Merge branches 'work.dcache-misc' and 'work.dcache2' into work.dcache

Documentation/filesystems/porting.rst

@@ -1061,3 +1061,37 @@ export_operations ->encode_fh() no longer has a default implementation to
 encode FILEID_INO32_GEN* file handles.
 Filesystems that used the default implementation may use the generic helper
 generic_encode_ino32_fh() explicitly.
+
+---
+
+**mandatory**
+
+The list of children anchored in parent dentry got turned into hlist now.
+Field names got changed (->d_children/->d_sib instead of ->d_subdirs/->d_child
+for anchor/entries resp.), so any affected places will be immediately caught
+by compiler.
+
+---
+
+**mandatory**
+
+->d_delete() instances are now called for dentries with ->d_lock held
+and refcount equal to 0.  They are not permitted to drop/regain ->d_lock.
+None of in-tree instances did anything of that sort.  Make sure yours do not...
+
+--
+
+**mandatory**
+
+->d_prune() instances are now called without ->d_lock held on the parent.
+->d_lock on dentry itself is still held; if you need per-parent exclusions (none
+of the in-tree instances did), use your own spinlock.
+
+->d_iput() and ->d_release() are called with victim dentry still in the
+list of parent's children.  It is still unhashed, marked killed, etc., just not
+removed from parent's ->d_children yet.
+
+Anyone iterating through the list of children needs to be aware of the
+half-killed dentries that might be seen there; taking ->d_lock on those will
+see them negative, unhashed and with negative refcount, which means that most
+of the in-kernel users would've done the right thing anyway without any adjustment.

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

@@ -145,10 +145,11 @@ spufs_evict_inode(struct inode *inode)
 
 static void spufs_prune_dir(struct dentry *dir)
 {
-	struct dentry *dentry, *tmp;
+	struct dentry *dentry;
+	struct hlist_node *n;
 
 	inode_lock(d_inode(dir));
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
+	hlist_for_each_entry_safe(dentry, n, &dir->d_children, d_sib) {
 		spin_lock(&dentry->d_lock);
 		if (simple_positive(dentry)) {
 			dget_dlock(dentry);

fs/afs/dynroot.c

@@ -370,7 +370,7 @@ int afs_dynroot_populate(struct super_block *sb)
 void afs_dynroot_depopulate(struct super_block *sb)
 {
 	struct afs_net *net = afs_sb2net(sb);
-	struct dentry *root = sb->s_root, *subdir, *tmp;
+	struct dentry *root = sb->s_root, *subdir;
 
 	/* Prevent more subdirs from being created */
 	mutex_lock(&net->proc_cells_lock);
@@ -379,10 +379,11 @@ void afs_dynroot_depopulate(struct super_block *sb)
 	mutex_unlock(&net->proc_cells_lock);
 
 	if (root) {
+		struct hlist_node *n;
 		inode_lock(root->d_inode);
 
 		/* Remove all the pins for dirs created for manually added cells */
-		list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) {
+		hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) {
 			if (subdir->d_fsdata) {
 				subdir->d_fsdata = NULL;
 				dput(subdir);

fs/autofs/expire.c

@@ -73,12 +73,9 @@ static int autofs_mount_busy(struct vfsmount *mnt,
 /* p->d_lock held */
 static struct dentry *positive_after(struct dentry *p, struct dentry *child)
 {
-	if (child)
-		child = list_next_entry(child, d_child);
-	else
-		child = list_first_entry(&p->d_subdirs, struct dentry, d_child);
+	child = child ? d_next_sibling(child) : d_first_child(p);
 
-	list_for_each_entry_from(child, &p->d_subdirs, d_child) {
+	hlist_for_each_entry_from(child, d_sib) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			dget_dlock(child);

fs/ceph/dir.c

@@ -174,7 +174,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
- * d_child when we initially get results back from the MDS, and
+ * d_children when we initially get results back from the MDS, and
  * falling back to a "normal" sync readdir if any dentries in the dir
  * are dropped.
  *

fs/ceph/mds_client.c

@@ -2128,7 +2128,7 @@ static bool drop_negative_children(struct dentry *dentry)
 		goto out;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+	hlist_for_each_entry(child, &dentry->d_children, d_sib) {
 		if (d_really_is_positive(child)) {
 			all_negative = false;
 			break;

fs/coda/cache.c

@@ -93,13 +93,13 @@ static void coda_flag_children(struct dentry *parent, int flag)
 	struct dentry *de;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(de, &parent->d_subdirs, d_child) {
+	hlist_for_each_entry(de, &parent->d_children, d_sib) {
+		struct inode *inode = d_inode_rcu(de);
 		/* don't know what to do with negative dentries */
-		if (d_inode(de) ) 
-			coda_flag_inode(d_inode(de), flag);
+		if (inode)
+			coda_flag_inode(inode, flag);
 	}
 	spin_unlock(&parent->d_lock);
-	return; 
 }
 
 void coda_flag_inode_children(struct inode *inode, int flag)

fs/libfs.c

@@ -104,15 +104,16 @@ EXPORT_SYMBOL(dcache_dir_close);
  * If no such element exists, NULL is returned.
  */
 static struct dentry *scan_positives(struct dentry *cursor,
-					struct list_head *p,
+					struct hlist_node **p,
 					loff_t count,
 					struct dentry *last)
 {
 	struct dentry *dentry = cursor->d_parent, *found = NULL;
 
 	spin_lock(&dentry->d_lock);
-	while ((p = p->next) != &dentry->d_subdirs) {
-		struct dentry *d = list_entry(p, struct dentry, d_child);
+	while (*p) {
+		struct dentry *d = hlist_entry(*p, struct dentry, d_sib);
+		p = &d->d_sib.next;
 		// we must at least skip cursors, to avoid livelocks
 		if (d->d_flags & DCACHE_DENTRY_CURSOR)
 			continue;
@@ -126,8 +127,10 @@ static struct dentry *scan_positives(struct dentry *cursor,
 			count = 1;
 		}
 		if (need_resched()) {
-			list_move(&cursor->d_child, p);
-			p = &cursor->d_child;
+			if (!hlist_unhashed(&cursor->d_sib))
+				__hlist_del(&cursor->d_sib);
+			hlist_add_behind(&cursor->d_sib, &d->d_sib);
+			p = &cursor->d_sib.next;
 			spin_unlock(&dentry->d_lock);
 			cond_resched();
 			spin_lock(&dentry->d_lock);
@@ -159,13 +162,12 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 		inode_lock_shared(dentry->d_inode);
 
 		if (offset > 2)
-			to = scan_positives(cursor, &dentry->d_subdirs,
+			to = scan_positives(cursor, &dentry->d_children.first,
 					    offset - 2, NULL);
 		spin_lock(&dentry->d_lock);
+		hlist_del_init(&cursor->d_sib);
 		if (to)
-			list_move(&cursor->d_child, &to->d_child);
-		else
-			list_del_init(&cursor->d_child);
+			hlist_add_behind(&cursor->d_sib, &to->d_sib);
 		spin_unlock(&dentry->d_lock);
 		dput(to);
 
@@ -187,19 +189,16 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *anchor = &dentry->d_subdirs;
 	struct dentry *next = NULL;
-	struct list_head *p;
+	struct hlist_node **p;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
 	if (ctx->pos == 2)
-		p = anchor;
-	else if (!list_empty(&cursor->d_child))
-		p = &cursor->d_child;
+		p = &dentry->d_children.first;
 	else
-		return 0;
+		p = &cursor->d_sib.next;
 
 	while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
@@ -207,13 +206,12 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 			      fs_umode_to_dtype(d_inode(next)->i_mode)))
 			break;
 		ctx->pos++;
-		p = &next->d_child;
+		p = &next->d_sib.next;
 	}
 	spin_lock(&dentry->d_lock);
+	hlist_del_init(&cursor->d_sib);
 	if (next)
-		list_move_tail(&cursor->d_child, &next->d_child);
-	else
-		list_del_init(&cursor->d_child);
+		hlist_add_before(&cursor->d_sib, &next->d_sib);
 	spin_unlock(&dentry->d_lock);
 	dput(next);
 
@@ -492,12 +490,11 @@ const struct file_operations simple_offset_dir_operations = {
 
 static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
 {
-	struct dentry *child = NULL;
-	struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs;
+	struct dentry *child = NULL, *d;
 
 	spin_lock(&parent->d_lock);
-	while ((p = p->next) != &parent->d_subdirs) {
-		struct dentry *d = container_of(p, struct dentry, d_child);
+	d = prev ? d_next_sibling(prev) : d_first_child(parent);
+	hlist_for_each_entry_from(d, d_sib) {
 		if (simple_positive(d)) {
 			spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
 			if (simple_positive(d))
@@ -658,7 +655,7 @@ int simple_empty(struct dentry *dentry)
 	int ret = 0;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+	hlist_for_each_entry(child, &dentry->d_children, d_sib) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			spin_unlock(&child->d_lock);

fs/nfsd/nfsctl.c

@@ -1236,63 +1236,34 @@ static inline void _nfsd_symlink(struct dentry *parent, const char *name,
 
 #endif
 
-static void clear_ncl(struct inode *inode)
+static void clear_ncl(struct dentry *dentry)
 {
+	struct inode *inode = d_inode(dentry);
 	struct nfsdfs_client *ncl = inode->i_private;
 
+	spin_lock(&inode->i_lock);
 	inode->i_private = NULL;
+	spin_unlock(&inode->i_lock);
 	kref_put(&ncl->cl_ref, ncl->cl_release);
 }
 
-static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
-{
-	struct nfsdfs_client *nc = inode->i_private;
-
-	if (nc)
-		kref_get(&nc->cl_ref);
-	return nc;
-}
-
 struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
 {
 	struct nfsdfs_client *nc;
 
-	inode_lock_shared(inode);
-	nc = __get_nfsdfs_client(inode);
-	inode_unlock_shared(inode);
+	spin_lock(&inode->i_lock);
+	nc = inode->i_private;
+	if (nc)
+		kref_get(&nc->cl_ref);
+	spin_unlock(&inode->i_lock);
 	return nc;
 }
-/* from __rpc_unlink */
-static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
-{
-	int ret;
-
-	clear_ncl(d_inode(dentry));
-	dget(dentry);
-	ret = simple_unlink(dir, dentry);
-	d_drop(dentry);
-	fsnotify_unlink(dir, dentry);
-	dput(dentry);
-	WARN_ON_ONCE(ret);
-}
-
-static void nfsdfs_remove_files(struct dentry *root)
-{
-	struct dentry *dentry, *tmp;
-
-	list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) {
-		if (!simple_positive(dentry)) {
-			WARN_ON_ONCE(1); /* I think this can't happen? */
-			continue;
-		}
-		nfsdfs_remove_file(d_inode(root), dentry);
-	}
-}
 
 /* XXX: cut'n'paste from simple_fill_super; figure out if we could share
  * code instead. */
 static  int nfsdfs_create_files(struct dentry *root,
 				const struct tree_descr *files,
+				struct nfsdfs_client *ncl,
 				struct dentry **fdentries)
 {
 	struct inode *dir = d_inode(root);
@@ -1311,8 +1282,9 @@ static  int nfsdfs_create_files(struct dentry *root,
 			dput(dentry);
 			goto out;
 		}
+		kref_get(&ncl->cl_ref);
 		inode->i_fop = files->ops;
-		inode->i_private = __get_nfsdfs_client(dir);
+		inode->i_private = ncl;
 		d_add(dentry, inode);
 		fsnotify_create(dir, dentry);
 		if (fdentries)
@@ -1321,7 +1293,6 @@ static  int nfsdfs_create_files(struct dentry *root,
 	inode_unlock(dir);
 	return 0;
 out:
-	nfsdfs_remove_files(root);
 	inode_unlock(dir);
 	return -ENOMEM;
 }
@@ -1341,7 +1312,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 	dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
 	if (IS_ERR(dentry)) /* XXX: tossing errors? */
 		return NULL;
-	ret = nfsdfs_create_files(dentry, files, fdentries);
+	ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
 	if (ret) {
 		nfsd_client_rmdir(dentry);
 		return NULL;
@@ -1352,20 +1323,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 /* Taken from __rpc_rmdir: */
 void nfsd_client_rmdir(struct dentry *dentry)
 {
-	struct inode *dir = d_inode(dentry->d_parent);
-	struct inode *inode = d_inode(dentry);
-	int ret;
-
-	inode_lock(dir);
-	nfsdfs_remove_files(dentry);
-	clear_ncl(inode);
-	dget(dentry);
-	ret = simple_rmdir(dir, dentry);
-	WARN_ON_ONCE(ret);
-	d_drop(dentry);
-	fsnotify_rmdir(dir, dentry);
-	dput(dentry);
-	inode_unlock(dir);
+	simple_recursive_removal(dentry, clear_ncl);
 }
 
 static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)

fs/notify/fsnotify.c

@@ -124,7 +124,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 		 * d_flags to indicate parental interest (their parent is the
 		 * original inode) */
 		spin_lock(&alias->d_lock);
-		list_for_each_entry(child, &alias->d_subdirs, d_child) {
+		hlist_for_each_entry(child, &alias->d_children, d_sib) {
 			if (!child->d_inode)
 				continue;
 

fs/tracefs/inode.c

@@ -199,26 +199,21 @@ static void change_gid(struct dentry *dentry, kgid_t gid)
  */
 static void set_gid(struct dentry *parent, kgid_t gid)
 {
-	struct dentry *this_parent;
-	struct list_head *next;
+	struct dentry *this_parent, *dentry;
 
 	this_parent = parent;
 	spin_lock(&this_parent->d_lock);
 
 	change_gid(this_parent, gid);
 repeat:
-	next = this_parent->d_subdirs.next;
+	dentry = d_first_child(this_parent);
 resume:
-	while (next != &this_parent->d_subdirs) {
-		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
-		next = tmp->next;
-
+	hlist_for_each_entry_from(dentry, d_sib) {
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 
 		change_gid(dentry, gid);
 
-		if (!list_empty(&dentry->d_subdirs)) {
+		if (!hlist_empty(&dentry->d_children)) {
 			spin_unlock(&this_parent->d_lock);
 			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
 			this_parent = dentry;
@@ -233,21 +228,20 @@ static void set_gid(struct dentry *parent, kgid_t gid)
 	rcu_read_lock();
 ascend:
 	if (this_parent != parent) {
-		struct dentry *child = this_parent;
-		this_parent = child->d_parent;
+		dentry = this_parent;
+		this_parent = dentry->d_parent;
 
-		spin_unlock(&child->d_lock);
+		spin_unlock(&dentry->d_lock);
 		spin_lock(&this_parent->d_lock);
 
 		/* go into the first sibling still alive */
-		do {
-			next = child->d_child.next;
-			if (next == &this_parent->d_subdirs)
-				goto ascend;
-			child = list_entry(next, struct dentry, d_child);
-		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
-		rcu_read_unlock();
-		goto resume;
+		hlist_for_each_entry_continue(dentry, d_sib) {
+			if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
+				rcu_read_unlock();
+				goto resume;
+			}
+		}
+		goto ascend;
 	}
 	rcu_read_unlock();
 	spin_unlock(&this_parent->d_lock);

include/linux/dcache.h

@@ -68,12 +68,12 @@ extern const struct qstr dotdot_name;
  * large memory footprint increase).
  */
 #ifdef CONFIG_64BIT
-# define DNAME_INLINE_LEN 32 /* 192 bytes */
+# define DNAME_INLINE_LEN 40 /* 192 bytes */
 #else
 # ifdef CONFIG_SMP
-#  define DNAME_INLINE_LEN 36 /* 128 bytes */
-# else
 #  define DNAME_INLINE_LEN 40 /* 128 bytes */
+# else
+#  define DNAME_INLINE_LEN 44 /* 128 bytes */
 # endif
 #endif
 
@@ -101,8 +101,8 @@ struct dentry {
 		struct list_head d_lru;		/* LRU list */
 		wait_queue_head_t *d_wait;	/* in-lookup ones only */
 	};
-	struct list_head d_child;	/* child of parent list */
-	struct list_head d_subdirs;	/* our children */
+	struct hlist_node d_sib;	/* child of parent list */
+	struct hlist_head d_children;	/* our children */
 	/*
 	 * d_alias and d_rcu can share memory
 	 */
@@ -564,4 +564,14 @@ struct name_snapshot {
 void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
 void release_dentry_name_snapshot(struct name_snapshot *);
 
+static inline struct dentry *d_first_child(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib);
+}
+
+static inline struct dentry *d_next_sibling(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
+}
+
 #endif	/* __LINUX_DCACHE_H */