1 files changed, 85 insertions, 24 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a78201b96179..74bc4a04befa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -890,6 +890,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				 struct io_uring_files_update *ip,
 				 unsigned nr_args);
 static int io_grab_files(struct io_kiocb *req);
+static void io_complete_rw_common(struct kiocb *kiocb, long res);
 static void io_cleanup_req(struct io_kiocb *req);
 static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 		       int fd, struct file **out_file, bool fixed);
@@ -1095,6 +1096,8 @@ static inline void io_prep_async_work(struct io_kiocb *req,
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 
+	io_req_init_async(req);
+
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file)
 			io_wq_hash_work(&req->work, file_inode(req->file));
@@ -1103,7 +1106,6 @@ static inline void io_prep_async_work(struct io_kiocb *req,
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
 
-	io_req_init_async(req);
 	io_req_work_grab_env(req, def);
 
 	*link = io_prep_linked_timeout(req);
@@ -1273,6 +1275,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (cqe) {
 		clear_bit(0, &ctx->sq_check_overflow);
 		clear_bit(0, &ctx->cq_check_overflow);
+		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
@@ -1310,6 +1313,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		if (list_empty(&ctx->cq_overflow_list)) {
 			set_bit(0, &ctx->sq_check_overflow);
 			set_bit(0, &ctx->cq_check_overflow);
+			ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
 		}
 		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
@@ -1749,6 +1753,14 @@ static void io_iopoll_queue(struct list_head *again)
 	do {
 		req = list_first_entry(again, struct io_kiocb, list);
 		list_del(&req->list);
+
+		/* shouldn't happen unless io_uring is dying, cancel reqs */
+		if (unlikely(!current->mm)) {
+			io_complete_rw_common(&req->rw.kiocb, -EAGAIN);
+			io_put_req(req);
+			continue;
+		}
+
 		refcount_inc(&req->refs);
 		io_queue_async_work(req);
 	} while (!list_empty(again));
@@ -1994,10 +2006,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 
 	WRITE_ONCE(req->result, res);
 	/* order with io_poll_complete() checking ->result */
-	if (res != -EAGAIN) {
-		smp_wmb();
-		WRITE_ONCE(req->iopoll_completed, 1);
-	}
+	smp_wmb();
+	WRITE_ONCE(req->iopoll_completed, 1);
 }
 
 /*
@@ -3544,6 +3554,7 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 	ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
 					&io->msg.iov);
@@ -3725,6 +3736,7 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 
 static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
 {
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 
 #ifdef CONFIG_COMPAT
@@ -3833,10 +3845,16 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
 
 		ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
 						kmsg->uaddr, flags);
-		if (force_nonblock && ret == -EAGAIN)
-			return io_setup_async_msg(req, kmsg);
+		if (force_nonblock && ret == -EAGAIN) {
+			ret = io_setup_async_msg(req, kmsg);
+			if (ret != -EAGAIN)
+				kfree(kbuf);
+			return ret;
+		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
+		if (kbuf)
+			kfree(kbuf);
 	}
 
 	if (kmsg && kmsg->iov != kmsg->fast_iov)
@@ -4065,6 +4083,29 @@ struct io_poll_table {
 	int error;
 };
 
+static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
+{
+	struct task_struct *tsk = req->task;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret, notify = TWA_RESUME;
+
+	/*
+	 * SQPOLL kernel thread doesn't need notification, just a wakeup.
+	 * If we're not using an eventfd, then TWA_RESUME is always fine,
+	 * as we won't have dependencies between request completions for
+	 * other kernel wait conditions.
+	 */
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		notify = 0;
+	else if (ctx->cq_ev_fd)
+		notify = TWA_SIGNAL;
+
+	ret = task_work_add(tsk, cb, notify);
+	if (!ret)
+		wake_up_process(tsk);
+	return ret;
+}
+
 static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 			   __poll_t mask, task_work_func_t func)
 {
@@ -4088,13 +4129,13 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	 * of executing it. We can't safely execute it anyway, as we may not
 	 * have the needed state needed for it anyway.
 	 */
-	ret = task_work_add(tsk, &req->task_work, true);
+	ret = io_req_task_work_add(req, &req->task_work);
 	if (unlikely(ret)) {
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, true);
+		task_work_add(tsk, &req->task_work, 0);
+		wake_up_process(tsk);
 	}
-	wake_up_process(tsk);
 	return 1;
 }
 
@@ -5353,9 +5394,6 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) {
 		const bool in_async = io_wq_current_is_worker();
 
-		if (req->result == -EAGAIN)
-			return -EAGAIN;
-
 		/* workqueue context doesn't hold uring_lock, grab it now */
 		if (in_async)
 			mutex_lock(&ctx->uring_lock);
@@ -6011,7 +6049,7 @@ static int io_sq_thread(void *data)
 		 * If submit got -EBUSY, flag us as needing the application
 		 * to enter the kernel to reap and flush events.
 		 */
-		if (!to_submit || ret == -EBUSY) {
+		if (!to_submit || ret == -EBUSY || need_resched()) {
 			/*
 			 * Drop cur_mm before scheduling, we can't hold it for
 			 * long periods (or over schedule()). Do this before
@@ -6027,7 +6065,7 @@ static int io_sq_thread(void *data)
 			 * more IO, we should wait for the application to
 			 * reap events and wake us up.
 			 */
-			if (!list_empty(&ctx->poll_list) ||
+			if (!list_empty(&ctx->poll_list) || need_resched() ||
 			    (!time_after(jiffies, timeout) && ret != -EBUSY &&
 			    !percpu_ref_is_dying(&ctx->refs))) {
 				if (current->task_works)
@@ -6053,9 +6091,9 @@ static int io_sq_thread(void *data)
 			}
 
 			/* Tell userspace we may need a wakeup call */
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
-			/* make sure to read SQ tail after writing flags */
-			smp_mb();
+			spin_unlock_irq(&ctx->completion_lock);
 
 			to_submit = io_sqring_entries(ctx);
 			if (!to_submit || ret == -EBUSY) {
@@ -6073,13 +6111,17 @@ static int io_sq_thread(void *data)
 				schedule();
 				finish_wait(&ctx->sqo_wait, &wait);
 
+				spin_lock_irq(&ctx->completion_lock);
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				spin_unlock_irq(&ctx->completion_lock);
 				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+			spin_unlock_irq(&ctx->completion_lock);
 		}
 
 		mutex_lock(&ctx->uring_lock);
@@ -6178,15 +6220,23 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	do {
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
+		/* make sure we run task_work before checking for signals */
 		if (current->task_works)
 			task_work_run();
-		if (io_should_wake(&iowq, false))
-			break;
-		schedule();
 		if (signal_pending(current)) {
+			if (current->jobctl & JOBCTL_TASK_WORK) {
+				spin_lock_irq(&current->sighand->siglock);
+				current->jobctl &= ~JOBCTL_TASK_WORK;
+				recalc_sigpending();
+				spin_unlock_irq(&current->sighand->siglock);
+				continue;
+			}
 			ret = -EINTR;
 			break;
 		}
+		if (io_should_wake(&iowq, false))
+			break;
+		schedule();
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
 
@@ -6658,6 +6708,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		for (i = 0; i < nr_tables; i++)
 			kfree(ctx->file_data->table[i].files);
 
+		percpu_ref_exit(&ctx->file_data->refs);
 		kfree(ctx->file_data->table);
 		kfree(ctx->file_data);
 		ctx->file_data = NULL;
@@ -6810,8 +6861,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 			}
 			table->files[index] = file;
 			err = io_sqe_file_register(ctx, file, i);
-			if (err)
+			if (err) {
+				fput(file);
 				break;
+			}
 		}
 		nr_args--;
 		done++;
@@ -7307,9 +7360,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_mem_free(ctx->sq_sqes);
 
 	percpu_ref_exit(&ctx->refs);
-	if (ctx->account_mem)
-		io_unaccount_mem(ctx->user,
-				ring_pages(ctx->sq_entries, ctx->cq_entries));
 	free_uid(ctx->user);
 	put_cred(ctx->creds);
 	kfree(ctx->cancel_hash);
@@ -7394,6 +7444,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	if (ctx->rings)
 		io_cqring_overflow_flush(ctx, true);
 	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+
+	/*
+	 * Do this upfront, so we won't have a grace period where the ring
+	 * is closed but resources aren't reaped yet. This can cause
+	 * spurious failure in setting up a new ring.
+	 */
+	if (ctx->account_mem)
+		io_unaccount_mem(ctx->user,
+				ring_pages(ctx->sq_entries, ctx->cq_entries));
+
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
 	queue_work(system_wq, &ctx->exit_work);
 }
@@ -7453,6 +7513,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			if (list_empty(&ctx->cq_overflow_list)) {
 				clear_bit(0, &ctx->sq_check_overflow);
 				clear_bit(0, &ctx->cq_check_overflow);
+				ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 			}
 			spin_unlock_irq(&ctx->completion_lock);