Merge branch 'for-5.19/io_uring-socket' into for-5.19/io_uring-passthrough

* for-5.19/io_uring-socket:
  io_uring: use the text representation of ops in trace
  io_uring: rename op -> opcode
  io_uring: add io_uring_get_opcode
  io_uring: add type to op enum
  io_uring: add socket(2) support
  net: add __sys_socket_file()
  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

fs/internal.h

@@ -191,3 +191,32 @@ long splice_file_to_pipe(struct file *in,
 			 struct pipe_inode_info *opipe,
 			 loff_t *offset,
 			 size_t len, unsigned int flags);
+
+/*
+ * fs/xattr.c:
+ */
+struct xattr_name {
+	char name[XATTR_NAME_MAX + 1];
+};
+
+struct xattr_ctx {
+	/* Value of attribute */
+	union {
+		const void __user *cvalue;
+		void __user *value;
+	};
+	void *kvalue;
+	size_t size;
+	/* Attribute name */
+	struct xattr_name *kname;
+	unsigned int flags;
+};
+
+
+ssize_t do_getxattr(struct user_namespace *mnt_userns,
+		    struct dentry *d,
+		    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,
+		struct xattr_ctx *ctx);

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>
@@ -578,6 +579,16 @@ struct io_accept {
 	unsigned long			nofile;
 };
 
+struct io_socket {
+	struct file			*file;
+	int				domain;
+	int				type;
+	int				protocol;
+	int				flags;
+	u32				file_slot;
+	unsigned long			nofile;
+};
+
 struct io_sync {
 	struct file			*file;
 	loff_t				len;
@@ -782,6 +793,12 @@ 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,
@@ -946,6 +963,8 @@ struct io_kiocb {
 		struct io_symlink	symlink;
 		struct io_hardlink	hardlink;
 		struct io_msg		msg;
+		struct io_xattr		xattr;
+		struct io_socket	sock;
 	};
 
 	u8				opcode;
@@ -1246,6 +1265,17 @@ 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] = {},
+	[IORING_OP_SOCKET] = {
+		.audit_skip		= 1,
+	},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -1290,6 +1320,107 @@ static struct kmem_cache *req_cachep;
 
 static const struct file_operations io_uring_fops;
 
+const char *io_uring_get_opcode(u8 opcode)
+{
+	switch ((enum io_uring_op)opcode) {
+	case IORING_OP_NOP:
+		return "NOP";
+	case IORING_OP_READV:
+		return "READV";
+	case IORING_OP_WRITEV:
+		return "WRITEV";
+	case IORING_OP_FSYNC:
+		return "FSYNC";
+	case IORING_OP_READ_FIXED:
+		return "READ_FIXED";
+	case IORING_OP_WRITE_FIXED:
+		return "WRITE_FIXED";
+	case IORING_OP_POLL_ADD:
+		return "POLL_ADD";
+	case IORING_OP_POLL_REMOVE:
+		return "POLL_REMOVE";
+	case IORING_OP_SYNC_FILE_RANGE:
+		return "SYNC_FILE_RANGE";
+	case IORING_OP_SENDMSG:
+		return "SENDMSG";
+	case IORING_OP_RECVMSG:
+		return "RECVMSG";
+	case IORING_OP_TIMEOUT:
+		return "TIMEOUT";
+	case IORING_OP_TIMEOUT_REMOVE:
+		return "TIMEOUT_REMOVE";
+	case IORING_OP_ACCEPT:
+		return "ACCEPT";
+	case IORING_OP_ASYNC_CANCEL:
+		return "ASYNC_CANCEL";
+	case IORING_OP_LINK_TIMEOUT:
+		return "LINK_TIMEOUT";
+	case IORING_OP_CONNECT:
+		return "CONNECT";
+	case IORING_OP_FALLOCATE:
+		return "FALLOCATE";
+	case IORING_OP_OPENAT:
+		return "OPENAT";
+	case IORING_OP_CLOSE:
+		return "CLOSE";
+	case IORING_OP_FILES_UPDATE:
+		return "FILES_UPDATE";
+	case IORING_OP_STATX:
+		return "STATX";
+	case IORING_OP_READ:
+		return "READ";
+	case IORING_OP_WRITE:
+		return "WRITE";
+	case IORING_OP_FADVISE:
+		return "FADVISE";
+	case IORING_OP_MADVISE:
+		return "MADVISE";
+	case IORING_OP_SEND:
+		return "SEND";
+	case IORING_OP_RECV:
+		return "RECV";
+	case IORING_OP_OPENAT2:
+		return "OPENAT2";
+	case IORING_OP_EPOLL_CTL:
+		return "EPOLL_CTL";
+	case IORING_OP_SPLICE:
+		return "SPLICE";
+	case IORING_OP_PROVIDE_BUFFERS:
+		return "PROVIDE_BUFFERS";
+	case IORING_OP_REMOVE_BUFFERS:
+		return "REMOVE_BUFFERS";
+	case IORING_OP_TEE:
+		return "TEE";
+	case IORING_OP_SHUTDOWN:
+		return "SHUTDOWN";
+	case IORING_OP_RENAMEAT:
+		return "RENAMEAT";
+	case IORING_OP_UNLINKAT:
+		return "UNLINKAT";
+	case IORING_OP_MKDIRAT:
+		return "MKDIRAT";
+	case IORING_OP_SYMLINKAT:
+		return "SYMLINKAT";
+	case IORING_OP_LINKAT:
+		return "LINKAT";
+	case IORING_OP_MSG_RING:
+		return "MSG_RING";
+	case IORING_OP_FSETXATTR:
+		return "FSETXATTR";
+	case IORING_OP_SETXATTR:
+		return "SETXATTR";
+	case IORING_OP_FGETXATTR:
+		return "FGETXATTR";
+	case IORING_OP_GETXATTR:
+		return "GETXATTR";
+	case IORING_OP_SOCKET:
+		return "SOCKET";
+	case IORING_OP_LAST:
+		return "INVALID";
+	}
+	return "INVALID";
+}
+
 struct sock *io_uring_get_socket(struct file *file)
 {
 #if defined(CONFIG_UNIX)
@@ -4205,6 +4336,257 @@ 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_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)
 {
@@ -5760,6 +6142,62 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_socket *sock = &req->sock;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->addr || sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+
+	sock->domain = READ_ONCE(sqe->fd);
+	sock->type = READ_ONCE(sqe->off);
+	sock->protocol = READ_ONCE(sqe->len);
+	sock->file_slot = READ_ONCE(sqe->file_index);
+	sock->nofile = rlimit(RLIMIT_NOFILE);
+
+	sock->flags = sock->type & ~SOCK_TYPE_MASK;
+	if (sock->file_slot && (sock->flags & SOCK_CLOEXEC))
+		return -EINVAL;
+	if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return -EINVAL;
+	return 0;
+}
+
+static int io_socket(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_socket *sock = &req->sock;
+	bool fixed = !!sock->file_slot;
+	struct file *file;
+	int ret, fd;
+
+	if (!fixed) {
+		fd = __get_unused_fd_flags(sock->flags, sock->nofile);
+		if (unlikely(fd < 0))
+			return fd;
+	}
+	file = __sys_socket_file(sock->domain, sock->type, sock->protocol);
+	if (IS_ERR(file)) {
+		if (!fixed)
+			put_unused_fd(fd);
+		ret = PTR_ERR(file);
+		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
+			return -EAGAIN;
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+		req_set_fail(req);
+	} else if (!fixed) {
+		fd_install(fd, file);
+		ret = fd;
+	} else {
+		ret = io_install_fixed_file(req, file, issue_flags,
+					    sock->file_slot - 1);
+	}
+	__io_req_complete(req, issue_flags, ret, 0);
+	return 0;
+}
+
 static int io_connect_prep_async(struct io_kiocb *req)
 {
 	struct io_async_connect *io = req->async_data;
@@ -5845,6 +6283,7 @@ IO_NETOP_PREP_ASYNC(sendmsg);
 IO_NETOP_PREP_ASYNC(recvmsg);
 IO_NETOP_PREP_ASYNC(connect);
 IO_NETOP_PREP(accept);
+IO_NETOP_PREP(socket);
 IO_NETOP_FN(send);
 IO_NETOP_FN(recv);
 #endif /* CONFIG_NET */
@@ -7147,6 +7586,16 @@ 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);
+	case IORING_OP_SOCKET:
+		return io_socket_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -7296,6 +7745,12 @@ 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) {
@@ -7452,6 +7907,21 @@ 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;
+	case IORING_OP_SOCKET:
+		ret = io_socket(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -12025,6 +12495,7 @@ 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));

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)
 {
@@ -539,44 +541,76 @@ 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->cvalue, 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, d_inode(d),
-						      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 dentry *d, 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, d_inode(d),
+						ctx->kvalue, ctx->size);
+}
+
+int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		struct xattr_ctx *ctx)
+{
+	setxattr_convert(mnt_userns, dentry, 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 = {
+		.cvalue   = 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;
 }
 
@@ -642,44 +676,61 @@ 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,
+	struct xattr_ctx *ctx)
 {
 	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;
+	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, d_inode(d),
-						    kvalue, error);
-		if (size && copy_to_user(value, kvalue, error))
+							ctx->kvalue, error);
+		if (ctx->size && copy_to_user(ctx->value, ctx->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;
+}
+
+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;
+	struct xattr_ctx ctx = {
+		.value    = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = 0,
+	};
+
+	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
+	if (error == 0 || error == sizeof(kname.name))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
+	error =  do_getxattr(mnt_userns, d, &ctx);
 
+	kvfree(ctx.kvalue);
 	return error;
 }
 

include/linux/io_uring.h

@@ -10,6 +10,7 @@ struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
+const char *io_uring_get_opcode(u8 opcode);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -42,6 +43,10 @@ static inline void io_uring_files_cancel(void)
 static inline void io_uring_free(struct task_struct *tsk)
 {
 }
+static inline const char *io_uring_get_opcode(u8 opcode)
+{
+	return "";
+}
 #endif
 
 #endif

include/linux/socket.h

@@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags,
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
+extern struct file *__sys_socket_file(int family, int type, int protocol);
 extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
 extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
 			      int addrlen, int file_flags);

include/trace/events/io_uring.h

@@ -7,6 +7,7 @@
 
 #include <linux/tracepoint.h>
 #include <uapi/linux/io_uring.h>
+#include <linux/io_uring.h>
 
 struct io_wq_work;
 
@@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__entry->rw		= rw;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
+		__entry->ctx, __entry->req, __entry->user_data,
+		io_uring_get_opcode(__entry->opcode),
 		__entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
 );
 
@@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer,
 		__entry->opcode	= opcode;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d",
-		__entry->ctx, __entry->req, __entry->data, __entry->opcode)
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s",
+		__entry->ctx, __entry->req, __entry->data,
+		io_uring_get_opcode(__entry->opcode))
 );
 
 /**
@@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link,
 		__entry->link		= link;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
-		__entry->link)
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p",
+		__entry->ctx, __entry->req, __entry->user_data,
+		io_uring_get_opcode(__entry->opcode), __entry->link)
 );
 
 /**
@@ -389,9 +392,9 @@ TRACE_EVENT(io_uring_submit_sqe,
 		__entry->sq_thread	= sq_thread;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, "
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
 		  "non block %d, sq_thread %d", __entry->ctx, __entry->req,
-		  __entry->user_data, __entry->opcode,
+		  __entry->user_data, io_uring_get_opcode(__entry->opcode),
 		  __entry->flags, __entry->force_nonblock, __entry->sq_thread)
 );
 
@@ -433,8 +436,9 @@ TRACE_EVENT(io_uring_poll_arm,
 		__entry->events		= events;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x",
-		  __entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x",
+		  __entry->ctx, __entry->req, __entry->user_data,
+		  io_uring_get_opcode(__entry->opcode),
 		  __entry->mask, __entry->events)
 );
 
@@ -470,8 +474,9 @@ TRACE_EVENT(io_uring_task_add,
 		__entry->mask		= mask;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x",
+		__entry->ctx, __entry->req, __entry->user_data,
+		io_uring_get_opcode(__entry->opcode),
 		__entry->mask)
 );
 
@@ -506,7 +511,7 @@ TRACE_EVENT(io_uring_req_failed,
 		__field( u16,			personality	)
 		__field( u32,			file_index	)
 		__field( u64,			pad1		)
-		__field( u64,			pad2		)
+		__field( u64,			addr3		)
 		__field( int,			error		)
 	),
 
@@ -525,22 +530,24 @@ TRACE_EVENT(io_uring_req_failed,
 		__entry->personality	= sqe->personality;
 		__entry->file_index	= sqe->file_index;
 		__entry->pad1		= sqe->__pad2[0];
-		__entry->pad2		= sqe->__pad2[1];
+		__entry->addr3		= sqe->addr3;
 		__entry->error		= error;
 	),
 
 	TP_printk("ring %p, req %p, user_data 0x%llx, "
-		  "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, "
+		  "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, "
 		  "len=%u, rw_flags=0x%x, buf_index=%d, "
-		  "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d",
+		  "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, "
+		  "error=%d",
 		  __entry->ctx, __entry->req, __entry->user_data,
-		  __entry->opcode, __entry->flags, __entry->ioprio,
+		  io_uring_get_opcode(__entry->opcode),
+		  __entry->flags, __entry->ioprio,
 		  (unsigned long long)__entry->off,
 		  (unsigned long long) __entry->addr, __entry->len,
 		  __entry->op_flags,
 		  __entry->buf_index, __entry->personality, __entry->file_index,
 		  (unsigned long long) __entry->pad1,
-		  (unsigned long long) __entry->pad2, __entry->error)
+		  (unsigned long long) __entry->addr3, __entry->error)
 );
 
 

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 {
@@ -117,7 +119,7 @@ enum {
  */
 #define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
 
-enum {
+enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
 	IORING_OP_WRITEV,
@@ -159,6 +161,11 @@ enum {
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
 	IORING_OP_MSG_RING,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
+	IORING_OP_FGETXATTR,
+	IORING_OP_GETXATTR,
+	IORING_OP_SOCKET,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,

net/socket.c

@@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags)
 struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
-		return file->private_data;	/* set in sock_map_fd */
+		return file->private_data;	/* set in sock_alloc_file */
 
 	return NULL;
 }
@@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
 }
 EXPORT_SYMBOL(sock_create_kern);
 
-int __sys_socket(int family, int type, int protocol)
+static struct socket *__sys_socket_create(int family, int type, int protocol)
 {
-	int retval;
 	struct socket *sock;
-	int flags;
+	int retval;
 
 	/* Check the SOCK_* constants for consistency.  */
 	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
@@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol)
 	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
 	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);
 
-	flags = type & ~SOCK_TYPE_MASK;
-	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
-		return -EINVAL;
+	if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return ERR_PTR(-EINVAL);
 	type &= SOCK_TYPE_MASK;
 
+	retval = sock_create(family, type, protocol, &sock);
+	if (retval < 0)
+		return ERR_PTR(retval);
+
+	return sock;
+}
+
+struct file *__sys_socket_file(int family, int type, int protocol)
+{
+	struct socket *sock;
+	struct file *file;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return ERR_CAST(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	retval = sock_create(family, type, protocol, &sock);
-	if (retval < 0)
-		return retval;
+	file = sock_alloc_file(sock, flags, NULL);
+	if (IS_ERR(file))
+		sock_release(sock);
+
+	return file;
+}
+
+int __sys_socket(int family, int type, int protocol)
+{
+	struct socket *sock;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return PTR_ERR(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
 	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
 }