Merge tag 'for-5.5/io_uring-20191121' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "A lot of stuff has been going on this cycle, with improving the
  support for networked IO (and hence unbounded request completion
  times) being one of the major themes. There's been a set of fixes done
  this week, I'll send those out as well once we're certain we're fully
  happy with them.

  This contains:

   - Unification of the "normal" submit path and the SQPOLL path (Pavel)

   - Support for sparse (and bigger) file sets, and updating of those
     file sets without needing to unregister/register again.

   - Independently sized CQ ring, instead of just making it always 2x
     the SQ ring size. This makes it more flexible for networked
     applications.

   - Support for overflowed CQ ring, never dropping events but providing
     backpressure on submits.

   - Add support for absolute timeouts, not just relative ones.

   - Support for generic cancellations. This divorces io_uring from
     workqueues as well, which additionally gets us one step closer to
     generic async system call support.

   - With cancellations, we can support grabbing the process file table
     as well, just like we do mm context. This allows support for system
     calls that create file descriptors, like accept4() support that's
     built on top of that.

   - Support for io_uring tracing (Dmitrii)

   - Support for linked timeouts. These abort an operation if it isn't
     completed by the time noted in the linke timeout.

   - Speedup tracking of poll requests

   - Various cleanups making the coder easier to follow (Jackie, Pavel,
     Bob, YueHaibing, me)

   - Update MAINTAINERS with new io_uring list"

* tag 'for-5.5/io_uring-20191121' of git://git.kernel.dk/linux-block: (64 commits)
  io_uring: make POLL_ADD/POLL_REMOVE scale better
  io-wq: remove now redundant struct io_wq_nulls_list
  io_uring: Fix getting file for non-fd opcodes
  io_uring: introduce req_need_defer()
  io_uring: clean up io_uring_cancel_files()
  io-wq: ensure free/busy list browsing see all items
  io-wq: ensure we have a stable view of ->cur_work for cancellations
  io_wq: add get/put_work handlers to io_wq_create()
  io_uring: check for validity of ->rings in teardown
  io_uring: fix potential deadlock in io_poll_wake()
  io_uring: use correct "is IO worker" helper
  io_uring: fix -ENOENT issue with linked timer with short timeout
  io_uring: don't do flush cancel under inflight_lock
  io_uring: flag SQPOLL busy condition to userspace
  io_uring: make ASYNC_CANCEL work with poll and timeout
  io_uring: provide fallback request for OOM situations
  io_uring: convert accept4() -ERESTARTSYS into -EINTR
  io_uring: fix error clear of ->file_table in io_sqe_files_register()
  io_uring: separate the io_free_req and io_free_req_find_next interface
  io_uring: keep io_put_req only responsible for release and put req
  ...

1 files changed, 41 insertions, 24 deletions

diff --git a/net/socket.c b/net/socket.c
index 3c6d60eadf7a..17bc1eee198a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1691,24 +1691,13 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
 	return __sys_listen(fd, backlog);
 }
 
-/*
- *	For accept, we attempt to create a new socket, set up the link
- *	with the client, wake up the client, then return the new
- *	connected fd. We collect the address of the connector in kernel
- *	space and move it to user at the very end. This is unclean because
- *	we open the socket then return an error.
- *
- *	1003.1g adds the ability to recvmsg() to query connection pending
- *	status to recvmsg. We need to add that support in a way thats
- *	clean when we restructure accept also.
- */
-
-int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
-		  int __user *upeer_addrlen, int flags)
+int __sys_accept4_file(struct file *file, unsigned file_flags,
+		       struct sockaddr __user *upeer_sockaddr,
+		       int __user *upeer_addrlen, int flags)
 {
 	struct socket *sock, *newsock;
 	struct file *newfile;
-	int err, len, newfd, fput_needed;
+	int err, len, newfd;
 	struct sockaddr_storage address;
 
 	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
@@ -1717,14 +1706,14 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	sock = sock_from_file(file, &err);
 	if (!sock)
 		goto out;
 
 	err = -ENFILE;
 	newsock = sock_alloc();
 	if (!newsock)
-		goto out_put;
+		goto out;
 
 	newsock->type = sock->type;
 	newsock->ops = sock->ops;
@@ -1739,20 +1728,21 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);
-		goto out_put;
+		goto out;
 	}
 	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
 	if (IS_ERR(newfile)) {
 		err = PTR_ERR(newfile);
 		put_unused_fd(newfd);
-		goto out_put;
+		goto out;
 	}
 
 	err = security_socket_accept(sock, newsock);
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
+	err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags,
+					false);
 	if (err < 0)
 		goto out_fd;
 
@@ -1773,15 +1763,42 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 
 	fd_install(newfd, newfile);
 	err = newfd;
-
-out_put:
-	fput_light(sock->file, fput_needed);
 out:
 	return err;
 out_fd:
 	fput(newfile);
 	put_unused_fd(newfd);
-	goto out_put;
+	goto out;
+
+}
+
+/*
+ *	For accept, we attempt to create a new socket, set up the link
+ *	with the client, wake up the client, then return the new
+ *	connected fd. We collect the address of the connector in kernel
+ *	space and move it to user at the very end. This is unclean because
+ *	we open the socket then return an error.
+ *
+ *	1003.1g adds the ability to recvmsg() to query connection pending
+ *	status to recvmsg. We need to add that support in a way thats
+ *	clean when we restructure accept also.
+ */
+
+int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+		  int __user *upeer_addrlen, int flags)
+{
+	int ret = -EBADF;
+	struct fd f;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = __sys_accept4_file(f.file, 0, upeer_sockaddr,
+						upeer_addrlen, flags);
+		if (f.flags)
+			fput(f.file);
+	}
+
+	return ret;
 }
 
 SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,