On 2018/11/10 3:43, Cong Wang wrote:
> Currently netdev_rx_csum_fault() only shows a device name,
> we need more information about the skb for debugging.
>
> Sample output:
>
> ens3: hw csum failure
> dev features: 0x0000000000014b89
> skb len=84 data_len=0 gso_size=0 gso_type=0 ip_summed=0 csum=0,
> csum_complete_sw=0, csum_valid=0
>
> Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com>
> ---
> include/linux/netdevice.h | 5 +++--
> net/core/datagram.c | 6 +++---
> net/core/dev.c | 10 ++++++++--
> net/sunrpc/socklib.c | 2 +-
> 4 files changed, 15 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 857f8abf7b91..fabcd9fa6cf7 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -4332,9 +4332,10 @@ static inline bool
> can_checksum_protocol(netdev_features_t features,
> }
>
> #ifdef CONFIG_BUG
> -void netdev_rx_csum_fault(struct net_device *dev);
> +void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb);
> #else
> -static inline void netdev_rx_csum_fault(struct net_device *dev)
> +static inline void netdev_rx_csum_fault(struct net_device *dev,
> + struct sk_buff *skb)
> {
> }
> #endif
> diff --git a/net/core/datagram.c b/net/core/datagram.c
> index 57f3a6fcfc1e..d8f4d55cd6c5 100644
> --- a/net/core/datagram.c
> +++ b/net/core/datagram.c
> @@ -736,7 +736,7 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb,
> int len)
> if (likely(!sum)) {
> if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
> !skb->csum_complete_sw)
> - netdev_rx_csum_fault(skb->dev);
> + netdev_rx_csum_fault(skb->dev, skb);
> }
> if (!skb_shared(skb))
> skb->csum_valid = !sum;
> @@ -756,7 +756,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
> if (likely(!sum)) {
> if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
> !skb->csum_complete_sw)
> - netdev_rx_csum_fault(skb->dev);
> + netdev_rx_csum_fault(skb->dev, skb);
> }
>
> if (!skb_shared(skb)) {
> @@ -810,7 +810,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
>
> if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
> !skb->csum_complete_sw)
> - netdev_rx_csum_fault(NULL);
> + netdev_rx_csum_fault(NULL, skb);
> }
> return 0;
> fault:
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 0ffcbdd55fa9..2b337df26117 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -3091,10 +3091,16 @@ EXPORT_SYMBOL(__skb_gso_segment);
>
> /* Take action when hardware reception checksum errors are detected. */
> #ifdef CONFIG_BUG
> -void netdev_rx_csum_fault(struct net_device *dev)
> +void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
> {
> if (net_ratelimit()) {
> pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
> + if (dev)
> + pr_err("dev features: %pNF\n", &dev->features);
> + pr_err("skb len=%d data_len=%d gso_size=%d gso_type=%d
> ip_summed=%d csum=%x, csum_complete_sw=%d, csum_valid=%d\n",
> + skb->len, skb->data_len, skb_shinfo(skb)->gso_size,
> + skb_shinfo(skb)->gso_type, skb->ip_summed, skb->csum,
> + skb->csum_complete_sw, skb->csum_valid);
This function also have the netdev available, use netdev_err to log the error?
Also, dev->features was dumped before this patch, why remove it?
> dump_stack();
> }
> }
> @@ -5779,7 +5785,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
> if (likely(!sum)) {
> if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
> !skb->csum_complete_sw)
> - netdev_rx_csum_fault(skb->dev);
> + netdev_rx_csum_fault(skb->dev, skb);
> }
>
> NAPI_GRO_CB(skb)->csum = wsum;
> diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
> index 9062967575c4..7e55cfc69697 100644
> --- a/net/sunrpc/socklib.c
> +++ b/net/sunrpc/socklib.c
> @@ -175,7 +175,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct
> sk_buff *skb)
> return -1;
> if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
> !skb->csum_complete_sw)
> - netdev_rx_csum_fault(skb->dev);
> + netdev_rx_csum_fault(skb->dev, skb);
> return 0;
> no_checksum:
> if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
>
