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
  ...

Documentation/ABI/testing/sysfs-fs-virtiofs

+What:		/sys/fs/virtiofs/<n>/tag
+Date:		Feb 2024
+Contact:	virtio-fs@lists.linux.dev
+Description:
+		[RO] The mount "tag" that can be used to mount this filesystem.
+
+What:		/sys/fs/virtiofs/<n>/device
+Date:		Feb 2024
+Contact:	virtio-fs@lists.linux.dev
+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)

fs/fuse/fuse_i.h

@@ -76,6 +76,16 @@ struct fuse_submount_lookup {
 	struct fuse_forget_link *forget;
 };
 
+/** Container for data related to mapping to backing file */
+struct fuse_backing {
+	struct file *file;
+	struct cred *cred;
+
+	/** refcount */
+	refcount_t count;
+	struct rcu_head rcu;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */
@@ -111,7 +121,7 @@ struct fuse_inode {
 	u64 attr_version;
 
 	union {
-		/* Write related fields (regular file only) */
+		/* read/write io cache (regular file only) */
 		struct {
 			/* Files usable in writepage.  Protected by fi->lock */
 			struct list_head write_files;
@@ -123,9 +133,15 @@ struct fuse_inode {
 			 * (FUSE_NOWRITE) means more writes are blocked */
 			int writectr;
 
+			/** Number of files/maps using page cache */
+			int iocachectr;
+
 			/* Waitq for writepage completion */
 			wait_queue_head_t page_waitq;
 
+			/* waitq for direct-io completion */
+			wait_queue_head_t direct_io_waitq;
+
 			/* List of writepage requestst (pending or sent) */
 			struct rb_root writepages;
 		};
@@ -173,6 +189,10 @@ struct fuse_inode {
 #endif
 	/** Submount specific lookup tracking */
 	struct fuse_submount_lookup *submount_lookup;
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	/** Reference to backing file in passthrough mode */
+	struct fuse_backing *fb;
+#endif
 };
 
 /** FUSE inode state bits */
@@ -187,19 +207,21 @@ enum {
 	FUSE_I_BAD,
 	/* Has btime */
 	FUSE_I_BTIME,
+	/* Wants or already has page cache IO */
+	FUSE_I_CACHE_IO_MODE,
 };
 
 struct fuse_conn;
 struct fuse_mount;
-struct fuse_release_args;
+union fuse_file_args;
 
 /** FUSE specific file data */
 struct fuse_file {
 	/** Fuse connection for this file */
 	struct fuse_mount *fm;
 
-	/* Argument space reserved for release */
-	struct fuse_release_args *release_args;
+	/* Argument space reserved for open/release */
+	union fuse_file_args *args;
 
 	/** Kernel file handle guaranteed to be unique */
 	u64 kh;
@@ -221,12 +243,6 @@ struct fuse_file {
 
 	/* Readdir related */
 	struct {
-		/*
-		 * Protects below fields against (crazy) parallel readdir on
-		 * same open file.  Uncontended in the normal case.
-		 */
-		struct mutex lock;
-
 		/* Dir stream position */
 		loff_t pos;
 
@@ -244,6 +260,15 @@ struct fuse_file {
 	/** Wait queue head for poll */
 	wait_queue_head_t poll_wait;
 
+	/** Does file hold a fi->iocachectr refcount? */
+	enum { IOM_NONE, IOM_CACHED, IOM_UNCACHED } iomode;
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	/** Reference to backing file in passthrough mode */
+	struct file *passthrough;
+	const struct cred *cred;
+#endif
+
 	/** Has flock been performed on this file? */
 	bool flock:1;
 };
@@ -283,6 +308,7 @@ struct fuse_args {
 	bool page_replace:1;
 	bool may_block:1;
 	bool is_ext:1;
+	bool is_pinned:1;
 	struct fuse_in_arg in_args[3];
 	struct fuse_arg out_args[2];
 	void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
@@ -295,6 +321,19 @@ struct fuse_args_pages {
 	unsigned int num_pages;
 };
 
+struct fuse_release_args {
+	struct fuse_args args;
+	struct fuse_release_in inarg;
+	struct inode *inode;
+};
+
+union fuse_file_args {
+	/* Used during open() */
+	struct fuse_open_out open_outarg;
+	/* Used during release() */
+	struct fuse_release_args release_args;
+};
+
 #define FUSE_ARGS(args) struct fuse_args args = {}
 
 /** The request IO state (for asynchronous processing) */
@@ -818,6 +857,12 @@ struct fuse_conn {
 	/* Is statx not implemented by fs? */
 	unsigned int no_statx:1;
 
+	/** Passthrough support for read/write IO */
+	unsigned int passthrough:1;
+
+	/** Maximum stack depth for passthrough backing files */
+	int max_stack_depth;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
@@ -867,6 +912,11 @@ struct fuse_conn {
 
 	/* New writepages go into this bucket */
 	struct fuse_sync_bucket __rcu *curr_bucket;
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	/** IDR for backing files ids */
+	struct idr backing_files_map;
+#endif
 };
 
 /*
@@ -940,7 +990,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation,
 
 static inline void fuse_make_bad(struct inode *inode)
 {
-	remove_inode_hash(inode);
 	set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state);
 }
 
@@ -1032,14 +1081,9 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
 			 size_t count, int opcode);
 
 
-/**
- * Send OPEN or OPENDIR request
- */
-int fuse_open_common(struct inode *inode, struct file *file, bool isdir);
-
-struct fuse_file *fuse_file_alloc(struct fuse_mount *fm);
+struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release);
 void fuse_file_free(struct fuse_file *ff);
-void fuse_finish_open(struct inode *inode, struct file *file);
+int fuse_finish_open(struct inode *inode, struct file *file);
 
 void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
 		       unsigned int flags);
@@ -1349,11 +1393,82 @@ int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa);
 int fuse_fileattr_set(struct mnt_idmap *idmap,
 		      struct dentry *dentry, struct fileattr *fa);
 
-/* file.c */
+/* iomode.c */
+int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff);
+int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb);
+void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff);
+
+int fuse_file_io_open(struct file *file, struct inode *inode);
+void fuse_file_io_release(struct fuse_file *ff, struct inode *inode);
 
+/* file.c */
 struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
 				 unsigned int open_flags, bool isdir);
 void fuse_file_release(struct inode *inode, struct fuse_file *ff,
 		       unsigned int open_flags, fl_owner_t id, bool isdir);
 
+/* passthrough.c */
+static inline struct fuse_backing *fuse_inode_backing(struct fuse_inode *fi)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	return READ_ONCE(fi->fb);
+#else
+	return NULL;
+#endif
+}
+
+static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi,
+							  struct fuse_backing *fb)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	return xchg(&fi->fb, fb);
+#else
+	return NULL;
+#endif
+}
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+struct fuse_backing *fuse_backing_get(struct fuse_backing *fb);
+void fuse_backing_put(struct fuse_backing *fb);
+#else
+
+static inline struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
+{
+	return NULL;
+}
+
+static inline void fuse_backing_put(struct fuse_backing *fb)
+{
+}
+#endif
+
+void fuse_backing_files_init(struct fuse_conn *fc);
+void fuse_backing_files_free(struct fuse_conn *fc);
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map);
+int fuse_backing_close(struct fuse_conn *fc, int backing_id);
+
+struct fuse_backing *fuse_passthrough_open(struct file *file,
+					   struct inode *inode,
+					   int backing_id);
+void fuse_passthrough_release(struct fuse_file *ff, struct fuse_backing *fb);
+
+static inline struct file *fuse_file_passthrough(struct fuse_file *ff)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+	return ff->passthrough;
+#else
+	return NULL;
+#endif
+}
+
+ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t fuse_passthrough_write_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
+				     struct pipe_inode_info *pipe,
+				     size_t len, unsigned int flags);
+ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
+				      struct file *out, loff_t *ppos,
+				      size_t len, unsigned int flags);
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma);
+
 #endif /* _FS_FUSE_I_H */

fs/fuse/inode.c

@@ -111,6 +111,9 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi))
 		goto out_free_forget;
 
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_inode_backing_set(fi, NULL);
+
 	return &fi->inode;
 
 out_free_forget:
@@ -129,6 +132,9 @@ static void fuse_free_inode(struct inode *inode)
 #ifdef CONFIG_FUSE_DAX
 	kfree(fi->dax);
 #endif
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_put(fuse_inode_backing(fi));
+
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
@@ -469,8 +475,11 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	} 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;
+		if (inode != d_inode(sb->s_root)) {
+			remove_inode_hash(inode);
+			iput(inode);
+			goto retry;
+		}
 	}
 	fi = get_fuse_inode(inode);
 	spin_lock(&fi->lock);
@@ -924,6 +933,9 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
 	fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
 
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		fuse_backing_files_init(fc);
+
 	INIT_LIST_HEAD(&fc->mounts);
 	list_add(&fm->fc_entry, &fc->mounts);
 	fm->fc = fc;
@@ -954,6 +966,8 @@ void fuse_conn_put(struct fuse_conn *fc)
 			WARN_ON(atomic_read(&bucket->count) != 1);
 			kfree(bucket);
 		}
+		if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+			fuse_backing_files_free(fc);
 		call_rcu(&fc->rcu, delayed_release);
 	}
 }
@@ -974,7 +988,7 @@ static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
 	attr.mode = mode;
 	attr.ino = FUSE_ROOT_ID;
 	attr.nlink = 1;
-	return fuse_iget(sb, 1, 0, &attr, 0, 0);
+	return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0);
 }
 
 struct fuse_inode_handle {
@@ -1117,6 +1131,11 @@ static struct dentry *fuse_get_parent(struct dentry *child)
 	return parent;
 }
 
+/* only for fid encoding; no support for file handle */
+static const struct export_operations fuse_export_fid_operations = {
+	.encode_fh	= fuse_encode_fh,
+};
+
 static const struct export_operations fuse_export_operations = {
 	.fh_to_dentry	= fuse_fh_to_dentry,
 	.fh_to_parent	= fuse_fh_to_parent,
@@ -1291,6 +1310,26 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->create_supp_group = 1;
 			if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
 				fc->direct_io_allow_mmap = 1;
+			/*
+			 * max_stack_depth is the max stack depth of FUSE fs,
+			 * so it has to be at least 1 to support passthrough
+			 * to backing files.
+			 *
+			 * with max_stack_depth > 1, the backing files can be
+			 * on a stacked fs (e.g. overlayfs) themselves and with
+			 * max_stack_depth == 1, FUSE fs can be stacked as the
+			 * underlying fs of a stacked fs (e.g. overlayfs).
+			 */
+			if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) &&
+			    (flags & FUSE_PASSTHROUGH) &&
+			    arg->max_stack_depth > 0 &&
+			    arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) {
+				fc->passthrough = 1;
+				fc->max_stack_depth = arg->max_stack_depth;
+				fm->sb->s_stack_depth = arg->max_stack_depth;
+			}
+			if (flags & FUSE_NO_EXPORT_SUPPORT)
+				fm->sb->s_export_op = &fuse_export_fid_operations;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1337,7 +1376,8 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
 		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
 		FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
-		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
+		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP |
+		FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		flags |= FUSE_MAP_ALIGNMENT;
@@ -1346,6 +1386,8 @@ void fuse_send_init(struct fuse_mount *fm)
 #endif
 	if (fm->fc->auto_submounts)
 		flags |= FUSE_SUBMOUNTS;
+	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+		flags |= FUSE_PASSTHROUGH;
 
 	ia->in.flags = flags;
 	ia->in.flags2 = flags >> 32;
@@ -1496,8 +1538,8 @@ static void fuse_fill_attr_from_inode(struct fuse_attr *attr,
 		.ctimensec	= ctime.tv_nsec,
 		.mode		= fi->inode.i_mode,
 		.nlink		= fi->inode.i_nlink,
-		.uid		= fi->inode.i_uid.val,
-		.gid		= fi->inode.i_gid.val,
+		.uid		= __kuid_val(fi->inode.i_uid),
+		.gid		= __kgid_val(fi->inode.i_gid),
 		.rdev		= fi->inode.i_rdev,
 		.blksize	= 1u << fi->inode.i_blkbits,
 	};
@@ -1534,6 +1576,7 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	sb->s_bdi = bdi_get(parent_sb->s_bdi);
 
 	sb->s_xattr = parent_sb->s_xattr;
+	sb->s_export_op = parent_sb->s_export_op;
 	sb->s_time_gran = parent_sb->s_time_gran;
 	sb->s_blocksize = parent_sb->s_blocksize;
 	sb->s_blocksize_bits = parent_sb->s_blocksize_bits;

fs/fuse/iomode.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE inode io modes.
+ *
+ * Copyright (c) 2024 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+
+/*
+ * Return true if need to wait for new opens in caching mode.
+ */
+static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi)
+{
+	return READ_ONCE(fi->iocachectr) < 0 && !fuse_inode_backing(fi);
+}
+
+/*
+ * Start cached io mode.
+ *
+ * Blocks new parallel dio writes and waits for the in-progress parallel dio
+ * writes to complete.
+ */
+int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+
+	/* There are no io modes if server does not implement open */
+	if (!ff->args)
+		return 0;
+
+	spin_lock(&fi->lock);
+	/*
+	 * Setting the bit advises new direct-io writes to use an exclusive
+	 * lock - without it the wait below might be forever.
+	 */
+	while (fuse_is_io_cache_wait(fi)) {
+		set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+		spin_unlock(&fi->lock);
+		wait_event(fi->direct_io_waitq, !fuse_is_io_cache_wait(fi));
+		spin_lock(&fi->lock);
+	}
+
+	/*
+	 * Check if inode entered passthrough io mode while waiting for parallel
+	 * dio write completion.
+	 */
+	if (fuse_inode_backing(fi)) {
+		clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+		spin_unlock(&fi->lock);
+		return -ETXTBSY;
+	}
+
+	WARN_ON(ff->iomode == IOM_UNCACHED);
+	if (ff->iomode == IOM_NONE) {
+		ff->iomode = IOM_CACHED;
+		if (fi->iocachectr == 0)
+			set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+		fi->iocachectr++;
+	}
+	spin_unlock(&fi->lock);
+	return 0;
+}
+
+static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+
+	spin_lock(&fi->lock);
+	WARN_ON(fi->iocachectr <= 0);
+	WARN_ON(ff->iomode != IOM_CACHED);
+	ff->iomode = IOM_NONE;
+	fi->iocachectr--;
+	if (fi->iocachectr == 0)
+		clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+	spin_unlock(&fi->lock);
+}
+
+/* Start strictly uncached io mode where cache access is not allowed */
+int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_backing *oldfb;
+	int err = 0;
+
+	spin_lock(&fi->lock);
+	/* deny conflicting backing files on same fuse inode */
+	oldfb = fuse_inode_backing(fi);
+	if (oldfb && oldfb != fb) {
+		err = -EBUSY;
+		goto unlock;
+	}
+	if (fi->iocachectr > 0) {
+		err = -ETXTBSY;
+		goto unlock;
+	}
+	WARN_ON(ff->iomode != IOM_NONE);
+	fi->iocachectr--;
+	ff->iomode = IOM_UNCACHED;
+
+	/* fuse inode holds a single refcount of backing file */
+	if (!oldfb) {
+		oldfb = fuse_inode_backing_set(fi, fb);
+		WARN_ON_ONCE(oldfb != NULL);
+	} else {
+		fuse_backing_put(fb);
+	}
+unlock:
+	spin_unlock(&fi->lock);
+	return err;
+}
+
+void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_backing *oldfb = NULL;
+
+	spin_lock(&fi->lock);
+	WARN_ON(fi->iocachectr >= 0);
+	WARN_ON(ff->iomode != IOM_UNCACHED);
+	ff->iomode = IOM_NONE;
+	fi->iocachectr++;
+	if (!fi->iocachectr) {
+		wake_up(&fi->direct_io_waitq);
+		oldfb = fuse_inode_backing_set(fi, NULL);
+	}
+	spin_unlock(&fi->lock);
+	if (oldfb)
+		fuse_backing_put(oldfb);
+}
+
+/*
+ * Open flags that are allowed in combination with FOPEN_PASSTHROUGH.
+ * A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write
+ * operations go directly to the server, but mmap is done on the backing file.
+ * FOPEN_PASSTHROUGH mode should not co-exist with any users of the fuse inode
+ * page cache, so FOPEN_KEEP_CACHE is a strange and undesired combination.
+ */
+#define FOPEN_PASSTHROUGH_MASK \
+	(FOPEN_PASSTHROUGH | FOPEN_DIRECT_IO | FOPEN_PARALLEL_DIRECT_WRITES | \
+	 FOPEN_NOFLUSH)
+
+static int fuse_file_passthrough_open(struct inode *inode, struct file *file)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_backing *fb;
+	int err;
+
+	/* Check allowed conditions for file open in passthrough mode */
+	if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) || !fc->passthrough ||
+	    (ff->open_flags & ~FOPEN_PASSTHROUGH_MASK))
+		return -EINVAL;
+
+	fb = fuse_passthrough_open(file, inode,
+				   ff->args->open_outarg.backing_id);
+	if (IS_ERR(fb))
+		return PTR_ERR(fb);
+
+	/* First passthrough file open denies caching inode io mode */
+	err = fuse_file_uncached_io_start(inode, ff, fb);
+	if (!err)
+		return 0;
+
+	fuse_passthrough_release(ff, fb);
+	fuse_backing_put(fb);
+
+	return err;
+}
+
+/* Request access to submit new io to inode via open file */
+int fuse_file_io_open(struct file *file, struct inode *inode)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	int err;
+
+	/*
+	 * io modes are not relevant with DAX and with server that does not
+	 * implement open.
+	 */
+	if (FUSE_IS_DAX(inode) || !ff->args)
+		return 0;
+
+	/*
+	 * Server is expected to use FOPEN_PASSTHROUGH for all opens of an inode
+	 * which is already open for passthrough.
+	 */
+	err = -EINVAL;
+	if (fuse_inode_backing(fi) && !(ff->open_flags & FOPEN_PASSTHROUGH))
+		goto fail;
+
+	/*
+	 * FOPEN_PARALLEL_DIRECT_WRITES requires FOPEN_DIRECT_IO.
+	 */
+	if (!(ff->open_flags & FOPEN_DIRECT_IO))
+		ff->open_flags &= ~FOPEN_PARALLEL_DIRECT_WRITES;
+
+	/*
+	 * First passthrough file open denies caching inode io mode.
+	 * First caching file open enters caching inode io mode.
+	 *
+	 * Note that if user opens a file open with O_DIRECT, but server did
+	 * not specify FOPEN_DIRECT_IO, a later fcntl() could remove O_DIRECT,
+	 * so we put the inode in caching mode to prevent parallel dio.
+	 */
+	if ((ff->open_flags & FOPEN_DIRECT_IO) &&
+	    !(ff->open_flags & FOPEN_PASSTHROUGH))
+		return 0;
+
+	if (ff->open_flags & FOPEN_PASSTHROUGH)
+		err = fuse_file_passthrough_open(inode, file);
+	else
+		err = fuse_file_cached_io_start(inode, ff);
+	if (err)
+		goto fail;
+
+	return 0;
+
+fail:
+	pr_debug("failed to open file in requested io mode (open_flags=0x%x, err=%i).\n",
+		 ff->open_flags, err);
+	/*
+	 * The file open mode determines the inode io mode.
+	 * Using incorrect open mode is a server mistake, which results in
+	 * user visible failure of open() with EIO error.
+	 */
+	return -EIO;
+}
+
+/* No more pending io and no new io possible to inode via open/mmapped file */
+void fuse_file_io_release(struct fuse_file *ff, struct inode *inode)
+{
+	/*
+	 * Last parallel dio close allows caching inode io mode.
+	 * Last caching file close exits caching inode io mode.
+	 */
+	switch (ff->iomode) {
+	case IOM_NONE:
+		/* Nothing to do */
+		break;
+	case IOM_UNCACHED:
+		fuse_file_uncached_io_end(inode, ff);
+		break;
+	case IOM_CACHED:
+		fuse_file_cached_io_end(inode, ff);
+		break;
+	}
+}

fs/fuse/passthrough.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE passthrough to backing file.
+ *
+ * Copyright (c) 2023 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/file.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+
+static void fuse_file_accessed(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+
+	fuse_invalidate_atime(inode);
+}
+
+static void fuse_file_modified(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+
+	fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
+}
+
+ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.user_file = file,
+		.accessed = fuse_file_accessed,
+	};
+
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+		 backing_file, iocb->ki_pos, count);
+
+	if (!count)
+		return 0;
+
+	ret = backing_file_read_iter(backing_file, iter, iocb, iocb->ki_flags,
+				     &ctx);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_write_iter(struct kiocb *iocb,
+				    struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.user_file = file,
+		.end_write = fuse_file_modified,
+	};
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+		 backing_file, iocb->ki_pos, count);
+
+	if (!count)
+		return 0;
+
+	inode_lock(inode);
+	ret = backing_file_write_iter(backing_file, iter, iocb, iocb->ki_flags,
+				      &ctx);
+	inode_unlock(inode);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
+				     struct pipe_inode_info *pipe,
+				     size_t len, unsigned int flags)
+{
+	struct fuse_file *ff = in->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.user_file = in,
+		.accessed = fuse_file_accessed,
+	};
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+		 backing_file, ppos ? *ppos : 0, len, flags);
+
+	return backing_file_splice_read(backing_file, ppos, pipe, len, flags,
+					&ctx);
+}
+
+ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
+				      struct file *out, loff_t *ppos,
+				      size_t len, unsigned int flags)
+{
+	struct fuse_file *ff = out->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct inode *inode = file_inode(out);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.user_file = out,
+		.end_write = fuse_file_modified,
+	};
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+		 backing_file, ppos ? *ppos : 0, len, flags);
+
+	inode_lock(inode);
+	ret = backing_file_splice_write(pipe, backing_file, ppos, len, flags,
+					&ctx);
+	inode_unlock(inode);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.user_file = file,
+		.accessed = fuse_file_accessed,
+	};
+
+	pr_debug("%s: backing_file=0x%p, start=%lu, end=%lu\n", __func__,
+		 backing_file, vma->vm_start, vma->vm_end);
+
+	return backing_file_mmap(backing_file, vma, &ctx);
+}
+
+struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
+{
+	if (fb && refcount_inc_not_zero(&fb->count))
+		return fb;
+	return NULL;
+}
+
+static void fuse_backing_free(struct fuse_backing *fb)
+{
+	pr_debug("%s: fb=0x%p\n", __func__, fb);
+
+	if (fb->file)
+		fput(fb->file);
+	put_cred(fb->cred);
+	kfree_rcu(fb, rcu);
+}
+
+void fuse_backing_put(struct fuse_backing *fb)
+{
+	if (fb && refcount_dec_and_test(&fb->count))
+		fuse_backing_free(fb);
+}
+
+void fuse_backing_files_init(struct fuse_conn *fc)
+{
+	idr_init(&fc->backing_files_map);
+}
+
+static int fuse_backing_id_alloc(struct fuse_conn *fc, struct fuse_backing *fb)
+{
+	int id;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock(&fc->lock);
+	/* FIXME: xarray might be space inefficient */
+	id = idr_alloc_cyclic(&fc->backing_files_map, fb, 1, 0, GFP_ATOMIC);
+	spin_unlock(&fc->lock);
+	idr_preload_end();
+
+	WARN_ON_ONCE(id == 0);
+	return id;
+}
+
+static struct fuse_backing *fuse_backing_id_remove(struct fuse_conn *fc,
+						   int id)
+{
+	struct fuse_backing *fb;
+
+	spin_lock(&fc->lock);
+	fb = idr_remove(&fc->backing_files_map, id);
+	spin_unlock(&fc->lock);
+
+	return fb;
+}
+
+static int fuse_backing_id_free(int id, void *p, void *data)
+{
+	struct fuse_backing *fb = p;
+
+	WARN_ON_ONCE(refcount_read(&fb->count) != 1);
+	fuse_backing_free(fb);
+	return 0;
+}
+
+void fuse_backing_files_free(struct fuse_conn *fc)
+{
+	idr_for_each(&fc->backing_files_map, fuse_backing_id_free, NULL);
+	idr_destroy(&fc->backing_files_map);
+}
+
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
+{
+	struct file *file;
+	struct super_block *backing_sb;
+	struct fuse_backing *fb = NULL;
+	int res;
+
+	pr_debug("%s: fd=%d flags=0x%x\n", __func__, map->fd, map->flags);
+
+	/* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+	res = -EPERM;
+	if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+		goto out;
+
+	res = -EINVAL;
+	if (map->flags)
+		goto out;
+
+	file = fget(map->fd);
+	res = -EBADF;
+	if (!file)
+		goto out;
+
+	res = -EOPNOTSUPP;
+	if (!file->f_op->read_iter || !file->f_op->write_iter)
+		goto out_fput;
+
+	backing_sb = file_inode(file)->i_sb;
+	res = -ELOOP;
+	if (backing_sb->s_stack_depth >= fc->max_stack_depth)
+		goto out_fput;
+
+	fb = kmalloc(sizeof(struct fuse_backing), GFP_KERNEL);
+	res = -ENOMEM;
+	if (!fb)
+		goto out_fput;
+
+	fb->file = file;
+	fb->cred = prepare_creds();
+	refcount_set(&fb->count, 1);
+
+	res = fuse_backing_id_alloc(fc, fb);
+	if (res < 0) {
+		fuse_backing_free(fb);
+		fb = NULL;
+	}
+
+out:
+	pr_debug("%s: fb=0x%p, ret=%i\n", __func__, fb, res);
+
+	return res;
+
+out_fput:
+	fput(file);
+	goto out;
+}
+
+int fuse_backing_close(struct fuse_conn *fc, int backing_id)
+{
+	struct fuse_backing *fb = NULL;
+	int err;
+
+	pr_debug("%s: backing_id=%d\n", __func__, backing_id);
+
+	/* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+	err = -EPERM;
+	if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+		goto out;
+
+	err = -EINVAL;
+	if (backing_id <= 0)
+		goto out;
+
+	err = -ENOENT;
+	fb = fuse_backing_id_remove(fc, backing_id);
+	if (!fb)
+		goto out;
+
+	fuse_backing_put(fb);
+	err = 0;
+out:
+	pr_debug("%s: fb=0x%p, err=%i\n", __func__, fb, err);
+
+	return err;
+}
+
+/*
+ * Setup passthrough to a backing file.
+ *
+ * Returns an fb object with elevated refcount to be stored in fuse inode.
+ */
+struct fuse_backing *fuse_passthrough_open(struct file *file,
+					   struct inode *inode,
+					   int backing_id)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_conn *fc = ff->fm->fc;
+	struct fuse_backing *fb = NULL;
+	struct file *backing_file;
+	int err;
+
+	err = -EINVAL;
+	if (backing_id <= 0)
+		goto out;
+
+	rcu_read_lock();
+	fb = idr_find(&fc->backing_files_map, backing_id);
+	fb = fuse_backing_get(fb);
+	rcu_read_unlock();
+
+	err = -ENOENT;
+	if (!fb)
+		goto out;
+
+	/* Allocate backing file per fuse file to store fuse path */
+	backing_file = backing_file_open(&file->f_path, file->f_flags,
+					 &fb->file->f_path, fb->cred);
+	err = PTR_ERR(backing_file);
+	if (IS_ERR(backing_file)) {
+		fuse_backing_put(fb);
+		goto out;
+	}
+
+	err = 0;
+	ff->passthrough = backing_file;
+	ff->cred = get_cred(fb->cred);
+out:
+	pr_debug("%s: backing_id=%d, fb=0x%p, backing_file=0x%p, err=%i\n", __func__,
+		 backing_id, fb, ff->passthrough, err);
+
+	return err ? ERR_PTR(err) : fb;
+}
+
+void fuse_passthrough_release(struct fuse_file *ff, struct fuse_backing *fb)
+{
+	pr_debug("%s: fb=0x%p, backing_file=0x%p\n", __func__,
+		 fb, ff->passthrough);
+
+	fput(ff->passthrough);
+	ff->passthrough = NULL;
+	put_cred(ff->cred);
+	ff->cred = NULL;
+}

fs/fuse/readdir.c

@@ -592,15 +592,11 @@ int fuse_readdir(struct file *file, struct dir_context *ctx)
 	if (fuse_is_bad(inode))
 		return -EIO;
 
-	mutex_lock(&ff->readdir.lock);
-
 	err = UNCACHED;
 	if (ff->open_flags & FOPEN_CACHE_DIR)
 		err = fuse_readdir_cached(file, ctx);
 	if (err == UNCACHED)
 		err = fuse_readdir_uncached(file, ctx);
 
-	mutex_unlock(&ff->readdir.lock);
-
 	return err;
 }

fs/fuse/virtio_fs.c

@@ -32,6 +32,9 @@
 static DEFINE_MUTEX(virtio_fs_mutex);
 static LIST_HEAD(virtio_fs_instances);
 
+/* The /sys/fs/virtio_fs/ kset */
+static struct kset *virtio_fs_kset;
+
 enum {
 	VQ_HIPRIO,
 	VQ_REQUEST
@@ -56,7 +59,7 @@ struct virtio_fs_vq {
 
 /* A virtio-fs device instance */
 struct virtio_fs {
-	struct kref refcount;
+	struct kobject kobj;
 	struct list_head list;    /* on virtio_fs_instances */
 	char *tag;
 	struct virtio_fs_vq *vqs;
@@ -162,18 +165,40 @@ static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
 		complete(&fsvq->in_flight_zero);
 }
 
-static void release_virtio_fs_obj(struct kref *ref)
+static ssize_t tag_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);
+
+	return sysfs_emit(buf, fs->tag);
+}
+
+static struct kobj_attribute virtio_fs_tag_attr = __ATTR_RO(tag);
+
+static struct attribute *virtio_fs_attrs[] = {
+	&virtio_fs_tag_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(virtio_fs);
+
+static void virtio_fs_ktype_release(struct kobject *kobj)
 {
-	struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
+	struct virtio_fs *vfs = container_of(kobj, struct virtio_fs, kobj);
 
 	kfree(vfs->vqs);
 	kfree(vfs);
 }
 
+static const struct kobj_type virtio_fs_ktype = {
+	.release = virtio_fs_ktype_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_groups = virtio_fs_groups,
+};
+
 /* Make sure virtiofs_mutex is held */
 static void virtio_fs_put(struct virtio_fs *fs)
 {
-	kref_put(&fs->refcount, release_virtio_fs_obj);
+	kobject_put(&fs->kobj);
 }
 
 static void virtio_fs_fiq_release(struct fuse_iqueue *fiq)
@@ -244,25 +269,46 @@ static void virtio_fs_start_all_queues(struct virtio_fs *fs)
 }
 
 /* Add a new instance to the list or return -EEXIST if tag name exists*/
-static int virtio_fs_add_instance(struct virtio_fs *fs)
+static int virtio_fs_add_instance(struct virtio_device *vdev,
+				  struct virtio_fs *fs)
 {
 	struct virtio_fs *fs2;
-	bool duplicate = false;
+	int ret;
 
 	mutex_lock(&virtio_fs_mutex);
 
 	list_for_each_entry(fs2, &virtio_fs_instances, list) {
-		if (strcmp(fs->tag, fs2->tag) == 0)
-			duplicate = true;
+		if (strcmp(fs->tag, fs2->tag) == 0) {
+			mutex_unlock(&virtio_fs_mutex);
+			return -EEXIST;
+		}
 	}
 
-	if (!duplicate)
-		list_add_tail(&fs->list, &virtio_fs_instances);
+	/* Use the virtio_device's index as a unique identifier, there is no
+	 * need to allocate our own identifiers because the virtio_fs instance
+	 * is only visible to userspace as long as the underlying virtio_device
+	 * exists.
+	 */
+	fs->kobj.kset = virtio_fs_kset;
+	ret = kobject_add(&fs->kobj, NULL, "%d", vdev->index);
+	if (ret < 0) {
+		mutex_unlock(&virtio_fs_mutex);
+		return ret;
+	}
+
+	ret = sysfs_create_link(&fs->kobj, &vdev->dev.kobj, "device");
+	if (ret < 0) {
+		kobject_del(&fs->kobj);
+		mutex_unlock(&virtio_fs_mutex);
+		return ret;
+	}
+
+	list_add_tail(&fs->list, &virtio_fs_instances);
 
 	mutex_unlock(&virtio_fs_mutex);
 
-	if (duplicate)
-		return -EEXIST;
+	kobject_uevent(&fs->kobj, KOBJ_ADD);
+
 	return 0;
 }
 
@@ -275,7 +321,7 @@ static struct virtio_fs *virtio_fs_find_instance(const char *tag)
 
 	list_for_each_entry(fs, &virtio_fs_instances, list) {
 		if (strcmp(fs->tag, tag) == 0) {
-			kref_get(&fs->refcount);
+			kobject_get(&fs->kobj);
 			goto found;
 		}
 	}
@@ -324,6 +370,16 @@ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs)
 		return -ENOMEM;
 	memcpy(fs->tag, tag_buf, len);
 	fs->tag[len] = '\0';
+
+	/* While the VIRTIO specification allows any character, newlines are
+	 * awkward on mount(8) command-lines and cause problems in the sysfs
+	 * "tag" attr and uevent TAG= properties. Forbid them.
+	 */
+	if (strchr(fs->tag, '\n')) {
+		dev_dbg(&vdev->dev, "refusing virtiofs tag with newline character\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -346,7 +402,7 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
 			kfree(req);
 			dec_in_flight_req(fsvq);
 		}
-	} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
+	} while (!virtqueue_enable_cb(vq));
 	spin_unlock(&fsvq->lock);
 }
 
@@ -628,7 +684,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
 			list_move_tail(&req->list, &reqs);
 			spin_unlock(&fpq->lock);
 		}
-	} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
+	} while (!virtqueue_enable_cb(vq));
 	spin_unlock(&fsvq->lock);
 
 	/* End requests */
@@ -872,7 +928,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 	fs = kzalloc(sizeof(*fs), GFP_KERNEL);
 	if (!fs)
 		return -ENOMEM;
-	kref_init(&fs->refcount);
+	kobject_init(&fs->kobj, &virtio_fs_ktype);
 	vdev->priv = fs;
 
 	ret = virtio_fs_read_tag(vdev, fs);
@@ -894,7 +950,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 	 */
 	virtio_device_ready(vdev);
 
-	ret = virtio_fs_add_instance(fs);
+	ret = virtio_fs_add_instance(vdev, fs);
 	if (ret < 0)
 		goto out_vqs;
 
@@ -903,11 +959,10 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 out_vqs:
 	virtio_reset_device(vdev);
 	virtio_fs_cleanup_vqs(vdev);
-	kfree(fs->vqs);
 
 out:
 	vdev->priv = NULL;
-	kfree(fs);
+	kobject_put(&fs->kobj);
 	return ret;
 }
 
@@ -931,6 +986,8 @@ static void virtio_fs_remove(struct virtio_device *vdev)
 	mutex_lock(&virtio_fs_mutex);
 	/* This device is going away. No one should get new reference */
 	list_del_init(&fs->list);
+	sysfs_remove_link(&fs->kobj, "device");
+	kobject_del(&fs->kobj);
 	virtio_fs_stop_all_queues(fs);
 	virtio_fs_drain_all_queues_locked(fs);
 	virtio_reset_device(vdev);
@@ -1517,21 +1574,56 @@ static struct file_system_type virtio_fs_type = {
 	.kill_sb	= virtio_kill_sb,
 };
 
+static int virtio_fs_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
+{
+	const struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);
+
+	add_uevent_var(env, "TAG=%s", fs->tag);
+	return 0;
+}
+
+static const struct kset_uevent_ops virtio_fs_uevent_ops = {
+	.uevent = virtio_fs_uevent,
+};
+
+static int __init virtio_fs_sysfs_init(void)
+{
+	virtio_fs_kset = kset_create_and_add("virtiofs", &virtio_fs_uevent_ops,
+					     fs_kobj);
+	if (!virtio_fs_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+static void virtio_fs_sysfs_exit(void)
+{
+	kset_unregister(virtio_fs_kset);
+	virtio_fs_kset = NULL;
+}
+
 static int __init virtio_fs_init(void)
 {
 	int ret;
 
-	ret = register_virtio_driver(&virtio_fs_driver);
+	ret = virtio_fs_sysfs_init();
 	if (ret < 0)
 		return ret;
 
+	ret = register_virtio_driver(&virtio_fs_driver);
+	if (ret < 0)
+		goto sysfs_exit;
+
 	ret = register_filesystem(&virtio_fs_type);
-	if (ret < 0) {
-		unregister_virtio_driver(&virtio_fs_driver);
-		return ret;
-	}
+	if (ret < 0)
+		goto unregister_virtio_driver;
 
 	return 0;
+
+unregister_virtio_driver:
+	unregister_virtio_driver(&virtio_fs_driver);
+sysfs_exit:
+	virtio_fs_sysfs_exit();
+	return ret;
 }
 module_init(virtio_fs_init);
 
@@ -1539,6 +1631,7 @@ static void __exit virtio_fs_exit(void)
 {
 	unregister_filesystem(&virtio_fs_type);
 	unregister_virtio_driver(&virtio_fs_driver);
+	virtio_fs_sysfs_exit();
 }
 module_exit(virtio_fs_exit);
 

include/uapi/linux/fuse.h

@@ -211,6 +211,12 @@
  *  7.39
  *  - add FUSE_DIRECT_IO_ALLOW_MMAP
  *  - add FUSE_STATX and related structures
+ *
+ *  7.40
+ *  - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag
+ *  - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag
+ *  - add FUSE_NO_EXPORT_SUPPORT init flag
+ *  - add FUSE_NOTIFY_RESEND, add FUSE_HAS_RESEND init flag
  */
 
 #ifndef _LINUX_FUSE_H
@@ -246,7 +252,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 39
+#define FUSE_KERNEL_MINOR_VERSION 40
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -353,6 +359,7 @@ struct fuse_file_lock {
  * FOPEN_STREAM: the file is stream-like (no file position at all)
  * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE)
  * FOPEN_PARALLEL_DIRECT_WRITES: Allow concurrent direct writes on the same inode
+ * FOPEN_PASSTHROUGH: passthrough read/write io for this open file
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
@@ -361,6 +368,7 @@ struct fuse_file_lock {
 #define FOPEN_STREAM		(1 << 4)
 #define FOPEN_NOFLUSH		(1 << 5)
 #define FOPEN_PARALLEL_DIRECT_WRITES	(1 << 6)
+#define FOPEN_PASSTHROUGH	(1 << 7)
 
 /**
  * INIT request/reply flags
@@ -410,6 +418,9 @@ struct fuse_file_lock {
  *			symlink and mknod (single group that matches parent)
  * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
  * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
+ * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support
+ * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit
+ *		    of the request ID indicates resend requests
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -449,6 +460,9 @@ struct fuse_file_lock {
 #define FUSE_CREATE_SUPP_GROUP	(1ULL << 34)
 #define FUSE_HAS_EXPIRE_ONLY	(1ULL << 35)
 #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+#define FUSE_PASSTHROUGH	(1ULL << 37)
+#define FUSE_NO_EXPORT_SUPPORT	(1ULL << 38)
+#define FUSE_HAS_RESEND		(1ULL << 39)
 
 /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
 #define FUSE_DIRECT_IO_RELAX	FUSE_DIRECT_IO_ALLOW_MMAP
@@ -635,6 +649,7 @@ enum fuse_notify_code {
 	FUSE_NOTIFY_STORE = 4,
 	FUSE_NOTIFY_RETRIEVE = 5,
 	FUSE_NOTIFY_DELETE = 6,
+	FUSE_NOTIFY_RESEND = 7,
 	FUSE_NOTIFY_CODE_MAX,
 };
 
@@ -761,7 +776,7 @@ struct fuse_create_in {
 struct fuse_open_out {
 	uint64_t	fh;
 	uint32_t	open_flags;
-	uint32_t	padding;
+	int32_t		backing_id;
 };
 
 struct fuse_release_in {
@@ -877,7 +892,8 @@ struct fuse_init_out {
 	uint16_t	max_pages;
 	uint16_t	map_alignment;
 	uint32_t	flags2;
-	uint32_t	unused[7];
+	uint32_t	max_stack_depth;
+	uint32_t	unused[6];
 };
 
 #define CUSE_INIT_INFO_MAX 4096
@@ -960,6 +976,14 @@ struct fuse_fallocate_in {
 	uint32_t	padding;
 };
 
+/**
+ * FUSE request unique ID flag
+ *
+ * Indicates whether this is a resend request. The receiver should handle this
+ * request accordingly.
+ */
+#define FUSE_UNIQUE_RESEND (1ULL << 63)
+
 struct fuse_in_header {
 	uint32_t	len;
 	uint32_t	opcode;
@@ -1049,9 +1073,18 @@ struct fuse_notify_retrieve_in {
 	uint64_t	dummy4;
 };
 
+struct fuse_backing_map {
+	int32_t		fd;
+	uint32_t	flags;
+	uint64_t	padding;
+};
+
 /* Device ioctls: */
 #define FUSE_DEV_IOC_MAGIC		229
 #define FUSE_DEV_IOC_CLONE		_IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t)
+#define FUSE_DEV_IOC_BACKING_OPEN	_IOW(FUSE_DEV_IOC_MAGIC, 1, \
+					     struct fuse_backing_map)
+#define FUSE_DEV_IOC_BACKING_CLOSE	_IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t)
 
 struct fuse_lseek_in {
 	uint64_t	fh;