Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Damien Le Moal <Damien.LeMoal@wdc.com>
To: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>,
	Bob Liu <bob.liu@oracle.com>, "axboe@kernel.dk" <axboe@kernel.dk>
Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>
Subject: Re: [PATCH] block: Bail out iteration functions upon SIGKILL.
Date: Tue, 12 Nov 2019 04:05:41 +0000
Message-ID: <BYAPR04MB58165EC2C792CE26AAAF361FE7770@BYAPR04MB5816.namprd04.prod.outlook.com> (raw)
In-Reply-To: <8fde32da-d5e5-11b7-9ed7-e3aa5b003647@i-love.sakura.ne.jp>

On 2019/11/08 20:54, Tetsuo Handa wrote:
> syzbot found that a thread can stall for minutes inside fallocate()
> after that thread was killed by SIGKILL [1]. While trying to allocate
> 64TB of disk space using fallocate() is legal, delaying termination of
> killed thread for minutes is bad. Thus, allow iteration functions in
> block/blk-lib.c to be killable.
> 
> [1] https://syzkaller.appspot.com/bug?id=9386d051e11e09973d5a4cf79af5e8cedf79386d
> 
> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
> Reported-by: syzbot <syzbot+b48daca8639150bc5e73@syzkaller.appspotmail.com>
> ---
>  block/blk-lib.c | 44 ++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 40 insertions(+), 4 deletions(-)
> 
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index 5f2c429..6ca7cae 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -7,9 +7,22 @@
>  #include <linux/bio.h>
>  #include <linux/blkdev.h>
>  #include <linux/scatterlist.h>
> +#include <linux/sched/signal.h>
>  
>  #include "blk.h"
>  
> +static int blk_should_abort(struct bio *bio)
> +{
> +	int ret;
> +
> +	cond_resched();
> +	if (!fatal_signal_pending(current))
> +		return 0;
> +	ret = submit_bio_wait(bio);

This will change the behavior of __blkdev_issue_discard() to a sync IO
execution instead of the current async execution since submit_bio_wait()
call is the responsibility of the caller (e.g. blkdev_issue_discard()).
Have you checked if users of __blkdev_issue_discard() are OK with that ?
f2fs, ext4, xfs, dm and nvme use this function.

Looking at f2fs, this does not look like it is going to work as expected
since the bio setup, including end_io callback, is done after this
function is called and a regular submit_bio() execution is being used.

> +	bio_put(bio);
> +	return ret ? ret : -EINTR;
> +}
> +
>  struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp)
>  {
>  	struct bio *new = bio_alloc(gfp, nr_pages);
> @@ -55,6 +68,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  		return -EINVAL;
>  
>  	while (nr_sects) {
> +		int ret;

Please add a white line after the declaration similarly to your change
in __blkdev_issue_write_same() and __blkdev_issue_zero_pages().

>  		sector_t req_sects = min_t(sector_t, nr_sects,
>  				bio_allowed_max_sectors(q));
>  
> @@ -75,7 +89,11 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>  		 * us to schedule out to avoid softlocking if preempt
>  		 * is disabled.
>  		 */
> -		cond_resched();
> +		ret = blk_should_abort(bio);
> +		if (ret) {
> +			*biop = NULL;
> +			return ret;
> +		}
>  	}
>  
>  	*biop = bio;
> @@ -154,6 +172,8 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
>  	max_write_same_sectors = bio_allowed_max_sectors(q);
>  
>  	while (nr_sects) {
> +		int ret;
> +
>  		bio = blk_next_bio(bio, 1, gfp_mask);
>  		bio->bi_iter.bi_sector = sector;
>  		bio_set_dev(bio, bdev);
> @@ -171,7 +191,11 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
>  			bio->bi_iter.bi_size = nr_sects << 9;
>  			nr_sects = 0;
>  		}
> -		cond_resched();
> +		ret = blk_should_abort(bio);
> +		if (ret) {
> +			*biop = NULL;
> +			return ret;
> +		}
>  	}
>  
>  	*biop = bio;
> @@ -230,6 +254,8 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
>  		return -EOPNOTSUPP;
>  
>  	while (nr_sects) {
> +		int ret;
> +
>  		bio = blk_next_bio(bio, 0, gfp_mask);
>  		bio->bi_iter.bi_sector = sector;
>  		bio_set_dev(bio, bdev);
> @@ -245,7 +271,11 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
>  			bio->bi_iter.bi_size = nr_sects << 9;
>  			nr_sects = 0;
>  		}
> -		cond_resched();
> +		ret = blk_should_abort(bio);
> +		if (ret) {
> +			*biop = NULL;
> +			return ret;
> +		}
>  	}
>  
>  	*biop = bio;
> @@ -281,6 +311,8 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
>  		return -EPERM;
>  
>  	while (nr_sects != 0) {
> +		int ret;
> +
>  		bio = blk_next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
>  				   gfp_mask);
>  		bio->bi_iter.bi_sector = sector;
> @@ -295,7 +327,11 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
>  			if (bi_size < sz)
>  				break;
>  		}
> -		cond_resched();
> +		ret = blk_should_abort(bio);
> +		if (ret) {
> +			*biop = NULL;
> +			return ret;
> +		}
>  	}
>  
>  	*biop = bio;
> 


-- 
Damien Le Moal
Western Digital Research

  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-23  7:56 INFO: task syz-executor can't die for more than 143 seconds. (2) syzbot
2019-10-24 10:08 ` Tetsuo Handa
2019-10-28  8:51   ` Bob Liu
2019-11-08 11:41     ` [PATCH] block: Bail out iteration functions upon SIGKILL Tetsuo Handa
2019-11-08 18:13       ` Chaitanya Kulkarni
2019-11-08 22:18         ` Chaitanya Kulkarni
2019-11-12  4:05       ` Damien Le Moal [this message]
2019-11-12 14:47         ` Tetsuo Handa
2019-11-13  1:54           ` Damien Le Moal
2019-11-13  6:55             ` Ming Lei
2019-11-13  7:11               ` Damien Le Moal
2019-11-13  7:49                 ` Ming Lei
2019-11-15 10:05             ` Tetsuo Handa
2019-11-18  0:02               ` Damien Le Moal

Reply instructions:

You may reply publically 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=BYAPR04MB58165EC2C792CE26AAAF361FE7770@BYAPR04MB5816.namprd04.prod.outlook.com \
    --to=damien.lemoal@wdc.com \
    --cc=axboe@kernel.dk \
    --cc=bob.liu@oracle.com \
    --cc=linux-block@vger.kernel.org \
    --cc=penguin-kernel@i-love.sakura.ne.jp \
    /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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org
	public-inbox-index linux-block

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git