[PATCH v7 0/3] io_uring: add getdents64 support

[PATCH v7 0/3] io_uring: add getdents64 support

[Stefan Roesch]

This series adds support for getdents64 in liburing. The intent is to
provide a more complete I/O interface for io_uring.

Patch 1: fs: add offset parameter to iterate_dir function.
  This adds an offset parameter to the iterate_dir()
  function. The new parameter allows the caller to specify
  the offset to use.

Patch 2: fs: split off vfs_getdents function from getdents64 system call
  This splits of the iterate_dir part of the syscall in its own
  dedicated function. This allows to call the function directly from
  io_uring.

Patch 3: io_uring: add support for getdents64
  Adds the functions to io_uring to support getdents64.

There is also a patch series for the changes to liburing. This includes
a new test. The patch series is called "liburing: add getdents support."

The following tests have been performed:
- new liburing getdents test program has been run
- xfstests have been run
- both tests have been repeated with the kernel memory leak checker
  and no leaks have been reported.


V7: - add loff_t *parameter to iterate_dir function
    - remove do_iterate_dir function
    - change callers of iterate_dir function
v6: - rebased patch series
v5: - remove old patch (v4 contained a patch file from v3)
V4: - silence compiler warnings
V3: - add do_iterate_dir() function to Patch 1
    - make iterate_dir() function call do_iterate_dir()
      This has the advantage that the function signature of iterate_dir
      does not change
V2: - updated the iterate_dir calls in fs/ksmbd, fs/ecryptfs and arch/alpha with
      the additional parameter.


Stefan Roesch (3):
  fs: add offset parameter to iterate_dir function
  fs: split off vfs_getdents function of getdents64 syscall
  io_uring: add support for getdents64

 arch/alpha/kernel/osf_sys.c   |  2 +-
 fs/ecryptfs/file.c            |  2 +-
 fs/exportfs/expfs.c           |  2 +-
 fs/internal.h                 |  8 +++++
 fs/io_uring.c                 | 52 +++++++++++++++++++++++++++++
 fs/ksmbd/smb2pdu.c            |  3 +-
 fs/ksmbd/vfs.c                |  4 +--
 fs/nfsd/nfs4recover.c         |  2 +-
 fs/nfsd/vfs.c                 |  2 +-
 fs/overlayfs/readdir.c        |  6 ++--
 fs/readdir.c                  | 62 +++++++++++++++++++++++++----------
 include/linux/fs.h            |  2 +-
 include/uapi/linux/io_uring.h |  1 +
 13 files changed, 119 insertions(+), 29 deletions(-)


base-commit: d09358c3d161dcea8f02eae1281bc996819cc769
-- 
2.30.2

[PATCH v7 1/3] fs: add offset parameter to iterate_dir function

[Stefan Roesch]

This change adds the offset parameter to the iterate_dir
function. The offset paramater allows the caller to specify
the offset position.

This change is required to support getdents in io_uring.

Signed-off-by: Stefan Roesch <shr@fb.com>
---
 arch/alpha/kernel/osf_sys.c |  2 +-
 fs/ecryptfs/file.c          |  2 +-
 fs/exportfs/expfs.c         |  2 +-
 fs/ksmbd/smb2pdu.c          |  3 ++-
 fs/ksmbd/vfs.c              |  4 ++--
 fs/nfsd/nfs4recover.c       |  2 +-
 fs/nfsd/vfs.c               |  2 +-
 fs/overlayfs/readdir.c      |  6 +++---
 fs/readdir.c                | 28 ++++++++++++++++++----------
 include/linux/fs.h          |  2 +-
 10 files changed, 31 insertions(+), 22 deletions(-)

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 8bbeebb73cf0..cf68c459bca6 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -162,7 +162,7 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd,
 	if (!arg.file)
 		return -EBADF;
 
-	error = iterate_dir(arg.file, &buf.ctx);
+	error = iterate_dir(arg.file, &buf.ctx, &arg.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (count != buf.count)
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 18d5b91cb573..b68f1945e615 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -109,7 +109,7 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
 		.sb = inode->i_sb,
 	};
 	lower_file = ecryptfs_file_to_lower(file);
-	rc = iterate_dir(lower_file, &buf.ctx);
+	rc = iterate_dir(lower_file, &buf.ctx, &lower_file->f_pos);
 	ctx->pos = buf.ctx.pos;
 	if (rc < 0)
 		goto out;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 0106eba46d5a..654e2d4b1d4f 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -323,7 +323,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	while (1) {
 		int old_seq = buffer.sequence;
 
-		error = iterate_dir(file, &buffer.ctx);
+		error = iterate_dir(file, &buffer.ctx, &file->f_pos);
 		if (buffer.found) {
 			error = 0;
 			break;
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 49c9da37315c..fd4cb995d06d 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -3925,7 +3925,8 @@ int smb2_query_dir(struct ksmbd_work *work)
 	dir_fp->readdir_data.private		= &query_dir_private;
 	set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir);
 
-	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx);
+	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx,
+			&dir_fp->filp->f_pos);
 	if (rc == 0)
 		restart_ctx(&dir_fp->readdir_data.ctx);
 	if (rc == -ENOSPC)
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index 19d36393974c..5b8e23d3c846 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -1136,7 +1136,7 @@ int ksmbd_vfs_empty_dir(struct ksmbd_file *fp)
 	set_ctx_actor(&readdir_data.ctx, __dir_empty);
 	readdir_data.dirent_count = 0;
 
-	err = iterate_dir(fp->filp, &readdir_data.ctx);
+	err = iterate_dir(fp->filp, &readdir_data.ctx, &fp->filp->f_pos);
 	if (readdir_data.dirent_count > 2)
 		err = -ENOTEMPTY;
 	else
@@ -1186,7 +1186,7 @@ static int ksmbd_vfs_lookup_in_dir(struct path *dir, char *name, size_t namelen)
 	if (IS_ERR(dfilp))
 		return PTR_ERR(dfilp);
 
-	ret = iterate_dir(dfilp, &readdir_data.ctx);
+	ret = iterate_dir(dfilp, &readdir_data.ctx, &dfilp->f_pos);
 	if (readdir_data.dirent_count > 0)
 		ret = 0;
 	fput(dfilp);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 6fedc49726bf..79a2799891e4 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -307,7 +307,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 		return status;
 	}
 
-	status = iterate_dir(nn->rec_file, &ctx.ctx);
+	status = iterate_dir(nn->rec_file, &ctx.ctx, &nn->rec_file->f_pos);
 	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c99857689e2c..085864c25318 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1980,7 +1980,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
 		buf.used = 0;
 		buf.full = 0;
 
-		host_err = iterate_dir(file, &buf.ctx);
+		host_err = iterate_dir(file, &buf.ctx, &file->f_pos);
 		if (buf.full)
 			host_err = 0;
 
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 150fdf3bc68d..52167ff9e513 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -306,7 +306,7 @@ static inline int ovl_dir_read(struct path *realpath,
 	do {
 		rdd->count = 0;
 		rdd->err = 0;
-		err = iterate_dir(realfile, &rdd->ctx);
+		err = iterate_dir(realfile, &rdd->ctx, &realfile->f_pos);
 		if (err >= 0)
 			err = rdd->err;
 	} while (!err && rdd->count);
@@ -722,7 +722,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
 			return PTR_ERR(rdt.cache);
 	}
 
-	err = iterate_dir(od->realfile, &rdt.ctx);
+	err = iterate_dir(od->realfile, &rdt.ctx, &od->realfile->f_pos);
 	ctx->pos = rdt.ctx.pos;
 
 	return err;
@@ -753,7 +753,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
 			err = ovl_iterate_real(file, ctx);
 		} else {
-			err = iterate_dir(od->realfile, ctx);
+			err = iterate_dir(od->realfile, ctx, &od->realfile->f_pos);
 		}
 		goto out;
 	}
diff --git a/fs/readdir.c b/fs/readdir.c
index 09e8ed7d4161..c1e6612e0f47 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -36,8 +36,13 @@
 	unsafe_copy_to_user(dst, src, len, label);		\
 } while (0)
 
-
-int iterate_dir(struct file *file, struct dir_context *ctx)
+/**
+ * iterate_dir - iterate over directory
+ * @file    : pointer to file struct of directory
+ * @ctx     : pointer to directory ctx structure
+ * @pos     : file offset
+ */
+int iterate_dir(struct file *file, struct dir_context *ctx, loff_t *pos)
 {
 	struct inode *inode = file_inode(file);
 	bool shared = false;
@@ -60,12 +65,15 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 
 	res = -ENOENT;
 	if (!IS_DEADDIR(inode)) {
-		ctx->pos = file->f_pos;
+		ctx->pos = *pos;
+
 		if (shared)
 			res = file->f_op->iterate_shared(file, ctx);
 		else
 			res = file->f_op->iterate(file, ctx);
-		file->f_pos = ctx->pos;
+
+		*pos = ctx->pos;
+
 		fsnotify_access(file);
 		file_accessed(file);
 	}
@@ -190,7 +198,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (buf.result)
 		error = buf.result;
 
@@ -283,7 +291,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -366,7 +374,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -379,7 +387,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 		else
 			error = count - buf.count;
 	}
-	fdput_pos(f);
+
 	return error;
 }
 
@@ -448,7 +456,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (buf.result)
 		error = buf.result;
 
@@ -534,7 +542,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6b8dc1a78df6..e1becbe86b07 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3340,7 +3340,7 @@ const char *simple_get_link(struct dentry *, struct inode *,
 			    struct delayed_call *);
 extern const struct inode_operations simple_symlink_inode_operations;
 
-extern int iterate_dir(struct file *, struct dir_context *);
+extern int iterate_dir(struct file *, struct dir_context *, loff_t *pos);
 
 int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 		int flags);
-- 
2.30.2

[PATCH v7 2/3] fs: split off vfs_getdents function of getdents64 syscall

[Stefan Roesch]

This splits off the vfs_getdents function from the getdents64 system
call. This allows io_uring to call the vfs_getdents function.

Signed-off-by: Stefan Roesch <shr@fb.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h |  8 ++++++++
 fs/readdir.c  | 36 ++++++++++++++++++++++++++++--------
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 7979ff8d168c..432ea3ce76ec 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -194,3 +194,11 @@ long splice_file_to_pipe(struct file *in,
 			 struct pipe_inode_info *opipe,
 			 loff_t *offset,
 			 size_t len, unsigned int flags);
+
+/*
+ * fs/readdir.c
+ */
+struct linux_dirent64;
+
+int vfs_getdents(struct file *file, struct linux_dirent64 __user *dirent,
+		 unsigned int count, loff_t *pos);
diff --git a/fs/readdir.c b/fs/readdir.c
index c1e6612e0f47..1b1fade87525 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -21,6 +21,7 @@
 #include <linux/unistd.h>
 #include <linux/compat.h>
 #include <linux/uaccess.h>
+#include "internal.h"
 
 #include <asm/unaligned.h>
 
@@ -359,22 +360,25 @@ 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)
+/**
+ * vfs_getdents - getdents without fdget
+ * @file    : pointer to file struct of directory
+ * @dirent  : pointer to user directory structure
+ * @count   : size of buffer
+ * @pos     : file pos
+ */
+int vfs_getdents(struct file *file, struct linux_dirent64 __user *dirent,
+		 unsigned int count, loff_t *pos)
 {
-	struct fd f;
 	struct getdents_callback64 buf = {
 		.ctx.actor = filldir64,
+		.ctx.pos = *pos,
 		.count = count,
 		.current_dir = dirent
 	};
 	int error;
 
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
+	error = iterate_dir(file, &buf.ctx, pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -391,6 +395,22 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	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, &f.file->f_pos);
+
+	fdput_pos(f);
+	return error;
+ }
+
 #ifdef CONFIG_COMPAT
 struct compat_old_linux_dirent {
 	compat_ulong_t	d_ino;
-- 
2.30.2

[PATCH v7 3/3] io_uring: add support for getdents64

[Stefan Roesch]

This adds support for getdents64 to io_uring.

Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c                 | 52 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 53 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5092dfe56da6..c8258c784116 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -693,6 +693,13 @@ struct io_hardlink {
 	int				flags;
 };
 
+struct io_getdents {
+	struct file			*file;
+	struct linux_dirent64 __user	*dirent;
+	unsigned int			count;
+	loff_t				pos;
+};
+
 struct io_async_connect {
 	struct sockaddr_storage		address;
 };
@@ -858,6 +865,7 @@ struct io_kiocb {
 		struct io_mkdir		mkdir;
 		struct io_symlink	symlink;
 		struct io_hardlink	hardlink;
+		struct io_getdents	getdents;
 	};
 
 	u8				opcode;
@@ -1107,6 +1115,9 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_MKDIRAT] = {},
 	[IORING_OP_SYMLINKAT] = {},
 	[IORING_OP_LINKAT] = {},
+	[IORING_OP_GETDENTS] = {
+		.needs_file		= 1,
+	},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -4068,6 +4079,42 @@ static int io_linkat(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;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = vfs_getdents(req->file, getdents->dirent, getdents->count, &getdents->pos);
+	if (ret < 0) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+
+		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)
 {
@@ -6574,6 +6621,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_symlinkat_prep(req, sqe);
 	case IORING_OP_LINKAT:
 		return io_linkat_prep(req, sqe);
+	case IORING_OP_GETDENTS:
+		return io_getdents_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6857,6 +6906,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_LINKAT:
 		ret = io_linkat(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 787f491f0d2a..57dc88db5793 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -143,6 +143,7 @@ enum {
 	IORING_OP_MKDIRAT,
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
+	IORING_OP_GETDENTS,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

Re: [PATCH v7 1/3] add offset parameter to iterate_dir function

[Chuck Lever III]

> On Dec 22, 2021, at 4:07 PM, Stefan Roesch <shr@fb.com> wrote:
> 
> This change adds the offset parameter to the iterate_dir
> function. The offset paramater allows the caller to specify
> the offset position.
> 
> This change is required to support getdents in io_uring.
> 
> Signed-off-by: Stefan Roesch <shr@fb.com>
> ---
> arch/alpha/kernel/osf_sys.c |  2 +-
> fs/ecryptfs/file.c          |  2 +-
> fs/exportfs/expfs.c         |  2 +-
> fs/ksmbd/smb2pdu.c          |  3 ++-
> fs/ksmbd/vfs.c              |  4 ++--
> fs/nfsd/nfs4recover.c       |  2 +-
> fs/nfsd/vfs.c               |  2 +-
> fs/overlayfs/readdir.c      |  6 +++---
> fs/readdir.c                | 28 ++++++++++++++++++----------
> include/linux/fs.h          |  2 +-
> 10 files changed, 31 insertions(+), 22 deletions(-)

Thanks for posting. The nfsd changes seem sensible to me.

Acked-by: Chuck Lever <chuck.lever@oracle.com>


> diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
> index 8bbeebb73cf0..cf68c459bca6 100644
> --- a/arch/alpha/kernel/osf_sys.c
> +++ b/arch/alpha/kernel/osf_sys.c
> @@ -162,7 +162,7 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd,
> 	if (!arg.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(arg.file, &buf.ctx);
> +	error = iterate_dir(arg.file, &buf.ctx, &arg.file->f_pos);
> 	if (error >= 0)
> 		error = buf.error;
> 	if (count != buf.count)
> diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
> index 18d5b91cb573..b68f1945e615 100644
> --- a/fs/ecryptfs/file.c
> +++ b/fs/ecryptfs/file.c
> @@ -109,7 +109,7 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
> 		.sb = inode->i_sb,
> 	};
> 	lower_file = ecryptfs_file_to_lower(file);
> -	rc = iterate_dir(lower_file, &buf.ctx);
> +	rc = iterate_dir(lower_file, &buf.ctx, &lower_file->f_pos);
> 	ctx->pos = buf.ctx.pos;
> 	if (rc < 0)
> 		goto out;
> diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
> index 0106eba46d5a..654e2d4b1d4f 100644
> --- a/fs/exportfs/expfs.c
> +++ b/fs/exportfs/expfs.c
> @@ -323,7 +323,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
> 	while (1) {
> 		int old_seq = buffer.sequence;
> 
> -		error = iterate_dir(file, &buffer.ctx);
> +		error = iterate_dir(file, &buffer.ctx, &file->f_pos);
> 		if (buffer.found) {
> 			error = 0;
> 			break;
> diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
> index 49c9da37315c..fd4cb995d06d 100644
> --- a/fs/ksmbd/smb2pdu.c
> +++ b/fs/ksmbd/smb2pdu.c
> @@ -3925,7 +3925,8 @@ int smb2_query_dir(struct ksmbd_work *work)
> 	dir_fp->readdir_data.private		= &query_dir_private;
> 	set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir);
> 
> -	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx);
> +	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx,
> +			&dir_fp->filp->f_pos);
> 	if (rc == 0)
> 		restart_ctx(&dir_fp->readdir_data.ctx);
> 	if (rc == -ENOSPC)
> diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
> index 19d36393974c..5b8e23d3c846 100644
> --- a/fs/ksmbd/vfs.c
> +++ b/fs/ksmbd/vfs.c
> @@ -1136,7 +1136,7 @@ int ksmbd_vfs_empty_dir(struct ksmbd_file *fp)
> 	set_ctx_actor(&readdir_data.ctx, __dir_empty);
> 	readdir_data.dirent_count = 0;
> 
> -	err = iterate_dir(fp->filp, &readdir_data.ctx);
> +	err = iterate_dir(fp->filp, &readdir_data.ctx, &fp->filp->f_pos);
> 	if (readdir_data.dirent_count > 2)
> 		err = -ENOTEMPTY;
> 	else
> @@ -1186,7 +1186,7 @@ static int ksmbd_vfs_lookup_in_dir(struct path *dir, char *name, size_t namelen)
> 	if (IS_ERR(dfilp))
> 		return PTR_ERR(dfilp);
> 
> -	ret = iterate_dir(dfilp, &readdir_data.ctx);
> +	ret = iterate_dir(dfilp, &readdir_data.ctx, &dfilp->f_pos);
> 	if (readdir_data.dirent_count > 0)
> 		ret = 0;
> 	fput(dfilp);
> diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
> index 6fedc49726bf..79a2799891e4 100644
> --- a/fs/nfsd/nfs4recover.c
> +++ b/fs/nfsd/nfs4recover.c
> @@ -307,7 +307,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
> 		return status;
> 	}
> 
> -	status = iterate_dir(nn->rec_file, &ctx.ctx);
> +	status = iterate_dir(nn->rec_file, &ctx.ctx, &nn->rec_file->f_pos);
> 	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
> 
> 	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index c99857689e2c..085864c25318 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -1980,7 +1980,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
> 		buf.used = 0;
> 		buf.full = 0;
> 
> -		host_err = iterate_dir(file, &buf.ctx);
> +		host_err = iterate_dir(file, &buf.ctx, &file->f_pos);
> 		if (buf.full)
> 			host_err = 0;
> 
> diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
> index 150fdf3bc68d..52167ff9e513 100644
> --- a/fs/overlayfs/readdir.c
> +++ b/fs/overlayfs/readdir.c
> @@ -306,7 +306,7 @@ static inline int ovl_dir_read(struct path *realpath,
> 	do {
> 		rdd->count = 0;
> 		rdd->err = 0;
> -		err = iterate_dir(realfile, &rdd->ctx);
> +		err = iterate_dir(realfile, &rdd->ctx, &realfile->f_pos);
> 		if (err >= 0)
> 			err = rdd->err;
> 	} while (!err && rdd->count);
> @@ -722,7 +722,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
> 			return PTR_ERR(rdt.cache);
> 	}
> 
> -	err = iterate_dir(od->realfile, &rdt.ctx);
> +	err = iterate_dir(od->realfile, &rdt.ctx, &od->realfile->f_pos);
> 	ctx->pos = rdt.ctx.pos;
> 
> 	return err;
> @@ -753,7 +753,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
> 		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
> 			err = ovl_iterate_real(file, ctx);
> 		} else {
> -			err = iterate_dir(od->realfile, ctx);
> +			err = iterate_dir(od->realfile, ctx, &od->realfile->f_pos);
> 		}
> 		goto out;
> 	}
> diff --git a/fs/readdir.c b/fs/readdir.c
> index 09e8ed7d4161..c1e6612e0f47 100644
> --- a/fs/readdir.c
> +++ b/fs/readdir.c
> @@ -36,8 +36,13 @@
> 	unsafe_copy_to_user(dst, src, len, label);		\
> } while (0)
> 
> -
> -int iterate_dir(struct file *file, struct dir_context *ctx)
> +/**
> + * iterate_dir - iterate over directory
> + * @file    : pointer to file struct of directory
> + * @ctx     : pointer to directory ctx structure
> + * @pos     : file offset
> + */
> +int iterate_dir(struct file *file, struct dir_context *ctx, loff_t *pos)
> {
> 	struct inode *inode = file_inode(file);
> 	bool shared = false;
> @@ -60,12 +65,15 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
> 
> 	res = -ENOENT;
> 	if (!IS_DEADDIR(inode)) {
> -		ctx->pos = file->f_pos;
> +		ctx->pos = *pos;
> +
> 		if (shared)
> 			res = file->f_op->iterate_shared(file, ctx);
> 		else
> 			res = file->f_op->iterate(file, ctx);
> -		file->f_pos = ctx->pos;
> +
> +		*pos = ctx->pos;
> +
> 		fsnotify_access(file);
> 		file_accessed(file);
> 	}
> @@ -190,7 +198,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
> 	if (!f.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(f.file, &buf.ctx);
> +	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
> 	if (buf.result)
> 		error = buf.result;
> 
> @@ -283,7 +291,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
> 	if (!f.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(f.file, &buf.ctx);
> +	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
> 	if (error >= 0)
> 		error = buf.error;
> 	if (buf.prev_reclen) {
> @@ -366,7 +374,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
> 	if (!f.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(f.file, &buf.ctx);
> +	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
> 	if (error >= 0)
> 		error = buf.error;
> 	if (buf.prev_reclen) {
> @@ -379,7 +387,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
> 		else
> 			error = count - buf.count;
> 	}
> -	fdput_pos(f);
> +
> 	return error;
> }
> 
> @@ -448,7 +456,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
> 	if (!f.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(f.file, &buf.ctx);
> +	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
> 	if (buf.result)
> 		error = buf.result;
> 
> @@ -534,7 +542,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
> 	if (!f.file)
> 		return -EBADF;
> 
> -	error = iterate_dir(f.file, &buf.ctx);
> +	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
> 	if (error >= 0)
> 		error = buf.error;
> 	if (buf.prev_reclen) {
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 6b8dc1a78df6..e1becbe86b07 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -3340,7 +3340,7 @@ const char *simple_get_link(struct dentry *, struct inode *,
> 			    struct delayed_call *);
> extern const struct inode_operations simple_symlink_inode_operations;
> 
> -extern int iterate_dir(struct file *, struct dir_context *);
> +extern int iterate_dir(struct file *, struct dir_context *, loff_t *pos);
> 
> int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
> 		int flags);
> -- 
> 2.30.2
> 

--
Chuck Lever

[PATCH v7 1/3] fs: add offset parameter to iterate_dir function

[Stefan Roesch]

This change adds the offset parameter to the iterate_dir
function. The offset paramater allows the caller to specify
the offset position.

This change is required to support getdents in io_uring.

Signed-off-by: Stefan Roesch <shr@fb.com>
---
 arch/alpha/kernel/osf_sys.c |  2 +-
 fs/ecryptfs/file.c          |  2 +-
 fs/exportfs/expfs.c         |  2 +-
 fs/ksmbd/smb2pdu.c          |  3 ++-
 fs/ksmbd/vfs.c              |  4 ++--
 fs/nfsd/nfs4recover.c       |  2 +-
 fs/nfsd/vfs.c               |  2 +-
 fs/overlayfs/readdir.c      |  6 +++---
 fs/readdir.c                | 28 ++++++++++++++++++----------
 include/linux/fs.h          |  2 +-
 10 files changed, 31 insertions(+), 22 deletions(-)

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 8bbeebb73cf0..cf68c459bca6 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -162,7 +162,7 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd,
 	if (!arg.file)
 		return -EBADF;
 
-	error = iterate_dir(arg.file, &buf.ctx);
+	error = iterate_dir(arg.file, &buf.ctx, &arg.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (count != buf.count)
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 18d5b91cb573..b68f1945e615 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -109,7 +109,7 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
 		.sb = inode->i_sb,
 	};
 	lower_file = ecryptfs_file_to_lower(file);
-	rc = iterate_dir(lower_file, &buf.ctx);
+	rc = iterate_dir(lower_file, &buf.ctx, &lower_file->f_pos);
 	ctx->pos = buf.ctx.pos;
 	if (rc < 0)
 		goto out;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 0106eba46d5a..654e2d4b1d4f 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -323,7 +323,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	while (1) {
 		int old_seq = buffer.sequence;
 
-		error = iterate_dir(file, &buffer.ctx);
+		error = iterate_dir(file, &buffer.ctx, &file->f_pos);
 		if (buffer.found) {
 			error = 0;
 			break;
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 49c9da37315c..fd4cb995d06d 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -3925,7 +3925,8 @@ int smb2_query_dir(struct ksmbd_work *work)
 	dir_fp->readdir_data.private		= &query_dir_private;
 	set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir);
 
-	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx);
+	rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx,
+			&dir_fp->filp->f_pos);
 	if (rc == 0)
 		restart_ctx(&dir_fp->readdir_data.ctx);
 	if (rc == -ENOSPC)
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index 19d36393974c..5b8e23d3c846 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -1136,7 +1136,7 @@ int ksmbd_vfs_empty_dir(struct ksmbd_file *fp)
 	set_ctx_actor(&readdir_data.ctx, __dir_empty);
 	readdir_data.dirent_count = 0;
 
-	err = iterate_dir(fp->filp, &readdir_data.ctx);
+	err = iterate_dir(fp->filp, &readdir_data.ctx, &fp->filp->f_pos);
 	if (readdir_data.dirent_count > 2)
 		err = -ENOTEMPTY;
 	else
@@ -1186,7 +1186,7 @@ static int ksmbd_vfs_lookup_in_dir(struct path *dir, char *name, size_t namelen)
 	if (IS_ERR(dfilp))
 		return PTR_ERR(dfilp);
 
-	ret = iterate_dir(dfilp, &readdir_data.ctx);
+	ret = iterate_dir(dfilp, &readdir_data.ctx, &dfilp->f_pos);
 	if (readdir_data.dirent_count > 0)
 		ret = 0;
 	fput(dfilp);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 6fedc49726bf..79a2799891e4 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -307,7 +307,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 		return status;
 	}
 
-	status = iterate_dir(nn->rec_file, &ctx.ctx);
+	status = iterate_dir(nn->rec_file, &ctx.ctx, &nn->rec_file->f_pos);
 	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c99857689e2c..085864c25318 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1980,7 +1980,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
 		buf.used = 0;
 		buf.full = 0;
 
-		host_err = iterate_dir(file, &buf.ctx);
+		host_err = iterate_dir(file, &buf.ctx, &file->f_pos);
 		if (buf.full)
 			host_err = 0;
 
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 150fdf3bc68d..52167ff9e513 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -306,7 +306,7 @@ static inline int ovl_dir_read(struct path *realpath,
 	do {
 		rdd->count = 0;
 		rdd->err = 0;
-		err = iterate_dir(realfile, &rdd->ctx);
+		err = iterate_dir(realfile, &rdd->ctx, &realfile->f_pos);
 		if (err >= 0)
 			err = rdd->err;
 	} while (!err && rdd->count);
@@ -722,7 +722,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
 			return PTR_ERR(rdt.cache);
 	}
 
-	err = iterate_dir(od->realfile, &rdt.ctx);
+	err = iterate_dir(od->realfile, &rdt.ctx, &od->realfile->f_pos);
 	ctx->pos = rdt.ctx.pos;
 
 	return err;
@@ -753,7 +753,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
 			err = ovl_iterate_real(file, ctx);
 		} else {
-			err = iterate_dir(od->realfile, ctx);
+			err = iterate_dir(od->realfile, ctx, &od->realfile->f_pos);
 		}
 		goto out;
 	}
diff --git a/fs/readdir.c b/fs/readdir.c
index 09e8ed7d4161..c1e6612e0f47 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -36,8 +36,13 @@
 	unsafe_copy_to_user(dst, src, len, label);		\
 } while (0)
 
-
-int iterate_dir(struct file *file, struct dir_context *ctx)
+/**
+ * iterate_dir - iterate over directory
+ * @file    : pointer to file struct of directory
+ * @ctx     : pointer to directory ctx structure
+ * @pos     : file offset
+ */
+int iterate_dir(struct file *file, struct dir_context *ctx, loff_t *pos)
 {
 	struct inode *inode = file_inode(file);
 	bool shared = false;
@@ -60,12 +65,15 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 
 	res = -ENOENT;
 	if (!IS_DEADDIR(inode)) {
-		ctx->pos = file->f_pos;
+		ctx->pos = *pos;
+
 		if (shared)
 			res = file->f_op->iterate_shared(file, ctx);
 		else
 			res = file->f_op->iterate(file, ctx);
-		file->f_pos = ctx->pos;
+
+		*pos = ctx->pos;
+
 		fsnotify_access(file);
 		file_accessed(file);
 	}
@@ -190,7 +198,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (buf.result)
 		error = buf.result;
 
@@ -283,7 +291,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -366,7 +374,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
@@ -379,7 +387,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 		else
 			error = count - buf.count;
 	}
-	fdput_pos(f);
+
 	return error;
 }
 
@@ -448,7 +456,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (buf.result)
 		error = buf.result;
 
@@ -534,7 +542,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	if (!f.file)
 		return -EBADF;
 
-	error = iterate_dir(f.file, &buf.ctx);
+	error = iterate_dir(f.file, &buf.ctx, &f.file->f_pos);
 	if (error >= 0)
 		error = buf.error;
 	if (buf.prev_reclen) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6b8dc1a78df6..e1becbe86b07 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3340,7 +3340,7 @@ const char *simple_get_link(struct dentry *, struct inode *,
 			    struct delayed_call *);
 extern const struct inode_operations simple_symlink_inode_operations;
 
-extern int iterate_dir(struct file *, struct dir_context *);
+extern int iterate_dir(struct file *, struct dir_context *, loff_t *pos);
 
 int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 		int flags);
-- 
2.30.2