Commit d2775984 authored by Jakub Kicinski's avatar Jakub Kicinski

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2020-10-22

1) Fix enforcing NULL check in verifier for new helper return types of
   RET_PTR_TO_{BTF_ID,MEM_OR_BTF_ID}_OR_NULL, from Martin KaFai Lau.

2) Fix bpf_redirect_neigh() helper API before it becomes frozen by adding
   nexthop information as argument, from Toke Høiland-Jørgensen.

3) Guard & fix compilation of bpf_tail_call_static() when __bpf__ arch is
   not defined by compiler or clang too old, from Daniel Borkmann.

4) Remove misplaced break after return in attach_type_to_prog_type(), from
   Tom Rix.
====================
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents d9b0e599 3652c9a1
......@@ -3244,7 +3244,8 @@ R: KP Singh <kpsingh@chromium.org>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Supported
Q: https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
W: https://bpf.io/
Q: https://patchwork.kernel.org/project/netdevbpf/list/?delegate=121173
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
F: Documentation/bpf/
......
......@@ -607,12 +607,21 @@ struct bpf_skb_data_end {
void *data_end;
};
struct bpf_nh_params {
u32 nh_family;
union {
u32 ipv4_nh;
struct in6_addr ipv6_nh;
};
};
struct bpf_redirect_info {
u32 flags;
u32 tgt_index;
void *tgt_value;
struct bpf_map *map;
u32 kern_flags;
struct bpf_nh_params nh;
};
DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
......
......@@ -3677,15 +3677,19 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
* long bpf_redirect_neigh(u32 ifindex, u64 flags)
* long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
* Description
* Redirect the packet to another net device of index *ifindex*
* and fill in L2 addresses from neighboring subsystem. This helper
* is somewhat similar to **bpf_redirect**\ (), except that it
* populates L2 addresses as well, meaning, internally, the helper
* performs a FIB lookup based on the skb's networking header to
* get the address of the next hop and then relies on the neighbor
* lookup for the L2 address of the nexthop.
* relies on the neighbor lookup for the L2 address of the nexthop.
*
* The helper will perform a FIB lookup based on the skb's
* networking header to get the address of the next hop, unless
* this is supplied by the caller in the *params* argument. The
* *plen* argument indicates the len of *params* and should be set
* to 0 if *params* is NULL.
*
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types, and enabled
......@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
__u8 dmac[6]; /* ETH_ALEN */
};
struct bpf_redir_neigh {
/* network family for lookup (AF_INET, AF_INET6) */
__u32 nh_family;
/* network address of nexthop; skips fib lookup to find gateway */
union {
__be32 ipv4_nh;
__u32 ipv6_nh[4]; /* in6_addr; network order */
};
};
enum bpf_task_fd_type {
BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
BPF_FD_TYPE_TRACEPOINT, /* tp name */
......
......@@ -2913,7 +2913,6 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
return BPF_PROG_TYPE_CGROUP_SKB;
break;
case BPF_CGROUP_INET_SOCK_CREATE:
case BPF_CGROUP_INET_SOCK_RELEASE:
case BPF_CGROUP_INET4_POST_BIND:
......
......@@ -5133,24 +5133,19 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].id = ++env->id_gen;
} else {
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
}
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
regs[BPF_REG_0].mem_size = meta.mem_size;
} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
......@@ -5199,6 +5194,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
if (reg_type_may_be_null(regs[BPF_REG_0].type))
regs[BPF_REG_0].id = ++env->id_gen;
if (is_ptr_cast_function(func_id)) {
/* For release_reference() */
regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
......@@ -7212,7 +7210,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
struct bpf_reg_state *reg, u32 id,
bool is_null)
{
if (reg_type_may_be_null(reg->type) && reg->id == id) {
if (reg_type_may_be_null(reg->type) && reg->id == id &&
!WARN_ON_ONCE(!reg->id)) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
* arithmetic on pointers that might be NULL.
......
......@@ -2165,12 +2165,12 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
}
#if IS_ENABLED(CONFIG_IPV6)
static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
struct net_device *dev, struct bpf_nh_params *nh)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
u32 hh_len = LL_RESERVED_SPACE(dev);
const struct in6_addr *nexthop;
struct dst_entry *dst = NULL;
struct neighbour *neigh;
if (dev_xmit_recursion()) {
......@@ -2196,8 +2196,13 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
}
rcu_read_lock_bh();
if (!nh) {
dst = skb_dst(skb);
nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
&ipv6_hdr(skb)->daddr);
} else {
nexthop = &nh->ipv6_nh;
}
neigh = ip_neigh_gw6(dev, nexthop);
if (likely(!IS_ERR(neigh))) {
int ret;
......@@ -2210,6 +2215,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
return ret;
}
rcu_read_unlock_bh();
if (dst)
IP6_INC_STATS(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
out_drop:
......@@ -2217,11 +2223,14 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
return -ENETDOWN;
}
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct net *net = dev_net(dev);
int err, ret = NET_XMIT_DROP;
if (!nh) {
struct dst_entry *dst;
struct flowi6 fl6 = {
.flowi6_flags = FLOWI_FLAG_ANYSRC,
......@@ -2238,8 +2247,11 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
goto out_drop;
skb_dst_set(skb, dst);
} else if (nh->nh_family != AF_INET6) {
goto out_drop;
}
err = bpf_out_neigh_v6(net, skb);
err = bpf_out_neigh_v6(net, skb, dev, nh);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
else
......@@ -2252,7 +2264,8 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
return ret;
}
#else
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
kfree_skb(skb);
return NET_XMIT_DROP;
......@@ -2260,11 +2273,9 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
#endif /* CONFIG_IPV6 */
#if IS_ENABLED(CONFIG_INET)
static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
struct net_device *dev, struct bpf_nh_params *nh)
{
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
u32 hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
bool is_v6gw = false;
......@@ -2292,7 +2303,21 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
}
rcu_read_lock_bh();
if (!nh) {
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = container_of(dst, struct rtable, dst);
neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
} else if (nh->nh_family == AF_INET6) {
neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
is_v6gw = true;
} else if (nh->nh_family == AF_INET) {
neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
} else {
rcu_read_unlock_bh();
goto out_drop;
}
if (likely(!IS_ERR(neigh))) {
int ret;
......@@ -2309,12 +2334,14 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
return -ENETDOWN;
}
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
const struct iphdr *ip4h = ip_hdr(skb);
struct net *net = dev_net(dev);
int err, ret = NET_XMIT_DROP;
struct rtable *rt;
if (!nh) {
struct flowi4 fl4 = {
.flowi4_flags = FLOWI_FLAG_ANYSRC,
.flowi4_mark = skb->mark,
......@@ -2324,6 +2351,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
struct rtable *rt;
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
......@@ -2334,8 +2362,9 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
}
skb_dst_set(skb, &rt->dst);
}
err = bpf_out_neigh_v4(net, skb);
err = bpf_out_neigh_v4(net, skb, dev, nh);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
else
......@@ -2348,14 +2377,16 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
return ret;
}
#else
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
kfree_skb(skb);
return NET_XMIT_DROP;
}
#endif /* CONFIG_INET */
static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
struct ethhdr *ethh = eth_hdr(skb);
......@@ -2370,9 +2401,9 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
skb_reset_network_header(skb);
if (skb->protocol == htons(ETH_P_IP))
return __bpf_redirect_neigh_v4(skb, dev);
return __bpf_redirect_neigh_v4(skb, dev, nh);
else if (skb->protocol == htons(ETH_P_IPV6))
return __bpf_redirect_neigh_v6(skb, dev);
return __bpf_redirect_neigh_v6(skb, dev, nh);
out:
kfree_skb(skb);
return -ENOTSUPP;
......@@ -2382,7 +2413,8 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
enum {
BPF_F_NEIGH = (1ULL << 1),
BPF_F_PEER = (1ULL << 2),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER)
BPF_F_NEXTHOP = (1ULL << 3),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
};
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
......@@ -2455,7 +2487,8 @@ int skb_do_redirect(struct sk_buff *skb)
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
__bpf_redirect_neigh(skb, dev) :
__bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
&ri->nh : NULL) :
__bpf_redirect(skb, dev, flags);
out_drop:
kfree_skb(skb);
......@@ -2504,16 +2537,21 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = {
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
int, plen, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
if (unlikely(flags))
if (unlikely((plen && plen < sizeof(*params)) || flags))
return TC_ACT_SHOT;
ri->flags = BPF_F_NEIGH;
ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
ri->tgt_index = ifindex;
BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
if (plen)
memcpy(&ri->nh, params, sizeof(ri->nh));
return TC_ACT_REDIRECT;
}
......@@ -2522,7 +2560,9 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
.arg2_type = ARG_ANYTHING,
.arg2_type = ARG_PTR_TO_MEM_OR_NULL,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
......
......@@ -44,17 +44,17 @@ static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
switch (proto) {
case ETH_P_8021Q:
case ETH_P_8021AD:
bpf_tail_call_static(skb, &jmp_table, PARSE_VLAN);
bpf_tail_call(skb, &jmp_table, PARSE_VLAN);
break;
case ETH_P_MPLS_UC:
case ETH_P_MPLS_MC:
bpf_tail_call_static(skb, &jmp_table, PARSE_MPLS);
bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
break;
case ETH_P_IP:
bpf_tail_call_static(skb, &jmp_table, PARSE_IP);
bpf_tail_call(skb, &jmp_table, PARSE_IP);
break;
case ETH_P_IPV6:
bpf_tail_call_static(skb, &jmp_table, PARSE_IPV6);
bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
break;
}
}
......
......@@ -453,6 +453,7 @@ class PrinterHelpers(Printer):
'struct bpf_perf_event_data',
'struct bpf_perf_event_value',
'struct bpf_pidns_info',
'struct bpf_redir_neigh',
'struct bpf_sk_lookup',
'struct bpf_sock',
'struct bpf_sock_addr',
......
......@@ -3677,15 +3677,19 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
* long bpf_redirect_neigh(u32 ifindex, u64 flags)
* long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
* Description
* Redirect the packet to another net device of index *ifindex*
* and fill in L2 addresses from neighboring subsystem. This helper
* is somewhat similar to **bpf_redirect**\ (), except that it
* populates L2 addresses as well, meaning, internally, the helper
* performs a FIB lookup based on the skb's networking header to
* get the address of the next hop and then relies on the neighbor
* lookup for the L2 address of the nexthop.
* relies on the neighbor lookup for the L2 address of the nexthop.
*
* The helper will perform a FIB lookup based on the skb's
* networking header to get the address of the next hop, unless
* this is supplied by the caller in the *params* argument. The
* *plen* argument indicates the len of *params* and should be set
* to 0 if *params* is NULL.
*
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types, and enabled
......@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
__u8 dmac[6]; /* ETH_ALEN */
};
struct bpf_redir_neigh {
/* network family for lookup (AF_INET, AF_INET6) */
__u32 nh_family;
/* network address of nexthop; skips fib lookup to find gateway */
union {
__be32 ipv4_nh;
__u32 ipv6_nh[4]; /* in6_addr; network order */
};
};
enum bpf_task_fd_type {
BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
BPF_FD_TYPE_TRACEPOINT, /* tp name */
......
......@@ -72,6 +72,7 @@
/*
* Helper function to perform a tail call with a constant/immediate map slot.
*/
#if __clang_major__ >= 8 && defined(__bpf__)
static __always_inline void
bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
{
......@@ -98,6 +99,7 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
:: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
: "r0", "r1", "r2", "r3", "r4", "r5");
}
#endif
/*
* Helper structure used by eBPF C program
......
......@@ -5,18 +5,17 @@
#include <bpf/libbpf.h>
#include <bpf/btf.h>
#include "test_ksyms_btf.skel.h"
#include "test_ksyms_btf_null_check.skel.h"
static int duration;
void test_ksyms_btf(void)
static void test_basic(void)
{
__u64 runqueues_addr, bpf_prog_active_addr;
__u32 this_rq_cpu;
int this_bpf_prog_active;
struct test_ksyms_btf *skel = NULL;
struct test_ksyms_btf__data *data;
struct btf *btf;
int percpu_datasec;
int err;
err = kallsyms_find("runqueues", &runqueues_addr);
......@@ -31,20 +30,6 @@ void test_ksyms_btf(void)
if (CHECK(err == -ENOENT, "ksym_find", "symbol 'bpf_prog_active' not found\n"))
return;
btf = libbpf_find_kernel_btf();
if (CHECK(IS_ERR(btf), "btf_exists", "failed to load kernel BTF: %ld\n",
PTR_ERR(btf)))
return;
percpu_datasec = btf__find_by_name_kind(btf, ".data..percpu",
BTF_KIND_DATASEC);
if (percpu_datasec < 0) {
printf("%s:SKIP:no PERCPU DATASEC in kernel btf\n",
__func__);
test__skip();
goto cleanup;
}
skel = test_ksyms_btf__open_and_load();
if (CHECK(!skel, "skel_open", "failed to open and load skeleton\n"))
goto cleanup;
......@@ -83,6 +68,42 @@ void test_ksyms_btf(void)
data->out__bpf_prog_active);
cleanup:
btf__free(btf);
test_ksyms_btf__destroy(skel);
}
static void test_null_check(void)
{
struct test_ksyms_btf_null_check *skel;
skel = test_ksyms_btf_null_check__open_and_load();
CHECK(skel, "skel_open", "unexpected load of a prog missing null check\n");
test_ksyms_btf_null_check__destroy(skel);
}
void test_ksyms_btf(void)
{
int percpu_datasec;
struct btf *btf;
btf = libbpf_find_kernel_btf();
if (CHECK(IS_ERR(btf), "btf_exists", "failed to load kernel BTF: %ld\n",
PTR_ERR(btf)))
return;
percpu_datasec = btf__find_by_name_kind(btf, ".data..percpu",
BTF_KIND_DATASEC);
btf__free(btf);
if (percpu_datasec < 0) {
printf("%s:SKIP:no PERCPU DATASEC in kernel btf\n",
__func__);
test__skip();
return;
}
if (test__start_subtest("basic"))
test_basic();
if (test__start_subtest("null_check"))
test_null_check();
}
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2020 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
extern const struct rq runqueues __ksym; /* struct type global var. */
extern const int bpf_prog_active __ksym; /* int type global var. */
SEC("raw_tp/sys_enter")
int handler(const void *ctx)
{
struct rq *rq;
int *active;
__u32 cpu;
cpu = bpf_get_smp_processor_id();
rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, cpu);
active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
if (active) {
/* READ_ONCE */
*(volatile int *)active;
/* !rq has not been tested, so verifier should reject. */
*(volatile int *)(&rq->cpu);
}
return 0;
}
char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
#include <stddef.h>
#include <stdint.h>
#include <stdbool.h>
......@@ -118,7 +119,7 @@ SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
return TC_ACT_SHOT;
return bpf_redirect_neigh(get_dev_ifindex(dev_src), 0);
return bpf_redirect_neigh(get_dev_ifindex(dev_src), NULL, 0, 0);
}
SEC("src_ingress") int tc_src(struct __sk_buff *skb)
......@@ -142,7 +143,7 @@ SEC("src_ingress") int tc_src(struct __sk_buff *skb)
if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
return TC_ACT_SHOT;
return bpf_redirect_neigh(get_dev_ifindex(dev_dst), 0);
return bpf_redirect_neigh(get_dev_ifindex(dev_dst), NULL, 0, 0);
}
char __license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
#include <stdint.h>
#include <stdbool.h>
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/stddef.h>
#include <linux/pkt_cls.h>
#include <linux/if_ether.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#ifndef ctx_ptr
# define ctx_ptr(field) (void *)(long)(field)
#endif
#define AF_INET 2
#define AF_INET6 10
static __always_inline int fill_fib_params_v4(struct __sk_buff *skb,
struct bpf_fib_lookup *fib_params)
{
void *data_end = ctx_ptr(skb->data_end);
void *data = ctx_ptr(skb->data);
struct iphdr *ip4h;
if (data + sizeof(struct ethhdr) > data_end)
return -1;
ip4h = (struct iphdr *)(data + sizeof(struct ethhdr));
if ((void *)(ip4h + 1) > data_end)
return -1;
fib_params->family = AF_INET;
fib_params->tos = ip4h->tos;
fib_params->l4_protocol = ip4h->protocol;
fib_params->sport = 0;
fib_params->dport = 0;
fib_params->tot_len = bpf_ntohs(ip4h->tot_len);
fib_params->ipv4_src = ip4h->saddr;
fib_params->ipv4_dst = ip4h->daddr;
return 0;
}
static __always_inline int fill_fib_params_v6(struct __sk_buff *skb,
struct bpf_fib_lookup *fib_params)
{
struct in6_addr *src = (struct in6_addr *)fib_params->ipv6_src;
struct in6_addr *dst = (struct in6_addr *)fib_params->ipv6_dst;
void *data_end = ctx_ptr(skb->data_end);
void *data = ctx_ptr(skb->data);
struct ipv6hdr *ip6h;
if (data + sizeof(struct ethhdr) > data_end)
return -1;
ip6h = (struct ipv6hdr *)(data + sizeof(struct ethhdr));
if ((void *)(ip6h + 1) > data_end)
return -1;
fib_params->family = AF_INET6;
fib_params->flowinfo = 0;
fib_params->l4_protocol = ip6h->nexthdr;
fib_params->sport = 0;
fib_params->dport = 0;
fib_params->tot_len = bpf_ntohs(ip6h->payload_len);
*src = ip6h->saddr;
*dst = ip6h->daddr;
return 0;
}
SEC("chk_egress") int tc_chk(struct __sk_buff *skb)
{
void *data_end = ctx_ptr(skb->data_end);
void *data = ctx_ptr(skb->data);
__u32 *raw = data;
if (data + sizeof(struct ethhdr) > data_end)
return TC_ACT_SHOT;
return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK;
}
static __always_inline int tc_redir(struct __sk_buff *skb)
{
struct bpf_fib_lookup fib_params = { .ifindex = skb->ingress_ifindex };
__u8 zero[ETH_ALEN * 2];
int ret = -1;
switch (skb->protocol) {
case __bpf_constant_htons(ETH_P_IP):
ret = fill_fib_params_v4(skb, &fib_params);
break;
case __bpf_constant_htons(ETH_P_IPV6):
ret = fill_fib_params_v6(skb, &fib_params);
break;
}
if (ret)
return TC_ACT_OK;
ret = bpf_fib_lookup(skb, &fib_params, sizeof(fib_params), 0);
if (ret == BPF_FIB_LKUP_RET_NOT_FWDED || ret < 0)
return TC_ACT_OK;
__builtin_memset(&zero, 0, sizeof(zero));
if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
return TC_ACT_SHOT;
if (ret == BPF_FIB_LKUP_RET_NO_NEIGH) {
struct bpf_redir_neigh nh_params = {};
nh_params.nh_family = fib_params.family;
__builtin_memcpy(&nh_params.ipv6_nh, &fib_params.ipv6_dst,
sizeof(nh_params.ipv6_nh));
return bpf_redirect_neigh(fib_params.ifindex, &nh_params,
sizeof(nh_params), 0);
} else if (ret == BPF_FIB_LKUP_RET_SUCCESS) {
void *data_end = ctx_ptr(skb->data_end);
struct ethhdr *eth = ctx_ptr(skb->data);
if (eth + 1 > data_end)
return TC_ACT_SHOT;
__builtin_memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
__builtin_memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
return bpf_redirect(fib_params.ifindex, 0);
}
return TC_ACT_SHOT;
}
/* these are identical, but keep them separate for compatibility with the
* section names expected by test_tc_redirect.sh
*/
SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
{
return tc_redir(skb);
}
SEC("src_ingress") int tc_src(struct __sk_buff *skb)
{
return tc_redir(skb);
}
char __license[] SEC("license") = "GPL";
......@@ -24,8 +24,7 @@ command -v timeout >/dev/null 2>&1 || \
{ echo >&2 "timeout is not available"; exit 1; }
command -v ping >/dev/null 2>&1 || \
{ echo >&2 "ping is not available"; exit 1; }
command -v ping6 >/dev/null 2>&1 || \
{ echo >&2 "ping6 is not available"; exit 1; }
if command -v ping6 >/dev/null 2>&1; then PING6=ping6; else PING6=ping; fi
command -v perl >/dev/null 2>&1 || \
{ echo >&2 "perl is not available"; exit 1; }
command -v jq >/dev/null 2>&1 || \
......@@ -152,7 +151,7 @@ netns_test_connectivity()
echo -e "${TEST}: ${GREEN}PASS${NC}"
TEST="ICMPv6 connectivity test"
ip netns exec ${NS_SRC} ping6 $PING_ARG ${IP6_DST}
ip netns exec ${NS_SRC} $PING6 $PING_ARG ${IP6_DST}
if [ $? -ne 0 ]; then
echo -e "${TEST}: ${RED}FAIL${NC}"
exit 1
......@@ -170,6 +169,7 @@ hex_mem_str()
netns_setup_bpf()
{
local obj=$1
local use_forwarding=${2:-0}
ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact
ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj $obj sec src_ingress
......@@ -179,6 +179,14 @@ netns_setup_bpf()
ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj $obj sec dst_ingress
ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress bpf da obj $obj sec chk_egress
if [ "$use_forwarding" -eq "1" ]; then
# bpf_fib_lookup() checks if forwarding is enabled
ip netns exec ${NS_FWD} sysctl -w net.ipv4.ip_forward=1
ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_dst_fwd.forwarding=1
ip netns exec ${NS_FWD} sysctl -w net.ipv6.conf.veth_src_fwd.forwarding=1
return 0
fi
veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex)
veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex)
......@@ -200,5 +208,9 @@ netns_setup_bpf test_tc_neigh.o
netns_test_connectivity
netns_cleanup
netns_setup
netns_setup_bpf test_tc_neigh_fib.o 1
netns_test_connectivity
netns_cleanup
netns_setup
netns_setup_bpf test_tc_peer.o
netns_test_connectivity
......@@ -631,3 +631,28 @@
.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
.result = ACCEPT,
},
{
"mark null check on return value of bpf_skc_to helpers",
.insns = {
BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_request_sock),
BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid mem access",
.result_unpriv = REJECT,
.errstr_unpriv = "unknown func",
},
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment