inode: convert inode lru list to generic lru list code.

[glommer@openvz.org: adapted for new LRU return codes]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Carlos Maiolino <cmaiolino@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Rientjes <rientjes@google.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: J. Bruce Fields <bfields@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

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
@@ -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
@@ -706,90 +682,79 @@ 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.
  */
-long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan)
+static enum lru_status
+inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 {
-	LIST_HEAD(freeable);
-	long nr_scanned;
-	long freed = 0;
-	unsigned long reap = 0;
-
-	spin_lock(&sb->s_inode_lru_lock);
-	for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
-		struct inode *inode;
-
-		if (list_empty(&sb->s_inode_lru))
-			break;
-
-		inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
+	struct list_head *freeable = arg;
+	struct inode	*inode = container_of(item, struct inode, i_lru);
 
 	/*
-		 * we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
-		 * so use a trylock. If we fail to get the lock, just move the
-		 * inode to the back of the list so we don't spin on it.
+	 * 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)) {
-			list_move(&inode->i_lru, &sb->s_inode_lru);
-			continue;
-		}
+	if (!spin_trylock(&inode->i_lock))
+		return LRU_SKIP;
 
 	/*
-		 * Referenced or dirty inodes are still in use. Give them
-		 * another pass through the LRU as we canot reclaim them now.
+	 * 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);
-			sb->s_nr_inodes_unused--;
 		this_cpu_dec(nr_unused);
-			continue;
+		return LRU_REMOVED;
 	}
 
 	/* recently referenced inodes get one more pass */
 	if (inode->i_state & I_REFERENCED) {
 		inode->i_state &= ~I_REFERENCED;
-			list_move(&inode->i_lru, &sb->s_inode_lru);
 		spin_unlock(&inode->i_lock);
-			continue;
+		return LRU_ROTATE;
 	}
+
 	if (inode_has_buffers(inode) || inode->i_data.nrpages) {
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-			spin_unlock(&sb->s_inode_lru_lock);
-			if (remove_inode_buffers(inode))
-				reap += invalidate_mapping_pages(&inode->i_data,
-								0, -1);
-			iput(inode);
-			spin_lock(&sb->s_inode_lru_lock);
-
-			if (inode != list_entry(sb->s_inode_lru.next,
-						struct inode, i_lru))
-				continue;	/* wrong inode or list_empty */
-			/* avoid lock inversions with trylock */
-			if (!spin_trylock(&inode->i_lock))
-				continue;
-			if (!can_unuse(inode)) {
-				spin_unlock(&inode->i_lock);
-				continue;
+		spin_unlock(lru_lock);
+		if (remove_inode_buffers(inode)) {
+			unsigned long reap;
+			reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
+			if (current_is_kswapd())
+				__count_vm_events(KSWAPD_INODESTEAL, reap);
+			else
+				__count_vm_events(PGINODESTEAL, reap);
+			if (current->reclaim_state)
+				current->reclaim_state->reclaimed_slab += reap;
 		}
+		iput(inode);
+		spin_lock(lru_lock);
+		return LRU_RETRY;
 	}
+
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
 	spin_unlock(&inode->i_lock);
 
-		list_move(&inode->i_lru, &freeable);
-		sb->s_nr_inodes_unused--;
+	list_move(&inode->i_lru, freeable);
 	this_cpu_dec(nr_unused);
-		freed++;
-	}
-	if (current_is_kswapd())
-		__count_vm_events(KSWAPD_INODESTEAL, reap);
-	else
-		__count_vm_events(PGINODESTEAL, reap);
-	spin_unlock(&sb->s_inode_lru_lock);
-	if (current->reclaim_state)
-		current->reclaim_state->reclaimed_slab += reap;
+	return LRU_REMOVED;
+}
+
+/*
+ * 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().
+ */
+long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan)
+{
+	LIST_HEAD(freeable);
+	long freed;
 
+	freed = list_lru_walk(&sb->s_inode_lru, inode_lru_isolate,
+						&freeable, nr_to_scan);
 	dispose_list(&freeable);
 	return freed;
 }

fs/super.c

@@ -78,14 +78,13 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	if (sb->s_op->nr_cached_objects)
 		fs_objects = sb->s_op->nr_cached_objects(sb);
 
-	total_objects = sb->s_nr_dentry_unused +
-			sb->s_nr_inodes_unused + fs_objects + 1;
+	inodes = list_lru_count(&sb->s_inode_lru);
+	total_objects = sb->s_nr_dentry_unused + inodes + fs_objects + 1;
 
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, sb->s_nr_dentry_unused,
 								total_objects);
-	inodes = mult_frac(sc->nr_to_scan, sb->s_nr_inodes_unused,
-								total_objects);
+	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
 
 	/*
 	 * prune the dcache first as the icache is pinned by it, then
@@ -119,7 +118,7 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 		total_objects = sb->s_op->nr_cached_objects(sb);
 
 	total_objects += sb->s_nr_dentry_unused;
-	total_objects += sb->s_nr_inodes_unused;
+	total_objects += list_lru_count(&sb->s_inode_lru);
 
 	total_objects = vfs_pressure_ratio(total_objects);
 	drop_super(sb);
@@ -194,8 +193,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		INIT_LIST_HEAD(&s->s_inodes);
 		INIT_LIST_HEAD(&s->s_dentry_lru);
 		spin_lock_init(&s->s_dentry_lru_lock);
-		INIT_LIST_HEAD(&s->s_inode_lru);
-		spin_lock_init(&s->s_inode_lru_lock);
+		list_lru_init(&s->s_inode_lru);
 		INIT_LIST_HEAD(&s->s_mounts);
 		init_rwsem(&s->s_umount);
 		lockdep_set_class(&s->s_umount, &type->s_umount_key);

include/linux/fs.h

@@ -10,6 +10,7 @@
 #include <linux/stat.h>
 #include <linux/cache.h>
 #include <linux/list.h>
+#include <linux/list_lru.h>
 #include <linux/llist.h>
 #include <linux/radix-tree.h>
 #include <linux/rbtree.h>
@@ -1275,10 +1276,7 @@ struct super_block {
 	struct list_head	s_dentry_lru;	/* unused dentry lru */
 	long			s_nr_dentry_unused;	/* # of dentry on lru */
 
-	/* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
-	spinlock_t		s_inode_lru_lock ____cacheline_aligned_in_smp;
-	struct list_head	s_inode_lru;		/* unused inode lru */
-	long			s_nr_inodes_unused;	/* # of inodes on lru */
+	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
 
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;