The patch titled
Subject: block: return on congested block device
has been added to the -mm tree. Its filename is
block-return-on-congested-block-device.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/block-return-on-congested-block-device.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/block-return-on-congested-block-device.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
Subject: block: return on congested block device
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.
Stacked devices such as md (the ones with make_request_fn hooks) currently
are not supported because it may block for housekeeping. For example, an
md can have a part of the device suspended. For this reason, only request
based devices are supported. In the future, this feature will be expanded
to stacked devices by teaching them how to handle the REQ_NOWAIT flags.
Link: http://lkml.kernel.org/r/20170615160002.17233-8-rgoldwyn@xxxxxxx
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Jens Axboe <axboe@xxxxxxxxx>
Cc: "Theodore Ts'o" <tytso@xxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Andreas Dilger <adilger.kernel@xxxxxxxxx>
Cc: Chris Mason <clm@xxxxxx>
Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Cc: David Sterba <dsterba@xxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Josef Bacik <jbacik@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
block/blk-core.c | 23 +++++++++++++++++++++--
block/blk-mq-sched.c | 3 +++
block/blk-mq.c | 2 ++
fs/direct-io.c | 10 ++++++++--
include/linux/bio.h | 6 ++++++
include/linux/blk_types.h | 2 ++
6 files changed, 42 insertions(+), 4 deletions(-)
diff -puN block/blk-core.c~block-return-on-congested-block-device block/blk-core.c
--- a/block/blk-core.c~block-return-on-congested-block-device
+++ a/block/blk-core.c
@@ -1256,6 +1256,11 @@ retry:
if (!IS_ERR(rq))
return rq;
+ if (op & 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;
@@ -1900,6 +1905,16 @@ generic_make_request_checks(struct bio *
goto end_io;
}
+ /*
+ * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+ * if queue is not a request based queue.
+ */
+
+ if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q)) {
+ err = -EOPNOTSUPP;
+ 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,
@@ -2057,7 +2072,7 @@ blk_qc_t generic_make_request(struct 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 */
@@ -2082,7 +2097,11 @@ blk_qc_t generic_make_request(struct 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 -puN block/blk-mq-sched.c~block-return-on-congested-block-device block/blk-mq-sched.c
--- a/block/blk-mq-sched.c~block-return-on-congested-block-device
+++ a/block/blk-mq-sched.c
@@ -83,6 +83,9 @@ struct request *blk_mq_sched_get_request
if (likely(!data->hctx))
data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+ if (op & REQ_NOWAIT)
+ data->flags |= BLK_MQ_REQ_NOWAIT;
+
if (e) {
data->flags |= BLK_MQ_REQ_INTERNAL;
diff -puN block/blk-mq.c~block-return-on-congested-block-device block/blk-mq.c
--- a/block/blk-mq.c~block-return-on-congested-block-device
+++ a/block/blk-mq.c
@@ -1562,6 +1562,8 @@ static blk_qc_t blk_mq_make_request(stru
rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
+ if (bio->bi_opf & REQ_NOWAIT)
+ bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
diff -puN fs/direct-io.c~block-return-on-congested-block-device fs/direct-io.c
--- a/fs/direct-io.c~block-return-on-congested-block-device
+++ a/fs/direct-io.c
@@ -480,8 +480,12 @@ static int dio_bio_complete(struct dio *
unsigned i;
int err;
- if (bio->bi_error)
- dio->io_error = -EIO;
+ if (bio->bi_error) {
+ if (bio->bi_error == -EAGAIN && (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
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 -puN include/linux/bio.h~block-return-on-congested-block-device include/linux/bio.h
--- a/include/linux/bio.h~block-return-on-congested-block-device
+++ a/include/linux/bio.h
@@ -418,6 +418,12 @@ static inline void bio_io_error(struct b
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 -puN include/linux/blk_types.h~block-return-on-congested-block-device include/linux/blk_types.h
--- a/include/linux/blk_types.h~block-return-on-congested-block-device
+++ a/include/linux/blk_types.h
@@ -205,6 +205,7 @@ enum req_flag_bits {
/* command specific flags for REQ_OP_WRITE_ZEROES: */
__REQ_NOUNMAP, /* do not free blocks when zeroing */
+ __REQ_NOWAIT, /* Don't wait if request will block */
__REQ_NR_BITS, /* stops here */
};
@@ -223,6 +224,7 @@ enum req_flag_bits {
#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND)
#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP)
+#define REQ_NOWAIT (1ULL << __REQ_NOWAIT)
#define REQ_FAILFAST_MASK \
(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
_
Patches currently in -mm which might be from rgoldwyn@xxxxxxxx are
fs-separate-out-kiocb-flags-setup-based-on-rwf_-flags.patch
fs-introduce-filemap_range_has_page.patch
fs-use-rwf_-flags-for-aio-operations.patch
fs-introduce-rwf_nowait-and-fmode_aio_nowait.patch
fs-return-if-direct-write-will-trigger-writeback.patch
fs-introduce-iomap_nowait.patch
block-return-on-congested-block-device.patch
ext4-nowait-aio-support.patch
xfs-nowait-aio-support.patch
btrfs-nowait-aio-support.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
