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, 294 insertions, 0 deletions

diff --git a/fs/utimes.c b/fs/utimes.c
new file mode 100644
index 000000000..e22664e41
--- /dev/null
+++ b/fs/utimes.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/utime.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/compat.h>
+#include <asm/unistd.h>
+#include <linux/filelock.h>
+#include "internal.h"
+
+static bool nsec_valid(long nsec)
+{
+	if (nsec == UTIME_OMIT || nsec == UTIME_NOW)
+		return true;
+
+	return nsec >= 0 && nsec <= 999999999;
+}
+
+int vfs_utimes(const struct path *path, struct timespec64 *times)
+{
+	int error;
+	struct iattr newattrs;
+	struct inode *inode = path->dentry->d_inode;
+	struct delegated_inode delegated_inode = { };
+
+	if (times) {
+		if (!nsec_valid(times[0].tv_nsec) ||
+		    !nsec_valid(times[1].tv_nsec))
+			return -EINVAL;
+		if (times[0].tv_nsec == UTIME_NOW &&
+		    times[1].tv_nsec == UTIME_NOW)
+			times = NULL;
+	}
+
+	error = mnt_want_write(path->mnt);
+	if (error)
+		goto out;
+
+	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
+	if (times) {
+		if (times[0].tv_nsec == UTIME_OMIT)
+			newattrs.ia_valid &= ~ATTR_ATIME;
+		else if (times[0].tv_nsec != UTIME_NOW) {
+			newattrs.ia_atime = times[0];
+			newattrs.ia_valid |= ATTR_ATIME_SET;
+		}
+
+		if (times[1].tv_nsec == UTIME_OMIT)
+			newattrs.ia_valid &= ~ATTR_MTIME;
+		else if (times[1].tv_nsec != UTIME_NOW) {
+			newattrs.ia_mtime = times[1];
+			newattrs.ia_valid |= ATTR_MTIME_SET;
+		}
+		/*
+		 * Tell setattr_prepare(), that this is an explicit time
+		 * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET
+		 * were used.
+		 */
+		newattrs.ia_valid |= ATTR_TIMES_SET;
+	} else {
+		newattrs.ia_valid |= ATTR_TOUCH;
+	}
+retry_deleg:
+	inode_lock(inode);
+	error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs,
+			      &delegated_inode);
+	inode_unlock(inode);
+	if (is_delegated(&delegated_inode)) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+
+	mnt_drop_write(path->mnt);
+out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(vfs_utimes);
+
+static int do_utimes_path(int dfd, const char __user *filename,
+		struct timespec64 *times, int flags)
+{
+	struct path path;
+	int lookup_flags = 0, error;
+
+	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
+		return -EINVAL;
+
+	if (!(flags & AT_SYMLINK_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+
+	CLASS(filename_uflags, name)(filename, flags);
+retry:
+	error = filename_lookup(dfd, name, lookup_flags, &path, NULL);
+	if (error)
+		return error;
+	error = vfs_utimes(&path, times);
+	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
+
+static int do_utimes_fd(int fd, struct timespec64 *times, int flags)
+{
+	if (flags)
+		return -EINVAL;
+
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EBADF;
+	return vfs_utimes(&fd_file(f)->f_path, times);
+}
+
+/*
+ * do_utimes - change times on filename or file descriptor
+ * @dfd: open file descriptor, -1 or AT_FDCWD
+ * @filename: path name or NULL
+ * @times: new times or NULL
+ * @flags: zero or more flags (only AT_SYMLINK_NOFOLLOW for the moment)
+ *
+ * If filename is NULL and dfd refers to an open file, then operate on
+ * the file.  Otherwise look up filename, possibly using dfd as a
+ * starting point.
+ *
+ * If times==NULL, set access and modification to current time,
+ * must be owner or have write permission.
+ * Else, update from *times, must be owner or super user.
+ */
+long do_utimes(int dfd, const char __user *filename, struct timespec64 *times,
+	       int flags)
+{
+	if (filename == NULL && dfd != AT_FDCWD)
+		return do_utimes_fd(dfd, times, flags);
+	return do_utimes_path(dfd, filename, times, flags);
+}
+
+SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename,
+		struct __kernel_timespec __user *, utimes, int, flags)
+{
+	struct timespec64 tstimes[2];
+
+	if (utimes) {
+		if ((get_timespec64(&tstimes[0], &utimes[0]) ||
+			get_timespec64(&tstimes[1], &utimes[1])))
+			return -EFAULT;
+
+		/* Nothing to do, we must not even check the path.  */
+		if (tstimes[0].tv_nsec == UTIME_OMIT &&
+		    tstimes[1].tv_nsec == UTIME_OMIT)
+			return 0;
+	}
+
+	return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags);
+}
+
+#ifdef __ARCH_WANT_SYS_UTIME
+/*
+ * futimesat(), utimes() and utime() are older versions of utimensat()
+ * that are provided for compatibility with traditional C libraries.
+ * On modern architectures, we always use libc wrappers around
+ * utimensat() instead.
+ */
+static long do_futimesat(int dfd, const char __user *filename,
+			 struct __kernel_old_timeval __user *utimes)
+{
+	struct __kernel_old_timeval times[2];
+	struct timespec64 tstimes[2];
+
+	if (utimes) {
+		if (copy_from_user(&times, utimes, sizeof(times)))
+			return -EFAULT;
+
+		/* This test is needed to catch all invalid values.  If we
+		   would test only in do_utimes we would miss those invalid
+		   values truncated by the multiplication with 1000.  Note
+		   that we also catch UTIME_{NOW,OMIT} here which are only
+		   valid for utimensat.  */
+		if (times[0].tv_usec >= 1000000 || times[0].tv_usec < 0 ||
+		    times[1].tv_usec >= 1000000 || times[1].tv_usec < 0)
+			return -EINVAL;
+
+		tstimes[0].tv_sec = times[0].tv_sec;
+		tstimes[0].tv_nsec = 1000 * times[0].tv_usec;
+		tstimes[1].tv_sec = times[1].tv_sec;
+		tstimes[1].tv_nsec = 1000 * times[1].tv_usec;
+	}
+
+	return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0);
+}
+
+
+SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename,
+		struct __kernel_old_timeval __user *, utimes)
+{
+	return do_futimesat(dfd, filename, utimes);
+}
+
+SYSCALL_DEFINE2(utimes, char __user *, filename,
+		struct __kernel_old_timeval __user *, utimes)
+{
+	return do_futimesat(AT_FDCWD, filename, utimes);
+}
+
+SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times)
+{
+	struct timespec64 tv[2];
+
+	if (times) {
+		if (get_user(tv[0].tv_sec, &times->actime) ||
+		    get_user(tv[1].tv_sec, &times->modtime))
+			return -EFAULT;
+		tv[0].tv_nsec = 0;
+		tv[1].tv_nsec = 0;
+	}
+	return do_utimes(AT_FDCWD, filename, times ? tv : NULL, 0);
+}
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+/*
+ * Not all architectures have sys_utime, so implement this in terms
+ * of sys_utimes.
+ */
+#ifdef __ARCH_WANT_SYS_UTIME32
+SYSCALL_DEFINE2(utime32, const char __user *, filename,
+		struct old_utimbuf32 __user *, t)
+{
+	struct timespec64 tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t->actime) ||
+		    get_user(tv[1].tv_sec, &t->modtime))
+			return -EFAULT;
+		tv[0].tv_nsec = 0;
+		tv[1].tv_nsec = 0;
+	}
+	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
+}
+#endif
+
+SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags)
+{
+	struct timespec64 tv[2];
+
+	if  (t) {
+		if (get_old_timespec32(&tv[0], &t[0]) ||
+		    get_old_timespec32(&tv[1], &t[1]))
+			return -EFAULT;
+
+		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
+			return 0;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, flags);
+}
+
+#ifdef __ARCH_WANT_SYS_UTIME32
+static long do_compat_futimesat(unsigned int dfd, const char __user *filename,
+				struct old_timeval32 __user *t)
+{
+	struct timespec64 tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
+		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
+		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
+		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
+			return -EFAULT;
+		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
+		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
+			return -EINVAL;
+		tv[0].tv_nsec *= 1000;
+		tv[1].tv_nsec *= 1000;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, 0);
+}
+
+SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct old_timeval32 __user *, t)
+{
+	return do_compat_futimesat(dfd, filename, t);
+}
+
+SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t)
+{
+	return do_compat_futimesat(AT_FDCWD, filename, t);
+}
+#endif
+#endif