[dm-devel] [PATCH 2/3] dm-zoned: improve error handling in i/o map code

[Damien Le Moal]

On 2019/08/06 10:06, Dmitry Fomichev wrote:
> Some errors are ignored in the I/O path during queueing chunks
> for processing by chunk works. Since at least these errors are
> transient in nature, it should be possible to retry the failed
> incoming commands.
> 
> The fix -
> 
> Errors that can happen while queueing chunks are carried upwards
> to the main mapping function and it now returns DM_MAPIO_REQUEUE
> for any incoming requests that can not be properly queued.
> 
> Error logging/debug messages are added where needed.
> 
> Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target")
> Cc: stable at vger.kernel.org
> Signed-off-by: Dmitry Fomichev <dmitry.fomichev at wdc.com>
> ---
>  drivers/md/dm-zoned-target.c | 22 ++++++++++++++++------
>  1 file changed, 16 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
> index 1bf6e6eebee1..c1992034c099 100644
> --- a/drivers/md/dm-zoned-target.c
> +++ b/drivers/md/dm-zoned-target.c
> @@ -514,22 +514,24 @@ static void dmz_flush_work(struct work_struct *work)
>   * Get a chunk work and start it to process a new BIO.
>   * If the BIO chunk has no work yet, create one.
>   */
> -static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
> +static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
>  {
>  	unsigned int chunk = dmz_bio_chunk(dmz->dev, bio);
>  	struct dm_chunk_work *cw;
> +	int ret = 0;
>  
>  	mutex_lock(&dmz->chunk_lock);
>  
>  	/* Get the BIO chunk work. If one is not active yet, create one */
>  	cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
>  	if (!cw) {
> -		int ret;
>  
>  		/* Create a new chunk work */
>  		cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO);
> -		if (!cw)
> +		if (unlikely(!cw)) {
> +			ret = -ENOMEM;
>  			goto out;
> +		}
>  
>  		INIT_WORK(&cw->work, dmz_chunk_work);
>  		refcount_set(&cw->refcount, 0);
> @@ -540,7 +542,6 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
>  		ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw);
>  		if (unlikely(ret)) {
>  			kfree(cw);
> -			cw = NULL;
>  			goto out;
>  		}
>  	}
> @@ -548,10 +549,12 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
>  	bio_list_add(&cw->bio_list, bio);
>  	dmz_get_chunk_work(cw);
>  
> +	dmz_reclaim_bio_acc(dmz->reclaim);
>  	if (queue_work(dmz->chunk_wq, &cw->work))
>  		dmz_get_chunk_work(cw);
>  out:
>  	mutex_unlock(&dmz->chunk_lock);
> +	return ret;
>  }
>  
>  /*
> @@ -565,6 +568,7 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
>  	sector_t sector = bio->bi_iter.bi_sector;
>  	unsigned int nr_sectors = bio_sectors(bio);
>  	sector_t chunk_sector;
> +	int ret;
>  
>  	dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
>  		      bio_op(bio), (unsigned long long)sector, nr_sectors,
> @@ -602,8 +606,14 @@ static int dmz_map(struct dm_target *ti, struct bio *bio)
>  		dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector);
>  
>  	/* Now ready to handle this BIO */
> -	dmz_reclaim_bio_acc(dmz->reclaim);
> -	dmz_queue_chunk_work(dmz, bio);
> +	ret = dmz_queue_chunk_work(dmz, bio);
> +	if (ret) {
> +		dmz_dev_debug(dmz->dev,
> +			      "BIO op %d, can't process chunk %llu, err %i\n",
> +			      bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio),
> +			      ret);
> +		return DM_MAPIO_REQUEUE;
> +	}
>  
>  	return DM_MAPIO_SUBMITTED;
>  }
> 

Reviewed-by: Damien Le Moal <damien.lemoal at wdc.com>

-- 
Damien Le Moal
Western Digital Research