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, 428 insertions, 0 deletions

diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c
new file mode 100644
index 000000000..9fb06dc16
--- /dev/null
+++ b/fs/cachefiles/cache.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Manage high-level VFS aspects of a cache.
+ *
+ * Copyright (C) 2007, 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/namei.h>
+#include <trace/events/fscache.h>
+#include "internal.h"
+
+/*
+ * Bring a cache online.
+ */
+int cachefiles_add_cache(struct cachefiles_cache *cache)
+{
+	struct fscache_cache *cache_cookie;
+	struct path path;
+	struct kstatfs stats;
+	struct dentry *graveyard, *cachedir, *root;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("");
+
+	cache_cookie = fscache_acquire_cache(cache->tag);
+	if (IS_ERR(cache_cookie))
+		return PTR_ERR(cache_cookie);
+
+	/* we want to work under the module's security ID */
+	ret = cachefiles_get_security_ID(cache);
+	if (ret < 0)
+		goto error_getsec;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+
+	/* look up the directory at the root of the cache */
+	ret = kern_path(cache->rootdirname, LOOKUP_DIRECTORY, &path);
+	if (ret < 0)
+		goto error_open_root;
+
+	cache->mnt = path.mnt;
+	root = path.dentry;
+
+	ret = -EINVAL;
+	if (is_idmapped_mnt(path.mnt)) {
+		pr_warn("File cache on idmapped mounts not supported");
+		goto error_unsupported;
+	}
+
+	/* Check features of the backing filesystem:
+	 * - Directories must support looking up and directory creation
+	 * - We create tmpfiles to handle invalidation
+	 * - We use xattrs to store metadata
+	 * - We need to be able to query the amount of space available
+	 * - We want to be able to sync the filesystem when stopping the cache
+	 * - We use DIO to/from pages, so the blocksize mustn't be too big.
+	 */
+	ret = -EOPNOTSUPP;
+	if (d_is_negative(root) ||
+	    !d_backing_inode(root)->i_op->lookup ||
+	    !d_backing_inode(root)->i_op->mkdir ||
+	    !d_backing_inode(root)->i_op->tmpfile ||
+	    !(d_backing_inode(root)->i_opflags & IOP_XATTR) ||
+	    !root->d_sb->s_op->statfs ||
+	    !root->d_sb->s_op->sync_fs ||
+	    root->d_sb->s_blocksize > PAGE_SIZE)
+		goto error_unsupported;
+
+	ret = -EROFS;
+	if (sb_rdonly(root->d_sb))
+		goto error_unsupported;
+
+	/* determine the security of the on-disk cache as this governs
+	 * security ID of files we create */
+	ret = cachefiles_determine_cache_security(cache, root, &saved_cred);
+	if (ret < 0)
+		goto error_unsupported;
+
+	/* get the cache size and blocksize */
+	ret = vfs_statfs(&path, &stats);
+	if (ret < 0)
+		goto error_unsupported;
+
+	ret = -ERANGE;
+	if (stats.f_bsize <= 0)
+		goto error_unsupported;
+
+	ret = -EOPNOTSUPP;
+	if (stats.f_bsize > PAGE_SIZE)
+		goto error_unsupported;
+
+	cache->bsize = stats.f_bsize;
+	cache->bshift = ilog2(stats.f_bsize);
+
+	_debug("blksize %u (shift %u)",
+	       cache->bsize, cache->bshift);
+
+	_debug("size %llu, avail %llu",
+	       (unsigned long long) stats.f_blocks,
+	       (unsigned long long) stats.f_bavail);
+
+	/* set up caching limits */
+	do_div(stats.f_files, 100);
+	cache->fstop = stats.f_files * cache->fstop_percent;
+	cache->fcull = stats.f_files * cache->fcull_percent;
+	cache->frun  = stats.f_files * cache->frun_percent;
+
+	_debug("limits {%llu,%llu,%llu} files",
+	       (unsigned long long) cache->frun,
+	       (unsigned long long) cache->fcull,
+	       (unsigned long long) cache->fstop);
+
+	do_div(stats.f_blocks, 100);
+	cache->bstop = stats.f_blocks * cache->bstop_percent;
+	cache->bcull = stats.f_blocks * cache->bcull_percent;
+	cache->brun  = stats.f_blocks * cache->brun_percent;
+
+	_debug("limits {%llu,%llu,%llu} blocks",
+	       (unsigned long long) cache->brun,
+	       (unsigned long long) cache->bcull,
+	       (unsigned long long) cache->bstop);
+
+	/* get the cache directory and check its type */
+	cachedir = cachefiles_get_directory(cache, root, "cache", NULL);
+	if (IS_ERR(cachedir)) {
+		ret = PTR_ERR(cachedir);
+		goto error_unsupported;
+	}
+
+	cache->store = cachedir;
+
+	/* get the graveyard directory */
+	graveyard = cachefiles_get_directory(cache, root, "graveyard", NULL);
+	if (IS_ERR(graveyard)) {
+		ret = PTR_ERR(graveyard);
+		goto error_unsupported;
+	}
+
+	cache->graveyard = graveyard;
+	cache->cache = cache_cookie;
+
+	ret = fscache_add_cache(cache_cookie, &cachefiles_cache_ops, cache);
+	if (ret < 0)
+		goto error_add_cache;
+
+	/* done */
+	set_bit(CACHEFILES_READY, &cache->flags);
+	dput(root);
+
+	pr_info("File cache on %s registered\n", cache_cookie->name);
+
+	/* check how much space the cache has */
+	cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check);
+	cachefiles_end_secure(cache, saved_cred);
+	_leave(" = 0 [%px]", cache->cache);
+	return 0;
+
+error_add_cache:
+	cachefiles_put_directory(cache->graveyard);
+	cache->graveyard = NULL;
+error_unsupported:
+	cachefiles_put_directory(cache->store);
+	cache->store = NULL;
+	mntput(cache->mnt);
+	cache->mnt = NULL;
+	dput(root);
+error_open_root:
+	cachefiles_end_secure(cache, saved_cred);
+	put_cred(cache->cache_cred);
+	cache->cache_cred = NULL;
+error_getsec:
+	fscache_relinquish_cache(cache_cookie);
+	cache->cache = NULL;
+	pr_err("Failed to register: %d\n", ret);
+	return ret;
+}
+
+/*
+ * See if we have space for a number of pages and/or a number of files in the
+ * cache
+ */
+int cachefiles_has_space(struct cachefiles_cache *cache,
+			 unsigned fnr, unsigned bnr,
+			 enum cachefiles_has_space_for reason)
+{
+	struct kstatfs stats;
+	u64 b_avail, b_writing;
+	int ret;
+
+	struct path path = {
+		.mnt	= cache->mnt,
+		.dentry	= cache->mnt->mnt_root,
+	};
+
+	//_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u",
+	//       (unsigned long long) cache->frun,
+	//       (unsigned long long) cache->fcull,
+	//       (unsigned long long) cache->fstop,
+	//       (unsigned long long) cache->brun,
+	//       (unsigned long long) cache->bcull,
+	//       (unsigned long long) cache->bstop,
+	//       fnr, bnr);
+
+	/* find out how many pages of blockdev are available */
+	memset(&stats, 0, sizeof(stats));
+
+	ret = vfs_statfs(&path, &stats);
+	if (ret < 0) {
+		trace_cachefiles_vfs_error(NULL, d_inode(path.dentry), ret,
+					   cachefiles_trace_statfs_error);
+		if (ret == -EIO)
+			cachefiles_io_error(cache, "statfs failed");
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	b_avail = stats.f_bavail;
+	b_writing = atomic_long_read(&cache->b_writing);
+	if (b_avail > b_writing)
+		b_avail -= b_writing;
+	else
+		b_avail = 0;
+
+	//_debug("avail %llu,%llu",
+	//       (unsigned long long)stats.f_ffree,
+	//       (unsigned long long)b_avail);
+
+	/* see if there is sufficient space */
+	if (stats.f_ffree > fnr)
+		stats.f_ffree -= fnr;
+	else
+		stats.f_ffree = 0;
+
+	if (b_avail > bnr)
+		b_avail -= bnr;
+	else
+		b_avail = 0;
+
+	ret = -ENOBUFS;
+	if (stats.f_ffree < cache->fstop ||
+	    b_avail < cache->bstop)
+		goto stop_and_begin_cull;
+
+	ret = 0;
+	if (stats.f_ffree < cache->fcull ||
+	    b_avail < cache->bcull)
+		goto begin_cull;
+
+	if (test_bit(CACHEFILES_CULLING, &cache->flags) &&
+	    stats.f_ffree >= cache->frun &&
+	    b_avail >= cache->brun &&
+	    test_and_clear_bit(CACHEFILES_CULLING, &cache->flags)
+	    ) {
+		_debug("cease culling");
+		cachefiles_state_changed(cache);
+	}
+
+	//_leave(" = 0");
+	return 0;
+
+stop_and_begin_cull:
+	switch (reason) {
+	case cachefiles_has_space_for_write:
+		fscache_count_no_write_space();
+		break;
+	case cachefiles_has_space_for_create:
+		fscache_count_no_create_space();
+		break;
+	default:
+		break;
+	}
+begin_cull:
+	if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) {
+		_debug("### CULL CACHE ###");
+		cachefiles_state_changed(cache);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Mark all the objects as being out of service and queue them all for cleanup.
+ */
+static void cachefiles_withdraw_objects(struct cachefiles_cache *cache)
+{
+	struct cachefiles_object *object;
+	unsigned int count = 0;
+
+	_enter("");
+
+	spin_lock(&cache->object_list_lock);
+
+	while (!list_empty(&cache->object_list)) {
+		object = list_first_entry(&cache->object_list,
+					  struct cachefiles_object, cache_link);
+		cachefiles_see_object(object, cachefiles_obj_see_withdrawal);
+		list_del_init(&object->cache_link);
+		fscache_withdraw_cookie(object->cookie);
+		count++;
+		if ((count & 63) == 0) {
+			spin_unlock(&cache->object_list_lock);
+			cond_resched();
+			spin_lock(&cache->object_list_lock);
+		}
+	}
+
+	spin_unlock(&cache->object_list_lock);
+	_leave(" [%u objs]", count);
+}
+
+/*
+ * Withdraw fscache volumes.
+ */
+static void cachefiles_withdraw_fscache_volumes(struct cachefiles_cache *cache)
+{
+	struct list_head *cur;
+	struct cachefiles_volume *volume;
+	struct fscache_volume *vcookie;
+
+	_enter("");
+retry:
+	spin_lock(&cache->object_list_lock);
+	list_for_each(cur, &cache->volumes) {
+		volume = list_entry(cur, struct cachefiles_volume, cache_link);
+
+		if (atomic_read(&volume->vcookie->n_accesses) == 0)
+			continue;
+
+		vcookie = fscache_try_get_volume(volume->vcookie,
+						 fscache_volume_get_withdraw);
+		if (vcookie) {
+			spin_unlock(&cache->object_list_lock);
+			fscache_withdraw_volume(vcookie);
+			fscache_put_volume(vcookie, fscache_volume_put_withdraw);
+			goto retry;
+		}
+	}
+	spin_unlock(&cache->object_list_lock);
+
+	_leave("");
+}
+
+/*
+ * Withdraw cachefiles volumes.
+ */
+static void cachefiles_withdraw_volumes(struct cachefiles_cache *cache)
+{
+	_enter("");
+
+	for (;;) {
+		struct fscache_volume *vcookie = NULL;
+		struct cachefiles_volume *volume = NULL;
+
+		spin_lock(&cache->object_list_lock);
+		if (!list_empty(&cache->volumes)) {
+			volume = list_first_entry(&cache->volumes,
+						  struct cachefiles_volume, cache_link);
+			vcookie = fscache_try_get_volume(volume->vcookie,
+							 fscache_volume_get_withdraw);
+			if (!vcookie) {
+				spin_unlock(&cache->object_list_lock);
+				cpu_relax();
+				continue;
+			}
+			list_del_init(&volume->cache_link);
+		}
+		spin_unlock(&cache->object_list_lock);
+		if (!volume)
+			break;
+
+		cachefiles_withdraw_volume(volume);
+		fscache_put_volume(vcookie, fscache_volume_put_withdraw);
+	}
+
+	_leave("");
+}
+
+/*
+ * Sync a cache to backing disk.
+ */
+static void cachefiles_sync_cache(struct cachefiles_cache *cache)
+{
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("%s", cache->cache->name);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disc */
+	cachefiles_begin_secure(cache, &saved_cred);
+	down_read(&cache->mnt->mnt_sb->s_umount);
+	ret = sync_filesystem(cache->mnt->mnt_sb);
+	up_read(&cache->mnt->mnt_sb->s_umount);
+	cachefiles_end_secure(cache, saved_cred);
+
+	if (ret == -EIO)
+		cachefiles_io_error(cache,
+				    "Attempt to sync backing fs superblock returned error %d",
+				    ret);
+}
+
+/*
+ * Withdraw cache objects.
+ */
+void cachefiles_withdraw_cache(struct cachefiles_cache *cache)
+{
+	struct fscache_cache *fscache = cache->cache;
+
+	pr_info("File cache on %s unregistering\n", fscache->name);
+
+	fscache_withdraw_cache(fscache);
+	cachefiles_withdraw_fscache_volumes(cache);
+
+	/* we now have to destroy all the active objects pertaining to this
+	 * cache - which we do by passing them off to thread pool to be
+	 * disposed of */
+	cachefiles_withdraw_objects(cache);
+	fscache_wait_for_objects(fscache);
+
+	cachefiles_withdraw_volumes(cache);
+	cachefiles_sync_cache(cache);
+	cache->cache = NULL;
+	fscache_relinquish_cache(fscache);
+}