Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | // SPDX-License-Identifier: GPL-2.0 #include <string.h> #include <linux/tcp.h> #include <linux/bpf.h> #include <netinet/in.h> #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; int page_size = 0; /* userspace should set it */ #ifndef SOL_TCP #define SOL_TCP IPPROTO_TCP #endif #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { __u8 val; }; struct { __uint(type, BPF_MAP_TYPE_SK_STORAGE); __uint(map_flags, BPF_F_NO_PREALLOC); __type(key, int); __type(value, struct sockopt_sk); } socket_storage_map SEC(".maps"); SEC("cgroup/getsockopt") int _getsockopt(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; __u8 *optval = ctx->optval; struct sockopt_sk *storage; struct bpf_sock *sk; /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) return 1; /* Make sure bpf_get_netns_cookie is callable. */ if (bpf_get_netns_cookie(NULL) == 0) return 0; if (bpf_get_netns_cookie(ctx) == 0) return 0; if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Not interested in SOL_SOCKET:SO_SNDBUF; * let next BPF program in the cgroup chain or kernel * handle it. */ return 1; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { /* Not interested in SOL_TCP:TCP_CONGESTION; * let next BPF program in the cgroup chain or kernel * handle it. */ return 1; } if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { /* Verify that TCP_ZEROCOPY_RECEIVE triggers. * It has a custom implementation for performance * reasons. */ /* Check that optval contains address (__u64) */ if (optval + sizeof(__u64) > optval_end) return 0; /* bounds check */ if (((struct tcp_zerocopy_receive *)optval)->address != 0) return 0; /* unexpected data */ return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) return 0; /* bounds check */ ctx->retval = 0; /* Reset system call return value to zero */ /* Always export 0x55 */ optval[0] = 0x55; ctx->optlen = 1; /* Userspace buffer is PAGE_SIZE * 2, but BPF * program can only see the first PAGE_SIZE * bytes of data. */ if (optval_end - optval != page_size) return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) return 0; /* couldn't get sk storage */ if (!ctx->retval) return 0; /* kernel should not have handled * SOL_CUSTOM, something is wrong! */ ctx->retval = 0; /* Reset system call return value to zero */ optval[0] = storage->val; ctx->optlen = 1; return 1; } SEC("cgroup/setsockopt") int _setsockopt(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; __u8 *optval = ctx->optval; struct sockopt_sk *storage; struct bpf_sock *sk; /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) return 1; /* Make sure bpf_get_netns_cookie is callable. */ if (bpf_get_netns_cookie(NULL) == 0) return 0; if (bpf_get_netns_cookie(ctx) == 0) return 0; if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Overwrite SO_SNDBUF value */ if (optval + sizeof(__u32) > optval_end) return 0; /* bounds check */ *(__u32 *)optval = 0x55AA; ctx->optlen = 4; return 1; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { /* Always use cubic */ if (optval + 5 > optval_end) return 0; /* bounds check */ memcpy(optval, "cubic", 5); ctx->optlen = 5; return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { /* Original optlen is larger than PAGE_SIZE. */ if (ctx->optlen != page_size * 2) return 0; /* unexpected data size */ if (optval + 1 > optval_end) return 0; /* bounds check */ /* Make sure we can trim the buffer. */ optval[0] = 0; ctx->optlen = 1; /* Usepace buffer is PAGE_SIZE * 2, but BPF * program can only see the first PAGE_SIZE * bytes of data. */ if (optval_end - optval != page_size) return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) return 0; /* couldn't get sk storage */ storage->val = optval[0]; ctx->optlen = -1; /* BPF has consumed this option, don't call kernel * setsockopt handler. */ return 1; } |