Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:6 as permitted sender) client-ip=2620:137:e000::3:6;
From:   Kanchan Joshi <joshi.k@samsung.com>
To:     Jens Axboe <axboe@kernel.dk>, Jonathan Corbet <corbet@lwn.net>,
        Alasdair Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@kernel.org>,
        Mikulas Patocka <mpatocka@redhat.com>,
        dm-devel@lists.linux.dev, Keith Busch <kbusch@kernel.org>,
        Christoph Hellwig <hch@lst.de>,
        Sagi Grimberg <sagi@grimberg.me>,
        Chaitanya Kulkarni <kch@nvidia.com>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Christian Brauner <brauner@kernel.org>
Cc:     martin.petersen@oracle.com, linux-scsi@vger.kernel.org,
        nitheshshetty@gmail.com, anuj1072538@gmail.com,
        gost.dev@samsung.com, mcgrof@kernel.org,
        Nitesh Shetty <nj.shetty@samsung.com>,
        Hannes Reinecke <hare@suse.de>,
        Kanchan Joshi <joshi.k@samsung.com>,
        Anuj Gupta <anuj20.g@samsung.com>, linux-block@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH v18 01/12] block: Introduce queue limits and sysfs for
 copy-offload support
Date:   Wed,  6 Dec 2023 15:32:33 +0530
Message-Id: <20231206100253.13100-2-joshi.k@samsung.com>
In-Reply-To: <20231206100253.13100-1-joshi.k@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 105P
DLP-Filter: Pass
References: <20231206100253.13100-1-joshi.k@samsung.com>
        <CGME20231206101038epcas5p49984074d09421f0f60e231e33db8b9e7@epcas5p4.samsung.com>
Precedence: bulk

From: Nitesh Shetty <nj.shetty@samsung.com>

Add device limits as sysfs entries,
	- copy_max_bytes (RW)
	- copy_max_hw_bytes (RO)

Above limits help to split the copy payload in block layer.
copy_max_bytes: maximum total length of copy in single payload.
copy_max_hw_bytes: Reflects the device supported maximum limit.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
---
 Documentation/ABI/stable/sysfs-block | 23 ++++++++++++++++++
 block/blk-settings.c                 | 24 +++++++++++++++++++
 block/blk-sysfs.c                    | 36 ++++++++++++++++++++++++++++
 include/linux/blkdev.h               | 13 ++++++++++
 4 files changed, 96 insertions(+)

diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 1fe9a553c37b..96ba701e57da 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -155,6 +155,29 @@ Description:
 		last zone of the device which may be smaller.
 
 
+What:		/sys/block/<disk>/queue/copy_max_bytes
+Date:		August 2023
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RW] This is the maximum number of bytes that the block layer
+		will allow for a copy request. This is always smaller or
+		equal to the maximum size allowed by the hardware, indicated by
+		'copy_max_hw_bytes'. An attempt to set a value higher than
+		'copy_max_hw_bytes' will truncate this to 'copy_max_hw_bytes'.
+		Writing '0' to this file will disable offloading copies for this
+		device, instead copy is done via emulation.
+
+
+What:		/sys/block/<disk>/queue/copy_max_hw_bytes
+Date:		August 2023
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RO] This is the maximum number of bytes that the hardware
+		will allow for single data copy request.
+		A value of 0 means that the device does not support
+		copy offload.
+
+
 What:		/sys/block/<disk>/queue/crypto/
 Date:		February 2022
 Contact:	linux-block@vger.kernel.org
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..4441711ac364 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -59,6 +59,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->zoned = BLK_ZONED_NONE;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
+	lim->max_copy_hw_sectors = 0;
+	lim->max_copy_sectors = 0;
 }
 
 /**
@@ -82,6 +84,8 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_copy_hw_sectors = UINT_MAX;
+	lim->max_copy_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
@@ -183,6 +187,22 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
+/*
+ * blk_queue_max_copy_hw_sectors - set max sectors for a single copy payload
+ * @q:	the request queue for the device
+ * @max_copy_sectors: maximum number of sectors to copy
+ */
+void blk_queue_max_copy_hw_sectors(struct request_queue *q,
+				   unsigned int max_copy_sectors)
+{
+	if (max_copy_sectors > (BLK_COPY_MAX_BYTES >> SECTOR_SHIFT))
+		max_copy_sectors = BLK_COPY_MAX_BYTES >> SECTOR_SHIFT;
+
+	q->limits.max_copy_hw_sectors = max_copy_sectors;
+	q->limits.max_copy_sectors = max_copy_sectors;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_copy_hw_sectors);
+
 /**
  * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
  * @q:  the request queue for the device
@@ -578,6 +598,10 @@ 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_copy_sectors = min(t->max_copy_sectors, b->max_copy_sectors);
+	t->max_copy_hw_sectors = min(t->max_copy_hw_sectors,
+				     b->max_copy_hw_sectors);
+
 	t->misaligned |= b->misaligned;
 
 	alignment = queue_limit_alignment_offset(b, start);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0b2d04766324..7193a1f015f9 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -199,6 +199,37 @@ static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *pag
 	return queue_var_show(0, page);
 }
 
+static ssize_t queue_copy_hw_max_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)
+		       q->limits.max_copy_hw_sectors << SECTOR_SHIFT);
+}
+
+static ssize_t queue_copy_max_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)
+		       q->limits.max_copy_sectors << SECTOR_SHIFT);
+}
+
+static ssize_t queue_copy_max_store(struct request_queue *q, const char *page,
+				    size_t count)
+{
+	unsigned long max_copy;
+	ssize_t ret = queue_var_store(&max_copy, page, count);
+
+	if (ret < 0)
+		return ret;
+
+	if (max_copy & (queue_logical_block_size(q) - 1))
+		return -EINVAL;
+
+	max_copy >>= SECTOR_SHIFT;
+	q->limits.max_copy_sectors = min_t(unsigned int, max_copy,
+					   q->limits.max_copy_hw_sectors);
+
+	return count;
+}
+
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(0, page);
@@ -517,6 +548,9 @@ QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones");
 QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones");
 QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones");
 
+QUEUE_RO_ENTRY(queue_copy_hw_max, "copy_max_hw_bytes");
+QUEUE_RW_ENTRY(queue_copy_max, "copy_max_bytes");
+
 QUEUE_RW_ENTRY(queue_nomerges, "nomerges");
 QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity");
 QUEUE_RW_ENTRY(queue_poll, "io_poll");
@@ -634,6 +668,8 @@ static struct attribute *queue_attrs[] = {
 	&queue_discard_max_entry.attr,
 	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_copy_hw_max_entry.attr,
+	&queue_copy_max_entry.attr,
 	&queue_write_same_max_entry.attr,
 	&queue_write_zeroes_max_entry.attr,
 	&queue_zone_append_max_entry.attr,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3f8a21cd9233..4e17945041c8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -311,6 +311,9 @@ struct queue_limits {
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	unsigned int		max_copy_hw_sectors;
+	unsigned int		max_copy_sectors;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
@@ -893,6 +896,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_discard_segments(struct request_queue *,
 		unsigned short);
+extern void blk_queue_max_copy_hw_sectors(struct request_queue *q,
+					  unsigned int max_copy_sectors);
 void blk_queue_max_secure_erase_sectors(struct request_queue *q,
 		unsigned int max_sectors);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
@@ -1211,6 +1216,14 @@ static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
 	return bdev_get_queue(bdev)->limits.discard_granularity;
 }
 
+/* maximum copy offload length, this is set to 128MB based on current testing */
+#define BLK_COPY_MAX_BYTES		(1 << 27)
+
+static inline unsigned int bdev_max_copy_sectors(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.max_copy_sectors;
+}
+
 static inline unsigned int
 bdev_max_secure_erase_sectors(struct block_device *bdev)
 {
-- 
2.35.1.500.gb896f729e2