All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
	Jeffle Xu <jefflexu@linux.alibaba.com>,
	Damien Le Moal <Damien.LeMoal@wdc.com>,
	Keith Busch <kbusch@kernel.org>, Sagi Grimberg <sagi@grimberg.me>,
	"Wunderlich, Mark" <mark.wunderlich@intel.com>,
	"Vasudevan, Anil" <anil.vasudevan@intel.com>,
	linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-nvme@lists.infradead.org
Subject: Re: [PATCH 13/16] block: switch polling to be bio based
Date: Fri, 18 Jun 2021 16:01:47 +0200	[thread overview]
Message-ID: <20210618140147.GA16258@lst.de> (raw)
In-Reply-To: <YMliP6sFVuPhMbOB@T590>

On Wed, Jun 16, 2021 at 10:30:23AM +0800, Ming Lei wrote:
> Not sure disk is valid, we only hold the disk when opening a bdev, but
> the bdev can be closed during polling.

How?  On a block device the caller needs to hold the block device open
to read/write from it.  On a file systems the file systems needs to
be mounted, which also holds a bdev reference.

> Also disk always holds one
> reference on request queue, so if disk is valid, no need to grab queue's
> refcnt in bio_poll().

But we need to avoid going into the lowlevel blk-mq polling code to not
reference the potentially freed hctxs or tags as correctly pointed by
yourself on the previous iteration.

WARNING: multiple messages have this Message-ID
From: Christoph Hellwig <hch@lst.de>
To: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
	Jeffle Xu <jefflexu@linux.alibaba.com>,
	Damien Le Moal <Damien.LeMoal@wdc.com>,
	Keith Busch <kbusch@kernel.org>, Sagi Grimberg <sagi@grimberg.me>,
	"Wunderlich, Mark" <mark.wunderlich@intel.com>,
	"Vasudevan, Anil" <anil.vasudevan@intel.com>,
	linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-nvme@lists.infradead.org
Subject: Re: [PATCH 13/16] block: switch polling to be bio based
Date: Fri, 18 Jun 2021 16:01:47 +0200	[thread overview]
Message-ID: <20210618140147.GA16258@lst.de> (raw)
In-Reply-To: <YMliP6sFVuPhMbOB@T590>

On Wed, Jun 16, 2021 at 10:30:23AM +0800, Ming Lei wrote:
> Not sure disk is valid, we only hold the disk when opening a bdev, but
> the bdev can be closed during polling.

How?  On a block device the caller needs to hold the block device open
to read/write from it.  On a file systems the file systems needs to
be mounted, which also holds a bdev reference.

> Also disk always holds one
> reference on request queue, so if disk is valid, no need to grab queue's
> refcnt in bio_poll().

But we need to avoid going into the lowlevel blk-mq polling code to not
reference the potentially freed hctxs or tags as correctly pointed by
yourself on the previous iteration.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  reply	other threads:[~2021-06-18 14:01 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-15 13:10 switch block layer polling to a bio based model v4 Christoph Hellwig
2021-06-15 13:10 ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 01/16] direct-io: remove blk_poll support Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 02/16] block: don't try to poll multi-bio I/Os in __blkdev_direct_IO Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 03/16] iomap: don't try to poll multi-bio I/Os in __iomap_dio_rw Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 04/16] blk-mq: factor out a blk_qc_to_hctx helper Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 05/16] blk-mq: factor out a "classic" poll helper Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 06/16] blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 07/16] blk-mq: remove blk_qc_t_valid Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 08/16] block: replace the spin argument to blk_iopoll with a flags argument Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 09/16] io_uring: don't sleep when polling for I/O Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 10/16] block: rename REQ_HIPRI to REQ_POLLED Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 11/16] block: use SLAB_TYPESAFE_BY_RCU for the bio slab Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 12/16] block: define 'struct bvec_iter' as packed Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 13/16] block: switch polling to be bio based Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-16  2:30   ` Ming Lei
2021-06-16  2:30     ` Ming Lei
2021-06-18 14:01     ` Christoph Hellwig [this message]
2021-06-18 14:01       ` Christoph Hellwig
2021-06-18 14:27       ` Ming Lei
2021-06-18 14:27         ` Ming Lei
2021-06-21  7:20         ` Christoph Hellwig
2021-06-21  7:20           ` Christoph Hellwig
2021-06-21  8:35           ` Ming Lei
2021-06-21  8:35             ` Ming Lei
2021-06-15 13:10 ` [PATCH 14/16] block: don't allow writing to the poll queue attribute Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 15/16] nvme-multipath: set QUEUE_FLAG_NOWAIT Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 13:10 ` [PATCH 16/16] nvme-multipath: enable polled I/O Christoph Hellwig
2021-06-15 13:10   ` Christoph Hellwig
2021-06-15 14:37 ` switch block layer polling to a bio based model v4 Keith Busch
2021-06-15 14:37   ` Keith Busch
2021-06-15 16:06   ` Christoph Hellwig
2021-06-15 16:06     ` Christoph Hellwig

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=20210618140147.GA16258@lst.de \
    --to=hch@lst.de \
    --cc=Damien.LeMoal@wdc.com \
    --cc=anil.vasudevan@intel.com \
    --cc=axboe@kernel.dk \
    --cc=jefflexu@linux.alibaba.com \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=mark.wunderlich@intel.com \
    --cc=ming.lei@redhat.com \
    --cc=sagi@grimberg.me \
    --subject='Re: [PATCH 13/16] block: switch polling to be bio based' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.