[PATCH v3 4/5] io_uring: add fsetxattr and setxattr support

[Stefan Roesch <shr@fb.com>]

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

Signed-off-by: Stefan Roesch <shr@fb.com>
---
 fs/io_uring.c                 | 171 ++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |   6 +-
 2 files changed, 176 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 568729677e25..b8e195472f05 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -81,6 +81,7 @@
 #include <linux/tracehook.h>
 #include <linux/audit.h>
 #include <linux/security.h>
+#include <linux/xattr.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -717,6 +718,13 @@ struct io_async_rw {
 	struct wait_page_queue		wpq;
 };
 
+struct io_xattr {
+	struct file			*file;
+	struct xattr_ctx		ctx;
+	void				*value;
+	struct filename			*filename;
+};
+
 enum {
 	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
 	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
@@ -856,6 +864,7 @@ struct io_kiocb {
 		struct io_mkdir		mkdir;
 		struct io_symlink	symlink;
 		struct io_hardlink	hardlink;
+		struct io_xattr		xattr;
 	};
 
 	u8				opcode;
@@ -1105,6 +1114,10 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_MKDIRAT] = {},
 	[IORING_OP_SYMLINKAT] = {},
 	[IORING_OP_LINKAT] = {},
+	[IORING_OP_FSETXATTR] = {
+		.needs_file = 1
+	},
+	[IORING_OP_SETXATTR] = {},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -3818,6 +3831,144 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static int __io_setxattr_prep(struct io_kiocb *req,
+			const struct io_uring_sqe *sqe,
+			struct user_namespace *user_ns)
+{
+	struct io_xattr *ix = &req->xattr;
+	const char __user *name;
+	void *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.size = READ_ONCE(sqe->len);
+	ix->ctx.flags = READ_ONCE(sqe->xattr_flags);
+
+	ix->ctx.kname = kmalloc(XATTR_NAME_MAX + 1, GFP_KERNEL);
+	if (!ix->ctx.kname)
+		return -ENOMEM;
+	ix->ctx.kname_sz = XATTR_NAME_MAX + 1;
+
+	ret = setxattr_setup(user_ns, name, &ix->ctx);
+	if (IS_ERR(ret)) {
+		kfree(ix->ctx.kname);
+		return PTR_ERR(ret);
+	}
+
+	ix->value = 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, current_user_ns());
+	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, file_mnt_user_ns(req->file));
+}
+
+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 = vfs_setxattr(mnt_user_ns(path->mnt), path->dentry,
+				ix->ctx.kname, ix->value, ix->ctx.size,
+				ix->ctx.flags);
+		mnt_drop_write(path->mnt);
+	}
+
+	return ret;
+}
+
+static int io_fsetxattr(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 = __io_setxattr(req, issue_flags, &req->file->f_path);
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	kfree(ix->ctx.kname);
+
+	if (ix->value)
+		kvfree(ix->value);
+	if (ret < 0)
+		req_set_fail(req);
+
+	io_req_complete(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 = do_user_path_at_empty(AT_FDCWD, ix->filename, lookup_flags, &path);
+	putname(ix->filename);
+	if (!ret) {
+		ret = __io_setxattr(req, issue_flags, &path);
+		path_put(&path);
+		if (retry_estale(ret, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
+	}
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	kfree(ix->ctx.kname);
+
+	if (ix->value)
+		kvfree(ix->value);
+	if (ret < 0)
+		req_set_fail(req);
+
+	io_req_complete(req, ret);
+	return 0;
+}
+
 static int io_unlinkat_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -6531,6 +6682,10 @@ 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_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",
@@ -6674,6 +6829,15 @@ static void io_clean_op(struct io_kiocb *req)
 			putname(req->hardlink.oldpath);
 			putname(req->hardlink.newpath);
 			break;
+		case IORING_OP_SETXATTR:
+			if (req->xattr.filename)
+				putname(req->xattr.filename);
+			fallthrough;
+		case IORING_OP_FSETXATTR:
+			kfree(req->xattr.ctx.kname);
+			if (req->xattr.value)
+				kvfree(req->xattr.value);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -6816,6 +6980,12 @@ 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_FSETXATTR:
+		ret = io_fsetxattr(req, issue_flags);
+		break;
+	case IORING_OP_SETXATTR:
+		ret = io_setxattr(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -11183,6 +11353,7 @@ 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 787f491f0d2a..dbf473900da2 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 {
@@ -143,6 +145,8 @@ enum {
 	IORING_OP_MKDIRAT,
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.30.2