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, 413 insertions, 0 deletions

diff --git a/fs/filesystems.c b/fs/filesystems.c
new file mode 100644
index 000000000..3083d904d
--- /dev/null
+++ b/fs/filesystems.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/filesystems.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  table of configured filesystems
+ */
+
+#include <linux/syscalls.h>
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kmod.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/fs_parser.h>
+#include <linux/rculist.h>
+
+/*
+ * Read-mostly filesystem drivers list.
+ *
+ * Readers walk under rcu_read_lock(); writers take file_systems_lock
+ * and publish via _rcu hlist primitives.  unregister_filesystem()
+ * synchronize_rcu()s after unlock so the embedded file_system_type
+ * can't go away under a reader.  To keep using a filesystem after
+ * the RCU section ends, take a module reference via try_module_get().
+ */
+static HLIST_HEAD(file_systems);
+static DEFINE_SPINLOCK(file_systems_lock);
+
+#ifdef CONFIG_PROC_FS
+/*
+ * Cache a stringified version of the filesystem list.
+ *
+ * The fs list gets queried a lot by userspace because of libselinux, including
+ * rather surprising programs (would you guess *sed* is on the list?). In order
+ * to reduce the overhead we cache the resulting string, which normally hangs
+ * around below 512 bytes in size.
+ *
+ * As the list almost never changes, its creation is not particularly optimized
+ * to keep things simple.
+ *
+ * We sort it out on read in order to not introduce a failure point for fs
+ * registration (in principle we may be unable to alloc memory for the list).
+ */
+struct file_systems_string {
+	struct rcu_head rcu;
+	unsigned long gen;
+	size_t len;
+	char string[];
+};
+
+static unsigned long file_systems_gen;
+static struct file_systems_string __read_mostly __rcu *file_systems_string;
+
+static void invalidate_filesystems_string(void);
+#else
+static inline void invalidate_filesystems_string(void) { }
+#endif
+
+/* WARNING: This can be used only if we _already_ own a reference */
+struct file_system_type *get_filesystem(struct file_system_type *fs)
+{
+	__module_get(fs->owner);
+	return fs;
+}
+
+void put_filesystem(struct file_system_type *fs)
+{
+	module_put(fs->owner);
+}
+
+static struct file_system_type *find_filesystem(const char *name, unsigned len)
+{
+	struct file_system_type *fs;
+
+	hlist_for_each_entry_rcu(fs, &file_systems, list,
+				 lockdep_is_held(&file_systems_lock))
+		if (strncmp(fs->name, name, len) == 0 && !fs->name[len])
+			return fs;
+	return NULL;
+}
+
+/**
+ *	register_filesystem - register a new filesystem
+ *	@fs: the file system structure
+ *
+ *	Adds the file system passed to the list of file systems the kernel
+ *	is aware of for mount and other syscalls. Returns 0 on success,
+ *	or a negative errno code on an error.
+ *
+ *	The &struct file_system_type that is passed is linked into the kernel
+ *	structures and must not be freed until the file system has been
+ *	unregistered.
+ */
+int register_filesystem(struct file_system_type *fs)
+{
+	if (fs->parameters &&
+	    !fs_validate_description(fs->name, fs->parameters))
+		return -EINVAL;
+
+	BUG_ON(strchr(fs->name, '.'));
+	if (!hlist_unhashed_lockless(&fs->list))
+		return -EBUSY;
+
+	guard(spinlock)(&file_systems_lock);
+	if (find_filesystem(fs->name, strlen(fs->name)))
+		return -EBUSY;
+	hlist_add_tail_rcu(&fs->list, &file_systems);
+	invalidate_filesystems_string();
+	return 0;
+}
+EXPORT_SYMBOL(register_filesystem);
+
+/**
+ *	unregister_filesystem - unregister a file system
+ *	@fs: filesystem to unregister
+ *
+ *	Remove a file system that was previously successfully registered
+ *	with the kernel. An error is returned if the file system is not found.
+ *	Zero is returned on a success.
+ *
+ *	Once this function has returned the &struct file_system_type structure
+ *	may be freed or reused.
+ */
+int unregister_filesystem(struct file_system_type *fs)
+{
+	scoped_guard(spinlock, &file_systems_lock) {
+		if (hlist_unhashed(&fs->list))
+			return -EINVAL;
+		hlist_del_init_rcu(&fs->list);
+		invalidate_filesystems_string();
+	}
+	synchronize_rcu();
+	return 0;
+}
+EXPORT_SYMBOL(unregister_filesystem);
+
+#ifdef CONFIG_SYSFS_SYSCALL
+static int fs_index(const char __user *__name)
+{
+	struct file_system_type *p;
+	char *name __free(kfree) = strndup_user(__name, PATH_MAX);
+	int index = 0;
+
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	guard(rcu)();
+	hlist_for_each_entry_rcu(p, &file_systems, list) {
+		if (strcmp(p->name, name) == 0)
+			return index;
+		index++;
+	}
+	return -EINVAL;
+}
+
+static int fs_name(unsigned int index, char __user *buf)
+{
+	struct file_system_type *p, *found = NULL;
+	int len, res;
+
+	scoped_guard(rcu) {
+		hlist_for_each_entry_rcu(p, &file_systems, list) {
+			if (index--)
+				continue;
+			if (try_module_get(p->owner))
+				found = p;
+			break;
+		}
+	}
+	if (!found)
+		return -EINVAL;
+
+	/* OK, we got the reference, so we can safely block */
+	len = strlen(found->name) + 1;
+	res = copy_to_user(buf, found->name, len) ? -EFAULT : 0;
+	put_filesystem(found);
+	return res;
+}
+
+static int fs_maxindex(void)
+{
+	struct file_system_type *p;
+	int index = 0;
+
+	guard(rcu)();
+	hlist_for_each_entry_rcu(p, &file_systems, list)
+		index++;
+	return index;
+}
+
+/*
+ * Whee.. Weird sysv syscall.
+ */
+SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2)
+{
+	int retval = -EINVAL;
+
+	switch (option) {
+	case 1:
+		retval = fs_index((const char __user *) arg1);
+		break;
+
+	case 2:
+		retval = fs_name(arg1, (char __user *) arg2);
+		break;
+
+	case 3:
+		retval = fs_maxindex();
+		break;
+	}
+	return retval;
+}
+#endif
+
+int __init list_bdev_fs_names(char *buf, size_t size)
+{
+	struct file_system_type *p;
+	size_t len;
+	int count = 0;
+
+	guard(rcu)();
+	hlist_for_each_entry_rcu(p, &file_systems, list) {
+		if (!(p->fs_flags & FS_REQUIRES_DEV))
+			continue;
+		len = strlen(p->name) + 1;
+		if (len > size) {
+			pr_warn("%s: truncating file system list\n", __func__);
+			break;
+		}
+		memcpy(buf, p->name, len);
+		buf += len;
+		size -= len;
+		count++;
+	}
+	return count;
+}
+
+#ifdef CONFIG_PROC_FS
+static void invalidate_filesystems_string(void)
+{
+	struct file_systems_string *old;
+
+	lockdep_assert_held_write(&file_systems_lock);
+	file_systems_gen++;
+	old = rcu_replace_pointer(file_systems_string, NULL,
+			   lockdep_is_held(&file_systems_lock));
+	if (old)
+		kfree_rcu(old, rcu);
+}
+
+static __cold noinline int regen_filesystems_string(void)
+{
+	struct file_system_type *p;
+	struct file_systems_string *old, *new;
+	size_t newlen, usedlen;
+	unsigned long gen;
+
+retry:
+	newlen = 0;
+
+	/* pre-calc space for each fs */
+	spin_lock(&file_systems_lock);
+	gen = file_systems_gen;
+	hlist_for_each_entry_rcu(p, &file_systems, list) {
+		if (!(p->fs_flags & FS_REQUIRES_DEV))
+			newlen += strlen("nodev");
+		newlen += strlen("\t") + strlen(p->name) + strlen("\n");
+	}
+	spin_unlock(&file_systems_lock);
+
+	new = kmalloc(offsetof(struct file_systems_string, string) + newlen + 1,
+		      GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	new->gen = gen;
+	new->len = newlen;
+	new->string[newlen] = '\0';
+
+	spin_lock(&file_systems_lock);
+	old = file_systems_string;
+
+	/*
+	 * Did someone beat us to it?
+	 */
+	if (old && old->gen == file_systems_gen) {
+		spin_unlock(&file_systems_lock);
+		kfree(new);
+		return 0;
+	}
+
+	/*
+	 * Did the list change in the meantime?
+	 */
+	if (gen != file_systems_gen) {
+		spin_unlock(&file_systems_lock);
+		kfree(new);
+		goto retry;
+	}
+
+	/*
+	 * Populate the string.
+	 *
+	 * We know we have just enough space because we calculated the right
+	 * size the previous time we had the lock and confirmed the list has
+	 * not changed after reacquiring it.
+	 */
+	usedlen = 0;
+	hlist_for_each_entry_rcu(p, &file_systems, list) {
+		usedlen += sprintf(&new->string[usedlen], "%s\t%s\n",
+				   (p->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev",
+				   p->name);
+	}
+
+	if (WARN_ON_ONCE(new->len != strlen(new->string))) {
+		/*
+		 * Should never happen of course, keep this in case someone changes string
+		 * generation above and messes it up.
+		 */
+		spin_unlock(&file_systems_lock);
+		kfree(new);
+		return -EINVAL;
+	}
+
+	rcu_assign_pointer(file_systems_string, new);
+	spin_unlock(&file_systems_lock);
+	if (old)
+		kfree_rcu(old, rcu);
+	return 0;
+}
+
+static __cold noinline int filesystems_proc_show_fallback(struct seq_file *m, void *v)
+{
+	struct file_system_type *p;
+
+	guard(rcu)();
+	hlist_for_each_entry_rcu(p, &file_systems, list) {
+		seq_printf(m, "%s\t%s\n",
+			   (p->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev",
+			   p->name);
+	}
+	return 0;
+}
+
+static int filesystems_proc_show(struct seq_file *m, void *v)
+{
+	struct file_systems_string *fss;
+
+	for (;;) {
+		scoped_guard(rcu) {
+			fss = rcu_dereference(file_systems_string);
+			if (likely(fss)) {
+				seq_write(m, fss->string, fss->len);
+				return 0;
+			}
+		}
+
+		int err = regen_filesystems_string();
+		if (unlikely(err))
+			return filesystems_proc_show_fallback(m, v);
+	}
+}
+
+static int __init proc_filesystems_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("filesystems", 0, NULL, filesystems_proc_show);
+	if (!pde)
+		return -ENOMEM;
+	proc_make_permanent(pde);
+	return 0;
+}
+module_init(proc_filesystems_init);
+#endif
+
+static struct file_system_type *__get_fs_type(const char *name, int len)
+{
+	struct file_system_type *fs;
+
+	guard(rcu)();
+	fs = find_filesystem(name, len);
+	if (fs && !try_module_get(fs->owner))
+		fs = NULL;
+	return fs;
+}
+
+struct file_system_type *get_fs_type(const char *name)
+{
+	struct file_system_type *fs;
+	const char *dot = strchr(name, '.');
+	int len = dot ? dot - name : strlen(name);
+
+	fs = __get_fs_type(name, len);
+	if (!fs && (request_module("fs-%.*s", len, name) == 0)) {
+		fs = __get_fs_type(name, len);
+		if (!fs)
+			pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n",
+				     len, name);
+	}
+
+	if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
+		put_filesystem(fs);
+		fs = NULL;
+	}
+	return fs;
+}
+EXPORT_SYMBOL(get_fs_type);