[PATCH v6 0/9] io_uring: add mkdir and [sym]linkat support

[PATCH v6 0/9] io_uring: add mkdir and [sym]linkat support

[Dmitry Kadashev]

This started out as an attempt to add mkdirat support to io_uring which
is heavily based on renameat() / unlinkat() support.

During the review process more operations were added (linkat, symlinkat,
mknodat) mainly to keep things uniform internally (in namei.c), and
with things changed in namei.c adding support for these operations to
io_uring is trivial, so that was done too (except for mknodat). See
https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/

The first patch is preparation with no functional changes, makes
do_mkdirat accept struct filename pointer rather than the user string.

The second one leverages that to implement mkdirat in io_uring.

3-6 just convert other similar do_* functions in namei.c to accept
struct filename, for uniformity with do_mkdirat, do_renameat and
do_unlinkat. No functional changes there.

7 changes do_* helpers in namei.c to return ints rather than some of
them returning ints and some longs.

8-9 add symlinkat and linkat support to io_uring correspondingly.

Based on for-5.14/io_uring.

v6:

- rebase
- add safety checks for IOPOLL mode
- add safety checks for unused sqe parts
- drop mknodat support from io_uring as requested by Jens
- add Christian's Acked-by

v5:
- rebase
- add symlinkat, linkat and mknodat support to io_uring

v4:
- update do_mknodat, do_symlinkat and do_linkat to accept struct
  filename for uniformity with do_mkdirat, do_renameat and do_unlinkat;

v3:
- rebase;

v2:
- do not mess with struct filename's refcount in do_mkdirat, instead add
  and use __filename_create() that does not drop the name on success;

Dmitry Kadashev (9):
  fs: make do_mkdirat() take struct filename
  io_uring: add support for IORING_OP_MKDIRAT
  fs: make do_mknodat() take struct filename
  fs: make do_symlinkat() take struct filename
  namei: add getname_uflags()
  fs: make do_linkat() take struct filename
  fs: update do_*() helpers to return ints
  io_uring: add support for IORING_OP_SYMLINKAT
  io_uring: add support for IORING_OP_LINKAT

 fs/exec.c                     |   8 +-
 fs/internal.h                 |   8 +-
 fs/io_uring.c                 | 196 ++++++++++++++++++++++++++++++++++
 fs/namei.c                    | 137 ++++++++++++++++--------
 include/linux/fs.h            |   1 +
 include/uapi/linux/io_uring.h |   4 +
 6 files changed, 301 insertions(+), 53 deletions(-)

-- 
2.30.2

[PATCH v6 1/9] fs: make do_mkdirat() take struct filename

[Dmitry Kadashev]

Pass in the struct filename pointers instead of the user string, and
update the three callers to do the same. This is heavily based on
commit dbea8d345177 ("fs: make do_renameat2() take struct filename").

This behaves like do_unlinkat() and do_renameat2().

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h |  1 +
 fs/namei.c    | 22 ++++++++++++++++------
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 6aeae7ef3380..848e165ef0f1 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -77,6 +77,7 @@ long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct user_namespace *mnt_userns, struct path *link);
 int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
 		 struct filename *newname, unsigned int flags);
+long do_mkdirat(int dfd, struct filename *name, umode_t mode);
 
 /*
  * namespace.c
diff --git a/fs/namei.c b/fs/namei.c
index 79b0ff9b151e..49317c018341 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3556,7 +3556,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	return file;
 }
 
-static struct dentry *filename_create(int dfd, struct filename *name,
+static struct dentry *__filename_create(int dfd, struct filename *name,
 				struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
@@ -3612,7 +3612,6 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 		error = err2;
 		goto fail;
 	}
-	putname(name);
 	return dentry;
 fail:
 	dput(dentry);
@@ -3627,6 +3626,16 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	return dentry;
 }
 
+static inline struct dentry *filename_create(int dfd, struct filename *name,
+				struct path *path, unsigned int lookup_flags)
+{
+	struct dentry *res = __filename_create(dfd, name, path, lookup_flags);
+
+	if (!IS_ERR(res))
+		putname(name);
+	return res;
+}
+
 struct dentry *kern_path_create(int dfd, const char *pathname,
 				struct path *path, unsigned int lookup_flags)
 {
@@ -3817,7 +3826,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
-static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
+long do_mkdirat(int dfd, struct filename *name, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
@@ -3825,7 +3834,7 @@ static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
 	unsigned int lookup_flags = LOOKUP_DIRECTORY;
 
 retry:
-	dentry = user_path_create(dfd, pathname, &path, lookup_flags);
+	dentry = __filename_create(dfd, name, &path, lookup_flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -3843,17 +3852,18 @@ static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+	putname(name);
 	return error;
 }
 
 SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 {
-	return do_mkdirat(dfd, pathname, mode);
+	return do_mkdirat(dfd, getname(pathname), mode);
 }
 
 SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 {
-	return do_mkdirat(AT_FDCWD, pathname, mode);
+	return do_mkdirat(AT_FDCWD, getname(pathname), mode);
 }
 
 /**
-- 
2.30.2

[PATCH v6 2/9] io_uring: add support for IORING_OP_MKDIRAT

[Dmitry Kadashev]

IORING_OP_MKDIRAT behaves like mkdirat(2) and takes the same flags
and arguments.

Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/io_uring.c                 | 59 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 60 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e7997f9bf879..7aa08ed78452 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -673,6 +673,13 @@ struct io_unlink {
 	struct filename			*filename;
 };
 
+struct io_mkdir {
+	struct file			*file;
+	int				dfd;
+	umode_t				mode;
+	struct filename			*filename;
+};
+
 struct io_completion {
 	struct file			*file;
 	struct list_head		list;
@@ -825,6 +832,7 @@ struct io_kiocb {
 		struct io_shutdown	shutdown;
 		struct io_rename	rename;
 		struct io_unlink	unlink;
+		struct io_mkdir		mkdir;
 		/* use only after cleaning per-op data, see io_clean_op() */
 		struct io_completion	compl;
 	};
@@ -1039,6 +1047,7 @@ static const struct io_op_def io_op_defs[] = {
 	},
 	[IORING_OP_RENAMEAT] = {},
 	[IORING_OP_UNLINKAT] = {},
+	[IORING_OP_MKDIRAT] = {},
 };
 
 static bool io_disarm_next(struct io_kiocb *req);
@@ -3548,6 +3557,48 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static int io_mkdirat_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_mkdir *mkd = &req->mkdir;
+	const char __user *fname;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	mkd->dfd = READ_ONCE(sqe->fd);
+	mkd->mode = READ_ONCE(sqe->len);
+
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	mkd->filename = getname(fname);
+	if (IS_ERR(mkd->filename))
+		return PTR_ERR(mkd->filename);
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+static int io_mkdirat(struct io_kiocb *req, int issue_flags)
+{
+	struct io_mkdir *mkd = &req->mkdir;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_complete(req, ret);
+	return 0;
+}
+
 static int io_shutdown_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -5956,6 +6007,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_renameat_prep(req, sqe);
 	case IORING_OP_UNLINKAT:
 		return io_unlinkat_prep(req, sqe);
+	case IORING_OP_MKDIRAT:
+		return io_mkdirat_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6117,6 +6170,9 @@ static void io_clean_op(struct io_kiocb *req)
 		case IORING_OP_UNLINKAT:
 			putname(req->unlink.filename);
 			break;
+		case IORING_OP_MKDIRAT:
+			putname(req->mkdir.filename);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -6245,6 +6301,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_UNLINKAT:
 		ret = io_unlinkat(req, issue_flags);
 		break;
+	case IORING_OP_MKDIRAT:
+		ret = io_mkdirat(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index f1f9ac114b51..49a24a149eeb 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -137,6 +137,7 @@ enum {
 	IORING_OP_SHUTDOWN,
 	IORING_OP_RENAMEAT,
 	IORING_OP_UNLINKAT,
+	IORING_OP_MKDIRAT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

[PATCH v6 3/9] fs: make do_mknodat() take struct filename

[Dmitry Kadashev]

Pass in the struct filename pointers instead of the user string, for
uniformity with the recently converted do_unlinkat(), do_renameat(),
do_mkdirat().

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210330071700.kpjoyp5zlni7uejm@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/namei.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 49317c018341..9fc981e28788 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3724,7 +3724,7 @@ static int may_mknod(umode_t mode)
 	}
 }
 
-static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+static long do_mknodat(int dfd, struct filename *name, umode_t mode,
 		unsigned int dev)
 {
 	struct user_namespace *mnt_userns;
@@ -3735,9 +3735,9 @@ static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 
 	error = may_mknod(mode);
 	if (error)
-		return error;
+		goto out1;
 retry:
-	dentry = user_path_create(dfd, filename, &path, lookup_flags);
+	dentry = __filename_create(dfd, name, &path, lookup_flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -3745,7 +3745,7 @@ static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 		mode &= ~current_umask();
 	error = security_path_mknod(&path, dentry, mode, dev);
 	if (error)
-		goto out;
+		goto out2;
 
 	mnt_userns = mnt_user_ns(path.mnt);
 	switch (mode & S_IFMT) {
@@ -3764,24 +3764,27 @@ static long do_mknodat(int dfd, const char __user *filename, umode_t mode,
 					  dentry, mode, 0);
 			break;
 	}
-out:
+out2:
 	done_path_create(&path, dentry);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+out1:
+	if (!IS_ERR(name))
+		putname(name);
 	return error;
 }
 
 SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 		unsigned int, dev)
 {
-	return do_mknodat(dfd, filename, mode, dev);
+	return do_mknodat(dfd, getname(filename), mode, dev);
 }
 
 SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
 {
-	return do_mknodat(AT_FDCWD, filename, mode, dev);
+	return do_mknodat(AT_FDCWD, getname(filename), mode, dev);
 }
 
 /**
-- 
2.30.2

[PATCH v6 4/9] fs: make do_symlinkat() take struct filename

[Dmitry Kadashev]

Pass in the struct filename pointers instead of the user string, for
uniformity with the recently converted do_mkdnodat(), do_unlinkat(),
do_renameat(), do_mkdirat().

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210330071700.kpjoyp5zlni7uejm@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/namei.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 9fc981e28788..76572d703e82 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4189,23 +4189,23 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-static long do_symlinkat(const char __user *oldname, int newdfd,
-		  const char __user *newname)
+static long do_symlinkat(struct filename *from, int newdfd,
+		  struct filename *to)
 {
 	int error;
-	struct filename *from;
 	struct dentry *dentry;
 	struct path path;
 	unsigned int lookup_flags = 0;
 
-	from = getname(oldname);
-	if (IS_ERR(from))
-		return PTR_ERR(from);
+	if (IS_ERR(from)) {
+		error = PTR_ERR(from);
+		goto out_putboth;
+	}
 retry:
-	dentry = user_path_create(newdfd, newname, &path, lookup_flags);
+	dentry = __filename_create(newdfd, to, &path, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
-		goto out_putname;
+		goto out_putfrom;
 
 	error = security_path_symlink(&path, dentry, from->name);
 	if (!error) {
@@ -4220,20 +4220,24 @@ static long do_symlinkat(const char __user *oldname, int newdfd,
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
-out_putname:
-	putname(from);
+out_putboth:
+	if (!IS_ERR(to))
+		putname(to);
+out_putfrom:
+	if (!IS_ERR(from))
+		putname(from);
 	return error;
 }
 
 SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
 {
-	return do_symlinkat(oldname, newdfd, newname);
+	return do_symlinkat(getname(oldname), newdfd, getname(newname));
 }
 
 SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
 {
-	return do_symlinkat(oldname, AT_FDCWD, newname);
+	return do_symlinkat(getname(oldname), AT_FDCWD, getname(newname));
 }
 
 /**
-- 
2.30.2

[PATCH v6 5/9] namei: add getname_uflags()

[Dmitry Kadashev]

There are a couple of places where we already open-code the (flags &
AT_EMPTY_PATH) check and io_uring will likely add another one in the
future.  Let's just add a simple helper getname_uflags() that handles
this directly and use it.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210415100815.edrn4a7cy26wkowe@wittgenstein/
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/exec.c          | 8 ++------
 fs/namei.c         | 8 ++++++++
 include/linux/fs.h | 1 +
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 18594f11c31f..df33ecaf2111 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2069,10 +2069,8 @@ SYSCALL_DEFINE5(execveat,
 		const char __user *const __user *, envp,
 		int, flags)
 {
-	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
-
 	return do_execveat(fd,
-			   getname_flags(filename, lookup_flags, NULL),
+			   getname_uflags(filename, flags),
 			   argv, envp, flags);
 }
 
@@ -2090,10 +2088,8 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
 		       const compat_uptr_t __user *, envp,
 		       int,  flags)
 {
-	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
-
 	return compat_do_execveat(fd,
-				  getname_flags(filename, lookup_flags, NULL),
+				  getname_uflags(filename, flags),
 				  argv, envp, flags);
 }
 #endif
diff --git a/fs/namei.c b/fs/namei.c
index 76572d703e82..010455938826 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -203,6 +203,14 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	return result;
 }
 
+struct filename *
+getname_uflags(const char __user *filename, int uflags)
+{
+	int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+	return getname_flags(filename, flags, NULL);
+}
+
 struct filename *
 getname(const char __user * filename)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c3c88fdb9b2a..5885a68d2c12 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2781,6 +2781,7 @@ static inline struct file *file_clone_open(struct file *file)
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
+extern struct filename *getname_uflags(const char __user *, int);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 extern void putname(struct filename *name);
-- 
2.30.2

[PATCH v6 6/9] fs: make do_linkat() take struct filename

[Dmitry Kadashev]

Pass in the struct filename pointers instead of the user string, for
uniformity with do_renameat2, do_unlinkat, do_mknodat, etc.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210330071700.kpjoyp5zlni7uejm@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/namei.c | 59 +++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 41 insertions(+), 18 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 010455938826..07b1619dd343 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2447,7 +2447,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	return err;
 }
 
-int filename_lookup(int dfd, struct filename *name, unsigned flags,
+static int __filename_lookup(int dfd, struct filename *name, unsigned flags,
 		    struct path *path, struct path *root)
 {
 	int retval;
@@ -2469,7 +2469,18 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags,
 		audit_inode(name, path->dentry,
 			    flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0);
 	restore_nameidata();
-	putname(name);
+	if (retval)
+		putname(name);
+	return retval;
+}
+
+int filename_lookup(int dfd, struct filename *name, unsigned flags,
+		    struct path *path, struct path *root)
+{
+	int retval = __filename_lookup(dfd, name, flags, path, root);
+
+	if (!retval)
+		putname(name);
 	return retval;
 }
 
@@ -4346,8 +4357,8 @@ EXPORT_SYMBOL(vfs_link);
  * with linux 2.0, and to avoid hard-linking to directories
  * and other special files.  --ADM
  */
-static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
-	      const char __user *newname, int flags)
+static int do_linkat(int olddfd, struct filename *old, int newdfd,
+	      struct filename *new, int flags)
 {
 	struct user_namespace *mnt_userns;
 	struct dentry *new_dentry;
@@ -4356,31 +4367,36 @@ static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
 	int how = 0;
 	int error;
 
-	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
-		return -EINVAL;
+	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) {
+		error = -EINVAL;
+		goto out_putnames;
+	}
 	/*
 	 * To use null names we require CAP_DAC_READ_SEARCH
 	 * This ensures that not everyone will be able to create
 	 * handlink using the passed filedescriptor.
 	 */
-	if (flags & AT_EMPTY_PATH) {
-		if (!capable(CAP_DAC_READ_SEARCH))
-			return -ENOENT;
-		how = LOOKUP_EMPTY;
+	if (flags & AT_EMPTY_PATH && !capable(CAP_DAC_READ_SEARCH)) {
+		error = -ENOENT;
+		goto out_putnames;
 	}
 
 	if (flags & AT_SYMLINK_FOLLOW)
 		how |= LOOKUP_FOLLOW;
 retry:
-	error = user_path_at(olddfd, oldname, how, &old_path);
+	error = __filename_lookup(olddfd, old, how, &old_path, NULL);
 	if (error)
-		return error;
+		goto out_putnew;
 
-	new_dentry = user_path_create(newdfd, newname, &new_path,
+	new_dentry = __filename_create(newdfd, new, &new_path,
 					(how & LOOKUP_REVAL));
 	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry))
-		goto out;
+	if (IS_ERR(new_dentry)) {
+		// On error `new` is freed by __filename_create, prevent extra freeing
+		// below
+		new = ERR_PTR(error);
+		goto out_putpath;
+	}
 
 	error = -EXDEV;
 	if (old_path.mnt != new_path.mnt)
@@ -4408,8 +4424,14 @@ static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
 		how |= LOOKUP_REVAL;
 		goto retry;
 	}
-out:
+out_putpath:
 	path_put(&old_path);
+out_putnames:
+	if (!IS_ERR(old))
+		putname(old);
+out_putnew:
+	if (!IS_ERR(new))
+		putname(new);
 
 	return error;
 }
@@ -4417,12 +4439,13 @@ static int do_linkat(int olddfd, const char __user *oldname, int newdfd,
 SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname, int, flags)
 {
-	return do_linkat(olddfd, oldname, newdfd, newname, flags);
+	return do_linkat(olddfd, getname_uflags(oldname, flags),
+		newdfd, getname(newname), flags);
 }
 
 SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
 {
-	return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+	return do_linkat(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0);
 }
 
 /**
-- 
2.30.2

[PATCH v6 7/9] fs: update do_*() helpers to return ints

[Dmitry Kadashev]

Update the following to return int rather than long, for uniformity with
the rest of the do_* helpers in namei.c:

* do_rmdir()
* do_unlinkat()
* do_mkdirat()
* do_mknodat()
* do_symlinkat()

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210514143202.dmzfcgz5hnauy7ze@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h |  6 +++---
 fs/namei.c    | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 848e165ef0f1..207a455e32d3 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -72,12 +72,12 @@ extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
 			   struct path *path, struct path *root);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
-long do_rmdir(int dfd, struct filename *name);
-long do_unlinkat(int dfd, struct filename *name);
+int do_rmdir(int dfd, struct filename *name);
+int do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct user_namespace *mnt_userns, struct path *link);
 int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
 		 struct filename *newname, unsigned int flags);
-long do_mkdirat(int dfd, struct filename *name, umode_t mode);
+int do_mkdirat(int dfd, struct filename *name, umode_t mode);
 
 /*
  * namespace.c
diff --git a/fs/namei.c b/fs/namei.c
index 07b1619dd343..f99de6e294ad 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3743,7 +3743,7 @@ static int may_mknod(umode_t mode)
 	}
 }
 
-static long do_mknodat(int dfd, struct filename *name, umode_t mode,
+static int do_mknodat(int dfd, struct filename *name, umode_t mode,
 		unsigned int dev)
 {
 	struct user_namespace *mnt_userns;
@@ -3848,7 +3848,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
-long do_mkdirat(int dfd, struct filename *name, umode_t mode)
+int do_mkdirat(int dfd, struct filename *name, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
@@ -3943,7 +3943,7 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_rmdir);
 
-long do_rmdir(int dfd, struct filename *name)
+int do_rmdir(int dfd, struct filename *name)
 {
 	struct user_namespace *mnt_userns;
 	int error = 0;
@@ -4081,7 +4081,7 @@ EXPORT_SYMBOL(vfs_unlink);
  * writeout happening, and we don't want to prevent access to the directory
  * while waiting on the I/O.
  */
-long do_unlinkat(int dfd, struct filename *name)
+int do_unlinkat(int dfd, struct filename *name)
 {
 	int error;
 	struct dentry *dentry;
@@ -4208,7 +4208,7 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-static long do_symlinkat(struct filename *from, int newdfd,
+static int do_symlinkat(struct filename *from, int newdfd,
 		  struct filename *to)
 {
 	int error;
-- 
2.30.2

[PATCH v6 8/9] io_uring: add support for IORING_OP_SYMLINKAT

[Dmitry Kadashev]

IORING_OP_SYMLINKAT behaves like symlinkat(2) and takes the same flags
and arguments.

Suggested-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h                 |  1 +
 fs/io_uring.c                 | 66 +++++++++++++++++++++++++++++++++++
 fs/namei.c                    |  3 +-
 include/uapi/linux/io_uring.h |  1 +
 4 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 207a455e32d3..3b3954214385 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -78,6 +78,7 @@ int may_linkat(struct user_namespace *mnt_userns, struct path *link);
 int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
 		 struct filename *newname, unsigned int flags);
 int do_mkdirat(int dfd, struct filename *name, umode_t mode);
+int do_symlinkat(struct filename *from, int newdfd, struct filename *to);
 
 /*
  * namespace.c
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7aa08ed78452..c161f06a3cea 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -680,6 +680,13 @@ struct io_mkdir {
 	struct filename			*filename;
 };
 
+struct io_symlink {
+	struct file			*file;
+	int				new_dfd;
+	struct filename			*oldpath;
+	struct filename			*newpath;
+};
+
 struct io_completion {
 	struct file			*file;
 	struct list_head		list;
@@ -833,6 +840,7 @@ struct io_kiocb {
 		struct io_rename	rename;
 		struct io_unlink	unlink;
 		struct io_mkdir		mkdir;
+		struct io_symlink	symlink;
 		/* use only after cleaning per-op data, see io_clean_op() */
 		struct io_completion	compl;
 	};
@@ -1048,6 +1056,7 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_RENAMEAT] = {},
 	[IORING_OP_UNLINKAT] = {},
 	[IORING_OP_MKDIRAT] = {},
+	[IORING_OP_SYMLINKAT] = {},
 };
 
 static bool io_disarm_next(struct io_kiocb *req);
@@ -3599,6 +3608,54 @@ static int io_mkdirat(struct io_kiocb *req, int issue_flags)
 	return 0;
 }
 
+static int io_symlinkat_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_symlink *sl = &req->symlink;
+	const char __user *oldpath, *newpath;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	sl->new_dfd = READ_ONCE(sqe->fd);
+	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+
+	sl->oldpath = getname(oldpath);
+	if (IS_ERR(sl->oldpath))
+		return PTR_ERR(sl->oldpath);
+
+	sl->newpath = getname(newpath);
+	if (IS_ERR(sl->newpath)) {
+		putname(sl->oldpath);
+		return PTR_ERR(sl->newpath);
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+static int io_symlinkat(struct io_kiocb *req, int issue_flags)
+{
+	struct io_symlink *sl = &req->symlink;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_complete(req, ret);
+	return 0;
+}
+
 static int io_shutdown_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -6009,6 +6066,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_unlinkat_prep(req, sqe);
 	case IORING_OP_MKDIRAT:
 		return io_mkdirat_prep(req, sqe);
+	case IORING_OP_SYMLINKAT:
+		return io_symlinkat_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6173,6 +6232,10 @@ static void io_clean_op(struct io_kiocb *req)
 		case IORING_OP_MKDIRAT:
 			putname(req->mkdir.filename);
 			break;
+		case IORING_OP_SYMLINKAT:
+			putname(req->symlink.oldpath);
+			putname(req->symlink.newpath);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -6304,6 +6367,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_MKDIRAT:
 		ret = io_mkdirat(req, issue_flags);
 		break;
+	case IORING_OP_SYMLINKAT:
+		ret = io_symlinkat(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/fs/namei.c b/fs/namei.c
index f99de6e294ad..f5b0379d2f8c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4208,8 +4208,7 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_symlink);
 
-static int do_symlinkat(struct filename *from, int newdfd,
-		  struct filename *to)
+int do_symlinkat(struct filename *from, int newdfd, struct filename *to)
 {
 	int error;
 	struct dentry *dentry;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 49a24a149eeb..796f37ab4ce3 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -138,6 +138,7 @@ enum {
 	IORING_OP_RENAMEAT,
 	IORING_OP_UNLINKAT,
 	IORING_OP_MKDIRAT,
+	IORING_OP_SYMLINKAT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

[PATCH v6 9/9] io_uring: add support for IORING_OP_LINKAT

[Dmitry Kadashev]

IORING_OP_LINKAT behaves like linkat(2) and takes the same flags and
arguments.

In some internal places 'hardlink' is used instead of 'link' to avoid
confusion with the SQE links. Name 'link' conflicts with the existing
'link' member of io_kiocb.

Suggested-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/
Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h                 |  2 +
 fs/io_uring.c                 | 71 +++++++++++++++++++++++++++++++++++
 fs/namei.c                    |  2 +-
 include/uapi/linux/io_uring.h |  2 +
 4 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/fs/internal.h b/fs/internal.h
index 3b3954214385..15a7d210cc67 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -79,6 +79,8 @@ int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
 		 struct filename *newname, unsigned int flags);
 int do_mkdirat(int dfd, struct filename *name, umode_t mode);
 int do_symlinkat(struct filename *from, int newdfd, struct filename *to);
+int do_linkat(int olddfd, struct filename *old, int newdfd,
+			struct filename *new, int flags);
 
 /*
  * namespace.c
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c161f06a3cea..14a90e4e4149 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -687,6 +687,15 @@ struct io_symlink {
 	struct filename			*newpath;
 };
 
+struct io_hardlink {
+	struct file			*file;
+	int				old_dfd;
+	int				new_dfd;
+	struct filename			*oldpath;
+	struct filename			*newpath;
+	int				flags;
+};
+
 struct io_completion {
 	struct file			*file;
 	struct list_head		list;
@@ -841,6 +850,7 @@ struct io_kiocb {
 		struct io_unlink	unlink;
 		struct io_mkdir		mkdir;
 		struct io_symlink	symlink;
+		struct io_hardlink	hardlink;
 		/* use only after cleaning per-op data, see io_clean_op() */
 		struct io_completion	compl;
 	};
@@ -1057,6 +1067,7 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_UNLINKAT] = {},
 	[IORING_OP_MKDIRAT] = {},
 	[IORING_OP_SYMLINKAT] = {},
+	[IORING_OP_LINKAT] = {},
 };
 
 static bool io_disarm_next(struct io_kiocb *req);
@@ -3656,6 +3667,57 @@ static int io_symlinkat(struct io_kiocb *req, int issue_flags)
 	return 0;
 }
 
+static int io_linkat_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_hardlink *lnk = &req->hardlink;
+	const char __user *oldf, *newf;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	lnk->old_dfd = READ_ONCE(sqe->fd);
+	lnk->new_dfd = READ_ONCE(sqe->len);
+	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	lnk->flags = READ_ONCE(sqe->hardlink_flags);
+
+	lnk->oldpath = getname(oldf);
+	if (IS_ERR(lnk->oldpath))
+		return PTR_ERR(lnk->oldpath);
+
+	lnk->newpath = getname(newf);
+	if (IS_ERR(lnk->newpath)) {
+		putname(lnk->oldpath);
+		return PTR_ERR(lnk->newpath);
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+static int io_linkat(struct io_kiocb *req, int issue_flags)
+{
+	struct io_hardlink *lnk = &req->hardlink;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
+				lnk->newpath, lnk->flags);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_complete(req, ret);
+	return 0;
+}
+
 static int io_shutdown_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -6068,6 +6130,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_mkdirat_prep(req, sqe);
 	case IORING_OP_SYMLINKAT:
 		return io_symlinkat_prep(req, sqe);
+	case IORING_OP_LINKAT:
+		return io_linkat_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6236,6 +6300,10 @@ static void io_clean_op(struct io_kiocb *req)
 			putname(req->symlink.oldpath);
 			putname(req->symlink.newpath);
 			break;
+		case IORING_OP_LINKAT:
+			putname(req->hardlink.oldpath);
+			putname(req->hardlink.newpath);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -6370,6 +6438,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_SYMLINKAT:
 		ret = io_symlinkat(req, issue_flags);
 		break;
+	case IORING_OP_LINKAT:
+		ret = io_linkat(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/fs/namei.c b/fs/namei.c
index f5b0379d2f8c..b85e457c43b7 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4356,7 +4356,7 @@ EXPORT_SYMBOL(vfs_link);
  * with linux 2.0, and to avoid hard-linking to directories
  * and other special files.  --ADM
  */
-static int do_linkat(int olddfd, struct filename *old, int newdfd,
+int do_linkat(int olddfd, struct filename *old, int newdfd,
 	      struct filename *new, int flags)
 {
 	struct user_namespace *mnt_userns;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 796f37ab4ce3..c735fc22e459 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -44,6 +44,7 @@ struct io_uring_sqe {
 		__u32		splice_flags;
 		__u32		rename_flags;
 		__u32		unlink_flags;
+		__u32		hardlink_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -139,6 +140,7 @@ enum {
 	IORING_OP_UNLINKAT,
 	IORING_OP_MKDIRAT,
 	IORING_OP_SYMLINKAT,
+	IORING_OP_LINKAT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

Re: [PATCH v6 2/9] io_uring: add support for IORING_OP_MKDIRAT

[Pavel Begunkov]

On 6/24/21 12:14 PM, Dmitry Kadashev wrote:
> IORING_OP_MKDIRAT behaves like mkdirat(2) and takes the same flags
> and arguments.

io_uring part looks good, great finally see it taken.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

> 
> Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
> Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
> ---
>  fs/io_uring.c                 | 59 +++++++++++++++++++++++++++++++++++
>  include/uapi/linux/io_uring.h |  1 +
>  2 files changed, 60 insertions(+)
> 
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index e7997f9bf879..7aa08ed78452 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -673,6 +673,13 @@ struct io_unlink {
>  	struct filename			*filename;
>  };
>  
> +struct io_mkdir {
> +	struct file			*file;
> +	int				dfd;
> +	umode_t				mode;
> +	struct filename			*filename;
> +};
> +
>  struct io_completion {
>  	struct file			*file;
>  	struct list_head		list;
> @@ -825,6 +832,7 @@ struct io_kiocb {
>  		struct io_shutdown	shutdown;
>  		struct io_rename	rename;
>  		struct io_unlink	unlink;
> +		struct io_mkdir		mkdir;
>  		/* use only after cleaning per-op data, see io_clean_op() */
>  		struct io_completion	compl;
>  	};
> @@ -1039,6 +1047,7 @@ static const struct io_op_def io_op_defs[] = {
>  	},
>  	[IORING_OP_RENAMEAT] = {},
>  	[IORING_OP_UNLINKAT] = {},
> +	[IORING_OP_MKDIRAT] = {},
>  };
>  
>  static bool io_disarm_next(struct io_kiocb *req);
> @@ -3548,6 +3557,48 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
>  	return 0;
>  }
>  
> +static int io_mkdirat_prep(struct io_kiocb *req,
> +			    const struct io_uring_sqe *sqe)
> +{
> +	struct io_mkdir *mkd = &req->mkdir;
> +	const char __user *fname;
> +
> +	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
> +		return -EINVAL;
> +	if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index)
> +		return -EINVAL;
> +	if (unlikely(req->flags & REQ_F_FIXED_FILE))
> +		return -EBADF;
> +
> +	mkd->dfd = READ_ONCE(sqe->fd);
> +	mkd->mode = READ_ONCE(sqe->len);
> +
> +	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
> +	mkd->filename = getname(fname);
> +	if (IS_ERR(mkd->filename))
> +		return PTR_ERR(mkd->filename);
> +
> +	req->flags |= REQ_F_NEED_CLEANUP;
> +	return 0;
> +}
> +
> +static int io_mkdirat(struct io_kiocb *req, int issue_flags)
> +{
> +	struct io_mkdir *mkd = &req->mkdir;
> +	int ret;
> +
> +	if (issue_flags & IO_URING_F_NONBLOCK)
> +		return -EAGAIN;
> +
> +	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
> +
> +	req->flags &= ~REQ_F_NEED_CLEANUP;
> +	if (ret < 0)
> +		req_set_fail(req);
> +	io_req_complete(req, ret);
> +	return 0;
> +}
> +
>  static int io_shutdown_prep(struct io_kiocb *req,
>  			    const struct io_uring_sqe *sqe)
>  {
> @@ -5956,6 +6007,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  		return io_renameat_prep(req, sqe);
>  	case IORING_OP_UNLINKAT:
>  		return io_unlinkat_prep(req, sqe);
> +	case IORING_OP_MKDIRAT:
> +		return io_mkdirat_prep(req, sqe);
>  	}
>  
>  	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
> @@ -6117,6 +6170,9 @@ static void io_clean_op(struct io_kiocb *req)
>  		case IORING_OP_UNLINKAT:
>  			putname(req->unlink.filename);
>  			break;
> +		case IORING_OP_MKDIRAT:
> +			putname(req->mkdir.filename);
> +			break;
>  		}
>  	}
>  	if ((req->flags & REQ_F_POLLED) && req->apoll) {
> @@ -6245,6 +6301,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
>  	case IORING_OP_UNLINKAT:
>  		ret = io_unlinkat(req, issue_flags);
>  		break;
> +	case IORING_OP_MKDIRAT:
> +		ret = io_mkdirat(req, issue_flags);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  		break;
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index f1f9ac114b51..49a24a149eeb 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -137,6 +137,7 @@ enum {
>  	IORING_OP_SHUTDOWN,
>  	IORING_OP_RENAMEAT,
>  	IORING_OP_UNLINKAT,
> +	IORING_OP_MKDIRAT,
>  
>  	/* this goes last, obviously */
>  	IORING_OP_LAST,
> 

-- 
Pavel Begunkov

Re: [PATCH v6 8/9] io_uring: add support for IORING_OP_SYMLINKAT

[Pavel Begunkov]

On 6/24/21 12:14 PM, Dmitry Kadashev wrote:
> IORING_OP_SYMLINKAT behaves like symlinkat(2) and takes the same flags
> and arguments.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

> 
> Suggested-by: Christian Brauner <christian.brauner@ubuntu.com>
> Link: https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/
> Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
> Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
> ---
>  fs/internal.h                 |  1 +
>  fs/io_uring.c                 | 66 +++++++++++++++++++++++++++++++++++
>  fs/namei.c                    |  3 +-
>  include/uapi/linux/io_uring.h |  1 +
>  4 files changed, 69 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/internal.h b/fs/internal.h
> index 207a455e32d3..3b3954214385 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -78,6 +78,7 @@ int may_linkat(struct user_namespace *mnt_userns, struct path *link);
>  int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
>  		 struct filename *newname, unsigned int flags);
>  int do_mkdirat(int dfd, struct filename *name, umode_t mode);
> +int do_symlinkat(struct filename *from, int newdfd, struct filename *to);
>  
>  /*
>   * namespace.c
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 7aa08ed78452..c161f06a3cea 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -680,6 +680,13 @@ struct io_mkdir {
>  	struct filename			*filename;
>  };
>  
> +struct io_symlink {
> +	struct file			*file;
> +	int				new_dfd;
> +	struct filename			*oldpath;
> +	struct filename			*newpath;
> +};
> +
>  struct io_completion {
>  	struct file			*file;
>  	struct list_head		list;
> @@ -833,6 +840,7 @@ struct io_kiocb {
>  		struct io_rename	rename;
>  		struct io_unlink	unlink;
>  		struct io_mkdir		mkdir;
> +		struct io_symlink	symlink;
>  		/* use only after cleaning per-op data, see io_clean_op() */
>  		struct io_completion	compl;
>  	};
> @@ -1048,6 +1056,7 @@ static const struct io_op_def io_op_defs[] = {
>  	[IORING_OP_RENAMEAT] = {},
>  	[IORING_OP_UNLINKAT] = {},
>  	[IORING_OP_MKDIRAT] = {},
> +	[IORING_OP_SYMLINKAT] = {},
>  };
>  
>  static bool io_disarm_next(struct io_kiocb *req);
> @@ -3599,6 +3608,54 @@ static int io_mkdirat(struct io_kiocb *req, int issue_flags)
>  	return 0;
>  }
>  
> +static int io_symlinkat_prep(struct io_kiocb *req,
> +			    const struct io_uring_sqe *sqe)
> +{
> +	struct io_symlink *sl = &req->symlink;
> +	const char __user *oldpath, *newpath;
> +
> +	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
> +		return -EINVAL;
> +	if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index)
> +		return -EINVAL;
> +	if (unlikely(req->flags & REQ_F_FIXED_FILE))
> +		return -EBADF;
> +
> +	sl->new_dfd = READ_ONCE(sqe->fd);
> +	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
> +	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
> +
> +	sl->oldpath = getname(oldpath);
> +	if (IS_ERR(sl->oldpath))
> +		return PTR_ERR(sl->oldpath);
> +
> +	sl->newpath = getname(newpath);
> +	if (IS_ERR(sl->newpath)) {
> +		putname(sl->oldpath);
> +		return PTR_ERR(sl->newpath);
> +	}
> +
> +	req->flags |= REQ_F_NEED_CLEANUP;
> +	return 0;
> +}
> +
> +static int io_symlinkat(struct io_kiocb *req, int issue_flags)
> +{
> +	struct io_symlink *sl = &req->symlink;
> +	int ret;
> +
> +	if (issue_flags & IO_URING_F_NONBLOCK)
> +		return -EAGAIN;
> +
> +	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
> +
> +	req->flags &= ~REQ_F_NEED_CLEANUP;
> +	if (ret < 0)
> +		req_set_fail(req);
> +	io_req_complete(req, ret);
> +	return 0;
> +}
> +
>  static int io_shutdown_prep(struct io_kiocb *req,
>  			    const struct io_uring_sqe *sqe)
>  {
> @@ -6009,6 +6066,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  		return io_unlinkat_prep(req, sqe);
>  	case IORING_OP_MKDIRAT:
>  		return io_mkdirat_prep(req, sqe);
> +	case IORING_OP_SYMLINKAT:
> +		return io_symlinkat_prep(req, sqe);
>  	}
>  
>  	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
> @@ -6173,6 +6232,10 @@ static void io_clean_op(struct io_kiocb *req)
>  		case IORING_OP_MKDIRAT:
>  			putname(req->mkdir.filename);
>  			break;
> +		case IORING_OP_SYMLINKAT:
> +			putname(req->symlink.oldpath);
> +			putname(req->symlink.newpath);
> +			break;
>  		}
>  	}
>  	if ((req->flags & REQ_F_POLLED) && req->apoll) {
> @@ -6304,6 +6367,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
>  	case IORING_OP_MKDIRAT:
>  		ret = io_mkdirat(req, issue_flags);
>  		break;
> +	case IORING_OP_SYMLINKAT:
> +		ret = io_symlinkat(req, issue_flags);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  		break;
> diff --git a/fs/namei.c b/fs/namei.c
> index f99de6e294ad..f5b0379d2f8c 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -4208,8 +4208,7 @@ int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
>  }
>  EXPORT_SYMBOL(vfs_symlink);
>  
> -static int do_symlinkat(struct filename *from, int newdfd,
> -		  struct filename *to)
> +int do_symlinkat(struct filename *from, int newdfd, struct filename *to)
>  {
>  	int error;
>  	struct dentry *dentry;
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index 49a24a149eeb..796f37ab4ce3 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -138,6 +138,7 @@ enum {
>  	IORING_OP_RENAMEAT,
>  	IORING_OP_UNLINKAT,
>  	IORING_OP_MKDIRAT,
> +	IORING_OP_SYMLINKAT,
>  
>  	/* this goes last, obviously */
>  	IORING_OP_LAST,
> 

-- 
Pavel Begunkov

Re: [PATCH v6 9/9] io_uring: add support for IORING_OP_LINKAT

[Pavel Begunkov]

On 6/24/21 12:14 PM, Dmitry Kadashev wrote:
> IORING_OP_LINKAT behaves like linkat(2) and takes the same flags and
> arguments.
> 
> In some internal places 'hardlink' is used instead of 'link' to avoid
> confusion with the SQE links. Name 'link' conflicts with the existing
> 'link' member of io_kiocb.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

> 
> Suggested-by: Christian Brauner <christian.brauner@ubuntu.com>
> Link: https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/
> Signed-off-by: Dmitry Kadashev <dkadashev@gmail.com>
> Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
> ---
>  fs/internal.h                 |  2 +
>  fs/io_uring.c                 | 71 +++++++++++++++++++++++++++++++++++
>  fs/namei.c                    |  2 +-
>  include/uapi/linux/io_uring.h |  2 +
>  4 files changed, 76 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/internal.h b/fs/internal.h
> index 3b3954214385..15a7d210cc67 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -79,6 +79,8 @@ int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
>  		 struct filename *newname, unsigned int flags);
>  int do_mkdirat(int dfd, struct filename *name, umode_t mode);
>  int do_symlinkat(struct filename *from, int newdfd, struct filename *to);
> +int do_linkat(int olddfd, struct filename *old, int newdfd,
> +			struct filename *new, int flags);
>  
>  /*
>   * namespace.c
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index c161f06a3cea..14a90e4e4149 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -687,6 +687,15 @@ struct io_symlink {
>  	struct filename			*newpath;
>  };
>  
> +struct io_hardlink {
> +	struct file			*file;
> +	int				old_dfd;
> +	int				new_dfd;
> +	struct filename			*oldpath;
> +	struct filename			*newpath;
> +	int				flags;
> +};
> +
>  struct io_completion {
>  	struct file			*file;
>  	struct list_head		list;
> @@ -841,6 +850,7 @@ struct io_kiocb {
>  		struct io_unlink	unlink;
>  		struct io_mkdir		mkdir;
>  		struct io_symlink	symlink;
> +		struct io_hardlink	hardlink;
>  		/* use only after cleaning per-op data, see io_clean_op() */
>  		struct io_completion	compl;
>  	};
> @@ -1057,6 +1067,7 @@ static const struct io_op_def io_op_defs[] = {
>  	[IORING_OP_UNLINKAT] = {},
>  	[IORING_OP_MKDIRAT] = {},
>  	[IORING_OP_SYMLINKAT] = {},
> +	[IORING_OP_LINKAT] = {},
>  };
>  
>  static bool io_disarm_next(struct io_kiocb *req);
> @@ -3656,6 +3667,57 @@ static int io_symlinkat(struct io_kiocb *req, int issue_flags)
>  	return 0;
>  }
>  
> +static int io_linkat_prep(struct io_kiocb *req,
> +			    const struct io_uring_sqe *sqe)
> +{
> +	struct io_hardlink *lnk = &req->hardlink;
> +	const char __user *oldf, *newf;
> +
> +	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
> +		return -EINVAL;
> +	if (sqe->ioprio || sqe->rw_flags || sqe->buf_index)
> +		return -EINVAL;
> +	if (unlikely(req->flags & REQ_F_FIXED_FILE))
> +		return -EBADF;
> +
> +	lnk->old_dfd = READ_ONCE(sqe->fd);
> +	lnk->new_dfd = READ_ONCE(sqe->len);
> +	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
> +	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
> +	lnk->flags = READ_ONCE(sqe->hardlink_flags);
> +
> +	lnk->oldpath = getname(oldf);
> +	if (IS_ERR(lnk->oldpath))
> +		return PTR_ERR(lnk->oldpath);
> +
> +	lnk->newpath = getname(newf);
> +	if (IS_ERR(lnk->newpath)) {
> +		putname(lnk->oldpath);
> +		return PTR_ERR(lnk->newpath);
> +	}
> +
> +	req->flags |= REQ_F_NEED_CLEANUP;
> +	return 0;
> +}
> +
> +static int io_linkat(struct io_kiocb *req, int issue_flags)
> +{
> +	struct io_hardlink *lnk = &req->hardlink;
> +	int ret;
> +
> +	if (issue_flags & IO_URING_F_NONBLOCK)
> +		return -EAGAIN;
> +
> +	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
> +				lnk->newpath, lnk->flags);
> +
> +	req->flags &= ~REQ_F_NEED_CLEANUP;
> +	if (ret < 0)
> +		req_set_fail(req);
> +	io_req_complete(req, ret);
> +	return 0;
> +}
> +
>  static int io_shutdown_prep(struct io_kiocb *req,
>  			    const struct io_uring_sqe *sqe)
>  {
> @@ -6068,6 +6130,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>  		return io_mkdirat_prep(req, sqe);
>  	case IORING_OP_SYMLINKAT:
>  		return io_symlinkat_prep(req, sqe);
> +	case IORING_OP_LINKAT:
> +		return io_linkat_prep(req, sqe);
>  	}
>  
>  	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
> @@ -6236,6 +6300,10 @@ static void io_clean_op(struct io_kiocb *req)
>  			putname(req->symlink.oldpath);
>  			putname(req->symlink.newpath);
>  			break;
> +		case IORING_OP_LINKAT:
> +			putname(req->hardlink.oldpath);
> +			putname(req->hardlink.newpath);
> +			break;
>  		}
>  	}
>  	if ((req->flags & REQ_F_POLLED) && req->apoll) {
> @@ -6370,6 +6438,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
>  	case IORING_OP_SYMLINKAT:
>  		ret = io_symlinkat(req, issue_flags);
>  		break;
> +	case IORING_OP_LINKAT:
> +		ret = io_linkat(req, issue_flags);
> +		break;
>  	default:
>  		ret = -EINVAL;
>  		break;
> diff --git a/fs/namei.c b/fs/namei.c
> index f5b0379d2f8c..b85e457c43b7 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -4356,7 +4356,7 @@ EXPORT_SYMBOL(vfs_link);
>   * with linux 2.0, and to avoid hard-linking to directories
>   * and other special files.  --ADM
>   */
> -static int do_linkat(int olddfd, struct filename *old, int newdfd,
> +int do_linkat(int olddfd, struct filename *old, int newdfd,
>  	      struct filename *new, int flags)
>  {
>  	struct user_namespace *mnt_userns;
> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> index 796f37ab4ce3..c735fc22e459 100644
> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -44,6 +44,7 @@ struct io_uring_sqe {
>  		__u32		splice_flags;
>  		__u32		rename_flags;
>  		__u32		unlink_flags;
> +		__u32		hardlink_flags;
>  	};
>  	__u64	user_data;	/* data to be passed back at completion time */
>  	union {
> @@ -139,6 +140,7 @@ enum {
>  	IORING_OP_UNLINKAT,
>  	IORING_OP_MKDIRAT,
>  	IORING_OP_SYMLINKAT,
> +	IORING_OP_LINKAT,
>  
>  	/* this goes last, obviously */
>  	IORING_OP_LAST,
> 

-- 
Pavel Begunkov

Re: [PATCH v6 0/9] io_uring: add mkdir and [sym]linkat support

[Jens Axboe]

On 6/24/21 5:14 AM, Dmitry Kadashev wrote:
> This started out as an attempt to add mkdirat support to io_uring which
> is heavily based on renameat() / unlinkat() support.
> 
> During the review process more operations were added (linkat, symlinkat,
> mknodat) mainly to keep things uniform internally (in namei.c), and
> with things changed in namei.c adding support for these operations to
> io_uring is trivial, so that was done too (except for mknodat). See
> https://lore.kernel.org/io-uring/20210514145259.wtl4xcsp52woi6ab@wittgenstein/
> 
> The first patch is preparation with no functional changes, makes
> do_mkdirat accept struct filename pointer rather than the user string.
> 
> The second one leverages that to implement mkdirat in io_uring.
> 
> 3-6 just convert other similar do_* functions in namei.c to accept
> struct filename, for uniformity with do_mkdirat, do_renameat and
> do_unlinkat. No functional changes there.
> 
> 7 changes do_* helpers in namei.c to return ints rather than some of
> them returning ints and some longs.
> 
> 8-9 add symlinkat and linkat support to io_uring correspondingly.
> 
> Based on for-5.14/io_uring.

Thanks for respinning it! I've applied it, thanks.

-- 
Jens Axboe