shrinker: convert superblock shrinkers to new API

Convert superblock shrinker to use the new count/scan API, and propagate
the API changes through to the filesystem callouts.  The filesystem
callouts already use a count/scan API, so it's just changing counters to
longs to match the VM API.

This requires the dentry and inode shrinker callouts to be converted to
the count/scan API.  This is mainly a mechanical change.

[glommer@openvz.org: use mult_frac for fractional proportions, build fixes]
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Acked-by: Mel Gorman <mgorman@suse.de>
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>

diff --git a/fs/dcache.c b/fs/dcache.c
index 509b49410943ef3e19dda508ffc78e05a60a114e..77d466b13fefceb29aa8f2d8c40dbd5e3ec7e7ec 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -913,11 +913,12 @@ static void shrink_dentry_list(struct list_head *list)
  * 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)
 {
        struct dentry *dentry;
        LIST_HEAD(referenced);
        LIST_HEAD(tmp);
+       long freed = 0;
 
 relock:
        spin_lock(&sb->s_dentry_lru_lock);
@@ -942,7 +943,8 @@ relock:
                        this_cpu_dec(nr_dentry_unused);
                        sb->s_nr_dentry_unused--;
                        spin_unlock(&dentry->d_lock);
-                       if (!--count)
+                       freed++;
+                       if (!--nr_to_scan)
                                break;
                }
                cond_resched_lock(&sb->s_dentry_lru_lock);
@@ -952,6 +954,7 @@ relock:
        spin_unlock(&sb->s_dentry_lru_lock);
 
        shrink_dentry_list(&tmp);
+       return freed;
 }
 
 /*

diff --git a/fs/inode.c b/fs/inode.c
index 2a3c37ea823d5579175d0d0387112d47b264885a..021d64768a553df798cc351e9155a08340bab6e0 100644 (file)
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -706,10 +706,11 @@ 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)
+long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan)
 {
        LIST_HEAD(freeable);
-       int nr_scanned;
+       long nr_scanned;
+       long freed = 0;
        unsigned long reap = 0;
 
        spin_lock(&sb->s_inode_lru_lock);
@@ -779,6 +780,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
                list_move(&inode->i_lru, &freeable);
                sb->s_nr_inodes_unused--;
                this_cpu_dec(nr_unused);
+               freed++;
        }
        if (current_is_kswapd())
                __count_vm_events(KSWAPD_INODESTEAL, reap);
@@ -789,6 +791,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
                current->reclaim_state->reclaimed_slab += reap;
 
        dispose_list(&freeable);
+       return freed;
 }
 
 static void __wait_on_freeing_inode(struct inode *inode);

diff --git a/fs/internal.h b/fs/internal.h
index b6495659d6e84dd9d3734887404ce08e690f0c4e..cb83a3417a68d91c914b9b9aaf6099adaed20e3b 100644 (file)
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -114,6 +114,7 @@ extern int open_check_o_direct(struct file *f);
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
+extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan);
 extern void inode_add_lru(struct inode *inode);
 
 /*
@@ -130,6 +131,7 @@ extern int invalidate_inodes(struct super_block *, bool);
  */
 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);
 
 /*
  * read_write.c

diff --git a/fs/super.c b/fs/super.c
index 3c5318694ccd4ad365903a7b150da889e3e57449..8aa2660642b97e5c735255448e2d06c099e966e4 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -53,11 +53,15 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
  * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
  * take a passive reference to the superblock to avoid this from occurring.
  */
-static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long super_cache_scan(struct shrinker *shrink,
+                                     struct shrink_control *sc)
 {
        struct super_block *sb;
-       int     fs_objects = 0;
-       int     total_objects;
+       long    fs_objects = 0;
+       long    total_objects;
+       long    freed = 0;
+       long    dentries;
+       long    inodes;
 
        sb = container_of(shrink, struct super_block, s_shrink);
 
@@ -65,11 +69,11 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
         * Deadlock avoidance.  We may hold various FS locks, and we don't want
         * to recurse into the FS that called us in clear_inode() and friends..
         */
-       if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS))
-               return -1;
+       if (!(sc->gfp_mask & __GFP_FS))
+               return SHRINK_STOP;
 
        if (!grab_super_passive(sb))
-               return -1;
+               return SHRINK_STOP;
 
        if (sb->s_op->nr_cached_objects)
                fs_objects = sb->s_op->nr_cached_objects(sb);
@@ -77,33 +81,46 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
        total_objects = sb->s_nr_dentry_unused +
                        sb->s_nr_inodes_unused + fs_objects + 1;
 
-       if (sc->nr_to_scan) {
-               int     dentries;
-               int     inodes;
-
-               /* 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);
-               if (fs_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
-                */
-               prune_dcache_sb(sb, dentries);
-               prune_icache_sb(sb, inodes);
+       /* 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);
 
-               if (fs_objects && sb->s_op->free_cached_objects) {
-                       sb->s_op->free_cached_objects(sb, fs_objects);
-                       fs_objects = sb->s_op->nr_cached_objects(sb);
-               }
-               total_objects = sb->s_nr_dentry_unused +
-                               sb->s_nr_inodes_unused + fs_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);
+       freed += prune_icache_sb(sb, inodes);
+
+       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);
        }
 
+       drop_super(sb);
+       return freed;
+}
+
+static unsigned long super_cache_count(struct shrinker *shrink,
+                                      struct shrink_control *sc)
+{
+       struct super_block *sb;
+       long    total_objects = 0;
+
+       sb = container_of(shrink, struct super_block, s_shrink);
+
+       if (!grab_super_passive(sb))
+               return 0;
+
+       if (sb->s_op && sb->s_op->nr_cached_objects)
+               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 = vfs_pressure_ratio(total_objects);
        drop_super(sb);
        return total_objects;
@@ -211,7 +228,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
                s->cleancache_poolid = -1;
 
                s->s_shrink.seeks = DEFAULT_SEEKS;
-               s->s_shrink.shrink = prune_super;
+               s->s_shrink.scan_objects = super_cache_scan;
+               s->s_shrink.count_objects = super_cache_count;
                s->s_shrink.batch = 1024;
        }
 out:

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 16219b9c67909a6a483678fb761db701a8cb00e6..73b62a24ceacaccfcd98f9accc10df40f319137e 100644 (file)
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1167,7 +1167,7 @@ xfs_reclaim_inodes(
  * them to be cleaned, which we hope will not be very long due to the
  * background walker having already kicked the IO off on those dirty inodes.
  */
-void
+long
 xfs_reclaim_inodes_nr(
        struct xfs_mount        *mp,
        int                     nr_to_scan)
@@ -1176,7 +1176,7 @@ xfs_reclaim_inodes_nr(
        xfs_reclaim_work_queue(mp);
        xfs_ail_push_all(mp->m_ail);
 
-       xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
+       return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
 }
 
 /*

diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 8a89f7d791bd9df3184fd9f66a15467f0f30f8dc..456f0144e1b6f3f189e0117cad3989e2c286f50c 100644 (file)
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -46,7 +46,7 @@ void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
-void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
+long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 979a77d4b87d1142c12b4b1cabcf41f75777041a..71d7aaebb91239edb316d6efc0a53f77c60252aa 100644 (file)
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1535,19 +1535,19 @@ xfs_fs_mount(
        return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
 }
 
-static int
+static long
 xfs_fs_nr_cached_objects(
        struct super_block      *sb)
 {
        return xfs_reclaim_inodes_count(XFS_M(sb));
 }
 
-static void
+static long
 xfs_fs_free_cached_objects(
        struct super_block      *sb,
-       int                     nr_to_scan)
+       long                    nr_to_scan)
 {
-       xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+       return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
 }
 
 static const struct super_operations xfs_super_operations = {

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 14a90f6886fa44611afdc030551487c7e41d94cd..0ae0bc3c1fdeb12b30223c962749f6af91bc4762 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1335,10 +1335,6 @@ struct super_block {
        struct workqueue_struct *s_dio_done_wq;
 };
 
-/* superblock cache pruning functions */
-extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
-extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);
-
 extern struct timespec current_fs_time(struct super_block *sb);
 
 /*
@@ -1631,8 +1627,8 @@ struct super_operations {
        ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
        int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
-       int (*nr_cached_objects)(struct super_block *);
-       void (*free_cached_objects)(struct super_block *, int);
+       long (*nr_cached_objects)(struct super_block *);
+       long (*free_cached_objects)(struct super_block *, long);
 };
 
 /*