fuse: implement open in passthrough mode

After getting a backing file id with FUSE_DEV_IOC_BACKING_OPEN ioctl,
a FUSE server can reply to an OPEN request with flag FOPEN_PASSTHROUGH
and the backing file id.

The FUSE server should reuse the same backing file id for all the open
replies of the same FUSE inode and open will fail (with -EIO) if a the
server attempts to open the same inode with conflicting io modes or to
setup passthrough to two different backing files for the same FUSE inode.
Using the same backing file id for several different inodes is allowed.

Opening a new file with FOPEN_DIRECT_IO for an inode that is already
open for passthrough is allowed, but only if the FOPEN_PASSTHROUGH flag
and correct backing file id are specified as well.

The read/write IO of such files will not use passthrough operations to
the backing file, but mmap, which does not support direct_io, will use
the backing file insead of using the page cache as it always did.

Even though all FUSE passthrough files of the same inode use the same
backing file as a backing inode reference, each FUSE file opens a unique
instance of a backing_file object to store the FUSE path that was used
to open the inode and the open flags of the specific open file.

The per-file, backing_file object is released along with the FUSE file.
The inode associated fuse_backing object is released when the last FUSE
passthrough file of that inode is released AND when the backing file id
is closed by the server using the FUSE_DEV_IOC_BACKING_CLOSE ioctl.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/file.c

@@ -295,6 +295,9 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
 	struct fuse_conn *fc = ff->fm->fc;
 	struct fuse_release_args *ra = &ff->args->release_args;
 
+	if (fuse_file_passthrough(ff))
+		fuse_passthrough_release(ff, fuse_inode_backing(fi));
+
 	/* Inode is NULL on error path of fuse_create_open() */
 	if (likely(fi)) {
 		spin_lock(&fi->lock);
@@ -1374,7 +1377,7 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from,
 		 * have raced, so check it again.
 		 */
 		if (fuse_io_past_eof(iocb, from) ||
-		    fuse_file_uncached_io_start(inode, ff) != 0) {
+		    fuse_file_uncached_io_start(inode, ff, NULL) != 0) {
 			inode_unlock_shared(inode);
 			inode_lock(inode);
 			*exclusive = true;
@@ -2527,6 +2530,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (FUSE_IS_DAX(file_inode(file)))
 		return fuse_dax_mmap(file, vma);
 
+	/* TODO: implement mmap to backing file */
+	if (fuse_file_passthrough(ff))
+		return -ENODEV;
+
 	/*
 	 * FOPEN_DIRECT_IO handling is special compared to O_DIRECT,
 	 * as does not allow MAP_SHARED mmap without FUSE_DIRECT_IO_ALLOW_MMAP.

fs/fuse/fuse_i.h

@@ -269,6 +269,12 @@ struct fuse_file {
 	/** 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;
 };
@@ -1394,7 +1400,7 @@ int fuse_fileattr_set(struct mnt_idmap *idmap,
 
 /* 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);
+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);
@@ -1426,11 +1432,38 @@ static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi,
 #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
+}
+
 #endif /* _FS_FUSE_I_H */

fs/fuse/iomode.c

@@ -17,7 +17,7 @@
  */
 static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi)
 {
-	return READ_ONCE(fi->iocachectr) < 0;
+	return READ_ONCE(fi->iocachectr) < 0 && !fuse_inode_backing(fi);
 }
 
 /*
@@ -45,6 +45,17 @@ int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff)
 		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;
@@ -71,12 +82,19 @@ static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff)
 }
 
 /* Start strictly uncached io mode where cache access is not allowed */
-int fuse_file_uncached_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)
 {
 	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;
@@ -84,6 +102,14 @@ int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff)
 	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;
@@ -92,15 +118,20 @@ unlock:
 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)
+	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);
 }
 
 /*
@@ -118,6 +149,7 @@ 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 */
@@ -125,11 +157,18 @@ static int fuse_file_passthrough_open(struct inode *inode, struct file *file)
 	    (ff->open_flags & ~FOPEN_PASSTHROUGH_MASK))
 		return -EINVAL;
 
-	/* TODO: implement backing file open */
-	return -EOPNOTSUPP;
+	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);
+	err = fuse_file_uncached_io_start(inode, ff, fb);
+	if (!err)
+		return 0;
+
+	fuse_passthrough_release(ff, fb);
+	fuse_backing_put(fb);
 
 	return err;
 }
@@ -138,6 +177,7 @@ static int fuse_file_passthrough_open(struct inode *inode, struct file *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;
 
 	/*
@@ -147,6 +187,14 @@ int fuse_file_io_open(struct file *file, struct inode *inode)
 	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.
 	 */

fs/fuse/passthrough.c

@@ -8,6 +8,7 @@
 #include "fuse_i.h"
 
 #include <linux/file.h>
+#include <linux/backing-file.h>
 
 struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
 {
@@ -164,3 +165,61 @@ out:
 
 	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;
+}