From aa7b4e02b328f0589b6133e72aafb1289f614a79 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 9 Oct 2017 15:55:45 -0300 Subject: tools include uapi bpf.h: Sync kernel ABI header with tooling header Silences the checker: Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h' The 90caccdd8cc0 ("bpf: fix bpf_tail_call() x64 JIT") cset only updated a comment in uapi/bpf.h. Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: David Ahern Cc: David S. Miller Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-rwx2cqbf0x1lwa1krsr6e6hd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 43ab5c402f98..f90860d1f897 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) -- cgit v1.2.3 From 34f79502bbcfab659b8729da68b5e387f96eb4c1 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 18 Oct 2017 07:10:36 -0700 Subject: bpf: avoid preempt enable/disable in sockmap using tcp_skb_cb region SK_SKB BPF programs are run from the socket/tcp context but early in the stack before much of the TCP metadata is needed in tcp_skb_cb. So we can use some unused fields to place BPF metadata needed for SK_SKB programs when implementing the redirect function. This allows us to drop the preempt disable logic. It does however require an API change so sk_redirect_map() has been updated to additionally provide ctx_ptr to skb. Note, we do however continue to disable/enable preemption around actual BPF program running to account for map updates. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- include/net/tcp.h | 5 ++++ kernel/bpf/sockmap.c | 19 +++++++------- net/core/filter.c | 29 +++++++++++----------- samples/sockmap/sockmap_kern.c | 2 +- tools/include/uapi/linux/bpf.h | 3 ++- tools/testing/selftests/bpf/bpf_helpers.h | 2 +- tools/testing/selftests/bpf/sockmap_verdict_prog.c | 4 +-- 8 files changed, 36 insertions(+), 30 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d29e58fde364..818a0b26249e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -728,7 +728,7 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); -struct sock *do_sk_redirect_map(void); +struct sock *do_sk_redirect_map(struct sk_buff *skb); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/net/tcp.h b/include/net/tcp.h index 89974c5286d8..b1ef98ebce53 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -840,6 +840,11 @@ struct tcp_skb_cb { struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ + struct { + __u32 key; + __u32 flags; + struct bpf_map *map; + } bpf; }; }; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index c68899d5b246..beaabb21c3a3 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -39,6 +39,7 @@ #include #include #include +#include struct bpf_stab { struct bpf_map map; @@ -101,9 +102,16 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) return SK_DROP; skb_orphan(skb); + /* We need to ensure that BPF metadata for maps is also cleared + * when we orphan the skb so that we don't have the possibility + * to reference a stale map. + */ + TCP_SKB_CB(skb)->bpf.map = NULL; skb->sk = psock->sock; bpf_compute_data_end(skb); + preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); + preempt_enable(); skb->sk = NULL; return rc; @@ -114,17 +122,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) struct sock *sk; int rc; - /* Because we use per cpu values to feed input from sock redirect - * in BPF program to do_sk_redirect_map() call we need to ensure we - * are not preempted. RCU read lock is not sufficient in this case - * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. - */ - preempt_disable(); rc = smap_verdict_func(psock, skb); switch (rc) { case SK_REDIRECT: - sk = do_sk_redirect_map(); - preempt_enable(); + sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -141,8 +142,6 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) /* Fall through and free skb otherwise */ case SK_DROP: default: - if (rc != SK_REDIRECT) - preempt_enable(); kfree_skb(skb); } } diff --git a/net/core/filter.c b/net/core/filter.c index 74b8c91fb5f4..ca1ba0bbfbc2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1839,31 +1839,31 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags) +BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, + struct bpf_map *, map, u32, key, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); if (unlikely(flags)) return SK_ABORTED; - ri->ifindex = key; - ri->flags = flags; - ri->map = map; + tcb->bpf.key = key; + tcb->bpf.flags = flags; + tcb->bpf.map = map; return SK_REDIRECT; } -struct sock *do_sk_redirect_map(void) +struct sock *do_sk_redirect_map(struct sk_buff *skb) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk = NULL; - if (ri->map) { - sk = __sock_map_lookup_elem(ri->map, ri->ifindex); + if (tcb->bpf.map) { + sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key); - ri->ifindex = 0; - ri->map = NULL; - /* we do not clear flags for future lookup */ + tcb->bpf.key = 0; + tcb->bpf.map = NULL; } return sk; @@ -1873,9 +1873,10 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_ANYTHING, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c index f9b38ef82dc2..52b0053274f4 100644 --- a/samples/sockmap/sockmap_kern.c +++ b/samples/sockmap/sockmap_kern.c @@ -62,7 +62,7 @@ int bpf_prog2(struct __sk_buff *skb) ret = 1; bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret); - return bpf_sk_redirect_map(&sock_map, ret, 0); + return bpf_sk_redirect_map(skb, &sock_map, ret, 0); } SEC("sockops") diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 43ab5c402f98..be9a631a69f7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -569,9 +569,10 @@ union bpf_attr { * @flags: reserved for future use * Return: 0 on success or negative error code * - * int bpf_sk_redirect_map(map, key, flags) + * int bpf_sk_redirect_map(skb, map, key, flags) * Redirect skb to a sock in map using key as a lookup key for the * sock in map. + * @skb: pointer to skb * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 36fb9161b34a..b2e02bdcd098 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -65,7 +65,7 @@ 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) = +static int (*bpf_sk_redirect_map)(void *ctx, 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) = diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c index 9b99bd10807d..2cd2d552938b 100644 --- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c @@ -61,8 +61,8 @@ int bpf_prog2(struct __sk_buff *skb) bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk); if (!map) - return bpf_sk_redirect_map(&sock_map_rx, sk, 0); - return bpf_sk_redirect_map(&sock_map_tx, sk, 0); + return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0); + return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0); } char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From bfa640757e9378c2f26867e723f1287e94f5a7ad Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 27 Oct 2017 09:45:53 -0700 Subject: bpf: rename sk_actions to align with bpf infrastructure Recent additions to support multiple programs in cgroups impose a strict requirement, "all yes is yes, any no is no". To enforce this the infrastructure requires the 'no' return code, SK_DROP in this case, to be 0. To apply these rules to SK_SKB program types the sk_actions return codes need to be adjusted. This fix adds SK_PASS and makes 'SK_DROP = 0'. Finally, remove SK_ABORTED to remove any chance that the API may allow aborted program flows to be passed up the stack. This would be incorrect behavior and allow programs to break existing policies. Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 +++--- kernel/bpf/sockmap.c | 3 ++- net/core/filter.c | 5 +++-- tools/include/uapi/linux/bpf.h | 4 ++-- 4 files changed, 10 insertions(+), 8 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f90860d1f897..0d7948ce2128 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -575,7 +575,7 @@ union bpf_attr { * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -786,8 +786,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6778fb773934..66f00a2b27f4 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -122,7 +122,8 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) preempt_enable(); skb->sk = NULL; - return rc; + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) diff --git a/net/core/filter.c b/net/core/filter.c index 68eaa2f81a8e..6ae94f825f72 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1844,14 +1844,15 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + /* If user passes invalid input drop the packet. */ if (unlikely(flags)) - return SK_ABORTED; + return SK_DROP; tcb->bpf.key = key; tcb->bpf.flags = flags; tcb->bpf.map = map; - return SK_REDIRECT; + return SK_PASS; } struct sock *do_sk_redirect_map(struct sk_buff *skb) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 24b35a1fd4d6..c174971afbe6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -787,8 +787,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; -- cgit v1.2.3