Blame view

samples/bpf/xdp_adjust_tail_kern.c 3.83 KB
c6ffd1ff7   Nikita V. Shirokov   bpf: add bpf_xdp_...
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
  /* SPDX-License-Identifier: GPL-2.0
   * Copyright (c) 2018 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.
   *
   * This program shows how to use bpf_xdp_adjust_tail() by
   * generating ICMPv4 "packet to big" (unreachable/ df bit set frag needed
   * to be more preice in case of v4)" where receiving packets bigger then
   * 600 bytes.
   */
  #define KBUILD_MODNAME "foo"
  #include <uapi/linux/bpf.h>
  #include <linux/in.h>
  #include <linux/if_ether.h>
  #include <linux/if_packet.h>
  #include <linux/if_vlan.h>
  #include <linux/ip.h>
  #include <linux/icmp.h>
7cf245a37   Toke Høiland-Jørgensen   samples/bpf: Use ...
21
  #include <bpf/bpf_helpers.h>
c6ffd1ff7   Nikita V. Shirokov   bpf: add bpf_xdp_...
22
23
24
25
26
  
  #define DEFAULT_TTL 64
  #define MAX_PCKT_SIZE 600
  #define ICMP_TOOBIG_SIZE 98
  #define ICMP_TOOBIG_PAYLOAD_SIZE 92
8fdf5b780   Daniel T. Lee   samples: bpf: Add...
27
28
  /* volatile to prevent compiler optimizations */
  static volatile __u32 max_pcktsz = MAX_PCKT_SIZE;
451d1dc88   Daniel T. Lee   samples: bpf: upd...
29
30
31
32
33
34
  struct {
  	__uint(type, BPF_MAP_TYPE_ARRAY);
  	__type(key, __u32);
  	__type(value, __u64);
  	__uint(max_entries, 1);
  } icmpcnt SEC(".maps");
c6ffd1ff7   Nikita V. Shirokov   bpf: add bpf_xdp_...
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
  
  static __always_inline void count_icmp(void)
  {
  	u64 key = 0;
  	u64 *icmp_count;
  
  	icmp_count = bpf_map_lookup_elem(&icmpcnt, &key);
  	if (icmp_count)
  		*icmp_count += 1;
  }
  
  static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth)
  {
  	struct ethhdr *eth;
  
  	eth = data;
  	memcpy(eth->h_source, orig_eth->h_dest, ETH_ALEN);
  	memcpy(eth->h_dest, orig_eth->h_source, ETH_ALEN);
  	eth->h_proto = orig_eth->h_proto;
  }
  
  static __always_inline __u16 csum_fold_helper(__u32 csum)
  {
  	return ~((csum & 0xffff) + (csum >> 16));
  }
  
  static __always_inline void ipv4_csum(void *data_start, int data_size,
  				      __u32 *csum)
  {
  	*csum = bpf_csum_diff(0, 0, data_start, data_size, *csum);
  	*csum = csum_fold_helper(*csum);
  }
  
  static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
  {
  	int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr);
  
  	if (bpf_xdp_adjust_head(xdp, 0 - headroom))
  		return XDP_DROP;
  	void *data = (void *)(long)xdp->data;
  	void *data_end = (void *)(long)xdp->data_end;
  
  	if (data + (ICMP_TOOBIG_SIZE + headroom) > data_end)
  		return XDP_DROP;
  
  	struct iphdr *iph, *orig_iph;
  	struct icmphdr *icmp_hdr;
  	struct ethhdr *orig_eth;
  	__u32 csum = 0;
  	__u64 off = 0;
  
  	orig_eth = data + headroom;
  	swap_mac(data, orig_eth);
  	off += sizeof(struct ethhdr);
  	iph = data + off;
  	off += sizeof(struct iphdr);
  	icmp_hdr = data + off;
  	off += sizeof(struct icmphdr);
  	orig_iph = data + off;
  	icmp_hdr->type = ICMP_DEST_UNREACH;
  	icmp_hdr->code = ICMP_FRAG_NEEDED;
8fdf5b780   Daniel T. Lee   samples: bpf: Add...
96
  	icmp_hdr->un.frag.mtu = htons(max_pcktsz - sizeof(struct ethhdr));
c6ffd1ff7   Nikita V. Shirokov   bpf: add bpf_xdp_...
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
  	icmp_hdr->checksum = 0;
  	ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum);
  	icmp_hdr->checksum = csum;
  	iph->ttl = DEFAULT_TTL;
  	iph->daddr = orig_iph->saddr;
  	iph->saddr = orig_iph->daddr;
  	iph->version = 4;
  	iph->ihl = 5;
  	iph->protocol = IPPROTO_ICMP;
  	iph->tos = 0;
  	iph->tot_len = htons(
  		ICMP_TOOBIG_SIZE + headroom - sizeof(struct ethhdr));
  	iph->check = 0;
  	csum = 0;
  	ipv4_csum(iph, sizeof(struct iphdr), &csum);
  	iph->check = csum;
  	count_icmp();
  	return XDP_TX;
  }
  
  
  static __always_inline int handle_ipv4(struct xdp_md *xdp)
  {
  	void *data_end = (void *)(long)xdp->data_end;
  	void *data = (void *)(long)xdp->data;
  	int pckt_size = data_end - data;
  	int offset;
8fdf5b780   Daniel T. Lee   samples: bpf: Add...
124
  	if (pckt_size > max(max_pcktsz, ICMP_TOOBIG_SIZE)) {
c6ffd1ff7   Nikita V. Shirokov   bpf: add bpf_xdp_...
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
  		offset = pckt_size - ICMP_TOOBIG_SIZE;
  		if (bpf_xdp_adjust_tail(xdp, 0 - offset))
  			return XDP_PASS;
  		return send_icmp4_too_big(xdp);
  	}
  	return XDP_PASS;
  }
  
  SEC("xdp_icmp")
  int _xdp_icmp(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 == htons(ETH_P_IP))
  		return handle_ipv4(xdp);
  	else
  		return XDP_PASS;
  }
  
  char _license[] SEC("license") = "GPL";