Re: [PATCH RFC v4 1/3] block: add BIO_COMPLETE_IN_TASK for task-context completion

[Jens Axboe <axboe@kernel.dk>]

On 3/25/26 12:43 PM, Tal Zussman wrote:
> diff --git a/block/bio.c b/block/bio.c
> index 8203bb7455a9..69ee0d93041f 100644
> --- a/block/bio.c
> +++ b/block/bio.c
> @@ -18,6 +18,7 @@
>  #include <linux/highmem.h>
>  #include <linux/blk-crypto.h>
>  #include <linux/xarray.h>
> +#include <linux/local_lock.h>
>  
>  #include <trace/events/block.h>
>  #include "blk.h"
> @@ -1714,6 +1715,60 @@ void bio_check_pages_dirty(struct bio *bio)
>  }
>  EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
>  
> +struct bio_complete_batch {
> +	local_lock_t lock;
> +	struct bio_list list;
> +	struct work_struct work;
> +};
> +
> +static DEFINE_PER_CPU(struct bio_complete_batch, bio_complete_batch) = {
> +	.lock = INIT_LOCAL_LOCK(lock),
> +};
> +
> +static void bio_complete_work_fn(struct work_struct *w)
> +{
> +	struct bio_complete_batch *batch;
> +	struct bio_list list;
> +
> +again:
> +	local_lock_irq(&bio_complete_batch.lock);
> +	batch = this_cpu_ptr(&bio_complete_batch);
> +	list = batch->list;
> +	bio_list_init(&batch->list);
> +	local_unlock_irq(&bio_complete_batch.lock);
> +
> +	while (!bio_list_empty(&list)) {
> +		struct bio *bio = bio_list_pop(&list);
> +		bio->bi_end_io(bio);
> +	}
> +
> +	local_lock_irq(&bio_complete_batch.lock);
> +	batch = this_cpu_ptr(&bio_complete_batch);
> +	if (!bio_list_empty(&batch->list)) {
> +		local_unlock_irq(&bio_complete_batch.lock);
> +
> +		if (!need_resched())
> +			goto again;
> +
> +		schedule_work_on(smp_processor_id(), &batch->work);
> +		return;
> +	}
> +	local_unlock_irq(&bio_complete_batch.lock);
> +}

bool looped = false;

do {
	if (looped && need_resched()) {
    		schedule_work_on(smp_processor_id(), &batch->work);
		break;
	}

	local_lock_irq(&bio_complete_batch.lock);
	batch = this_cpu_ptr(&bio_complete_batch);
	list = batch->list;
	bio_list_init(&batch->list);
	local_unlock_irq(&bio_complete_batch.lock);

	if (bio_list_empty(&list))
		break;

	do {
		struct bio *bio = bio_list_pop(&list);
		bio->bi_end_io(bio);
	} while (!bio_list_empty(&list));
	looped = true;
} while (1);

would be a lot easier to read, and avoid needing the list manipulation
included twice.

> +static void bio_queue_completion(struct bio *bio)
> +{
> +	struct bio_complete_batch *batch;
> +	unsigned long flags;
> +
> +	local_lock_irqsave(&bio_complete_batch.lock, flags);
> +	batch = this_cpu_ptr(&bio_complete_batch);
> +	bio_list_add(&batch->list, bio);
> +	local_unlock_irqrestore(&bio_complete_batch.lock, flags);
> +
> +	schedule_work_on(smp_processor_id(), &batch->work);
> +}

Maybe do something ala:

static void bio_queue_completion(struct bio *bio)
{
	struct bio_complete_batch *batch;
	unsigned long flags;
	bool was_empty;

	local_lock_irqsave(&bio_complete_batch.lock, flags);
	batch = this_cpu_ptr(&bio_complete_batch);
	was_empty = bio_list_empty(&batch->list);
	bio_list_add(&batch->list, bio);
	local_unlock_irqrestore(&bio_complete_batch.lock, flags);

	if (was_empty)
		schedule_work_on(smp_processor_id(), &batch->work);
}

Outside of these mostly nits, I like this approach. It avoids my main
worry with this, which was contention on the list locks. And on the
io_uring side, we'll never hit the !in_task() path anyway, as the
completions are run from the task always. The bio flag makes sense for
this.

-- 
Jens Axboe