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, 559 insertions, 0 deletions

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
new file mode 100644
index 000000000..8f7cd32f5
--- /dev/null
+++ b/tools/perf/util/util.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "perf.h"
+#include "util.h"
+#include "debug.h"
+#include "event.h"
+#include <api/fs/fs.h>
+#include <sys/stat.h>
+#include <sys/utsname.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/capability.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/time64.h>
+#include <linux/overflow.h>
+#include <unistd.h>
+#include "cap.h"
+#include "strlist.h"
+#include "string2.h"
+
+/*
+ * XXX We need to find a better place for these things...
+ */
+
+const char *input_name;
+
+bool perf_singlethreaded = true;
+
+void perf_set_singlethreaded(void)
+{
+	perf_singlethreaded = true;
+}
+
+void perf_set_multithreaded(void)
+{
+	perf_singlethreaded = false;
+}
+
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
+
+int sysctl__max_stack(void)
+{
+	int value;
+
+	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+		sysctl_perf_event_max_stack = value;
+
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
+	return sysctl_perf_event_max_stack;
+}
+
+bool sysctl__nmi_watchdog_enabled(void)
+{
+	static bool cached;
+	static bool nmi_watchdog;
+	int value;
+
+	if (cached)
+		return nmi_watchdog;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+		return false;
+
+	nmi_watchdog = (value > 0) ? true : false;
+	cached = true;
+
+	return nmi_watchdog;
+}
+
+bool exclude_GH_default;
+
+bool perf_host  = true;
+bool perf_guest = false;
+
+void event_attr_init(struct perf_event_attr *attr)
+{
+	/* to capture ABI version */
+	attr->size = sizeof(*attr);
+
+	if (!exclude_GH_default)
+		return;
+
+	if (!perf_host)
+		attr->exclude_host  = 1;
+	if (!perf_guest)
+		attr->exclude_guest = 1;
+}
+
+int mkdir_p(char *path, mode_t mode)
+{
+	struct stat st;
+	int err;
+	char *d = path;
+
+	if (*d != '/')
+		return -1;
+
+	if (stat(path, &st) == 0)
+		return 0;
+
+	while (*++d == '/');
+
+	while ((d = strchr(d, '/'))) {
+		*d = '\0';
+		err = stat(path, &st) && mkdir(path, mode);
+		*d++ = '/';
+		if (err)
+			return -1;
+		while (*d == '/')
+			++d;
+	}
+	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
+}
+
+static bool match_pat(char *file, const char **pat)
+{
+	int i = 0;
+
+	if (!pat)
+		return true;
+
+	while (pat[i]) {
+		if (strglobmatch(file, pat[i]))
+			return true;
+
+		i++;
+	}
+
+	return false;
+}
+
+/*
+ * The depth specify how deep the removal will go.
+ * 0       - will remove only files under the 'path' directory
+ * 1 .. x  - will dive in x-level deep under the 'path' directory
+ *
+ * If specified the pat is array of string patterns ended with NULL,
+ * which are checked upon every file/directory found. Only matching
+ * ones are removed.
+ *
+ * The function returns:
+ *    0 on success
+ *   -1 on removal failure with errno set
+ *   -2 on pattern failure
+ */
+static int rm_rf_depth_pat(const char *path, int depth, const char **pat)
+{
+	DIR *dir;
+	int ret;
+	struct dirent *d;
+	char namebuf[PATH_MAX];
+	struct stat statbuf;
+
+	/* Do not fail if there's no file. */
+	ret = lstat(path, &statbuf);
+	if (ret)
+		return 0;
+
+	/* Try to remove any file we get. */
+	if (!(statbuf.st_mode & S_IFDIR))
+		return unlink(path);
+
+	/* We have directory in path. */
+	dir = opendir(path);
+	if (dir == NULL)
+		return -1;
+
+	while ((d = readdir(dir)) != NULL && !ret) {
+
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+
+		if (!match_pat(d->d_name, pat)) {
+			ret =  -2;
+			break;
+		}
+
+		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+			  path, d->d_name);
+
+		/* We have to check symbolic link itself */
+		ret = lstat(namebuf, &statbuf);
+		if (ret < 0) {
+			pr_debug("stat failed: %s\n", namebuf);
+			break;
+		}
+
+		if (S_ISDIR(statbuf.st_mode))
+			ret = depth ? rm_rf_depth_pat(namebuf, depth - 1, pat) : 0;
+		else
+			ret = unlink(namebuf);
+	}
+	closedir(dir);
+
+	if (ret < 0)
+		return ret;
+
+	return rmdir(path);
+}
+
+static int rm_rf_a_kcore_dir(const char *path, const char *name)
+{
+	char kcore_dir_path[PATH_MAX];
+	const char *pat[] = {
+		"kcore",
+		"kallsyms",
+		"modules",
+		NULL,
+	};
+
+	snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/%s", path, name);
+
+	return rm_rf_depth_pat(kcore_dir_path, 0, pat);
+}
+
+static bool kcore_dir_filter(const char *name __maybe_unused, struct dirent *d)
+{
+	const char *pat[] = {
+		"kcore_dir",
+		"kcore_dir__[1-9]*",
+		NULL,
+	};
+
+	return match_pat(d->d_name, pat);
+}
+
+static int rm_rf_kcore_dir(const char *path)
+{
+	struct strlist *kcore_dirs;
+	struct str_node *nd;
+	int ret;
+
+	kcore_dirs = lsdir(path, kcore_dir_filter);
+
+	if (!kcore_dirs)
+		return 0;
+
+	strlist__for_each_entry(nd, kcore_dirs) {
+		ret = rm_rf_a_kcore_dir(path, nd->s);
+		if (ret)
+			return ret;
+	}
+
+	strlist__delete(kcore_dirs);
+
+	return 0;
+}
+
+void cpumask_to_cpulist(char *cpumask, char *cpulist)
+{
+	int i, j, bm_size, nbits;
+	int len = strlen(cpumask);
+	unsigned long *bm;
+	char cpus[MAX_NR_CPUS];
+
+	for (i = 0; i < len; i++) {
+		if (cpumask[i] == ',') {
+			for (j = i; j < len; j++)
+				cpumask[j] = cpumask[j + 1];
+		}
+	}
+
+	len = strlen(cpumask);
+	bm_size = (len + 15) / 16;
+	nbits = bm_size * 64;
+	if (nbits <= 0)
+		return;
+
+	bm = calloc(bm_size, sizeof(unsigned long));
+	if (!bm)
+		goto free_bm;
+
+	for (i = 0; i < bm_size; i++) {
+		char blk[17];
+		int blklen = len > 16 ? 16 : len;
+
+		strncpy(blk, cpumask + len - blklen, blklen);
+		blk[blklen] = '\0';
+		bm[i] = strtoul(blk, NULL, 16);
+		cpumask[len - blklen] = '\0';
+		len = strlen(cpumask);
+	}
+
+	bitmap_scnprintf(bm, nbits, cpus, sizeof(cpus));
+	strcpy(cpulist, cpus);
+
+free_bm:
+	free(bm);
+}
+
+void print_separator2(int pre_dash_cnt, const char *s, int post_dash_cnt)
+{
+	printf("%.*s%s%.*s\n", pre_dash_cnt, graph_dotted_line, s, post_dash_cnt,
+	       graph_dotted_line);
+}
+
+int rm_rf_perf_data(const char *path)
+{
+	const char *pat[] = {
+		"data",
+		"data.*",
+		NULL,
+	};
+
+	rm_rf_kcore_dir(path);
+
+	return rm_rf_depth_pat(path, 0, pat);
+}
+
+int rm_rf(const char *path)
+{
+	return rm_rf_depth_pat(path, INT_MAX, NULL);
+}
+
+/* A filter which removes dot files */
+bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d)
+{
+	return d->d_name[0] != '.';
+}
+
+/* lsdir reads a directory and store it in strlist */
+struct strlist *lsdir(const char *name,
+		      bool (*filter)(const char *, struct dirent *))
+{
+	struct strlist *list = NULL;
+	DIR *dir;
+	struct dirent *d;
+
+	dir = opendir(name);
+	if (!dir)
+		return NULL;
+
+	list = strlist__new(NULL, NULL);
+	if (!list) {
+		errno = ENOMEM;
+		goto out;
+	}
+
+	while ((d = readdir(dir)) != NULL) {
+		if (!filter || filter(name, d))
+			strlist__add(list, d->d_name);
+	}
+
+out:
+	closedir(dir);
+	return list;
+}
+
+size_t hex_width(u64 v)
+{
+	size_t n = 1;
+
+	while ((v >>= 4))
+		++n;
+
+	return n;
+}
+
+int perf_event_paranoid(void)
+{
+	int value;
+
+	if (sysctl__read_int("kernel/perf_event_paranoid", &value))
+		return INT_MAX;
+
+	return value;
+}
+
+bool perf_event_paranoid_check(int max_level)
+{
+	return perf_cap__capable(CAP_SYS_ADMIN) ||
+	       perf_cap__capable(CAP_PERFMON) ||
+	       perf_event_paranoid() <= max_level;
+}
+
+int perf_tip(char **strp, const char *dirpath)
+{
+	struct strlist *tips;
+	struct str_node *node;
+	struct strlist_config conf = {
+		.dirname = dirpath,
+		.file_only = true,
+	};
+	int ret = 0;
+
+	*strp = NULL;
+	tips = strlist__new("tips.txt", &conf);
+	if (tips == NULL)
+		return -errno;
+
+	if (strlist__nr_entries(tips) == 0)
+		goto out;
+
+	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
+	if (asprintf(strp, "Tip: %s", node->s) < 0)
+		ret = -ENOMEM;
+
+out:
+	strlist__delete(tips);
+
+	return ret;
+}
+
+char *perf_exe(char *buf, int len)
+{
+	int n;
+
+	if (len <= 0)
+		return buf;
+
+	n = readlink("/proc/self/exe", buf, len - 1);
+	if (n > 0) {
+		buf[n] = 0;
+		return buf;
+	}
+	if (len < (int)sizeof("perf")) {
+		buf[0] = '\0';
+		return buf;
+	}
+
+	return strcpy(buf, "perf");
+}
+
+void perf_debuginfod_setup(struct perf_debuginfod *di)
+{
+	/*
+	 * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod
+	 * processing is not triggered, otherwise we set it to 'di->urls'
+	 * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value.
+	 */
+	if (!di->set)
+		setenv("DEBUGINFOD_URLS", "", 1);
+	else if (di->urls && strcmp(di->urls, "system"))
+		setenv("DEBUGINFOD_URLS", di->urls, 1);
+
+	pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
+
+#ifndef HAVE_DEBUGINFOD_SUPPORT
+	if (di->set)
+		pr_warning("WARNING: debuginfod support requested, but perf is not built with it\n");
+#endif
+}
+
+/*
+ * Return a new filename prepended with task's root directory if it's in
+ * a chroot.  Callers should free the returned string.
+ */
+char *filename_with_chroot(int pid, const char *filename)
+{
+	char buf[PATH_MAX];
+	char proc_root[32];
+	char *new_name = NULL;
+	int ret;
+
+	scnprintf(proc_root, sizeof(proc_root), "/proc/%d/root", pid);
+	ret = readlink(proc_root, buf, sizeof(buf) - 1);
+	if (ret <= 0)
+		return NULL;
+
+	/* readlink(2) does not append a null byte to buf */
+	buf[ret] = '\0';
+
+	if (!strcmp(buf, "/"))
+		return NULL;
+
+	if (strstr(buf, "(deleted)"))
+		return NULL;
+
+	if (asprintf(&new_name, "%s/%s", buf, filename) < 0)
+		return NULL;
+
+	return new_name;
+}
+
+/*
+ * Reallocate an array *arr of size *arr_sz so that it is big enough to contain
+ * x elements of size msz, initializing new entries to *init_val or zero if
+ * init_val is NULL
+ */
+int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x, size_t msz, const void *init_val)
+{
+	size_t new_sz = *arr_sz;
+	void *new_arr;
+	size_t i;
+
+	if (!new_sz)
+		new_sz = msz >= 64 ? 1 : roundup(64, msz); /* Start with at least 64 bytes */
+	while (x >= new_sz) {
+		if (check_mul_overflow(new_sz, (size_t)2, &new_sz))
+			return -ENOMEM;
+	}
+	if (new_sz == *arr_sz)
+		return 0;
+	new_arr = calloc(new_sz, msz);
+	if (!new_arr)
+		return -ENOMEM;
+	if (*arr_sz)
+		memcpy(new_arr, *arr, *arr_sz * msz);
+	if (init_val) {
+		for (i = *arr_sz; i < new_sz; i++)
+			memcpy(new_arr + (i * msz), init_val, msz);
+	}
+	*arr = new_arr;
+	*arr_sz = new_sz;
+	return 0;
+}
+
+#ifndef HAVE_SCHED_GETCPU_SUPPORT
+int sched_getcpu(void)
+{
+#ifdef __NR_getcpu
+	unsigned int cpu;
+	int err = syscall(__NR_getcpu, &cpu, NULL, NULL);
+
+	if (!err)
+		return cpu;
+#else
+	errno = ENOSYS;
+#endif
+	return -1;
+}
+#endif
+
+#ifndef HAVE_SCANDIRAT_SUPPORT
+int scandirat(int dirfd, const char *dirp,
+	      struct dirent ***namelist,
+	      int (*filter)(const struct dirent *),
+	      int (*compar)(const struct dirent **, const struct dirent **))
+{
+	char path[PATH_MAX];
+	int err, fd = openat(dirfd, dirp, O_PATH);
+
+	if (fd < 0)
+		return fd;
+
+	snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+	err = scandir(path, namelist, filter, compar);
+	close(fd);
+	return err;
+}
+#endif
+
+/* basename version that takes a const input string */
+const char *perf_basename(const char *path)
+{
+	const char *base = strrchr(path, '/');
+
+	return base ? base + 1 : path;
+}