Linux-api Archive on lore.kernel.org
 help / color / Atom feed
From: Kanchan Joshi <joshi.k@samsung.com>
To: axboe@kernel.dk, viro@zeniv.linux.org.uk, bcrl@kvack.org
Cc: willy@infradead.org, hch@infradead.org, Damien.LeMoal@wdc.com,
	asml.silence@gmail.com, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-aio@kvack.org,
	io-uring@vger.kernel.org, linux-block@vger.kernel.org,
	linux-api@vger.kernel.org, Kanchan Joshi <joshi.k@samsung.com>,
	Selvakumar S <selvakuma.s1@samsung.com>,
	Nitesh Shetty <nj.shetty@samsung.com>,
	Arnav Dawn <a.dawn@samsung.com>,
	Javier Gonzalez <javier.gonz@samsung.com>
Subject: [PATCH v4 4/6] block: add zone append handling for direct I/O path
Date: Fri, 24 Jul 2020 21:19:20 +0530
Message-ID: <1595605762-17010-5-git-send-email-joshi.k@samsung.com> (raw)
In-Reply-To: <1595605762-17010-1-git-send-email-joshi.k@samsung.com>

For zoned block device, opt in for 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 written-offset, in bytes, to upper layer via ret2 of
kiocb->ki_complete interface.
Write with the flag IOCB_ZONE_APPEND are ensured not be be short.
Prevent short write and instead return failure if appending write spans
beyond end of device.
Return failure if write is larger than max_append_limit and therefore
requires formation of multiple bios.

Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Selvakumar S <selvakuma.s1@samsung.com>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Arnav Dawn <a.dawn@samsung.com>
Signed-off-by: Javier Gonzalez <javier.gonz@samsung.com>
---
 fs/block_dev.c | 51 +++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 47860e5..3b5836b 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 +304,14 @@ static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
 	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
 }
 
+static inline long long blkdev_bio_ret2(struct kiocb *iocb, struct bio *bio)
+{
+	/* return written-offset for zone append in bytes */
+	if (op_is_write(bio_op(bio)) && iocb->ki_flags & IOCB_ZONE_APPEND)
+		return bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	return 0;
+}
+
 static void blkdev_bio_end_io(struct bio *bio)
 {
 	struct blkdev_dio *dio = bio->bi_private;
@@ -307,15 +324,17 @@ static void blkdev_bio_end_io(struct bio *bio)
 		if (!dio->is_sync) {
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
+			long long ret2;
 
 			if (likely(!dio->bio.bi_status)) {
 				ret = dio->size;
 				iocb->ki_pos += ret;
+				ret2 = blkdev_bio_ret2(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, ret2);
 			if (dio->multi_bio)
 				bio_put(&dio->bio);
 		} else {
@@ -382,6 +401,7 @@ __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 +411,9 @@ __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 +437,12 @@ __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 +1865,7 @@ 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 +1891,11 @@ 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)
@@ -2017,7 +2046,9 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
-	iov_iter_truncate(from, size - iocb->ki_pos);
+	if (iov_iter_truncate(from, size - iocb->ki_pos) &&
+			(iocb->ki_flags & IOCB_ZONE_APPEND))
+		return -ENOSPC;
 
 	blk_start_plug(&plug);
 	ret = __generic_file_write_iter(iocb, from);
-- 
2.7.4


  parent reply index

Thread overview: 49+ 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     ` Kanchan Joshi [this message]
2020-07-26 15:19       ` [PATCH v4 4/6] block: add zone append handling for direct I/O path 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
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
2020-07-31  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=1595605762-17010-5-git-send-email-joshi.k@samsung.com \
    --to=joshi.k@samsung.com \
    --cc=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=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

Linux-api Archive on lore.kernel.org

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

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-api


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