Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 598 insertions, 0 deletions

diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 000000000..73568c782
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <errno.h>
+#include <limits.h>
+#include <time.h>
+#include <stdlib.h>
+#include <linux/zalloc.h>
+#include <linux/err.h>
+#include <perf/cpumap.h>
+#include <perf/evlist.h>
+#include <perf/mmap.h>
+
+#include "debug.h"
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "record.h"
+#include "tests.h"
+#include "util/mmap.h"
+#include "util/sample.h"
+#include "pmus.h"
+
+static int spin_sleep(void)
+{
+	struct timeval start, now, diff, maxtime;
+	struct timespec ts;
+	int err, i;
+
+	maxtime.tv_sec = 0;
+	maxtime.tv_usec = 50000;
+
+	err = gettimeofday(&start, NULL);
+	if (err)
+		return err;
+
+	/* Spin for 50ms */
+	while (1) {
+		for (i = 0; i < 1000; i++)
+			barrier();
+
+		err = gettimeofday(&now, NULL);
+		if (err)
+			return err;
+
+		timersub(&now, &start, &diff);
+		if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+			break;
+	}
+
+	ts.tv_nsec = 50 * 1000 * 1000;
+	ts.tv_sec = 0;
+
+	/* Sleep for 50ms */
+	err = nanosleep(&ts, NULL);
+	if (err == EINTR)
+		err = 0;
+
+	return err;
+}
+
+struct switch_tracking {
+	struct evsel *switch_evsel;
+	struct evsel *cycles_evsel;
+	pid_t *tids;
+	int nr_tids;
+	int comm_seen[4];
+	int cycles_before_comm_1;
+	int cycles_between_comm_2_and_comm_3;
+	int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+		      union perf_event *event, const char *comm, int nr)
+{
+	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) {
+		if (switch_tracking->comm_seen[nr]) {
+			pr_debug("Duplicate comm event\n");
+			return -1;
+		}
+		switch_tracking->comm_seen[nr] = 1;
+		pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+		return 1;
+	}
+	return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+	int i, nr = cpu + 1;
+
+	if (cpu < 0)
+		return -1;
+
+	if (!switch_tracking->tids) {
+		switch_tracking->tids = calloc(nr, sizeof(pid_t));
+		if (!switch_tracking->tids)
+			return -1;
+		for (i = 0; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	if (cpu >= switch_tracking->nr_tids) {
+		void *addr;
+
+		addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+		if (!addr)
+			return -1;
+		switch_tracking->tids = addr;
+		for (i = switch_tracking->nr_tids; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int process_sample_event(struct evlist *evlist,
+				union perf_event *event,
+				struct switch_tracking *switch_tracking)
+{
+	struct perf_sample sample;
+	struct evsel *evsel;
+	pid_t next_tid, prev_tid;
+	int cpu, err;
+
+	perf_sample__init(&sample, /*all=*/false);
+	if (evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
+		err = -1;
+		goto out;
+	}
+
+	evsel = sample.evsel;
+	if (!evsel)
+		evsel = evlist__id2evsel(evlist, sample.id);
+
+	if (evsel == switch_tracking->switch_evsel) {
+		next_tid = perf_sample__intval(&sample, "next_pid");
+		prev_tid = perf_sample__intval(&sample, "prev_pid");
+		cpu = sample.cpu;
+		pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+			  cpu, prev_tid, next_tid);
+		err = check_cpu(switch_tracking, cpu);
+		if (err)
+			goto out;
+		/*
+		 * Check for no missing sched_switch events i.e. that the
+		 * evsel->core.system_wide flag has worked.
+		 */
+		if (switch_tracking->tids[cpu] != -1 &&
+		    switch_tracking->tids[cpu] != prev_tid) {
+			pr_debug("Missing sched_switch events\n");
+			err = -1;
+			goto out;
+		}
+		switch_tracking->tids[cpu] = next_tid;
+	}
+
+	if (evsel == switch_tracking->cycles_evsel) {
+		pr_debug3("cycles event\n");
+		if (!switch_tracking->comm_seen[0])
+			switch_tracking->cycles_before_comm_1 = 1;
+		if (switch_tracking->comm_seen[1] &&
+		    !switch_tracking->comm_seen[2])
+			switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+		if (switch_tracking->comm_seen[3])
+			switch_tracking->cycles_after_comm_4 = 1;
+	}
+
+	err = 0;
+out:
+	perf_sample__exit(&sample);
+	return err;
+}
+
+static int process_event(struct evlist *evlist, union perf_event *event,
+			 struct switch_tracking *switch_tracking)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(evlist, event, switch_tracking);
+
+	if (event->header.type == PERF_RECORD_COMM) {
+		int err, done = 0;
+
+		err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+		if (err < 0)
+			return -1;
+		done += err;
+		if (done != 1) {
+			pr_debug("Unexpected comm event\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+struct event_node {
+	struct list_head list;
+	union perf_event *event;
+	u64 event_time;
+};
+
+static int add_event(struct evlist *evlist, struct list_head *events,
+		     union perf_event *event)
+{
+	struct perf_sample sample;
+	struct event_node *node;
+
+	node = malloc(sizeof(struct event_node));
+	if (!node) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+	node->event = event;
+	list_add(&node->list, events);
+
+	if (evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
+		perf_sample__exit(&sample);
+		return -1;
+	}
+
+	if (!sample.time) {
+		pr_debug("event with no time\n");
+		perf_sample__exit(&sample);
+		return -1;
+	}
+
+	node->event_time = sample.time;
+
+	perf_sample__exit(&sample);
+	return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+	struct event_node *node;
+
+	while (!list_empty(events)) {
+		node = list_entry(events->next, struct event_node, list);
+		list_del_init(&node->list);
+		free(node);
+	}
+}
+
+static int compar(const void *a, const void *b)
+{
+	const struct event_node *nodea = a;
+	const struct event_node *nodeb = b;
+	s64 cmp = nodea->event_time - nodeb->event_time;
+
+	return cmp < 0 ? -1 : (cmp > 0 ? 1 : 0);
+}
+
+static int process_events(struct evlist *evlist,
+			  struct switch_tracking *switch_tracking)
+{
+	union perf_event *event;
+	unsigned pos, cnt = 0;
+	LIST_HEAD(events);
+	struct event_node *events_array, *node;
+	struct mmap *md;
+	int i, ret;
+
+	for (i = 0; i < evlist__core(evlist)->nr_mmaps; i++) {
+		md = &evlist__mmap(evlist)[i];
+		if (perf_mmap__read_init(&md->core) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
+			cnt += 1;
+			ret = add_event(evlist, &events, event);
+			 perf_mmap__consume(&md->core);
+			if (ret < 0)
+				goto out_free_nodes;
+		}
+		perf_mmap__read_done(&md->core);
+	}
+
+	events_array = calloc(cnt, sizeof(struct event_node));
+	if (!events_array) {
+		pr_debug("calloc failed\n");
+		ret = -1;
+		goto out_free_nodes;
+	}
+
+	pos = 0;
+	list_for_each_entry(node, &events, list)
+		events_array[pos++] = *node;
+
+	qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+	for (pos = 0; pos < cnt; pos++) {
+		ret = process_event(evlist, events_array[pos].event,
+				    switch_tracking);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	pr_debug("%u events recorded\n", cnt);
+	free(events_array);
+out_free_nodes:
+	free_event_nodes(&events);
+	return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->core.system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	const char *sched_switch = "sched:sched_switch";
+	const char *cycles = "cpu-cycles:u";
+	struct switch_tracking switch_tracking = { .tids = NULL, };
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct perf_thread_map *threads = NULL;
+	struct perf_cpu_map *cpus = NULL;
+	struct evlist *evlist = NULL;
+	struct evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+	struct evsel *switch_evsel, *tracking_evsel;
+	const char *comm;
+	int err = -1;
+
+	threads = thread_map__new_by_tid(getpid());
+	if (!threads) {
+		pr_debug("thread_map__new failed!\n");
+		goto out_err;
+	}
+
+	cpus = perf_cpu_map__new_online_cpus();
+	if (!cpus) {
+		pr_debug("perf_cpu_map__new failed!\n");
+		goto out_err;
+	}
+
+	evlist = evlist__new();
+	if (!evlist) {
+		pr_debug("evlist__new failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__set_maps(evlist__core(evlist), cpus, threads);
+
+	/* First event */
+	err = parse_event(evlist, "cpu-clock:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	cpu_clocks_evsel = evlist__last(evlist);
+
+	/* Second event */
+	err = parse_event(evlist, cycles);
+	if (err) {
+		pr_debug("Failed to parse event %s\n", cycles);
+		goto out_err;
+	}
+
+	cycles_evsel = evlist__last(evlist);
+
+	/* Third event */
+	if (!evlist__can_select_event(evlist, sched_switch)) {
+		pr_debug("No sched_switch\n");
+		err = 0;
+		goto out;
+	}
+
+	switch_evsel = evlist__add_sched_switch(evlist, true);
+	if (IS_ERR(switch_evsel)) {
+		err = PTR_ERR(switch_evsel);
+		pr_debug("Failed to create event %s\n", sched_switch);
+		goto out_err;
+	}
+
+	switch_evsel->immediate = true;
+
+	/* Test moving an event to the front */
+	if (cycles_evsel == evlist__first(evlist)) {
+		pr_debug("cycles event already at front");
+		goto out_err;
+	}
+	evlist__to_front(evlist, cycles_evsel);
+	if (cycles_evsel != evlist__first(evlist)) {
+		pr_debug("Failed to move cycles event to front");
+		goto out_err;
+	}
+
+	evsel__set_sample_bit(cycles_evsel, CPU);
+	evsel__set_sample_bit(cycles_evsel, TIME);
+
+	/* Fourth event */
+	err = parse_event(evlist, "dummy:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	tracking_evsel = evlist__last(evlist);
+
+	evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->core.attr.freq = 0;
+	tracking_evsel->core.attr.sample_period = 1;
+
+	evsel__set_sample_bit(tracking_evsel, TIME);
+
+	/* Config events */
+	evlist__config(evlist, &opts, NULL);
+
+	/* Check moved event is still at the front */
+	if (cycles_evsel != evlist__first(evlist)) {
+		pr_debug("Front event no longer at front");
+		goto out_err;
+	}
+
+	/* Check tracking event is tracking */
+	if (!tracking_evsel->core.attr.mmap || !tracking_evsel->core.attr.comm) {
+		pr_debug("Tracking event not tracking\n");
+		goto out_err;
+	}
+
+	/* Check non-tracking events are not tracking */
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel != tracking_evsel) {
+			if (evsel->core.attr.mmap || evsel->core.attr.comm) {
+				pr_debug("Non-tracking event is tracking\n");
+				goto out_err;
+			}
+		}
+	}
+
+	if (evlist__open(evlist) < 0) {
+		pr_debug("Not supported\n");
+		err = 0;
+		goto out;
+	}
+
+	err = evlist__do_mmap(evlist, UINT_MAX);
+	if (err) {
+		pr_debug("evlist__mmap failed!\n");
+		goto out_err;
+	}
+
+	evlist__enable(evlist);
+
+	err = evsel__disable(cpu_clocks_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 1";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = evsel__disable(cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 2";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 3";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = evsel__enable(cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 4";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	evlist__disable(evlist);
+
+	switch_tracking.switch_evsel = switch_evsel;
+	switch_tracking.cycles_evsel = cycles_evsel;
+
+	err = process_events(evlist, &switch_tracking);
+
+	zfree(&switch_tracking.tids);
+
+	if (err)
+		goto out_err;
+
+	/* Check all 4 comm events were seen i.e. that evsel->tracking works */
+	if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+	    !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+		pr_debug("Missing comm events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled */
+	if (!switch_tracking.cycles_before_comm_1) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got disabled */
+	if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+		pr_debug("cycles events even though event was disabled\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled again */
+	if (!switch_tracking.cycles_after_comm_4) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+out:
+	if (evlist) {
+		evlist__disable(evlist);
+		evlist__put(evlist);
+	}
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
+
+	return err;
+
+out_err:
+	err = -1;
+	goto out;
+}
+
+DEFINE_SUITE_EXCLUSIVE("Track with sched_switch", switch_tracking);