Merge branch 'vfs-scale-working' of git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin

* 'vfs-scale-working' of git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin: (57 commits)
  fs: scale mntget/mntput
  fs: rename vfsmount counter helpers
  fs: implement faster dentry memcmp
  fs: prefetch inode data in dcache lookup
  fs: improve scalability of pseudo filesystems
  fs: dcache per-inode inode alias locking
  fs: dcache per-bucket dcache hash locking
  bit_spinlock: add required includes
  kernel: add bl_list
  xfs: provide simple rcu-walk ACL implementation
  btrfs: provide simple rcu-walk ACL implementation
  ext2,3,4: provide simple rcu-walk ACL implementation
  fs: provide simple rcu-walk generic_check_acl implementation
  fs: provide rcu-walk aware permission i_ops
  fs: rcu-walk aware d_revalidate method
  fs: cache optimise dentry and inode for rcu-walk
  fs: dcache reduce branches in lookup path
  fs: dcache remove d_mounted
  fs: fs_struct use seqlock
  fs: rcu-walk for path lookup
  ...

20 files changed, 586 insertions, 203 deletions

diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h
index 7113a32a86e..e612575a259 100644
--- a/include/linux/bit_spinlock.h
+++ b/include/linux/bit_spinlock.h
@@ -1,6 +1,10 @@
 #ifndef __LINUX_BIT_SPINLOCK_H
 #define __LINUX_BIT_SPINLOCK_H
 
+#include <linux/kernel.h>
+#include <linux/preempt.h>
+#include <asm/atomic.h>
+
 /*
  *  bit-based spin_lock()
  *
diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h
index 2e914d0771b..4ccc59c1ea8 100644
--- a/include/linux/coda_linux.h
+++ b/include/linux/coda_linux.h
@@ -37,7 +37,7 @@ extern const struct file_operations coda_ioctl_operations;
 /* operations shared over more than one file */
 int coda_open(struct inode *i, struct file *f);
 int coda_release(struct inode *i, struct file *f);
-int coda_permission(struct inode *inode, int mask);
+int coda_permission(struct inode *inode, int mask, unsigned int flags);
 int coda_revalidate_inode(struct dentry *);
 int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 int coda_setattr(struct dentry *, struct iattr *);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 6a4aea30aa0..bd07758943e 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -4,7 +4,9 @@
 #include <asm/atomic.h>
 #include <linux/list.h>
 #include <linux/rculist.h>
+#include <linux/rculist_bl.h>
 #include <linux/spinlock.h>
+#include <linux/seqlock.h>
 #include <linux/cache.h>
 #include <linux/rcupdate.h>
 
@@ -45,6 +47,27 @@ struct dentry_stat_t {
 };
 extern struct dentry_stat_t dentry_stat;
 
+/*
+ * Compare 2 name strings, return 0 if they match, otherwise non-zero.
+ * The strings are both count bytes long, and count is non-zero.
+ */
+static inline int dentry_cmp(const unsigned char *cs, size_t scount,
+				const unsigned char *ct, size_t tcount)
+{
+	int ret;
+	if (scount != tcount)
+		return 1;
+	do {
+		ret = (*cs != *ct);
+		if (ret)
+			break;
+		cs++;
+		ct++;
+		tcount--;
+	} while (tcount);
+	return ret;
+}
+
 /* Name hashing routines. Initial hash value */
 /* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
 #define init_name_hash()		0
@@ -81,25 +104,33 @@ full_name_hash(const unsigned char *name, unsigned int len)
  * large memory footprint increase).
  */
 #ifdef CONFIG_64BIT
-#define DNAME_INLINE_LEN_MIN 32 /* 192 bytes */
+# define DNAME_INLINE_LEN 32 /* 192 bytes */
 #else
-#define DNAME_INLINE_LEN_MIN 40 /* 128 bytes */
+# ifdef CONFIG_SMP
+#  define DNAME_INLINE_LEN 36 /* 128 bytes */
+# else
+#  define DNAME_INLINE_LEN 40 /* 128 bytes */
+# endif
 #endif
 
 struct dentry {
-	atomic_t d_count;
+	/* RCU lookup touched fields */
 	unsigned int d_flags;		/* protected by d_lock */
-	spinlock_t d_lock;		/* per dentry lock */
-	int d_mounted;
-	struct inode *d_inode;		/* Where the name belongs to - NULL is
-					 * negative */
-	/*
-	 * The next three fields are touched by __d_lookup.  Place them here
-	 * so they all fit in a cache line.
-	 */
-	struct hlist_node d_hash;	/* lookup hash list */
+	seqcount_t d_seq;		/* per dentry seqlock */
+	struct hlist_bl_node d_hash;	/* lookup hash list */
 	struct dentry *d_parent;	/* parent directory */
 	struct qstr d_name;
+	struct inode *d_inode;		/* Where the name belongs to - NULL is
+					 * negative */
+	unsigned char d_iname[DNAME_INLINE_LEN];	/* small names */
+
+	/* Ref lookup also touches following */
+	unsigned int d_count;		/* protected by d_lock */
+	spinlock_t d_lock;		/* per dentry lock */
+	const struct dentry_operations *d_op;
+	struct super_block *d_sb;	/* The root of the dentry tree */
+	unsigned long d_time;		/* used by d_revalidate */
+	void *d_fsdata;			/* fs-specific data */
 
 	struct list_head d_lru;		/* LRU list */
 	/*
@@ -111,12 +142,6 @@ struct dentry {
 	} d_u;
 	struct list_head d_subdirs;	/* our children */
 	struct list_head d_alias;	/* inode alias list */
-	unsigned long d_time;		/* used by d_revalidate */
-	const struct dentry_operations *d_op;
-	struct super_block *d_sb;	/* The root of the dentry tree */
-	void *d_fsdata;			/* fs-specific data */
-
-	unsigned char d_iname[DNAME_INLINE_LEN_MIN];	/* small names */
 };
 
 /*
@@ -133,96 +158,61 @@ enum dentry_d_lock_class
 
 struct dentry_operations {
 	int (*d_revalidate)(struct dentry *, struct nameidata *);
-	int (*d_hash) (struct dentry *, struct qstr *);
-	int (*d_compare) (struct dentry *, struct qstr *, struct qstr *);
-	int (*d_delete)(struct dentry *);
+	int (*d_hash)(const struct dentry *, const struct inode *,
+			struct qstr *);
+	int (*d_compare)(const struct dentry *, const struct inode *,
+			const struct dentry *, const struct inode *,
+			unsigned int, const char *, const struct qstr *);
+	int (*d_delete)(const struct dentry *);
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)(struct dentry *, char *, int);
-};
-
-/* the dentry parameter passed to d_hash and d_compare is the parent
- * directory of the entries to be compared. It is used in case these
- * functions need any directory specific information for determining
- * equivalency classes.  Using the dentry itself might not work, as it
- * might be a negative dentry which has no information associated with
- * it */
+} ____cacheline_aligned;
 
 /*
-locking rules:
-		big lock	dcache_lock	d_lock   may block
-d_revalidate:	no		no		no       yes
-d_hash		no		no		no       yes
-d_compare:	no		yes		yes      no
-d_delete:	no		yes		no       no
-d_release:	no		no		no       yes
-d_iput:		no		no		no       yes
+ * Locking rules for dentry_operations callbacks are to be found in
+ * Documentation/filesystems/Locking. Keep it updated!
+ *
+ * FUrther descriptions are found in Documentation/filesystems/vfs.txt.
+ * Keep it updated too!
  */
 
 /* d_flags entries */
 #define DCACHE_AUTOFS_PENDING 0x0001    /* autofs: "under construction" */
-#define DCACHE_NFSFS_RENAMED  0x0002    /* this dentry has been "silly
-					 * renamed" and has to be
-					 * deleted on the last dput()
-					 */
-#define	DCACHE_DISCONNECTED 0x0004
-     /* This dentry is possibly not currently connected to the dcache tree,
-      * in which case its parent will either be itself, or will have this
-      * flag as well.  nfsd will not use a dentry with this bit set, but will
-      * first endeavour to clear the bit either by discovering that it is
-      * connected, or by performing lookup operations.   Any filesystem which
-      * supports nfsd_operations MUST have a lookup function which, if it finds
-      * a directory inode with a DCACHE_DISCONNECTED dentry, will d_move
-      * that dentry into place and return that dentry rather than the passed one,
-      * typically using d_splice_alias.
-      */
+#define DCACHE_NFSFS_RENAMED  0x0002
+     /* this dentry has been "silly renamed" and has to be deleted on the last
+      * dput() */
+
+#define	DCACHE_DISCONNECTED	0x0004
+     /* This dentry is possibly not currently connected to the dcache tree, in
+      * which case its parent will either be itself, or will have this flag as
+      * well.  nfsd will not use a dentry with this bit set, but will first
+      * endeavour to clear the bit either by discovering that it is connected,
+      * or by performing lookup operations.   Any filesystem which supports
+      * nfsd_operations MUST have a lookup function which, if it finds a
+      * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that
+      * dentry into place and return that dentry rather than the passed one,
+      * typically using d_splice_alias. */
 
 #define DCACHE_REFERENCED	0x0008  /* Recently used, don't discard. */
 #define DCACHE_UNHASHED		0x0010	
-
-#define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched by inotify */
+#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020
+     /* Parent inode is watched by inotify */
 
 #define DCACHE_COOKIE		0x0040	/* For use by dcookie subsystem */
-
-#define DCACHE_FSNOTIFY_PARENT_WATCHED	0x0080 /* Parent inode is watched by some fsnotify listener */
+#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080
+     /* Parent inode is watched by some fsnotify listener */
 
 #define DCACHE_CANT_MOUNT	0x0100
+#define DCACHE_GENOCIDE		0x0200
+#define DCACHE_MOUNTED		0x0400	/* is a mountpoint */
 
-extern spinlock_t dcache_lock;
-extern seqlock_t rename_lock;
-
-/**
- * d_drop - drop a dentry
- * @dentry: dentry to drop
- *
- * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
- * be found through a VFS lookup any more. Note that this is different from
- * deleting the dentry - d_delete will try to mark the dentry negative if
- * possible, giving a successful _negative_ lookup, while d_drop will
- * just make the cache lookup fail.
- *
- * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
- * reason (NFS timeouts or autofs deletes).
- *
- * __d_drop requires dentry->d_lock.
- */
-
-static inline void __d_drop(struct dentry *dentry)
-{
-	if (!(dentry->d_flags & DCACHE_UNHASHED)) {
-		dentry->d_flags |= DCACHE_UNHASHED;
-		hlist_del_rcu(&dentry->d_hash);
-	}
-}
+#define DCACHE_OP_HASH		0x1000
+#define DCACHE_OP_COMPARE	0x2000
+#define DCACHE_OP_REVALIDATE	0x4000
+#define DCACHE_OP_DELETE	0x8000
 
-static inline void d_drop(struct dentry *dentry)
-{
-	spin_lock(&dcache_lock);
-	spin_lock(&dentry->d_lock);
- 	__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&dcache_lock);
-}
+extern seqlock_t rename_lock;
 
 static inline int dname_external(struct dentry *dentry)
 {
@@ -235,10 +225,14 @@ static inline int dname_external(struct dentry *dentry)
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_materialise_unique(struct dentry *, struct inode *);
+extern void __d_drop(struct dentry *dentry);
+extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
+extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
+extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern struct dentry * d_obtain_alias(struct inode *);
@@ -296,14 +290,40 @@ static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *in
 	return res;
 }
 
+extern void dentry_update_name_case(struct dentry *, struct qstr *);
+
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
-extern struct dentry * d_lookup(struct dentry *, struct qstr *);
-extern struct dentry * __d_lookup(struct dentry *, struct qstr *);
-extern struct dentry * d_hash_and_lookup(struct dentry *, struct qstr *);
+extern struct dentry *d_lookup(struct dentry *, struct qstr *);
+extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *);
+extern struct dentry *__d_lookup(struct dentry *, struct qstr *);
+extern struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
+				unsigned *seq, struct inode **inode);
+
+/**
+ * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok
+ * @dentry: dentry to take a ref on
+ * @seq: seqcount to verify against
+ * @Returns: 0 on failure, else 1.
+ *
+ * __d_rcu_to_refcount operates on a dentry,seq pair that was returned
+ * by __d_lookup_rcu, to get a reference on an rcu-walk dentry.
+ */
+static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq)
+{
+	int ret = 0;
+
+	assert_spin_locked(&dentry->d_lock);
+	if (!read_seqcount_retry(&dentry->d_seq, seq)) {
+		ret = 1;
+		dentry->d_count++;
+	}
+
+	return ret;
+}
 
 /* validate "insecure" dentry pointer */
 extern int d_validate(struct dentry *, struct dentry *);
@@ -316,34 +336,37 @@ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
 extern char *__d_path(const struct path *path, struct path *root, char *, int);
 extern char *d_path(const struct path *, char *, int);
 extern char *d_path_with_unreachable(const struct path *, char *, int);
-extern char *__dentry_path(struct dentry *, char *, int);
+extern char *dentry_path_raw(struct dentry *, char *, int);
 extern char *dentry_path(struct dentry *, char *, int);
 
 /* Allocation counts.. */
 
 /**
- *	dget, dget_locked	-	get a reference to a dentry
+ *	dget, dget_dlock -	get a reference to a dentry
  *	@dentry: dentry to get a reference to
  *
  *	Given a dentry or %NULL pointer increment the reference count
  *	if appropriate and return the dentry. A dentry will not be 
- *	destroyed when it has references. dget() should never be
- *	called for dentries with zero reference counter. For these cases
- *	(preferably none, functions in dcache.c are sufficient for normal
- *	needs and they take necessary precautions) you should hold dcache_lock
- *	and call dget_locked() instead of dget().
+ *	destroyed when it has references.
  */
- 
+static inline struct dentry *dget_dlock(struct dentry *dentry)
+{
+	if (dentry)
+		dentry->d_count++;
+	return dentry;
+}
+
 static inline struct dentry *dget(struct dentry *dentry)
 {
 	if (dentry) {
-		BUG_ON(!atomic_read(&dentry->d_count));
-		atomic_inc(&dentry->d_count);
+		spin_lock(&dentry->d_lock);
+		dget_dlock(dentry);
+		spin_unlock(&dentry->d_lock);
 	}
 	return dentry;
 }
 
-extern struct dentry * dget_locked(struct dentry *);
+extern struct dentry *dget_parent(struct dentry *dentry);
 
 /**
  *	d_unhashed -	is dentry hashed
@@ -374,21 +397,11 @@ static inline void dont_mount(struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 }
 
-static inline struct dentry *dget_parent(struct dentry *dentry)
-{
-	struct dentry *ret;
-
-	spin_lock(&dentry->d_lock);
-	ret = dget(dentry->d_parent);
-	spin_unlock(&dentry->d_lock);
-	return ret;
-}
-
 extern void dput(struct dentry *);
 
 static inline int d_mountpoint(struct dentry *dentry)
 {
-	return dentry->d_mounted;
+	return dentry->d_flags & DCACHE_MOUNTED;
 }
 
 extern struct vfsmount *lookup_mnt(struct path *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 090f0eacde2..baf3e556ff0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -392,6 +392,7 @@ struct inodes_stat_t {
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
+#include <linux/rculist_bl.h>
 
 #include <asm/atomic.h>
 #include <asm/byteorder.h>
@@ -733,16 +734,31 @@ struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
 
 struct inode {
+	/* RCU path lookup touches following: */
+	umode_t			i_mode;
+	uid_t			i_uid;
+	gid_t			i_gid;
+	const struct inode_operations	*i_op;
+	struct super_block	*i_sb;
+
+	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
+	unsigned int		i_flags;
+	struct mutex		i_mutex;
+
+	unsigned long		i_state;
+	unsigned long		dirtied_when;	/* jiffies of first dirtying */
+
 	struct hlist_node	i_hash;
 	struct list_head	i_wb_list;	/* backing dev IO list */
 	struct list_head	i_lru;		/* inode LRU list */
 	struct list_head	i_sb_list;
-	struct list_head	i_dentry;
+	union {
+		struct list_head	i_dentry;
+		struct rcu_head		i_rcu;
+	};
 	unsigned long		i_ino;
 	atomic_t		i_count;
 	unsigned int		i_nlink;
-	uid_t			i_uid;
-	gid_t			i_gid;
 	dev_t			i_rdev;
 	unsigned int		i_blkbits;
 	u64			i_version;
@@ -755,13 +771,8 @@ struct inode {
 	struct timespec		i_ctime;
 	blkcnt_t		i_blocks;
 	unsigned short          i_bytes;
-	umode_t			i_mode;
-	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
-	struct mutex		i_mutex;
 	struct rw_semaphore	i_alloc_sem;
-	const struct inode_operations	*i_op;
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
-	struct super_block	*i_sb;
 	struct file_lock	*i_flock;
 	struct address_space	*i_mapping;
 	struct address_space	i_data;
@@ -782,11 +793,6 @@ struct inode {
 	struct hlist_head	i_fsnotify_marks;
 #endif
 
-	unsigned long		i_state;
-	unsigned long		dirtied_when;	/* jiffies of first dirtying */
-
-	unsigned int		i_flags;
-
 #ifdef CONFIG_IMA
 	/* protected by i_lock */
 	unsigned int		i_readcount; /* struct files open RO */
@@ -1372,13 +1378,13 @@ struct super_block {
 	const struct xattr_handler **s_xattr;
 
 	struct list_head	s_inodes;	/* all inodes */
-	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
+	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 #ifdef CONFIG_SMP
 	struct list_head __percpu *s_files;
 #else
 	struct list_head	s_files;
 #endif
-	/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
+	/* 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 */
 
@@ -1545,9 +1551,18 @@ struct file_operations {
 	int (*setlease)(struct file *, long, struct file_lock **);
 };
 
+#define IPERM_FLAG_RCU	0x0001
+
 struct inode_operations {
-	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
 	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+	void * (*follow_link) (struct dentry *, struct nameidata *);
+	int (*permission) (struct inode *, int, unsigned int);
+	int (*check_acl)(struct inode *, int, unsigned int);
+
+	int (*readlink) (struct dentry *, char __user *,int);
+	void (*put_link) (struct dentry *, struct nameidata *, void *);
+
+	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1556,12 +1571,7 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
-	int (*readlink) (struct dentry *, char __user *,int);
-	void * (*follow_link) (struct dentry *, struct nameidata *);
-	void (*put_link) (struct dentry *, struct nameidata *, void *);
 	void (*truncate) (struct inode *);
-	int (*permission) (struct inode *, int);
-	int (*check_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
@@ -1573,7 +1583,7 @@ struct inode_operations {
 			  loff_t len);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
-};
+} ____cacheline_aligned;
 
 struct seq_file;
 
@@ -2158,8 +2168,8 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int inode_permission(struct inode *, int);
-extern int generic_permission(struct inode *, int,
-		int (*check_acl)(struct inode *, int));
+extern int generic_permission(struct inode *, int, unsigned int,
+		int (*check_acl)(struct inode *, int, unsigned int));
 
 static inline bool execute_ok(struct inode *inode)
 {
@@ -2230,6 +2240,7 @@ extern void iget_failed(struct inode *);
 extern void end_writeback(struct inode *);
 extern void __destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
+extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_suid(struct file *);
 
@@ -2446,6 +2457,10 @@ static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;
 
+	/*
+	 * Don't strictly need d_lock here? If the parent ino could change
+	 * then surely we'd have a deeper race in the caller?
+	 */
 	spin_lock(&dentry->d_lock);
 	res = dentry->d_parent->d_inode->i_ino;
 	spin_unlock(&dentry->d_lock);
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index a42b5bf02f8..003dc0fd734 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -2,10 +2,13 @@
 #define _LINUX_FS_STRUCT_H
 
 #include <linux/path.h>
+#include <linux/spinlock.h>
+#include <linux/seqlock.h>
 
 struct fs_struct {
 	int users;
 	spinlock_t lock;
+	seqcount_t seq;
 	int umask;
 	int in_exec;
 	struct path root, pwd;
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index b10bcdeaef7..2a53f10712b 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -17,7 +17,6 @@
 
 /*
  * fsnotify_d_instantiate - instantiate a dentry for inode
- * Called with dcache_lock held.
  */
 static inline void fsnotify_d_instantiate(struct dentry *dentry,
 					  struct inode *inode)
@@ -62,7 +61,6 @@ static inline int fsnotify_perm(struct file *file, int mask)
 
 /*
  * fsnotify_d_move - dentry has been moved
- * Called with dcache_lock and dentry->d_lock held.
  */
 static inline void fsnotify_d_move(struct dentry *dentry)
 {
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 7380763595d..69ad89b5048 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -329,9 +329,15 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
 {
 	struct dentry *parent;
 
-	assert_spin_locked(&dcache_lock);
 	assert_spin_locked(&dentry->d_lock);
 
+	/*
+	 * Serialisation of setting PARENT_WATCHED on the dentries is provided
+	 * by d_lock. If inotify_inode_watched changes after we have taken
+	 * d_lock, the following __fsnotify_update_child_dentry_flags call will
+	 * find our entry, so it will spin until we complete here, and update
+	 * us with the new state.
+	 */
 	parent = dentry->d_parent;
 	if (parent->d_inode && fsnotify_inode_watches_children(parent->d_inode))
 		dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
@@ -341,15 +347,12 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
 
 /*
  * fsnotify_d_instantiate - instantiate a dentry for inode
- * Called with dcache_lock held.
  */
 static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
 {
 	if (!inode)
 		return;
 
-	assert_spin_locked(&dcache_lock);
-
 	spin_lock(&dentry->d_lock);
 	__fsnotify_update_dcache_flags(dentry);
 	spin_unlock(&dentry->d_lock);
diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h
index 574bea4013b..0437e377b55 100644
--- a/include/linux/generic_acl.h
+++ b/include/linux/generic_acl.h
@@ -10,6 +10,6 @@ extern const struct xattr_handler generic_acl_default_handler;
 
 int generic_acl_init(struct inode *, struct inode *);
 int generic_acl_chmod(struct inode *);
-int generic_check_acl(struct inode *inode, int mask);
+int generic_check_acl(struct inode *inode, int mask, unsigned int flags);
 
 #endif /* LINUX_GENERIC_ACL_H */
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
new file mode 100644
index 00000000000..9ee97e7f2be
--- /dev/null
+++ b/include/linux/list_bl.h
@@ -0,0 +1,144 @@
+#ifndef _LINUX_LIST_BL_H
+#define _LINUX_LIST_BL_H
+
+#include <linux/list.h>
+
+/*
+ * Special version of lists, where head of the list has a lock in the lowest
+ * bit. This is useful for scalable hash tables without increasing memory
+ * footprint overhead.
+ *
+ * For modification operations, the 0 bit of hlist_bl_head->first
+ * pointer must be set.
+ *
+ * With some small modifications, this can easily be adapted to store several
+ * arbitrary bits (not just a single lock bit), if the need arises to store
+ * some fast and compact auxiliary data.
+ */
+
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+#define LIST_BL_LOCKMASK	1UL
+#else
+#define LIST_BL_LOCKMASK	0UL
+#endif
+
+#ifdef CONFIG_DEBUG_LIST
+#define LIST_BL_BUG_ON(x) BUG_ON(x)
+#else
+#define LIST_BL_BUG_ON(x)
+#endif
+
+
+struct hlist_bl_head {
+	struct hlist_bl_node *first;
+};
+
+struct hlist_bl_node {
+	struct hlist_bl_node *next, **pprev;
+};
+#define INIT_HLIST_BL_HEAD(ptr) \
+	((ptr)->first = NULL)
+
+static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
+{
+	h->next = NULL;
+	h->pprev = NULL;
+}
+
+#define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member)
+
+static inline int hlist_bl_unhashed(const struct hlist_bl_node *h)
+{
+	return !h->pprev;
+}
+
+static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h)
+{
+	return (struct hlist_bl_node *)
+		((unsigned long)h->first & ~LIST_BL_LOCKMASK);
+}
+
+static inline void hlist_bl_set_first(struct hlist_bl_head *h,
+					struct hlist_bl_node *n)
+{
+	LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
+	LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK));
+	h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK);
+}
+
+static inline int hlist_bl_empty(const struct hlist_bl_head *h)
+{
+	return !((unsigned long)h->first & ~LIST_BL_LOCKMASK);
+}
+
+static inline void hlist_bl_add_head(struct hlist_bl_node *n,
+					struct hlist_bl_head *h)
+{
+	struct hlist_bl_node *first = hlist_bl_first(h);
+
+	n->next = first;
+	if (first)
+		first->pprev = &n->next;
+	n->pprev = &h->first;
+	hlist_bl_set_first(h, n);
+}
+
+static inline void __hlist_bl_del(struct hlist_bl_node *n)
+{
+	struct hlist_bl_node *next = n->next;
+	struct hlist_bl_node **pprev = n->pprev;
+
+	LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
+
+	/* pprev may be `first`, so be careful not to lose the lock bit */
+	*pprev = (struct hlist_bl_node *)
+			((unsigned long)next |
+			 ((unsigned long)*pprev & LIST_BL_LOCKMASK));
+	if (next)
+		next->pprev = pprev;
+}
+
+static inline void hlist_bl_del(struct hlist_bl_node *n)
+{
+	__hlist_bl_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_bl_del_init(struct hlist_bl_node *n)
+{
+	if (!hlist_bl_unhashed(n)) {
+		__hlist_bl_del(n);
+		INIT_HLIST_BL_NODE(n);
+	}
+}
+
+/**
+ * hlist_bl_for_each_entry	- iterate over list of given type
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ *
+ */
+#define hlist_bl_for_each_entry(tpos, pos, head, member)		\
+	for (pos = hlist_bl_first(head);				\
+	     pos &&							\
+		({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @n:		another &struct hlist_node to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member)	 \
+	for (pos = hlist_bl_first(head);				 \
+	     pos && ({ n = pos->next; 1; }) && 				 \
+		({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = n)
+
+#endif
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 5e7a59408dd..1869ea24a73 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -13,6 +13,7 @@
 #include <linux/list.h>
 #include <linux/nodemask.h>
 #include <linux/spinlock.h>
+#include <linux/seqlock.h>
 #include <asm/atomic.h>
 
 struct super_block;
@@ -46,12 +47,24 @@ struct mnt_namespace;
 
 #define MNT_INTERNAL	0x4000
 
+struct mnt_pcp {
+	int mnt_count;
+	int mnt_writers;
+};
+
 struct vfsmount {
 	struct list_head mnt_hash;
 	struct vfsmount *mnt_parent;	/* fs we are mounted on */
 	struct dentry *mnt_mountpoint;	/* dentry of mountpoint */
 	struct dentry *mnt_root;	/* root of the mounted tree */
 	struct super_block *mnt_sb;	/* pointer to superblock */
+#ifdef CONFIG_SMP
+	struct mnt_pcp __percpu *mnt_pcp;
+	atomic_t mnt_longrefs;
+#else
+	int mnt_count;
+	int mnt_writers;
+#endif
 	struct list_head mnt_mounts;	/* list of children, anchored here */
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	int mnt_flags;
@@ -70,57 +83,25 @@ struct vfsmount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	int mnt_id;			/* mount identifier */
 	int mnt_group_id;		/* peer group identifier */
-	/*
-	 * We put mnt_count & mnt_expiry_mark at the end of struct vfsmount
-	 * to let these frequently modified fields in a separate cache line
-	 * (so that reads of mnt_flags wont ping-pong on SMP machines)
-	 */
-	atomic_t mnt_count;
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
 	int mnt_ghosts;
-#ifdef CONFIG_SMP
-	int __percpu *mnt_writers;
-#else
-	int mnt_writers;
-#endif
 };
 
-static inline int *get_mnt_writers_ptr(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	return mnt->mnt_writers;
-#else
-	return &mnt->mnt_writers;
-#endif
-}
-
-static inline struct vfsmount *mntget(struct vfsmount *mnt)
-{
-	if (mnt)
-		atomic_i