From: Keith Busch <kbusch@meta.com>
To: <linux-block@vger.kernel.org>, <linux-nvme@lists.infradead.org>,
<axboe@kernel.dk>, <hch@lst.de>, <io-uring@vger.kernel.org>
Cc: <linux-fsdevel@vger.kernel.org>, <joshi.k@samsung.com>,
<javier.gonz@samsung.com>, Keith Busch <kbusch@kernel.org>
Subject: [PATCHv8 3/6] block: introduce max_write_hints queue limit
Date: Thu, 17 Oct 2024 09:09:34 -0700 [thread overview]
Message-ID: <20241017160937.2283225-4-kbusch@meta.com> (raw)
In-Reply-To: <20241017160937.2283225-1-kbusch@meta.com>
From: Keith Busch <kbusch@kernel.org>
Drivers with hardware that support write hints need a way to export how
many are available so applications can generically query this.
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
Documentation/ABI/stable/sysfs-block | 7 +++++++
block/blk-settings.c | 3 +++
block/blk-sysfs.c | 3 +++
block/fops.c | 2 ++
include/linux/blkdev.h | 12 ++++++++++++
5 files changed, 27 insertions(+)
diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 8353611107154..f2db2cabb8e75 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -506,6 +506,13 @@ Description:
[RO] Maximum size in bytes of a single element in a DMA
scatter/gather list.
+What: /sys/block/<disk>/queue/max_write_hints
+Date: October 2024
+Contact: linux-block@vger.kernel.org
+Description:
+ [RO] Maximum number of write hints supported, 0 if not
+ supported. If supported, valid values are 1 through
+ max_write_hints, inclusive.
What: /sys/block/<disk>/queue/max_segments
Date: March 2010
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a446654ddee5e..921fb4d334fa4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -43,6 +43,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
/* Inherit limits from component devices */
+ lim->max_write_hints = USHRT_MAX;
lim->max_segments = USHRT_MAX;
lim->max_discard_segments = USHRT_MAX;
lim->max_hw_sectors = UINT_MAX;
@@ -544,6 +545,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->max_segment_size = min_not_zero(t->max_segment_size,
b->max_segment_size);
+ t->max_write_hints = min(t->max_write_hints, b->max_write_hints);
+
alignment = queue_limit_alignment_offset(b, start);
/* Bottom device has different alignment. Check that it is
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 741b95dfdbf6f..85f48ca461049 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -104,6 +104,7 @@ QUEUE_SYSFS_LIMIT_SHOW(max_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_segment_size)
+QUEUE_SYSFS_LIMIT_SHOW(max_write_hints)
QUEUE_SYSFS_LIMIT_SHOW(logical_block_size)
QUEUE_SYSFS_LIMIT_SHOW(physical_block_size)
QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors)
@@ -457,6 +458,7 @@ QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb");
QUEUE_RO_ENTRY(queue_max_segments, "max_segments");
QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments");
QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size");
+QUEUE_RO_ENTRY(queue_max_write_hints, "max_write_hints");
QUEUE_RW_LOAD_MODULE_ENTRY(elv_iosched, "scheduler");
QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size");
@@ -591,6 +593,7 @@ static struct attribute *queue_attrs[] = {
&queue_max_discard_segments_entry.attr,
&queue_max_integrity_segments_entry.attr,
&queue_max_segment_size_entry.attr,
+ &queue_max_write_hints_entry.attr,
&queue_hw_sector_size_entry.attr,
&queue_logical_block_size_entry.attr,
&queue_physical_block_size_entry.attr,
diff --git a/block/fops.c b/block/fops.c
index 85b9b97d372c8..d0b16d3975fd6 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -376,6 +376,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (blkdev_dio_invalid(bdev, iocb->ki_pos, iter, is_atomic))
return -EINVAL;
+ if (iocb->ki_write_hint > bdev_max_write_hints(bdev))
+ return -EINVAL;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
if (likely(nr_pages <= BIO_MAX_VECS)) {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6b78a68e0bd9c..01aba0ffeff6e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -393,6 +393,8 @@ struct queue_limits {
unsigned short max_integrity_segments;
unsigned short max_discard_segments;
+ unsigned short max_write_hints;
+
unsigned int max_open_zones;
unsigned int max_active_zones;
@@ -1183,6 +1185,11 @@ static inline unsigned short queue_max_segments(const struct request_queue *q)
return q->limits.max_segments;
}
+static inline unsigned short queue_max_write_hints(struct request_queue *q)
+{
+ return q->limits.max_write_hints;
+}
+
static inline unsigned short queue_max_discard_segments(const struct request_queue *q)
{
return q->limits.max_discard_segments;
@@ -1230,6 +1237,11 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev)
return queue_max_segments(bdev_get_queue(bdev));
}
+static inline unsigned short bdev_max_write_hints(struct block_device *bdev)
+{
+ return queue_max_write_hints(bdev_get_queue(bdev));
+}
+
static inline unsigned queue_logical_block_size(const struct request_queue *q)
{
return q->limits.logical_block_size;
--
2.43.5
next prev parent reply other threads:[~2024-10-17 16:11 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-17 16:09 [PATCHv8 0/6] write hints for nvme fdp Keith Busch
2024-10-17 16:09 ` [PATCHv8 1/6] block, fs: restore kiocb based write hint processing Keith Busch
2024-10-18 5:50 ` Christoph Hellwig
2024-10-21 15:47 ` Keith Busch
2024-10-21 17:09 ` Bart Van Assche
2024-10-21 19:35 ` Keith Busch
2024-10-22 6:43 ` Christoph Hellwig
2024-10-22 14:37 ` Keith Busch
2024-10-22 14:40 ` Christoph Hellwig
2024-10-18 16:11 ` Bart Van Assche
2024-10-17 16:09 ` [PATCHv8 2/6] block: use generic u16 for write hints Keith Busch
2024-10-18 5:46 ` Christoph Hellwig
2024-10-24 19:45 ` Keith Busch
2024-10-25 12:20 ` Christoph Hellwig
2024-10-18 6:00 ` Hannes Reinecke
2024-10-18 16:12 ` Bart Van Assche
2024-10-21 15:03 ` Keith Busch
2024-10-17 16:09 ` Keith Busch [this message]
2024-10-18 5:51 ` [PATCHv8 3/6] block: introduce max_write_hints queue limit Christoph Hellwig
2024-10-18 6:01 ` Hannes Reinecke
2024-10-18 16:18 ` Bart Van Assche
2024-10-21 15:02 ` Keith Busch
2024-10-17 16:09 ` [PATCHv8 4/6] fs: introduce per-io hint support flag Keith Busch
2024-10-18 5:52 ` Christoph Hellwig
2024-10-18 6:03 ` Hannes Reinecke
2024-10-17 16:09 ` [PATCHv8 5/6] io_uring: enable per-io hinting capability Keith Busch
2024-10-18 5:53 ` Christoph Hellwig
2024-10-18 6:03 ` Hannes Reinecke
2024-10-17 16:09 ` [PATCHv8 6/6] nvme: enable FDP support Keith Busch
2024-10-18 10:48 ` Kanchan Joshi
2024-10-21 15:08 ` Keith Busch
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=20241017160937.2283225-4-kbusch@meta.com \
--to=kbusch@meta.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=io-uring@vger.kernel.org \
--cc=javier.gonz@samsung.com \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nvme@lists.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