From: Goldwyn Rodrigues <rgoldwyn@suse.de>
To: linux-fsdevel@vger.kernel.org
Cc: jack@suse.com, hch@infradead.org, linux-block@vger.kernel.org,
linux-btrfs@vger.kernel.org, linux-ext4@vger.kernel.org,
linux-xfs@vger.kernel.org, sagi@grimberg.me, avi@scylladb.com,
axboe@kernel.dk, linux-api@vger.kernel.org, willy@infradead.org,
tom.leiming@gmail.com, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH 5/8] nowait aio: return on congested block device
Date: Fri, 14 Apr 2017 07:02:54 -0500 [thread overview]
Message-ID: <20170414120257.8932-6-rgoldwyn@suse.de> (raw)
In-Reply-To: <20170414120257.8932-1-rgoldwyn@suse.de>
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
A new bio operation flag REQ_NOWAIT is introduced to identify bio's
orignating from iocb with IOCB_NOWAIT. This flag indicates
to return immediately if a request cannot be made instead
of retrying.
To facilitate this, QUEUE_FLAG_NOWAIT is set to devices
which support this. While currently this is set to
virtio and sd only. Support to more devices will be added soon
once I am sure they don't block. Currently blocks such as dm/md
block while performing sync.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
block/blk-core.c | 24 ++++++++++++++++++++++--
block/blk-mq-sched.c | 3 +++
block/blk-mq.c | 4 ++++
drivers/block/virtio_blk.c | 3 +++
drivers/scsi/sd.c | 3 +++
fs/direct-io.c | 10 ++++++++--
include/linux/bio.h | 6 ++++++
include/linux/blk_types.h | 2 ++
include/linux/blkdev.h | 3 +++
9 files changed, 54 insertions(+), 4 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index d772c221cc17..54698521756b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1232,6 +1232,11 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
if (!IS_ERR(rq))
return rq;
+ if (bio && (bio->bi_opf & REQ_NOWAIT)) {
+ blk_put_rl(rl);
+ return ERR_PTR(-EAGAIN);
+ }
+
if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
blk_put_rl(rl);
return rq;
@@ -1870,6 +1875,18 @@ generic_make_request_checks(struct bio *bio)
goto end_io;
}
+ if (bio->bi_opf & REQ_NOWAIT) {
+ if (!blk_queue_nowait(q)) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
+ if (!(bio->bi_opf & REQ_SYNC)) {
+ err = -EINVAL;
+ goto end_io;
+ }
+ }
+
+
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
@@ -2021,7 +2038,7 @@ blk_qc_t generic_make_request(struct bio *bio)
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- if (likely(blk_queue_enter(q, false) == 0)) {
+ if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
struct bio_list lower, same;
/* Create a fresh bio_list for all subordinate requests */
@@ -2046,7 +2063,10 @@ blk_qc_t generic_make_request(struct bio *bio)
bio_list_merge(&bio_list_on_stack[0], &same);
bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
- bio_io_error(bio);
+ if (unlikely(!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT)))
+ bio_wouldblock_error(bio);
+ else
+ bio_io_error(bio);
}
bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index c974a1bbf4cb..9f88190ff395 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -119,6 +119,9 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
if (likely(!data->hctx))
data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+ if (bio && (bio->bi_opf & REQ_NOWAIT))
+ data->flags |= BLK_MQ_REQ_NOWAIT;
+
if (e) {
data->flags |= BLK_MQ_REQ_INTERNAL;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 572966f49596..8b9b1a411ce2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1538,6 +1538,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
+ if (bio && (bio->bi_opf & REQ_NOWAIT))
+ bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
@@ -1662,6 +1664,8 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
+ if (bio && (bio->bi_opf & REQ_NOWAIT))
+ bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 1d4c9f8bc1e1..7481124c5025 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -731,6 +731,9 @@ static int virtblk_probe(struct virtio_device *vdev)
/* No real sector limit. */
blk_queue_max_hw_sectors(q, -1U);
+ /* Request queue supports BIO_NOWAIT */
+ queue_flag_set_unlocked(QUEUE_FLAG_NOWAIT, q);
+
/* Host can optionally specify maximum segment size and number of
* segments. */
err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fcfeddc79331..9df85ee165be 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3177,6 +3177,9 @@ static int sd_probe(struct device *dev)
SD_MOD_TIMEOUT);
}
+ /* Support BIO_NOWAIT */
+ queue_flag_set_unlocked(QUEUE_FLAG_NOWAIT, sdp->request_queue);
+
device_initialize(&sdkp->dev);
sdkp->dev.parent = dev;
sdkp->dev.class = &sd_disk_class;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index a04ebea77de8..a802168284e1 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -480,8 +480,12 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
unsigned i;
int err;
- if (bio->bi_error)
- dio->io_error = -EIO;
+ if (bio->bi_error) {
+ if (bio->bi_opf & REQ_NOWAIT)
+ dio->io_error = -EAGAIN;
+ else
+ dio->io_error = -EIO;
+ }
if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
err = bio->bi_error;
@@ -1197,6 +1201,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
if (iov_iter_rw(iter) == WRITE) {
dio->op = REQ_OP_WRITE;
dio->op_flags = REQ_SYNC | REQ_IDLE;
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ dio->op_flags |= REQ_NOWAIT;
} else {
dio->op = REQ_OP_READ;
}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8e521194f6fc..1a9270744b1e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -425,6 +425,12 @@ static inline void bio_io_error(struct bio *bio)
bio_endio(bio);
}
+static inline void bio_wouldblock_error(struct bio *bio)
+{
+ bio->bi_error = -EAGAIN;
+ bio_endio(bio);
+}
+
struct request_queue;
extern int bio_phys_segments(struct request_queue *, struct bio *);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d703acb55d0f..5ce4da30ba43 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -187,6 +187,7 @@ enum req_flag_bits {
__REQ_PREFLUSH, /* request for cache flush */
__REQ_RAHEAD, /* read ahead, can fail anytime */
__REQ_BACKGROUND, /* background IO */
+ __REQ_NOWAIT, /* Don't wait if request will block */
__REQ_NR_BITS, /* stops here */
};
@@ -203,6 +204,7 @@ enum req_flag_bits {
#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH)
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND)
+#define REQ_NOWAIT (1ULL << __REQ_NOWAIT)
#define REQ_FAILFAST_MASK \
(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7548f332121a..df0b1245d955 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -610,6 +610,8 @@ struct request_queue {
#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */
#define QUEUE_FLAG_DAX 26 /* device supports DAX */
#define QUEUE_FLAG_STATS 27 /* track rq completion times */
+/* can return immediately on congestion (for REQ_NOWAIT) */
+#define QUEUE_FLAG_NOWAIT 28
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
@@ -700,6 +702,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
#define blk_queue_secure_erase(q) \
(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
+#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
#define blk_noretry_request(rq) \
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
--
2.12.0
next prev parent reply other threads:[~2017-04-14 12:02 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-14 12:02 [PATCH 0/8 v6] No wait AIO Goldwyn Rodrigues
[not found] ` <20170414120257.8932-1-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-04-14 12:02 ` [PATCH 1/8] Use RWF_* flags for AIO operations Goldwyn Rodrigues
[not found] ` <20170414120257.8932-2-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-04-19 6:37 ` Christoph Hellwig
2017-04-14 12:02 ` [PATCH 2/8] nowait aio: Introduce RWF_NOWAIT Goldwyn Rodrigues
2017-04-19 6:39 ` Christoph Hellwig
[not found] ` <20170419063930.GB20053-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2017-04-19 10:30 ` Goldwyn Rodrigues
[not found] ` <2d816e3e-3625-7ebd-8550-68a7cc9c1a2e-l3A5Bk7waGM@public.gmane.org>
2017-04-19 11:03 ` Jan Kara
2017-04-14 12:02 ` [PATCH 3/8] nowait aio: return if direct write will trigger writeback Goldwyn Rodrigues
2017-04-14 12:02 ` [PATCH 4/8] nowait-aio: Introduce IOMAP_NOWAIT Goldwyn Rodrigues
2017-04-19 6:39 ` Christoph Hellwig
[not found] ` <20170414120257.8932-5-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-04-19 7:12 ` Jan Kara
2017-04-14 12:02 ` Goldwyn Rodrigues [this message]
2017-04-19 6:45 ` [PATCH 5/8] nowait aio: return on congested block device Christoph Hellwig
2017-04-19 15:21 ` Goldwyn Rodrigues
2017-04-20 13:43 ` Jan Kara
2017-04-24 21:10 ` Goldwyn Rodrigues
2017-04-25 2:28 ` Jens Axboe
2017-04-14 12:02 ` [PATCH 6/8] nowait aio: ext4 Goldwyn Rodrigues
2017-04-14 12:02 ` [PATCH 7/8] nowait aio: xfs Goldwyn Rodrigues
2017-04-19 6:45 ` Christoph Hellwig
2017-04-14 12:02 ` [PATCH 8/8] nowait aio: btrfs Goldwyn Rodrigues
[not found] ` <20170414120257.8932-9-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-04-18 11:39 ` David Sterba
-- strict thread matches above, loose matches on Subject: below --
2017-05-09 12:22 [PATCH 0/8 v7] No wait AIO Goldwyn Rodrigues
2017-05-09 12:22 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues
2017-05-11 7:44 ` Christoph Hellwig
[not found] ` <20170511074451.GD15626-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2017-05-11 18:16 ` Goldwyn Rodrigues
2017-04-03 18:52 [PATCH 0/8 v4] No wait AIO Goldwyn Rodrigues
2017-04-03 18:53 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues
2017-04-04 6:49 ` Christoph Hellwig
2017-03-15 21:50 [PATCH 0/8 v3] No wait AIO Goldwyn Rodrigues
2017-03-15 21:51 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues
[not found] ` <20170315215107.5628-6-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-03-16 14:33 ` Jens Axboe
2017-03-17 2:03 ` Ming Lei
2017-03-17 12:23 ` Goldwyn Rodrigues
[not found] ` <eee4683d-9f44-434f-b97f-b0b24c7b3dab-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2017-03-24 11:32 ` Goldwyn Rodrigues
2017-03-24 14:39 ` Jens Axboe
2017-03-16 21:31 ` Dave Chinner
2017-03-17 12:23 ` Goldwyn Rodrigues
2017-03-20 17:33 ` Jan Kara
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=20170414120257.8932-6-rgoldwyn@suse.de \
--to=rgoldwyn@suse.de \
--cc=avi@scylladb.com \
--cc=axboe@kernel.dk \
--cc=hch@infradead.org \
--cc=jack@suse.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=sagi@grimberg.me \
--cc=tom.leiming@gmail.com \
--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
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;
as well as URLs for NNTP newsgroup(s).