18 files changed, 103 insertions, 74 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index c8c78ba07827..86d4db15473e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -896,7 +896,7 @@ EXPORT_SYMBOL(shrink_dcache_parent);
  *
  * In this case we return -1 to tell the caller that we baled.
  */
-static int shrink_dcache_memory(int nr, gfp_t gfp_mask)
+static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         if (nr) {
                 if (!(gfp_mask & __GFP_FS))
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index dbab3fdc2582..0898f3ec8212 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1358,7 +1358,7 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 }
 
 
-static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask)
+static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         struct gfs2_glock *gl;
         int may_demote;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index b256d6f24288..8f02d3db8f42 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -77,7 +77,7 @@ 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(int nr, gfp_t gfp_mask)
+int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         struct gfs2_quota_data *qd;
         struct gfs2_sbd *sdp;
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 195f60c8bd14..e7d236ca48bd 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -51,7 +51,7 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
         return ret;
 }
 
-extern int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask);
+extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask);
 extern const struct quotactl_ops gfs2_quotactl_ops;
 
 #endif /* __QUOTA_DOT_H__ */
diff --git a/fs/inode.c b/fs/inode.c
index 2bee20ae3d65..722860b323a9 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -512,7 +512,7 @@ static void prune_icache(int nr_to_scan)
  * This function is passed the number of inodes to scan, and it returns the
  * total number of remaining possibly-reclaimable inodes.
  */
-static int shrink_icache_memory(int nr, gfp_t gfp_mask)
+static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         if (nr) {
                 /*
diff --git a/fs/mbcache.c b/fs/mbcache.c
index ec88ff3d04a9..e28f21b95344 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -115,7 +115,7 @@ mb_cache_indexes(struct mb_cache *cache)
  * What the mbcache registers as to get shrunk dynamically.
  */
 
-static int mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask);
+static int mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask);
 
 static struct shrinker mb_cache_shrinker = {
         .shrink = mb_cache_shrink_fn,
@@ -191,13 +191,14 @@ forget:
  * This function is called by the kernel memory management when memory
  * gets low.
  *
+ * @shrink: (ignored)
  * @nr_to_scan: Number of objects to scan
  * @gfp_mask: (ignored)
  *
  * Returns the number of objects which are present in the cache.
  */
 static int
-mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask)
+mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
         LIST_HEAD(free_list);
         struct list_head *l, *ltmp;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 782b431ef91c..e60416d3f818 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1710,7 +1710,7 @@ static void nfs_access_free_list(struct list_head *head)
         }
 }
 
-int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask)
+int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
         LIST_HEAD(head);
         struct nfs_inode *nfsi;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d8bd619e386c..e70f44b9b3f4 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -205,7 +205,8 @@ extern struct rpc_procinfo nfs4_procedures[];
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 
 /* dir.c */
-extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask);
+extern int nfs_access_cache_shrinker(struct shrinker *shrink,
+                                        int nr_to_scan, gfp_t gfp_mask);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 12c233da1b6b..437d2ca2de97 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -676,7 +676,7 @@ static void prune_dqcache(int count)
  * This is called from kswapd when we think we need some
  * more memory
  */
-static int shrink_dqcache_memory(int nr, gfp_t gfp_mask)
+static int shrink_dqcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         if (nr) {
                 spin_lock(&dq_list_lock);
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 02feb59cefca..0b201114a5ad 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -277,7 +277,7 @@ static int kick_a_thread(void)
         return 0;
 }
 
-int ubifs_shrinker(int nr, gfp_t gfp_mask)
+int ubifs_shrinker(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
         int freed, contention = 0;
         long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 2eef553d50c8..04310878f449 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1575,7 +1575,7 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int ubifs_tnc_end_commit(struct ubifs_info *c);
 
 /* shrinker.c */
-int ubifs_shrinker(int nr_to_scan, gfp_t gfp_mask);
+int ubifs_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask);
 
 /* commit.c */
 int ubifs_bg_thread(void *info);
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 649ade8ef598..2ee3f7a60163 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -45,7 +45,7 @@
 
 static kmem_zone_t *xfs_buf_zone;
 STATIC int xfsbufd(void *);
-STATIC int xfsbufd_wakeup(int, gfp_t);
+STATIC int xfsbufd_wakeup(struct shrinker *, int, gfp_t);
 STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int);
 static struct shrinker xfs_buf_shake = {
         .shrink = xfsbufd_wakeup,
@@ -340,7 +340,7 @@ _xfs_buf_lookup_pages(
                                         __func__, gfp_mask);
 
                         XFS_STATS_INC(xb_page_retries);
-                        xfsbufd_wakeup(0, gfp_mask);
+                        xfsbufd_wakeup(NULL, 0, gfp_mask);
                         congestion_wait(BLK_RW_ASYNC, HZ/50);
                         goto retry;
                 }
@@ -1762,6 +1762,7 @@ xfs_buf_runall_queues(
 
 STATIC int
 xfsbufd_wakeup(
+        struct shrinker         *shrink,
         int                     priority,
         gfp_t                   mask)
 {
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index f2d1718c9165..80938c736c27 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1883,7 +1883,6 @@ init_xfs_fs(void)
                 goto out_cleanup_procfs;
 
         vfs_initquota();
-        xfs_inode_shrinker_init();
 
         error = register_filesystem(&xfs_fs_type);
         if (error)
@@ -1911,7 +1910,6 @@ exit_xfs_fs(void)
 {
         vfs_exitquota();
         unregister_filesystem(&xfs_fs_type);
-        xfs_inode_shrinker_destroy();
         xfs_sysctl_unregister();
         xfs_cleanup_procfs();
         xfs_buf_terminate();
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index ef7f0218bccb..a51a07c3a70c 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -144,6 +144,41 @@ restart:
         return last_error;
 }
 
+/*
+ * Select the next per-ag structure to iterate during the walk. The reclaim
+ * walk is optimised only to walk AGs with reclaimable inodes in them.
+ */
+static struct xfs_perag *
+xfs_inode_ag_iter_next_pag(
+        struct xfs_mount        *mp,
+        xfs_agnumber_t          *first,
+        int                     tag)
+{
+        struct xfs_perag        *pag = NULL;
+
+        if (tag == XFS_ICI_RECLAIM_TAG) {
+                int found;
+                int ref;
+
+                spin_lock(&mp->m_perag_lock);
+                found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
+                                (void **)&pag, *first, 1, tag);
+                if (found <= 0) {
+                        spin_unlock(&mp->m_perag_lock);
+                        return NULL;
+                }
+                *first = pag->pag_agno + 1;
+                /* open coded pag reference increment */
+                ref = atomic_inc_return(&pag->pag_ref);
+                spin_unlock(&mp->m_perag_lock);
+                trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_);
+        } else {
+                pag = xfs_perag_get(mp, *first);
+                (*first)++;
+        }
+        return pag;
+}
+
 int
 xfs_inode_ag_iterator(
         struct xfs_mount        *mp,
@@ -154,16 +189,15 @@ xfs_inode_ag_iterator(
         int                     exclusive,
         int                     *nr_to_scan)
 {
+        struct xfs_perag        *pag;
         int                     error = 0;
         int                     last_error = 0;
         xfs_agnumber_t          ag;
         int                     nr;
 
         nr = nr_to_scan ? *nr_to_scan : INT_MAX;
-        for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
-                struct xfs_perag        *pag;
-
-                pag = xfs_perag_get(mp, ag);
+        ag = 0;
+        while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, tag))) {
                 error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
                                                 exclusive, &nr);
                 xfs_perag_put(pag);
@@ -640,6 +674,17 @@ __xfs_inode_set_reclaim_tag(
         radix_tree_tag_set(&pag->pag_ici_root,
                            XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
                            XFS_ICI_RECLAIM_TAG);
+
+        if (!pag->pag_ici_reclaimable) {
+                /* propagate the reclaim tag up into the perag radix tree */
+                spin_lock(&ip->i_mount->m_perag_lock);
+                radix_tree_tag_set(&ip->i_mount->m_perag_tree,
+                                XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+                                XFS_ICI_RECLAIM_TAG);
+                spin_unlock(&ip->i_mount->m_perag_lock);
+                trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
+                                                        -1, _RET_IP_);
+        }
         pag->pag_ici_reclaimable++;
 }
 
@@ -674,6 +719,16 @@ __xfs_inode_clear_reclaim_tag(
         radix_tree_tag_clear(&pag->pag_ici_root,
                         XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
         pag->pag_ici_reclaimable--;
+        if (!pag->pag_ici_reclaimable) {
+                /* clear the reclaim tag from the perag radix tree */
+                spin_lock(&ip->i_mount->m_perag_lock);
+                radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
+                                XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+                                XFS_ICI_RECLAIM_TAG);
+                spin_unlock(&ip->i_mount->m_perag_lock);
+                trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
+                                                        -1, _RET_IP_);
+        }
 }
 
 /*
@@ -828,83 +883,52 @@ xfs_reclaim_inodes(
 
 /*
  * Shrinker infrastructure.
- *
- * This is all far more complex than it needs to be. It adds a global list of
- * mounts because the shrinkers can only call a global context. We need to make
- * the shrinkers pass a context to avoid the need for global state.
  */
-static LIST_HEAD(xfs_mount_list);
-static struct rw_semaphore xfs_mount_list_lock;
-
 static int
 xfs_reclaim_inode_shrink(
+        struct shrinker *shrink,
         int             nr_to_scan,
         gfp_t           gfp_mask)
 {
         struct xfs_mount *mp;
         struct xfs_perag *pag;
         xfs_agnumber_t  ag;
-        int             reclaimable = 0;
+        int             reclaimable;
 
+        mp = container_of(shrink, struct xfs_mount, m_inode_shrink);
         if (nr_to_scan) {
                 if (!(gfp_mask & __GFP_FS))
                         return -1;
 
-                down_read(&xfs_mount_list_lock);
-                list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
-                        xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
+                xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
                                         XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan);
-                        if (nr_to_scan <= 0)
-                                break;
-                }
-                up_read(&xfs_mount_list_lock);
-        }
+                /* if we don't exhaust the scan, don't bother coming back */
+                if (nr_to_scan > 0)
+                        return -1;
+       }
 
-        down_read(&xfs_mount_list_lock);
-        list_for_each_entry(mp, &xfs_mount_list, m_mplist) {
-                for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
-                        pag = xfs_perag_get(mp, ag);
-                        reclaimable += pag->pag_ici_reclaimable;
-                        xfs_perag_put(pag);
-                }
+        reclaimable = 0;
+        ag = 0;
+        while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag,
+                                        XFS_ICI_RECLAIM_TAG))) {
+                reclaimable += pag->pag_ici_reclaimable;
+                xfs_perag_put(pag);
         }
-        up_read(&xfs_mount_list_lock);
         return reclaimable;
 }
 
-static struct shrinker xfs_inode_shrinker = {
-        .shrink = xfs_reclaim_inode_shrink,
-        .seeks = DEFAULT_SEEKS,
-};
-
-void __init
-xfs_inode_shrinker_init(void)
-{
-        init_rwsem(&xfs_mount_list_lock);
-        register_shrinker(&xfs_inode_shrinker);
-}
-
-void
-xfs_inode_shrinker_destroy(void)
-{
-        ASSERT(list_empty(&xfs_mount_list));
-        unregister_shrinker(&xfs_inode_shrinker);
-}
-
 void
 xfs_inode_shrinker_register(
         struct xfs_mount        *mp)
 {
-        down_write(&xfs_mount_list_lock);
-        list_add_tail(&mp->m_mplist, &xfs_mount_list);
-        up_write(&xfs_mount_list_lock);
+        mp->m_inode_shrink.shrink = xfs_reclaim_inode_shrink;
+        mp->m_inode_shrink.seeks = DEFAULT_SEEKS;
+        register_shrinker(&mp->m_inode_shrink);
 }
 
 void
 xfs_inode_shrinker_unregister(
         struct xfs_mount        *mp)
 {
-        down_write(&xfs_mount_list_lock);
-        list_del(&mp->m_mplist);
-        up_write(&xfs_mount_list_lock);
+        unregister_shrinker(&mp->m_inode_shrink);
 }
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index cdcbaaca9880..e28139aaa4aa 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -55,8 +55,6 @@ int xfs_inode_ag_iterator(struct xfs_mount *mp,
         int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
         int flags, int tag, int write_lock, int *nr_to_scan);
 
-void xfs_inode_shrinker_init(void);
-void xfs_inode_shrinker_destroy(void);
 void xfs_inode_shrinker_register(struct xfs_mount *mp);
 void xfs_inode_shrinker_unregister(struct xfs_mount *mp);
 
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index 73d5aa117384..302820690904 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -124,7 +124,10 @@ DEFINE_EVENT(xfs_perag_class, name,	\
                  unsigned long caller_ip),                                      \
         TP_ARGS(mp, agno, refcount, caller_ip))
 DEFINE_PERAG_REF_EVENT(xfs_perag_get);
+DEFINE_PERAG_REF_EVENT(xfs_perag_get_reclaim);
 DEFINE_PERAG_REF_EVENT(xfs_perag_put);
+DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim);
+DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim);
 
 TRACE_EVENT(xfs_attr_list_node_descend,
         TP_PROTO(struct xfs_attr_list_context *ctx,
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 8c117ff2e3ab..67c018392d62 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -69,7 +69,7 @@ STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
 
 STATIC int      xfs_qm_init_quotainos(xfs_mount_t *);
 STATIC int      xfs_qm_init_quotainfo(xfs_mount_t *);
-STATIC int      xfs_qm_shake(int, gfp_t);
+STATIC int      xfs_qm_shake(struct shrinker *, int, gfp_t);
 
 static struct shrinker xfs_qm_shaker = {
         .shrink = xfs_qm_shake,
@@ -2117,7 +2117,10 @@ xfs_qm_shake_freelist(
  */
 /* ARGSUSED */
 STATIC int
-xfs_qm_shake(int nr_to_scan, gfp_t gfp_mask)
+xfs_qm_shake(
+        struct shrinker *shrink,
+        int             nr_to_scan,
+        gfp_t           gfp_mask)
 {
         int     ndqused, nfree, n;
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1d2c7eed4eda..5761087ee8ea 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -259,7 +259,7 @@ typedef struct xfs_mount {
         wait_queue_head_t       m_wait_single_sync_task;
         __int64_t               m_update_flags; /* sb flags we need to update
                                                    on the next remount,rw */
-        struct list_head        m_mplist;       /* inode shrinker mount list */
+        struct shrinker         m_inode_shrink; /* inode reclaim shrinker */
 } xfs_mount_t;
 
 /*