mbcache2: reimplement mbcache

Original mbcache was designed to have more features than what ext?
filesystems ended up using. It supported entry being in more hashes, it
had a home-grown rwlocking of each entry, and one cache could cache
entries from multiple filesystems. This genericity also resulted in more
complex locking, larger cache entries, and generally more code
complexity.

This is reimplementation of the mbcache functionality to exactly fit the
purpose ext? filesystems use it for. Cache entries are now considerably
smaller (7 instead of 13 longs), the code is considerably smaller as
well (414 vs 913 lines of code), and IMO also simpler. The new code is
also much more lightweight.

I have measured the speed using artificial xattr-bench benchmark, which
spawns P processes, each process sets xattr for F different files, and
the value of xattr is randomly chosen from a pool of V values. Averages
of runtimes for 5 runs for various combinations of parameters are below.
The first value in each cell is old mbache, the second value is the new
mbcache.

V=10
F\P	1		2		4		8		16		32		64
10	0.158,0.157	0.208,0.196	0.500,0.277	0.798,0.400	3.258,0.584	13.807,1.047	61.339,2.803
100	0.172,0.167	0.279,0.222	0.520,0.275	0.825,0.341	2.981,0.505	12.022,1.202	44.641,2.943
1000	0.185,0.174	0.297,0.239	0.445,0.283	0.767,0.340	2.329,0.480	6.342,1.198	16.440,3.888

V=100
F\P	1		2		4		8		16		32		64
10	0.162,0.153	0.200,0.186	0.362,0.257	0.671,0.496	1.433,0.943	3.801,1.345	7.938,2.501
100	0.153,0.160	0.221,0.199	0.404,0.264	0.945,0.379	1.556,0.485	3.761,1.156	7.901,2.484
1000	0.215,0.191	0.303,0.246	0.471,0.288	0.960,0.347	1.647,0.479	3.916,1.176	8.058,3.160

V=1000
F\P	1		2		4		8		16		32		64
10	0.151,0.129	0.210,0.163	0.326,0.245	0.685,0.521	1.284,0.859	3.087,2.251	6.451,4.801
100	0.154,0.153	0.211,0.191	0.276,0.282	0.687,0.506	1.202,0.877	3.259,1.954	8.738,2.887
1000	0.145,0.179	0.202,0.222	0.449,0.319	0.899,0.333	1.577,0.524	4.221,1.240	9.782,3.579

V=10000
F\P	1		2		4		8		16		32		64
10	0.161,0.154	0.198,0.190	0.296,0.256	0.662,0.480	1.192,0.818	2.989,2.200	6.362,4.746
100	0.176,0.174	0.236,0.203	0.326,0.255	0.696,0.511	1.183,0.855	4.205,3.444	19.510,17.760
1000	0.199,0.183	0.240,0.227	1.159,1.014	2.286,2.154	6.023,6.039	---,10.933	---,36.620

V=100000
F\P	1		2		4		8		16		32		64
10	0.171,0.162	0.204,0.198	0.285,0.230	0.692,0.500	1.225,0.881	2.990,2.243	6.379,4.771
100	0.151,0.171	0.220,0.210	0.295,0.255	0.720,0.518	1.226,0.844	3.423,2.831	19.234,17.544
1000	0.192,0.189	0.249,0.225	1.162,1.043	2.257,2.093	5.853,4.997	---,10.399	---,32.198

We see that the new code is faster in pretty much all the cases and
starting from 4 processes there are significant gains with the new code
resulting in upto 20-times shorter runtimes. Also for large numbers of
cached entries all values for the old code could not be measured as the
kernel started hitting softlockups and died before the test completed.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
(cherry picked from commit f9a61eb4)
CVE-2015-8952
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Acked-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>

fs/Makefile

@@ -41,7 +41,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
 obj-$(CONFIG_BINFMT_FLAT)	+= binfmt_flat.o
 
-obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o
+obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o mbcache2.o
 obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_COREDUMP)		+= coredump.o

fs/mbcache2.c

+#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/mbcache2.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
+ * mb2_cache_entry_delete_block()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * They use hash of a block contents as a key and block number as a value.
+ * That's why keys need not be unique (different xattr blocks may end up having
+ * the same hash). However block number 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 mb2_cache {
+	/* Hash table of entries */
+	struct hlist_bl_head	*c_hash;
+	/* log2 of hash table size */
+	int			c_bucket_bits;
+	/* Protects c_lru_list, c_entry_count */
+	spinlock_t		c_lru_list_lock;
+	struct list_head	c_lru_list;
+	/* Number of entries in cache */
+	unsigned long		c_entry_count;
+	struct shrinker		c_shrink;
+};
+
+static struct kmem_cache *mb2_entry_cache;
+
+/*
+ * mb2_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
+ * @block - block that contains data
+ *
+ * Creates entry in @cache with key @key and records that data is stored in
+ * block @block. The function returns -EBUSY if entry with the same key
+ * and for the same block already exists in cache. Otherwise 0 is returned.
+ */
+int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key,
+			   sector_t block)
+{
+	struct mb2_cache_entry *entry, *dup;
+	struct hlist_bl_node *dup_node;
+	struct hlist_bl_head *head;
+
+	entry = kmem_cache_alloc(mb2_entry_cache, mask);
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->e_lru_list);
+	/* One ref for hash, one ref returned */
+	atomic_set(&entry->e_refcnt, 1);
+	entry->e_key = key;
+	entry->e_block = block;
+	head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	entry->e_hash_list_head = head;
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+		if (dup->e_key == key && dup->e_block == block) {
+			hlist_bl_unlock(head);
+			kmem_cache_free(mb2_entry_cache, entry);
+			return -EBUSY;
+		}
+	}
+	hlist_bl_add_head(&entry->e_hash_list, head);
+	hlist_bl_unlock(head);
+
+	spin_lock(&cache->c_lru_list_lock);
+	list_add_tail(&entry->e_lru_list, &cache->c_lru_list);
+	/* Grab ref for LRU list */
+	atomic_inc(&entry->e_refcnt);
+	cache->c_entry_count++;
+	spin_unlock(&cache->c_lru_list_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(mb2_cache_entry_create);
+
+void __mb2_cache_entry_free(struct mb2_cache_entry *entry)
+{
+	kmem_cache_free(mb2_entry_cache, entry);
+}
+EXPORT_SYMBOL(__mb2_cache_entry_free);
+
+static struct mb2_cache_entry *__entry_find(struct mb2_cache *cache,
+					    struct mb2_cache_entry *entry,
+					    u32 key)
+{
+	struct mb2_cache_entry *old_entry = entry;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+
+	if (entry)
+		head = entry->e_hash_list_head;
+	else
+		head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	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 mb2_cache_entry,
+				       e_hash_list);
+		if (entry->e_key == key) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
+		}
+		node = node->next;
+	}
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	if (old_entry)
+		mb2_cache_entry_put(cache, old_entry);
+
+	return entry;
+}
+
+/*
+ * mb2_cache_entry_find_first - find the first entry in cache with given key
+ * @cache: cache where we should search
+ * @key: key to look for
+ *
+ * Search in @cache for entry with key @key. Grabs reference to the first
+ * entry found and returns the entry.
+ */
+struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache,
+						   u32 key)
+{
+	return __entry_find(cache, NULL, key);
+}
+EXPORT_SYMBOL(mb2_cache_entry_find_first);
+
+/*
+ * mb2_cache_entry_find_next - find next entry in cache with the same
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next 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 entry in the hash chain. The function
+ * drops reference to @entry and returns with a reference to the found entry.
+ */
+struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache,
+						  struct mb2_cache_entry *entry)
+{
+	return __entry_find(cache, entry, entry->e_key);
+}
+EXPORT_SYMBOL(mb2_cache_entry_find_next);
+
+/* mb2_cache_entry_delete_block - remove information about block from cache
+ * @cache - cache we work with
+ * @key - key of the entry to remove
+ * @block - block containing data for @key
+ *
+ * Remove entry from cache @cache with key @key with data stored in @block.
+ */
+void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key,
+				  sector_t block)
+{
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb2_cache_entry *entry;
+
+	head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_lru_list_lock);
+			if (!list_empty(&entry->e_lru_list)) {
+				list_del_init(&entry->e_lru_list);
+				cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
+			}
+			spin_unlock(&cache->c_lru_list_lock);
+			mb2_cache_entry_put(cache, entry);
+			return;
+		}
+	}
+	hlist_bl_unlock(head);
+}
+EXPORT_SYMBOL(mb2_cache_entry_delete_block);
+
+/* mb2_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
+ *
+ * Move entry in lru list to reflect the fact that it was used.
+ */
+void mb2_cache_entry_touch(struct mb2_cache *cache,
+			   struct mb2_cache_entry *entry)
+{
+	spin_lock(&cache->c_lru_list_lock);
+	if (!list_empty(&entry->e_lru_list))
+		list_move_tail(&cache->c_lru_list, &entry->e_lru_list);
+	spin_unlock(&cache->c_lru_list_lock);
+}
+EXPORT_SYMBOL(mb2_cache_entry_touch);
+
+static unsigned long mb2_cache_count(struct shrinker *shrink,
+				     struct shrink_control *sc)
+{
+	struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
+					       c_shrink);
+
+	return cache->c_entry_count;
+}
+
+/* Shrink number of entries in cache */
+static unsigned long mb2_cache_scan(struct shrinker *shrink,
+				    struct shrink_control *sc)
+{
+	int nr_to_scan = sc->nr_to_scan;
+	struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
+					      c_shrink);
+	struct mb2_cache_entry *entry;
+	struct hlist_bl_head *head;
+	unsigned int shrunk = 0;
+
+	spin_lock(&cache->c_lru_list_lock);
+	while (nr_to_scan-- && !list_empty(&cache->c_lru_list)) {
+		entry = list_first_entry(&cache->c_lru_list,
+					 struct mb2_cache_entry, e_lru_list);
+		list_del_init(&entry->e_lru_list);
+		cache->c_entry_count--;
+		/*
+		 * We keep LRU list reference so that entry doesn't go away
+		 * from under us.
+		 */
+		spin_unlock(&cache->c_lru_list_lock);
+		head = entry->e_hash_list_head;
+		hlist_bl_lock(head);
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		}
+		hlist_bl_unlock(head);
+		if (mb2_cache_entry_put(cache, entry))
+			shrunk++;
+		cond_resched();
+		spin_lock(&cache->c_lru_list_lock);
+	}
+	spin_unlock(&cache->c_lru_list_lock);
+
+	return shrunk;
+}
+
+/*
+ * mb2_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
+ *
+ * Create cache for keys with 2^bucket_bits hash entries.
+ */
+struct mb2_cache *mb2_cache_create(int bucket_bits)
+{
+	struct mb2_cache *cache;
+	int bucket_count = 1 << bucket_bits;
+	int i;
+
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
+	cache = kzalloc(sizeof(struct mb2_cache), GFP_KERNEL);
+	if (!cache)
+		goto err_out;
+	cache->c_bucket_bits = bucket_bits;
+	INIT_LIST_HEAD(&cache->c_lru_list);
+	spin_lock_init(&cache->c_lru_list_lock);
+	cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
+				GFP_KERNEL);
+	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.count_objects = mb2_cache_count;
+	cache->c_shrink.scan_objects = mb2_cache_scan;
+	cache->c_shrink.seeks = DEFAULT_SEEKS;
+	register_shrinker(&cache->c_shrink);
+
+	return cache;
+
+err_out:
+	module_put(THIS_MODULE);
+	return NULL;
+}
+EXPORT_SYMBOL(mb2_cache_create);
+
+/*
+ * mb2_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 mb2_cache_destroy(struct mb2_cache *cache)
+{
+	struct mb2_cache_entry *entry, *next;
+
+	unregister_shrinker(&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_lru_list, e_lru_list) {
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		} else
+			WARN_ON(1);
+		list_del(&entry->e_lru_list);
+		WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+		mb2_cache_entry_put(cache, entry);
+	}
+	kfree(cache->c_hash);
+	kfree(cache);
+	module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL(mb2_cache_destroy);
+
+static int __init mb2cache_init(void)
+{
+	mb2_entry_cache = kmem_cache_create("mbcache",
+				sizeof(struct mb2_cache_entry), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	BUG_ON(!mb2_entry_cache);
+	return 0;
+}
+
+static void __exit mb2cache_exit(void)
+{
+	kmem_cache_destroy(mb2_entry_cache);
+}
+
+module_init(mb2cache_init)
+module_exit(mb2cache_exit)
+
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");

include/linux/mbcache2.h

+#ifndef _LINUX_MB2CACHE_H
+#define _LINUX_MB2CACHE_H
+
+#include <linux/hash.h>
+#include <linux/list_bl.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+#include <linux/fs.h>
+
+struct mb2_cache;
+
+struct mb2_cache_entry {
+	/* LRU list - protected by cache->c_lru_list_lock */
+	struct list_head	e_lru_list;
+	/* Hash table list - protected by bitlock in e_hash_list_head */
+	struct hlist_bl_node	e_hash_list;
+	atomic_t		e_refcnt;
+	/* Key in hash - stable during lifetime of the entry */
+	u32			e_key;
+	/* Block number of hashed block - stable during lifetime of the entry */
+	sector_t		e_block;
+	/* Head of hash list (for list bit lock) - stable */
+	struct hlist_bl_head	*e_hash_list_head;
+};
+
+struct mb2_cache *mb2_cache_create(int bucket_bits);
+void mb2_cache_destroy(struct mb2_cache *cache);
+
+int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key,
+			   sector_t block);
+void __mb2_cache_entry_free(struct mb2_cache_entry *entry);
+static inline int mb2_cache_entry_put(struct mb2_cache *cache,
+				      struct mb2_cache_entry *entry)
+{
+	if (!atomic_dec_and_test(&entry->e_refcnt))
+		return 0;
+	__mb2_cache_entry_free(entry);
+	return 1;
+}
+
+void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key,
+				  sector_t block);
+struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache,
+						   u32 key);
+struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache,
+						  struct mb2_cache_entry *entry);
+void mb2_cache_entry_touch(struct mb2_cache *cache,
+			   struct mb2_cache_entry *entry);
+
+#endif	/* _LINUX_MB2CACHE_H */