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],
Selvakumar S <[email protected]>,
Kanchan Joshi <[email protected]>,
Nitesh Shetty <[email protected]>,
Arnav Dawn <[email protected]>,
Javier Gonzalez <[email protected]>
Subject: [PATCH v3 2/4] block: add zone append handling for direct I/O path
Date: Mon, 6 Jul 2020 00:17:48 +0530 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
From: Selvakumar S <[email protected]>
For zoned block device, subscribe to zone-append by setting
FMODE_ZONE_APPEND during open. Make direct IO submission path use
IOCB_ZONE_APPEND to send bio with append op. Make direct IO completion
return zone-relative offset, in sector unit, to upper layer using
kiocb->ki_complete interface.
Return failure if write is larger than max_append_limit and therefore
requires formation of multiple bios.
Signed-off-by: Selvakumar S <[email protected]>
Signed-off-by: Kanchan Joshi <[email protected]>
Signed-off-by: Nitesh Shetty <[email protected]>
Signed-off-by: Arnav Dawn <[email protected]>
Signed-off-by: Javier Gonzalez <[email protected]>
---
fs/block_dev.c | 49 ++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 40 insertions(+), 9 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 47860e5..941fb22 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -178,10 +178,19 @@ static struct inode *bdev_file_inode(struct file *file)
return file->f_mapping->host;
}
-static unsigned int dio_bio_write_op(struct kiocb *iocb)
+static unsigned int dio_bio_op(bool is_read, struct kiocb *iocb)
{
- unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+ unsigned int op;
+ if (is_read)
+ return REQ_OP_READ;
+
+ if (iocb->ki_flags & IOCB_ZONE_APPEND)
+ op = REQ_OP_ZONE_APPEND;
+ else
+ op = REQ_OP_WRITE;
+
+ op |= REQ_SYNC | REQ_IDLE;
/* avoid the need for a I/O completion work item */
if (iocb->ki_flags & IOCB_DSYNC)
op |= REQ_FUA;
@@ -207,6 +216,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
loff_t pos = iocb->ki_pos;
bool should_dirty = false;
+ bool is_read = (iov_iter_rw(iter) == READ);
struct bio bio;
ssize_t ret;
blk_qc_t qc;
@@ -231,18 +241,17 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
bio.bi_private = current;
bio.bi_end_io = blkdev_bio_end_io_simple;
bio.bi_ioprio = iocb->ki_ioprio;
+ bio.bi_opf = dio_bio_op(is_read, iocb);
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
goto out;
ret = bio.bi_iter.bi_size;
- if (iov_iter_rw(iter) == READ) {
- bio.bi_opf = REQ_OP_READ;
+ if (is_read) {
if (iter_is_iovec(iter))
should_dirty = true;
} else {
- bio.bi_opf = dio_bio_write_op(iocb);
task_io_account_write(ret);
}
if (iocb->ki_flags & IOCB_HIPRI)
@@ -295,6 +304,16 @@ static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
}
+static inline long blkdev_bio_res2(struct kiocb *iocb, struct bio *bio)
+{
+ /* calculate zone relative offset for zone append */
+ if (op_is_write(bio_op(bio)) && iocb->ki_flags & IOCB_ZONE_APPEND) {
+ sector_t zone_sec = blk_queue_zone_sectors(bio->bi_disk->queue);
+ return bio->bi_iter.bi_sector & (zone_sec - 1);
+ }
+ return 0;
+}
+
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
@@ -307,15 +326,17 @@ static void blkdev_bio_end_io(struct bio *bio)
if (!dio->is_sync) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
+ long res2;
if (likely(!dio->bio.bi_status)) {
ret = dio->size;
iocb->ki_pos += ret;
+ res2 = blkdev_bio_res2(iocb, bio);
} else {
ret = blk_status_to_errno(dio->bio.bi_status);
}
- 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 +403,7 @@ __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 = dio_bio_op(is_read, iocb);
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
@@ -391,11 +413,9 @@ __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);
}
@@ -419,6 +439,12 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
}
if (!dio->multi_bio) {
+ /* zone-append cannot work with multi bio*/
+ if (!is_read && iocb->ki_flags & IOCB_ZONE_APPEND) {
+ bio->bi_status = BLK_STS_IOERR;
+ bio_endio(bio);
+ break;
+ }
/*
* AIO needs an extra reference to ensure the dio
* structure which is embedded into the first bio
@@ -1841,6 +1867,7 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
static int blkdev_open(struct inode * inode, struct file * filp)
{
struct block_device *bdev;
+ int ret;
/*
* Preserve backwards compatibility and allow large file access
@@ -1866,7 +1893,11 @@ static int blkdev_open(struct inode * inode, struct file * filp)
filp->f_mapping = bdev->bd_inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
- return blkdev_get(bdev, filp->f_mode, filp);
+ ret = blkdev_get(bdev, filp->f_mode, filp);
+ if (blk_queue_is_zoned(bdev->bd_disk->queue))
+ filp->f_mode |= FMODE_ZONE_APPEND;
+
+ return ret;
}
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
--
2.7.4
next prev parent reply other threads:[~2020-07-05 18:52 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20200705185204epcas5p3adeb4fc3473c5fc0472a7396783c5267@epcas5p3.samsung.com>
2020-07-05 18:47 ` [PATCH v3 0/4] zone-append support in io-uring and aio Kanchan Joshi
[not found] ` <CGME20200705185211epcas5p4059d05d2fcedb91829300a7a7d03fda3@epcas5p4.samsung.com>
2020-07-05 18:47 ` [PATCH v3 1/4] fs: introduce FMODE_ZONE_APPEND and IOCB_ZONE_APPEND Kanchan Joshi
[not found] ` <CGME20200705185217epcas5p1cc12d4b892f057a1fe06d73a00869daa@epcas5p1.samsung.com>
2020-07-05 18:47 ` Kanchan Joshi [this message]
[not found] ` <CGME20200705185221epcas5p28b6d060df829b751109265222285da0e@epcas5p2.samsung.com>
2020-07-05 18:47 ` [PATCH v3 3/4] block: enable zone-append for iov_iter of bvec type Kanchan Joshi
[not found] ` <CGME20200705185227epcas5p16fba3cb92561794b960184c89fdf2bb7@epcas5p1.samsung.com>
2020-07-05 18:47 ` [PATCH v3 4/4] io_uring: add support for zone-append Kanchan Joshi
2020-07-05 21:00 ` Jens Axboe
2020-07-05 21:09 ` Matthew Wilcox
2020-07-05 21:12 ` Jens Axboe
2020-07-06 14:10 ` Matthew Wilcox
2020-07-06 14:27 ` Jens Axboe
2020-07-06 14:32 ` Matthew Wilcox
2020-07-06 14:33 ` Jens Axboe
2020-07-07 15:11 ` Kanchan Joshi
2020-07-07 15:52 ` Matthew Wilcox
2020-07-07 16:00 ` Christoph Hellwig
2020-07-07 20:23 ` Kanchan Joshi
2020-07-07 20:40 ` Jens Axboe
2020-07-07 22:18 ` Matthew Wilcox
2020-07-07 22:37 ` Jens Axboe
2020-07-08 12:58 ` Kanchan Joshi
2020-07-08 14:22 ` Matthew Wilcox
2020-07-08 16:41 ` Kanchan Joshi
2020-07-08 14:54 ` Jens Axboe
2020-07-08 14:58 ` Matthew Wilcox
2020-07-08 14:59 ` Jens Axboe
2020-07-08 15:02 ` Matthew Wilcox
2020-07-08 15:06 ` Jens Axboe
2020-07-08 16:08 ` Javier González
2020-07-08 16:33 ` Matthew Wilcox
2020-07-08 16:38 ` Jens Axboe
2020-07-08 17:13 ` Kanchan Joshi
2020-07-08 16:43 ` Javier González
2020-07-06 13:58 ` Kanchan Joshi
2020-07-09 10:15 ` Christoph Hellwig
2020-07-09 13:58 ` Jens Axboe
2020-07-09 14:00 ` Christoph Hellwig
2020-07-09 14:05 ` Jens Axboe
2020-07-09 18:36 ` Kanchan Joshi
2020-07-09 18:50 ` Pavel Begunkov
2020-07-09 18:53 ` Pavel Begunkov
2020-07-09 18:50 ` Jens Axboe
2020-07-09 19:05 ` Kanchan Joshi
2020-07-10 13:10 ` Christoph Hellwig
2020-07-10 13:48 ` Matthew Wilcox
2020-07-10 13:49 ` Christoph Hellwig
2020-07-10 13:51 ` Matthew Wilcox
2020-07-10 14:11 ` Kanchan Joshi
2020-07-20 16:49 ` Kanchan Joshi
2020-07-20 17:14 ` Matthew Wilcox
2020-07-20 20:17 ` Kanchan Joshi
2020-07-21 0:59 ` Damien Le Moal
2020-07-21 1:15 ` Matthew Wilcox
2020-07-21 1:29 ` Jens Axboe
2020-07-21 2:19 ` Damien Le Moal
2020-07-10 14:09 ` Jens Axboe
2020-07-20 16:46 ` Kanchan Joshi
2020-07-10 13:09 ` Christoph Hellwig
2020-07-10 13:29 ` Kanchan Joshi
2020-07-10 13:43 ` Christoph Hellwig
2020-07-20 17:02 ` Kanchan Joshi
2020-07-10 13:57 ` Kanchan Joshi
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=1593974870-18919-3-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