The existing code 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. skb->data is set 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 TCP header with skb_gro_pull and sets the transport header. Then returns skb->data to its position before this block.

This commit introduces 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. Thus, there is no modification of skb->data, all operations use skb_gro_* helpers, and the frag0 fast path can be taken for IPv6 packets with ext headers.

Signed-off-by: Richard Gobert richardbgobert@gmail.com Reviewed-by: Willem de Bruijn willemb@google.com Reviewed-by: David Ahern dsahern@kernel.org --- 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..cca64c7809be 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 + sizeof(*opth), off); + 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)); }

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

flush--;

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, and another test which checks that packets with different extension header data do not coalesce in GRO.

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 Reviewed-by: Willem de Bruijn willemb@google.com --- tools/testing/selftests/net/gro.c | 93 +++++++++++++++++++++++++++++-- 1 file changed, 87 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index 30024d0ed373..353e1e867fbb 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -71,6 +71,12 @@ #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 +#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00" +#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11" + +#define ipv6_optlen(p) (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))

static const char *addr6_src = "fdaa::2"; static const char *addr6_dst = "fdaa::1"; @@ -104,7 +110,7 @@ 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 +122,30 @@ 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 { + BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE); + BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE); + + /* same size for HBH and Fragment extension header types */ + 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. + */ 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 +598,39 @@ 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, char *ext_payload) +{ + struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset); + struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN); + char *exthdr_payload_start = (char *)(exthdr + 1); + + exthdr->hdrlen = 0; + exthdr->nexthdr = IPPROTO_TCP; + + memcpy(exthdr_payload_start, ext_payload, MIN_EXTHDR_SIZE - sizeof(*exthdr)); + + 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); +} + +static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2) +{ + 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, ext_data1); + 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, ext_data2); + 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 +752,7 @@ 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); create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0); memset(extpkt, 0, extpkt_len);

@@ -760,6 +815,7 @@ 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 +823,7 @@ 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;

tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len);

@@ -880,7 +936,21 @@ 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 packets with ext header with same payload */ + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1); + sleep(1); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + sleep(1); + /* send IPv6 packets with ext header with different payload */ + send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2); + sleep(1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } } else if (strcmp(testname, "large") == 0) { @@ -997,6 +1067,17 @@ static void gro_receiver(void) */ printf("fragmented ip6 doesn't coalesce: "); correct_payload[0] = PAYLOAD_LEN * 2; + correct_payload[1] = PAYLOAD_LEN; + correct_payload[2] = PAYLOAD_LEN; + check_recv_pkts(rxfd, correct_payload, 3); + + printf("ipv6 with ext header does coalesce: "); + correct_payload[0] = PAYLOAD_LEN * 2; + check_recv_pkts(rxfd, correct_payload, 1); + + printf("ipv6 with ext header with different payloads doesn't coalesce: "); + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN; check_recv_pkts(rxfd, correct_payload, 2); } } else if (strcmp(testname, "large") == 0) {