Merge tag 'io_uring-5.6-20200320' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "Two different fixes in here:

   - Fix for a potential NULL pointer deref for links with async or
     drain marked (Pavel)

   - Fix for not properly checking RLIMIT_NOFILE for async punted
     operations.

     This affects openat/openat2, which were added this cycle, and
     accept4. I did a full audit of other cases where we might check
     current->signal->rlim[] and found only RLIMIT_FSIZE for buffered
     writes and fallocate. That one is fixed and queued for 5.7 and
     marked stable"

* tag 'io_uring-5.6-20200320' of git://git.kernel.dk/linux-block:
  io_uring: make sure accept honor rlimit nofile
  io_uring: make sure openat/openat2 honor rlimit nofile
  io_uring: NULL-deref for IOSQE_{ASYNC,DRAIN}

Author: torvalds

fs/file.c

@@ -540,9 +540,14 @@ static int alloc_fd(unsigned start, unsigned flags)
 	return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
 }
 
+int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
+{
+	return __alloc_fd(current->files, 0, nofile, flags);
+}
+
 int get_unused_fd_flags(unsigned flags)
 {
-	return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags);
+	return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE));
 }
 EXPORT_SYMBOL(get_unused_fd_flags);
 

fs/io_uring.c

@@ -343,6 +343,7 @@ struct io_accept {
 	struct sockaddr __user		*addr;
 	int __user			*addr_len;
 	int				flags;
+	unsigned long			nofile;
 };
 
 struct io_sync {
@@ -397,6 +398,7 @@ struct io_open {
 	struct filename			*filename;
 	struct statx __user		*buffer;
 	struct open_how			how;
+	unsigned long			nofile;
 };
 
 struct io_files_update {
@@ -2577,6 +2579,7 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return ret;
 	}
 
+	req->open.nofile = rlimit(RLIMIT_NOFILE);
 	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
@@ -2618,6 +2621,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return ret;
 	}
 
+	req->open.nofile = rlimit(RLIMIT_NOFILE);
 	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
@@ -2636,7 +2640,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret)
 		goto err;
 
-	ret = get_unused_fd_flags(req->open.how.flags);
+	ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile);
 	if (ret < 0)
 		goto err;
 
@@ -3321,6 +3325,7 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	accept->flags = READ_ONCE(sqe->accept_flags);
+	accept->nofile = rlimit(RLIMIT_NOFILE);
 	return 0;
 #else
 	return -EOPNOTSUPP;
@@ -3337,7 +3342,8 @@ static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
 
 	file_flags = force_nonblock ? O_NONBLOCK : 0;
 	ret = __sys_accept4_file(req->file, file_flags, accept->addr,
-					accept->addr_len, accept->flags);
+					accept->addr_len, accept->flags,
+					accept->nofile);
 	if (ret == -EAGAIN && force_nonblock)
 		return -EAGAIN;
 	if (ret == -ERESTARTSYS)
@@ -4131,6 +4137,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
 {
 	ssize_t ret = 0;
 
+	if (!sqe)
+		return 0;
+
 	if (io_op_defs[req->opcode].file_table) {
 		ret = io_grab_files(req);
 		if (unlikely(ret))
@@ -4907,6 +4916,11 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
 			req->flags |= REQ_F_LINK;
 			INIT_LIST_HEAD(&req->link_list);
+
+			if (io_alloc_async_ctx(req)) {
+				ret = -EAGAIN;
+				goto err_req;
+			}
 			ret = io_req_defer_prep(req, sqe);
 			if (ret)
 				req->flags |= REQ_F_FAIL_LINK;

include/linux/file.h

@@ -85,6 +85,7 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
 extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
+extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
 

include/linux/socket.h

@@ -401,7 +401,8 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			int addr_len);
 extern int __sys_accept4_file(struct file *file, unsigned file_flags,
 			struct sockaddr __user *upeer_sockaddr,
-			 int __user *upeer_addrlen, int flags);
+			 int __user *upeer_addrlen, int flags,
+			 unsigned long nofile);
 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);

net/socket.c

@@ -1707,7 +1707,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
 
 int __sys_accept4_file(struct file *file, unsigned file_flags,
 		       struct sockaddr __user *upeer_sockaddr,
-		       int __user *upeer_addrlen, int flags)
+		       int __user *upeer_addrlen, int flags,
+		       unsigned long nofile)
 {
 	struct socket *sock, *newsock;
 	struct file *newfile;
@@ -1738,7 +1739,7 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	 */
 	__module_get(newsock->ops->owner);
 
-	newfd = get_unused_fd_flags(flags);
+	newfd = __get_unused_fd_flags(flags, nofile);
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);
@@ -1807,7 +1808,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 	f = fdget(fd);
 	if (f.file) {
 		ret = __sys_accept4_file(f.file, 0, upeer_sockaddr,
-						upeer_addrlen, flags);
+						upeer_addrlen, flags,
+						rlimit(RLIMIT_NOFILE));
 		if (f.flags)
 			fput(f.file);
 	}