Merge tag 'perf-core-for-mingo-4.20-20180919' 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:

perf test improvements:

- Add watchpoint entry (Ravi Bangoria)

Build fixes:

- Initialize perf_data_file fd field to fix building the CTF (trace format)
  converter with with gcc 4.8.4 on Ubuntu 14.04 (Jérémie Galarneau)

- Use -Wno-redundant-decls to build with PYTHON=python3 to
  build the python binding, fixing the build in systems such
  as Clear Linux (Arnaldo Carvalho de Melo)

Hardware tracing improvements:

- Suppress AUX/OVERWRITE records (Alexander Shishkin)

Infrastructure changes:

- Adopt PTR_ERR_OR_ZERO from the kernel and use it in
  the bpf-loader instead of open coded equivalent (Ding Xiang)

- Improve the event ordering code to make it clear and fix
  a bug related to freeing of events when using pipe mode
  from 'record' to 'inject' (Jiri Olsa)

- Some prep work to facilitate per-cpu threads to write
  record data to per-cpu files (Jiri Olsa)

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

30 files changed, 519 insertions, 230 deletions

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d3cf407e374..4a9937076331 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,10 +459,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
+		 *
+		 * Note: the OVERWRITE records by themselves are not considered
+		 * useful, as they don't communicate any *new* information,
+		 * aside from the short-lived offset, that becomes history at
+		 * the next event sched-in and therefore isn't useful.
+		 * The userspace that needs to copy out AUX data in overwrite
+		 * mode should know to use user_page::aux_head for the actual
+		 * offset. So, from now on we don't output AUX records that
+		 * have *only* OVERWRITE flag set.
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
+			perf_event_aux_event(handle->event, aux_head, size,
+			                     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h
index 7a8b61ad44cb..094649667bae 100644
--- a/tools/include/linux/err.h
+++ b/tools/include/linux/err.h
@@ -52,4 +52,11 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 	return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
 }
 
+static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	else
+		return 0;
+}
 #endif /* _LINUX_ERR_H */
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 830481b8db26..93d679eaf1f4 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,12 +283,11 @@ out_put:
 	return ret;
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a3b346359ba0..b4a29f435b06 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -86,12 +86,10 @@ static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
-static int perf_event__repipe_op2_synth(struct perf_tool *tool,
-					union perf_event *event,
-					struct perf_session *session
-					__maybe_unused)
+static int perf_event__repipe_op2_synth(struct perf_session *session,
+					union perf_event *event)
 {
-	return perf_event__repipe_synth(tool, event);
+	return perf_event__repipe_synth(session->tool, event);
 }
 
 static int perf_event__repipe_attr(struct perf_tool *tool,
@@ -133,10 +131,10 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
 	return 0;
 }
 
-static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static s64 perf_event__repipe_auxtrace(struct perf_session *session,
+				       union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
 	int ret;
@@ -174,9 +172,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 #else
 
 static s64
-perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
-			    union perf_event *event __maybe_unused,
-			    struct perf_session *session __maybe_unused)
+perf_event__repipe_auxtrace(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused)
 {
 	pr_err("AUX area tracing not supported\n");
 	return -EINVAL;
@@ -362,26 +359,24 @@ static int perf_event__repipe_exit(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(struct perf_tool *tool,
-					   union perf_event *event,
-					   struct perf_session *session)
+static int perf_event__repipe_tracing_data(struct perf_session *session,
+					   union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_tracing_data(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_tracing_data(session, event);
 
 	return err;
 }
 
-static int perf_event__repipe_id_index(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static int perf_event__repipe_id_index(struct perf_session *session,
+				       union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_id_index(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_id_index(session, event);
 
 	return err;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9853552bcf16..0980dfe3396b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -106,9 +106,12 @@ static bool switch_output_time(struct record *rec)
 	       trigger_is_ready(&switch_output_trigger);
 }
 
-static int record__write(struct record *rec, void *bf, size_t size)
+static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused,
+			 void *bf, size_t size)
 {
-	if (perf_data__write(rec->session->data, bf, size) < 0) {
+	struct perf_data_file *file = &rec->session->data->file;
+
+	if (perf_data_file__write(file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
@@ -127,15 +130,15 @@ static int process_synthesized_event(struct perf_tool *tool,
 				     struct machine *machine __maybe_unused)
 {
 	struct record *rec = container_of(tool, struct record, tool);
-	return record__write(rec, event, event->header.size);
+	return record__write(rec, NULL, event, event->header.size);
 }
 
-static int record__pushfn(void *to, void *bf, size_t size)
+static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size)
 {
 	struct record *rec = to;
 
 	rec->samples++;
-	return record__write(rec, bf, size);
+	return record__write(rec, map, bf, size);
 }
 
 static volatile int done;
@@ -170,6 +173,7 @@ static void record__sig_exit(void)
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 static int record__process_auxtrace(struct perf_tool *tool,
+				    struct perf_mmap *map,
 				    union perf_event *event, void *data1,
 				    size_t len1, void *data2, size_t len2)
 {
@@ -197,21 +201,21 @@ static int record__process_auxtrace(struct perf_tool *tool,
 	if (padding)
 		padding = 8 - padding;
 
-	record__write(rec, event, event->header.size);
-	record__write(rec, data1, len1);
+	record__write(rec, map, event, event->header.size);
+	record__write(rec, map, data1, len1);
 	if (len2)
-		record__write(rec, data2, len2);
-	record__write(rec, &pad, padding);
+		record__write(rec, map, data2, len2);
+	record__write(rec, map, &pad, padding);
 
 	return 0;
 }
 
 static int record__auxtrace_mmap_read(struct record *rec,
-				      struct auxtrace_mmap *mm)
+				      struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read(map, rec->itr, &rec->tool,
 				  record__process_auxtrace);
 	if (ret < 0)
 		return ret;
@@ -223,11 +227,11 @@ static int record__auxtrace_mmap_read(struct record *rec,
 }
 
 static int record__auxtrace_mmap_read_snapshot(struct record *rec,
-					       struct auxtrace_mmap *mm)
+					       struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read_snapshot(map, rec->itr, &rec->tool,
 					   record__process_auxtrace,
 					   rec->opts.auxtrace_snapshot_size);
 	if (ret < 0)
@@ -245,13 +249,12 @@ static int record__auxtrace_read_snapshot_all(struct record *rec)
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm =
-				&rec->evlist->mmap[i].auxtrace_mmap;
+		struct perf_mmap *map = &rec->evlist->mmap[i];
 
-		if (!mm->base)
+		if (!map->auxtrace_mmap.base)
 			continue;
 
-		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+		if (record__auxtrace_mmap_read_snapshot(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
@@ -295,7 +298,7 @@ static int record__auxtrace_init(struct record *rec)
 
 static inline
 int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
-			       struct auxtrace_mmap *mm __maybe_unused)
+			       struct perf_mmap *map __maybe_unused)
 {
 	return 0;
 }
@@ -529,17 +532,17 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
+		struct perf_mmap *map = &maps[i];
 
-		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
+		if (map->base) {
+			if (perf_mmap__push(map, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
 		}
 
-		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
-		    record__auxtrace_mmap_read(rec, mm) != 0) {
+		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
+		    record__auxtrace_mmap_read(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
@@ -550,7 +553,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	 * at least one event.
 	 */
 	if (bytes_written != rec->bytes_written)
-		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
+		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
 
 	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e12bcd1765..7507e4d6dce1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -201,14 +201,13 @@ static void setup_forced_leader(struct report *report,
 		perf_evlist__force_leader(evlist);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session __maybe_unused)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
-	struct report *rep = container_of(tool, struct report, tool);
+	struct report *rep = container_of(session->tool, struct report, tool);
 
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 
 	if (event->feat.feat_id != HEADER_LAST_FEATURE) {
 		pr_err("failed: wrong feature ID: %" PRIu64 "\n",
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6176bae177c2..765391b6c88c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2965,9 +2965,8 @@ static void script__setup_sample_type(struct perf_script *script)
 	}
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -2981,9 +2980,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session __maybe_unused)
+static int process_stat_config_event(struct perf_session *session __maybe_unused,
+				     union perf_event *event)
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 	return 0;
@@ -3009,10 +3007,10 @@ static int set_maps(struct perf_script *script)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->threads) {
@@ -3028,10 +3026,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->cpus) {
@@ -3046,21 +3044,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
 #ifdef HAVE_AUXTRACE_SUPPORT
-static int perf_script__process_auxtrace_info(struct perf_tool *tool,
-					      union perf_event *event,
-					      struct perf_session *session)
+static int perf_script__process_auxtrace_info(struct perf_session *session,
+					      union perf_event *event)
 {
-	int ret = perf_event__process_auxtrace_info(tool, event, session);
+	struct perf_tool *tool = session->tool;
+
+	int ret = perf_event__process_auxtrace_info(session, event);
 
 	if (ret == 0) {
 		struct perf_script *script = container_of(tool, struct perf_script, tool);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0b0e3961d511..b86aba1c8028 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1354,9 +1354,8 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *stat_round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -1381,10 +1380,10 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool,
-			      union perf_event *event,
-			      struct perf_session *session __maybe_unused)
+int process_stat_config_event(struct perf_session *session,
+			      union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
@@ -1424,10 +1423,10 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	if (st->threads) {
@@ -1443,10 +1442,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 	struct cpu_map *cpus;
 
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6c108fa79ae3..0b2b8305c965 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -21,6 +21,7 @@ perf-y += python-use.o
 perf-y += bp_signal.o
 perf-y += bp_signal_overflow.o
 perf-y += bp_account.o
+perf-y += wp.o
 perf-y += task-exit.o
 perf-y += sw-clock.o
 perf-y += mmap-thread-lookup.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d7a5e1b9aa6f..54ca7d87236f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -121,6 +121,15 @@ static struct test generic_tests[] = {
 		.is_supported = test__bp_signal_is_supported,
 	},
 	{
+		.desc = "Watchpoint",
+		.func = test__wp,
+		.subtest = {
+			.skip_if_fail	= false,
+			.get_nr		= test__wp_subtest_get_nr,
+			.get_desc	= test__wp_subtest_get_desc,
+		},
+	},
+	{
 		.desc = "Number of exit events of a simple workload",
 		.func = test__task_exit,
 	},
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a9760e790563..8e26a4148f30 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -59,6 +59,9 @@ int test__python_use(struct test *test, int subtest);
 int test__bp_signal(struct test *test, int subtest);
 int test__bp_signal_overflow(struct test *test, int subtest);
 int test__bp_accounting(struct test *test, int subtest);
+int test__wp(struct test *test, int subtest);
+const char *test__wp_subtest_get_desc(int subtest);
+int test__wp_subtest_get_nr(void);
 int test__task_exit(struct test *test, int subtest);
 int test__mem(struct test *test, int subtest);
 int test__sw_clock_freq(struct test *test, int subtest);
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
new file mode 100644
index 000000000000..017a99317f94
--- /dev/null
+++ b/tools/perf/tests/wp.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <linux/hw_breakpoint.h>
+#include "tests.h"
+#include "debug.h"
+#include "cloexec.h"
+
+#define WP_TEST_ASSERT_VAL(fd, text, val)       \
+do {                                            \
+	long long count;                        \
+	wp_read(fd, &count, sizeof(long long)); \
+	TEST_ASSERT_VAL(text, count == val);    \
+} while (0)
+
+volatile u64 data1;
+volatile u8 data2[3];
+
+static int wp_read(int fd, long long *count, int size)
+{
+	int ret = read(fd, count, size);
+
+	if (ret != size) {
+		pr_debug("failed to read: %d\n", ret);
+		return -1;
+	}
+	return 0;
+}
+
+static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
+				 void *wp_addr, unsigned long wp_len)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type           = PERF_TYPE_BREAKPOINT;
+	attr->size           = sizeof(struct perf_event_attr);
+	attr->config         = 0;
+	attr->bp_type        = wp_type;
+	attr->bp_addr        = (unsigned long)wp_addr;
+	attr->bp_len         = wp_len;
+	attr->sample_period  = 1;
+	attr->sample_type    = PERF_SAMPLE_IP;
+	attr->exclude_kernel = 1;
+	attr->exclude_hv     = 1;
+}
+
+static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
+{
+	int fd;
+	struct perf_event_attr attr;
+
+	get__perf_event_attr(&attr, wp_type, wp_addr, wp_len);
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0)
+		pr_debug("failed opening event %x\n", attr.bp_type);
+
+	return fd;
+}
+
+static int wp_ro_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_wo_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 0);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_rw_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R | HW_BREAKPOINT_W, (void *)&data1,
+		     sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_modify_test(void)
+{
+	int fd, ret;
+	unsigned long tmp = rand();
+	struct perf_event_attr new_attr;
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	data1 = tmp;
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Modify watchpoint with disabled = 1 */
+	get__perf_event_attr(&new_attr, HW_BREAKPOINT_W, (void *)&data2[0],
+			     sizeof(u8) * 2);
+	new_attr.disabled = 1;
+	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);
+	if (ret < 0) {
+		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Enable the event */
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0) {
+		pr_debug("Failed to enable event\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	data2[2] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static bool wp_ro_supported(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	return false;
+#else
+	return true;
+#endif
+}
+
+static void wp_ro_skip_msg(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	pr_debug("Hardware does not support read only watchpoints.\n");
+#endif
+}
+
+static struct {
+	const char *desc;
+	int (*target_func)(void);
+	bool (*is_supported)(void);
+	void (*skip_msg)(void);
+} wp_testcase_table[] = {
+	{
+		.desc = "Read Only Watchpoint",
+		.target_func = &wp_ro_test,
+		.is_supported = &wp_ro_supported,
+		.skip_msg = &wp_ro_skip_msg,
+	},
+	{
+		.desc = "Write Only Watchpoint",
+		.target_func = &wp_wo_test,
+	},
+	{
+		.desc = "Read / Write Watchpoint",
+		.target_func = &wp_rw_test,
+	},
+	{
+		.desc = "Modify Watchpoint",
+		.target_func = &wp_modify_test,
+	},
+};
+
+int test__wp_subtest_get_nr(void)
+{
+	return (int)ARRAY_SIZE(wp_testcase_table);
+}
+
+const char *test__wp_subtest_get_desc(int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return NULL;
+	return wp_testcase_table[i].desc;
+}
+
+int test__wp(struct test *test __maybe_unused, int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return TEST_FAIL;
+
+	if (wp_testcase_table[i].is_supported &&
+	    !wp_testcase_table[i].is_supported()) {
+		wp_testcase_table[i].skip_msg();
+		return TEST_SKIP;
+	}
+
+	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
+}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db1511359c5e..c4617bcfd521 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -906,9 +906,8 @@ out_free:
 	return err;
 }
 
-int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event,
-				      struct perf_session *session)
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 
@@ -932,9 +931,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	}
 }
 
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event)
 {
 	s64 err;
 
@@ -950,7 +948,7 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
 		return -EINVAL;
 
-	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	err = session->auxtrace->process_auxtrace_event(session, event, session->tool);
 	if (err < 0)
 		return err;
 
@@ -1185,9 +1183,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
 	}
 }
 
-int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session)
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event)
 {
 	if (auxtrace__dont_decode(session))
 		return 0;
@@ -1196,11 +1193,12 @@ int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+static int __auxtrace_mmap__read(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 bool snapshot, size_t snapshot_size)
 {
+	struct auxtrace_mmap *mm = &map->auxtrace_mmap;
 	u64 head, old = mm->prev, offset, ref;
 	unsigned char *data = mm->base;
 	size_t size, head_off, old_off, len1, len2, padding;
@@ -1287,7 +1285,7 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	ev.auxtrace.tid = mm->tid;
 	ev.auxtrace.cpu = mm->cpu;
 
-	if (fn(tool, &ev, data1, len1, data2, len2))
+	if (fn(tool, map, &ev, data1, len1, data2, len2))
 		return -1;
 
 	mm->prev = head;
@@ -1306,18 +1304,18 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	return 1;
 }
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+	return __auxtrace_mmap__read(map, itr, tool, fn, false, 0);
 }
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+	return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size);
 }
 
 /**
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 71fc3bd74299..a86b7eab6673 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -33,6 +33,7 @@ union perf_event;
 struct perf_session;
 struct perf_evlist;
 struct perf_tool;
+struct perf_mmap;
 struct option;
 struct record_opts;
 struct auxtrace_info_event;
@@ -434,13 +435,14 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   bool per_cpu);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  struct perf_mmap *map,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn);
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
@@ -517,15 +519,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
 					 struct perf_session *session,
 					 perf_event__handler_t process);
-int perf_event__process_auxtrace_info(struct perf_tool *tool,
-				      union perf_event *event,
-				      struct perf_session *session);
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
-int perf_event__process_auxtrace_error(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session);
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event);
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event);
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 47aac41349a2..f9ae1a993806 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1615,7 +1615,7 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
+	return PTR_ERR_OR_ZERO(evsel);
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index abd38abf1d91..f75d4aa612c5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file.path = input,
+		.file      = { .path = input, .fd = -1 },
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 91e6d9cfd906..c78051ad1fcc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3448,10 +3448,10 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 	return ret;
 }
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session __maybe_unused)
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct feat_fd ff = { .fd = 0 };
 	struct feature_event *fe = (struct feature_event *)event;
 	int type = fe->header.type;
@@ -3856,9 +3856,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
 	int fd = perf_data__fd(session->data);
@@ -3924,9 +3923,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event)
 {
 	__event_process_build_id(&event->build_id,
 				 event->build_id.filename,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index ff2a1263fb9b..e17903caa71d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -116,9 +116,8 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool,
 				      perf_event__handler_t process,
 				      bool is_pipe);
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session);
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event);
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
@@ -148,17 +147,15 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_session *session);
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
 				    struct dso *pos, u16 misc,
 				    perf_event__handler_t process,
 				    struct machine *machine);
-int perf_event__process_build_id(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event);
 bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 215f69f41672..cdb95b3a1213 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -281,7 +281,7 @@ int perf_mmap__read_init(struct perf_mmap *map)
 }
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size))
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	unsigned char *data = md->base + page_size;
@@ -300,7 +300,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		size = md->mask + 1 - (md->start & md->mask);
 		md->start += size;
 
-		if (push(to, buf, size) < 0) {
+		if (push(md, to, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -310,7 +310,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	size = md->end - md->start;
 	md->start += size;
 
-	if (push(to, buf, size) < 0) {
+	if (push(md, to, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47c7956..e603314dc792 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -93,7 +93,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size));
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bad9e0296e9a..1904e7f6ec84 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -80,14 +80,20 @@ static union perf_event *dup_event(struct ordered_events *oe,
 	return oe->copy_on_queue ? __dup_event(oe, event) : event;
 }
 
-static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+static void __free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (event && oe->copy_on_queue) {
+	if (event) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
 }
 
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue)
+		__free_dup_event(oe, event);
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
 static struct ordered_event *alloc_event(struct ordered_events *oe,
 					 union perf_event *event)
@@ -95,21 +101,49 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
 	union perf_event *new_event;
+	size_t size;
 
 	new_event = dup_event(oe, event);
 	if (!new_event)
 		return NULL;
 
+	/*
+	 * We maintain the following scheme of buffers for ordered
+	 * event allocation:
+	 *
+	 *   to_free list -> buffer1 (64K)
+	 *                   buffer2 (64K)
+	 *                   ...
+	 *
+	 * Each buffer keeps an array of ordered events objects:
+	 *    buffer -> event[0]
+	 *              event[1]
+	 *              ...
+	 *
+	 * Each allocated ordered event is linked to one of
+	 * following lists:
+	 *   - time ordered list 'events'
+	 *   - list of currently removed events 'cache'
+	 *
+	 * Allocation of the ordered event uses the following order
+	 * to get the memory:
+	 *   - use recently removed object from 'cache' list
+	 *   - use available object in current allocation buffer
+	 *   - allocate new buffer if the current buffer is full
+	 *
+	 * Removal of ordered event object moves it from events to
+	 * the cache list.
+	 */
+	size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new);
+
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
 		list_del(&new->list);
 	} else if (oe->buffer) {
-		new = oe->buffer + oe->buffer_idx;
+		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
-	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
-
+	} else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) {
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
 			free_dup_event(oe, new_event);
@@ -122,11 +156,11 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 		oe->cur_alloc_size += size;
 		list_add(&oe->buffer->list, &oe->to_free);
 
-		/* First entry is abused to maintain the to_free list. */
-		oe->buffer_idx = 2;
-		new = oe->buffer + 1;
+		oe->buffer_idx = 1;
+		new = &oe->buffer->event[0];
 	} else {
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+		return NULL;
 	}
 
 	new->event = new_event;
@@ -300,15 +334,38 @@ void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t d
 	oe->deliver	   = deliver;
 }
 
+static void
+ordered_events_buffer__free(struct ordered_events_buffer *buffer,
+			    unsigned int max, struct ordered_events *oe)
+{
+	if (oe->copy_on_queue) {
+		unsigned int i;
+
+		for (i = 0; i < max; i++)
+			__free_dup_event(oe, buffer->event[i].event);
+	}
+
+	free(buffer);
+}
+
 void ordered_events__free(struct ordered_events *oe)
 {
-	while (!list_empty(&oe->to_free)) {
-		struct ordered_event *event;
+	struct ordered_events_buffer *buffer, *tmp;
 
-		event = list_entry(oe->to_free.next, struct ordered_event, list);
-		list_del(&event->list);
-		free_dup_event(oe, event->event);
-		free(event);
+	if (list_empty(&oe->to_free))
+		return;
+
+	/*
+	 * Current buffer might not have all the events allocated
+	 * yet, we need to free only allocated ones ...
+	 */
+	list_del(&oe->buffer->list);
+	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+
+	/* ... and continue with the rest */
+	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
+		list_del(&buffer->list);
+		ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
 	}
 }
 
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 8c7a2948593e..1338d5c345dc 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -25,23 +25,28 @@ struct ordered_events;
 typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
 					 struct ordered_event *event);
 
+struct ordered_events_buffer {
+	struct list_head	list;
+	struct ordered_event	event[0];
+};
+
 struct ordered_events {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	u64			max_alloc_size;
-	u64			cur_alloc_size;
-	struct list_head	events;
-	struct list_head	cache;
-	struct list_head	to_free;
-	struct ordered_event	*buffer;
-	struct ordered_event	*last;
-	ordered_events__deliver_t deliver;
-	int			buffer_idx;
-	unsigned int		nr_events;
-	enum oe_flush		last_flush_type;
-	u32			nr_unordered_events;
-	bool                    copy_on_queue;
+	u64				 last_flush;
+	u64				 next_flush;
+	u64				 max_timestamp;
+	u64				 max_alloc_size;
+	u64				 cur_alloc_size;
+	struct list_head		 events;
+	struct list_head		 cache;
+	struct list_head		 to_free;
+	struct ordered_events_buffer	*buffer;
+	struct ordered_event		*last;
+	ordered_events__deliver_t	 deliver;
+	int				 buffer_idx;
+	unsigned int			 nr_events;
+	enum oe_flush			 last_flush_type;
+	u32				 nr_unordered_events;
+	bool				 copy_on_queue;
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8b9369303561..7d2c8ce6cfad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -199,12 +199,10 @@ void perf_session__delete(struct perf_session *session)
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+static int process_event_synth_tracing_data_stub(struct perf_session *session
 						 __maybe_unused,
 						 union perf_event *event
-						 __maybe_unused,
-						 struct perf_session *session
-						__maybe_unused)
+						 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -277,10 +275,8 @@ static int skipn(int fd, off_t n)
 	return 0;
 }
 
-static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused,
+				       union perf_event *event)
 {
 	dump_printf(": unhandled!\n");
 	if (perf_data__is_pipe(session->data))
@@ -288,9 +284,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -298,9 +293,8 @@ static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
 
 
 static
-int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_thread_map(event, stdout);
@@ -310,9 +304,8 @@ int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
-			       union perf_event *event __maybe_unused,
-			       struct perf_session *session __maybe_unused)
+int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
+			       union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_cpu_map(event, stdout);
@@ -322,9 +315,8 @@ int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *session __maybe_unused)
+int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_config(event, stdout);
@@ -333,10 +325,8 @@ int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_stub(struct perf_tool *tool __maybe_unused,
-			     union perf_event *event __maybe_unused,
-			     struct perf_session *perf_session
-			     __maybe_unused)
+static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
+			     union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat(event, stdout);
@@ -345,10 +335,8 @@ static int process_stat_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *perf_session
-				   __maybe_unused)
+static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
+				   union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_round(event, stdout);
@@ -1374,37 +1362,37 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(tool, event, session);
+		return tool->tracing_data(session, event);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(tool, event, session);
+		return tool->build_id(session, event);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(tool, event, session);
+		return tool->id_index(session, event);
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(tool, event, session);
+		return tool->auxtrace_info(session, event);
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(tool, event, session);
+		return tool->auxtrace(session, event);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(tool, event, session);
+		return tool->auxtrace_error(session, event);
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(tool, event, session);
+		return tool->thread_map(session, event);
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(tool, event, session);
+		return tool->cpu_map(session, event);
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(tool, event, session);
+		return tool->stat_config(session, event);
 	case PERF_RECORD_STAT:
-		return tool->stat(tool, event, session);
+		return tool->stat(session, event);
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(tool, event, session);
+		return tool->stat_round(session, event);
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(tool, event, session);
+		return tool->time_conv(session, event);
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(tool, event, session);
+		return tool->feature(session, event);
 	default:
 		return -EINVAL;
 	}
@@ -2133,9 +2121,8 @@ out:
 	return err;
 }
 
-int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event)
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct id_index_event *ie = &event->id_index;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da40b4b380ca..d96eccd7d27f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -120,9 +120,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
-int perf_event__process_id_index(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event);
 
 int perf_event__synthesize_id_index(struct perf_tool *tool,
 				    perf_event__handler_t process,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5d3172bcc4ae..4d40515307b8 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -374,9 +374,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	return 0;
 }
 
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event,
-				   struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event)
 {
 	struct perf_counts_values count;
 	struct stat_event *st = &event->stat;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 3a13a6dc5a62..2f9c9159a364 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -199,9 +199,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 struct perf_tool;
 union perf_event;
 struct perf_session;
-int perf_event__process_stat_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct perf_session *session);
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event);
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 183c91453522..56e4ca54020a 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -26,15 +26,12 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist);
 
-typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
+typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
+typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
-typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
-
 enum show_feature_header {
 	SHOW_FEAT_NO_HEADER = 0,
 	SHOW_FEAT_HEADER,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eac5b858a371..093352e93d50 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -221,7 +221,7 @@ out:
 	return err;
 }
 
-static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dc58254a2b69..14508ee7707a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,6 +6,7 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -35,6 +36,7 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);