Merge tag 'for-5.5/io_uring-post-20191128' of git://git.kernel.dk/linux-block

Pull more io_uring updates from Jens Axboe:
 "As mentioned in the first pull request, there was a later batch as
  well. This contains fixes to the stuff that already went in, cleanups,
  and a few later additions. In particular, this contains:

   - Cleanups/fixes/unification of the submission and completion path
     (Pavel,me)

   - Linked timeouts improvements (Pavel,me)

   - Error path fixes (me)

   - Fix lookup window where cancellations wouldn't work (me)

   - Improve DRAIN support (Pavel)

   - Fix backlog flushing -EBUSY on submit (me)

   - Add support for connect(2) (me)

   - Fix for non-iter based fixed IO (Pavel)

   - creds inheritance for async workers (me)

   - Disable cmsg/ancillary data for sendmsg/recvmsg (me)

   - Shrink io_kiocb to 3 cachelines (me)

   - NUMA fix for io-wq (Jann)"

* tag 'for-5.5/io_uring-post-20191128' of git://git.kernel.dk/linux-block: (42 commits)
  io_uring: make poll->wait dynamically allocated
  io-wq: shrink io_wq_work a bit
  io-wq: fix handling of NUMA node IDs
  io_uring: use kzalloc instead of kcalloc for single-element allocations
  io_uring: cleanup io_import_fixed()
  io_uring: inline struct sqe_submit
  io_uring: store timeout's sqe->off in proper place
  net: disallow ancillary data for __sys_{send,recv}msg_file()
  net: separate out the msghdr copy from ___sys_{send,recv}msg()
  io_uring: remove superfluous check for sqe->off in io_accept()
  io_uring: async workers should inherit the user creds
  io-wq: have io_wq_create() take a 'data' argument
  io_uring: fix dead-hung for non-iter fixed rw
  io_uring: add support for IORING_OP_CONNECT
  net: add __sys_connect_file() helper
  io_uring: only return -EBUSY for submit on non-flushed backlog
  io_uring: only !null ptr to io_issue_sqe()
  io_uring: simplify io_req_link_next()
  io_uring: pass only !null to io_req_find_next()
  io_uring: remove io_free_req_find_next()
  ...

fs/io-wq.h

@@ -11,6 +11,7 @@ enum {
 	IO_WQ_WORK_NEEDS_FILES	= 16,
 	IO_WQ_WORK_UNBOUND	= 32,
 	IO_WQ_WORK_INTERNAL	= 64,
+	IO_WQ_WORK_CB		= 128,
 
 	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
 };
@@ -21,15 +22,60 @@ enum io_wq_cancel {
 	IO_WQ_CANCEL_NOTFOUND,	/* work not found */
 };
 
+struct io_wq_work_node {
+	struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+	struct io_wq_work_node *first;
+	struct io_wq_work_node *last;
+};
+
+static inline void wq_list_add_tail(struct io_wq_work_node *node,
+				    struct io_wq_work_list *list)
+{
+	if (!list->first) {
+		list->first = list->last = node;
+	} else {
+		list->last->next = node;
+		list->last = node;
+	}
+}
+
+static inline void wq_node_del(struct io_wq_work_list *list,
+			       struct io_wq_work_node *node,
+			       struct io_wq_work_node *prev)
+{
+	if (node == list->first)
+		list->first = node->next;
+	if (node == list->last)
+		list->last = prev;
+	if (prev)
+		prev->next = node->next;
+}
+
+#define wq_list_for_each(pos, prv, head)			\
+	for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_empty(list)	((list)->first == NULL)
+#define INIT_WQ_LIST(list)	do {				\
+	(list)->first = NULL;					\
+	(list)->last = NULL;					\
+} while (0)
+
 struct io_wq_work {
-	struct list_head list;
+	union {
+		struct io_wq_work_node list;
+		void *data;
+	};
 	void (*func)(struct io_wq_work **);
-	unsigned flags;
 	struct files_struct *files;
+	unsigned flags;
 };
 
 #define INIT_IO_WORK(work, _func)			\
 	do {						\
+		(work)->list.next = NULL;		\
 		(work)->func = _func;			\
 		(work)->flags = 0;			\
 		(work)->files = NULL;			\
@@ -38,9 +84,16 @@ struct io_wq_work {
 typedef void (get_work_fn)(struct io_wq_work *);
 typedef void (put_work_fn)(struct io_wq_work *);
 
-struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm,
-				struct user_struct *user,
-				get_work_fn *get_work, put_work_fn *put_work);
+struct io_wq_data {
+	struct mm_struct *mm;
+	struct user_struct *user;
+	struct cred *creds;
+
+	get_work_fn *get_work;
+	put_work_fn *put_work;
+};
+
+struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
 void io_wq_destroy(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);

include/linux/socket.h

@@ -399,6 +399,9 @@ 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 int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_connect_file(struct file *file,
+			struct sockaddr __user *uservaddr, int addrlen,
+			int file_flags);
 extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
 			 int addrlen);
 extern int __sys_listen(int fd, int backlog);

include/trace/events/io_uring.h

@@ -163,35 +163,35 @@ TRACE_EVENT(io_uring_queue_async_work,
 );
 
 /**
- * io_uring_defer_list - called before the io_uring work added into defer_list
+ * io_uring_defer - called when an io_uring request is deferred
  *
  * @ctx:	pointer to a ring context structure
  * @req:	pointer to a deferred request
- * @shadow: whether request is shadow or not
+ * @user_data:	user data associated with the request
  *
  * Allows to track deferred requests, to get an insight about what requests are
  * not started immediately.
  */
 TRACE_EVENT(io_uring_defer,
 
-	TP_PROTO(void *ctx, void *req, bool shadow),
+	TP_PROTO(void *ctx, void *req, unsigned long long user_data),
 
-	TP_ARGS(ctx, req, shadow),
+	TP_ARGS(ctx, req, user_data),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
 		__field(  void *,	req		)
-		__field(  bool,		shadow	)
+		__field(  unsigned long long, data	)
 	),
 
 	TP_fast_assign(
 		__entry->ctx	= ctx;
 		__entry->req	= req;
-		__entry->shadow	= shadow;
+		__entry->data	= user_data;
 	),
 
-	TP_printk("ring %p, request %p%s", __entry->ctx, __entry->req,
-			  __entry->shadow ? ", shadow": "")
+	TP_printk("ring %p, request %p user_data %llu", __entry->ctx,
+			__entry->req, __entry->data)
 );
 
 /**

include/uapi/linux/io_uring.h

@@ -73,6 +73,7 @@ struct io_uring_sqe {
 #define IORING_OP_ACCEPT	13
 #define IORING_OP_ASYNC_CANCEL	14
 #define IORING_OP_LINK_TIMEOUT	15
+#define IORING_OP_CONNECT	16
 
 /*
  * sqe->fsync_flags

net/socket.c

@@ -1825,32 +1825,46 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
  *	include the -EINPROGRESS status for such sockets.
  */
 
-int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
+int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr,
+		       int addrlen, int file_flags)
 {
 	struct socket *sock;
 	struct sockaddr_storage address;
-	int err, fput_needed;
+	int err;
 
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	sock = sock_from_file(file, &err);
 	if (!sock)
 		goto out;
 	err = move_addr_to_kernel(uservaddr, addrlen, &address);
 	if (err < 0)
-		goto out_put;
+		goto out;
 
 	err =
 	    security_socket_connect(sock, (struct sockaddr *)&address, addrlen);
 	if (err)
-		goto out_put;
+		goto out;
 
 	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
-				 sock->file->f_flags);
-out_put:
-	fput_light(sock->file, fput_needed);
+				 sock->file->f_flags | file_flags);
 out:
 	return err;
 }
 
+int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
+{
+	int ret = -EBADF;
+	struct fd f;
+
+	f = fdget(fd);
+	if (f.file) {
+		ret = __sys_connect_file(f.file, uservaddr, addrlen, 0);
+		if (f.flags)
+			fput(f.file);
+	}
+
+	return ret;
+}
+
 SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
 		int, addrlen)
 {
@@ -2250,15 +2264,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 	return err < 0 ? err : 0;
 }
 
-static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
-			 struct msghdr *msg_sys, unsigned int flags,
-			 struct used_address *used_address,
-			 unsigned int allowed_msghdr_flags)
+static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
+			   unsigned int flags, struct used_address *used_address,
+			   unsigned int allowed_msghdr_flags)
 {
-	struct compat_msghdr __user *msg_compat =
-	    (struct compat_msghdr __user *)msg;
-	struct sockaddr_storage address;
-	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
 	unsigned char ctl[sizeof(struct cmsghdr) + 20]
 				__aligned(sizeof(__kernel_size_t));
 	/* 20 is size of ipv6_pktinfo */
@@ -2266,19 +2275,10 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 	int ctl_len;
 	ssize_t err;
 
-	msg_sys->msg_name = &address;
-
-	if (MSG_CMSG_COMPAT & flags)
-		err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov);
-	else
-		err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
-	if (err < 0)
-		return err;
-
 	err = -ENOBUFS;
 
 	if (msg_sys->msg_controllen > INT_MAX)
-		goto out_freeiov;
+		goto out;
 	flags |= (msg_sys->msg_flags & allowed_msghdr_flags);
 	ctl_len = msg_sys->msg_controllen;
 	if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
@@ -2286,7 +2286,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 		    cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl,
 						     sizeof(ctl));
 		if (err)
-			goto out_freeiov;
+			goto out;
 		ctl_buf = msg_sys->msg_control;
 		ctl_len = msg_sys->msg_controllen;
 	} else if (ctl_len) {
@@ -2295,7 +2295,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 		if (ctl_len > sizeof(ctl)) {
 			ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL);
 			if (ctl_buf == NULL)
-				goto out_freeiov;
+				goto out;
 		}
 		err = -EFAULT;
 		/*
@@ -2341,7 +2341,47 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 out_freectl:
 	if (ctl_buf != ctl)
 		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
-out_freeiov:
+out:
+	return err;
+}
+
+static int sendmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct iovec **iov)
+{
+	int err;
+
+	if (flags & MSG_CMSG_COMPAT) {
+		struct compat_msghdr __user *msg_compat;
+
+		msg_compat = (struct compat_msghdr __user *) umsg;
+		err = get_compat_msghdr(msg, msg_compat, NULL, iov);
+	} else {
+		err = copy_msghdr_from_user(msg, umsg, NULL, iov);
+	}
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
+			 struct msghdr *msg_sys, unsigned int flags,
+			 struct used_address *used_address,
+			 unsigned int allowed_msghdr_flags)
+{
+	struct sockaddr_storage address;
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	ssize_t err;
+
+	msg_sys->msg_name = &address;
+
+	err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov);
+	if (err < 0)
+		return err;
+
+	err = ____sys_sendmsg(sock, msg_sys, flags, used_address,
+				allowed_msghdr_flags);
 	kfree(iov);
 	return err;
 }
@@ -2349,12 +2389,27 @@ 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 *msg,
+long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg,
 			unsigned int flags)
 {
-	struct msghdr msg_sys;
+	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;
+	}
 
-	return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
+	err = ____sys_sendmsg(sock, &msg, flags, NULL, 0);
+out:
+	kfree(iov);
+	return err;
 }
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
@@ -2460,33 +2515,41 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
 	return __sys_sendmmsg(fd, mmsg, vlen, flags, true);
 }
 
-static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
-			 struct msghdr *msg_sys, unsigned int flags, int nosec)
+static int recvmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct sockaddr __user **uaddr,
+			       struct iovec **iov)
 {
-	struct compat_msghdr __user *msg_compat =
-	    (struct compat_msghdr __user *)msg;
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	unsigned long cmsg_ptr;
-	int len;
 	ssize_t err;
 
-	/* kernel mode address */
-	struct sockaddr_storage addr;
-
-	/* user mode address pointers */
-	struct sockaddr __user *uaddr;
-	int __user *uaddr_len = COMPAT_NAMELEN(msg);
+	if (MSG_CMSG_COMPAT & flags) {
+		struct compat_msghdr __user *msg_compat;
 
-	msg_sys->msg_name = &addr;
-
-	if (MSG_CMSG_COMPAT & flags)
-		err = get_compat_msghdr(msg_sys, msg_compat, &uaddr, &iov);
-	else
-		err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov);
+		msg_compat = (struct compat_msghdr __user *) umsg;
+		err = get_compat_msghdr(msg, msg_compat, uaddr, iov);
+	} else {
+		err = copy_msghdr_from_user(msg, umsg, uaddr, iov);
+	}
 	if (err < 0)
 		return err;
 
+	return 0;
+}
+
+static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys,
+			   struct user_msghdr __user *msg,
+			   struct sockaddr __user *uaddr,
+			   unsigned int flags, int nosec)
+{
+	struct compat_msghdr __user *msg_compat =
+					(struct compat_msghdr __user *) msg;
+	int __user *uaddr_len = COMPAT_NAMELEN(msg);
+	struct sockaddr_storage addr;
+	unsigned long cmsg_ptr;
+	int len;
+	ssize_t err;
+
+	msg_sys->msg_name = &addr;
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
 
@@ -2497,7 +2560,7 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 		flags |= MSG_DONTWAIT;
 	err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, flags);
 	if (err < 0)
-		goto out_freeiov;
+		goto out;
 	len = err;
 
 	if (uaddr != NULL) {
@@ -2505,12 +2568,12 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 					msg_sys->msg_namelen, uaddr,
 					uaddr_len);
 		if (err < 0)
-			goto out_freeiov;
+			goto out;
 	}
 	err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT),
 			 COMPAT_FLAGS(msg));
 	if (err)
-		goto out_freeiov;
+		goto out;
 	if (MSG_CMSG_COMPAT & flags)
 		err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr,
 				 &msg_compat->msg_controllen);
@@ -2518,10 +2581,25 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 		err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr,
 				 &msg->msg_controllen);
 	if (err)
-		goto out_freeiov;
+		goto out;
 	err = len;
+out:
+	return err;
+}
+
+static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
+			 struct msghdr *msg_sys, unsigned int flags, int nosec)
+{
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	/* user mode address pointers */
+	struct sockaddr __user *uaddr;
+	ssize_t err;
 
-out_freeiov:
+	err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov);
+	if (err < 0)
+		return err;
+
+	err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec);
 	kfree(iov);
 	return err;
 }
@@ -2530,12 +2608,28 @@ 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 *msg,
+long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg,
 			unsigned int flags)
 {
-	struct msghdr msg_sys;
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	struct sockaddr_storage address;
+	struct msghdr msg = { .msg_name = &address };
+	struct sockaddr __user *uaddr;
+	ssize_t err;
 
-	return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+	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;
+	}
+
+	err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0);
+out:
+	kfree(iov);
+	return err;
 }
 
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,