Merge tag 'fuse-update-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:

 - Add passthrough mode for regular file I/O.

   This allows performing read and write (also via memory maps) on a
   backing file without incurring the overhead of roundtrips to
   userspace. For now this is only allowed to privileged servers, but
   this limitation will go away in the future (Amir Goldstein)

 - Fix interaction of direct I/O mode with memory maps (Bernd Schubert)

 - Export filesystem tags through sysfs for virtiofs (Stefan Hajnoczi)

 - Allow resending queued requests for server crash recovery (Zhao Chen)

 - Misc fixes and cleanups

* tag 'fuse-update-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (38 commits)
  fuse: get rid of ff->readdir.lock
  fuse: remove unneeded lock which protecting update of congestion_threshold
  fuse: Fix missing FOLL_PIN for direct-io
  fuse: remove an unnecessary if statement
  fuse: Track process write operations in both direct and writethrough modes
  fuse: Use the high bit of request ID for indicating resend requests
  fuse: Introduce a new notification type for resend pending requests
  fuse: add support for explicit export disabling
  fuse: __kuid_val/__kgid_val helpers in fuse_fill_attr_from_inode()
  fuse: fix typo for fuse_permission comment
  fuse: Convert fuse_writepage_locked to take a folio
  fuse: Remove fuse_writepage
  virtio_fs: remove duplicate check if queue is broken
  fuse: use FUSE_ROOT_ID in fuse_get_root_inode()
  fuse: don't unhash root
  fuse: fix root lookup with nonzero generation
  fuse: replace remaining make_bad_inode() with fuse_make_bad()
  virtiofs: drop __exit from virtio_fs_sysfs_exit()
  fuse: implement passthrough for mmap
  fuse: implement splice read/write passthrough
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-virtiofs

@@ -0,0 +1,11 @@
+What:		/sys/fs/virtiofs/<n>/tag
+Date:		Feb 2024
+Contact:	[email protected]
+Description:
+		[RO] The mount "tag" that can be used to mount this filesystem.
+
+What:		/sys/fs/virtiofs/<n>/device
+Date:		Feb 2024
+Contact:	[email protected]
+Description:
+		Symlink to the virtio device that exports this filesystem.

fs/fuse/Kconfig

@@ -52,3 +52,14 @@ config FUSE_DAX
 
 	  If you want to allow mounting a Virtio Filesystem with the "dax"
 	  option, answer Y.
+
+config FUSE_PASSTHROUGH
+	bool "FUSE passthrough operations support"
+	default y
+	depends on FUSE_FS
+	select FS_STACK
+	help
+	  This allows bypassing FUSE server by mapping specific FUSE operations
+	  to be performed directly on a backing file.
+
+	  If you want to allow passthrough operations, answer Y.

fs/fuse/Makefile

@@ -8,6 +8,8 @@ obj-$(CONFIG_CUSE) += cuse.o
 obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
 
 fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o
+fuse-y += iomode.o
 fuse-$(CONFIG_FUSE_DAX) += dax.o
+fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
 
 virtiofs-y := virtio_fs.o

fs/fuse/control.c

@@ -174,11 +174,7 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
 	if (!fc)
 		goto out;
 
-	down_read(&fc->killsb);
-	spin_lock(&fc->bg_lock);
-	fc->congestion_threshold = val;
-	spin_unlock(&fc->bg_lock);
-	up_read(&fc->killsb);
+	WRITE_ONCE(fc->congestion_threshold, val);
 	fuse_conn_put(fc);
 out:
 	return ret;

fs/fuse/dev.c

@@ -1775,6 +1775,61 @@ static int fuse_notify_retrieve(struct fuse_conn *fc, unsigned int size,
 	return err;
 }
 
+/*
+ * Resending all processing queue requests.
+ *
+ * During a FUSE daemon panics and failover, it is possible for some inflight
+ * requests to be lost and never returned. As a result, applications awaiting
+ * replies would become stuck forever. To address this, we can use notification
+ * to trigger resending of these pending requests to the FUSE daemon, ensuring
+ * they are properly processed again.
+ *
+ * Please note that this strategy is applicable only to idempotent requests or
+ * if the FUSE daemon takes careful measures to avoid processing duplicated
+ * non-idempotent requests.
+ */
+static void fuse_resend(struct fuse_conn *fc)
+{
+	struct fuse_dev *fud;
+	struct fuse_req *req, *next;
+	struct fuse_iqueue *fiq = &fc->iq;
+	LIST_HEAD(to_queue);
+	unsigned int i;
+
+	spin_lock(&fc->lock);
+	if (!fc->connected) {
+		spin_unlock(&fc->lock);
+		return;
+	}
+
+	list_for_each_entry(fud, &fc->devices, entry) {
+		struct fuse_pqueue *fpq = &fud->pq;
+
+		spin_lock(&fpq->lock);
+		for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+			list_splice_tail_init(&fpq->processing[i], &to_queue);
+		spin_unlock(&fpq->lock);
+	}
+	spin_unlock(&fc->lock);
+
+	list_for_each_entry_safe(req, next, &to_queue, list) {
+		__set_bit(FR_PENDING, &req->flags);
+		/* mark the request as resend request */
+		req->in.h.unique |= FUSE_UNIQUE_RESEND;
+	}
+
+	spin_lock(&fiq->lock);
+	/* iq and pq requests are both oldest to newest */
+	list_splice(&to_queue, &fiq->pending);
+	fiq->ops->wake_pending_and_unlock(fiq);
+}
+
+static int fuse_notify_resend(struct fuse_conn *fc)
+{
+	fuse_resend(fc);
+	return 0;
+}
+
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
@@ -1800,6 +1855,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 	case FUSE_NOTIFY_DELETE:
 		return fuse_notify_delete(fc, size, cs);
 
+	case FUSE_NOTIFY_RESEND:
+		return fuse_notify_resend(fc);
+
 	default:
 		fuse_copy_finish(cs);
 		return -EINVAL;
@@ -2251,43 +2309,91 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
 	return 0;
 }
 
-static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
-			   unsigned long arg)
+static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
 {
 	int res;
 	int oldfd;
 	struct fuse_dev *fud = NULL;
 	struct fd f;
 
+	if (get_user(oldfd, argp))
+		return -EFAULT;
+
+	f = fdget(oldfd);
+	if (!f.file)
+		return -EINVAL;
+
+	/*
+	 * Check against file->f_op because CUSE
+	 * uses the same ioctl handler.
+	 */
+	if (f.file->f_op == file->f_op)
+		fud = fuse_get_dev(f.file);
+
+	res = -EINVAL;
+	if (fud) {
+		mutex_lock(&fuse_mutex);
+		res = fuse_device_clone(fud->fc, file);
+		mutex_unlock(&fuse_mutex);
+	}
+
+	fdput(f);
+	return res;
+}
+
+static long fuse_dev_ioctl_backing_open(struct file *file,
+					struct fuse_backing_map __user *argp)
+{
+	struct fuse_dev *fud = fuse_get_dev(file);
+	struct fuse_backing_map map;
+
+	if (!fud)
+		return -EPERM;
+
+	if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&map, argp, sizeof(map)))
+		return -EFAULT;
+
+	return fuse_backing_open(fud->fc, &map);
+}
+
+static long fuse_dev_ioctl_backing_close(struct file *file, __u32 __user *argp)
+{
+	struct fuse_dev *fud = fuse_get_dev(file);
+	int backing_id;
+
+	if (!fud)
+		return -EPERM;
+
+	if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		return -EOPNOTSUPP;
+
+	if (get_user(backing_id, argp))
+		return -EFAULT;
+
+	return fuse_backing_close(fud->fc, backing_id);
+}
+
+static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
+			   unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+
 	switch (cmd) {
 	case FUSE_DEV_IOC_CLONE:
-		if (get_user(oldfd, (__u32 __user *)arg))
-			return -EFAULT;
+		return fuse_dev_ioctl_clone(file, argp);
 
-		f = fdget(oldfd);
-		if (!f.file)
-			return -EINVAL;
+	case FUSE_DEV_IOC_BACKING_OPEN:
+		return fuse_dev_ioctl_backing_open(file, argp);
+
+	case FUSE_DEV_IOC_BACKING_CLOSE:
+		return fuse_dev_ioctl_backing_close(file, argp);
 
-		/*
-		 * Check against file->f_op because CUSE
-		 * uses the same ioctl handler.
-		 */
-		if (f.file->f_op == file->f_op)
-			fud = fuse_get_dev(f.file);
-
-		res = -EINVAL;
-		if (fud) {
-			mutex_lock(&fuse_mutex);
-			res = fuse_device_clone(fud->fc, file);
-			mutex_unlock(&fuse_mutex);
-		}
-		fdput(f);
-		break;
 	default:
-		res = -ENOTTY;
-		break;
+		return -ENOTTY;
 	}
-	return res;
 }
 
 const struct file_operations fuse_dev_operations = {

fs/fuse/dir.c

@@ -391,6 +391,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
 	err = -EIO;
 	if (fuse_invalid_attr(&outarg->attr))
 		goto out_put_forget;
+	if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) {
+		pr_warn_once("root generation should be zero\n");
+		outarg->generation = 0;
+	}
 
 	*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
 			   &outarg->attr, ATTR_TIMEOUT(outarg),
@@ -615,7 +619,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	FUSE_ARGS(args);
 	struct fuse_forget_link *forget;
 	struct fuse_create_in inarg;
-	struct fuse_open_out outopen;
+	struct fuse_open_out *outopenp;
 	struct fuse_entry_out outentry;
 	struct fuse_inode *fi;
 	struct fuse_file *ff;
@@ -630,7 +634,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 		goto out_err;
 
 	err = -ENOMEM;
-	ff = fuse_file_alloc(fm);
+	ff = fuse_file_alloc(fm, true);
 	if (!ff)
 		goto out_put_forget_req;
 
@@ -659,8 +663,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	args.out_numargs = 2;
 	args.out_args[0].size = sizeof(outentry);
 	args.out_args[0].value = &outentry;
-	args.out_args[1].size = sizeof(outopen);
-	args.out_args[1].value = &outopen;
+	/* Store outarg for fuse_finish_open() */
+	outopenp = &ff->args->open_outarg;
+	args.out_args[1].size = sizeof(*outopenp);
+	args.out_args[1].value = outopenp;
 
 	err = get_create_ext(&args, dir, entry, mode);
 	if (err)
@@ -676,9 +682,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	    fuse_invalid_attr(&outentry.attr))
 		goto out_free_ff;
 
-	ff->fh = outopen.fh;
+	ff->fh = outopenp->fh;
 	ff->nodeid = outentry.nodeid;
-	ff->open_flags = outopen.open_flags;
+	ff->open_flags = outopenp->open_flags;
 	inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
 			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0);
 	if (!inode) {
@@ -692,13 +698,15 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_dir_changed(dir);
-	err = finish_open(file, entry, generic_file_open);
+	err = generic_file_open(inode, file);
+	if (!err) {
+		file->private_data = ff;
+		err = finish_open(file, entry, fuse_finish_open);
+	}
 	if (err) {
 		fi = get_fuse_inode(inode);
 		fuse_sync_release(fi, ff, flags);
 	} else {
-		file->private_data = ff;
-		fuse_finish_open(inode, file);
 		if (fm->fc->atomic_o_trunc && trunc)
 			truncate_pagecache(inode, 0);
 		else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
@@ -1210,7 +1218,7 @@ static int fuse_do_statx(struct inode *inode, struct file *file,
 	if (((sx->mask & STATX_SIZE) && !fuse_valid_size(sx->size)) ||
 	    ((sx->mask & STATX_TYPE) && (!fuse_valid_type(sx->mode) ||
 					 inode_wrong_type(inode, sx->mode)))) {
-		make_bad_inode(inode);
+		fuse_make_bad(inode);
 		return -EIO;
 	}
 
@@ -1485,7 +1493,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask)
  *
  * 1) Local access checking ('default_permissions' mount option) based
  * on file mode.  This is the plain old disk filesystem permission
- * modell.
+ * model.
  *
  * 2) "Remote" access checking, where server is responsible for
  * checking permission in each inode operation.  An exception to this
@@ -1630,7 +1638,30 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 
 static int fuse_dir_open(struct inode *inode, struct file *file)
 {
-	return fuse_open_common(inode, file, true);
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	int err;
+
+	if (fuse_is_bad(inode))
+		return -EIO;
+
+	err = generic_file_open(inode, file);
+	if (err)
+		return err;
+
+	err = fuse_do_open(fm, get_node_id(inode), file, true);
+	if (!err) {
+		struct fuse_file *ff = file->private_data;
+
+		/*
+		 * Keep handling FOPEN_STREAM and FOPEN_NONSEEKABLE for
+		 * directories for backward compatibility, though it's unlikely
+		 * to be useful.
+		 */
+		if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE))
+			nonseekable_open(inode, file);
+	}
+
+	return err;
 }
 
 static int fuse_dir_release(struct inode *inode, struct file *file)