io_uring: remove indirect ctx into sqo injection

We use ->ctx_new_list to notify sqo about new ctx pending, then sqo
should stop and splice it to its sqd->ctx_list, paired with
->sq_thread_comp.

The last one is broken because nobody reinitialises it, and trying to
fix it would only add more complexity and bugs. And the first isn't
really needed as is done under park(), that protects from races well.
Add ctx into sqd->ctx_list directly (under park()), it's much simpler
and allows to kill both, ctx_new_list and sq_thread_comp.

note: apparently there is no real problem at the moment, because
sq_thread_comp is used only by io_sq_thread_finish() followed by
parking, where list_del(&ctx->sqd_list) removes it well regardless
whether it's in the new or the active list.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 3 insertions, 25 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7072c0eb22c1..5c045a9f7ffe 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -262,7 +262,6 @@ struct io_sq_data {
 
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
-	struct list_head	ctx_new_list;
 
 	struct task_struct	*thread;
 	struct wait_queue_head	wait;
@@ -398,7 +397,6 @@ struct io_ring_ctx {
 	struct user_struct	*user;
 
 	struct completion	ref_comp;
-	struct completion	sq_thread_comp;
 
 #if defined(CONFIG_UNIX)
 	struct socket		*ring_sock;
@@ -1137,7 +1135,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->ref_comp);
-	init_completion(&ctx->sq_thread_comp);
 	idr_init(&ctx->io_buffer_idr);
 	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
 	mutex_init(&ctx->uring_lock);
@@ -6640,19 +6637,6 @@ static void io_sqd_update_thread_idle(struct io_sq_data *sqd)
 	sqd->sq_thread_idle = sq_thread_idle;
 }
 
-static void io_sqd_init_new(struct io_sq_data *sqd)
-{
-	struct io_ring_ctx *ctx;
-
-	while (!list_empty(&sqd->ctx_new_list)) {
-		ctx = list_first_entry(&sqd->ctx_new_list, struct io_ring_ctx, sqd_list);
-		list_move_tail(&ctx->sqd_list, &sqd->ctx_list);
-		complete(&ctx->sq_thread_comp);
-	}
-
-	io_sqd_update_thread_idle(sqd);
-}
-
 static int io_sq_thread(void *data)
 {
 	struct io_sq_data *sqd = data;
@@ -6683,11 +6667,8 @@ static int io_sq_thread(void *data)
 			up_read(&sqd->rw_lock);
 			cond_resched();
 			down_read(&sqd->rw_lock);
-			continue;
-		}
-		if (unlikely(!list_empty(&sqd->ctx_new_list))) {
-			io_sqd_init_new(sqd);
 			timeout = jiffies + sqd->sq_thread_idle;
+			continue;
 		}
 		if (fatal_signal_pending(current))
 			break;
@@ -7099,9 +7080,6 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
 
 	if (sqd) {
 		complete(&sqd->startup);
-		if (sqd->thread)
-			wait_for_completion(&ctx->sq_thread_comp);
-
 		io_sq_thread_park(sqd);
 		list_del(&ctx->sqd_list);
 		io_sqd_update_thread_idle(sqd);
@@ -7153,7 +7131,6 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
 
 	refcount_set(&sqd->refs, 1);
 	INIT_LIST_HEAD(&sqd->ctx_list);
-	INIT_LIST_HEAD(&sqd->ctx_new_list);
 	init_rwsem(&sqd->rw_lock);
 	init_waitqueue_head(&sqd->wait);
 	init_completion(&sqd->startup);
@@ -7834,7 +7811,8 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 			ctx->sq_thread_idle = HZ;
 
 		io_sq_thread_park(sqd);
-		list_add(&ctx->sqd_list, &sqd->ctx_new_list);
+		list_add(&ctx->sqd_list, &sqd->ctx_list);
+		io_sqd_update_thread_idle(sqd);
 		io_sq_thread_unpark(sqd);
 
 		if (sqd->thread)