search for: vhost_get_vring_used_base

...nter at bit 31, the check (s.num > 0xffff) won't be able to catch the illegal index 0x8000~0xffff for packed ring. > + vq->last_used_idx = s.num; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > + vq->last_used_wrap_counter = wrap_counter; > + break; > + case VHOST_GET_VRING_USED_BASE: Do we need the new VHOST_GET_VRING_USED_BASE and VHOST_SET_VRING_USED_BASE ops? We are going to merge below series in DPDK: http://patches.dpdk.org/patch/45874/ We may need to reach an agreement first. > + s.index = idx; > + s.num = vq->last_used_idx; > + if (vhost_has_feature...

...nter at bit 31, the check (s.num > 0xffff) won't be able to catch the illegal index 0x8000~0xffff for packed ring. > + vq->last_used_idx = s.num; > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > + vq->last_used_wrap_counter = wrap_counter; > + break; > + case VHOST_GET_VRING_USED_BASE: Do we need the new VHOST_GET_VRING_USED_BASE and VHOST_SET_VRING_USED_BASE ops? We are going to merge below series in DPDK: http://patches.dpdk.org/patch/45874/ We may need to reach an agreement first. > + s.index = idx; > + s.num = vq->last_used_idx; > + if (vhost_has_feature...

...xffff for >> packed ring. >> Do we need to clarify this in the spec? >>> + vq->last_used_idx = s.num; >>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) >>> + vq->last_used_wrap_counter = wrap_counter; >>> + break; >>> + case VHOST_GET_VRING_USED_BASE: >> Do we need the new VHOST_GET_VRING_USED_BASE and >> VHOST_SET_VRING_USED_BASE ops? >> >> We are going to merge below series in DPDK: >> >> http://patches.dpdk.org/patch/45874/ >> >> We may need to reach an agreement first. If we agree that 64K vi...

...xffff for >> packed ring. >> Do we need to clarify this in the spec? >>> + vq->last_used_idx = s.num; >>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) >>> + vq->last_used_wrap_counter = wrap_counter; >>> + break; >>> + case VHOST_GET_VRING_USED_BASE: >> Do we need the new VHOST_GET_VRING_USED_BASE and >> VHOST_SET_VRING_USED_BASE ops? >> >> We are going to merge below series in DPDK: >> >> http://patches.dpdk.org/patch/45874/ >> >> We may need to reach an agreement first. If we agree that 64K vi...

...ant the illegal index 0x8000-0xffff. > >>>>> + vq->last_used_idx = s.num; >>>>> + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) >>>>> + vq->last_used_wrap_counter = wrap_counter; >>>>> + break; >>>>> + case VHOST_GET_VRING_USED_BASE: >>>> Do we need the new VHOST_GET_VRING_USED_BASE and >>>> VHOST_SET_VRING_USED_BASE ops? >>>> >>>> We are going to merge below series in DPDK: >>>> >>>> http://patches.dpdk.org/patch/45874/ >>>> >>>> W...

...ffff) > won't be able to catch the illegal index 0x8000~0xffff for > packed ring. > > > + vq->last_used_idx = s.num; > > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > > + vq->last_used_wrap_counter = wrap_counter; > > + break; > > + case VHOST_GET_VRING_USED_BASE: > > Do we need the new VHOST_GET_VRING_USED_BASE and > VHOST_SET_VRING_USED_BASE ops? > > We are going to merge below series in DPDK: > > http://patches.dpdk.org/patch/45874/ > > We may need to reach an agreement first. > > > > + s.index = idx; > &g...

...pec? Isn't this all internal vhost stuff? > > > > + vq->last_used_idx = s.num; > > > > + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) > > > > + vq->last_used_wrap_counter = wrap_counter; > > > > + break; > > > > + case VHOST_GET_VRING_USED_BASE: > > > Do we need the new VHOST_GET_VRING_USED_BASE and > > > VHOST_SET_VRING_USED_BASE ops? > > > > > > We are going to merge below series in DPDK: > > > > > > http://patches.dpdk.org/patch/45874/ > > > > > > We may need to...

...CKED)) { + wrap_counter = s.num >> 31; + s.num &= ~(1 << 31); + } + if (s.num > 0xffff) { + r = -EINVAL; + break; + } + vq->last_used_idx = s.num; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + vq->last_used_wrap_counter = wrap_counter; + break; + case VHOST_GET_VRING_USED_BASE: + s.index = idx; + s.num = vq->last_used_idx; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + s.num |= vq->last_used_wrap_counter << 31; if (copy_to_user(argp, &s, sizeof s)) r = -EFAULT; break; @@ -1734,6 +1802,9 @@ int vhost_vq_init_access(struct vhost_virtque...

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 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