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: Mon, 21 Jun 2021 09:20:05 +0200	[thread overview]
Message-ID: <20210621072005.GA6651@lst.de> (raw)
In-Reply-To: <YMytSIBm7k2pqFlc@T590>

On Fri, Jun 18, 2021 at 10:27:20PM +0800, Ming Lei wrote:
> > 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.
> 
> +       rcu_read_lock();
> +       bio = READ_ONCE(kiocb->private);
> +       if (bio && bio->bi_bdev)
> 
> The bio may be ended now from another polling job, then the disk is
> closed & deleted, and released. Then request queue & hctxs are released.
> 
> +               ret = bio_poll(bio, flags);
> 
> But disk & request queue & hctx can still be referred in above bio_poll().

I don't see how this can happen.  A bio stashed into kiocb->private needs
to belong to the correct device initially.  For it to point to the "wrong"
device it needs to have been completed on the correct one, and then be
reused for a different device.  At the point it is reused that device
must obviously have been alive, and for it to be freed a RCU grace
period must have been passed.  And that grace period can't have started
earlier than when iocb_bio_iopoll was called.

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: Mon, 21 Jun 2021 09:20:05 +0200	[thread overview]
Message-ID: <20210621072005.GA6651@lst.de> (raw)
In-Reply-To: <YMytSIBm7k2pqFlc@T590>

On Fri, Jun 18, 2021 at 10:27:20PM +0800, Ming Lei wrote:
> > 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.
> 
> +       rcu_read_lock();
> +       bio = READ_ONCE(kiocb->private);
> +       if (bio && bio->bi_bdev)
> 
> The bio may be ended now from another polling job, then the disk is
> closed & deleted, and released. Then request queue & hctxs are released.
> 
> +               ret = bio_poll(bio, flags);
> 
> But disk & request queue & hctx can still be referred in above bio_poll().

I don't see how this can happen.  A bio stashed into kiocb->private needs
to belong to the correct device initially.  For it to point to the "wrong"
device it needs to have been completed on the correct one, and then be
reused for a different device.  At the point it is reused that device
must obviously have been alive, and for it to be freed a RCU grace
period must have been passed.  And that grace period can't have started
earlier than when iocb_bio_iopoll was called.

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

  reply	other threads:[~2021-06-21  7:20 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
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 [this message]
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=20210621072005.GA6651@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.