fs: icache RCU free inodes

RCU free the struct inode. This will allow:

- Subsequent store-free path walking patch. The inode must be consulted for
  permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
  to take i_lock no longer need to take sb_inode_list_lock to walk the list in
  the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
  page lock to follow page->mapping.

The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.

In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.

The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>

Documentation/filesystems/porting

@@ -346,3 +346,17 @@ look at examples of other filesystems) for guidance.
 for details of what locks to replace dcache_lock with in order to protect
 particular things. Most of the time, a filesystem only needs ->d_lock, which
 protects *all* the dcache state of a given dentry.
+
+--
+[mandatory]
+
+	Filesystems must RCU-free their inodes, if they can have been accessed
+via rcu-walk path walk (basically, if the file can have had a path name in the
+vfs namespace).
+
+	i_dentry and i_rcu share storage in a union, and the vfs expects
+i_dentry to be reinitialized before it is freed, so an:
+
+  INIT_LIST_HEAD(&inode->i_dentry);
+
+must be done in the RCU callback.

arch/powerpc/platforms/cell/spufs/inode.c

@@ -71,12 +71,18 @@ spufs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void
-spufs_destroy_inode(struct inode *inode)
+static void spufs_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
 	kmem_cache_free(spufs_inode_cache, SPUFS_I(inode));
 }
 
+static void spufs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, spufs_i_callback);
+}
+
 static void
 spufs_init_once(void *p)
 {

drivers/staging/pohmelfs/inode.c

@@ -826,6 +826,13 @@ const struct address_space_operations pohmelfs_aops = {
 	.set_page_dirty 	= __set_page_dirty_nobuffers,
 };
 
+static void pohmelfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(pohmelfs_inode_cache, POHMELFS_I(inode));
+}
+
 /*
  * ->detroy_inode() callback. Deletes inode from the caches
  *  and frees private data.
@@ -842,8 +849,8 @@ static void pohmelfs_destroy_inode(struct inode *inode)
 
 	dprintk("%s: pi: %p, inode: %p, ino: %llu.\n",
 		__func__, pi, &pi->vfs_inode, pi->ino);
-	kmem_cache_free(pohmelfs_inode_cache, pi);
 	atomic_long_dec(&psb->total_inodes);
+	call_rcu(&inode->i_rcu, pohmelfs_i_callback);
 }
 
 /*

drivers/staging/smbfs/inode.c

@@ -62,9 +62,16 @@ static struct inode *smb_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void smb_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(smb_inode_cachep, SMB_I(inode));
+}
+
 static void smb_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(smb_inode_cachep, SMB_I(inode));
+	call_rcu(&inode->i_rcu, smb_i_callback);
 }
 
 static void init_once(void *foo)

fs/9p/vfs_inode.c

@@ -237,9 +237,16 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
  *
  */
 
+static void v9fs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(vcookie_cache, v9fs_inode2cookie(inode));
+}
+
 void v9fs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(vcookie_cache, v9fs_inode2cookie(inode));
+	call_rcu(&inode->i_rcu, v9fs_i_callback);
 }
 #endif
 

fs/adfs/super.c

@@ -240,9 +240,16 @@ static struct inode *adfs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void adfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
+}
+
 static void adfs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
+	call_rcu(&inode->i_rcu, adfs_i_callback);
 }
 
 static void init_once(void *foo)

fs/affs/super.c

@@ -95,9 +95,16 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
 	return &i->vfs_inode;
 }
 
+static void affs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(affs_inode_cachep, AFFS_I(inode));
+}
+
 static void affs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(affs_inode_cachep, AFFS_I(inode));
+	call_rcu(&inode->i_rcu, affs_i_callback);
 }
 
 static void init_once(void *foo)

fs/afs/super.c

@@ -498,6 +498,14 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
 	return &vnode->vfs_inode;
 }
 
+static void afs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(afs_inode_cachep, vnode);
+}
+
 /*
  * destroy an AFS inode struct
  */
@@ -511,7 +519,7 @@ static void afs_destroy_inode(struct inode *inode)
 
 	ASSERTCMP(vnode->server, ==, NULL);
 
-	kmem_cache_free(afs_inode_cachep, vnode);
+	call_rcu(&inode->i_rcu, afs_i_callback);
 	atomic_dec(&afs_count_active_inodes);
 }
 

fs/befs/linuxvfs.c

@@ -284,12 +284,18 @@ befs_alloc_inode(struct super_block *sb)
         return &bi->vfs_inode;
 }
 
-static void
-befs_destroy_inode(struct inode *inode)
+static void befs_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(befs_inode_cachep, BEFS_I(inode));
 }
 
+static void befs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, befs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct befs_inode_info *bi = (struct befs_inode_info *) foo;

fs/bfs/inode.c

@@ -248,9 +248,16 @@ static struct inode *bfs_alloc_inode(struct super_block *sb)
 	return &bi->vfs_inode;
 }
 
+static void bfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(bfs_inode_cachep, BFS_I(inode));
+}
+
 static void bfs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(bfs_inode_cachep, BFS_I(inode));
+	call_rcu(&inode->i_rcu, bfs_i_callback);
 }
 
 static void init_once(void *foo)

fs/block_dev.c

@@ -409,13 +409,20 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void bdev_destroy_inode(struct inode *inode)
+static void bdev_i_callback(struct rcu_head *head)
 {
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct bdev_inode *bdi = BDEV_I(inode);
 
+	INIT_LIST_HEAD(&inode->i_dentry);
 	kmem_cache_free(bdev_cachep, bdi);
 }
 
+static void bdev_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, bdev_i_callback);
+}
+
 static void init_once(void *foo)
 {
 	struct bdev_inode *ei = (struct bdev_inode *) foo;

fs/btrfs/inode.c

@@ -6495,6 +6495,13 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	return inode;
 }
 
+static void btrfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+}
+
 void btrfs_destroy_inode(struct inode *inode)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -6564,7 +6571,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	inode_tree_del(inode);
 	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
 free:
-	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+	call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
 
 int btrfs_drop_inode(struct inode *inode)

fs/ceph/inode.c

@@ -368,6 +368,15 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	return &ci->vfs_inode;
 }
 
+static void ceph_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(ceph_inode_cachep, ci);
+}
+
 void ceph_destroy_inode(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -407,7 +416,7 @@ void ceph_destroy_inode(struct inode *inode)
 	if (ci->i_xattrs.prealloc_blob)
 		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
-	kmem_cache_free(ceph_inode_cachep, ci);
+	call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
 

fs/cifs/cifsfs.c

@@ -334,10 +334,17 @@ cifs_alloc_inode(struct super_block *sb)
 	return &cifs_inode->vfs_inode;
 }
 
+static void cifs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
+}
+
 static void
 cifs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
+	call_rcu(&inode->i_rcu, cifs_i_callback);
 }
 
 static void

fs/coda/inode.c

@@ -56,9 +56,16 @@ static struct inode *coda_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void coda_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(coda_inode_cachep, ITOC(inode));
+}
+
 static void coda_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(coda_inode_cachep, ITOC(inode));
+	call_rcu(&inode->i_rcu, coda_i_callback);
 }
 
 static void init_once(void *foo)

fs/ecryptfs/super.c

@@ -62,6 +62,16 @@ out:
 	return inode;
 }
 
+static void ecryptfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct ecryptfs_inode_info *inode_info;
+	inode_info = ecryptfs_inode_to_private(inode);
+
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
+}
+
 /**
  * ecryptfs_destroy_inode
  * @inode: The ecryptfs inode
@@ -88,7 +98,7 @@ static void ecryptfs_destroy_inode(struct inode *inode)
 		}
 	}
 	ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
-	kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
+	call_rcu(&inode->i_rcu, ecryptfs_i_callback);
 }
 
 /**

fs/efs/super.c

@@ -65,9 +65,16 @@ static struct inode *efs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void efs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
+}
+
 static void efs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
+	call_rcu(&inode->i_rcu, efs_i_callback);
 }
 
 static void init_once(void *foo)

fs/exofs/super.c

@@ -150,12 +150,19 @@ static struct inode *exofs_alloc_inode(struct super_block *sb)
 	return &oi->vfs_inode;
 }
 
+static void exofs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
+}
+
 /*
  * Remove an inode from the cache
  */
 static void exofs_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
+	call_rcu(&inode->i_rcu, exofs_i_callback);
 }
 
 /*

fs/ext2/super.c

@@ -161,9 +161,16 @@ static struct inode *ext2_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void ext2_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
+}
+
 static void ext2_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
+	call_rcu(&inode->i_rcu, ext2_i_callback);
 }
 
 static void init_once(void *foo)

fs/ext3/super.c

@@ -479,6 +479,13 @@ static struct inode *ext3_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+static void ext3_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
+}
+
 static void ext3_destroy_inode(struct inode *inode)
 {
 	if (!list_empty(&(EXT3_I(inode)->i_orphan))) {
@@ -489,7 +496,7 @@ static void ext3_destroy_inode(struct inode *inode)
 				false);
 		dump_stack();
 	}
-	kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
+	call_rcu(&inode->i_rcu, ext3_i_callback);
 }
 
 static void init_once(void *foo)