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>
Cc:     javier@javigon.com, chaitanyak@nvidia.com,
        linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
        dm-devel@redhat.com, linux-nvme@lists.infradead.org,
        linux-fsdevel@vger.kernel.org, axboe@kernel.dk,
        msnitzer@redhat.com, bvanassche@acm.org,
        martin.petersen@oracle.com, hare@suse.de, kbusch@kernel.org,
        hch@lst.de, Frederick.Knight@netapp.com, osandov@fb.com,
        lsf-pc@lists.linux-foundation.org, djwong@kernel.org,
        josef@toxicpanda.com, clm@fb.com, dsterba@suse.com, tytso@mit.edu,
        jack@suse.com, joshi.k@samsung.com, arnav.dawn@samsung.com,
        nitheshshetty@gmail.com, Nitesh Shetty <nj.shetty@samsung.com>,
        SelvaKumar S <selvakuma.s1@samsung.com>,
        Alasdair Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@redhat.com>,
        Sagi Grimberg <sagi@grimberg.me>,
        James Smart <james.smart@broadcom.com>,
        Chaitanya Kulkarni <kch@nvidia.com>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        linux-kernel@vger.kernel.org
Subject: [PATCH v3 02/10] block: Introduce queue limits for copy-offload
 support
Date:   Mon, 14 Feb 2022 13:29:52 +0530
Message-Id: <20220214080002.18381-3-nj.shetty@samsung.com>
In-Reply-To: <20220214080002.18381-1-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: <20220214080002.18381-1-nj.shetty@samsung.com>
        <CGME20220214080605epcas5p16868dae515a6355cf9fecf22df4f3c3d@epcas5p1.samsung.com>
To:     unlisted-recipients:; (no To-header on input)
Precedence: bulk

Add device limits as sysfs entries,
        - copy_offload (RW)
        - copy_max_bytes (RW)
        - copy_max_hw_bytes (RO)
        - copy_max_range_bytes (RW)
        - copy_max_range_hw_bytes (RO)
        - copy_max_nr_ranges (RW)
        - copy_max_nr_ranges_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_range_bytes: maximum length in a single entry.
copy_max_nr_ranges: maximum number of entries in a payload.
copy_max_*_hw_*: Reflects the device supported maximum limits.

Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: SelvaKumar S <selvakuma.s1@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
---
 block/blk-settings.c   |  59 ++++++++++++++++++
 block/blk-sysfs.c      | 138 +++++++++++++++++++++++++++++++++++++++++
 include/linux/blkdev.h |  13 ++++
 3 files changed, 210 insertions(+)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index b880c70e22e4..4baccc93a294 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -57,6 +57,12 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->misaligned = 0;
 	lim->zoned = BLK_ZONED_NONE;
 	lim->zone_write_granularity = 0;
+	lim->max_hw_copy_sectors = 0;
+	lim->max_copy_sectors = 0;
+	lim->max_hw_copy_nr_ranges = 0;
+	lim->max_copy_nr_ranges = 0;
+	lim->max_hw_copy_range_sectors = 0;
+	lim->max_copy_range_sectors = 0;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -82,6 +88,12 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_write_same_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_hw_copy_sectors = ULONG_MAX;
+	lim->max_copy_sectors = ULONG_MAX;
+	lim->max_hw_copy_range_sectors = UINT_MAX;
+	lim->max_copy_range_sectors = UINT_MAX;
+	lim->max_hw_copy_nr_ranges = USHRT_MAX;
+	lim->max_copy_nr_ranges = USHRT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
@@ -178,6 +190,45 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
+/**
+ * blk_queue_max_copy_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_sectors(struct request_queue *q,
+		unsigned int max_copy_sectors)
+{
+	q->limits.max_hw_copy_sectors = max_copy_sectors;
+	q->limits.max_copy_sectors = max_copy_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_copy_sectors);
+
+/**
+ * blk_queue_max_copy_range_sectors - set max sectors for a single range, in a copy payload
+ * @q:  the request queue for the device
+ * @max_copy_range_sectors: maximum number of sectors to copy in a single range
+ **/
+void blk_queue_max_copy_range_sectors(struct request_queue *q,
+		unsigned int max_copy_range_sectors)
+{
+	q->limits.max_hw_copy_range_sectors = max_copy_range_sectors;
+	q->limits.max_copy_range_sectors = max_copy_range_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_copy_range_sectors);
+
+/**
+ * blk_queue_max_copy_nr_ranges - set max number of ranges, in a copy payload
+ * @q:  the request queue for the device
+ * @max_copy_nr_ranges: maximum number of ranges
+ **/
+void blk_queue_max_copy_nr_ranges(struct request_queue *q,
+		unsigned int max_copy_nr_ranges)
+{
+	q->limits.max_hw_copy_nr_ranges = max_copy_nr_ranges;
+	q->limits.max_copy_nr_ranges = max_copy_nr_ranges;
+}
+EXPORT_SYMBOL(blk_queue_max_copy_nr_ranges);
+
 /**
  * blk_queue_max_write_same_sectors - set max sectors for a single write same
  * @q:  the request queue for the device
@@ -541,6 +592,14 @@ 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_hw_copy_sectors = min(t->max_hw_copy_sectors, b->max_hw_copy_sectors);
+	t->max_copy_range_sectors = min(t->max_copy_range_sectors, b->max_copy_range_sectors);
+	t->max_hw_copy_range_sectors = min(t->max_hw_copy_range_sectors,
+						b->max_hw_copy_range_sectors);
+	t->max_copy_nr_ranges = min(t->max_copy_nr_ranges, b->max_copy_nr_ranges);
+	t->max_hw_copy_nr_ranges = min(t->max_hw_copy_nr_ranges, b->max_hw_copy_nr_ranges);
+
 	t->misaligned |= b->misaligned;
 
 	alignment = queue_limit_alignment_offset(b, start);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9f32882ceb2f..9ddd07f142d9 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -212,6 +212,129 @@ 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)
+{
+	unsigned long copy_offload;
+	ssize_t ret = queue_var_store(&copy_offload, page, count);
+
+	if (ret < 0)
+		return ret;
+
+	if (copy_offload && !q->limits.max_hw_copy_sectors)
+		return -EINVAL;
+
+	if (copy_offload)
+		blk_queue_flag_set(QUEUE_FLAG_COPY, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_COPY, q);
+
+	return ret;
+}
+
+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_hw_copy_sectors << 9);
+}
+
+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 << 9);
+}
+
+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 >>= 9;
+	if (max_copy > q->limits.max_hw_copy_sectors)
+		max_copy = q->limits.max_hw_copy_sectors;
+
+	q->limits.max_copy_sectors = max_copy;
+	return ret;
+}
+
+static ssize_t queue_copy_range_max_hw_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_copy_range_sectors << 9);
+}
+
+static ssize_t queue_copy_range_max_show(struct request_queue *q,
+		char *page)
+{
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_copy_range_sectors << 9);
+}
+
+static ssize_t queue_copy_range_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 >>= 9;
+	if (max_copy > UINT_MAX)
+		return -EINVAL;
+
+	if (max_copy > q->limits.max_hw_copy_range_sectors)
+		max_copy = q->limits.max_hw_copy_range_sectors;
+
+	q->limits.max_copy_range_sectors = max_copy;
+	return ret;
+}
+
+static ssize_t queue_copy_nr_ranges_max_hw_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.max_hw_copy_nr_ranges, page);
+}
+
+static ssize_t queue_copy_nr_ranges_max_show(struct request_queue *q,
+		char *page)
+{
+	return queue_var_show(q->limits.max_copy_nr_ranges, page);
+}
+
+static ssize_t queue_copy_nr_ranges_max_store(struct request_queue *q,
+				       const char *page, size_t count)
+{
+	unsigned long max_nr;
+	ssize_t ret = queue_var_store(&max_nr, page, count);
+
+	if (ret < 0)
+		return ret;
+
+	if (max_nr > USHRT_MAX)
+		return -EINVAL;
+
+	if (max_nr > q->limits.max_hw_copy_nr_ranges)
+		max_nr = q->limits.max_hw_copy_nr_ranges;
+
+	q->limits.max_copy_nr_ranges = max_nr;
+	return ret;
+}
+
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
 {
 	return sprintf(page, "%llu\n",
@@ -597,6 +720,14 @@ 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_hw_bytes");
+QUEUE_RW_ENTRY(queue_copy_max, "copy_max_bytes");
+QUEUE_RO_ENTRY(queue_copy_range_max_hw, "copy_max_range_hw_bytes");
+QUEUE_RW_ENTRY(queue_copy_range_max, "copy_max_range_bytes");
+QUEUE_RO_ENTRY(queue_copy_nr_ranges_max_hw, "copy_max_nr_ranges_hw");
+QUEUE_RW_ENTRY(queue_copy_nr_ranges_max, "copy_max_nr_ranges");
+
 QUEUE_RW_ENTRY(queue_nomerges, "nomerges");
 QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity");
 QUEUE_RW_ENTRY(queue_poll, "io_poll");
@@ -643,6 +774,13 @@ 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_copy_range_max_hw_entry.attr,
+	&queue_copy_range_max_entry.attr,
+	&queue_copy_nr_ranges_max_hw_entry.attr,
+	&queue_copy_nr_ranges_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 efed3820cbf7..792e6d556589 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -254,6 +254,13 @@ struct queue_limits {
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	unsigned long		max_hw_copy_sectors;
+	unsigned long		max_copy_sectors;
+	unsigned int		max_hw_copy_range_sectors;
+	unsigned int		max_copy_range_sectors;
+	unsigned short		max_hw_copy_nr_ranges;
+	unsigned short		max_copy_nr_ranges;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
@@ -562,6 +569,7 @@ struct request_queue {
 #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_COPY		30	/* supports copy offload */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\
@@ -585,6 +593,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #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_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(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_secure_erase(q) \
@@ -958,6 +967,10 @@ extern void blk_queue_max_discard_segments(struct request_queue *,
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
+extern void blk_queue_max_copy_sectors(struct request_queue *q, unsigned int max_copy_sectors);
+extern void blk_queue_max_copy_range_sectors(struct request_queue *q,
+		unsigned int max_copy_range_sectors);
+extern void blk_queue_max_copy_nr_ranges(struct request_queue *q, unsigned int max_copy_nr_ranges);
 extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
 extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
-- 
2.30.0-rc0