[PATCH v5 12/12] virtio-blk: use BDRV_REQ_REGISTERED_BUF optimization hint

[Stefan Hajnoczi <stefanha@redhat.com>]

Register guest RAM using BlockRAMRegistrar and set the
BDRV_REQ_REGISTERED_BUF flag so block drivers can optimize memory
accesses in I/O requests.

This is for vdpa-blk, vhost-user-blk, and other I/O interfaces that rely
on DMA mapping/unmapping.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/hw/virtio/virtio-blk.h |  2 ++
 hw/block/virtio-blk.c          | 39 ++++++++++++++++++++++------------
 2 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index d311c57cca..7f589b4146 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -19,6 +19,7 @@
 #include "hw/block/block.h"
 #include "sysemu/iothread.h"
 #include "sysemu/block-backend.h"
+#include "sysemu/block-ram-registrar.h"
 #include "qom/object.h"
 
 #define TYPE_VIRTIO_BLK "virtio-blk-device"
@@ -64,6 +65,7 @@ struct VirtIOBlock {
     struct VirtIOBlockDataPlane *dataplane;
     uint64_t host_features;
     size_t config_size;
+    BlockRAMRegistrar blk_ram_registrar;
 };
 
 typedef struct VirtIOBlockReq {
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index e9ba752f6b..907f012c45 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -21,6 +21,7 @@
 #include "hw/block/block.h"
 #include "hw/qdev-properties.h"
 #include "sysemu/blockdev.h"
+#include "sysemu/block-ram-registrar.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/runstate.h"
 #include "hw/virtio/virtio-blk.h"
@@ -384,12 +385,14 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
     }
 }
 
-static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
+static inline void submit_requests(VirtIOBlock *s, MultiReqBuffer *mrb,
                                    int start, int num_reqs, int niov)
 {
+    BlockBackend *blk = s->blk;
     QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
     int64_t sector_num = mrb->reqs[start]->sector_num;
     bool is_write = mrb->is_write;
+    BdrvRequestFlags flags = 0;
 
     if (num_reqs > 1) {
         int i;
@@ -420,12 +423,18 @@ static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
                               num_reqs - 1);
     }
 
+    if (blk_ram_registrar_ok(&s->blk_ram_registrar)) {
+        flags |= BDRV_REQ_REGISTERED_BUF;
+    }
+
     if (is_write) {
-        blk_aio_pwritev(blk, sector_num << BDRV_SECTOR_BITS, qiov, 0,
-                        virtio_blk_rw_complete, mrb->reqs[start]);
+        blk_aio_pwritev(blk, sector_num << BDRV_SECTOR_BITS, qiov,
+                        flags, virtio_blk_rw_complete,
+                        mrb->reqs[start]);
     } else {
-        blk_aio_preadv(blk, sector_num << BDRV_SECTOR_BITS, qiov, 0,
-                       virtio_blk_rw_complete, mrb->reqs[start]);
+        blk_aio_preadv(blk, sector_num << BDRV_SECTOR_BITS, qiov,
+                       flags, virtio_blk_rw_complete,
+                       mrb->reqs[start]);
     }
 }
 
@@ -447,14 +456,14 @@ static int multireq_compare(const void *a, const void *b)
     }
 }
 
-static void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
+static void virtio_blk_submit_multireq(VirtIOBlock *s, MultiReqBuffer *mrb)
 {
     int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
     uint32_t max_transfer;
     int64_t sector_num = 0;
 
     if (mrb->num_reqs == 1) {
-        submit_requests(blk, mrb, 0, 1, -1);
+        submit_requests(s, mrb, 0, 1, -1);
         mrb->num_reqs = 0;
         return;
     }
@@ -474,11 +483,11 @@ static void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
              * 3. merge would exceed maximum transfer length of backend device
              */
             if (sector_num + nb_sectors != req->sector_num ||
-                niov > blk_get_max_iov(blk) - req->qiov.niov ||
+                niov > blk_get_max_iov(s->blk) - req->qiov.niov ||
                 req->qiov.size > max_transfer ||
                 nb_sectors > (max_transfer -
                               req->qiov.size) / BDRV_SECTOR_SIZE) {
-                submit_requests(blk, mrb, start, num_reqs, niov);
+                submit_requests(s, mrb, start, num_reqs, niov);
                 num_reqs = 0;
             }
         }
@@ -494,7 +503,7 @@ static void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
         num_reqs++;
     }
 
-    submit_requests(blk, mrb, start, num_reqs, niov);
+    submit_requests(s, mrb, start, num_reqs, niov);
     mrb->num_reqs = 0;
 }
 
@@ -509,7 +518,7 @@ static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
      * Make sure all outstanding writes are posted to the backing device.
      */
     if (mrb->is_write && mrb->num_reqs > 0) {
-        virtio_blk_submit_multireq(s->blk, mrb);
+        virtio_blk_submit_multireq(s, mrb);
     }
     blk_aio_flush(s->blk, virtio_blk_flush_complete, req);
 }
@@ -689,7 +698,7 @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
                                   is_write != mrb->is_write ||
                                   !s->conf.request_merging)) {
-            virtio_blk_submit_multireq(s->blk, mrb);
+            virtio_blk_submit_multireq(s, mrb);
         }
 
         assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
@@ -796,7 +805,7 @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
     } while (!virtio_queue_empty(vq));
 
     if (mrb.num_reqs) {
-        virtio_blk_submit_multireq(s->blk, &mrb);
+        virtio_blk_submit_multireq(s, &mrb);
     }
 
     blk_io_unplug(s->blk);
@@ -845,7 +854,7 @@ void virtio_blk_process_queued_requests(VirtIOBlock *s, bool is_bh)
     }
 
     if (mrb.num_reqs) {
-        virtio_blk_submit_multireq(s->blk, &mrb);
+        virtio_blk_submit_multireq(s, &mrb);
     }
     if (is_bh) {
         blk_dec_in_flight(s->conf.conf.blk);
@@ -1227,6 +1236,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     }
 
     s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
+    blk_ram_registrar_init(&s->blk_ram_registrar, s->blk);
     blk_set_dev_ops(s->blk, &virtio_block_ops, s);
 
     blk_iostatus_enable(s->blk);
@@ -1252,6 +1262,7 @@ static void virtio_blk_device_unrealize(DeviceState *dev)
         virtio_del_queue(vdev, i);
     }
     qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
+    blk_ram_registrar_destroy(&s->blk_ram_registrar);
     qemu_del_vm_change_state_handler(s->change);
     blockdev_mark_auto_del(s->blk);
     virtio_cleanup(vdev);
-- 
2.37.3