On 8/11/23 03:52, Nitesh Shetty wrote:
> + * Description:
> + * Copy source offset to destination offset within block device, using
> + * device's native copy offload feature.
Offloading the copy operation is not guaranteed so I think that needs to
be reflected in the above comment.
> + * We perform copy operation by sending 2 bio's.
> + * 1. We take a plug and send a REQ_OP_COPY_SRC bio along with source
> + * sector and length. Once this bio reaches request layer, we form a
> + * request and wait for dst bio to arrive.
What will happen if the queue depth of the request queue at the bottom
is one?
> + blk_start_plug(&plug);
> + dst_bio = blk_next_bio(src_bio, bdev, 0, REQ_OP_COPY_DST, gfp);
blk_next_bio() can return NULL so its return value should be checked.
> + dst_bio->bi_iter.bi_size = chunk;
> + dst_bio->bi_iter.bi_sector = pos_out >> SECTOR_SHIFT;
> + dst_bio->bi_end_io = blkdev_copy_offload_dst_endio;
> + dst_bio->bi_private = offload_io;
Thanks,
Bart.
@@ -10,6 +10,22 @@
#include "blk.h"
+/* Keeps track of all outstanding copy IO */
+struct blkdev_copy_io {
+ atomic_t refcount;
+ ssize_t copied;
+ int status;
+ struct task_struct *waiter;
+ void (*endio)(void *private, int status, ssize_t copied);
+ void *private;
+};
+
+/* Keeps track of single outstanding copy offload IO */
+struct blkdev_copy_offload_io {
+ struct blkdev_copy_io *cio;
+ loff_t offset;
+};
+
static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
{
unsigned int discard_granularity = bdev_discard_granularity(bdev);
@@ -115,6 +131,186 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL(blkdev_issue_discard);
+static inline ssize_t 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)
+{
+ unsigned int align = max(bdev_logical_block_size(bdev_out),
+ bdev_logical_block_size(bdev_in)) - 1;
+
+ if ((pos_in & align) || (pos_out & align) || (len & align) || !len ||
+ len >= COPY_MAX_BYTES)
+ return -EINVAL;
+
+ return 0;
+}
+
+static inline void blkdev_copy_endio(struct blkdev_copy_io *cio)
+{
+ if (cio->endio) {
+ cio->endio(cio->private, cio->status, cio->copied);
+ kfree(cio);
+ } else {
+ struct task_struct *waiter = cio->waiter;
+
+ WRITE_ONCE(cio->waiter, NULL);
+ blk_wake_io_task(waiter);
+ }
+}
+
+/*
+ * 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 complete.
+ * Returns the length of bytes copied or error
+ */
+static ssize_t blkdev_copy_wait_io_completion(struct blkdev_copy_io *cio)
+{
+ ssize_t ret;
+
+ for (;;) {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ if (!READ_ONCE(cio->waiter))
+ break;
+ blk_io_schedule();
+ }
+ __set_current_state(TASK_RUNNING);
+ ret = cio->copied;
+ kfree(cio);
+
+ return ret;
+}
+
+static void blkdev_copy_offload_dst_endio(struct bio *bio)
+{
+ struct blkdev_copy_offload_io *offload_io = bio->bi_private;
+ struct blkdev_copy_io *cio = offload_io->cio;
+
+ if (bio->bi_status) {
+ cio->copied = min_t(ssize_t, offload_io->offset, cio->copied);
+ if (!cio->status)
+ cio->status = blk_status_to_errno(bio->bi_status);
+ }
+ bio_put(bio);
+
+ if (atomic_dec_and_test(&cio->refcount))
+ blkdev_copy_endio(cio);
+}
+
+/*
+ * @bdev: block device
+ * @pos_in: source offset
+ * @pos_out: destination offset
+ * @len: length in bytes to be copied
+ * @endio: endio function to be called on completion of copy operation,
+ * for synchronous operation this should be NULL
+ * @private: endio function will be called with this private data,
+ * for synchronous operation this should be NULL
+ * @gfp_mask: memory allocation flags (for bio_alloc)
+ *
+ * For synchronous operation returns the length of bytes copied or error
+ * For asynchronous operation returns -EIOCBQUEUED or error
+ *
+ * Description:
+ * Copy source offset to destination offset within block device, using
+ * device's native copy offload feature.
+ * We perform copy operation by sending 2 bio's.
+ * 1. We take a plug and send a REQ_OP_COPY_SRC bio along with source
+ * sector and length. Once this bio reaches request layer, we form a
+ * request and wait for dst bio to arrive.
+ * 2. We issue REQ_OP_COPY_DST bio along with destination sector, length.
+ * Once this bio reaches request layer and find a request with previously
+ * sent source info we merge the destination bio and return.
+ * 3. Release the plug and request is sent to driver
+ * This design works only for drivers with request queue.
+ */
+ssize_t blkdev_copy_offload(struct block_device *bdev, loff_t pos_in,
+ loff_t pos_out, size_t len,
+ void (*endio)(void *, int, ssize_t),
+ void *private, gfp_t gfp)
+{
+ struct blkdev_copy_io *cio;
+ struct blkdev_copy_offload_io *offload_io;
+ struct bio *src_bio, *dst_bio;
+ ssize_t rem, chunk, ret;
+ ssize_t max_copy_bytes = bdev_max_copy_sectors(bdev) << SECTOR_SHIFT;
+ struct blk_plug plug;
+
+ if (!max_copy_bytes)
+ return -EINVAL;
+
+ ret = blkdev_copy_sanity_check(bdev, pos_in, bdev, pos_out, len);
+ if (ret)
+ return ret;
+
+ cio = kzalloc(sizeof(*cio), GFP_KERNEL);
+ if (!cio)
+ return -ENOMEM;
+ atomic_set(&cio->refcount, 1);
+ cio->waiter = current;
+ cio->endio = endio;
+ cio->private = private;
+
+ /*
+ * If there is a error, copied will be set to least successfully
+ * completed copied length
+ */
+ cio->copied = len;
+ for (rem = len; rem > 0; rem -= chunk) {
+ chunk = min(rem, max_copy_bytes);
+
+ offload_io = kzalloc(sizeof(*offload_io), GFP_KERNEL);
+ if (!offload_io)
+ goto err_free_cio;
+ offload_io->cio = cio;
+ /*
+ * For partial completion, we use offload_io->offset to truncate
+ * successful copy length
+ */
+ offload_io->offset = len - rem;
+
+ src_bio = bio_alloc(bdev, 0, REQ_OP_COPY_SRC, gfp);
+ if (!src_bio)
+ goto err_free_offload_io;
+ src_bio->bi_iter.bi_size = chunk;
+ src_bio->bi_iter.bi_sector = pos_in >> SECTOR_SHIFT;
+
+ blk_start_plug(&plug);
+ dst_bio = blk_next_bio(src_bio, bdev, 0, REQ_OP_COPY_DST, gfp);
+ dst_bio->bi_iter.bi_size = chunk;
+ dst_bio->bi_iter.bi_sector = pos_out >> SECTOR_SHIFT;
+ dst_bio->bi_end_io = blkdev_copy_offload_dst_endio;
+ dst_bio->bi_private = offload_io;
+
+ if (rem != chunk)
+ atomic_inc(&cio->refcount);
+ submit_bio(dst_bio);
+ blk_finish_plug(&plug);
+ pos_in += chunk;
+ pos_out += chunk;
+ }
+
+ if (cio->endio)
+ return -EIOCBQUEUED;
+
+ return blkdev_copy_wait_io_completion(cio);
+
+err_free_offload_io:
+ kfree(offload_io);
+err_free_cio:
+ cio->copied = min_t(ssize_t, cio->copied, (len - rem));
+ cio->status = -ENOMEM;
+ if (rem == len) {
+ kfree(cio);
+ return cio->status;
+ }
+ if (cio->endio)
+ return cio->status;
+
+ return blkdev_copy_wait_io_completion(cio);
+}
+EXPORT_SYMBOL_GPL(blkdev_copy_offload);
+
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)
@@ -1042,6 +1042,10 @@ 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);
+ssize_t blkdev_copy_offload(struct block_device *bdev, loff_t pos_in,
+ loff_t pos_out, size_t len,
+ void (*endio)(void *, int, ssize_t),
+ void *private, 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 */