virtio_blk: add discard and write zeroes support

In commit 88c85538, "virtio-blk: add discard and write zeroes features
to specification" (https://github.com/oasis-tcs/virtio-spec), the virtio
block specification has been extended to add VIRTIO_BLK_T_DISCARD and
VIRTIO_BLK_T_WRITE_ZEROES commands.  This patch enables support for
discard and write zeroes in the virtio-blk driver when the device
advertises the corresponding features, VIRTIO_BLK_F_DISCARD and
VIRTIO_BLK_F_WRITE_ZEROES.

Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Signed-off-by: Daniel Verkamp <dverkamp@chromium.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 81 insertions, 2 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 086c6bb12baa..0f39efb4b3aa 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -18,6 +18,7 @@
 
 #define PART_BITS 4
 #define VQ_NAME_LEN 16
+#define MAX_DISCARD_SEGMENTS 256u
 
 static int major;
 static DEFINE_IDA(vd_index_ida);
@@ -172,10 +173,48 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
+static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+	unsigned short n = 0;
+	struct virtio_blk_discard_write_zeroes *range;
+	struct bio *bio;
+	u32 flags = 0;
+
+	if (unmap)
+		flags |= VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP;
+
+	range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
+	if (!range)
+		return -ENOMEM;
+
+	__rq_for_each_bio(bio, req) {
+		u64 sector = bio->bi_iter.bi_sector;
+		u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+
+		range[n].flags = cpu_to_le32(flags);
+		range[n].num_sectors = cpu_to_le32(num_sectors);
+		range[n].sector = cpu_to_le64(sector);
+		n++;
+	}
+
+	req->special_vec.bv_page = virt_to_page(range);
+	req->special_vec.bv_offset = offset_in_page(range);
+	req->special_vec.bv_len = sizeof(*range) * segments;
+	req->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+	return 0;
+}
+
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		kfree(page_address(req->special_vec.bv_page) +
+		      req->special_vec.bv_offset);
+	}
+
 	switch (req_op(req)) {
 	case REQ_OP_SCSI_IN:
 	case REQ_OP_SCSI_OUT:
@@ -225,6 +264,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int qid = hctx->queue_num;
 	int err;
 	bool notify = false;
+	bool unmap = false;
 	u32 type;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
@@ -237,6 +277,13 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	case REQ_OP_FLUSH:
 		type = VIRTIO_BLK_T_FLUSH;
 		break;
+	case REQ_OP_DISCARD:
+		type = VIRTIO_BLK_T_DISCARD;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		type = VIRTIO_BLK_T_WRITE_ZEROES;
+		unmap = !(req->cmd_flags & REQ_NOUNMAP);
+		break;
 	case REQ_OP_SCSI_IN:
 	case REQ_OP_SCSI_OUT:
 		type = VIRTIO_BLK_T_SCSI_CMD;
@@ -256,6 +303,12 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(req);
 
+	if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) {
+		err = virtblk_setup_discard_write_zeroes(req, unmap);
+		if (err)
+			return BLK_STS_RESOURCE;
+	}
+
 	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(req) == WRITE)
@@ -802,6 +855,32 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (!err && opt_io_size)
 		blk_queue_io_opt(q, blk_size * opt_io_size);
 
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
+		q->limits.discard_granularity = blk_size;
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     discard_sector_alignment, &v);
+		q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0;
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_discard_sectors, &v);
+		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);
+
+		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
+			     &v);
+		blk_queue_max_discard_segments(q,
+					       min_not_zero(v,
+							    MAX_DISCARD_SEGMENTS));
+
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_write_zeroes_sectors, &v);
+		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
+	}
+
 	virtblk_update_capacity(vblk, false);
 	virtio_device_ready(vdev);
 
@@ -895,14 +974,14 @@ static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SCSI,
 #endif
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
-	VIRTIO_BLK_F_MQ,
+	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
 }
 ;
 static unsigned int features[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
-	VIRTIO_BLK_F_MQ,
+	VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES,
 };
 
 static struct virtio_driver virtio_blk = {