 	bool first = true;
-	size_t linesz;
-	char *line = NULL;
-	unsigned indent;
-
-	init_rem_hits();
-
-	hists__for_each_format(hists, fmt)
-		perf_hpp__reset_width(fmt, hists);
-
-	if (symbol_conf.col_width_list_str)
-		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
-
-	if (!show_header)
-		goto print_entries;
-
-	fprintf(fp, "# ");
-
-	if (symbol_conf.report_hierarchy) {
-		list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
-			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
-				perf_hpp__reset_width(fmt, hists);
-		}
-		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
-		goto print_entries;
-	}
 
 	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
@@ -673,16 +658,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
-		fprintf(fp, "%s", bf);
+		fmt->header(fmt, hpp, hists);
+		fprintf(fp, "%s", hpp->buf);
 	}
 
 	fprintf(fp, "\n");
-	if (max_rows && ++nr_rows >= max_rows)
-		goto out;
 
 	if (sep)
-		goto print_entries;
+		return 1;
 
 	first = true;
 
@@ -699,20 +682,60 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		width = fmt->width(fmt, hpp, hists);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
 
 	fprintf(fp, "\n");
-	if (max_rows && ++nr_rows >= max_rows)
-		goto out;
-
 	fprintf(fp, "#\n");
-	if (max_rows && ++nr_rows >= max_rows)
+	return 3;
+}
+
+static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+{
+	char bf[96];
+	struct perf_hpp dummy_hpp = {
+		.buf	= bf,
+		.size	= sizeof(bf),
+	};
+
+	fprintf(fp, "# ");
+
+	if (symbol_conf.report_hierarchy)
+		return hists__fprintf_hierarchy_headers(hists, &dummy_hpp, fp);
+	else
+		return hists__fprintf_standard_headers(hists, &dummy_hpp, fp);
+
+}
+
+size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
+		      int max_cols, float min_pcnt, FILE *fp,
+		      bool use_callchain)
+{
+	struct perf_hpp_fmt *fmt;
+	struct rb_node *nd;
+	size_t ret = 0;
+	const char *sep = symbol_conf.field_sep;
+	int nr_rows = 0;
+	size_t linesz;
+	char *line = NULL;
+	unsigned indent;
+
+	init_rem_hits();
+
+	hists__for_each_format(hists, fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
+	if (show_header)
+		nr_rows += hists__fprintf_headers(hists, fp);
+
+	if (max_rows && nr_rows >= max_rows)
 		goto out;
 
-print_entries:
 	linesz = hists__sort_list_width(hists) + 3 + 1;
 	linesz += perf_hpp__color_overhead();
 	line = malloc(linesz);
@@ -734,7 +757,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 20aef90bf194..62b147366d01 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -387,9 +387,8 @@ void disable_buildid_cache(void)
 	no_buildid_cache = true;
 }
 
-static char *build_id_cache__dirname_from_path(const char *name,
-					       bool is_kallsyms, bool is_vdso,
-					       const char *sbuild_id)
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+			       bool is_kallsyms, bool is_vdso)
 {
 	char *realname = (char *)name, *filename;
 	bool slash = is_kallsyms || is_vdso;
@@ -417,8 +416,7 @@ int build_id_cache__list_build_ids(const char *pathname,
 	char *dir_name;
 	int ret = 0;
 
-	dir_name = build_id_cache__dirname_from_path(pathname, false, false,
-						     NULL);
+	dir_name = build_id_cache__cachedir(NULL, pathname, false, false);
 	if (!dir_name)
 		return -ENOMEM;
 
@@ -444,8 +442,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			goto out_free;
 	}
 
-	dir_name = build_id_cache__dirname_from_path(name, is_kallsyms,
-						     is_vdso, sbuild_id);
+	dir_name = build_id_cache__cachedir(sbuild_id, name,
+					    is_kallsyms, is_vdso);
 	if (!dir_name)
 		goto out_free;
 
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index e5435f46e48e..d8c7f2fc6a87 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -30,6 +30,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
 int perf_session__write_buildid_table(struct perf_session *session, int fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+			       bool is_kallsyms, bool is_vdso);
 int build_id_cache__list_build_ids(const char *pathname,
 				   struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 8749eca3055f..31e09a4e8862 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -742,6 +742,9 @@ static void perf_config_set__purge(struct perf_config_set *set)
 
 void perf_config_set__delete(struct perf_config_set *set)
 {
+	if (set == NULL)
+		return;
+
 	perf_config_set__purge(set);
 	free(set);
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d1f19e0012d4..2515cfdb7365 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1081,7 +1081,7 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed)
 {
 	if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
-		const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+		const int width = fmt->width(fmt, hpp, he->hists);
 		if (printed < width) {
 			advance_hpp(hpp, printed);
 			printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7b54ccf1b737..a19112872ff9 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -159,7 +159,8 @@ void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-		      int max_cols, float min_pcnt, FILE *fp);
+		      int max_cols, float min_pcnt, FILE *fp,
+		      bool use_callchain);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
@@ -214,9 +215,9 @@ struct perf_hpp {
 struct perf_hpp_fmt {
 	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		      struct perf_evsel *evsel);
+		      struct hists *hists);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		     struct perf_evsel *evsel);
+		     struct hists *hists);
 	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hist_entry *he);
 	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 75465f89a413..bbc368e7d1e4 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -10,18 +10,33 @@
 #include "debug.h"
 #include "symbol.h"
 
+unsigned int perf_mem_events__loads_ldlat = 30;
+
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
 	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
 };
 #undef E
 
 #undef E
 
+static char mem_loads_name[100];
+static bool mem_loads_name__init;
+
 char *perf_mem_events__name(int i)
 {
+	if (i == PERF_MEM_EVENTS__LOAD) {
+		if (!mem_loads_name__init) {
+			mem_loads_name__init = true;
+			scnprintf(mem_loads_name, sizeof(mem_loads_name),
+				  perf_mem_events[i].name,
+				  perf_mem_events__loads_ldlat);
+		}
+		return mem_loads_name;
+	}
+
 	return (char *)perf_mem_events[i].name;
 }
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 5d6d93066a6e..7f69bf9d789d 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -18,6 +18,7 @@ enum {
 };
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 74401a20106d..084756c17309 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -67,7 +67,6 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
 	return ret;
 }
 
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
@@ -1603,6 +1602,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 	p = strchr(argv[1], ':');
 	if (p) {
 		tp->module = strndup(argv[1], p - argv[1]);
+		if (!tp->module) {
+			ret = -ENOMEM;
+			goto out;
+		}
 		p++;
 	} else
 		p = argv[1];
@@ -1712,7 +1715,7 @@ char *synthesize_perf_probe_arg(struct perf_probe_arg *pa)
 }
 
 /* Compose only probe point (not argument) */
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
 	struct strbuf buf;
 	char *tmp, *ret = NULL;
@@ -1751,30 +1754,36 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 	return ret;
 }
 
-#if 0
 char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 {
-	char *buf;
-	int i, len, ret;
+	struct strbuf buf;
+	char *tmp, *ret = NULL;
+	int i;
 
-	buf = synthesize_perf_probe_point(&pev->point);
-	if (!buf)
+	if (strbuf_init(&buf, 64))
 		return NULL;
+	if (pev->event)
+		if (strbuf_addf(&buf, "%s:%s=", pev->group ?: PERFPROBE_GROUP,
+				pev->event) < 0)
+			goto out;
+
+	tmp = synthesize_perf_probe_point(&pev->point);
+	if (!tmp || strbuf_addstr(&buf, tmp) < 0)
+		goto out;
+	free(tmp);
 
-	len = strlen(buf);
 	for (i = 0; i < pev->nargs; i++) {
-		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pev->args[i].name);
-		if (ret <= 0) {
-			free(buf);
-			return NULL;
-		}
-		len += ret;
+		tmp = synthesize_perf_probe_arg(pev->args + i);
+		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0)
+			goto out;
+		free(tmp);
 	}
 
-	return buf;
+	ret = strbuf_detach(&buf, NULL);
+out:
+	strbuf_release(&buf);
+	return ret;
 }
-#endif
 
 static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
 					    struct strbuf *buf, int depth)
@@ -2026,6 +2035,79 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 	memset(pev, 0, sizeof(*pev));
 }
 
+#define strdup_or_goto(str, label)	\
+({ char *__p = NULL; if (str && !(__p = strdup(str))) goto label; __p; })
+
+static int perf_probe_point__copy(struct perf_probe_point *dst,
+				  struct perf_probe_point *src)
+{
+	dst->file = strdup_or_goto(src->file, out_err);
+	dst->function = strdup_or_goto(src->function, out_err);
+	dst->lazy_line = strdup_or_goto(src->lazy_line, out_err);
+	dst->line = src->line;
+	dst->retprobe = src->retprobe;
+	dst->offset = src->offset;
+	return 0;
+
+out_err:
+	clear_perf_probe_point(dst);
+	return -ENOMEM;
+}
+
+static int perf_probe_arg__copy(struct perf_probe_arg *dst,
+				struct perf_probe_arg *src)
+{
+	struct perf_probe_arg_field *field, **ppfield;
+
+	dst->name = strdup_or_goto(src->name, out_err);
+	dst->var = strdup_or_goto(src->var, out_err);
+	dst->type = strdup_or_goto(src->type, out_err);
+
+	field = src->field;
+	ppfield = &(dst->field);
+	while (field) {
+		*ppfield = zalloc(sizeof(*field));
+		if (!*ppfield)
+			goto out_err;
+		(*ppfield)->name = strdup_or_goto(field->name, out_err);
+		(*ppfield)->index = field->index;
+		(*ppfield)->ref = field->ref;
+		field = field->next;
+		ppfield = &((*ppfield)->next);
+	}
+	return 0;
+out_err:
+	return -ENOMEM;
+}
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+			   struct perf_probe_event *src)
+{
+	int i;
+
+	dst->event = strdup_or_goto(src->event, out_err);
+	dst->group = strdup_or_goto(src->group, out_err);
+	dst->target = strdup_or_goto(src->target, out_err);
+	dst->uprobes = src->uprobes;
+
+	if (perf_probe_point__copy(&dst->point, &src->point) < 0)
+		goto out_err;
+
+	dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs);
+	if (!dst->args)
+		goto out_err;
+	dst->nargs = src->nargs;
+
+	for (i = 0; i < src->nargs; i++)
+		if (perf_probe_arg__copy(&dst->args[i], &src->args[i]) < 0)
+			goto out_err;
+	return 0;
+
+out_err:
+	clear_perf_probe_event(dst);
+	return -ENOMEM;
+}
+
 void clear_probe_trace_event(struct probe_trace_event *tev)
 {
 	struct probe_trace_arg_ref *ref, *next;
@@ -2432,6 +2514,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 {
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
+	struct probe_cache *cache = NULL;
 	struct strlist *namelist;
 
 	fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
@@ -2473,6 +2556,14 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 	if (ret == -EINVAL && pev->uprobes)
 		warn_uprobe_event_compat(tev);
+	if (ret == 0 && probe_conf.cache) {
+		cache = probe_cache__new(pev->target);
+		if (!cache ||
+		    probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 ||
+		    probe_cache__commit(cache) < 0)
+			pr_warning("Failed to add event to probe cache\n");
+		probe_cache__delete(cache);
+	}
 
 	strlist__delete(namelist);
 close_out:
@@ -2501,9 +2592,6 @@ static int find_probe_functions(struct map *map, char *name,
 	return found;
 }
 
-#define strdup_or_goto(str, label)	\
-	({ char *__p = strdup(str); if (!__p) goto label; __p; })
-
 void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
 				struct probe_trace_event *tev __maybe_unused,
 				struct map *map __maybe_unused,
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5a27eb4fad05..432b690d3f17 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_conf {
 	bool	show_location_range;
 	bool	force_add;
 	bool	no_inlines;
+	bool	cache;
 	int	max_probes;
 };
 extern struct probe_conf probe_conf;
@@ -121,6 +122,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
+char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+			   struct perf_probe_event *src);
 
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3fe6214970e6..25a40427003e 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  *
  */
+#include <sys/uio.h>
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
@@ -324,3 +325,333 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 
 	return ret;
 }
+
+/* Caller must ensure to remove this entry from list */
+static void probe_cache_entry__delete(struct probe_cache_entry *entry)
+{
+	if (entry) {
+		BUG_ON(!list_empty(&entry->node));
+
+		strlist__delete(entry->tevlist);
+		clear_perf_probe_event(&entry->pev);
+		zfree(&entry->spev);
+		free(entry);
+	}
+}
+
+static struct probe_cache_entry *
+probe_cache_entry__new(struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = zalloc(sizeof(*entry));
+
+	if (entry) {
+		INIT_LIST_HEAD(&entry->node);
+		entry->tevlist = strlist__new(NULL, NULL);
+		if (!entry->tevlist)
+			zfree(&entry);
+		else if (pev) {
+			entry->spev = synthesize_perf_probe_command(pev);
+			if (!entry->spev ||
+			    perf_probe_event__copy(&entry->pev, pev) < 0) {
+				probe_cache_entry__delete(entry);
+				return NULL;
+			}
+		}
+	}
+
+	return entry;
+}
+
+/* For the kernel probe caches, pass target = NULL */
+static int probe_cache__open(struct probe_cache *pcache, const char *target)
+{
+	char cpath[PATH_MAX];
+	char sbuildid[SBUILD_ID_SIZE];
+	char *dir_name;
+	bool is_kallsyms = !target;
+	int ret, fd;
+
+	if (target)
+		ret = filename__sprintf_build_id(target, sbuildid);
+	else {
+		target = DSO__NAME_KALLSYMS;
+		ret = sysfs__sprintf_build_id("/", sbuildid);
+	}
+	if (ret < 0) {
+		pr_debug("Failed to get build-id from %s.\n", target);
+		return ret;
+	}
+
+	/* If we have no buildid cache, make it */
+	if (!build_id_cache__cached(sbuildid)) {
+		ret = build_id_cache__add_s(sbuildid, target,
+					    is_kallsyms, NULL);
+		if (ret < 0) {
+			pr_debug("Failed to add build-id cache: %s\n", target);
+			return ret;
+		}
+	}
+
+	dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+					    false);
+	if (!dir_name)
+		return -ENOMEM;
+
+	snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
+	fd = open(cpath, O_CREAT | O_RDWR, 0644);
+	if (fd < 0)
+		pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
+	free(dir_name);
+	pcache->fd = fd;
+
+	return fd;
+}
+
+static int probe_cache__load(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry = NULL;
+	char buf[MAX_CMDLEN], *p;
+	int ret = 0;
+	FILE *fp;
+
+	fp = fdopen(dup(pcache->fd), "r");
+	if (!fp)
+		return -EINVAL;
+
+	while (!feof(fp)) {
+		if (!fgets(buf, MAX_CMDLEN, fp))
+			break;
+		p = strchr(buf, '\n');
+		if (p)
+			*p = '\0';
+		if (buf[0] == '#') {	/* #perf_probe_event */
+			entry = probe_cache_entry__new(NULL);
+			if (!entry) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			entry->spev = strdup(buf + 1);
+			if (entry->spev)
+				ret = parse_perf_probe_command(buf + 1,
+								&entry->pev);
+			else
+				ret = -ENOMEM;
+			if (ret < 0) {
+				probe_cache_entry__delete(entry);
+				goto out;
+			}
+			list_add_tail(&entry->node, &pcache->entries);
+		} else {	/* trace_probe_event */
+			if (!entry) {
+				ret = -EINVAL;
+				goto out;
+			}
+			strlist__add(entry->tevlist, buf);
+		}
+	}
+out:
+	fclose(fp);
+	return ret;
+}
+
+static struct probe_cache *probe_cache__alloc(void)
+{
+	struct probe_cache *pcache = zalloc(sizeof(*pcache));
+
+	if (pcache) {
+		INIT_LIST_HEAD(&pcache->entries);
+		pcache->fd = -EINVAL;
+	}
+	return pcache;
+}
+
+void probe_cache__purge(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry, *n;
+
+	list_for_each_entry_safe(entry, n, &pcache->entries, node) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+}
+
+void probe_cache__delete(struct probe_cache *pcache)
+{
+	if (!pcache)
+		return;
+
+	probe_cache__purge(pcache);
+	if (pcache->fd > 0)
+		close(pcache->fd);
+	free(pcache);
+}
+
+struct probe_cache *probe_cache__new(const char *target)
+{
+	struct probe_cache *pcache = probe_cache__alloc();
+	int ret;
+
+	if (!pcache)
+		return NULL;
+
+	ret = probe_cache__open(pcache, target);
+	if (ret < 0) {
+		pr_debug("Cache open error: %d\n", ret);
+		goto out_err;
+	}
+
+	ret = probe_cache__load(pcache);
+	if (ret < 0) {
+		pr_debug("Cache read error: %d\n", ret);
+		goto out_err;
+	}
+
+	return pcache;
+
+out_err:
+	probe_cache__delete(pcache);
+	return NULL;
+}
+
+static bool streql(const char *a, const char *b)
+{
+	if (a == b)
+		return true;
+
+	if (!a || !b)
+		return false;
+
+	return !strcmp(a, b);
+}
+
+static struct probe_cache_entry *
+probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *cmd = synthesize_perf_probe_command(pev);
+
+	if (!cmd)
+		return NULL;
+
+	list_for_each_entry(entry, &pcache->entries, node) {
+		/* Hit if same event name or same command-string */
+		if ((pev->event &&
+		     (streql(entry->pev.group, pev->group) &&
+		      streql(entry->pev.event, pev->event))) ||
+		    (!strcmp(entry->spev, cmd)))
+			goto found;
+	}
+	entry = NULL;
+
+found:
+	free(cmd);
+	return entry;
+}
+
+int probe_cache__add_entry(struct probe_cache *pcache,
+			   struct perf_probe_event *pev,
+			   struct probe_trace_event *tevs, int ntevs)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *command;
+	int i, ret = 0;
+
+	if (!pcache || !pev || !tevs || ntevs <= 0) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Remove old cache entry */
+	entry = probe_cache__find(pcache, pev);
+	if (entry) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+
+	ret = -ENOMEM;
+	entry = probe_cache_entry__new(pev);
+	if (!entry)
+		goto out_err;
+
+	for (i = 0; i < ntevs; i++) {
+		if (!tevs[i].point.symbol)
+			continue;
+
+		command = synthesize_probe_trace_command(&tevs[i]);
+		if (!command)
+			goto out_err;
+		strlist__add(entry->tevlist, command);
+		free(command);
+	}
+	list_add_tail(&entry->node, &pcache->entries);
+	pr_debug("Added probe cache: %d\n", ntevs);
+	return 0;
+
+out_err:
+	pr_debug("Failed to add probe caches\n");
+	probe_cache_entry__delete(entry);
+	return ret;
+}
+
+static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
+{
+	struct str_node *snode;
+	struct stat st;
+	struct iovec iov[3];
+	int ret;
+	/* Save stat for rollback */
+	ret = fstat(fd, &st);
+	if (ret < 0)
+		return ret;
+
+	pr_debug("Writing cache: #%s\n", entry->spev);
+	iov[0].iov_base = (void *)"#"; iov[0].iov_len = 1;
+	iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
+	iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
+	ret = writev(fd, iov, 3);
+	if (ret < (int)iov[1].iov_len + 2)
+		goto rollback;
+
+	strlist__for_each(snode, entry->tevlist) {
+		iov[0].iov_base = (void *)snode->s;
+		iov[0].iov_len = strlen(snode->s);
+		iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;
+		ret = writev(fd, iov, 2);
+		if (ret < (int)iov[0].iov_len + 1)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	/* Rollback to avoid cache file corruption */
+	if (ret > 0)
+		ret = -1;
+	if (ftruncate(fd, st.st_size) < 0)
+		ret = -2;
+
+	return ret;
+}
+
+int probe_cache__commit(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry;
+	int ret = 0;
+
+	/* TBD: if we do not update existing entries, skip it */
+	ret = lseek(pcache->fd, 0, SEEK_SET);
+	if (ret < 0)
+		goto out;
+
+	ret = ftruncate(pcache->fd, 0);
+	if (ret < 0)
+		goto out;
+
+	list_for_each_entry(entry, &pcache->entries, node) {
+		ret = probe_cache_entry__write(entry, pcache->fd);
+		pr_debug("Cache committed: %d\n", ret);
+		if (ret < 0)
+			break;
+	}
+out:
+	return ret;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 18ac9cf51c34..d872e3df7e59 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -5,6 +5,19 @@
 #include "strfilter.h"
 #include "probe-event.h"
 
+/* Cache of probe definitions */
+struct probe_cache_entry {
+	struct list_head	node;
+	struct perf_probe_event pev;
+	char			*spev;
+	struct strlist		*tevlist;
+};
+
+struct probe_cache {
+	int	fd;
+	struct list_head entries;
+};
+
 #define PF_FL_UPROBE	1
 #define PF_FL_RW	2
 
@@ -18,5 +31,12 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 				  struct strlist *plist);
 int probe_file__del_strlist(int fd, struct strlist *namelist);
 
+struct probe_cache *probe_cache__new(const char *target);
+int probe_cache__add_entry(struct probe_cache *pcache,
+			   struct perf_probe_event *pev,
+			   struct probe_trace_event *tevs, int ntevs);
+int probe_cache__commit(struct probe_cache *pcache);
+void probe_cache__purge(struct probe_cache *pcache);
+void probe_cache__delete(struct probe_cache *pcache);
 
 #endif
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c4e9bd70723c..896d34ebcc1e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1218,7 +1218,7 @@ struct sort_entry sort_mem_daddr_dso = {
 	.se_header	= "Data Object",
 	.se_cmp		= sort__dso_daddr_cmp,
 	.se_snprintf	= hist_entry__dso_daddr_snprintf,
-	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+	.se_width_idx	= HISTC_MEM_DADDR_DSO,
 };
 
 struct sort_entry sort_mem_locked = {
@@ -1488,7 +1488,7 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct perf_evsel *evsel)
+			      struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1496,14 +1496,14 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+		len = hists__col_len(hists, hse->se->se_width_idx);
 
 	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 			     struct perf_hpp *hpp __maybe_unused,
-			     struct perf_evsel *evsel)
+			     struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1511,7 +1511,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+		len = hists__col_len(hists, hse->se->se_width_idx);
 
 	return len;
 }
@@ -1793,7 +1793,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 }
 
 static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct perf_evsel *evsel __maybe_unused)
+			      struct hists *hists __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
@@ -1808,7 +1808,7 @@ static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int __sort__hde_width(struct perf_hpp_fmt *fmt,
 			     struct perf_hpp *hpp __maybe_unused,
-			     struct perf_evsel *evsel __maybe_unused)
+			     struct hists *hists __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 23504ad5d6dd..e08b9a092a23 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -97,20 +97,17 @@ int rm_rf(char *path)
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
 
-		ret = stat(namebuf, &statbuf);
+		/* We have to check symbolic link itself */
+		ret = lstat(namebuf, &statbuf);
 		if (ret < 0) {
 			pr_debug("stat failed: %s\n", namebuf);
 			break;
 		}
 
-		if (S_ISREG(statbuf.st_mode))
-			ret = unlink(namebuf);
-		else if (S_ISDIR(statbuf.st_mode))
+		if (S_ISDIR(statbuf.st_mode))
 			ret = rm_rf(namebuf);
-		else {
-			pr_debug("unknown file: %s\n", namebuf);
-			ret = -1;
-		}
+		else
+			ret = unlink(namebuf);
 	}
 	closedir(dir);