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

Conflicts:
	tools/Makefile

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

. Honor parallel jobs, fix from Borislav Petkov

. Introduce tools/lib/lk library, initially just removing duplication
  among tools/perf and tools/vm. from Borislav Petkov

. Fix build on non-glibc systems due to libio.h absence, from Cody P Schafer.

. Remove some perf_session and tracing dead code, from David Ahern.

. Introduce perf stat --repeat forever, from Frederik Deweerdt.

. Add perf test entries for checking --cpu in record and stat, from Jiri Olsa.

. Add perf test entries for checking breakpoint overflow signal handler issues,
  from Jiri Olsa.

. Add perf test entry for for checking number of EXIT events, from Namhyung Kim.

. Simplify some perf_evlist methods and to allow 'stat' to share code with
  'record' and 'trace'.

. Remove dead code in related to libtraceevent integration, from Namhyung Kim.

. Event group view for 'annotate' in --stdio, --tui and --gtk, from Namhyung Kim.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
[ resolved the trivial merge conflict with upstream ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

25 files changed, 371 insertions, 553 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index d33fe937e6f1..d102716c43a1 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -14,6 +14,7 @@
 #include "symbol.h"
 #include "debug.h"
 #include "annotate.h"
+#include "evsel.h"
 #include <pthread.h>
 #include <linux/bitops.h>
 
@@ -602,8 +603,42 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 	return NULL;
 }
 
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path)
+{
+	struct source_line *src_line = notes->src->lines;
+	double percent = 0.0;
+
+	if (src_line) {
+		size_t sizeof_src_line = sizeof(*src_line) +
+				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+
+		while (offset < end) {
+			src_line = (void *)notes->src->lines +
+					(sizeof_src_line * offset);
+
+			if (*path == NULL)
+				*path = src_line->path;
+
+			percent += src_line->p[evidx].percent;
+			offset++;
+		}
+	} else {
+		struct sym_hist *h = annotation__histogram(notes, evidx);
+		unsigned int hits = 0;
+
+		while (offset < end)
+			hits += h->addr[offset++];
+
+		if (h->sum)
+			percent = 100.0 * hits / h->sum;
+	}
+
+	return percent;
+}
+
 static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
-		      int evidx, u64 len, int min_pcnt, int printed,
+		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
 		      int max_lines, struct disasm_line *queue)
 {
 	static const char *prev_line;
@@ -611,34 +646,37 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 	if (dl->offset != -1) {
 		const char *path = NULL;
-		unsigned int hits = 0;
-		double percent = 0.0;
+		double percent, max_percent = 0.0;
+		double *ppercents = &percent;
+		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
-		struct source_line *src_line = notes->src->lines;
-		struct sym_hist *h = annotation__histogram(notes, evidx);
 		s64 offset = dl->offset;
 		const u64 addr = start + offset;
 		struct disasm_line *next;
 
 		next = disasm__get_next_ip_line(&notes->src->source, dl);
 
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (src_line) {
-				if (path == NULL)
-					path = src_line[offset].path;
-				percent += src_line[offset].percent;
-			} else
-				hits += h->addr[offset];
-
-			++offset;
+		if (perf_evsel__is_group_event(evsel)) {
+			nr_percent = evsel->nr_members;
+			ppercents = calloc(nr_percent, sizeof(double));
+			if (ppercents == NULL)
+				return -1;
 		}
 
-		if (src_line == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
+		for (i = 0; i < nr_percent; i++) {
+			percent = disasm__calc_percent(notes,
+					notes->src->lines ? i : evsel->idx + i,
+					offset,
+					next ? next->offset : (s64) len,
+					&path);
+
+			ppercents[i] = percent;
+			if (percent > max_percent)
+				max_percent = percent;
+		}
 
-		if (percent < min_pcnt)
+		if (max_percent < min_pcnt)
 			return -1;
 
 		if (max_lines && printed >= max_lines)
@@ -648,12 +686,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 			list_for_each_entry_from(queue, &notes->src->source, node) {
 				if (queue == dl)
 					break;
-				disasm_line__print(queue, sym, start, evidx, len,
+				disasm_line__print(queue, sym, start, evsel, len,
 						    0, 0, 1, NULL);
 			}
 		}
 
-		color = get_percent_color(percent);
+		color = get_percent_color(max_percent);
 
 		/*
 		 * Also color the filename and line if needed, with
@@ -669,25 +707,59 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 			}
 		}
 
-		color_fprintf(stdout, color, " %7.2f", percent);
+		for (i = 0; i < nr_percent; i++) {
+			percent = ppercents[i];
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+		}
+
 		printf(" :	");
 		color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
 		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+		if (ppercents != &percent)
+			free(ppercents);
+
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
+		int width = 8;
+
 		if (queue)
 			return -1;
 
+		if (perf_evsel__is_group_event(evsel))
+			width *= evsel->nr_members;
+
 		if (!*dl->line)
-			printf("         :\n");
+			printf(" %*s:\n", width, " ");
 		else
-			printf("         :	%s\n", dl->line);
+			printf(" %*s:	%s\n", width, " ", dl->line);
 	}
 
 	return 0;
 }
 
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ *  0000000000415500 <_init>:
+ *    415500:       sub    $0x8,%rsp
+ *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
+ *    41550b:       test   %rax,%rax
+ *    41550e:       je     415515 <_init+0x15>
+ *    415510:       callq  416e70 <__gmon_start__@plt>
+ *    415515:       add    $0x8,%rsp
+ *    415519:       retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ *  <offset>       <name>  <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
 static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 				      FILE *file, size_t privsize)
 {
@@ -858,7 +930,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 	struct source_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
-	int ret;
+	int i, ret;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -866,7 +938,8 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 
 		ret = strcmp(iter->path, src_line->path);
 		if (ret == 0) {
-			iter->percent_sum += src_line->percent;
+			for (i = 0; i < src_line->nr_pcnt; i++)
+				iter->p[i].percent_sum += src_line->p[i].percent;
 			return;
 		}
 
@@ -876,12 +949,26 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 			p = &(*p)->rb_right;
 	}
 
-	src_line->percent_sum = src_line->percent;
+	for (i = 0; i < src_line->nr_pcnt; i++)
+		src_line->p[i].percent_sum = src_line->p[i].percent;
 
 	rb_link_node(&src_line->node, parent, p);
 	rb_insert_color(&src_line->node, root);
 }
 
+static int cmp_source_line(struct source_line *a, struct source_line *b)
+{
+	int i;
+
+	for (i = 0; i < a->nr_pcnt; i++) {
+		if (a->p[i].percent_sum == b->p[i].percent_sum)
+			continue;
+		return a->p[i].percent_sum > b->p[i].percent_sum;
+	}
+
+	return 0;
+}
+
 static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
 {
 	struct source_line *iter;
@@ -892,7 +979,7 @@ static void __resort_source_line(struct rb_root *root, struct source_line *src_l
 		parent = *p;
 		iter = rb_entry(parent, struct source_line, node);
 
-		if (src_line->percent_sum > iter->percent_sum)
+		if (cmp_source_line(src_line, iter))
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -924,32 +1011,52 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct source_line *src_line = notes->src->lines;
+	size_t sizeof_src_line;
 	int i;
 
-	for (i = 0; i < len; i++)
-		free(src_line[i].path);
+	sizeof_src_line = sizeof(*src_line) +
+			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+
+	for (i = 0; i < len; i++) {
+		free(src_line->path);
+		src_line = (void *)src_line + sizeof_src_line;
+	}
 
-	free(src_line);
+	free(notes->src->lines);
 	notes->src->lines = NULL;
 }
 
 /* Get the filename:line for the colored entries */
 static int symbol__get_source_line(struct symbol *sym, struct map *map,
-				   int evidx, struct rb_root *root, int len,
+				   struct perf_evsel *evsel,
+				   struct rb_root *root, int len,
 				   const char *filename)
 {
 	u64 start;
-	int i;
+	int i, k;
+	int evidx = evsel->idx;
 	char cmd[PATH_MAX * 2];
 	struct source_line *src_line;
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
 	struct rb_root tmp_root = RB_ROOT;
+	int nr_pcnt = 1;
+	u64 h_sum = h->sum;
+	size_t sizeof_src_line = sizeof(struct source_line);
+
+	if (perf_evsel__is_group_event(evsel)) {
+		for (i = 1; i < evsel->nr_members; i++) {
+			h = annotation__histogram(notes, evidx + i);
+			h_sum += h->sum;
+		}
+		nr_pcnt = evsel->nr_members;
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+	}
 
-	if (!h->sum)
+	if (!h_sum)
 		return 0;
 
-	src_line = notes->src->lines = calloc(len, sizeof(struct source_line));
+	src_line = notes->src->lines = calloc(len, sizeof_src_line);
 	if (!notes->src->lines)
 		return -1;
 
@@ -960,29 +1067,41 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 		size_t line_len;
 		u64 offset;
 		FILE *fp;
+		double percent_max = 0.0;
 
-		src_line[i].percent = 100.0 * h->addr[i] / h->sum;
-		if (src_line[i].percent <= 0.5)
-			continue;
+		src_line->nr_pcnt = nr_pcnt;
+
+		for (k = 0; k < nr_pcnt; k++) {
+			h = annotation__histogram(notes, evidx + k);
+			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+
+			if (src_line->p[k].percent > percent_max)
+				percent_max = src_line->p[k].percent;
+		}
+
+		if (percent_max <= 0.5)
+			goto next;
 
 		offset = start + i;
 		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
 		fp = popen(cmd, "r");
 		if (!fp)
-			continue;
+			goto next;
 
 		if (getline(&path, &line_len, fp) < 0 || !line_len)
-			goto next;
+			goto next_close;
 
-		src_line[i].path = malloc(sizeof(char) * line_len + 1);
-		if (!src_line[i].path)
-			goto next;
+		src_line->path = malloc(sizeof(char) * line_len + 1);
+		if (!src_line->path)
+			goto next_close;
 
-		strcpy(src_line[i].path, path);
-		insert_source_line(&tmp_root, &src_line[i]);
+		strcpy(src_line->path, path);
+		insert_source_line(&tmp_root, src_line);
 
-	next:
+	next_close:
 		pclose(fp);
+	next:
+		src_line = (void *)src_line + sizeof_src_line;
 	}
 
 	resort_source_line(root, &tmp_root);
@@ -1004,24 +1123,33 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 	node = rb_first(root);
 	while (node) {
-		double percent;
+		double percent, percent_max = 0.0;
 		const char *color;
 		char *path;
+		int i;
 
 		src_line = rb_entry(node, struct source_line, node);
-		percent = src_line->percent_sum;
-		color = get_percent_color(percent);
+		for (i = 0; i < src_line->nr_pcnt; i++) {
+			percent = src_line->p[i].percent_sum;
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (percent > percent_max)
+				percent_max = percent;
+		}
+
 		path = src_line->path;
+		color = get_percent_color(percent_max);
+		color_fprintf(stdout, color, " %s", path);
 
-		color_fprintf(stdout, color, " %7.2f %s", percent, path);
 		node = rb_next(node);
 	}
 }
 
-static void symbol__annotate_hits(struct symbol *sym, int evidx)
+static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct sym_hist *h = annotation__histogram(notes, evidx);
+	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
 	u64 len = symbol__size(sym), offset;
 
 	for (offset = 0; offset < len; ++offset)
@@ -1031,9 +1159,9 @@ static void symbol__annotate_hits(struct symbol *sym, int evidx)
 	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
-int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
-			    bool full_paths, int min_pcnt, int max_lines,
-			    int context)
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context)
 {
 	struct dso *dso = map->dso;
 	char *filename;
@@ -1044,6 +1172,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 	int printed = 2, queue_len = 0;
 	int more = 0;
 	u64 len;
+	int width = 8;
+	int namelen;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1055,12 +1185,18 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 		d_filename = basename(filename);
 
 	len = symbol__size(sym);
+	namelen = strlen(d_filename);
+
+	if (perf_evsel__is_group_event(evsel))
+		width *= evsel->nr_members;
 
-	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
-	printf("------------------------------------------------\n");
+	printf(" %-*.*s|	Source code & Disassembly of %s\n",
+	       width, width, "Percent", d_filename);
+	printf("-%-*.*s-------------------------------------\n",
+	       width+namelen, width+namelen, graph_dotted_line);
 
 	if (verbose)
-		symbol__annotate_hits(sym, evidx);
+		symbol__annotate_hits(sym, evsel);
 
 	list_for_each_entry(pos, &notes->src->source, node) {
 		if (context && queue == NULL) {
@@ -1068,7 +1204,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 			queue_len = 0;
 		}
 
-		switch (disasm_line__print(pos, sym, start, evidx, len,
+		switch (disasm_line__print(pos, sym, start, evsel, len,
 					    min_pcnt, printed, max_lines,
 					    queue)) {
 		case 0:
@@ -1163,9 +1299,9 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp)
 	return printed;
 }
 
-int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
-			 bool print_lines, bool full_paths, int min_pcnt,
-			 int max_lines)
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines)
 {
 	struct dso *dso = map->dso;
 	const char *filename = dso->long_name;
@@ -1178,12 +1314,12 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
 	len = symbol__size(sym);
 
 	if (print_lines) {
-		symbol__get_source_line(sym, map, evidx, &source_line,
+		symbol__get_source_line(sym, map, evsel, &source_line,
 					len, filename);
 		print_summary(&source_line, filename);
 	}
 
-	symbol__annotate_printf(sym, map, evidx, full_paths,
+	symbol__annotate_printf(sym, map, evsel, full_paths,
 				min_pcnt, max_lines, 0);
 	if (print_lines)
 		symbol__free_source_line(sym, len);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index c422440fe611..6f3c16f01ab4 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -50,6 +50,8 @@ bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 
+struct annotation;
+
 struct disasm_line {
 	struct list_head    node;
 	s64		    offset;
@@ -68,17 +70,24 @@ void disasm_line__free(struct disasm_line *dl);
 struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path);
 
 struct sym_hist {
 	u64		sum;
 	u64		addr[0];
 };
 
-struct source_line {
-	struct rb_node	node;
+struct source_line_percent {
 	double		percent;
 	double		percent_sum;
+};
+
+struct source_line {
+	struct rb_node	node;
 	char		*path;
+	int		nr_pcnt;
+	struct source_line_percent p[1];
 };
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
@@ -130,47 +139,49 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
-int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
-			    bool full_paths, int min_pcnt, int max_lines,
-			    int context);
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void disasm__purge(struct list_head *head);
 
-int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
-			 bool print_lines, bool full_paths, int min_pcnt,
-			 int max_lines);
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines);
 
 #ifdef NEWT_SUPPORT
-int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__tui_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
-				       struct map *map __maybe_unused,
-				       int evidx __maybe_unused,
-				       struct hist_browser_timer *hbt
-				       __maybe_unused)
+				struct map *map __maybe_unused,
+				struct perf_evsel *evsel  __maybe_unused,
+				struct hist_browser_timer *hbt
+				__maybe_unused)
 {
 	return 0;
 }
 #endif
 
 #ifdef GTK2_SUPPORT
-int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__gtk_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
 
-static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx,
+static inline int hist_entry__gtk_annotate(struct hist_entry *he,
+					   struct perf_evsel *evsel,
 					   struct hist_browser_timer *hbt)
 {
-	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, hbt);
+	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
 }
 
 void perf_gtk__show_annotations(void);
 #else
 static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused,
-					   int evidx __maybe_unused,
-					   struct hist_browser_timer *hbt
-					   __maybe_unused)
+				struct perf_evsel *evsel __maybe_unused,
+				struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c
deleted file mode 100644
index dd8b19319c03..000000000000
--- a/tools/perf/util/debugfs.c
+++ /dev/null
@@ -1,114 +0,0 @@
-#include "util.h"
-#include "debugfs.h"
-#include "cache.h"
-
-#include <linux/kernel.h>
-#include <sys/mount.h>
-
-static int debugfs_premounted;
-char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
-char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
-
-static const char *debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug/",
-	"/debug/",
-	0,
-};
-
-static int debugfs_found;
-
-/* find the path to the mounted debugfs */
-const char *debugfs_find_mountpoint(void)
-{
-	const char **ptr;
-	char type[100];
-	FILE *fp;
-
-	if (debugfs_found)
-		return (const char *) debugfs_mountpoint;
-
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			debugfs_found = 1;
-			strcpy(debugfs_mountpoint, *ptr);
-			return debugfs_mountpoint;
-		}
-		ptr++;
-	}
-
-	/* give up and parse /proc/mounts */
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		return NULL;
-
-	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
-		      debugfs_mountpoint, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
-			break;
-	}
-	fclose(fp);
-
-	if (strcmp(type, "debugfs") != 0)
-		return NULL;
-
-	debugfs_found = 1;
-
-	return debugfs_mountpoint;
-}
-
-/* verify that a mountpoint is actually a debugfs instance */
-
-int debugfs_valid_mountpoint(const char *debugfs)
-{
-	struct statfs st_fs;
-
-	if (statfs(debugfs, &st_fs) < 0)
-		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
-		return -ENOENT;
-
-	return 0;
-}
-
-static void debugfs_set_tracing_events_path(const char *mountpoint)
-{
-	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
-		 mountpoint, "tracing/events");
-}
-
-/* mount the debugfs somewhere if it's not mounted */
-
-char *debugfs_mount(const char *mountpoint)
-{
-	/* see if it's already mounted */
-	if (debugfs_find_mountpoint()) {
-		debugfs_premounted = 1;
-		goto out;
-	}
-
-	/* if not mounted and no argument */
-	if (mountpoint == NULL) {
-		/* see if environment variable set */
-		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
-		/* if no environment variable, use default */
-		if (mountpoint == NULL)
-			mountpoint = "/sys/kernel/debug";
-	}
-
-	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
-		return NULL;
-
-	/* save the mountpoint */
-	debugfs_found = 1;
-	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
-out:
-	debugfs_set_tracing_events_path(debugfs_mountpoint);
-	return debugfs_mountpoint;
-}
-
-void debugfs_set_path(const char *mountpoint)
-{
-	snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint);
-	debugfs_set_tracing_events_path(mountpoint);
-}
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
deleted file mode 100644
index 68f3e87ec57f..000000000000
--- a/tools/perf/util/debugfs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __DEBUGFS_H__
-#define __DEBUGFS_H__
-
-const char *debugfs_find_mountpoint(void);
-int debugfs_valid_mountpoint(const char *debugfs);
-char *debugfs_mount(const char *mountpoint);
-void debugfs_set_path(const char *mountpoint);
-
-extern char debugfs_mountpoint[];
-extern char tracing_events_path[];
-
-#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c8be0fbc5145..f7c727801aab 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -7,7 +7,7 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 #include "util.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -38,13 +38,12 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	evlist->workload.pid = -1;
 }
 
-struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
-				     struct thread_map *threads)
+struct perf_evlist *perf_evlist__new(void)
 {
 	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
 
 	if (evlist != NULL)
-		perf_evlist__init(evlist, cpus, threads);
+		perf_evlist__init(evlist, NULL, NULL);
 
 	return evlist;
 }
@@ -228,12 +227,14 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
@@ -244,12 +245,14 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
@@ -258,7 +261,9 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -417,7 +422,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__all(evlist->cpus))
-		evlist->nr_mmaps = evlist->threads->nr;
+		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
@@ -442,11 +447,13 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 {
 	struct perf_evsel *evsel;
 	int cpu, thread;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			list_for_each_entry(evsel, &evlist->entries, node) {
 				int fd = FD(evsel, cpu, thread);
 
@@ -470,7 +477,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		if (evlist->mmap[cpu].base != NULL) {
 			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
 			evlist->mmap[cpu].base = NULL;
@@ -483,8 +490,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 {
 	struct perf_evsel *evsel;
 	int thread;
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
 		list_for_each_entry(evsel, &evlist->entries, node) {
@@ -509,7 +517,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		if (evlist->mmap[thread].base != NULL) {
 			munmap(evlist->mmap[thread].base, evlist->mmap_len);
 			evlist->mmap[thread].base = NULL;
@@ -610,7 +618,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if (evsel->filter == NULL)
@@ -629,7 +637,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
@@ -712,10 +720,20 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 	evlist->selected = evsel;
 }
 
+void perf_evlist__close(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int ncpus = cpu_map__nr(evlist->cpus);
+	int nthreads = thread_map__nr(evlist->threads);
+
+	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+		perf_evsel__close(evsel, ncpus, nthreads);
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
-	int err, ncpus, nthreads;
+	int err;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
@@ -725,19 +743,15 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	return 0;
 out_err:
-	ncpus = evlist->cpus ? evlist->cpus->nr : 1;
-	nthreads = evlist->threads ? evlist->threads->nr : 1;
-
-	list_for_each_entry_reverse(evsel, &evlist->entries, node)
-		perf_evsel__close(evsel, ncpus, nthreads);
-
+	perf_evlist__close(evlist);
 	errno = -err;
 	return err;
 }
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_record_opts *opts,
-				  const char *argv[])
+				  struct perf_target *target,
+				  const char *argv[], bool pipe_output,
+				  bool want_signal)
 {
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
@@ -759,7 +773,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 	}
 
 	if (!evlist->workload.pid) {
-		if (opts->pipe_output)
+		if (pipe_output)
 			dup2(2, 1);
 
 		close(child_ready_pipe[0]);
@@ -787,11 +801,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 		execvp(argv[0], (char **)argv);
 
 		perror(argv[0]);
-		kill(getppid(), SIGUSR1);
+		if (want_signal)
+			kill(getppid(), SIGUSR1);
 		exit(-1);
 	}
 
-	if (perf_target__none(&opts->target))
+	if (perf_target__none(target))
 		evlist->threads->map[0] = evlist->workload.pid;
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 2dd07bd60b4f..0583d36252be 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -49,8 +49,7 @@ struct perf_evsel_str_handler {
 	void	   *handler;
 };
 
-struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
-				     struct thread_map *threads);
+struct perf_evlist *perf_evlist__new(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -82,13 +81,15 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
+void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_record_opts *opts,
-				  const char *argv[]);
+				  struct perf_target *target,
+				  const char *argv[], bool pipe_output,
+				  bool want_signal);
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9c82f98f26de..1adb824610f0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -10,7 +10,7 @@
 #include <byteswap.h>
 #include <linux/bitops.h>
 #include "asm/bug.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "event-parse.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -633,6 +633,12 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return 0;
 }
 
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
+				 (ncpus * sizeof(struct perf_counts_values))));
+}
+
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
 {
 	evsel->counts = zalloc((sizeof(*evsel->counts) +
@@ -673,9 +679,8 @@ void perf_evsel__free_counts(struct perf_evsel *evsel)
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
-	xyarray__delete(evsel->fd);
-	xyarray__delete(evsel->sample_id);
-	free(evsel->id);
+	perf_evsel__free_fd(evsel);
+	perf_evsel__free_id(evsel);
 }
 
 void perf_evsel__delete(struct perf_evsel *evsel)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 52021c3087df..3f156ccc1acb 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -9,6 +9,7 @@
 #include "xyarray.h"
 #include "cgroup.h"
 #include "hist.h"
+#include "symbol.h"
  
 struct perf_counts_values {
 	union {
@@ -120,6 +121,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
@@ -246,11 +248,34 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
 
+/**
+ * perf_evsel__is_group_leader - Return whether given evsel is a leader event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if @evsel is a group leader or a stand-alone event
+ */
 static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
 {
 	return evsel->leader == evsel;
 }
 
+/**
+ * perf_evsel__is_group_event - Return whether given evsel is a group event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true iff event group view is enabled and @evsel is a actual group
+ * leader which has other members in the group
+ */
+static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
+{
+	if (!symbol_conf.event_group)
+		return false;
+
+	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f4bfd79ef6a7..a9b7349f7c5f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2789,7 +2789,7 @@ int perf_session__read_header(struct perf_session *session, int fd)
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
-	session->evlist = perf_evlist__new(NULL, NULL);
+	session->evlist = perf_evlist__new();
 	if (session->evlist == NULL)
 		return -ENOMEM;
 
@@ -2940,7 +2940,7 @@ int perf_event__process_attr(union perf_event *event,
 	struct perf_evlist *evlist = *pevlist;
 
 	if (evlist == NULL) {
-		*pevlist = evlist = perf_evlist__new(NULL, NULL);
+		*pevlist = evlist = perf_evlist__new();
 		if (evlist == NULL)
 			return -ENOMEM;
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 226a4ae2f936..848331377bdb 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -177,7 +177,7 @@ struct hist_browser_timer {
 
 #ifdef NEWT_SUPPORT
 #include "../ui/keysyms.h"
-int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
+int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt);
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
@@ -196,7 +196,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 
 static inline int hist_entry__tui_annotate(struct hist_entry *self
 					   __maybe_unused,
-					   int evidx __maybe_unused,
+					   struct perf_evsel *evsel
+					   __maybe_unused,
 					   struct hist_browser_timer *hbt
 					   __maybe_unused)
 {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index efdb38e65a92..c5e3b123782b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1003,6 +1003,17 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	return 0;
 }
 
+static void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
 int machine__process_exit_event(struct machine *machine, union perf_event *event)
 {
 	struct thread *thread = machine__find_thread(machine, event->fork.tid);
@@ -1039,17 +1050,6 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 	return ret;
 }
 
-void machine__remove_thread(struct machine *machine, struct thread *th)
-{
-	machine->last_match = NULL;
-	rb_erase(&th->rb_node, &machine->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &machine->dead_threads);
-}
-
 static bool symbol__match_parent_regex(struct symbol *sym)
 {
 	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5ac5892f2326..e0b2c00b2e75 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,7 +97,6 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
-void machine__remove_thread(struct machine *machine, struct thread *th);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c84f48cf9678..6c8bb0fb189b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,7 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 49a256e6e0a2..aa04bf9c9ad7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,7 +40,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 64536a993f4a..f75ae1b9900c 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -15,7 +15,6 @@ util/thread_map.c
 util/util.c
 util/xyarray.c
 util/cgroup.c
-util/debugfs.c
 util/rblist.c
 util/strlist.c
 util/sysfs.c
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bd85280bb6e8..ab265c2cfab3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1365,18 +1365,6 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
 	return machine__fprintf(&session->machines.host, fp);
 }
 
-void perf_session__remove_thread(struct perf_session *session,
-				 struct thread *th)
-{
-	/*
-	 * FIXME: This one makes no sense, we need to remove the thread from
-	 * the machine it belongs to, perf_session can have many machines, so
-	 * doing it always on ->machines.host is wrong.  Fix when auditing all
-	 * the 'perf kvm' code.
-	 */
-	machine__remove_thread(&session->machines.host, th);
-}
-
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b5c0847edfa9..6b51d47acdba 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -72,7 +72,6 @@ void perf_event__attr_swap(struct perf_event_attr *attr);
 int perf_session__create_kernel_maps(struct perf_session *self);
 
 void perf_session__set_id_hdr_size(struct perf_session *session);
-void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
 struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 73d510269784..6b0ed322907e 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -24,6 +24,7 @@ cflags += getenv('CFLAGS', '').split()
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
+liblk = getenv('LIBLK')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -32,7 +33,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
-		  extra_objects = [libtraceevent],
+		  extra_objects = [libtraceevent, liblk],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index f718df8a3c59..0cd8b3108084 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -21,4 +21,9 @@ void thread_map__delete(struct thread_map *threads);
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
+static inline int thread_map__nr(struct thread_map *threads)
+{
+	return threads ? threads->nr : 1;
+}
+
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index a8d81c35ef66..5729f434c5b1 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,35 +38,14 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "evsel.h"
 
 #define VERSION "0.5"
 
-#define TRACE_CTRL	"tracing_on"
-#define TRACE		"trace"
-#define AVAILABLE	"available_tracers"
-#define CURRENT		"current_tracer"
-#define ITER_CTRL	"trace_options"
-#define MAX_LATENCY	"tracing_max_latency"
-
-unsigned int page_size;
-
 static const char *output_file = "trace.info";
 static int output_fd;
 
-struct event_list {
-	struct event_list *next;
-	const char *event;
-};
-
-struct events {
-	struct events *sibling;
-	struct events *children;
-	struct events *next;
-	char *name;
-};
-
 
 static void *malloc_or_die(unsigned int size)
 {
@@ -80,7 +59,7 @@ static void *malloc_or_die(unsigned int size)
 
 static const char *find_debugfs(void)
 {
-	const char *path = debugfs_mount(NULL);
+	const char *path = perf_debugfs_mount(NULL);
 
 	if (!path)
 		die("Your kernel not support debugfs filesystem");
@@ -131,17 +110,10 @@ static void put_tracing_file(char *file)
 	free(file);
 }
 
-static ssize_t calc_data_size;
-
 static ssize_t write_or_die(const void *buf, size_t len)
 {
 	int ret;
 
-	if (calc_data_size) {
-		calc_data_size += len;
-		return len;
-	}
-
 	ret = write(output_fd, buf, len);
 	if (ret < 0)
 		die("writing to '%s'", output_file);
@@ -457,7 +429,6 @@ static void tracing_data_header(void)
 	write_or_die(buf, 1);
 
 	/* save page_size */
-	page_size = sysconf(_SC_PAGESIZE);
 	write_or_die(&page_size, 4);
 }
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 3aabcd687cd5..4454835a9ebc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -183,43 +183,6 @@ void event_format__print(struct event_format *event,
 	trace_seq_do_printf(&s);
 }
 
-void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
-{
-	int type = trace_parse_common_type(pevent, data);
-	struct event_format *event = pevent_find_event(pevent, type);
-
-	if (!event) {
-		warning("ug! no event found for type %d", type);
-		return;
-	}
-
-	event_format__print(event, cpu, data, size);
-}
-
-void print_event(struct pevent *pevent, int cpu, void *data, int size,
-		 unsigned long long nsecs, char *comm)
-{
-	struct pevent_record record;
-	struct trace_seq s;
-	int pid;
-
-	pevent->latency_format = latency_format;
-
-	record.ts = nsecs;
-	record.cpu = cpu;
-	record.size = size;
-	record.data = data;
-	pid = pevent_data_pid(pevent, &record);
-
-	if (!pevent_pid_is_registered(pevent, pid))
-		pevent_register_comm(pevent, comm, pid);
-
-	trace_seq_init(&s);
-	pevent_print_event(pevent, &s, &record);
-	trace_seq_do_printf(&s);
-	printf("\n");
-}
-
 void parse_proc_kallsyms(struct pevent *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3741572696af..7cb24635adf2 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -41,8 +41,6 @@
 
 static int input_fd;
 
-static int read_page;
-
 int file_bigendian;
 int host_bigendian;
 static int long_size;
@@ -287,205 +285,6 @@ static void read_event_files(struct pevent *pevent)
 	}
 }
 
-struct cpu_data {
-	unsigned long long	offset;
-	unsigned long long	size;
-	unsigned long long	timestamp;
-	struct pevent_record	*next;
-	char			*page;
-	int			cpu;
-	int			index;
-	int			page_size;
-};
-
-static struct cpu_data *cpu_data;
-
-static void update_cpu_data_index(int cpu)
-{
-	cpu_data[cpu].offset += page_size;
-	cpu_data[cpu].size -= page_size;
-	cpu_data[cpu].index = 0;
-}
-
-static void get_next_page(int cpu)
-{
-	off_t save_seek;
-	off_t ret;
-
-	if (!cpu_data[cpu].page)
-		return;
-
-	if (read_page) {
-		if (cpu_data[cpu].size <= page_size) {
-			free(cpu_data[cpu].page);
-			cpu_data[cpu].page = NULL;
-			return;
-		}
-
-		update_cpu_data_index(cpu);
-
-		/* other parts of the code may expect the pointer to not move */
-		save_seek = lseek(input_fd, 0, SEEK_CUR);
-
-		ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET);
-		if (ret == (off_t)-1)
-			die("failed to lseek");
-		ret = read(input_fd, cpu_data[cpu].page, page_size);
-		if (ret < 0)
-			die("failed to read page");
-
-		/* reset the file pointer back */
-		lseek(input_fd, save_seek, SEEK_SET);
-
-		return;
-	}
-
-	munmap(cpu_data[cpu].page, page_size);
-	cpu_data[cpu].page = NULL;
-
-	if (cpu_data[cpu].size <= page_size)
-		return;
-
-	update_cpu_data_index(cpu);
-
-	cpu_data[cpu].page = mmap(NULL, page_size, PROT_READ, MAP_PRIVATE,
-				  input_fd, cpu_data[cpu].offset);
-	if (cpu_data[cpu].page == MAP_FAILED)
-		die("failed to mmap cpu %d at offset 0x%llx",
-		    cpu, cpu_data[cpu].offset);
-}
-
-static unsigned int type_len4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return (type_len_ts >> 27) & ((1 << 5) - 1);
-	else
-		return type_len_ts & ((1 << 5) - 1);
-}
-
-static unsigned int ts4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return type_len_ts & ((1 << 27) - 1);
-	else
-		return type_len_ts >> 5;
-}
-
-static int calc_index(void *ptr, int cpu)
-{
-	return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page;
-}
-
-struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu)
-{
-	struct pevent_record *data;
-	void *page = cpu_data[cpu].page;
-	int idx = cpu_data[cpu].index;
-	void *ptr = page + idx;
-	unsigned long long extend;
-	unsigned int type_len_ts;
-	unsigned int type_len;
-	unsigned int delta;
-	unsigned int length = 0;
-
-	if (cpu_data[cpu].next)
-		return cpu_data[cpu].next;
-
-	if (!page)
-		return NULL;
-
-	if (!idx) {
-		/* FIXME: handle header page */
-		if (header_page_ts_size != 8)
-			die("expected a long long type for timestamp");
-		cpu_data[cpu].timestamp = data2host8(pevent, ptr);
-		ptr += 8;
-		switch (header_page_size_size) {
-		case 4:
-			cpu_data[cpu].page_size = data2host4(pevent, ptr);
-			ptr += 4;
-			break;
-		case 8:
-			cpu_data[cpu].page_size = data2host8(pevent, ptr);
-			ptr += 8;
-			break;
-		default:
-			die("bad long size");
-		}
-		ptr = cpu_data[cpu].page + header_page_data_offset;
-	}
-
-read_again:
-	idx = calc_index(ptr, cpu);
-
-	if (idx >= cpu_data[cpu].page_size) {
-		get_next_page(cpu);
-		return trace_peek_data(pevent, cpu);
-	}
-
-	type_len_ts = data2host4(pevent, ptr);
-	ptr += 4;
-
-	type_len = type_len4host(type_len_ts);
-	delta = ts4host(type_len_ts);
-
-	switch (type_len) {
-	case RINGBUF_TYPE_PADDING:
-		if (!delta)
-			die("error, hit unexpected end of page");
-		length = data2host4(pevent, ptr);
-		ptr += 4;
-		length *= 4;
-		ptr += length;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_EXTEND:
-		extend = data2host4(pevent, ptr);
-		ptr += 4;
-		extend <<= TS_SHIFT;
-		extend += delta;
-		cpu_data[cpu].timestamp += extend;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_STAMP:
-		ptr += 12;
-		break;
-	case 0:
-		length = data2host4(pevent, ptr);
-		ptr += 4;
-		die("here! length=%d", length);
-		break;
-	default:
-		length = type_len * 4;
-		break;
-	}
-
-	cpu_data[cpu].timestamp += delta;
-
-	data = malloc_or_die(sizeof(*data));
-	memset(data, 0, sizeof(*data));
-
-	data->ts = cpu_data[cpu].timestamp;
-	data->size = length;
-	data->data = ptr;
-	ptr += length;
-
-	cpu_data[cpu].index = calc_index(ptr, cpu);
-	cpu_data[cpu].next = data;
-
-	return data;
-}
-
-struct pevent_record *trace_read_data(struct pevent *pevent, int cpu)
-{
-	struct pevent_record *data;
-
-	data = trace_peek_data(pevent, cpu);
-	cpu_data[cpu].next = NULL;
-
-	return data;
-}
-
 ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 {
 	char buf[BUFSIZ];
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a55fd37ffea1..28ccde8ba20f 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -30,13 +30,9 @@ enum {
 int bigendian(void);
 
 struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
-void print_trace_event(struct pevent *pevent, int cpu, void *data, int size);
 void event_format__print(struct event_format *event,
 			 int cpu, void *data, int size);
 
-void print_event(struct pevent *pevent, int cpu, void *data, int size,
-		 unsigned long long nsecs, char *comm);
-
 int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
 int parse_event_file(struct pevent *pevent,
 		     char *buf, unsigned long size, char *sys);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 805d1f52c5b4..59d868add275 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,8 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
+char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
+
 void event_attr_init(struct perf_event_attr *attr)
 {
 	if (!perf_host)
@@ -242,3 +244,28 @@ void get_term_dimensions(struct winsize *ws)
 	ws->ws_row = 25;
 	ws->ws_col = 80;
 }
+
+static void set_tracing_events_path(const char *mountpoint)
+{
+	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
+		 mountpoint, "tracing/events");
+}
+
+const char *perf_debugfs_mount(const char *mountpoint)
+{
+	const char *mnt;
+
+	mnt = debugfs_mount(mountpoint);
+	if (!mnt)
+		return NULL;
+
+	set_tracing_events_path(mnt);
+
+	return mnt;
+}
+
+void perf_debugfs_set_path(const char *mntpt)
+{
+	snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt);
+	set_tracing_events_path(mntpt);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 09b4c26b71aa..6a0781c3a573 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -73,10 +73,14 @@
 #include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
+#include <lk/debugfs.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
+extern char tracing_events_path[];
+extern void perf_debugfs_set_path(const char *mountpoint);
+const char *perf_debugfs_mount(const char *mountpoint);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -274,5 +278,4 @@ extern unsigned int page_size;
 
 struct winsize;
 void get_term_dimensions(struct winsize *ws);
-
-#endif
+#endif /* GIT_COMPAT_UTIL_H */