[PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Petri Gynther]

1. Add bytes_compl local variable to collect transmitted bytes
   - dev->stats updates can then be moved outside the while-loop
   - bytes_compl is also needed for future BQL support
2. When bcmgenet device uses Tx checksum offload, each transmitted
   skb has an extra 64-byte header prepended to it. This needs to
   be deducted when counting transmitted bytes.
3. skb->len covers the entire length of skb, whether it is linear or
   fragmented. Thus, when we clean the fragments, do not increase
   transmitted bytes.

Signed-off-by: Petri Gynther <pgynther@google.com>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 6746fd0..9990582 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1171,6 +1171,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
+	unsigned int bytes_compl = 0;
 	unsigned int c_index;
 	unsigned int txbds_ready;
 	unsigned int txbds_processed = 0;
@@ -1193,16 +1194,14 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 		tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr];
 		if (tx_cb_ptr->skb) {
 			pkts_compl++;
-			dev->stats.tx_packets++;
-			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
+			bytes_compl += tx_cb_ptr->skb->len -
+				       (priv->desc_64b_en ? 64 : 0);
 			dma_unmap_single(&dev->dev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
 					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
-			dev->stats.tx_bytes +=
-				dma_unmap_len(tx_cb_ptr, dma_len);
 			dma_unmap_page(&dev->dev,
 				       dma_unmap_addr(tx_cb_ptr, dma_addr),
 				       dma_unmap_len(tx_cb_ptr, dma_len),
@@ -1220,6 +1219,9 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	ring->free_bds += txbds_processed;
 	ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
 
+	dev->stats.tx_packets += pkts_compl;
+	dev->stats.tx_bytes += bytes_compl;
+
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
 		txq = netdev_get_tx_queue(dev, ring->queue);
 		if (netif_tx_queue_stopped(txq))
-- 
2.8.0.rc3.226.g39d4020

[PATCH net 2/2] net: bcmgenet: fix skb_len in bcmgenet_xmit_single()

[Petri Gynther]

skb_len needs to be skb_headlen(skb) in bcmgenet_xmit_single().

Fragmented skbs can have only Ethernet + IP + TCP headers (14+20+20=54 bytes)
in the linear buffer, followed by the rest in fragments. Bumping skb_len to
ETH_ZLEN would be incorrect for this case, as it would introduce garbage
between TCP header and the fragment data.

This also works with regular/non-fragmented small packets < ETH_ZLEN bytes.
Successfully tested this on GENETv3 with 42-byte ARP frames.

For testing, I used:
ethtool -K eth0 tx-checksum-ipv4 off
ethtool -K eth0 tx-checksum-ipv6 off
echo 0 > /proc/sys/net/ipv4/tcp_timestamps

Signed-off-by: Petri Gynther <pgynther@google.com>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9990582..00da239 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1298,7 +1298,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 
 	tx_cb_ptr->skb = skb;
 
-	skb_len = skb_headlen(skb) < ETH_ZLEN ? ETH_ZLEN : skb_headlen(skb);
+	skb_len = skb_headlen(skb);
 
 	mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE);
 	ret = dma_mapping_error(kdev, mapping);
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH net 2/2] net: bcmgenet: fix skb_len in bcmgenet_xmit_single()

[Eric Dumazet]

On Wed, 2016-03-23 at 13:01 -0700, Petri Gynther wrote:
> skb_len needs to be skb_headlen(skb) in bcmgenet_xmit_single().
> 
> Fragmented skbs can have only Ethernet + IP + TCP headers (14+20+20=54 bytes)
> in the linear buffer, followed by the rest in fragments. Bumping skb_len to
> ETH_ZLEN would be incorrect for this case, as it would introduce garbage
> between TCP header and the fragment data.
> 
> This also works with regular/non-fragmented small packets < ETH_ZLEN bytes.
> Successfully tested this on GENETv3 with 42-byte ARP frames.
> 
> For testing, I used:
> ethtool -K eth0 tx-checksum-ipv4 off
> ethtool -K eth0 tx-checksum-ipv6 off
> echo 0 > /proc/sys/net/ipv4/tcp_timestamps
> 
> Signed-off-by: Petri Gynther <pgynther@google.com>
> ---
>  drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> index 9990582..00da239 100644
> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> @@ -1298,7 +1298,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
>  
>  	tx_cb_ptr->skb = skb;
>  
> -	skb_len = skb_headlen(skb) < ETH_ZLEN ? ETH_ZLEN : skb_headlen(skb);
> +	skb_len = skb_headlen(skb);
>  
>  	mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE);
>  	ret = dma_mapping_error(kdev, mapping);

Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Eric Dumazet]

On Wed, 2016-03-23 at 13:01 -0700, Petri Gynther wrote:
> 1. Add bytes_compl local variable to collect transmitted bytes
>    - dev->stats updates can then be moved outside the while-loop
>    - bytes_compl is also needed for future BQL support
> 2. When bcmgenet device uses Tx checksum offload, each transmitted
>    skb has an extra 64-byte header prepended to it. This needs to
>    be deducted when counting transmitted bytes.
> 3. skb->len covers the entire length of skb, whether it is linear or
>    fragmented. Thus, when we clean the fragments, do not increase
>    transmitted bytes.
> 
> Signed-off-by: Petri Gynther <pgynther@google.com>
> ---
>  drivers/net/ethernet/broadcom/genet/bcmgenet.c | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> index 6746fd0..9990582 100644
> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
> @@ -1171,6 +1171,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
>  	struct enet_cb *tx_cb_ptr;
>  	struct netdev_queue *txq;
>  	unsigned int pkts_compl = 0;
> +	unsigned int bytes_compl = 0;
>  	unsigned int c_index;
>  	unsigned int txbds_ready;
>  	unsigned int txbds_processed = 0;
> @@ -1193,16 +1194,14 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
>  		tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr];
>  		if (tx_cb_ptr->skb) {
>  			pkts_compl++;
> -			dev->stats.tx_packets++;
> -			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
> +			bytes_compl += tx_cb_ptr->skb->len -
> +				       (priv->desc_64b_en ? 64 : 0);

Please do not use this 64 scalar, prefer sizeof(struct status_64)

I know this driver uses skb_pull(skb, 64); len -= 64; in
bcmgenet_desc_rx(), but I would prefer not adding magic values.

Thanks.

Re: [PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Florian Fainelli]

On March 23, 2016 2:23:57 PM PDT, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>On Wed, 2016-03-23 at 13:01 -0700, Petri Gynther wrote:
>> 1. Add bytes_compl local variable to collect transmitted bytes
>>    - dev->stats updates can then be moved outside the while-loop
>>    - bytes_compl is also needed for future BQL support
>> 2. When bcmgenet device uses Tx checksum offload, each transmitted
>>    skb has an extra 64-byte header prepended to it. This needs to
>>    be deducted when counting transmitted bytes.
>> 3. skb->len covers the entire length of skb, whether it is linear or
>>    fragmented. Thus, when we clean the fragments, do not increase
>>    transmitted bytes.
>> 
>> Signed-off-by: Petri Gynther <pgynther@google.com>
>> ---
>>  drivers/net/ethernet/broadcom/genet/bcmgenet.c | 10 ++++++----
>>  1 file changed, 6 insertions(+), 4 deletions(-)
>> 
>> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> index 6746fd0..9990582 100644
>> --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>> @@ -1171,6 +1171,7 @@ static unsigned int
>__bcmgenet_tx_reclaim(struct net_device *dev,
>>  	struct enet_cb *tx_cb_ptr;
>>  	struct netdev_queue *txq;
>>  	unsigned int pkts_compl = 0;
>> +	unsigned int bytes_compl = 0;
>>  	unsigned int c_index;
>>  	unsigned int txbds_ready;
>>  	unsigned int txbds_processed = 0;
>> @@ -1193,16 +1194,14 @@ static unsigned int
>__bcmgenet_tx_reclaim(struct net_device *dev,
>>  		tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr];
>>  		if (tx_cb_ptr->skb) {
>>  			pkts_compl++;
>> -			dev->stats.tx_packets++;
>> -			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
>> +			bytes_compl += tx_cb_ptr->skb->len -
>> +				       (priv->desc_64b_en ? 64 : 0);
>
>Please do not use this 64 scalar, prefer sizeof(struct status_64)
>
>I know this driver uses skb_pull(skb, 64); len -= 64; in
>bcmgenet_desc_rx(), but I would prefer not adding magic values.

Agreed, and just so we are more robust and ready to add BQL in the features please store this information in skb->cb, in the same spirit as what this does:

https://github.com/ffainelli/linux/commits/genet-bql

Thanks.

-- 
Florian

Re: [PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Florian Fainelli]

On March 23, 2016 1:01:28 PM PDT, Petri Gynther <pgynther@google.com> wrote:
>1. Add bytes_compl local variable to collect transmitted bytes
>   - dev->stats updates can then be moved outside the while-loop
>   - bytes_compl is also needed for future BQL support
>2. When bcmgenet device uses Tx checksum offload, each transmitted
>   skb has an extra 64-byte header prepended to it. This needs to
>   be deducted when counting transmitted bytes.
>3. skb->len covers the entire length of skb, whether it is linear or
>   fragmented. Thus, when we clean the fragments, do not increase
>   transmitted bytes.
>
>Signed-off-by: Petri Gynther <pgynther@google.com>

Acked-by: Florian Fainelli <f.fainelli@gmail.com>

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")

-- 
Florian

Re: [PATCH net 1/2] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Florian Fainelli]

On March 23, 2016 1:01:28 PM PDT, Petri Gynther <pgynther@google.com> wrote:
>1. Add bytes_compl local variable to collect transmitted bytes
>   - dev->stats updates can then be moved outside the while-loop
>   - bytes_compl is also needed for future BQL support
>2. When bcmgenet device uses Tx checksum offload, each transmitted
>   skb has an extra 64-byte header prepended to it. This needs to
>   be deducted when counting transmitted bytes.
>3. skb->len covers the entire length of skb, whether it is linear or
>   fragmented. Thus, when we clean the fragments, do not increase
>   transmitted bytes.
>
>Signed-off-by: Petri Gynther <pgynther@google.com>

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")

Acked-by: Florian Fainelli <f.fainelli@gmail.com>

>---
> drivers/net/ethernet/broadcom/genet/bcmgenet.c | 10 ++++++----
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
>diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>index 6746fd0..9990582 100644
>--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
>@@ -1171,6 +1171,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct
>net_device *dev,
> 	struct enet_cb *tx_cb_ptr;
> 	struct netdev_queue *txq;
> 	unsigned int pkts_compl = 0;
>+	unsigned int bytes_compl = 0;
> 	unsigned int c_index;
> 	unsigned int txbds_ready;
> 	unsigned int txbds_processed = 0;
>@@ -1193,16 +1194,14 @@ static unsigned int
>__bcmgenet_tx_reclaim(struct net_device *dev,
> 		tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr];
> 		if (tx_cb_ptr->skb) {
> 			pkts_compl++;
>-			dev->stats.tx_packets++;
>-			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
>+			bytes_compl += tx_cb_ptr->skb->len -
>+				       (priv->desc_64b_en ? 64 : 0);
> 			dma_unmap_single(&dev->dev,
> 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
> 					 dma_unmap_len(tx_cb_ptr, dma_len),
> 					 DMA_TO_DEVICE);
> 			bcmgenet_free_cb(tx_cb_ptr);
> 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
>-			dev->stats.tx_bytes +=
>-				dma_unmap_len(tx_cb_ptr, dma_len);
> 			dma_unmap_page(&dev->dev,
> 				       dma_unmap_addr(tx_cb_ptr, dma_addr),
> 				       dma_unmap_len(tx_cb_ptr, dma_len),
>@@ -1220,6 +1219,9 @@ static unsigned int __bcmgenet_tx_reclaim(struct
>net_device *dev,
> 	ring->free_bds += txbds_processed;
> 	ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
> 
>+	dev->stats.tx_packets += pkts_compl;
>+	dev->stats.tx_bytes += bytes_compl;
>+
> 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
> 		txq = netdev_get_tx_queue(dev, ring->queue);
> 		if (netif_tx_queue_stopped(txq))


-- 
Florian