[dpdk-dev] [PATCH v3] vhost: fix async copy fail on multi-page buffers

[Fu, Patrick]

Hi,

> -----Original Message-----
> From: Xia, Chenbo <chenbo.xia at intel.com>
> Sent: Monday, July 27, 2020 9:14 PM
> To: Fu, Patrick <patrick.fu at intel.com>; dev at dpdk.org;
> maxime.coquelin at redhat.com
> Subject: RE: [PATCH v3] vhost: fix async copy fail on multi-page buffers
> 
> Hi Patrick,
> 
> > -----Original Message-----
> > From: Fu, Patrick <patrick.fu at intel.com>
> > Sent: Monday, July 27, 2020 2:33 PM
> > To: dev at dpdk.org; maxime.coquelin at redhat.com; Xia, Chenbo
> > <chenbo.xia at intel.com>
> > Cc: Fu, Patrick <patrick.fu at intel.com>
> > Subject: [PATCH v3] vhost: fix async copy fail on multi-page buffers
> >
> >  lib/librte_vhost/vhost.h      | 50 +++++++++++++++++++++++++++++++++++
> >  lib/librte_vhost/virtio_net.c | 40 +++++++++++++++++-----------
> >  2 files changed, 75 insertions(+), 15 deletions(-)
> >
> > +	} else {
> > +		for (i = 0; i < dev->nr_guest_pages; i++) {
> > +			page = &dev->guest_pages[i];
> > +
> > +			if (gpa >= page->guest_phys_addr) {
> > +				if (gpa + gpa_size <
> 
> Should the '<' be '<=' here?
> 
Yes, it should be. Will update in v4 patch

> >  static __rte_always_inline uint64_t
> >  hva_to_gpa(struct virtio_net *dev, uint64_t vva, uint64_t len)  {
> > diff --git a/lib/librte_vhost/virtio_net.c
> > b/lib/librte_vhost/virtio_net.c index
> > 95a0bc19f..124a33a10 100644
> > --- a/lib/librte_vhost/virtio_net.c
> > +++ b/lib/librte_vhost/virtio_net.c
> > @@ -980,6 +980,7 @@ async_mbuf_to_desc(struct virtio_net *dev, struct
> > vhost_virtqueue *vq,
> >  	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
> >  	struct virtio_net_hdr_mrg_rxbuf tmp_hdr, *hdr = NULL;
> >  	int error = 0;
> > +	uint64_t mapped_len;
> >
> >  	uint32_t tlen = 0;
> >  	int tvec_idx = 0;
> > @@ -1072,24 +1073,31 @@ async_mbuf_to_desc(struct virtio_net *dev,
> > struct vhost_virtqueue *vq,
> >
> >  		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
> >
> > -		if (unlikely(cpy_len >= cpy_threshold)) {
> > -			hpa = (void *)(uintptr_t)gpa_to_hpa(dev,
> > -					buf_iova + buf_offset, cpy_len);
> > +		while (unlikely(cpy_len && cpy_len >= cpy_threshold)) {
> > +			hpa = (void *)(uintptr_t)gpa_to_first_hpa(dev,
> > +					buf_iova + buf_offset,
> > +					cpy_len, &mapped_len);
> >
> > -			if (unlikely(!hpa)) {
> > -				error = -1;
> > -				goto out;
> > -			}
> > +			if (unlikely(!hpa || mapped_len < cpy_threshold))
> > +				break;
> >
> >  			async_fill_vec(src_iovec + tvec_idx,
> >  				(void *)(uintptr_t)rte_pktmbuf_iova_offset(m,
> > -						mbuf_offset), cpy_len);
> > +				mbuf_offset), (size_t)mapped_len);
> >
> > -			async_fill_vec(dst_iovec + tvec_idx, hpa, cpy_len);
> > +			async_fill_vec(dst_iovec + tvec_idx,
> > +					hpa, (size_t)mapped_len);
> >
> > -			tlen += cpy_len;
> > +			tlen += (uint32_t)mapped_len;
> > +			cpy_len -= (uint32_t)mapped_len;
> > +			mbuf_avail  -= (uint32_t)mapped_len;
> > +			mbuf_offset += (uint32_t)mapped_len;
> > +			buf_avail  -= (uint32_t)mapped_len;
> > +			buf_offset += (uint32_t)mapped_len;
> 
> Will it be ok we just transform the uint64_t to uint32_t here?
> What if mapped_len > MAX uint32_t ?
> 

"mapped_len" could not exceed "cpy_len" (according to the gpa_to_first_hpa() logic). As cpy_len is uint32, mapped_len is safe to down casting.

Thanks,

Patrick