From: Kanchan Joshi <[email protected]>
To: [email protected], [email protected], [email protected]
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected],
[email protected], [email protected],
[email protected], [email protected],
[email protected],
SelvaKumar S <[email protected]>,
Kanchan Joshi <[email protected]>,
Nitesh Shetty <[email protected]>,
Javier Gonzalez <[email protected]>
Subject: [PATCH v4 6/6] io_uring: add support for zone-append
Date: Fri, 24 Jul 2020 21:19:22 +0530 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
From: SelvaKumar S <[email protected]>
Repurpose [cqe->res, cqe->flags] into cqe->res64 (signed) to report
64bit written-offset for zone-append. The appending-write which requires
reporting written-location (conveyed by IOCB_ZONE_APPEND flag) is
ensured not to be a short-write; this avoids the need to report
number-of-bytes-copied.
append-offset is returned by lower-layer to io-uring via ret2 of
ki_complete interface. Make changes to collect it and send to user-space
via cqe->res64.
Signed-off-by: SelvaKumar S <[email protected]>
Signed-off-by: Kanchan Joshi <[email protected]>
Signed-off-by: Nitesh Shetty <[email protected]>
Signed-off-by: Javier Gonzalez <[email protected]>
---
fs/io_uring.c | 49 ++++++++++++++++++++++++++++++++++++-------
include/uapi/linux/io_uring.h | 9 ++++++--
2 files changed, 48 insertions(+), 10 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7809ab2..6510cf5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -401,7 +401,14 @@ struct io_rw {
/* NOTE: kiocb has the file as the first member, so don't do it here */
struct kiocb kiocb;
u64 addr;
- u64 len;
+ union {
+ /*
+ * len is used only during submission.
+ * append_offset is used only during completion.
+ */
+ u64 len;
+ u64 append_offset;
+ };
};
struct io_connect {
@@ -541,6 +548,7 @@ enum {
REQ_F_NO_FILE_TABLE_BIT,
REQ_F_QUEUE_TIMEOUT_BIT,
REQ_F_WORK_INITIALIZED_BIT,
+ REQ_F_ZONE_APPEND_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -598,6 +606,8 @@ enum {
REQ_F_QUEUE_TIMEOUT = BIT(REQ_F_QUEUE_TIMEOUT_BIT),
/* io_wq_work is initialized */
REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT),
+ /* to return zone append offset */
+ REQ_F_ZONE_APPEND = BIT(REQ_F_ZONE_APPEND_BIT),
};
struct async_poll {
@@ -1244,8 +1254,15 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
req->flags &= ~REQ_F_OVERFLOW;
if (cqe) {
WRITE_ONCE(cqe->user_data, req->user_data);
- WRITE_ONCE(cqe->res, req->result);
- WRITE_ONCE(cqe->flags, req->cflags);
+ if (unlikely(req->flags & REQ_F_ZONE_APPEND)) {
+ if (likely(req->result > 0))
+ WRITE_ONCE(cqe->res64, req->rw.append_offset);
+ else
+ WRITE_ONCE(cqe->res64, req->result);
+ } else {
+ WRITE_ONCE(cqe->res, req->result);
+ WRITE_ONCE(cqe->flags, req->cflags);
+ }
} else {
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1284,8 +1301,15 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
cqe = io_get_cqring(ctx);
if (likely(cqe)) {
WRITE_ONCE(cqe->user_data, req->user_data);
- WRITE_ONCE(cqe->res, res);
- WRITE_ONCE(cqe->flags, cflags);
+ if (unlikely(req->flags & REQ_F_ZONE_APPEND)) {
+ if (likely(res > 0))
+ WRITE_ONCE(cqe->res64, req->rw.append_offset);
+ else
+ WRITE_ONCE(cqe->res64, res);
+ } else {
+ WRITE_ONCE(cqe->res, res);
+ WRITE_ONCE(cqe->flags, cflags);
+ }
} else if (ctx->cq_overflow_flushed) {
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1943,7 +1967,7 @@ static inline void req_set_fail_links(struct io_kiocb *req)
req->flags |= REQ_F_FAIL_LINK;
}
-static void io_complete_rw_common(struct kiocb *kiocb, long res)
+static void io_complete_rw_common(struct kiocb *kiocb, long res, long long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
int cflags = 0;
@@ -1955,6 +1979,9 @@ static void io_complete_rw_common(struct kiocb *kiocb, long res)
req_set_fail_links(req);
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_kbuf(req);
+ if (req->flags & REQ_F_ZONE_APPEND)
+ req->rw.append_offset = res2;
+
__io_cqring_add_event(req, res, cflags);
}
@@ -1962,7 +1989,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
- io_complete_rw_common(kiocb, res);
+ io_complete_rw_common(kiocb, res, res2);
io_put_req(req);
}
@@ -1976,8 +2003,11 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long long res2)
if (res != req->result)
req_set_fail_links(req);
req->result = res;
- if (res != -EAGAIN)
+ if (res != -EAGAIN) {
+ if (req->flags & REQ_F_ZONE_APPEND)
+ req->rw.append_offset = res2;
WRITE_ONCE(req->iopoll_completed, 1);
+ }
}
/*
@@ -2739,6 +2769,9 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
SB_FREEZE_WRITE);
}
kiocb->ki_flags |= IOCB_WRITE;
+ /* zone-append requires few extra steps during completion */
+ if (kiocb->ki_flags & IOCB_ZONE_APPEND)
+ req->flags |= REQ_F_ZONE_APPEND;
if (!force_nonblock)
current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92c2269..2580d93 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -156,8 +156,13 @@ enum {
*/
struct io_uring_cqe {
__u64 user_data; /* sqe->data submission passed back */
- __s32 res; /* result code for this event */
- __u32 flags;
+ union {
+ struct {
+ __s32 res; /* result code for this event */
+ __u32 flags;
+ };
+ __s64 res64; /* appending offset for zone append */
+ };
};
/*
--
2.7.4
next prev parent reply other threads:[~2020-07-24 16:24 UTC|newest]
Thread overview: 55+ 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 ` Kanchan Joshi [this message]
2020-07-24 16:29 ` [PATCH v4 6/6] io_uring: add support for zone-append 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
2022-03-02 20:47 ` Luis Chamberlain
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
2020-09-07 7:01 ` Kanchan Joshi
2020-09-08 15:18 ` hch
2020-09-24 17:19 ` Kanchan Joshi
2020-09-25 2:52 ` Damien Le Moal
2020-09-28 18:58 ` Kanchan Joshi
2020-09-29 1:24 ` Damien Le Moal
2020-09-29 18:49 ` Kanchan Joshi
2022-03-02 20:43 ` Luis Chamberlain
2020-07-31 9:38 ` Kanchan Joshi
2022-03-02 20:51 ` Luis Chamberlain
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=1595605762-17010-7-git-send-email-joshi.k@samsung.com \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox