IO-Uring Archive on lore.kernel.org
 help / color / Atom feed
From: Kanchan Joshi <joshiiitr@gmail.com>
To: "hch@infradead.org" <hch@infradead.org>
Cc: Damien Le Moal <Damien.LeMoal@wdc.com>,
	Jens Axboe <axboe@kernel.dk>,
	Pavel Begunkov <asml.silence@gmail.com>,
	Kanchan Joshi <joshi.k@samsung.com>,
	"viro@zeniv.linux.org.uk" <viro@zeniv.linux.org.uk>,
	"bcrl@kvack.org" <bcrl@kvack.org>,
	Matthew Wilcox <willy@infradead.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"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>,
	"linux-api@vger.kernel.org" <linux-api@vger.kernel.org>,
	SelvaKumar S <selvakuma.s1@samsung.com>,
	Nitesh Shetty <nj.shetty@samsung.com>,
	Javier Gonzalez <javier.gonz@samsung.com>,
	Johannes Thumshirn <Johannes.Thumshirn@wdc.com>,
	Naohiro Aota <Naohiro.Aota@wdc.com>
Subject: Re: [PATCH v4 6/6] io_uring: add support for zone-append
Date: Fri, 31 Jul 2020 20:37:35 +0530
Message-ID: <CA+1E3r+7ZChHK+ZH06LitijEbZ0=UhOtAzLpw4SWVY1ZN4HOSw@mail.gmail.com> (raw)
In-Reply-To: <20200731130802.GA16665@infradead.org>

On Fri, Jul 31, 2020 at 6:38 PM hch@infradead.org <hch@infradead.org> wrote:
>
> And FYI, this is what I'd do for a hacky aio-only prototype (untested):
>
>
> diff --git a/fs/aio.c b/fs/aio.c
> index 91e7cc4a9f179b..42b1934e38758b 100644
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -1438,7 +1438,10 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
>         }
>
>         iocb->ki_res.res = res;
> -       iocb->ki_res.res2 = res2;
> +       if ((kiocb->ki_flags & IOCB_REPORT_OFFSET) && res > 0)
> +               iocb->ki_res.res2 = kiocb->ki_pos - res;
> +       else
> +               iocb->ki_res.res2 = res2;
>         iocb_put(iocb);
>  }
>
> @@ -1452,6 +1455,8 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
>         req->ki_flags = iocb_flags(req->ki_filp);
>         if (iocb->aio_flags & IOCB_FLAG_RESFD)
>                 req->ki_flags |= IOCB_EVENTFD;
> +       if (iocb->aio_flags & IOCB_FLAG_REPORT_OFFSET)
> +               req->ki_flags |= IOCB_REPORT_OFFSET;
>         req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp));
>         if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
>                 /*
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index f5abba86107d86..522b0a3437d420 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -316,6 +316,7 @@ enum rw_hint {
>  #define IOCB_WRITE             (1 << 6)
>  #define IOCB_NOWAIT            (1 << 7)
>  #define IOCB_NOIO              (1 << 9)
> +#define IOCB_REPORT_OFFSET     (1 << 10)
>
>  struct kiocb {
>         struct file             *ki_filp;
> diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
> index 8387e0af0f768a..e4313d7aa3b7e7 100644
> --- a/include/uapi/linux/aio_abi.h
> +++ b/include/uapi/linux/aio_abi.h
> @@ -55,6 +55,7 @@ enum {
>   */
>  #define IOCB_FLAG_RESFD                (1 << 0)
>  #define IOCB_FLAG_IOPRIO       (1 << 1)
> +#define IOCB_FLAG_REPORT_OFFSET        (1 << 2)
>
>  /* read() from /dev/aio returns these structures. */
>  struct io_event {

Looks good, but it drops io_uring.
How about two flags -
1. RWF_REPORT_OFFSET (only for aio)  ----> aio fails the second one
2. RWF_REPORT_OFFSET_INDIRECT (for io_uring).  ----> uring fails the first one
Since these are RWF flags, they can be used by other sync/async
transports also in future if need be.
Either of these flags will set single IOCB_REPORT_OFFSET, which can be
used by FS/Block etc (they don't have to worry how uring/aio sends it
up).

This is what I mean in code -

diff --git a/fs/aio.c b/fs/aio.c
index 91e7cc4a9f17..307dfbfb04f7 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1472,6 +1472,11 @@ static int aio_prep_rw(struct kiocb *req, const
struct iocb *iocb)
        ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
        if (unlikely(ret))
                return ret;
+       /* support only direct offset */
+       if (unlikely(iocb->aio_rw_flags & RWF_REPORT_OFFSET_INDIRECT))
+               return -EOPNOTSUPP;
+
        req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */
        return 0;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3e406bc1f855..5fa21644251f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2451,6 +2451,7 @@ static int io_prep_rw(struct io_kiocb *req,
const struct io_uring_sqe *sqe,
        struct kiocb *kiocb = &req->rw.kiocb;
        unsigned ioprio;
        int ret;
+       rwf_t rw_flags;

        if (S_ISREG(file_inode(req->file)->i_mode))
                req->flags |= REQ_F_ISREG;
@@ -2462,9 +2463,13 @@ static int io_prep_rw(struct io_kiocb *req,
const struct io_uring_sqe *sqe,
        }
        kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
        kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
-       ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
+       rw_flags = READ_ONCE(sqe->rw_flags);
+       ret = kiocb_set_rw_flags(kiocb, rw_flags);
        if (unlikely(ret))
                return ret;
+       /* support only indirect offset */
+       if (unlikely(rw_flags & RWF_REPORT_OFFSET_DIRECT))
+               return -EOPNOTSUPP;

        ioprio = READ_ONCE(sqe->ioprio);
        if (ioprio) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8a00ba99284e..fe2f1f5c5d33 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3296,8 +3296,17 @@ static inline int kiocb_set_rw_flags(struct
kiocb *ki, rwf_t flags)
                ki->ki_flags |= IOCB_DSYNC;
        if (flags & RWF_SYNC)
                ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
-       if (flags & RWF_APPEND)
+       if (flags & RWF_APPEND) {
                ki->ki_flags |= IOCB_APPEND;
+               /*
+                * 1. These flags do not make sense when used standalone
+                * 2. RWF_REPORT_OFFSET_DIRECT = report result
directly (for aio)
+                * 3. RWF_REPORT_INDIRECT_OFFSER = use pointer (for io_uring)
+                * */
+               if (flags & RWF_REPORT_OFFSET_DIRECT ||
+                               flags & RWF_REPORT_OFFSET_INDIRECT)
+                       ki->ki_flags |= IOCB_REPORT_OFFSET;

  reply index

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20200724155244epcas5p2902f57e36e490ee8772da19aa9408cdc@epcas5p2.samsung.com>
2020-07-24 15:49 ` [PATCH v4 0/6] zone-append support in io-uring and aio Kanchan Joshi
     [not found]   ` <CGME20200724155258epcas5p1a75b926950a18cd1e6c8e7a047e6c589@epcas5p1.samsung.com>
2020-07-24 15:49     ` [PATCH v4 1/6] fs: introduce FMODE_ZONE_APPEND and IOCB_ZONE_APPEND Kanchan Joshi
2020-07-24 16:34       ` Jens Axboe
2020-07-26 15:18       ` Christoph Hellwig
2020-07-28  1:49         ` Matthew Wilcox
2020-07-28  7:26           ` Christoph Hellwig
     [not found]   ` <CGME20200724155324epcas5p18e1d3b4402d1e4a8eca87d0b56a3fa9b@epcas5p1.samsung.com>
2020-07-24 15:49     ` [PATCH v4 2/6] fs: change ki_complete interface to support 64bit ret2 Kanchan Joshi
2020-07-26 15:18       ` Christoph Hellwig
     [not found]   ` <CGME20200724155329epcas5p345ba6bad0b8fe18056bb4bcd26c10019@epcas5p3.samsung.com>
2020-07-24 15:49     ` [PATCH v4 3/6] uio: return status with iov truncation Kanchan Joshi
     [not found]   ` <CGME20200724155341epcas5p15bfc55927f2abb60f19784270fe8e377@epcas5p1.samsung.com>
2020-07-24 15:49     ` [PATCH v4 4/6] block: add zone append handling for direct I/O path Kanchan Joshi
2020-07-26 15:19       ` Christoph Hellwig
     [not found]   ` <CGME20200724155346epcas5p2cfb383fe9904a45280c6145f4c13e1b4@epcas5p2.samsung.com>
2020-07-24 15:49     ` [PATCH v4 5/6] block: enable zone-append for iov_iter of bvec type Kanchan Joshi
2020-07-26 15:20       ` Christoph Hellwig
     [not found]   ` <CGME20200724155350epcas5p3b8f1d59eda7f8fbb38c828f692d42fd6@epcas5p3.samsung.com>
2020-07-24 15:49     ` [PATCH v4 6/6] io_uring: add support for zone-append Kanchan Joshi
2020-07-24 16:29       ` Jens Axboe
2020-07-27 19:16         ` Kanchan Joshi
2020-07-27 20:34           ` Jens Axboe
2020-07-30 16:08             ` Pavel Begunkov
2020-07-30 16:13               ` Jens Axboe
2020-07-30 16:26                 ` Pavel Begunkov
2020-07-30 17:16                   ` Jens Axboe
2020-07-30 17:38                     ` Pavel Begunkov
2020-07-30 17:51                       ` Kanchan Joshi
2020-07-30 17:54                         ` Jens Axboe
2020-07-30 18:25                           ` Kanchan Joshi
2020-07-31  6:42                             ` Damien Le Moal
2020-07-31  6:45                               ` hch
2020-07-31  6:59                                 ` Damien Le Moal
2020-07-31  7:58                                   ` Kanchan Joshi
2020-07-31  8:14                                     ` Damien Le Moal
2020-07-31  9:14                                       ` hch
2020-07-31  9:34                                         ` Damien Le Moal
2020-07-31  9:41                                           ` hch
2020-07-31 10:16                                             ` Damien Le Moal
2020-07-31 12:51                                               ` hch
2020-07-31 13:08                                                 ` hch
2020-07-31 15:07                                                   ` Kanchan Joshi [this message]
2020-08-05  7:35                                                 ` Damien Le Moal
2020-08-14  8:14                                                   ` hch
2020-08-14  8:27                                                     ` Damien Le Moal
2020-08-14 12:04                                                       ` hch
2020-08-14 12:20                                                         ` Damien Le Moal
2020-07-31  9:38                                       ` Kanchan Joshi
2020-07-31  7:08                               ` Kanchan Joshi
2020-07-30 15:57       ` Pavel Begunkov

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='CA+1E3r+7ZChHK+ZH06LitijEbZ0=UhOtAzLpw4SWVY1ZN4HOSw@mail.gmail.com' \
    --to=joshiiitr@gmail.com \
    --cc=Damien.LeMoal@wdc.com \
    --cc=Johannes.Thumshirn@wdc.com \
    --cc=Naohiro.Aota@wdc.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-api@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nj.shetty@samsung.com \
    --cc=selvakuma.s1@samsung.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.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

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