@@ -18,7 +18,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
- test_l4lb_noinline.o
+ test_l4lb_noinline.o test_xdp_noinline.o
TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
test_offload.py
@@ -54,6 +54,7 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
-Wno-compare-distinct-pointer-types
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
+$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
%.o: %.c
$(CLANG) $(CLANG_FLAGS) \
@@ -257,6 +257,86 @@ static void test_l4lb_all(void)
test_l4lb(file2);
}
+static void test_xdp_noinline(void)
+{
+ const char *file = "./test_xdp_noinline.o";
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ struct vip key = {.protocol = 6};
+ struct vip_meta {
+ __u32 flags;
+ __u32 vip_num;
+ } value = {.vip_num = VIP_NUM};
+ __u32 stats_key = VIP_NUM;
+ struct vip_stats {
+ __u64 bytes;
+ __u64 pkts;
+ } stats[nr_cpus];
+ struct real_definition {
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ __u8 flags;
+ } real_def = {.dst = MAGIC_VAL};
+ __u32 ch_key = 11, real_num = 3;
+ __u32 duration, retval, size;
+ int err, i, prog_fd, map_fd;
+ __u64 bytes = 0, pkts = 0;
+ struct bpf_object *obj;
+ char buf[128];
+ u32 *magic = (u32 *)buf;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+ if (err) {
+ error_cnt++;
+ return;
+ }
+
+ map_fd = bpf_find_map(__func__, obj, "vip_map");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &key, &value, 0);
+
+ map_fd = bpf_find_map(__func__, obj, "ch_rings");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+ map_fd = bpf_find_map(__func__, obj, "reals");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+ err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != 1 || size != 54 ||
+ *magic != MAGIC_VAL, "ipv4",
+ "err %d errno %d retval %d size %d magic %x\n",
+ err, errno, retval, size, *magic);
+
+ err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != 1 || size != 74 ||
+ *magic != MAGIC_VAL, "ipv6",
+ "err %d errno %d retval %d size %d magic %x\n",
+ err, errno, retval, size, *magic);
+
+ map_fd = bpf_find_map(__func__, obj, "stats");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_lookup_elem(map_fd, &stats_key, stats);
+ for (i = 0; i < nr_cpus; i++) {
+ bytes += stats[i].bytes;
+ pkts += stats[i].pkts;
+ }
+ if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+ error_cnt++;
+ printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts);
+ }
+out:
+ bpf_object__close(obj);
+}
+
static void test_tcp_estats(void)
{
const char *file = "./test_tcp_estats.o";
@@ -766,6 +846,7 @@ int main(void)
test_pkt_access();
test_xdp();
test_l4lb_all();
+ test_xdp_noinline();
test_tcp_estats();
test_bpf_obj_id();
test_pkt_md_access();
new file mode 100644
@@ -0,0 +1,833 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+
+#define bpf_printk(fmt, ...) \
+({ \
+ char ____fmt[] = fmt; \
+ bpf_trace_printk(____fmt, sizeof(____fmt), \
+ ##__VA_ARGS__); \
+})
+
+static __u32 rol32(__u32 word, unsigned int shift)
+{
+ return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c) \
+{ \
+ a -= c; a ^= rol32(c, 4); c += b; \
+ b -= a; b ^= rol32(a, 6); a += c; \
+ c -= b; c ^= rol32(b, 8); b += a; \
+ a -= c; a ^= rol32(c, 16); c += b; \
+ b -= a; b ^= rol32(a, 19); a += c; \
+ c -= b; c ^= rol32(b, 4); b += a; \
+}
+
+#define __jhash_final(a, b, c) \
+{ \
+ c ^= b; c -= rol32(b, 14); \
+ a ^= c; a -= rol32(c, 11); \
+ b ^= a; b -= rol32(a, 25); \
+ c ^= b; c -= rol32(b, 16); \
+ a ^= c; a -= rol32(c, 4); \
+ b ^= a; b -= rol32(a, 14); \
+ c ^= b; c -= rol32(b, 24); \
+}
+
+#define JHASH_INITVAL 0xdeadbeef
+
+typedef unsigned int u32;
+
+static __attribute__ ((noinline))
+u32 jhash(const void *key, u32 length, u32 initval)
+{
+ u32 a, b, c;
+ const unsigned char *k = key;
+
+ a = b = c = JHASH_INITVAL + length + initval;
+
+ while (length > 12) {
+ a += *(u32 *)(k);
+ b += *(u32 *)(k + 4);
+ c += *(u32 *)(k + 8);
+ __jhash_mix(a, b, c);
+ length -= 12;
+ k += 12;
+ }
+ switch (length) {
+ case 12: c += (u32)k[11]<<24;
+ case 11: c += (u32)k[10]<<16;
+ case 10: c += (u32)k[9]<<8;
+ case 9: c += k[8];
+ case 8: b += (u32)k[7]<<24;
+ case 7: b += (u32)k[6]<<16;
+ case 6: b += (u32)k[5]<<8;
+ case 5: b += k[4];
+ case 4: a += (u32)k[3]<<24;
+ case 3: a += (u32)k[2]<<16;
+ case 2: a += (u32)k[1]<<8;
+ case 1: a += k[0];
+ __jhash_final(a, b, c);
+ case 0: /* Nothing left to add */
+ break;
+ }
+
+ return c;
+}
+
+static __attribute__ ((noinline))
+u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+ a += initval;
+ b += initval;
+ c += initval;
+ __jhash_final(a, b, c);
+ return c;
+}
+
+static __attribute__ ((noinline))
+u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+ return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+struct flow_key {
+ union {
+ __be32 src;
+ __be32 srcv6[4];
+ };
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ union {
+ __u32 ports;
+ __u16 port16[2];
+ };
+ __u8 proto;
+};
+
+struct packet_description {
+ struct flow_key flow;
+ __u8 flags;
+};
+
+struct ctl_value {
+ union {
+ __u64 value;
+ __u32 ifindex;
+ __u8 mac[6];
+ };
+};
+
+struct vip_definition {
+ union {
+ __be32 vip;
+ __be32 vipv6[4];
+ };
+ __u16 port;
+ __u16 family;
+ __u8 proto;
+};
+
+struct vip_meta {
+ __u32 flags;
+ __u32 vip_num;
+};
+
+struct real_pos_lru {
+ __u32 pos;
+ __u64 atime;
+};
+
+struct real_definition {
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ __u8 flags;
+};
+
+struct lb_stats {
+ __u64 v2;
+ __u64 v1;
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(struct vip_definition),
+ .value_size = sizeof(struct vip_meta),
+ .max_entries = 512,
+ .map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = {
+ .type = BPF_MAP_TYPE_LRU_HASH,
+ .key_size = sizeof(struct flow_key),
+ .value_size = sizeof(struct real_pos_lru),
+ .max_entries = 300,
+ .map_flags = 1U << 1,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u32),
+ .max_entries = 12 * 655,
+ .map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) reals = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct real_definition),
+ .max_entries = 40,
+ .map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) stats = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct lb_stats),
+ .max_entries = 515,
+ .map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct ctl_value),
+ .max_entries = 16,
+ .map_flags = 0,
+};
+
+struct eth_hdr {
+ unsigned char eth_dest[6];
+ unsigned char eth_source[6];
+ unsigned short eth_proto;
+};
+
+static inline __u64 calc_offset(bool is_ipv6, bool is_icmp)
+{
+ __u64 off = sizeof(struct eth_hdr);
+ if (is_ipv6) {
+ off += sizeof(struct ipv6hdr);
+ if (is_icmp)
+ off += sizeof(struct icmp6hdr) + sizeof(struct ipv6hdr);
+ } else {
+ off += sizeof(struct iphdr);
+ if (is_icmp)
+ off += sizeof(struct icmphdr) + sizeof(struct iphdr);
+ }
+ return off;
+}
+
+static __attribute__ ((noinline))
+bool parse_udp(void *data, void *data_end,
+ bool is_ipv6, struct packet_description *pckt)
+{
+
+ bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
+ __u64 off = calc_offset(is_ipv6, is_icmp);
+ struct udphdr *udp;
+ udp = data + off;
+
+ if (udp + 1 > data_end)
+ return 0;
+ if (!is_icmp) {
+ pckt->flow.port16[0] = udp->source;
+ pckt->flow.port16[1] = udp->dest;
+ } else {
+ pckt->flow.port16[0] = udp->dest;
+ pckt->flow.port16[1] = udp->source;
+ }
+ return 1;
+}
+
+static __attribute__ ((noinline))
+bool parse_tcp(void *data, void *data_end,
+ bool is_ipv6, struct packet_description *pckt)
+{
+
+ bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
+ __u64 off = calc_offset(is_ipv6, is_icmp);
+ struct tcphdr *tcp;
+
+ tcp = data + off;
+ if (tcp + 1 > data_end)
+ return 0;
+ if (tcp->syn)
+ pckt->flags |= (1 << 1);
+ if (!is_icmp) {
+ pckt->flow.port16[0] = tcp->source;
+ pckt->flow.port16[1] = tcp->dest;
+ } else {
+ pckt->flow.port16[0] = tcp->dest;
+ pckt->flow.port16[1] = tcp->source;
+ }
+ return 1;
+}
+
+static __attribute__ ((noinline))
+bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
+ struct packet_description *pckt,
+ struct real_definition *dst, __u32 pkt_bytes)
+{
+ struct eth_hdr *new_eth;
+ struct eth_hdr *old_eth;
+ struct ipv6hdr *ip6h;
+ __u32 ip_suffix;
+ void *data_end;
+ void *data;
+
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+ return 0;
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+ new_eth = data;
+ ip6h = data + sizeof(struct eth_hdr);
+ old_eth = data + sizeof(struct ipv6hdr);
+ if (new_eth + 1 > data_end ||
+ old_eth + 1 > data_end || ip6h + 1 > data_end)
+ return 0;
+ memcpy(new_eth->eth_dest, cval->mac, 6);
+ memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
+ new_eth->eth_proto = 56710;
+ ip6h->version = 6;
+ ip6h->priority = 0;
+ memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+
+ ip6h->nexthdr = IPPROTO_IPV6;
+ ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
+ ip6h->payload_len =
+ __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
+ ip6h->hop_limit = 4;
+
+ ip6h->saddr.in6_u.u6_addr32[0] = 1;
+ ip6h->saddr.in6_u.u6_addr32[1] = 2;
+ ip6h->saddr.in6_u.u6_addr32[2] = 3;
+ ip6h->saddr.in6_u.u6_addr32[3] = ip_suffix;
+ memcpy(ip6h->daddr.in6_u.u6_addr32, dst->dstv6, 16);
+ return 1;
+}
+
+static __attribute__ ((noinline))
+bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
+ struct packet_description *pckt,
+ struct real_definition *dst, __u32 pkt_bytes)
+{
+
+ __u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
+ struct eth_hdr *new_eth;
+ struct eth_hdr *old_eth;
+ __u16 *next_iph_u16;
+ struct iphdr *iph;
+ __u32 csum = 0;
+ void *data_end;
+ void *data;
+
+ ip_suffix <<= 15;
+ ip_suffix ^= pckt->flow.src;
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+ return 0;
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+ new_eth = data;
+ iph = data + sizeof(struct eth_hdr);
+ old_eth = data + sizeof(struct iphdr);
+ if (new_eth + 1 > data_end ||
+ old_eth + 1 > data_end || iph + 1 > data_end)
+ return 0;
+ memcpy(new_eth->eth_dest, cval->mac, 6);
+ memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
+ new_eth->eth_proto = 8;
+ iph->version = 4;
+ iph->ihl = 5;
+ iph->frag_off = 0;
+ iph->protocol = IPPROTO_IPIP;
+ iph->check = 0;
+ iph->tos = 1;
+ iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
+ /* don't update iph->daddr, since it will overwrite old eth_proto
+ * and multiple iterations of bpf_prog_run() will fail
+ */
+
+ iph->saddr = ((0xFFFF0000 & ip_suffix) | 4268) ^ dst->dst;
+ iph->ttl = 4;
+
+ next_iph_u16 = (__u16 *) iph;
+#pragma clang loop unroll(full)
+ for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
+ csum += *next_iph_u16++;
+ iph->check = ~((csum & 0xffff) + (csum >> 16));
+ if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
+ return 0;
+ return 1;
+}
+
+static __attribute__ ((noinline))
+bool decap_v6(struct xdp_md *xdp, void **data, void **data_end, bool inner_v4)
+{
+ struct eth_hdr *new_eth;
+ struct eth_hdr *old_eth;
+
+ old_eth = *data;
+ new_eth = *data + sizeof(struct ipv6hdr);
+ memcpy(new_eth->eth_source, old_eth->eth_source, 6);
+ memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
+ if (inner_v4)
+ new_eth->eth_proto = 8;
+ else
+ new_eth->eth_proto = 56710;
+ if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct ipv6hdr)))
+ return 0;
+ *data = (void *)(long)xdp->data;
+ *data_end = (void *)(long)xdp->data_end;
+ return 1;
+}
+
+static __attribute__ ((noinline))
+bool decap_v4(struct xdp_md *xdp, void **data, void **data_end)
+{
+ struct eth_hdr *new_eth;
+ struct eth_hdr *old_eth;
+
+ old_eth = *data;
+ new_eth = *data + sizeof(struct iphdr);
+ memcpy(new_eth->eth_source, old_eth->eth_source, 6);
+ memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
+ new_eth->eth_proto = 8;
+ if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
+ return 0;
+ *data = (void *)(long)xdp->data;
+ *data_end = (void *)(long)xdp->data_end;
+ return 1;
+}
+
+static __attribute__ ((noinline))
+int swap_mac_and_send(void *data, void *data_end)
+{
+ unsigned char tmp_mac[6];
+ struct eth_hdr *eth;
+
+ eth = data;
+ memcpy(tmp_mac, eth->eth_source, 6);
+ memcpy(eth->eth_source, eth->eth_dest, 6);
+ memcpy(eth->eth_dest, tmp_mac, 6);
+ return XDP_TX;
+}
+
+static __attribute__ ((noinline))
+int send_icmp_reply(void *data, void *data_end)
+{
+ struct icmphdr *icmp_hdr;
+ __u16 *next_iph_u16;
+ __u32 tmp_addr = 0;
+ struct iphdr *iph;
+ __u32 csum1 = 0;
+ __u32 csum = 0;
+ __u64 off = 0;
+
+ if (data + sizeof(struct eth_hdr)
+ + sizeof(struct iphdr) + sizeof(struct icmphdr) > data_end)
+ return XDP_DROP;
+ off += sizeof(struct eth_hdr);
+ iph = data + off;
+ off += sizeof(struct iphdr);
+ icmp_hdr = data + off;
+ icmp_hdr->type = 0;
+ icmp_hdr->checksum += 0x0007;
+ iph->ttl = 4;
+ tmp_addr = iph->daddr;
+ iph->daddr = iph->saddr;
+ iph->saddr = tmp_addr;
+ iph->check = 0;
+ next_iph_u16 = (__u16 *) iph;
+#pragma clang loop unroll(full)
+ for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
+ csum += *next_iph_u16++;
+ iph->check = ~((csum & 0xffff) + (csum >> 16));
+ return swap_mac_and_send(data, data_end);
+}
+
+static __attribute__ ((noinline))
+int send_icmp6_reply(void *data, void *data_end)
+{
+ struct icmp6hdr *icmp_hdr;
+ struct ipv6hdr *ip6h;
+ __be32 tmp_addr[4];
+ __u64 off = 0;
+
+ if (data + sizeof(struct eth_hdr)
+ + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) > data_end)
+ return XDP_DROP;
+ off += sizeof(struct eth_hdr);
+ ip6h = data + off;
+ off += sizeof(struct ipv6hdr);
+ icmp_hdr = data + off;
+ icmp_hdr->icmp6_type = 129;
+ icmp_hdr->icmp6_cksum -= 0x0001;
+ ip6h->hop_limit = 4;
+ memcpy(tmp_addr, ip6h->saddr.in6_u.u6_addr32, 16);
+ memcpy(ip6h->saddr.in6_u.u6_addr32, ip6h->daddr.in6_u.u6_addr32, 16);
+ memcpy(ip6h->daddr.in6_u.u6_addr32, tmp_addr, 16);
+ return swap_mac_and_send(data, data_end);
+}
+
+static __attribute__ ((noinline))
+int parse_icmpv6(void *data, void *data_end, __u64 off,
+ struct packet_description *pckt)
+{
+ struct icmp6hdr *icmp_hdr;
+ struct ipv6hdr *ip6h;
+
+ icmp_hdr = data + off;
+ if (icmp_hdr + 1 > data_end)
+ return XDP_DROP;
+ if (icmp_hdr->icmp6_type == 128)
+ return send_icmp6_reply(data, data_end);
+ if (icmp_hdr->icmp6_type != 3)
+ return XDP_PASS;
+ off += sizeof(struct icmp6hdr);
+ ip6h = data + off;
+ if (ip6h + 1 > data_end)
+ return XDP_DROP;
+ pckt->flow.proto = ip6h->nexthdr;
+ pckt->flags |= (1 << 0);
+ memcpy(pckt->flow.srcv6, ip6h->daddr.in6_u.u6_addr32, 16);
+ memcpy(pckt->flow.dstv6, ip6h->saddr.in6_u.u6_addr32, 16);
+ return -1;
+}
+
+static __attribute__ ((noinline))
+int parse_icmp(void *data, void *data_end, __u64 off,
+ struct packet_description *pckt)
+{
+ struct icmphdr *icmp_hdr;
+ struct iphdr *iph;
+
+ icmp_hdr = data + off;
+ if (icmp_hdr + 1 > data_end)
+ return XDP_DROP;
+ if (icmp_hdr->type == 8)
+ return send_icmp_reply(data, data_end);
+ if ((icmp_hdr->type != 3) || (icmp_hdr->code != 4))
+ return XDP_PASS;
+ off += sizeof(struct icmphdr);
+ iph = data + off;
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+ if (iph->ihl != 5)
+ return XDP_DROP;
+ pckt->flow.proto = iph->protocol;
+ pckt->flags |= (1 << 0);
+ pckt->flow.src = iph->daddr;
+ pckt->flow.dst = iph->saddr;
+ return -1;
+}
+
+static __attribute__ ((noinline))
+__u32 get_packet_hash(struct packet_description *pckt,
+ bool hash_16bytes)
+{
+ if (hash_16bytes)
+ return jhash_2words(jhash(pckt->flow.srcv6, 16, 12),
+ pckt->flow.ports, 24);
+ else
+ return jhash_2words(pckt->flow.src, pckt->flow.ports,
+ 24);
+}
+
+__attribute__ ((noinline))
+static bool get_packet_dst(struct real_definition **real,
+ struct packet_description *pckt,
+ struct vip_meta *vip_info,
+ bool is_ipv6, void *lru_map)
+{
+ struct real_pos_lru new_dst_lru = { };
+ bool hash_16bytes = is_ipv6;
+ __u32 *real_pos, hash, key;
+ __u64 cur_time;
+
+ if (vip_info->flags & (1 << 2))
+ hash_16bytes = 1;
+ if (vip_info->flags & (1 << 3)) {
+ pckt->flow.port16[0] = pckt->flow.port16[1];
+ memset(pckt->flow.srcv6, 0, 16);
+ }
+ hash = get_packet_hash(pckt, hash_16bytes);
+ if (hash != 0x358459b7 /* jhash of ipv4 packet */ &&
+ hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
+ return 0;
+ key = 2 * vip_info->vip_num + hash % 2;
+ real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+ if (!real_pos)
+ return 0;
+ key = *real_pos;
+ *real = bpf_map_lookup_elem(&reals, &key);
+ if (!(*real))
+ return 0;
+ if (!(vip_info->flags & (1 << 1))) {
+ __u32 conn_rate_key = 512 + 2;
+ struct lb_stats *conn_rate_stats =
+ bpf_map_lookup_elem(&stats, &conn_rate_key);
+
+ if (!conn_rate_stats)
+ return 1;
+ cur_time = bpf_ktime_get_ns();
+ if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) {
+ conn_rate_stats->v1 = 1;
+ conn_rate_stats->v2 = cur_time;
+ } else {
+ conn_rate_stats->v1 += 1;
+ if (conn_rate_stats->v1 >= 1)
+ return 1;
+ }
+ if (pckt->flow.proto == IPPROTO_UDP)
+ new_dst_lru.atime = cur_time;
+ new_dst_lru.pos = key;
+ bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0);
+ }
+ return 1;
+}
+
+__attribute__ ((noinline))
+static void connection_table_lookup(struct real_definition **real,
+ struct packet_description *pckt,
+ void *lru_map)
+{
+
+ struct real_pos_lru *dst_lru;
+ __u64 cur_time;
+ __u32 key;
+
+ dst_lru = bpf_map_lookup_elem(lru_map, &pckt->flow);
+ if (!dst_lru)
+ return;
+ if (pckt->flow.proto == IPPROTO_UDP) {
+ cur_time = bpf_ktime_get_ns();
+ if (cur_time - dst_lru->atime > 300000)
+ return;
+ dst_lru->atime = cur_time;
+ }
+ key = dst_lru->pos;
+ *real = bpf_map_lookup_elem(&reals, &key);
+}
+
+/* don't believe your eyes!
+ * below function has 6 arguments whereas bpf and llvm allow maximum of 5
+ * but since it's _static_ llvm can optimize one argument away
+ */
+__attribute__ ((noinline))
+static int process_l3_headers_v6(struct packet_description *pckt,
+ __u8 *protocol, __u64 off,
+ __u16 *pkt_bytes, void *data,
+ void *data_end)
+{
+ struct ipv6hdr *ip6h;
+ __u64 iph_len;
+ int action;
+
+ ip6h = data + off;
+ if (ip6h + 1 > data_end)
+ return XDP_DROP;
+ iph_len = sizeof(struct ipv6hdr);
+ *protocol = ip6h->nexthdr;
+ pckt->flow.proto = *protocol;
+ *pkt_bytes = __builtin_bswap16(ip6h->payload_len);
+ off += iph_len;
+ if (*protocol == 45) {
+ return XDP_DROP;
+ } else if (*protocol == 59) {
+ action = parse_icmpv6(data, data_end, off, pckt);
+ if (action >= 0)
+ return action;
+ } else {
+ memcpy(pckt->flow.srcv6, ip6h->saddr.in6_u.u6_addr32, 16);
+ memcpy(pckt->flow.dstv6, ip6h->daddr.in6_u.u6_addr32, 16);
+ }
+ return -1;
+}
+
+__attribute__ ((noinline))
+static int process_l3_headers_v4(struct packet_description *pckt,
+ __u8 *protocol, __u64 off,
+ __u16 *pkt_bytes, void *data,
+ void *data_end)
+{
+ struct iphdr *iph;
+ __u64 iph_len;
+ int action;
+
+ iph = data + off;
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+ if (iph->ihl != 5)
+ return XDP_DROP;
+ *protocol = iph->protocol;
+ pckt->flow.proto = *protocol;
+ *pkt_bytes = __builtin_bswap16(iph->tot_len);
+ off += 20;
+ if (iph->frag_off & 65343)
+ return XDP_DROP;
+ if (*protocol == IPPROTO_ICMP) {
+ action = parse_icmp(data, data_end, off, pckt);
+ if (action >= 0)
+ return action;
+ } else {
+ pckt->flow.src = iph->saddr;
+ pckt->flow.dst = iph->daddr;
+ }
+ return -1;
+}
+
+__attribute__ ((noinline))
+static int process_packet(void *data, __u64 off, void *data_end,
+ bool is_ipv6, struct xdp_md *xdp)
+{
+
+ struct real_definition *dst = NULL;
+ struct packet_description pckt = { };
+ struct vip_definition vip = { };
+ struct lb_stats *data_stats;
+ struct eth_hdr *eth = data;
+ void *lru_map = &lru_cache;
+ struct vip_meta *vip_info;
+ __u32 lru_stats_key = 513;
+ __u32 mac_addr_pos = 0;
+ __u32 stats_key = 512;
+ struct ctl_value *cval;
+ __u16 pkt_bytes;
+ __u64 iph_len;
+ __u8 protocol;
+ __u32 vip_num;
+ int action;
+
+ if (is_ipv6)
+ action = process_l3_headers_v6(&pckt, &protocol, off,
+ &pkt_bytes, data, data_end);
+ else
+ action = process_l3_headers_v4(&pckt, &protocol, off,
+ &pkt_bytes, data, data_end);
+ if (action >= 0)
+ return action;
+ protocol = pckt.flow.proto;
+ if (protocol == IPPROTO_TCP) {
+ if (!parse_tcp(data, data_end, is_ipv6, &pckt))
+ return XDP_DROP;
+ } else if (protocol == IPPROTO_UDP) {
+ if (!parse_udp(data, data_end, is_ipv6, &pckt))
+ return XDP_DROP;
+ } else {
+ return XDP_TX;
+ }
+
+ if (is_ipv6)
+ memcpy(vip.vipv6, pckt.flow.dstv6, 16);
+ else
+ vip.vip = pckt.flow.dst;
+ vip.port = pckt.flow.port16[1];
+ vip.proto = pckt.flow.proto;
+ vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+ if (!vip_info) {
+ vip.port = 0;
+ vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+ if (!vip_info)
+ return XDP_PASS;
+ if (!(vip_info->flags & (1 << 4)))
+ pckt.flow.port16[1] = 0;
+ }
+ if (data_end - data > 1400)
+ return XDP_DROP;
+ data_stats = bpf_map_lookup_elem(&stats, &stats_key);
+ if (!data_stats)
+ return XDP_DROP;
+ data_stats->v1 += 1;
+ if (!dst) {
+ if (vip_info->flags & (1 << 0))
+ pckt.flow.port16[0] = 0;
+ if (!(pckt.flags & (1 << 1)) && !(vip_info->flags & (1 << 1)))
+ connection_table_lookup(&dst, &pckt, lru_map);
+ if (dst)
+ goto out;
+ if (pckt.flow.proto == IPPROTO_TCP) {
+ struct lb_stats *lru_stats =
+ bpf_map_lookup_elem(&stats, &lru_stats_key);
+
+ if (!lru_stats)
+ return XDP_DROP;
+ if (pckt.flags & (1 << 1))
+ lru_stats->v1 += 1;
+ else
+ lru_stats->v2 += 1;
+ }
+ if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6, lru_map))
+ return XDP_DROP;
+ data_stats->v2 += 1;
+ }
+out:
+ cval = bpf_map_lookup_elem(&ctl_array, &mac_addr_pos);
+ if (!cval)
+ return XDP_DROP;
+ if (dst->flags & (1 << 0)) {
+ if (!encap_v6(xdp, cval, &pckt, dst, pkt_bytes))
+ return XDP_DROP;
+ } else {
+ if (!encap_v4(xdp, cval, &pckt, dst, pkt_bytes))
+ return XDP_DROP;
+ }
+ vip_num = vip_info->vip_num;
+ data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+ if (!data_stats)
+ return XDP_DROP;
+ data_stats->v1 += 1;
+ data_stats->v2 += pkt_bytes;
+
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+ if (data + 4 > data_end)
+ return XDP_DROP;
+ *(u32 *)data = dst->dst;
+ return XDP_DROP;
+}
+
+__attribute__ ((section("xdp-test"), used))
+int balancer_ingress(struct xdp_md *ctx)
+{
+ void *data = (void *)(long)ctx->data;
+ void *data_end = (void *)(long)ctx->data_end;
+ struct eth_hdr *eth = data;
+ __u32 eth_proto;
+ __u32 nh_off;
+
+ nh_off = sizeof(struct eth_hdr);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+ eth_proto = eth->eth_proto;
+ if (eth_proto == 8)
+ return process_packet(data, nh_off, data_end, 0, ctx);
+ else if (eth_proto == 56710)
+ return process_packet(data, nh_off, data_end, 1, ctx);
+ else
+ return XDP_DROP;
+}
+
+char _license[] __attribute__ ((section("license"), used)) = "GPL";
+int _version __attribute__ ((section("version"), used)) = 1;