perf kvm: Apply new perf_mmap__read_event() interface

index e7f1b182fc15..1a93debc1e8d 100644
@@ -2472,8 +2472,14 @@ again:
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
+		struct perf_mmap *md;
+		u64 end, start;
 
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			struct perf_sample sample;
 
 			++trace->nr_events;

@@ -2486,7 +2492,7 @@ again:
 
 			trace__handle_event(trace, event, &sample);
 next_event:
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md, false);
 
 			if (interrupted)
 				goto out_disable;

@@ -2496,6 +2502,7 @@ next_event:
 				draining = true;
 			}
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (trace->nr_events == before) {

index 2918cac7a142..35fb5ef7d290 100644
@@ -983,13 +983,19 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
+	struct perf_mmap *md;
+	u64 end, start;
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	event = perf_evlist__mmap_read(evlist, cpu);
+	md = &evlist->mmap[cpu];
+	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		goto end;
+
+	event = perf_mmap__read_event(md, false, &start, end);
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;

@@ -1007,14 +1013,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
-		perf_evlist__mmap_consume(evlist, cpu);
+		perf_mmap__consume(md, false);
 
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
 		return pyevent;
 	}
-
+end:
 	Py_INCREF(Py_None);
 	return Py_None;
 }

index e8399beca62b..09c9c9f9e827 100644
@@ -176,13 +176,20 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
+		struct perf_mmap *md;
+		u64 end, start;
 
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			const u32 type = event->header.type;
 
 			if (type == PERF_RECORD_SAMPLE)
 				count ++;
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (count != expect) {

index c7115d369511..03ed8c77b1bb 100644
@@ -409,15 +409,22 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 			  struct state *state)
 {
 	union perf_event *event;
+	struct perf_mmap *md;
+	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md, false);
 			if (ret < 0)
 				return ret;
 		}
+		perf_mmap__read_done(md);
 	}
 	return 0;
 }

index c46530918938..4590d8fb91ab 100644
@@ -27,18 +27,24 @@
 static int find_comm(struct perf_evlist *evlist, const char *comm)
 {
 	union perf_event *event;
+	struct perf_mmap *md;
+	u64 end, start;
 	int i, found;
 
 	found = 0;
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
 			    (pid_t)event->comm.pid == getpid() &&
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md, false);
 		}
+		perf_mmap__read_done(md);
 	}
 	return found;
 }

index c0e971da965c..44c58d69cd87 100644
@@ -38,6 +38,8 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 	char sbuf[STRERR_BUFSIZE];
+	struct perf_mmap *md;
+	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {

@@ -106,7 +108,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			++foo;
 		}
 
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {

@@ -129,9 +135,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md, false);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	err = 0;
 	evlist__for_each_entry(evlist, evsel) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {

index 43519267b93b..620b21023f72 100644
@@ -86,8 +86,14 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
+			struct perf_mmap *md;
+			u64 end, start;
 
-			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			md = &evlist->mmap[i];
+			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+				continue;
+
+			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 				const u32 type = event->header.type;
 				int tp_flags;
 				struct perf_sample sample;

@@ -95,7 +101,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 				++nr_events;
 
 				if (type != PERF_RECORD_SAMPLE) {
-					perf_evlist__mmap_consume(evlist, i);
+					perf_mmap__consume(md, false);
 					continue;
 				}
 

@@ -115,6 +121,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 				goto out_ok;
 			}
+			perf_mmap__read_done(md);
 		}
 
 		if (nr_events == before)

index 0afafab85238..31f3f70adca6 100644
@@ -164,8 +164,14 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
+			struct perf_mmap *md;
+			u64 end, start;
 
-			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			md = &evlist->mmap[i];
+			if (perf_mmap__read_init(md, false, &start, &end) < 0)
+				continue;
+
+			while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 				const u32 type = event->header.type;
 				const char *name = perf_event__name(type);
 

@@ -266,8 +272,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 					++errs;
 				}
 
-				perf_evlist__mmap_consume(evlist, i);
+				perf_mmap__consume(md, false);
 			}
+			perf_mmap__read_done(md);
 		}
 
 		/*

index 06abe8108b33..7f82d91ef473 100644
@@ -60,6 +60,8 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	union perf_event *event;
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
+	struct perf_mmap *md;
+	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);

@@ -109,7 +111,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	perf_evlist__disable(evlist);
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||

@@ -128,8 +134,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md, false);
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (!comm1_time || !comm2_time)

index f6c72f915d48..e6320e267ba5 100644
@@ -39,6 +39,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	};
 	struct cpu_map *cpus;
 	struct thread_map *threads;
+	struct perf_mmap *md;
+	u64 end, start;
 
 	attr.sample_freq = 500;
 

@@ -93,7 +95,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 	perf_evlist__disable(evlist);
 
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)

@@ -108,9 +114,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		total_periods += sample.period;
 		nr_samples++;
 next_event:
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md, false);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	if ((u64) nr_samples == total_periods) {
 		pr_debug("All (%d) samples have period value of 1!\n",
 			 nr_samples);

index 33e00295a972..10c4dcdc2324 100644
@@ -258,16 +258,23 @@ static int process_events(struct perf_evlist *evlist,
 	unsigned pos, cnt = 0;
 	LIST_HEAD(events);
 	struct event_node *events_array, *node;
+	struct perf_mmap *md;
+	u64 end, start;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
-			perf_evlist__mmap_consume(evlist, i);
+			 perf_mmap__consume(md, false);
 			if (ret < 0)
 				goto out_free_nodes;
 		}
+		perf_mmap__read_done(md);
 	}
 
 	events_array = calloc(cnt, sizeof(struct event_node));

index 01b62b81751b..02b0888b72a3 100644
@@ -47,6 +47,8 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	char sbuf[STRERR_BUFSIZE];
 	struct cpu_map *cpus;
 	struct thread_map *threads;
+	struct perf_mmap *md;
+	u64 end, start;
 
 	signal(SIGCHLD, sig_handler);
 

@@ -110,13 +112,19 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	perf_evlist__start_workload(evlist);
 
 retry:
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md, false);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	if (!exited || !nr_exit) {
 		perf_evlist__poll(evlist, -1);
 		goto retry;

index 7b7d535396f7..41a4666f1519 100644
@@ -702,29 +702,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
 	return perf_evlist__set_paused(evlist, false);
 }
 
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int 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);
-}
-
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
-{
-	return perf_evlist__mmap_read_forward(evlist, idx);
-}
-
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
-{
-	perf_mmap__consume(&evlist->mmap[idx], false);
-}
-
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;

@@ -761,7 +738,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 		map[i].fd = -1;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
-		 * one extra to let perf_evlist__mmap_consume() get the last
+		 * one extra to let perf_mmap__consume() get the last
 		 * events after all real references (perf_mmap__get()) are
 		 * dropped.
 		 *

index 336b838e6957..6c41b2f78713 100644
@@ -129,10 +129,6 @@ 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_evlist__mmap_read(struct perf_evlist *evlist, int idx);
-
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
-						 int idx);
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);

index 91531a7c8fbf..4f27c464ce0b 100644
@@ -63,25 +63,6 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 	return event;
 }
 
-/*
- * legacy interface for mmap read.
- * Don't use it. Use perf_mmap__read_event().
- */
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
-{
-	u64 head;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(map);
-
-	return perf_mmap__read(map, &map->prev, head);
-}
-
 /*
  * Read event from ring buffer one by one.
  * Return one event for each call.

@@ -191,7 +172,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
 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
+	 * The last one will be done at perf_mmap__consume(), so that we
 	 * make sure we don't prevent tools from consuming every last event in
 	 * the ring buffer.
 	 *

index 55d919dc5bc6..d2703d3b8366 100644
@@ -743,16 +743,24 @@ static bool verify_vcpu(int vcpu)
 static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 				   u64 *mmap_time)
 {
+	struct perf_evlist *evlist = kvm->evlist;
 	union perf_event *event;
+	struct perf_mmap *md;
+	u64 end, start;
 	u64 timestamp;
 	s64 n = 0;
 	int err;
 
 	*mmap_time = ULLONG_MAX;
-	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
-		err = perf_evlist__parse_sample_timestamp(kvm->evlist, event, &timestamp);
+	md = &evlist->mmap[idx];
+	err = perf_mmap__read_init(md, false, &start, &end);
+	if (err < 0)
+		return (err == -EAGAIN) ? 0 : -1;
+
+	while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
-			perf_evlist__mmap_consume(kvm->evlist, idx);
+			perf_mmap__consume(md, false);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}

@@ -762,7 +770,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 		 * FIXME: Here we can't consume the event, as perf_session__queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
 		 */
-		perf_evlist__mmap_consume(kvm->evlist, idx);
+		perf_mmap__consume(md, false);
 
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);

@@ -779,6 +787,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			break;
 	}
 
+	perf_mmap__read_done(md);
 	return n;
 }