io_uring: extend task put optimisations

Now with IRQ completions done via IRQ, almost all requests freeing
are done from the context of submitter task, so it makes sense to
extend task_put optimisation from io_req_free_batch_finish() to cover
all the cases including task_work by moving it into io_put_task().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/824a7cbd745ddeee4a0f3ff85c558a24fd005872.1629302453.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -1623,10 +1623,14 @@ static inline void io_put_task(struct task_struct *task, int nr)
 {
 	struct io_uring_task *tctx = task->io_uring;
 
-	percpu_counter_sub(&tctx->inflight, nr);
-	if (unlikely(atomic_read(&tctx->in_idle)))
-		wake_up(&tctx->wait);
-	put_task_struct_many(task, nr);
+	if (likely(task == current)) {
+		tctx->cached_refs += nr;
+	} else {
+		percpu_counter_sub(&tctx->inflight, nr);
+		if (unlikely(atomic_read(&tctx->in_idle)))
+			wake_up(&tctx->wait);
+		put_task_struct_many(task, nr);
+	}
 }
 
 static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
@@ -2171,9 +2175,7 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 {
 	if (rb->ctx_refs)
 		percpu_ref_put_many(&ctx->refs, rb->ctx_refs);
-	if (rb->task == current)
-		current->io_uring->cached_refs += rb->task_refs;
-	else if (rb->task)
+	if (rb->task)
 		io_put_task(rb->task, rb->task_refs);
 }