Displaying 20 results from an estimated 23 matches for "last_used_wrap_counter".
2018 Oct 12
2
[PATCH net-next V2 6/8] vhost: packed ring support
...; + }
Do we want to put wrap_counter at bit 15?
If put wrap_counter 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...
2018 Oct 12
2
[PATCH net-next V2 6/8] vhost: packed ring support
...; + }
Do we want to put wrap_counter at bit 15?
If put wrap_counter 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...
2018 Oct 15
2
[PATCH net-next V2 6/8] vhost: packed ring support
...(s.num > 0xffff)
>> won't be able to catch the illegal index 0x8000~0xffff 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...
2018 Oct 15
2
[PATCH net-next V2 6/8] vhost: packed ring support
...(s.num > 0xffff)
>> won't be able to catch the illegal index 0x8000~0xffff 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...
2018 Oct 15
1
[PATCH net-next V2 6/8] vhost: packed ring support
...t;> Do we need to clarify this in the spec?
> Isn't this all internal vhost stuff?
I meant 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:
>&...
2018 Oct 12
0
[PATCH net-next V2 6/8] vhost: packed ring support
...otifications.
> If put wrap_counter 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 ne...
2018 Oct 15
0
[PATCH net-next V2 6/8] vhost: packed ring support
...f for
> > > packed ring.
> > >
>
> Do we need to clarify this in the spec?
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:
> > >...
2018 Jul 16
0
[PATCH net-next V2 6/8] vhost: packed ring support
...rivers/vhost/vhost.c b/drivers/vhost/vhost.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_acces...
2018 Jul 16
3
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...; - more compact math for event idx
>> - fix failure of SET_VRING_BASE when avail_wrap_counter is true
>> - fix not copy avail_wrap_counter during GET_VRING_BASE
>> - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
>> - rename used_wrap_counter to last_used_wrap_counter
>> - rebase to net-next
>>
>> Changes from RFC V4:
>>
>> - fix signalled_used index recording
>> - track avail index correctly
>> - various minor fixes
>>
>> Changes from RFC V3:
>>
>> - Fix math on event idx checking
>> - Sync...
2018 Jul 16
3
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...; - more compact math for event idx
>> - fix failure of SET_VRING_BASE when avail_wrap_counter is true
>> - fix not copy avail_wrap_counter during GET_VRING_BASE
>> - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
>> - rename used_wrap_counter to last_used_wrap_counter
>> - rebase to net-next
>>
>> Changes from RFC V4:
>>
>> - fix signalled_used index recording
>> - track avail index correctly
>> - various minor fixes
>>
>> Changes from RFC V3:
>>
>> - Fix math on event idx checking
>> - Sync...
2018 Jul 16
11
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...iers during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device stru...
2018 Jul 16
11
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...iers during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device stru...
2018 Jul 16
0
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...d_packed_n()
> - more compact math for event idx
> - fix failure of SET_VRING_BASE when avail_wrap_counter is true
> - fix not copy avail_wrap_counter during GET_VRING_BASE
> - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
> - rename used_wrap_counter to last_used_wrap_counter
> - rebase to net-next
>
> Changes from RFC V4:
>
> - fix signalled_used index recording
> - track avail index correctly
> - various minor fixes
>
> Changes from RFC V3:
>
> - Fix math on event idx checking
> - Sync last avail wrap counter through GET/SET_VRI...
2019 Jul 17
0
[PATCH V3 00/15] Packed virtqueue support for vhost
...d_n()
> - more compact math for event idx
> - fix failure of SET_VRING_BASE when avail_wrap_counter is true
> - fix not copy avail_wrap_counter during GET_VRING_BASE
> - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing
> - last_used_idx
> - rename used_wrap_counter to last_used_wrap_counter
> - rebase to net-next
>
> Changes from RFC V4:
> - fix signalled_used index recording
> - track avail index correctly
> - various minor fixes
>
> Changes from RFC V3:
> - Fix math on event idx checking
> - Sync last avail wrap counter through GET/SET_VRING_BASE
>...
2018 Jul 16
0
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...r event idx
> > > - fix failure of SET_VRING_BASE when avail_wrap_counter is true
> > > - fix not copy avail_wrap_counter during GET_VRING_BASE
> > > - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
> > > - rename used_wrap_counter to last_used_wrap_counter
> > > - rebase to net-next
> > >
> > > Changes from RFC V4:
> > >
> > > - fix signalled_used index recording
> > > - track avail index correctly
> > > - various minor fixes
> > >
> > > Changes from RFC V3:
> >...
2018 Jul 03
12
[PATCH net-next 0/8] Packed virtqueue for vhost
...iers during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device stru...
2018 Jul 03
12
[PATCH net-next 0/8] Packed virtqueue for vhost
...iers during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device stru...
2019 Jul 17
17
[PATCH V3 00/15] Packed virtqueue support for vhost
...rs during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing
- last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device struct...
2019 Jul 17
17
[PATCH V3 00/15] Packed virtqueue support for vhost
...rs during vhost_add_used_packed_n()
- more compact math for event idx
- fix failure of SET_VRING_BASE when avail_wrap_counter is true
- fix not copy avail_wrap_counter during GET_VRING_BASE
- introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing
- last_used_idx
- rename used_wrap_counter to last_used_wrap_counter
- rebase to net-next
Changes from RFC V4:
- fix signalled_used index recording
- track avail index correctly
- various minor fixes
Changes from RFC V3:
- Fix math on event idx checking
- Sync last avail wrap counter through GET/SET_VRING_BASE
- remove desc_event prefix in the driver/device struct...
2018 Jul 17
1
[PATCH net-next V2 0/8] Packed virtqueue support for vhost
...idx
>>>> - fix failure of SET_VRING_BASE when avail_wrap_counter is true
>>>> - fix not copy avail_wrap_counter during GET_VRING_BASE
>>>> - introduce SET_VRING_USED_BASE/GET_VRING_USED_BASE for syncing last_used_idx
>>>> - rename used_wrap_counter to last_used_wrap_counter
>>>> - rebase to net-next
>>>>
>>>> Changes from RFC V4:
>>>>
>>>> - fix signalled_used index recording
>>>> - track avail index correctly
>>>> - various minor fixes
>>>>
>>>> Changes from RF...