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, 421 insertions, 0 deletions

diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
new file mode 100644
index 000000000..3bcd9f35e
--- /dev/null
+++ b/fs/hostfs/hostfs_user.c
@@ -0,0 +1,421 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#include <stdio.h>
+#include <stddef.h>
+#include <unistd.h>
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+#include <sys/syscall.h>
+#include "hostfs.h"
+#include <utime.h>
+
+static void statx_to_hostfs(const struct statx *buf, struct hostfs_stat *p)
+{
+	p->ino = buf->stx_ino;
+	p->mode = buf->stx_mode;
+	p->nlink = buf->stx_nlink;
+	p->uid = buf->stx_uid;
+	p->gid = buf->stx_gid;
+	p->size = buf->stx_size;
+	p->atime.tv_sec = buf->stx_atime.tv_sec;
+	p->atime.tv_nsec = buf->stx_atime.tv_nsec;
+	p->ctime.tv_sec = buf->stx_ctime.tv_sec;
+	p->ctime.tv_nsec = buf->stx_ctime.tv_nsec;
+	p->mtime.tv_sec = buf->stx_mtime.tv_sec;
+	p->mtime.tv_nsec = buf->stx_mtime.tv_nsec;
+	if (buf->stx_mask & STATX_BTIME) {
+		p->btime.tv_sec = buf->stx_btime.tv_sec;
+		p->btime.tv_nsec = buf->stx_btime.tv_nsec;
+	} else {
+		memset(&p->btime, 0, sizeof(p->btime));
+	}
+	p->blksize = buf->stx_blksize;
+	p->blocks = buf->stx_blocks;
+	p->rdev.maj = buf->stx_rdev_major;
+	p->rdev.min = buf->stx_rdev_minor;
+	p->dev.maj = buf->stx_dev_major;
+	p->dev.min = buf->stx_dev_minor;
+}
+
+int stat_file(const char *path, struct hostfs_stat *p, int fd)
+{
+	struct statx buf;
+	int flags = AT_SYMLINK_NOFOLLOW;
+
+	if (fd >= 0) {
+		flags |= AT_EMPTY_PATH;
+		path = "";
+	}
+
+	if ((statx(fd, path, flags, STATX_BASIC_STATS | STATX_BTIME, &buf)) < 0)
+		return -errno;
+
+	statx_to_hostfs(&buf, p);
+	return 0;
+}
+
+int access_file(char *path, int r, int w, int x)
+{
+	int mode = 0;
+
+	if (r)
+		mode = R_OK;
+	if (w)
+		mode |= W_OK;
+	if (x)
+		mode |= X_OK;
+	if (access(path, mode) != 0)
+		return -errno;
+	else return 0;
+}
+
+int open_file(char *path, int r, int w, int append)
+{
+	int mode = 0, fd;
+
+	if (r && !w)
+		mode = O_RDONLY;
+	else if (!r && w)
+		mode = O_WRONLY;
+	else if (r && w)
+		mode = O_RDWR;
+	else panic("Impossible mode in open_file");
+
+	if (append)
+		mode |= O_APPEND;
+	fd = open64(path, mode);
+	if (fd < 0)
+		return -errno;
+	else return fd;
+}
+
+void *open_dir(char *path, int *err_out)
+{
+	DIR *dir;
+
+	dir = opendir(path);
+	*err_out = errno;
+
+	return dir;
+}
+
+void seek_dir(void *stream, unsigned long long pos)
+{
+	DIR *dir = stream;
+
+	seekdir(dir, pos);
+}
+
+char *read_dir(void *stream, unsigned long long *pos_out,
+	       unsigned long long *ino_out, int *len_out,
+	       unsigned int *type_out)
+{
+	DIR *dir = stream;
+	struct dirent *ent;
+
+	ent = readdir(dir);
+	if (ent == NULL)
+		return NULL;
+	*len_out = strlen(ent->d_name);
+	*ino_out = ent->d_ino;
+	*type_out = ent->d_type;
+	*pos_out = ent->d_off;
+	return ent->d_name;
+}
+
+int read_file(int fd, unsigned long long *offset, char *buf, int len)
+{
+	int n;
+
+	n = pread64(fd, buf, len, *offset);
+	if (n < 0)
+		return -errno;
+	*offset += n;
+	return n;
+}
+
+int write_file(int fd, unsigned long long *offset, const char *buf, int len)
+{
+	int n;
+
+	n = pwrite64(fd, buf, len, *offset);
+	if (n < 0)
+		return -errno;
+	*offset += n;
+	return n;
+}
+
+int lseek_file(int fd, long long offset, int whence)
+{
+	int ret;
+
+	ret = lseek64(fd, offset, whence);
+	if (ret < 0)
+		return -errno;
+	return 0;
+}
+
+int fsync_file(int fd, int datasync)
+{
+	int ret;
+	if (datasync)
+		ret = fdatasync(fd);
+	else
+		ret = fsync(fd);
+
+	if (ret < 0)
+		return -errno;
+	return 0;
+}
+
+int replace_file(int oldfd, int fd)
+{
+	return dup2(oldfd, fd);
+}
+
+void close_file(void *stream)
+{
+	close(*((int *) stream));
+}
+
+void close_dir(void *stream)
+{
+	closedir(stream);
+}
+
+int file_create(char *name, int mode)
+{
+	int fd;
+
+	fd = open64(name, O_CREAT | O_RDWR, mode);
+	if (fd < 0)
+		return -errno;
+	return fd;
+}
+
+int set_attr(const char *file, struct hostfs_iattr *attrs, int fd)
+{
+	struct hostfs_stat st;
+	struct timeval times[2];
+	int err, ma;
+
+	if (attrs->ia_valid & HOSTFS_ATTR_MODE) {
+		if (fd >= 0) {
+			if (fchmod(fd, attrs->ia_mode) != 0)
+				return -errno;
+		} else if (chmod(file, attrs->ia_mode) != 0) {
+			return -errno;
+		}
+	}
+	if (attrs->ia_valid & HOSTFS_ATTR_UID) {
+		if (fd >= 0) {
+			if (fchown(fd, attrs->ia_uid, -1))
+				return -errno;
+		} else if (chown(file, attrs->ia_uid, -1)) {
+			return -errno;
+		}
+	}
+	if (attrs->ia_valid & HOSTFS_ATTR_GID) {
+		if (fd >= 0) {
+			if (fchown(fd, -1, attrs->ia_gid))
+				return -errno;
+		} else if (chown(file, -1, attrs->ia_gid)) {
+			return -errno;
+		}
+	}
+	if (attrs->ia_valid & HOSTFS_ATTR_SIZE) {
+		if (fd >= 0) {
+			if (ftruncate(fd, attrs->ia_size))
+				return -errno;
+		} else if (truncate(file, attrs->ia_size)) {
+			return -errno;
+		}
+	}
+
+	/*
+	 * Update accessed and/or modified time, in two parts: first set
+	 * times according to the changes to perform, and then call futimes()
+	 * or utimes() to apply them.
+	 */
+	ma = (HOSTFS_ATTR_ATIME_SET | HOSTFS_ATTR_MTIME_SET);
+	if (attrs->ia_valid & ma) {
+		err = stat_file(file, &st, fd);
+		if (err != 0)
+			return err;
+
+		times[0].tv_sec = st.atime.tv_sec;
+		times[0].tv_usec = st.atime.tv_nsec / 1000;
+		times[1].tv_sec = st.mtime.tv_sec;
+		times[1].tv_usec = st.mtime.tv_nsec / 1000;
+
+		if (attrs->ia_valid & HOSTFS_ATTR_ATIME_SET) {
+			times[0].tv_sec = attrs->ia_atime.tv_sec;
+			times[0].tv_usec = attrs->ia_atime.tv_nsec / 1000;
+		}
+		if (attrs->ia_valid & HOSTFS_ATTR_MTIME_SET) {
+			times[1].tv_sec = attrs->ia_mtime.tv_sec;
+			times[1].tv_usec = attrs->ia_mtime.tv_nsec / 1000;
+		}
+
+		if (fd >= 0) {
+			if (futimes(fd, times) != 0)
+				return -errno;
+		} else if (utimes(file, times) != 0) {
+			return -errno;
+		}
+	}
+
+	/* Note: ctime is not handled */
+	if (attrs->ia_valid & (HOSTFS_ATTR_ATIME | HOSTFS_ATTR_MTIME)) {
+		err = stat_file(file, &st, fd);
+		attrs->ia_atime = st.atime;
+		attrs->ia_mtime = st.mtime;
+		if (err != 0)
+			return err;
+	}
+	return 0;
+}
+
+int make_symlink(const char *from, const char *to)
+{
+	int err;
+
+	err = symlink(to, from);
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int unlink_file(const char *file)
+{
+	int err;
+
+	err = unlink(file);
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int do_mkdir(const char *file, int mode)
+{
+	int err;
+
+	err = mkdir(file, mode);
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int hostfs_do_rmdir(const char *file)
+{
+	int err;
+
+	err = rmdir(file);
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor)
+{
+	int err;
+
+	err = mknod(file, mode, os_makedev(major, minor));
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int link_file(const char *to, const char *from)
+{
+	int err;
+
+	err = link(to, from);
+	if (err)
+		return -errno;
+	return 0;
+}
+
+int hostfs_do_readlink(char *file, char *buf, int size)
+{
+	int n;
+
+	n = readlink(file, buf, size);
+	if (n < 0)
+		return -errno;
+	if (n < size)
+		buf[n] = '\0';
+	return n;
+}
+
+int rename_file(char *from, char *to)
+{
+	int err;
+
+	err = rename(from, to);
+	if (err < 0)
+		return -errno;
+	return 0;
+}
+
+int rename2_file(char *from, char *to, unsigned int flags)
+{
+	int err;
+
+#ifndef SYS_renameat2
+#  ifdef __x86_64__
+#    define SYS_renameat2 316
+#  endif
+#  ifdef __i386__
+#    define SYS_renameat2 353
+#  endif
+#endif
+
+#ifdef SYS_renameat2
+	err = syscall(SYS_renameat2, AT_FDCWD, from, AT_FDCWD, to, flags);
+	if (err < 0) {
+		if (errno != ENOSYS)
+			return -errno;
+		else
+			return -EINVAL;
+	}
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
+int do_statfs(char *root, long *bsize_out, long long *blocks_out,
+	      long long *bfree_out, long long *bavail_out,
+	      long long *files_out, long long *ffree_out,
+	      void *fsid_out, int fsid_size, long *namelen_out)
+{
+	struct statfs64 buf;
+	int err;
+
+	err = statfs64(root, &buf);
+	if (err < 0)
+		return -errno;
+
+	*bsize_out = buf.f_bsize;
+	*blocks_out = buf.f_blocks;
+	*bfree_out = buf.f_bfree;
+	*bavail_out = buf.f_bavail;
+	*files_out = buf.f_files;
+	*ffree_out = buf.f_ffree;
+	memcpy(fsid_out, &buf.f_fsid,
+	       sizeof(buf.f_fsid) > fsid_size ? fsid_size :
+	       sizeof(buf.f_fsid));
+	*namelen_out = buf.f_namelen;
+
+	return 0;
+}