Merge tag 'fuse-update-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Fix a page locking bug in write (introduced in 2.6.26)

 - Allow sgid bit to be killed in setacl()

 - Miscellaneous fixes and cleanups

* tag 'fuse-update-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  cuse: simplify refcount
  cuse: prevent clone
  virtiofs: fix userns
  virtiofs: remove useless function
  virtiofs: split requests that exceed virtqueue size
  virtiofs: fix memory leak in virtio_fs_probe()
  fuse: invalidate attrs when page writeback completes
  fuse: add a flag FUSE_SETXATTR_ACL_KILL_SGID to kill SGID
  fuse: extend FUSE_SETXATTR request
  fuse: fix matching of FUSE_DEV_IOC_CLONE command
  fuse: fix a typo
  fuse: don't zero pages twice
  fuse: fix typo for fuse_conn.max_pages comment
  fuse: fix write deadlock

fs/fuse/acl.c

@@ -71,6 +71,7 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		return -EINVAL;
 
 	if (acl) {
+		unsigned int extra_flags = 0;
 		/*
 		 * Fuse userspace is responsible for updating access
 		 * permissions in the inode, if needed. fuse_setxattr
@@ -94,7 +95,11 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 			return ret;
 		}
 
-		ret = fuse_setxattr(inode, name, value, size, 0);
+		if (!in_group_p(i_gid_into_mnt(&init_user_ns, inode)) &&
+		    !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
+			extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
+
+		ret = fuse_setxattr(inode, name, value, size, 0, extra_flags);
 		kfree(value);
 	} else {
 		ret = fuse_removexattr(inode, name);

fs/fuse/cuse.c

@@ -511,20 +511,18 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	fuse_conn_init(&cc->fc, &cc->fm, file->f_cred->user_ns,
 		       &fuse_dev_fiq_ops, NULL);
 
+	cc->fc.release = cuse_fc_release;
 	fud = fuse_dev_alloc_install(&cc->fc);
-	if (!fud) {
-		kfree(cc);
+	fuse_conn_put(&cc->fc);
+	if (!fud)
 		return -ENOMEM;
-	}
 
 	INIT_LIST_HEAD(&cc->list);
-	cc->fc.release = cuse_fc_release;
 
 	cc->fc.initialized = 1;
 	rc = cuse_send_init(cc);
 	if (rc) {
 		fuse_dev_free(fud);
-		fuse_conn_put(&cc->fc);
 		return rc;
 	}
 	file->private_data = fud;
@@ -561,8 +559,6 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
 		unregister_chrdev_region(cc->cdev->dev, 1);
 		cdev_del(cc->cdev);
 	}
-	/* Base reference is now owned by "fud" */
-	fuse_conn_put(&cc->fc);
 
 	rc = fuse_dev_release(inode, file);	/* puts the base reference */
 
@@ -627,6 +623,8 @@ static int __init cuse_init(void)
 	cuse_channel_fops.owner		= THIS_MODULE;
 	cuse_channel_fops.open		= cuse_channel_open;
 	cuse_channel_fops.release	= cuse_channel_release;
+	/* CUSE is not prepared for FUSE_DEV_IOC_CLONE */
+	cuse_channel_fops.unlocked_ioctl	= NULL;
 
 	cuse_class = class_create(THIS_MODULE, "cuse");
 	if (IS_ERR(cuse_class))

fs/fuse/dev.c

@@ -2233,11 +2233,8 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
 	int oldfd;
 	struct fuse_dev *fud = NULL;
 
-	if (_IOC_TYPE(cmd) != FUSE_DEV_IOC_MAGIC)
-		return -ENOTTY;
-
-	switch (_IOC_NR(cmd)) {
-	case _IOC_NR(FUSE_DEV_IOC_CLONE):
+	switch (cmd) {
+	case FUSE_DEV_IOC_CLONE:
 		res = -EFAULT;
 		if (!get_user(oldfd, (__u32 __user *)arg)) {
 			struct file *old = fget(oldfd);

fs/fuse/file.c

@@ -802,21 +802,12 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 
-	if (fc->writeback_cache) {
-		/*
-		 * A hole in a file. Some data after the hole are in page cache,
-		 * but have not reached the client fs yet. So, the hole is not
-		 * present there.
-		 */
-		int i;
-		int start_idx = num_read >> PAGE_SHIFT;
-		size_t off = num_read & (PAGE_SIZE - 1);
-
-		for (i = start_idx; i < ap->num_pages; i++) {
-			zero_user_segment(ap->pages[i], off, PAGE_SIZE);
-			off = 0;
-		}
-	} else {
+	/*
+	 * If writeback_cache is enabled, a short read means there's a hole in
+	 * the file.  Some data after the hole is in page cache, but has not
+	 * reached the client fs yet.  So the hole is not present there.
+	 */
+	if (!fc->writeback_cache) {
 		loff_t pos = page_offset(ap->pages[0]) + num_read;
 		fuse_read_update_size(inode, pos, attr_ver);
 	}
@@ -1103,6 +1094,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 	struct fuse_file *ff = file->private_data;
 	struct fuse_mount *fm = ff->fm;
 	unsigned int offset, i;
+	bool short_write;
 	int err;
 
 	for (i = 0; i < ap->num_pages; i++)
@@ -1117,32 +1109,38 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 	if (!err && ia->write.out.size > count)
 		err = -EIO;
 
+	short_write = ia->write.out.size < count;
 	offset = ap->descs[0].offset;
 	count = ia->write.out.size;
 	for (i = 0; i < ap->num_pages; i++) {
 		struct page *page = ap->pages[i];
 
-		if (!err && !offset && count >= PAGE_SIZE)
-			SetPageUptodate(page);
-
-		if (count > PAGE_SIZE - offset)
-			count -= PAGE_SIZE - offset;
-		else
-			count = 0;
-		offset = 0;
-
-		unlock_page(page);
+		if (err) {
+			ClearPageUptodate(page);
+		} else {
+			if (count >= PAGE_SIZE - offset)
+				count -= PAGE_SIZE - offset;
+			else {
+				if (short_write)
+					ClearPageUptodate(page);
+				count = 0;
+			}
+			offset = 0;
+		}
+		if (ia->write.page_locked && (i == ap->num_pages - 1))
+			unlock_page(page);
 		put_page(page);
 	}
 
 	return err;
 }
 
-static ssize_t fuse_fill_write_pages(struct fuse_args_pages *ap,
+static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 				     struct address_space *mapping,
 				     struct iov_iter *ii, loff_t pos,
 				     unsigned int max_pages)
 {
+	struct fuse_args_pages *ap = &ia->ap;
 	struct fuse_conn *fc = get_fuse_conn(mapping->host);
 	unsigned offset = pos & (PAGE_SIZE - 1);
 	size_t count = 0;
@@ -1195,6 +1193,16 @@ static ssize_t fuse_fill_write_pages(struct fuse_args_pages *ap,
 		if (offset == PAGE_SIZE)
 			offset = 0;
 
+		/* If we copied full page, mark it uptodate */
+		if (tmp == PAGE_SIZE)
+			SetPageUptodate(page);
+
+		if (PageUptodate(page)) {
+			unlock_page(page);
+		} else {
+			ia->write.page_locked = true;
+			break;
+		}
 		if (!fc->big_writes)
 			break;
 	} while (iov_iter_count(ii) && count < fc->max_write &&
@@ -1238,7 +1246,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb,
 			break;
 		}
 
-		count = fuse_fill_write_pages(ap, mapping, ii, pos, nr_pages);
+		count = fuse_fill_write_pages(&ia, mapping, ii, pos, nr_pages);
 		if (count <= 0) {
 			err = count;
 		} else {
@@ -1753,8 +1761,17 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
 		container_of(args, typeof(*wpa), ia.ap.args);
 	struct inode *inode = wpa->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
 
 	mapping_set_error(inode->i_mapping, error);
+	/*
+	 * A writeback finished and this might have updated mtime/ctime on
+	 * server making local mtime/ctime stale.  Hence invalidate attrs.
+	 * Do this only if writeback_cache is not enabled.  If writeback_cache
+	 * is enabled, we trust local ctime/mtime.
+	 */
+	if (!fc->writeback_cache)
+		fuse_invalidate_attr(inode);
 	spin_lock(&fi->lock);
 	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	while (wpa->next) {

fs/fuse/fuse_i.h

@@ -552,9 +552,12 @@ struct fuse_conn {
 	/** Maximum write size */
 	unsigned max_write;
 
-	/** Maxmum number of pages that can be used in a single request */
+	/** Maximum number of pages that can be used in a single request */
 	unsigned int max_pages;
 
+	/** Constrain ->max_pages to this value during feature negotiation */
+	unsigned int max_pages_limit;
+
 	/** Input queue */
 	struct fuse_iqueue iq;
 
@@ -668,6 +671,9 @@ struct fuse_conn {
 	/** Is setxattr not implemented by fs? */
 	unsigned no_setxattr:1;
 
+	/** Does file server support extended setxattr */
+	unsigned setxattr_ext:1;
+
 	/** Is getxattr not implemented by fs? */
 	unsigned no_getxattr:1;
 
@@ -713,7 +719,7 @@ struct fuse_conn {
 	/** Use enhanced/automatic page cache invalidation. */
 	unsigned auto_inval_data:1;
 
-	/** Filesystem is fully reponsible for page cache invalidation. */
+	/** Filesystem is fully responsible for page cache invalidation. */
 	unsigned explicit_inval_data:1;
 
 	/** Does the filesystem support readdirplus? */
@@ -934,6 +940,7 @@ struct fuse_io_args {
 		struct {
 			struct fuse_write_in in;
 			struct fuse_write_out out;
+			bool page_locked;
 		} write;
 	};
 	struct fuse_args_pages ap;
@@ -1193,7 +1200,7 @@ void fuse_unlock_inode(struct inode *inode, bool locked);
 bool fuse_lock_inode(struct inode *inode);
 
 int fuse_setxattr(struct inode *inode, const char *name, const void *value,
-		  size_t size, int flags);
+		  size_t size, int flags, unsigned int extra_flags);
 ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
 		      size_t size);
 ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);

fs/fuse/inode.c

@@ -712,6 +712,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 	fc->user_ns = get_user_ns(user_ns);
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
+	fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
 
 	INIT_LIST_HEAD(&fc->mounts);
 	list_add(&fm->fc_entry, &fc->mounts);
@@ -1040,7 +1041,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->abort_err = 1;
 			if (arg->flags & FUSE_MAX_PAGES) {
 				fc->max_pages =
-					min_t(unsigned int, FUSE_MAX_MAX_PAGES,
+					min_t(unsigned int, fc->max_pages_limit,
 					max_t(unsigned int, arg->max_pages, 1));
 			}
 			if (IS_ENABLED(CONFIG_FUSE_DAX) &&
@@ -1052,6 +1053,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->handle_killpriv_v2 = 1;
 				fm->sb->s_flags |= SB_NOSEC;
 			}
+			if (arg->flags & FUSE_SETXATTR_EXT)
+				fc->setxattr_ext = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1095,7 +1098,7 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
 		FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
-		FUSE_HANDLE_KILLPRIV_V2;
+		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		ia->in.flags |= FUSE_MAP_ALIGNMENT;

fs/fuse/virtio_fs.c

@@ -18,6 +18,12 @@
 #include <linux/uio.h>
 #include "fuse_i.h"
 
+/* Used to help calculate the FUSE connection's max_pages limit for a request's
+ * size. Parts of the struct fuse_req are sliced into scattergather lists in
+ * addition to the pages used, so this can help account for that overhead.
+ */
+#define FUSE_HEADER_OVERHEAD    4
+
 /* List of virtio-fs device instances and a lock for the list. Also provides
  * mutual exclusion in device removal and mounting path
  */
@@ -127,11 +133,6 @@ static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
 	return &fs->vqs[vq->index];
 }
 
-static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
-{
-	return &vq_to_fsvq(vq)->fud->pq;
-}
-
 /* Should be called with fsvq->lock held. */
 static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
 {
@@ -896,6 +897,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 out_vqs:
 	vdev->config->reset(vdev);
 	virtio_fs_cleanup_vqs(vdev, fs);
+	kfree(fs->vqs);
 
 out:
 	vdev->priv = NULL;
@@ -1413,9 +1415,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 {
 	struct virtio_fs *fs;
 	struct super_block *sb;
-	struct fuse_conn *fc;
+	struct fuse_conn *fc = NULL;
 	struct fuse_mount *fm;
-	int err;
+	unsigned int virtqueue_size;
+	int err = -EIO;
 
 	/* This gets a reference on virtio_fs object. This ptr gets installed
 	 * in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
@@ -1427,6 +1430,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 		return -EINVAL;
 	}
 
+	virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq);
+	if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD))
+		goto out_err;
+
 	err = -ENOMEM;
 	fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL);
 	if (!fc)
@@ -1436,12 +1443,15 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 	if (!fm)
 		goto out_err;
 
-	fuse_conn_init(fc, fm, get_user_ns(current_user_ns()),
-		       &virtio_fs_fiq_ops, fs);
+	fuse_conn_init(fc, fm, fsc->user_ns, &virtio_fs_fiq_ops, fs);
 	fc->release = fuse_free_conn;
 	fc->delete_stale = true;
 	fc->auto_submounts = true;
 
+	/* Tell FUSE to split requests that exceed the virtqueue's size */
+	fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit,
+				    virtqueue_size - FUSE_HEADER_OVERHEAD);
+
 	fsc->s_fs_info = fm;
 	sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc);
 	if (fsc->s_fs_info) {

fs/fuse/xattr.c

@@ -12,7 +12,7 @@
 #include <linux/posix_acl_xattr.h>
 
 int fuse_setxattr(struct inode *inode, const char *name, const void *value,
-		  size_t size, int flags)
+		  size_t size, int flags, unsigned int extra_flags)
 {
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	FUSE_ARGS(args);
@@ -25,10 +25,13 @@ int fuse_setxattr(struct inode *inode, const char *name, const void *value,
 	memset(&inarg, 0, sizeof(inarg));
 	inarg.size = size;
 	inarg.flags = flags;
+	inarg.setxattr_flags = extra_flags;
+
 	args.opcode = FUSE_SETXATTR;
 	args.nodeid = get_node_id(inode);
 	args.in_numargs = 3;
-	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].size = fm->fc->setxattr_ext ?
+		sizeof(inarg) : FUSE_COMPAT_SETXATTR_IN_SIZE;
 	args.in_args[0].value = &inarg;
 	args.in_args[1].size = strlen(name) + 1;
 	args.in_args[1].value = name;
@@ -199,7 +202,7 @@ static int fuse_xattr_set(const struct xattr_handler *handler,
 	if (!value)
 		return fuse_removexattr(inode, name);
 
-	return fuse_setxattr(inode, name, value, size, flags);
+	return fuse_setxattr(inode, name, value, size, flags, 0);
 }
 
 static bool no_xattr_list(struct dentry *dentry)

include/uapi/linux/fuse.h

@@ -179,6 +179,8 @@
  *  7.33
  *  - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID, FATTR_KILL_SUIDGID
  *  - add FUSE_OPEN_KILL_SUIDGID
+ *  - extend fuse_setxattr_in, add FUSE_SETXATTR_EXT
+ *  - add FUSE_SETXATTR_ACL_KILL_SGID
  */
 
 #ifndef _LINUX_FUSE_H
@@ -330,6 +332,7 @@ struct fuse_file_lock {
  *			does not have CAP_FSETID. Additionally upon
  *			write/truncate sgid is killed only if file has group
  *			execute permission. (Same as Linux VFS behavior).
+ * FUSE_SETXATTR_EXT:	Server supports extended struct fuse_setxattr_in
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -360,6 +363,7 @@ struct fuse_file_lock {
 #define FUSE_MAP_ALIGNMENT	(1 << 26)
 #define FUSE_SUBMOUNTS		(1 << 27)
 #define FUSE_HANDLE_KILLPRIV_V2	(1 << 28)
+#define FUSE_SETXATTR_EXT	(1 << 29)
 
 /**
  * CUSE INIT request/reply flags
@@ -451,6 +455,12 @@ struct fuse_file_lock {
  */
 #define FUSE_OPEN_KILL_SUIDGID	(1 << 0)
 
+/**
+ * setxattr flags
+ * FUSE_SETXATTR_ACL_KILL_SGID: Clear SGID when system.posix_acl_access is set
+ */
+#define FUSE_SETXATTR_ACL_KILL_SGID	(1 << 0)
+
 enum fuse_opcode {
 	FUSE_LOOKUP		= 1,
 	FUSE_FORGET		= 2,  /* no reply */
@@ -681,9 +691,13 @@ struct fuse_fsync_in {
 	uint32_t	padding;
 };
 
+#define FUSE_COMPAT_SETXATTR_IN_SIZE 8
+
 struct fuse_setxattr_in {
 	uint32_t	size;
 	uint32_t	flags;
+	uint32_t	setxattr_flags;
+	uint32_t	padding;
 };
 
 struct fuse_getxattr_in {