[PATCH 0/3] fuse: atomic open

[PATCH 0/3] fuse: atomic open

[jamz]

From: Jimmy Zuber <jamz@amazon.com>

Add FUSE_OPEN_ATOMIC, allowing the kernel to skip LOOKUP to improve
performance. A server implementing FUSE_OPEN_ATOMIC will look up
the name, create it if O_CREAT is supplied, and open it in one request.

The reply says whether the file was created, as Miklos suggested in [1].
The overall pattern follows his sketch in [2]. For a cached
name, the kernel compares the returned nodeid with the cached one and
looks the name up again on a mismatch.

A server without FUSE_OPEN_ATOMIC replies -ENOSYS and keeps today's
behaviour.

Tested with a new selftest under UML and KVM.

[1] https://lore.kernel.org/all/CAJfpeguEK4JsFo60=yHkpLL6XkDGS7cQ5GOhiFL379KsYk0TsQ@mail.gmail.com/
[2] https://lore.kernel.org/all/CAJfpegvXtXY=Pbxv+dMGFR8mvWN0DUwhSo6NwaVexk6Y6sao+w@mail.gmail.com/


Jimmy Zuber (3):
  fuse: add FUSE_OPEN_ATOMIC
  fuse: open cached files with FUSE_OPEN_ATOMIC
  selftests/fuse: add test for FUSE_OPEN_ATOMIC

 fs/fuse/dir.c                                 | 359 +++++++++++--
 fs/fuse/file.c                                |   4 +-
 fs/fuse/fuse_i.h                              |   4 +
 include/uapi/linux/fuse.h                     |   8 +-
 .../selftests/filesystems/fuse/.gitignore     |   1 +
 .../selftests/filesystems/fuse/Makefile       |   3 +-
 .../filesystems/fuse/atomic_open_test.c       | 473 ++++++++++++++++++
 7 files changed, 797 insertions(+), 55 deletions(-)
 create mode 100644 tools/testing/selftests/filesystems/fuse/atomic_open_test.c


base-commit: b776cbe24cc1b79c7f5101762b0069b3f48b6a4b
-- 
2.50.1

[PATCH 1/3] fuse: add FUSE_OPEN_ATOMIC

[jamz]

From: Jimmy Zuber <jamz@amazon.com>

Add FUSE_OPEN_ATOMIC, allowing the kernel to skip LOOKUP to improve
performance. A server implementing FUSE_OPEN_ATOMIC will look up
the name, create it if O_CREAT is supplied, and open it in one request.

The server replies with the entry and the open file. If the file was
created, the server returns FOPEN_CREATED, or just the entry if it
was not created. If the name does not exist, the server returns a
zero nodeid, cacheable like a negative LOOKUP. An existing file
opened with O_TRUNC is returned unopened, so that truncation can be
performed after permissions are checked.

FMODE_CREATED is set only when the server reports that it created the
file. Therefore a file created by someone else between LOOKUP and
CREATE is no longer opened without a permission check.

A server without the request replies -ENOSYS, and the kernel falls back to
FUSE_LOOKUP, keeping backwards compatibility.

Assisted-by: Claude:claude-opus-5-5 [Claude-Code]
Signed-off-by: Jimmy Zuber <jamz@amazon.com>
---
 fs/fuse/dir.c             | 112 +++++++++++++++++++++++++++++++++++---
 fs/fuse/fuse_i.h          |   3 +
 include/uapi/linux/fuse.h |   8 ++-
 3 files changed, 113 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index f48fafccce4b..34d2271eb248 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -815,7 +815,47 @@ static void free_ext_value(struct fuse_args *args)
 }
 
 /*
- * Atomic create+open operation
+ * FUSE_OPEN_ATOMIC found an existing name and left the open to the VFS.  A
+ * zero nodeid means the name does not exist.
+ */
+static int fuse_open_atomic_found(struct inode *dir, struct dentry *entry,
+				  struct file *file,
+				  struct fuse_entry_out *outarg,
+				  struct fuse_forget_link *forget, int epoch,
+				  u64 attr_version, u64 evict_ctr)
+{
+	struct fuse_conn *fc = get_fuse_conn(dir);
+	struct inode *inode = NULL;
+	struct dentry *res;
+
+	if (outarg->nodeid) {
+		inode = fuse_iget(dir->i_sb, outarg->nodeid, outarg->generation,
+				  &outarg->attr, ATTR_TIMEOUT(outarg),
+				  attr_version, evict_ctr);
+		if (!inode) {
+			fuse_chan_queue_forget(fc->chan, forget,
+					       outarg->nodeid, 1);
+			return -ENOMEM;
+		}
+	}
+	kfree(forget);
+	if (inode && get_node_id(inode) == FUSE_ROOT_ID) {
+		iput(inode);
+		return -EIO;
+	}
+
+	d_drop(entry);
+	res = d_splice_alias(inode, entry);
+	if (!IS_ERR(res)) {
+		fuse_dentry_set_epoch(res ?: entry, epoch);
+		fuse_change_entry_timeout(res ?: entry, outarg);
+	}
+	return finish_no_open(file, res);
+}
+
+/*
+ * Atomic create+open operation, or lookup with optional create and open for
+ * FUSE_OPEN_ATOMIC
  *
  * If the filesystem doesn't support this, then fall back to separate
  * 'mknod' + 'open' requests.
@@ -833,8 +873,12 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	struct fuse_entry_out outentry;
 	struct fuse_inode *fi;
 	struct fuse_file *ff;
+	u64 attr_version, evict_ctr;
 	int epoch, err;
 	bool trunc = flags & O_TRUNC;
+	bool atomic = opcode == FUSE_OPEN_ATOMIC;
+	bool create = !atomic || (flags & O_CREAT);
+	bool locked, created;
 
 	/* Userspace expects S_IFREG in create mode */
 	BUG_ON((mode & S_IFMT) != S_IFREG);
@@ -878,26 +922,62 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	outopenp = &ff->args->open_outarg;
 	args.out_args[1].size = sizeof(*outopenp);
 	args.out_args[1].value = outopenp;
+	/* FUSE_OPEN_ATOMIC leaves out fuse_open_out if it did not open */
+	args.out_argvar = atomic;
 
-	err = get_create_ext(idmap, &args, dir, entry, mode);
-	if (err)
-		goto out_free_ff;
+	if (create) {
+		err = get_create_ext(idmap, &args, dir, entry, mode);
+		if (err)
+			goto out_free_ff;
+	} else {
+		idmap = &invalid_mnt_idmap;
+	}
 
+	attr_version = fuse_get_attr_version(fm->fc);
+	evict_ctr = fuse_get_evict_ctr(fm->fc);
+
+	/* Without O_CREAT the parent is locked shared, as for a lookup */
+	locked = !create && fuse_lock_inode(dir);
 	err = fuse_simple_idmap_request(idmap, fm, &args);
+	fuse_unlock_inode(dir, locked);
 	free_ext_value(&args);
-	if (err)
+	if (err < 0)
 		goto out_free_ff;
 
 	err = -EIO;
+	if (atomic && !args.out_args[1].size) {
+		/* A zero nodeid: the name does not exist and was not created */
+		if (!outentry.nodeid && create)
+			goto out_free_ff;
+		if (outentry.nodeid && (invalid_nodeid(outentry.nodeid) ||
+					fuse_invalid_attr(&outentry.attr)))
+			goto out_free_ff;
+		fuse_file_free(ff);
+		return fuse_open_atomic_found(dir, entry, file, &outentry,
+					      forget, epoch, attr_version,
+					      evict_ctr);
+	}
+
 	if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) ||
-	    fuse_invalid_attr(&outentry.attr))
+	    fuse_invalid_attr(&outentry.attr) ||
+	    args.out_args[1].size != sizeof(*outopenp))
 		goto out_free_ff;
 
+	created = !atomic || (outopenp->open_flags & FOPEN_CREATED);
+	if (atomic) {
+		/* Only O_CREAT creates; O_TRUNC opens are left to the VFS */
+		if ((created && !create) || (!created && trunc))
+			goto out_free_ff;
+		if (created)
+			file->f_mode |= FMODE_CREATED;
+	}
+
 	ff->fh = outopenp->fh;
 	ff->nodeid = outentry.nodeid;
 	ff->open_flags = outopenp->open_flags;
 	inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
-			  &outentry.attr, ATTR_TIMEOUT(&outentry), 0, 0);
+			  &outentry.attr, ATTR_TIMEOUT(&outentry),
+			  created ? 0 : attr_version, created ? 0 : evict_ctr);
 	if (!inode) {
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(NULL, ff, flags);
@@ -906,10 +986,14 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 		goto out_err;
 	}
 	kfree(forget);
-	d_instantiate(entry, inode);
+	if (d_in_lookup(entry))
+		d_splice_alias(inode, entry);
+	else
+		d_instantiate(entry, inode);
 	fuse_dentry_set_epoch(entry, epoch);
 	fuse_change_entry_timeout(entry, &outentry);
-	fuse_dir_changed(dir);
+	if (created)
+		fuse_dir_changed(dir);
 	err = generic_file_open(inode, file);
 	if (!err) {
 		file->private_data = ff;
@@ -947,6 +1031,16 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 	if (fuse_is_bad(dir))
 		return -EIO;
 
+	if (!fc->no_open_atomic && (d_in_lookup(entry) || (flags & O_CREAT))) {
+		err = fuse_create_open(idmap, dir, entry, file, flags,
+				       mode | S_IFREG, FUSE_OPEN_ATOMIC);
+		if (err == -EEXIST)
+			fuse_invalidate_entry(entry);
+		if (err != -ENOSYS)
+			return err;
+		fc->no_open_atomic = 1;
+	}
+
 	if (d_in_lookup(entry)) {
 		struct dentry *res = fuse_lookup(dir, entry, 0);
 		if (res || d_really_is_positive(entry))
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 8546855386b5..ba6dc4c43a1f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -589,6 +589,9 @@ struct fuse_conn {
 	/** @no_create: Is create not implemented by fs? */
 	unsigned no_create:1;
 
+	/** @no_open_atomic: Is open atomic not implemented by fs? */
+	unsigned no_open_atomic:1;
+
 	/** @no_bmap: Is bmap not implemented by fs? */
 	unsigned no_bmap:1;
 
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 10a7f31c4bdf..745b686c468f 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -251,6 +251,9 @@
  *
  *  7.47
  *  - add FUSE_HAS_SYNCFS opt-in flag for privileged userspace servers
+ *
+ *  7.48
+ *  - add FUSE_OPEN_ATOMIC and FOPEN_CREATED
  */
 
 #ifndef _LINUX_FUSE_H
@@ -286,7 +289,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 47
+#define FUSE_KERNEL_MINOR_VERSION 48
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -400,6 +403,7 @@ struct fuse_file_lock {
  *                           (FUSE_URING_ZERO_COPY) and the request carries page
  *                           payload. Otherwise reads/writes fall back to
  *                           copying.
+ * FOPEN_CREATED: FUSE_OPEN_ATOMIC created the file
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
@@ -410,6 +414,7 @@ struct fuse_file_lock {
 #define FOPEN_PARALLEL_DIRECT_WRITES	(1 << 6)
 #define FOPEN_PASSTHROUGH	(1 << 7)
 #define FOPEN_IO_URING_ZERO_COPY (1 << 8)
+#define FOPEN_CREATED		(1 << 9)
 
 /**
  * INIT request/reply flags
@@ -690,6 +695,7 @@ enum fuse_opcode {
 	FUSE_TMPFILE		= 51,
 	FUSE_STATX		= 52,
 	FUSE_COPY_FILE_RANGE_64	= 53,
+	FUSE_OPEN_ATOMIC	= 54,
 
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,
-- 
2.50.1

[PATCH 2/3] fuse: open cached files with FUSE_OPEN_ATOMIC

[jamz]

From: Jimmy Zuber <jamz@amazon.com>

When the server implements FUSE_OPEN_ATOMIC, skip LOOKUP for a
regular file being opened, opening it by name from fuse_open() instead.
If the name now refers to a different file or to nothing, drop the
dentry and return -EOPENSTALE, so that the VFS looks the name up again.
A matching reply refreshes the attributes and the entry timeout.

If the server replies -ENOSYS, fuse_open() sends the skipped LOOKUP
itself.

Assisted-by: Claude:claude-opus-5-5 [Claude-Code]
Signed-off-by: Jimmy Zuber <jamz@amazon.com>
---
 fs/fuse/dir.c    | 247 ++++++++++++++++++++++++++++++++++++++---------
 fs/fuse/file.c   |   4 +-
 fs/fuse/fuse_i.h |   1 +
 3 files changed, 208 insertions(+), 44 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 34d2271eb248..ea265a8d179f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -379,6 +379,60 @@ static void fuse_lookup_init(struct fuse_args *args, u64 nodeid,
 	args->out_args[0].value = outarg;
 }
 
+/*
+ * Look the name of @entry up again.  Returns 1 if it still refers to the
+ * inode of @entry, refreshing its attributes and entry timeout, 0 if it does
+ * not, or -ENOMEM / -EINTR.
+ */
+static int fuse_revalidate_lookup(struct inode *dir, const struct qstr *name,
+				  struct dentry *entry)
+{
+	struct inode *inode = d_inode(entry);
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_entry_out outarg;
+	FUSE_ARGS(args);
+	struct fuse_forget_link *forget;
+	u64 attr_version;
+	int ret;
+
+	forget = fuse_alloc_forget();
+	if (!forget)
+		return -ENOMEM;
+
+	attr_version = fuse_get_attr_version(fm->fc);
+
+	fuse_lookup_init(&args, get_node_id(dir), name, &outarg);
+	ret = fuse_simple_request(fm, &args);
+	/* Zero nodeid is same as -ENOENT */
+	if (!ret && !outarg.nodeid)
+		ret = -ENOENT;
+	if (!ret) {
+		if (outarg.nodeid != get_node_id(inode) ||
+		    (bool) IS_AUTOMOUNT(inode) != (bool) (outarg.attr.flags & FUSE_ATTR_SUBMOUNT)) {
+			fuse_chan_queue_forget(fm->fc->chan, forget,
+					       outarg.nodeid, 1);
+			return 0;
+		}
+		spin_lock(&fi->lock);
+		fi->nlookup++;
+		spin_unlock(&fi->lock);
+	}
+	kfree(forget);
+	if (ret == -ENOMEM || ret == -EINTR)
+		return ret;
+	if (ret || fuse_invalid_attr(&outarg.attr) ||
+	    fuse_stale_inode(inode, outarg.generation, &outarg.attr))
+		return 0;
+
+	forget_all_cached_acls(inode);
+	fuse_change_attributes(inode, &outarg.attr, NULL,
+			       ATTR_TIMEOUT(&outarg),
+			       attr_version);
+	fuse_change_entry_timeout(entry, &outarg);
+	return 1;
+}
+
 /*
  * Check whether the dentry is still valid
  *
@@ -392,7 +446,6 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
 				  struct dentry *entry, unsigned int flags)
 {
 	struct inode *inode;
-	struct fuse_mount *fm;
 	struct fuse_conn *fc;
 	struct fuse_inode *fi;
 	struct fuse_dentry *fd = entry->d_fsdata;
@@ -407,57 +460,24 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
 		goto invalid;
 	else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
 		 (flags & (LOOKUP_EXCL | LOOKUP_REVAL | LOOKUP_RENAME_TARGET))) {
-		struct fuse_entry_out outarg;
-		FUSE_ARGS(args);
-		struct fuse_forget_link *forget;
-		u64 attr_version;
-
 		/* For negative dentries, always do a fresh lookup */
 		if (!inode)
 			goto invalid;
 
+		/* fuse_open_revalidate() checks the name of a file it opens */
+		if (!fc->no_open_atomic && (flags & LOOKUP_OPEN) &&
+		    !(flags & (LOOKUP_EXCL | LOOKUP_REVAL |
+			       LOOKUP_RENAME_TARGET)) &&
+		    S_ISREG(inode->i_mode) && !d_mountpoint(entry))
+			goto valid;
+
 		ret = -ECHILD;
 		if (flags & LOOKUP_RCU)
 			goto out;
 
-		fm = get_fuse_mount(inode);
-
-		forget = fuse_alloc_forget();
-		ret = -ENOMEM;
-		if (!forget)
-			goto out;
-
-		attr_version = fuse_get_attr_version(fm->fc);
-
-		fuse_lookup_init(&args, get_node_id(dir), name, &outarg);
-		ret = fuse_simple_request(fm, &args);
-		/* Zero nodeid is same as -ENOENT */
-		if (!ret && !outarg.nodeid)
-			ret = -ENOENT;
-		if (!ret) {
-			fi = get_fuse_inode(inode);
-			if (outarg.nodeid != get_node_id(inode) ||
-			    (bool) IS_AUTOMOUNT(inode) != (bool) (outarg.attr.flags & FUSE_ATTR_SUBMOUNT)) {
-				fuse_chan_queue_forget(fm->fc->chan, forget,
-						  outarg.nodeid, 1);
-				goto invalid;
-			}
-			spin_lock(&fi->lock);
-			fi->nlookup++;
-			spin_unlock(&fi->lock);
-		}
-		kfree(forget);
-		if (ret == -ENOMEM || ret == -EINTR)
+		ret = fuse_revalidate_lookup(dir, name, entry);
+		if (ret <= 0)
 			goto out;
-		if (ret || fuse_invalid_attr(&outarg.attr) ||
-		    fuse_stale_inode(inode, outarg.generation, &outarg.attr))
-			goto invalid;
-
-		forget_all_cached_acls(inode);
-		fuse_change_attributes(inode, &outarg.attr, NULL,
-				       ATTR_TIMEOUT(&outarg),
-				       attr_version);
-		fuse_change_entry_timeout(entry, &outarg);
 	} else if (inode) {
 		fi = get_fuse_inode(inode);
 		if (flags & LOOKUP_RCU) {
@@ -467,6 +487,7 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
 			fuse_advise_use_readdirplus(dir);
 		}
 	}
+valid:
 	ret = 1;
 out:
 	return ret;
@@ -1018,6 +1039,146 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
 	return err;
 }
 
+/*
+ * Open a regular file whose dentry has expired with FUSE_OPEN_ATOMIC, which
+ * revalidates the name in the same request.  Returns 1 if the file still
+ * needs FUSE_OPEN, or -EOPENSTALE if the name no longer refers to it.
+ */
+int fuse_open_revalidate(struct file *file)
+{
+	struct dentry *entry = file->f_path.dentry;
+	struct inode *inode = d_inode(entry);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	struct fuse_conn *fc = fm->fc;
+	FUSE_ARGS(args);
+	struct fuse_forget_link *forget;
+	struct fuse_create_in inarg;
+	struct fuse_entry_out outentry;
+	struct fuse_open_out *outopenp;
+	struct name_snapshot name;
+	struct dentry *parent;
+	struct fuse_file *ff;
+	u64 attr_version;
+	int err;
+
+	if (fc->no_open_atomic || IS_ROOT(entry) || !S_ISREG(inode->i_mode) ||
+	    !time_before64(fuse_dentry_time(entry), get_jiffies_64()))
+		return 1;
+
+	forget = fuse_alloc_forget();
+	if (!forget)
+		return -ENOMEM;
+	ff = fuse_file_alloc(fm, true);
+	if (!ff) {
+		kfree(forget);
+		return -ENOMEM;
+	}
+
+	memset(&inarg, 0, sizeof(inarg));
+	memset(&outentry, 0, sizeof(outentry));
+	inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
+	inarg.mode = S_IFREG;
+	parent = dget_parent(entry);
+	take_dentry_name_snapshot(&name, entry);
+	args.opcode = FUSE_OPEN_ATOMIC;
+	args.nodeid = get_node_id(d_inode(parent));
+	args.in_numargs = 2;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	args.in_args[1].size = name.name.len + 1;
+	args.in_args[1].value = name.name.name;
+	args.out_numargs = 2;
+	args.out_args[0].size = sizeof(outentry);
+	args.out_args[0].value = &outentry;
+	outopenp = &ff->args->open_outarg;
+	args.out_args[1].size = sizeof(*outopenp);
+	args.out_args[1].value = outopenp;
+	args.out_argvar = true;
+
+	attr_version = fuse_get_attr_version(fc);
+	err = fuse_simple_request(fm, &args);
+	if (err == -ENOSYS) {
+		/* d_revalidate() skipped the LOOKUP, so send it here */
+		fc->no_open_atomic = 1;
+		err = fuse_revalidate_lookup(d_inode(parent), &name.name,
+					     entry);
+		if (!err) {
+			d_drop(entry);
+			err = -EOPENSTALE;
+		}
+		release_dentry_name_snapshot(&name);
+		dput(parent);
+		fuse_file_free(ff);
+		kfree(forget);
+		return err;
+	}
+	release_dentry_name_snapshot(&name);
+	dput(parent);
+
+	if (err == -ENOENT) {
+		d_drop(entry);
+		err = -EOPENSTALE;
+	}
+	if (err < 0)
+		goto out_free;
+
+	if (args.out_args[1].size) {
+		ff->fh = outopenp->fh;
+		ff->nodeid = outentry.nodeid;
+		ff->open_flags = outopenp->open_flags;
+	}
+
+	/* The retry looks the name up again */
+	err = -EOPENSTALE;
+	if (outentry.nodeid != get_node_id(inode) ||
+	    fuse_invalid_attr(&outentry.attr) ||
+	    fuse_stale_inode(inode, outentry.generation, &outentry.attr)) {
+		d_drop(entry);
+		goto out_release;
+	}
+
+	/* Only O_CREAT creates; O_TRUNC leaves the file unopened */
+	err = -EIO;
+	if (args.out_args[1].size &&
+	    (args.out_args[1].size != sizeof(*outopenp) ||
+	     (outopenp->open_flags & FOPEN_CREATED) ||
+	     (file->f_flags & O_TRUNC)))
+		goto out_release;
+
+	spin_lock(&fi->lock);
+	fi->nlookup++;
+	spin_unlock(&fi->lock);
+	kfree(forget);
+	forget_all_cached_acls(inode);
+	fuse_change_attributes(inode, &outentry.attr, NULL,
+			       ATTR_TIMEOUT(&outentry), attr_version);
+	fuse_change_entry_timeout(entry, &outentry);
+
+	if (!args.out_args[1].size) {
+		fuse_file_free(ff);
+		return 1;
+	}
+	file->private_data = ff;
+	return 0;
+
+out_release:
+	if (outentry.nodeid)
+		fuse_chan_queue_forget(fc->chan, forget, outentry.nodeid, 1);
+	else
+		kfree(forget);
+	if (args.out_args[1].size)
+		fuse_sync_release(NULL, ff, file->f_flags);
+	else
+		fuse_file_free(ff);
+	return err;
+
+out_free:
+	fuse_file_free(ff);
+	kfree(forget);
+	return err;
+}
+
 static int fuse_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
 		      umode_t, dev_t);
 static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6d707f2b3bff..8f4a14de760a 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -278,7 +278,9 @@ static int fuse_open(struct inode *inode, struct file *file)
 	if (is_wb_truncate || vdax_truncate)
 		fuse_set_nowrite(inode);
 
-	err = fuse_do_open(fm, get_node_id(inode), file, false);
+	err = fuse_open_revalidate(file);
+	if (err > 0)
+		err = fuse_do_open(fm, get_node_id(inode), file, false);
 	if (!err) {
 		ff = file->private_data;
 		err = fuse_finish_open(inode, file);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ba6dc4c43a1f..eabbb36c8dfd 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -954,6 +954,7 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
 struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release);
 void fuse_file_free(struct fuse_file *ff);
 int fuse_finish_open(struct inode *inode, struct file *file);
+int fuse_open_revalidate(struct file *file);
 
 void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
 		       unsigned int flags);
-- 
2.50.1

[PATCH 3/3] selftests/fuse: add test for FUSE_OPEN_ATOMIC

[jamz]

From: Jimmy Zuber <jamz@amazon.com>

Check the requests sent when opening and creating new, existing, missing
and expired names, against a raw /dev/fuse server with and without
FUSE_OPEN_ATOMIC, and that opening an existing read-only file is still
permission checked.

Assisted-by: Claude:claude-opus-5-5 [Claude-Code]
Signed-off-by: Jimmy Zuber <jamz@amazon.com>
---
 .../selftests/filesystems/fuse/.gitignore     |   1 +
 .../selftests/filesystems/fuse/Makefile       |   3 +-
 .../filesystems/fuse/atomic_open_test.c       | 473 ++++++++++++++++++
 3 files changed, 476 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/filesystems/fuse/atomic_open_test.c

diff --git a/tools/testing/selftests/filesystems/fuse/.gitignore b/tools/testing/selftests/filesystems/fuse/.gitignore
index b5b03db1118c..6e529fee96d4 100644
--- a/tools/testing/selftests/filesystems/fuse/.gitignore
+++ b/tools/testing/selftests/filesystems/fuse/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+atomic_open_test
 fuse_mnt
 fusectl_test
 test_syncfs
diff --git a/tools/testing/selftests/filesystems/fuse/Makefile b/tools/testing/selftests/filesystems/fuse/Makefile
index c2de8d225447..2fe20f0e9143 100644
--- a/tools/testing/selftests/filesystems/fuse/Makefile
+++ b/tools/testing/selftests/filesystems/fuse/Makefile
@@ -3,7 +3,7 @@
 CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
 
 TEST_GEN_PROGS := fusectl_test test_syncfs
-TEST_GEN_PROGS += write_extend_eof_test
+TEST_GEN_PROGS += write_extend_eof_test atomic_open_test
 TEST_GEN_FILES := fuse_mnt
 
 # fuse_acl_cache_test requires libfuse3; add it only when the library is present.
@@ -16,6 +16,7 @@ endif
 include ../../lib.mk
 
 $(OUTPUT)/write_extend_eof_test: LDLIBS += -lpthread
+$(OUTPUT)/atomic_open_test: LDLIBS += -lpthread
 
 VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null)
 ifeq ($(VAR_CFLAGS),)
diff --git a/tools/testing/selftests/filesystems/fuse/atomic_open_test.c b/tools/testing/selftests/filesystems/fuse/atomic_open_test.c
new file mode 100644
index 000000000000..880367d6cb96
--- /dev/null
+++ b/tools/testing/selftests/filesystems/fuse/atomic_open_test.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test open() and create with and without FUSE_OPEN_ATOMIC.
+ *
+ * Requires root to mount fuse.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <linux/fuse.h>
+
+#include "../../kselftest_harness.h"
+
+#define FUSE_ROOT_ID	1
+#define MAX_WRITE	(128 * 1024)
+#define MAX_ENTRIES	16
+#define NOBODY		65534
+
+struct entry {
+	char name[64];
+	uint64_t nodeid;
+	uint32_t mode;
+	uint64_t entry_valid;
+};
+
+/* Server state, shared with the responder thread. */
+struct server {
+	int fd;
+	int atomic;
+	struct entry ent[MAX_ENTRIES];
+	int nent;
+	int nr_lookup, nr_create, nr_open, nr_open_atomic, nr_setattr;
+};
+
+static void reply(int fd, uint64_t unique, int error, void *data, size_t len)
+{
+	struct fuse_out_header oh = {
+		.len = sizeof(oh) + (data ? len : 0),
+		.error = error,
+		.unique = unique,
+	};
+	struct iovec iov[2] = { { &oh, sizeof(oh) }, { data, len } };
+
+	/* Errors here are teardown races (device closed on unmount); ignore. */
+	if (writev(fd, iov, data ? 2 : 1) < 0)
+		return;
+}
+
+static struct entry *find(struct server *s, const char *name)
+{
+	int i;
+
+	for (i = 0; i < s->nent; i++)
+		if (!strcmp(s->ent[i].name, name))
+			return &s->ent[i];
+	return NULL;
+}
+
+static struct entry *add(struct server *s, const char *name, uint32_t mode)
+{
+	struct entry *e = &s->ent[s->nent];
+
+	snprintf(e->name, sizeof(e->name), "%.63s", name);
+	e->nodeid = FUSE_ROOT_ID + 1 + s->nent++;
+	e->mode = mode;
+	e->entry_valid = 3600;
+	return e;
+}
+
+/* A NULL entry is a negative entry, cached like a found one. */
+static void fill_entry(struct fuse_entry_out *out, struct entry *e)
+{
+	memset(out, 0, sizeof(*out));
+	out->entry_valid = e ? e->entry_valid : 3600;
+	if (!e)
+		return;
+	out->nodeid = e->nodeid;
+	out->attr_valid = 3600;
+	out->attr.ino = e->nodeid;
+	out->attr.mode = e->mode;
+	out->attr.nlink = S_ISDIR(e->mode) ? 2 : 1;
+	out->attr.blksize = 4096;
+}
+
+static void *server_thread(void *arg)
+{
+	struct server *s = arg;
+	static char buf[MAX_WRITE + 4096];
+
+	for (;;) {
+		ssize_t n = read(s->fd, buf, sizeof(buf));
+		struct fuse_in_header *ih = (void *)buf;
+
+		if (n < 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
+			return NULL;	/* device closed on unmount */
+		}
+		if (n < (ssize_t)sizeof(*ih))
+			continue;
+
+		switch (ih->opcode) {
+		case FUSE_INIT: {
+			struct fuse_init_in *in = (void *)(ih + 1);
+			struct fuse_init_out out = {0};
+
+			out.major = FUSE_KERNEL_VERSION;
+			out.minor = FUSE_KERNEL_MINOR_VERSION;
+			out.max_readahead = in->max_readahead;
+			out.max_write = MAX_WRITE;
+			out.max_background = 16;
+			out.congestion_threshold = 12;
+			out.flags = FUSE_INIT_EXT;
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_GETATTR:
+		case FUSE_SETATTR: {
+			struct fuse_attr_out out = {0};
+			struct fuse_entry_out eo;
+			int i;
+
+			if (ih->opcode == FUSE_SETATTR)
+				s->nr_setattr++;
+			out.attr_valid = 3600;
+			if (ih->nodeid == FUSE_ROOT_ID) {
+				out.attr.ino = FUSE_ROOT_ID;
+				out.attr.mode = S_IFDIR | 0777;
+				out.attr.nlink = 2;
+			}
+			for (i = 0; i < s->nent; i++) {
+				if (s->ent[i].nodeid == ih->nodeid) {
+					fill_entry(&eo, &s->ent[i]);
+					out.attr = eo.attr;
+				}
+			}
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_LOOKUP: {
+			struct fuse_entry_out out;
+
+			s->nr_lookup++;
+			fill_entry(&out, find(s, (char *)(ih + 1)));
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_CREATE:
+		case FUSE_OPEN_ATOMIC: {
+			struct fuse_create_in *in = (void *)(ih + 1);
+			const char *name = (char *)(in + 1);
+			struct entry *e = find(s, name);
+			struct {
+				struct fuse_entry_out entry;
+				struct fuse_open_out open;
+			} out = {0};
+
+			if (ih->opcode == FUSE_CREATE)
+				s->nr_create++;
+			else
+				s->nr_open_atomic++;
+			if (ih->opcode == FUSE_OPEN_ATOMIC && !s->atomic) {
+				reply(s->fd, ih->unique, -ENOSYS, NULL, 0);
+				break;
+			}
+			if (e && (in->flags & O_CREAT) &&
+			    (in->flags & O_EXCL)) {
+				reply(s->fd, ih->unique, -EEXIST, NULL, 0);
+				break;
+			}
+			if (!e && !(in->flags & O_CREAT)) {
+				fill_entry(&out.entry, NULL);
+				reply(s->fd, ih->unique, 0, &out.entry,
+				      sizeof(out.entry));
+				break;
+			}
+			if (e && (!S_ISREG(e->mode) || (in->flags & O_TRUNC))) {
+				fill_entry(&out.entry, e);
+				reply(s->fd, ih->unique, 0, &out.entry,
+				      sizeof(out.entry));
+				break;
+			}
+			if (!e) {
+				e = add(s, name, S_IFREG | in->mode);
+				if (ih->opcode == FUSE_OPEN_ATOMIC)
+					out.open.open_flags = FOPEN_CREATED;
+			}
+			fill_entry(&out.entry, e);
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_TMPFILE: {
+			struct fuse_create_in *in = (void *)(ih + 1);
+			struct entry e = {
+				.nodeid = 100,
+				.mode = S_IFREG | in->mode,
+				.entry_valid = 3600,
+			};
+			struct {
+				struct fuse_entry_out entry;
+				struct fuse_open_out open;
+			} out = {0};
+
+			fill_entry(&out.entry, &e);
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_OPEN: {
+			struct fuse_open_out out = {0};
+
+			s->nr_open++;
+			reply(s->fd, ih->unique, 0, &out, sizeof(out));
+			break;
+		}
+		case FUSE_FLUSH:
+		case FUSE_RELEASE:
+			reply(s->fd, ih->unique, 0, NULL, 0);
+			break;
+		case FUSE_FORGET:
+		case FUSE_BATCH_FORGET:
+			break;
+		default:
+			reply(s->fd, ih->unique, -EOPNOTSUPP, NULL, 0);
+			break;
+		}
+	}
+}
+
+FIXTURE(fuse)
+{
+	struct server *srv;
+	char dir[64];
+	int mounted;
+};
+
+FIXTURE_VARIANT(fuse)
+{
+	int atomic;
+};
+
+FIXTURE_VARIANT_ADD(fuse, atomic)
+{
+	.atomic = 1,
+};
+
+FIXTURE_VARIANT_ADD(fuse, plain)
+{
+	.atomic = 0,
+};
+
+FIXTURE_SETUP(fuse)
+{
+	char opts[128];
+	struct stat st;
+	pthread_t t;
+
+	if (geteuid() != 0)
+		SKIP(return, "need root to mount fuse");
+
+	self->srv = mmap(NULL, sizeof(*self->srv), PROT_READ | PROT_WRITE,
+			 MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, self->srv);
+	self->srv->atomic = variant->atomic;
+	add(self->srv, "ro", S_IFREG | 0444);
+	add(self->srv, "rw", S_IFREG | 0644);
+	add(self->srv, "stale", S_IFREG | 0644)->entry_valid = 0;
+
+	self->srv->fd = open("/dev/fuse", O_RDWR);
+	ASSERT_GE(self->srv->fd, 0);
+
+	strcpy(self->dir, "/tmp/fuse_aopen_XXXXXX");
+	ASSERT_NE(NULL, mkdtemp(self->dir));
+
+	snprintf(opts, sizeof(opts),
+		 "fd=%d,rootmode=40000,user_id=0,group_id=0,default_permissions,allow_other",
+		 self->srv->fd);
+	ASSERT_EQ(0, mount("fuse", self->dir, "fuse", 0, opts));
+	self->mounted = 1;
+
+	ASSERT_EQ(0, pthread_create(&t, NULL, server_thread, self->srv));
+	pthread_detach(t);
+
+	/* Wait for FUSE_INIT: the root GETATTR is queued behind it */
+	ASSERT_EQ(0, stat(self->dir, &st));
+}
+
+FIXTURE_TEARDOWN(fuse)
+{
+	if (self->mounted)
+		umount2(self->dir, MNT_DETACH);
+	if (self->srv && self->srv != MAP_FAILED) {
+		if (self->srv->fd > 0)
+			close(self->srv->fd);
+		munmap(self->srv, sizeof(*self->srv));
+	}
+	if (self->dir[0])
+		rmdir(self->dir);
+}
+
+/* Open @name as an unprivileged user and return the errno, or 0. */
+static int open_as_nobody(const char *dir, const char *name, int flags)
+{
+	char path[128];
+	int status, fd;
+	pid_t pid;
+
+	snprintf(path, sizeof(path), "%s/%s", dir, name);
+	pid = fork();
+	if (pid < 0)
+		return -1;
+	if (pid == 0) {
+		if (setgid(NOBODY) || setuid(NOBODY))
+			_exit(255);
+		fd = open(path, flags, 0644);
+		_exit(fd < 0 ? errno : 0);
+	}
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+static int open_at(const char *dir, const char *name, int flags)
+{
+	char path[128];
+
+	snprintf(path, sizeof(path), "%s/%s", dir, name);
+	return open(path, flags, 0644);
+}
+
+TEST_F(fuse, create_new)
+{
+	int fd;
+
+	fd = open_at(self->dir, "a", O_CREAT | O_WRONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	fd = open_at(self->dir, "b", O_CREAT | O_EXCL | O_WRONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	fd = open(self->dir, O_TMPFILE | O_RDWR, 0600);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	EXPECT_EQ(0, self->srv->nr_open);
+	if (variant->atomic) {
+		EXPECT_EQ(2, self->srv->nr_open_atomic);
+		EXPECT_EQ(0, self->srv->nr_lookup);
+		EXPECT_EQ(0, self->srv->nr_create);
+	} else {
+		EXPECT_EQ(1, self->srv->nr_open_atomic);
+		EXPECT_EQ(2, self->srv->nr_lookup);
+		EXPECT_EQ(2, self->srv->nr_create);
+	}
+}
+
+TEST_F(fuse, create_existing)
+{
+	int fd;
+
+	ASSERT_EQ(-1, open_at(self->dir, "ro", O_CREAT | O_EXCL | O_WRONLY));
+	ASSERT_EQ(EEXIST, errno);
+	ASSERT_EQ(EACCES, open_as_nobody(self->dir, "ro", O_CREAT | O_RDWR));
+
+	/* Truncation goes through FUSE_OPEN and SETATTR. */
+	fd = open_at(self->dir, "rw", O_CREAT | O_TRUNC | O_WRONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	EXPECT_EQ(0, self->srv->nr_create);
+	EXPECT_EQ(1, self->srv->nr_open);
+	EXPECT_EQ(1, self->srv->nr_setattr);
+	if (variant->atomic) {
+		EXPECT_EQ(3, self->srv->nr_open_atomic);
+		EXPECT_EQ(0, self->srv->nr_lookup);
+	} else {
+		EXPECT_EQ(1, self->srv->nr_open_atomic);
+		EXPECT_EQ(2, self->srv->nr_lookup);
+	}
+}
+
+TEST_F(fuse, open_existing)
+{
+	int fd;
+
+	ASSERT_EQ(EACCES, open_as_nobody(self->dir, "ro", O_RDWR));
+
+	fd = open_at(self->dir, "ro", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	ASSERT_EQ(-1, open_at(self->dir, "missing", O_RDONLY));
+	ASSERT_EQ(ENOENT, errno);
+	ASSERT_EQ(-1, open_at(self->dir, "missing", O_RDONLY));
+	ASSERT_EQ(ENOENT, errno);
+
+	EXPECT_EQ(1, self->srv->nr_open);
+	if (variant->atomic) {
+		EXPECT_EQ(2, self->srv->nr_open_atomic);
+		EXPECT_EQ(0, self->srv->nr_lookup);
+	} else {
+		EXPECT_EQ(1, self->srv->nr_open_atomic);
+		EXPECT_EQ(2, self->srv->nr_lookup);
+	}
+}
+
+TEST_F(fuse, open_stale)
+{
+	struct stat st;
+	int fd;
+
+	fd = open_at(self->dir, "stale", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	/* The entry has expired, the reopen checks the name. */
+	fd = open_at(self->dir, "stale", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	/* Another file takes the name: the open finds the new one. */
+	find(self->srv, "stale")->nodeid = 200;
+	fd = open_at(self->dir, "stale", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(0, fstat(fd, &st));
+	EXPECT_EQ(200, st.st_ino);
+	close(fd);
+
+	if (variant->atomic) {
+		EXPECT_EQ(4, self->srv->nr_open_atomic);
+		EXPECT_EQ(0, self->srv->nr_lookup);
+		EXPECT_EQ(0, self->srv->nr_open);
+	} else {
+		EXPECT_EQ(1, self->srv->nr_open_atomic);
+		EXPECT_EQ(4, self->srv->nr_lookup);
+		EXPECT_EQ(3, self->srv->nr_open);
+	}
+}
+
+TEST_F(fuse, open_stale_first)
+{
+	char path[128];
+	struct stat st;
+	int fd;
+
+	/* The first FUSE_OPEN_ATOMIC comes from reopening a cached name */
+	snprintf(path, sizeof(path), "%s/stale", self->dir);
+	ASSERT_EQ(0, stat(path, &st));
+	fd = open(path, O_RDONLY);
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	EXPECT_EQ(1, self->srv->nr_open_atomic);
+	if (variant->atomic) {
+		EXPECT_EQ(1, self->srv->nr_lookup);
+		EXPECT_EQ(0, self->srv->nr_open);
+	} else {
+		EXPECT_EQ(2, self->srv->nr_lookup);
+		EXPECT_EQ(1, self->srv->nr_open);
+	}
+}
+
+TEST_HARNESS_MAIN
-- 
2.50.1