On Mon, Dec 4, 2023 at 3:23 PM Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx> wrote:
>
> introduce virtqueue_get_buf_ctx_dma() to collect the dma info when
> get buf from virtio core for premapped mode.
>
> If the virtio queue is premapped mode, the virtio-net send buf may
> have many desc. Every desc dma address need to be unmap. So here we
> introduce a new helper to collect the dma address of the buffer from
> the virtio core.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@xxxxxxxxxxxxxxxxx>
> ---
> drivers/virtio/virtio_ring.c | 157 +++++++++++++++++++++++------------
> include/linux/virtio.h | 16 ++++
> 2 files changed, 121 insertions(+), 52 deletions(-)
>
> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> index 51d8f3299c10..103d181f05bb 100644
> --- a/drivers/virtio/virtio_ring.c
> +++ b/drivers/virtio/virtio_ring.c
> @@ -362,6 +362,26 @@ static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
> return vq->dma_dev;
> }
>
> +static void collect_dma_info(const struct vring_virtqueue *vq,
Not a native speaker, but it looks to me like "get_dma_info" is better here.
> + struct virtio_dma_head *dma,
> + dma_addr_t addr, unsigned int length)
> +{
> + if (WARN_ON_ONCE(!dma))
> + return;
So all the callers did:
if (!vq->do_unmap)
collect_dma_info()
It's a strong hint that we should move the vq->do_unmap inside
collect_dma_info()?
> +
> + if (unlikely(dma->next >= dma->num)) {
> + dev_warn_once(&vq->vq.vdev->dev,
> + "premapped vq: collect dma miss: %pad %u\n",
> + &addr, length);
Let's use BAD_RING() for consistency.
Btw, the message seems ambiguous here.
> + return;
> + }
> +
> + dma->items[dma->next].addr = addr;
> + dma->items[dma->next].length = length;
> +
> + ++dma->next;
> +}
> +
> /* Map one sg entry. */
> static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist *sg,
> enum dma_data_direction direction, dma_addr_t *addr)
> @@ -441,12 +461,17 @@ static void virtqueue_init(struct vring_virtqueue *vq, u32 num)
> */
>
> static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
> - const struct vring_desc *desc)
> + const struct vring_desc *desc,
> + struct virtio_dma_head *dma)
> {
> u16 flags;
>
> - if (!vq->do_unmap)
> + if (!vq->do_unmap) {
> + collect_dma_info(vq, dma,
> + virtio64_to_cpu(vq->vq.vdev, desc->addr),
> + virtio32_to_cpu(vq->vq.vdev, desc->len));
> return;
> + }
>
> flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
>
> @@ -458,7 +483,7 @@ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq,
> }
>
> static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
> - unsigned int i)
> + unsigned int i, struct virtio_dma_head *dma)
> {
> struct vring_desc_extra *extra = vq->split.desc_extra;
> u16 flags;
> @@ -466,18 +491,15 @@ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
> flags = extra[i].flags;
>
> if (flags & VRING_DESC_F_INDIRECT) {
> - if (!vq->use_dma_api)
> - goto out;
> -
> - dma_unmap_single(vring_dma_dev(vq),
> - extra[i].addr,
> - extra[i].len,
> - (flags & VRING_DESC_F_WRITE) ?
> - DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + if (vq->use_dma_api)
> + dma_unmap_single(vring_dma_dev(vq),
> + extra[i].addr,
> + extra[i].len,
> + (flags & VRING_DESC_F_WRITE) ?
> + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + } else if (!vq->do_unmap) {
> + collect_dma_info(vq, dma, extra[i].addr, extra[i].len);
> } else {
> - if (!vq->do_unmap)
> - goto out;
> -
> dma_unmap_page(vring_dma_dev(vq),
> extra[i].addr,
> extra[i].len,
> @@ -485,7 +507,6 @@ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq,
> DMA_FROM_DEVICE : DMA_TO_DEVICE);
> }
>
> -out:
> return extra[i].next;
> }
>
> @@ -717,10 +738,10 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
> if (i == err_idx)
> break;
> if (indirect) {
> - vring_unmap_one_split_indirect(vq, &desc[i]);
> + vring_unmap_one_split_indirect(vq, &desc[i], NULL);
So this will trigger the WARN_ON_ONCE() in collect_dma_info()?
> i = virtio16_to_cpu(_vq->vdev, desc[i].next);
> } else
> - i = vring_unmap_one_split(vq, i);
> + i = vring_unmap_one_split(vq, i, NULL);
> }
>
> free_indirect:
> @@ -763,7 +784,7 @@ static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
> }
>
> static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
> - void **ctx)
> + struct virtio_dma_head *dma, void **ctx)
> {
> unsigned int i, j;
> __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
> @@ -775,12 +796,12 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
> i = head;
>
> while (vq->split.vring.desc[i].flags & nextflag) {
> - vring_unmap_one_split(vq, i);
> + vring_unmap_one_split(vq, i, dma);
> i = vq->split.desc_extra[i].next;
> vq->vq.num_free++;
> }
>
> - vring_unmap_one_split(vq, i);
> + vring_unmap_one_split(vq, i, dma);
> vq->split.desc_extra[i].next = vq->free_head;
> vq->free_head = head;
>
> @@ -802,10 +823,8 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
> VRING_DESC_F_INDIRECT));
> BUG_ON(len == 0 || len % sizeof(struct vring_desc));
>
> - if (vq->do_unmap) {
> - for (j = 0; j < len / sizeof(struct vring_desc); j++)
> - vring_unmap_one_split_indirect(vq, &indir_desc[j]);
> - }
> + for (j = 0; j < len / sizeof(struct vring_desc); j++)
> + vring_unmap_one_split_indirect(vq, &indir_desc[j], dma);
>
> kfree(indir_desc);
> vq->split.desc_state[head].indir_desc = NULL;
> @@ -822,6 +841,7 @@ static bool more_used_split(const struct vring_virtqueue *vq)
>
> static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
> unsigned int *len,
> + struct virtio_dma_head *dma,
> void **ctx)
> {
> struct vring_virtqueue *vq = to_vvq(_vq);
> @@ -862,7 +882,7 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
>
> /* detach_buf_split clears data, so grab it now. */
> ret = vq->split.desc_state[i].data;
> - detach_buf_split(vq, i, ctx);
> + detach_buf_split(vq, i, dma, ctx);
> vq->last_used_idx++;
> /* If we expect an interrupt for the next entry, tell host
> * by writing event index and flush out the write before
> @@ -984,7 +1004,7 @@ static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
> continue;
> /* detach_buf_split clears data, so grab it now. */
> buf = vq->split.desc_state[i].data;
> - detach_buf_split(vq, i, NULL);
> + detach_buf_split(vq, i, NULL, NULL);
> vq->split.avail_idx_shadow--;
> vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
> vq->split.avail_idx_shadow);
> @@ -1221,7 +1241,8 @@ static u16 packed_last_used(u16 last_used_idx)
> }
>
> static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
> - const struct vring_desc_extra *extra)
> + const struct vring_desc_extra *extra,
> + struct virtio_dma_head *dma)
> {
> u16 flags;
>
> @@ -1235,10 +1256,9 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
> extra->addr, extra->len,
> (flags & VRING_DESC_F_WRITE) ?
> DMA_FROM_DEVICE : DMA_TO_DEVICE);
> + } else if (!vq->do_unmap) {
> + collect_dma_info(vq, dma, extra->addr, extra->len);
> } else {
> - if (!vq->do_unmap)
> - return;
> -
> dma_unmap_page(vring_dma_dev(vq),
> extra->addr, extra->len,
> (flags & VRING_DESC_F_WRITE) ?
> @@ -1247,12 +1267,15 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq,
> }
>
> static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
> - const struct vring_packed_desc *desc)
> + const struct vring_packed_desc *desc,
> + struct virtio_dma_head *dma)
> {
> u16 flags;
>
> - if (!vq->do_unmap)
> + if (!vq->do_unmap) {
> + collect_dma_info(vq, dma, le64_to_cpu(desc->addr), le32_to_cpu(desc->len));
> return;
> + }
>
> flags = le16_to_cpu(desc->flags);
>
> @@ -1389,7 +1412,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
> err_idx = i;
>
> for (i = 0; i < err_idx; i++)
> - vring_unmap_desc_packed(vq, &desc[i]);
> + vring_unmap_desc_packed(vq, &desc[i], NULL);
>
> free_desc:
> kfree(desc);
> @@ -1539,7 +1562,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
> for (n = 0; n < total_sg; n++) {
> if (i == err_idx)
> break;
> - vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]);
> + vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr], NULL);
> curr = vq->packed.desc_extra[curr].next;
> i++;
> if (i >= vq->packed.vring.num)
> @@ -1600,7 +1623,9 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
> }
>
> static void detach_buf_packed(struct vring_virtqueue *vq,
> - unsigned int id, void **ctx)
> + unsigned int id,
> + struct virtio_dma_head *dma,
> + void **ctx)
> {
> struct vring_desc_state_packed *state = NULL;
> struct vring_packed_desc *desc;
> @@ -1615,13 +1640,10 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
> vq->free_head = id;
> vq->vq.num_free += state->num;
>
> - if (unlikely(vq->do_unmap)) {
> - 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;
> - }
> + curr = id;
> + for (i = 0; i < state->num; i++) {
> + vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr], dma);
> + curr = vq->packed.desc_extra[curr].next;
I wonder if !dma && vq->do_unmap is valid, we need to document it somewhere.
And we can keep the unlikely() optimization as is.
> }
>
> if (vq->indirect) {
> @@ -1632,12 +1654,9 @@ static void detach_buf_packed(struct vring_virtqueue *vq,
> if (!desc)
> return;
>
> - if (vq->do_unmap) {
> - len = vq->packed.desc_extra[id].len;
> - for (i = 0; i < len / sizeof(struct vring_packed_desc);
> - i++)
> - vring_unmap_desc_packed(vq, &desc[i]);
> - }
> + len = vq->packed.desc_extra[id].len;
> + for (i = 0; i < len / sizeof(struct vring_packed_desc); i++)
> + vring_unmap_desc_packed(vq, &desc[i], dma);
> kfree(desc);
> state->indir_desc = NULL;
> } else if (ctx) {
> @@ -1672,6 +1691,7 @@ static bool more_used_packed(const struct vring_virtqueue *vq)
>
> static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
> unsigned int *len,
> + struct virtio_dma_head *dma,
> void **ctx)
> {
> struct vring_virtqueue *vq = to_vvq(_vq);
> @@ -1712,7 +1732,7 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
>
> /* detach_buf_packed clears data, so grab it now. */
> ret = vq->packed.desc_state[id].data;
> - detach_buf_packed(vq, id, ctx);
> + detach_buf_packed(vq, id, dma, ctx);
>
> last_used += vq->packed.desc_state[id].num;
> if (unlikely(last_used >= vq->packed.vring.num)) {
> @@ -1877,7 +1897,7 @@ static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
> continue;
> /* detach_buf clears data, so grab it now. */
> buf = vq->packed.desc_state[i].data;
> - detach_buf_packed(vq, i, NULL);
> + detach_buf_packed(vq, i, NULL, NULL);
> END_USE(vq);
> return buf;
> }
> @@ -2417,11 +2437,44 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
> {
> struct vring_virtqueue *vq = to_vvq(_vq);
>
> - return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
> - virtqueue_get_buf_ctx_split(_vq, len, ctx);
> + return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, NULL, ctx) :
> + virtqueue_get_buf_ctx_split(_vq, len, NULL, ctx);
> }
> EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
>
> +/**
> + * virtqueue_get_buf_ctx_dma - get the next used buffer with the dma info
> + * @_vq: the struct virtqueue we're talking about.
> + * @len: the length written into the buffer
> + * @dma: the head of the array to store the dma info
> + * @ctx: extra context for the token
> + *
> + * If the device wrote data into the buffer, @len will be set to the
> + * amount written. This means you don't need to clear the buffer
> + * beforehand to ensure there's no data leakage in the case of short
> + * writes.
> + *
> + * Caller must ensure we don't call this with other virtqueue
> + * operations at the same time (except where noted).
> + *
> + * We store the dma info of every descriptor of this buf to the dma->items
> + * array. If the array size is too small, some dma info may be missed, so
> + * the caller must ensure the array is enough.
large enough?
> The dma->next is the out value
> + * to the caller,
What do you mean by "out value to the caller" ?
Thanks
> indicates the num of the used items.
> + *
> + * Returns NULL if there are no used buffers, or the "data" token
> + * handed to virtqueue_add_*().
> + */
> +void *virtqueue_get_buf_ctx_dma(struct virtqueue *_vq, unsigned int *len,
> + struct virtio_dma_head *dma, void **ctx)
> +{
> + struct vring_virtqueue *vq = to_vvq(_vq);
> +
> + return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, dma, ctx) :
> + virtqueue_get_buf_ctx_split(_vq, len, dma, ctx);
> +}
> +EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx_dma);
> +
> void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
> {
> return virtqueue_get_buf_ctx(_vq, len, NULL);
> diff --git a/include/linux/virtio.h b/include/linux/virtio.h
> index 4cc614a38376..572aecec205b 100644
> --- a/include/linux/virtio.h
> +++ b/include/linux/virtio.h
> @@ -75,6 +75,22 @@ void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
> void *virtqueue_get_buf_ctx(struct virtqueue *vq, unsigned int *len,
> void **ctx);
>
> +struct virtio_dma_item {
> + dma_addr_t addr;
> + unsigned int length;
> +};
> +
> +struct virtio_dma_head {
> + /* total num of items. */
> + u16 num;
> + /* point to the next item to store dma info. */
> + u16 next;
> + struct virtio_dma_item items[];
> +};
> +
> +void *virtqueue_get_buf_ctx_dma(struct virtqueue *_vq, unsigned int *len,
> + struct virtio_dma_head *dma, void **ctx);
> +
> void virtqueue_disable_cb(struct virtqueue *vq);
>
> bool virtqueue_enable_cb(struct virtqueue *vq);
> --
> 2.32.0.3.g01195cf9f
>
