diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 899f40310bc3e3c5137f3eb9abb5292a3e1d7e08..a8552b8a2ab6e770c25ef4351f48cc1768dd1e81 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -65,6 +65,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0; bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; bool is_sockops = strncmp(event, "sockops", 7) == 0; + bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0; size_t insns_cnt = size / sizeof(struct bpf_insn); enum bpf_prog_type prog_type; char buf[256]; @@ -92,6 +93,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_type = BPF_PROG_TYPE_CGROUP_SOCK; } else if (is_sockops) { prog_type = BPF_PROG_TYPE_SOCK_OPS; + } else if (is_sk_skb) { + prog_type = BPF_PROG_TYPE_SK_SKB; } else { printf("Unknown event '%s'\n", event); return -1; @@ -109,7 +112,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk) return 0; - if (is_socket || is_sockops) { + if (is_socket || is_sockops || is_sk_skb) { if (is_socket) event += 6; else @@ -567,7 +570,8 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) memcmp(shname, "perf_event", 10) == 0 || memcmp(shname, "socket", 6) == 0 || memcmp(shname, "cgroup/", 7) == 0 || - memcmp(shname, "sockops", 7) == 0) { + memcmp(shname, "sockops", 7) == 0 || + memcmp(shname, "sk_skb", 6) == 0) { ret = load_and_attach(shname, data->d_buf, data->d_size); if (ret != 0) diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..9291ab8e0f8c5a089425ae65f9ee20e718e0a9ff --- /dev/null +++ b/samples/sockmap/Makefile @@ -0,0 +1,78 @@ +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o + +# List of programs to build +hostprogs-y := sockmap + +# Libbpf dependencies +LIBBPF := ../../tools/lib/bpf/bpf.o + +HOSTCFLAGS += -I$(objtree)/usr/include +HOSTCFLAGS += -I$(srctree)/tools/lib/ +HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ +HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include +HOSTCFLAGS += -I$(srctree)/tools/perf + +sockmap-objs := ../bpf/bpf_load.o $(LIBBPF) sockmap_user.o + +# Tell kbuild to always build the programs +always := $(hostprogs-y) +always += sockmap_kern.o + +HOSTLOADLIBES_sockmap += -lelf -lpthread + +# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: +# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang +LLC ?= llc +CLANG ?= clang + +# Trick to allow make to be run from this directory +all: + $(MAKE) -C ../../ $(CURDIR)/ + +clean: + $(MAKE) -C ../../ M=$(CURDIR) clean + @rm -f *~ + +$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c + $(call if_changed_dep,cc_s_c) + +$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE + $(call filechk,offsets,__SYSCALL_NRS_H__) + +clean-files += syscall_nrs.h + +FORCE: + + +# Verify LLVM compiler tools are available and bpf target is supported by llc +.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC) + +verify_cmds: $(CLANG) $(LLC) + @for TOOL in $^ ; do \ + if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \ + echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\ + exit 1; \ + else true; fi; \ + done + +verify_target_bpf: verify_cmds + @if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \ + echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\ + echo " NOTICE: LLVM version >= 3.7.1 required" ;\ + exit 2; \ + else true; fi + +$(src)/*.c: verify_target_bpf + +# asm/sysreg.h - inline assembly used by it is incompatible with llvm. +# But, there is no easy way to fix it, so just exclude it since it is +# useless for BPF samples. +$(obj)/%.o: $(src)/%.c + $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ + -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ + -Wno-compare-distinct-pointer-types \ + -Wno-gnu-variable-sized-type-not-at-end \ + -Wno-address-of-packed-member -Wno-tautological-compare \ + -Wno-unknown-warning-option \ + -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c new file mode 100644 index 0000000000000000000000000000000000000000..6ff986f7059b84daf085c7ea7f74549f1b0864f8 --- /dev/null +++ b/samples/sockmap/sockmap_kern.c @@ -0,0 +1,110 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * 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 is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include "../../tools/testing/selftests/bpf/bpf_helpers.h" +#include "../../tools/testing/selftests/bpf/bpf_endian.h" + +/* Sockmap sample program connects a client and a backend together + * using cgroups. + * + * client:X <---> frontend:80 client:X <---> backend:80 + * + * For simplicity we hard code values here and bind 1:1. The hard + * coded values are part of the setup in sockmap.sh script that + * is associated with this BPF program. + * + * The bpf_printk is verbose and prints information as connections + * are established and verdicts are decided. + */ + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + int ret = 0; + + if (lport == 10000) + ret = 10; + else + ret = 1; + + bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret); + return bpf_sk_redirect_map(&sock_map, ret, 0); +} + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 lport, rport; + int op, err = 0, index, key, ret; + + + op = (int) skops->op; + + switch (op) { + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (lport == 10000) { + ret = 1; + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST, + BPF_SOCKMAP_STRPARSER); + bpf_printk("passive(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (bpf_ntohl(rport) == 10001) { + ret = 10; + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST, + BPF_SOCKMAP_STRPARSER); + bpf_printk("active(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + default: + break; + } + + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c new file mode 100644 index 0000000000000000000000000000000000000000..fb78f5abefb4c5ace195b51ffe2826de5bebcaab --- /dev/null +++ b/samples/sockmap/sockmap_user.c @@ -0,0 +1,286 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * 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 is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "../bpf/bpf_load.h" +#include "../bpf/bpf_util.h" +#include "../bpf/libbpf.h" + +int running; +void running_handler(int a); + +/* randomly selected ports for testing on lo */ +#define S1_PORT 10000 +#define S2_PORT 10001 + +static int sockmap_test_sockets(int rate, int dot) +{ + int i, sc, err, max_fd, one = 1; + int s1, s2, c1, c2, p1, p2; + struct sockaddr_in addr; + struct timeval timeout; + char buf[1024] = {0}; + int *fds[4] = {&s1, &s2, &c1, &c2}; + fd_set w; + + s1 = s2 = p1 = p2 = c1 = c2 = 0; + + /* Init sockets */ + for (i = 0; i < 4; i++) { + *fds[i] = socket(AF_INET, SOCK_STREAM, 0); + if (*fds[i] < 0) { + perror("socket s1 failed()"); + err = *fds[i]; + goto out; + } + } + + /* Allow reuse */ + for (i = 0; i < 2; i++) { + err = setsockopt(*fds[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + perror("setsockopt failed()"); + goto out; + } + } + + /* Non-blocking sockets */ + for (i = 0; i < 4; i++) { + err = ioctl(*fds[i], FIONBIO, (char *)&one); + if (err < 0) { + perror("ioctl s1 failed()"); + goto out; + } + } + + /* Bind server sockets */ + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + + addr.sin_port = htons(S1_PORT); + err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s1 failed()\n"); + goto out; + } + + addr.sin_port = htons(S2_PORT); + err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s2 failed()\n"); + goto out; + } + + /* Listen server sockets */ + addr.sin_port = htons(S1_PORT); + err = listen(s1, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + goto out; + } + + addr.sin_port = htons(S2_PORT); + err = listen(s2, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + goto out; + } + + /* Initiate Connect */ + addr.sin_port = htons(S1_PORT); + err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c1 failed()\n"); + goto out; + } + + addr.sin_port = htons(S2_PORT); + err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c2 failed()\n"); + goto out; + } + + /* Accept Connecrtions */ + p1 = accept(s1, NULL, NULL); + if (p1 < 0) { + perror("accept s1 failed()\n"); + goto out; + } + + p2 = accept(s2, NULL, NULL); + if (p2 < 0) { + perror("accept s1 failed()\n"); + goto out; + } + + max_fd = p2; + timeout.tv_sec = 10; + timeout.tv_usec = 0; + + printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); + printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", + c1, s1, c2, s2); + + /* Ping/Pong data from client to server */ + sc = send(c1, buf, sizeof(buf), 0); + if (sc < 0) { + perror("send failed()\n"); + goto out; + } + + do { + int s, rc, i; + + /* FD sets */ + FD_ZERO(&w); + FD_SET(c1, &w); + FD_SET(c2, &w); + FD_SET(p1, &w); + FD_SET(p2, &w); + + s = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (s == -1) { + perror("select()"); + break; + } else if (!s) { + fprintf(stderr, "unexpected timeout\n"); + break; + } + + for (i = 0; i <= max_fd && s > 0; ++i) { + if (!FD_ISSET(i, &w)) + continue; + + s--; + + rc = recv(i, buf, sizeof(buf), 0); + if (rc < 0) { + if (errno != EWOULDBLOCK) { + perror("recv failed()\n"); + break; + } + } + + if (rc == 0) { + close(i); + break; + } + + sc = send(i, buf, rc, 0); + if (sc < 0) { + perror("send failed()\n"); + break; + } + } + sleep(rate); + if (dot) { + printf("."); + fflush(stdout); + + } + } while (running); + +out: + close(s1); + close(s2); + close(p1); + close(p2); + close(c1); + close(c2); + return err; +} + +int main(int argc, char **argv) +{ + int rate = 1, dot = 1; + char filename[256]; + int err, cg_fd; + char *cg_path; + + cg_path = argv[argc - 1]; + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + running = 1; + + /* catch SIGINT */ + signal(SIGINT, running_handler); + + if (load_bpf_file(filename)) { + fprintf(stderr, "load_bpf_file: (%s) %s\n", + filename, strerror(errno)); + return 1; + } + + /* Cgroup configuration */ + cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY); + if (cg_fd < 0) { + fprintf(stderr, "ERROR: (%i) open cg path failed: %s\n", + cg_fd, cg_path); + return cg_fd; + } + + /* Attach programs to sockmap */ + err = __bpf_prog_attach(prog_fd[0], prog_fd[1], map_fd[0], + BPF_CGROUP_SMAP_INGRESS, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + + /* Attach to cgroups */ + err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", + err, strerror(errno)); + return err; + } + + err = sockmap_test_sockets(rate, dot); + if (err) { + fprintf(stderr, "ERROR: test socket failed: %d\n", err); + return err; + } + return 0; +} + +void running_handler(int a) +{ + running = 0; +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bf3b2e23045569da71ad152df3949febe2864da2..2d97dd27c8f64f5e6162472aae9b70eea58f1dda 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -110,6 +110,7 @@ enum bpf_map_type { BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, }; enum bpf_prog_type { @@ -127,6 +128,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, }; enum bpf_attach_type { @@ -134,11 +136,18 @@ enum bpf_attach_type { BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_SOCK_OPS, + BPF_CGROUP_SMAP_INGRESS, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_sockmap_flags { + BPF_SOCKMAP_UNSPEC, + BPF_SOCKMAP_STRPARSER, + __MAX_BPF_SOCKMAP_FLAG +}; + /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -210,6 +219,7 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 attach_bpf_fd2; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -545,6 +555,23 @@ union bpf_attr { * @mode: operation mode (enum bpf_adj_room_mode) * @flags: reserved for future use * Return: 0 on success or negative error code + * + * int bpf_sk_redirect_map(map, key, flags) + * Redirect skb to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_REDIRECT + * + * int bpf_sock_map_update(skops, map, key, flags, map_flags) + * @skops: pointer to bpf_sock_ops + * @map: pointer to sockmap to update + * @key: key to insert/update sock in map + * @flags: same flags as map update elem + * @map_flags: sock map specific flags + * bit 1: Enable strparser + * other bits: reserved */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -598,7 +625,9 @@ union bpf_attr { FN(set_hash), \ FN(setsockopt), \ FN(skb_adjust_room), \ - FN(redirect_map), + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -675,6 +704,15 @@ struct __sk_buff { __u32 data; __u32 data_end; __u32 napi_id; + + /* accessed by BPF_PROG_TYPE_sk_skb types */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; struct bpf_tunnel_key { @@ -734,6 +772,12 @@ struct xdp_md { __u32 data_end; }; +enum sk_action { + SK_ABORTED = 0, + SK_DROP, + SK_REDIRECT, +}; + #define BPF_TAG_SIZE 8 struct bpf_prog_info { diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index e5bbb090bf88549111f939dcd7c1f500e6f84a4f..77660157a68445edb7cb0e82ce239f5eafec9822 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -211,20 +211,28 @@ int bpf_obj_get(const char *pathname) return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); } -int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, - unsigned int flags) +int __bpf_prog_attach(int prog_fd1, int prog_fd2, int target_fd, + enum bpf_attach_type type, + unsigned int flags) { union bpf_attr attr; bzero(&attr, sizeof(attr)); attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd; + attr.attach_bpf_fd = prog_fd1; + attr.attach_bpf_fd2 = prog_fd2; attr.attach_type = type; attr.attach_flags = flags; return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, + unsigned int flags) +{ + return __bpf_prog_attach(prog_fd, 0, target_fd, type, flags); +} + int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 418c86e69bcbfae71d93d07c7054afa08b149c18..eaee585c1cead0fb7b8956859f49f107bf952b91 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -50,6 +50,10 @@ int bpf_obj_pin(int fd, const char *pathname); int bpf_obj_get(const char *pathname); int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +int __bpf_prog_attach(int prog1, int prog2, + int attachable_fd, + enum bpf_attach_type type, + unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index acbd6051946772e0385a5871cb212c89e7a64d0c..73092d4a898ed14d908199e1a8ae869bea205aab 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -65,6 +65,13 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; +static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = + (void *) BPF_FUNC_sk_redirect_map; +static int (*bpf_sock_map_update)(void *map, void *key, void *value, + unsigned long long flags, + unsigned long long map_lags) = + (void *) BPF_FUNC_sock_map_update; + /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions