Merge tag 'perf-core-for-mingo-20160715' 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:

User visible changes:

 - Allow reading from a backward ring buffer (one setup via sys_perf_event_open()
   with perf_event_attr.write_backward = 1) (Wang Nan)

Infrastructure changes:

 - Fix the build on Android NDK r12b (initially just for ARM), that is now port
   of my perf-build container collection and will get tested prior to sending
   patches upstream (Arnaldo Carvalho de Melo)

 - Add correct header for IPv6 definitions

 - Fix bitsperlong.h fallout (Arnaldo Carvalho de Melo, Peter Zijlstra)

 - Use base 0 (auto) in filename__read_ull(), so that we can handle hex values too (Jiri Olsa)

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

22 files changed, 441 insertions, 152 deletions

diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
index cfd661c6fc17..45eca517efb3 100644
--- a/tools/include/asm-generic/bitsperlong.h
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -3,31 +3,12 @@
 
 #include <uapi/asm-generic/bitsperlong.h>
 
-/*
- * In the kernel, where this file comes from, we can rely on CONFIG_64BIT,
- * here we have to make amends with what the various compilers provides us
- * to figure out if we're on a 64-bit machine...
- */
 #ifdef __SIZEOF_LONG__
-# if __SIZEOF_LONG__ == 8
-#  define CONFIG_64BIT
-# endif
+#define BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__)
 #else
-# ifdef __WORDSIZE
-#  if __WORDSIZE == 64
-#   define CONFIG_64BIT
-#  endif
-# else
-#  error Failed to determine BITS_PER_LONG value
-# endif
+#define BITS_PER_LONG __WORDSIZE
 #endif
 
-#ifdef CONFIG_64BIT
-#define BITS_PER_LONG 64
-#else
-#define BITS_PER_LONG 32
-#endif /* CONFIG_64BIT */
-
 #if BITS_PER_LONG != __BITS_PER_LONG
 #error Inconsistent word size. Check asm/bitsperlong.h
 #endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index fa7208a32d76..e33fc1df3935 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -9,6 +9,17 @@
 # define __always_inline	inline __attribute__((always_inline))
 #endif
 
+#ifdef __ANDROID__
+/*
+ * FIXME: Big hammer to get rid of tons of:
+ *   "warning: always_inline function might not be inlinable"
+ *
+ * At least on android-ndk-r12/platforms/android-24/arch-arm
+ */
+#undef __always_inline
+#define __always_inline	inline
+#endif
+
 #define __user
 
 #ifndef __attribute_const__
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
index e87fd800fa8d..71287dddc05f 100644
--- a/tools/lib/api/fd/array.h
+++ b/tools/lib/api/fd/array.h
@@ -22,6 +22,7 @@ struct fdarray {
 	struct pollfd *entries;
 	union {
 		int    idx;
+		void   *ptr;
 	} *priv;
 };
 
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 08556cf2c70d..ba7094b945ff 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -283,6 +283,11 @@ int filename__read_int(const char *filename, int *value)
 	return err;
 }
 
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 0 for base, the strtoull detects the
+ * base automatically (see man strtoull).
+ */
 int filename__read_ull(const char *filename, unsigned long long *value)
 {
 	char line[64];
@@ -292,7 +297,7 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 		return -1;
 
 	if (read(fd, line, sizeof(line)) > 0) {
-		*value = strtoull(line, NULL, 10);
+		*value = strtoull(line, NULL, 0);
 		if (*value != ULLONG_MAX)
 			err = 0;
 	}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3a7bd175f73c..664c90c8e22b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -23,6 +23,7 @@
  *  Frederic Weisbecker gave his permission to relicense the code to
  *  the Lesser General Public License.
  */
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -33,7 +34,7 @@
 #include <limits.h>
 #include <linux/string.h>
 
-#include <netinet/ip6.h>
+#include <netinet/in.h>
 #include "event-parse.h"
 #include "event-utils.h"
 
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 9a3110cac604..1f75b0a046cc 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -26,7 +26,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include
+INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi
 CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 92d84b277032..4ed30f45c6da 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -664,7 +664,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 				  struct symbol *func)
 {
 	struct instruction *insn, *prev_jump;
-	struct rela *text_rela, *rodata_rela, *prev_rela;
+	struct rela *text_rela, *rodata_rela, *prev_rela = NULL;
 	int ret;
 
 	prev_jump = NULL;
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5b46b1d1a37c..69966abf65d1 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -367,6 +367,28 @@ options.
 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj
 in config file is set to true.
 
+--tail-synthesize::
+Instead of collecting non-sample events (for example, fork, comm, mmap) at
+the beginning of record, collect them during finalizing an output file.
+The collected non-sample events reflects the status of the system when
+record is finished.
+
+--overwrite::
+Makes all events use an overwritable ring buffer. An overwritable ring
+buffer works like a flight recorder: when it gets full, the kernel will
+overwrite the oldest records, that thus will never make it to the
+perf.data file.
+
+When '--overwrite' and '--switch-output' are used perf records and drops
+events until it receives a signal, meaning that something unusual was
+detected that warrants taking a snapshot of the most current events,
+those fitting in the ring buffer at that moment.
+
+'overwrite' attribute can also be set or canceled for an event using
+config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'.
+
+Implies --tail-synthesize.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d9f5cc3a3667..8f2c16d9275f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -119,11 +119,10 @@ backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 }
 
 static int
-rb_find_range(struct perf_evlist *evlist,
-	      void *data, int mask, u64 head, u64 old,
-	      u64 *start, u64 *end)
+rb_find_range(void *data, int mask, u64 head, u64 old,
+	      u64 *start, u64 *end, bool backward)
 {
-	if (!evlist->backward) {
+	if (!backward) {
 		*start = old;
 		*end = head;
 		return 0;
@@ -132,9 +131,10 @@ rb_find_range(struct perf_evlist *evlist,
 	return backward_rb_find_range(data, mask, head, start, end);
 }
 
-static int record__mmap_read(struct record *rec, struct perf_evlist *evlist, int idx)
+static int
+record__mmap_read(struct record *rec, struct perf_mmap *md,
+		  bool overwrite, bool backward)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
 	u64 end = head, start = old;
@@ -143,8 +143,8 @@ static int record__mmap_read(struct record *rec, struct perf_evlist *evlist, int
 	void *buf;
 	int rc = 0;
 
-	if (rb_find_range(evlist, data, md->mask, head,
-			  old, &start, &end))
+	if (rb_find_range(data, md->mask, head,
+			  old, &start, &end, backward))
 		return -1;
 
 	if (start == end)
@@ -157,7 +157,7 @@ static int record__mmap_read(struct record *rec, struct perf_evlist *evlist, int
 		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 		md->prev = head;
-		perf_evlist__mmap_consume(evlist, idx);
+		perf_mmap__consume(md, overwrite || backward);
 		return 0;
 	}
 
@@ -182,7 +182,7 @@ static int record__mmap_read(struct record *rec, struct perf_evlist *evlist, int
 	}
 
 	md->prev = head;
-	perf_evlist__mmap_consume(evlist, idx);
+	perf_mmap__consume(md, overwrite || backward);
 out:
 	return rc;
 }
@@ -498,20 +498,30 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist)
+static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
+				    bool backward)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
+	struct perf_mmap *maps;
 
 	if (!evlist)
 		return 0;
 
+	maps = backward ? evlist->backward_mmap : evlist->mmap;
+	if (!maps)
+		return 0;
+
+	if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+		return 0;
+
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm = &evlist->mmap[i].auxtrace_mmap;
+		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
-		if (evlist->mmap[i].base) {
-			if (record__mmap_read(rec, evlist, i) != 0) {
+		if (maps[i].base) {
+			if (record__mmap_read(rec, &maps[i],
+					      evlist->overwrite, backward) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -531,6 +541,8 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
+	if (backward)
+		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
 	return rc;
 }
@@ -539,11 +551,11 @@ static int record__mmap_read_all(struct record *rec)
 {
 	int err;
 
-	err = record__mmap_read_evlist(rec, rec->evlist);
+	err = record__mmap_read_evlist(rec, rec->evlist, false);
 	if (err)
 		return err;
 
-	return err;
+	return record__mmap_read_evlist(rec, rec->evlist, true);
 }
 
 static void record__init_features(struct record *rec)
@@ -592,13 +604,16 @@ record__finish_output(struct record *rec)
 	return;
 }
 
-static int record__synthesize_workload(struct record *rec)
+static int record__synthesize_workload(struct record *rec, bool tail)
 {
 	struct {
 		struct thread_map map;
 		struct thread_map_data map_data;
 	} thread_map;
 
+	if (rec->opts.tail_synthesize != tail)
+		return 0;
+
 	thread_map.map.nr = 1;
 	thread_map.map.map[0].pid = rec->evlist->workload.pid;
 	thread_map.map.map[0].comm = NULL;
@@ -609,7 +624,7 @@ static int record__synthesize_workload(struct record *rec)
 						 rec->opts.proc_map_timeout);
 }
 
-static int record__synthesize(struct record *rec);
+static int record__synthesize(struct record *rec, bool tail);
 
 static int
 record__switch_output(struct record *rec, bool at_exit)
@@ -620,6 +635,10 @@ record__switch_output(struct record *rec, bool at_exit)
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
 
+	record__synthesize(rec, true);
+	if (target__none(&rec->opts.target))
+		record__synthesize_workload(rec, true);
+
 	rec->samples = 0;
 	record__finish_output(rec);
 	err = fetch_current_timestamp(timestamp, sizeof(timestamp));
@@ -642,7 +661,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	/* Output tracking events */
 	if (!at_exit) {
-		record__synthesize(rec);
+		record__synthesize(rec, false);
 
 		/*
 		 * In 'perf record --switch-output' without -a,
@@ -654,7 +673,7 @@ record__switch_output(struct record *rec, bool at_exit)
 		 * perf_event__synthesize_thread_map() for those events.
 		 */
 		if (target__none(&rec->opts.target))
-			record__synthesize_workload(rec);
+			record__synthesize_workload(rec, false);
 	}
 	return fd;
 }
@@ -689,8 +708,12 @@ perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused
 static const struct perf_event_mmap_page *
 perf_evlist__pick_pc(struct perf_evlist *evlist)
 {
-	if (evlist && evlist->mmap && evlist->mmap[0].base)
-		return evlist->mmap[0].base;
+	if (evlist) {
+		if (evlist->mmap && evlist->mmap[0].base)
+			return evlist->mmap[0].base;
+		if (evlist->backward_mmap && evlist->backward_mmap[0].base)
+			return evlist->backward_mmap[0].base;
+	}
 	return NULL;
 }
 
@@ -704,7 +727,7 @@ static const struct perf_event_mmap_page *record__pick_pc(struct record *rec)
 	return NULL;
 }
 
-static int record__synthesize(struct record *rec)
+static int record__synthesize(struct record *rec, bool tail)
 {
 	struct perf_session *session = rec->session;
 	struct machine *machine = &session->machines.host;
@@ -714,6 +737,9 @@ static int record__synthesize(struct record *rec)
 	int fd = perf_data_file__fd(file);
 	int err = 0;
 
+	if (rec->opts.tail_synthesize != tail)
+		return 0;
+
 	if (file->is_pipe) {
 		err = perf_event__synthesize_attrs(tool, session,
 						   process_synthesized_event);
@@ -877,7 +903,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	machine = &session->machines.host;
 
-	err = record__synthesize(rec);
+	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;
 
@@ -937,6 +963,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	for (;;) {
 		unsigned long long hits = rec->samples;
 
+		/*
+		 * rec->evlist->bkw_mmap_state is possible to be
+		 * BKW_MMAP_EMPTY here: when done == true and
+		 * hits != rec->samples in previous round.
+		 *
+		 * perf_evlist__toggle_bkw_mmap ensure we never
+		 * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING.
+		 */
+		if (trigger_is_hit(&switch_output_trigger) || done || draining)
+			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
+
 		if (record__mmap_read_all(rec) < 0) {
 			trigger_error(&auxtrace_snapshot_trigger);
 			trigger_error(&switch_output_trigger);
@@ -956,8 +993,26 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 
 		if (trigger_is_hit(&switch_output_trigger)) {
+			/*
+			 * If switch_output_trigger is hit, the data in
+			 * overwritable ring buffer should have been collected,
+			 * so bkw_mmap_state should be set to BKW_MMAP_EMPTY.
+			 *
+			 * If SIGUSR2 raise after or during record__mmap_read_all(),
+			 * record__mmap_read_all() didn't collect data from
+			 * overwritable ring buffer. Read again.
+			 */
+			if (rec->evlist->bkw_mmap_state == BKW_MMAP_RUNNING)
+				continue;
 			trigger_ready(&switch_output_trigger);
 
+			/*
+			 * Reenable events in overwrite ring buffer after
+			 * record__mmap_read_all(): we should have collected
+			 * data from it.
+			 */
+			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING);
+
 			if (!quiet)
 				fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
 					waking);
@@ -1012,6 +1067,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (!quiet)
 		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
+	if (target__none(&rec->opts.target))
+		record__synthesize_workload(rec, true);
+
 out_child:
 	if (forks) {
 		int exit_status;
@@ -1030,6 +1088,7 @@ out_child:
 	} else
 		status = err;
 
+	record__synthesize(rec, true);
 	/* this will be recalculated during process_buildids() */
 	rec->samples = 0;
 
@@ -1354,6 +1413,9 @@ struct option __record_options[] = {
 	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
 			&record.opts.no_inherit_set,
 			"child tasks do not inherit counters"),
+	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
+		    "synthesize non-sample events at the end of output"),
+	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
 		     "number of mmap data pages and AUX area tracing mmap pages",
@@ -1564,6 +1626,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 	}
 
+	if (record.opts.overwrite)
+		record.opts.tail_synthesize = true;
+
 	if (rec->evlist->nr_entries == 0 &&
 	    perf_evlist__add_default(rec->evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 4b2ff021434c..64c06961bfe4 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -503,7 +503,7 @@ void pthread__unblock_sigwinch(void)
 static void cache_line_size(int *cacheline_sizep)
 {
 	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-		perror("cannot determine cache line size");
+		pr_debug("cannot determine cache line size");
 }
 #endif
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cd8f1b150f9e..a7e0f1497244 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -59,6 +59,8 @@ struct record_opts {
 	bool	     record_switch_events;
 	bool	     all_kernel;
 	bool	     all_user;
+	bool	     tail_synthesize;
+	bool	     overwrite;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index f20ea4c0d0cb..615780cbfe1d 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,8 +31,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 
-		perf_evlist__mmap_read_catchup(evlist, i);
-		while ((event = perf_evlist__mmap_read_backward(evlist, i)) != NULL) {
+		perf_mmap__read_catchup(&evlist->backward_mmap[i]);
+		while ((event = perf_mmap__read_backward(&evlist->backward_mmap[i])) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -108,7 +108,11 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 	}
 
 	bzero(&parse_error, sizeof(parse_error));
-	err = parse_events(evlist, "syscalls:sys_enter_prctl", &parse_error);
+	/*
+	 * Set backward bit, ring buffer should be writing from end. Record
+	 * it in aux evlist
+	 */
+	err = parse_events(evlist, "syscalls:sys_enter_prctl/overwrite/", &parse_error);
 	if (err) {
 		pr_debug("Failed to parse tracepoint event, try use root\n");
 		ret = TEST_SKIP;
@@ -117,10 +121,6 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 
 	perf_evlist__config(evlist, &opts, NULL);
 
-	/* Set backward bit, ring buffer should be writing from end */
-	evlist__for_each_entry(evlist, evsel)
-		evsel->attr.write_backward = 1;
-
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 862e69c2690d..2a40b8e1def7 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -15,6 +15,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
+#include "asm/bug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -27,8 +28,8 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+static void perf_mmap__munmap(struct perf_mmap *map);
+static void perf_mmap__put(struct perf_mmap *map);
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
@@ -44,7 +45,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__set_maps(evlist, cpus, threads);
 	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
-	evlist->backward = false;
+	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -122,6 +123,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 	fdarray__exit(&evlist->pollfd);
 }
 
@@ -465,7 +467,8 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	return 0;
 }
 
-static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx, short revent)
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+				     struct perf_mmap *map, short revent)
 {
 	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
 	/*
@@ -473,7 +476,7 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 	 * close the associated evlist->mmap[] entry.
 	 */
 	if (pos >= 0) {
-		evlist->pollfd.priv[pos].idx = idx;
+		evlist->pollfd.priv[pos].ptr = map;
 
 		fcntl(fd, F_SETFL, O_NONBLOCK);
 	}
@@ -483,15 +486,16 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
 {
-	return __perf_evlist__add_pollfd(evlist, fd, -1, POLLIN);
+	return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN);
 }
 
 static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
 					 void *arg __maybe_unused)
 {
-	struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+	struct perf_mmap *map = fda->priv[fd].ptr;
 
-	perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+	if (map)
+		perf_mmap__put(map);
 }
 
 int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
@@ -688,8 +692,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
 	int i;
 
+	if (!evlist->backward_mmap)
+		return 0;
+
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->mmap[i].fd;
+		int fd = evlist->backward_mmap[i].fd;
 		int err;
 
 		if (fd < 0)
@@ -701,12 +708,12 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 	return 0;
 }
 
-int perf_evlist__pause(struct perf_evlist *evlist)
+static int perf_evlist__pause(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, true);
 }
 
-int perf_evlist__resume(struct perf_evlist *evlist)
+static int perf_evlist__resume(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, false);
 }
@@ -781,9 +788,8 @@ broken_event:
 	return event;
 }
 
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head;
 	u64 old = md->prev;
 
@@ -795,13 +801,12 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
 
 	head = perf_mmap__read_head(md);
 
-	return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+	return perf_mmap__read(md, check_messup, old, head, &md->prev);
 }
 
 union perf_event *
-perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
+perf_mmap__read_backward(struct perf_mmap *md)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head, end;
 	u64 start = md->prev;
 
@@ -836,16 +841,38 @@ perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 	return perf_mmap__read(md, false, start, end, &md->prev);
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
 {
-	if (!evlist->backward)
-		return perf_evlist__mmap_read_forward(evlist, idx);
-	return perf_evlist__mmap_read_backward(evlist, idx);
+	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * Check messup is required for forward overwritable ring buffer:
+	 * memory pointed by md->prev can be overwritten in this case.
+	 * No need for read-write ring buffer: kernel stop outputting when
+	 * it hit md->prev (perf_mmap__consume()).
+	 */
+	return perf_mmap__read_forward(md, evlist->overwrite);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * No need to check messup for backward ring buffer:
+	 * We can always read arbitrary long data from a backward
+	 * ring buffer unless we forget to pause it before reading.
+	 */
+	return perf_mmap__read_backward(md);
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+	return perf_evlist__mmap_read_forward(evlist, idx);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *md)
+{
 	u64 head;
 
 	if (!atomic_read(&md->refcnt))
@@ -855,38 +882,44 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 	md->prev = head;
 }
 
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__read_catchup(&evlist->mmap[idx]);
+}
+
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
 	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
-static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+static void perf_mmap__get(struct perf_mmap *map)
 {
-	atomic_inc(&evlist->mmap[idx].refcnt);
+	atomic_inc(&map->refcnt);
 }
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+static void perf_mmap__put(struct perf_mmap *md)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-
 	BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
 
 	if (atomic_dec_and_test(&md->refcnt))
-		__perf_evlist__munmap(evlist, idx);
+		perf_mmap__munmap(md);
 }
 
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-
-	if (!evlist->overwrite) {
+	if (!overwrite) {
 		u64 old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
 
 	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-		perf_evlist__mmap_put(evlist, idx);
+		perf_mmap__put(md);
+}
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
 int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
@@ -917,44 +950,52 @@ void __weak auxtrace_mmap_params__set_idx(
 {
 }
 
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+static void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (evlist->mmap[idx].base != NULL) {
-		munmap(evlist->mmap[idx].base, evlist->mmap_len);
-		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].fd = -1;
-		atomic_set(&evlist->mmap[idx].refcnt, 0);
+	if (map->base != NULL) {
+		munmap(map->base, perf_mmap__mmap_len(map));
+		map->base = NULL;
+		map->fd = -1;
+		atomic_set(&map->refcnt, 0);
 	}
-	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
+	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-void perf_evlist__munmap(struct perf_evlist *evlist)
+static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;
 
-	if (evlist->mmap == NULL)
-		return;
+	if (evlist->mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->mmap[i]);
 
-	for (i = 0; i < evlist->nr_mmaps; i++)
-		__perf_evlist__munmap(evlist, i);
+	if (evlist->backward_mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->backward_mmap[i]);
+}
 
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+	perf_evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 }
 
-static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	int i;
+	struct perf_mmap *map;
 
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
-	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
-	if (!evlist->mmap)
-		return -ENOMEM;
+	map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	if (!map)
+		return NULL;
 
 	for (i = 0; i < evlist->nr_mmaps; i++)
-		evlist->mmap[i].fd = -1;
-	return 0;
+		map[i].fd = -1;
+	return map;
 }
 
 struct mmap_params {
@@ -963,8 +1004,8 @@ struct mmap_params {
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
-			       struct mmap_params *mp, int fd)
+static int perf_mmap__mmap(struct perf_mmap *map,
+			   struct mmap_params *mp, int fd)
 {
 	/*
 	 * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -979,21 +1020,21 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	atomic_set(&evlist->mmap[idx].refcnt, 2);
-	evlist->mmap[idx].prev = 0;
-	evlist->mmap[idx].mask = mp->mask;
-	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
-				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
+	atomic_set(&map->refcnt, 2);
+	map->prev = 0;
+	map->mask = mp->mask;
+	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+			 MAP_SHARED, fd, 0);
+	if (map->base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
 			  errno);
-		evlist->mmap[idx].base = NULL;
+		map->base = NULL;
 		return -1;
 	}
-	evlist->mmap[idx].fd = fd;
+	map->fd = fd;
 
-	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
-				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+				&mp->auxtrace_mp, map->base, fd))
 		return -1;
 
 	return 0;
@@ -1003,23 +1044,36 @@ static bool
 perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 			 struct perf_evsel *evsel)
 {
-	if (evsel->overwrite)
+	if (evsel->attr.write_backward)
 		return false;
 	return true;
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu,
-				       int thread, int *output)
+				       int thread, int *_output, int *_output_backward)
 {
 	struct perf_evsel *evsel;
 	int revent;
 
 	evlist__for_each_entry(evlist, evsel) {
+		struct perf_mmap *maps = evlist->mmap;
+		int *output = _output;
 		int fd;
 
-		if (evsel->overwrite != (evlist->overwrite && evlist->backward))
-			continue;
+		if (evsel->attr.write_backward) {
+			output = _output_backward;
+			maps = evlist->backward_mmap;
+
+			if (!maps) {
+				maps = perf_evlist__alloc_mmap(evlist);
+				if (!maps)
+					return -1;
+				evlist->backward_mmap = maps;
+				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
+					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+			}
+		}
 
 		if (evsel->system_wide && thread)
 			continue;
@@ -1028,13 +1082,14 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
 		if (*output == -1) {
 			*output = fd;
-			if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
+
+			if (perf_mmap__mmap(&maps[idx], mp, *output)  < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
 
-			perf_evlist__mmap_get(evlist, idx);
+			perf_mmap__get(&maps[idx]);
 		}
 
 		revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0;
@@ -1047,8 +1102,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		 * Therefore don't add it for polling.
 		 */
 		if (!evsel->system_wide &&
-		    __perf_evlist__add_pollfd(evlist, fd, idx, revent) < 0) {
-			perf_evlist__mmap_put(evlist, idx);
+		    __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) {
+			perf_mmap__put(&maps[idx]);
 			return -1;
 		}
 
@@ -1074,13 +1129,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output))
+							thread, &output, &output_backward))
 				goto out_unmap;
 		}
 	}
@@ -1088,8 +1144,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		__perf_evlist__munmap(evlist, cpu);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1102,20 +1157,20 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output))
+						&output, &output_backward))
 			goto out_unmap;
 	}
 
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++)
-		__perf_evlist__munmap(evlist, thread);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1248,7 +1303,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
 	};
 
-	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+	if (!evlist->mmap)
+		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+	if (!evlist->mmap)
 		return -ENOMEM;
 
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
@@ -1919,3 +1976,61 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 
 	return NULL;
 }
+
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
+				  enum bkw_mmap_state state)
+{
+	enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
+	enum action {
+		NONE,
+		PAUSE,
+		RESUME,
+	} action = NONE;
+
+	if (!evlist->backward_mmap)
+		return;
+
+	switch (old_state) {
+	case BKW_MMAP_NOTREADY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;;
+		break;
+	}
+	case BKW_MMAP_RUNNING: {
+		if (state != BKW_MMAP_DATA_PENDING)
+			goto state_err;
+		action = PAUSE;
+		break;
+	}
+	case BKW_MMAP_DATA_PENDING: {
+		if (state != BKW_MMAP_EMPTY)
+			goto state_err;
+		break;
+	}
+	case BKW_MMAP_EMPTY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;
+		action = RESUME;
+		break;
+	}
+	default:
+		WARN_ONCE(1, "Shouldn't get there\n");
+	}
+
+	evlist->bkw_mmap_state = state;
+
+	switch (action) {
+	case PAUSE:
+		perf_evlist__pause(evlist);
+		break;
+	case RESUME:
+		perf_evlist__resume(evlist);
+		break;
+	case NONE:
+	default:
+		break;
+	}
+
+state_err:
+	return;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index afd087761a47..4fd034f22d2f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -35,6 +35,40 @@ struct perf_mmap {
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
+static inline size_t
+perf_mmap__mmap_len(struct perf_mmap *map)
+{
+	return map->mask + 1 + page_size;
+}
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+	BKW_MMAP_NOTREADY,
+	BKW_MMAP_RUNNING,
+	BKW_MMAP_DATA_PENDING,
+	BKW_MMAP_EMPTY,
+};
+
 struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -44,17 +78,18 @@ struct perf_evlist {
 	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
-	bool		 backward;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
 	u64		 combined_sample_type;
+	enum bkw_mmap_state bkw_mmap_state;
 	struct {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
+	struct perf_mmap *backward_mmap;
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
@@ -129,6 +164,14 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
 
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+void perf_mmap__read_catchup(struct perf_mmap *md);
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
@@ -139,8 +182,6 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
-int perf_evlist__pause(struct perf_evlist *evlist);
-int perf_evlist__resume(struct perf_evlist *evlist);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ba0f59fa3d5d..8c54df61fe64 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -695,6 +695,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			 */
 			attr->inherit = term->val.inherit ? 1 : 0;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
+			attr->write_backward = term->val.overwrite ? 1 : 0;
+			break;
 		default:
 			break;
 		}
@@ -776,6 +779,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
+	attr->write_backward = opts->overwrite ? 1 : 0;
 
 	perf_evsel__set_sample_bit(evsel, IP);
 	perf_evsel__set_sample_bit(evsel, TID);
@@ -1377,6 +1381,9 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (perf_missing_features.write_backward && evsel->attr.write_backward)
+		return -EINVAL;
+
 	if (evsel->system_wide)
 		nthreads = 1;
 	else
@@ -1407,11 +1414,6 @@ fallback_missing_features:
 	if (perf_missing_features.lbr_flags)
 		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
-	if (perf_missing_features.write_backward) {
-		if (evsel->overwrite)
-			return -EINVAL;
-		evsel->attr.write_backward = false;
-	}
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1513,7 +1515,7 @@ try_fallback:
 	 */
 	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
 		perf_missing_features.write_backward = true;
-		goto fallback_missing_features;
+		goto out_close;
 	} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
 		perf_missing_features.clockid_wrong = true;
 		goto fallback_missing_features;
@@ -2422,7 +2424,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"We found oprofile daemon running, please stop it and try again.");
 		break;
 	case EINVAL:
-		if (evsel->overwrite && perf_missing_features.write_backward)
+		if (evsel->attr.write_backward && perf_missing_features.write_backward)
 			return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
 		if (perf_missing_features.clockid)
 			return scnprintf(msg, size, "clockid feature not supported.");
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d73391e8740e..8a4a6c9f1480 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -45,6 +45,7 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -59,6 +60,7 @@ struct perf_evsel_config_term {
 		u64	stack_user;
 		int	max_stack;
 		bool	inherit;
+		bool	overwrite;
 	} val;
 };
 
@@ -114,7 +116,6 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
-	bool			overwrite;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 375af0e02831..6c913c3914fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -902,6 +902,8 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
+	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 };
 
 static bool config_term_shrinked;
@@ -994,6 +996,12 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+		CHECK_TYPE_VAL(NUM);
+		break;
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 		CHECK_TYPE_VAL(STR);
 		break;
@@ -1046,6 +1054,8 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1118,6 +1128,12 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1);
+			break;
 		default:
 			break;
 		}
@@ -2412,9 +2428,9 @@ static void config_terms_list(char *buf, size_t buf_sz)
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	/* "branch_type" is the longest name */
+	/* "no-overwrite" is the longest name */
 	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
-			  (sizeof("branch_type") - 1)];
+			  (sizeof("no-overwrite") - 1)];
 
 	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b4aa7eb2df73..d1edbf8cc66a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -69,6 +69,8 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
+	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 3c15b33b2e84..7a2519435da0 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -202,6 +202,8 @@ stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
+overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
+no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 078d49626494..5d61242a6e64 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1499,10 +1499,27 @@ int perf_session__register_idle_thread(struct perf_session *session)
 	return err;
 }
 
+static void
+perf_session__warn_order(const struct perf_session *session)
+{
+	const struct ordered_events *oe = &session->ordered_events;
+	struct perf_evsel *evsel;
+	bool should_warn = true;
+
+	evlist__for_each_entry(session->evlist, evsel) {
+		if (evsel->attr.write_backward)
+			should_warn = false;
+	}
+
+	if (!should_warn)
+		return;
+	if (oe->nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+}
+
 static void perf_session__warn_about_errors(const struct perf_session *session)
 {
 	const struct events_stats *stats = &session->evlist->stats;
-	const struct ordered_events *oe = &session->ordered_events;
 
 	if (session->tool->lost == perf_event__process_lost &&
 	    stats->nr_events[PERF_RECORD_LOST] != 0) {
@@ -1559,8 +1576,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_unprocessable_samples);
 	}
 
-	if (oe->nr_unordered_events != 0)
-		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+	perf_session__warn_order(session);
 
 	events_stats__auxtrace_error_warn(stats);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5854b4660a49..947d21f38398 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2381,6 +2381,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
+		if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+			return -EINVAL;
+
 		if (sd->entry == &sort_mem_daddr_sym)
 			list->sym = 1;
 
@@ -2424,7 +2427,10 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 		if (*tok) {
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
-				error("Invalid --sort key: `%s'", tok);
+				if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+					error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
+				else
+					error("Invalid --sort key: `%s'", tok);
 				break;
 			} else if (ret == -ESRCH) {
 				error("Unknown --sort key: `%s'", tok);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 6178cab82374..843cbba8f9d3 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -360,7 +360,7 @@ void print_binary(unsigned char *data, size_t len,
 		  size_t bytes_per_line, print_binary_t printer,
 		  void *extra);
 
-#ifndef __GLIBC__
+#if !defined(__GLIBC__) && !defined(__ANDROID__)
 extern int sched_getcpu(void);
 #endif