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

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

[Coco Li]

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;
+
+	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

[RFC net-next v4 2/2] bnxt: Use generic HBH removal helper in tx path

[Coco Li]

Eric Dumazet implemented Big TCP that allowed bigger TSO/GRO packet sizes
for IPv6 traffic. See patch series:
'commit 89527be8d8d6 ("net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes")'

This reduces the number of packets traversing the networking stack and
should usually improves performance. However, it also inserts a
temporary Hop-by-hop IPv6 extension header.

Using the HBH header removal method in the previous path, the extra header
be removed in bnxt drivers to allow it to send big TCP packets (bigger
TSO packets) as well.

Tested:
Compiled locally

To further test functional correctness, update the GSO/GRO limit on the
physical NIC:

ip link set eth0 gso_max_size 181000
ip link set eth0 gro_max_size 181000

Note that if there are bonding or ipvan devices on top of the physical
NIC, their GSO sizes need to be updated as well.

Then, IPv6/TCP packets with sizes larger than 64k can be observed.

Big TCP functionality is tested by Michael, feature checks not yet.

Tested by Michael:
I've confirmed with our hardware team that this is supported by our
chips, and I've tested it up to gso_max_size of 524280.  Thanks.

Tested-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0fe164b42c5d..c2713cb5debd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -389,6 +389,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_BUSY;
 	}
 
+	if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto tx_free;
+
 	length = skb->len;
 	len = skb_headlen(skb);
 	last_frag = skb_shinfo(skb)->nr_frags;
@@ -11342,9 +11345,28 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off,
 
 		if (hdrlen > 64)
 			return false;
+
+		/* The ext header may be a hop-by-hop header inserted for
+		 * big TCP purposes. This will be removed before sending
+		 * from NIC, so do not count it.
+		 */
+		if (*nexthdr == NEXTHDR_HOP) {
+			if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
+				goto increment_hdr;
+
+			struct hop_jumbo_hdr *jhdr = (struct hop_jumbo_hdr *)(nexthdr + hdrlen);
+
+			if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
+			    (jhdr->nexthdr != IPPROTO_TCP && jhdr->nexthdr != IPPROTO_UDP))
+				goto increment_hdr;
+
+			goto next_hdr;
+		}
+increment_hdr:
+		hdr_count++;
+next_hdr:
 		nexthdr = &hp->nexthdr;
 		start += hdrlen;
-		hdr_count++;
 	}
 	if (nextp) {
 		/* Caller will check inner protocol */
@@ -13657,6 +13679,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev->features &= ~NETIF_F_LRO;
 	dev->priv_flags |= IFF_UNICAST_FLT;
 
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 #endif
-- 
2.39.0.rc0.267.gcb52ba06e7-goog

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

[Michael Chan]

[-- Attachment #1: Type: text/plain, Size: 4120 bytes --]

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
>

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4209 bytes --]

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

[Eric Dumazet]

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
>

Re: [RFC net-next v4 2/2] bnxt: Use generic HBH removal helper in tx path

[Eric Dumazet]

On Fri, Dec 2, 2022 at 11:12 PM Coco Li <lixiaoyan@google.com> wrote:
>
> Eric Dumazet implemented Big TCP that allowed bigger TSO/GRO packet sizes
> for IPv6 traffic. See patch series:
> 'commit 89527be8d8d6 ("net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes")'
>
> This reduces the number of packets traversing the networking stack and
> should usually improves performance. However, it also inserts a
> temporary Hop-by-hop IPv6 extension header.
>
> Using the HBH header removal method in the previous path, the extra header
> be removed in bnxt drivers to allow it to send big TCP packets (bigger
> TSO packets) as well.
>
> Tested:
> Compiled locally
>
> To further test functional correctness, update the GSO/GRO limit on the
> physical NIC:
>
> ip link set eth0 gso_max_size 181000
> ip link set eth0 gro_max_size 181000
>
> Note that if there are bonding or ipvan devices on top of the physical
> NIC, their GSO sizes need to be updated as well.
>
> Then, IPv6/TCP packets with sizes larger than 64k can be observed.
>
> Big TCP functionality is tested by Michael, feature checks not yet.
>
> Tested by Michael:
> I've confirmed with our hardware team that this is supported by our
> chips, and I've tested it up to gso_max_size of 524280.  Thanks.
>
> Tested-by: Michael Chan <michael.chan@broadcom.com>
> Reviewed-by: Michael Chan <michael.chan@broadcom.com>
> Signed-off-by: Coco Li <lixiaoyan@google.com>
> ---
>  drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++++++++++++++++++++-
>  1 file changed, 25 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index 0fe164b42c5d..c2713cb5debd 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -389,6 +389,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
>                         return NETDEV_TX_BUSY;
>         }
>
> +       if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
> +               goto tx_free;
> +
>         length = skb->len;
>         len = skb_headlen(skb);
>         last_frag = skb_shinfo(skb)->nr_frags;
> @@ -11342,9 +11345,28 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off,
>
>                 if (hdrlen > 64)
>                         return false;
> +
> +               /* The ext header may be a hop-by-hop header inserted for
> +                * big TCP purposes. This will be removed before sending
> +                * from NIC, so do not count it.
> +                */
> +               if (*nexthdr == NEXTHDR_HOP) {
> +                       if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
> +                               goto increment_hdr;
> +
> +                       struct hop_jumbo_hdr *jhdr = (struct hop_jumbo_hdr *)(nexthdr + hdrlen);

We discourage adding a variable declaration in the middle of code.

> +
> +                       if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
> +                           (jhdr->nexthdr != IPPROTO_TCP && jhdr->nexthdr != IPPROTO_UDP))

Why testing IPPROTO_UDP ? I do not think we support BIG UDP yet.

> +                               goto increment_hdr;
> +
> +                       goto next_hdr;
> +               }
> +increment_hdr:
> +               hdr_count++;
> +next_hdr:
>                 nexthdr = &hp->nexthdr;
>                 start += hdrlen;
> -               hdr_count++;
>         }
>         if (nextp) {
>                 /* Caller will check inner protocol */
> @@ -13657,6 +13679,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
>                 dev->features &= ~NETIF_F_LRO;
>         dev->priv_flags |= IFF_UNICAST_FLT;
>
> +       netif_set_tso_max_size(dev, GSO_MAX_SIZE);
> +
>  #ifdef CONFIG_BNXT_SRIOV
>         init_waitqueue_head(&bp->sriov_cfg_wait);
>  #endif
> --
> 2.39.0.rc0.267.gcb52ba06e7-goog
>

Re: [RFC net-next v4 2/2] bnxt: Use generic HBH removal helper in tx path

[Michael Chan]

[-- Attachment #1: Type: text/plain, Size: 3312 bytes --]

On Sun, Dec 4, 2022 at 9:14 PM Eric Dumazet <edumazet@google.com> wrote:
>
> On Fri, Dec 2, 2022 at 11:12 PM Coco Li <lixiaoyan@google.com> wrote:
> >
> > Eric Dumazet implemented Big TCP that allowed bigger TSO/GRO packet sizes
> > for IPv6 traffic. See patch series:
> > 'commit 89527be8d8d6 ("net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes")'
> >
> > This reduces the number of packets traversing the networking stack and
> > should usually improves performance. However, it also inserts a
> > temporary Hop-by-hop IPv6 extension header.
> >
> > Using the HBH header removal method in the previous path, the extra header
> > be removed in bnxt drivers to allow it to send big TCP packets (bigger
> > TSO packets) as well.
> >
> > Tested:
> > Compiled locally
> >
> > To further test functional correctness, update the GSO/GRO limit on the
> > physical NIC:
> >
> > ip link set eth0 gso_max_size 181000
> > ip link set eth0 gro_max_size 181000
> >
> > Note that if there are bonding or ipvan devices on top of the physical
> > NIC, their GSO sizes need to be updated as well.
> >
> > Then, IPv6/TCP packets with sizes larger than 64k can be observed.
> >
> > Big TCP functionality is tested by Michael, feature checks not yet.
> >
> > Tested by Michael:
> > I've confirmed with our hardware team that this is supported by our
> > chips, and I've tested it up to gso_max_size of 524280.  Thanks.
> >
> > Tested-by: Michael Chan <michael.chan@broadcom.com>
> > Reviewed-by: Michael Chan <michael.chan@broadcom.com>
> > Signed-off-by: Coco Li <lixiaoyan@google.com>
> > ---
> >  drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++++++++++++++++++++-
> >  1 file changed, 25 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> > index 0fe164b42c5d..c2713cb5debd 100644
> > --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> > +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> > @@ -389,6 +389,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
> >                         return NETDEV_TX_BUSY;
> >         }
> >
> > +       if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
> > +               goto tx_free;
> > +
> >         length = skb->len;
> >         len = skb_headlen(skb);
> >         last_frag = skb_shinfo(skb)->nr_frags;
> > @@ -11342,9 +11345,28 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off,
> >
> >                 if (hdrlen > 64)
> >                         return false;
> > +
> > +               /* The ext header may be a hop-by-hop header inserted for
> > +                * big TCP purposes. This will be removed before sending
> > +                * from NIC, so do not count it.
> > +                */
> > +               if (*nexthdr == NEXTHDR_HOP) {
> > +                       if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
> > +                               goto increment_hdr;
> > +
> > +                       struct hop_jumbo_hdr *jhdr = (struct hop_jumbo_hdr *)(nexthdr + hdrlen);
>
> We discourage adding a variable declaration in the middle of code.
>

This doesn't work.  Initially nexthdr points to the nexthdr in the
ipv6 header.  It should be coded like this:

struct hop_jumbo_hdr *jhdr = (struct hop_jumbo_hdr *)hp;

Thanks.

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4209 bytes --]