diff options
| author | Peter Xu <peterx@redhat.com> | 2018-04-27 17:07:24 +0800 |
|---|---|---|
| committer | Michael S. Tsirkin <mst@redhat.com> | 2018-05-23 03:14:41 +0300 |
| commit | ffcbbe722fcb3c162318cba1b94a115498e25acd (patch) | |
| tree | 39d0dd6539a56592896ceebd38741e26c9721dfc /hw/virtio/vhost.c | |
| parent | b7b126442977dcfa5641e38b084bd13a0b366cff (diff) | |
vhost: add trace for IOTLB miss
Add some trace points for IOTLB translation for vhost. After vhost-user
is setup, the only IO path that QEMU will participate should be the
IOMMU translation, so it'll be good we can track this with explicit
timestamps when needed to see how long time we take to do the
translation, and whether there's anything stuck inside. It might be
useful for triaging vhost-user problems.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Diffstat (limited to 'hw/virtio/vhost.c')
| -rw-r--r-- | hw/virtio/vhost.c | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 9d5850a7d7..b08290036d 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -894,12 +894,15 @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write) rcu_read_lock(); + trace_vhost_iotlb_miss(dev, 1); + iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as, iova, write); if (iotlb.target_as != NULL) { ret = vhost_memory_region_lookup(dev, iotlb.translated_addr, &uaddr, &len); if (ret) { + trace_vhost_iotlb_miss(dev, 3); error_report("Fail to lookup the translated address " "%"PRIx64, iotlb.translated_addr); goto out; @@ -911,10 +914,14 @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write) ret = vhost_backend_update_device_iotlb(dev, iova, uaddr, len, iotlb.perm); if (ret) { + trace_vhost_iotlb_miss(dev, 4); error_report("Fail to update device iotlb"); goto out; } } + + trace_vhost_iotlb_miss(dev, 2); + out: rcu_read_unlock(); |