patches for DPDK stable branches
 help / color / mirror / Atom feed
* [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost
@ 2021-07-08 10:44 Cheng Jiang
  2021-07-15  8:37 ` Xia, Chenbo
  2021-07-15  9:50 ` [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring " Cheng Jiang
  0 siblings, 2 replies; 6+ messages in thread
From: Cheng Jiang @ 2021-07-08 10:44 UTC (permalink / raw)
  To: maxime.coquelin, Chenbo.Xia
  Cc: dev, jiayu.hu, yvonnex.yang, Cheng Jiang, stable

We introduced some new indexes in async vhost. If we don't pay
attention to the management of these indexes, they will eventually
overflow and lead to errors. This patch is to check and keep these
indexes within a reasonable range.

Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
Cc: stable@dpdk.org

Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
---
 lib/vhost/virtio_net.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
index f4a2c88d8b..61cb5a126c 100644
--- a/lib/vhost/virtio_net.c
+++ b/lib/vhost/virtio_net.c
@@ -1614,6 +1614,7 @@ store_dma_desc_info_packed(struct vring_used_elem_packed *s_ring,
 
 	if (d_idx + count <= ring_size) {
 		rte_memcpy(d_ring + d_idx, s_ring + s_idx, count * elem_size);
+
 	} else {
 		uint16_t size = ring_size - d_idx;
 
@@ -2036,7 +2037,7 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 
 		slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq->size;
 		if (it_pool[it_idx].count) {
-			uint16_t from, to;
+			uint16_t from;
 
 			async_descs_idx += num_descs;
 			async_fill_desc(&tdes[pkt_burst_idx++],
@@ -2055,11 +2056,13 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 			 * descriptors.
 			 */
 			from = vq->shadow_used_idx - num_buffers;
-			to = vq->async_buffer_idx_packed % vq->size;
 			store_dma_desc_info_packed(vq->shadow_used_packed,
-					vq->async_buffers_packed, vq->size, from, to, num_buffers);
+					vq->async_buffers_packed, vq->size, from,
+					vq->async_buffer_idx_packed, num_buffers);
 
 			vq->async_buffer_idx_packed += num_buffers;
+			if (vq->async_buffer_idx_packed >= vq->size)
+				vq->async_buffer_idx_packed -= vq->size;
 			vq->shadow_used_idx -= num_buffers;
 		} else {
 			comp_pkts[num_done_pkts++] = pkts[pkt_idx];
@@ -2112,6 +2115,8 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 		dma_error_handler_packed(vq, async_descs, async_descs_idx, slot_idx, pkt_err,
 					&pkt_idx, &num_async_pkts, &num_done_pkts);
 	vq->async_pkts_idx += num_async_pkts;
+	if (vq->async_pkts_idx >= vq->size)
+		vq->async_pkts_idx -= vq->size;
 	*comp_count = num_done_pkts;
 
 	if (likely(vq->shadow_used_idx)) {
@@ -2160,7 +2165,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue *vq,
 	uint16_t from, to;
 
 	do {
-		from = vq->last_async_buffer_idx_packed % vq->size;
+		from = vq->last_async_buffer_idx_packed;
 		to = (from + nr_left) % vq->size;
 		if (to > from) {
 			vhost_update_used_packed(vq, vq->async_buffers_packed + from, to - from);
@@ -2169,7 +2174,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue *vq,
 		} else {
 			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
 				vq->size - from);
-			vq->last_async_buffer_idx_packed += vq->size - from;
+			vq->last_async_buffer_idx_packed = 0;
 			nr_left -= vq->size - from;
 		}
 	} while (nr_left > 0);
@@ -2252,10 +2257,13 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 			vhost_vring_call_split(dev, vq);
 		}
 	} else {
-		if (vq_is_packed(dev))
+		if (vq_is_packed(dev)) {
 			vq->last_async_buffer_idx_packed += n_buffers;
-		else
+			if (vq->last_async_buffer_idx_packed >= vq->size)
+				vq->last_async_buffer_idx_packed -= vq->size;
+		} else {
 			vq->last_async_desc_idx_split += n_descs;
+		}
 	}
 
 done:
-- 
2.29.2


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost
  2021-07-08 10:44 [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost Cheng Jiang
@ 2021-07-15  8:37 ` Xia, Chenbo
  2021-07-15  8:50   ` Jiang, Cheng1
  2021-07-15  9:50 ` [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring " Cheng Jiang
  1 sibling, 1 reply; 6+ messages in thread
From: Xia, Chenbo @ 2021-07-15  8:37 UTC (permalink / raw)
  To: Jiang, Cheng1, maxime.coquelin; +Cc: dev, Hu, Jiayu, Yang, YvonneX, stable

Hi Cheng,

> -----Original Message-----
> From: Jiang, Cheng1 <cheng1.jiang@intel.com>
> Sent: Thursday, July 8, 2021 6:45 PM
> To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>
> Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> <yvonnex.yang@intel.com>; Jiang, Cheng1 <cheng1.jiang@intel.com>;
> stable@dpdk.org
> Subject: [PATCH] vhost: fix index overflow issue in async vhost

Since this fix is packed ring only, maybe 'fix index overflow for packed ring 
in async vhost' is better.

> 
> We introduced some new indexes in async vhost. If we don't pay
> attention to the management of these indexes, they will eventually
> overflow and lead to errors. This patch is to check and keep these
> indexes within a reasonable range.

Ditto. Should mention packed ring here.

> 
> Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
> ---
>  lib/vhost/virtio_net.c | 22 +++++++++++++++-------
>  1 file changed, 15 insertions(+), 7 deletions(-)
> 
> diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
> index f4a2c88d8b..61cb5a126c 100644
> --- a/lib/vhost/virtio_net.c
> +++ b/lib/vhost/virtio_net.c
> @@ -1614,6 +1614,7 @@ store_dma_desc_info_packed(struct vring_used_elem_packed
> *s_ring,
> 
>  	if (d_idx + count <= ring_size) {
>  		rte_memcpy(d_ring + d_idx, s_ring + s_idx, count * elem_size);
> +

Do we need a blank line here?

Thanks,
Chenbo

>  	} else {
>  		uint16_t size = ring_size - d_idx;
> 
> @@ -2036,7 +2037,7 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
> 
>  		slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq->size;
>  		if (it_pool[it_idx].count) {
> -			uint16_t from, to;
> +			uint16_t from;
> 
>  			async_descs_idx += num_descs;
>  			async_fill_desc(&tdes[pkt_burst_idx++],
> @@ -2055,11 +2056,13 @@ virtio_dev_rx_async_submit_packed(struct virtio_net
> *dev,
>  			 * descriptors.
>  			 */
>  			from = vq->shadow_used_idx - num_buffers;
> -			to = vq->async_buffer_idx_packed % vq->size;
>  			store_dma_desc_info_packed(vq->shadow_used_packed,
> -					vq->async_buffers_packed, vq->size, from, to,
> num_buffers);
> +					vq->async_buffers_packed, vq->size, from,
> +					vq->async_buffer_idx_packed, num_buffers);
> 
>  			vq->async_buffer_idx_packed += num_buffers;
> +			if (vq->async_buffer_idx_packed >= vq->size)
> +				vq->async_buffer_idx_packed -= vq->size;
>  			vq->shadow_used_idx -= num_buffers;
>  		} else {
>  			comp_pkts[num_done_pkts++] = pkts[pkt_idx];
> @@ -2112,6 +2115,8 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
>  		dma_error_handler_packed(vq, async_descs, async_descs_idx,
> slot_idx, pkt_err,
>  					&pkt_idx, &num_async_pkts, &num_done_pkts);
>  	vq->async_pkts_idx += num_async_pkts;
> +	if (vq->async_pkts_idx >= vq->size)
> +		vq->async_pkts_idx -= vq->size;
>  	*comp_count = num_done_pkts;
> 
>  	if (likely(vq->shadow_used_idx)) {
> @@ -2160,7 +2165,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue
> *vq,
>  	uint16_t from, to;
> 
>  	do {
> -		from = vq->last_async_buffer_idx_packed % vq->size;
> +		from = vq->last_async_buffer_idx_packed;
>  		to = (from + nr_left) % vq->size;
>  		if (to > from) {
>  			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
> to - from);
> @@ -2169,7 +2174,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue
> *vq,
>  		} else {
>  			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
>  				vq->size - from);
> -			vq->last_async_buffer_idx_packed += vq->size - from;
> +			vq->last_async_buffer_idx_packed = 0;
>  			nr_left -= vq->size - from;
>  		}
>  	} while (nr_left > 0);
> @@ -2252,10 +2257,13 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid,
> uint16_t queue_id,
>  			vhost_vring_call_split(dev, vq);
>  		}
>  	} else {
> -		if (vq_is_packed(dev))
> +		if (vq_is_packed(dev)) {
>  			vq->last_async_buffer_idx_packed += n_buffers;
> -		else
> +			if (vq->last_async_buffer_idx_packed >= vq->size)
> +				vq->last_async_buffer_idx_packed -= vq->size;
> +		} else {
>  			vq->last_async_desc_idx_split += n_descs;
> +		}
>  	}
> 
>  done:
> --
> 2.29.2


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost
  2021-07-15  8:37 ` Xia, Chenbo
@ 2021-07-15  8:50   ` Jiang, Cheng1
  0 siblings, 0 replies; 6+ messages in thread
From: Jiang, Cheng1 @ 2021-07-15  8:50 UTC (permalink / raw)
  To: Xia, Chenbo, maxime.coquelin; +Cc: dev, Hu, Jiayu, Yang, YvonneX, stable

Hi Chenbo,

> -----Original Message-----
> From: Xia, Chenbo <chenbo.xia@intel.com>
> Sent: Thursday, July 15, 2021 4:37 PM
> To: Jiang, Cheng1 <cheng1.jiang@intel.com>; maxime.coquelin@redhat.com
> Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> <yvonnex.yang@intel.com>; stable@dpdk.org
> Subject: RE: [PATCH] vhost: fix index overflow issue in async vhost
> 
> Hi Cheng,
> 
> > -----Original Message-----
> > From: Jiang, Cheng1 <cheng1.jiang@intel.com>
> > Sent: Thursday, July 8, 2021 6:45 PM
> > To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>
> > Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> > <yvonnex.yang@intel.com>; Jiang, Cheng1 <cheng1.jiang@intel.com>;
> > stable@dpdk.org
> > Subject: [PATCH] vhost: fix index overflow issue in async vhost
> 
> Since this fix is packed ring only, maybe 'fix index overflow for packed ring in
> async vhost' is better.
> 

Sure, that make sense.
I'll fix it in the next version.

> >
> > We introduced some new indexes in async vhost. If we don't pay
> > attention to the management of these indexes, they will eventually
> > overflow and lead to errors. This patch is to check and keep these
> > indexes within a reasonable range.
> 
> Ditto. Should mention packed ring here.

Sure.


> 
> >
> > Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
> > ---
> >  lib/vhost/virtio_net.c | 22 +++++++++++++++-------
> >  1 file changed, 15 insertions(+), 7 deletions(-)
> >
> > diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c index
> > f4a2c88d8b..61cb5a126c 100644
> > --- a/lib/vhost/virtio_net.c
> > +++ b/lib/vhost/virtio_net.c
> > @@ -1614,6 +1614,7 @@ store_dma_desc_info_packed(struct
> > vring_used_elem_packed *s_ring,
> >
> >  	if (d_idx + count <= ring_size) {
> >  		rte_memcpy(d_ring + d_idx, s_ring + s_idx, count *
> elem_size);
> > +
> 
Maybe it's a typo. I'll fix it.

Thanks,
Cheng

> Do we need a blank line here?
> 
> Thanks,
> Chenbo
> 
> >  	} else {
> >  		uint16_t size = ring_size - d_idx;
> >
> > @@ -2036,7 +2037,7 @@ virtio_dev_rx_async_submit_packed(struct
> > virtio_net *dev,
> >
> >  		slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq-
> >size;
> >  		if (it_pool[it_idx].count) {
> > -			uint16_t from, to;
> > +			uint16_t from;
> >
> >  			async_descs_idx += num_descs;
> >  			async_fill_desc(&tdes[pkt_burst_idx++],
> > @@ -2055,11 +2056,13 @@ virtio_dev_rx_async_submit_packed(struct
> > virtio_net *dev,
> >  			 * descriptors.
> >  			 */
> >  			from = vq->shadow_used_idx - num_buffers;
> > -			to = vq->async_buffer_idx_packed % vq->size;
> >  			store_dma_desc_info_packed(vq-
> >shadow_used_packed,
> > -					vq->async_buffers_packed, vq->size,
> from, to,
> > num_buffers);
> > +					vq->async_buffers_packed, vq->size,
> from,
> > +					vq->async_buffer_idx_packed,
> num_buffers);
> >
> >  			vq->async_buffer_idx_packed += num_buffers;
> > +			if (vq->async_buffer_idx_packed >= vq->size)
> > +				vq->async_buffer_idx_packed -= vq->size;
> >  			vq->shadow_used_idx -= num_buffers;
> >  		} else {
> >  			comp_pkts[num_done_pkts++] = pkts[pkt_idx]; @@
> -2112,6 +2115,8 @@
> > virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
> >  		dma_error_handler_packed(vq, async_descs,
> async_descs_idx,
> > slot_idx, pkt_err,
> >  					&pkt_idx, &num_async_pkts,
> &num_done_pkts);
> >  	vq->async_pkts_idx += num_async_pkts;
> > +	if (vq->async_pkts_idx >= vq->size)
> > +		vq->async_pkts_idx -= vq->size;
> >  	*comp_count = num_done_pkts;
> >
> >  	if (likely(vq->shadow_used_idx)) {
> > @@ -2160,7 +2165,7 @@ write_back_completed_descs_packed(struct
> > vhost_virtqueue *vq,
> >  	uint16_t from, to;
> >
> >  	do {
> > -		from = vq->last_async_buffer_idx_packed % vq->size;
> > +		from = vq->last_async_buffer_idx_packed;
> >  		to = (from + nr_left) % vq->size;
> >  		if (to > from) {
> >  			vhost_update_used_packed(vq, vq-
> >async_buffers_packed + from, to -
> > from); @@ -2169,7 +2174,7 @@
> write_back_completed_descs_packed(struct
> > vhost_virtqueue *vq,
> >  		} else {
> >  			vhost_update_used_packed(vq, vq-
> >async_buffers_packed + from,
> >  				vq->size - from);
> > -			vq->last_async_buffer_idx_packed += vq->size -
> from;
> > +			vq->last_async_buffer_idx_packed = 0;
> >  			nr_left -= vq->size - from;
> >  		}
> >  	} while (nr_left > 0);
> > @@ -2252,10 +2257,13 @@ uint16_t
> rte_vhost_poll_enqueue_completed(int
> > vid, uint16_t queue_id,
> >  			vhost_vring_call_split(dev, vq);
> >  		}
> >  	} else {
> > -		if (vq_is_packed(dev))
> > +		if (vq_is_packed(dev)) {
> >  			vq->last_async_buffer_idx_packed += n_buffers;
> > -		else
> > +			if (vq->last_async_buffer_idx_packed >= vq->size)
> > +				vq->last_async_buffer_idx_packed -= vq-
> >size;
> > +		} else {
> >  			vq->last_async_desc_idx_split += n_descs;
> > +		}
> >  	}
> >
> >  done:
> > --
> > 2.29.2


^ permalink raw reply	[flat|nested] 6+ messages in thread

* [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring in async vhost
  2021-07-08 10:44 [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost Cheng Jiang
  2021-07-15  8:37 ` Xia, Chenbo
@ 2021-07-15  9:50 ` Cheng Jiang
  2021-07-16  2:30   ` Xia, Chenbo
  2021-07-20  2:44   ` Xia, Chenbo
  1 sibling, 2 replies; 6+ messages in thread
From: Cheng Jiang @ 2021-07-15  9:50 UTC (permalink / raw)
  To: maxime.coquelin, Chenbo.Xia
  Cc: dev, jiayu.hu, yvonnex.yang, Cheng Jiang, stable

We introduced some new indexes in packed ring of async vhost. They
will eventually overflow and lead to errors if the ring size is not
a power of 2. This patch is to check and keep these indexes within a
reasonable range.

Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
Cc: stable@dpdk.org

Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
---
 lib/vhost/virtio_net.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
index f4a2c88d8b..bfb2bf8fc4 100644
--- a/lib/vhost/virtio_net.c
+++ b/lib/vhost/virtio_net.c
@@ -2036,7 +2036,7 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 
 		slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq->size;
 		if (it_pool[it_idx].count) {
-			uint16_t from, to;
+			uint16_t from;
 
 			async_descs_idx += num_descs;
 			async_fill_desc(&tdes[pkt_burst_idx++],
@@ -2055,11 +2055,13 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 			 * descriptors.
 			 */
 			from = vq->shadow_used_idx - num_buffers;
-			to = vq->async_buffer_idx_packed % vq->size;
 			store_dma_desc_info_packed(vq->shadow_used_packed,
-					vq->async_buffers_packed, vq->size, from, to, num_buffers);
+					vq->async_buffers_packed, vq->size, from,
+					vq->async_buffer_idx_packed, num_buffers);
 
 			vq->async_buffer_idx_packed += num_buffers;
+			if (vq->async_buffer_idx_packed >= vq->size)
+				vq->async_buffer_idx_packed -= vq->size;
 			vq->shadow_used_idx -= num_buffers;
 		} else {
 			comp_pkts[num_done_pkts++] = pkts[pkt_idx];
@@ -2112,6 +2114,8 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
 		dma_error_handler_packed(vq, async_descs, async_descs_idx, slot_idx, pkt_err,
 					&pkt_idx, &num_async_pkts, &num_done_pkts);
 	vq->async_pkts_idx += num_async_pkts;
+	if (vq->async_pkts_idx >= vq->size)
+		vq->async_pkts_idx -= vq->size;
 	*comp_count = num_done_pkts;
 
 	if (likely(vq->shadow_used_idx)) {
@@ -2160,7 +2164,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue *vq,
 	uint16_t from, to;
 
 	do {
-		from = vq->last_async_buffer_idx_packed % vq->size;
+		from = vq->last_async_buffer_idx_packed;
 		to = (from + nr_left) % vq->size;
 		if (to > from) {
 			vhost_update_used_packed(vq, vq->async_buffers_packed + from, to - from);
@@ -2169,7 +2173,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue *vq,
 		} else {
 			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
 				vq->size - from);
-			vq->last_async_buffer_idx_packed += vq->size - from;
+			vq->last_async_buffer_idx_packed = 0;
 			nr_left -= vq->size - from;
 		}
 	} while (nr_left > 0);
@@ -2252,10 +2256,13 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
 			vhost_vring_call_split(dev, vq);
 		}
 	} else {
-		if (vq_is_packed(dev))
+		if (vq_is_packed(dev)) {
 			vq->last_async_buffer_idx_packed += n_buffers;
-		else
+			if (vq->last_async_buffer_idx_packed >= vq->size)
+				vq->last_async_buffer_idx_packed -= vq->size;
+		} else {
 			vq->last_async_desc_idx_split += n_descs;
+		}
 	}
 
 done:
-- 
2.29.2


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring in async vhost
  2021-07-15  9:50 ` [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring " Cheng Jiang
@ 2021-07-16  2:30   ` Xia, Chenbo
  2021-07-20  2:44   ` Xia, Chenbo
  1 sibling, 0 replies; 6+ messages in thread
From: Xia, Chenbo @ 2021-07-16  2:30 UTC (permalink / raw)
  To: Jiang, Cheng1, maxime.coquelin; +Cc: dev, Hu, Jiayu, Yang, YvonneX, stable

> -----Original Message-----
> From: Jiang, Cheng1 <cheng1.jiang@intel.com>
> Sent: Thursday, July 15, 2021 5:51 PM
> To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>
> Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> <yvonnex.yang@intel.com>; Jiang, Cheng1 <cheng1.jiang@intel.com>;
> stable@dpdk.org
> Subject: [PATCH v2] vhost: fix index overflow for packed ring in async vhost
> 
> We introduced some new indexes in packed ring of async vhost. They
> will eventually overflow and lead to errors if the ring size is not
> a power of 2. This patch is to check and keep these indexes within a
> reasonable range.
> 
> Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
> ---
>  lib/vhost/virtio_net.c | 21 ++++++++++++++-------
>  1 file changed, 14 insertions(+), 7 deletions(-)
> 
> diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
> index f4a2c88d8b..bfb2bf8fc4 100644
> --- a/lib/vhost/virtio_net.c
> +++ b/lib/vhost/virtio_net.c
> @@ -2036,7 +2036,7 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
> 
>  		slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq->size;
>  		if (it_pool[it_idx].count) {
> -			uint16_t from, to;
> +			uint16_t from;
> 
>  			async_descs_idx += num_descs;
>  			async_fill_desc(&tdes[pkt_burst_idx++],
> @@ -2055,11 +2055,13 @@ virtio_dev_rx_async_submit_packed(struct virtio_net
> *dev,
>  			 * descriptors.
>  			 */
>  			from = vq->shadow_used_idx - num_buffers;
> -			to = vq->async_buffer_idx_packed % vq->size;
>  			store_dma_desc_info_packed(vq->shadow_used_packed,
> -					vq->async_buffers_packed, vq->size, from, to,
> num_buffers);
> +					vq->async_buffers_packed, vq->size, from,
> +					vq->async_buffer_idx_packed, num_buffers);
> 
>  			vq->async_buffer_idx_packed += num_buffers;
> +			if (vq->async_buffer_idx_packed >= vq->size)
> +				vq->async_buffer_idx_packed -= vq->size;
>  			vq->shadow_used_idx -= num_buffers;
>  		} else {
>  			comp_pkts[num_done_pkts++] = pkts[pkt_idx];
> @@ -2112,6 +2114,8 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
>  		dma_error_handler_packed(vq, async_descs, async_descs_idx,
> slot_idx, pkt_err,
>  					&pkt_idx, &num_async_pkts, &num_done_pkts);
>  	vq->async_pkts_idx += num_async_pkts;
> +	if (vq->async_pkts_idx >= vq->size)
> +		vq->async_pkts_idx -= vq->size;
>  	*comp_count = num_done_pkts;
> 
>  	if (likely(vq->shadow_used_idx)) {
> @@ -2160,7 +2164,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue
> *vq,
>  	uint16_t from, to;
> 
>  	do {
> -		from = vq->last_async_buffer_idx_packed % vq->size;
> +		from = vq->last_async_buffer_idx_packed;
>  		to = (from + nr_left) % vq->size;
>  		if (to > from) {
>  			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
> to - from);
> @@ -2169,7 +2173,7 @@ write_back_completed_descs_packed(struct vhost_virtqueue
> *vq,
>  		} else {
>  			vhost_update_used_packed(vq, vq->async_buffers_packed + from,
>  				vq->size - from);
> -			vq->last_async_buffer_idx_packed += vq->size - from;
> +			vq->last_async_buffer_idx_packed = 0;
>  			nr_left -= vq->size - from;
>  		}
>  	} while (nr_left > 0);
> @@ -2252,10 +2256,13 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid,
> uint16_t queue_id,
>  			vhost_vring_call_split(dev, vq);
>  		}
>  	} else {
> -		if (vq_is_packed(dev))
> +		if (vq_is_packed(dev)) {
>  			vq->last_async_buffer_idx_packed += n_buffers;
> -		else
> +			if (vq->last_async_buffer_idx_packed >= vq->size)
> +				vq->last_async_buffer_idx_packed -= vq->size;
> +		} else {
>  			vq->last_async_desc_idx_split += n_descs;
> +		}
>  	}
> 
>  done:
> --
> 2.29.2

Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring in async vhost
  2021-07-15  9:50 ` [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring " Cheng Jiang
  2021-07-16  2:30   ` Xia, Chenbo
@ 2021-07-20  2:44   ` Xia, Chenbo
  1 sibling, 0 replies; 6+ messages in thread
From: Xia, Chenbo @ 2021-07-20  2:44 UTC (permalink / raw)
  To: Jiang, Cheng1, maxime.coquelin; +Cc: dev, Hu, Jiayu, Yang, YvonneX, stable

> -----Original Message-----
> From: Jiang, Cheng1 <cheng1.jiang@intel.com>
> Sent: Thursday, July 15, 2021 5:51 PM
> To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>
> Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> <yvonnex.yang@intel.com>; Jiang, Cheng1 <cheng1.jiang@intel.com>;
> stable@dpdk.org
> Subject: [PATCH v2] vhost: fix index overflow for packed ring in async vhost
> 
> We introduced some new indexes in packed ring of async vhost. They
> will eventually overflow and lead to errors if the ring size is not
> a power of 2. This patch is to check and keep these indexes within a
> reasonable range.
> 
> Fixes: 873e8dad6f49 ("vhost: support packed ring in async datapath")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
> ---
> --
> 2.29.2

Applied to next-virtio/main, thanks.

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2021-07-20  2:45 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-07-08 10:44 [dpdk-stable] [PATCH] vhost: fix index overflow issue in async vhost Cheng Jiang
2021-07-15  8:37 ` Xia, Chenbo
2021-07-15  8:50   ` Jiang, Cheng1
2021-07-15  9:50 ` [dpdk-stable] [PATCH v2] vhost: fix index overflow for packed ring " Cheng Jiang
2021-07-16  2:30   ` Xia, Chenbo
2021-07-20  2:44   ` Xia, Chenbo

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).