virtio: move allocation to virtqueue_pop/vring_pop

The return code of virtqueue_pop/vring_pop is unused except to check for
errors or 0.  We can thus easily move allocation inside the functions
and just return a pointer to the VirtQueueElement.

The advantage is that we will be able to allocate only the space that
is needed for the actual size of the s/g list instead of the full
VIRTQUEUE_MAX_SIZE items.  Currently VirtQueueElement takes about 48K
of memory, and this kind of allocation puts a lot of stress on malloc.
By cutting the size by two or three orders of magnitude, malloc can
use much more efficient algorithms.

The patch is pretty large, but changes to each device are testable
more or less independently.  Splitting it would mostly add churn.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>

2 files changed, 17 insertions, 16 deletions

diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c
index c77b3a1058..8340326a50 100644
--- a/hw/scsi/virtio-scsi-dataplane.c
+++ b/hw/scsi/virtio-scsi-dataplane.c
@@ -81,15 +81,16 @@ fail_vring:
 VirtIOSCSIReq *virtio_scsi_pop_req_vring(VirtIOSCSI *s,
                                          VirtIOSCSIVring *vring)
 {
-    VirtIOSCSIReq *req = virtio_scsi_init_req(s, NULL);
-    int r;
+    VirtIOSCSICommon *vs = (VirtIOSCSICommon *)s;
+    VirtIOSCSIReq *req;
 
-    req->vring = vring;
-    r = vring_pop((VirtIODevice *)s, &vring->vring, &req->elem);
-    if (r < 0) {
-        virtio_scsi_free_req(req);
-        req = NULL;
+    req = vring_pop((VirtIODevice *)s, &vring->vring,
+                    sizeof(VirtIOSCSIReq) + vs->cdb_size);
+    if (!req) {
+        return NULL;
     }
+    virtio_scsi_init_req(s, NULL, req);
+    req->vring = vring;
     return req;
 }
 
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 7fdf6ade98..50a3cb28b5 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -41,19 +41,15 @@ static inline SCSIDevice *virtio_scsi_device_find(VirtIOSCSI *s, uint8_t *lun)
     return scsi_device_find(&s->bus, 0, lun[1], virtio_scsi_get_lun(lun));
 }
 
-VirtIOSCSIReq *virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq)
+void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req)
 {
-    VirtIOSCSIReq *req;
-    VirtIOSCSICommon *vs = (VirtIOSCSICommon *)s;
     const size_t zero_skip = offsetof(VirtIOSCSIReq, vring);
 
-    req = g_malloc(sizeof(*req) + vs->cdb_size);
     req->vq = vq;
     req->dev = s;
     qemu_sglist_init(&req->qsgl, DEVICE(s), 8, &address_space_memory);
     qemu_iovec_init(&req->resp_iov, 1);
     memset((uint8_t *)req + zero_skip, 0, sizeof(*req) - zero_skip);
-    return req;
 }
 
 void virtio_scsi_free_req(VirtIOSCSIReq *req)
@@ -174,11 +170,14 @@ static int virtio_scsi_parse_req(VirtIOSCSIReq *req,
 
 static VirtIOSCSIReq *virtio_scsi_pop_req(VirtIOSCSI *s, VirtQueue *vq)
 {
-    VirtIOSCSIReq *req = virtio_scsi_init_req(s, vq);
-    if (!virtqueue_pop(vq, &req->elem)) {
-        virtio_scsi_free_req(req);
+    VirtIOSCSICommon *vs = (VirtIOSCSICommon *)s;
+    VirtIOSCSIReq *req;
+
+    req = virtqueue_pop(vq, sizeof(VirtIOSCSIReq) + vs->cdb_size);
+    if (!req) {
         return NULL;
     }
+    virtio_scsi_init_req(s, vq, req);
     return req;
 }
 
@@ -203,8 +202,9 @@ static void *virtio_scsi_load_request(QEMUFile *f, SCSIRequest *sreq)
 
     qemu_get_be32s(f, &n);
     assert(n < vs->conf.num_queues);
-    req = virtio_scsi_init_req(s, vs->cmd_vqs[n]);
+    req = g_malloc(sizeof(VirtIOSCSIReq) + vs->cdb_size);
     qemu_get_buffer(f, (unsigned char *)&req->elem, sizeof(req->elem));
+    virtio_scsi_init_req(s, vs->cmd_vqs[n], req);
 
     virtqueue_map(&req->elem);