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, 491 insertions, 0 deletions

diff --git a/fs/fsopen.c b/fs/fsopen.c
new file mode 100644
index 000000000..ae19e5136
--- /dev/null
+++ b/fs/fsopen.c
@@ -0,0 +1,491 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Filesystem access-by-fd.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/anon_inodes.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <uapi/linux/mount.h>
+#include "internal.h"
+#include "mount.h"
+
+static inline const char *fetch_message_locked(struct fc_log *log, size_t len,
+					       bool *need_free)
+{
+	const char *p;
+	int index;
+
+	if (unlikely(log->head == log->tail))
+		return ERR_PTR(-ENODATA);
+
+	index = log->tail & (ARRAY_SIZE(log->buffer) - 1);
+	p = log->buffer[index];
+	if (unlikely(strlen(p) > len))
+		return ERR_PTR(-EMSGSIZE);
+
+	log->buffer[index] = NULL;
+	*need_free = log->need_free & (1 << index);
+	log->need_free &= ~(1 << index);
+	log->tail++;
+
+	return p;
+}
+
+/*
+ * Allow the user to read back any error, warning or informational messages.
+ * Only one message is returned for each read(2) call.
+ */
+static ssize_t fscontext_read(struct file *file,
+			      char __user *_buf, size_t len, loff_t *pos)
+{
+	struct fs_context *fc = file->private_data;
+	ssize_t err;
+	const char *p __free(kfree) = NULL, *message;
+	bool need_free;
+	int n;
+
+	err = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (err < 0)
+		return err;
+	message = fetch_message_locked(fc->log.log, len, &need_free);
+	mutex_unlock(&fc->uapi_mutex);
+	if (IS_ERR(message))
+		return PTR_ERR(message);
+
+	if (need_free)
+		p = message;
+
+	n = strlen(message);
+	if (copy_to_user(_buf, message, n))
+		return -EFAULT;
+	return n;
+}
+
+static int fscontext_release(struct inode *inode, struct file *file)
+{
+	struct fs_context *fc = file->private_data;
+
+	if (fc) {
+		file->private_data = NULL;
+		put_fs_context(fc);
+	}
+	return 0;
+}
+
+const struct file_operations fscontext_fops = {
+	.read		= fscontext_read,
+	.release	= fscontext_release,
+};
+
+/*
+ * Attach a filesystem context to a file and an fd.
+ */
+static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags)
+{
+	int fd;
+
+	fd = anon_inode_getfd("[fscontext]", &fscontext_fops, fc,
+			      O_RDWR | o_flags);
+	if (fd < 0)
+		put_fs_context(fc);
+	return fd;
+}
+
+static int fscontext_alloc_log(struct fs_context *fc)
+{
+	fc->log.log = kzalloc_obj(*fc->log.log);
+	if (!fc->log.log)
+		return -ENOMEM;
+	refcount_set(&fc->log.log->usage, 1);
+	fc->log.log->owner = fc->fs_type->owner;
+	return 0;
+}
+
+/*
+ * Open a filesystem by name so that it can be configured for mounting.
+ *
+ * We are allowed to specify a container in which the filesystem will be
+ * opened, thereby indicating which namespaces will be used (notably, which
+ * network namespace will be used for network filesystems).
+ */
+SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
+{
+	struct file_system_type *fs_type;
+	struct fs_context *fc;
+	const char *fs_name;
+	int ret;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if (flags & ~FSOPEN_CLOEXEC)
+		return -EINVAL;
+
+	fs_name = strndup_user(_fs_name, PAGE_SIZE);
+	if (IS_ERR(fs_name))
+		return PTR_ERR(fs_name);
+
+	fs_type = get_fs_type(fs_name);
+	kfree(fs_name);
+	if (!fs_type)
+		return -ENODEV;
+
+	fc = fs_context_for_mount(fs_type, 0);
+	put_filesystem(fs_type);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	fc->phase = FS_CONTEXT_CREATE_PARAMS;
+
+	ret = fscontext_alloc_log(fc);
+	if (ret < 0)
+		goto err_fc;
+
+	return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0);
+
+err_fc:
+	put_fs_context(fc);
+	return ret;
+}
+
+/*
+ * Pick a superblock into a context for reconfiguration.
+ */
+SYSCALL_DEFINE3(fspick, int, dfd, const char __user *, path, unsigned int, flags)
+{
+	struct fs_context *fc;
+	struct path target;
+	unsigned int lookup_flags;
+	int ret;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if ((flags & ~(FSPICK_CLOEXEC |
+		       FSPICK_SYMLINK_NOFOLLOW |
+		       FSPICK_NO_AUTOMOUNT |
+		       FSPICK_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	if (flags & FSPICK_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & FSPICK_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	CLASS(filename_flags, filename)(path,
+			 (flags & FSPICK_EMPTY_PATH) ? LOOKUP_EMPTY : 0);
+	ret = filename_lookup(dfd, filename, lookup_flags, &target, NULL);
+	if (ret < 0)
+		goto err;
+
+	ret = -EINVAL;
+	if (target.mnt->mnt_root != target.dentry)
+		goto err_path;
+
+	fc = fs_context_for_reconfigure(target.dentry, 0, 0);
+	if (IS_ERR(fc)) {
+		ret = PTR_ERR(fc);
+		goto err_path;
+	}
+
+	fc->phase = FS_CONTEXT_RECONF_PARAMS;
+
+	ret = fscontext_alloc_log(fc);
+	if (ret < 0)
+		goto err_fc;
+
+	path_put(&target);
+	return fscontext_create_fd(fc, flags & FSPICK_CLOEXEC ? O_CLOEXEC : 0);
+
+err_fc:
+	put_fs_context(fc);
+err_path:
+	path_put(&target);
+err:
+	return ret;
+}
+
+static int vfs_cmd_create(struct fs_context *fc, bool exclusive)
+{
+	struct super_block *sb;
+	int ret;
+
+	if (fc->phase != FS_CONTEXT_CREATE_PARAMS)
+		return -EBUSY;
+
+	if (!mount_capable(fc))
+		return -EPERM;
+
+	fc->phase = FS_CONTEXT_CREATING;
+	fc->exclusive = exclusive;
+
+	ret = vfs_get_tree(fc);
+	if (ret) {
+		fc->phase = FS_CONTEXT_FAILED;
+		return ret;
+	}
+
+	sb = fc->root->d_sb;
+	ret = security_sb_kern_mount(sb);
+	if (unlikely(ret)) {
+		fc_drop_locked(fc);
+		fc->phase = FS_CONTEXT_FAILED;
+		return ret;
+	}
+
+	/* vfs_get_tree() callchains will have grabbed @s_umount */
+	up_write(&sb->s_umount);
+	fc->phase = FS_CONTEXT_AWAITING_MOUNT;
+	return 0;
+}
+
+static int vfs_cmd_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb;
+	int ret;
+
+	if (fc->phase != FS_CONTEXT_RECONF_PARAMS)
+		return -EBUSY;
+
+	fc->phase = FS_CONTEXT_RECONFIGURING;
+
+	sb = fc->root->d_sb;
+	if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) {
+		fc->phase = FS_CONTEXT_FAILED;
+		return -EPERM;
+	}
+
+	down_write(&sb->s_umount);
+	ret = reconfigure_super(fc);
+	up_write(&sb->s_umount);
+	if (ret) {
+		fc->phase = FS_CONTEXT_FAILED;
+		return ret;
+	}
+
+	vfs_clean_context(fc);
+	return 0;
+}
+
+/*
+ * Check the state and apply the configuration.  Note that this function is
+ * allowed to 'steal' the value by setting param->xxx to NULL before returning.
+ */
+static int vfs_fsconfig_locked(struct fs_context *fc, int cmd,
+			       struct fs_parameter *param)
+{
+	int ret;
+
+	ret = finish_clean_context(fc);
+	if (ret)
+		return ret;
+	switch (cmd) {
+	case FSCONFIG_CMD_CREATE:
+		return vfs_cmd_create(fc, false);
+	case FSCONFIG_CMD_CREATE_EXCL:
+		return vfs_cmd_create(fc, true);
+	case FSCONFIG_CMD_RECONFIGURE:
+		return vfs_cmd_reconfigure(fc);
+	default:
+		if (fc->phase != FS_CONTEXT_CREATE_PARAMS &&
+		    fc->phase != FS_CONTEXT_RECONF_PARAMS)
+			return -EBUSY;
+
+		return vfs_parse_fs_param(fc, param);
+	}
+}
+
+/**
+ * sys_fsconfig - Set parameters and trigger actions on a context
+ * @fd: The filesystem context to act upon
+ * @cmd: The action to take
+ * @_key: Where appropriate, the parameter key to set
+ * @_value: Where appropriate, the parameter value to set
+ * @aux: Additional information for the value
+ *
+ * This system call is used to set parameters on a context, including
+ * superblock settings, data source and security labelling.
+ *
+ * Actions include triggering the creation of a superblock and the
+ * reconfiguration of the superblock attached to the specified context.
+ *
+ * When setting a parameter, @cmd indicates the type of value being proposed
+ * and @_key indicates the parameter to be altered.
+ *
+ * @_value and @aux are used to specify the value, should a value be required:
+ *
+ * (*) fsconfig_set_flag: No value is specified.  The parameter must be boolean
+ *     in nature.  The key may be prefixed with "no" to invert the
+ *     setting. @_value must be NULL and @aux must be 0.
+ *
+ * (*) fsconfig_set_string: A string value is specified.  The parameter can be
+ *     expecting boolean, integer, string or take a path.  A conversion to an
+ *     appropriate type will be attempted (which may include looking up as a
+ *     path).  @_value points to a NUL-terminated string and @aux must be 0.
+ *
+ * (*) fsconfig_set_binary: A binary blob is specified.  @_value points to the
+ *     blob and @aux indicates its size.  The parameter must be expecting a
+ *     blob.
+ *
+ * (*) fsconfig_set_path: A non-empty path is specified.  The parameter must be
+ *     expecting a path object.  @_value points to a NUL-terminated string that
+ *     is the path and @aux is a file descriptor at which to start a relative
+ *     lookup or AT_FDCWD.
+ *
+ * (*) fsconfig_set_path_empty: As fsconfig_set_path, but with AT_EMPTY_PATH
+ *     implied.
+ *
+ * (*) fsconfig_set_fd: An open file descriptor is specified.  @_value must be
+ *     NULL and @aux indicates the file descriptor.
+ */
+SYSCALL_DEFINE5(fsconfig,
+		int, fd,
+		unsigned int, cmd,
+		const char __user *, _key,
+		const void __user *, _value,
+		int, aux)
+{
+	struct fs_context *fc;
+	int ret;
+	int lookup_flags = 0;
+
+	struct fs_parameter param = {
+		.type	= fs_value_is_undefined,
+	};
+
+	if (fd < 0)
+		return -EINVAL;
+
+	switch (cmd) {
+	case FSCONFIG_SET_FLAG:
+		if (!_key || _value || aux)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_STRING:
+		if (!_key || !_value || aux)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_BINARY:
+		if (!_key || !_value || aux <= 0 || aux > 1024 * 1024)
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_PATH:
+	case FSCONFIG_SET_PATH_EMPTY:
+		if (!_key || !_value || (aux != AT_FDCWD && aux < 0))
+			return -EINVAL;
+		break;
+	case FSCONFIG_SET_FD:
+		if (!_key || _value || aux < 0)
+			return -EINVAL;
+		break;
+	case FSCONFIG_CMD_CREATE:
+	case FSCONFIG_CMD_CREATE_EXCL:
+	case FSCONFIG_CMD_RECONFIGURE:
+		if (_key || _value || aux)
+			return -EINVAL;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EBADF;
+	if (fd_file(f)->f_op != &fscontext_fops)
+		return -EINVAL;
+
+	fc = fd_file(f)->private_data;
+
+	if (_key) {
+		param.key = strndup_user(_key, 256);
+		if (IS_ERR(param.key))
+			return PTR_ERR(param.key);
+	}
+
+	switch (cmd) {
+	case FSCONFIG_SET_FLAG:
+		param.type = fs_value_is_flag;
+		break;
+	case FSCONFIG_SET_STRING:
+		param.type = fs_value_is_string;
+		param.string = strndup_user(_value, 256);
+		if (IS_ERR(param.string)) {
+			ret = PTR_ERR(param.string);
+			goto out_key;
+		}
+		param.size = strlen(param.string);
+		break;
+	case FSCONFIG_SET_BINARY:
+		param.type = fs_value_is_blob;
+		param.size = aux;
+		param.blob = memdup_user_nul(_value, aux);
+		if (IS_ERR(param.blob)) {
+			ret = PTR_ERR(param.blob);
+			goto out_key;
+		}
+		break;
+	case FSCONFIG_SET_PATH_EMPTY:
+		lookup_flags = LOOKUP_EMPTY;
+		fallthrough;
+	case FSCONFIG_SET_PATH:
+		param.type = fs_value_is_filename;
+		param.name = getname_flags(_value, lookup_flags);
+		if (IS_ERR(param.name)) {
+			ret = PTR_ERR(param.name);
+			goto out_key;
+		}
+		param.dirfd = aux;
+		param.size = strlen(param.name->name);
+		break;
+	case FSCONFIG_SET_FD:
+		param.type = fs_value_is_file;
+		ret = -EBADF;
+		param.file = fget_raw(aux);
+		if (!param.file)
+			goto out_key;
+		param.dirfd = aux;
+		break;
+	default:
+		break;
+	}
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret == 0) {
+		ret = vfs_fsconfig_locked(fc, cmd, &param);
+		mutex_unlock(&fc->uapi_mutex);
+	}
+
+	/* Clean up the our record of any value that we obtained from
+	 * userspace.  Note that the value may have been stolen by the LSM or
+	 * filesystem, in which case the value pointer will have been cleared.
+	 */
+	switch (cmd) {
+	case FSCONFIG_SET_STRING:
+	case FSCONFIG_SET_BINARY:
+		kfree(param.string);
+		break;
+	case FSCONFIG_SET_PATH:
+	case FSCONFIG_SET_PATH_EMPTY:
+		if (param.name)
+			putname(param.name);
+		break;
+	case FSCONFIG_SET_FD:
+		if (param.file)
+			fput(param.file);
+		break;
+	default:
+		break;
+	}
+out_key:
+	kfree(param.key);
+	return ret;
+}