Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs pile 4 from Al Viro:
 "list_lru pile, mostly"

This came out of Andrew's pile, Al ended up doing the merge work so that
Andrew didn't have to.

Additionally, a few fixes.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (42 commits)
  super: fix for destroy lrus
  list_lru: dynamically adjust node arrays
  shrinker: Kill old ->shrink API.
  shrinker: convert remaining shrinkers to count/scan API
  staging/lustre/libcfs: cleanup linux-mem.h
  staging/lustre/ptlrpc: convert to new shrinker API
  staging/lustre/obdclass: convert lu_object shrinker to count/scan API
  staging/lustre/ldlm: convert to shrinkers to count/scan API
  hugepage: convert huge zero page shrinker to new shrinker API
  i915: bail out earlier when shrinker cannot acquire mutex
  drivers: convert shrinkers to new count/scan API
  fs: convert fs shrinkers to new scan/count API
  xfs: fix dquot isolation hang
  xfs-convert-dquot-cache-lru-to-list_lru-fix
  xfs: convert dquot cache lru to list_lru
  xfs: rework buffer dispose list tracking
  xfs-convert-buftarg-lru-to-generic-code-fix
  xfs: convert buftarg LRU to generic code
  fs: convert inode and dentry shrinking to be node aware
  vmscan: per-node deferred work
  ...

28 files changed, 823 insertions, 666 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index dddc67fed73..1bd4614ce93 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -37,6 +37,7 @@
 #include <linux/rculist_bl.h>
 #include <linux/prefetch.h>
 #include <linux/ratelimit.h>
+#include <linux/list_lru.h>
 #include "internal.h"
 #include "mount.h"
 
@@ -48,7 +49,7 @@
  *   - the dcache hash table
  * s_anon bl list spinlock protects:
  *   - the s_anon list (see __d_drop)
- * dcache_lru_lock protects:
+ * dentry->d_sb->s_dentry_lru_lock protects:
  *   - the dcache lru lists and counters
  * d_lock protects:
  *   - d_flags
@@ -63,7 +64,7 @@
  * Ordering:
  * dentry->d_inode->i_lock
  *   dentry->d_lock
- *     dcache_lru_lock
+ *     dentry->d_sb->s_dentry_lru_lock
  *     dcache_hash_bucket lock
  *     s_anon lock
  *
@@ -81,7 +82,6 @@
 int sysctl_vfs_cache_pressure __read_mostly = 100;
 EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
 
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
 EXPORT_SYMBOL(rename_lock);
@@ -146,23 +146,47 @@ struct dentry_stat_t dentry_stat = {
 	.age_limit = 45,
 };
 
-static DEFINE_PER_CPU(unsigned int, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry_unused);
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-static int get_nr_dentry(void)
+
+/*
+ * Here we resort to our own counters instead of using generic per-cpu counters
+ * for consistency with what the vfs inode code does. We are expected to harvest
+ * better code and performance by having our own specialized counters.
+ *
+ * Please note that the loop is done over all possible CPUs, not over all online
+ * CPUs. The reason for this is that we don't want to play games with CPUs going
+ * on and off. If one of them goes off, we will just keep their counters.
+ *
+ * glommer: See cffbc8a for details, and if you ever intend to change this,
+ * please update all vfs counters to match.
+ */
+static long get_nr_dentry(void)
 {
 	int i;
-	int sum = 0;
+	long sum = 0;
 	for_each_possible_cpu(i)
 		sum += per_cpu(nr_dentry, i);
 	return sum < 0 ? 0 : sum;
 }
 
+static long get_nr_dentry_unused(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(nr_dentry_unused, i);
+	return sum < 0 ? 0 : sum;
+}
+
 int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
 		   size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
-	return proc_dointvec(table, write, buffer, lenp, ppos);
+	dentry_stat.nr_unused = get_nr_dentry_unused();
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #endif
 
@@ -333,52 +357,35 @@ static void dentry_unlink_inode(struct dentry * dentry)
 }
 
 /*
- * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
+ * dentry_lru_(add|del)_list) must be called with d_lock held.
  */
 static void dentry_lru_add(struct dentry *dentry)
 {
 	if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) {
-		spin_lock(&dcache_lru_lock);
+		if (list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
+			this_cpu_inc(nr_dentry_unused);
 		dentry->d_flags |= DCACHE_LRU_LIST;
-		list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
-		dentry->d_sb->s_nr_dentry_unused++;
-		dentry_stat.nr_unused++;
-		spin_unlock(&dcache_lru_lock);
 	}
 }
 
-static void __dentry_lru_del(struct dentry *dentry)
-{
-	list_del_init(&dentry->d_lru);
-	dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
-	dentry->d_sb->s_nr_dentry_unused--;
-	dentry_stat.nr_unused--;
-}
-
 /*
  * Remove a dentry with references from the LRU.
+ *
+ * If we are on the shrink list, then we can get to try_prune_one_dentry() and
+ * lose our last reference through the parent walk. In this case, we need to
+ * remove ourselves from the shrink list, not the LRU.
  */
 static void dentry_lru_del(struct dentry *dentry)
 {
-	if (!list_empty(&dentry->d_lru)) {
-		spin_lock(&dcache_lru_lock);
-		__dentry_lru_del(dentry);
-		spin_unlock(&dcache_lru_lock);
+	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
+		list_del_init(&dentry->d_lru);
+		dentry->d_flags &= ~DCACHE_SHRINK_LIST;
+		return;
 	}
-}
 
-static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
-{
-	spin_lock(&dcache_lru_lock);
-	if (list_empty(&dentry->d_lru)) {
-		dentry->d_flags |= DCACHE_LRU_LIST;
-		list_add_tail(&dentry->d_lru, list);
-		dentry->d_sb->s_nr_dentry_unused++;
-		dentry_stat.nr_unused++;
-	} else {
-		list_move_tail(&dentry->d_lru, list);
-	}
-	spin_unlock(&dcache_lru_lock);
+	if (list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru))
+		this_cpu_dec(nr_dentry_unused);
+	dentry->d_flags &= ~DCACHE_LRU_LIST;
 }
 
 /**
@@ -474,7 +481,8 @@ EXPORT_SYMBOL(d_drop);
  * If ref is non-zero, then decrement the refcount too.
  * Returns dentry requiring refcount drop, or NULL if we're done.
  */
-static inline struct dentry *dentry_kill(struct dentry *dentry)
+static inline struct dentry *
+dentry_kill(struct dentry *dentry, int unlock_on_failure)
 	__releases(dentry->d_lock)
 {
 	struct inode *inode;
@@ -483,8 +491,10 @@ static inline struct dentry *dentry_kill(struct dentry *dentry)
 	inode = dentry->d_inode;
 	if (inode && !spin_trylock(&inode->i_lock)) {
 relock:
-		spin_unlock(&dentry->d_lock);
-		cpu_relax();
+		if (unlock_on_failure) {
+			spin_unlock(&dentry->d_lock);
+			cpu_relax();
+		}
 		return dentry; /* try again with same dentry */
 	}
 	if (IS_ROOT(dentry))
@@ -567,7 +577,7 @@ repeat:
 	return;
 
 kill_it:
-	dentry = dentry_kill(dentry);
+	dentry = dentry_kill(dentry, 1);
 	if (dentry)
 		goto repeat;
 }
@@ -787,12 +797,12 @@ EXPORT_SYMBOL(d_prune_aliases);
  *
  * This may fail if locks cannot be acquired no problem, just try again.
  */
-static void try_prune_one_dentry(struct dentry *dentry)
+static struct dentry * try_prune_one_dentry(struct dentry *dentry)
 	__releases(dentry->d_lock)
 {
 	struct dentry *parent;
 
-	parent = dentry_kill(dentry);
+	parent = dentry_kill(dentry, 0);
 	/*
 	 * If dentry_kill returns NULL, we have nothing more to do.
 	 * if it returns the same dentry, trylocks failed. In either
@@ -804,17 +814,18 @@ static void try_prune_one_dentry(struct dentry *dentry)
 	 * fragmentation.
 	 */
 	if (!parent)
-		return;
+		return NULL;
 	if (parent == dentry)
-		return;
+		return dentry;
 
 	/* Prune ancestors. */
 	dentry = parent;
 	while (dentry) {
 		if (lockref_put_or_lock(&dentry->d_lockref))
-			return;
-		dentry = dentry_kill(dentry);
+			return NULL;
+		dentry = dentry_kill(dentry, 1);
 	}
+	return NULL;
 }
 
 static void shrink_dentry_list(struct list_head *list)
@@ -833,76 +844,143 @@ static void shrink_dentry_list(struct list_head *list)
 		}
 
 		/*
+		 * The dispose list is isolated and dentries are not accounted
+		 * to the LRU here, so we can simply remove it from the list
+		 * here regardless of whether it is referenced or not.
+		 */
+		list_del_init(&dentry->d_lru);
+		dentry->d_flags &= ~DCACHE_SHRINK_LIST;
+
+		/*
 		 * We found an inuse dentry which was not removed from
-		 * the LRU because of laziness during lookup.  Do not free
-		 * it - just keep it off the LRU list.
+		 * the LRU because of laziness during lookup. Do not free it.
 		 */
 		if (dentry->d_lockref.count) {
-			dentry_lru_del(dentry);
 			spin_unlock(&dentry->d_lock);
 			continue;
 		}
-
 		rcu_read_unlock();
 
-		try_prune_one_dentry(dentry);
+		dentry = try_prune_one_dentry(dentry);
 
 		rcu_read_lock();
+		if (dentry) {
+			dentry->d_flags |= DCACHE_SHRINK_LIST;
+			list_add(&dentry->d_lru, list);
+			spin_unlock(&dentry->d_lock);
+		}
 	}
 	rcu_read_unlock();
 }
 
+static enum lru_status
+dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+{
+	struct list_head *freeable = arg;
+	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
+
+
+	/*
+	 * we are inverting the lru lock/dentry->d_lock here,
+	 * so use a trylock. If we fail to get the lock, just skip
+	 * it
+	 */
+	if (!spin_trylock(&dentry->d_lock))
+		return LRU_SKIP;
+
+	/*
+	 * Referenced dentries are still in use. If they have active
+	 * counts, just remove them from the LRU. Otherwise give them
+	 * another pass through the LRU.
+	 */
+	if (dentry->d_lockref.count) {
+		list_del_init(&dentry->d_lru);
+		spin_unlock(&dentry->d_lock);
+		return LRU_REMOVED;
+	}
+
+	if (dentry->d_flags & DCACHE_REFERENCED) {
+		dentry->d_flags &= ~DCACHE_REFERENCED;
+		spin_unlock(&dentry->d_lock);
+
+		/*
+		 * The list move itself will be made by the common LRU code. At
+		 * this point, we've dropped the dentry->d_lock but keep the
+		 * lru lock. This is safe to do, since every list movement is
+		 * protected by the lru lock even if both locks are held.
+		 *
+		 * This is guaranteed by the fact that all LRU management
+		 * functions are intermediated by the LRU API calls like
+		 * list_lru_add and list_lru_del. List movement in this file
+		 * only ever occur through this functions or through callbacks
+		 * like this one, that are called from the LRU API.
+		 *
+		 * The only exceptions to this are functions like
+		 * shrink_dentry_list, and code that first checks for the
+		 * DCACHE_SHRINK_LIST flag.  Those are guaranteed to be
+		 * operating only with stack provided lists after they are
+		 * properly isolated from the main list.  It is thus, always a
+		 * local access.
+		 */
+		return LRU_ROTATE;
+	}
+
+	dentry->d_flags |= DCACHE_SHRINK_LIST;
+	list_move_tail(&dentry->d_lru, freeable);
+	this_cpu_dec(nr_dentry_unused);
+	spin_unlock(&dentry->d_lock);
+
+	return LRU_REMOVED;
+}
+
 /**
  * prune_dcache_sb - shrink the dcache
  * @sb: superblock
- * @count: number of entries to try to free
+ * @nr_to_scan : number of entries to try to free
+ * @nid: which node to scan for freeable entities
  *
- * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
  * done when we need more memory an called from the superblock shrinker
  * function.
  *
  * This function may fail to free any resources if all the dentries are in
  * use.
  */
-void prune_dcache_sb(struct super_block *sb, int count)
+long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
+		     int nid)
 {
-	struct dentry *dentry;
-	LIST_HEAD(referenced);
-	LIST_HEAD(tmp);
+	LIST_HEAD(dispose);
+	long freed;
 
-relock:
-	spin_lock(&dcache_lru_lock);
-	while (!list_empty(&sb->s_dentry_lru)) {
-		dentry = list_entry(sb->s_dentry_lru.prev,
-				struct dentry, d_lru);
-		BUG_ON(dentry->d_sb != sb);
-
-		if (!spin_trylock(&dentry->d_lock)) {
-			spin_unlock(&dcache_lru_lock);
-			cpu_relax();
-			goto relock;
-		}
+	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
+				       &dispose, &nr_to_scan);
+	shrink_dentry_list(&dispose);
+	return freed;
+}
 
-		if (dentry->d_flags & DCACHE_REFERENCED) {
-			dentry->d_flags &= ~DCACHE_REFERENCED;
-			list_move(&dentry->d_lru, &referenced);
-			spin_unlock(&dentry->d_lock);
-		} else {
-			list_move_tail(&dentry->d_lru, &tmp);
-			dentry->d_flags |= DCACHE_SHRINK_LIST;
-			spin_unlock(&dentry->d_lock);
-			if (!--count)
-				break;
-		}
-		cond_resched_lock(&dcache_lru_lock);
-	}
-	if (!list_empty(&referenced))
-		list_splice(&referenced, &sb->s_dentry_lru);
-	spin_unlock(&dcache_lru_lock);
+static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
+						spinlock_t *lru_lock, void *arg)
+{
+	struct list_head *freeable = arg;
+	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
 
-	shrink_dentry_list(&tmp);
+	/*
+	 * we are inverting the lru lock/dentry->d_lock here,
+	 * so use a trylock. If we fail to get the lock, just skip
+	 * it
+	 */
+	if (!spin_trylock(&dentry->d_lock))
+		return LRU_SKIP;
+
+	dentry->d_flags |= DCACHE_SHRINK_LIST;
+	list_move_tail(&dentry->d_lru, freeable);
+	this_cpu_dec(nr_dentry_unused);
+	spin_unlock(&dentry->d_lock);
+
+	return LRU_REMOVED;
 }
 
+
 /**
  * shrink_dcache_sb - shrink dcache for a superblock
  * @sb: superblock
@@ -912,16 +990,17 @@ relock:
  */
 void shrink_dcache_sb(struct super_block *sb)
 {
-	LIST_HEAD(tmp);
+	long freed;
 
-	spin_lock(&dcache_lru_lock);
-	while (!list_empty(&sb->s_dentry_lru)) {
-		list_splice_init(&sb->s_dentry_lru, &tmp);
-		spin_unlock(&dcache_lru_lock);
-		shrink_dentry_list(&tmp);
-		spin_lock(&dcache_lru_lock);
-	}
-	spin_unlock(&dcache_lru_lock);
+	do {
+		LIST_HEAD(dispose);
+
+		freed = list_lru_walk(&sb->s_dentry_lru,
+			dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+
+		this_cpu_sub(nr_dentry_unused, freed);
+		shrink_dentry_list(&dispose);
+	} while (freed > 0);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -1283,7 +1362,8 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
 	if (dentry->d_lockref.count) {
 		dentry_lru_del(dentry);
 	} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
-		dentry_lru_move_list(dentry, &data->dispose);
+		dentry_lru_del(dentry);
+		list_add_tail(&dentry->d_lru, &data->dispose);
 		dentry->d_flags |= DCACHE_SHRINK_LIST;
 		data->found++;
 		ret = D_WALK_NORETRY;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index c00e055b628..9fd702f5bfb 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -44,6 +44,7 @@ static void drop_slab(void)
 		.gfp_mask = GFP_KERNEL,
 	};
 
+	nodes_setall(shrink.nodes_to_scan);
 	do {
 		nr_objects = shrink_slab(&shrink, 1000, 1000);
 	} while (nr_objects > 10);
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 2d1bdbe78c0..3981ff78395 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -931,13 +931,15 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 	struct ext4_inode_info *ei;
 	struct list_head *cur, *tmp;
 	LIST_HEAD(skipped);
-	int ret, nr_shrunk = 0;
+	int nr_shrunk = 0;
 	int retried = 0, skip_precached = 1, nr_skipped = 0;
 
 	spin_lock(&sbi->s_es_lru_lock);
 
 retry:
 	list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+		int shrunk;
+
 		/*
 		 * If we have already reclaimed all extents from extent
 		 * status tree, just stop the loop immediately.
@@ -964,13 +966,13 @@ retry:
 			continue;
 
 		write_lock(&ei->i_es_lock);
-		ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
+		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
 		if (ei->i_es_lru_nr == 0)
 			list_del_init(&ei->i_es_lru);
 		write_unlock(&ei->i_es_lock);
 
-		nr_shrunk += ret;
-		nr_to_scan -= ret;
+		nr_shrunk += shrunk;
+		nr_to_scan -= shrunk;
 		if (nr_to_scan == 0)
 			break;
 	}
@@ -1007,7 +1009,20 @@ retry:
 	return nr_shrunk;
 }
 
-static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long ext4_es_count(struct shrinker *shrink,
+				   struct shrink_control *sc)
+{
+	unsigned long nr;
+	struct ext4_sb_info *sbi;
+
+	sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker);
+	nr = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+	trace_ext4_es_shrink_enter(sbi->s_sb, sc->nr_to_scan, nr);
+	return nr;
+}
+
+static unsigned long ext4_es_scan(struct shrinker *shrink,
+				  struct shrink_control *sc)
 {
 	struct ext4_sb_info *sbi = container_of(shrink,
 					struct ext4_sb_info, s_es_shrinker);
@@ -1022,9 +1037,8 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 
 	nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
 
-	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
 	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
-	return ret;
+	return nr_shrunk;
 }
 
 void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
@@ -1032,7 +1046,8 @@ void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 	INIT_LIST_HEAD(&sbi->s_es_lru);
 	spin_lock_init(&sbi->s_es_lru_lock);
 	sbi->s_es_last_sorted = 0;
-	sbi->s_es_shrinker.shrink = ext4_es_shrink;
+	sbi->s_es_shrinker.scan_objects = ext4_es_scan;
+	sbi->s_es_shrinker.count_objects = ext4_es_count;
 	sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
 	register_shrinker(&sbi->s_es_shrinker);
 }
@@ -1076,7 +1091,7 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 	struct ext4_es_tree *tree = &ei->i_es_tree;
 	struct rb_node *node;
 	struct extent_status *es;
-	int nr_shrunk = 0;
+	unsigned long nr_shrunk = 0;
 	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 722329cac98..c2f41b4d00b 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1427,21 +1427,22 @@ __acquires(&lru_lock)
  * gfs2_dispose_glock_lru() above.
  */
 
-static void gfs2_scan_glock_lru(int nr)
+static long gfs2_scan_glock_lru(int nr)
 {
 	struct gfs2_glock *gl;
 	LIST_HEAD(skipped);
 	LIST_HEAD(dispose);
+	long freed = 0;
 
 	spin_lock(&lru_lock);
-	while(nr && !list_empty(&lru_list)) {
+	while ((nr-- >= 0) && !list_empty(&lru_list)) {
 		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
 
 		/* Test for being demotable */
 		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
 			list_move(&gl->gl_lru, &dispose);
 			atomic_dec(&lru_count);
-			nr--;
+			freed++;
 			continue;
 		}
 
@@ -1451,23 +1452,28 @@ static void gfs2_scan_glock_lru(int nr)
 	if (!list_empty(&dispose))
 		gfs2_dispose_glock_lru(&dispose);
 	spin_unlock(&lru_lock);
+
+	return freed;
 }
 
-static int gfs2_shrink_glock_memory(struct shrinker *shrink,
-				    struct shrink_control *sc)
+static unsigned long gfs2_glock_shrink_scan(struct shrinker *shrink,
+					    struct shrink_control *sc)
 {
-	if (sc->nr_to_scan) {
-		if (!(sc->gfp_mask & __GFP_FS))
-			return -1;
-		gfs2_scan_glock_lru(sc->nr_to_scan);
-	}
+	if (!(sc->gfp_mask & __GFP_FS))
+		return SHRINK_STOP;
+	return gfs2_scan_glock_lru(sc->nr_to_scan);
+}
 
-	return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
+static unsigned long gfs2_glock_shrink_count(struct shrinker *shrink,
+					     struct shrink_control *sc)
+{
+	return vfs_pressure_ratio(atomic_read(&lru_count));
 }
 
 static struct shrinker glock_shrinker = {
-	.shrink = gfs2_shrink_glock_memory,
 	.seeks = DEFAULT_SEEKS,
+	.count_objects = gfs2_glock_shrink_count,
+	.scan_objects = gfs2_glock_shrink_scan,
 };
 
 /**
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 7b0f5043cf2..351586e24e3 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -32,7 +32,8 @@
 struct workqueue_struct *gfs2_control_wq;
 
 static struct shrinker qd_shrinker = {
-	.shrink = gfs2_shrink_qd_memory,
+	.count_objects = gfs2_qd_shrink_count,
+	.scan_objects = gfs2_qd_shrink_scan,
 	.seeks = DEFAULT_SEEKS,
 };
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3768c2f40e4..db441359ee8 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -75,17 +75,16 @@ static LIST_HEAD(qd_lru_list);
 static atomic_t qd_lru_count = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(qd_lru_lock);
 
-int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
+unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
+				  struct shrink_control *sc)
 {
 	struct gfs2_quota_data *qd;
 	struct gfs2_sbd *sdp;
 	int nr_to_scan = sc->nr_to_scan;
-
-	if (nr_to_scan == 0)
-		goto out;
+	long freed = 0;
 
 	if (!(sc->gfp_mask & __GFP_FS))
-		return -1;
+		return SHRINK_STOP;
 
 	spin_lock(&qd_lru_lock);
 	while (nr_to_scan && !list_empty(&qd_lru_list)) {
@@ -110,11 +109,16 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
 		kmem_cache_free(gfs2_quotad_cachep, qd);
 		spin_lock(&qd_lru_lock);
 		nr_to_scan--;
+		freed++;
 	}
 	spin_unlock(&qd_lru_lock);
+	return freed;
+}
 
-out:
-	return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
+unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
+				   struct shrink_control *sc)
+{
+	return vfs_pressure_ratio(atomic_read(&qd_lru_count));
 }
 
 static u64 qd2index(struct gfs2_quota_data *qd)
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 4f5e6e44ed8..0f64d9deb1b 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -53,8 +53,10 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
 	return ret;
 }
 
-extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
-				 struct shrink_control *sc);
+extern unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
+					  struct shrink_control *sc);
+extern unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
+					 struct shrink_control *sc);
 extern const struct quotactl_ops gfs2_quotactl_ops;
 
 #endif /* __QUOTA_DOT_H__ */
diff --git a/fs/inode.c b/fs/inode.c
index 93a0625b46e..b33ba8e021c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -17,6 +17,7 @@
 #include <linux/prefetch.h>
 #include <linux/buffer_head.h> /* for inode_has_buffers */
 #include <linux/ratelimit.h>
+#include <linux/list_lru.h>
 #include "internal.h"
 
 /*
@@ -24,7 +25,7 @@
  *
  * inode->i_lock protects:
  *   inode->i_state, inode->i_hash, __iget()
- * inode->i_sb->s_inode_lru_lock protects:
+ * Inode LRU list locks protect:
  *   inode->i_sb->s_inode_lru, inode->i_lru
  * inode_sb_list_lock protects:
  *   sb->s_inodes, inode->i_sb_list
@@ -37,7 +38,7 @@
  *
  * inode_sb_list_lock
  *   inode->i_lock
- *     inode->i_sb->s_inode_lru_lock
+ *     Inode LRU list locks
  *
  * bdi->wb.list_lock
  *   inode->i_lock
@@ -70,33 +71,33 @@ EXPORT_SYMBOL(empty_aops);
  */
 struct inodes_stat_t inodes_stat;
 
-static DEFINE_PER_CPU(unsigned int, nr_inodes);
-static DEFINE_PER_CPU(unsigned int, nr_unused);
+static DEFINE_PER_CPU(unsigned long, nr_inodes);
+static DEFINE_PER_CPU(unsigned long, nr_unused);
 
 static struct kmem_cache *inode_cachep __read_mostly;
 
-static int get_nr_inodes(void)
+static long get_nr_inodes(void)
 {
 	int i;
-	int sum = 0;
+	long sum = 0;
 	for_each_possible_cpu(i)
 		sum += per_cpu(nr_inodes, i);
 	return sum < 0 ? 0 : sum;
 }
 
-static inline int get_nr_inodes_unused(void)
+static inline long get_nr_inodes_unused(void)
 {
 	int i;
-	int sum = 0;
+	long sum = 0;
 	for_each_possible_cpu(i)
 		sum += per_cpu(nr_unused, i);
 	return sum < 0 ? 0 : sum;
 }
 
-int get_nr_dirty_inodes(void)
+long get_nr_dirty_inodes(void)
 {
 	/* not actually dirty inodes, but a wild approximation */
-	int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
+	long nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
 	return nr_dirty > 0 ? nr_dirty : 0;
 }
 
@@ -109,7 +110,7 @@ int proc_nr_inodes(ctl_table *table, int write,
 {
 	inodes_stat.nr_inodes = get_nr_inodes();
 	inodes_stat.nr_unused = get_nr_inodes_unused();
-	return proc_dointvec(table, write, buffer, lenp, ppos);
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #endif
 
@@ -401,13 +402,8 @@ EXPORT_SYMBOL(ihold);
 
 static void inode_lru_list_add(struct inode *inode)
 {
-	spin_lock(&inode->i_sb->s_inode_lru_lock);
-	if (list_empty(&inode->i_lru)) {
-		list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
-		inode->i_sb->s_nr_inodes_unused++;
+	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_inc(nr_unused);
-	}
-	spin_unlock(&inode->i_sb->s_inode_lru_lock);
 }
 
 /*
@@ -425,13 +421,9 @@ void inode_add_lru(struct inode *inode)
 
 static void inode_lru_list_del(struct inode *inode)
 {
-	spin_lock(&inode->i_sb->s_inode_lru_lock);
-	if (!list_empty(&inode->i_lru)) {
-		list_del_init(&inode->i_lru);
-		inode->i_sb->s_nr_inodes_unused--;
+
+	if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_dec(nr_unused);
-	}
-	spin_unlock(&inode->i_sb->s_inode_lru_lock);
 }
 
 /**
@@ -675,24 +667,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	return busy;
 }
 
-static int can_unuse(struct inode *inode)
-{
-	if (inode->i_state & ~I_REFERENCED)
-		return 0;
-	if (inode_has_buffers(inode))
-		return 0;
-	if (atomic_read(&inode->i_count))
-		return 0;
-	if (inode->i_data.nrpages)
-		return 0;
-	return 1;
-}
-
 /*
- * Walk the superblock inode LRU for freeable inodes and attempt to free them.
- * This is called from the superblock shrinker function with a number of inodes
- * to trim from the LRU. Inodes to be freed are moved to a temporary list and
- * then are freed outside inode_lock by dispose_list().
+ * Isolate the inode from the LRU in preparation for freeing it.
  *
  * Any inodes which are pinned purely because of attached pagecache have their
  * pagecache removed.  If the inode has metadata buffers attached to
@@ -706,89 +682,82 @@ static int can_unuse(struct inode *inode)
  * LRU does not have strict ordering. Hence we don't want to reclaim inodes
  * with this flag set because they are the inodes that are out of order.
  */
-void prune_icache_sb(struct super_block *sb, int nr_to_scan)
+static enum lru_status
+inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 {
-	LIST_HEAD(freeable);
-	int nr_scanned;
-	unsigned long reap = 0;
+	struct list_head *freeable = arg;
+	struct inode	*inode = container_of(item, struct inode, i_lru);
 
-	spin_lock(&sb->s_inode_lru_lock);
-	for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
-		struct inode *inode;
+	/*
+	 * we are inverting the lru lock/inode->i_lock here, so use a trylock.
+	 * If we fail to get the lock, just skip it.
+	 */
+	if (!spin_trylock(&inode->i_lock))
+		return LRU_SKIP;
 
-		if (list_empty(&sb->s_inode_lru))
-			break;
+	/*
+	 * Referenced or dirty inodes are still in use. Give them another pass
+	 * through the LRU as we canot reclaim them now.
+	 */
+	if (atomic_read(&inode->i_count) ||
+	    (inode->i_state & ~I_REFERENCED)) {
+		list_del_init(&inode->i_lru);
+		spin_unlock(&inode->i_lock);