[PATCH net-next v6 1/2] IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver

[PATCH net-next v6 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.

Tested:
Compiled and ran with ethtool -K eth1 tso off
Could send Big TCP packets

Signed-off-by: Coco Li <lixiaoyan@google.com>
---
 include/net/ipv6.h     | 33 +++++++++++++++++++++++++++++++++
 net/ipv6/ip6_offload.c | 27 ++++-----------------------
 2 files changed, 37 insertions(+), 23 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d383c895592a..03f3af02a9a6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -500,6 +500,39 @@ 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));
+
+	__skb_pull(skb, hophdr_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.rc1.256.g54fd8350bd-goog

[RFC net-next v6 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 patch, 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.

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 9f8a6ce4b356..b281091a1b1d 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;
@@ -11283,6 +11286,7 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off,
 			      u8 **nextp)
 {
 	struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off);
+	struct hop_jumbo_hdr *jhdr;
 	int hdr_count = 0;
 	u8 *nexthdr;
 	int start;
@@ -11310,9 +11314,27 @@ 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;
+
+			jhdr = (struct hop_jumbo_hdr *)hp;
+			if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
+			    jhdr->nexthdr != IPPROTO_TCP)
+				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 */
@@ -13633,6 +13655,8 @@ 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.rc1.256.g54fd8350bd-goog

Re: [RFC net-next v6 2/2] bnxt: Use generic HBH removal helper in tx path

[Michael Chan]

[-- Attachment #1: Type: text/plain, Size: 1188 bytes --]

On Fri, Dec 9, 2022 at 8:16 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 patch, 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.
>
> Signed-off-by: Coco Li <lixiaoyan@google.com>

Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Tested-by: Michael Chan <michael.chan@broadcom.com>

Thanks.

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

Re: [PATCH net-next v6 1/2] IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver

[patchwork-bot+netdevbpf]

Hello:

This series was applied to netdev/net-next.git (master)
by Jakub Kicinski <kuba@kernel.org>:

On Sat, 10 Dec 2022 04:16:45 +0000 you 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.
> 
> [...]

Here is the summary with links:
  - [net-next,v6,1/2] IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
    https://git.kernel.org/netdev/net-next/c/89300468e2b2
  - [RFC,net-next,v6,2/2] bnxt: Use generic HBH removal helper in tx path
    https://git.kernel.org/netdev/net-next/c/b6488b161ab2

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html

[PATCH net-next v6 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.

Tested:
Compiled and ran with ethtool -K eth1 tso off
Could send Big TCP packets

Signed-off-by: Coco Li <lixiaoyan@google.com>
---
 include/net/ipv6.h     | 33 +++++++++++++++++++++++++++++++++
 net/ipv6/ip6_offload.c | 27 ++++-----------------------
 2 files changed, 37 insertions(+), 23 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d383c895592a..03f3af02a9a6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -500,6 +500,39 @@ 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));
+
+	__skb_pull(skb, hophdr_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.rc1.256.g54fd8350bd-goog

[RFC net-next v6 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 patch, 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.

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 9f8a6ce4b356..b281091a1b1d 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;
@@ -11283,6 +11286,7 @@ static bool bnxt_exthdr_check(struct bnxt *bp, struct sk_buff *skb, int nw_off,
 			      u8 **nextp)
 {
 	struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + nw_off);
+	struct hop_jumbo_hdr *jhdr;
 	int hdr_count = 0;
 	u8 *nexthdr;
 	int start;
@@ -11310,9 +11314,27 @@ 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;
+
+			jhdr = (struct hop_jumbo_hdr *)hp;
+			if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
+			    jhdr->nexthdr != IPPROTO_TCP)
+				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 */
@@ -13633,6 +13655,8 @@ 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.rc1.256.g54fd8350bd-goog