Richard Gobert wrote:

This commit adds net_offload to IPv6 Hop-by-Hop extension headers (as it is done for routing and dstopts) since it is supported in GSO and GRO. This allows to remove specific HBH conditionals in GSO and GRO when pulling and parsing an incoming packet.

Signed-off-by: Richard Gobert richardbgobert@gmail.com

Reviewed-by: Willem de Bruijn willemb@google.com

---

net/ipv6/exthdrs_offload.c | 11 +++++++++++ net/ipv6/ip6_offload.c | 25 +++++++++++-------------- 2 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index 06750d65d480..4c00398f4dca 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -16,6 +16,10 @@ static const struct net_offload dstopt_offload = { .flags = INET6_PROTO_GSO_EXTHDR, }; +static const struct net_offload hbh_offload = {

• .flags = INET6_PROTO_GSO_EXTHDR,

+};

int __init ipv6_exthdrs_offload_init(void) { int ret; @@ -28,9 +32,16 @@ int __init ipv6_exthdrs_offload_init(void) if (ret) goto out_rt;

• ret = inet6_add_offload(&hbh_offload, IPPROTO_HOPOPTS);
• if (ret)

• goto out_dstopts;
  

out: return ret; +out_dstopts:

• inet6_del_offload(&dstopt_offload, IPPROTO_DSTOPTS);

out_rt: inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING); goto out; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index d6314287338d..0e0b5fed0995 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -45,15 +45,13 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) struct ipv6_opt_hdr *opth; int len;

• if (proto != NEXTHDR_HOP) {
  

• 	ops = rcu_dereference(inet6_offloads[proto]);
  

• ops = rcu_dereference(inet6_offloads[proto]);
  

• 	if (unlikely(!ops))
  

• 		break;
  

• if (unlikely(!ops))
  

• 	break;
  

• 	if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
  

• 		break;
  

• }
  

• if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
  

• 	break;
  

if (unlikely(!pskb_may_pull(skb, 8))) break; @@ -171,13 +169,12 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph, proto = iph->nexthdr; for (;;) {

• if (proto != NEXTHDR_HOP) {
  

• 	*opps = rcu_dereference(inet6_offloads[proto]);
  

• 	if (unlikely(!(*opps)))
  

• 		break;
  

• 	if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
  

• 		break;
  

• }
  

• *opps = rcu_dereference(inet6_offloads[proto]);
  

• if (unlikely(!(*opps)))
  

• 	break;
  

• if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
  

• 	break;
  

• opth = (void *)opth + optlen; optlen = ipv6_optlen(opth); len += optlen;

-- 2.36.1

Richard Gobert wrote:

This commit utilizes a new helper function, ipv6_gro_pull_exthdrs, which is used in ipv6_gro_receive to pull ipv6 ext headers instead of ipv6_gso_pull_exthdrs. To use ipv6_gso_pull_exthdr, pskb_pull and __skb_push must be used, and frag0 must be invalidated. This commit removes unnecessary code around the call to ipv6_gso_pull_exthdrs and enables the frag0 fast path in IPv6 packets with ext headers.

Signed-off-by: Richard Gobert richardbgobert@gmail.com

net/ipv6/ip6_offload.c | 51 +++++++++++++++++++++++++++++++++--------- 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 0e0b5fed0995..a3b8d9127dbb 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -37,6 +37,40 @@ INDIRECT_CALL_L4(cb, f2, f1, head, skb); \ }) +static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto) +{

• const struct net_offload *ops = NULL;
• struct ipv6_opt_hdr *opth;
• for (;;) {

• int len;
  

• ops = rcu_dereference(inet6_offloads[proto]);
  

• if (unlikely(!ops))
  

• 	break;
  

• if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
  

• 	break;
  

• opth = skb_gro_header(skb, off + 8, off);
  

When changing this code, it would be great to make it more self documenting. It's not entirely clear what that 8 is based on. sizeof(*opth) is only 2. Probably an optimization to handle the most common extension headers in a single pskb_may_pull? If so, this new code does not have that concern, so can just use sizeof(*opth). Or else add a const int likely_max_opt_hdr_len = 8 or so.

• if (unlikely(!opth))
  

• 	break;
  

• len = ipv6_optlen(opth);
  

• opth = skb_gro_header(skb, off + len, off);
  

• if (unlikely(!opth))
  

• 	break;
  

• proto = opth->nexthdr;
  

• off += len;
  

• }
• skb_gro_pull(skb, off - skb_network_offset(skb));
• return proto;

+}

static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) { const struct net_offload *ops = NULL; @@ -203,28 +237,25 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, goto out; skb_set_network_header(skb, off);

• skb_gro_pull(skb, sizeof(*iph));
• skb_set_transport_header(skb, skb_gro_offset(skb));

• flush += ntohs(iph->payload_len) != skb_gro_len(skb);

• flush += ntohs(iph->payload_len) != skb->len - hlen;

proto = iph->nexthdr; ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) {

• pskb_pull(skb, skb_gro_offset(skb));
  

• skb_gro_frag0_invalidate(skb);
  

• proto = ipv6_gso_pull_exthdrs(skb, proto);
  

• skb_gro_pull(skb, -skb_transport_offset(skb));
  

• skb_reset_transport_header(skb);
  

• __skb_push(skb, skb_gro_offset(skb));
  

• proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
  

ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out;

• iph = ipv6_hdr(skb);
  

• iph = skb_gro_network_header(skb);
  

• } else {

• skb_gro_pull(skb, sizeof(*iph));
  

  }

This code is non-obvious and has proven fragile (57ea52a8651). Changes are best as simple as they can be, with ample documentation. My attempt, as arrived at during review:

The existing always pulls the IPv6 header and sets the transport offset initially. Then optionally again pulls any extension headers in ipv6_gso_pull_exthdrs and sets the transport offset again on return from that call.

The new code adds a small optimization to only pull and set transport offset once.

The existing code needs to set skb->data at the start of the first extension header before calling ipv6_gso_pull_exthdrs, and must disable the frag0 optimization because that function uses pskb_may_pull/pskb_pull instead of skb_gro_ helpers. It sets the GRO offset to the inner TCP header with skb_gro_pull and sets the transport header. Then returns skb->data to its position before this block.

The new code is much simpler: it does not have to modify skb->data, as all operations are with skb_gro_ helpers.

Aside from the small comment above, and suggestion to include something like this summary in the code and/or avoid the extra optimization,

Reviewed-by: Willem de Bruijn willemb@google.com

• skb_set_transport_header(skb, skb_gro_offset(skb));
• NAPI_GRO_CB(skb)->proto = proto;

flush--; -- 2.36.1

Richard Gobert wrote:

Currently there is no test which checks that IPv6 extension header packets successfully coalesce. This commit adds a test, which verifies two IPv6 packets with HBH extension headers do coalesce.

I changed the receive socket filter to accept a packet with one extension header. This change exposed a bug in the fragment test -- the old BPF did not accept the fragment packet. I updated correct_num_packets in the fragment test accordingly.

Signed-off-by: Richard Gobert richardbgobert@gmail.com

Thanks for adding test coverage along with the feature, and as part of the existing gro test too.

---

tools/testing/selftests/net/gro.c | 78 ++++++++++++++++++++++++++++--- 1 file changed, 71 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index 30024d0ed373..4ee34dca8e5f 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -71,6 +71,10 @@ #define MAX_PAYLOAD (IP_MAXPACKET - sizeof(struct tcphdr) - sizeof(struct ipv6hdr)) #define NUM_LARGE_PKT (MAX_PAYLOAD / MSS) #define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) +#define MIN_EXTHDR_SIZE 8 /* minimum size of IPv6 extension header */

+#define ipv6_optlen(p) (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */

static const char *addr6_src = "fdaa::2"; static const char *addr6_dst = "fdaa::1"; @@ -104,7 +108,7 @@ static void setup_sock_filter(int fd) const int dport_off = tcp_offset + offsetof(struct tcphdr, dest); const int ethproto_off = offsetof(struct ethhdr, h_proto); int optlen = 0;

• int ipproto_off;

• int ipproto_off, opt_ipproto_off; int next_off;

if (proto == PF_INET) @@ -116,14 +120,27 @@ static void setup_sock_filter(int fd) if (strcmp(testname, "ip") == 0) { if (proto == PF_INET) optlen = sizeof(struct ip_timestamp);

• else
  

• 	optlen = sizeof(struct ip6_frag);
  

• else {
  

• 	// same size for HBH and Fragment extension header types
  

no C++ style comments

Also, instead of comments here and at the MIN_EXTHDR_SIZE definition, perhaps cleaner as self documenting code:

BUILD_BUG_ON(MIN_EXTHDR_SIZE != sizeof(struct ip6_hbh)); BUILD_BUG_ON(MIN_EXTHDR_SIZE != sizeof(struct ip6_dest)); BUILD_BUG_ON(MIN_EXTHDR_SIZE < sizeof(struct ip6_frag));

• 	optlen = MIN_EXTHDR_SIZE;
  

• 	opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr) +
  

• 		offsetof(struct ip6_ext, ip6e_nxt);
  

• }
  

  }

• /*

• * this filter validates the following:
  

• *	- packet is IPv4/IPv6 according to the running test.
  

• *	- packet is TCP. Also handles the case of one extension header and then TCP.
  

• *	- checks the packet tcp dport equals to DPORT.
  

• *     (also handles the case of one extension header and then TCP.)
  

• */
  

nit: for filewide consistency: netdev style:

/* start comment * more comment */

struct sock_filter filter[] = { BPF_STMT(BPF_LD + BPF_H + BPF_ABS, ethproto_off),

• 	BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 7),
  

• 	BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 9),
  BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, ipproto_off),
  

• 	BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 2, 0),
  

• 	BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, opt_ipproto_off),
  BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 0, 5),
  BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, dport_off),
  BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 2, 0),
  

@@ -576,6 +593,39 @@ static void add_ipv4_ts_option(void *buf, void *optpkt) iph->check = checksum_fold(iph, sizeof(struct iphdr) + optlen, 0); } +static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type) +{

• struct ipv6_opt_hdr *hbh_hdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset);
• struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN);
• int opt_len;
• hbh_hdr->hdrlen = 0;
• hbh_hdr->nexthdr = IPPROTO_TCP;
• opt_len = ipv6_optlen(hbh_hdr);
• memcpy(optpkt, buf, tcp_offset);
• memcpy(optpkt + tcp_offset + MIN_EXTHDR_SIZE, buf + tcp_offset,

• sizeof(struct tcphdr) + PAYLOAD_LEN);
  

• iph->nexthdr = exthdr_type;
• iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE);

+}

+/* Send IPv6 packet with extension header */ +static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr) +{

• static char buf[MAX_HDR_LEN + PAYLOAD_LEN];
• static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE];
• create_packet(buf, 0, 0, PAYLOAD_LEN, 0);
• add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS);
• write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);
• create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0);
• add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_HOPOPTS);
• write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);

+}

/* IPv4 options shouldn't coalesce */ static void send_ip_options(int fd, struct sockaddr_ll *daddr) { @@ -697,7 +747,7 @@ static void send_fragment6(int fd, struct sockaddr_ll *daddr) create_packet(buf, PAYLOAD_LEN * i, 0, PAYLOAD_LEN, 0); write_packet(fd, buf, bufpkt_len, daddr); }

• sleep(1);

Leftover debug, or necessary fix to existing test?

create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); memset(extpkt, 0, extpkt_len); @@ -760,6 +810,7 @@ static void check_recv_pkts(int fd, int *correct_payload, vlog("}, Total %d packets\nReceived {", correct_num_pkts); while (1) {

• ip_ext_len = 0;
  

  pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); if (pkt_size < 0) error(1, errno, "could not receive");

@@ -767,7 +818,7 @@ static void check_recv_pkts(int fd, int *correct_payload, if (iph->version == 4) ip_ext_len = (iph->ihl - 5) * 4; else if (ip6h->version == 6 && ip6h->nexthdr != IPPROTO_TCP)

• 	ip_ext_len = sizeof(struct ip6_frag);
  

• 	ip_ext_len = MIN_EXTHDR_SIZE;
  

struct ip6_frag is > MIN_EXTHDR_SIZE. Need both cases?

else if (ip6h->version == 6 && ip6h->nexthdr == NEXTHDR_FRAGMENT ip_ext_len = sizeof(struct ip6_frag); else if (ip6h->version == 6 && ip6h->nexthdr != IPPROTO_TCP) ip_ext_len = MIN_EXTHDR_SIZE;

tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len); @@ -880,7 +931,14 @@ static void gro_sender(void) sleep(1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (proto == PF_INET6) {

• 	sleep(1);
  send_fragment6(txfd, &daddr);
  

• 	sleep(1);
  

• 	write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
  

• 	sleep(1);
  

• 	send_ipv6_exthdr(txfd, &daddr);
  

• 	sleep(1);
  

For the casual reader: these sleeps are not leftover debug statements unfortunately. The same exists in the PF_INET branch:

/* Modified packets may be received out of order. * Sleep function added to enforce test boundaries * so that fin pkts are not received prior to other pkts. */

	write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
}

} else if (strcmp(testname, "large") == 0) { @@ -997,7 +1055,13 @@ static void gro_receiver(void) */ printf("fragmented ip6 doesn't coalesce: "); correct_payload[0] = PAYLOAD_LEN * 2;

• 	check_recv_pkts(rxfd, correct_payload, 2);
  

• 	correct_payload[1] = PAYLOAD_LEN;
  

• 	correct_payload[2] = PAYLOAD_LEN;
  

• 	check_recv_pkts(rxfd, correct_payload, 3);
  

• 	correct_payload[0] = PAYLOAD_LEN * 2;
  

• 	printf("ipv6 with extension header DOES coalesce: ");
  

• 	check_recv_pkts(rxfd, correct_payload, 1);
  

It might be worth adding a test with two different extension headers. To verify that these should not coalesce.

Either different ipprotos, like IPPROTO_DSTOPTS vs IPPROTO_HOPOPTS. Perhaps more intesting are two of the same ipproto but with different content.

}

} else if (strcmp(testname, "large") == 0) { int offset = proto == PF_INET ? 20 : 0; -- 2.36.1