├── LICENSE ├── README.md ├── network.c ├── network.h └── network.py /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # The Beginner's Guide to eBPF Programming for Networking 2 | 3 | As seen at Cloud Native eBPF Day 2021. 4 | 5 | ## Setup 6 | 7 | Create a container that we can issue curl requests to. 8 | 9 | ``` 10 | docker run -d --rm --name backend-A -h backend-A --env TERM=xterm-color nginxdemos/hello:plain-text 11 | 12 | # Get the IP address of this target 13 | docker exec -it backend-A ip a 14 | ``` 15 | 16 | Create a privileged container from which we can run eBPF programs. We will attach most of our programs to its `eth0` virtual 17 | interface. 18 | 19 | ``` 20 | docker run --rm -it -v /usr:/usr -v /home:/home -v /sys:/sys --privileged --env TERM=xterm-color -h container ubuntu 21 | ``` 22 | 23 | Assuming you cloned this repo into your home directory, the mount of `/home` 24 | means you can `cd /home//ebpf-networking` within this container to 25 | find this example code. 26 | 27 | In a separate terminal window, observe the debug trace output: 28 | 29 | ```bash 30 | sudo cat /sys/kernel/debug/tracing/trace_pipe 31 | ``` 32 | 33 | ## Prerequisites 34 | 35 | These examples use [BCC](https://github.com/iovisor/bcc) 36 | 37 | ## Examples 38 | 39 | See the 40 | [slides](https://speakerdeck.com/lizrice/beginners-guide-to-ebpf-programming-for-networking) 41 | and video (coming soon) for more info on the different examples included here, 42 | and how to use them. 43 | 44 | Examples include 45 | * Kprobe on tcp_v4_connect() kernel function 46 | * Attaching a socket filter to a raw socket 47 | * XDP 48 | * Traffic control - adding a filter on ingress 49 | 50 | ## More examples 51 | 52 | This is part of a series of eBPF example code that are indexed at [lizrice/ebpf-beginners](https://github.com/lizrice/ebpf-beginners) 53 | 54 | -------------------------------------------------------------------------------- /network.c: -------------------------------------------------------------------------------- 1 | #include "network.h" 2 | 3 | #include 4 | #include 5 | #include 6 | #include 7 | #include 8 | 9 | int tcpconnect(void *ctx) { 10 | bpf_trace_printk("[tcpconnect]\n"); 11 | return 0; 12 | } 13 | 14 | int socket_filter(struct __sk_buff *skb) { 15 | unsigned char *cursor = 0; 16 | 17 | struct ethernet_t *ethernet = cursor_advance(cursor, sizeof(*ethernet)); 18 | // Look for IP packets 19 | if (ethernet->type != 0x0800) { 20 | return 0; 21 | } 22 | 23 | struct ip_t *ip = cursor_advance(cursor, sizeof(*ip)); 24 | 25 | if (ip->nextp == 0x01) { 26 | bpf_trace_printk("[socket_filter] ICMP request for %x\n", ip->dst); 27 | } 28 | 29 | if (ip->nextp == 0x06) { 30 | bpf_trace_printk("[socket_filter] TCP packet for %x\n", ip->dst); 31 | // Send TCP packets to userspace 32 | return -1; 33 | } 34 | 35 | return 0; 36 | } 37 | 38 | int xdp(struct xdp_md *ctx) { 39 | void *data = (void *)(long)ctx->data; 40 | void *data_end = (void *)(long)ctx->data_end; 41 | 42 | if (is_icmp_ping_request(data, data_end)) { 43 | struct iphdr *iph = data + sizeof(struct ethhdr); 44 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 45 | bpf_trace_printk("[xdp] ICMP request for %x type %x\n", iph->daddr, 46 | icmp->type); 47 | } 48 | 49 | return XDP_PASS; 50 | } 51 | 52 | int tc(struct __sk_buff *skb) { 53 | bpf_trace_printk("[tc] ingress got packet\n"); 54 | 55 | void *data = (void *)(long)skb->data; 56 | void *data_end = (void *)(long)skb->data_end; 57 | 58 | if (is_icmp_ping_request(data, data_end)) { 59 | struct iphdr *iph = data + sizeof(struct ethhdr); 60 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 61 | bpf_trace_printk("[tc] ICMP request for %x type %x\n", iph->daddr, 62 | icmp->type); 63 | return TC_ACT_SHOT; 64 | } 65 | return TC_ACT_OK; 66 | } 67 | 68 | int tc_drop(struct __sk_buff *skb) { 69 | bpf_trace_printk("[tc] dropping packet\n"); 70 | return TC_ACT_SHOT; 71 | } 72 | 73 | int tc_pingpong(struct __sk_buff *skb) { 74 | bpf_trace_printk("[tc] ingress got packet\n"); 75 | 76 | void *data = (void *)(long)skb->data; 77 | void *data_end = (void *)(long)skb->data_end; 78 | 79 | if (!is_icmp_ping_request(data, data_end)) { 80 | return TC_ACT_OK; 81 | } 82 | 83 | struct iphdr *iph = data + sizeof(struct ethhdr); 84 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 85 | bpf_trace_printk("[tc] ICMP request for %x type %x\n", iph->daddr, 86 | icmp->type); 87 | 88 | swap_mac_addresses(skb); 89 | swap_ip_addresses(skb); 90 | 91 | // Change the type of the ICMP packet to 0 (ICMP Echo Reply) (was 8 for ICMP 92 | // Echo request) 93 | update_icmp_type(skb, 8, 0); 94 | 95 | // Redirecting the modified skb on the same interface to be transmitted 96 | // again 97 | bpf_clone_redirect(skb, skb->ifindex, 0); 98 | 99 | // We modified the packet and redirected a clone of it, so drop this one 100 | return TC_ACT_SHOT; 101 | } 102 | -------------------------------------------------------------------------------- /network.h: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | #include 5 | #include 6 | #include 7 | 8 | static __always_inline unsigned short is_icmp_ping_request(void *data, 9 | void *data_end) { 10 | struct ethhdr *eth = data; 11 | if (data + sizeof(struct ethhdr) > data_end) 12 | return 0; 13 | 14 | if (bpf_ntohs(eth->h_proto) != ETH_P_IP) 15 | return 0; 16 | 17 | struct iphdr *iph = data + sizeof(struct ethhdr); 18 | if (data + sizeof(struct ethhdr) + sizeof(struct iphdr) > data_end) 19 | return 0; 20 | 21 | if (iph->protocol != 0x01) 22 | // We're only interested in ICMP packets 23 | return 0; 24 | 25 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 26 | if (data + sizeof(struct ethhdr) + sizeof(struct iphdr) + 27 | sizeof(struct icmphdr) > 28 | data_end) 29 | return 0; 30 | 31 | return (icmp->type == 8); 32 | } 33 | 34 | static __always_inline unsigned short ping_request_to_reply(void *data, 35 | void *data_end) { 36 | struct ethhdr *eth = data; 37 | if (data + sizeof(struct ethhdr) > data_end) 38 | return 0; 39 | 40 | if (bpf_ntohs(eth->h_proto) != ETH_P_IP) 41 | return 0; 42 | 43 | struct iphdr *iph = data + sizeof(struct ethhdr); 44 | if (data + sizeof(struct ethhdr) + sizeof(struct iphdr) > data_end) 45 | return 0; 46 | 47 | if (iph->protocol != 0x01) 48 | // We're only interested in ICMP packets 49 | return 0; 50 | 51 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 52 | if (data + sizeof(struct ethhdr) + sizeof(struct iphdr) + 53 | sizeof(struct icmphdr) > 54 | data_end) 55 | return 0; 56 | 57 | return (icmp->type == 8); 58 | } 59 | 60 | static __always_inline void swap_mac_addresses(struct __sk_buff *skb) { 61 | unsigned char src_mac[6]; 62 | unsigned char dst_mac[6]; 63 | bpf_skb_load_bytes(skb, offsetof(struct ethhdr, h_source), src_mac, 6); 64 | bpf_skb_load_bytes(skb, offsetof(struct ethhdr, h_dest), dst_mac, 6); 65 | bpf_skb_store_bytes(skb, offsetof(struct ethhdr, h_source), dst_mac, 6, 0); 66 | bpf_skb_store_bytes(skb, offsetof(struct ethhdr, h_dest), src_mac, 6, 0); 67 | } 68 | 69 | #define IP_SRC_OFF (ETH_HLEN + offsetof(struct iphdr, saddr)) 70 | #define IP_DST_OFF (ETH_HLEN + offsetof(struct iphdr, daddr)) 71 | 72 | static __always_inline void swap_ip_addresses(struct __sk_buff *skb) { 73 | unsigned char src_ip[4]; 74 | unsigned char dst_ip[4]; 75 | bpf_skb_load_bytes(skb, IP_SRC_OFF, src_ip, 4); 76 | bpf_skb_load_bytes(skb, IP_DST_OFF, dst_ip, 4); 77 | bpf_skb_store_bytes(skb, IP_SRC_OFF, dst_ip, 4, 0); 78 | bpf_skb_store_bytes(skb, IP_DST_OFF, src_ip, 4, 0); 79 | } 80 | 81 | #define ICMP_CSUM_OFF \ 82 | (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct icmphdr, checksum)) 83 | #define ICMP_TYPE_OFF \ 84 | (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct icmphdr, type)) 85 | 86 | static __always_inline void update_icmp_type(struct __sk_buff *skb, 87 | unsigned char old_type, 88 | unsigned char new_type) { 89 | bpf_l4_csum_replace(skb, ICMP_CSUM_OFF, old_type, new_type, 2); 90 | bpf_skb_store_bytes(skb, ICMP_TYPE_OFF, &new_type, sizeof(new_type), 0); 91 | } 92 | -------------------------------------------------------------------------------- /network.py: -------------------------------------------------------------------------------- 1 | #include "network.h" 2 | 3 | #include 4 | #include 5 | #include 6 | #include 7 | #include 8 | 9 | int tcpconnect(void *ctx) { 10 | bpf_trace_printk("[tcpconnect]\n"); 11 | return 0; 12 | } 13 | 14 | int socket_filter(struct __sk_buff *skb) { 15 | unsigned char *cursor = 0; 16 | 17 | struct ethernet_t *ethernet = cursor_advance(cursor, sizeof(*ethernet)); 18 | // Look for IP packets 19 | if (ethernet->type != 0x0800) { 20 | return 0; 21 | } 22 | 23 | struct ip_t *ip = cursor_advance(cursor, sizeof(*ip)); 24 | 25 | if (ip->nextp == 0x01) { 26 | bpf_trace_printk("[socket_filter] ICMP request for %x\n", ip->dst); 27 | } 28 | 29 | if (ip->nextp == 0x06) { 30 | bpf_trace_printk("[socket_filter] TCP packet for %x\n", ip->dst); 31 | // Send TCP packets to userspace 32 | return -1; 33 | } 34 | 35 | return 0; 36 | } 37 | 38 | int xdp(struct xdp_md *ctx) { 39 | void *data = (void *)(long)ctx->data; 40 | void *data_end = (void *)(long)ctx->data_end; 41 | 42 | if (is_icmp_ping_request(data, data_end)) { 43 | struct iphdr *iph = data + sizeof(struct ethhdr); 44 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 45 | bpf_trace_printk("[xdp] ICMP request for %x type %x\n", iph->daddr, 46 | icmp->type); 47 | } 48 | 49 | return XDP_PASS; 50 | } 51 | 52 | int tc(struct __sk_buff *skb) { 53 | bpf_trace_printk("[tc] ingress got packet\n"); 54 | 55 | void *data = (void *)(long)skb->data; 56 | void *data_end = (void *)(long)skb->data_end; 57 | 58 | if (is_icmp_ping_request(data, data_end)) { 59 | struct iphdr *iph = data + sizeof(struct ethhdr); 60 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 61 | bpf_trace_printk("[tc] ICMP request for %x type %x\n", iph->daddr, 62 | icmp->type); 63 | return TC_ACT_SHOT; 64 | } 65 | return TC_ACT_OK; 66 | } 67 | 68 | int tc_drop(struct __sk_buff *skb) { 69 | bpf_trace_printk("[tc] dropping packet\n"); 70 | return TC_ACT_SHOT; 71 | } 72 | 73 | int tc_pingpong(struct __sk_buff *skb) { 74 | bpf_trace_printk("[tc] ingress got packet\n"); 75 | 76 | void *data = (void *)(long)skb->data; 77 | void *data_end = (void *)(long)skb->data_end; 78 | 79 | if (!is_icmp_ping_request(data, data_end)) { 80 | return TC_ACT_OK; 81 | } 82 | 83 | struct iphdr *iph = data + sizeof(struct ethhdr); 84 | struct icmphdr *icmp = data + sizeof(struct ethhdr) + sizeof(struct iphdr); 85 | bpf_trace_printk("[tc] ICMP request for %x type %x\n", iph->daddr, 86 | icmp->type); 87 | 88 | swap_mac_addresses(skb); 89 | swap_ip_addresses(skb); 90 | 91 | // Change the type of the ICMP packet to 0 (ICMP Echo Reply) (was 8 for ICMP 92 | // Echo request) 93 | update_icmp_type(skb, 8, 0); 94 | 95 | // Redirecting the modified skb on the same interface to be transmitted 96 | // again 97 | bpf_clone_redirect(skb, skb->ifindex, 0); 98 | 99 | // We modified the packet and redirected a clone of it, so drop this one 100 | return TC_ACT_SHOT; 101 | } 102 | --------------------------------------------------------------------------------