Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Nitesh Shetty <nj.shetty@samsung.com>
To:     axboe@kernel.dk, agk@redhat.com, snitzer@kernel.org,
        dm-devel@redhat.com, kbusch@kernel.org, hch@lst.de,
        sagi@grimberg.me, james.smart@broadcom.com, kch@nvidia.com,
        damien.lemoal@opensource.wdc.com, naohiro.aota@wdc.com,
        jth@kernel.org, viro@zeniv.linux.org.uk
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org,
        anuj20.g@samsung.com, joshi.k@samsung.com, p.raghav@samsung.com,
        nitheshshetty@gmail.com, gost.dev@samsung.com,
        Nitesh Shetty <nj.shetty@samsung.com>,
        Hannes Reinecke <hare@suse.de>
Subject: [PATCH v5 01/10] block: Introduce queue limits for copy-offload
 support
Date:   Wed, 23 Nov 2022 11:28:18 +0530
Message-Id: <20221123055827.26996-2-nj.shetty@samsung.com>
In-Reply-To: <20221123055827.26996-1-nj.shetty@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 105P
DLP-Filter: Pass
References: <20221123055827.26996-1-nj.shetty@samsung.com>
        <CGME20221123061014epcas5p150fd8add12fe6d09b63c56972818e6a2@epcas5p1.samsung.com>
Precedence: bulk

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

Above limits help to split the copy payload in block layer.
copy_offload: used for setting copy offload(1) or emulation(0).
copy_max_bytes: maximum total length of copy in single payload.
copy_max_bytes_hw: Reflects the device supported maximum limit.

Reviewed-by: Hannes Reinecke <hare@suse.de>
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 | 36 ++++++++++++++++
 block/blk-settings.c                 | 24 +++++++++++
 block/blk-sysfs.c                    | 64 ++++++++++++++++++++++++++++
 include/linux/blkdev.h               | 12 ++++++
 include/uapi/linux/fs.h              |  3 ++
 5 files changed, 139 insertions(+)

diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index cd14ecb3c9a5..e0c9be009706 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -155,6 +155,42 @@ Description:
 		last zone of the device which may be smaller.
 
 
+What:		/sys/block/<disk>/queue/copy_offload
+Date:		November 2022
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RW] When read, this file shows whether offloading copy to
+		device is enabled (1) or disabled (0). Writing '0' to this
+		file will disable offloading copies for this device.
+		Writing any '1' value will enable this feature. If device
+		does not support offloading, then writing 1, will result in
+		error.
+
+
+What:		/sys/block/<disk>/queue/copy_max_bytes
+Date:		November 2022
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RW] While 'copy_max_bytes_hw' is the hardware limit for the
+		device, 'copy_max_bytes' setting is the software limit.
+		Setting this value lower will make Linux issue smaller size
+		copies from block layer.
+
+
+What:		/sys/block/<disk>/queue/copy_max_bytes_hw
+Date:		November 2022
+Contact:	linux-block@vger.kernel.org
+Description:
+		[RO] Devices that support offloading copy functionality may have
+		internal limits on the number of bytes that can be offloaded
+		in a single operation. The `copy_max_bytes_hw`
+		parameter is set by the device driver to the maximum number of
+		bytes that can be copied in a single operation. Copy
+		requests issued to the device must not exceed this limit.
+		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 0477c4d527fe..ca6f15a70fdc 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -58,6 +58,8 @@ 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_sectors_hw = 0;
+	lim->max_copy_sectors = 0;
 }
 
 /**
@@ -81,6 +83,8 @@ 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_sectors_hw = ULONG_MAX;
+	lim->max_copy_sectors = ULONG_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
@@ -177,6 +181,22 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
+/**
+ * blk_queue_max_copy_sectors_hw - 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_sectors_hw(struct request_queue *q,
+		unsigned int max_copy_sectors)
+{
+	if (max_copy_sectors >= MAX_COPY_TOTAL_LENGTH)
+		max_copy_sectors = MAX_COPY_TOTAL_LENGTH;
+
+	q->limits.max_copy_sectors_hw = max_copy_sectors;
+	q->limits.max_copy_sectors = max_copy_sectors;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_copy_sectors_hw);
+
 /**
  * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
  * @q:  the request queue for the device
@@ -572,6 +592,10 @@ 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_sectors_hw = min(t->max_copy_sectors_hw,
+						b->max_copy_sectors_hw);
+
 	t->misaligned |= b->misaligned;
 
 	alignment = queue_limit_alignment_offset(b, start);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 02e94c4beff1..903285b04029 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -212,6 +212,63 @@ 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_offload_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_copy(q), page);
+}
+
+static ssize_t queue_copy_offload_store(struct request_queue *q,
+				       const char *page, size_t count)
+{
+	s64 copy_offload;
+	ssize_t ret = queue_var_store64(&copy_offload, page);
+
+	if (ret < 0)
+		return ret;
+
+	if (copy_offload && !q->limits.max_copy_sectors_hw)
+		return -EINVAL;
+
+	if (copy_offload)
+		blk_queue_flag_set(QUEUE_FLAG_COPY, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_COPY, q);
+
+	return count;
+}
+
+static ssize_t queue_copy_max_hw_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)
+			q->limits.max_copy_sectors_hw << 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)
+{
+	s64 max_copy;
+	ssize_t ret = queue_var_store64(&max_copy, page);
+
+	if (ret < 0)
+		return ret;
+
+	if (max_copy & (queue_logical_block_size(q) - 1))
+		return -EINVAL;
+
+	max_copy >>= SECTOR_SHIFT;
+	if (max_copy > q->limits.max_copy_sectors_hw)
+		max_copy = q->limits.max_copy_sectors_hw;
+
+	q->limits.max_copy_sectors = max_copy;
+	return count;
+}
+
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(0, page);
@@ -604,6 +661,10 @@ 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_RW_ENTRY(queue_copy_offload, "copy_offload");
+QUEUE_RO_ENTRY(queue_copy_max_hw, "copy_max_bytes_hw");
+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");
@@ -651,6 +712,9 @@ static struct attribute *queue_attrs[] = {
 	&queue_discard_max_entry.attr,
 	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_copy_offload_entry.attr,
+	&queue_copy_max_hw_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 a0452ba08e9a..3ac324208f2f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -302,6 +302,9 @@ struct queue_limits {
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	unsigned long		max_copy_sectors_hw;
+	unsigned long		max_copy_sectors;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
@@ -573,6 +576,7 @@ struct request_queue {
 #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_COPY		32	/* supports copy offload */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
 				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
@@ -593,6 +597,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
+#define blk_queue_copy(q)	test_bit(QUEUE_FLAG_COPY, &(q)->queue_flags)
 #define blk_queue_zone_resetall(q)	\
 	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
 #define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
@@ -913,6 +918,8 @@ 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_sectors_hw(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);
@@ -1231,6 +1238,11 @@ static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
 	return bdev_get_queue(bdev)->limits.discard_granularity;
 }
 
+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)
 {
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index b7b56871029c..b3ad173f619c 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -64,6 +64,9 @@ struct fstrim_range {
 	__u64 minlen;
 };
 
+/* maximum total copy length */
+#define MAX_COPY_TOTAL_LENGTH	(1 << 27)
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
-- 
2.35.1.500.gb896f729e2