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

4 files changed, 419 insertions, 0 deletions

diff --git a/samples/cgroup/.gitignore b/samples/cgroup/.gitignore
new file mode 100644
index 000000000..3a0161194
--- /dev/null
+++ b/samples/cgroup/.gitignore
@@ -0,0 +1,3 @@
+/cgroup_event_listener
+/memcg_event_listener
+
diff --git a/samples/cgroup/Makefile b/samples/cgroup/Makefile
new file mode 100644
index 000000000..526c85697
--- /dev/null
+++ b/samples/cgroup/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+userprogs-always-y += cgroup_event_listener memcg_event_listener
+
+userccflags += -I usr/include
diff --git a/samples/cgroup/cgroup_event_listener.c b/samples/cgroup/cgroup_event_listener.c
new file mode 100644
index 000000000..3d70dc831
--- /dev/null
+++ b/samples/cgroup/cgroup_event_listener.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>"
+
+int main(int argc, char **argv)
+{
+	int efd = -1;
+	int cfd = -1;
+	int event_control = -1;
+	char event_control_path[PATH_MAX];
+	char line[LINE_MAX];
+	int ret;
+
+	if (argc != 3)
+		errx(1, "%s", USAGE_STR);
+
+	cfd = open(argv[1], O_RDONLY);
+	if (cfd == -1)
+		err(1, "Cannot open %s", argv[1]);
+
+	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+			dirname(argv[1]));
+	if (ret >= PATH_MAX)
+		errx(1, "Path to cgroup.event_control is too long");
+
+	event_control = open(event_control_path, O_WRONLY);
+	if (event_control == -1)
+		err(1, "Cannot open %s", event_control_path);
+
+	efd = eventfd(0, 0);
+	if (efd == -1)
+		err(1, "eventfd() failed");
+
+	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+	if (ret >= LINE_MAX)
+		errx(1, "Arguments string is too long");
+
+	ret = write(event_control, line, strlen(line) + 1);
+	if (ret == -1)
+		err(1, "Cannot write to cgroup.event_control");
+
+	while (1) {
+		uint64_t result;
+
+		ret = read(efd, &result, sizeof(result));
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+			err(1, "Cannot read from eventfd");
+		}
+		assert(ret == sizeof(result));
+
+		ret = access(event_control_path, W_OK);
+		if ((ret == -1) && (errno == ENOENT)) {
+			puts("The cgroup seems to have removed.");
+			break;
+		}
+
+		if (ret == -1)
+			err(1, "cgroup.event_control is not accessible any more");
+
+		printf("%s %s: crossed\n", argv[1], argv[2]);
+	}
+
+	return 0;
+}
diff --git a/samples/cgroup/memcg_event_listener.c b/samples/cgroup/memcg_event_listener.c
new file mode 100644
index 000000000..41425edbd
--- /dev/null
+++ b/samples/cgroup/memcg_event_listener.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * memcg_event_listener.c - Simple listener of memcg memory.events
+ *
+ * Copyright (c) 2023, SaluteDevices. All Rights Reserved.
+ *
+ * Author: Dmitry Rokosov <ddrokosov@salutedevices.com>
+ */
+
+#include <err.h>
+#include <errno.h>
+#include <limits.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/inotify.h>
+#include <unistd.h>
+
+/* Size of buffer to use when reading inotify events */
+#define INOTIFY_BUFFER_SIZE 8192
+
+#define INOTIFY_EVENT_NEXT(event, length) ({         \
+	(length) -= sizeof(*(event)) + (event)->len; \
+	(event)++;                                   \
+})
+
+#define INOTIFY_EVENT_OK(event, length) ((length) >= (ssize_t)sizeof(*(event)))
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+
+struct memcg_counters {
+	long low;
+	long high;
+	long max;
+	long oom;
+	long oom_kill;
+	long oom_group_kill;
+};
+
+struct memcg_events {
+	struct memcg_counters counters;
+	char path[PATH_MAX];
+	int inotify_fd;
+	int inotify_wd;
+};
+
+static void print_memcg_counters(const struct memcg_counters *counters)
+{
+	printf("MEMCG events:\n");
+	printf("\tlow: %ld\n", counters->low);
+	printf("\thigh: %ld\n", counters->high);
+	printf("\tmax: %ld\n", counters->max);
+	printf("\toom: %ld\n", counters->oom);
+	printf("\toom_kill: %ld\n", counters->oom_kill);
+	printf("\toom_group_kill: %ld\n", counters->oom_group_kill);
+}
+
+static int get_memcg_counter(char *line, const char *name, long *counter)
+{
+	size_t len = strlen(name);
+	char *endptr;
+	long tmp;
+
+	if (memcmp(line, name, len)) {
+		warnx("Counter line %s has wrong name, %s is expected",
+		      line, name);
+		return -EINVAL;
+	}
+
+	/* skip the whitespace delimiter */
+	len += 1;
+
+	errno = 0;
+	tmp = strtol(&line[len], &endptr, 10);
+	if (((tmp == LONG_MAX || tmp == LONG_MIN) && errno == ERANGE) ||
+	    (errno && !tmp)) {
+		warnx("Failed to parse: %s", &line[len]);
+		return -ERANGE;
+	}
+
+	if (endptr == &line[len]) {
+		warnx("Not digits were found in line %s", &line[len]);
+		return -EINVAL;
+	}
+
+	if (!(*endptr == '\0' || (*endptr == '\n' && *++endptr == '\0'))) {
+		warnx("Further characters after number: %s", endptr);
+		return -EINVAL;
+	}
+
+	*counter = tmp;
+
+	return 0;
+}
+
+static int read_memcg_events(struct memcg_events *events, bool show_diff)
+{
+	FILE *fp = fopen(events->path, "re");
+	size_t i;
+	int ret = 0;
+	bool any_new_events = false;
+	char *line = NULL;
+	size_t len = 0;
+	struct memcg_counters new_counters;
+	struct memcg_counters *counters = &events->counters;
+	struct {
+		const char *name;
+		long *new;
+		long *old;
+	} map[] = {
+		{
+			.name = "low",
+			.new = &new_counters.low,
+			.old = &counters->low,
+		},
+		{
+			.name = "high",
+			.new = &new_counters.high,
+			.old = &counters->high,
+		},
+		{
+			.name = "max",
+			.new = &new_counters.max,
+			.old = &counters->max,
+		},
+		{
+			.name = "oom",
+			.new = &new_counters.oom,
+			.old = &counters->oom,
+		},
+		{
+			.name = "oom_kill",
+			.new = &new_counters.oom_kill,
+			.old = &counters->oom_kill,
+		},
+		{
+			.name = "oom_group_kill",
+			.new = &new_counters.oom_group_kill,
+			.old = &counters->oom_group_kill,
+		},
+	};
+
+	if (!fp) {
+		warn("Failed to open memcg events file %s", events->path);
+		return -EBADF;
+	}
+
+	/* Read new values for memcg counters */
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		ssize_t nread;
+
+		errno = 0;
+		nread = getline(&line, &len, fp);
+		if (nread == -1) {
+			if (errno) {
+				warn("Failed to read line for counter %s",
+				     map[i].name);
+				ret = -EIO;
+				goto exit;
+			}
+
+			break;
+		}
+
+		ret = get_memcg_counter(line, map[i].name, map[i].new);
+		if (ret) {
+			warnx("Failed to get counter value from line %s", line);
+			goto exit;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		long diff;
+
+		if (*map[i].new > *map[i].old) {
+			diff = *map[i].new - *map[i].old;
+
+			if (show_diff)
+				printf("*** %ld MEMCG %s event%s, "
+				       "change counter %ld => %ld\n",
+				       diff, map[i].name,
+				       (diff == 1) ? "" : "s",
+				       *map[i].old, *map[i].new);
+
+			*map[i].old += diff;
+			any_new_events = true;
+		}
+	}
+
+	if (show_diff && !any_new_events)
+		printf("*** No new untracked memcg events available\n");
+
+exit:
+	free(line);
+	fclose(fp);
+
+	return ret;
+}
+
+static void process_memcg_events(struct memcg_events *events,
+				 struct inotify_event *event)
+{
+	int ret;
+
+	if (events->inotify_wd != event->wd) {
+		warnx("Unknown inotify event %d, should be %d", event->wd,
+		      events->inotify_wd);
+		return;
+	}
+
+	printf("Received event in %s:\n", events->path);
+
+	if (!(event->mask & IN_MODIFY)) {
+		warnx("No IN_MODIFY event, skip it");
+		return;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */true);
+	if (ret)
+		warnx("Can't read memcg events");
+}
+
+static void monitor_events(struct memcg_events *events)
+{
+	struct pollfd fds[1];
+	int ret;
+
+	printf("Started monitoring memory events from '%s'...\n", events->path);
+
+	fds[0].fd = events->inotify_fd;
+	fds[0].events = POLLIN;
+
+	for (;;) {
+		ret = poll(fds, ARRAY_SIZE(fds), -1);
+		if (ret < 0 && errno != EAGAIN)
+			err(EXIT_FAILURE, "Can't poll memcg events (%d)", ret);
+
+		if (fds[0].revents & POLLERR)
+			err(EXIT_FAILURE, "Got POLLERR during monitor events");
+
+		if (fds[0].revents & POLLIN) {
+			struct inotify_event *event;
+			char buffer[INOTIFY_BUFFER_SIZE];
+			ssize_t length;
+
+			length = read(fds[0].fd, buffer, INOTIFY_BUFFER_SIZE);
+			if (length <= 0)
+				continue;
+
+			event = (struct inotify_event *)buffer;
+			while (INOTIFY_EVENT_OK(event, length)) {
+				process_memcg_events(events, event);
+				event = INOTIFY_EVENT_NEXT(event, length);
+			}
+		}
+	}
+}
+
+static int initialize_memcg_events(struct memcg_events *events,
+				   const char *cgroup)
+{
+	int ret;
+
+	memset(events, 0, sizeof(struct memcg_events));
+
+	ret = snprintf(events->path, PATH_MAX,
+		       "/sys/fs/cgroup/%s/memory.events", cgroup);
+	if (ret >= PATH_MAX) {
+		warnx("Path to cgroup memory.events is too long");
+		return -EMSGSIZE;
+	} else if (ret < 0) {
+		warn("Can't generate cgroup event full name");
+		return ret;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */false);
+	if (ret) {
+		warnx("Failed to read initial memcg events state (%d)", ret);
+		return ret;
+	}
+
+	events->inotify_fd = inotify_init();
+	if (events->inotify_fd < 0) {
+		warn("Failed to setup new inotify device");
+		return -EMFILE;
+	}
+
+	events->inotify_wd = inotify_add_watch(events->inotify_fd,
+					       events->path, IN_MODIFY);
+	if (events->inotify_wd < 0) {
+		warn("Couldn't add monitor in dir %s", events->path);
+		return -EIO;
+	}
+
+	printf("Initialized MEMCG events with counters:\n");
+	print_memcg_counters(&events->counters);
+
+	return 0;
+}
+
+static void cleanup_memcg_events(struct memcg_events *events)
+{
+	inotify_rm_watch(events->inotify_fd, events->inotify_wd);
+	close(events->inotify_fd);
+}
+
+int main(int argc, const char **argv)
+{
+	struct memcg_events events;
+	ssize_t ret;
+
+	if (argc != 2)
+		errx(EXIT_FAILURE, "Usage: %s <cgroup>", argv[0]);
+
+	ret = initialize_memcg_events(&events, argv[1]);
+	if (ret)
+		errx(EXIT_FAILURE, "Can't initialize memcg events (%zd)", ret);
+
+	monitor_events(&events);
+
+	cleanup_memcg_events(&events);
+
+	printf("Exiting memcg event listener...\n");
+
+	return EXIT_SUCCESS;
+}