aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/filter.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/filter.c')
-rw-r--r--net/core/filter.c350
1 files changed, 299 insertions, 51 deletions
diff --git a/net/core/filter.c b/net/core/filter.c
index 647c63a7b25b..22eb2edf5573 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2963,42 +2963,113 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
}
}
-static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+
+#define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \
+ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
+ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
+ BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+
+static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
+ u64 flags)
{
- u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
+ bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
+ u16 mac_len = 0, inner_net = 0, inner_trans = 0;
+ unsigned int gso_type = SKB_GSO_DODGY;
int ret;
- if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
- return -ENOTSUPP;
+ if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
+ /* udp gso_size delineates datagrams, only allow if fixed */
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ||
+ !(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+ return -ENOTSUPP;
+ }
- ret = skb_cow(skb, len_diff);
+ ret = skb_cow_head(skb, len_diff);
if (unlikely(ret < 0))
return ret;
+ if (encap) {
+ if (skb->protocol != htons(ETH_P_IP) &&
+ skb->protocol != htons(ETH_P_IPV6))
+ return -ENOTSUPP;
+
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 &&
+ flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+ return -EINVAL;
+
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE &&
+ flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+ return -EINVAL;
+
+ if (skb->encapsulation)
+ return -EALREADY;
+
+ mac_len = skb->network_header - skb->mac_header;
+ inner_net = skb->network_header;
+ inner_trans = skb->transport_header;
+ }
+
ret = bpf_skb_net_hdr_push(skb, off, len_diff);
if (unlikely(ret < 0))
return ret;
+ if (encap) {
+ /* inner mac == inner_net on l3 encap */
+ skb->inner_mac_header = inner_net;
+ skb->inner_network_header = inner_net;
+ skb->inner_transport_header = inner_trans;
+ skb_set_inner_protocol(skb, skb->protocol);
+
+ skb->encapsulation = 1;
+ skb_set_network_header(skb, mac_len);
+
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+ gso_type |= SKB_GSO_UDP_TUNNEL;
+ else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE)
+ gso_type |= SKB_GSO_GRE;
+ else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+ gso_type |= SKB_GSO_IPXIP6;
+ else
+ gso_type |= SKB_GSO_IPXIP4;
+
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
+ flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) {
+ int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ?
+ sizeof(struct ipv6hdr) :
+ sizeof(struct iphdr);
+
+ skb_set_transport_header(skb, mac_len + nh_len);
+ }
+ }
+
if (skb_is_gso(skb)) {
struct skb_shared_info *shinfo = skb_shinfo(skb);
/* Due to header grow, MSS needs to be downgraded. */
- skb_decrease_gso_size(shinfo, len_diff);
+ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+ skb_decrease_gso_size(shinfo, len_diff);
+
/* Header must be checked, and gso_segs recomputed. */
- shinfo->gso_type |= SKB_GSO_DODGY;
+ shinfo->gso_type |= gso_type;
shinfo->gso_segs = 0;
}
return 0;
}
-static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
+static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
+ u64 flags)
{
- u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
int ret;
- if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
- return -ENOTSUPP;
+ if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
+ /* udp gso_size delineates datagrams, only allow if fixed */
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ||
+ !(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+ return -ENOTSUPP;
+ }
ret = skb_unclone(skb, GFP_ATOMIC);
if (unlikely(ret < 0))
@@ -3012,7 +3083,9 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
struct skb_shared_info *shinfo = skb_shinfo(skb);
/* Due to header shrink, MSS can be upgraded. */
- skb_increase_gso_size(shinfo, len_diff);
+ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+ skb_increase_gso_size(shinfo, len_diff);
+
/* Header must be checked, and gso_segs recomputed. */
shinfo->gso_type |= SKB_GSO_DODGY;
shinfo->gso_segs = 0;
@@ -3027,49 +3100,50 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
SKB_MAX_ALLOC;
}
-static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
+BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
+ u32, mode, u64, flags)
{
- bool trans_same = skb->transport_header == skb->network_header;
u32 len_cur, len_diff_abs = abs(len_diff);
u32 len_min = bpf_skb_net_base_len(skb);
u32 len_max = __bpf_skb_max_len(skb);
__be16 proto = skb->protocol;
bool shrink = len_diff < 0;
+ u32 off;
int ret;
+ if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK))
+ return -EINVAL;
if (unlikely(len_diff_abs > 0xfffU))
return -EFAULT;
if (unlikely(proto != htons(ETH_P_IP) &&
proto != htons(ETH_P_IPV6)))
return -ENOTSUPP;
+ off = skb_mac_header_len(skb);
+ switch (mode) {
+ case BPF_ADJ_ROOM_NET:
+ off += bpf_skb_net_base_len(skb);
+ break;
+ case BPF_ADJ_ROOM_MAC:
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+
len_cur = skb->len - skb_network_offset(skb);
- if (skb_transport_header_was_set(skb) && !trans_same)
- len_cur = skb_network_header_len(skb);
if ((shrink && (len_diff_abs >= len_cur ||
len_cur - len_diff_abs < len_min)) ||
(!shrink && (skb->len + len_diff_abs > len_max &&
!skb_is_gso(skb))))
return -ENOTSUPP;
- ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) :
- bpf_skb_net_grow(skb, len_diff_abs);
+ ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) :
+ bpf_skb_net_grow(skb, off, len_diff_abs, flags);
bpf_compute_data_pointers(skb);
return ret;
}
-BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
- u32, mode, u64, flags)
-{
- if (unlikely(flags))
- return -EINVAL;
- if (likely(mode == BPF_ADJ_ROOM_NET))
- return bpf_skb_adjust_net(skb, len_diff);
-
- return -ENOTSUPP;
-}
-
static const struct bpf_func_proto bpf_skb_adjust_room_proto = {
.func = bpf_skb_adjust_room,
.gpl_only = false,
@@ -5156,15 +5230,15 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
return sk;
}
-/* bpf_sk_lookup performs the core lookup for different types of sockets,
+/* bpf_skc_lookup performs the core lookup for different types of sockets,
* taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
* Returns the socket as an 'unsigned long' to simplify the casting in the
* callers to satisfy BPF_CALL declarations.
*/
-static unsigned long
-__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
- struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
- u64 flags)
+static struct sock *
+__bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+ u64 flags)
{
struct sock *sk = NULL;
u8 family = AF_UNSPEC;
@@ -5192,15 +5266,27 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
put_net(net);
}
+out:
+ return sk;
+}
+
+static struct sock *
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+ u64 flags)
+{
+ struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
+ ifindex, proto, netns_id, flags);
+
if (sk)
sk = sk_to_full_sk(sk);
-out:
- return (unsigned long) sk;
+
+ return sk;
}
-static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
- u8 proto, u64 netns_id, u64 flags)
+static struct sock *
+bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ u8 proto, u64 netns_id, u64 flags)
{
struct net *caller_net;
int ifindex;
@@ -5213,14 +5299,47 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
ifindex = 0;
}
- return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
- proto, netns_id, flags);
+ return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
+ netns_id, flags);
+}
+
+static struct sock *
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ u8 proto, u64 netns_id, u64 flags)
+{
+ struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id,
+ flags);
+
+ if (sk)
+ sk = sk_to_full_sk(sk);
+
+ return sk;
+}
+
+BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP,
+ netns_id, flags);
}
+static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = {
+ .func = bpf_skc_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
- return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+ return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP,
+ netns_id, flags);
}
static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
@@ -5238,7 +5357,8 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
- return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+ return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP,
+ netns_id, flags);
}
static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
@@ -5273,8 +5393,9 @@ BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
struct net *caller_net = dev_net(ctx->rxq->dev);
int ifindex = ctx->rxq->dev->ifindex;
- return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
- IPPROTO_UDP, netns_id, flags);
+ return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+ ifindex, IPPROTO_UDP, netns_id,
+ flags);
}
static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -5289,14 +5410,38 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
.arg5_type = ARG_ANYTHING,
};
+BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+ struct net *caller_net = dev_net(ctx->rxq->dev);
+ int ifindex = ctx->rxq->dev->ifindex;
+
+ return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
+ ifindex, IPPROTO_TCP, netns_id,
+ flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
+ .func = bpf_xdp_skc_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
{
struct net *caller_net = dev_net(ctx->rxq->dev);
int ifindex = ctx->rxq->dev->ifindex;
- return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
- IPPROTO_TCP, netns_id, flags);
+ return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+ ifindex, IPPROTO_TCP, netns_id,
+ flags);
}
static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -5311,11 +5456,31 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
.arg5_type = ARG_ANYTHING,
};
+BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
+ sock_net(ctx->sk), 0,
+ IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
+ .func = bpf_sock_addr_skc_lookup_tcp,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
- return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
- IPPROTO_TCP, netns_id, flags);
+ return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+ sock_net(ctx->sk), 0, IPPROTO_TCP,
+ netns_id, flags);
}
static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -5332,8 +5497,9 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
- return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
- IPPROTO_UDP, netns_id, flags);
+ return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+ sock_net(ctx->sk), 0, IPPROTO_UDP,
+ netns_id, flags);
}
static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
@@ -5461,6 +5627,74 @@ static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
};
+
+BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
+ struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+ u32 cookie;
+ int ret;
+
+ if (unlikely(th_len < sizeof(*th)))
+ return -EINVAL;
+
+ /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
+ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+ return -EINVAL;
+
+ if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+ return -EINVAL;
+
+ if (!th->ack || th->rst || th->syn)
+ return -ENOENT;
+
+ if (tcp_synq_no_recent_overflow(sk))
+ return -ENOENT;
+
+ cookie = ntohl(th->ack_seq) - 1;
+
+ switch (sk->sk_family) {
+ case AF_INET:
+ if (unlikely(iph_len < sizeof(struct iphdr)))
+ return -EINVAL;
+
+ ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+ break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+ case AF_INET6:
+ if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+ return -EINVAL;
+
+ ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+ break;
+#endif /* CONFIG_IPV6 */
+
+ default:
+ return -EPROTONOSUPPORT;
+ }
+
+ if (ret > 0)
+ return 0;
+
+ return -ENOENT;
+#else
+ return -ENOTSUPP;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
+ .func = bpf_tcp_check_syncookie,
+ .gpl_only = true,
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_SOCK_COMMON,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE,
+};
+
#endif /* CONFIG_INET */
bool bpf_helper_changes_pkt_data(void *func)
@@ -5586,6 +5820,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sock_addr_sk_lookup_udp_proto;
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
+ case BPF_FUNC_skc_lookup_tcp:
+ return &bpf_sock_addr_skc_lookup_tcp_proto;
#endif /* CONFIG_INET */
default:
return bpf_base_func_proto(func_id);
@@ -5719,6 +5955,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_tcp_sock_proto;
case BPF_FUNC_get_listener_sock:
return &bpf_get_listener_sock_proto;
+ case BPF_FUNC_skc_lookup_tcp:
+ return &bpf_skc_lookup_tcp_proto;
+ case BPF_FUNC_tcp_check_syncookie:
+ return &bpf_tcp_check_syncookie_proto;
+ case BPF_FUNC_skb_ecn_set_ce:
+ return &bpf_skb_ecn_set_ce_proto;
#endif
default:
return bpf_base_func_proto(func_id);
@@ -5754,6 +5996,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_sk_lookup_tcp_proto;
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
+ case BPF_FUNC_skc_lookup_tcp:
+ return &bpf_xdp_skc_lookup_tcp_proto;
+ case BPF_FUNC_tcp_check_syncookie:
+ return &bpf_tcp_check_syncookie_proto;
#endif
default:
return bpf_base_func_proto(func_id);
@@ -5846,6 +6092,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_lookup_udp_proto;
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
+ case BPF_FUNC_skc_lookup_tcp:
+ return &bpf_skc_lookup_tcp_proto;
#endif
default:
return bpf_base_func_proto(func_id);