Adding upstream version 6.7.12.upstream/6.7.12

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 233 insertions, 429 deletions

diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index e7d749991..6e86e6188 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -87,13 +87,10 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 		io_file_bitmap_clear(&ctx->file_table, slot_index);
 	}
 
-	ret = io_scm_file_account(ctx, file);
-	if (!ret) {
-		*io_get_tag_slot(ctx->file_data, slot_index) = 0;
-		io_fixed_file_set(file_slot, file);
-		io_file_bitmap_set(&ctx->file_table, slot_index);
-	}
-	return ret;
+	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
+	io_fixed_file_set(file_slot, file);
+	io_file_bitmap_set(&ctx->file_table, slot_index);
+	return 0;
 }
 
 int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
diff --git a/io_uring/futex.c b/io_uring/futex.c
index 3c3575303..792a03df5 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -159,6 +159,7 @@ bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
 	hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) {
 		if (!io_match_task_safe(req, task, cancel_all))
 			continue;
+		hlist_del_init(&req->hash_node);
 		__io_futex_cancel(ctx, req);
 		found = true;
 	}
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 59f5791c9..13a9d9fcd 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -60,7 +60,6 @@
 #include <linux/net.h>
 #include <net/sock.h>
 #include <net/af_unix.h>
-#include <net/scm.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -177,19 +176,6 @@ static struct ctl_table kernel_io_uring_disabled_table[] = {
 };
 #endif
 
-struct sock *io_uring_get_socket(struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	if (io_is_uring_fops(file)) {
-		struct io_ring_ctx *ctx = file->private_data;
-
-		return ctx->ring_sock->sk;
-	}
-#endif
-	return NULL;
-}
-EXPORT_SYMBOL(io_uring_get_socket);
-
 static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
 {
 	if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
@@ -1188,12 +1174,11 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
 
 static unsigned int handle_tw_list(struct llist_node *node,
 				   struct io_ring_ctx **ctx,
-				   struct io_tw_state *ts,
-				   struct llist_node *last)
+				   struct io_tw_state *ts)
 {
 	unsigned int count = 0;
 
-	while (node && node != last) {
+	do {
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
@@ -1217,7 +1202,7 @@ static unsigned int handle_tw_list(struct llist_node *node,
 			*ctx = NULL;
 			cond_resched();
 		}
-	}
+	} while (node);
 
 	return count;
 }
@@ -1236,22 +1221,6 @@ static inline struct llist_node *io_llist_xchg(struct llist_head *head,
 	return xchg(&head->first, new);
 }
 
-/**
- * io_llist_cmpxchg - possibly swap all entries in a lock-less list
- * @head:	the head of lock-less list to delete all entries
- * @old:	expected old value of the first entry of the list
- * @new:	new entry as the head of the list
- *
- * perform a cmpxchg on the first entry of the list.
- */
-
-static inline struct llist_node *io_llist_cmpxchg(struct llist_head *head,
-						  struct llist_node *old,
-						  struct llist_node *new)
-{
-	return cmpxchg(&head->first, old, new);
-}
-
 static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 {
 	struct llist_node *node = llist_del_all(&tctx->task_list);
@@ -1286,9 +1255,7 @@ void tctx_task_work(struct callback_head *cb)
 	struct io_ring_ctx *ctx = NULL;
 	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
 						  task_work);
-	struct llist_node fake = {};
 	struct llist_node *node;
-	unsigned int loops = 0;
 	unsigned int count = 0;
 
 	if (unlikely(current->flags & PF_EXITING)) {
@@ -1296,21 +1263,9 @@ void tctx_task_work(struct callback_head *cb)
 		return;
 	}
 
-	do {
-		loops++;
-		node = io_llist_xchg(&tctx->task_list, &fake);
-		count += handle_tw_list(node, &ctx, &ts, &fake);
-
-		/* skip expensive cmpxchg if there are items in the list */
-		if (READ_ONCE(tctx->task_list.first) != &fake)
-			continue;
-		if (ts.locked && !wq_list_empty(&ctx->submit_state.compl_reqs)) {
-			io_submit_flush_completions(ctx);
-			if (READ_ONCE(tctx->task_list.first) != &fake)
-				continue;
-		}
-		node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL);
-	} while (node != &fake);
+	node = llist_del_all(&tctx->task_list);
+	if (node)
+		count = handle_tw_list(node, &ctx, &ts);
 
 	ctx_flush_and_put(ctx, &ts);
 
@@ -1318,7 +1273,7 @@ void tctx_task_work(struct callback_head *cb)
 	if (unlikely(atomic_read(&tctx->in_cancel)))
 		io_uring_drop_tctx_refs(current);
 
-	trace_io_uring_task_work_run(tctx, count, loops);
+	trace_io_uring_task_work_run(tctx, count, 1);
 }
 
 static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
@@ -1415,7 +1370,20 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 	}
 }
 
-static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts)
+static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events,
+				       int min_events)
+{
+	if (llist_empty(&ctx->work_llist))
+		return false;
+	if (events < min_events)
+		return true;
+	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+	return false;
+}
+
+static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
+			       int min_events)
 {
 	struct llist_node *node;
 	unsigned int loops = 0;
@@ -1444,18 +1412,20 @@ again:
 	}
 	loops++;
 
-	if (!llist_empty(&ctx->work_llist))
+	if (io_run_local_work_continue(ctx, ret, min_events))
 		goto again;
 	if (ts->locked) {
 		io_submit_flush_completions(ctx);
-		if (!llist_empty(&ctx->work_llist))
+		if (io_run_local_work_continue(ctx, ret, min_events))
 			goto again;
 	}
+
 	trace_io_uring_local_work_run(ctx, ret, loops);
 	return ret;
 }
 
-static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
+static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
+					   int min_events)
 {
 	struct io_tw_state ts = { .locked = true, };
 	int ret;
@@ -1463,20 +1433,20 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
 	if (llist_empty(&ctx->work_llist))
 		return 0;
 
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	/* shouldn't happen! */
 	if (WARN_ON_ONCE(!ts.locked))
 		mutex_lock(&ctx->uring_lock);
 	return ret;
 }
 
-static int io_run_local_work(struct io_ring_ctx *ctx)
+static int io_run_local_work(struct io_ring_ctx *ctx, int min_events)
 {
 	struct io_tw_state ts = {};
 	int ret;
 
 	ts.locked = mutex_trylock(&ctx->uring_lock);
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	if (ts.locked)
 		mutex_unlock(&ctx->uring_lock);
 
@@ -1672,7 +1642,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
 		    io_task_work_pending(ctx)) {
 			u32 tail = ctx->cached_cq_tail;
 
-			(void) io_run_local_work_locked(ctx);
+			(void) io_run_local_work_locked(ctx, min);
 
 			if (task_work_pending(current) ||
 			    wq_list_empty(&ctx->iopoll_list)) {
@@ -2515,7 +2485,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
 {
 	if (!llist_empty(&ctx->work_llist)) {
 		__set_current_state(TASK_RUNNING);
-		if (io_run_local_work(ctx) > 0)
+		if (io_run_local_work(ctx, INT_MAX) > 0)
 			return 0;
 	}
 	if (io_run_task_work() > 0)
@@ -2538,7 +2508,7 @@ static bool current_pending_io(void)
 static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq)
 {
-	int io_wait, ret;
+	int ret;
 
 	if (unlikely(READ_ONCE(ctx->check_cq)))
 		return 1;
@@ -2556,7 +2526,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	 * can take into account that the task is waiting for IO - turns out
 	 * to be important for low QD IO.
 	 */
-	io_wait = current->in_iowait;
 	if (current_pending_io())
 		current->in_iowait = 1;
 	ret = 0;
@@ -2564,7 +2533,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 		schedule();
 	else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS))
 		ret = -ETIME;
-	current->in_iowait = io_wait;
+	current->in_iowait = 0;
 	return ret;
 }
 
@@ -2583,7 +2552,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	if (!io_allowed_run_tw(ctx))
 		return -EEXIST;
 	if (!llist_empty(&ctx->work_llist))
-		io_run_local_work(ctx);
+		io_run_local_work(ctx, min_events);
 	io_run_task_work();
 	io_cqring_overflow_flush(ctx);
 	/* if user messes with these they will just get an early return */
@@ -2621,11 +2590,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
+		int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
 		unsigned long check_cq;
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
-			int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
-
 			atomic_set(&ctx->cq_wait_nr, nr_wait);
 			set_current_state(TASK_INTERRUPTIBLE);
 		} else {
@@ -2644,7 +2612,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		 */
 		io_run_task_work();
 		if (!llist_empty(&ctx->work_llist))
-			io_run_local_work(ctx);
+			io_run_local_work(ctx, nr_wait);
 
 		/*
 		 * Non-local task_work will be run on exit to userspace, but
@@ -2715,7 +2683,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages,
 	struct page **page_array;
 	unsigned int nr_pages;
 	void *page_addr;
-	int ret, i;
+	int ret, i, pinned;
 
 	*npages = 0;
 
@@ -2729,12 +2697,12 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages,
 	if (!page_array)
 		return ERR_PTR(-ENOMEM);
 
-	ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
-					page_array);
-	if (ret != nr_pages) {
-err:
-		io_pages_free(&page_array, ret > 0 ? ret : 0);
-		return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT);
+
+	pinned = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
+				     page_array);
+	if (pinned != nr_pages) {
+		ret = (pinned < 0) ? pinned : -EFAULT;
+		goto free_pages;
 	}
 
 	page_addr = page_address(page_array[0]);
@@ -2748,7 +2716,7 @@ err:
 		 * didn't support this feature.
 		 */
 		if (PageHighMem(page_array[i]))
-			goto err;
+			goto free_pages;
 
 		/*
 		 * No support for discontig pages for now, should either be a
@@ -2757,13 +2725,17 @@ err:
 		 * just fail them with EINVAL.
 		 */
 		if (page_address(page_array[i]) != page_addr)
-			goto err;
+			goto free_pages;
 		page_addr += PAGE_SIZE;
 	}
 
 	*pages = page_array;
 	*npages = nr_pages;
 	return page_to_virt(page_array[0]);
+
+free_pages:
+	io_pages_free(&page_array, pinned > 0 ? pinned : 0);
+	return ERR_PTR(ret);
 }
 
 static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr,
@@ -2785,14 +2757,15 @@ static void io_rings_free(struct io_ring_ctx *ctx)
 	if (!(ctx->flags & IORING_SETUP_NO_MMAP)) {
 		io_mem_free(ctx->rings);
 		io_mem_free(ctx->sq_sqes);
-		ctx->rings = NULL;
-		ctx->sq_sqes = NULL;
 	} else {
 		io_pages_free(&ctx->ring_pages, ctx->n_ring_pages);
 		ctx->n_ring_pages = 0;
 		io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages);
 		ctx->n_sqe_pages = 0;
 	}
+
+	ctx->rings = NULL;
+	ctx->sq_sqes = NULL;
 }
 
 void *io_mem_alloc(size_t size)
@@ -2952,13 +2925,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		io_rsrc_node_destroy(ctx, ctx->rsrc_node);
 
 	WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
-
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		ctx->ring_sock->file = NULL; /* so that iput() is called */
-		sock_release(ctx->ring_sock);
-	}
-#endif
 	WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
 
 	io_alloc_cache_free(&ctx->rsrc_node_cache, io_rsrc_node_cache_free);
@@ -3374,7 +3340,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 
 	if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) &&
 	    io_allowed_defer_tw_run(ctx))
-		ret |= io_run_local_work(ctx) > 0;
+		ret |= io_run_local_work(ctx, INT_MAX) > 0;
 	ret |= io_cancel_defer_files(ctx, task, cancel_all);
 	mutex_lock(&ctx->uring_lock);
 	ret |= io_poll_remove_all(ctx, task, cancel_all);
@@ -3736,7 +3702,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			 * it should handle ownership problems if any.
 			 */
 			if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
-				(void)io_run_local_work_locked(ctx);
+				(void)io_run_local_work_locked(ctx, min_complete);
 		}
 		mutex_unlock(&ctx->uring_lock);
 	}
@@ -3880,32 +3846,12 @@ static int io_uring_install_fd(struct file *file)
 /*
  * Allocate an anonymous fd, this is what constitutes the application
  * visible backing of an io_uring instance. The application mmaps this
- * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
- * we have to tie this fd to a socket for file garbage collection purposes.
+ * fd to gain access to the SQ/CQ ring details.
  */
 static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
-	struct file *file;
-#if defined(CONFIG_UNIX)
-	int ret;
-
-	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
-				&ctx->ring_sock);
-	if (ret)
-		return ERR_PTR(ret);
-#endif
-
-	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
-#if defined(CONFIG_UNIX)
-	if (IS_ERR(file)) {
-		sock_release(ctx->ring_sock);
-		ctx->ring_sock = NULL;
-	} else {
-		ctx->ring_sock->file = file;
-	}
-#endif
-	return file;
 }
 
 static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index c9992cd7f..0d66a7058 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -61,7 +61,6 @@ struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 			       unsigned issue_flags);
 
 void __io_req_task_work_add(struct io_kiocb *req, unsigned flags);
-bool io_is_uring_fops(struct file *file);
 bool io_alloc_async_data(struct io_kiocb *req);
 void io_req_task_queue(struct io_kiocb *req);
 void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
diff --git a/io_uring/net.c b/io_uring/net.c
index 161622029..5a4001139 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -87,7 +87,7 @@ static inline bool io_check_multishot(struct io_kiocb *req,
 	 * generic paths but multipoll may decide to post extra cqes.
 	 */
 	return !(issue_flags & IO_URING_F_IOWQ) ||
-		!(issue_flags & IO_URING_F_MULTISHOT) ||
+		!(req->flags & REQ_F_APOLL_MULTISHOT) ||
 		!req->ctx->task_complete;
 }
 
@@ -204,16 +204,115 @@ static int io_setup_async_msg(struct io_kiocb *req,
 	return -EAGAIN;
 }
 
+#ifdef CONFIG_COMPAT
+static int io_compat_msg_copy_hdr(struct io_kiocb *req,
+				  struct io_async_msghdr *iomsg,
+				  struct compat_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct compat_iovec __user *uiov;
+	int ret;
+
+	if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg)))
+		return -EFAULT;
+
+	uiov = compat_ptr(msg->msg_iov);
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		compat_ssize_t clen;
+
+		iomsg->free_iov = NULL;
+		if (msg->msg_iovlen == 0) {
+			sr->len = 0;
+		} else if (msg->msg_iovlen > 1) {
+			return -EINVAL;
+		} else {
+			if (!access_ok(uiov, sizeof(*uiov)))
+				return -EFAULT;
+			if (__get_user(clen, &uiov->iov_len))
+				return -EFAULT;
+			if (clen < 0)
+				return -EINVAL;
+			sr->len = clen;
+		}
+
+		return 0;
+	}
+
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen,
+				UIO_FASTIOV, &iomsg->free_iov,
+				&iomsg->msg.msg_iter, true);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+#endif
+
+static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
+			   struct user_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	int ret;
+
+	if (copy_from_user(msg, sr->umsg, sizeof(*sr->umsg)))
+		return -EFAULT;
+
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		if (msg->msg_iovlen == 0) {
+			sr->len = iomsg->fast_iov[0].iov_len = 0;
+			iomsg->fast_iov[0].iov_base = NULL;
+			iomsg->free_iov = NULL;
+		} else if (msg->msg_iovlen > 1) {
+			return -EINVAL;
+		} else {
+			if (copy_from_user(iomsg->fast_iov, msg->msg_iov,
+					   sizeof(*msg->msg_iov)))
+				return -EFAULT;
+			sr->len = iomsg->fast_iov[0].iov_len;
+			iomsg->free_iov = NULL;
+		}
+
+		return 0;
+	}
+
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, UIO_FASTIOV,
+				&iomsg->free_iov, &iomsg->msg.msg_iter, false);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+
 static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 			       struct io_async_msghdr *iomsg)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct user_msghdr msg;
 	int ret;
 
 	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->free_iov = iomsg->fast_iov;
-	ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags,
-					&iomsg->free_iov);
+	iomsg->msg.msg_iter.nr_segs = 0;
+
+#ifdef CONFIG_COMPAT
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
+
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE);
+		if (unlikely(ret))
+			return ret;
+
+		return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+	}
+#endif
+
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE);
+	if (unlikely(ret))
+		return ret;
+
+	ret = __copy_msghdr(&iomsg->msg, &msg, NULL);
+
 	/* save msg_control as sys_sendmsg() overwrites it */
 	sr->msg_control = iomsg->msg.msg_control_user;
 	return ret;
@@ -435,142 +534,77 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
-static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg)
+static int io_recvmsg_mshot_prep(struct io_kiocb *req,
+				 struct io_async_msghdr *iomsg,
+				 int namelen, size_t controllen)
 {
-	int hdr;
-
-	if (iomsg->namelen < 0)
-		return true;
-	if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out),
-			       iomsg->namelen, &hdr))
-		return true;
-	if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr))
-		return true;
+	if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) ==
+			  (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) {
+		int hdr;
+
+		if (unlikely(namelen < 0))
+			return -EOVERFLOW;
+		if (check_add_overflow(sizeof(struct io_uring_recvmsg_out),
+					namelen, &hdr))
+			return -EOVERFLOW;
+		if (check_add_overflow(hdr, controllen, &hdr))
+			return -EOVERFLOW;
+
+		iomsg->namelen = namelen;
+		iomsg->controllen = controllen;
+		return 0;
+	}
 
-	return false;
+	return 0;
 }
 
-static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
-				 struct io_async_msghdr *iomsg)
+static int io_recvmsg_copy_hdr(struct io_kiocb *req,
+			       struct io_async_msghdr *iomsg)
 {
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	struct user_msghdr msg;
 	int ret;
 
-	if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg)))
-		return -EFAULT;
-
-	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		if (msg.msg_iovlen == 0) {
-			sr->len = iomsg->fast_iov[0].iov_len = 0;
-			iomsg->fast_iov[0].iov_base = NULL;
-			iomsg->free_iov = NULL;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov)))
-				return -EFAULT;
-			sr->len = iomsg->fast_iov[0].iov_len;
-			iomsg->free_iov = NULL;
-		}
-
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV,
-				     &iomsg->free_iov, &iomsg->msg.msg_iter,
-				     false);
-		if (ret > 0)
-			ret = 0;
-	}
-
-	return ret;
-}
+	iomsg->msg.msg_name = &iomsg->addr;
+	iomsg->msg.msg_iter.nr_segs = 0;
 
 #ifdef CONFIG_COMPAT
-static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
-					struct io_async_msghdr *iomsg)
-{
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
-	struct compat_msghdr msg;
-	struct compat_iovec __user *uiov;
-	int ret;
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
 
-	if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg)))
-		return -EFAULT;
-
-	ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	uiov = compat_ptr(msg.msg_iov);
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		compat_ssize_t clen;
-
-		iomsg->free_iov = NULL;
-		if (msg.msg_iovlen == 0) {
-			sr->len = 0;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (!access_ok(uiov, sizeof(*uiov)))
-				return -EFAULT;
-			if (__get_user(clen, &uiov->iov_len))
-				return -EFAULT;
-			if (clen < 0)
-				return -EINVAL;
-			sr->len = clen;
-		}
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST);
+		if (unlikely(ret))
+			return ret;
 
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen,
-				   UIO_FASTIOV, &iomsg->free_iov,
-				   &iomsg->msg.msg_iter, true);
-		if (ret < 0)
+		ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr);
+		if (unlikely(ret))
 			return ret;
-	}
 
-	return 0;
-}
+		return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen,
+						cmsg.msg_controllen);
+	}
 #endif
 
-static int io_recvmsg_copy_hdr(struct io_kiocb *req,
-			       struct io_async_msghdr *iomsg)
-{
-	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->msg.msg_iter.nr_segs = 0;
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST);
+	if (unlikely(ret))
+		return ret;
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return __io_compat_recvmsg_copy_hdr(req, iomsg);
-#endif
+	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
+	if (unlikely(ret))
+		return ret;
 
-	return __io_recvmsg_copy_hdr(req, iomsg);
+	return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen,
+					msg.msg_controllen);
 }
 
 int io_recvmsg_prep_async(struct io_kiocb *req)
 {
+	struct io_async_msghdr *iomsg;
 	int ret;
 
 	if (!io_msg_alloc_async_prep(req))
 		return -ENOMEM;
-	ret = io_recvmsg_copy_hdr(req, req->async_data);
+	iomsg = req->async_data;
+	ret = io_recvmsg_copy_hdr(req, iomsg);
 	if (!ret)
 		req->flags |= REQ_F_NEED_CLEANUP;
 	return ret;
@@ -881,7 +915,8 @@ retry_multishot:
 			kfree(kmsg->free_iov);
 		io_netmsg_recycle(req, issue_flags);
 		req->flags &= ~REQ_F_NEED_CLEANUP;
-	}
+	} else if (ret == -EAGAIN)
+		return io_setup_async_msg(req, kmsg, issue_flags);
 
 	return ret;
 }
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 7513afc7b..c6f478962 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -539,14 +539,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->wait.private = (void *) wqe_private;
 
 	if (poll->events & EPOLLEXCLUSIVE) {
-		/*
-		 * Exclusive waits may only wake a limited amount of entries
-		 * rather than all of them, this may interfere with lazy
-		 * wake if someone does wait(events > 1). Ensure we don't do
-		 * lazy wake for those, as we need to process each one as they
-		 * come in.
-		 */
-		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
 	} else {
 		add_wait_queue(head, &poll->wait);
@@ -618,6 +610,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		req->flags &= ~REQ_F_HASH_LOCKED;
 
+
+	/*
+	 * Exclusive waits may only wake a limited amount of entries
+	 * rather than all of them, this may interfere with lazy
+	 * wake if someone does wait(events > 1). Ensure we don't do
+	 * lazy wake for those, as we need to process each one as they
+	 * come in.
+	 */
+	if (poll->events & EPOLLEXCLUSIVE)
+		req->flags |= REQ_F_POLL_NO_LAZY;
+
 	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
 
 	if (unlikely(ipt->error || !ipt->nr_entries)) {
@@ -995,7 +998,6 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
 	struct io_hash_bucket *bucket;
 	struct io_kiocb *preq;
 	int ret2, ret = 0;
-	struct io_tw_state ts = { .locked = true };
 
 	io_ring_submit_lock(ctx, issue_flags);
 	preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket);
@@ -1044,7 +1046,8 @@ found:
 
 	req_set_fail(preq);
 	io_req_set_res(preq, -ECANCELED, 0);
-	io_req_task_complete(preq, &ts);
+	preq->io_task_work.func = io_req_task_complete;
+	io_req_task_work_add(preq);
 out:
 	io_ring_submit_unlock(ctx, issue_flags);
 	if (ret < 0) {
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index f521c5965..4818b7923 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -24,7 +24,6 @@ struct io_rsrc_update {
 };
 
 static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 				  struct io_mapped_ubuf **pimu,
 				  struct page **last_hpage);
@@ -157,7 +156,7 @@ static void io_rsrc_put_work(struct io_rsrc_node *node)
 
 	switch (node->type) {
 	case IORING_RSRC_FILE:
-		io_rsrc_file_put(node->ctx, prsrc);
+		fput(prsrc->file);
 		break;
 	case IORING_RSRC_BUFFER:
 		io_rsrc_buf_put(node->ctx, prsrc);
@@ -402,23 +401,13 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				break;
 			}
 			/*
-			 * Don't allow io_uring instances to be registered. If
-			 * UNIX isn't enabled, then this causes a reference
-			 * cycle and this instance can never get freed. If UNIX
-			 * is enabled we'll handle it just fine, but there's
-			 * still no point in allowing a ring fd as it doesn't
-			 * support regular read/write anyway.
+			 * Don't allow io_uring instances to be registered.
 			 */
 			if (io_is_uring_fops(file)) {
 				fput(file);
 				err = -EBADF;
 				break;
 			}
-			err = io_scm_file_account(ctx, file);
-			if (err) {
-				fput(file);
-				break;
-			}
 			*io_get_tag_slot(data, i) = tag;
 			io_fixed_file_set(file_slot, file);
 			io_file_bitmap_set(&ctx->file_table, i);
@@ -675,22 +664,12 @@ void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		struct file *file = io_file_from_index(&ctx->file_table, i);
 
-		/* skip scm accounted files, they'll be freed by ->ring_sock */
-		if (!file || io_file_need_scm(file))
+		if (!file)
 			continue;
 		io_file_bitmap_clear(&ctx->file_table, i);
 		fput(file);
 	}
 
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		struct sock *sock = ctx->ring_sock->sk;
-		struct sk_buff *skb;
-
-		while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
-			kfree_skb(skb);
-	}
-#endif
 	io_free_file_tables(&ctx->file_table);
 	io_file_table_set_alloc_range(ctx, 0, 0);
 	io_rsrc_data_free(ctx->file_data);
@@ -718,137 +697,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	return ret;
 }
 
-/*
- * Ensure the UNIX gc is aware of our file set, so we are certain that
- * the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing. We account only files that can hold other
- * files because otherwise they can't form a loop and so are not interesting
- * for GC.
- */
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sk = ctx->ring_sock->sk;
-	struct sk_buff_head *head = &sk->sk_receive_queue;
-	struct scm_fp_list *fpl;
-	struct sk_buff *skb;
-
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-
-	/*
-	 * See if we can merge this file into an existing skb SCM_RIGHTS
-	 * file set. If there's no room, fall back to allocating a new skb
-	 * and filling it in.
-	 */
-	spin_lock_irq(&head->lock);
-	skb = skb_peek(head);
-	if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD)
-		__skb_unlink(skb, head);
-	else
-		skb = NULL;
-	spin_unlock_irq(&head->lock);
-
-	if (!skb) {
-		fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
-		if (!fpl)
-			return -ENOMEM;
-
-		skb = alloc_skb(0, GFP_KERNEL);
-		if (!skb) {
-			kfree(fpl);
-			return -ENOMEM;
-		}
-
-		fpl->user = get_uid(current_user());
-		fpl->max = SCM_MAX_FD;
-		fpl->count = 0;
-
-		UNIXCB(skb).fp = fpl;
-		skb->sk = sk;
-		skb->destructor = io_uring_destruct_scm;
-		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
-	}
-
-	fpl = UNIXCB(skb).fp;
-	fpl->fp[fpl->count++] = get_file(file);
-	unix_inflight(fpl->user, file);
-	skb_queue_head(head, skb);
-	fput(file);
-#endif
-	return 0;
-}
-
-static __cold void io_rsrc_file_scm_put(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sock = ctx->ring_sock->sk;
-	struct sk_buff_head list, *head = &sock->sk_receive_queue;
-	struct sk_buff *skb;
-	int i;
-
-	__skb_queue_head_init(&list);
-
-	/*
-	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
-	 * remove this entry and rearrange the file array.
-	 */
-	skb = skb_dequeue(head);
-	while (skb) {
-		struct scm_fp_list *fp;
-
-		fp = UNIXCB(skb).fp;
-		for (i = 0; i < fp->count; i++) {
-			int left;
-
-			if (fp->fp[i] != file)
-				continue;
-
-			unix_notinflight(fp->user, fp->fp[i]);
-			left = fp->count - 1 - i;
-			if (left) {
-				memmove(&fp->fp[i], &fp->fp[i + 1],
-						left * sizeof(struct file *));
-			}
-			fp->count--;
-			if (!fp->count) {
-				kfree_skb(skb);
-				skb = NULL;
-			} else {
-				__skb_queue_tail(&list, skb);
-			}
-			fput(file);
-			file = NULL;
-			break;
-		}
-
-		if (!file)
-			break;
-
-		__skb_queue_tail(&list, skb);
-
-		skb = skb_dequeue(head);
-	}
-
-	if (skb_peek(&list)) {
-		spin_lock_irq(&head->lock);
-		while ((skb = __skb_dequeue(&list)) != NULL)
-			__skb_queue_tail(head, skb);
-		spin_unlock_irq(&head->lock);
-	}
-#endif
-}
-
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
-{
-	struct file *file = prsrc->file;
-
-	if (likely(!io_file_need_scm(file)))
-		fput(file);
-	else
-		io_rsrc_file_scm_put(ctx, file);
-}
-
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags)
 {
@@ -897,21 +745,12 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			goto fail;
 
 		/*
-		 * Don't allow io_uring instances to be registered. If UNIX
-		 * isn't enabled, then this causes a reference cycle and this
-		 * instance can never get freed. If UNIX is enabled we'll
-		 * handle it just fine, but there's still no point in allowing
-		 * a ring fd as it doesn't support regular read/write anyway.
+		 * Don't allow io_uring instances to be registered.
 		 */
 		if (io_is_uring_fops(file)) {
 			fput(file);
 			goto fail;
 		}
-		ret = io_scm_file_account(ctx, file);
-		if (ret) {
-			fput(file);
-			goto fail;
-		}
 		file_slot = io_fixed_file_slot(&ctx->file_table, i);
 		io_fixed_file_set(file_slot, file);
 		io_file_bitmap_set(&ctx->file_table, i);
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 08ac0d8e0..7238b9cfe 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -75,21 +75,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx);
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags);
 
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
-
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return false;
-}
-
-static inline int io_scm_file_account(struct io_ring_ctx *ctx,
-				      struct file *file)
-{
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-	return __io_scm_file_account(ctx, file);
-}
-
 int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
 			     unsigned nr_args);
 int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 9394bf83e..70c5beb05 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -926,6 +926,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	 */
 	if (!file_can_poll(req->file))
 		return -EBADFD;
+	if (issue_flags & IO_URING_F_IOWQ)
+		return -EAGAIN;
 
 	ret = __io_read(req, issue_flags);
 
@@ -940,6 +942,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 		 */
 		if (io_kbuf_recycle(req, issue_flags))
 			rw->len = 0;
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_ISSUE_SKIP_COMPLETE;
 		return -EAGAIN;
 	}
 
diff --git a/io_uring/waitid.c b/io_uring/waitid.c
index 6f8519786..77d340666 100644
--- a/io_uring/waitid.c
+++ b/io_uring/waitid.c
@@ -125,12 +125,6 @@ static void io_waitid_complete(struct io_kiocb *req, int ret)
 
 	lockdep_assert_held(&req->ctx->uring_lock);
 
-	/*
-	 * Did cancel find it meanwhile?
-	 */
-	if (hlist_unhashed(&req->hash_node))
-		return;
-
 	hlist_del_init(&req->hash_node);
 
 	ret = io_waitid_finish(req, ret);
@@ -202,6 +196,7 @@ bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
 	hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) {
 		if (!io_match_task_safe(req, task, cancel_all))
 			continue;
+		hlist_del_init(&req->hash_node);
 		__io_waitid_cancel(ctx, req);
 		found = true;
 	}