diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-02 16:40:27 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-02 16:40:27 -0700 |
commit | 8d65b08debc7e62b2c6032d7fe7389d895b92cbc (patch) | |
tree | 0c3141b60c3a03cc32742b5750c5e763b9dae489 /tools/testing | |
parent | 5a0387a8a8efb90ae7fea1e2e5c62de3efa74691 (diff) | |
parent | 5d15af6778b8e4ed1fd41b040283af278e7a9a72 (diff) | |
download | op-kernel-dev-8d65b08debc7e62b2c6032d7fe7389d895b92cbc.zip op-kernel-dev-8d65b08debc7e62b2c6032d7fe7389d895b92cbc.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Millar:
"Here are some highlights from the 2065 networking commits that
happened this development cycle:
1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)
2) Add a generic XDP driver, so that anyone can test XDP even if they
lack a networking device whose driver has explicit XDP support
(me).
3) Sparc64 now has an eBPF JIT too (me)
4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
Starovoitov)
5) Make netfitler network namespace teardown less expensive (Florian
Westphal)
6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)
7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)
8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)
9) Multiqueue support in stmmac driver (Joao Pinto)
10) Remove TCP timewait recycling, it never really could possibly work
well in the real world and timestamp randomization really zaps any
hint of usability this feature had (Soheil Hassas Yeganeh)
11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
Aleksandrov)
12) Add socket busy poll support to epoll (Sridhar Samudrala)
13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
and several others)
14) IPSEC hw offload infrastructure (Steffen Klassert)"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
tipc: refactor function tipc_sk_recv_stream()
tipc: refactor function tipc_sk_recvmsg()
net: thunderx: Optimize page recycling for XDP
net: thunderx: Support for XDP header adjustment
net: thunderx: Add support for XDP_TX
net: thunderx: Add support for XDP_DROP
net: thunderx: Add basic XDP support
net: thunderx: Cleanup receive buffer allocation
net: thunderx: Optimize CQE_TX handling
net: thunderx: Optimize RBDR descriptor handling
net: thunderx: Support for page recycling
ipx: call ipxitf_put() in ioctl error path
net: sched: add helpers to handle extended actions
qed*: Fix issues in the ptp filter config implementation.
qede: Fix concurrency issue in PTP Tx path processing.
stmmac: Add support for SIMATIC IOT2000 platform
net: hns: fix ethtool_get_strings overflow in hns driver
tcp: fix wraparound issue in tcp_lp
bpf, arm64: fix jit branch offset related to ldimm64
bpf, arm64: implement jiting of BPF_XADD
...
Diffstat (limited to 'tools/testing')
-rw-r--r-- | tools/testing/selftests/bpf/Makefile | 17 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/bpf_endian.h | 23 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/bpf_util.h | 7 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_iptunnel_common.h | 37 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_l4lb.c | 473 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_lru_map.c | 104 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_maps.c | 66 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_pkt_access.c | 64 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_progs.c | 283 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_verifier.c | 287 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/test_xdp.c | 235 | ||||
-rw-r--r-- | tools/testing/selftests/net/Makefile | 2 | ||||
-rwxr-xr-x | tools/testing/selftests/net/netdevice.sh | 200 | ||||
-rw-r--r-- | tools/testing/selftests/net/psock_fanout.c | 93 |
14 files changed, 1808 insertions, 83 deletions
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 9af09e8..d8d94b9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -8,16 +8,18 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -LDLIBS += -lcap +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +LDLIBS += -lcap -lelf -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs + +TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o TEST_PROGS := test_kmod.sh include ../lib.mk -BPFOBJ := $(OUTPUT)/bpf.o +BPFOBJ := $(OUTPUT)/libbpf.a $(TEST_GEN_PROGS): $(BPFOBJ) @@ -28,3 +30,10 @@ force: $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ + +CLANG ?= clang + +%.o: %.c + $(CLANG) -I../../../include/uapi -I../../../../samples/bpf/ \ + -D__x86_64__ -Wno-compare-distinct-pointer-types \ + -O2 -target bpf -c $< -o $@ diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h new file mode 100644 index 0000000..19d0604 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -0,0 +1,23 @@ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +#include <asm/byteorder.h> + +#if __BYTE_ORDER == __LITTLE_ENDIAN +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +#elif __BYTE_ORDER == __BIG_ENDIAN +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +#else +# error "Fix your __BYTE_ORDER?!" +#endif + +#define bpf_htons(x) \ + (__builtin_constant_p(x) ? \ + __constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x) \ + (__builtin_constant_p(x) ? \ + __constant_ntohs(x) : __bpf_ntohs(x)) + +#endif diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 84a5d18..20ecbaa 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -35,4 +35,11 @@ static inline unsigned int bpf_num_possible_cpus(void) return possible_cpus; } +#define __bpf_percpu_val_align __attribute__((__aligned__(8))) + +#define BPF_DECLARE_PERCPU(type, name) \ + struct { type v; /* padding */ } __bpf_percpu_val_align \ + name[bpf_num_possible_cpus()] +#define bpf_percpu(name, cpu) name[(cpu)].v + #endif /* __BPF_UTIL__ */ diff --git a/tools/testing/selftests/bpf/test_iptunnel_common.h b/tools/testing/selftests/bpf/test_iptunnel_common.h new file mode 100644 index 0000000..e4cd252 --- /dev/null +++ b/tools/testing/selftests/bpf/test_iptunnel_common.h @@ -0,0 +1,37 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _TEST_IPTNL_COMMON_H +#define _TEST_IPTNL_COMMON_H + +#include <linux/types.h> + +#define MAX_IPTNL_ENTRIES 256U + +struct vip { + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 dport; + __u16 family; + __u8 protocol; +}; + +struct iptnl_info { + union { + __u32 v6[4]; + __u32 v4; + } saddr; + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 family; + __u8 dmac[6]; +}; + +#endif diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/test_l4lb.c new file mode 100644 index 0000000..1e10c95 --- /dev/null +++ b/tools/testing/selftests/bpf/test_l4lb.c @@ -0,0 +1,473 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#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" +#include "test_iptunnel_common.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +static inline __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 inline 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 inline 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 inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct bpf_map_def SEC("maps") vip_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct vip_meta), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ch_rings = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = CH_RINGS_SIZE, +}; + +struct bpf_map_def SEC("maps") reals = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct real_definition), + .max_entries = MAX_REALS, +}; + +struct bpf_map_def SEC("maps") stats = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct vip_stats), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ctl_array = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct ctl_value), + .max_entries = CTL_MAP_SIZE, +}; + +static __always_inline __u32 get_packet_hash(struct packet_description *pckt, + bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __always_inline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE; + __u32 key = RING_SIZE * vip_info->vip_num + hash; + __u32 *real_pos; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __always_inline 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 TC_ACT_SHOT; + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __always_inline 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 TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __always_inline bool parse_udp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __always_inline int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct __sk_buff *skb) +{ + void *pkt_start = (void *)(long)skb->data; + struct packet_description pckt = {}; + struct eth_hdr *eth = pkt_start; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("l4lb-demo") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + return process_packet(data, nh_off, data_end, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + return process_packet(data, nh_off, data_end, true, ctx); + else + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 00b0aff..8c10c91 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -22,7 +22,7 @@ #include "bpf_util.h" #define LOCAL_FREE_TARGET (128) -#define PERCPU_FREE_TARGET (16) +#define PERCPU_FREE_TARGET (4) static int nr_cpus; @@ -191,12 +191,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) - /* Ther percpu lru list (i.e each cpu has its own LRU - * list) does not have a local free list. Hence, - * it will only free old nodes till there is no free - * from the LRU list. Hence, this test does not apply - * to BPF_F_NO_COMMON_LRU - */ + /* This test is only applicable to common LRU list */ return; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, @@ -227,7 +222,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } /* Insert 1+tgt_free to 2*tgt_free @@ -273,12 +268,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) - /* Ther percpu lru list (i.e each cpu has its own LRU - * list) does not have a local free list. Hence, - * it will only free old nodes till there is no free - * from the LRU list. Hence, this test does not apply - * to BPF_F_NO_COMMON_LRU - */ + /* This test is only applicable to common LRU list */ return; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, @@ -290,11 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) assert(batch_size * 2 == tgt_free); map_size = tgt_free + batch_size; - if (map_flags & BPF_F_NO_COMMON_LRU) - lru_map_fd = create_map(map_type, map_flags, - map_size * nr_cpus); - else - lru_map_fd = create_map(map_type, map_flags, map_size); + lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); @@ -341,7 +327,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); assert(value[0] == 4321); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } value[0] = 1234; @@ -361,7 +347,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -387,6 +373,10 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) unsigned int map_size; int next_cpu = 0; + if (map_flags & BPF_F_NO_COMMON_LRU) + /* This test is only applicable to common LRU list */ + return; + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); @@ -396,11 +386,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) assert(batch_size * 2 == tgt_free); map_size = tgt_free * 2; - if (map_flags & BPF_F_NO_COMMON_LRU) - lru_map_fd = create_map(map_type, map_flags, - map_size * nr_cpus); - else - lru_map_fd = create_map(map_type, map_flags, map_size); + lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); @@ -419,7 +405,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } /* Add 1+2*tgt_free to tgt_free*5/2 @@ -431,7 +417,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -491,7 +477,7 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, - BPF_NOEXIST)); + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -566,6 +552,65 @@ static void test_lru_sanity5(int map_type, int map_flags) printf("Pass\n"); } +/* Test list rotation for BPF_F_NO_COMMON_LRU map */ +static void test_lru_sanity6(int map_type, int map_flags, int tgt_free) +{ + int lru_map_fd, expected_map_fd; + unsigned long long key, value[nr_cpus]; + unsigned int map_size = tgt_free * 2; + int next_cpu = 0; + + if (!(map_flags & BPF_F_NO_COMMON_LRU)) + return; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, &next_cpu) != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); + assert(expected_map_fd != -1); + + lru_map_fd = create_map(map_type, map_flags, map_size * nr_cpus); + assert(lru_map_fd != -1); + + value[0] = 1234; + + for (key = 1; key <= tgt_free; key++) { + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + for (; key <= tgt_free * 2; key++) { + unsigned long long stable_key; + + /* Make ref bit sticky for key: [1, tgt_free] */ + for (stable_key = 1; stable_key <= tgt_free; stable_key++) { + /* Mark the ref bit */ + assert(!bpf_map_lookup_elem(lru_map_fd, &stable_key, + value)); + } + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + } + + for (; key <= tgt_free * 3; key++) { + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; @@ -593,6 +638,7 @@ int main(int argc, char **argv) test_lru_sanity3(map_types[t], map_flags[f], tgt_free); test_lru_sanity4(map_types[t], map_flags[f], tgt_free); test_lru_sanity5(map_types[t], map_flags[f]); + test_lru_sanity6(map_types[t], map_flags[f], tgt_free); printf("\n"); } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 20f1871..9331452 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -28,7 +28,7 @@ static int map_flags; static void test_hashmap(int task, void *data) { - long long key, next_key, value; + long long key, next_key, first_key, value; int fd; fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), @@ -89,10 +89,13 @@ static void test_hashmap(int task, void *data) assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); /* Iterate over two elements. */ + assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && + (first_key == 1 || first_key == 2)); assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && - (next_key == 1 || next_key == 2)); + (next_key == first_key)); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && - (next_key == 1 || next_key == 2)); + (next_key == 1 || next_key == 2) && + (next_key != first_key)); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && errno == ENOENT); @@ -105,6 +108,8 @@ static void test_hashmap(int task, void *data) key = 0; /* Check that map is empty. */ + assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + errno == ENOENT); assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && errno == ENOENT); @@ -132,20 +137,20 @@ static void test_hashmap_sizes(int task, void *data) static void test_hashmap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); - long long value[nr_cpus]; - long long key, next_key; + BPF_DECLARE_PERCPU(long, value); + long long key, next_key, first_key; int expected_key_mask = 0; int fd, i; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), - sizeof(value[0]), 2, map_flags); + sizeof(bpf_percpu(value, 0)), 2, map_flags); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); } for (i = 0; i < nr_cpus; i++) - value[i] = i + 100; + bpf_percpu(value, i) = i + 100; key = 1; /* Insert key=1 element. */ @@ -165,8 +170,9 @@ static void test_hashmap_percpu(int task, void *data) /* Check that key=1 can be found. Value could be 0 if the lookup * was run from a different CPU. */ - value[0] = 1; - assert(bpf_map_lookup_elem(fd, &key, value) == 0 && value[0] == 100); + bpf_percpu(value, 0) = 1; + assert(bpf_map_lookup_elem(fd, &key, value) == 0 && + bpf_percpu(value, 0) == 100); key = 2; /* Check that key=2 is not found. */ @@ -193,14 +199,20 @@ static void test_hashmap_percpu(int task, void *data) assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); /* Iterate over two elements. */ + assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && + ((expected_key_mask & first_key) == first_key)); while (!bpf_map_get_next_key(fd, &key, &next_key)) { + if (first_key) { + assert(next_key == first_key); + first_key = 0; + } assert((expected_key_mask & next_key) == next_key); expected_key_mask &= ~next_key; assert(bpf_map_lookup_elem(fd, &next_key, value) == 0); for (i = 0; i < nr_cpus; i++) - assert(value[i] == i + 100); + assert(bpf_percpu(value, i) == i + 100); key = next_key; } @@ -219,6 +231,8 @@ static void test_hashmap_percpu(int task, void *data) key = 0; /* Check that map is empty. */ + assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + errno == ENOENT); assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && errno == ENOENT); @@ -264,6 +278,8 @@ static void test_arraymap(int task, void *data) assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); /* Iterate over two elements. */ + assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && + next_key == 0); assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && next_key == 0); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && @@ -281,34 +297,36 @@ static void test_arraymap(int task, void *data) static void test_arraymap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); + BPF_DECLARE_PERCPU(long, values); int key, next_key, fd, i; - long long values[nr_cpus]; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), 2, 0); + sizeof(bpf_percpu(values, 0)), 2, 0); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); } for (i = 0; i < nr_cpus; i++) - values[i] = i + 100; + bpf_percpu(values, i) = i + 100; key = 1; /* Insert key=1 element. */ assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0); - values[0] = 0; + bpf_percpu(values, 0) = 0; assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 && errno == EEXIST); /* Check that key=1 can be found. */ - assert(bpf_map_lookup_elem(fd, &key, values) == 0 && values[0] == 100); + assert(bpf_map_lookup_elem(fd, &key, values) == 0 && + bpf_percpu(values, 0) == 100); key = 0; /* Check that key=0 is also found and zero initialized. */ assert(bpf_map_lookup_elem(fd, &key, values) == 0 && - values[0] == 0 && values[nr_cpus - 1] == 0); + bpf_percpu(values, 0) == 0 && + bpf_percpu(values, nr_cpus - 1) == 0); /* Check that key=2 cannot be inserted due to max_entries limit. */ key = 2; @@ -319,6 +337,8 @@ static void test_arraymap_percpu(int task, void *data) assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT); /* Iterate over two elements. */ + assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && + next_key == 0); assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && next_key == 0); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && @@ -336,15 +356,15 @@ static void test_arraymap_percpu(int task, void *data) static void test_arraymap_percpu_many_keys(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); + BPF_DECLARE_PERCPU(long, values); /* nr_keys is not too large otherwise the test stresses percpu * allocator more than anything else */ unsigned int nr_keys = 2000; - long long values[nr_cpus]; int key, fd, i; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), nr_keys, 0); + sizeof(bpf_percpu(values, 0)), nr_keys, 0); if (fd < 0) { printf("Failed to create per-cpu arraymap '%s'!\n", strerror(errno)); @@ -352,19 +372,19 @@ static void test_arraymap_percpu_many_keys(void) } for (i = 0; i < nr_cpus; i++) - values[i] = i + 10; + bpf_percpu(values, i) = i + 10; for (key = 0; key < nr_keys; key++) assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0); for (key = 0; key < nr_keys; key++) { for (i = 0; i < nr_cpus; i++) - values[i] = 0; + bpf_percpu(values, i) = 0; assert(bpf_map_lookup_elem(fd, &key, values) == 0); for (i = 0; i < nr_cpus; i++) - assert(values[i] == i + 10); + assert(bpf_percpu(values, i) == i + 10); } close(fd); @@ -400,6 +420,8 @@ static void test_map_large(void) errno == E2BIG); /* Iterate through all elements. */ + assert(bpf_map_get_next_key(fd, NULL, &key) == 0); + key.c = -1; for (i = 0; i < MAP_SIZE; i++) assert(bpf_map_get_next_key(fd, &key, &key) == 0); assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); @@ -499,6 +521,7 @@ static void test_map_parallel(void) errno == EEXIST); /* Check that all elements were inserted. */ + assert(bpf_map_get_next_key(fd, NULL, &key) == 0); key = -1; for (i = 0; i < MAP_SIZE; i++) assert(bpf_map_get_next_key(fd, &key, &key) == 0); @@ -518,6 +541,7 @@ static void test_map_parallel(void) /* Nothing should be left. */ key = -1; + assert(bpf_map_get_next_key(fd, NULL, &key) == -1 && errno == ENOENT); assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); } diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c new file mode 100644 index 0000000..39387bb --- /dev/null +++ b/tools/testing/selftests/bpf/test_pkt_access.c @@ -0,0 +1,64 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define barrier() __asm__ __volatile__("": : :"memory") +int _version SEC("version") = 1; + +SEC("test1") +int process(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + struct tcphdr *tcp = NULL; + __u8 proto = 255; + __u64 ihl_len; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(eth + 1); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + tcp = (struct tcphdr *)((void *)(iph) + ihl_len); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len); + } + + if (tcp) { + if (((void *)(tcp) + 20) > data_end || proto != 6) + return TC_ACT_SHOT; + barrier(); /* to force ordering of checks */ + if (((void *)(tcp) + 18) > data_end) + return TC_ACT_SHOT; + if (tcp->urg_ptr == 123) + return TC_ACT_OK; + } + + return TC_ACT_UNSPEC; +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c new file mode 100644 index 0000000..4ed049a --- /dev/null +++ b/tools/testing/selftests/bpf/test_progs.c @@ -0,0 +1,283 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stdio.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <stdlib.h> + +#include <linux/types.h> +typedef __u16 __sum16; +#include <arpa/inet.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/wait.h> +#include <sys/resource.h> + +#include <linux/bpf.h> +#include <linux/err.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "test_iptunnel_common.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +static int error_cnt, pass_cnt; + +#define MAGIC_BYTES 123 + +/* ipv4 test vector */ +static struct { + struct ethhdr eth; + struct iphdr iph; + struct tcphdr tcp; +} __packed pkt_v4 = { + .eth.h_proto = bpf_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = 6, + .iph.tot_len = bpf_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, +}; + +/* ipv6 test vector */ +static struct { + struct ethhdr eth; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed pkt_v6 = { + .eth.h_proto = bpf_htons(ETH_P_IPV6), + .iph.nexthdr = 6, + .iph.payload_len = bpf_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, +}; + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + error_cnt++; \ + printf("%s:FAIL:%s ", __func__, tag); \ + printf(format); \ + } else { \ + pass_cnt++; \ + printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ + } \ +}) + +static int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int err; + + obj = bpf_object__open(file); + if (IS_ERR(obj)) { + error_cnt++; + return -ENOENT; + } + + prog = bpf_program__next(NULL, obj); + if (!prog) { + bpf_object__close(obj); + error_cnt++; + return -ENOENT; + } + + bpf_program__set_type(prog, type); + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + error_cnt++; + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(prog); + return 0; +} + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) { + printf("%s:FAIL:map '%s' not found\n", test, name); + error_cnt++; + return -1; + } + return bpf_map__fd(map); +} + +static void test_pkt_access(void) +{ + const char *file = "./test_pkt_access.o"; + struct bpf_object *obj; + __u32 duration, retval; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (err) + return; + + err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || errno || retval, "ipv4", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + + err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6), + NULL, NULL, &retval, &duration); + CHECK(err || errno || retval, "ipv6", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + bpf_object__close(obj); +} + +static void test_xdp(void) +{ + struct vip key4 = {.protocol = 6, .family = AF_INET}; + struct vip key6 = {.protocol = 6, .family = AF_INET6}; + struct iptnl_info value4 = {.family = AF_INET}; + struct iptnl_info value6 = {.family = AF_INET6}; + const char *file = "./test_xdp.o"; + struct bpf_object *obj; + char buf[128]; + struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr); + struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + __u32 duration, retval, size; + int err, prog_fd, map_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) + return; + + map_fd = bpf_find_map(__func__, obj, "vip2tnl"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &key4, &value4, 0); + bpf_map_update_elem(map_fd, &key6, &value6, 0); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + CHECK(err || errno || retval != XDP_TX || size != 74 || + iph->protocol != IPPROTO_IPIP, "ipv4", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != XDP_TX || size != 114 || + iph6->nexthdr != IPPROTO_IPV6, "ipv6", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); +out: + bpf_object__close(obj); +} + +#define MAGIC_VAL 0x1234 +#define NUM_ITER 100000 +#define VIP_NUM 5 + +static void test_l4lb(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + const char *file = "./test_l4lb.o"; + 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_SCHED_CLS, &obj, &prog_fd); + if (err) + 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 != 7/*TC_ACT_REDIRECT*/ || 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 != 7/*TC_ACT_REDIRECT*/ || 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_l4lb:FAIL:stats %lld %lld\n", bytes, pkts); + } +out: + bpf_object__close(obj); +} + +int main(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); + + test_pkt_access(); + test_xdp(); + test_l4lb(); + + printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c848e90..3773562 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -46,6 +46,7 @@ #define MAX_INSNS 512 #define MAX_FIXUPS 8 +#define MAX_NR_MAPS 4 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) @@ -55,6 +56,7 @@ struct bpf_test { int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; int fixup_prog[MAX_FIXUPS]; + int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; enum { @@ -189,6 +191,86 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "test6 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0), + BPF_RAW_INSN(0, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "test7 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "test8 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 1, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "uses reserved fields", + .result = REJECT, + }, + { + "test9 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, 0, 1, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test10 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, BPF_REG_1, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test11 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test12 ld_imm64", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "not pointing to valid bpf_map", + .result = REJECT, + }, + { + "test13 ld_imm64", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1), + BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { "no bpf_exit", .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), @@ -329,6 +411,30 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "invalid fp arithmetic", + /* If this gets ever changed, make sure JITs can deal with it. */ + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 8), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer arithmetic", + .result_unpriv = REJECT, + .errstr = "R1 invalid mem access", + .result = REJECT, + }, + { + "non-invalid fp arithmetic", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { "invalid argument register", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, @@ -770,6 +876,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, vlan_tci)), BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, napi_id)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), BPF_EXIT_INSN(), }, .result = ACCEPT, @@ -1796,6 +1905,20 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "unpriv: adding of fp", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "pointer arithmetic prohibited", + .result_unpriv = REJECT, + .errstr = "R1 invalid mem access", + .result = REJECT, + }, + { "unpriv: cmp of stack pointer", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -1809,16 +1932,22 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { - "unpriv: obfuscate stack pointer", + "stack pointer arithmetic", .insns = { - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1), + BPF_ST_MEM(0, BPF_REG_2, 4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), + BPF_ST_MEM(0, BPF_REG_2, 4, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R2 pointer arithmetic", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -2467,6 +2596,25 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "direct packet access: test16 (arith on data_end)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid access to packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to packet: test1, valid packet_ptr range", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -4720,6 +4868,75 @@ static struct bpf_test tests[] = { .result = REJECT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map in map access", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .result = ACCEPT, + }, + { + "invalid inner map pointer", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .errstr = "R1 type=inv expected=map_ptr", + .errstr_unpriv = "R1 pointer arithmetic prohibited", + .result = REJECT, + }, + { + "forgot null checking on the inner map pointer", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .errstr = "R1 type=map_value_or_null expected=map_ptr", + .result = REJECT, } }; @@ -4757,42 +4974,73 @@ static int create_prog_array(void) return fd; } +static int create_map_in_map(void) +{ + int inner_map_fd, outer_map_fd; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(int), 1, 0); + if (inner_map_fd < 0) { + printf("Failed to create array '%s'!\n", strerror(errno)); + return inner_map_fd; + } + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, + sizeof(int), inner_map_fd, 1, 0); + if (outer_map_fd < 0) + printf("Failed to create array of maps '%s'!\n", + strerror(errno)); + + close(inner_map_fd); + + return outer_map_fd; +} + static char bpf_vlog[32768]; static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, - int *fd_f1, int *fd_f2, int *fd_f3) + int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; int *fixup_prog = test->fixup_prog; + int *fixup_map_in_map = test->fixup_map_in_map; /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing * that really matters is value size in this case. */ if (*fixup_map1) { - *fd_f1 = create_map(sizeof(long long), 1); + map_fds[0] = create_map(sizeof(long long), 1); do { - prog[*fixup_map1].imm = *fd_f1; + prog[*fixup_map1].imm = map_fds[0]; fixup_map1++; } while (*fixup_map1); } if (*fixup_map2) { - *fd_f2 = create_map(sizeof(struct test_val), 1); + map_fds[1] = create_map(sizeof(struct test_val), 1); do { - prog[*fixup_map2].imm = *fd_f2; + prog[*fixup_map2].imm = map_fds[1]; fixup_map2++; } while (*fixup_map2); } if (*fixup_prog) { - *fd_f3 = create_prog_array(); + map_fds[2] = create_prog_array(); do { - prog[*fixup_prog].imm = *fd_f3; + prog[*fixup_prog].imm = map_fds[2]; fixup_prog++; } while (*fixup_prog); } + + if (*fixup_map_in_map) { + map_fds[3] = create_map_in_map(); + do { + prog[*fixup_map_in_map].imm = map_fds[3]; + fixup_map_in_map++; + } while (*fixup_map_in_map); + } } static void do_test_single(struct bpf_test *test, bool unpriv, @@ -4802,10 +5050,14 @@ static void do_test_single(struct bpf_test *test, bool unpriv, struct bpf_insn *prog = test->insns; int prog_len = probe_filter_length(prog); int prog_type = test->prog_type; - int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1; + int map_fds[MAX_NR_MAPS]; const char *expected_err; + int i; + + for (i = 0; i < MAX_NR_MAPS; i++) + map_fds[i] = -1; - do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3); + do_test_fixup(test, prog, map_fds); fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, "GPL", 0, bpf_vlog, @@ -4848,9 +5100,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, " (NOTE: reject due to unknown alignment)" : ""); close_fds: close(fd_prog); - close(fd_f1); - close(fd_f2); - close(fd_f3); + for (i = 0; i < MAX_NR_MAPS; i++) + close(map_fds[i]); sched_yield(); return; fail_log: diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/test_xdp.c new file mode 100644 index 0000000..5e7df8b --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp.c @@ -0,0 +1,235 @@ +/* Copyright (c) 2016,2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_iptunnel_common.h" + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") vip2tnl = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct iptnl_info), + .max_entries = MAX_IPTNL_ENTRIES, +}; + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index fbfe5d0..35cbb4c 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,7 +5,7 @@ CFLAGS += -I../../../../usr/include/ reuseport_bpf_numa: LDFLAGS += -lnuma -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh new file mode 100755 index 0000000..4e00568 --- /dev/null +++ b/tools/testing/selftests/net/netdevice.sh @@ -0,0 +1,200 @@ +#!/bin/sh +# +# This test is for checking network interface +# For the moment it tests only ethernet interface (but wifi could be easily added) +# +# We assume that all network driver are loaded +# if not they probably have failed earlier in the boot process and their logged error will be catched by another test +# + +# this function will try to up the interface +# if already up, nothing done +# arg1: network interface name +kci_net_start() +{ + netdev=$1 + + ip link show "$netdev" |grep -q UP + if [ $? -eq 0 ];then + echo "SKIP: $netdev: interface already up" + return 0 + fi + + ip link set "$netdev" up + if [ $? -ne 0 ];then + echo "FAIL: $netdev: Fail to up interface" + return 1 + else + echo "PASS: $netdev: set interface up" + NETDEV_STARTED=1 + fi + return 0 +} + +# this function will try to setup an IP and MAC address on a network interface +# Doing nothing if the interface was already up +# arg1: network interface name +kci_net_setup() +{ + netdev=$1 + + # do nothing if the interface was already up + if [ $NETDEV_STARTED -eq 0 ];then + return 0 + fi + + MACADDR='02:03:04:05:06:07' + ip link set dev $netdev address "$MACADDR" + if [ $? -ne 0 ];then + echo "FAIL: $netdev: Cannot set MAC address" + else + ip link show $netdev |grep -q "$MACADDR" + if [ $? -eq 0 ];then + echo "PASS: $netdev: set MAC address" + else + echo "FAIL: $netdev: Cannot set MAC address" + fi + fi + + #check that the interface did not already have an IP + ip address show "$netdev" |grep '^[[:space:]]*inet' + if [ $? -eq 0 ];then + echo "SKIP: $netdev: already have an IP" + return 0 + fi + + # TODO what ipaddr to set ? DHCP ? + echo "SKIP: $netdev: set IP address" + return 0 +} + +# test an ethtool command +# arg1: return code for not supported (see ethtool code source) +# arg2: summary of the command +# arg3: command to execute +kci_netdev_ethtool_test() +{ + if [ $# -le 2 ];then + echo "SKIP: $netdev: ethtool: invalid number of arguments" + return 1 + fi + $3 >/dev/null + ret=$? + if [ $ret -ne 0 ];then + if [ $ret -eq "$1" ];then + echo "SKIP: $netdev: ethtool $2 not supported" + else + echo "FAIL: $netdev: ethtool $2" + return 1 + fi + else + echo "PASS: $netdev: ethtool $2" + fi + return 0 +} + +# test ethtool commands +# arg1: network interface name +kci_netdev_ethtool() +{ + netdev=$1 + + #check presence of ethtool + ethtool --version 2>/dev/null >/dev/null + if [ $? -ne 0 ];then + echo "SKIP: ethtool not present" + return 1 + fi + + TMP_ETHTOOL_FEATURES="$(mktemp)" + if [ ! -e "$TMP_ETHTOOL_FEATURES" ];then + echo "SKIP: Cannot create a tmp file" + return 1 + fi + + ethtool -k "$netdev" > "$TMP_ETHTOOL_FEATURES" + if [ $? -ne 0 ];then + echo "FAIL: $netdev: ethtool list features" + rm "$TMP_ETHTOOL_FEATURES" + return 1 + fi + echo "PASS: $netdev: ethtool list features" + #TODO for each non fixed features, try to turn them on/off + rm "$TMP_ETHTOOL_FEATURES" + + kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev" + kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev" + return 0 +} + +# stop a netdev +# arg1: network interface name +kci_netdev_stop() +{ + netdev=$1 + + if [ $NETDEV_STARTED -eq 0 ];then + echo "SKIP: $netdev: interface kept up" + return 0 + fi + + ip link set "$netdev" down + if [ $? -ne 0 ];then + echo "FAIL: $netdev: stop interface" + return 1 + fi + echo "PASS: $netdev: stop interface" + return 0 +} + +# run all test on a netdev +# arg1: network interface name +kci_test_netdev() +{ + NETDEV_STARTED=0 + IFACE_TO_UPDOWN="$1" + IFACE_TO_TEST="$1" + #check for VLAN interface + MASTER_IFACE="$(echo $1 | cut -d@ -f2)" + if [ ! -z "$MASTER_IFACE" ];then + IFACE_TO_UPDOWN="$MASTER_IFACE" + IFACE_TO_TEST="$(echo $1 | cut -d@ -f1)" + fi + + NETDEV_STARTED=0 + kci_net_start "$IFACE_TO_UPDOWN" + + kci_net_setup "$IFACE_TO_TEST" + + kci_netdev_ethtool "$IFACE_TO_TEST" + + kci_netdev_stop "$IFACE_TO_UPDOWN" + return 0 +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +ip -Version 2>/dev/null >/dev/null +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without the ip tool" + exit 0 +fi + +TMP_LIST_NETDEV="$(mktemp)" +if [ ! -e "$TMP_LIST_NETDEV" ];then + echo "FAIL: Cannot create a tmp file" + exit 1 +fi + +ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\ -f2 | cut -d: -f1> "$TMP_LIST_NETDEV" +while read netdev +do + kci_test_netdev "$netdev" +done < "$TMP_LIST_NETDEV" + +rm "$TMP_LIST_NETDEV" +exit 0 diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index e62bb35..989f917 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -71,7 +71,7 @@ /* Open a socket in a given fanout mode. * @return -1 if mode is bad, a valid socket otherwise */ -static int sock_fanout_open(uint16_t typeflags, int num_packets) +static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) { int fd, val; @@ -81,8 +81,7 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) exit(1); } - /* fanout group ID is always 0: tests whether old groups are deleted */ - val = ((int) typeflags) << 16; + val = (((int) typeflags) << 16) | group_id; if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) { if (close(fd)) { perror("close packet"); @@ -113,6 +112,20 @@ static void sock_fanout_set_cbpf(int fd) } } +static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id) +{ + int sockopt; + socklen_t sockopt_len = sizeof(sockopt); + + if (getsockopt(fd, SOL_PACKET, PACKET_FANOUT, + &sockopt, &sockopt_len)) { + perror("failed to getsockopt"); + exit(1); + } + *typeflags = sockopt >> 16; + *group_id = sockopt & 0xfffff; +} + static void sock_fanout_set_ebpf(int fd) { const int len_off = __builtin_offsetof(struct __sk_buff, len); @@ -241,26 +254,26 @@ static void test_control_group(void) fprintf(stderr, "test: control multiple sockets\n"); - fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 20); + fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0); if (fds[0] == -1) { fprintf(stderr, "ERROR: failed to open HASH socket\n"); exit(1); } if (sock_fanout_open(PACKET_FANOUT_HASH | - PACKET_FANOUT_FLAG_DEFRAG, 10) != -1) { + PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong flag defrag\n"); exit(1); } if (sock_fanout_open(PACKET_FANOUT_HASH | - PACKET_FANOUT_FLAG_ROLLOVER, 10) != -1) { + PACKET_FANOUT_FLAG_ROLLOVER, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong flag ro\n"); exit(1); } - if (sock_fanout_open(PACKET_FANOUT_CPU, 10) != -1) { + if (sock_fanout_open(PACKET_FANOUT_CPU, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong mode\n"); exit(1); } - fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 20); + fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0); if (fds[1] == -1) { fprintf(stderr, "ERROR: failed to join group\n"); exit(1); @@ -271,6 +284,61 @@ static void test_control_group(void) } } +/* Test creating a unique fanout group ids */ +static void test_unique_fanout_group_ids(void) +{ + int fds[3]; + uint16_t typeflags, first_group_id, second_group_id; + + fprintf(stderr, "test: unique ids\n"); + + fds[0] = sock_fanout_open(PACKET_FANOUT_HASH | + PACKET_FANOUT_FLAG_UNIQUEID, 0); + if (fds[0] == -1) { + fprintf(stderr, "ERROR: failed to create a unique id group.\n"); + exit(1); + } + + sock_fanout_getopts(fds[0], &typeflags, &first_group_id); + if (typeflags != PACKET_FANOUT_HASH) { + fprintf(stderr, "ERROR: unexpected typeflags %x\n", typeflags); + exit(1); + } + + if (sock_fanout_open(PACKET_FANOUT_CPU, first_group_id) != -1) { + fprintf(stderr, "ERROR: joined group with wrong type.\n"); + exit(1); + } + + fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, first_group_id); + if (fds[1] == -1) { + fprintf(stderr, + "ERROR: failed to join previously created group.\n"); + exit(1); + } + + fds[2] = sock_fanout_open(PACKET_FANOUT_HASH | + PACKET_FANOUT_FLAG_UNIQUEID, 0); + if (fds[2] == -1) { + fprintf(stderr, + "ERROR: failed to create a second unique id group.\n"); + exit(1); + } + + sock_fanout_getopts(fds[2], &typeflags, &second_group_id); + if (sock_fanout_open(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_UNIQUEID, + second_group_id) != -1) { + fprintf(stderr, + "ERROR: specified a group id when requesting unique id\n"); + exit(1); + } + + if (close(fds[0]) || close(fds[1]) || close(fds[2])) { + fprintf(stderr, "ERROR: closing sockets\n"); + exit(1); + } +} + static int test_datapath(uint16_t typeflags, int port_off, const int expect1[], const int expect2[]) { @@ -281,8 +349,8 @@ static int test_datapath(uint16_t typeflags, int port_off, fprintf(stderr, "test: datapath 0x%hx\n", typeflags); - fds[0] = sock_fanout_open(typeflags, 20); - fds[1] = sock_fanout_open(typeflags, 20); + fds[0] = sock_fanout_open(typeflags, 0); + fds[1] = sock_fanout_open(typeflags, 0); if (fds[0] == -1 || fds[1] == -1) { fprintf(stderr, "ERROR: failed open\n"); exit(1); @@ -349,10 +417,12 @@ int main(int argc, char **argv) const int expect_cpu0[2][2] = { { 20, 0 }, { 20, 0 } }; const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; + const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; int port_off = 2, tries = 5, ret; test_control_single(); test_control_group(); + test_unique_fanout_group_ids(); /* find a set of ports that do not collide onto the same socket */ ret = test_datapath(PACKET_FANOUT_HASH, port_off, @@ -383,6 +453,9 @@ int main(int argc, char **argv) ret |= test_datapath(PACKET_FANOUT_CPU, port_off, expect_cpu1[0], expect_cpu1[1]); + ret |= test_datapath(PACKET_FANOUT_FLAG_UNIQUEID, port_off, + expect_uniqueid[0], expect_uniqueid[1]); + if (ret) return 1; |