[PATCH v4 02/10] block: Add copy offload support infrastructure

[Nitesh Shetty]

Introduce blkdev_issue_copy which supports source and destination bdevs,
and an array of (source, destination and copy length) tuples.
Introduce REQ_COPY copy offload operation flag. Create a read-write
bio pair with a token as payload and submitted to the device in order.
Read request populates token with source specific information which
is then passed with write request.
This design is courtesy Mikulas Patocka's token based copy

Larger copy will be divided, based on max_copy_sectors,
max_copy_range_sector limits.

Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
Signed-off-by: Arnav Dawn <arnav.dawn@xxxxxxxxxxx>
---
 block/blk-lib.c           | 232 ++++++++++++++++++++++++++++++++++++++
 block/blk.h               |   2 +
 include/linux/blk_types.h |  21 ++++
 include/linux/blkdev.h    |   2 +
 include/uapi/linux/fs.h   |  14 +++
 5 files changed, 271 insertions(+)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 09b7e1200c0f..ba9da2d2f429 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -117,6 +117,238 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
+/*
+ * Wait on and process all in-flight BIOs.  This must only be called once
+ * all bios have been issued so that the refcount can only decrease.
+ * This just waits for all bios to make it through bio_copy_end_io. IO
+ * errors are propagated through cio->io_error.
+ */
+static int cio_await_completion(struct cio *cio)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cio->lock, flags);
+	if (cio->refcount) {
+		cio->waiter = current;
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		spin_unlock_irqrestore(&cio->lock, flags);
+		blk_io_schedule();
+		/* wake up sets us TASK_RUNNING */
+		spin_lock_irqsave(&cio->lock, flags);
+		cio->waiter = NULL;
+		ret = cio->io_err;
+	}
+	spin_unlock_irqrestore(&cio->lock, flags);
+	kvfree(cio);
+
+	return ret;
+}
+
+static void bio_copy_end_io(struct bio *bio)
+{
+	struct copy_ctx *ctx = bio->bi_private;
+	struct cio *cio = ctx->cio;
+	sector_t clen;
+	int ri = ctx->range_idx;
+	unsigned long flags;
+	bool wake = false;
+
+	if (bio->bi_status) {
+		cio->io_err = bio->bi_status;
+		clen = (bio->bi_iter.bi_sector << SECTOR_SHIFT) - ctx->start_sec;
+		cio->rlist[ri].comp_len = min_t(sector_t, clen, cio->rlist[ri].comp_len);
+	}
+	__free_page(bio->bi_io_vec[0].bv_page);
+	kfree(ctx);
+	bio_put(bio);
+
+	spin_lock_irqsave(&cio->lock, flags);
+	if (((--cio->refcount) <= 0) && cio->waiter)
+		wake = true;
+	spin_unlock_irqrestore(&cio->lock, flags);
+	if (wake)
+		wake_up_process(cio->waiter);
+}
+
+/*
+ * blk_copy_offload	- Use device's native copy offload feature
+ * Go through user provide payload, prepare new payload based on device's copy offload limits.
+ */
+int blk_copy_offload(struct block_device *src_bdev, int nr_srcs,
+		struct range_entry *rlist, struct block_device *dst_bdev, gfp_t gfp_mask)
+{
+	struct request_queue *sq = bdev_get_queue(src_bdev);
+	struct request_queue *dq = bdev_get_queue(dst_bdev);
+	struct bio *read_bio, *write_bio;
+	struct copy_ctx *ctx;
+	struct cio *cio;
+	struct page *token;
+	sector_t src_blk, copy_len, dst_blk;
+	sector_t remaining, max_copy_len = LONG_MAX;
+	unsigned long flags;
+	int ri = 0, ret = 0;
+
+	cio = kzalloc(sizeof(struct cio), GFP_KERNEL);
+	if (!cio)
+		return -ENOMEM;
+	cio->rlist = rlist;
+	spin_lock_init(&cio->lock);
+
+	max_copy_len = min_t(sector_t, sq->limits.max_copy_sectors, dq->limits.max_copy_sectors);
+	max_copy_len = min3(max_copy_len, (sector_t)sq->limits.max_copy_range_sectors,
+			(sector_t)dq->limits.max_copy_range_sectors) << SECTOR_SHIFT;
+
+	for (ri = 0; ri < nr_srcs; ri++) {
+		cio->rlist[ri].comp_len = rlist[ri].len;
+		src_blk = rlist[ri].src;
+		dst_blk = rlist[ri].dst;
+		for (remaining = rlist[ri].len; remaining > 0; remaining -= copy_len) {
+			copy_len = min(remaining, max_copy_len);
+
+			token = alloc_page(gfp_mask);
+			if (unlikely(!token)) {
+				ret = -ENOMEM;
+				goto err_token;
+			}
+
+			ctx = kzalloc(sizeof(struct copy_ctx), gfp_mask);
+			if (!ctx) {
+				ret = -ENOMEM;
+				goto err_ctx;
+			}
+			ctx->cio = cio;
+			ctx->range_idx = ri;
+			ctx->start_sec = dst_blk;
+
+			read_bio = bio_alloc(src_bdev, 1, REQ_OP_READ | REQ_COPY | REQ_NOMERGE,
+					gfp_mask);
+			if (!read_bio) {
+				ret = -ENOMEM;
+				goto err_read_bio;
+			}
+			read_bio->bi_iter.bi_sector = src_blk >> SECTOR_SHIFT;
+			__bio_add_page(read_bio, token, PAGE_SIZE, 0);
+			/*__bio_add_page increases bi_size by len, so overwrite it with copy len*/
+			read_bio->bi_iter.bi_size = copy_len;
+			ret = submit_bio_wait(read_bio);
+			bio_put(read_bio);
+			if (ret)
+				goto err_read_bio;
+
+			write_bio = bio_alloc(dst_bdev, 1, REQ_OP_WRITE | REQ_COPY | REQ_NOMERGE,
+					gfp_mask);
+			if (!write_bio) {
+				ret = -ENOMEM;
+				goto err_read_bio;
+			}
+			write_bio->bi_iter.bi_sector = dst_blk >> SECTOR_SHIFT;
+			__bio_add_page(write_bio, token, PAGE_SIZE, 0);
+			/*__bio_add_page increases bi_size by len, so overwrite it with copy len*/
+			write_bio->bi_iter.bi_size = copy_len;
+			write_bio->bi_end_io = bio_copy_end_io;
+			write_bio->bi_private = ctx;
+
+			spin_lock_irqsave(&cio->lock, flags);
+			++cio->refcount;
+			spin_unlock_irqrestore(&cio->lock, flags);
+
+			submit_bio(write_bio);
+			src_blk += copy_len;
+			dst_blk += copy_len;
+		}
+	}
+
+	/* Wait for completion of all IO's*/
+	return cio_await_completion(cio);
+
+err_read_bio:
+	kfree(ctx);
+err_ctx:
+	__free_page(token);
+err_token:
+	rlist[ri].comp_len = min_t(sector_t, rlist[ri].comp_len, (rlist[ri].len - remaining));
+
+	cio->io_err = ret;
+	return cio_await_completion(cio);
+}
+
+static inline int blk_copy_sanity_check(struct block_device *src_bdev,
+		struct block_device *dst_bdev, struct range_entry *rlist, int nr)
+{
+	unsigned int align_mask = max(
+			bdev_logical_block_size(dst_bdev), bdev_logical_block_size(src_bdev)) - 1;
+	sector_t len = 0;
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		if (rlist[i].len)
+			len += rlist[i].len;
+		else
+			return -EINVAL;
+		if ((rlist[i].dst & align_mask) || (rlist[i].src & align_mask) ||
+				(rlist[i].len & align_mask))
+			return -EINVAL;
+		rlist[i].comp_len = 0;
+	}
+
+	if (len && len >= MAX_COPY_TOTAL_LENGTH)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline bool blk_check_copy_offload(struct request_queue *src_q,
+		struct request_queue *dest_q)
+{
+	if (blk_queue_copy(dest_q) && blk_queue_copy(src_q))
+		return true;
+
+	return false;
+}
+
+/*
+ * blkdev_issue_copy - queue a copy
+ * @src_bdev:	source block device
+ * @nr_srcs:	number of source ranges to copy
+ * @rlist:	array of source/dest/len
+ * @dest_bdev:	destination block device
+ * @gfp_mask:   memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *	Copy source ranges from source block device to destination block device.
+ *	length of a source range cannot be zero.
+ */
+int blkdev_issue_copy(struct block_device *src_bdev, int nr,
+		struct range_entry *rlist, struct block_device *dest_bdev, gfp_t gfp_mask)
+{
+	struct request_queue *src_q = bdev_get_queue(src_bdev);
+	struct request_queue *dest_q = bdev_get_queue(dest_bdev);
+	int ret = -EINVAL;
+
+	if (!src_q || !dest_q)
+		return -ENXIO;
+
+	if (!nr)
+		return -EINVAL;
+
+	if (nr >= MAX_COPY_NR_RANGE)
+		return -EINVAL;
+
+	if (bdev_read_only(dest_bdev))
+		return -EPERM;
+
+	ret = blk_copy_sanity_check(src_bdev, dest_bdev, rlist, nr);
+	if (ret)
+		return ret;
+
+	if (blk_check_copy_offload(src_q, dest_q))
+		ret = blk_copy_offload(src_bdev, nr, rlist, dest_bdev, gfp_mask);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_issue_copy);
+
 static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
 		struct bio **biop, unsigned flags)
diff --git a/block/blk.h b/block/blk.h
index 434017701403..6010eda58c70 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -291,6 +291,8 @@ static inline bool blk_may_split(struct request_queue *q, struct bio *bio)
 		break;
 	}
 
+	if (unlikely(op_is_copy(bio->bi_opf)))
+		return false;
 	/*
 	 * All drivers must accept single-segments bios that are <= PAGE_SIZE.
 	 * This is a quick and dirty check that relies on the fact that
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index c62274466e72..f5b01f284c43 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -418,6 +418,7 @@ enum req_flag_bits {
 	/* for driver use */
 	__REQ_DRV,
 	__REQ_SWAP,		/* swapping request. */
+	__REQ_COPY,		/* copy request */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -443,6 +444,7 @@ enum req_flag_bits {
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
 #define REQ_SWAP		(1ULL << __REQ_SWAP)
+#define REQ_COPY		(1ULL << __REQ_COPY)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -459,6 +461,11 @@ enum stat_group {
 	NR_STAT_GROUPS
 };
 
+static inline bool op_is_copy(unsigned int op)
+{
+	return (op & REQ_COPY);
+}
+
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
 
@@ -533,4 +540,18 @@ struct blk_rq_stat {
 	u64 batch;
 };
 
+struct cio {
+	struct range_entry *rlist;
+	struct task_struct *waiter;     /* waiting task (NULL if none) */
+	spinlock_t lock;		/* protects refcount and waiter */
+	int refcount;
+	blk_status_t io_err;
+};
+
+struct copy_ctx {
+	int range_idx;
+	sector_t start_sec;
+	struct cio *cio;
+};
+
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3596fd37fae7..c6cb3fe82ba2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1121,6 +1121,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop);
 int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp);
+int blkdev_issue_copy(struct block_device *src_bdev, int nr_srcs,
+		struct range_entry *src_rlist, struct block_device *dest_bdev, gfp_t gfp_mask);
 
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index bdf7b404b3e7..822c28cebf3a 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -64,6 +64,20 @@ struct fstrim_range {
 	__u64 minlen;
 };
 
+/* Maximum no of entries supported */
+#define MAX_COPY_NR_RANGE	(1 << 12)
+
+/* maximum total copy length */
+#define MAX_COPY_TOTAL_LENGTH	(1 << 27)
+
+/* Source range entry for copy */
+struct range_entry {
+	__u64 src;
+	__u64 dst;
+	__u64 len;
+	__u64 comp_len;
+};
+
 /* 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