From: Christoph Hellwig <hch@lst.de>
To: Jens Axboe <axboe@kernel.dk>
Cc: nvdimm@lists.linux.dev, "Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
linux-nvme@lists.infradead.org, "Song Liu" <song@kernel.org>,
linux-mtd@lists.infradead.org,
"Vineeth Vijayan" <vneethv@linux.ibm.com>,
"Alasdair Kergon" <agk@redhat.com>,
drbd-dev@lists.linbit.com, linux-s390@vger.kernel.org,
linux-scsi@vger.kernel.org, "Richard Weinberger" <richard@nod.at>,
"Geert Uytterhoeven" <geert@linux-m68k.org>,
"Yu Kuai" <yukuai3@huawei.com>,
dm-devel@lists.linux.dev, linux-um@lists.infradead.org,
"Mike Snitzer" <snitzer@kernel.org>,
"Josef Bacik" <josef@toxicpanda.com>,
nbd@other.debian.org, linux-raid@vger.kernel.org,
linux-m68k@lists.linux-m68k.org,
"Mikulas Patocka" <mpatocka@redhat.com>,
xen-devel@lists.xenproject.org, ceph-devel@vger.kernel.org,
"Ming Lei" <ming.lei@redhat.com>,
linux-bcache@vger.kernel.org, linux-block@vger.kernel.org,
"Martin K. Petersen" <martin.petersen@oracle.com>,
linux-mmc@vger.kernel.org,
"Philipp Reisner" <philipp.reisner@linbit.com>,
"Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>,
virtualization@lists.linux.dev,
"Lars Ellenberg" <lars.ellenberg@linbit.com>,
linuxppc-dev@lists.ozlabs.org,
"Roger Pau Monné" <roger.pau@citrix.com>
Subject: [PATCH 19/26] block: move the nowait flag to queue_limits
Date: Mon, 17 Jun 2024 08:04:46 +0200 [thread overview]
Message-ID: <20240617060532.127975-20-hch@lst.de> (raw)
In-Reply-To: <20240617060532.127975-1-hch@lst.de>
Move the nowait flag into the queue_limits feature field so that it can
be set atomically with the queue frozen.
Stacking drivers are simplified in that they now can simply set the
flag, and blk_stack_limits will clear it when the features is not
supported by any of the underlying devices.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-mq-debugfs.c | 1 -
block/blk-mq.c | 2 +-
block/blk-settings.c | 9 +++++++++
drivers/block/brd.c | 4 ++--
drivers/md/dm-table.c | 18 +++---------------
drivers/md/md.c | 18 +-----------------
drivers/nvme/host/multipath.c | 3 +--
include/linux/blkdev.h | 9 +++++----
8 files changed, 22 insertions(+), 42 deletions(-)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 957774e40b1d0c..62b132e9a9ce3b 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -96,7 +96,6 @@ static const char *const blk_queue_flag_name[] = {
QUEUE_FLAG_NAME(ZONE_RESETALL),
QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
QUEUE_FLAG_NAME(HCTX_ACTIVE),
- QUEUE_FLAG_NAME(NOWAIT),
QUEUE_FLAG_NAME(SQ_SCHED),
QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE),
};
diff --git a/block/blk-mq.c b/block/blk-mq.c
index cf67dc13f7dd4c..43235acc87505f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4118,7 +4118,7 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
if (!lim)
lim = &default_lim;
- lim->features |= BLK_FEAT_IO_STAT;
+ lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
q = blk_alloc_queue(lim, set->numa_node);
if (IS_ERR(q))
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 536ee202fcdccb..bf4622c19b5c09 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -459,6 +459,15 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->features |= (b->features & BLK_FEAT_INHERIT_MASK);
+ /*
+ * BLK_FEAT_NOWAIT needs to be supported both by the stacking driver
+ * and all underlying devices. The stacking driver sets the flag
+ * before stacking the limits, and this will clear the flag if any
+ * of the underlying devices does not support it.
+ */
+ if (!(b->features & BLK_FEAT_NOWAIT))
+ t->features &= ~BLK_FEAT_NOWAIT;
+
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_user_sectors = min_not_zero(t->max_user_sectors,
b->max_user_sectors);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index d77deb571dbd06..a300645cd9d4a5 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -335,7 +335,8 @@ static int brd_alloc(int i)
.max_hw_discard_sectors = UINT_MAX,
.max_discard_segments = 1,
.discard_granularity = PAGE_SIZE,
- .features = BLK_FEAT_SYNCHRONOUS,
+ .features = BLK_FEAT_SYNCHRONOUS |
+ BLK_FEAT_NOWAIT,
};
list_for_each_entry(brd, &brd_devices, brd_list)
@@ -367,7 +368,6 @@ static int brd_alloc(int i)
strscpy(disk->disk_name, buf, DISK_NAME_LEN);
set_capacity(disk, rd_size * 2);
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue);
err = add_disk(disk);
if (err)
goto out_cleanup_disk;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index aaf379cb15d91f..84d636712c7284 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -582,7 +582,7 @@ int dm_split_args(int *argc, char ***argvp, char *input)
static void dm_set_stacking_limits(struct queue_limits *limits)
{
blk_set_stacking_limits(limits);
- limits->features |= BLK_FEAT_IO_STAT;
+ limits->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
}
/*
@@ -1746,12 +1746,6 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
return true;
}
-static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- return !bdev_nowait(dev->bdev);
-}
-
static bool dm_table_supports_nowait(struct dm_table *t)
{
for (unsigned int i = 0; i < t->num_targets; i++) {
@@ -1759,10 +1753,6 @@ static bool dm_table_supports_nowait(struct dm_table *t)
if (!dm_target_supports_nowait(ti->type))
return false;
-
- if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
- return false;
}
return true;
@@ -1824,10 +1814,8 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
{
int r;
- if (dm_table_supports_nowait(t))
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+ if (!dm_table_supports_nowait(t))
+ limits->features &= ~BLK_FEAT_NOWAIT;
if (!dm_table_supports_discards(t)) {
limits->max_hw_discard_sectors = 0;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8db0db8d5a27ac..f1c7d4f281c521 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5788,7 +5788,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
int error;
struct queue_limits lim = {
.features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
- BLK_FEAT_IO_STAT,
+ BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT,
};
/*
@@ -6150,13 +6150,6 @@ int md_run(struct mddev *mddev)
}
}
- if (!mddev_is_dm(mddev)) {
- struct request_queue *q = mddev->gendisk->queue;
-
- /* Set the NOWAIT flags if all underlying devices support it */
- if (nowait)
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
- }
if (pers->sync_request) {
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_redundancy_group))
@@ -7115,15 +7108,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
if (!mddev->thread)
md_update_sb(mddev, 1);
- /*
- * If the new disk does not support REQ_NOWAIT,
- * disable on the whole MD.
- */
- if (!bdev_nowait(rdev->bdev)) {
- pr_info("%s: Disabling nowait because %pg does not support nowait\n",
- mdname(mddev), rdev->bdev);
- blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
- }
/*
* Kick recovery, maybe this spare has to be added to the
* array immediately.
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 173796f2ddea9f..61a162c9cf4e6c 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -538,7 +538,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
blk_set_stacking_limits(&lim);
lim.dma_alignment = 3;
- lim.features |= BLK_FEAT_IO_STAT;
+ lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
if (head->ids.csi != NVME_CSI_ZNS)
lim.max_zone_append_sectors = 0;
@@ -550,7 +550,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
sprintf(head->disk->disk_name, "nvme%dn%d",
ctrl->subsys->instance, head->instance);
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
/*
* This assumes all controllers that refer to a namespace either
* support poll queues or not. That is not a strict guarantee,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cee7b44a142513..f3d4519d609d95 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -304,6 +304,9 @@ enum {
/* always completes in submit context */
BLK_FEAT_SYNCHRONOUS = (1u << 6),
+
+ /* supports REQ_NOWAIT */
+ BLK_FEAT_NOWAIT = (1u << 7),
};
/*
@@ -580,12 +583,10 @@ struct request_queue {
#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */
#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */
-#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */
#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */
#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE 31 /* quiesce_tagset skip the queue*/
-#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_SAME_COMP) | \
- (1UL << QUEUE_FLAG_NOWAIT))
+#define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP)
void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -1348,7 +1349,7 @@ static inline bool bdev_fua(struct block_device *bdev)
static inline bool bdev_nowait(struct block_device *bdev)
{
- return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+ return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT;
}
static inline bool bdev_is_zoned(struct block_device *bdev)
--
2.43.0
next prev parent reply other threads:[~2024-06-17 6:20 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-17 6:04 move features flags into queue_limits v2 Christoph Hellwig
2024-06-17 6:04 ` [PATCH 01/26] xen-blkfront: don't disable cache flushes when they fail Christoph Hellwig
2024-06-17 7:55 ` Roger Pau Monné
2024-06-17 10:03 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 02/26] sd: remove sd_is_zoned Christoph Hellwig
2024-06-18 1:39 ` Chaitanya Kulkarni
2024-06-17 6:04 ` [PATCH 03/26] sd: move zone limits setup out of sd_read_block_characteristics Christoph Hellwig
2024-06-17 6:12 ` Damien Le Moal
2024-06-17 10:04 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 04/26] loop: stop using loop_reconfigure_limits in __loop_clr_fd Christoph Hellwig
2024-06-17 6:04 ` [PATCH 05/26] loop: always update discard settings in loop_reconfigure_limits Christoph Hellwig
2024-06-17 6:04 ` [PATCH 06/26] loop: regularize upgrading the block size for direct I/O Christoph Hellwig
2024-06-17 6:13 ` Damien Le Moal
2024-06-17 6:04 ` [PATCH 07/26] loop: also use the default block size from an underlying block device Christoph Hellwig
2024-06-17 6:14 ` Damien Le Moal
2024-06-17 6:04 ` [PATCH 08/26] loop: fold loop_update_rotational into loop_reconfigure_limits Christoph Hellwig
2024-06-17 6:04 ` [PATCH 09/26] virtio_blk: remove virtblk_update_cache_mode Christoph Hellwig
2024-06-18 1:39 ` Chaitanya Kulkarni
2024-06-17 6:04 ` [PATCH 10/26] nbd: move setting the cache control flags to __nbd_set_size Christoph Hellwig
2024-06-17 6:04 ` [PATCH 11/26] block: freeze the queue in queue_attr_store Christoph Hellwig
2024-06-18 1:41 ` Chaitanya Kulkarni
2024-06-17 6:04 ` [PATCH 12/26] block: remove blk_flush_policy Christoph Hellwig
2024-06-18 1:42 ` Chaitanya Kulkarni
2024-06-17 6:04 ` [PATCH 13/26] block: move cache control settings out of queue->flags Christoph Hellwig
2024-06-17 6:23 ` Damien Le Moal
2024-06-17 10:36 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 14/26] block: move the nonrot flag to queue_limits Christoph Hellwig
2024-06-17 10:36 ` Hannes Reinecke
2024-06-24 17:08 ` Keith Busch
2024-06-24 17:24 ` Christoph Hellwig
2024-07-04 11:11 ` Simon Fernandez
2024-07-25 11:35 ` Wouter Verhelst
2024-07-25 13:00 ` Christoph Hellwig
2024-06-17 6:04 ` [PATCH 15/26] block: move the add_random " Christoph Hellwig
2024-06-17 10:38 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 16/26] block: move the io_stat flag setting " Christoph Hellwig
2024-06-17 6:25 ` Damien Le Moal
2024-06-17 10:38 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 17/26] block: move the stable_writes flag " Christoph Hellwig
2024-06-17 10:40 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 18/26] block: move the synchronous " Christoph Hellwig
2024-06-17 10:40 ` Hannes Reinecke
2024-06-17 6:04 ` Christoph Hellwig [this message]
2024-06-17 6:26 ` [PATCH 19/26] block: move the nowait " Damien Le Moal
2024-06-17 10:41 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 20/26] block: move the dax " Christoph Hellwig
2024-06-17 10:42 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 21/26] block: move the poll " Christoph Hellwig
2024-06-17 10:42 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 22/26] block: move the zoned flag into the features field Christoph Hellwig
2024-06-17 10:43 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 23/26] block: move the zone_resetall flag to queue_limits Christoph Hellwig
2024-06-17 10:43 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 24/26] block: move the pci_p2pdma " Christoph Hellwig
2024-06-17 10:44 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 25/26] block: move the skip_tagset_quiesce " Christoph Hellwig
2024-06-17 10:45 ` Hannes Reinecke
2024-06-17 6:04 ` [PATCH 26/26] block: move the bounce flag into the features field Christoph Hellwig
2024-06-17 10:45 ` Hannes Reinecke
2024-06-17 14:35 ` Keith Busch
2024-06-19 14:18 ` move features flags into queue_limits v2 Jens Axboe
2024-06-19 14:21 ` Jens Axboe
2024-06-19 14:23 ` Christoph Hellwig
-- strict thread matches above, loose matches on Subject: below --
2024-06-11 5:19 move features flags into queue_limits Christoph Hellwig
2024-06-11 5:19 ` [PATCH 19/26] block: move the nowait flag to queue_limits Christoph Hellwig
2024-06-11 8:16 ` Damien Le Moal
2024-06-12 5:01 ` Christoph Hellwig
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=20240617060532.127975-20-hch@lst.de \
--to=hch@lst.de \
--cc=agk@redhat.com \
--cc=axboe@kernel.dk \
--cc=ceph-devel@vger.kernel.org \
--cc=christoph.boehmwalder@linbit.com \
--cc=dm-devel@lists.linux.dev \
--cc=drbd-dev@lists.linbit.com \
--cc=geert@linux-m68k.org \
--cc=jasowang@redhat.com \
--cc=josef@toxicpanda.com \
--cc=lars.ellenberg@linbit.com \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-m68k@lists.linux-m68k.org \
--cc=linux-mmc@vger.kernel.org \
--cc=linux-mtd@lists.infradead.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linux-um@lists.infradead.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=mpatocka@redhat.com \
--cc=mst@redhat.com \
--cc=nbd@other.debian.org \
--cc=nvdimm@lists.linux.dev \
--cc=philipp.reisner@linbit.com \
--cc=richard@nod.at \
--cc=roger.pau@citrix.com \
--cc=snitzer@kernel.org \
--cc=song@kernel.org \
--cc=virtualization@lists.linux.dev \
--cc=vneethv@linux.ibm.com \
--cc=xen-devel@lists.xenproject.org \
--cc=yukuai3@huawei.com \
/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).