From: Andrey Ignatov <r...@fb.com>
Add selftest to work with bpf_sock_addr context from
`BPF_PROG_TYPE_CGROUP_INET4_BIND` and BPF_PROG_TYPE_CGROUP_INET6_BIND`
programs.
Try to bind(2) on IP:port and apply:
* loads to make sure context can be read correctly, including narrow
loads (byte, half) for IP and full-size loads (word) for all fields;
* stores to those fields allowed by verifier.
All combination from IPv4/IPv6 and TCP/UDP are tested.
Test passes when expected data can be read from context in the
BPF-program, and after the call to bind(2) socket is bound to IP:port
pair that was written by BPF-program to the context.
Example:
# ./test_sock_addr
Attached bind4 program.
Test case #1 (IPv4/TCP):
Requested: bind(192.168.1.254, 4040) ..
Actual: bind(127.0.0.1, 4444)
Test case #2 (IPv4/UDP):
Requested: bind(192.168.1.254, 4040) ..
Actual: bind(127.0.0.1, 4444)
Attached bind6 program.
Test case #3 (IPv6/TCP):
Requested: bind(face:b00c:1234:5678::abcd, 6060) ..
Actual: bind(::1, 6666)
Test case #4 (IPv6/UDP):
Requested: bind(face:b00c:1234:5678::abcd, 6060) ..
Actual: bind(::1, 6666)
### SUCCESS
Signed-off-by: Andrey Ignatov <r...@fb.com>
Acked-by: Alexei Starovoitov <a...@kernel.org>
Signed-off-by: Alexei Starovoitov <a...@kernel.org>
---
tools/include/uapi/linux/bpf.h | 24 ++
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/test_sock_addr.c | 463 +++++++++++++++++++++++++++
3 files changed, 489 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_sock_addr.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index db6bdc375126..a6af06bb5efb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -133,6 +133,8 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SOCK_OPS,
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
+ BPF_PROG_TYPE_CGROUP_INET4_BIND,
+ BPF_PROG_TYPE_CGROUP_INET6_BIND,
};
enum bpf_attach_type {
@@ -143,6 +145,8 @@ enum bpf_attach_type {
BPF_SK_SKB_STREAM_PARSER,
BPF_SK_SKB_STREAM_VERDICT,
BPF_CGROUP_DEVICE,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
__MAX_BPF_ATTACH_TYPE
};
@@ -952,6 +956,26 @@ struct bpf_map_info {
__u64 netns_ino;
} __attribute__((aligned(8)));
+/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
+ * by user and intended to be used by socket (e.g. to bind to, depends on
+ * attach attach type).
+ */
+struct bpf_sock_addr {
+ __u32 user_family; /* Allows 4-byte read, but no write. */
+ __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 4-byte read and write.
+ * Stored in network byte order
+ */
+ __u32 family; /* Allows 4-byte read, but no write */
+ __u32 type; /* Allows 4-byte read, but no write */
+ __u32 protocol; /* Allows 4-byte read, but no write */
+};
+
/* User bpf_sock_ops struct to access socket values and specify request ops
* and their replies.
* Some of this fields are in network (bigendian) byte order and may need
diff --git a/tools/testing/selftests/bpf/Makefile
b/tools/testing/selftests/bpf/Makefile
index 8567a858b789..f319b67fd0f6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -15,7 +15,7 @@ LDLIBS += -lcap -lelf -lrt -lpthread
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
test_progs \
- test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
+ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
test_sock_addr
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o
sockmap_parse_prog.o \
@@ -42,6 +42,7 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_sock_addr: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c
b/tools/testing/selftests/bpf/test_sock_addr.c
new file mode 100644
index 000000000000..18ea250484dc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -0,0 +1,463 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <linux/filter.h>
+
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+
+#define CG_PATH "/foo"
+
+#define SERV4_IP "192.168.1.254"
+#define SERV4_REWRITE_IP "127.0.0.1"
+#define SERV4_PORT 4040
+#define SERV4_REWRITE_PORT 4444
+
+#define SERV6_IP "face:b00c:1234:5678::abcd"
+#define SERV6_REWRITE_IP "::1"
+#define SERV6_PORT 6060
+#define SERV6_REWRITE_PORT 6666
+
+#define INET_NTOP_BUF 40
+
+typedef int (*load_fn)(void);
+typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
+
+struct program {
+ enum bpf_attach_type type;
+ load_fn loadfn;
+ int fd;
+ const char *name;
+};
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int mk_sockaddr(int domain, const char *ip, unsigned short port,
+ struct sockaddr *addr, socklen_t addr_len)
+{
+ struct sockaddr_in6 *addr6;
+ struct sockaddr_in *addr4;
+
+ if (domain != AF_INET && domain != AF_INET6) {
+ log_err("Unsupported address family");
+ return -1;
+ }
+
+ memset(addr, 0, addr_len);
+
+ if (domain == AF_INET) {
+ if (addr_len < sizeof(struct sockaddr_in))
+ return -1;
+ addr4 = (struct sockaddr_in *)addr;
+ addr4->sin_family = domain;
+ addr4->sin_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr4->sin_addr) != 1) {
+ log_err("Invalid IPv4: %s", ip);
+ return -1;
+ }
+ } else if (domain == AF_INET6) {
+ if (addr_len < sizeof(struct sockaddr_in6))
+ return -1;
+ addr6 = (struct sockaddr_in6 *)addr;
+ addr6->sin6_family = domain;
+ addr6->sin6_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr6->sin6_addr) != 1) {
+ log_err("Invalid IPv6: %s", ip);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int load_insns(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, const char *comment)
+{
+ int ret;
+
+ ret = bpf_load_program(type, insns, insns_cnt, "GPL", 0, bpf_log_buf,
+ BPF_LOG_BUF_SIZE);
+ if (ret < 0) {
+ log_err(">>> Loading %s program error.\n"
+ ">>> Output from verifier:\n%s\n-------\n",
+ comment, bpf_log_buf);
+ }
+
+ return ret;
+}
+
+/* [1] These testing programs try to read different context fields, including
+ * narrow loads of different sizes from user_ip4 and user_ip6, and write to
+ * those allowed to be overridden.
+ *
+ * [2] BPF_LD_IMM64 & BPF_JMP_REG are used below whenever there is a need to
+ * compare a register with unsigned 32bit integer. BPF_JMP_IMM can't be used
+ * in such cases since it accepts only _signed_ 32bit integer as IMM
+ * argument. Also note that BPF_LD_IMM64 contains 2 instructions what matters
+ * to count jumps properly.
+ */
+
+static int bind4_prog_load(void)
+{
+ union {
+ uint8_t u4_addr8[4];
+ uint16_t u4_addr16[2];
+ uint32_t u4_addr32;
+ } ip4;
+ struct sockaddr_in addr4_rw;
+
+ if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
+ log_err("Invalid IPv4: %s", SERV4_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
+ (struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
+ return -1;
+
+ /* See [1]. */
+ struct bpf_insn insns[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (sk.family == AF_INET && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, family)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16),
+
+ /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, type)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
+ BPF_JMP_A(1),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12),
+
+ /* 1st_byte_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10),
+
+ /* 1st_half_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8),
+
+ /* whole_user_ip4 == expected) { */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
+
+ /* user_ip4 = addr4_rw.sin_addr */
+ BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_addr.s_addr),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+
+ /* user_port = addr4_rw.sin_port */
+ BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_port),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_port)),
+ /* } */
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ };
+
+ return load_insns(BPF_PROG_TYPE_CGROUP_INET4_BIND, insns,
+ sizeof(insns) / sizeof(struct bpf_insn),
+ "bind() for AF_INET");
+}
+
+static int bind6_prog_load(void)
+{
+ struct sockaddr_in6 addr6_rw;
+ struct in6_addr ip6;
+
+ if (inet_pton(AF_INET6, SERV6_IP, (void *)&ip6) != 1) {
+ log_err("Invalid IPv6: %s", SERV6_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET6, SERV6_REWRITE_IP, SERV6_REWRITE_PORT,
+ (struct sockaddr *)&addr6_rw, sizeof(addr6_rw)) == -1)
+ return -1;
+
+ /* See [1]. */
+ struct bpf_insn insns[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (sk.family == AF_INET6 && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, family)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18),
+
+ /* 5th_byte_of_user_ip6 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[1])),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr[4], 16),
+
+ /* 3rd_half_of_user_ip6 == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[1])),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr16[2], 14),
+
+ /* last_word_of_user_ip6 == expected) { */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[3])),
+ BPF_LD_IMM64(BPF_REG_8, ip6.s6_addr32[3]), /* See [2]. */
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 10),
+
+
+#define STORE_IPV6_WORD(N) \
+ BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_addr.s6_addr32[N]), \
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \
+ offsetof(struct bpf_sock_addr, user_ip6[N]))
+
+ /* user_ip6 = addr6_rw.sin6_addr */
+ STORE_IPV6_WORD(0),
+ STORE_IPV6_WORD(1),
+ STORE_IPV6_WORD(2),
+ STORE_IPV6_WORD(3),
+
+ /* user_port = addr6_rw.sin6_port */
+ BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_port),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_port)),
+
+ /* } */
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ };
+
+ return load_insns(BPF_PROG_TYPE_CGROUP_INET6_BIND, insns,
+ sizeof(insns) / sizeof(struct bpf_insn),
+ "bind() for AF_INET6");
+}
+
+static void print_ip_port(int sockfd, info_fn fn, const char *fmt)
+{
+ char addr_buf[INET_NTOP_BUF];
+ struct sockaddr_storage addr;
+ struct sockaddr_in6 *addr6;
+ struct sockaddr_in *addr4;
+ socklen_t addr_len;
+ unsigned short port;
+ void *nip;
+
+ addr_len = sizeof(struct sockaddr_storage);
+ memset(&addr, 0, addr_len);
+
+ if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) {
+ if (addr.ss_family == AF_INET) {
+ addr4 = (struct sockaddr_in *)&addr;
+ nip = (void *)&addr4->sin_addr;
+ port = ntohs(addr4->sin_port);
+ } else if (addr.ss_family == AF_INET6) {
+ addr6 = (struct sockaddr_in6 *)&addr;
+ nip = (void *)&addr6->sin6_addr;
+ port = ntohs(addr6->sin6_port);
+ } else {
+ return;
+ }
+ const char *addr_str =
+ inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF);
+ printf(fmt, addr_str ? addr_str : "??", port);
+ }
+}
+
+static void print_local_ip_port(int sockfd, const char *fmt)
+{
+ print_ip_port(sockfd, getsockname, fmt);
+}
+
+static int start_server(int type, const struct sockaddr_storage *addr,
+ socklen_t addr_len)
+{
+
+ int fd;
+
+ fd = socket(addr->ss_family, type, 0);
+ if (fd == -1) {
+ log_err("Failed to create server socket");
+ goto out;
+ }
+
+ if (bind(fd, (const struct sockaddr *)addr, addr_len) == -1) {
+ log_err("Failed to bind server socket");
+ goto close_out;
+ }
+
+ if (type == SOCK_STREAM) {
+ if (listen(fd, 128) == -1) {
+ log_err("Failed to listen on server socket");
+ goto close_out;
+ }
+ }
+
+ print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n");
+
+ goto out;
+close_out:
+ close(fd);
+ fd = -1;
+out:
+ return fd;
+}
+
+static void print_test_case_num(int domain, int type)
+{
+ static int test_num;
+
+ printf("Test case #%d (%s/%s):\n", ++test_num,
+ (domain == AF_INET ? "IPv4" :
+ domain == AF_INET6 ? "IPv6" :
+ "unknown_domain"),
+ (type == SOCK_STREAM ? "TCP" :
+ type == SOCK_DGRAM ? "UDP" :
+ "unknown_type"));
+}
+
+static int run_test_case(int domain, int type, const char *ip,
+ unsigned short port)
+{
+ struct sockaddr_storage addr;
+ socklen_t addr_len = sizeof(addr);
+ int servfd = -1;
+ int err = 0;
+
+ print_test_case_num(domain, type);
+
+ if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr,
+ addr_len) == -1)
+ return -1;
+
+ printf("\tRequested: bind(%s, %d) ..\n", ip, port);
+ servfd = start_server(type, &addr, addr_len);
+ if (servfd == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(servfd);
+ return err;
+}
+
+static void close_progs_fds(struct program *progs, size_t prog_cnt)
+{
+ size_t i;
+
+ for (i = 0; i < prog_cnt; ++i) {
+ close(progs[i].fd);
+ progs[i].fd = -1;
+ }
+}
+
+static int load_and_attach_progs(int cgfd, struct program *progs,
+ size_t prog_cnt)
+{
+ size_t i;
+
+ for (i = 0; i < prog_cnt; ++i) {
+ progs[i].fd = progs[i].loadfn();
+ if (progs[i].fd == -1) {
+ log_err("Failed to load program %s", progs[i].name);
+ goto err;
+ }
+ if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type,
+ BPF_F_ALLOW_OVERRIDE) == -1) {
+ log_err("Failed to attach program %s", progs[i].name);
+ goto err;
+ }
+ printf("Attached %s program.\n", progs[i].name);
+ }
+
+ return 0;
+err:
+ close_progs_fds(progs, prog_cnt);
+ return -1;
+}
+
+static int run_domain_test(int domain, int cgfd, struct program *progs,
+ size_t prog_cnt, const char *ip, unsigned short port)
+{
+ int err = 0;
+
+ if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1)
+ goto err;
+
+ if (run_test_case(domain, SOCK_STREAM, ip, port) == -1)
+ goto err;
+
+ if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close_progs_fds(progs, prog_cnt);
+ return err;
+}
+
+static int run_test(void)
+{
+ size_t inet6_prog_cnt;
+ size_t inet_prog_cnt;
+ int cgfd = -1;
+ int err = 0;
+
+ struct program inet6_progs[] = {
+ {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6"},
+ };
+ inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program);
+
+ struct program inet_progs[] = {
+ {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4"},
+ };
+ inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program);
+
+ if (setup_cgroup_environment())
+ goto err;
+
+ cgfd = create_and_get_cgroup(CG_PATH);
+ if (!cgfd)
+ goto err;
+
+ if (join_cgroup(CG_PATH))
+ goto err;
+
+ if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP,
+ SERV4_PORT) == -1)
+ goto err;
+
+ if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt,
+ SERV6_IP, SERV6_PORT) == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(cgfd);
+ cleanup_cgroup_environment();
+ printf(err ? "### FAIL\n" : "### SUCCESS\n");
+ return err;
+}
+
+int main(int argc, char **argv)
+{
+ return run_test();
+}
--
2.9.5
