Re: [PATCH vhost v2 19/19] virtio_net: sq support premapped mode

["Michael S. Tsirkin" <mst@redhat.com>]

On Mon, Feb 26, 2024 at 07:00:09AM -0500, Michael S. Tsirkin wrote:
> On Mon, Feb 26, 2024 at 07:41:20PM +0800, Xuan Zhuo wrote:
> > On Mon, 26 Feb 2024 06:39:51 -0500, "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > > On Mon, Feb 26, 2024 at 05:24:11PM +0800, Xuan Zhuo wrote:
> > > > On Sun, 25 Feb 2024 03:38:48 -0500, "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > > > > On Fri, Feb 23, 2024 at 04:27:26PM +0800, Xuan Zhuo wrote:
> > > > > > If the xsk is enabling, the xsk tx will share the send queue.
> > > > > > But the xsk requires that the send queue use the premapped mode.
> > > > > > So the send queue must support premapped mode.
> > > > > >
> > > > > > cmd:
> > > > > >     sh samples/pktgen/pktgen_sample01_simple.sh -i eth0 \
> > > > > >         -s 16 -d 10.0.0.128 -m 00:16:3e:2c:c8:2e -n 0 -p 100
> > > > > > CPU:
> > > > > >     Intel(R) Xeon(R) Platinum 8369B CPU @ 2.70GHz
> > > > > >
> > > > > > Machine:
> > > > > >     ecs.g7.2xlarge(Aliyun)
> > > > > >
> > > > > > before:              1600010.00
> > > > > > after(no-premapped): 1599966.00
> > > > > > after(premapped):    1600014.00
> > > > > >
> > > > > > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > > > > > ---
> > > > > >  drivers/net/virtio_net.c | 136 +++++++++++++++++++++++++++++++++++++--
> > > > > >  1 file changed, 132 insertions(+), 4 deletions(-)
> > > > > >
> > > > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > > > index 7715bb7032ec..b83ef6afc4fb 100644
> > > > > > --- a/drivers/net/virtio_net.c
> > > > > > +++ b/drivers/net/virtio_net.c
> > > > > > @@ -146,6 +146,25 @@ struct virtnet_rq_dma {
> > > > > >  	u16 need_sync;
> > > > > >  };
> > > > > >
> > > > > > +struct virtnet_sq_dma {
> > > > > > +	union {
> > > > > > +		struct virtnet_sq_dma *next;
> > > > > > +		void *data;
> > > > > > +	};
> > > > > > +
> > > > > > +	u32 num;
> > > > > > +
> > > > > > +	dma_addr_t addr[MAX_SKB_FRAGS + 2];
> > > > > > +	u32 len[MAX_SKB_FRAGS + 2];
> > > > > > +};
> > > > > > +
> > > > > > +struct virtnet_sq_dma_head {
> > > > > > +	/* record for kfree */
> > > > > > +	void *p;
> > > > > > +
> > > > > > +	struct virtnet_sq_dma *free;
> > > > > > +};
> > > > > > +
> > > > > >  /* Internal representation of a send virtqueue */
> > > > > >  struct send_queue {
> > > > > >  	/* Virtqueue associated with this send _queue */
> > > > > > @@ -165,6 +184,8 @@ struct send_queue {
> > > > > >
> > > > > >  	/* Record whether sq is in reset state. */
> > > > > >  	bool reset;
> > > > > > +
> > > > > > +	struct virtnet_sq_dma_head dmainfo;
> > > > > >  };
> > > > > >
> > > > > >  /* Internal representation of a receive virtqueue */
> > > > > > @@ -368,6 +389,95 @@ static struct xdp_frame *ptr_to_xdp(void *ptr)
> > > > > >  	return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
> > > > > >  }
> > > > > >
> > > > > > +static struct virtnet_sq_dma *virtnet_sq_unmap(struct send_queue *sq, void **data)
> > > > > > +{
> > > > > > +	struct virtnet_sq_dma *d;
> > > > > > +	int i;
> > > > > > +
> > > > > > +	d = *data;
> > > > > > +	*data = d->data;
> > > > > > +
> > > > > > +	for (i = 0; i < d->num; ++i)
> > > > > > +		virtqueue_dma_unmap_page_attrs(sq->vq, d->addr[i], d->len[i],
> > > > > > +					       DMA_TO_DEVICE, 0);
> > > > > > +
> > > > > > +	d->next = sq->dmainfo.free;
> > > > > > +	sq->dmainfo.free = d;
> > > > > > +
> > > > > > +	return d;
> > > > > > +}
> > > > > > +
> > > > > > +static struct virtnet_sq_dma *virtnet_sq_map_sg(struct send_queue *sq,
> > > > > > +						int nents, void *data)
> > > > > > +{
> > > > > > +	struct virtnet_sq_dma *d;
> > > > > > +	struct scatterlist *sg;
> > > > > > +	int i;
> > > > > > +
> > > > > > +	if (!sq->dmainfo.free)
> > > > > > +		return NULL;
> > > > > > +
> > > > > > +	d = sq->dmainfo.free;
> > > > > > +	sq->dmainfo.free = d->next;
> > > > > > +
> > > > > > +	for_each_sg(sq->sg, sg, nents, i) {
> > > > > > +		if (virtqueue_dma_map_sg_attrs(sq->vq, sg, DMA_TO_DEVICE, 0))
> > > > > > +			goto err;
> > > > > > +
> > > > > > +		d->addr[i] = sg->dma_address;
> > > > > > +		d->len[i] = sg->length;
> > > > > > +	}
> > > > > > +
> > > > > > +	d->data = data;
> > > > > > +	d->num = i;
> > > > > > +	return d;
> > > > > > +
> > > > > > +err:
> > > > > > +	d->num = i;
> > > > > > +	virtnet_sq_unmap(sq, (void **)&d);
> > > > > > +	return NULL;
> > > > > > +}
> > > > >
> > > > >
> > > > > Do I see a reimplementation of linux/llist.h here?
> > > > >
> > > > >
> > > > > > +
> > > > > > +static int virtnet_add_outbuf(struct send_queue *sq, u32 num, void *data)
> > > > > > +{
> > > > > > +	int ret;
> > > > > > +
> > > > > > +	if (sq->vq->premapped) {
> > > > > > +		data = virtnet_sq_map_sg(sq, num, data);
> > > > > > +		if (!data)
> > > > > > +			return -ENOMEM;
> > > > > > +	}
> > > > > > +
> > > > > > +	ret = virtqueue_add_outbuf(sq->vq, sq->sg, num, data, GFP_ATOMIC);
> > > > > > +	if (ret && sq->vq->premapped)
> > > > > > +		virtnet_sq_unmap(sq, &data);
> > > > > > +
> > > > > > +	return ret;
> > > > > > +}
> > > > > > +
> > > > > > +static int virtnet_sq_init_dma_mate(struct send_queue *sq)
> > > > >
> > > > > Mate? The popular south african drink?
> > > > >
> > > > > > +{
> > > > > > +	struct virtnet_sq_dma *d;
> > > > > > +	int num, i;
> > > > > > +
> > > > > > +	num = virtqueue_get_vring_size(sq->vq);
> > > > > > +
> > > > > > +	sq->dmainfo.free = kcalloc(num, sizeof(*sq->dmainfo.free), GFP_KERNEL);
> > > > > > +	if (!sq->dmainfo.free)
> > > > > > +		return -ENOMEM;
> > > > >
> > > > >
> > > > > This could be quite a bit of memory for a large queue.  And for a bunch
> > > > > of common cases where unmap is a nop (e.g. iommu pt) this does nothing
> > > > > useful at all.  And also, this does nothing useful if PLATFORM_ACCESS is off
> > > > > which is super common.
> > > > >
> > > > > A while ago I proposed:
> > > > > - extend DMA APIs so one can query whether unmap is a nop
> > > >
> > > >
> > > > We may have trouble for this.
> > > >
> > > > dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
> > > > 		size_t offset, size_t size, enum dma_data_direction dir,
> > > > 		unsigned long attrs)
> > > > {
> > > > 	const struct dma_map_ops *ops = get_dma_ops(dev);
> > > > 	dma_addr_t addr;
> > > >
> > > > 	BUG_ON(!valid_dma_direction(dir));
> > > >
> > > > 	if (WARN_ON_ONCE(!dev->dma_mask))
> > > > 		return DMA_MAPPING_ERROR;
> > > >
> > > > 	if (dma_map_direct(dev, ops) ||
> > > > 	    arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size))
> > > > 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
> > > > 	else
> > > > 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
> > > > 	kmsan_handle_dma(page, offset, size, dir);
> > > > 	debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
> > > >
> > > > 	return addr;
> > > > }
> > > >
> > > > arch_dma_map_page_direct will check the dma address.
> > > > So we can not judge by the API in advance.
> > > >
> > > > Thanks.
> > >
> > > So if dma_map_direct is false we'll still waste some memory.
> > > So be it.
> > 
> > arch_dma_map_page_direct default is marco (false), just for powerpc
> > it is a function. So I think we can skip it.
> > 
> > If the dma_map_direct is false, I think should save the dma info.
> > 
> > Thanks.
> 
> 
> Would already be an improvement.
> But can we have better names?
> 
> I'd prefer:
> 
> dma_can_skip_unmap
> dma_can_skip_sync
> 
> Because we do not know for sure if it's direct unless
> we have the page.

we might need to add these callbacks to dma ops too, I think
with iommu pt that is the case and it is pretty common,
right?

> -- 
> MST