[RFC PATCH v5 4/4] dm kcopyd: add simple copy offload support

[SelvaKumar S <selvakuma.s1@samsung.com>]

Introduce copy_jobs to use copy-offload if it is natively
supported (by underlying device) or else fall back to original method.

run_copy_jobs() calls block layer copy offload api with
BLKDEV_COPY_NOEMULATION. On successful completion, if only one destination
device was present, then jobs is queued for completion. If multiple
destinations were present, the completed destination is zeroed and
pushed to pages_jobs to process copy offload for other destinations. In
case of copy_offload failure, remaining destinations are processed via
regular copying mechanism.

Signed-off-by: SelvaKumar S <selvakuma.s1@samsung.com>
---
 drivers/md/dm-kcopyd.c | 49 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 43 insertions(+), 6 deletions(-)

diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 1bbe4a34ef4c..2442c4870e97 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -74,18 +74,20 @@ struct dm_kcopyd_client {
 	atomic_t nr_jobs;
 
 /*
- * We maintain four lists of jobs:
+ * We maintain five lists of jobs:
  *
- * i)   jobs waiting for pages
- * ii)  jobs that have pages, and are waiting for the io to be issued.
- * iii) jobs that don't need to do any IO and just run a callback
- * iv) jobs that have completed.
+ * i)	jobs waiting to try copy offload
+ * ii)   jobs waiting for pages
+ * iii)  jobs that have pages, and are waiting for the io to be issued.
+ * iv) jobs that don't need to do any IO and just run a callback
+ * v) jobs that have completed.
  *
- * All four of these are protected by job_lock.
+ * All five of these are protected by job_lock.
  */
 	spinlock_t job_lock;
 	struct list_head callback_jobs;
 	struct list_head complete_jobs;
+	struct list_head copy_jobs;
 	struct list_head io_jobs;
 	struct list_head pages_jobs;
 };
@@ -581,6 +583,36 @@ static int run_io_job(struct kcopyd_job *job)
 	return r;
 }
 
+static int run_copy_job(struct kcopyd_job *job)
+{
+	int r, i, count = 0;
+	unsigned long flags = 0;
+	struct range_entry srange;
+
+	flags |= BLKDEV_COPY_NOEMULATION;
+	for (i = 0; i < job->num_dests; i++) {
+		srange.src = job->source.sector;
+		srange.len = job->source.count;
+
+		r = blkdev_issue_copy(job->source.bdev, 1, &srange,
+			job->dests[i].bdev, job->dests[i].sector, GFP_KERNEL, flags);
+		if (r)
+			break;
+
+		job->dests[i].count = 0;
+		count++;
+	}
+
+	if (count == job->num_dests) {
+		push(&job->kc->complete_jobs, job);
+	} else {
+		push(&job->kc->pages_jobs, job);
+		r = 0;
+	}
+
+	return r;
+}
+
 static int run_pages_job(struct kcopyd_job *job)
 {
 	int r;
@@ -662,6 +694,7 @@ static void do_work(struct work_struct *work)
 	spin_unlock_irqrestore(&kc->job_lock, flags);
 
 	blk_start_plug(&plug);
+	process_jobs(&kc->copy_jobs, kc, run_copy_job);
 	process_jobs(&kc->complete_jobs, kc, run_complete_job);
 	process_jobs(&kc->pages_jobs, kc, run_pages_job);
 	process_jobs(&kc->io_jobs, kc, run_io_job);
@@ -679,6 +712,8 @@ static void dispatch_job(struct kcopyd_job *job)
 	atomic_inc(&kc->nr_jobs);
 	if (unlikely(!job->source.count))
 		push(&kc->callback_jobs, job);
+	else if (job->source.bdev->bd_disk == job->dests[0].bdev->bd_disk)
+		push(&kc->copy_jobs, job);
 	else if (job->pages == &zero_page_list)
 		push(&kc->io_jobs, job);
 	else
@@ -919,6 +954,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
 	spin_lock_init(&kc->job_lock);
 	INIT_LIST_HEAD(&kc->callback_jobs);
 	INIT_LIST_HEAD(&kc->complete_jobs);
+	INIT_LIST_HEAD(&kc->copy_jobs);
 	INIT_LIST_HEAD(&kc->io_jobs);
 	INIT_LIST_HEAD(&kc->pages_jobs);
 	kc->throttle = throttle;
@@ -974,6 +1010,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc)
 
 	BUG_ON(!list_empty(&kc->callback_jobs));
 	BUG_ON(!list_empty(&kc->complete_jobs));
+	BUG_ON(!list_empty(&kc->copy_jobs));
 	BUG_ON(!list_empty(&kc->io_jobs));
 	BUG_ON(!list_empty(&kc->pages_jobs));
 	destroy_workqueue(kc->kcopyd_wq);
-- 
2.25.1