From a5fa25adf03d4b063aece74ba70ccbb3a71af122 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:03:56 -0700 Subject: bpf: Change bpf_sk_release and bpf_sk_*cgroup_id to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON The previous patch allows the networking bpf prog to use the bpf_skc_to_*() helpers to get a PTR_TO_BTF_ID socket pointer, e.g. "struct tcp_sock *". It allows the bpf prog to read all the fields of the tcp_sock. This patch changes the bpf_sk_release() and bpf_sk_*cgroup_id() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. For example, the following will work: sk = bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); if (!sk) return; tp = bpf_skc_to_tcp_sock(sk); if (!tp) { bpf_sk_release(sk); return; } lsndtime = tp->lsndtime; /* Pass tp to bpf_sk_release() will also work */ bpf_sk_release(tp); Since PTR_TO_BTF_ID could be NULL, the helper taking ARG_PTR_TO_BTF_ID_SOCK_COMMON has to check for NULL at runtime. A btf_id of "struct sock" may not always mean a fullsock. Regardless the helper's running context may get a non-fullsock or not, considering fullsock check/handling is pretty cheap, it is better to keep the same verifier expectation on helper that takes ARG_PTR_TO_BTF_ID* will be able to handle the minisock situation. In the bpf_sk_*cgroup_id() case, it will try to get a fullsock by using sk_to_full_sk() as its skb variant bpf_sk"b"_*cgroup_id() has already been doing. bpf_sk_release can already handle minisock, so nothing special has to be done. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200925000356.3856047-1-kafai@fb.com --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a22812561064..c96a56d9c3be 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2512,7 +2512,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * long bpf_sk_release(struct bpf_sock *sock) + * long bpf_sk_release(void *sock) * Description * Release the reference held by *sock*. *sock* must be a * non-**NULL** pointer that was returned from @@ -3234,11 +3234,11 @@ union bpf_attr { * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. * - * u64 bpf_sk_cgroup_id(struct bpf_sock *sk) + * u64 bpf_sk_cgroup_id(void *sk) * Description * Return the cgroup v2 id of the socket *sk*. * - * *sk* must be a non-**NULL** pointer to a full socket, e.g. one + * *sk* must be a non-**NULL** pointer to a socket, e.g. one * returned from **bpf_sk_lookup_xxx**\ (), * **bpf_sk_fullsock**\ (), etc. The format of returned id is * same as in **bpf_skb_cgroup_id**\ (). @@ -3248,7 +3248,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level) + * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level) * Description * Return id of cgroup v2 that is ancestor of cgroup associated * with the *sk* at the *ancestor_level*. The root cgroup is at -- cgit v1.2.3 From 592a3498648af000e93dff2d36229ab11cd8c7f6 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:02 -0700 Subject: bpf: Change bpf_sk_storage_*() to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_sk_storage_*() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. A micro benchmark has been done on a "cgroup_skb/egress" bpf program which does a bpf_sk_storage_get(). It was driven by netperf doing a 4096 connected UDP_STREAM test with 64bytes packet. The stats from "kernel.bpf_stats_enabled" shows no meaningful difference. The sk_storage_get_btf_proto, sk_storage_delete_btf_proto, btf_sk_storage_get_proto, and btf_sk_storage_delete_proto are no longer needed, so they are removed. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20200925000402.3856307-1-kafai@fb.com --- include/net/bpf_sk_storage.h | 2 -- include/uapi/linux/bpf.h | 1 + kernel/bpf/bpf_lsm.c | 4 ++-- net/core/bpf_sk_storage.c | 29 ++++++----------------------- net/ipv4/bpf_tcp_ca.c | 23 ++--------------------- tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 12 insertions(+), 48 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 119f4c9c3a9c..3c516dd07caf 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -20,8 +20,6 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; -extern const struct bpf_func_proto sk_storage_get_btf_proto; -extern const struct bpf_func_proto sk_storage_delete_btf_proto; struct bpf_local_storage_elem; struct bpf_sk_storage_diag; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c96a56d9c3be..0ec6dbeb17a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2861,6 +2861,7 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). * * long bpf_send_signal(u32 sig) * Description diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 9cd1428c7199..78ea8a7bd27f 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -56,9 +56,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; case BPF_FUNC_sk_storage_get: - return &sk_storage_get_btf_proto; + return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: - return &sk_storage_delete_btf_proto; + return &bpf_sk_storage_delete_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 838efc682cff..c907f0dc7f87 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -269,7 +269,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, { struct bpf_local_storage_data *sdata; - if (flags > BPF_SK_STORAGE_GET_F_CREATE) + if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = sk_storage_lookup(sk, map, true); @@ -299,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { + if (!sk || !sk_fullsock(sk)) + return -EINVAL; + if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; @@ -355,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -375,27 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, -}; - -const struct bpf_func_proto sk_storage_get_btf_proto = { - .func = bpf_sk_storage_get, - .gpl_only = false, - .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, - .arg4_type = ARG_ANYTHING, -}; - -const struct bpf_func_proto sk_storage_delete_btf_proto = { - .func = bpf_sk_storage_delete, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; struct bpf_sk_storage_diag { diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 74a2ef598c31..618954f82764 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -28,22 +28,6 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; -static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly; -static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly; - -static void convert_sk_func_proto(struct bpf_func_proto *to, const struct bpf_func_proto *from) -{ - int i; - - *to = *from; - for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) { - if (to->arg_type[i] == ARG_PTR_TO_SOCKET) { - to->arg_type[i] = ARG_PTR_TO_BTF_ID; - to->arg_btf_id[i] = &tcp_sock_id; - } - } -} - static int bpf_tcp_ca_init(struct btf *btf) { s32 type_id; @@ -59,9 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); - convert_sk_func_proto(&btf_sk_storage_get_proto, &bpf_sk_storage_get_proto); - convert_sk_func_proto(&btf_sk_storage_delete_proto, &bpf_sk_storage_delete_proto); - return 0; } @@ -188,9 +169,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_tcp_send_ack: return &bpf_tcp_send_ack_proto; case BPF_FUNC_sk_storage_get: - return &btf_sk_storage_get_proto; + return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: - return &btf_sk_storage_delete_proto; + return &bpf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c96a56d9c3be..0ec6dbeb17a5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2861,6 +2861,7 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). * * long bpf_send_signal(u32 sig) * Description -- cgit v1.2.3 From c0df236e1394970f3503a8fb103de95d000014ca Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:09 -0700 Subject: bpf: Change bpf_tcp_*_syncookie to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_tcp_*_syncookie() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20200925000409.3856725-1-kafai@fb.com --- include/uapi/linux/bpf.h | 4 ++-- net/core/filter.c | 8 ++++---- tools/include/uapi/linux/bpf.h | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0ec6dbeb17a5..69b9e30375bc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2692,7 +2692,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Check whether *iph* and *th* contain a valid SYN cookie ACK for * the listening socket in *sk*. @@ -2878,7 +2878,7 @@ union bpf_attr { * * **-EAGAIN** if bpf program can try again. * - * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Try to issue a SYN cookie for the packet with corresponding * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. diff --git a/net/core/filter.c b/net/core/filter.c index 06d397eeef2a..1d88e9b498eb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6086,7 +6086,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len u32 cookie; int ret; - if (unlikely(th_len < sizeof(*th))) + if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ @@ -6139,7 +6139,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6153,7 +6153,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, u32 cookie; u16 mss; - if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) @@ -6208,7 +6208,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0ec6dbeb17a5..69b9e30375bc 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2692,7 +2692,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Check whether *iph* and *th* contain a valid SYN cookie ACK for * the listening socket in *sk*. @@ -2878,7 +2878,7 @@ union bpf_attr { * * **-EAGAIN** if bpf program can try again. * - * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Try to issue a SYN cookie for the packet with corresponding * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. -- cgit v1.2.3 From 27e5203bd9c5cc6d54dcac48c3027f3f04522b8b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Sep 2020 17:04:15 -0700 Subject: bpf: Change bpf_sk_assign to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON This patch changes the bpf_sk_assign() to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer returned by the bpf_skc_to_*() helpers also. The bpf_sk_lookup_assign() is taking ARG_PTR_TO_SOCKET_"OR_NULL". Meaning it specifically takes a literal NULL. ARG_PTR_TO_BTF_ID_SOCK_COMMON does not allow a literal NULL, so another ARG type is required for this purpose and another follow-up patch can be used if there is such need. Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200925000415.3857374-1-kafai@fb.com --- include/uapi/linux/bpf.h | 2 +- net/core/filter.c | 4 ++-- tools/include/uapi/linux/bpf.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 69b9e30375bc..2d6519a2ed77 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3107,7 +3107,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This * description applies to **BPF_PROG_TYPE_SCHED_CLS** and diff --git a/net/core/filter.c b/net/core/filter.c index 1d88e9b498eb..af88935e24b1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6217,7 +6217,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { - if (flags != 0) + if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; @@ -6241,7 +6241,7 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 69b9e30375bc..2d6519a2ed77 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3107,7 +3107,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This * description applies to **BPF_PROG_TYPE_SCHED_CLS** and -- cgit v1.2.3