DM-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>, Song Liu <song@kernel.org>,
	Hans de Goede <hdegoede@redhat.com>,
	Richard Weinberger <richard@nod.at>,
	linux-mtd@lists.infradead.org, dm-devel@redhat.com,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	drbd-dev@lists.linbit.com, linux-raid@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	cgroups@vger.kernel.org
Subject: Re: [PATCH 10/14] bdi: remove BDI_CAP_SYNCHRONOUS_IO
Date: Sun, 26 Jul 2020 12:06:39 -0700
Message-ID: <20200726190639.GA560221@google.com> (raw)
In-Reply-To: <20200726150333.305527-11-hch@lst.de>

On Sun, Jul 26, 2020 at 05:03:29PM +0200, Christoph Hellwig wrote:
> BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to
> decided if ->rw_page can be used on a block device.  Just check up for
> the method instead.  The only complication is that zram needs a second
> set of block_device_operations as it can switch between modes that
> actually support ->rw_page and those who don't.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  drivers/block/brd.c           |  1 -
>  drivers/block/zram/zram_drv.c | 19 +++++++++++++------
>  drivers/nvdimm/btt.c          |  2 --
>  drivers/nvdimm/pmem.c         |  1 -
>  include/linux/backing-dev.h   |  9 ---------
>  mm/swapfile.c                 |  2 +-
>  6 files changed, 14 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/block/brd.c b/drivers/block/brd.c
> index 2723a70eb85593..cc49a921339f77 100644
> --- a/drivers/block/brd.c
> +++ b/drivers/block/brd.c
> @@ -403,7 +403,6 @@ static struct brd_device *brd_alloc(int i)
>  	disk->flags		= GENHD_FL_EXT_DEVT;
>  	sprintf(disk->disk_name, "ram%d", i);
>  	set_capacity(disk, rd_size * 2);
> -	brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
>  
>  	/* Tell the block layer that this is not a rotational device */
>  	blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue);
> diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
> index 9100ac36670afc..d73ddf018fa65f 100644
> --- a/drivers/block/zram/zram_drv.c
> +++ b/drivers/block/zram/zram_drv.c
> @@ -52,6 +52,9 @@ static unsigned int num_devices = 1;
>   */
>  static size_t huge_class_size;
>  
> +static const struct block_device_operations zram_devops;
> +static const struct block_device_operations zram_wb_devops;
> +
>  static void zram_free_page(struct zram *zram, size_t index);
>  static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
>  				u32 index, int offset, struct bio *bio);
> @@ -408,8 +411,7 @@ static void reset_bdev(struct zram *zram)
>  	zram->backing_dev = NULL;
>  	zram->old_block_size = 0;
>  	zram->bdev = NULL;
> -	zram->disk->queue->backing_dev_info->capabilities |=
> -				BDI_CAP_SYNCHRONOUS_IO;
> +	zram->disk->fops = &zram_devops;
>  	kvfree(zram->bitmap);
>  	zram->bitmap = NULL;
>  }
> @@ -528,8 +530,7 @@ static ssize_t backing_dev_store(struct device *dev,
>  	 * freely but in fact, IO is going on so finally could cause
>  	 * use-after-free when the IO is really done.
>  	 */
> -	zram->disk->queue->backing_dev_info->capabilities &=
> -			~BDI_CAP_SYNCHRONOUS_IO;
> +	zram->disk->fops = &zram_wb_devops;
>  	up_write(&zram->init_lock);

For zram, regardless of BDI_CAP_SYNCHRONOUS_IO, it have used rw_page
every time on read/write path. This one with next patch will make zram
use bio instead of rw_page when it's declared !BDI_CAP_SYNCHRONOUS_IO,
which introduce regression for performance.

In the swap code, BDI_CAP_SYNCHRONOUS_IO is used to avoid swap cache
when the page was private. bdev_read_page is not designed to rely on
synchronous operation. That's why this patch breaks the old behavior.

>  
>  	pr_info("setup backing device %s\n", file_name);
> @@ -1819,6 +1820,13 @@ static const struct block_device_operations zram_devops = {
>  	.owner = THIS_MODULE
>  };
>  
> +static const struct block_device_operations zram_wb_devops = {
> +	.open = zram_open,
> +	.submit_bio = zram_submit_bio,
> +	.swap_slot_free_notify = zram_slot_free_notify,
> +	.owner = THIS_MODULE
> +};
> +
>  static DEVICE_ATTR_WO(compact);
>  static DEVICE_ATTR_RW(disksize);
>  static DEVICE_ATTR_RO(initstate);
> @@ -1946,8 +1954,7 @@ static int zram_add(void)
>  	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
>  		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
>  
> -	zram->disk->queue->backing_dev_info->capabilities |=
> -			(BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO);
> +	zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
>  	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
>  
>  	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
> diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
> index 412d21d8f64351..b4184dc9b41eb4 100644
> --- a/drivers/nvdimm/btt.c
> +++ b/drivers/nvdimm/btt.c
> @@ -1540,8 +1540,6 @@ static int btt_blk_init(struct btt *btt)
>  	btt->btt_disk->private_data = btt;
>  	btt->btt_disk->queue = btt->btt_queue;
>  	btt->btt_disk->flags = GENHD_FL_EXT_DEVT;
> -	btt->btt_disk->queue->backing_dev_info->capabilities |=
> -			BDI_CAP_SYNCHRONOUS_IO;
>  
>  	blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
>  	blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 94790e6e0e4ce1..436b83fb24ad61 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -478,7 +478,6 @@ static int pmem_attach_disk(struct device *dev,
>  	disk->queue		= q;
>  	disk->flags		= GENHD_FL_EXT_DEVT;
>  	disk->private_data	= pmem;
> -	disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
>  	nvdimm_namespace_disk_name(ndns, disk->disk_name);
>  	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
>  			/ 512);
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index 52583b6f2ea05d..860ea33571bce5 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
> @@ -122,9 +122,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
>   * BDI_CAP_NO_WRITEBACK:   Don't write pages back
>   * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
>   * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
> - *
> - * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
> - *			   inefficient.
>   */
>  #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
>  #define BDI_CAP_NO_WRITEBACK	0x00000002
> @@ -132,7 +129,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
>  #define BDI_CAP_STABLE_WRITES	0x00000008
>  #define BDI_CAP_STRICTLIMIT	0x00000010
>  #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
> -#define BDI_CAP_SYNCHRONOUS_IO	0x00000040
>  
>  #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
>  	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
> @@ -174,11 +170,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
>  long congestion_wait(int sync, long timeout);
>  long wait_iff_congested(int sync, long timeout);
>  
> -static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi)
> -{
> -	return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO;
> -}
> -
>  static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
>  {
>  	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 6c26916e95fd4a..18eac97b10e502 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -3230,7 +3230,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>  	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
>  		p->flags |= SWP_STABLE_WRITES;
>  
> -	if (bdi_cap_synchronous_io(inode_to_bdi(inode)))
> +	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
>  		p->flags |= SWP_SYNCHRONOUS_IO;
>  
>  	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
> -- 
> 2.27.0
> 

  reply index

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-26 15:03 bdi cleanups v3 Christoph Hellwig
2020-07-26 15:03 ` [PATCH 01/14] fs: remove the unused SB_I_MULTIROOT flag Christoph Hellwig
2020-07-26 15:03 ` [PATCH 03/14] drbd: remove RB_CONGESTED_REMOTE Christoph Hellwig
     [not found] ` <20200726150333.305527-1-hch-jcswGhMUV9g@public.gmane.org>
2020-07-26 15:03   ` [PATCH 02/14] drbd: remove dead code in device_to_statistics Christoph Hellwig
2020-07-26 15:03   ` [PATCH 04/14] bdi: initialize ->ra_pages in bdi_init Christoph Hellwig
2020-07-26 15:03   ` [PATCH 05/14] md: update the optimal I/O size on reshape Christoph Hellwig
2020-07-26 15:03   ` [PATCH 06/14] block: lift setting the readahead size into the block layer Christoph Hellwig
2020-08-26 22:07     ` Mike Snitzer
2020-09-02 15:11       ` Christoph Hellwig
2020-09-02 16:20         ` Mike Snitzer
2020-09-10  9:28           ` Christoph Hellwig
2020-09-10 17:15             ` Mike Snitzer
2020-09-15  7:05               ` Christoph Hellwig
2020-07-26 15:03   ` [PATCH 07/14] block: make QUEUE_SYSFS_BIT_FNS a little more useful Christoph Hellwig
2020-07-29  8:57     ` [block] 54529aac98: fsmark.files_per_sec -13.6% regression kernel test robot
2020-07-30  2:14     ` [block] 54529aac98: blktests.block.005.fail kernel test robot
2020-07-26 15:03   ` [PATCH 08/14] block: add helper macros for queue sysfs entries Christoph Hellwig
2020-07-26 15:03   ` [PATCH 13/14] bdi: invert BDI_CAP_NO_ACCT_WB Christoph Hellwig
2020-07-26 15:03 ` [PATCH 09/14] bdi: remove BDI_CAP_CGROUP_WRITEBACK Christoph Hellwig
2020-07-26 15:03 ` [PATCH 10/14] bdi: remove BDI_CAP_SYNCHRONOUS_IO Christoph Hellwig
2020-07-26 19:06   ` Minchan Kim [this message]
     [not found]     ` <20200726190639.GA560221-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2020-07-27  7:58       ` Christoph Hellwig
2020-07-26 15:03 ` [PATCH 11/14] mm: use SWP_SYNCHRONOUS_IO more intelligently Christoph Hellwig
2020-07-26 15:03 ` [PATCH 12/14] bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag Christoph Hellwig
2020-07-26 15:03 ` [PATCH 14/14] bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag Christoph Hellwig
2020-07-26 15:12 ` bdi cleanups v3 Christoph Hellwig
  -- strict thread matches above, loose matches on Subject: below --
2020-07-24  7:32 Christoph Hellwig
2020-07-24  7:33 ` [PATCH 10/14] bdi: remove BDI_CAP_SYNCHRONOUS_IO Christoph Hellwig
2020-07-28 12:26   ` Johannes Thumshirn
2020-07-22  6:25 bdi cleanups v2 Christoph Hellwig
2020-07-22  6:25 ` [PATCH 10/14] bdi: remove BDI_CAP_SYNCHRONOUS_IO Christoph Hellwig
2020-07-20  7:51 bdi cleanups Christoph Hellwig
2020-07-20  7:51 ` [PATCH 10/14] bdi: remove BDI_CAP_SYNCHRONOUS_IO 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=20200726190639.GA560221@google.com \
    --to=minchan@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=dm-devel@redhat.com \
    --cc=drbd-dev@lists.linbit.com \
    --cc=hch@lst.de \
    --cc=hdegoede@redhat.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-mtd@lists.infradead.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=richard@nod.at \
    --cc=song@kernel.org \
    /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

DM-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/dm-devel/0 dm-devel/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 dm-devel dm-devel/ https://lore.kernel.org/dm-devel \
		dm-devel@redhat.com
	public-inbox-index dm-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/com.redhat.dm-devel


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