search for: last_avail_wrap_counter

...397,48 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg > vq->last_avail_idx = s.num; > /* Forget the cached index value. */ > vq->avail_idx = vq->last_avail_idx; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { > + vq->last_avail_wrap_counter = wrap_counter; > + vq->avail_wrap_counter = vq->last_avail_wrap_counter; > + } > break; > case VHOST_GET_VRING_BASE: > s.index = idx; > s.num = vq->last_avail_idx; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > + s.num |= vq->last_avail_...

...397,48 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg > vq->last_avail_idx = s.num; > /* Forget the cached index value. */ > vq->avail_idx = vq->last_avail_idx; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { > + vq->last_avail_wrap_counter = wrap_counter; > + vq->avail_wrap_counter = vq->last_avail_wrap_counter; > + } > break; > case VHOST_GET_VRING_BASE: > s.index = idx; > s.num = vq->last_avail_idx; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > + s.num |= vq->last_avail_...

...st_dev *d, unsigned int ioctl, void __user *arg >>> vq->last_avail_idx = s.num; >>> /* Forget the cached index value. */ >>> vq->avail_idx = vq->last_avail_idx; >>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { >>> + vq->last_avail_wrap_counter = wrap_counter; >>> + vq->avail_wrap_counter = vq->last_avail_wrap_counter; >>> + } >>> break; >>> case VHOST_GET_VRING_BASE: >>> s.index = idx; >>> s.num = vq->last_avail_idx; >>> + if (vhost_has_feature(vq,...

...st_dev *d, unsigned int ioctl, void __user *arg >>> vq->last_avail_idx = s.num; >>> /* Forget the cached index value. */ >>> vq->avail_idx = vq->last_avail_idx; >>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { >>> + vq->last_avail_wrap_counter = wrap_counter; >>> + vq->avail_wrap_counter = vq->last_avail_wrap_counter; >>> + } >>> break; >>> case VHOST_GET_VRING_BASE: >>> s.index = idx; >>> s.num = vq->last_avail_idx; >>> + if (vhost_has_feature(vq,...

...*arg >>>>> vq->last_avail_idx = s.num; >>>>> /* Forget the cached index value. */ >>>>> vq->avail_idx = vq->last_avail_idx; >>>>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { >>>>> + vq->last_avail_wrap_counter = wrap_counter; >>>>> + vq->avail_wrap_counter = vq->last_avail_wrap_counter; >>>>> + } >>>>> break; >>>>> case VHOST_GET_VRING_BASE: >>>>> s.index = idx; >>>>> s.num = vq->last_...

...g_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg > > vq->last_avail_idx = s.num; > > /* Forget the cached index value. */ > > vq->avail_idx = vq->last_avail_idx; > > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { > > + vq->last_avail_wrap_counter = wrap_counter; > > + vq->avail_wrap_counter = vq->last_avail_wrap_counter; > > + } > > break; > > case VHOST_GET_VRING_BASE: > > s.index = idx; > > s.num = vq->last_avail_idx; > > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) &...

...__user *arg > > > > vq->last_avail_idx = s.num; > > > > /* Forget the cached index value. */ > > > > vq->avail_idx = vq->last_avail_idx; > > > > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { > > > > + vq->last_avail_wrap_counter = wrap_counter; > > > > + vq->avail_wrap_counter = vq->last_avail_wrap_counter; > > > > + } > > > > break; > > > > case VHOST_GET_VRING_BASE: > > > > s.index = idx; > > > > s.num = vq->last_avail_idx;...

...st.c index 060a431..63b79e8 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -323,6 +323,9 @@ static void vhost_vq_reset(struct vhost_dev *dev, vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); vq->busyloop_timeout = 0; + vq->last_used_wrap_counter = true; + vq->last_avail_wrap_counter = true; + vq->avail_wrap_counter = true; vq->umem = NULL; vq->iotlb = NULL; __vhost_vq_meta_reset(vq); @@ -1106,11 +1109,22 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) return 0; } -static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned...

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's guest driver series at https://patchwork.ozlabs.org/cover/942297/ Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's guest driver series at https://patchwork.ozlabs.org/cover/942297/ Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V5 at https://lkml.org/lkml/2018/5/22/138. Some fixups and tweaks were needed on top of Tiwei's code to make it run for event index. Pktgen reports about 20% improvement on TX PPS when doing pktgen from guest to host. No ovbious improvement on RX PPS. We can do lots of optimizations on top but for simple

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's RFC V6 at https://lkml.org/lkml/2018/6/5/120. Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test virtio-net pmd as well when

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's RFC V6 at https://lkml.org/lkml/2018/6/5/120. Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test virtio-net pmd as well when

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be