IO-Uring Archive on lore.kernel.org
 help / color / Atom feed
From: Damien Le Moal <Damien.LeMoal@wdc.com>
To: Kanchan Joshi <joshi.k@samsung.com>,
	"axboe@kernel.dk" <axboe@kernel.dk>,
	"viro@zeniv.linux.org.uk" <viro@zeniv.linux.org.uk>,
	"bcrl@kvack.org" <bcrl@kvack.org>
Cc: "asml.silence@gmail.com" <asml.silence@gmail.com>,
	"hch@infradead.org" <hch@infradead.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"mb@lightnvm.io" <mb@lightnvm.io>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-aio@kvack.org" <linux-aio@kvack.org>,
	"io-uring@vger.kernel.org" <io-uring@vger.kernel.org>,
	"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
	"selvakuma.s1@samsung.com" <selvakuma.s1@samsung.com>,
	"nj.shetty@samsung.com" <nj.shetty@samsung.com>,
	"javier.gonz@samsung.com" <javier.gonz@samsung.com>,
	Arnav Dawn <a.dawn@samsung.com>
Subject: Re: [PATCH v2 1/2] fs,block: Introduce RWF_ZONE_APPEND and handling in direct IO path
Date: Fri, 26 Jun 2020 02:50:20 +0000
Message-ID: <CY4PR04MB37511FB1D3B3491A2CED5470E7930@CY4PR04MB3751.namprd04.prod.outlook.com> (raw)
In-Reply-To: <1593105349-19270-2-git-send-email-joshi.k@samsung.com>

On 2020/06/26 2:18, Kanchan Joshi wrote:
> Introduce RWF_ZONE_APPEND flag to represent zone-append. User-space
> sends this with write. Add IOCB_ZONE_APPEND which is set in
> kiocb->ki_flags on receiving RWF_ZONE_APPEND.
> Make direct IO submission path use IOCB_ZONE_APPEND to send bio with
> append op. Direct IO completion returns zone-relative offset, in sector
> unit, to upper layer using kiocb->ki_complete interface.
> Report error if zone-append is requested on regular file or on sync
> kiocb (i.e. one without ki_complete).
> 
> Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
> Signed-off-by: SelvaKumar S <selvakuma.s1@samsung.com>
> Signed-off-by: Arnav Dawn <a.dawn@samsung.com>
> Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
> Signed-off-by: Javier Gonzalez <javier.gonz@samsung.com>
> ---
>  fs/block_dev.c          | 28 ++++++++++++++++++++++++----
>  include/linux/fs.h      |  9 +++++++++
>  include/uapi/linux/fs.h |  5 ++++-
>  3 files changed, 37 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index 47860e5..5180268 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -185,6 +185,10 @@ static unsigned int dio_bio_write_op(struct kiocb *iocb)
>  	/* avoid the need for a I/O completion work item */
>  	if (iocb->ki_flags & IOCB_DSYNC)
>  		op |= REQ_FUA;
> +
> +	if (iocb->ki_flags & IOCB_ZONE_APPEND)
> +		op |= REQ_OP_ZONE_APPEND;

This is wrong. REQ_OP_WRITE is already set in the declaration of "op". How can
this work ?

> +
>  	return op;
>  }
>  
> @@ -295,6 +299,14 @@ static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
>  	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
>  }
>  
> +static inline long blkdev_bio_end_io_append(struct bio *bio)
> +{
> +	sector_t zone_sectors = blk_queue_zone_sectors(bio->bi_disk->queue);
> +
> +	/* calculate zone relative offset for zone append */

The name of the function may be better spelling out zone_append instead of just
append. But see next comment.

> +	return bio->bi_iter.bi_sector & (zone_sectors - 1);
> +}
> +
>  static void blkdev_bio_end_io(struct bio *bio)
>  {
>  	struct blkdev_dio *dio = bio->bi_private;
> @@ -307,15 +319,19 @@ static void blkdev_bio_end_io(struct bio *bio)
>  		if (!dio->is_sync) {
>  			struct kiocb *iocb = dio->iocb;
>  			ssize_t ret;
> +			long res2 = 0;
>  
>  			if (likely(!dio->bio.bi_status)) {
>  				ret = dio->size;
>  				iocb->ki_pos += ret;
> +

Blank line not needed.

> +				if (iocb->ki_flags & IOCB_ZONE_APPEND)> +					res2 = blkdev_bio_end_io_append(bio);

The name blkdev_bio_end_io_append() implies a bio end_io callback function,
which is not the case. What about naming this blkdev_bio_res2() and move the if
inside it ?

>  			} else {
>  				ret = blk_status_to_errno(dio->bio.bi_status);

add "res2 = 0;" here and drop the declaration initialization. That will avoid
doing the assignment twice for zone append case.

>  			}
>  
> -			dio->iocb->ki_complete(iocb, ret, 0);
> +			dio->iocb->ki_complete(iocb, ret, res2);
>  			if (dio->multi_bio)
>  				bio_put(&dio->bio);
>  		} else {
> @@ -382,6 +398,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
>  		bio->bi_private = dio;
>  		bio->bi_end_io = blkdev_bio_end_io;
>  		bio->bi_ioprio = iocb->ki_ioprio;
> +		bio->bi_opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);

Personally, I would prefer a plain "if () else". Or even better: change
dio_bio_write_op() into dio_bio_op() and just have:

		bio->bi_opf = dio_bio_op(iocb);

>  
>  		ret = bio_iov_iter_get_pages(bio, iter);
>  		if (unlikely(ret)) {
> @@ -391,11 +408,9 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
>  		}
>  
>  		if (is_read) {
> -			bio->bi_opf = REQ_OP_READ;
>  			if (dio->should_dirty)
>  				bio_set_pages_dirty(bio);
>  		} else {
> -			bio->bi_opf = dio_bio_write_op(iocb);
>  			task_io_account_write(bio->bi_iter.bi_size);
>  		}
>  
> @@ -465,12 +480,17 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
>  static ssize_t
>  blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  {
> +	bool is_sync = is_sync_kiocb(iocb);
>  	int nr_pages;
>  
> +	/* zone-append is supported only on async-kiocb */
> +	if (is_sync && iocb->ki_flags & IOCB_ZONE_APPEND)
> +		return -EINVAL;
> +
>  	nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1);
>  	if (!nr_pages)
>  		return 0;
> -	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
> +	if (is_sync && nr_pages <= BIO_MAX_PAGES)
>  		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
>  
>  	return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES));
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 6c4ab4d..3202d9a 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -315,6 +315,7 @@ enum rw_hint {
>  #define IOCB_SYNC		(1 << 5)
>  #define IOCB_WRITE		(1 << 6)
>  #define IOCB_NOWAIT		(1 << 7)
> +#define IOCB_ZONE_APPEND	(1 << 8)
>  
>  struct kiocb {
>  	struct file		*ki_filp;
> @@ -3456,6 +3457,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
>  		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
>  	if (flags & RWF_APPEND)
>  		ki->ki_flags |= IOCB_APPEND;
> +	if (flags & RWF_ZONE_APPEND) {
> +		/* currently support block device only */
> +		umode_t mode = file_inode(ki->ki_filp)->i_mode;
> +
> +		if (!(S_ISBLK(mode)))
> +			return -EOPNOTSUPP;
> +		ki->ki_flags |= IOCB_ZONE_APPEND;
> +	}
>  	return 0;
>  }
>  
> diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
> index 379a612..1ce06e9 100644
> --- a/include/uapi/linux/fs.h
> +++ b/include/uapi/linux/fs.h
> @@ -299,8 +299,11 @@ typedef int __bitwise __kernel_rwf_t;
>  /* per-IO O_APPEND */
>  #define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
>  
> +/* per-IO O_APPEND */
> +#define RWF_ZONE_APPEND	((__force __kernel_rwf_t)0x00000020)
> +
>  /* mask of flags supported by the kernel */
>  #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
> -			 RWF_APPEND)
> +			 RWF_APPEND | RWF_ZONE_APPEND)
>  
>  #endif /* _UAPI_LINUX_FS_H */
> 


-- 
Damien Le Moal
Western Digital Research

  reply index

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20200625171829epcas5p268486a0780571edb4999fc7b3caab602@epcas5p2.samsung.com>
2020-06-25 17:15 ` [PATCH v2 0/2] zone-append support in io-uring and aio Kanchan Joshi
     [not found]   ` <CGME20200625171834epcas5p226a24dfcb84cfa83fe29a2bd17795d85@epcas5p2.samsung.com>
2020-06-25 17:15     ` [PATCH v2 1/2] fs,block: Introduce RWF_ZONE_APPEND and handling in direct IO path Kanchan Joshi
2020-06-26  2:50       ` Damien Le Moal [this message]
2020-06-29 18:32         ` Kanchan Joshi
2020-06-30  0:37           ` Damien Le Moal
2020-06-30  7:40             ` Kanchan Joshi
2020-06-30  7:52               ` Damien Le Moal
2020-06-30  7:56                 ` Damien Le Moal
2020-06-30  8:16                   ` Kanchan Joshi
2020-06-26  8:58       ` Christoph Hellwig
2020-06-26 21:15         ` Kanchan Joshi
2020-06-27  6:51           ` Christoph Hellwig
     [not found]   ` <CGME20200625171838epcas5p449183e12770187142d8d55a9bf422a8d@epcas5p4.samsung.com>
2020-06-25 17:15     ` [PATCH v2 2/2] io_uring: add support for zone-append Kanchan Joshi
2020-06-25 19:40       ` Pavel Begunkov
2020-06-26  3:11   ` [PATCH v2 0/2] zone-append support in io-uring and aio Damien Le Moal
2020-06-26  6:37     ` javier.gonz
2020-06-26  6:56       ` Damien Le Moal
2020-06-26  7:03         ` javier.gonz@samsung.com
2020-06-26 22:15     ` Kanchan Joshi
2020-06-30 12:46   ` Matthew Wilcox

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=CY4PR04MB37511FB1D3B3491A2CED5470E7930@CY4PR04MB3751.namprd04.prod.outlook.com \
    --to=damien.lemoal@wdc.com \
    --cc=a.dawn@samsung.com \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=bcrl@kvack.org \
    --cc=hch@infradead.org \
    --cc=io-uring@vger.kernel.org \
    --cc=javier.gonz@samsung.com \
    --cc=joshi.k@samsung.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mb@lightnvm.io \
    --cc=nj.shetty@samsung.com \
    --cc=selvakuma.s1@samsung.com \
    --cc=viro@zeniv.linux.org.uk \
    /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

IO-Uring Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/io-uring/0 io-uring/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 io-uring io-uring/ https://lore.kernel.org/io-uring \
		io-uring@vger.kernel.org
	public-inbox-index io-uring

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.io-uring


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