Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

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");