With latest llvm17, selftest fexit_bpf2bpf/func_replace_return_code has the following verification failure: 0: R1=ctx(off=0,imm=0) R10=fp0 ; int connect_v4_prog(struct bpf_sock_addr *ctx) 0: (bf) r7 = r1 ; R1=ctx(off=0,imm=0) R7_w=ctx(off=0,imm=0) 1: (b4) w6 = 0 ; R6_w=0 ; memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr)); ... ; return do_bind(ctx) ? 1 : 0; 179: (bf) r1 = r7 ; R1=ctx(off=0,imm=0) R7=ctx(off=0,imm=0) 180: (85) call pc+147 Func#3 is global and valid. Skipping. 181: R0_w=scalar() 181: (bc) w6 = w0 ; R0_w=scalar() R6_w=scalar(umax=4294967295,var_off=(0x0; 0xffffffff)) 182: (05) goto pc-129 ; } 54: (bc) w0 = w6 ; R0_w=scalar(umax=4294967295,var_off=(0x0; 0xffffffff)) R6_w=scalar(umax=4294967295,var_off=(0x0; 0xffffffff)) 55: (95) exit At program exit the register R0 has value (0x0; 0xffffffff) should have been in (0x0; 0x1) processed 281 insns (limit 1000000) max_states_per_insn 1 total_states 26 peak_states 26 mark_read 13 -- END PROG LOAD LOG -- libbpf: prog 'connect_v4_prog': failed to load: -22 The corresponding source code: __attribute__ ((noinline)) int do_bind(struct bpf_sock_addr *ctx) { struct sockaddr_in sa = {}; sa.sin_family = AF_INET; sa.sin_port = bpf_htons(0); sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) return 0; return 1; } ... SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { ... return do_bind(ctx) ? 1 : 0; } Insn 180 is a call to 'do_bind'. The call's return value is also the return value for the program. Since do_bind() returns 0/1, so it is legitimate for compiler to optimize 'return do_bind(ctx) ? 1 : 0' to 'return do_bind(ctx)'. However, such optimization breaks verifier as the return value of 'do_bind()' is marked as any scalar which violates the requirement of prog return value 0/1. There are two ways to fix this problem, (1) changing 'return 1' in do_bind() to e.g. 'return 10' so the compiler has to do 'do_bind(ctx) ? 1 :0', or (2) suggested by Andrii, marking do_bind() with __weak attribute so the compiler cannot make any assumption on do_bind() return value. This patch adopted adding __weak approach which is simpler and more resistant to potential compiler optimizations. Suggested-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20230310012410.2920570-1-yhs@fb.com
200 lines
4.4 KiB
C
200 lines
4.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
// Copyright (c) 2018 Facebook
|
|
|
|
#include <string.h>
|
|
|
|
#include <linux/stddef.h>
|
|
#include <linux/bpf.h>
|
|
#include <linux/in.h>
|
|
#include <linux/in6.h>
|
|
#include <linux/tcp.h>
|
|
#include <linux/if.h>
|
|
#include <errno.h>
|
|
|
|
#include <bpf/bpf_helpers.h>
|
|
#include <bpf/bpf_endian.h>
|
|
|
|
#include "bpf_tcp_helpers.h"
|
|
|
|
#define SRC_REWRITE_IP4 0x7f000004U
|
|
#define DST_REWRITE_IP4 0x7f000001U
|
|
#define DST_REWRITE_PORT4 4444
|
|
|
|
#ifndef TCP_CA_NAME_MAX
|
|
#define TCP_CA_NAME_MAX 16
|
|
#endif
|
|
|
|
#ifndef TCP_NOTSENT_LOWAT
|
|
#define TCP_NOTSENT_LOWAT 25
|
|
#endif
|
|
|
|
#ifndef IFNAMSIZ
|
|
#define IFNAMSIZ 16
|
|
#endif
|
|
|
|
__attribute__ ((noinline)) __weak
|
|
int do_bind(struct bpf_sock_addr *ctx)
|
|
{
|
|
struct sockaddr_in sa = {};
|
|
|
|
sa.sin_family = AF_INET;
|
|
sa.sin_port = bpf_htons(0);
|
|
sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
|
|
|
|
if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static __inline int verify_cc(struct bpf_sock_addr *ctx,
|
|
char expected[TCP_CA_NAME_MAX])
|
|
{
|
|
char buf[TCP_CA_NAME_MAX];
|
|
int i;
|
|
|
|
if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
|
|
return 1;
|
|
|
|
for (i = 0; i < TCP_CA_NAME_MAX; i++) {
|
|
if (buf[i] != expected[i])
|
|
return 1;
|
|
if (buf[i] == 0)
|
|
break;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static __inline int set_cc(struct bpf_sock_addr *ctx)
|
|
{
|
|
char reno[TCP_CA_NAME_MAX] = "reno";
|
|
char cubic[TCP_CA_NAME_MAX] = "cubic";
|
|
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno)))
|
|
return 1;
|
|
if (verify_cc(ctx, reno))
|
|
return 1;
|
|
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
|
|
return 1;
|
|
if (verify_cc(ctx, cubic))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static __inline int bind_to_device(struct bpf_sock_addr *ctx)
|
|
{
|
|
char veth1[IFNAMSIZ] = "test_sock_addr1";
|
|
char veth2[IFNAMSIZ] = "test_sock_addr2";
|
|
char missing[IFNAMSIZ] = "nonexistent_dev";
|
|
char del_bind[IFNAMSIZ] = "";
|
|
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
|
|
&veth1, sizeof(veth1)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
|
|
&veth2, sizeof(veth2)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
|
|
&missing, sizeof(missing)) != -ENODEV)
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
|
|
&del_bind, sizeof(del_bind)))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static __inline int set_keepalive(struct bpf_sock_addr *ctx)
|
|
{
|
|
int zero = 0, one = 1;
|
|
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one)))
|
|
return 1;
|
|
if (ctx->type == SOCK_STREAM) {
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one)))
|
|
return 1;
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one)))
|
|
return 1;
|
|
}
|
|
if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero)))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static __inline int set_notsent_lowat(struct bpf_sock_addr *ctx)
|
|
{
|
|
int lowat = 65535;
|
|
|
|
if (ctx->type == SOCK_STREAM) {
|
|
if (bpf_setsockopt(ctx, SOL_TCP, TCP_NOTSENT_LOWAT, &lowat, sizeof(lowat)))
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
SEC("cgroup/connect4")
|
|
int connect_v4_prog(struct bpf_sock_addr *ctx)
|
|
{
|
|
struct bpf_sock_tuple tuple = {};
|
|
struct bpf_sock *sk;
|
|
|
|
/* Verify that new destination is available. */
|
|
memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr));
|
|
memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport));
|
|
|
|
tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
|
|
tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
|
|
|
|
/* Bind to device and unbind it. */
|
|
if (bind_to_device(ctx))
|
|
return 0;
|
|
|
|
if (set_keepalive(ctx))
|
|
return 0;
|
|
|
|
if (set_notsent_lowat(ctx))
|
|
return 0;
|
|
|
|
if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
|
|
return 0;
|
|
else if (ctx->type == SOCK_STREAM)
|
|
sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4),
|
|
BPF_F_CURRENT_NETNS, 0);
|
|
else
|
|
sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4),
|
|
BPF_F_CURRENT_NETNS, 0);
|
|
|
|
if (!sk)
|
|
return 0;
|
|
|
|
if (sk->src_ip4 != tuple.ipv4.daddr ||
|
|
sk->src_port != DST_REWRITE_PORT4) {
|
|
bpf_sk_release(sk);
|
|
return 0;
|
|
}
|
|
|
|
bpf_sk_release(sk);
|
|
|
|
/* Rewrite congestion control. */
|
|
if (ctx->type == SOCK_STREAM && set_cc(ctx))
|
|
return 0;
|
|
|
|
/* Rewrite destination. */
|
|
ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
|
|
ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
|
|
|
|
return do_bind(ctx) ? 1 : 0;
|
|
}
|
|
|
|
char _license[] SEC("license") = "GPL";
|