xen-blkfront: use a different scatterlist for each request

In blkif_queue_request blkfront iterates over the scatterlist in order
to set the segments of the request, and in blkif_completion blkfront
iterates over the raw request, which makes it hard to know the exact
position of the source and destination memory positions.

This can be solved by allocating a scatterlist for each request, that
will be keep until the request is finished, allowing us to copy the
data back to the original memory without having to iterate over the
raw request.

Oracle-Bug: 16660413 - LARGE ASYNCHRONOUS READS APPEAR BROKEN ON 2.6.39-400
CC: [e-mail]
Signed-off-by: Roger Pau Monné <[e-mail]>
Reported-and-Tested-by: Anne Milicia <[e-mail]>
Signed-off-by: Konrad Rzeszutek Wilk <[e-mail]>

drivers/block/xen-blkfront.c

···
 	struct request *request;
 	struct grant **grants_used;
 	struct grant **indirect_grants;
+	struct scatterlist *sg;
 };
 
 struct split_bio {
···
 	enum blkif_state connected;
 	int ring_ref;
 	struct blkif_front_ring ring;
-	struct scatterlist *sg;
 	unsigned int evtchn, irq;
 	struct request_queue *rq;
 	struct work_struct work;
···
 		       req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
 		BUG_ON(info->max_indirect_segments &&
 		       req->nr_phys_segments > info->max_indirect_segments);
-		nseg = blk_rq_map_sg(req->q, req, info->sg);
+		nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
 		ring_req->u.rw.id = id;
 		if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
 			/*
···
 			}
 			ring_req->u.rw.nr_segments = nseg;
 		}
-		for_each_sg(info->sg, sg, nseg, i) {
+		for_each_sg(info->shadow[id].sg, sg, nseg, i) {
 			fsect = sg->offset >> 9;
 			lsect = fsect + (sg->length >> 9) - 1;
 
···
 	}
 	BUG_ON(info->persistent_gnts_c != 0);
 
-	kfree(info->sg);
-	info->sg = NULL;
 	for (i = 0; i < BLK_RING_SIZE; i++) {
 		/*
 		 * Clear persistent grants present in requests already
···
 		info->shadow[i].grants_used = NULL;
 		kfree(info->shadow[i].indirect_grants);
 		info->shadow[i].indirect_grants = NULL;
+		kfree(info->shadow[i].sg);
+		info->shadow[i].sg = NULL;
 	}
 
 	/* No more gnttab callback work. */
···
 			     struct blkif_response *bret)
 {
 	int i = 0;
-	struct bio_vec *bvec;
-	struct req_iterator iter;
-	unsigned long flags;
+	struct scatterlist *sg;
 	char *bvec_data;
 	void *shared_data;
-	unsigned int offset = 0;
 	int nseg;
 
 	nseg = s->req.operation == BLKIF_OP_INDIRECT ?
···
 		 * than PAGE_SIZE, we have to keep track of the current offset,
 		 * to be sure we are copying the data from the right shared page.
 		 */
-		rq_for_each_segment(bvec, s->request, iter) {
-			BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
-			if (bvec->bv_offset < offset)
-				i++;
-			BUG_ON(i >= nseg);
+		for_each_sg(s->sg, sg, nseg, i) {
+			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 			shared_data = kmap_atomic(
 				pfn_to_page(s->grants_used[i]->pfn));
-			bvec_data = bvec_kmap_irq(bvec, &flags);
-			memcpy(bvec_data, shared_data + bvec->bv_offset,
-				bvec->bv_len);
-			bvec_kunmap_irq(bvec_data, &flags);
+			bvec_data = kmap_atomic(sg_page(sg));
+			memcpy(bvec_data   + sg->offset,
+			       shared_data + sg->offset,
+			       sg->length);
+			kunmap_atomic(bvec_data);
 			kunmap_atomic(shared_data);
-			offset = bvec->bv_offset + bvec->bv_len;
 		}
 	}
 	/* Add the persistent grant into the list of free grants */
···
 						  xen_blkif_max_segments);
 		segs = info->max_indirect_segments;
 	}
-	info->sg = kzalloc(sizeof(info->sg[0]) * segs, GFP_KERNEL);
-	if (info->sg == NULL)
-		goto out_of_memory;
-	sg_init_table(info->sg, segs);
 
 	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
 	if (err)
···
 		info->shadow[i].grants_used = kzalloc(
 			sizeof(info->shadow[i].grants_used[0]) * segs,
 			GFP_NOIO);
+		info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
 		if (info->max_indirect_segments)
 			info->shadow[i].indirect_grants = kzalloc(
 				sizeof(info->shadow[i].indirect_grants[0]) *
 				INDIRECT_GREFS(segs),
 				GFP_NOIO);
 		if ((info->shadow[i].grants_used == NULL) ||
+			(info->shadow[i].sg == NULL) ||
 		     (info->max_indirect_segments &&
 		     (info->shadow[i].indirect_grants == NULL)))
 			goto out_of_memory;
+		sg_init_table(info->shadow[i].sg, segs);
 	}
 
 
 	return 0;
 
 out_of_memory:
-	kfree(info->sg);
-	info->sg = NULL;
 	for (i = 0; i < BLK_RING_SIZE; i++) {
 		kfree(info->shadow[i].grants_used);
 		info->shadow[i].grants_used = NULL;
+		kfree(info->shadow[i].sg);
+		info->shadow[i].sg = NULL;
 		kfree(info->shadow[i].indirect_grants);
 		info->shadow[i].indirect_grants = NULL;
 	}