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:     Jens Axboe <axboe@kernel.dk>, Jonathan Corbet <corbet@lwn.net>,
        Alasdair Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@kernel.org>, dm-devel@redhat.com,
        Keith Busch <kbusch@kernel.org>,
        Christoph Hellwig <hch@lst.de>,
        Sagi Grimberg <sagi@grimberg.me>,
        James Smart <james.smart@broadcom.com>,
        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,
        willy@infradead.org, hare@suse.de, djwong@kernel.org,
        bvanassche@acm.org, ming.lei@redhat.com, dlemoal@kernel.org,
        nitheshshetty@gmail.com, gost.dev@samsung.com,
        Nitesh Shetty <nj.shetty@samsung.com>,
        Damien Le Moal <damien.lemoal@opensource.wdc.com>,
        Anuj Gupta <anuj20.g@samsung.com>,
        Vincent Fu <vincent.fu@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 v12 9/9] null_blk: add support for copy offload
Date:   Mon,  5 Jun 2023 17:47:25 +0530
Message-Id: <20230605121732.28468-10-nj.shetty@samsung.com>
In-Reply-To: <20230605121732.28468-1-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: <20230605121732.28468-1-nj.shetty@samsung.com>
        <CGME20230605122416epcas5p3b37c08a7bf7ad57361b22be0f30d3bf7@epcas5p3.samsung.com>
Precedence: bulk

Implementaion is based on existing read and write infrastructure.
copy_max_bytes: A new configfs and module parameter is introduced, which
can be used to set hardware/driver supported maximum copy limit.

Suggested-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Vincent Fu <vincent.fu@samsung.com>
---
 Documentation/block/null_blk.rst  |   5 ++
 drivers/block/null_blk/main.c     | 108 ++++++++++++++++++++++++++++--
 drivers/block/null_blk/null_blk.h |   8 +++
 3 files changed, 116 insertions(+), 5 deletions(-)

diff --git a/Documentation/block/null_blk.rst b/Documentation/block/null_blk.rst
index 4dd78f24d10a..6153e02fcf13 100644
--- a/Documentation/block/null_blk.rst
+++ b/Documentation/block/null_blk.rst
@@ -149,3 +149,8 @@ zone_size=[MB]: Default: 256
 zone_nr_conv=[nr_conv]: Default: 0
   The number of conventional zones to create when block device is zoned.  If
   zone_nr_conv >= nr_zones, it will be reduced to nr_zones - 1.
+
+copy_max_bytes=[size in bytes]: Default: COPY_MAX_BYTES
+  A module and configfs parameter which can be used to set hardware/driver
+  supported maximum copy offload limit.
+  COPY_MAX_BYTES(=128MB at present) is defined in fs.h
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index b3fedafe301e..34e009b3ebd5 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -157,6 +157,10 @@ static int g_max_sectors;
 module_param_named(max_sectors, g_max_sectors, int, 0444);
 MODULE_PARM_DESC(max_sectors, "Maximum size of a command (in 512B sectors)");
 
+static unsigned long g_copy_max_bytes = COPY_MAX_BYTES;
+module_param_named(copy_max_bytes, g_copy_max_bytes, ulong, 0444);
+MODULE_PARM_DESC(copy_max_bytes, "Maximum size of a copy command (in bytes)");
+
 static unsigned int nr_devices = 1;
 module_param(nr_devices, uint, 0444);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
@@ -409,6 +413,7 @@ NULLB_DEVICE_ATTR(home_node, uint, NULL);
 NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
 NULLB_DEVICE_ATTR(blocksize, uint, NULL);
 NULLB_DEVICE_ATTR(max_sectors, uint, NULL);
+NULLB_DEVICE_ATTR(copy_max_bytes, uint, NULL);
 NULLB_DEVICE_ATTR(irqmode, uint, NULL);
 NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
 NULLB_DEVICE_ATTR(index, uint, NULL);
@@ -550,6 +555,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_queue_mode,
 	&nullb_device_attr_blocksize,
 	&nullb_device_attr_max_sectors,
+	&nullb_device_attr_copy_max_bytes,
 	&nullb_device_attr_irqmode,
 	&nullb_device_attr_hw_queue_depth,
 	&nullb_device_attr_index,
@@ -656,7 +662,8 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"poll_queues,power,queue_mode,shared_tag_bitmap,size,"
 			"submit_queues,use_per_node_hctx,virt_boundary,zoned,"
 			"zone_capacity,zone_max_active,zone_max_open,"
-			"zone_nr_conv,zone_offline,zone_readonly,zone_size\n");
+			"zone_nr_conv,zone_offline,zone_readonly,zone_size,"
+			"copy_max_bytes\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -722,6 +729,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->queue_mode = g_queue_mode;
 	dev->blocksize = g_bs;
 	dev->max_sectors = g_max_sectors;
+	dev->copy_max_bytes = g_copy_max_bytes;
 	dev->irqmode = g_irqmode;
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
@@ -1271,6 +1279,78 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	return err;
 }
 
+static inline void nullb_setup_copy_read(struct nullb *nullb, struct bio *bio)
+{
+	struct nullb_copy_token *token = bvec_kmap_local(&bio->bi_io_vec[0]);
+
+	token->subsys = "nullb";
+	token->sector_in = bio->bi_iter.bi_sector;
+	token->nullb = nullb;
+	token->sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+}
+
+static inline int nullb_setup_copy_write(struct nullb *nullb,
+		struct bio *bio, bool is_fua)
+{
+	struct nullb_copy_token *token = bvec_kmap_local(&bio->bi_io_vec[0]);
+	sector_t sector_in, sector_out;
+	void *in, *out;
+	size_t rem, temp;
+	unsigned long offset_in, offset_out;
+	struct nullb_page *t_page_in, *t_page_out;
+	int ret = -EIO;
+
+	if (unlikely(memcmp(token->subsys, "nullb", 5)))
+		return -EINVAL;
+	if (unlikely(token->nullb != nullb))
+		return -EINVAL;
+	if (WARN_ON(token->sectors != bio->bi_iter.bi_size >> SECTOR_SHIFT))
+		return -EINVAL;
+
+	sector_in = token->sector_in;
+	sector_out = bio->bi_iter.bi_sector;
+	rem = token->sectors << SECTOR_SHIFT;
+
+	spin_lock_irq(&nullb->lock);
+	while (rem > 0) {
+		temp = min_t(size_t, nullb->dev->blocksize, rem);
+		offset_in = (sector_in & SECTOR_MASK) << SECTOR_SHIFT;
+		offset_out = (sector_out & SECTOR_MASK) << SECTOR_SHIFT;
+
+		if (null_cache_active(nullb) && !is_fua)
+			null_make_cache_space(nullb, PAGE_SIZE);
+
+		t_page_in = null_lookup_page(nullb, sector_in, false,
+			!null_cache_active(nullb));
+		if (!t_page_in)
+			goto err;
+		t_page_out = null_insert_page(nullb, sector_out,
+			!null_cache_active(nullb) || is_fua);
+		if (!t_page_out)
+			goto err;
+
+		in = kmap_local_page(t_page_in->page);
+		out = kmap_local_page(t_page_out->page);
+
+		memcpy(out + offset_out, in + offset_in, temp);
+		kunmap_local(out);
+		kunmap_local(in);
+		__set_bit(sector_out & SECTOR_MASK, t_page_out->bitmap);
+
+		if (is_fua)
+			null_free_sector(nullb, sector_out, true);
+
+		rem -= temp;
+		sector_in += temp >> SECTOR_SHIFT;
+		sector_out += temp >> SECTOR_SHIFT;
+	}
+
+	ret = 0;
+err:
+	spin_unlock_irq(&nullb->lock);
+	return ret;
+}
+
 static int null_handle_rq(struct nullb_cmd *cmd)
 {
 	struct request *rq = cmd->rq;
@@ -1280,13 +1360,20 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 	sector_t sector = blk_rq_pos(rq);
 	struct req_iterator iter;
 	struct bio_vec bvec;
+	bool fua = rq->cmd_flags & REQ_FUA;
+
+	if (rq->cmd_flags & REQ_COPY) {
+		if (op_is_write(req_op(rq)))
+			return nullb_setup_copy_write(nullb, rq->bio, fua);
+		nullb_setup_copy_read(nullb, rq->bio);
+		return 0;
+	}
 
 	spin_lock_irq(&nullb->lock);
 	rq_for_each_segment(bvec, rq, iter) {
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(req_op(rq)), sector,
-				     rq->cmd_flags & REQ_FUA);
+				     op_is_write(req_op(rq)), sector, fua);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;
@@ -1307,13 +1394,20 @@ static int null_handle_bio(struct nullb_cmd *cmd)
 	sector_t sector = bio->bi_iter.bi_sector;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
+	bool fua = bio->bi_opf & REQ_FUA;
+
+	if (bio->bi_opf & REQ_COPY) {
+		if (op_is_write(bio_op(bio)))
+			return nullb_setup_copy_write(nullb, bio, fua);
+		nullb_setup_copy_read(nullb, bio);
+		return 0;
+	}
 
 	spin_lock_irq(&nullb->lock);
 	bio_for_each_segment(bvec, bio, iter) {
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(bio_op(bio)), sector,
-				     bio->bi_opf & REQ_FUA);
+				     op_is_write(bio_op(bio)), sector, fua);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;
@@ -2161,6 +2255,10 @@ static int null_add_dev(struct nullb_device *dev)
 		dev->max_sectors = queue_max_hw_sectors(nullb->q);
 	dev->max_sectors = min(dev->max_sectors, BLK_DEF_MAX_SECTORS);
 	blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
+	blk_queue_max_copy_sectors_hw(nullb->q,
+			       dev->copy_max_bytes >> SECTOR_SHIFT);
+	if (dev->copy_max_bytes)
+		blk_queue_flag_set(QUEUE_FLAG_COPY, nullb->disk->queue);
 
 	if (dev->virt_boundary)
 		blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 929f659dd255..3dda593b0747 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -67,6 +67,13 @@ enum {
 	NULL_Q_MQ	= 2,
 };
 
+struct nullb_copy_token {
+	char *subsys;
+	struct nullb *nullb;
+	sector_t sector_in;
+	sector_t sectors;
+};
+
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_group group;
@@ -107,6 +114,7 @@ struct nullb_device {
 	unsigned int queue_mode; /* block interface */
 	unsigned int blocksize; /* block size */
 	unsigned int max_sectors; /* Max sectors per command */
+	unsigned long copy_max_bytes; /* Max copy offload length in bytes */
 	unsigned int irqmode; /* IRQ completion handler */
 	unsigned int hw_queue_depth; /* queue depth */
 	unsigned int index; /* index of the disk, only valid with a disk */
-- 
2.35.1.500.gb896f729e2