[RFC PATCH 3/3] io_uring: set times inline when the filesystem cannot sleep

[Méven Car]

IORING_OP_UTIMENSAT always went to io-wq. On tmpfs the setattr only
changes the inode in memory, so the handoff to a worker cost more than
the work: 2000 files took 7 ms with utimensat(2) and 20 ms through the
ring.

Try the request inline first. The lookup uses LOOKUP_CACHED, and the
freeze protection and the inode lock are only tried, the former with
the new mnt_want_write_trylock(). A filesystem whose ->setattr() never
sleeps for a change of times alone says so with
FS_SETATTR_TIMES_NOWAIT, which tmpfs sets. Any other filesystem, an
uncached path, a contended lock or a delegation returns -EAGAIN, and
io_uring sends the request to io-wq as before.

Signed-off-by: Méven Car <meven@xxxxxxx>
---
 fs/internal.h      |  3 ++-
 fs/namespace.c     | 20 +++++++++++++++++++
 fs/utimes.c        | 48 +++++++++++++++++++++++++++++++++++++---------
 include/linux/fs.h |  1 +
 io_uring/fs.c      | 26 +++++++++++++++----------
 mm/shmem.c         |  3 ++-
 6 files changed, 80 insertions(+), 21 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 985b2bc5895e..e991b63bb714 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -64,7 +64,7 @@ int filename_symlinkat(struct filename *from, int newdfd, struct filename *to);
 int filename_linkat(int olddfd, struct filename *old, int newdfd,
 			struct filename *new, int flags);
 int filename_utimensat(int dfd, struct filename *name,
-		       struct timespec64 *times, int flags);
+		       struct timespec64 *times, int flags, bool nowait);
 int vfs_tmpfile(struct mnt_idmap *idmap,
 		const struct path *parentpath,
 		struct file *file, umode_t mode);
@@ -86,6 +86,7 @@ extern int sb_prepare_remount_readonly(struct super_block *);
 extern void __init mnt_init(void);
 
 int mnt_get_write_access_file(struct file *file);
+int mnt_want_write_trylock(struct vfsmount *m);
 void mnt_put_write_access_file(struct file *file);
 
 extern void dissolve_on_fput(struct vfsmount *);
diff --git a/fs/namespace.c b/fs/namespace.c
index ae5dc64f8b45..f4aadd4e1958 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -499,6 +499,26 @@ int mnt_want_write(struct vfsmount *m)
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
 
+/**
+ * mnt_want_write_trylock - get write access to a mount without waiting
+ * @m: the mount on which to take a write
+ *
+ * Like mnt_want_write(), but returns -EAGAIN instead of waiting when the
+ * filesystem is frozen.  When the write operation is finished,
+ * mnt_drop_write() must be called.
+ */
+int mnt_want_write_trylock(struct vfsmount *m)
+{
+	int ret;
+
+	if (!sb_start_write_trylock(m->mnt_sb))
+		return -EAGAIN;
+	ret = mnt_get_write_access(m);
+	if (ret)
+		sb_end_write(m->mnt_sb);
+	return ret;
+}
+
 /**
  * mnt_get_write_access_file - get write access to a file's mount
  * @file: the file who's mount on which to take a write
diff --git a/fs/utimes.c b/fs/utimes.c
index 8072f05ac8dc..f70ad9003fa9 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -18,7 +18,9 @@ static bool nsec_valid(long nsec)
 	return nsec >= 0 && nsec <= 999999999;
 }
 
-int vfs_utimes(const struct path *path, struct timespec64 *times)
+/* With @nowait, returns -EAGAIN instead of sleeping */
+static int __vfs_utimes(const struct path *path, struct timespec64 *times,
+			bool nowait)
 {
 	int error;
 	struct iattr newattrs;
@@ -34,9 +36,17 @@ int vfs_utimes(const struct path *path, struct timespec64 *times)
 			times = NULL;
 	}
 
-	error = mnt_want_write(path->mnt);
-	if (error)
-		goto out;
+	if (nowait) {
+		if (!(inode->i_sb->s_type->fs_flags & FS_SETATTR_TIMES_NOWAIT))
+			return -EAGAIN;
+		error = mnt_want_write_trylock(path->mnt);
+		if (error)
+			goto out;
+	} else {
+		error = mnt_want_write(path->mnt);
+		if (error)
+			goto out;
+	}
 
 	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
 	if (times) {
@@ -63,24 +73,40 @@ int vfs_utimes(const struct path *path, struct timespec64 *times)
 		newattrs.ia_valid |= ATTR_TOUCH;
 	}
 retry_deleg:
-	inode_lock(inode);
+	if (!nowait) {
+		inode_lock(inode);
+	} else if (!inode_trylock(inode)) {
+		error = -EAGAIN;
+		goto drop;
+	}
 	error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs,
 			      &delegated_inode);
 	inode_unlock(inode);
 	if (is_delegated(&delegated_inode)) {
+		if (nowait) {
+			iput(delegated_inode.di_inode);
+			delegated_inode.di_inode = NULL;
+			error = -EAGAIN;
+			goto drop;
+		}
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}
-
+drop:
 	mnt_drop_write(path->mnt);
 out:
 	return error;
 }
+
+int vfs_utimes(const struct path *path, struct timespec64 *times)
+{
+	return __vfs_utimes(path, times, false);
+}
 EXPORT_SYMBOL_GPL(vfs_utimes);
 
 int filename_utimensat(int dfd, struct filename *name,
-		       struct timespec64 *times, int flags)
+		       struct timespec64 *times, int flags, bool nowait)
 {
 	struct path path;
 	int lookup_flags = 0, error;
@@ -90,13 +116,17 @@ int filename_utimensat(int dfd, struct filename *name,
 
 	if (!(flags & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
+	if (nowait)
+		lookup_flags |= LOOKUP_CACHED;
 
 retry:
 	error = filename_lookup(dfd, name, lookup_flags, &path, NULL);
 	if (error)
 		return error;
-	error = vfs_utimes(&path, times);
+	error = __vfs_utimes(&path, times, nowait);
 	path_put(&path);
+	if (nowait && error == -ESTALE)
+		return -EAGAIN;
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
@@ -108,7 +138,7 @@ static int do_utimes_path(int dfd, const char __user *filename,
 		struct timespec64 *times, int flags)
 {
 	CLASS(filename_uflags, name)(filename, flags);
-	return filename_utimensat(dfd, name, times, flags);
+	return filename_utimensat(dfd, name, times, flags, false);
 }
 
 static int do_utimes_fd(int fd, struct timespec64 *times, int flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f9d1e05e8ae6..d1800fba15d8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2296,6 +2296,7 @@ struct file_system_type {
 #define FS_POWER_FREEZE		256	/* Always freeze on suspend/hibernate */
 #define FS_USERNS_MOUNT_RESTRICTED 512	/* Restrict mount in userns if not already visible */
 #define FS_USERNS_DELEGATABLE	1024	/* Can be mounted inside userns from outside */
+#define FS_SETATTR_TIMES_NOWAIT	2048	/* ->setattr() of times alone never sleeps */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/io_uring/fs.c b/io_uring/fs.c
index 85e0a1cb6b47..79f6f39ce267 100644
--- a/io_uring/fs.c
+++ b/io_uring/fs.c
@@ -356,38 +356,44 @@ int io_utimensat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		if (ut->dfd == AT_FDCWD)
 			return -EFAULT;
 		ut->flags |= IO_UTIMENSAT_NO_PATH;
-		goto out;
+		return 0;
 	}
 	err = delayed_getname_uflags(&ut->filename, fname, ut->flags);
 	if (unlikely(err))
 		return err;
 	req->flags |= REQ_F_NEED_CLEANUP;
-out:
-	req->flags |= REQ_F_FORCE_ASYNC;
 	return 0;
 }
 
-static int __io_utimensat(struct io_utimensat *ut, struct filename *name)
+static int __io_utimensat(struct io_utimensat *ut, struct filename *name,
+			  bool force_nonblock)
 {
 	int flags = ut->flags & (AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH);
 
-	return filename_utimensat(ut->dfd, name, ut->times, flags);
+	return filename_utimensat(ut->dfd, name, ut->times, flags,
+				  force_nonblock);
 }
 
 int io_utimensat(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_utimensat *ut = io_kiocb_to_cmd(req, struct io_utimensat);
+	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 	int ret = 0;
 
-	WARN_ON_ONCE((issue_flags & IO_URING_F_NONBLOCK) &&
-		     !(ut->flags & IO_UTIMENSAT_NOOP));
-
 	if (ut->flags & IO_UTIMENSAT_NO_PATH) {
 		CLASS(filename_kernel, name)("");
-		ret = __io_utimensat(ut, name);
+		ret = __io_utimensat(ut, name, force_nonblock);
+		if (ret == -EAGAIN && force_nonblock)
+			return -EAGAIN;
 	} else if (!(ut->flags & IO_UTIMENSAT_NOOP)) {
 		CLASS(filename_complete_delayed, name)(&ut->filename);
-		ret = __io_utimensat(ut, name);
+		ret = __io_utimensat(ut, name, force_nonblock);
+		if (ret == -EAGAIN && force_nonblock) {
+			ret = putname_to_delayed(&ut->filename,
+						 no_free_ptr(name));
+			if (likely(!ret))
+				return -EAGAIN;
+		}
 	}
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
diff --git a/mm/shmem.c b/mm/shmem.c
index 897fa2b61346..405b39fc5d0e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -5310,7 +5310,8 @@ static struct file_system_type shmem_fs_type = {
 	.parameters	= shmem_fs_parameters,
 #endif
 	.kill_sb	= kill_anon_super,
-	.fs_flags	= FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags	= FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME |
+			  FS_SETATTR_TIMES_NOWAIT,
 };
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_TMPFS)
-- 
2.56.0