list_lru: introduce list_lru_shrink_{count,walk}

Kmem accounting of memcg is unusable now, because it lacks slab shrinker
support. That means when we hit the limit we will get ENOMEM w/o any
chance to recover. What we should do then is to call shrink_slab, which
would reclaim old inode/dentry caches from this cgroup. This is what
this patch set is intended to do.

Basically, it does two things. First, it introduces the notion of
per-memcg slab shrinker. A shrinker that wants to reclaim objects per
cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be
passed the memory cgroup to scan from in shrink_control->memcg. For
such shrinkers shrink_slab iterates over the whole cgroup subtree under
the target cgroup and calls the shrinker for each kmem-active memory
cgroup.

Secondly, this patch set makes the list_lru structure per-memcg. It's
done transparently to list_lru users - everything they have to do is to
tell list_lru_init that they want memcg-aware list_lru. Then the
list_lru will automatically distribute objects among per-memcg lists
basing on which cgroup the object is accounted to. This way to make FS
shrinkers (icache, dcache) memcg-aware we only need to make them use
memcg-aware list_lru, and this is what this patch set does.

As before, this patch set only enables per-memcg kmem reclaim when the
pressure goes from memory.limit, not from memory.kmem.limit. Handling
memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and
it is still unclear whether we will have this knob in the unified
hierarchy.

This patch (of 9):

NUMA aware slab shrinkers use the list_lru structure to distribute
objects coming from different NUMA nodes to different lists. Whenever
such a shrinker needs to count or scan objects from a particular node,
it issues commands like this:

count = list_lru_count_node(lru, sc->nid);
freed = list_lru_walk_node(lru, sc->nid, isolate_func,
isolate_arg, &sc->nr_to_scan);

where sc is an instance of the shrink_control structure passed to it
from vmscan.

To simplify this, let's add special list_lru functions to be used by
shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which
consolidate the nid and nr_to_scan arguments in the shrink_control
structure.

This will also allow us to avoid patching shrinkers that use list_lru
when we make shrink_slab() per-memcg - all we will have to do is extend
the shrink_control structure to include the target memcg and make
list_lru_shrink_{count,walk} handle this appropriately.

Signed-off-by: Vladimir Davydov <[e-mail]>
Suggested-by: Dave Chinner <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Greg Thelen <[e-mail]>
Cc: Glauber Costa <[e-mail]>
Cc: Alexander Viro <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: Pekka Enberg <[e-mail]>
Cc: David Rientjes <[e-mail]>
Cc: Joonsoo Kim <[e-mail]>
Cc: Tejun Heo <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

fs/dcache.c

···
 /**
  * prune_dcache_sb - shrink the dcache
  * @sb: superblock
- * @nr_to_scan : number of entries to try to free
- * @nid: which node to scan for freeable entities
+ * @sc: shrink control, passed to list_lru_shrink_walk()
  *
- * 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
+ * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
+ * is done when we need more memory and called from the superblock shrinker
  * function.
  *
  * This function may fail to free any resources if all the dentries are in
  * use.
  */
-long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(dispose);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
+				     dentry_lru_isolate, &dispose);
 	shrink_dentry_list(&dispose);
 	return freed;
 }

fs/gfs2/quota.c

···
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
-				   &dispose, &sc->nr_to_scan);
+	freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
+				     gfs2_qd_isolate, &dispose);
 
 	gfs2_qd_dispose(&dispose);
 
···
 static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
 					  struct shrink_control *sc)
 {
-	return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
+	return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
 }
 
 struct shrinker gfs2_qd_shrinker = {

fs/inode.c

···
  * 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,
-		     int nid)
+long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(freeable);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
-				       &freeable, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
+				     inode_lru_isolate, &freeable);
 	dispose_list(&freeable);
 	return freed;
 }

fs/internal.h

···
 struct linux_binprm;
 struct path;
 struct mount;
+struct shrink_control;
 
 /*
  * block_dev.c
···
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
 extern void inode_add_lru(struct inode *inode);
 
 /*
···
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern int d_set_mounted(struct dentry *dentry);
-extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
 
 /*
  * read_write.c

fs/super.c

···
 	if (sb->s_op->nr_cached_objects)
 		fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
 
-	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
-	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
 	total_objects = dentries + inodes + fs_objects + 1;
 	if (!total_objects)
 		total_objects = 1;
···
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
 	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
 
 	/*
 	 * prune the dcache first as the icache is pinned by it, then
 	 * prune the icache, followed by the filesystem specific caches
 	 */
-	freed = prune_dcache_sb(sb, dentries, sc->nid);
-	freed += prune_icache_sb(sb, inodes, sc->nid);
+	sc->nr_to_scan = dentries;
+	freed = prune_dcache_sb(sb, sc);
+	sc->nr_to_scan = inodes;
+	freed += prune_icache_sb(sb, sc);
 
-	if (fs_objects) {
-		fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
-								total_objects);
+	if (fs_objects)
 		freed += sb->s_op->free_cached_objects(sb, fs_objects,
 						       sc->nid);
-	}
 
 	drop_super(sb);
 	return freed;
···
 	 * scalability bottleneck. The counts could get updated
 	 * between super_cache_count and super_cache_scan anyway.
 	 * Call to super_cache_count with shrinker_rwsem held
-	 * ensures the safety of call to list_lru_count_node() and
+	 * ensures the safety of call to list_lru_shrink_count() and
 	 * s_op->nr_cached_objects().
 	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb,
 						 sc->nid);
 
-	total_objects += list_lru_count_node(&sb->s_dentry_lru,
-						 sc->nid);
-	total_objects += list_lru_count_node(&sb->s_inode_lru,
-						 sc->nid);
+	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
 
 	total_objects = vfs_pressure_ratio(total_objects);
 	return total_objects;

fs/xfs/xfs_buf.c

···
 					struct xfs_buftarg, bt_shrinker);
 	LIST_HEAD(dispose);
 	unsigned long		freed;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
-	freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&btp->bt_lru, sc,
+				     xfs_buftarg_isolate, &dispose);
 
 	while (!list_empty(&dispose)) {
 		struct xfs_buf *bp;
···
 {
 	struct xfs_buftarg	*btp = container_of(shrink,
 					struct xfs_buftarg, bt_shrinker);
-	return list_lru_count_node(&btp->bt_lru, sc->nid);
+	return list_lru_shrink_count(&btp->bt_lru, sc);
 }
 
 void

fs/xfs/xfs_qm.c

···
 	struct xfs_qm_isolate	isol;
 	unsigned long		freed;
 	int			error;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
 	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
 		return 0;
···
 	INIT_LIST_HEAD(&isol.buffers);
 	INIT_LIST_HEAD(&isol.dispose);
 
-	freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
-					&nr_to_scan);
+	freed = list_lru_shrink_walk(&qi->qi_lru, sc,
+				     xfs_qm_dquot_isolate, &isol);
 
 	error = xfs_buf_delwri_submit(&isol.buffers);
 	if (error)
···
 	struct xfs_quotainfo	*qi = container_of(shrink,
 					struct xfs_quotainfo, qi_shrinker);
 
-	return list_lru_count_node(&qi->qi_lru, sc->nid);
+	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
 /*

include/linux/list_lru.h

···
 
 #include <linux/list.h>
 #include <linux/nodemask.h>
+#include <linux/shrinker.h>
 
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
···
  * Callers that want such a guarantee need to provide an outer lock.
  */
 unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+						  struct shrink_control *sc)
+{
+	return list_lru_count_node(lru, sc->nid);
+}
+
 static inline unsigned long list_lru_count(struct list_lru *lru)
 {
 	long count = 0;
···
 unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
 				 list_lru_walk_cb isolate, void *cb_arg,
 				 unsigned long *nr_to_walk);
+
+static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+		     list_lru_walk_cb isolate, void *cb_arg)
+{
+	return list_lru_walk_node(lru, sc->nid, isolate, cb_arg,
+				  &sc->nr_to_scan);
+}
 
 static inline unsigned long
 list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,

mm/workingset.c

···
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
 	local_irq_enable();
 
 	pages = node_present_pages(sc->nid);
···
 
 	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
 	local_irq_disable();
-	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
-				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	ret =  list_lru_shrink_walk(&workingset_shadow_nodes, sc,
+				    shadow_lru_isolate, NULL);
 	local_irq_enable();
 	return ret;
 }