io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: JeffleXu <jefflexu@linux.alibaba.com>
To: snitzer@redhat.com
Cc: linux-block@vger.kernel.org, dm-devel@redhat.com,
	io-uring@vger.kernel.org
Subject: Re: [dm-devel] [PATCH RFC 7/7] dm: add support for IO polling
Date: Fri, 8 Jan 2021 11:12:26 +0800	[thread overview]
Message-ID: <c052e81f-1ade-dbd2-f5cb-259aca9d5b0f@linux.alibaba.com> (raw)
In-Reply-To: <20201223112624.78955-8-jefflexu@linux.alibaba.com>



On 12/23/20 7:26 PM, Jeffle Xu wrote:
> Enable iopoll when all underlying target devices supports iopoll.
> 
> Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
> ---
>  drivers/md/dm-table.c | 28 ++++++++++++++++++++++++++++
>  drivers/md/dm.c       |  1 +
>  2 files changed, 29 insertions(+)
> 
> diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
> index 188f41287f18..b0cd5bf58c3c 100644
> --- a/drivers/md/dm-table.c
> +++ b/drivers/md/dm-table.c
> @@ -1791,6 +1791,31 @@ static bool dm_table_requires_stable_pages(struct dm_table *t)
>  	return false;
>  }
>  
> +static int device_supports_poll(struct dm_target *ti, struct dm_dev *dev,
> +				sector_t start, sector_t len, void *data)
> +{
> +	struct request_queue *q = bdev_get_queue(dev->bdev);
> +
> +	return q && test_bit(QUEUE_FLAG_POLL, &q->queue_flags);
> +}
> +
> +static bool dm_table_supports_poll(struct dm_table *t)
> +{
> +	struct dm_target *ti;
> +	unsigned int i;
> +
> +	/* Ensure that all targets support iopoll. */
> +	for (i = 0; i < dm_table_get_num_targets(t); i++) {
> +		ti = dm_table_get_target(t, i);
> +
> +		if (!ti->type->iterate_devices ||
> +		    !ti->type->iterate_devices(ti, device_supports_poll, NULL))
> +			return false;
> +	}
> +
> +	return true;
> +}
> +
>  void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
>  			       struct queue_limits *limits)
>  {
> @@ -1883,6 +1908,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
>  #endif
>  
>  	blk_queue_update_readahead(q);
> +
> +	if (dm_table_supports_poll(t))
> +		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
>  }
>  

This works in arbitrary bio-based DM stacking. Suppose the following
device stack:

    dm0
    dm1
nvme0  nvme1


dm 0 will check if dm1 has QUEUE_FLAG_POLL flag set.


>  unsigned int dm_table_get_num_targets(struct dm_table *t)
> diff --git a/drivers/md/dm.c b/drivers/md/dm.c
> index 03c2b867acaa..ffd2c5ead256 100644
> --- a/drivers/md/dm.c
> +++ b/drivers/md/dm.c
> @@ -3049,6 +3049,7 @@ static const struct pr_ops dm_pr_ops = {
>  };
>  
>  static const struct block_device_operations dm_blk_dops = {
> +	.iopoll = blk_bio_poll,
>  	.submit_bio = dm_submit_bio,
>  	.open = dm_blk_open,
>  	.release = dm_blk_close,
> 

-- 
Thanks,
Jeffle

  reply	other threads:[~2021-01-08  3:13 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-23 11:26 [PATCH RFC 0/7] dm: add support of iopoll Jeffle Xu
2020-12-23 11:26 ` [PATCH RFC 1/7] block: move definition of blk_qc_t to types.h Jeffle Xu
2021-01-07 19:04   ` Mike Snitzer
2020-12-23 11:26 ` [PATCH RFC 2/7] block: add helper function fetching gendisk from queue Jeffle Xu
2021-01-07 20:31   ` Mike Snitzer
2020-12-23 11:26 ` [PATCH RFC 3/7] block: add iopoll method for non-mq device Jeffle Xu
2021-01-07 21:47   ` Mike Snitzer
2021-01-08  3:24     ` [dm-devel] " JeffleXu
2021-01-08 17:33       ` Mike Snitzer
2021-01-11  7:50         ` [dm-devel] " JeffleXu
2020-12-23 11:26 ` [PATCH RFC 4/7] block: define blk_qc_t as uintptr_t Jeffle Xu
2021-01-07 21:52   ` Mike Snitzer
2020-12-23 11:26 ` [PATCH RFC 5/7] dm: always return BLK_QC_T_NONE for bio-based device Jeffle Xu
2021-01-07 21:54   ` Mike Snitzer
2020-12-23 11:26 ` [PATCH RFC 6/7] block: track cookies of split bios " Jeffle Xu
2021-01-07 22:18   ` Mike Snitzer
2021-01-08  3:08     ` [dm-devel] " JeffleXu
2021-01-08 17:26       ` Mike Snitzer
2021-01-12  5:46         ` [dm-devel] " JeffleXu
2021-01-12 16:13           ` Mike Snitzer
2021-01-14  9:16             ` [dm-devel] " JeffleXu
2021-01-14 14:30               ` Mike Snitzer
2021-01-12  7:11         ` [dm-devel] " JeffleXu
2020-12-23 11:26 ` [PATCH RFC 7/7] dm: add support for IO polling Jeffle Xu
2021-01-08  3:12   ` JeffleXu [this message]
2021-01-07  1:14 ` [dm-devel] [PATCH RFC 0/7] dm: add support of iopoll JeffleXu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=c052e81f-1ade-dbd2-f5cb-259aca9d5b0f@linux.alibaba.com \
    --to=jefflexu@linux.alibaba.com \
    --cc=dm-devel@redhat.com \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=snitzer@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).