[PATCH v11 3/9] block: add emulation for copy

From: Nitesh Shetty
Date: Mon May 22 2023 - 07:16:46 EST


For the devices which does not support copy, copy emulation is added.
It is required for in-kernel users like fabrics, where file descriptor is
not available and hence they can't use copy_file_range.
Copy-emulation is implemented by reading from source into memory and
writing to the corresponding destination asynchronously.
Also emulation is used, if copy offload fails or partially completes.

Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
Signed-off-by: Vincent Fu <vincent.fu@xxxxxxxxxxx>
Signed-off-by: Anuj Gupta <anuj20.g@xxxxxxxxxxx>
---
block/blk-lib.c | 175 ++++++++++++++++++++++++++++++++++++++++-
block/blk-map.c | 4 +-
include/linux/blkdev.h | 3 +
3 files changed, 179 insertions(+), 3 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index ed089e703cb1..ba32545eb8d5 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -295,6 +295,172 @@ static int __blkdev_copy_offload(struct block_device *bdev_in, loff_t pos_in,
return blkdev_copy_wait_completion(cio);
}

+static void *blkdev_copy_alloc_buf(sector_t req_size, sector_t *alloc_size,
+ gfp_t gfp_mask)
+{
+ int min_size = PAGE_SIZE;
+ void *buf;
+
+ while (req_size >= min_size) {
+ buf = kvmalloc(req_size, gfp_mask);
+ if (buf) {
+ *alloc_size = req_size;
+ return buf;
+ }
+ /* retry half the requested size */
+ req_size >>= 1;
+ }
+
+ return NULL;
+}
+
+static void blkdev_copy_emulate_write_endio(struct bio *bio)
+{
+ struct copy_ctx *ctx = bio->bi_private;
+ struct cio *cio = ctx->cio;
+ sector_t clen;
+
+ if (bio->bi_status) {
+ clen = (bio->bi_iter.bi_sector << SECTOR_SHIFT) - cio->pos_out;
+ cio->comp_len = min_t(sector_t, clen, cio->comp_len);
+ }
+ kvfree(page_address(bio->bi_io_vec[0].bv_page));
+ bio_map_kern_endio(bio);
+ kfree(ctx);
+ if (atomic_dec_and_test(&cio->refcount)) {
+ if (cio->endio) {
+ cio->endio(cio->private, cio->comp_len);
+ kfree(cio);
+ } else
+ blk_wake_io_task(cio->waiter);
+ }
+}
+
+static void blkdev_copy_emulate_read_endio(struct bio *read_bio)
+{
+ struct copy_ctx *ctx = read_bio->bi_private;
+ struct cio *cio = ctx->cio;
+ sector_t clen;
+
+ if (read_bio->bi_status) {
+ clen = (read_bio->bi_iter.bi_sector << SECTOR_SHIFT) -
+ cio->pos_in;
+ cio->comp_len = min_t(sector_t, clen, cio->comp_len);
+ __free_page(read_bio->bi_io_vec[0].bv_page);
+ bio_map_kern_endio(read_bio);
+ kfree(ctx);
+
+ if (atomic_dec_and_test(&cio->refcount)) {
+ if (cio->endio) {
+ cio->endio(cio->private, cio->comp_len);
+ kfree(cio);
+ } else
+ blk_wake_io_task(cio->waiter);
+ }
+ }
+ schedule_work(&ctx->dispatch_work);
+ kfree(read_bio);
+}
+
+/*
+ * If native copy offload feature is absent, this function tries to emulate,
+ * by copying data from source to a temporary buffer and from buffer to
+ * destination device.
+ * Returns the length of bytes copied or error if encountered
+ */
+static int __blkdev_copy_emulate(struct block_device *bdev_in, loff_t pos_in,
+ struct block_device *bdev_out, loff_t pos_out, size_t len,
+ cio_iodone_t endio, void *private, gfp_t gfp_mask)
+{
+ struct request_queue *in = bdev_get_queue(bdev_in);
+ struct request_queue *out = bdev_get_queue(bdev_out);
+ struct bio *read_bio, *write_bio;
+ void *buf = NULL;
+ struct copy_ctx *ctx;
+ struct cio *cio;
+ sector_t buf_len, req_len, rem = 0;
+ sector_t max_src_hw_len = min_t(unsigned int,
+ queue_max_hw_sectors(in),
+ queue_max_segments(in) << (PAGE_SHIFT - SECTOR_SHIFT))
+ << SECTOR_SHIFT;
+ sector_t max_dst_hw_len = min_t(unsigned int,
+ queue_max_hw_sectors(out),
+ queue_max_segments(out) << (PAGE_SHIFT - SECTOR_SHIFT))
+ << SECTOR_SHIFT;
+ sector_t max_hw_len = min_t(unsigned int,
+ max_src_hw_len, max_dst_hw_len);
+
+ cio = kzalloc(sizeof(struct cio), GFP_KERNEL);
+ if (!cio)
+ return -ENOMEM;
+ atomic_set(&cio->refcount, 0);
+ cio->pos_in = pos_in;
+ cio->pos_out = pos_out;
+ cio->waiter = current;
+ cio->endio = endio;
+ cio->private = private;
+
+ for (rem = len; rem > 0; rem -= buf_len) {
+ req_len = min_t(int, max_hw_len, rem);
+
+ buf = blkdev_copy_alloc_buf(req_len, &buf_len, gfp_mask);
+ if (!buf)
+ goto err_alloc_buf;
+
+ ctx = kzalloc(sizeof(struct copy_ctx), gfp_mask);
+ if (!ctx)
+ goto err_ctx;
+
+ read_bio = bio_map_kern(in, buf, buf_len, gfp_mask);
+ if (IS_ERR(read_bio))
+ goto err_read_bio;
+
+ write_bio = bio_map_kern(out, buf, buf_len, gfp_mask);
+ if (IS_ERR(write_bio))
+ goto err_write_bio;
+
+ ctx->cio = cio;
+ ctx->write_bio = write_bio;
+ INIT_WORK(&ctx->dispatch_work, blkdev_copy_dispatch_work);
+
+ read_bio->bi_iter.bi_sector = pos_in >> SECTOR_SHIFT;
+ read_bio->bi_iter.bi_size = buf_len;
+ read_bio->bi_opf = REQ_OP_READ | REQ_SYNC;
+ bio_set_dev(read_bio, bdev_in);
+ read_bio->bi_end_io = blkdev_copy_emulate_read_endio;
+ read_bio->bi_private = ctx;
+
+ write_bio->bi_iter.bi_size = buf_len;
+ write_bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
+ bio_set_dev(write_bio, bdev_out);
+ write_bio->bi_end_io = blkdev_copy_emulate_write_endio;
+ write_bio->bi_iter.bi_sector = pos_out >> SECTOR_SHIFT;
+ write_bio->bi_private = ctx;
+
+ atomic_inc(&cio->refcount);
+ submit_bio(read_bio);
+
+ pos_in += buf_len;
+ pos_out += buf_len;
+ }
+
+ /* Wait for completion of all IO's*/
+ return blkdev_copy_wait_completion(cio);
+
+err_write_bio:
+ bio_put(read_bio);
+err_read_bio:
+ kfree(ctx);
+err_ctx:
+ kvfree(buf);
+err_alloc_buf:
+ cio->comp_len -= min_t(sector_t, cio->comp_len, len - rem);
+ if (!atomic_read(&cio->refcount))
+ return -ENOMEM;
+ /* Wait for submitted IOs to complete */
+ return blkdev_copy_wait_completion(cio);
+}
+
static inline int blkdev_copy_sanity_check(struct block_device *bdev_in,
loff_t pos_in, struct block_device *bdev_out, loff_t pos_out,
size_t len)
@@ -342,9 +508,16 @@ int blkdev_issue_copy(struct block_device *bdev_in, loff_t pos_in,
if (ret)
return ret;

- if (blk_queue_copy(q_in) && blk_queue_copy(q_out))
+ if (blk_queue_copy(q_in) && blk_queue_copy(q_out)) {
ret = __blkdev_copy_offload(bdev_in, pos_in, bdev_out, pos_out,
len, endio, private, gfp_mask);
+ if (ret < 0)
+ ret = 0;
+ }
+
+ if (ret != len)
+ ret = __blkdev_copy_emulate(bdev_in, pos_in + ret, bdev_out,
+ pos_out + ret, len - ret, endio, private, gfp_mask);

return ret;
}
diff --git a/block/blk-map.c b/block/blk-map.c
index 04c55f1c492e..e79eb4d2e545 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -363,7 +363,7 @@ static void bio_invalidate_vmalloc_pages(struct bio *bio)
#endif
}

-static void bio_map_kern_endio(struct bio *bio)
+void bio_map_kern_endio(struct bio *bio)
{
bio_invalidate_vmalloc_pages(bio);
bio_uninit(bio);
@@ -380,7 +380,7 @@ static void bio_map_kern_endio(struct bio *bio)
* Map the kernel address into a bio suitable for io to a block
* device. Returns an error pointer in case of error.
*/
-static struct bio *bio_map_kern(struct request_queue *q, void *data,
+struct bio *bio_map_kern(struct request_queue *q, void *data,
unsigned int len, gfp_t gfp_mask)
{
unsigned long kaddr = (unsigned long)data;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6f2814ab4741..a95c26faa8b6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1054,6 +1054,9 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
int blkdev_issue_copy(struct block_device *bdev_in, loff_t pos_in,
struct block_device *bdev_out, loff_t pos_out, size_t len,
cio_iodone_t end_io, void *private, gfp_t gfp_mask);
+struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
+ gfp_t gfp_mask);
+void bio_map_kern_endio(struct bio *bio);

#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */
#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */
--
2.35.1.500.gb896f729e2