fuse update for 5.14

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSQHSd0lITzzeNWNm3h3BK/laaZPAUCYORvYQAKCRDh3BK/laaZ
 PCfvAQCbU+PW2RbwlqjZMet6w9qorh29XYe786P5pNRVbMYCygD+N45l66Sbd/Rz
 7M7ioVDseyTW4dnLhb8SzSNB0zr6jQs=
 =MDvD
 -----END PGP SIGNATURE-----

Merge tag 'fuse-update-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Fixes for virtiofs submounts

 - Misc fixes and cleanups

* tag 'fuse-update-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  virtiofs: Fix spelling mistakes
  fuse: use DIV_ROUND_UP helper macro for calculations
  fuse: fix illegal access to inode with reused nodeid
  fuse: allow fallocate(FALLOC_FL_ZERO_RANGE)
  fuse: Make fuse_fill_super_submount() static
  fuse: Switch to fc_mount() for submounts
  fuse: Call vfs_get_tree() for submounts
  fuse: add dedicated filesystem context ops for submounts
  virtiofs: propagate sync() to file server
  fuse: reject internal errno
  fuse: check connected before queueing on fpq->io
  fuse: ignore PG_workingset after stealing
  fuse: Fix infinite loop in sget_fc()
  fuse: Fix crash if superblock of submount gets killed early
  fuse: Fix crash in fuse_dentry_automount() error path

fs/fuse/dax.c

@@ -213,7 +213,7 @@ static int fuse_setup_one_mapping(struct inode *inode, unsigned long start_idx,
 	dmap->writable = writable;
 	if (!upgrade) {
 		/*
-		 * We don't take a refernce on inode. inode is valid right now
+		 * We don't take a reference on inode. inode is valid right now
 		 * and when inode is going away, cleanup logic should first
 		 * cleanup dmap entries.
 		 */
@@ -622,7 +622,7 @@ static int fuse_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 	}
 
 	/*
-	 * If read beyond end of file happnes, fs code seems to return
+	 * If read beyond end of file happens, fs code seems to return
 	 * it as hole
 	 */
 iomap_hole:
@@ -1207,7 +1207,7 @@ static void fuse_dax_free_mem_worker(struct work_struct *work)
 			 ret);
 	}
 
-	/* If number of free ranges are still below threhold, requeue */
+	/* If number of free ranges are still below threshold, requeue */
 	kick_dmap_free_worker(fcd, 1);
 }
 

fs/fuse/dev.c

@@ -91,7 +91,7 @@ static void fuse_drop_waiting(struct fuse_conn *fc)
 {
 	/*
 	 * lockess check of fc->connected is okay, because atomic_dec_and_test()
-	 * provides a memory barrier mached with the one in fuse_wait_aborted()
+	 * provides a memory barrier matched with the one in fuse_wait_aborted()
 	 * to ensure no wake-up is missed.
 	 */
 	if (atomic_dec_and_test(&fc->num_waiting) &&
@@ -783,6 +783,7 @@ static int fuse_check_page(struct page *page)
 	       1 << PG_uptodate |
 	       1 << PG_lru |
 	       1 << PG_active |
+	       1 << PG_workingset |
 	       1 << PG_reclaim |
 	       1 << PG_waiters))) {
 		dump_page(page, "fuse: trying to steal weird page");
@@ -1271,6 +1272,15 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 		goto restart;
 	}
 	spin_lock(&fpq->lock);
+	/*
+	 *  Must not put request on fpq->io queue after having been shut down by
+	 *  fuse_abort_conn()
+	 */
+	if (!fpq->connected) {
+		req->out.h.error = err = -ECONNABORTED;
+		goto out_end;
+
+	}
 	list_add(&req->list, &fpq->io);
 	spin_unlock(&fpq->lock);
 	cs->req = req;
@@ -1857,7 +1867,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	}
 
 	err = -EINVAL;
-	if (oh.error <= -1000 || oh.error > 0)
+	if (oh.error <= -512 || oh.error > 0)
 		goto copy_finish;
 
 	spin_lock(&fpq->lock);

fs/fuse/dir.c

@@ -252,7 +252,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 		if (ret == -ENOMEM)
 			goto out;
 		if (ret || fuse_invalid_attr(&outarg.attr) ||
-		    inode_wrong_type(inode, outarg.attr.mode))
+		    fuse_stale_inode(inode, outarg.generation, &outarg.attr))
 			goto invalid;
 
 		forget_all_cached_acls(inode);
@@ -309,68 +309,23 @@ static int fuse_dentry_delete(const struct dentry *dentry)
 static struct vfsmount *fuse_dentry_automount(struct path *path)
 {
 	struct fs_context *fsc;
-	struct fuse_mount *parent_fm = get_fuse_mount_super(path->mnt->mnt_sb);
-	struct fuse_conn *fc = parent_fm->fc;
-	struct fuse_mount *fm;
 	struct vfsmount *mnt;
 	struct fuse_inode *mp_fi = get_fuse_inode(d_inode(path->dentry));
-	struct super_block *sb;
-	int err;
 
 	fsc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry);
-	if (IS_ERR(fsc)) {
-		err = PTR_ERR(fsc);
-		goto out;
-	}
+	if (IS_ERR(fsc))
+		return ERR_CAST(fsc);
 
-	err = -ENOMEM;
-	fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL);
-	if (!fm)
-		goto out_put_fsc;
-
-	fsc->s_fs_info = fm;
-	sb = sget_fc(fsc, NULL, set_anon_super_fc);
-	if (IS_ERR(sb)) {
-		err = PTR_ERR(sb);
-		kfree(fm);
-		goto out_put_fsc;
-	}
-	fm->fc = fuse_conn_get(fc);
-
-	/* Initialize superblock, making @mp_fi its root */
-	err = fuse_fill_super_submount(sb, mp_fi);
-	if (err)
-		goto out_put_sb;
-
-	sb->s_flags |= SB_ACTIVE;
-	fsc->root = dget(sb->s_root);
-	/* We are done configuring the superblock, so unlock it */
-	up_write(&sb->s_umount);
-
-	down_write(&fc->killsb);
-	list_add_tail(&fm->fc_entry, &fc->mounts);
-	up_write(&fc->killsb);
+	/* Pass the FUSE inode of the mount for fuse_get_tree_submount() */
+	fsc->fs_private = mp_fi;
 
 	/* Create the submount */
-	mnt = vfs_create_mount(fsc);
-	if (IS_ERR(mnt)) {
-		err = PTR_ERR(mnt);
-		goto out_put_fsc;
-	}
-	mntget(mnt);
+	mnt = fc_mount(fsc);
+	if (!IS_ERR(mnt))
+		mntget(mnt);
+
 	put_fs_context(fsc);
 	return mnt;
-
-out_put_sb:
-	/*
-	 * Only jump here when fsc->root is NULL and sb is still locked
-	 * (otherwise put_fs_context() will put the superblock)
-	 */
-	deactivate_locked_super(sb);
-out_put_fsc:
-	put_fs_context(fsc);
-out:
-	return ERR_PTR(err);
 }
 
 const struct dentry_operations fuse_dentry_operations = {

fs/fuse/file.c

@@ -645,7 +645,7 @@ static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
  * == bytes_transferred or rw == WRITE, the caller sets 'pos' to -1.
  *
  * An example:
- * User requested DIO read of 64K. It was splitted into two 32K fuse requests,
+ * User requested DIO read of 64K. It was split into two 32K fuse requests,
  * both submitted asynchronously. The first of them was ACKed by userspace as
  * fully completed (req->out.args[0].size == 32K) resulting in pos == -1. The
  * second request was ACKed as short, e.g. only 1K was read, resulting in
@@ -1403,7 +1403,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 		nbytes += ret;
 
 		ret += start;
-		npages = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
+		npages = DIV_ROUND_UP(ret, PAGE_SIZE);
 
 		ap->descs[ap->num_pages].offset = start;
 		fuse_page_descs_length_init(ap->descs, ap->num_pages, npages);
@@ -2905,11 +2905,13 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 	};
 	int err;
 	bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) ||
-			   (mode & FALLOC_FL_PUNCH_HOLE);
+			   (mode & (FALLOC_FL_PUNCH_HOLE |
+				    FALLOC_FL_ZERO_RANGE));
 
 	bool block_faults = FUSE_IS_DAX(inode) && lock_inode;
 
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
 	if (fm->fc->no_fallocate)
@@ -2924,7 +2926,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 				goto out;
 		}
 
-		if (mode & FALLOC_FL_PUNCH_HOLE) {
+		if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) {
 			loff_t endbyte = offset + length - 1;
 
 			err = fuse_writeback_range(inode, offset, endbyte);
@@ -2964,7 +2966,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 			file_update_time(file);
 	}
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
+	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
 		truncate_pagecache_range(inode, offset, offset + length - 1);
 
 	fuse_invalidate_attr(inode);

fs/fuse/fuse_i.h

@@ -761,6 +761,9 @@ struct fuse_conn {
 	/* Auto-mount submounts announced by the server */
 	unsigned int auto_submounts:1;
 
+	/* Propagate syncfs() to server */
+	unsigned int sync_fs:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
@@ -867,6 +870,13 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc)
 	return atomic64_read(&fc->attr_version);
 }
 
+static inline bool fuse_stale_inode(const struct inode *inode, int generation,
+				    struct fuse_attr *attr)
+{
+	return inode->i_generation != generation ||
+		inode_wrong_type(inode, attr->mode);
+}
+
 static inline void fuse_make_bad(struct inode *inode)
 {
 	remove_inode_hash(inode);
@@ -1081,15 +1091,6 @@ void fuse_send_init(struct fuse_mount *fm);
  */
 int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx);
 
-/*
- * Fill in superblock for submounts
- * @sb: partially-initialized superblock to fill in
- * @parent_fi: The fuse_inode of the parent filesystem where this submount is
- * 	       mounted
- */
-int fuse_fill_super_submount(struct super_block *sb,
-			     struct fuse_inode *parent_fi);
-
 /*
  * Remove the mount from the connection
  *
@@ -1097,6 +1098,11 @@ int fuse_fill_super_submount(struct super_block *sb,
  */
 bool fuse_mount_remove(struct fuse_mount *fm);
 
+/*
+ * Setup context ops for submounts
+ */
+int fuse_init_fs_context_submount(struct fs_context *fsc);
+
 /*
  * Shut down the connection (possibly sending DESTROY request).
  */

fs/fuse/inode.c

@@ -350,8 +350,8 @@ retry:
 		inode->i_generation = generation;
 		fuse_init_inode(inode, attr);
 		unlock_new_inode(inode);
-	} else if (inode_wrong_type(inode, attr->mode)) {
-		/* Inode has changed type, any I/O on the old should fail */
+	} else if (fuse_stale_inode(inode, generation, attr)) {
+		/* nodeid was reused, any I/O on the old inode should fail */
 		fuse_make_bad(inode);
 		iput(inode);
 		goto retry;
@@ -506,6 +506,45 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return err;
 }
 
+static int fuse_sync_fs(struct super_block *sb, int wait)
+{
+	struct fuse_mount *fm = get_fuse_mount_super(sb);
+	struct fuse_conn *fc = fm->fc;
+	struct fuse_syncfs_in inarg;
+	FUSE_ARGS(args);
+	int err;
+
+	/*
+	 * Userspace cannot handle the wait == 0 case.  Avoid a
+	 * gratuitous roundtrip.
+	 */
+	if (!wait)
+		return 0;
+
+	/* The filesystem is being unmounted.  Nothing to do. */
+	if (!sb->s_root)
+		return 0;
+
+	if (!fc->sync_fs)
+		return 0;
+
+	memset(&inarg, 0, sizeof(inarg));
+	args.in_numargs = 1;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	args.opcode = FUSE_SYNCFS;
+	args.nodeid = get_node_id(sb->s_root->d_inode);
+	args.out_numargs = 0;
+
+	err = fuse_simple_request(fm, &args);
+	if (err == -ENOSYS) {
+		fc->sync_fs = 0;
+		err = 0;
+	}
+
+	return err;
+}
+
 enum {
 	OPT_SOURCE,
 	OPT_SUBTYPE,
@@ -909,6 +948,7 @@ static const struct super_operations fuse_super_operations = {
 	.put_super	= fuse_put_super,
 	.umount_begin	= fuse_umount_begin,
 	.statfs		= fuse_statfs,
+	.sync_fs	= fuse_sync_fs,
 	.show_options	= fuse_show_options,
 };
 
@@ -1275,8 +1315,8 @@ static void fuse_sb_defaults(struct super_block *sb)
 		sb->s_xattr = fuse_no_acl_xattr_handlers;
 }
 
-int fuse_fill_super_submount(struct super_block *sb,
-			     struct fuse_inode *parent_fi)
+static int fuse_fill_super_submount(struct super_block *sb,
+				    struct fuse_inode *parent_fi)
 {
 	struct fuse_mount *fm = get_fuse_mount_super(sb);
 	struct super_block *parent_sb = parent_fi->inode.i_sb;
@@ -1313,6 +1353,58 @@ int fuse_fill_super_submount(struct super_block *sb,
 	return 0;
 }
 
+/* Filesystem context private data holds the FUSE inode of the mount point */
+static int fuse_get_tree_submount(struct fs_context *fsc)
+{
+	struct fuse_mount *fm;
+	struct fuse_inode *mp_fi = fsc->fs_private;
+	struct fuse_conn *fc = get_fuse_conn(&mp_fi->inode);
+	struct super_block *sb;
+	int err;
+
+	fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL);
+	if (!fm)
+		return -ENOMEM;
+
+	fsc->s_fs_info = fm;
+	sb = sget_fc(fsc, NULL, set_anon_super_fc);
+	if (IS_ERR(sb)) {
+		kfree(fm);
+		return PTR_ERR(sb);
+	}
+	fm->fc = fuse_conn_get(fc);
+
+	/* Initialize superblock, making @mp_fi its root */
+	err = fuse_fill_super_submount(sb, mp_fi);
+	if (err) {
+		fuse_conn_put(fc);
+		kfree(fm);
+		sb->s_fs_info = NULL;
+		deactivate_locked_super(sb);
+		return err;
+	}
+
+	down_write(&fc->killsb);
+	list_add_tail(&fm->fc_entry, &fc->mounts);
+	up_write(&fc->killsb);
+
+	sb->s_flags |= SB_ACTIVE;
+	fsc->root = dget(sb->s_root);
+
+	return 0;
+}
+
+static const struct fs_context_operations fuse_context_submount_ops = {
+	.get_tree	= fuse_get_tree_submount,
+};
+
+int fuse_init_fs_context_submount(struct fs_context *fsc)
+{
+	fsc->ops = &fuse_context_submount_ops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fuse_init_fs_context_submount);
+
 int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 {
 	struct fuse_dev *fud = NULL;

fs/fuse/readdir.c

@@ -200,9 +200,12 @@ retry:
 	if (!d_in_lookup(dentry)) {
 		struct fuse_inode *fi;
 		inode = d_inode(dentry);
+		if (inode && get_node_id(inode) != o->nodeid)
+			inode = NULL;
 		if (!inode ||
-		    get_node_id(inode) != o->nodeid ||
-		    inode_wrong_type(inode, o->attr.mode)) {
+		    fuse_stale_inode(inode, o->generation, &o->attr)) {
+			if (inode)
+				fuse_make_bad(inode);
 			d_invalidate(dentry);
 			dput(dentry);
 			goto retry;

fs/fuse/virtio_fs.c

@@ -1447,6 +1447,7 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 	fc->release = fuse_free_conn;
 	fc->delete_stale = true;
 	fc->auto_submounts = true;
+	fc->sync_fs = true;
 
 	/* Tell FUSE to split requests that exceed the virtqueue's size */
 	fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit,
@@ -1496,6 +1497,9 @@ static int virtio_fs_init_fs_context(struct fs_context *fsc)
 {
 	struct fuse_fs_context *ctx;
 
+	if (fsc->purpose == FS_CONTEXT_FOR_SUBMOUNT)
+		return fuse_init_fs_context_submount(fsc);
+
 	ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;

include/uapi/linux/fuse.h

@@ -181,6 +181,9 @@
  *  - add FUSE_OPEN_KILL_SUIDGID
  *  - extend fuse_setxattr_in, add FUSE_SETXATTR_EXT
  *  - add FUSE_SETXATTR_ACL_KILL_SGID
+ *
+ *  7.34
+ *  - add FUSE_SYNCFS
  */
 
 #ifndef _LINUX_FUSE_H
@@ -216,7 +219,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 33
+#define FUSE_KERNEL_MINOR_VERSION 34
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -509,6 +512,7 @@ enum fuse_opcode {
 	FUSE_COPY_FILE_RANGE	= 47,
 	FUSE_SETUPMAPPING	= 48,
 	FUSE_REMOVEMAPPING	= 49,
+	FUSE_SYNCFS		= 50,
 
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,
@@ -971,4 +975,8 @@ struct fuse_removemapping_one {
 #define FUSE_REMOVEMAPPING_MAX_ENTRY   \
 		(PAGE_SIZE / sizeof(struct fuse_removemapping_one))
 
+struct fuse_syncfs_in {
+	uint64_t	padding;
+};
+
 #endif /* _LINUX_FUSE_H */