1 files changed, 106 insertions, 66 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index de650df9ac53..3affd96a98ba 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -183,17 +183,12 @@ struct fixed_file_table {
 	struct file		**files;
 };
 
-enum {
-	FFD_F_ATOMIC,
-};
-
 struct fixed_file_data {
 	struct fixed_file_table		*table;
 	struct io_ring_ctx		*ctx;
 
 	struct percpu_ref		refs;
 	struct llist_head		put_llist;
-	unsigned long			state;
 	struct work_struct		ref_work;
 	struct completion		done;
 };
@@ -348,6 +343,7 @@ struct io_accept {
 	struct sockaddr __user		*addr;
 	int __user			*addr_len;
 	int				flags;
+	unsigned long			nofile;
 };
 
 struct io_sync {
@@ -402,6 +398,7 @@ struct io_open {
 	struct filename			*filename;
 	struct statx __user		*buffer;
 	struct open_how			how;
+	unsigned long			nofile;
 };
 
 struct io_files_update {
@@ -1004,6 +1001,7 @@ static void io_kill_timeout(struct io_kiocb *req)
 	if (ret != -1) {
 		atomic_inc(&req->ctx->cq_timeouts);
 		list_del_init(&req->list);
+		req->flags |= REQ_F_COMP_LOCKED;
 		io_cqring_fill_event(req, 0);
 		io_put_req(req);
 	}
@@ -1483,10 +1481,10 @@ static void io_free_req(struct io_kiocb *req)
 __attribute__((nonnull))
 static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
 {
-	io_req_find_next(req, nxtptr);
-
-	if (refcount_dec_and_test(&req->refs))
+	if (refcount_dec_and_test(&req->refs)) {
+		io_req_find_next(req, nxtptr);
 		__io_free_req(req);
+	}
 }
 
 static void io_put_req(struct io_kiocb *req)
@@ -1821,6 +1819,10 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
 		list_add(&req->list, &ctx->poll_list);
 	else
 		list_add_tail(&req->list, &ctx->poll_list);
+
+	if ((ctx->flags & IORING_SETUP_SQPOLL) &&
+	    wq_has_sleeper(&ctx->sqo_wait))
+		wake_up(&ctx->sqo_wait);
 }
 
 static void io_file_put(struct io_submit_state *state)
@@ -2071,7 +2073,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 		ssize_t ret;
 		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
 		*iovec = NULL;
-		return ret;
+		return ret < 0 ? ret : sqe_len;
 	}
 
 	if (req->io) {
@@ -2577,6 +2579,7 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return ret;
 	}
 
+	req->open.nofile = rlimit(RLIMIT_NOFILE);
 	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
@@ -2618,6 +2621,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return ret;
 	}
 
+	req->open.nofile = rlimit(RLIMIT_NOFILE);
 	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
@@ -2636,7 +2640,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret)
 		goto err;
 
-	ret = get_unused_fd_flags(req->open.how.flags);
+	ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile);
 	if (ret < 0)
 		goto err;
 
@@ -3002,6 +3006,11 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
 
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		sr->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+
 	if (!io || req->opcode == IORING_OP_SEND)
 		return 0;
 	/* iovec is already imported */
@@ -3154,6 +3163,11 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
 
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		sr->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+
 	if (!io || req->opcode == IORING_OP_RECV)
 		return 0;
 	/* iovec is already imported */
@@ -3311,6 +3325,7 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	accept->flags = READ_ONCE(sqe->accept_flags);
+	accept->nofile = rlimit(RLIMIT_NOFILE);
 	return 0;
 #else
 	return -EOPNOTSUPP;
@@ -3327,7 +3342,8 @@ static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
 
 	file_flags = force_nonblock ? O_NONBLOCK : 0;
 	ret = __sys_accept4_file(req->file, file_flags, accept->addr,
-					accept->addr_len, accept->flags);
+					accept->addr_len, accept->flags,
+					accept->nofile);
 	if (ret == -EAGAIN && force_nonblock)
 		return -EAGAIN;
 	if (ret == -ERESTARTSYS)
@@ -4121,6 +4137,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
 {
 	ssize_t ret = 0;
 
+	if (!sqe)
+		return 0;
+
 	if (io_op_defs[req->opcode].file_table) {
 		ret = io_grab_files(req);
 		if (unlikely(ret))
@@ -4705,11 +4724,21 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_kiocb *linked_timeout;
 	struct io_kiocb *nxt = NULL;
+	const struct cred *old_creds = NULL;
 	int ret;
 
 again:
 	linked_timeout = io_prep_linked_timeout(req);
 
+	if (req->work.creds && req->work.creds != current_cred()) {
+		if (old_creds)
+			revert_creds(old_creds);
+		if (old_creds == req->work.creds)
+			old_creds = NULL; /* restored original creds */
+		else
+			old_creds = override_creds(req->work.creds);
+	}
+
 	ret = io_issue_sqe(req, sqe, &nxt, true);
 
 	/*
@@ -4735,7 +4764,7 @@ punt:
 
 err:
 	/* drop submission reference */
-	io_put_req(req);
+	io_put_req_find_next(req, &nxt);
 
 	if (linked_timeout) {
 		if (!ret)
@@ -4759,6 +4788,8 @@ done_req:
 			goto punt;
 		goto again;
 	}
+	if (old_creds)
+		revert_creds(old_creds);
 }
 
 static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -4803,7 +4834,6 @@ static inline void io_queue_link_head(struct io_kiocb *req)
 static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			  struct io_submit_state *state, struct io_kiocb **link)
 {
-	const struct cred *old_creds = NULL;
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned int sqe_flags;
 	int ret, id;
@@ -4818,14 +4848,12 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	id = READ_ONCE(sqe->personality);
 	if (id) {
-		const struct cred *personality_creds;
-
-		personality_creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!personality_creds)) {
+		req->work.creds = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!req->work.creds)) {
 			ret = -EINVAL;
 			goto err_req;
 		}
-		old_creds = override_creds(personality_creds);
+		get_cred(req->work.creds);
 	}
 
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
@@ -4837,8 +4865,6 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 err_req:
 		io_cqring_add_event(req, ret);
 		io_double_put_req(req);
-		if (old_creds)
-			revert_creds(old_creds);
 		return false;
 	}
 
@@ -4890,6 +4916,11 @@ err_req:
 		if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
 			req->flags |= REQ_F_LINK;
 			INIT_LIST_HEAD(&req->link_list);
+
+			if (io_alloc_async_ctx(req)) {
+				ret = -EAGAIN;
+				goto err_req;
+			}
 			ret = io_req_defer_prep(req, sqe);
 			if (ret)
 				req->flags |= REQ_F_FAIL_LINK;
@@ -4899,8 +4930,6 @@ err_req:
 		}
 	}
 
-	if (old_creds)
-		revert_creds(old_creds);
 	return true;
 }
 
@@ -5081,9 +5110,8 @@ static int io_sq_thread(void *data)
 	const struct cred *old_cred;
 	mm_segment_t old_fs;
 	DEFINE_WAIT(wait);
-	unsigned inflight;
 	unsigned long timeout;
-	int ret;
+	int ret = 0;
 
 	complete(&ctx->completions[1]);
 
@@ -5091,39 +5119,19 @@ static int io_sq_thread(void *data)
 	set_fs(USER_DS);
 	old_cred = override_creds(ctx->creds);
 
-	ret = timeout = inflight = 0;
+	timeout = jiffies + ctx->sq_thread_idle;
 	while (!kthread_should_park()) {
 		unsigned int to_submit;
 
-		if (inflight) {
+		if (!list_empty(&ctx->poll_list)) {
 			unsigned nr_events = 0;
 
-			if (ctx->flags & IORING_SETUP_IOPOLL) {
-				/*
-				 * inflight is the count of the maximum possible
-				 * entries we submitted, but it can be smaller
-				 * if we dropped some of them. If we don't have
-				 * poll entries available, then we know that we
-				 * have nothing left to poll for. Reset the
-				 * inflight count to zero in that case.
-				 */
-				mutex_lock(&ctx->uring_lock);
-				if (!list_empty(&ctx->poll_list))
-					io_iopoll_getevents(ctx, &nr_events, 0);
-				else
-					inflight = 0;
-				mutex_unlock(&ctx->uring_lock);
-			} else {
-				/*
-				 * Normal IO, just pretend everything completed.
-				 * We don't have to poll completions for that.
-				 */
-				nr_events = inflight;
-			}
-
-			inflight -= nr_events;
-			if (!inflight)
+			mutex_lock(&ctx->uring_lock);
+			if (!list_empty(&ctx->poll_list))
+				io_iopoll_getevents(ctx, &nr_events, 0);
+			else
 				timeout = jiffies + ctx->sq_thread_idle;
+			mutex_unlock(&ctx->uring_lock);
 		}
 
 		to_submit = io_sqring_entries(ctx);
@@ -5152,7 +5160,7 @@ static int io_sq_thread(void *data)
 			 * more IO, we should wait for the application to
 			 * reap events and wake us up.
 			 */
-			if (inflight ||
+			if (!list_empty(&ctx->poll_list) ||
 			    (!time_after(jiffies, timeout) && ret != -EBUSY &&
 			    !percpu_ref_is_dying(&ctx->refs))) {
 				cond_resched();
@@ -5162,6 +5170,19 @@ static int io_sq_thread(void *data)
 			prepare_to_wait(&ctx->sqo_wait, &wait,
 						TASK_INTERRUPTIBLE);
 
+			/*
+			 * While doing polled IO, before going to sleep, we need
+			 * to check if there are new reqs added to poll_list, it
+			 * is because reqs may have been punted to io worker and
+			 * will be added to poll_list later, hence check the
+			 * poll_list again.
+			 */
+			if ((ctx->flags & IORING_SETUP_IOPOLL) &&
+			    !list_empty_careful(&ctx->poll_list)) {
+				finish_wait(&ctx->sqo_wait, &wait);
+				continue;
+			}
+
 			/* Tell userspace we may need a wakeup call */
 			ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
 			/* make sure to read SQ tail after writing flags */
@@ -5189,8 +5210,7 @@ static int io_sq_thread(void *data)
 		mutex_lock(&ctx->uring_lock);
 		ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
 		mutex_unlock(&ctx->uring_lock);
-		if (ret > 0)
-			inflight += ret;
+		timeout = jiffies + ctx->sq_thread_idle;
 	}
 
 	set_fs(old_fs);
@@ -5324,6 +5344,23 @@ static void io_file_ref_kill(struct percpu_ref *ref)
 	complete(&data->done);
 }
 
+static void io_file_ref_exit_and_free(struct work_struct *work)
+{
+	struct fixed_file_data *data;
+
+	data = container_of(work, struct fixed_file_data, ref_work);
+
+	/*
+	 * Ensure any percpu-ref atomic switch callback has run, it could have
+	 * been in progress when the files were being unregistered. Once
+	 * that's done, we can safely exit and free the ref and containing
+	 * data structure.
+	 */
+	rcu_barrier();
+	percpu_ref_exit(&data->refs);
+	kfree(data);
+}
+
 static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
 	struct fixed_file_data *data = ctx->file_data;
@@ -5336,14 +5373,14 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	flush_work(&data->ref_work);
 	wait_for_completion(&data->done);
 	io_ring_file_ref_flush(data);
-	percpu_ref_exit(&data->refs);
 
 	__io_sqe_files_unregister(ctx);
 	nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
 	for (i = 0; i < nr_tables; i++)
 		kfree(data->table[i].files);
 	kfree(data->table);
-	kfree(data);
+	INIT_WORK(&data->ref_work, io_file_ref_exit_and_free);
+	queue_work(system_wq, &data->ref_work);
 	ctx->file_data = NULL;
 	ctx->nr_user_files = 0;
 	return 0;
@@ -5595,7 +5632,6 @@ static void io_ring_file_ref_switch(struct work_struct *work)
 
 	data = container_of(work, struct fixed_file_data, ref_work);
 	io_ring_file_ref_flush(data);
-	percpu_ref_get(&data->refs);
 	percpu_ref_switch_to_percpu(&data->refs);
 }
 
@@ -5771,8 +5807,13 @@ static void io_atomic_switch(struct percpu_ref *ref)
 {
 	struct fixed_file_data *data;
 
+	/*
+	 * Juggle reference to ensure we hit zero, if needed, so we can
+	 * switch back to percpu mode
+	 */
 	data = container_of(ref, struct fixed_file_data, refs);
-	clear_bit(FFD_F_ATOMIC, &data->state);
+	percpu_ref_put(&data->refs);
+	percpu_ref_get(&data->refs);
 }
 
 static bool io_queue_file_removal(struct fixed_file_data *data,
@@ -5795,11 +5836,7 @@ static bool io_queue_file_removal(struct fixed_file_data *data,
 	llist_add(&pfile->llist, &data->put_llist);
 
 	if (pfile == &pfile_stack) {
-		if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
-			percpu_ref_put(&data->refs);
-			percpu_ref_switch_to_atomic(&data->refs,
-							io_atomic_switch);
-		}
+		percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
 		wait_for_completion(&done);
 		flush_work(&data->ref_work);
 		return false;
@@ -5873,10 +5910,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 		up->offset++;
 	}
 
-	if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
-		percpu_ref_put(&data->refs);
+	if (ref_switch)
 		percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
-	}
 
 	return done ? done : err;
 }
@@ -6334,6 +6369,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_sqe_buffer_unregister(ctx);
 	io_sqe_files_unregister(ctx);
 	io_eventfd_unregister(ctx);
+	idr_destroy(&ctx->personality_idr);
 
 #if defined(CONFIG_UNIX)
 	if (ctx->ring_sock) {
@@ -6647,6 +6683,7 @@ out_fput:
 	return submitted ? submitted : ret;
 }
 
+#ifdef CONFIG_PROC_FS
 static int io_uring_show_cred(int id, void *p, void *data)
 {
 	const struct cred *cred = p;
@@ -6720,6 +6757,7 @@ static void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 		percpu_ref_put(&ctx->refs);
 	}
 }
+#endif
 
 static const struct file_operations io_uring_fops = {
 	.release	= io_uring_release,
@@ -6731,7 +6769,9 @@ static const struct file_operations io_uring_fops = {
 #endif
 	.poll		= io_uring_poll,
 	.fasync		= io_uring_fasync,
+#ifdef CONFIG_PROC_FS
 	.show_fdinfo	= io_uring_show_fdinfo,
+#endif
 };
 
 static int io_allocate_scq_urings(struct io_ring_ctx *ctx,