Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs pile 4 from Al Viro:
 "list_lru pile, mostly"

This came out of Andrew's pile, Al ended up doing the merge work so that
Andrew didn't have to.

Additionally, a few fixes.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (42 commits)
  super: fix for destroy lrus
  list_lru: dynamically adjust node arrays
  shrinker: Kill old ->shrink API.
  shrinker: convert remaining shrinkers to count/scan API
  staging/lustre/libcfs: cleanup linux-mem.h
  staging/lustre/ptlrpc: convert to new shrinker API
  staging/lustre/obdclass: convert lu_object shrinker to count/scan API
  staging/lustre/ldlm: convert to shrinkers to count/scan API
  hugepage: convert huge zero page shrinker to new shrinker API
  i915: bail out earlier when shrinker cannot acquire mutex
  drivers: convert shrinkers to new count/scan API
  fs: convert fs shrinkers to new scan/count API
  xfs: fix dquot isolation hang
  xfs-convert-dquot-cache-lru-to-list_lru-fix
  xfs: convert dquot cache lru to list_lru
  xfs: rework buffer dispose list tracking
  xfs-convert-buftarg-lru-to-generic-code-fix
  xfs: convert buftarg LRU to generic code
  fs: convert inode and dentry shrinking to be node aware
  vmscan: per-node deferred work
  ...

6 files changed, 196 insertions, 39 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index feaa8d88eef7..59066e0b4ff1 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -55,11 +55,11 @@ struct qstr {
 #define hashlen_len(hashlen)  ((u32)((hashlen) >> 32))
 
 struct dentry_stat_t {
-	int nr_dentry;
-	int nr_unused;
-	int age_limit;          /* age in seconds */
-	int want_pages;         /* pages requested by system */
-	int dummy[2];
+	long nr_dentry;
+	long nr_unused;
+	long age_limit;          /* age in seconds */
+	long want_pages;         /* pages requested by system */
+	long dummy[2];
 };
 extern struct dentry_stat_t dentry_stat;
 
@@ -395,4 +395,8 @@ static inline bool d_mountpoint(const struct dentry *dentry)
 
 extern int sysctl_vfs_cache_pressure;
 
+static inline unsigned long vfs_pressure_ratio(unsigned long val)
+{
+	return mult_frac(val, sysctl_vfs_cache_pressure, 100);
+}
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 529d8711baba..a4acd3c61190 100644
--- a/include/linux/fs.h
+++ b/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>
@@ -1269,15 +1270,6 @@ struct super_block {
 	struct list_head	s_files;
 #endif
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
-	/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
-	struct list_head	s_dentry_lru;	/* unused dentry lru */
-	int			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 */
-	int			s_nr_inodes_unused;	/* # of inodes on lru */
-
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
@@ -1331,11 +1323,14 @@ struct super_block {
 
 	/* AIO completions deferred from interrupt context */
 	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);
+	/*
+	 * Keep the lru lists last in the structure so they always sit on their
+	 * own individual cachelines.
+	 */
+	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
+	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
+};
 
 extern struct timespec current_fs_time(struct super_block *sb);
 
@@ -1629,8 +1624,8 @@ 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 *, int);
+	long (*free_cached_objects)(struct super_block *, long, int);
 };
 
 /*
@@ -2494,7 +2489,6 @@ extern const struct file_operations generic_ro_fops;
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
 extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
-extern int vfs_follow_link(struct nameidata *, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
new file mode 100644
index 000000000000..3ce541753c88
--- /dev/null
+++ b/include/linux/list_lru.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
+ * Authors: David Chinner and Glauber Costa
+ *
+ * Generic LRU infrastructure
+ */
+#ifndef _LRU_LIST_H
+#define _LRU_LIST_H
+
+#include <linux/list.h>
+#include <linux/nodemask.h>
+
+/* list_lru_walk_cb has to always return one of those */
+enum lru_status {
+	LRU_REMOVED,		/* item removed from list */
+	LRU_ROTATE,		/* item referenced, give another pass */
+	LRU_SKIP,		/* item cannot be locked, skip */
+	LRU_RETRY,		/* item not freeable. May drop the lock
+				   internally, but has to return locked. */
+};
+
+struct list_lru_node {
+	spinlock_t		lock;
+	struct list_head	list;
+	/* kept as signed so we can catch imbalance bugs */
+	long			nr_items;
+} ____cacheline_aligned_in_smp;
+
+struct list_lru {
+	struct list_lru_node	*node;
+	nodemask_t		active_nodes;
+};
+
+void list_lru_destroy(struct list_lru *lru);
+int list_lru_init(struct list_lru *lru);
+
+/**
+ * list_lru_add: add an element to the lru list's tail
+ * @list_lru: the lru pointer
+ * @item: the item to be added.
+ *
+ * If the element is already part of a list, this function returns doing
+ * nothing. Therefore the caller does not need to keep state about whether or
+ * not the element already belongs in the list and is allowed to lazy update
+ * it. Note however that this is valid for *a* list, not *this* list. If
+ * the caller organize itself in a way that elements can be in more than
+ * one type of list, it is up to the caller to fully remove the item from
+ * the previous list (with list_lru_del() for instance) before moving it
+ * to @list_lru
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_add(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_del: delete an element to the lru list
+ * @list_lru: the lru pointer
+ * @item: the item to be deleted.
+ *
+ * This function works analogously as list_lru_add in terms of list
+ * manipulation. The comments about an element already pertaining to
+ * a list are also valid for list_lru_del.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_del(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_count_node: return the number of objects currently held by @lru
+ * @lru: the lru pointer.
+ * @nid: the node id to count from.
+ *
+ * Always return a non-negative number, 0 for empty lists. There is no
+ * guarantee that the list is not updated while the count is being computed.
+ * 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_count(struct list_lru *lru)
+{
+	long count = 0;
+	int nid;
+
+	for_each_node_mask(nid, lru->active_nodes)
+		count += list_lru_count_node(lru, nid);
+
+	return count;
+}
+
+typedef enum lru_status
+(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
+/**
+ * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * @lru: the lru pointer.
+ * @nid: the node id to scan from.
+ * @isolate: callback function that is resposible for deciding what to do with
+ *  the item currently being scanned
+ * @cb_arg: opaque type that will be passed to @isolate
+ * @nr_to_walk: how many items to scan.
+ *
+ * This function will scan all elements in a particular list_lru, calling the
+ * @isolate callback for each of those items, along with the current list
+ * spinlock and a caller-provided opaque. The @isolate callback can choose to
+ * drop the lock internally, but *must* return with the lock held. The callback
+ * will return an enum lru_status telling the list_lru infrastructure what to
+ * do with the object being scanned.
+ *
+ * Please note that nr_to_walk does not mean how many objects will be freed,
+ * just how many objects will be scanned.
+ *
+ * Return value: the number of objects effectively removed from the LRU.
+ */
+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_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+	      void *cb_arg, unsigned long nr_to_walk)
+{
+	long isolated = 0;
+	int nid;
+
+	for_each_node_mask(nid, lru->active_nodes) {
+		isolated += list_lru_walk_node(lru, nid, isolate,
+					       cb_arg, &nr_to_walk);
+		if (nr_to_walk <= 0)
+			break;
+	}
+	return isolated;
+}
+#endif /* _LRU_LIST_H */
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index ac6b8ee07825..68c097077ef0 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -4,39 +4,67 @@
 /*
  * This struct is used to pass information from page reclaim to the shrinkers.
  * We consolidate the values for easier extention later.
+ *
+ * The 'gfpmask' refers to the allocation we are currently trying to
+ * fulfil.
  */
 struct shrink_control {
 	gfp_t gfp_mask;
 
-	/* How many slab objects shrinker() should scan and try to reclaim */
+	/*
+	 * How many objects scan_objects should scan and try to reclaim.
+	 * This is reset before every call, so it is safe for callees
+	 * to modify.
+	 */
 	unsigned long nr_to_scan;
+
+	/* shrink from these nodes */
+	nodemask_t nodes_to_scan;
+	/* current node being shrunk (for NUMA aware shrinkers) */
+	int nid;
 };
 
+#define SHRINK_STOP (~0UL)
 /*
  * A callback you can register to apply pressure to ageable caches.
  *
- * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
- * and a 'gfpmask'.  It should look through the least-recently-used
- * 'nr_to_scan' entries and attempt to free them up.  It should return
- * the number of objects which remain in the cache.  If it returns -1, it means
- * it cannot do any scanning at this time (eg. there is a risk of deadlock).
+ * @count_objects should return the number of freeable items in the cache. If
+ * there are no objects to free or the number of freeable items cannot be
+ * determined, it should return 0. No deadlock checks should be done during the
+ * count callback - the shrinker relies on aggregating scan counts that couldn't
+ * be executed due to potential deadlocks to be run at a later call when the
+ * deadlock condition is no longer pending.
  *
- * The 'gfpmask' refers to the allocation we are currently trying to
- * fulfil.
+ * @scan_objects will only be called if @count_objects returned a non-zero
+ * value for the number of freeable objects. The callout should scan the cache
+ * and attempt to free items from the cache. It should then return the number
+ * of objects freed during the scan, or SHRINK_STOP if progress cannot be made
+ * due to potential deadlocks. If SHRINK_STOP is returned, then no further
+ * attempts to call the @scan_objects will be made from the current reclaim
+ * context.
  *
- * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
- * querying the cache size, so a fastpath for that case is appropriate.
+ * @flags determine the shrinker abilities, like numa awareness
  */
 struct shrinker {
-	int (*shrink)(struct shrinker *, struct shrink_control *sc);
+	unsigned long (*count_objects)(struct shrinker *,
+				       struct shrink_control *sc);
+	unsigned long (*scan_objects)(struct shrinker *,
+				      struct shrink_control *sc);
+
 	int seeks;	/* seeks to recreate an obj */
 	long batch;	/* reclaim batch size, 0 = default */
+	unsigned long flags;
 
 	/* These are for internal use */
 	struct list_head list;
-	atomic_long_t nr_in_batch; /* objs pending delete */
+	/* objs pending delete, per node */
+	atomic_long_t *nr_deferred;
 };
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
-extern void register_shrinker(struct shrinker *);
+
+/* Flags */
+#define SHRINKER_NUMA_AWARE (1 << 0)
+
+extern int register_shrinker(struct shrinker *);
 extern void unregister_shrinker(struct shrinker *);
 #endif
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 63cfcccaebb3..132a985aba8b 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -202,7 +202,7 @@ TRACE_EVENT(mm_shrink_slab_start,
 
 	TP_fast_assign(
 		__entry->shr = shr;
-		__entry->shrink = shr->shrink;
+		__entry->shrink = shr->scan_objects;
 		__entry->nr_objects_to_shrink = nr_objects_to_shrink;
 		__entry->gfp_flags = sc->gfp_mask;
 		__entry->pgs_scanned = pgs_scanned;
@@ -241,7 +241,7 @@ TRACE_EVENT(mm_shrink_slab_end,
 
 	TP_fast_assign(
 		__entry->shr = shr;
-		__entry->shrink = shr->shrink;
+		__entry->shrink = shr->scan_objects;
 		__entry->unused_scan = unused_scan_cnt;
 		__entry->new_scan = new_scan_cnt;
 		__entry->retval = shrinker_retval;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index a4ed56cf0eac..6c28b61bb690 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -49,9 +49,9 @@ struct files_stat_struct {
 };
 
 struct inodes_stat_t {
-	int nr_inodes;
-	int nr_unused;
-	int dummy[5];		/* padding for sysctl ABI compatibility */
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
 };