[PATCH v14 06/12] fuse: introduce FUSE_PASSTHROUGH capability

[Amir Goldstein <amir73il@gmail.com>]

FUSE_PASSTHROUGH capability to passthrough FUSE operations to backing
files will be made available with kernel config CONFIG_FUSE_PASSTHROUGH.

When requesting FUSE_PASSTHROUGH, userspace needs to specify the
max_stack_depth that is allowed for FUSE on top of backing files.

Introduce a refcounted fuse_backing object that will be used to
associate an open backing file with a fuse inode.

This association will be used when replying to OPEN with the flag
FOPEN_PASSTHROUGH to setup passthrough of read/write operations on the
open fuse file to the associated backing file.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/fuse/Kconfig           | 11 +++++++++++
 fs/fuse/Makefile          |  1 +
 fs/fuse/fuse_i.h          | 19 +++++++++++++++++++
 fs/fuse/inode.c           | 20 ++++++++++++++++++++
 fs/fuse/passthrough.c     | 30 ++++++++++++++++++++++++++++++
 include/uapi/linux/fuse.h | 12 ++++++++++--
 6 files changed, 91 insertions(+), 2 deletions(-)
 create mode 100644 fs/fuse/passthrough.c

diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 038ed0b9aaa5..8674dbfbe59d 100644
--- a/fs/fuse/Kconfig
+++ b/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.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 0c48b35c058d..504acfb71402 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -9,5 +9,6 @@ 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-$(CONFIG_FUSE_DAX) += dax.o
+fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
 
 virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6e6e721f421b..5be51358542e 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -63,6 +63,15 @@ struct fuse_forget_link {
 	struct fuse_forget_link *next;
 };
 
+/** Container for data related to mapping to backing file */
+struct fuse_backing {
+	struct file *file;
+
+	/** refcount */
+	refcount_t count;
+	struct rcu_head rcu;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */
@@ -803,6 +812,12 @@ 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;
 
@@ -1340,4 +1355,8 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
 void fuse_file_release(struct inode *inode, struct fuse_file *ff,
 		       unsigned int open_flags, fl_owner_t id, bool isdir);
 
+/* passthrough.c */
+struct fuse_backing *fuse_backing_get(struct fuse_backing *fb);
+void fuse_backing_put(struct fuse_backing *fb);
+
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2e4eb7cf26fb..7e01eb5a04dc 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1234,6 +1234,24 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->create_supp_group = 1;
 			if (flags & FUSE_DIRECT_IO_RELAX)
 				fc->direct_io_relax = 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;
+			}
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1289,6 +1307,8 @@ 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;
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
new file mode 100644
index 000000000000..e8639c0a9ac6
--- /dev/null
+++ b/fs/fuse/passthrough.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE passthrough to backing file.
+ *
+ * Copyright (c) 2023 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/file.h>
+
+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)
+{
+	if (fb->file)
+		fput(fb->file);
+	kfree_rcu(fb, rcu);
+}
+
+void fuse_backing_put(struct fuse_backing *fb)
+{
+	if (fb && refcount_dec_and_test(&fb->count))
+		fuse_backing_free(fb);
+}
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index db92a7202b34..acb42a76f7ff 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -211,6 +211,10 @@
  *  7.39
  *  - add FUSE_DIRECT_IO_RELAX
  *  - add FUSE_STATX and related structures
+ *
+ *  7.40
+ *  - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH flag
+ *  - add FOPEN_PASSTHROUGH
  */
 
 #ifndef _LINUX_FUSE_H
@@ -246,7 +250,7 @@
 #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 +357,7 @@ 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 operations for this open file
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
@@ -361,6 +366,7 @@ 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
@@ -450,6 +456,7 @@ struct fuse_file_lock {
 #define FUSE_CREATE_SUPP_GROUP	(1ULL << 34)
 #define FUSE_HAS_EXPIRE_ONLY	(1ULL << 35)
 #define FUSE_DIRECT_IO_RELAX	(1ULL << 36)
+#define FUSE_PASSTHROUGH	(1ULL << 37)
 
 /**
  * CUSE INIT request/reply flags
@@ -875,7 +882,8 @@ 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
-- 
2.34.1