[Qemu-devel] [PATCH RFC 1/2] virtio-blk: add DISCARD and WRITE ZEROES features

[Stefano Garzarella <sgarzare@redhat.com>]

This patch adds the support of DISCARD and WRITE ZEROES commands,
that have been introduced in the virtio-blk protocol to have
better performance when using SSD backend.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
 hw/block/virtio-blk.c | 79 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index f208c6ddb9..8850957751 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -145,6 +145,25 @@ out:
     aio_context_release(blk_get_aio_context(s->conf.conf.blk));
 }
 
+static void virtio_blk_discard_wzeroes_complete(void *opaque, int ret)
+{
+    VirtIOBlockReq *req = opaque;
+    VirtIOBlock *s = req->dev;
+
+    aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
+    if (ret) {
+        if (virtio_blk_handle_rw_error(req, -ret, 0)) {
+            goto out;
+        }
+    }
+
+    virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
+    virtio_blk_free_request(req);
+
+out:
+    aio_context_release(blk_get_aio_context(s->conf.conf.blk));
+}
+
 #ifdef __linux__
 
 typedef struct {
@@ -584,6 +603,56 @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         virtio_blk_free_request(req);
         break;
     }
+    /*
+     * VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with
+     * VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement,
+     * so we must mask it for these requests, then we will check the type.
+     */
+    case VIRTIO_BLK_T_DISCARD & ~VIRTIO_BLK_T_OUT:
+    case VIRTIO_BLK_T_WRITE_ZEROES & ~VIRTIO_BLK_T_OUT:
+    {
+        struct virtio_blk_discard_write_zeroes dwz_hdr;
+        uint64_t sector;
+        int bytes;
+
+        if (unlikely(iov_to_buf(out_iov, out_num, 0, &dwz_hdr,
+                                sizeof(dwz_hdr)) != sizeof(dwz_hdr))) {
+            virtio_error(vdev, "virtio-blk discard/wzeroes header too short");
+            return -1;
+        }
+
+        sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &dwz_hdr.sector);
+        bytes = virtio_ldl_p(VIRTIO_DEVICE(req->dev),
+                             &dwz_hdr.num_sectors) << BDRV_SECTOR_BITS;
+
+        if (!virtio_blk_sect_range_ok(req->dev, sector, bytes)) {
+            virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+            virtio_blk_free_request(req);
+            return 0;
+        }
+
+        if ((type & ~(VIRTIO_BLK_T_BARRIER)) == VIRTIO_BLK_T_DISCARD) {
+            blk_aio_pdiscard(req->dev->blk, sector << BDRV_SECTOR_BITS, bytes,
+                             virtio_blk_discard_wzeroes_complete, req);
+        } else if ((type & ~(VIRTIO_BLK_T_BARRIER)) ==
+                   VIRTIO_BLK_T_WRITE_ZEROES) {
+            int flags = 0;
+
+            if (virtio_ldl_p(VIRTIO_DEVICE(req->dev), &dwz_hdr.flags) &
+                VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
+                flags |= BDRV_REQ_MAY_UNMAP;
+            }
+
+            blk_aio_pwrite_zeroes(req->dev->blk, sector << BDRV_SECTOR_BITS,
+                                  bytes, flags,
+                                  virtio_blk_discard_wzeroes_complete, req);
+        } else { /* Unsupported if VIRTIO_BLK_T_OUT is not set */
+            virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
+            virtio_blk_free_request(req);
+        }
+
+        break;
+    }
     default:
         virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
         virtio_blk_free_request(req);
@@ -763,6 +832,14 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
     blkcfg.alignment_offset = 0;
     blkcfg.wce = blk_enable_write_cache(s->blk);
     virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues);
+    virtio_stl_p(vdev, &blkcfg.max_discard_sectors, BDRV_REQUEST_MAX_SECTORS);
+    virtio_stl_p(vdev, &blkcfg.max_discard_seg, 1);
+    virtio_stl_p(vdev, &blkcfg.discard_sector_alignment,
+                 blk_size >> BDRV_SECTOR_BITS);
+    virtio_stl_p(vdev, &blkcfg.max_write_zeroes_sectors,
+                 BDRV_REQUEST_MAX_SECTORS);
+    virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1);
+    blkcfg.write_zeroes_may_unmap = 1;
     memcpy(config, &blkcfg, sizeof(struct virtio_blk_config));
 }
 
@@ -787,6 +864,8 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
     virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
     virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
     virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
+    virtio_add_feature(&features, VIRTIO_BLK_F_DISCARD);
+    virtio_add_feature(&features, VIRTIO_BLK_F_WRITE_ZEROES);
     if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
         if (s->conf.scsi) {
             error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
-- 
2.20.1