if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
- if (!grab_super_passive(sb))
+ if (!trylock_super(sb))
return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
- fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
+ fs_objects = sb->s_op->nr_cached_objects(sb, sc);
- 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
+ *
+ * Ensure that we always scan at least one object - memcg kmem
+ * accounting uses this to fully empty the caches.
*/
- freed = prune_dcache_sb(sb, dentries, sc->nid);
- freed += prune_icache_sb(sb, inodes, sc->nid);
+ sc->nr_to_scan = dentries + 1;
+ freed = prune_dcache_sb(sb, sc);
+ sc->nr_to_scan = inodes + 1;
+ freed += prune_icache_sb(sb, sc);
if (fs_objects) {
- fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
- total_objects);
- freed += sb->s_op->free_cached_objects(sb, fs_objects,
- sc->nid);
+ sc->nr_to_scan = fs_objects + 1;
+ freed += sb->s_op->free_cached_objects(sb, sc);
}
- drop_super(sb);
+ up_read(&sb->s_umount);
return freed;
}
sb = container_of(shrink, struct super_block, s_shrink);
/*
- * Don't call grab_super_passive as it is a potential
+ * Don't call trylock_super as it is a potential
* 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 = sb->s_op->nr_cached_objects(sb, sc);
- 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;
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
- if (list_lru_init(&s->s_dentry_lru))
+ if (list_lru_init_memcg(&s->s_dentry_lru))
goto fail;
- if (list_lru_init(&s->s_inode_lru))
+ if (list_lru_init_memcg(&s->s_inode_lru))
goto fail;
init_rwsem(&s->s_umount);
s->s_shrink.scan_objects = super_cache_scan;
s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
- s->s_shrink.flags = SHRINKER_NUMA_AWARE;
+ s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
return s;
fail:
unregister_shrinker(&s->s_shrink);
fs->kill_sb(s);
+ /*
+ * Since list_lru_destroy() may sleep, we cannot call it from
+ * put_super(), where we hold the sb_lock. Therefore we destroy
+ * the lru lists right now.
+ */
+ list_lru_destroy(&s->s_dentry_lru);
+ list_lru_destroy(&s->s_inode_lru);
+
put_filesystem(fs);
put_super(s);
} else {
}
/*
- * grab_super_passive - acquire a passive reference
+ * trylock_super - try to grab ->s_umount shared
* @sb: reference we are trying to grab
*
- * Tries to acquire a passive reference. This is used in places where we
+ * Try to prevent fs shutdown. This is used in places where we
* cannot take an active reference but we need to ensure that the
- * superblock does not go away while we are working on it. It returns
- * false if a reference was not gained, and returns true with the s_umount
- * lock held in read mode if a reference is gained. On successful return,
- * the caller must drop the s_umount lock and the passive reference when
- * done.
+ * filesystem is not shut down while we are working on it. It returns
+ * false if we cannot acquire s_umount or if we lose the race and
+ * filesystem already got into shutdown, and returns true with the s_umount
+ * lock held in read mode in case of success. On successful return,
+ * the caller must drop the s_umount lock when done.
+ *
+ * Note that unlike get_super() et.al. this one does *not* bump ->s_count.
+ * The reason why it's safe is that we are OK with doing trylock instead
+ * of down_read(). There's a couple of places that are OK with that, but
+ * it's very much not a general-purpose interface.
*/
-bool grab_super_passive(struct super_block *sb)
+bool trylock_super(struct super_block *sb)
{
- spin_lock(&sb_lock);
- if (hlist_unhashed(&sb->s_instances)) {
- spin_unlock(&sb_lock);
- return false;
- }
-
- sb->s_count++;
- spin_unlock(&sb_lock);
-
if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root && (sb->s_flags & MS_BORN))
+ if (!hlist_unhashed(&sb->s_instances) &&
+ sb->s_root && (sb->s_flags & MS_BORN))
return true;
up_read(&sb->s_umount);
}
- put_super(sb);
return false;
}
remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
if (remount_ro) {
- if (sb->s_pins.first) {
+ if (!hlist_empty(&sb->s_pins)) {
up_write(&sb->s_umount);
- sb_pin_kill(sb);
+ group_pin_kill(&sb->s_pins);
down_write(&sb->s_umount);
if (!sb->s_root)
return 0;
git.openpandora.org / pandora-kernel.git / blobdiff