Merge branch 'work.icache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs inode freeing updates from Al Viro:
 "Introduction of separate method for RCU-delayed part of
  ->destroy_inode() (if any).

  Pretty much as posted, except that destroy_inode() stashes
  ->free_inode into the victim (anon-unioned with ->i_fops) before
  scheduling i_callback() and the last two patches (sockfs conversion
  and folding struct socket_wq into struct socket) are excluded - that
  pair should go through netdev once davem reopens his tree"

* 'work.icache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (58 commits)
  orangefs: make use of ->free_inode()
  shmem: make use of ->free_inode()
  hugetlb: make use of ->free_inode()
  overlayfs: make use of ->free_inode()
  jfs: switch to ->free_inode()
  fuse: switch to ->free_inode()
  ext4: make use of ->free_inode()
  ecryptfs: make use of ->free_inode()
  ceph: use ->free_inode()
  btrfs: use ->free_inode()
  afs: switch to use of ->free_inode()
  dax: make use of ->free_inode()
  ntfs: switch to ->free_inode()
  securityfs: switch to ->free_inode()
  apparmor: switch to ->free_inode()
  rpcpipe: switch to ->free_inode()
  bpf: switch to ->free_inode()
  mqueue: switch to ->free_inode()
  ufs: switch to ->free_inode()
  coda: switch to ->free_inode()
  ...

Documentation/filesystems/Locking

@@ -118,6 +118,7 @@ set:		exclusive
 --------------------------- super_operations ---------------------------
 prototypes:
 	struct inode *(*alloc_inode)(struct super_block *sb);
+	void (*free_inode)(struct inode *);
 	void (*destroy_inode)(struct inode *);
 	void (*dirty_inode) (struct inode *, int flags);
 	int (*write_inode) (struct inode *, struct writeback_control *wbc);
@@ -139,6 +140,7 @@ locking rules:
 	All may block [not true, see below]
 			s_umount
 alloc_inode:
+free_inode:				called from RCU callback
 destroy_inode:
 dirty_inode:
 write_inode:

Documentation/filesystems/porting

@@ -638,3 +638,28 @@ in your dentry operations instead.
 	inode to d_splice_alias() will also do the right thing (equivalent of
 	d_add(dentry, NULL); return NULL;), so that kind of special cases
 	also doesn't need a separate treatment.
+--
+[strongly recommended]
+	take the RCU-delayed parts of ->destroy_inode() into a new method -
+	->free_inode().  If ->destroy_inode() becomes empty - all the better,
+	just get rid of it.  Synchronous work (e.g. the stuff that can't
+	be done from an RCU callback, or any WARN_ON() where we want the
+	stack trace) *might* be movable to ->evict_inode(); however,
+	that goes only for the things that are not needed to balance something
+	done by ->alloc_inode().  IOW, if it's cleaning up the stuff that
+	might have accumulated over the life of in-core inode, ->evict_inode()
+	might be a fit.
+
+	Rules for inode destruction:
+		* if ->destroy_inode() is non-NULL, it gets called
+		* if ->free_inode() is non-NULL, it gets scheduled by call_rcu()
+		* combination of NULL ->destroy_inode and NULL ->free_inode is
+		  treated as NULL/free_inode_nonrcu, to preserve the compatibility.
+
+	Note that the callback (be it via ->free_inode() or explicit call_rcu()
+	in ->destroy_inode()) is *NOT* ordered wrt superblock destruction;
+	as the matter of fact, the superblock and all associated structures
+	might be already gone.  The filesystem driver is guaranteed to be still
+	there, but that's it.  Freeing memory in the callback is fine; doing
+	more than that is possible, but requires a lot of care and is best
+	avoided.

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

@@ -71,17 +71,11 @@ spufs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void spufs_i_callback(struct rcu_head *head)
+static void spufs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	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)
 {
@@ -739,7 +733,7 @@ spufs_fill_super(struct super_block *sb, void *data, int silent)
 	struct spufs_sb_info *info;
 	static const struct super_operations s_ops = {
 		.alloc_inode = spufs_alloc_inode,
-		.destroy_inode = spufs_destroy_inode,
+		.free_inode = spufs_free_inode,
 		.statfs = simple_statfs,
 		.evict_inode = spufs_evict_inode,
 		.show_options = spufs_show_options,

drivers/dax/super.c

@@ -412,11 +412,9 @@ static struct dax_device *to_dax_dev(struct inode *inode)
 	return container_of(inode, struct dax_device, inode);
 }
 
-static void dax_i_callback(struct rcu_head *head)
+static void dax_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct dax_device *dax_dev = to_dax_dev(inode);
-
 	kfree(dax_dev->host);
 	dax_dev->host = NULL;
 	if (inode->i_rdev)
@@ -427,16 +425,15 @@ static void dax_i_callback(struct rcu_head *head)
 static void dax_destroy_inode(struct inode *inode)
 {
 	struct dax_device *dax_dev = to_dax_dev(inode);
-
 	WARN_ONCE(test_bit(DAXDEV_ALIVE, &dax_dev->flags),
 			"kill_dax() must be called before final iput()\n");
-	call_rcu(&inode->i_rcu, dax_i_callback);
 }
 
 static const struct super_operations dax_sops = {
 	.statfs = simple_statfs,
 	.alloc_inode = dax_alloc_inode,
 	.destroy_inode = dax_destroy_inode,
+	.free_inode = dax_free_inode,
 	.drop_inode = generic_delete_inode,
 };
 

drivers/staging/erofs/super.c

@@ -57,9 +57,8 @@ static struct inode *alloc_inode(struct super_block *sb)
 	return &vi->vfs_inode;
 }
 
-static void i_callback(struct rcu_head *head)
+static void free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct erofs_vnode *vi = EROFS_V(inode);
 
 	/* be careful RCU symlink path (see ext4_inode_info->i_data)! */
@@ -71,11 +70,6 @@ static void i_callback(struct rcu_head *head)
 	kmem_cache_free(erofs_inode_cachep, vi);
 }
 
-static void destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, i_callback);
-}
-
 static int superblock_read(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi;
@@ -668,7 +662,7 @@ out:
 const struct super_operations erofs_sops = {
 	.put_super = erofs_put_super,
 	.alloc_inode = alloc_inode,
-	.destroy_inode = destroy_inode,
+	.free_inode = free_inode,
 	.statfs = erofs_statfs,
 	.show_options = erofs_show_options,
 	.remount_fs = erofs_remount,

fs/9p/v9fs_vfs.h

@@ -58,7 +58,7 @@ extern const struct file_operations v9fs_mmap_file_operations_dotl;
 extern struct kmem_cache *v9fs_inode_cache;
 
 struct inode *v9fs_alloc_inode(struct super_block *sb);
-void v9fs_destroy_inode(struct inode *inode);
+void v9fs_free_inode(struct inode *inode);
 struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		    struct inode *inode, umode_t mode, dev_t);

fs/9p/vfs_inode.c

@@ -253,21 +253,15 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
 }
 
 /**
- * v9fs_destroy_inode - destroy an inode
+ * v9fs_free_inode - destroy an inode
  *
  */
 
-static void v9fs_i_callback(struct rcu_head *head)
+void v9fs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(v9fs_inode_cache, V9FS_I(inode));
 }
 
-void v9fs_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, v9fs_i_callback);
-}
-
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		    struct inode *inode, umode_t mode, dev_t rdev)
 {

fs/9p/vfs_super.c

@@ -344,7 +344,7 @@ static int v9fs_write_inode_dotl(struct inode *inode,
 
 static const struct super_operations v9fs_super_ops = {
 	.alloc_inode = v9fs_alloc_inode,
-	.destroy_inode = v9fs_destroy_inode,
+	.free_inode = v9fs_free_inode,
 	.statfs = simple_statfs,
 	.evict_inode = v9fs_evict_inode,
 	.show_options = v9fs_show_options,
@@ -354,7 +354,7 @@ static const struct super_operations v9fs_super_ops = {
 
 static const struct super_operations v9fs_super_ops_dotl = {
 	.alloc_inode = v9fs_alloc_inode,
-	.destroy_inode = v9fs_destroy_inode,
+	.free_inode = v9fs_free_inode,
 	.statfs = v9fs_statfs,
 	.drop_inode = v9fs_drop_inode,
 	.evict_inode = v9fs_evict_inode,

fs/adfs/super.c

@@ -248,17 +248,11 @@ static struct inode *adfs_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void adfs_i_callback(struct rcu_head *head)
+static void adfs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
 }
 
-static void adfs_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, adfs_i_callback);
-}
-
 static void init_once(void *foo)
 {
 	struct adfs_inode_info *ei = (struct adfs_inode_info *) foo;
@@ -290,7 +284,7 @@ static void destroy_inodecache(void)
 
 static const struct super_operations adfs_sops = {
 	.alloc_inode	= adfs_alloc_inode,
-	.destroy_inode	= adfs_destroy_inode,
+	.free_inode	= adfs_free_inode,
 	.drop_inode	= generic_delete_inode,
 	.write_inode	= adfs_write_inode,
 	.put_super	= adfs_put_super,

fs/affs/super.c

@@ -111,17 +111,11 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
 	return &i->vfs_inode;
 }
 
-static void affs_i_callback(struct rcu_head *head)
+static void affs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(affs_inode_cachep, AFFS_I(inode));
 }
 
-static void affs_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, affs_i_callback);
-}
-
 static void init_once(void *foo)
 {
 	struct affs_inode_info *ei = (struct affs_inode_info *) foo;
@@ -155,7 +149,7 @@ static void destroy_inodecache(void)
 
 static const struct super_operations affs_sops = {
 	.alloc_inode	= affs_alloc_inode,
-	.destroy_inode	= affs_destroy_inode,
+	.free_inode	= affs_free_inode,
 	.write_inode	= affs_write_inode,
 	.evict_inode	= affs_evict_inode,
 	.put_super	= affs_put_super,

fs/afs/super.c

@@ -33,6 +33,7 @@ static void afs_i_init_once(void *foo);
 static void afs_kill_super(struct super_block *sb);
 static struct inode *afs_alloc_inode(struct super_block *sb);
 static void afs_destroy_inode(struct inode *inode);
+static void afs_free_inode(struct inode *inode);
 static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int afs_show_devname(struct seq_file *m, struct dentry *root);
 static int afs_show_options(struct seq_file *m, struct dentry *root);
@@ -56,6 +57,7 @@ static const struct super_operations afs_super_ops = {
 	.alloc_inode	= afs_alloc_inode,
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
+	.free_inode	= afs_free_inode,
 	.evict_inode	= afs_evict_inode,
 	.show_devname	= afs_show_devname,
 	.show_options	= afs_show_options,
@@ -660,11 +662,9 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
 	return &vnode->vfs_inode;
 }
 
-static void afs_i_callback(struct rcu_head *head)
+static void afs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
-	struct afs_vnode *vnode = AFS_FS_I(inode);
-	kmem_cache_free(afs_inode_cachep, vnode);
+	kmem_cache_free(afs_inode_cachep, AFS_FS_I(inode));
 }
 
 /*
@@ -680,7 +680,6 @@ static void afs_destroy_inode(struct inode *inode)
 
 	ASSERTCMP(vnode->cb_interest, ==, NULL);
 
-	call_rcu(&inode->i_rcu, afs_i_callback);
 	atomic_dec(&afs_count_active_inodes);
 }
 

fs/befs/linuxvfs.c

@@ -44,7 +44,7 @@ static struct dentry *befs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
 static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
-static void befs_destroy_inode(struct inode *inode);
+static void befs_free_inode(struct inode *inode);
 static void befs_destroy_inodecache(void);
 static int befs_symlink_readpage(struct file *, struct page *);
 static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
@@ -64,7 +64,7 @@ static struct dentry *befs_get_parent(struct dentry *child);
 
 static const struct super_operations befs_sops = {
 	.alloc_inode	= befs_alloc_inode,	/* allocate a new inode */
-	.destroy_inode	= befs_destroy_inode, /* deallocate an inode */
+	.free_inode	= befs_free_inode, /* deallocate an inode */
 	.put_super	= befs_put_super,	/* uninit super */
 	.statfs		= befs_statfs,	/* statfs */
 	.remount_fs	= befs_remount,
@@ -281,17 +281,11 @@ befs_alloc_inode(struct super_block *sb)
 	return &bi->vfs_inode;
 }
 
-static void befs_i_callback(struct rcu_head *head)
+static void befs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	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

@@ -245,17 +245,11 @@ static struct inode *bfs_alloc_inode(struct super_block *sb)
 	return &bi->vfs_inode;
 }
 
-static void bfs_i_callback(struct rcu_head *head)
+static void bfs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(bfs_inode_cachep, BFS_I(inode));
 }
 
-static void bfs_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, bfs_i_callback);
-}
-
 static void init_once(void *foo)
 {
 	struct bfs_inode_info *bi = foo;
@@ -287,7 +281,7 @@ static void destroy_inodecache(void)
 
 static const struct super_operations bfs_sops = {
 	.alloc_inode	= bfs_alloc_inode,
-	.destroy_inode	= bfs_destroy_inode,
+	.free_inode	= bfs_free_inode,
 	.write_inode	= bfs_write_inode,
 	.evict_inode	= bfs_evict_inode,
 	.put_super	= bfs_put_super,

fs/block_dev.c

@@ -790,17 +790,9 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
-static void bdev_i_callback(struct rcu_head *head)
+static void bdev_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
-	struct bdev_inode *bdi = BDEV_I(inode);
-
-	kmem_cache_free(bdev_cachep, bdi);
-}
-
-static void bdev_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, bdev_i_callback);
+	kmem_cache_free(bdev_cachep, BDEV_I(inode));
 }
 
 static void init_once(void *foo)
@@ -840,7 +832,7 @@ static void bdev_evict_inode(struct inode *inode)
 static const struct super_operations bdev_sops = {
 	.statfs = simple_statfs,
 	.alloc_inode = bdev_alloc_inode,
-	.destroy_inode = bdev_destroy_inode,
+	.free_inode = bdev_free_inode,
 	.drop_inode = generic_delete_inode,
 	.evict_inode = bdev_evict_inode,
 };

fs/btrfs/ctree.h

@@ -3267,6 +3267,7 @@ void btrfs_evict_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
+void btrfs_free_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
 void __cold btrfs_destroy_cachep(void);

fs/btrfs/inode.c

@@ -9206,9 +9206,8 @@ void btrfs_test_destroy_inode(struct inode *inode)
 }
 #endif
 
-static void btrfs_i_callback(struct rcu_head *head)
+void btrfs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 
@@ -9234,7 +9233,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	 * created.
 	 */
 	if (!root)
-		goto free;
+		return;
 
 	while (1) {
 		ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
@@ -9252,8 +9251,6 @@ void btrfs_destroy_inode(struct inode *inode)
 	btrfs_qgroup_check_reserved_leak(inode);
 	inode_tree_del(inode);
 	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
-free:
-	call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
 
 int btrfs_drop_inode(struct inode *inode)

fs/btrfs/super.c

@@ -2298,6 +2298,7 @@ static const struct super_operations btrfs_super_ops = {
 	.show_devname	= btrfs_show_devname,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
+	.free_inode	= btrfs_free_inode,
 	.statfs		= btrfs_statfs,
 	.remount_fs	= btrfs_remount,
 	.freeze_fs	= btrfs_freeze,

fs/ceph/inode.c

@@ -519,9 +519,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	return &ci->vfs_inode;
 }
 
-static void ceph_i_callback(struct rcu_head *head)
+void ceph_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	kfree(ci->i_symlink);
@@ -581,8 +580,6 @@ void ceph_destroy_inode(struct inode *inode)
 		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
 	ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
-
-	call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
 int ceph_drop_inode(struct inode *inode)

fs/ceph/super.c

@@ -848,6 +848,7 @@ static void ceph_umount_begin(struct super_block *sb)
 static const struct super_operations ceph_super_ops = {
 	.alloc_inode	= ceph_alloc_inode,
 	.destroy_inode	= ceph_destroy_inode,
+	.free_inode	= ceph_free_inode,
 	.write_inode    = ceph_write_inode,
 	.drop_inode	= ceph_drop_inode,
 	.sync_fs        = ceph_sync_fs,

fs/ceph/super.h

@@ -874,6 +874,7 @@ extern const struct inode_operations ceph_file_iops;
 
 extern struct inode *ceph_alloc_inode(struct super_block *sb);
 extern void ceph_destroy_inode(struct inode *inode);
+extern void ceph_free_inode(struct inode *inode);
 extern int ceph_drop_inode(struct inode *inode);
 
 extern struct inode *ceph_get_inode(struct super_block *sb,