Merge tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block

Pull io_uring xattr support from Jens Axboe:
 "Support for the xattr variants"

* tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block:
  io_uring: cleanup error-handling around io_req_complete
  io_uring: fix trace for reduced sqe padding
  io_uring: add fgetxattr and getxattr support
  io_uring: add fsetxattr and setxattr support
  fs: split off do_getxattr from getxattr
  fs: split off setxattr_copy and do_setxattr function from setxattr

1 files changed, 296 insertions, 26 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0c6a14276186..e4c9f776919b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -80,6 +80,7 @@
 #include <linux/io_uring.h>
 #include <linux/audit.h>
 #include <linux/security.h>
+#include <linux/xattr.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -803,6 +804,12 @@ 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,
@@ -973,6 +980,7 @@ struct io_kiocb {
 		struct io_symlink	symlink;
 		struct io_hardlink	hardlink;
 		struct io_msg		msg;
+		struct io_xattr		xattr;
 	};
 
 	u8				opcode;
@@ -1281,6 +1289,14 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.iopoll			= 1,
 	},
+	[IORING_OP_FSETXATTR] = {
+		.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() */
@@ -2333,6 +2349,8 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
 
 static inline void io_req_complete(struct io_kiocb *req, s32 res)
 {
+	if (res < 0)
+		req_set_fail(req);
 	__io_req_complete(req, 0, res, 0);
 }
 
@@ -4299,12 +4317,258 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
 				ren->newpath, ren->flags);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	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);
+	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.cvalue = 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);
+
+	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);
+
+		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)
+{
+	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.cvalue = 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)
 {
@@ -4345,8 +4609,6 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
 		ret = do_unlinkat(un->dfd, un->filename);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -4385,8 +4647,6 @@ static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
 	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;
 }
@@ -4431,8 +4691,6 @@ static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
 	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;
 }
@@ -4480,8 +4738,6 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
 				lnk->newpath, lnk->flags);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -4515,8 +4771,6 @@ static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
 		return -ENOTSOCK;
 
 	ret = __sys_shutdown_sock(sock, req->shutdown.how);
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 #else
@@ -4574,7 +4828,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
 done:
 	if (ret != sp->len)
 		req_set_fail(req);
-	io_req_complete(req, ret);
+	__io_req_complete(req, 0, ret, 0);
 	return 0;
 }
 
@@ -4619,7 +4873,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
 done:
 	if (ret != sp->len)
 		req_set_fail(req);
-	io_req_complete(req, ret);
+	__io_req_complete(req, 0, ret, 0);
 	return 0;
 }
 
@@ -4714,8 +4968,6 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
 	ret = vfs_fsync_range(req->file, req->sync.off,
 				end > 0 ? end : LLONG_MAX,
 				req->sync.flags & IORING_FSYNC_DATASYNC);
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -4741,9 +4993,7 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
 		return -EAGAIN;
 	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
 				req->sync.len);
-	if (ret < 0)
-		req_set_fail(req);
-	else
+	if (ret >= 0)
 		fsnotify_modify(req->file);
 	io_req_complete(req, ret);
 	return 0;
@@ -5255,8 +5505,6 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
 		return -EAGAIN;
 
 	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 #else
@@ -5338,9 +5586,6 @@ static int io_statx(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
 		       ctx->buffer);
-
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -5433,8 +5678,6 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = sync_file_range(req->file, req->sync.off, req->sync.len,
 				req->sync.flags);
-	if (ret < 0)
-		req_set_fail(req);
 	io_req_complete(req, ret);
 	return 0;
 }
@@ -7400,6 +7643,14 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_linkat_prep(req, sqe);
 	case IORING_OP_MSG_RING:
 		return io_msg_ring_prep(req, sqe);
+	case IORING_OP_FSETXATTR:
+		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",
@@ -7549,6 +7800,12 @@ static void io_clean_op(struct io_kiocb *req)
 			if (req->statx.filename)
 				putname(req->statx.filename);
 			break;
+		case IORING_OP_SETXATTR:
+		case IORING_OP_FSETXATTR:
+		case IORING_OP_GETXATTR:
+		case IORING_OP_FGETXATTR:
+			__io_xattr_finish(req);
+			break;
 		}
 	}
 	if ((req->flags & REQ_F_POLLED) && req->apoll) {
@@ -7705,6 +7962,18 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_MSG_RING:
 		ret = io_msg_ring(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;
+	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;
@@ -12444,6 +12713,7 @@ 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));