search for: desc_pack

...struct vring_avail __user *avail, - struct vring_used __user *used) +static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + + /* FIXME: check device area and driver area */ + return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) && + access_ok(VERIFY_WRITE, packed, num * sizeof(*packed)); +} + +static int vq_access_ok_split(struct vhost_virtqueue *vq,...

Hi all: This RFC implement a subset of packed ring which was described at https://github.com/oasis-tcs/virtio-docs/blob/master/virtio-v1.1-packed-wd07.pdf . The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost

Hi all: This RFC implement a subset of packed ring which was described at https://github.com/oasis-tcs/virtio-docs/blob/master/virtio-v1.1-packed-wd07.pdf . The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost

...s/vhost/vhost.c > index a36e5ad2..112f680 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -1112,10 +1112,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, > struct vring_used __user *used) > { > struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; > + struct vring_packed_desc_event *driver_event = > + (struct vring_packed_desc_event *)avail; > + struct vring_packed_desc_event *device_event = > + (struct vring_packed_desc_event *)used; > > - /* FIXME: check device area and dr...

...s/vhost/vhost.c > index a36e5ad2..112f680 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -1112,10 +1112,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, > struct vring_used __user *used) > { > struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; > + struct vring_packed_desc_event *driver_event = > + (struct vring_packed_desc_event *)avail; > + struct vring_packed_desc_event *device_event = > + (struct vring_packed_desc_event *)used; > > - /* FIXME: check device area and dr...

...struct vring_avail __user *avail, - struct vring_used __user *used) +static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used) +{ + struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + + /* FIXME: check device area and driver area */ + return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) && + access_ok(VERIFY_WRITE, packed, num * sizeof(*packed)); +} +static int vq_access_ok_split(struct vhost_virtqueue *vq,...

...struct vring_desc *desc) return next; } -static int get_indirect(struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num, - struct vring_desc *indirect) +static unsigned next_desc_packed(struct vhost_virtqueue *vq, + struct vring_packed_desc *desc) +{ + return desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT); +} + +static int get_indirect_split(struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned...

...git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 0f3f07c..cccbc82 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1115,10 +1115,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, struct vring_used __user *used) { struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + struct vring_packed_desc_event *driver_event = + (struct vring_packed_desc_event *)avail; + struct vring_packed_desc_event *device_event = + (struct vring_packed_desc_event *)used; - /* TODO: check device area and driver area */ return access_ok...

...it a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a36e5ad2..112f680 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1112,10 +1112,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, struct vring_used __user *used) { struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; + struct vring_packed_desc_event *driver_event = + (struct vring_packed_desc_event *)avail; + struct vring_packed_desc_event *device_event = + (struct vring_packed_desc_event *)used; - /* FIXME: check device area and driver area */ return access_o...

...t(struct vhost_dev *dev, > diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h > index 8a9df4f..02d7a36 100644 > --- a/drivers/vhost/vhost.h > +++ b/drivers/vhost/vhost.h > @@ -96,8 +96,14 @@ struct vhost_virtqueue { > struct vring_desc __user *desc; > struct vring_desc_packed __user *desc_packed; Do you think it'd be better to name the desc type as struct vring_packed_desc? And it will be consistent with other names, like: struct vring_packed; struct vring_packed_desc_event; > }; > - struct vring_avail __user *avail; > - struct vring_used __user *use...

...uest, using eventfd. */ >> void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) >> { >> @@ -2802,10 +2930,34 @@ static bool vhost_enable_notify_packed(struct vhost_dev *dev, >> struct vhost_virtqueue *vq) >> { >> struct vring_desc_packed *d = vq->desc_packed + vq->avail_idx; >> - __virtio16 flags; >> + __virtio16 flags = RING_EVENT_FLAGS_ENABLE; >> int ret; >> >> - /* FIXME: disable notification through device area */ >> + if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY)) >&...

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

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

...rs/vhost/vhost.c > index 0f3f07c..cccbc82 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -1115,10 +1115,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, > struct vring_used __user *used) > { > struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; > + struct vring_packed_desc_event *driver_event = > + (struct vring_packed_desc_event *)avail; > + struct vring_packed_desc_event *device_event = > + (struct vring_packed_desc_event *)used; > > - /* TODO: check device area and dri...

...rs/vhost/vhost.c > index 0f3f07c..cccbc82 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -1115,10 +1115,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num, > struct vring_used __user *used) > { > struct vring_desc_packed *packed = (struct vring_desc_packed *)desc; > + struct vring_packed_desc_event *driver_event = > + (struct vring_packed_desc_event *)avail; > + struct vring_packed_desc_event *device_event = > + (struct vring_packed_desc_event *)used; > > - /* TODO: check device area and dri...

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 RFC implement packed ring layout. The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost and guest. Testpmd (rxonly) in guest reports 2.4Mpps. Testpmd (txonly) repots about 2.1Mpps. Notes: The event

Hi all: This RFC implement packed ring layout. The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost and guest. Testpmd (rxonly) in guest reports 2.4Mpps. Testpmd (txonly) repots about 2.1Mpps. Notes: The event