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, 444 insertions, 0 deletions

diff --git a/fs/mbcache.c b/fs/mbcache.c
new file mode 100644
index 000000000..2a6319b40
--- /dev/null
+++ b/fs/mbcache.c
@@ -0,0 +1,444 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/list_bl.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/mbcache.h>
+
+/*
+ * Mbcache is a simple key-value store. Keys need not be unique, however
+ * key-value pairs are expected to be unique (we use this fact in
+ * mb_cache_entry_delete_or_get()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * Ext4 also uses it for deduplication of xattr values stored in inodes.
+ * They use hash of data as a key and provide a value that may represent a
+ * block or inode number. That's why keys need not be unique (hash of different
+ * data may be the same). However user provided value always uniquely
+ * identifies a cache entry.
+ *
+ * We provide functions for creation and removal of entries, search by key,
+ * and a special "delete entry with given key-value pair" operation. Fixed
+ * size hash table is used for fast key lookups.
+ */
+
+struct mb_cache {
+	/* Hash table of entries */
+	struct hlist_bl_head	*c_hash;
+	/* log2 of hash table size */
+	int			c_bucket_bits;
+	/* Maximum entries in cache to avoid degrading hash too much */
+	unsigned long		c_max_entries;
+	/* Protects c_list, c_entry_count */
+	spinlock_t		c_list_lock;
+	struct list_head	c_list;
+	/* Number of entries in cache */
+	unsigned long		c_entry_count;
+	struct shrinker		*c_shrink;
+	/* Work for shrinking when the cache has too many entries */
+	struct work_struct	c_shrink_work;
+};
+
+static struct kmem_cache *mb_entry_cache;
+
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned long nr_to_scan);
+
+static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache,
+							u32 key)
+{
+	return &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+}
+
+/*
+ * Number of entries to reclaim synchronously when there are too many entries
+ * in cache
+ */
+#define SYNC_SHRINK_BATCH 64
+
+/*
+ * mb_cache_entry_create - create entry in cache
+ * @cache - cache where the entry should be created
+ * @mask - gfp mask with which the entry should be allocated
+ * @key - key of the entry
+ * @value - value of the entry
+ * @reusable - is the entry reusable by others?
+ *
+ * Creates entry in @cache with key @key and value @value. The function returns
+ * -EBUSY if entry with the same key and value already exists in cache.
+ * Otherwise 0 is returned.
+ */
+int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
+			  u64 value, bool reusable)
+{
+	struct mb_cache_entry *entry, *dup;
+	struct hlist_bl_node *dup_node;
+	struct hlist_bl_head *head;
+
+	/* Schedule background reclaim if there are too many entries */
+	if (cache->c_entry_count >= cache->c_max_entries)
+		schedule_work(&cache->c_shrink_work);
+	/* Do some sync reclaim if background reclaim cannot keep up */
+	if (cache->c_entry_count >= 2*cache->c_max_entries)
+		mb_cache_shrink(cache, SYNC_SHRINK_BATCH);
+
+	entry = kmem_cache_alloc(mb_entry_cache, mask);
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->e_list);
+	/*
+	 * We create entry with two references. One reference is kept by the
+	 * hash table, the other reference is used to protect us from
+	 * mb_cache_entry_delete_or_get() until the entry is fully setup. This
+	 * avoids nesting of cache->c_list_lock into hash table bit locks which
+	 * is problematic for RT.
+	 */
+	atomic_set(&entry->e_refcnt, 2);
+	entry->e_key = key;
+	entry->e_value = value;
+	entry->e_flags = 0;
+	if (reusable)
+		set_bit(MBE_REUSABLE_B, &entry->e_flags);
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+		if (dup->e_key == key && dup->e_value == value) {
+			hlist_bl_unlock(head);
+			kmem_cache_free(mb_entry_cache, entry);
+			return -EBUSY;
+		}
+	}
+	hlist_bl_add_head(&entry->e_hash_list, head);
+	hlist_bl_unlock(head);
+	spin_lock(&cache->c_list_lock);
+	list_add_tail(&entry->e_list, &cache->c_list);
+	cache->c_entry_count++;
+	spin_unlock(&cache->c_list_lock);
+	mb_cache_entry_put(cache, entry);
+
+	return 0;
+}
+EXPORT_SYMBOL(mb_cache_entry_create);
+
+void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry)
+{
+	struct hlist_bl_head *head;
+
+	head = mb_cache_entry_head(cache, entry->e_key);
+	hlist_bl_lock(head);
+	hlist_bl_del(&entry->e_hash_list);
+	hlist_bl_unlock(head);
+	kmem_cache_free(mb_entry_cache, entry);
+}
+EXPORT_SYMBOL(__mb_cache_entry_free);
+
+/*
+ * mb_cache_entry_wait_unused - wait to be the last user of the entry
+ *
+ * @entry - entry to work on
+ *
+ * Wait to be the last user of the entry.
+ */
+void mb_cache_entry_wait_unused(struct mb_cache_entry *entry)
+{
+	wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2);
+}
+EXPORT_SYMBOL(mb_cache_entry_wait_unused);
+
+static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
+					   struct mb_cache_entry *entry,
+					   u32 key)
+{
+	struct mb_cache_entry *old_entry = entry;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
+		node = entry->e_hash_list.next;
+	else
+		node = hlist_bl_first(head);
+	while (node) {
+		entry = hlist_bl_entry(node, struct mb_cache_entry,
+				       e_hash_list);
+		if (entry->e_key == key &&
+		    test_bit(MBE_REUSABLE_B, &entry->e_flags) &&
+		    atomic_inc_not_zero(&entry->e_refcnt))
+			goto out;
+		node = node->next;
+	}
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	if (old_entry)
+		mb_cache_entry_put(cache, old_entry);
+
+	return entry;
+}
+
+/*
+ * mb_cache_entry_find_first - find the first reusable entry with the given key
+ * @cache: cache where we should search
+ * @key: key to look for
+ *
+ * Search in @cache for a reusable entry with key @key. Grabs reference to the
+ * first reusable entry found and returns the entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
+						 u32 key)
+{
+	return __entry_find(cache, NULL, key);
+}
+EXPORT_SYMBOL(mb_cache_entry_find_first);
+
+/*
+ * mb_cache_entry_find_next - find next reusable entry with the same key
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next reusable entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races with the
+ * search), finds the first reusable entry in the hash chain. The function drops
+ * reference to @entry and returns with a reference to the found entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
+						struct mb_cache_entry *entry)
+{
+	return __entry_find(cache, entry, entry->e_key);
+}
+EXPORT_SYMBOL(mb_cache_entry_find_next);
+
+/*
+ * mb_cache_entry_get - get a cache entry by value (and key)
+ * @cache - cache we work with
+ * @key - key
+ * @value - value
+ */
+struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
+					  u64 value)
+{
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_value == value &&
+		    atomic_inc_not_zero(&entry->e_refcnt))
+			goto out;
+	}
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	return entry;
+}
+EXPORT_SYMBOL(mb_cache_entry_get);
+
+/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users
+ * @cache - cache we work with
+ * @key - key
+ * @value - value
+ *
+ * Remove entry from cache @cache with key @key and value @value. The removal
+ * happens only if the entry is unused. The function returns NULL in case the
+ * entry was successfully removed or there's no entry in cache. Otherwise the
+ * function grabs reference of the entry that we failed to delete because it
+ * still has users and return it.
+ */
+struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache,
+						    u32 key, u64 value)
+{
+	struct mb_cache_entry *entry;
+
+	entry = mb_cache_entry_get(cache, key, value);
+	if (!entry)
+		return NULL;
+
+	/*
+	 * Drop the ref we got from mb_cache_entry_get() and the initial hash
+	 * ref if we are the last user
+	 */
+	if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2)
+		return entry;
+
+	spin_lock(&cache->c_list_lock);
+	if (!list_empty(&entry->e_list))
+		list_del_init(&entry->e_list);
+	cache->c_entry_count--;
+	spin_unlock(&cache->c_list_lock);
+	__mb_cache_entry_free(cache, entry);
+	return NULL;
+}
+EXPORT_SYMBOL(mb_cache_entry_delete_or_get);
+
+/* mb_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
+ *
+ * Marks entry as used to give hit higher chances of surviving in cache.
+ */
+void mb_cache_entry_touch(struct mb_cache *cache,
+			  struct mb_cache_entry *entry)
+{
+	set_bit(MBE_REFERENCED_B, &entry->e_flags);
+}
+EXPORT_SYMBOL(mb_cache_entry_touch);
+
+static unsigned long mb_cache_count(struct shrinker *shrink,
+				    struct shrink_control *sc)
+{
+	struct mb_cache *cache = shrink->private_data;
+
+	return cache->c_entry_count;
+}
+
+/* Shrink number of entries in cache */
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned long nr_to_scan)
+{
+	struct mb_cache_entry *entry;
+	unsigned long shrunk = 0;
+
+	spin_lock(&cache->c_list_lock);
+	while (nr_to_scan-- && !list_empty(&cache->c_list)) {
+		entry = list_first_entry(&cache->c_list,
+					 struct mb_cache_entry, e_list);
+		/* Drop initial hash reference if there is no user */
+		if (test_bit(MBE_REFERENCED_B, &entry->e_flags) ||
+		    atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) {
+			clear_bit(MBE_REFERENCED_B, &entry->e_flags);
+			list_move_tail(&entry->e_list, &cache->c_list);
+			continue;
+		}
+		list_del_init(&entry->e_list);
+		cache->c_entry_count--;
+		spin_unlock(&cache->c_list_lock);
+		__mb_cache_entry_free(cache, entry);
+		shrunk++;
+		cond_resched();
+		spin_lock(&cache->c_list_lock);
+	}
+	spin_unlock(&cache->c_list_lock);
+
+	return shrunk;
+}
+
+static unsigned long mb_cache_scan(struct shrinker *shrink,
+				   struct shrink_control *sc)
+{
+	struct mb_cache *cache = shrink->private_data;
+	return mb_cache_shrink(cache, sc->nr_to_scan);
+}
+
+/* We shrink 1/X of the cache when we have too many entries in it */
+#define SHRINK_DIVISOR 16
+
+static void mb_cache_shrink_worker(struct work_struct *work)
+{
+	struct mb_cache *cache = container_of(work, struct mb_cache,
+					      c_shrink_work);
+	mb_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR);
+}
+
+/*
+ * mb_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
+ *
+ * Create cache for keys with 2^bucket_bits hash entries.
+ */
+struct mb_cache *mb_cache_create(int bucket_bits)
+{
+	struct mb_cache *cache;
+	unsigned long bucket_count = 1UL << bucket_bits;
+	unsigned long i;
+
+	cache = kzalloc_obj(struct mb_cache);
+	if (!cache)
+		goto err_out;
+	cache->c_bucket_bits = bucket_bits;
+	cache->c_max_entries = bucket_count << 4;
+	INIT_LIST_HEAD(&cache->c_list);
+	spin_lock_init(&cache->c_list_lock);
+	cache->c_hash = kmalloc_objs(struct hlist_bl_head, bucket_count);
+	if (!cache->c_hash) {
+		kfree(cache);
+		goto err_out;
+	}
+	for (i = 0; i < bucket_count; i++)
+		INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
+
+	cache->c_shrink = shrinker_alloc(0, "mbcache-shrinker");
+	if (!cache->c_shrink) {
+		kfree(cache->c_hash);
+		kfree(cache);
+		goto err_out;
+	}
+
+	cache->c_shrink->count_objects = mb_cache_count;
+	cache->c_shrink->scan_objects = mb_cache_scan;
+	cache->c_shrink->private_data = cache;
+
+	shrinker_register(cache->c_shrink);
+
+	INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker);
+
+	return cache;
+
+err_out:
+	return NULL;
+}
+EXPORT_SYMBOL(mb_cache_create);
+
+/*
+ * mb_cache_destroy - destroy cache
+ * @cache: the cache to destroy
+ *
+ * Free all entries in cache and cache itself. Caller must make sure nobody
+ * (except shrinker) can reach @cache when calling this.
+ */
+void mb_cache_destroy(struct mb_cache *cache)
+{
+	struct mb_cache_entry *entry, *next;
+
+	cancel_work_sync(&cache->c_shrink_work);
+	shrinker_free(cache->c_shrink);
+
+	/*
+	 * We don't bother with any locking. Cache must not be used at this
+	 * point.
+	 */
+	list_for_each_entry_safe(entry, next, &cache->c_list, e_list) {
+		list_del(&entry->e_list);
+		WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+		mb_cache_entry_put(cache, entry);
+	}
+	kfree(cache->c_hash);
+	kfree(cache);
+}
+EXPORT_SYMBOL(mb_cache_destroy);
+
+static int __init mbcache_init(void)
+{
+	mb_entry_cache = KMEM_CACHE(mb_cache_entry, SLAB_RECLAIM_ACCOUNT);
+	if (!mb_entry_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+static void __exit mbcache_exit(void)
+{
+	kmem_cache_destroy(mb_entry_cache);
+}
+
+module_init(mbcache_init)
+module_exit(mbcache_exit)
+
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");