From: Jason Wang <jasowang@redhat.com> To: Tiwei Bie <tiwei.bie@intel.com>, mst@redhat.com, virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Cc: wexu@redhat.com, jfreimann@redhat.com Subject: Re: [RFC v3 4/5] virtio_ring: add event idx support in packed ring Date: Wed, 2 May 2018 10:51:06 +0800 [thread overview] Message-ID: <34781052-df9f-e505-cd3f-08e460b34dcc@redhat.com> (raw) In-Reply-To: <20180425051550.24342-5-tiwei.bie@intel.com> On 2018年04月25日 13:15, Tiwei Bie wrote: > This commit introduces the event idx support in packed > ring. This feature is temporarily disabled, because the > implementation in this patch may not work as expected, > and some further discussions on the implementation are > needed, e.g. do we have to check the wrap counter when > checking whether a kick is needed? > > Signed-off-by: Tiwei Bie <tiwei.bie@intel.com> > --- > drivers/virtio/virtio_ring.c | 53 ++++++++++++++++++++++++++++++++++++++++---- > 1 file changed, 49 insertions(+), 4 deletions(-) > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c > index 0181e93897be..b1039c2985b9 100644 > --- a/drivers/virtio/virtio_ring.c > +++ b/drivers/virtio/virtio_ring.c > @@ -986,7 +986,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, > static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > { > struct vring_virtqueue *vq = to_vvq(_vq); > - u16 flags; > + u16 new, old, off_wrap, flags; > bool needs_kick; > u32 snapshot; > > @@ -995,7 +995,12 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > * suppressions. */ > virtio_mb(vq->weak_barriers); > > + old = vq->next_avail_idx - vq->num_added; > + new = vq->next_avail_idx; > + vq->num_added = 0; > + > snapshot = *(u32 *)vq->vring_packed.device; > + off_wrap = virtio16_to_cpu(_vq->vdev, snapshot & 0xffff); > flags = cpu_to_virtio16(_vq->vdev, snapshot >> 16) & 0x3; > > #ifdef DEBUG > @@ -1006,7 +1011,10 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > vq->last_add_time_valid = false; > #endif > > - needs_kick = (flags != VRING_EVENT_F_DISABLE); > + if (flags == VRING_EVENT_F_DESC) > + needs_kick = vring_need_event(off_wrap & ~(1<<15), new, old); I wonder whether or not the math is correct. Both new and event are in the unit of descriptor ring size, but old looks not. Thanks > + else > + needs_kick = (flags != VRING_EVENT_F_DISABLE); > END_USE(vq); > return needs_kick; > } > @@ -1116,6 +1124,15 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, > if (vq->last_used_idx >= vq->vring_packed.num) > vq->last_used_idx -= vq->vring_packed.num; > > + /* If we expect an interrupt for the next entry, tell host > + * by writing event index and flush out the write before > + * the read in the next get_buf call. */ > + if (vq->event_flags_shadow == VRING_EVENT_F_DESC) > + virtio_store_mb(vq->weak_barriers, > + &vq->vring_packed.driver->off_wrap, > + cpu_to_virtio16(_vq->vdev, vq->last_used_idx | > + (vq->wrap_counter << 15))); > + > #ifdef DEBUG > vq->last_add_time_valid = false; > #endif > @@ -1143,10 +1160,17 @@ static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq) > > /* We optimistically turn back on interrupts, then check if there was > * more to do. */ > + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to > + * either clear the flags bit or point the event index at the next > + * entry. Always update the event index to keep code simple. */ > + > + vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev, > + vq->last_used_idx | (vq->wrap_counter << 15)); > > if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { > virtio_wmb(vq->weak_barriers); > - vq->event_flags_shadow = VRING_EVENT_F_ENABLE; > + vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC : > + VRING_EVENT_F_ENABLE; > vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, > vq->event_flags_shadow); > } > @@ -1172,15 +1196,34 @@ static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx) > static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) > { > struct vring_virtqueue *vq = to_vvq(_vq); > + u16 bufs, used_idx, wrap_counter; > > START_USE(vq); > > /* We optimistically turn back on interrupts, then check if there was > * more to do. */ > + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to > + * either clear the flags bit or point the event index at the next > + * entry. Always update the event index to keep code simple. */ > + > + /* TODO: tune this threshold */ > + bufs = (u16)(vq->next_avail_idx - vq->last_used_idx) * 3 / 4; > + > + used_idx = vq->last_used_idx + bufs; > + wrap_counter = vq->wrap_counter; > + > + if (used_idx >= vq->vring_packed.num) { > + used_idx -= vq->vring_packed.num; > + wrap_counter ^= 1; > + } > + > + vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev, > + used_idx | (wrap_counter << 15)); > > if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { > virtio_wmb(vq->weak_barriers); > - vq->event_flags_shadow = VRING_EVENT_F_ENABLE; > + vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC : > + VRING_EVENT_F_ENABLE; > vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, > vq->event_flags_shadow); > } > @@ -1822,8 +1865,10 @@ void vring_transport_features(struct virtio_device *vdev) > switch (i) { > case VIRTIO_RING_F_INDIRECT_DESC: > break; > +#if 0 > case VIRTIO_RING_F_EVENT_IDX: > break; > +#endif > case VIRTIO_F_VERSION_1: > break; > case VIRTIO_F_IOMMU_PLATFORM:
WARNING: multiple messages have this Message-ID (diff)
From: Jason Wang <jasowang@redhat.com> To: Tiwei Bie <tiwei.bie@intel.com>, mst@redhat.com, virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Cc: wexu@redhat.com Subject: Re: [RFC v3 4/5] virtio_ring: add event idx support in packed ring Date: Wed, 2 May 2018 10:51:06 +0800 [thread overview] Message-ID: <34781052-df9f-e505-cd3f-08e460b34dcc@redhat.com> (raw) In-Reply-To: <20180425051550.24342-5-tiwei.bie@intel.com> On 2018年04月25日 13:15, Tiwei Bie wrote: > This commit introduces the event idx support in packed > ring. This feature is temporarily disabled, because the > implementation in this patch may not work as expected, > and some further discussions on the implementation are > needed, e.g. do we have to check the wrap counter when > checking whether a kick is needed? > > Signed-off-by: Tiwei Bie <tiwei.bie@intel.com> > --- > drivers/virtio/virtio_ring.c | 53 ++++++++++++++++++++++++++++++++++++++++---- > 1 file changed, 49 insertions(+), 4 deletions(-) > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c > index 0181e93897be..b1039c2985b9 100644 > --- a/drivers/virtio/virtio_ring.c > +++ b/drivers/virtio/virtio_ring.c > @@ -986,7 +986,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, > static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > { > struct vring_virtqueue *vq = to_vvq(_vq); > - u16 flags; > + u16 new, old, off_wrap, flags; > bool needs_kick; > u32 snapshot; > > @@ -995,7 +995,12 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > * suppressions. */ > virtio_mb(vq->weak_barriers); > > + old = vq->next_avail_idx - vq->num_added; > + new = vq->next_avail_idx; > + vq->num_added = 0; > + > snapshot = *(u32 *)vq->vring_packed.device; > + off_wrap = virtio16_to_cpu(_vq->vdev, snapshot & 0xffff); > flags = cpu_to_virtio16(_vq->vdev, snapshot >> 16) & 0x3; > > #ifdef DEBUG > @@ -1006,7 +1011,10 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) > vq->last_add_time_valid = false; > #endif > > - needs_kick = (flags != VRING_EVENT_F_DISABLE); > + if (flags == VRING_EVENT_F_DESC) > + needs_kick = vring_need_event(off_wrap & ~(1<<15), new, old); I wonder whether or not the math is correct. Both new and event are in the unit of descriptor ring size, but old looks not. Thanks > + else > + needs_kick = (flags != VRING_EVENT_F_DISABLE); > END_USE(vq); > return needs_kick; > } > @@ -1116,6 +1124,15 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, > if (vq->last_used_idx >= vq->vring_packed.num) > vq->last_used_idx -= vq->vring_packed.num; > > + /* If we expect an interrupt for the next entry, tell host > + * by writing event index and flush out the write before > + * the read in the next get_buf call. */ > + if (vq->event_flags_shadow == VRING_EVENT_F_DESC) > + virtio_store_mb(vq->weak_barriers, > + &vq->vring_packed.driver->off_wrap, > + cpu_to_virtio16(_vq->vdev, vq->last_used_idx | > + (vq->wrap_counter << 15))); > + > #ifdef DEBUG > vq->last_add_time_valid = false; > #endif > @@ -1143,10 +1160,17 @@ static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq) > > /* We optimistically turn back on interrupts, then check if there was > * more to do. */ > + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to > + * either clear the flags bit or point the event index at the next > + * entry. Always update the event index to keep code simple. */ > + > + vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev, > + vq->last_used_idx | (vq->wrap_counter << 15)); > > if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { > virtio_wmb(vq->weak_barriers); > - vq->event_flags_shadow = VRING_EVENT_F_ENABLE; > + vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC : > + VRING_EVENT_F_ENABLE; > vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, > vq->event_flags_shadow); > } > @@ -1172,15 +1196,34 @@ static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx) > static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) > { > struct vring_virtqueue *vq = to_vvq(_vq); > + u16 bufs, used_idx, wrap_counter; > > START_USE(vq); > > /* We optimistically turn back on interrupts, then check if there was > * more to do. */ > + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to > + * either clear the flags bit or point the event index at the next > + * entry. Always update the event index to keep code simple. */ > + > + /* TODO: tune this threshold */ > + bufs = (u16)(vq->next_avail_idx - vq->last_used_idx) * 3 / 4; > + > + used_idx = vq->last_used_idx + bufs; > + wrap_counter = vq->wrap_counter; > + > + if (used_idx >= vq->vring_packed.num) { > + used_idx -= vq->vring_packed.num; > + wrap_counter ^= 1; > + } > + > + vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev, > + used_idx | (wrap_counter << 15)); > > if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) { > virtio_wmb(vq->weak_barriers); > - vq->event_flags_shadow = VRING_EVENT_F_ENABLE; > + vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC : > + VRING_EVENT_F_ENABLE; > vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev, > vq->event_flags_shadow); > } > @@ -1822,8 +1865,10 @@ void vring_transport_features(struct virtio_device *vdev) > switch (i) { > case VIRTIO_RING_F_INDIRECT_DESC: > break; > +#if 0 > case VIRTIO_RING_F_EVENT_IDX: > break; > +#endif > case VIRTIO_F_VERSION_1: > break; > case VIRTIO_F_IOMMU_PLATFORM: _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2018-05-02 2:51 UTC|newest] Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-04-25 5:15 [RFC v3 0/5] virtio: support packed ring Tiwei Bie 2018-04-25 5:15 ` [RFC v3 1/5] virtio: add packed ring definitions Tiwei Bie 2018-04-25 5:15 ` Tiwei Bie 2018-04-25 5:15 ` [RFC v3 2/5] virtio_ring: support creating packed ring Tiwei Bie 2018-04-25 5:15 ` Tiwei Bie 2018-04-25 5:15 ` [RFC v3 3/5] virtio_ring: add packed ring support Tiwei Bie 2018-05-10 7:32 ` Jason Wang 2018-05-10 7:32 ` Jason Wang 2018-05-10 7:34 ` Jason Wang 2018-05-10 7:34 ` Jason Wang 2018-05-10 8:56 ` Tiwei Bie 2018-05-10 8:56 ` Tiwei Bie 2018-05-10 9:49 ` Jason Wang 2018-05-10 10:50 ` Tiwei Bie 2018-05-10 10:50 ` Tiwei Bie 2018-05-10 9:49 ` Jason Wang 2018-04-25 5:15 ` Tiwei Bie 2018-04-25 5:15 ` [RFC v3 4/5] virtio_ring: add event idx support in packed ring Tiwei Bie 2018-05-02 2:51 ` Jason Wang [this message] 2018-05-02 2:51 ` Jason Wang 2018-05-02 7:28 ` Tiwei Bie 2018-05-02 13:51 ` Michael S. Tsirkin 2018-05-02 15:12 ` Tiwei Bie 2018-05-02 15:12 ` Tiwei Bie 2018-05-02 15:42 ` Michael S. Tsirkin 2018-05-02 15:42 ` Michael S. Tsirkin 2018-05-03 1:11 ` Tiwei Bie 2018-05-03 1:11 ` Tiwei Bie 2018-05-03 1:44 ` Michael S. Tsirkin 2018-05-03 1:44 ` Michael S. Tsirkin 2018-05-03 2:09 ` Tiwei Bie 2018-05-03 2:09 ` Tiwei Bie 2018-05-03 7:25 ` Jason Wang 2018-05-03 7:25 ` Jason Wang 2018-05-03 13:54 ` Tiwei Bie 2018-05-03 13:54 ` Tiwei Bie 2018-05-08 3:05 ` Jason Wang 2018-05-08 3:05 ` Jason Wang 2018-05-08 5:40 ` Jason Wang 2018-05-08 6:44 ` Tiwei Bie 2018-05-08 7:16 ` Jason Wang 2018-05-08 7:16 ` Jason Wang 2018-05-08 9:16 ` Tiwei Bie 2018-05-08 9:16 ` Tiwei Bie 2018-05-08 9:34 ` Jason Wang 2018-05-08 9:34 ` Jason Wang 2018-05-08 9:44 ` Tiwei Bie 2018-05-08 9:44 ` Tiwei Bie 2018-05-09 3:43 ` Jason Wang 2018-05-09 3:43 ` Jason Wang 2018-05-08 6:44 ` Tiwei Bie 2018-05-08 5:40 ` Jason Wang 2018-05-02 13:51 ` Michael S. Tsirkin 2018-05-02 7:28 ` Tiwei Bie 2018-05-16 5:01 ` Jason Wang 2018-05-16 5:55 ` Tiwei Bie 2018-05-16 5:55 ` Tiwei Bie 2018-05-16 5:01 ` Jason Wang 2018-04-25 5:15 ` Tiwei Bie 2018-04-25 5:15 ` [RFC v3 5/5] virtio_ring: enable " Tiwei Bie 2018-04-25 5:15 ` Tiwei Bie 2018-04-27 3:56 ` [RFC v3 0/5] virtio: support " Jason Wang 2018-04-27 4:18 ` Michael S. Tsirkin 2018-04-27 6:17 ` Jason Wang 2018-04-27 9:12 ` Tiwei Bie 2018-04-27 9:12 ` Tiwei Bie 2018-04-28 2:45 ` Jason Wang 2018-04-28 2:45 ` Jason Wang 2018-04-27 6:17 ` Jason Wang 2018-04-27 4:18 ` Michael S. Tsirkin 2018-04-27 3:56 ` Jason Wang 2018-05-02 3:49 ` Jason Wang 2018-05-02 3:49 ` Jason Wang
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=34781052-df9f-e505-cd3f-08e460b34dcc@redhat.com \ --to=jasowang@redhat.com \ --cc=jfreimann@redhat.com \ --cc=linux-kernel@vger.kernel.org \ --cc=mst@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=tiwei.bie@intel.com \ --cc=virtualization@lists.linux-foundation.org \ --cc=wexu@redhat.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.