Merge tag 'perf-core-for-mingo-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

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

New features:

  - Add API to set values of map entries in a BPF object, be it
    individual map slots or ranges (Wang Nan)

  - Introduce support for the 'bpf-output' event (Wang Nan)

  - Add glue to read perf events in a BPF program (Wang Nan)

User visible changes:

  - Don't stop PMU parsing on alias parse error, allowing the
    addition of new sysfs PMU files without breaking old tools (Andi Kleen)

  - Implement '%' operation in libtraceevent (Daniel Bristot de Oliveira)

  - Allow specifying events via -e in 'perf mem record', also listing what events
    can be specified via 'perf mem record -e list' (Jiri Olsa)

  - Improve support to 'data_src', 'weight' and 'addr' fields in
    'perf script' (Jiri Olsa)

Infrastructure changes:

  - Export cacheline routines (Jiri Olsa)

  - Remove strbuf_{remove,splice}(), dead code (Arnaldo Carvalho de Melo)

Fixes:

  - Sort key fixes: Alignment for srcline, file, trace; fix
    segfault for dynamic, trace events related sort keys (Namyung Kim)

Build fixes:

  - Remove duplicate typedef config_term_func_t definition,
    fixing the build on older systems (Arnaldo Carvalho de Melo)

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

26 files changed, 1300 insertions, 121 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index c3bd294a63d1..575e75174087 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1951,6 +1951,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		   strcmp(token, "*") == 0 ||
 		   strcmp(token, "^") == 0 ||
 		   strcmp(token, "/") == 0 ||
+		   strcmp(token, "%") == 0 ||
 		   strcmp(token, "<") == 0 ||
 		   strcmp(token, ">") == 0 ||
 		   strcmp(token, "<=") == 0 ||
@@ -3689,6 +3690,9 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		case '/':
 			val = left / right;
 			break;
+		case '%':
+			val = left % right;
+			break;
 		case '*':
 			val = left * right;
 			break;
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 96c1a4cfbbbf..f4dd2b48f90f 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -86,8 +86,7 @@ static int check_emacsclient_version(void)
 		return -1;
 	}
 
-	strbuf_remove(&buffer, 0, strlen("emacsclient"));
-	version = atoi(buffer.buf);
+	version = atoi(buffer.buf + strlen("emacsclient"));
 
 	if (version < 22) {
 		fprintf(stderr,
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 390170041696..b3f8a89ede40 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,8 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -21,11 +23,55 @@ struct perf_mem {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+			       const char *str, int unset __maybe_unused)
+{
+	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	int j;
+
+	if (strcmp(str, "list")) {
+		if (!perf_mem_events__parse(str)) {
+			mem->operation = 0;
+			return 0;
+		}
+		exit(-1);
+	}
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = &perf_mem_events[j];
+
+		fprintf(stderr, "%-20s%s",
+			e->tag, verbose ? "" : "\n");
+		if (verbose)
+			fprintf(stderr, " [%s]\n", e->name);
+	}
+	exit(0);
+}
+
+static const char * const __usage[] = {
+	"perf mem record [<options>] [<command>]",
+	"perf mem record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,23 +81,34 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	rec_argv[i++] = "record";
 
 	if (mem->operation & MEM_OPERATION_LOAD)
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-loads/pp";
-	}
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
 
-	if (mem->operation & MEM_OPERATION_STORE) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-stores/pp";
-	}
+		rec_argv[i++] = perf_mem_events[j].name;
+	};
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	if (verbose > 0) {
+		pr_debug("calling: record ");
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
 	ret = cmd_record(i, rec_argv, NULL);
 	free(rec_argv);
 	return ret;
@@ -298,7 +355,6 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cf3a28d83066..7d11162b6c41 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -32,6 +32,7 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"
+#include "util/bpf-loader.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -536,6 +537,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_child;
+	}
+
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214d820f..f4caf4898245 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -58,6 +58,8 @@ enum perf_output_field {
 	PERF_OUTPUT_IREGS	    = 1U << 14,
 	PERF_OUTPUT_BRSTACK	    = 1U << 15,
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
+	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
+	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 };
 
 struct output_option {
@@ -81,6 +83,8 @@ struct output_option {
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -131,7 +135,8 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -242,6 +247,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_SRC) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+					PERF_OUTPUT_DATA_SRC))
+		return -EINVAL;
+
+	if (PRINT_FIELD(WEIGHT) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+					PERF_OUTPUT_WEIGHT))
+		return -EINVAL;
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -673,6 +688,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(event, sample, thread, attr);
 
+	if (PRINT_FIELD(DATA_SRC))
+		printf("%16" PRIx64, sample->data_src);
+
+	if (PRINT_FIELD(WEIGHT))
+		printf("%16" PRIu64, sample->weight);
+
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
 			printf(" ");
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 4aed5cb4ac2d..199501c71e27 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -112,7 +112,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	parse_evlist.error = &parse_error;
 	INIT_LIST_HEAD(&parse_evlist.list);
 
-	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
 	if (err || list_empty(&parse_evlist.list)) {
 		pr_debug("Failed to add events selected by BPF\n");
 		return TEST_FAIL;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 1ba4117d9c2d..12223d791e9f 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -645,6 +645,9 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 	if (perf_hpp__is_sort_entry(fmt))
 		return perf_hpp__reset_sort_width(fmt, hists);
 
+	if (perf_hpp__is_dynamic_entry(fmt))
+		return;
+
 	BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX);
 
 	switch (fmt->idx) {
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a34752d28488..df2b690970ac 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 0bdccf423b27..0967ce601931 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -16,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+enum bpf_map_op_type {
+	BPF_MAP_OP_SET_VALUE,
+	BPF_MAP_OP_SET_EVSEL,
+};
+
+enum bpf_map_key_type {
+	BPF_MAP_KEY_ALL,
+	BPF_MAP_KEY_RANGES,
+};
+
+struct bpf_map_op {
+	struct list_head list;
+	enum bpf_map_op_type op_type;
+	enum bpf_map_key_type key_type;
+	union {
+		struct parse_events_array array;
+	} k;
+	union {
+		u64 value;
+		struct perf_evsel *evsel;
+	} v;
+};
+
+struct bpf_map_priv {
+	struct list_head ops_list;
+};
+
+static void
+bpf_map_op__delete(struct bpf_map_op *op)
+{
+	if (!list_empty(&op->list))
+		list_del(&op->list);
+	if (op->key_type == BPF_MAP_KEY_RANGES)
+		parse_events__clear_array(&op->k.array);
+	free(op);
+}
+
+static void
+bpf_map_priv__purge(struct bpf_map_priv *priv)
+{
+	struct bpf_map_op *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
+		list_del_init(&pos->list);
+		bpf_map_op__delete(pos);
+	}
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+		    void *_priv)
+{
+	struct bpf_map_priv *priv = _priv;
+
+	bpf_map_priv__purge(priv);
+	free(priv);
+}
+
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
+{
+	op->key_type = BPF_MAP_KEY_ALL;
+	if (!term)
+		return 0;
+
+	if (term->array.nr_ranges) {
+		size_t memsz = term->array.nr_ranges *
+				sizeof(op->k.array.ranges[0]);
+
+		op->k.array.ranges = memdup(term->array.ranges, memsz);
+		if (!op->k.array.ranges) {
+			pr_debug("No enough memory to alloc indices for map\n");
+			return -ENOMEM;
+		}
+		op->key_type = BPF_MAP_KEY_RANGES;
+		op->k.array.nr_ranges = term->array.nr_ranges;
+	}
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map_op__new(struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = zalloc(sizeof(*op));
+	if (!op) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	INIT_LIST_HEAD(&op->list);
+
+	err = bpf_map_op_setkey(op, term);
+	if (err) {
+		free(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
+{
+	struct bpf_map_priv *priv;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("Failed to get private from map %s\n", map_name);
+		return err;
+	}
+
+	if (!priv) {
+		priv = zalloc(sizeof(*priv));
+		if (!priv) {
+			pr_debug("No enough memory to alloc map private\n");
+			return -ENOMEM;
+		}
+		INIT_LIST_HEAD(&priv->ops_list);
+
+		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+			free(priv);
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+	}
+
+	list_add_tail(&op->list, &priv->ops_list);
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = bpf_map_op__new(term);
+	if (IS_ERR(op))
+		return op;
+
+	err = bpf_map__add_op(map, op);
+	if (err) {
+		bpf_map_op__delete(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+__bpf_map__config_value(struct bpf_map *map,
+			struct parse_events_term *term)
+{
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (def.type != BPF_MAP_TYPE_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+	if (def.key_size < sizeof(unsigned int)) {
+		pr_debug("Map %s has incorrect key size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+	}
+	switch (def.value_size) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		pr_debug("Map %s has incorrect value size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_VALUE;
+	op->v.value = term->val.num;
+	return 0;
+}
+
+static int
+bpf_map__config_value(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
+		pr_debug("ERROR: wrong value type for 'value'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_value(map, term);
+}
+
+static int
+__bpf_map__config_event(struct bpf_map *map,
+			struct parse_events_term *term,
+			struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+	if (!evsel) {
+		pr_debug("Event (for '%s') '%s' doesn't exist\n",
+			 map_name, term->val.str);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return err;
+	}
+
+	/*
+	 * No need to check key_size and value_size:
+	 * kernel has already checked them.
+	 */
+	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_EVSEL;
+	op->v.evsel = evsel;
+	return 0;
+}
+
+static int
+bpf_map__config_event(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
+		pr_debug("ERROR: wrong value type for 'event'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_event(map, term, evlist);
+}
+
+struct bpf_obj_config__map_func {
+	const char *config_opt;
+	int (*config_func)(struct bpf_map *, struct parse_events_term *,
+			   struct perf_evlist *);
+};
+
+struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
+	{"value", bpf_map__config_value},
+	{"event", bpf_map__config_event},
+};
+
+static int
+config_map_indices_range_check(struct parse_events_term *term,
+			       struct bpf_map *map,
+			       const char *map_name)
+{
+	struct parse_events_array *array = &term->array;
+	struct bpf_map_def def;
+	unsigned int i;
+	int err;
+
+	if (!array->nr_ranges)
+		return 0;
+	if (!array->ranges) {
+		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+			 map_name, (int)array->nr_ranges);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	for (i = 0; i < array->nr_ranges; i++) {
+		unsigned int start = array->ranges[i].start;
+		size_t length = array->ranges[i].length;
+		unsigned int idx = start + length - 1;
+
+		if (idx >= def.max_entries) {
+			pr_debug("ERROR: index %d too large\n", idx);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+		}
+	}
+	return 0;
+}
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *key_scan_pos)
+{
+	/* key is "map:<mapname>.<config opt>" */
+	char *map_name = strdup(term->config + sizeof("map:") - 1);
+	struct bpf_map *map;
+	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+	char *map_opt;
+	size_t i;
+
+	if (!map_name)
+		return -ENOMEM;
+
+	map_opt = strchr(map_name, '.');
+	if (!map_opt) {
+		pr_debug("ERROR: Invalid map config: %s\n", map_name);
+		goto out;
+	}
+
+	*map_opt++ = '\0';
+	if (*map_opt == '\0') {
+		pr_debug("ERROR: Invalid map option: %s\n", term->config);
+		goto out;
+	}
+
+	map = bpf_object__get_map_by_name(obj, map_name);
+	if (!map) {
+		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
+		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+		goto out;
+	}
+
+	*key_scan_pos += strlen(map_opt);
+	err = config_map_indices_range_check(term, map, map_name);
+	if (err)
+		goto out;
+	*key_scan_pos -= strlen(map_opt);
+
+	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
+		struct bpf_obj_config__map_func *func =
+				&bpf_obj_config__map_funcs[i];
+
+		if (strcmp(map_opt, func->config_opt) == 0) {
+			err = func->config_func(map, term, evlist);
+			goto out;
+		}
+	}
+
+	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
+	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+	free(map_name);
+	if (!err)
+		key_scan_pos += strlen(map_opt);
+	return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *error_pos)
+{
+	int key_scan_pos = 0;
+	int err;
+
+	if (!obj || !term || !term->config)
+		return -EINVAL;
+
+	if (!prefixcmp(term->config, "map:")) {
+		key_scan_pos = sizeof("map:") - 1;
+		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+		goto out;
+	}
+	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+	if (error_pos)
+		*error_pos = key_scan_pos;
+	return err;
+
+}
+
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+				 struct bpf_map_def *pdef,
+				 struct bpf_map_op *op,
+				 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+		      void *arg, const char *name,
+		      int map_fd, struct bpf_map_def *pdef,
+		      struct bpf_map_op *op)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < pdef->max_entries; i++) {
+		err = func(name, map_fd, pdef, op, &i, arg);
+		if (err) {
+			pr_debug("ERROR: failed to insert value to %s[%u]\n",
+				 name, i);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+			 const char *name, int map_fd,
+			 struct bpf_map_def *pdef,
+			 struct bpf_map_op *op)
+{
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < op->k.array.nr_ranges; i++) {
+		unsigned int start = op->k.array.ranges[i].start;
+		size_t length = op->k.array.ranges[i].length;
+
+		for (j = 0; j < length; j++) {
+			unsigned int idx = start + j;
+
+			err = func(name, map_fd, pdef, op, &idx, arg);
+			if (err) {
+				pr_debug("ERROR: failed to insert value to %s[%u]\n",
+					 name, idx);
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+			   map_config_func_t func,
+			   void *arg)
+{
+	int err, map_fd;
+	const char *name;
+	struct bpf_map_op *op;
+	struct bpf_map_def def;
+	struct bpf_map_priv *priv;
+
+	name = bpf_map__get_name(map);
+
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("ERROR: failed to get private from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	if (!priv || list_empty(&priv->ops_list)) {
+		pr_debug("INFO: nothing to config for map %s\n", name);
+		return 0;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: failed to get definition from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	map_fd = bpf_map__get_fd(map);
+	if (map_fd < 0) {
+		pr_debug("ERROR: failed to get fd from map %s\n", name);
+		return map_fd;
+	}
+
+	list_for_each_entry(op, &priv->ops_list, list) {
+		switch (def.type) {
+		case BPF_MAP_TYPE_ARRAY:
+		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+			switch (op->key_type) {
+			case BPF_MAP_KEY_ALL:
+				err = foreach_key_array_all(func, arg, name,
+							    map_fd, &def, op);
+				break;
+			case BPF_MAP_KEY_RANGES:
+				err = foreach_key_array_ranges(func, arg, name,
+							       map_fd, &def,
+							       op);
+				break;
+			default:
+				pr_debug("ERROR: keytype for map '%s' invalid\n",
+					 name);
+				return -BPF_LOADER_ERRNO__INTERNAL;
+			}
+			if (err)
+				return err;
+			break;
+		default:
+			pr_debug("ERROR: type of '%s' incorrect\n", name);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+		}
+	}
+
+	return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+			   size_t val_size, u64 val)
+{
+	int err = 0;
+
+	switch (val_size) {
+	case 1: {
+		u8 _val = (u8)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 2: {
+		u16 _val = (u16)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 4: {
+		u32 _val = (u32)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 8: {
+		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+		break;
+	}
+	default:
+		pr_debug("ERROR: invalid value size\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+			   struct perf_evsel *evsel)
+{
+	struct xyarray *xy = evsel->fd;
+	struct perf_event_attr *attr;
+	unsigned int key, events;
+	bool check_pass = false;
+	int *evt_fd;
+	int err;
+
+	if (!xy) {
+		pr_debug("ERROR: evsel not ready for map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (xy->row_size / xy->entry_size != 1) {
+		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+			 name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+	}
+
+	attr = &evsel->attr;
+	if (attr->inherit) {
+		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+	}
+
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
+	if (attr->type == PERF_TYPE_RAW)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_HARDWARE)
+		check_pass = true;
+	if (!check_pass) {
+		pr_debug("ERROR: Event type is wrong for map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+	}
+
+	events = xy->entries / (xy->row_size / xy->entry_size);
+	key = *((unsigned int *)pkey);
+	if (key >= events) {
+		pr_debug("ERROR: there is no event %d for map %s\n",
+			 key, name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+	}
+	evt_fd = xyarray__entry(xy, key, 0);
+	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+			     struct bpf_map_def *pdef __maybe_unused,
+			     struct bpf_map_op *op,
+			     void *pkey, void *arg __maybe_unused)
+{
+	int err;
+
+	switch (op->op_type) {
+	case BPF_MAP_OP_SET_VALUE:
+		err = apply_config_value_for_key(map_fd, pkey,
+						 pdef->value_size,
+						 op->v.value);
+		break;
+	case BPF_MAP_OP_SET_EVSEL:
+		err = apply_config_evsel_for_key(name, map_fd, pkey,
+						 op->v.evsel);
+		break;
+	default:
+		pr_debug("ERROR: unknown value type for '%s'\n", name);
+		err = -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+	return bpf_map_config_foreach_key(map,
+					  apply_obj_config_map_for_key,
+					  NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int err;
+
+	bpf_map__for_each(map, obj) {
+		err = apply_obj_config_map(map);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+	struct bpf_object *obj, *tmp;
+	int err;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		err = apply_obj_config_object(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
 	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
 	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
+	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
+	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
+	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
+	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
 };
 
 static int
@@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			     struct parse_events_term *term __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     int *error_pos __maybe_unused, int err,
+			     char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+			    "Can't use this config term with this map type");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+			    "Cannot set event to BPF map in multi-thread tracing");
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+			    "%s (Hint: use -i to turn off inherit)", emsg);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+			    "Can only put raw, hardware and BPF output event into a BPF map");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc0457e2b6..be4311944e3d 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,25 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
 	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
 	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
+	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
+	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
 		     bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+		    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+			     struct parse_events_term *term,
+			     struct perf_evlist *evlist,
+			     int *error_pos, int err, char *buf,
+			     size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +110,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+		struct parse_events_term *term __maybe_unused,
+		struct perf_evlist *evlist __maybe_unused,
+		int *error_pos __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
+bpf__apply_obj_config(void)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			 struct parse_events_term *term __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 int *error_pos __maybe_unused,
+			 int err __maybe_unused,
+			 char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 0f577162c699..c42e1967e970 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1741,3 +1741,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
 	tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+			       const char *str)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (!evsel->name)
+			continue;
+		if (strcmp(str, evsel->name) == 0)
+			return evsel;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7c4d9a206776..a0d15221db6e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6ae20d0056de..0902fe418754 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8e75434bd01c..efad78f811ad 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -364,6 +364,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 827c6cbcd05d..017eb5c42c37 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	if (h->transaction)
 		hists__new_col_len(hists, HISTC_TRANSACTION,
 				   hist_entry__transaction_len());
+
+	if (h->trace_output)
+		hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000000..b1507c04b257
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,51 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include "mem-events.h"
+#include "debug.h"
+
+#define E(t, n) { .tag = t, .name = n }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
+	E("ldlat-stores",	"cpu/mem-stores/P"),
+};
+
+#undef E
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000000..2995bae6ac33
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,22 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	const char	*tag;
+	const char	*name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+int perf_mem_events__parse(const char *str);
+
+#endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2996aa4207bd..4c19d5e79d8c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -363,7 +363,7 @@ static int config_attr(struct perf_event_attr *attr,
 
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2,
-			   struct parse_events_error *error,
+			   struct parse_events_error *err,
 			   struct list_head *head_config)
 {
 	struct perf_event_attr attr;
@@ -425,7 +425,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	attr.type = PERF_TYPE_HW_CACHE;
 
 	if (head_config) {
-		if (config_attr(&attr, head_config, error,
+		if (config_attr(&attr, head_config, err,
 				config_term_common))
 			return -EINVAL;
 
@@ -581,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 struct __add_bpf_event_param {
 	struct parse_events_evlist *data;
 	struct list_head *list;
+	struct list_head *head_config;
 };
 
 static int add_bpf_event(struct probe_trace_event *tev, int fd,
@@ -597,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 		 tev->group, tev->event, fd);
 
 	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-					  tev->event, evlist->error, NULL);
+					  tev->event, evlist->error,
+					  param->head_config);
 	if (err) {
 		struct perf_evsel *evsel, *tmp;
 
@@ -622,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj)
+			      struct bpf_object *obj,
+			      struct list_head *head_config)
 {
 	int err;
 	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {data, list};
+	struct __add_bpf_event_param param = {data, list, head_config};
 	static bool registered_unprobe_atexit = false;
 
 	if (IS_ERR(obj) || !obj) {
@@ -672,17 +675,99 @@ errout:
 	return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+			struct bpf_object *obj,
+			struct list_head *head_config)
+{
+	struct parse_events_term *term;
+	int error_pos;
+
+	if (!head_config || list_empty(head_config))
+		return 0;
+
+	list_for_each_entry(term, head_config, list) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+			snprintf(errbuf, sizeof(errbuf),
+				 "Invalid config term for BPF object");
+			errbuf[BUFSIZ - 1] = '\0';
+
+			data->error->idx = term->err_term;
+			data->error->str = strdup(errbuf);
+			return -EINVAL;
+		}
+
+		err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+		if (err) {
+			bpf__strerror_config_obj(obj, term, data->evlist,
+						 &error_pos, err, errbuf,
+						 sizeof(errbuf));
+			data->error->help = strdup(
+"Hint:\tValid config terms:\n"
+"     \tmap:[<arraymap>].value<indices>=[value]\n"
+"     \tmap:[<eventmap>].event<indices>=[event]\n"
+"\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
+"     \t(add -v to see detail)");
+			data->error->str = strdup(errbuf);
+			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+				data->error->idx = term->err_val;
+			else
+				data->error->idx = term->err_term + error_pos;
+			return err;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Split config terms:
+ * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
+ *  'call-graph=fp' is 'evt config', should be applied to each
+ *  events in bpf.c.
+ * 'map:array.value[0]=1' is 'obj config', should be processed
+ * with parse_events_config_bpf.
+ *
+ * Move object config terms from the first list to obj_head_config.
+ */
+static void
+split_bpf_config_terms(struct list_head *evt_head_config,
+		       struct list_head *obj_head_config)
+{
+	struct parse_events_term *term, *temp;
+
+	/*
+	 * Currectly, all possible user config term
+	 * belong to bpf object. parse_events__is_hardcoded_term()
+	 * happends to be a good flag.
+	 *
+	 * See parse_events_config_bpf() and
+	 * config_term_tracepoint().
+	 */
+	list_for_each_entry_safe(term, temp, evt_head_config, list)
+		if (!parse_events__is_hardcoded_term(term))
+			list_move_tail(&term->list, obj_head_config);
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source)
+			  bool source,
+			  struct list_head *head_config)
 {
+	int err;
 	struct bpf_object *obj;
+	LIST_HEAD(obj_head_config);
+
+	if (head_config)
+		split_bpf_config_terms(head_config, &obj_head_config);
 
 	obj = bpf__prepare_load(bpf_file_name, source);
 	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
-		int err;
 
 		err = PTR_ERR(obj);
 
@@ -700,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 		return err;
 	}
 
-	return parse_events_load_bpf_obj(data, list, obj);
+	err = parse_events_load_bpf_obj(data, list, obj, head_config);
+	if (err)
+		return err;
+	err = parse_events_config_bpf(data, obj, &obj_head_config);
+
+	/*
+	 * Caller doesn't know anything about obj_head_config,
+	 * so combine them together again before returnning.
+	 */
+	if (head_config)
+		list_splice_tail(&obj_head_config, head_config);
+	return err;
 }
 
 static int
@@ -841,10 +937,6 @@ void parse_events__shrink_config_terms(void)
 	config_term_shrinked = true;
 }
 
-typedef int config_term_func_t(struct perf_event_attr *attr,
-			       struct parse_events_term *term,
-			       struct parse_events_error *err);
-
 static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
 			      struct parse_events_error *err)
@@ -1485,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list  = LIST_HEAD_INIT(data.list),
-		.idx   = evlist->nr_entries,
-		.error = err,
+		.list   = LIST_HEAD_INIT(data.list),
+		.idx    = evlist->nr_entries,
+		.error  = err,
+		.evlist = evlist,
 	};
 	int ret;
 
@@ -2163,6 +2256,8 @@ void parse_events_terms__purge(struct list_head *terms)
 	struct parse_events_term *term, *h;
 
 	list_for_each_entry_safe(term, h, terms, list) {
+		if (term->array.nr_ranges)
+			free(term->array.ranges);
 		list_del_init(&term->list);
 		free(term);
 	}
@@ -2176,6 +2271,11 @@ void parse_events_terms__delete(struct list_head *terms)
 	free(terms);
 }
 
+void parse_events__clear_array(struct parse_events_array *a)
+{
+	free(a->ranges);
+}
+
 void parse_events_evlist_error(struct parse_events_evlist *data,
 			       int idx, const char *str)
 {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d5eb2af78826..67e493088e81 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -72,8 +72,17 @@ enum {
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
+struct parse_events_array {
+	size_t nr_ranges;
+	struct {
+		unsigned int start;
+		size_t length;
+	} *ranges;
+};
+
 struct parse_events_term {
 	char *config;
+	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -99,6 +108,7 @@ struct parse_events_evlist {
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
+	struct perf_evlist	  *evlist;
 };
 
 struct parse_events_terms {
@@ -119,6 +129,7 @@ int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
 void parse_events_terms__delete(struct list_head *terms);
 void parse_events_terms__purge(struct list_head *terms);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
@@ -129,12 +140,14 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source);
+			  bool source,
+			  struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj);
+			      struct bpf_object *obj,
+			      struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 99486e6a8b97..1477fbc78993 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -122,7 +123,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -176,6 +177,14 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"			{ BEGIN(config); return ']'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+,			{ return ','; }
+"\.\.\."		{ return PE_ARRAY_RANGE; }
+}
+
 <config>{
 	/*
 	 * Please update config_term_names when new static term is added.
@@ -195,6 +204,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
+\[all\]			{ return PE_ARRAY_ALL; }
+"["			{ BEGIN(array); return '['; }
 }
 
 <mem>{
@@ -237,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 6a2d006ea77f..d1fbcabbe70d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -83,6 +84,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -94,6 +98,7 @@ static inc_group_count(struct list_head *list,
 		char *sys;
 		char *event;
 	} tracepoint_name;
+	struct parse_events_array array;
 }
 %%
 
@@ -437,24 +442,26 @@ PE_RAW opt_event_config
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -570,6 +577,86 @@ PE_TERM
 	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+	struct parse_events_term *term;
+	int i;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+
+	term->array = $2;
+	$$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+	term->array = $2;
+	$$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+	$$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+	$$.nr_ranges = 0;
+	$$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+	struct parse_events_array new_array;
+
+	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+	new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+				  new_array.nr_ranges);
+	ABORT_ON(!new_array.ranges);
+	memcpy(&new_array.ranges[0], $1.ranges,
+	       $1.nr_ranges * sizeof(new_array.ranges[0]));
+	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+	       $3.nr_ranges * sizeof(new_array.ranges[0]));
+	free($1.ranges);
+	free($3.ranges);
+	$$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+	struct parse_events_array array;
+
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = 1;
+	$$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+	struct parse_events_array array;
+
+	ABORT_ON($3 < $1);
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = $3 - $1 + 1;
+	$$ = array;
+}
 
 sep_dc: ':' |
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index cf59fbaee491..ce61f79dbaae 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -284,13 +284,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int ret = 0;
 
 	event_dir = opendir(dir);
 	if (!event_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(event_dir))) {
+	while ((evt_ent = readdir(event_dir))) {
 		char path[PATH_MAX];
 		char *name = evt_ent->d_name;
 		FILE *file;
@@ -306,17 +305,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
-		ret = -EINVAL;
 		file = fopen(path, "r");
-		if (!file)
-			break;
+		if (!file) {
+			pr_debug("Cannot open %s\n", path);
+			continue;
+		}
 
-		ret = perf_pmu__new_alias(head, dir, name, file);
+		if (perf_pmu__new_alias(head, dir, name, file) < 0)
+			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
 
 	closedir(event_dir);
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index de715756f281..5388f7940474 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -286,36 +286,35 @@ struct sort_entry sort_sym = {
 
 /* --sort srcline */
 
+static char *hist_entry__get_srcline(struct hist_entry *he)
+{
+	struct map *map = he->ms.map;
+
+	if (!map)
+		return SRCLINE_UNKNOWN;
+
+	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
+			   he->ms.sym, true);
+}
+
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcline) {
-		if (!left->ms.map)
-			left->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = left->ms.map;
-			left->srcline = get_srcline(map->dso,
-					   map__rip_2objdump(map, left->ip),
-						    left->ms.sym, true);
-		}
-	}
-	if (!right->srcline) {
-		if (!right->ms.map)
-			right->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = right->ms.map;
-			right->srcline = get_srcline(map->dso,
-					     map__rip_2objdump(map, right->ip),
-						     right->ms.sym, true);
-		}
-	}
+	if (!left->srcline)
+		left->srcline = hist_entry__get_srcline(left);
+	if (!right->srcline)
+		right->srcline = hist_entry__get_srcline(right);
+
 	return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
+	if (!he->srcline)
+		he->srcline = hist_entry__get_srcline(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -329,11 +328,14 @@ struct sort_entry sort_srcline = {
 
 static char no_srcfile[1];
 
-static char *get_srcfile(struct hist_entry *e)
+static char *hist_entry__get_srcfile(struct hist_entry *e)
 {
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
+	if (!map)
+		return no_srcfile;
+
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
 			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
@@ -350,25 +352,21 @@ static char *get_srcfile(struct hist_entry *e)
 static int64_t
 sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcfile) {
-		if (!left->ms.map)
-			left->srcfile = no_srcfile;
-		else
-			left->srcfile = get_srcfile(left);
-	}
-	if (!right->srcfile) {
-		if (!right->ms.map)
-			right->srcfile = no_srcfile;
-		else
-			right->srcfile = get_srcfile(right);
-	}
+	if (!left->srcfile)
+		left->srcfile = hist_entry__get_srcfile(left);
+	if (!right->srcfile)
+		right->srcfile = hist_entry__get_srcfile(right);
+
 	return strcmp(right->srcfile, left->srcfile);
 }
 
 static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
+	if (!he->srcfile)
+		he->srcfile = hist_entry__get_srcfile(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile);
 }
 
 struct sort_entry sort_srcfile = {
@@ -485,9 +483,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
 	if (right->trace_output == NULL)
 		right->trace_output = get_trace_output(right);
 
-	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
-	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
-
 	return strcmp(right->trace_output, left->trace_output);
 }
 
@@ -498,11 +493,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 
 	evsel = hists_to_evsel(he->hists);
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
-		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 
 	if (he->trace_output == NULL)
 		he->trace_output = get_trace_output(he);
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+	return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output);
 }
 
 struct sort_entry sort_trace = {
@@ -843,7 +838,6 @@ static const char * const tlb_access[] = {
 	"Walker",
 	"Fault",
 };
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
 
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -865,7 +859,7 @@ static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
 
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -920,7 +914,6 @@ static const char * const mem_lvl[] = {
 	"I/O",
 	"Uncached",
 };
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
 
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -942,7 +935,7 @@ static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -988,7 +981,6 @@ static const char * const snoop_access[] = {
 	"Hit",
 	"HitM",
 };
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
 
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -1003,7 +995,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	if (he->mem_info)
 		m = he->mem_info->data_src.mem_snoop;
 
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -1020,12 +1012,6 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1835,6 +1821,20 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
 	return fmt->cmp == __sort__hde_cmp;
 }
 
+static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_dynamic_entry *hde_a;
+	struct hpp_dynamic_entry *hde_b;
+
+	if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b))
+		return false;
+
+	hde_a = container_of(a, struct hpp_dynamic_entry, hpp);
+	hde_b = container_of(b, struct hpp_dynamic_entry, hpp);
+
+	return hde_a->field == hde_b->field;
+}
+
 static void hde_free(struct perf_hpp_fmt *fmt)
 {
 	struct hpp_dynamic_entry *hde;
@@ -1867,6 +1867,7 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
 	hde->hpp.cmp = __sort__hde_cmp;
 	hde->hpp.collapse = __sort__hde_cmp;
 	hde->hpp.sort = __sort__hde_cmp;
+	hde->hpp.equal = __sort__hde_equal;
 	hde->hpp.free = hde_free;
 
 	INIT_LIST_HEAD(&hde->hpp.list);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 89a1273fd2da..5b9c6246de6d 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -162,6 +162,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 25671fa16618..d3d279275432 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -51,30 +51,6 @@ void strbuf_grow(struct strbuf *sb, size_t extra)
 	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
 }
 
-static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
-				   const void *data, size_t dlen)
-{
-	if (pos + len < pos)
-		die("you want to use way too much memory");
-	if (pos > sb->len)
-		die("`pos' is too far after the end of the buffer");
-	if (pos + len > sb->len)
-		die("`pos + len' is too far after the end of the buffer");
-
-	if (dlen >= len)
-		strbuf_grow(sb, dlen - len);
-	memmove(sb->buf + pos + dlen,
-			sb->buf + pos + len,
-			sb->len - pos - len);
-	memcpy(sb->buf + pos, data, dlen);
-	strbuf_setlen(sb, sb->len + dlen - len);
-}
-
-void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
-{
-	strbuf_splice(sb, pos, len, NULL, 0);
-}
-
 void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 {
 	strbuf_grow(sb, len);
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 529f2f035249..7a32c838884d 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -77,8 +77,6 @@ static inline void strbuf_addch(struct strbuf *sb, int c) {
 	sb->buf[sb->len] = '\0';
 }
 
-extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
-
 extern void strbuf_add(struct strbuf *, const void *, size_t);
 static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
 	strbuf_add(sb, s, strlen(s));