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, 572 insertions, 0 deletions

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
new file mode 100644
index 000000000..9844dcf35
--- /dev/null
+++ b/fs/devpts/inode.c
@@ -0,0 +1,572 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* -*- linux-c -*- --------------------------------------------------------- *
+ *
+ * linux/fs/devpts/inode.c
+ *
+ *  Copyright 1998-2004 H. Peter Anvin -- All Rights Reserved
+ *
+ * ------------------------------------------------------------------------- */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/tty.h>
+#include <linux/mutex.h>
+#include <linux/magic.h>
+#include <linux/idr.h>
+#include <linux/devpts_fs.h>
+#include <linux/fsnotify.h>
+#include <linux/seq_file.h>
+
+#define DEVPTS_DEFAULT_MODE 0600
+/*
+ * ptmx is a new node in /dev/pts and will be unused in legacy (single-
+ * instance) mode. To prevent surprises in user space, set permissions of
+ * ptmx to 0. Use 'chmod' or remount with '-o ptmxmode' to set meaningful
+ * permissions.
+ */
+#define DEVPTS_DEFAULT_PTMX_MODE 0000
+#define PTMX_MINOR	2
+
+/*
+ * sysctl support for setting limits on the number of Unix98 ptys allocated.
+ * Otherwise one can eat up all kernel memory by opening /dev/ptmx repeatedly.
+ */
+static int pty_limit = NR_UNIX98_PTY_DEFAULT;
+static int pty_reserve = NR_UNIX98_PTY_RESERVE;
+static int pty_limit_min;
+static int pty_limit_max = INT_MAX;
+static atomic_t pty_count = ATOMIC_INIT(0);
+
+static const struct ctl_table pty_table[] = {
+	{
+		.procname	= "max",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.data		= &pty_limit,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &pty_limit_min,
+		.extra2		= &pty_limit_max,
+	}, {
+		.procname	= "reserve",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.data		= &pty_reserve,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &pty_limit_min,
+		.extra2		= &pty_limit_max,
+	}, {
+		.procname	= "nr",
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.data		= &pty_count,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+struct pts_mount_opts {
+	int setuid;
+	int setgid;
+	kuid_t   uid;
+	kgid_t   gid;
+	umode_t mode;
+	umode_t ptmxmode;
+	int reserve;
+	int max;
+};
+
+enum {
+	Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance,  Opt_max,
+	Opt_err
+};
+
+static const struct fs_parameter_spec devpts_param_specs[] = {
+	fsparam_gid	("gid",		Opt_gid),
+	fsparam_s32	("max",		Opt_max),
+	fsparam_u32oct	("mode",	Opt_mode),
+	fsparam_flag	("newinstance",	Opt_newinstance),
+	fsparam_u32oct	("ptmxmode",	Opt_ptmxmode),
+	fsparam_uid	("uid",		Opt_uid),
+	{}
+};
+
+struct pts_fs_info {
+	struct ida allocated_ptys;
+	struct pts_mount_opts mount_opts;
+	struct super_block *sb;
+	struct inode *ptmx_inode; // borrowed
+};
+
+static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+static int devpts_ptmx_path(struct path *path)
+{
+	struct super_block *sb;
+	int err;
+
+	/* Is a devpts filesystem at "pts" in the same directory? */
+	err = path_pts(path);
+	if (err)
+		return err;
+
+	/* Is the path the root of a devpts filesystem? */
+	sb = path->mnt->mnt_sb;
+	if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+	    (path->mnt->mnt_root != sb->s_root))
+		return -ENODEV;
+
+	return 0;
+}
+
+/*
+ * Try to find a suitable devpts filesystem. We support the following
+ * scenarios:
+ * - The ptmx device node is located in the same directory as the devpts
+ *   mount where the pts device nodes are located.
+ *   This is e.g. the case when calling open on the /dev/pts/ptmx device
+ *   node when the devpts filesystem is mounted at /dev/pts.
+ * - The ptmx device node is located outside the devpts filesystem mount
+ *   where the pts device nodes are located. For example, the ptmx device
+ *   is a symlink, separate device node, or bind-mount.
+ *   A supported scenario is bind-mounting /dev/pts/ptmx to /dev/ptmx and
+ *   then calling open on /dev/ptmx. In this case a suitable pts
+ *   subdirectory can be found in the common parent directory /dev of the
+ *   devpts mount and the ptmx bind-mount, after resolving the /dev/ptmx
+ *   bind-mount.
+ *   If no suitable pts subdirectory can be found this function will fail.
+ *   This is e.g. the case when bind-mounting /dev/pts/ptmx to /ptmx.
+ */
+struct vfsmount *devpts_mntget(struct file *filp, struct pts_fs_info *fsi)
+{
+	struct path path;
+	int err = 0;
+
+	path = filp->f_path;
+	path_get(&path);
+
+	/* Walk upward while the start point is a bind mount of
+	 * a single file.
+	 */
+	while (path.mnt->mnt_root == path.dentry)
+		if (follow_up(&path) == 0)
+			break;
+
+	/* devpts_ptmx_path() finds a devpts fs or returns an error. */
+	if ((path.mnt->mnt_sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+	    (DEVPTS_SB(path.mnt->mnt_sb) != fsi))
+		err = devpts_ptmx_path(&path);
+	dput(path.dentry);
+	if (!err) {
+		if (DEVPTS_SB(path.mnt->mnt_sb) == fsi)
+			return path.mnt;
+
+		err = -ENODEV;
+	}
+
+	mntput(path.mnt);
+	return ERR_PTR(err);
+}
+
+struct pts_fs_info *devpts_acquire(struct file *filp)
+{
+	struct pts_fs_info *result;
+	struct path path;
+	struct super_block *sb;
+
+	path = filp->f_path;
+	path_get(&path);
+
+	/* Has the devpts filesystem already been found? */
+	if (path.mnt->mnt_sb->s_magic != DEVPTS_SUPER_MAGIC) {
+		int err;
+
+		err = devpts_ptmx_path(&path);
+		if (err) {
+			result = ERR_PTR(err);
+			goto out;
+		}
+	}
+
+	/*
+	 * pty code needs to hold extra references in case of last /dev/tty close
+	 */
+	sb = path.mnt->mnt_sb;
+	atomic_inc(&sb->s_active);
+	result = DEVPTS_SB(sb);
+
+out:
+	path_put(&path);
+	return result;
+}
+
+void devpts_release(struct pts_fs_info *fsi)
+{
+	deactivate_super(fsi->sb);
+}
+
+/*
+ * devpts_parse_param - Parse mount parameters
+ */
+static int devpts_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct pts_fs_info *fsi = fc->s_fs_info;
+	struct pts_mount_opts *opts = &fsi->mount_opts;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, devpts_param_specs, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_uid:
+		opts->uid = result.uid;
+		opts->setuid = 1;
+		break;
+	case Opt_gid:
+		opts->gid = result.gid;
+		opts->setgid = 1;
+		break;
+	case Opt_mode:
+		opts->mode = result.uint_32 & S_IALLUGO;
+		break;
+	case Opt_ptmxmode:
+		opts->ptmxmode = result.uint_32 & S_IALLUGO;
+		break;
+	case Opt_newinstance:
+		break;
+	case Opt_max:
+		if (result.uint_32 > NR_UNIX98_PTY_MAX)
+			return invalf(fc, "max out of range");
+		opts->max = result.uint_32;
+		break;
+	}
+
+	return 0;
+}
+
+static int mknod_ptmx(struct super_block *sb, struct fs_context *fc)
+{
+	int mode;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct dentry *root = sb->s_root;
+	struct pts_fs_info *fsi = DEVPTS_SB(sb);
+	struct pts_mount_opts *opts = &fsi->mount_opts;
+	kuid_t ptmx_uid = current_fsuid();
+	kgid_t ptmx_gid = current_fsgid();
+
+	dentry = simple_start_creating(root, "ptmx");
+	if (IS_ERR(dentry)) {
+		pr_err("Unable to alloc dentry for ptmx node\n");
+		return PTR_ERR(dentry);
+	}
+
+	/*
+	 * Create a new 'ptmx' node in this mount of devpts.
+	 */
+	inode = new_inode(sb);
+	if (!inode) {
+		simple_done_creating(dentry);
+		pr_err("Unable to alloc inode for ptmx node\n");
+		return -ENOMEM;
+	}
+
+	inode->i_ino = 2;
+	simple_inode_init_ts(inode);
+
+	mode = S_IFCHR|opts->ptmxmode;
+	init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2));
+	inode->i_uid = ptmx_uid;
+	inode->i_gid = ptmx_gid;
+	fsi->ptmx_inode = inode;
+
+	d_make_persistent(dentry, inode);
+
+	simple_done_creating(dentry);
+
+	return 0;
+}
+
+static void update_ptmx_mode(struct pts_fs_info *fsi)
+{
+	fsi->ptmx_inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
+}
+
+static int devpts_reconfigure(struct fs_context *fc)
+{
+	struct pts_fs_info *fsi = DEVPTS_SB(fc->root->d_sb);
+	struct pts_fs_info *new = fc->s_fs_info;
+
+	/* Apply the revised options.  We don't want to change ->reserve.
+	 * Ideally, we'd update each option conditionally on it having been
+	 * explicitly changed, but the default is to reset everything so that
+	 * would break UAPI...
+	 */
+	fsi->mount_opts.setuid		= new->mount_opts.setuid;
+	fsi->mount_opts.setgid		= new->mount_opts.setgid;
+	fsi->mount_opts.uid		= new->mount_opts.uid;
+	fsi->mount_opts.gid		= new->mount_opts.gid;
+	fsi->mount_opts.mode		= new->mount_opts.mode;
+	fsi->mount_opts.ptmxmode	= new->mount_opts.ptmxmode;
+	fsi->mount_opts.max		= new->mount_opts.max;
+
+	/*
+	 * parse_mount_options() restores options to default values
+	 * before parsing and may have changed ptmxmode. So, update the
+	 * mode in the inode too. Bogus options don't fail the remount,
+	 * so do this even on error return.
+	 */
+	update_ptmx_mode(fsi);
+
+	return 0;
+}
+
+static int devpts_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct pts_fs_info *fsi = DEVPTS_SB(root->d_sb);
+	struct pts_mount_opts *opts = &fsi->mount_opts;
+
+	if (opts->setuid)
+		seq_printf(seq, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, opts->uid));
+	if (opts->setgid)
+		seq_printf(seq, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, opts->gid));
+	seq_printf(seq, ",mode=%03o", opts->mode);
+	seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
+	if (opts->max < NR_UNIX98_PTY_MAX)
+		seq_printf(seq, ",max=%d", opts->max);
+
+	return 0;
+}
+
+static const struct super_operations devpts_sops = {
+	.statfs		= simple_statfs,
+	.show_options	= devpts_show_options,
+};
+
+static int devpts_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct pts_fs_info *fsi = DEVPTS_SB(s);
+	struct inode *inode;
+
+	s->s_iflags &= ~SB_I_NODEV;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = DEVPTS_SUPER_MAGIC;
+	s->s_op = &devpts_sops;
+	s->s_d_flags = DCACHE_DONTCACHE;
+	s->s_time_gran = 1;
+	fsi->sb = s;
+
+	inode = new_inode(s);
+	if (!inode)
+		return -ENOMEM;
+	inode->i_ino = 1;
+	simple_inode_init_ts(inode);
+	inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR;
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+	set_nlink(inode, 2);
+
+	s->s_root = d_make_root(inode);
+	if (!s->s_root) {
+		pr_err("get root dentry failed\n");
+		return -ENOMEM;
+	}
+
+	return mknod_ptmx(s, fc);
+}
+
+/*
+ * devpts_get_tree()
+ *
+ *     Mount a new (private) instance of devpts.  PTYs created in this
+ *     instance are independent of the PTYs in other devpts instances.
+ */
+static int devpts_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, devpts_fill_super);
+}
+
+static void devpts_free_fc(struct fs_context *fc)
+{
+	kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations devpts_context_ops = {
+	.free		= devpts_free_fc,
+	.parse_param	= devpts_parse_param,
+	.get_tree	= devpts_get_tree,
+	.reconfigure	= devpts_reconfigure,
+};
+
+/*
+ * Set up the filesystem mount context.
+ */
+static int devpts_init_fs_context(struct fs_context *fc)
+{
+	struct pts_fs_info *fsi;
+
+	fsi = kzalloc_obj(struct pts_fs_info);
+	if (!fsi)
+		return -ENOMEM;
+
+	ida_init(&fsi->allocated_ptys);
+	fsi->mount_opts.uid     = GLOBAL_ROOT_UID;
+	fsi->mount_opts.gid     = GLOBAL_ROOT_GID;
+	fsi->mount_opts.mode    = DEVPTS_DEFAULT_MODE;
+	fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+	fsi->mount_opts.max     = NR_UNIX98_PTY_MAX;
+
+	if (fc->purpose == FS_CONTEXT_FOR_MOUNT &&
+	    current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns)
+		fsi->mount_opts.reserve = true;
+
+	fc->s_fs_info = fsi;
+	fc->ops = &devpts_context_ops;
+	return 0;
+}
+
+static void devpts_kill_sb(struct super_block *sb)
+{
+	struct pts_fs_info *fsi = DEVPTS_SB(sb);
+
+	if (fsi)
+		ida_destroy(&fsi->allocated_ptys);
+	kfree(fsi);
+	kill_anon_super(sb);
+}
+
+static struct file_system_type devpts_fs_type = {
+	.name		= "devpts",
+	.init_fs_context = devpts_init_fs_context,
+	.parameters	= devpts_param_specs,
+	.kill_sb	= devpts_kill_sb,
+	.fs_flags	= FS_USERNS_MOUNT,
+};
+
+/*
+ * The normal naming convention is simply /dev/pts/<number>; this conforms
+ * to the System V naming convention
+ */
+
+int devpts_new_index(struct pts_fs_info *fsi)
+{
+	int index = -ENOSPC;
+
+	if (atomic_inc_return(&pty_count) >= (pty_limit -
+			  (fsi->mount_opts.reserve ? 0 : pty_reserve)))
+		goto out;
+
+	index = ida_alloc_max(&fsi->allocated_ptys, fsi->mount_opts.max - 1,
+			GFP_KERNEL);
+
+out:
+	if (index < 0)
+		atomic_dec(&pty_count);
+	return index;
+}
+
+void devpts_kill_index(struct pts_fs_info *fsi, int idx)
+{
+	ida_free(&fsi->allocated_ptys, idx);
+	atomic_dec(&pty_count);
+}
+
+/**
+ * devpts_pty_new -- create a new inode in /dev/pts/
+ * @fsi: Filesystem info for this instance.
+ * @index: used as a name of the node
+ * @priv: what's given back by devpts_get_priv
+ *
+ * The dentry for the created inode is returned.
+ * Remove it from /dev/pts/ with devpts_pty_kill().
+ */
+struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
+{
+	struct dentry *dentry;
+	struct super_block *sb = fsi->sb;
+	struct inode *inode;
+	struct dentry *root;
+	struct pts_mount_opts *opts;
+	char s[12];
+
+	root = sb->s_root;
+	opts = &fsi->mount_opts;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_ino = index + 3;
+	inode->i_uid = opts->setuid ? opts->uid : current_fsuid();
+	inode->i_gid = opts->setgid ? opts->gid : current_fsgid();
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index));
+
+	sprintf(s, "%d", index);
+
+	dentry = d_alloc_name(root, s);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	dentry->d_fsdata = priv;
+	d_make_persistent(dentry, inode);
+	fsnotify_create(d_inode(root), dentry);
+	dput(dentry);
+	return dentry; // borrowed
+}
+
+/**
+ * devpts_get_priv -- get private data for a slave
+ * @dentry: dentry of the slave
+ *
+ * Returns whatever was passed as priv in devpts_pty_new for a given inode.
+ */
+void *devpts_get_priv(struct dentry *dentry)
+{
+	if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC)
+		return NULL;
+	return dentry->d_fsdata;
+}
+
+/**
+ * devpts_pty_kill -- remove inode form /dev/pts/
+ * @dentry: dentry of the slave to be removed
+ *
+ * This is an inverse operation of devpts_pty_new.
+ */
+void devpts_pty_kill(struct dentry *dentry)
+{
+	WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
+
+	dentry->d_fsdata = NULL;
+	drop_nlink(dentry->d_inode);
+	d_drop(dentry);
+	fsnotify_unlink(d_inode(dentry->d_parent), dentry);
+	d_make_discardable(dentry);
+}
+
+static int __init init_devpts_fs(void)
+{
+	int err = register_filesystem(&devpts_fs_type);
+	if (!err) {
+		register_sysctl("kernel/pty", pty_table);
+	}
+	return err;
+}
+module_init(init_devpts_fs)