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, 646 insertions, 0 deletions

diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
new file mode 100644
index 000000000..c7be16a79
--- /dev/null
+++ b/tools/perf/util/cgroup.c
@@ -0,0 +1,646 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <subcmd/parse-options.h>
+#include "evsel.h"
+#include "cgroup.h"
+#include "evlist.h"
+#include "rblist.h"
+#include "metricgroup.h"
+#include "stat.h"
+#include <linux/zalloc.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/statfs.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
+#include <api/fs/fs.h>
+#include <ftw.h>
+#include <regex.h>
+
+int nr_cgroups;
+bool cgrp_event_expanded;
+
+/* used to match cgroup name with patterns */
+struct cgroup_name {
+	struct list_head list;
+	bool used;
+	char name[];
+};
+static LIST_HEAD(cgroup_list);
+
+static int open_cgroup(const char *name)
+{
+	char path[PATH_MAX + 1];
+	char mnt[PATH_MAX + 1];
+	int fd;
+
+
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
+		return -1;
+
+	scnprintf(path, PATH_MAX, "%s/%s", mnt, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		fprintf(stderr, "no access to cgroup %s\n", path);
+
+	return fd;
+}
+
+#ifdef HAVE_FILE_HANDLE
+static u64 __read_cgroup_id(const char *path)
+{
+	struct {
+		struct file_handle fh;
+		uint64_t cgroup_id;
+	} handle;
+	int mount_id;
+
+	handle.fh.handle_bytes = sizeof(handle.cgroup_id);
+	if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0)
+		return -1ULL;
+
+	return handle.cgroup_id;
+}
+
+int read_cgroup_id(struct cgroup *cgrp)
+{
+	char path[PATH_MAX + 1];
+	char mnt[PATH_MAX + 1];
+
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
+		return -1;
+
+	scnprintf(path, PATH_MAX, "%s/%s", mnt, cgrp->name);
+
+	cgrp->id = __read_cgroup_id(path);
+	return 0;
+}
+#else
+static inline u64 __read_cgroup_id(const char *path __maybe_unused) { return -1ULL; }
+#endif  /* HAVE_FILE_HANDLE */
+
+#ifndef CGROUP2_SUPER_MAGIC
+#define CGROUP2_SUPER_MAGIC  0x63677270
+#endif
+
+int cgroup_is_v2(const char *subsys)
+{
+	char mnt[PATH_MAX + 1];
+	struct statfs stbuf;
+
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, subsys))
+		return -1;
+
+	if (statfs(mnt, &stbuf) < 0)
+		return -1;
+
+	return (stbuf.f_type == CGROUP2_SUPER_MAGIC);
+}
+
+static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str)
+{
+	struct evsel *counter;
+	/*
+	 * check if cgrp is already defined, if so we reuse it
+	 */
+	evlist__for_each_entry(evlist, counter) {
+		if (!counter->cgrp)
+			continue;
+		if (!strcmp(counter->cgrp->name, str))
+			return cgroup__get(counter->cgrp);
+	}
+
+	return NULL;
+}
+
+struct cgroup *cgroup__new(const char *name, bool do_open)
+{
+	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
+
+	if (cgroup != NULL) {
+		refcount_set(&cgroup->refcnt, 1);
+
+		cgroup->name = strdup(name);
+		if (!cgroup->name)
+			goto out_err;
+
+		if (do_open) {
+			cgroup->fd = open_cgroup(name);
+			if (cgroup->fd == -1)
+				goto out_free_name;
+		} else {
+			cgroup->fd = -1;
+		}
+	}
+
+	return cgroup;
+
+out_free_name:
+	zfree(&cgroup->name);
+out_err:
+	free(cgroup);
+	return NULL;
+}
+
+struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name)
+{
+	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
+
+	return cgroup ?: cgroup__new(name, true);
+}
+
+static int add_cgroup(struct evlist *evlist, const char *str)
+{
+	struct evsel *counter;
+	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
+	int n;
+
+	if (!cgrp)
+		return -1;
+	/*
+	 * find corresponding event
+	 * if add cgroup N, then need to find event N
+	 */
+	n = 0;
+	evlist__for_each_entry(evlist, counter) {
+		if (n == nr_cgroups)
+			goto found;
+		n++;
+	}
+
+	cgroup__put(cgrp);
+	return -1;
+found:
+	counter->cgrp = cgrp;
+	return 0;
+}
+
+static void cgroup__delete(struct cgroup *cgroup)
+{
+	if (cgroup->fd >= 0)
+		close(cgroup->fd);
+	zfree(&cgroup->name);
+	free(cgroup);
+}
+
+void cgroup__put(struct cgroup *cgrp)
+{
+	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
+		cgroup__delete(cgrp);
+	}
+}
+
+struct cgroup *cgroup__get(struct cgroup *cgroup)
+{
+       if (cgroup)
+		refcount_inc(&cgroup->refcnt);
+       return cgroup;
+}
+
+static void evsel__set_default_cgroup(struct evsel *evsel, struct cgroup *cgroup)
+{
+	if (evsel->cgrp == NULL)
+		evsel->cgrp = cgroup__get(cgroup);
+}
+
+void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		evsel__set_default_cgroup(evsel, cgroup);
+}
+
+/* helper function for ftw() in match_cgroups and list_cgroups */
+static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unused,
+			   int typeflag, struct FTW *ftwbuf __maybe_unused)
+{
+	struct cgroup_name *cn;
+
+	if (typeflag != FTW_D)
+		return 0;
+
+	cn = malloc(sizeof(*cn) + strlen(fpath) + 1);
+	if (cn == NULL)
+		return -1;
+
+	cn->used = false;
+	strcpy(cn->name, fpath);
+
+	list_add_tail(&cn->list, &cgroup_list);
+	return 0;
+}
+
+static int check_and_add_cgroup_name(const char *fpath)
+{
+	struct cgroup_name *cn;
+
+	list_for_each_entry(cn, &cgroup_list, list) {
+		if (!strcmp(cn->name, fpath))
+			return 0;
+	}
+
+	/* pretend if it's added by ftw() */
+	return add_cgroup_name(fpath, NULL, FTW_D, NULL);
+}
+
+static void release_cgroup_list(void)
+{
+	struct cgroup_name *cn;
+
+	while (!list_empty(&cgroup_list)) {
+		cn = list_first_entry(&cgroup_list, struct cgroup_name, list);
+		list_del(&cn->list);
+		free(cn);
+	}
+}
+
+/* collect given cgroups only */
+static int list_cgroups(const char *str)
+{
+	const char *p, *e, *eos = str + strlen(str);
+	struct cgroup_name *cn;
+	char *s;
+
+	/* use given name as is when no regex is given */
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		if (e - str) {
+			int ret;
+
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+
+			ret = check_and_add_cgroup_name(s);
+			free(s);
+			if (ret < 0)
+				return -1;
+		} else {
+			if (check_and_add_cgroup_name("/") < 0)
+				return -1;
+		}
+
+		if (!p)
+			break;
+		str = p+1;
+	}
+
+	/* these groups will be used */
+	list_for_each_entry(cn, &cgroup_list, list)
+		cn->used = true;
+
+	return 0;
+}
+
+/* collect all cgroups first and then match with the pattern */
+static int match_cgroups(const char *str)
+{
+	char mnt[PATH_MAX];
+	const char *p, *e, *eos = str + strlen(str);
+	struct cgroup_name *cn;
+	regex_t reg;
+	int prefix_len;
+	char *s;
+
+	if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event"))
+		return -1;
+
+	/* cgroup_name will have a full path, skip the root directory */
+	prefix_len = strlen(mnt);
+
+	/* collect all cgroups in the cgroup_list */
+	if (nftw(mnt, add_cgroup_name, 20, 0) < 0)
+		return -1;
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			if (regcomp(&reg, s, REG_NOSUB)) {
+				free(s);
+				return -1;
+			}
+
+			/* check cgroup name with the pattern */
+			list_for_each_entry(cn, &cgroup_list, list) {
+				char *name = cn->name + prefix_len;
+
+				if (name[0] == '/' && name[1])
+					name++;
+				if (!regexec(&reg, name, 0, NULL, 0))
+					cn->used = true;
+			}
+			regfree(&reg);
+			free(s);
+		} else {
+			/* first entry to root cgroup */
+			cn = list_first_entry(&cgroup_list, struct cgroup_name,
+					      list);
+			cn->used = true;
+		}
+
+		if (!p)
+			break;
+		str = p+1;
+	}
+	return prefix_len;
+}
+
+int parse_cgroups(const struct option *opt, const char *str,
+		  int unset __maybe_unused)
+{
+	struct evlist *evlist = *(struct evlist **)opt->value;
+	struct evsel *counter;
+	struct cgroup *cgrp = NULL;
+	const char *p, *e, *eos = str + strlen(str);
+	char *s;
+	int ret, i;
+
+	if (list_empty(&evlist__core(evlist)->entries)) {
+		fprintf(stderr, "must define events before cgroups\n");
+		return -1;
+	}
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			ret = add_cgroup(evlist, s);
+			free(s);
+			if (ret)
+				return -1;
+		}
+		/* nr_cgroups is increased een for empty cgroups */
+		nr_cgroups++;
+		if (!p)
+			break;
+		str = p+1;
+	}
+	/* for the case one cgroup combine to multiple events */
+	i = 0;
+	if (nr_cgroups == 1) {
+		evlist__for_each_entry(evlist, counter) {
+			if (i == 0)
+				cgrp = counter->cgrp;
+			else {
+				counter->cgrp = cgrp;
+				refcount_inc(&cgrp->refcnt);
+			}
+			i++;
+		}
+	}
+	return 0;
+}
+
+static bool has_pattern_string(const char *str)
+{
+	return !!strpbrk(str, "{}[]()|*+?^$");
+}
+
+int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgroup)
+{
+	struct evlist *orig_list, *tmp_list;
+	struct rblist orig_metric_events;
+	struct cgroup *cgrp = NULL;
+	struct cgroup_name *cn;
+	int ret = -1;
+	int prefix_len;
+
+	if (evlist__nr_entries(evlist) == 0) {
+		fprintf(stderr, "must define events before cgroups\n");
+		return -EINVAL;
+	}
+
+	orig_list = evlist__new();
+	tmp_list = evlist__new();
+	if (orig_list == NULL || tmp_list == NULL) {
+		fprintf(stderr, "memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* save original events and init evlist */
+	evlist__splice_list_tail(orig_list, &evlist__core(evlist)->entries);
+	evlist__core(evlist)->nr_entries = 0;
+
+	orig_metric_events = *evlist__metric_events(evlist);
+	metricgroup__rblist_init(evlist__metric_events(evlist));
+
+	if (has_pattern_string(str))
+		prefix_len = match_cgroups(str);
+	else
+		prefix_len = list_cgroups(str);
+
+	if (prefix_len < 0)
+		goto out_err;
+
+	list_for_each_entry(cn, &cgroup_list, list) {
+		struct evsel *pos;
+		char *name;
+
+		if (!cn->used)
+			continue;
+
+		/* cgroup_name might have a full path, skip the prefix */
+		name = cn->name + prefix_len;
+		if (name[0] == '/' && name[1])
+			name++;
+
+		/* the cgroup can go away in the meantime */
+		cgrp = cgroup__new(name, open_cgroup);
+		if (cgrp == NULL)
+			continue;
+
+		/* copy the list and set to the new cgroup. */
+		evlist__for_each_entry(orig_list, pos) {
+			struct evsel *evsel = evsel__clone(pos);
+
+			if (evsel == NULL)
+				goto out_err;
+
+			/* stash the copy during the copying. */
+			pos->priv = evsel;
+			cgroup__put(evsel->cgrp);
+			evsel->cgrp = cgroup__get(cgrp);
+
+			evlist__add(tmp_list, evsel);
+		}
+		/* update leader information using stashed pointer to copy. */
+		evlist__for_each_entry(orig_list, pos) {
+			struct evsel *evsel = pos->priv;
+
+			if (evsel__leader(pos))
+				evsel__set_leader(evsel, evsel__leader(pos)->priv);
+
+			if (pos->metric_leader)
+				evsel->metric_leader = pos->metric_leader->priv;
+
+			if (pos->first_wildcard_match)
+				evsel->first_wildcard_match = pos->first_wildcard_match->priv;
+		}
+		/* the stashed copy is no longer used. */
+		evlist__for_each_entry(orig_list, pos)
+			pos->priv = NULL;
+
+		/* cgroup__new() has a refcount, release it here */
+		cgroup__put(cgrp);
+		nr_cgroups++;
+
+		if (metricgroup__copy_metric_events(tmp_list, cgrp,
+						    evlist__metric_events(evlist),
+						    &orig_metric_events) < 0)
+			goto out_err;
+
+		evlist__splice_list_tail(evlist, &evlist__core(tmp_list)->entries);
+		evlist__core(tmp_list)->nr_entries = 0;
+	}
+
+	if (list_empty(&evlist__core(evlist)->entries)) {
+		fprintf(stderr, "no cgroup matched: %s\n", str);
+		goto out_err;
+	}
+
+	ret = 0;
+	cgrp_event_expanded = true;
+
+out_err:
+	evlist__put(orig_list);
+	evlist__put(tmp_list);
+	metricgroup__rblist_exit(&orig_metric_events);
+	release_cgroup_list();
+
+	return ret;
+}
+
+static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id,
+					bool create, const char *path)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct cgroup *cgrp;
+
+	while (*p != NULL) {
+		parent = *p;
+		cgrp = rb_entry(parent, struct cgroup, node);
+
+		if (cgrp->id == id)
+			return cgrp;
+
+		if (cgrp->id < id)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	if (!create)
+		return NULL;
+
+	cgrp = malloc(sizeof(*cgrp));
+	if (cgrp == NULL)
+		return NULL;
+
+	cgrp->name = strdup(path);
+	if (cgrp->name == NULL) {
+		free(cgrp);
+		return NULL;
+	}
+
+	cgrp->fd = -1;
+	cgrp->id = id;
+	refcount_set(&cgrp->refcnt, 1);
+
+	rb_link_node(&cgrp->node, parent, p);
+	rb_insert_color(&cgrp->node, root);
+
+	return cgrp;
+}
+
+struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id,
+			       const char *path)
+{
+	struct cgroup *cgrp;
+
+	down_write(&env->cgroups.lock);
+	cgrp = __cgroup__findnew(&env->cgroups.tree, id, true, path);
+	up_write(&env->cgroups.lock);
+	return cgrp;
+}
+
+struct cgroup *__cgroup__find(struct rb_root *root, uint64_t id)
+{
+	return __cgroup__findnew(root, id, /*create=*/false, /*path=*/NULL);
+}
+
+struct cgroup *cgroup__find(struct perf_env *env, uint64_t id)
+{
+	struct cgroup *cgrp;
+
+	down_read(&env->cgroups.lock);
+	cgrp = __cgroup__findnew(&env->cgroups.tree, id, false, NULL);
+	up_read(&env->cgroups.lock);
+	return cgrp;
+}
+
+void perf_env__purge_cgroups(struct perf_env *env)
+{
+	struct rb_node *node;
+	struct cgroup *cgrp;
+
+	down_write(&env->cgroups.lock);
+	while (!RB_EMPTY_ROOT(&env->cgroups.tree)) {
+		node = rb_first(&env->cgroups.tree);
+		cgrp = rb_entry(node, struct cgroup, node);
+
+		rb_erase(node, &env->cgroups.tree);
+		cgroup__put(cgrp);
+	}
+	up_write(&env->cgroups.lock);
+}
+
+void read_all_cgroups(struct rb_root *root)
+{
+	char mnt[PATH_MAX];
+	struct cgroup_name *cn;
+	int prefix_len;
+
+	if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event"))
+		return;
+
+	/* cgroup_name will have a full path, skip the root directory */
+	prefix_len = strlen(mnt);
+
+	/* collect all cgroups in the cgroup_list */
+	if (nftw(mnt, add_cgroup_name, 20, 0) < 0)
+		return;
+
+	list_for_each_entry(cn, &cgroup_list, list) {
+		const char *name;
+		u64 cgrp_id;
+
+		/* cgroup_name might have a full path, skip the prefix */
+		name = cn->name + prefix_len;
+		if (name[0] == '\0')
+			name = "/";
+
+		cgrp_id = __read_cgroup_id(cn->name);
+		__cgroup__findnew(root, cgrp_id, /*create=*/true, name);
+	}
+
+	release_cgroup_list();
+}