[PATCH v4 0/2] io_uring: add support for IORING_OP_GETDENTS

[PATCH v4 0/2] io_uring: add support for IORING_OP_GETDENTS

[Lennert Buytenhek]

(These patches depend on IORING_OP_MKDIRAT going in first -- see
the changelog entry for v2 below.)

These patches add support for IORING_OP_GETDENTS, which is a new io_uring
opcode that more or less does an lseek(sqe->fd, sqe->off, SEEK_SET)
followed by a getdents64(sqe->fd, (void *)sqe->addr, sqe->len).

A dumb test program which recursively scans through a directory tree
and prints the names of all directories and files it encounters along
the way is available here:

	https://krautbox.wantstofly.org/~buytenh/uringfind-v3.c

Changes since v3 RFC:

- Made locking in io_getdents() unconditional, as the prior
  optimization was racy.  (Pointed out by Pavel Begunkov.)

- Rebase onto for-5.13/io_uring as of 2021/03/12 plus a manually
  applied version of the mkdirat patch.

Changes since v2 RFC:

- Rebase onto io_uring-2021-02-17 plus a manually applied version of
  the mkdirat patch.  The latter is needed because userland (liburing)
  has already merged the opcode for IORING_OP_MKDIRAT (in commit
  "io_uring.h: 5.12 pending kernel sync") while this opcode isn't in
  the kernel yet (as of io_uring-2021-02-17), and this means that this
  can't be merged until IORING_OP_MKDIRAT is merged.

- Adapt to changes made in "io_uring: replace force_nonblock with flags"
  that are in io_uring-2021-02-17.

Changes since v1 RFC:

- Drop the trailing '64' from IORING_OP_GETDENTS64 (suggested by
  Matthew Wilcox).

- Instead of requiring that sqe->off be zero, use this field to pass
  in a directory offset to start reading from.  For the first
  IORING_OP_GETDENTS call on a directory, this can be set to zero,
  and for subsequent calls, it can be set to the ->d_off field of
  the last struct linux_dirent64 returned by the previous call.

Lennert Buytenhek (2):
  readdir: split the core of getdents64(2) out into vfs_getdents()
  io_uring: add support for IORING_OP_GETDENTS

 fs/io_uring.c                 |   66 ++++++++++++++++++++++++++++++++++++++++++
 fs/readdir.c                  |   25 ++++++++++-----
 include/linux/fs.h            |    4 ++
 include/uapi/linux/io_uring.h |    1
 4 files changed, 88 insertions(+), 8 deletions(-)

[PATCH v4 1/2] readdir: split the core of getdents64(2) out into vfs_getdents()

[Lennert Buytenhek]

So that IORING_OP_GETDENTS may use it, split out the core of the
getdents64(2) syscall into a helper function, vfs_getdents().

vfs_getdents() calls into filesystems' ->iterate{,_shared}() which
expect serialization on struct file, which means that callers of
vfs_getdents() are responsible for either using fdget_pos() or
performing the equivalent serialization by hand.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
---
 fs/readdir.c       | 25 +++++++++++++++++--------
 include/linux/fs.h |  4 ++++
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/fs/readdir.c b/fs/readdir.c
index 19434b3c982c..f52167c1eb61 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -348,10 +348,9 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
 	return -EFAULT;
 }
 
-SYSCALL_DEFINE3(getdents64, unsigned int, fd,
-		struct linux_dirent64 __user *, dirent, unsigned int, count)
+int vfs_getdents(struct file *file, struct linux_dirent64 __user *dirent,
+		 unsigned int count)
 {
-	struct fd f;
 	struct getdents_callback64 buf = {
 		.ctx.actor = filldir64,
 		.count = count,
@@ -359,11 +358,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	};
 	int error;
 
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(file, &buf.ctx);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -376,6 +371,20 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 		else
 			error = count - buf.count;
 	}
+	return error;
+}
+
+SYSCALL_DEFINE3(getdents64, unsigned int, fd,
+		struct linux_dirent64 __user *, dirent, unsigned int, count)
+{
+	struct fd f;
+	int error;
+
+	f = fdget_pos(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = vfs_getdents(f.file, dirent, count);
 	fdput_pos(f);
 	return error;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ec8f3ddf4a6a..c03235883e18 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3227,6 +3227,10 @@ extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
+struct linux_dirent64;
+int vfs_getdents(struct file *file, struct linux_dirent64 __user *dirent,
+		 unsigned int count);
+
 int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 		int flags);
 int vfs_fstat(int fd, struct kstat *stat);
-- 
2.29.2

Re: [PATCH v4 1/2] readdir: split the core of getdents64(2) out into vfs_getdents()

[Jens Axboe]

On 3/12/21 8:49 AM, Lennert Buytenhek wrote:
> So that IORING_OP_GETDENTS may use it, split out the core of the
> getdents64(2) syscall into a helper function, vfs_getdents().
> 
> vfs_getdents() calls into filesystems' ->iterate{,_shared}() which
> expect serialization on struct file, which means that callers of
> vfs_getdents() are responsible for either using fdget_pos() or
> performing the equivalent serialization by hand.

Al, how do you feel about this one?

-- 
Jens Axboe

[PATCH v4 2/2] io_uring: add support for IORING_OP_GETDENTS

[Lennert Buytenhek]

IORING_OP_GETDENTS behaves much like getdents64(2) and takes the same
arguments, but with a small twist: it takes an additional offset
argument, and reading from the specified directory starts at the given
offset.

For the first IORING_OP_GETDENTS call on a directory, the offset
parameter can be set to zero, and for subsequent calls, it can be
set to the ->d_off field of the last struct linux_dirent64 returned
by the previous IORING_OP_GETDENTS call.

Internally, if necessary, IORING_OP_GETDENTS will vfs_llseek() to
the right directory position before calling vfs_getdents().

IORING_OP_GETDENTS may or may not update the specified directory's
file offset, and the file offset should not be relied upon having
any particular value during or after an IORING_OP_GETDENTS call.

Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
---
 fs/io_uring.c                 | 66 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 67 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index eef957139915..306e2bd9fd75 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -640,6 +640,13 @@ struct io_mkdir {
 	struct filename			*filename;
 };
 
+struct io_getdents {
+	struct file			*file;
+	struct linux_dirent64 __user	*dirent;
+	unsigned int			count;
+	loff_t				pos;
+};
+
 struct io_completion {
 	struct file			*file;
 	struct list_head		list;
@@ -774,6 +781,7 @@ struct io_kiocb {
 		struct io_rename	rename;
 		struct io_unlink	unlink;
 		struct io_mkdir		mkdir;
+		struct io_getdents	getdents;
 		/* use only after cleaning per-op data, see io_clean_op() */
 		struct io_completion	compl;
 	};
@@ -988,6 +996,9 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_RENAMEAT] = {},
 	[IORING_OP_UNLINKAT] = {},
 	[IORING_OP_MKDIRAT] = {},
+	[IORING_OP_GETDENTS] = {
+		.needs_file		= 1,
+	},
 };
 
 static bool io_disarm_next(struct io_kiocb *req);
@@ -4310,6 +4321,56 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static int io_getdents_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_getdents *getdents = &req->getdents;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+
+	getdents->pos = READ_ONCE(sqe->off);
+	getdents->dirent = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	getdents->count = READ_ONCE(sqe->len);
+	return 0;
+}
+
+static int io_getdents(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_getdents *getdents = &req->getdents;
+	int ret = 0;
+
+	/* getdents always requires a blocking context */
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	/* for vfs_llseek and to serialize ->iterate_shared() on this file */
+	mutex_lock(&req->file->f_pos_lock);
+
+	if (req->file->f_pos != getdents->pos) {
+		loff_t res = vfs_llseek(req->file, getdents->pos, SEEK_SET);
+		if (res < 0)
+			ret = res;
+	}
+
+	if (ret == 0) {
+		ret = vfs_getdents(req->file, getdents->dirent,
+				   getdents->count);
+	}
+
+	mutex_unlock(&req->file->f_pos_lock);
+
+	if (ret < 0) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+		req_set_fail_links(req);
+	}
+	io_req_complete(req, ret);
+	return 0;
+}
+
 #if defined(CONFIG_NET)
 static int io_setup_async_msg(struct io_kiocb *req,
 			      struct io_async_msghdr *kmsg)
@@ -5813,6 +5874,8 @@ 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_GETDENTS:
+		return io_getdents_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6075,6 +6138,9 @@ 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_GETDENTS:
+		ret = io_getdents(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 89b1225998c0..b12d49361022 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_GETDENTS,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.29.2