[RFC,net-next,v4,1/2] IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver

Message ID 20221202221213.236564-1-lixiaoyan@google.com
State New
Headers
Series [RFC,net-next,v4,1/2] IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver |

Commit Message

Coco Li Dec. 2, 2022, 10:12 p.m. UTC
  IPv6/TCP and GRO stacks can build big TCP packets with an added
temporary Hop By Hop header.

Is GSO is not involved, then the temporary header needs to be removed in
the driver. This patch provides a generic helper for drivers that need
to modify their headers in place.

Signed-off-by: Coco Li <lixiaoyan@google.com>
---
 include/net/ipv6.h     | 35 +++++++++++++++++++++++++++++++++++
 net/ipv6/ip6_offload.c | 27 ++++-----------------------
 2 files changed, 39 insertions(+), 23 deletions(-)
  

Comments

Michael Chan Dec. 5, 2022, 2:23 a.m. UTC | #1
On Fri, Dec 2, 2022 at 2:12 PM Coco Li <lixiaoyan@google.com> wrote:
>
> IPv6/TCP and GRO stacks can build big TCP packets with an added
> temporary Hop By Hop header.
>
> Is GSO is not involved, then the temporary header needs to be removed in
> the driver. This patch provides a generic helper for drivers that need
> to modify their headers in place.
>
> Signed-off-by: Coco Li <lixiaoyan@google.com>
> ---
>  include/net/ipv6.h     | 35 +++++++++++++++++++++++++++++++++++
>  net/ipv6/ip6_offload.c | 27 ++++-----------------------
>  2 files changed, 39 insertions(+), 23 deletions(-)
>
> diff --git a/include/net/ipv6.h b/include/net/ipv6.h
> index d383c895592a..08adec74f067 100644
> --- a/include/net/ipv6.h
> +++ b/include/net/ipv6.h
> @@ -500,6 +500,41 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
>         return jhdr->nexthdr;
>  }
>
> +/* Return 0 if HBH header is successfully removed
> + * Or if HBH removal is unnecessary (packet is not big TCP)
> + * Return error to indicate dropping the packet
> + */
> +static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb)
> +{
> +       const int hophdr_len = sizeof(struct hop_jumbo_hdr);
> +       int nexthdr = ipv6_has_hopopt_jumbo(skb);
> +       struct ipv6hdr *h6;
> +
> +       if (!nexthdr)
> +               return 0;
> +
> +       if (skb_cow_head(skb, 0))
> +               return -1;
> +
> +       /* Remove the HBH header.
> +        * Layout: [Ethernet header][IPv6 header][HBH][L4 Header]
> +        */
> +       memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb),
> +               skb_network_header(skb) - skb_mac_header(skb) +
> +               sizeof(struct ipv6hdr));
> +
> +       if (unlikely(!pskb_may_pull(skb, hophdr_len)))
> +               return -1;
> +

This version doesn't seem to work.  I think you need to add hophdr_len
to skb->data and subtract it from skb->len.

> +       skb->network_header += hophdr_len;
> +       skb->mac_header += hophdr_len;
> +
> +       h6 = ipv6_hdr(skb);
> +       h6->nexthdr = nexthdr;
> +
> +       return 0;
> +}
> +
>  static inline bool ipv6_accept_ra(struct inet6_dev *idev)
>  {
>         /* If forwarding is enabled, RA are not accepted unless the special
> diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
> index 3ee345672849..00dc2e3b0184 100644
> --- a/net/ipv6/ip6_offload.c
> +++ b/net/ipv6/ip6_offload.c
> @@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
>         struct sk_buff *segs = ERR_PTR(-EINVAL);
>         struct ipv6hdr *ipv6h;
>         const struct net_offload *ops;
> -       int proto, nexthdr;
> +       int proto, err;
>         struct frag_hdr *fptr;
>         unsigned int payload_len;
>         u8 *prevhdr;
> @@ -87,28 +87,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
>         bool gso_partial;
>
>         skb_reset_network_header(skb);
> -       nexthdr = ipv6_has_hopopt_jumbo(skb);
> -       if (nexthdr) {
> -               const int hophdr_len = sizeof(struct hop_jumbo_hdr);
> -               int err;
> -
> -               err = skb_cow_head(skb, 0);
> -               if (err < 0)
> -                       return ERR_PTR(err);
> -
> -               /* remove the HBH header.
> -                * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
> -                */
> -               memmove(skb_mac_header(skb) + hophdr_len,
> -                       skb_mac_header(skb),
> -                       ETH_HLEN + sizeof(struct ipv6hdr));
> -               skb->data += hophdr_len;
> -               skb->len -= hophdr_len;
> -               skb->network_header += hophdr_len;
> -               skb->mac_header += hophdr_len;
> -               ipv6h = (struct ipv6hdr *)skb->data;
> -               ipv6h->nexthdr = nexthdr;
> -       }
> +       err = ipv6_hopopt_jumbo_remove(skb);
> +       if (err)
> +               return ERR_PTR(err);
>         nhoff = skb_network_header(skb) - skb_mac_header(skb);
>         if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
>                 goto out;
> --
> 2.39.0.rc0.267.gcb52ba06e7-goog
>
  
Eric Dumazet Dec. 5, 2022, 5:11 a.m. UTC | #2
On Fri, Dec 2, 2022 at 11:12 PM Coco Li <lixiaoyan@google.com> wrote:
>
> IPv6/TCP and GRO stacks can build big TCP packets with an added
> temporary Hop By Hop header.
>
> Is GSO is not involved, then the temporary header needs to be removed in
> the driver. This patch provides a generic helper for drivers that need
> to modify their headers in place.
>
> Signed-off-by: Coco Li <lixiaoyan@google.com>
> ---
>  include/net/ipv6.h     | 35 +++++++++++++++++++++++++++++++++++
>  net/ipv6/ip6_offload.c | 27 ++++-----------------------
>  2 files changed, 39 insertions(+), 23 deletions(-)
>
> diff --git a/include/net/ipv6.h b/include/net/ipv6.h
> index d383c895592a..08adec74f067 100644
> --- a/include/net/ipv6.h
> +++ b/include/net/ipv6.h
> @@ -500,6 +500,41 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
>         return jhdr->nexthdr;
>  }
>
> +/* Return 0 if HBH header is successfully removed
> + * Or if HBH removal is unnecessary (packet is not big TCP)
> + * Return error to indicate dropping the packet
> + */
> +static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb)
> +{
> +       const int hophdr_len = sizeof(struct hop_jumbo_hdr);
> +       int nexthdr = ipv6_has_hopopt_jumbo(skb);
> +       struct ipv6hdr *h6;
> +
> +       if (!nexthdr)
> +               return 0;
> +
> +       if (skb_cow_head(skb, 0))
> +               return -1;
> +
> +       /* Remove the HBH header.
> +        * Layout: [Ethernet header][IPv6 header][HBH][L4 Header]
> +        */
> +       memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb),
> +               skb_network_header(skb) - skb_mac_header(skb) +
> +               sizeof(struct ipv6hdr));
> +

> +       if (unlikely(!pskb_may_pull(skb, hophdr_len)))
> +               return -1;
> +
> +       skb->network_header += hophdr_len;
> +       skb->mac_header += hophdr_len;
> +
> +       h6 = ipv6_hdr(skb);
> +       h6->nexthdr = nexthdr;

Coco, I think you should test this patch on one of your host (no need
for bnxt NIC) and

ethtool -K eth1 tso off

Thanks.

> +
> +       return 0;
> +}
> +
>  static inline bool ipv6_accept_ra(struct inet6_dev *idev)
>  {
>         /* If forwarding is enabled, RA are not accepted unless the special
> diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
> index 3ee345672849..00dc2e3b0184 100644
> --- a/net/ipv6/ip6_offload.c
> +++ b/net/ipv6/ip6_offload.c
> @@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
>         struct sk_buff *segs = ERR_PTR(-EINVAL);
>         struct ipv6hdr *ipv6h;
>         const struct net_offload *ops;
> -       int proto, nexthdr;
> +       int proto, err;
>         struct frag_hdr *fptr;
>         unsigned int payload_len;
>         u8 *prevhdr;
> @@ -87,28 +87,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
>         bool gso_partial;
>
>         skb_reset_network_header(skb);
> -       nexthdr = ipv6_has_hopopt_jumbo(skb);
> -       if (nexthdr) {
> -               const int hophdr_len = sizeof(struct hop_jumbo_hdr);
> -               int err;
> -
> -               err = skb_cow_head(skb, 0);
> -               if (err < 0)
> -                       return ERR_PTR(err);
> -
> -               /* remove the HBH header.
> -                * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
> -                */
> -               memmove(skb_mac_header(skb) + hophdr_len,
> -                       skb_mac_header(skb),
> -                       ETH_HLEN + sizeof(struct ipv6hdr));
> -               skb->data += hophdr_len;
> -               skb->len -= hophdr_len;
> -               skb->network_header += hophdr_len;
> -               skb->mac_header += hophdr_len;
> -               ipv6h = (struct ipv6hdr *)skb->data;
> -               ipv6h->nexthdr = nexthdr;
> -       }
> +       err = ipv6_hopopt_jumbo_remove(skb);
> +       if (err)
> +               return ERR_PTR(err);
>         nhoff = skb_network_header(skb) - skb_mac_header(skb);
>         if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
>                 goto out;
> --
> 2.39.0.rc0.267.gcb52ba06e7-goog
>
  

Patch

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d383c895592a..08adec74f067 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -500,6 +500,41 @@  static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
 	return jhdr->nexthdr;
 }
 
+/* Return 0 if HBH header is successfully removed
+ * Or if HBH removal is unnecessary (packet is not big TCP)
+ * Return error to indicate dropping the packet
+ */
+static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb)
+{
+	const int hophdr_len = sizeof(struct hop_jumbo_hdr);
+	int nexthdr = ipv6_has_hopopt_jumbo(skb);
+	struct ipv6hdr *h6;
+
+	if (!nexthdr)
+		return 0;
+
+	if (skb_cow_head(skb, 0))
+		return -1;
+
+	/* Remove the HBH header.
+	 * Layout: [Ethernet header][IPv6 header][HBH][L4 Header]
+	 */
+	memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb),
+		skb_network_header(skb) - skb_mac_header(skb) +
+		sizeof(struct ipv6hdr));
+
+	if (unlikely(!pskb_may_pull(skb, hophdr_len)))
+		return -1;
+
+	skb->network_header += hophdr_len;
+	skb->mac_header += hophdr_len;
+
+	h6 = ipv6_hdr(skb);
+	h6->nexthdr = nexthdr;
+
+	return 0;
+}
+
 static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 {
 	/* If forwarding is enabled, RA are not accepted unless the special
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 3ee345672849..00dc2e3b0184 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -77,7 +77,7 @@  static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct ipv6hdr *ipv6h;
 	const struct net_offload *ops;
-	int proto, nexthdr;
+	int proto, err;
 	struct frag_hdr *fptr;
 	unsigned int payload_len;
 	u8 *prevhdr;
@@ -87,28 +87,9 @@  static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	bool gso_partial;
 
 	skb_reset_network_header(skb);
-	nexthdr = ipv6_has_hopopt_jumbo(skb);
-	if (nexthdr) {
-		const int hophdr_len = sizeof(struct hop_jumbo_hdr);
-		int err;
-
-		err = skb_cow_head(skb, 0);
-		if (err < 0)
-			return ERR_PTR(err);
-
-		/* remove the HBH header.
-		 * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
-		 */
-		memmove(skb_mac_header(skb) + hophdr_len,
-			skb_mac_header(skb),
-			ETH_HLEN + sizeof(struct ipv6hdr));
-		skb->data += hophdr_len;
-		skb->len -= hophdr_len;
-		skb->network_header += hophdr_len;
-		skb->mac_header += hophdr_len;
-		ipv6h = (struct ipv6hdr *)skb->data;
-		ipv6h->nexthdr = nexthdr;
-	}
+	err = ipv6_hopopt_jumbo_remove(skb);
+	if (err)
+		return ERR_PTR(err);
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
 		goto out;