On Tue, 26 Mar 2024 03:32:43 -0400, "Michael S. Tsirkin" <mst@xxxxxxxxxx> wrote:
> On Thu, Mar 21, 2024 at 04:20:09PM +0800, Xuan Zhuo wrote:
> > On Thu, 21 Mar 2024 13:57:06 +0800, Jason Wang <jasowang@xxxxxxxxxx> wrote:
> > > On Tue, Mar 12, 2024 at 11:36 AM Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx> wrote:
> > > >
> > > > In the functions vring_unmap_extra_packed and vring_unmap_desc_packed,
> > > > multiple checks are made whether unmap is performed and whether it is
> > > > INDIRECT.
> > > >
> > > > These two functions are usually called in a loop, and we should put the
> > > > check outside the loop.
> > > >
> > > > And we unmap the descs with VRING_DESC_F_INDIRECT on the same path with
> > > > other descs, that make the thing more complex. If we distinguish the
> > > > descs with VRING_DESC_F_INDIRECT before unmap, thing will be clearer.
> > > >
> > > > 1. only one desc of the desc table is used, we do not need the loop
> > > > 2. the called unmap api is difference from the other desc
> > > > 3. the vq->premapped is not needed to check
> > > > 4. the vq->indirect is not needed to check
> > > > 5. the state->indir_desc must not be null
> > > >
> > > > Signed-off-by: Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx>
> > > > ---
> > > > drivers/virtio/virtio_ring.c | 78 ++++++++++++++++++------------------
> > > > 1 file changed, 40 insertions(+), 38 deletions(-)
> > > >
> > > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> > > > index c2779e34aac7..0dfbd17e5a87 100644
> > > > --- a/drivers/virtio/virtio_ring.c
> > > > +++ b/drivers/virtio/virtio_ring.c
> > > > @@ -1214,6 +1214,7 @@ static u16 packed_last_used(u16 last_used_idx)
> > > > return last_used_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR));
> > > > }
> > > >
> > > > +/* caller must check vring_need_unmap_buffer() */
> > > > static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
> > > > const struct vring_desc_extra *extra)
> > > > {
> > > > @@ -1221,33 +1222,18 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
> > > >
> > > > flags = extra->flags;
> > > >
> > > > - if (flags & VRING_DESC_F_INDIRECT) {
> > > > - if (!vq->use_dma_api)
> > > > - return;
> > > > -
> > > > - dma_unmap_single(vring_dma_dev(vq),
> > > > - extra->addr, extra->len,
> > > > - (flags & VRING_DESC_F_WRITE) ?
> > > > - DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > > > - } else {
> > > > - if (!vring_need_unmap_buffer(vq))
> > > > - return;
> > > > -
> > > > - dma_unmap_page(vring_dma_dev(vq),
> > > > - extra->addr, extra->len,
> > > > - (flags & VRING_DESC_F_WRITE) ?
> > > > - DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > > > - }
> > > > + dma_unmap_page(vring_dma_dev(vq),
> > > > + extra->addr, extra->len,
> > > > + (flags & VRING_DESC_F_WRITE) ?
> > > > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > > > }
> > > >
> > > > +/* caller must check vring_need_unmap_buffer() */
> > > > static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
> > > > const struct vring_packed_desc *desc)
> > > > {
> > > > u16 flags;
> > > >
> > > > - if (!vring_need_unmap_buffer(vq))
> > > > - return;
> > > > -
> > > > flags = le16_to_cpu(desc->flags);
> > > >
> > > > dma_unmap_page(vring_dma_dev(vq),
> > > > @@ -1323,7 +1309,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
> > > > total_sg * sizeof(struct vring_packed_desc),
> > > > DMA_TO_DEVICE);
> > > > if (vring_mapping_error(vq, addr)) {
> > > > - if (vq->premapped)
> > > > + if (!vring_need_unmap_buffer(vq))
> > > > goto free_desc;
> > > >
> > > > goto unmap_release;
> > > > @@ -1338,10 +1324,11 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
> > > > vq->packed.desc_extra[id].addr = addr;
> > > > vq->packed.desc_extra[id].len = total_sg *
> > > > sizeof(struct vring_packed_desc);
> > > > - vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
> > > > - vq->packed.avail_used_flags;
> > > > }
> > > >
> > > > + vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
> > > > + vq->packed.avail_used_flags;
> > > > +
> > > > /*
> > > > * A driver MUST NOT make the first descriptor in the list
> > > > * available before all subsequent descriptors comprising
> > > > @@ -1382,6 +1369,8 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
> > > > unmap_release:
> > > > err_idx = i;
> > > >
> > > > + WARN_ON(!vring_need_unmap_buffer(vq));
> > > > +
> > > > for (i = 0; i < err_idx; i++)
> > > > vring_unmap_desc_packed(vq, &desc[i]);
> > > >
> > > > @@ -1475,12 +1464,13 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
> > > > desc[i].len = cpu_to_le32(sg->length);
> > > > desc[i].id = cpu_to_le16(id);
> > > >
> > > > - if (unlikely(vq->use_dma_api)) {
> > > > + if (vring_need_unmap_buffer(vq)) {
> > > > vq->packed.desc_extra[curr].addr = addr;
> > > > vq->packed.desc_extra[curr].len = sg->length;
> > > > - vq->packed.desc_extra[curr].flags =
> > > > - le16_to_cpu(flags);
> > > > }
> > > > +
> > > > + vq->packed.desc_extra[curr].flags = le16_to_cpu(flags);
> > > > +
> > > > prev = curr;
> > > > curr = vq->packed.desc_extra[curr].next;
> > > >
> > > > @@ -1530,6 +1520,8 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
> > > >
> > > > vq->packed.avail_used_flags = avail_used_flags;
> > > >
> > > > + WARN_ON(!vring_need_unmap_buffer(vq));
> > > > +
> > > > for (n = 0; n < total_sg; n++) {
> > > > if (i == err_idx)
> > > > break;
> > > > @@ -1599,7 +1591,9 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
> > > > struct vring_desc_state_packed *state = NULL;
> > > > struct vring_packed_desc *desc;
> > > > unsigned int i, curr;
> > > > + u16 flags;
> > > >
> > > > + flags = vq->packed.desc_extra[id].flags;
> > > > state = &vq->packed.desc_state[id];
> > > >
> > > > /* Clear data ptr. */
> > > > @@ -1609,22 +1603,32 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
> > > > vq->free_head = id;
> > > > vq->vq.num_free += state->num;
> > > >
> > > > - if (unlikely(vq->use_dma_api)) {
> > > > - curr = id;
> > > > - for (i = 0; i < state->num; i++) {
> > > > - vring_unmap_extra_packed(vq,
> > > > - &vq->packed.desc_extra[curr]);
> > > > - curr = vq->packed.desc_extra[curr].next;
> > > > + if (!(flags & VRING_DESC_F_INDIRECT)) {
> > > > + if (vring_need_unmap_buffer(vq)) {
> > > > + curr = id;
> > > > + for (i = 0; i < state->num; i++) {
> > > > + vring_unmap_extra_packed(vq,
> > > > + &vq->packed.desc_extra[curr]);
> > > > + curr = vq->packed.desc_extra[curr].next;
> > > > + }
> > > > }
> > > > - }
> > > >
> > > > - if (vq->indirect) {
> > > > + if (ctx)
> > > > + *ctx = state->indir_desc;
> > > > + } else {
> > > > + const struct vring_desc_extra *extra;
> > > > u32 len;
> > > >
> > > > + if (vq->use_dma_api) {
> > > > + extra = &vq->packed.desc_extra[id];
> > > > + dma_unmap_single(vring_dma_dev(vq),
> > > > + extra->addr, extra->len,
> > > > + (flags & VRING_DESC_F_WRITE) ?
> > > > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > > > + }
> > >
> > > Theoretically, indirect descriptors could be chained. It is supported
> > > without this patch but not here.
> >
> >
> > YES. But now, that is not supported by "add", so I think we
> > do not need to think about it.
> >
> > Thanks.
>
>
> the "add" you are referring to is virtio drivers in the linux guest?
> That's not the only guest and there's no way to be sure
> no one does it. We can make some unusual operations go somewhat
> slower but breaking them outright is not a good idea.
"add" means virtqueue_add_packed/virtqueue_add_split.
If the virtqueue_add_packed/virtqueue_add_split do not chain
the indirect desc, then I think do not consider the case that
the indirect desc wash chained.
That was all done by the linux virtio core, we do not need to
consider other cases.
Thanks.
>
> > >
> > > Thanks
> > >
> > > > +
> > > > /* Free the indirect table, if any, now that it's unmapped. */
> > > > desc = state->indir_desc;
> > > > - if (!desc)
> > > > - return;
> > > >
> > > > if (vring_need_unmap_buffer(vq)) {
> > > > len = vq->packed.desc_extra[id].len;
> > > > @@ -1634,8 +1638,6 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
> > > > }
> > > > kfree(desc);
> > > > state->indir_desc = NULL;
> > > > - } else if (ctx) {
> > > > - *ctx = state->indir_desc;
> > > > }
> > > > }
> > > >
> > > > --
> > > > 2.32.0.3.g01195cf9f
> > > >
> > >
>
