[PATCH v11 0/4] io_uring: add xattr support

[PATCH v11 0/4] io_uring: add xattr support

[Stefan Roesch]

This adds the xattr support to io_uring. The intent is to have a more
complete support for file operations in io_uring.

This change adds support for the following functions to io_uring:
- fgetxattr
- fsetxattr
- getxattr
- setxattr

Patch 1: fs: split off setxattr_copy and do_setxattr function from setxattr
  Split off the setup part of the setxattr function in the setxattr_copy
  function. Split off the processing part in do_setxattr.

Patch 2: fs: split off do_getxattr from getxattr
  Split of the do_getxattr part from getxattr. This will
  allow it to be invoked it from io_uring.

Patch 3: io_uring: add fsetxattr and setxattr support
  This adds new functions to support the fsetxattr and setxattr
  functions.

Patch 4: io_uring: add fgetxattr and getxattr support
  This adds new functions to support the fgetxattr and getxattr
  functions.


There are two additional patches:
  liburing: Add support for xattr api's.
            This also includes the tests for the new code.
  xfstests: Add support for io_uring xattr support.


V11: - removed the do_user_path_at_empty function and directly
       call filename_lookup
     - introduce __io_xattr_finish and io_xattr_finish functions
       to unify the cleanup code
     - remove the older __io_setxattr_finish function
V10: - move do_user_path_at_empty definition to fs/internal.h
     - introduce __io_setxattr_finish function
     - introduce __io_getxattr_finish function
V9 : - keep kvalue in struct xattr_ctx
V8 : - introduce xattr_name struct as advised by Linus
     - remove kname_sz field in xattr_ctx
V7 : - split off setxattr in two functions as recommeneded by
       Christian.
V6 : - reverted addition of kname array to xattr_ctx structure
       Adding the kname array increases the io_kiocb beyond 64 bytes
       (increases it to 224 bytes). We try hard to limit it to 64 bytes.
       Keeping the original interface also is a bit more efficient.
     - addressed Pavel's reordering comment
     - addressed Pavel's putname comment
     - addressed Pavel's kvfree comment
     - rebased on for-5.17/io_uring-getdents64
V5 : - add kname array to xattr_ctx structure
V4 : - rebased patch series
V3 : - remove req->file checks in prep functions
     - change size parameter in do_xattr
V2 : - split off function do_user_path_empty instead of changing
       the function signature of user_path_at
     - Fix datatype size problem in do_getxattr


Stefan Roesch (4):
  fs: split off setxattr_copy and do_setxattr function from setxattr
  fs: split off do_getxattr from getxattr
  io_uring: add fsetxattr and setxattr support
  io_uring: add fgetxattr and getxattr support

 fs/internal.h                 |  28 ++++
 fs/io_uring.c                 | 298 ++++++++++++++++++++++++++++++++++
 fs/xattr.c                    | 114 +++++++++----
 include/uapi/linux/io_uring.h |   8 +-
 4 files changed, 411 insertions(+), 37 deletions(-)


base-commit: b4518682080d3a1cdd6ea45a54ff6772b8b2797a
-- 
2.30.2

[PATCH v11 1/4] fs: split off setxattr_copy and do_setxattr function from setxattr

[Stefan Roesch]

This splits of the setup part of the function
setxattr in its own dedicated function called
setxattr_copy. In addition it also exposes a
new function called do_setxattr for making the
setxattr call.

This makes it possible to call these two functions
from io_uring in the processing of an xattr request.

Signed-off-by: Stefan Roesch <shr@fb.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h | 21 +++++++++++++
 fs/xattr.c    | 82 ++++++++++++++++++++++++++++++++++++---------------
 2 files changed, 79 insertions(+), 24 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 432ea3ce76ec..00c98b0cd634 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -202,3 +202,24 @@ struct linux_dirent64;
 
 int vfs_getdents(struct file *file, struct linux_dirent64 __user *dirent,
 		 unsigned int count, loff_t *pos);
+
+ /*
+  * fs/xattr.c:
+  */
+struct xattr_name {
+	char name[XATTR_NAME_MAX + 1];
+};
+
+struct xattr_ctx {
+	/* Value of attribute */
+	const void __user *value;
+	void *kvalue;
+	size_t size;
+	/* Attribute name */
+	struct xattr_name *kname;
+	unsigned int flags;
+};
+
+int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
+int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		struct xattr_ctx *ctx);
diff --git a/fs/xattr.c b/fs/xattr.c
index 5c8c5175b385..dec7ac3e0e89 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -25,6 +25,8 @@
 
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 static const char *
 strcmp_prefix(const char *a, const char *a_prefix)
 {
@@ -539,43 +541,75 @@ EXPORT_SYMBOL_GPL(vfs_removexattr);
 /*
  * Extended attribute SET operations
  */
-static long
-setxattr(struct user_namespace *mnt_userns, struct dentry *d,
-	 const char __user *name, const void __user *value, size_t size,
-	 int flags)
+
+int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
 {
 	int error;
-	void *kvalue = NULL;
-	char kname[XATTR_NAME_MAX + 1];
 
-	if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
+	if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
 		return -EINVAL;
 
-	error = strncpy_from_user(kname, name, sizeof(kname));
-	if (error == 0 || error == sizeof(kname))
-		error = -ERANGE;
+	error = strncpy_from_user(ctx->kname->name, name,
+				sizeof(ctx->kname->name));
+	if (error == 0 || error == sizeof(ctx->kname->name))
+		return  -ERANGE;
 	if (error < 0)
 		return error;
 
-	if (size) {
-		if (size > XATTR_SIZE_MAX)
+	error = 0;
+	if (ctx->size) {
+		if (ctx->size > XATTR_SIZE_MAX)
 			return -E2BIG;
-		kvalue = kvmalloc(size, GFP_KERNEL);
-		if (!kvalue)
-			return -ENOMEM;
-		if (copy_from_user(kvalue, value, size)) {
-			error = -EFAULT;
-			goto out;
+
+		ctx->kvalue = vmemdup_user(ctx->value, ctx->size);
+		if (IS_ERR(ctx->kvalue)) {
+			error = PTR_ERR(ctx->kvalue);
+			ctx->kvalue = NULL;
 		}
-		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
-		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
-			posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size);
 	}
 
-	error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags);
-out:
-	kvfree(kvalue);
+	return error;
+}
+
+static void setxattr_convert(struct user_namespace *mnt_userns,
+			struct xattr_ctx *ctx)
+{
+	if (ctx->size &&
+		((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
+		(strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)))
+		posix_acl_fix_xattr_from_user(mnt_userns, ctx->kvalue, ctx->size);
+}
+
+int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		struct xattr_ctx *ctx)
+{
+	setxattr_convert(mnt_userns, ctx);
+	return vfs_setxattr(mnt_userns, dentry, ctx->kname->name,
+			ctx->kvalue, ctx->size, ctx->flags);
+}
+
+static long
+setxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	const char __user *name, const void __user *value, size_t size,
+	int flags)
+{
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.value    = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = flags,
+	};
+	int error;
+
+	error = setxattr_copy(name, &ctx);
+	if (error)
+		return error;
+
+	error = do_setxattr(mnt_userns, d, &ctx);
 
+	kvfree(ctx.kvalue);
 	return error;
 }
 
-- 
2.30.2

[PATCH v11 2/4] fs: split off do_getxattr from getxattr

[Stefan Roesch]

This splits off do_getxattr function from the getxattr
function. This will allow io_uring to call it from its
io worker.

Signed-off-by: Stefan Roesch <shr@fb.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/internal.h |  7 +++++++
 fs/xattr.c    | 32 ++++++++++++++++++++------------
 2 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 00c98b0cd634..942b2005a2be 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -220,6 +220,13 @@ struct xattr_ctx {
 	unsigned int flags;
 };
 
+
+ssize_t do_getxattr(struct user_namespace *mnt_userns,
+		    struct dentry *d,
+		    const char *kname,
+		    void __user *value,
+		    size_t size);
+
 int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
 int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		struct xattr_ctx *ctx);
diff --git a/fs/xattr.c b/fs/xattr.c
index dec7ac3e0e89..7f2b805ed56c 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -675,19 +675,12 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 /*
  * Extended attribute GET operations
  */
-static ssize_t
-getxattr(struct user_namespace *mnt_userns, struct dentry *d,
-	 const char __user *name, void __user *value, size_t size)
+ssize_t
+do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	const char *kname, void __user *value, size_t size)
 {
-	ssize_t error;
 	void *kvalue = NULL;
-	char kname[XATTR_NAME_MAX + 1];
-
-	error = strncpy_from_user(kname, name, sizeof(kname));
-	if (error == 0 || error == sizeof(kname))
-		error = -ERANGE;
-	if (error < 0)
-		return error;
+	ssize_t error;
 
 	if (size) {
 		if (size > XATTR_SIZE_MAX)
@@ -711,10 +704,25 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
 	}
 
 	kvfree(kvalue);
-
 	return error;
 }
 
+static ssize_t
+getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	 const char __user *name, void __user *value, size_t size)
+{
+	ssize_t error;
+	struct xattr_name kname;
+
+	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
+	if (error == 0 || error == sizeof(kname.name))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
+	return do_getxattr(mnt_userns, d, kname.name, value, size);
+}
+
 static ssize_t path_getxattr(const char __user *pathname,
 			     const char __user *name, void __user *value,
 			     size_t size, unsigned int lookup_flags)
-- 
2.30.2

[PATCH v11 3/4] io_uring: add fsetxattr and setxattr support

[Stefan Roesch]

This adds support to io_uring for the fsetxattr and setxattr API.

Signed-off-by: Stefan Roesch <shr@fb.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 fs/io_uring.c                 | 165 ++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |   6 +-
 2 files changed, 170 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c8258c784116..2d1eb276a648 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -82,6 +82,7 @@
 #include <linux/audit.h>
 #include <linux/security.h>
 #include <linux/atomic-ref.h>
+#include <linux/xattr.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -726,6 +727,12 @@ struct io_async_rw {
 	struct wait_page_queue		wpq;
 };
 
+struct io_xattr {
+	struct file			*file;
+	struct xattr_ctx		ctx;
+	struct filename			*filename;
+};
+
 enum {
 	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
 	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
@@ -866,6 +873,7 @@ struct io_kiocb {
 		struct io_symlink	symlink;
 		struct io_hardlink	hardlink;
 		struct io_getdents	getdents;
+		struct io_xattr		xattr;
 	};
 
 	u8				opcode;
@@ -1118,6 +1126,10 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_GETDENTS] = {
 		.needs_file		= 1,
 	},
+	[IORING_OP_FSETXATTR] = {
+		.needs_file = 1
+	},
+	[IORING_OP_SETXATTR] = {},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -3887,6 +3899,144 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static inline void __io_xattr_finish(struct io_kiocb *req)
+{
+	struct io_xattr *ix = &req->xattr;
+
+	if (ix->filename)
+		putname(ix->filename);
+
+	kfree(ix->ctx.kname);
+	kvfree(ix->ctx.kvalue);
+}
+
+static void io_xattr_finish(struct io_kiocb *req, int ret)
+{
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+
+	__io_xattr_finish(req);
+	if (ret < 0)
+		req_set_fail(req);
+
+	io_req_complete(req, ret);
+}
+
+static int __io_setxattr_prep(struct io_kiocb *req,
+			const struct io_uring_sqe *sqe)
+{
+	struct io_xattr *ix = &req->xattr;
+	const char __user *name;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (unlikely(sqe->ioprio))
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	ix->filename = NULL;
+	name = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	ix->ctx.value = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	ix->ctx.kvalue = NULL;
+	ix->ctx.size = READ_ONCE(sqe->len);
+	ix->ctx.flags = READ_ONCE(sqe->xattr_flags);
+
+	ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
+	if (!ix->ctx.kname)
+		return -ENOMEM;
+
+	ret = setxattr_copy(name, &ix->ctx);
+	if (ret) {
+		kfree(ix->ctx.kname);
+		return ret;
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+static int io_setxattr_prep(struct io_kiocb *req,
+			const struct io_uring_sqe *sqe)
+{
+	struct io_xattr *ix = &req->xattr;
+	const char __user *path;
+	int ret;
+
+	ret = __io_setxattr_prep(req, sqe);
+	if (ret)
+		return ret;
+
+	path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
+
+	ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
+	if (IS_ERR(ix->filename)) {
+		ret = PTR_ERR(ix->filename);
+		ix->filename = NULL;
+	}
+
+	return ret;
+}
+
+static int io_fsetxattr_prep(struct io_kiocb *req,
+			const struct io_uring_sqe *sqe)
+{
+	return __io_setxattr_prep(req, sqe);
+}
+
+static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags,
+			struct path *path)
+{
+	struct io_xattr *ix = &req->xattr;
+	int ret;
+
+	ret = mnt_want_write(path->mnt);
+	if (!ret) {
+		ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx);
+		mnt_drop_write(path->mnt);
+	}
+
+	return ret;
+}
+
+static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags)
+{
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = __io_setxattr(req, issue_flags, &req->file->f_path);
+	io_xattr_finish(req, ret);
+
+	return 0;
+}
+
+static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_xattr *ix = &req->xattr;
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	struct path path;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+retry:
+	ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
+	if (!ret) {
+		ret = __io_setxattr(req, issue_flags, &path);
+		path_put(&path);
+		if (retry_estale(ret, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
+	}
+
+	io_xattr_finish(req, ret);
+	return 0;
+}
+
 static int io_unlinkat_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -6623,6 +6773,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_linkat_prep(req, sqe);
 	case IORING_OP_GETDENTS:
 		return io_getdents_prep(req, sqe);
+	case IORING_OP_FSETXATTR:
+		return io_fsetxattr_prep(req, sqe);
+	case IORING_OP_SETXATTR:
+		return io_setxattr_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6764,6 +6918,10 @@ static void io_clean_op(struct io_kiocb *req)
 			putname(req->hardlink.oldpath);
 			putname(req->hardlink.newpath);
 			break;
+		case IORING_OP_SETXATTR:
+		case IORING_OP_FSETXATTR:
+			__io_xattr_finish(req);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -6909,6 +7067,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_GETDENTS:
 		ret = io_getdents(req, issue_flags);
 		break;
+	case IORING_OP_FSETXATTR:
+		ret = io_fsetxattr(req, issue_flags);
+		break;
+	case IORING_OP_SETXATTR:
+		ret = io_setxattr(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -11277,6 +11441,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(42, __u16,  personality);
 	BUILD_BUG_SQE_ELEM(44, __s32,  splice_fd_in);
 	BUILD_BUG_SQE_ELEM(44, __u32,  file_index);
+	BUILD_BUG_SQE_ELEM(48, __u64,  addr3);
 
 	BUILD_BUG_ON(sizeof(struct io_uring_files_update) !=
 		     sizeof(struct io_uring_rsrc_update));
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 57dc88db5793..c62a8bec8cd4 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -45,6 +45,7 @@ struct io_uring_sqe {
 		__u32		rename_flags;
 		__u32		unlink_flags;
 		__u32		hardlink_flags;
+		__u32		xattr_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -60,7 +61,8 @@ struct io_uring_sqe {
 		__s32	splice_fd_in;
 		__u32	file_index;
 	};
-	__u64	__pad2[2];
+	__u64	addr3;
+	__u64	__pad2[1];
 };
 
 enum {
@@ -144,6 +146,8 @@ enum {
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
 	IORING_OP_GETDENTS,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

[PATCH v11 4/4] io_uring: add fgetxattr and getxattr support

[Stefan Roesch]

This adds support to io_uring for the fgetxattr and getxattr API.

Signed-off-by: Stefan Roesch <shr@fb.com>
---
 fs/io_uring.c                 | 133 ++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |   2 +
 2 files changed, 135 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2d1eb276a648..a16073e151f4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1130,6 +1130,10 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file = 1
 	},
 	[IORING_OP_SETXATTR] = {},
+	[IORING_OP_FGETXATTR] = {
+		.needs_file = 1
+	},
+	[IORING_OP_GETXATTR] = {},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -3921,6 +3925,123 @@ static void io_xattr_finish(struct io_kiocb *req, int ret)
 	io_req_complete(req, ret);
 }
 
+static int __io_getxattr_prep(struct io_kiocb *req,
+			      const struct io_uring_sqe *sqe)
+{
+	struct io_xattr *ix = &req->xattr;
+	const char __user *name;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (unlikely(sqe->ioprio))
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	ix->filename = NULL;
+	ix->ctx.kvalue = NULL;
+	name = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	ix->ctx.value = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	ix->ctx.size = READ_ONCE(sqe->len);
+	ix->ctx.flags = READ_ONCE(sqe->xattr_flags);
+
+	if (ix->ctx.flags)
+		return -EINVAL;
+
+	ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
+	if (!ix->ctx.kname)
+		return -ENOMEM;
+
+	ret = strncpy_from_user(ix->ctx.kname->name, name,
+				sizeof(ix->ctx.kname->name));
+	if (!ret || ret == sizeof(ix->ctx.kname->name))
+		ret = -ERANGE;
+	if (ret < 0) {
+		kfree(ix->ctx.kname);
+		return ret;
+	}
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	return 0;
+}
+
+static int io_fgetxattr_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+	return __io_getxattr_prep(req, sqe);
+}
+
+static int io_getxattr_prep(struct io_kiocb *req,
+			    const struct io_uring_sqe *sqe)
+{
+	struct io_xattr *ix = &req->xattr;
+	const char __user *path;
+	int ret;
+
+	ret = __io_getxattr_prep(req, sqe);
+	if (ret)
+		return ret;
+
+	path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
+
+	ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
+	if (IS_ERR(ix->filename)) {
+		ret = PTR_ERR(ix->filename);
+		ix->filename = NULL;
+	}
+
+	return ret;
+}
+
+static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_xattr *ix = &req->xattr;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+	ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt),
+			req->file->f_path.dentry,
+			ix->ctx.kname->name,
+			(void __user *)ix->ctx.value,
+			ix->ctx.size);
+
+	io_xattr_finish(req, ret);
+	return 0;
+}
+
+static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_xattr *ix = &req->xattr;
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	struct path path;
+	int ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
+retry:
+	ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
+	if (!ret) {
+		ret = do_getxattr(mnt_user_ns(path.mnt),
+				path.dentry,
+				ix->ctx.kname->name,
+				(void __user *)ix->ctx.value,
+				ix->ctx.size);
+
+		path_put(&path);
+		if (retry_estale(ret, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
+	}
+
+	io_xattr_finish(req, ret);
+	return 0;
+}
+
 static int __io_setxattr_prep(struct io_kiocb *req,
 			const struct io_uring_sqe *sqe)
 {
@@ -6777,6 +6898,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_fsetxattr_prep(req, sqe);
 	case IORING_OP_SETXATTR:
 		return io_setxattr_prep(req, sqe);
+	case IORING_OP_FGETXATTR:
+		return io_fgetxattr_prep(req, sqe);
+	case IORING_OP_GETXATTR:
+		return io_getxattr_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6920,6 +7045,8 @@ static void io_clean_op(struct io_kiocb *req)
 			break;
 		case IORING_OP_SETXATTR:
 		case IORING_OP_FSETXATTR:
+		case IORING_OP_GETXATTR:
+		case IORING_OP_FGETXATTR:
 			__io_xattr_finish(req);
 			break;
 		}
@@ -7073,6 +7200,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_SETXATTR:
 		ret = io_setxattr(req, issue_flags);
 		break;
+	case IORING_OP_FGETXATTR:
+		ret = io_fgetxattr(req, issue_flags);
+		break;
+	case IORING_OP_GETXATTR:
+		ret = io_getxattr(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 c62a8bec8cd4..efc7ac9b3a6b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -148,6 +148,8 @@ enum {
 	IORING_OP_GETDENTS,
 	IORING_OP_FSETXATTR,
 	IORING_OP_SETXATTR,
+	IORING_OP_FGETXATTR,
+	IORING_OP_GETXATTR,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2

Re: [PATCH v11 2/4] fs: split off do_getxattr from getxattr

[Christian Brauner]

On Tue, Jan 04, 2022 at 11:09:34AM -0800, Stefan Roesch wrote:
> This splits off do_getxattr function from the getxattr
> function. This will allow io_uring to call it from its
> io worker.
> 
> Signed-off-by: Stefan Roesch <shr@fb.com>
> Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
> ---
>  fs/internal.h |  7 +++++++
>  fs/xattr.c    | 32 ++++++++++++++++++++------------
>  2 files changed, 27 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/internal.h b/fs/internal.h
> index 00c98b0cd634..942b2005a2be 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -220,6 +220,13 @@ struct xattr_ctx {
>  	unsigned int flags;
>  };
>  
> +
> +ssize_t do_getxattr(struct user_namespace *mnt_userns,
> +		    struct dentry *d,
> +		    const char *kname,
> +		    void __user *value,
> +		    size_t size);
> +
>  int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
>  int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
>  		struct xattr_ctx *ctx);
> diff --git a/fs/xattr.c b/fs/xattr.c
> index dec7ac3e0e89..7f2b805ed56c 100644
> --- a/fs/xattr.c
> +++ b/fs/xattr.c
> @@ -675,19 +675,12 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
>  /*
>   * Extended attribute GET operations
>   */
> -static ssize_t
> -getxattr(struct user_namespace *mnt_userns, struct dentry *d,
> -	 const char __user *name, void __user *value, size_t size)
> +ssize_t
> +do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
> +	const char *kname, void __user *value, size_t size)
>  {
> -	ssize_t error;
>  	void *kvalue = NULL;
> -	char kname[XATTR_NAME_MAX + 1];
> -
> -	error = strncpy_from_user(kname, name, sizeof(kname));
> -	if (error == 0 || error == sizeof(kname))
> -		error = -ERANGE;
> -	if (error < 0)
> -		return error;
> +	ssize_t error;
>  
>  	if (size) {
>  		if (size > XATTR_SIZE_MAX)
> @@ -711,10 +704,25 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>  	}
>  
>  	kvfree(kvalue);
> -
>  	return error;
>  }
>  
> +static ssize_t
> +getxattr(struct user_namespace *mnt_userns, struct dentry *d,
> +	 const char __user *name, void __user *value, size_t size)
> +{
> +	ssize_t error;
> +	struct xattr_name kname;
> +
> +	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
> +	if (error == 0 || error == sizeof(kname.name))
> +		error = -ERANGE;
> +	if (error < 0)
> +		return error;
> +
> +	return do_getxattr(mnt_userns, d, kname.name, value, size);
> +}

Fwiw, this could have the same signature as do_setxattr(). So sm along
the lines of (completely untested):

Subject: [PATCH] UNTESTED

---
 fs/internal.h |  8 ++------
 fs/xattr.c    | 36 ++++++++++++++++++++++--------------
 2 files changed, 24 insertions(+), 20 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 942b2005a2be..d2332496724b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -220,12 +220,8 @@ struct xattr_ctx {
 	unsigned int flags;
 };
 
-
-ssize_t do_getxattr(struct user_namespace *mnt_userns,
-		    struct dentry *d,
-		    const char *kname,
-		    void __user *value,
-		    size_t size);
+ssize_t do_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		    struct xattr_ctx *ctx);
 
 int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
 int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
diff --git a/fs/xattr.c b/fs/xattr.c
index 7f2b805ed56c..52bcfe149a9f 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -675,35 +675,34 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 /*
  * Extended attribute GET operations
  */
-ssize_t
-do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
-	const char *kname, void __user *value, size_t size)
+ssize_t do_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		    struct xattr_ctx *ctx)
+
 {
-	void *kvalue = NULL;
 	ssize_t error;
+	char *kname = ctx->kname.name;
 
-	if (size) {
-		if (size > XATTR_SIZE_MAX)
-			size = XATTR_SIZE_MAX;
-		kvalue = kvzalloc(size, GFP_KERNEL);
-		if (!kvalue)
+	if (ctx->size) {
+		if (ctx->size > XATTR_SIZE_MAX)
+			ctx->size = XATTR_SIZE_MAX;
+		ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
+		if (!ctx->kvalue)
 			return -ENOMEM;
 	}
 
-	error = vfs_getxattr(mnt_userns, d, kname, kvalue, size);
+	error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size);
 	if (error > 0) {
 		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
 		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
 			posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error);
-		if (size && copy_to_user(value, kvalue, error))
+		if (ctx->size && copy_to_user(value, kvalue, error))
 			error = -EFAULT;
-	} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
+	} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
 		/* The file system tried to returned a value bigger
 		   than XATTR_SIZE_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
 
-	kvfree(kvalue);
 	return error;
 }
 
@@ -713,6 +712,12 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
 {
 	ssize_t error;
 	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.value    = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+	};
 
 	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
 	if (error == 0 || error == sizeof(kname.name))
@@ -720,7 +725,10 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
 	if (error < 0)
 		return error;
 
-	return do_getxattr(mnt_userns, d, kname.name, value, size);
+	error = do_getxattr(mnt_userns, d, &ctx);
+
+	kvfree(ctx.kvalue);
+	return error;
 }
 
 static ssize_t path_getxattr(const char __user *pathname,
-- 
2.32.0

Re: [PATCH v11 2/4] fs: split off do_getxattr from getxattr

[Stefan Roesch]

On 1/5/22 5:22 AM, Christian Brauner wrote:
> On Tue, Jan 04, 2022 at 11:09:34AM -0800, Stefan Roesch wrote:
>> This splits off do_getxattr function from the getxattr
>> function. This will allow io_uring to call it from its
>> io worker.
>>
>> Signed-off-by: Stefan Roesch <shr@fb.com>
>> Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
>> ---
>>  fs/internal.h |  7 +++++++
>>  fs/xattr.c    | 32 ++++++++++++++++++++------------
>>  2 files changed, 27 insertions(+), 12 deletions(-)
>>
>> diff --git a/fs/internal.h b/fs/internal.h
>> index 00c98b0cd634..942b2005a2be 100644
>> --- a/fs/internal.h
>> +++ b/fs/internal.h
>> @@ -220,6 +220,13 @@ struct xattr_ctx {
>>  	unsigned int flags;
>>  };
>>  
>> +
>> +ssize_t do_getxattr(struct user_namespace *mnt_userns,
>> +		    struct dentry *d,
>> +		    const char *kname,
>> +		    void __user *value,
>> +		    size_t size);
>> +
>>  int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
>>  int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
>>  		struct xattr_ctx *ctx);
>> diff --git a/fs/xattr.c b/fs/xattr.c
>> index dec7ac3e0e89..7f2b805ed56c 100644
>> --- a/fs/xattr.c
>> +++ b/fs/xattr.c
>> @@ -675,19 +675,12 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
>>  /*
>>   * Extended attribute GET operations
>>   */
>> -static ssize_t
>> -getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>> -	 const char __user *name, void __user *value, size_t size)
>> +ssize_t
>> +do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>> +	const char *kname, void __user *value, size_t size)
>>  {
>> -	ssize_t error;
>>  	void *kvalue = NULL;
>> -	char kname[XATTR_NAME_MAX + 1];
>> -
>> -	error = strncpy_from_user(kname, name, sizeof(kname));
>> -	if (error == 0 || error == sizeof(kname))
>> -		error = -ERANGE;
>> -	if (error < 0)
>> -		return error;
>> +	ssize_t error;
>>  
>>  	if (size) {
>>  		if (size > XATTR_SIZE_MAX)
>> @@ -711,10 +704,25 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>>  	}
>>  
>>  	kvfree(kvalue);
>> -
>>  	return error;
>>  }
>>  
>> +static ssize_t
>> +getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>> +	 const char __user *name, void __user *value, size_t size)
>> +{
>> +	ssize_t error;
>> +	struct xattr_name kname;
>> +
>> +	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
>> +	if (error == 0 || error == sizeof(kname.name))
>> +		error = -ERANGE;
>> +	if (error < 0)
>> +		return error;
>> +
>> +	return do_getxattr(mnt_userns, d, kname.name, value, size);
>> +}
> 
> Fwiw, this could have the same signature as do_setxattr(). So sm along
> the lines of (completely untested):
> 

Christian, I made changes similar to the ones you recommended.
However I needed to introduce a union in the xattr_ctx structure.
For the setxattr function we require a const pointer and for getxattr
function we only require a pointer.

In addition it also needs changes in io_uring.c to pass in the context.

v12 has these changes.

> Subject: [PATCH] UNTESTED
> 
> ---
>  fs/internal.h |  8 ++------
>  fs/xattr.c    | 36 ++++++++++++++++++++++--------------
>  2 files changed, 24 insertions(+), 20 deletions(-)
> 
> diff --git a/fs/internal.h b/fs/internal.h
> index 942b2005a2be..d2332496724b 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -220,12 +220,8 @@ struct xattr_ctx {
>  	unsigned int flags;
>  };
>  
> -
> -ssize_t do_getxattr(struct user_namespace *mnt_userns,
> -		    struct dentry *d,
> -		    const char *kname,
> -		    void __user *value,
> -		    size_t size);
> +ssize_t do_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
> +		    struct xattr_ctx *ctx);
>  
>  int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
>  int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
> diff --git a/fs/xattr.c b/fs/xattr.c
> index 7f2b805ed56c..52bcfe149a9f 100644
> --- a/fs/xattr.c
> +++ b/fs/xattr.c
> @@ -675,35 +675,34 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
>  /*
>   * Extended attribute GET operations
>   */
> -ssize_t
> -do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
> -	const char *kname, void __user *value, size_t size)
> +ssize_t do_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
> +		    struct xattr_ctx *ctx)
> +
>  {
> -	void *kvalue = NULL;
>  	ssize_t error;
> +	char *kname = ctx->kname.name;
>  
> -	if (size) {
> -		if (size > XATTR_SIZE_MAX)
> -			size = XATTR_SIZE_MAX;
> -		kvalue = kvzalloc(size, GFP_KERNEL);
> -		if (!kvalue)
> +	if (ctx->size) {
> +		if (ctx->size > XATTR_SIZE_MAX)
> +			ctx->size = XATTR_SIZE_MAX;
> +		ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
> +		if (!ctx->kvalue)
>  			return -ENOMEM;
>  	}
>  
> -	error = vfs_getxattr(mnt_userns, d, kname, kvalue, size);
> +	error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size);
>  	if (error > 0) {
>  		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
>  		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
>  			posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error);
> -		if (size && copy_to_user(value, kvalue, error))
> +		if (ctx->size && copy_to_user(value, kvalue, error))
>  			error = -EFAULT;
> -	} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
> +	} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
>  		/* The file system tried to returned a value bigger
>  		   than XATTR_SIZE_MAX bytes. Not possible. */
>  		error = -E2BIG;
>  	}
>  
> -	kvfree(kvalue);
>  	return error;
>  }
>  
> @@ -713,6 +712,12 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>  {
>  	ssize_t error;
>  	struct xattr_name kname;
> +	struct xattr_ctx ctx = {
> +		.value    = value,
> +		.kvalue   = NULL,
> +		.size     = size,
> +		.kname    = &kname,
> +	};
>  
>  	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
>  	if (error == 0 || error == sizeof(kname.name))
> @@ -720,7 +725,10 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
>  	if (error < 0)
>  		return error;
>  
> -	return do_getxattr(mnt_userns, d, kname.name, value, size);
> +	error = do_getxattr(mnt_userns, d, &ctx);
> +
> +	kvfree(ctx.kvalue);
> +	return error;
>  }
>  
>  static ssize_t path_getxattr(const char __user *pathname,