Merge tag 'for-linus-20191205' of git://git.kernel.dk/linux-block

Pull more block and io_uring updates from Jens Axboe:
 "I wasn't expecting this to be so big, and if I was, I would have used
  separate branches for this. Going forward I'll be doing separate
  branches for the current tree, just like for the next kernel version
  tree. In any case, this contains:

   - Series from Christoph that fixes an inherent race condition with
     zoned devices and revalidation.

   - null_blk zone size fix (Damien)

   - Fix for a regression in this merge window that caused busy spins by
     sending empty disk uevents (Eric)

   - Fix for a regression in this merge window for bfq stats (Hou)

   - Fix for io_uring creds allocation failure handling (me)

   - io_uring -ERESTARTSYS send/recvmsg fix (me)

   - Series that fixes the need for applications to retain state across
     async request punts for io_uring. This one is a bit larger than I
     would have hoped, but I think it's important we get this fixed for
     5.5.

   - connect(2) improvement for io_uring, handling EINPROGRESS instead
     of having applications needing to poll for it (me)

   - Have io_uring use a hash for poll requests instead of an rbtree.
     This turned out to work much better in practice, so I think we
     should make the switch now. For some workloads, even with a fair
     amount of cancellations, the insertion sort is just too expensive.
     (me)

   - Various little io_uring fixes (me, Jackie, Pavel, LimingWu)

   - Fix for brd unaligned IO, and a warning for the future (Ming)

   - Fix for a bio integrity data leak (Justin)

   - bvec_iter_advance() improvement (Pavel)

   - Xen blkback page unmap fix (SeongJae)

  The major items in here are all well tested, and on the liburing side
  we continue to add regression and feature test cases. We're up to 50
  topic cases now, each with anywhere from 1 to more than 10 cases in
  each"

* tag 'for-linus-20191205' of git://git.kernel.dk/linux-block: (33 commits)
  block: fix memleak of bio integrity data
  io_uring: fix a typo in a comment
  bfq-iosched: Ensure bio->bi_blkg is valid before using it
  io_uring: hook all linked requests via link_list
  io_uring: fix error handling in io_queue_link_head
  io_uring: use hash table for poll command lookups
  io-wq: clear node->next on list deletion
  io_uring: ensure deferred timeouts copy necessary data
  io_uring: allow IO_SQE_* flags on IORING_OP_TIMEOUT
  null_blk: remove unused variable warning on !CONFIG_BLK_DEV_ZONED
  brd: warn on un-aligned buffer
  brd: remove max_hw_sectors queue limit
  xen/blkback: Avoid unmapping unmapped grant pages
  io_uring: handle connect -EINPROGRESS like -EAGAIN
  block: set the zone size in blk_revalidate_disk_zones atomically
  block: don't handle bio based drivers in blk_revalidate_disk_zones
  block: allocate the zone bitmaps lazily
  block: replace seq_zones_bitmap with conv_zones_bitmap
  block: simplify blkdev_nr_zones
  block: remove the empty line at the end of blk-zoned.c
  ...

1 files changed, 25 insertions, 51 deletions

diff --git a/net/socket.c b/net/socket.c
index ea28cbb9e2e7..b343db1489bd 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1826,26 +1826,22 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
  *	include the -EINPROGRESS status for such sockets.
  */
 
-int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr,
+int __sys_connect_file(struct file *file, struct sockaddr_storage *address,
 		       int addrlen, int file_flags)
 {
 	struct socket *sock;
-	struct sockaddr_storage address;
 	int err;
 
 	sock = sock_from_file(file, &err);
 	if (!sock)
 		goto out;
-	err = move_addr_to_kernel(uservaddr, addrlen, &address);
-	if (err < 0)
-		goto out;
 
 	err =
-	    security_socket_connect(sock, (struct sockaddr *)&address, addrlen);
+	    security_socket_connect(sock, (struct sockaddr *)address, addrlen);
 	if (err)
 		goto out;
 
-	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
+	err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen,
 				 sock->file->f_flags | file_flags);
 out:
 	return err;
@@ -1858,7 +1854,11 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
 
 	f = fdget(fd);
 	if (f.file) {
-		ret = __sys_connect_file(f.file, uservaddr, addrlen, 0);
+		struct sockaddr_storage address;
+
+		ret = move_addr_to_kernel(uservaddr, addrlen, &address);
+		if (!ret)
+			ret = __sys_connect_file(f.file, &address, addrlen, 0);
 		if (f.flags)
 			fput(f.file);
 	}
@@ -2346,9 +2346,9 @@ out:
 	return err;
 }
 
-static int sendmsg_copy_msghdr(struct msghdr *msg,
-			       struct user_msghdr __user *umsg, unsigned flags,
-			       struct iovec **iov)
+int sendmsg_copy_msghdr(struct msghdr *msg,
+			struct user_msghdr __user *umsg, unsigned flags,
+			struct iovec **iov)
 {
 	int err;
 
@@ -2390,27 +2390,14 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 /*
  *	BSD sendmsg interface
  */
-long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg,
+long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg,
 			unsigned int flags)
 {
-	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
-	struct sockaddr_storage address;
-	struct msghdr msg = { .msg_name = &address };
-	ssize_t err;
-
-	err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov);
-	if (err)
-		return err;
 	/* disallow ancillary data requests from this path */
-	if (msg.msg_control || msg.msg_controllen) {
-		err = -EINVAL;
-		goto out;
-	}
+	if (msg->msg_control || msg->msg_controllen)
+		return -EINVAL;
 
-	err = ____sys_sendmsg(sock, &msg, flags, NULL, 0);
-out:
-	kfree(iov);
-	return err;
+	return ____sys_sendmsg(sock, msg, flags, NULL, 0);
 }
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
@@ -2516,10 +2503,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
 	return __sys_sendmmsg(fd, mmsg, vlen, flags, true);
 }
 
-static int recvmsg_copy_msghdr(struct msghdr *msg,
-			       struct user_msghdr __user *umsg, unsigned flags,
-			       struct sockaddr __user **uaddr,
-			       struct iovec **iov)
+int recvmsg_copy_msghdr(struct msghdr *msg,
+			struct user_msghdr __user *umsg, unsigned flags,
+			struct sockaddr __user **uaddr,
+			struct iovec **iov)
 {
 	ssize_t err;
 
@@ -2609,28 +2596,15 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
  *	BSD recvmsg interface
  */
 
-long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg,
-			unsigned int flags)
+long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
+			struct user_msghdr __user *umsg,
+			struct sockaddr __user *uaddr, unsigned int flags)
 {
-	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
-	struct sockaddr_storage address;
-	struct msghdr msg = { .msg_name = &address };
-	struct sockaddr __user *uaddr;
-	ssize_t err;
-
-	err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov);
-	if (err)
-		return err;
 	/* disallow ancillary data requests from this path */
-	if (msg.msg_control || msg.msg_controllen) {
-		err = -EINVAL;
-		goto out;
-	}
+	if (msg->msg_control || msg->msg_controllen)
+		return -EINVAL;
 
-	err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0);
-out:
-	kfree(iov);
-	return err;
+	return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0);
 }
 
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,