[PATCH v3 4/4] vfs: Use dlock list for superblock's inode list

[Waiman Long]

When many threads are trying to add or delete inode to or from
a superblock's s_inodes list, spinlock contention on the list can
become a performance bottleneck.

This patch changes the s_inodes field to become a dlock list which
is a distributed set of lists with per-list spinlocks.  As a result,
the following superblock inode list (sb->s_inodes) iteration functions
in vfs are also being modified:

 1. iterate_bdevs()
 2. drop_pagecache_sb()
 3. wait_sb_inodes()
 4. evict_inodes()
 5. invalidate_inodes()
 6. fsnotify_unmount_inodes()
 7. add_dquot_ref()
 8. remove_dquot_ref()

With an exit microbenchmark that creates a large number of threads,
attachs many inodes to them and then exits. The runtimes of that
microbenchmark with 1000 threads before and after the patch on a
4-socket Intel E7-4820 v3 system (40 cores, 80 threads) were as
follows:

  Kernel            Elapsed Time    System Time
  ------            ------------    -----------
  Vanilla 4.5-rc4      65.29s         82m14s
  Patched 4.5-rc4      22.81s         23m03s

Before the patch, spinlock contention at the inode_sb_list_add()
function at the startup phase and the inode_sb_list_del() function at
the exit phase were about 79% and 93% of total CPU time respectively
(as measured by perf). After the patch, the dlock_list_add()
function consumed only about 0.04% of CPU time at startup phase. The
dlock_list_del() function consumed about 0.4% of CPU time at exit
phase. There were still some spinlock contention, but they happened
elsewhere.

Signed-off-by: Waiman Long <Waiman.Long@xxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
---
 fs/block_dev.c         |   13 +++++++------
 fs/drop_caches.c       |   10 +++++-----
 fs/fs-writeback.c      |   13 +++++++------
 fs/inode.c             |   36 +++++++++++++++---------------------
 fs/notify/inode_mark.c |   10 +++++-----
 fs/quota/dquot.c       |   16 ++++++++--------
 fs/super.c             |    7 ++++---
 include/linux/fs.h     |    8 ++++----
 8 files changed, 55 insertions(+), 58 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 71ccab1..f410c62 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1896,11 +1896,13 @@ EXPORT_SYMBOL(__invalidate_device);
 void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 {
 	struct inode *inode, *old_inode = NULL;
+	DEFINE_DLOCK_LIST_ITER(iter);
 
-	spin_lock(&blockdev_superblock->s_inode_list_lock);
-	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
-		struct address_space *mapping = inode->i_mapping;
+	while (dlock_list_next(&blockdev_superblock->s_inodes, &iter)) {
+		struct address_space *mapping;
 
+		inode   = list_entry(iter.curr, struct inode, i_sb_list);
+		mapping = inode->i_mapping;
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
 		    mapping->nrpages == 0) {
@@ -1909,7 +1911,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&blockdev_superblock->s_inode_list_lock);
+		spin_unlock(iter.lock);
 		/*
 		 * We hold a reference to 'inode' so it couldn't have been
 		 * removed from s_inodes list while we dropped the
@@ -1923,8 +1925,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 
 		func(I_BDEV(inode), arg);
 
-		spin_lock(&blockdev_superblock->s_inode_list_lock);
+		spin_lock(iter.lock);
 	}
-	spin_unlock(&blockdev_superblock->s_inode_list_lock);
 	iput(old_inode);
 }
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index d72d52b..2fcd19d 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -16,9 +16,10 @@ int sysctl_drop_caches;
 static void drop_pagecache_sb(struct super_block *sb, void *unused)
 {
 	struct inode *inode, *toput_inode = NULL;
+	DEFINE_DLOCK_LIST_ITER(iter);
 
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		spin_lock(&inode->i_lock);
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
 		    (inode->i_mapping->nrpages == 0)) {
@@ -27,15 +28,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
+		spin_unlock(iter.lock);
 
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
 
-		spin_lock(&sb->s_inode_list_lock);
+		spin_lock(iter.lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 	iput(toput_inode);
 }
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 989a2ce..7258aab 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2155,6 +2155,7 @@ EXPORT_SYMBOL(__mark_inode_dirty);
 static void wait_sb_inodes(struct super_block *sb)
 {
 	struct inode *inode, *old_inode = NULL;
+	DEFINE_DLOCK_LIST_ITER(iter);
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -2163,7 +2164,6 @@ static void wait_sb_inodes(struct super_block *sb)
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	mutex_lock(&sb->s_sync_lock);
-	spin_lock(&sb->s_inode_list_lock);
 
 	/*
 	 * Data integrity sync. Must wait for all pages under writeback,
@@ -2172,9 +2172,11 @@ static void wait_sb_inodes(struct super_block *sb)
 	 * In which case, the inode may not be on the dirty list, but
 	 * we still have to wait for that writeout.
 	 */
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		struct address_space *mapping = inode->i_mapping;
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
+		struct address_space *mapping;
 
+		inode   = list_entry(iter.curr, struct inode, i_sb_list);
+		mapping = inode->i_mapping;
 		spin_lock(&inode->i_lock);
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
 		    (mapping->nrpages == 0)) {
@@ -2183,7 +2185,7 @@ static void wait_sb_inodes(struct super_block *sb)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
+		spin_unlock(iter.lock);
 
 		/*
 		 * We hold a reference to 'inode' so it couldn't have been
@@ -2205,9 +2207,8 @@ static void wait_sb_inodes(struct super_block *sb)
 
 		cond_resched();
 
-		spin_lock(&sb->s_inode_list_lock);
+		spin_lock(iter.lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 	iput(old_inode);
 	mutex_unlock(&sb->s_sync_lock);
 }
diff --git a/fs/inode.c b/fs/inode.c
index 8204813..c048ab3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -28,7 +28,7 @@
  *   inode->i_state, inode->i_hash, __iget()
  * Inode LRU list locks protect:
  *   inode->i_sb->s_inode_lru, inode->i_lru
- * inode->i_sb->s_inode_list_lock protects:
+ * inode->i_sb->s_inodes->head->lock protects:
  *   inode->i_sb->s_inodes, inode->i_sb_list
  * bdi->wb.list_lock protects:
  *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
@@ -37,7 +37,7 @@
  *
  * Lock ordering:
  *
- * inode->i_sb->s_inode_list_lock
+ * inode->i_sb->s_inodes->head->lock
  *   inode->i_lock
  *     Inode LRU list locks
  *
@@ -45,7 +45,7 @@
  *   inode->i_lock
  *
  * inode_hash_lock
- *   inode->i_sb->s_inode_list_lock
+ *   inode->i_sb->s_inodes->head->lock
  *   inode->i_lock
  *
  * iunique_lock
@@ -431,19 +431,14 @@ static void inode_lru_list_del(struct inode *inode)
  */
 void inode_sb_list_add(struct inode *inode)
 {
-	spin_lock(&inode->i_sb->s_inode_list_lock);
-	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
-	spin_unlock(&inode->i_sb->s_inode_list_lock);
+	dlock_list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
 }
 EXPORT_SYMBOL_GPL(inode_sb_list_add);
 
 static inline void inode_sb_list_del(struct inode *inode)
 {
-	if (!list_empty(&inode->i_sb_list)) {
-		spin_lock(&inode->i_sb->s_inode_list_lock);
-		list_del_init(&inode->i_sb_list);
-		spin_unlock(&inode->i_sb->s_inode_list_lock);
-	}
+	if (!list_empty(&inode->i_sb_list.list))
+		dlock_list_del(&inode->i_sb_list);
 }
 
 static unsigned long hash(struct super_block *sb, unsigned long hashval)
@@ -598,11 +593,13 @@ static void dispose_list(struct list_head *head)
 void evict_inodes(struct super_block *sb)
 {
 	struct inode *inode;
+	struct dlock_list_iter iter;
 	LIST_HEAD(dispose);
 
 again:
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	init_dlock_list_iter(&iter);
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		if (atomic_read(&inode->i_count))
 			continue;
 
@@ -623,13 +620,12 @@ again:
 		 * bit so we don't livelock.
 		 */
 		if (need_resched()) {
-			spin_unlock(&sb->s_inode_list_lock);
+			spin_unlock(iter.lock);
 			cond_resched();
 			dispose_list(&dispose);
 			goto again;
 		}
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
 }
@@ -649,9 +645,10 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	int busy = 0;
 	struct inode *inode;
 	LIST_HEAD(dispose);
+	DEFINE_DLOCK_LIST_ITER(iter);
 
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
 			spin_unlock(&inode->i_lock);
@@ -673,7 +670,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 		spin_unlock(&inode->i_lock);
 		list_add(&inode->i_lru, &dispose);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
 
@@ -888,7 +884,7 @@ struct inode *new_inode_pseudo(struct super_block *sb)
 		spin_lock(&inode->i_lock);
 		inode->i_state = 0;
 		spin_unlock(&inode->i_lock);
-		INIT_LIST_HEAD(&inode->i_sb_list);
+		init_dlock_list_node(&inode->i_sb_list);
 	}
 	return inode;
 }
@@ -909,8 +905,6 @@ struct inode *new_inode(struct super_block *sb)
 {
 	struct inode *inode;
 
-	spin_lock_prefetch(&sb->s_inode_list_lock);
-
 	inode = new_inode_pseudo(sb);
 	if (inode)
 		inode_sb_list_add(inode);
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index a364524..6e4e8b8 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -151,14 +151,15 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 void fsnotify_unmount_inodes(struct super_block *sb)
 {
 	struct inode *inode, *iput_inode = NULL;
+	DEFINE_DLOCK_LIST_ITER(iter);
 
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
 		/*
 		 * We cannot __iget() an inode in state I_FREEING,
 		 * I_WILL_FREE, or I_NEW which is fine because by that point
 		 * the inode cannot have any associated watches.
 		 */
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
 			spin_unlock(&inode->i_lock);
@@ -178,7 +179,7 @@ void fsnotify_unmount_inodes(struct super_block *sb)
 
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
+		spin_unlock(iter.lock);
 
 		if (iput_inode)
 			iput(iput_inode);
@@ -190,9 +191,8 @@ void fsnotify_unmount_inodes(struct super_block *sb)
 
 		iput_inode = inode;
 
-		spin_lock(&sb->s_inode_list_lock);
+		spin_lock(iter.lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 
 	if (iput_inode)
 		iput(iput_inode);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index ff21980..b55f396 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -936,12 +936,13 @@ static int dqinit_needed(struct inode *inode, int type)
 static void add_dquot_ref(struct super_block *sb, int type)
 {
 	struct inode *inode, *old_inode = NULL;
+	DEFINE_DLOCK_LIST_ITER(iter);
 #ifdef CONFIG_QUOTA_DEBUG
 	int reserved = 0;
 #endif
 
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		spin_lock(&inode->i_lock);
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
 		    !atomic_read(&inode->i_writecount) ||
@@ -951,7 +952,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
+		spin_unlock(iter.lock);
 
 #ifdef CONFIG_QUOTA_DEBUG
 		if (unlikely(inode_get_rsv_space(inode) > 0))
@@ -969,9 +970,8 @@ static void add_dquot_ref(struct super_block *sb, int type)
 		 * later.
 		 */
 		old_inode = inode;
-		spin_lock(&sb->s_inode_list_lock);
+		spin_lock(iter.lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 	iput(old_inode);
 
 #ifdef CONFIG_QUOTA_DEBUG
@@ -1039,15 +1039,16 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 {
 	struct inode *inode;
 	int reserved = 0;
+	DEFINE_DLOCK_LIST_ITER(iter);
 
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (dlock_list_next(&sb->s_inodes, &iter)) {
 		/*
 		 *  We have to scan also I_NEW inodes because they can already
 		 *  have quota pointer initialized. Luckily, we need to touch
 		 *  only quota pointers and these have separate locking
 		 *  (dq_data_lock).
 		 */
+		inode = list_entry(iter.curr, struct inode, i_sb_list);
 		spin_lock(&dq_data_lock);
 		if (!IS_NOQUOTA(inode)) {
 			if (unlikely(inode_get_rsv_space(inode) > 0))
@@ -1056,7 +1057,6 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 		}
 		spin_unlock(&dq_data_lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
 #ifdef CONFIG_QUOTA_DEBUG
 	if (reserved) {
 		printk(KERN_WARNING "VFS (%s): Writes happened after quota"
diff --git a/fs/super.c b/fs/super.c
index d78b984..4c33204 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -163,6 +163,7 @@ static void destroy_super(struct super_block *s)
 {
 	list_lru_destroy(&s->s_dentry_lru);
 	list_lru_destroy(&s->s_inode_lru);
+	free_dlock_list_head(&s->s_inodes);
 	security_sb_free(s);
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
@@ -204,9 +205,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	mutex_init(&s->s_sync_lock);
-	INIT_LIST_HEAD(&s->s_inodes);
-	spin_lock_init(&s->s_inode_list_lock);
 
+	if (alloc_dlock_list_head(&s->s_inodes))
+		goto fail;
 	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
 	if (list_lru_init_memcg(&s->s_inode_lru))
@@ -427,7 +428,7 @@ void generic_shutdown_super(struct super_block *sb)
 		if (sop->put_super)
 			sop->put_super(sb);
 
-		if (!list_empty(&sb->s_inodes)) {
+		if (!dlock_list_empty(&sb->s_inodes)) {
 			printk("VFS: Busy inodes after unmount of %s. "
 			   "Self-destruct in 5 seconds.  Have a nice day...\n",
 			   sb->s_id);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dd28814..d5233ec 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -32,6 +32,7 @@
 #include <linux/workqueue.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/delayed_call.h>
+#include <linux/dlock-list.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -664,7 +665,7 @@ struct inode {
 	u16			i_wb_frn_history;
 #endif
 	struct list_head	i_lru;		/* inode LRU list */
-	struct list_head	i_sb_list;
+	struct dlock_list_node	i_sb_list;
 	union {
 		struct hlist_head	i_dentry;
 		struct rcu_head		i_rcu;
@@ -1445,9 +1446,8 @@ struct super_block {
 	 */
 	int s_stack_depth;
 
-	/* s_inode_list_lock protects s_inodes */
-	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
-	struct list_head	s_inodes;	/* all inodes */
+	/* The internal percpu locks protect s_inodes */
+	struct dlock_list_head s_inodes;	/* all inodes */
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
-- 
1.7.1