Re: [PATCH v4 2/6] block: add blk_interposer

[Mike Snitzer <snitzer@xxxxxxxxxx>]

On Wed, Feb 03 2021 at 10:53am -0500,
Sergei Shtepa <sergei.shtepa@xxxxxxxxx> wrote:

> blk_interposer allows to intercept bio requests, remap bio to another devices or add new bios.
> 
> Signed-off-by: Sergei Shtepa <sergei.shtepa@xxxxxxxxx>
> ---
>  block/bio.c               |  2 +
>  block/blk-core.c          | 33 ++++++++++++++++
>  block/genhd.c             | 82 +++++++++++++++++++++++++++++++++++++++
>  include/linux/blk_types.h |  6 ++-
>  include/linux/genhd.h     | 18 +++++++++
>  5 files changed, 139 insertions(+), 2 deletions(-)
> 
> diff --git a/block/bio.c b/block/bio.c
> index 1f2cc1fbe283..f6f135eb84b5 100644
> --- a/block/bio.c
> +++ b/block/bio.c
> @@ -684,6 +684,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
>  	bio_set_flag(bio, BIO_CLONED);
>  	if (bio_flagged(bio_src, BIO_THROTTLED))
>  		bio_set_flag(bio, BIO_THROTTLED);
> +	if (bio_flagged(bio_src, BIO_INTERPOSED))
> +		bio_set_flag(bio, BIO_INTERPOSED);
>  	bio->bi_opf = bio_src->bi_opf;
>  	bio->bi_ioprio = bio_src->bi_ioprio;
>  	bio->bi_write_hint = bio_src->bi_write_hint;
> diff --git a/block/blk-core.c b/block/blk-core.c
> index 7663a9b94b80..c84bc42ba88b 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -1032,6 +1032,32 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
>  	return ret;
>  }
>  
> +static blk_qc_t __submit_bio_interposed(struct bio *bio)
> +{
> +	struct bio_list bio_list[2] = { };
> +	blk_qc_t ret = BLK_QC_T_NONE;
> +
> +	current->bio_list = bio_list;
> +	if (likely(bio_queue_enter(bio) == 0)) {
> +		struct gendisk *disk = bio->bi_disk;
> +
> +		if (likely(blk_has_interposer(disk))) {
> +			bio_set_flag(bio, BIO_INTERPOSED);
> +			disk->interposer->ip_submit_bio(bio);
> +		} else /* interposer was removed */
> +			bio_list_add(&current->bio_list[0], bio);

style nit:

} else {
	/* interposer was removed */
	bio_list_add(&current->bio_list[0], bio);
}

> +
> +		blk_queue_exit(disk->queue);
> +	}
> +	current->bio_list = NULL;
> +
> +	/* Resubmit remaining bios */
> +	while ((bio = bio_list_pop(&bio_list[0])))
> +		ret = submit_bio_noacct(bio);
> +
> +	return ret;
> +}
> +
>  /**
>   * submit_bio_noacct - re-submit a bio to the block device layer for I/O
>   * @bio:  The bio describing the location in memory and on the device.
> @@ -1057,6 +1083,13 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
>  		return BLK_QC_T_NONE;
>  	}
>  
> +	/*
> +	 * Checking the BIO_INTERPOSED flag is necessary so that the bio
> +	 * created by the blk_interposer do not get to it for processing.
> +	 */
> +	if (blk_has_interposer(bio->bi_disk) &&
> +	    !bio_flagged(bio, BIO_INTERPOSED))
> +		return __submit_bio_interposed(bio);
>  	if (!bio->bi_disk->fops->submit_bio)
>  		return __submit_bio_noacct_mq(bio);
>  	return __submit_bio_noacct(bio);
> diff --git a/block/genhd.c b/block/genhd.c
> index 419548e92d82..39785a3ef703 100644
> --- a/block/genhd.c
> +++ b/block/genhd.c
> @@ -30,6 +30,7 @@
>  static struct kobject *block_depr;
>  
>  DECLARE_RWSEM(bdev_lookup_sem);
> +DEFINE_MUTEX(bdev_interposer_mutex);

Seems you're using this mutex to protect access to disk->interposer in
attach/detach.  This is to prevent attach/detach races to same device?

Thankfully attach/detach isn't in the bio submission fast path but it'd
be helpful to document what this mutex is protecting).

A storm of attach or detach will all hit this global mutex though...

Mike