Received-SPF: pass (google.com: domain of linux-kernel+bounces-9443-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
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>, 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>, 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 v19 02/12] Add infrastructure for copy offload in block and
 request layer.
Date: Fri, 22 Dec 2023 11:42:56 +0530
Message-Id: <20231222061313.12260-3-nj.shetty@samsung.com>
In-Reply-To: <20231222061313.12260-1-nj.shetty@samsung.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 105P
DLP-Filter: Pass
References: <20231222061313.12260-1-nj.shetty@samsung.com>
	<CGME20231222062105epcas5p1c21613f0c44451d579ae4cd24003cca2@epcas5p1.samsung.com>

We add two new opcode REQ_OP_COPY_DST, REQ_OP_COPY_SRC.
Since copy is a composite operation involving src and dst sectors/lba,
each needs to be represented by a separate bio to make it compatible
with device mapper.
We expect caller to take a plug and send bio with destination information,
followed by bio with source information.
Once the dst bio arrives we form a request and wait for source
bio. Upon arrival of source bio we merge these two bio's and send
corresponding request down to device driver.
Merging non copy offload bio is avoided by checking for copy specific
opcodes in merge function.

Signed-off-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
---
 block/blk-core.c          |  7 +++++++
 block/blk-merge.c         | 41 +++++++++++++++++++++++++++++++++++++++
 block/blk.h               | 16 +++++++++++++++
 block/elevator.h          |  1 +
 include/linux/bio.h       |  6 +-----
 include/linux/blk_types.h | 10 ++++++++++
 6 files changed, 76 insertions(+), 5 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 2eca76ccf4ee..51c6cc3022f4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -121,6 +121,8 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(ZONE_APPEND),
 	REQ_OP_NAME(WRITE_ZEROES),
+	REQ_OP_NAME(COPY_SRC),
+	REQ_OP_NAME(COPY_DST),
 	REQ_OP_NAME(DRV_IN),
 	REQ_OP_NAME(DRV_OUT),
 };
@@ -800,6 +802,11 @@ void submit_bio_noacct(struct bio *bio)
 		if (!q->limits.max_write_zeroes_sectors)
 			goto not_supported;
 		break;
+	case REQ_OP_COPY_SRC:
+	case REQ_OP_COPY_DST:
+		if (!q->limits.max_copy_sectors)
+			goto not_supported;
+		break;
 	default:
 		break;
 	}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 65e75efa9bd3..bcb55ba48107 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -158,6 +158,20 @@ static struct bio *bio_split_write_zeroes(struct bio *bio,
 	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
 }
 
+static struct bio *bio_split_copy(struct bio *bio,
+				  const struct queue_limits *lim,
+				  unsigned int *nsegs)
+{
+	*nsegs = 1;
+	if (bio_sectors(bio) <= lim->max_copy_sectors)
+		return NULL;
+	/*
+	 * We don't support splitting for a copy bio. End it with EIO if
+	 * splitting is required and return an error pointer.
+	 */
+	return ERR_PTR(-EIO);
+}
+
 /*
  * Return the maximum number of sectors from the start of a bio that may be
  * submitted as a single request to a block device. If enough sectors remain,
@@ -366,6 +380,12 @@ struct bio *__bio_split_to_limits(struct bio *bio,
 	case REQ_OP_WRITE_ZEROES:
 		split = bio_split_write_zeroes(bio, lim, nr_segs, bs);
 		break;
+	case REQ_OP_COPY_SRC:
+	case REQ_OP_COPY_DST:
+		split = bio_split_copy(bio, lim, nr_segs);
+		if (IS_ERR(split))
+			return NULL;
+		break;
 	default:
 		split = bio_split_rw(bio, lim, nr_segs, bs,
 				get_max_io_size(bio, lim) << SECTOR_SHIFT);
@@ -922,6 +942,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
+	if (blk_copy_offload_mergable(rq, bio))
+		return true;
+
 	if (req_op(rq) != bio_op(bio))
 		return false;
 
@@ -951,6 +974,8 @@ enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 {
 	if (blk_discard_mergable(rq))
 		return ELEVATOR_DISCARD_MERGE;
+	else if (blk_copy_offload_mergable(rq, bio))
+		return ELEVATOR_COPY_OFFLOAD_MERGE;
 	else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
 	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
@@ -1053,6 +1078,20 @@ static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q,
 	return BIO_MERGE_FAILED;
 }
 
+static enum bio_merge_status bio_attempt_copy_offload_merge(struct request *req,
+							    struct bio *bio)
+{
+	if (req->__data_len != bio->bi_iter.bi_size)
+		return BIO_MERGE_FAILED;
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->nr_phys_segments++;
+	req->__data_len += bio->bi_iter.bi_size;
+
+	return BIO_MERGE_OK;
+}
+
 static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 						   struct request *rq,
 						   struct bio *bio,
@@ -1073,6 +1112,8 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 		break;
 	case ELEVATOR_DISCARD_MERGE:
 		return bio_attempt_discard_merge(q, rq, bio);
+	case ELEVATOR_COPY_OFFLOAD_MERGE:
+		return bio_attempt_copy_offload_merge(rq, bio);
 	default:
 		return BIO_MERGE_NONE;
 	}
diff --git a/block/blk.h b/block/blk.h
index 08a358bc0919..3d51d7827abb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -159,6 +159,20 @@ static inline bool blk_discard_mergable(struct request *req)
 	return false;
 }
 
+/*
+ * Copy offload sends a pair of bio with REQ_OP_COPY_DST and REQ_OP_COPY_SRC
+ * operation by taking a plug.
+ * Initially DST bio is sent which forms a request and
+ * waits for SRC bio to arrive. Once SRC bio arrives
+ * we merge it and send request down to driver.
+ */
+static inline bool blk_copy_offload_mergable(struct request *req,
+					     struct bio *bio)
+{
+	return (req_op(req) == REQ_OP_COPY_DST &&
+		bio_op(bio) == REQ_OP_COPY_SRC);
+}
+
 static inline unsigned int blk_rq_get_max_segments(struct request *rq)
 {
 	if (req_op(rq) == REQ_OP_DISCARD)
@@ -300,6 +314,8 @@ static inline bool bio_may_exceed_limits(struct bio *bio,
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
 	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_COPY_SRC:
+	case REQ_OP_COPY_DST:
 		return true; /* non-trivial splitting decisions */
 	default:
 		break;
diff --git a/block/elevator.h b/block/elevator.h
index 7ca3d7b6ed82..eec442bbf384 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -18,6 +18,7 @@ enum elv_merge {
 	ELEVATOR_FRONT_MERGE	= 1,
 	ELEVATOR_BACK_MERGE	= 2,
 	ELEVATOR_DISCARD_MERGE	= 3,
+	ELEVATOR_COPY_OFFLOAD_MERGE	= 4,
 };
 
 struct blk_mq_alloc_data;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 41d417ee1349..ed746738755a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -53,11 +53,7 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs)
  */
 static inline bool bio_has_data(struct bio *bio)
 {
-	if (bio &&
-	    bio->bi_iter.bi_size &&
-	    bio_op(bio) != REQ_OP_DISCARD &&
-	    bio_op(bio) != REQ_OP_SECURE_ERASE &&
-	    bio_op(bio) != REQ_OP_WRITE_ZEROES)
+	if (bio && (bio_op(bio) == REQ_OP_READ || bio_op(bio) == REQ_OP_WRITE))
 		return true;
 
 	return false;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b29ebd53417d..344dd3740a87 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -395,6 +395,10 @@ enum req_op {
 	/* reset all the zone present on the device */
 	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
 
+	/* copy offload src and dst operation */
+	REQ_OP_COPY_SRC		= (__force blk_opf_t)18,
+	REQ_OP_COPY_DST		= (__force blk_opf_t)19,
+
 	/* Driver private requests */
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
 	REQ_OP_DRV_OUT		= (__force blk_opf_t)35,
@@ -483,6 +487,12 @@ static inline bool op_is_write(blk_opf_t op)
 	return !!(op & (__force blk_opf_t)1);
 }
 
+static inline bool op_is_copy(blk_opf_t op)
+{
+	return ((op & REQ_OP_MASK) == REQ_OP_COPY_SRC ||
+		(op & REQ_OP_MASK) == REQ_OP_COPY_DST);
+}
+
 /*
  * Check if the bio or request is one that needs special treatment in the
  * flush state machine.
-- 
2.35.1.500.gb896f729e2