aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/net/inet6_hashtables.h56
-rw-r--r--include/net/inet_hashtables.h49
-rw-r--r--include/net/sock.h7
-rw-r--r--include/uapi/linux/bpf.h3
-rw-r--r--net/core/filter.c2
-rw-r--r--net/ipv4/udp.c8
-rw-r--r--net/ipv6/udp.c8
-rw-r--r--tools/include/uapi/linux/bpf.h3
8 files changed, 115 insertions, 21 deletions
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index a6722d6ef80f..284b5ce7205d 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -103,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net,
daddr, hnum, dif, sdif);
}
+static inline
+struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr, const __be16 sport,
+ const struct in6_addr *daddr, const __be16 dport,
+ bool *refcounted, inet6_ehashfn_t *ehashfn)
+{
+ struct sock *sk, *reuse_sk;
+ bool prefetched;
+
+ sk = skb_steal_sock(skb, refcounted, &prefetched);
+ if (!sk)
+ return NULL;
+
+ if (!prefetched)
+ return sk;
+
+ if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_state != TCP_LISTEN)
+ return sk;
+ } else if (sk->sk_protocol == IPPROTO_UDP) {
+ if (sk->sk_state != TCP_CLOSE)
+ return sk;
+ } else {
+ return sk;
+ }
+
+ reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, ntohs(dport),
+ ehashfn);
+ if (!reuse_sk)
+ return sk;
+
+ /* We've chosen a new reuseport sock which is never refcounted. This
+ * implies that sk also isn't refcounted.
+ */
+ WARN_ON_ONCE(*refcounted);
+
+ return reuse_sk;
+}
+
static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
const __be16 sport,
@@ -110,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
int iif, int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb, refcounted);
-
+ struct net *net = dev_net(skb_dst(skb)->dev);
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct sock *sk;
+
+ sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport,
+ refcounted, inet6_ehashfn);
+ if (IS_ERR(sk))
+ return NULL;
if (sk)
return sk;
- return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
- doff, &ipv6_hdr(skb)->saddr, sport,
- &ipv6_hdr(skb)->daddr, ntohs(dport),
+ return __inet6_lookup(net, hashinfo, skb,
+ doff, &ip6h->saddr, sport,
+ &ip6h->daddr, ntohs(dport),
iif, sdif, refcounted);
}
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index c0532cc7587f..1177effabed3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -449,6 +449,46 @@ static inline struct sock *inet_lookup(struct net *net,
return sk;
}
+static inline
+struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
+ const __be32 saddr, const __be16 sport,
+ const __be32 daddr, const __be16 dport,
+ bool *refcounted, inet_ehashfn_t *ehashfn)
+{
+ struct sock *sk, *reuse_sk;
+ bool prefetched;
+
+ sk = skb_steal_sock(skb, refcounted, &prefetched);
+ if (!sk)
+ return NULL;
+
+ if (!prefetched)
+ return sk;
+
+ if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_state != TCP_LISTEN)
+ return sk;
+ } else if (sk->sk_protocol == IPPROTO_UDP) {
+ if (sk->sk_state != TCP_CLOSE)
+ return sk;
+ } else {
+ return sk;
+ }
+
+ reuse_sk = inet_lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, ntohs(dport),
+ ehashfn);
+ if (!reuse_sk)
+ return sk;
+
+ /* We've chosen a new reuseport sock which is never refcounted. This
+ * implies that sk also isn't refcounted.
+ */
+ WARN_ON_ONCE(*refcounted);
+
+ return reuse_sk;
+}
+
static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb,
int doff,
@@ -457,13 +497,18 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
const int sdif,
bool *refcounted)
{
- struct sock *sk = skb_steal_sock(skb, refcounted);
+ struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
+ struct sock *sk;
+ sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport,
+ refcounted, inet_ehashfn);
+ if (IS_ERR(sk))
+ return NULL;
if (sk)
return sk;
- return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+ return __inet_lookup(net, hashinfo, skb,
doff, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb), sdif,
refcounted);
diff --git a/include/net/sock.h b/include/net/sock.h
index 7ae44bf866af..74cbfb15d289 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2815,20 +2815,23 @@ sk_is_refcounted(struct sock *sk)
* skb_steal_sock - steal a socket from an sk_buff
* @skb: sk_buff to steal the socket from
* @refcounted: is set to true if the socket is reference-counted
+ * @prefetched: is set to true if the socket was assigned from bpf
*/
static inline struct sock *
-skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched)
{
if (skb->sk) {
struct sock *sk = skb->sk;
*refcounted = true;
- if (skb_sk_is_prefetched(skb))
+ *prefetched = skb_sk_is_prefetched(skb);
+ if (*prefetched)
*refcounted = sk_is_refcounted(sk);
skb->destructor = NULL;
skb->sk = NULL;
return sk;
}
+ *prefetched = false;
*refcounted = false;
return NULL;
}
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 739c15906a65..7fc98f4b63e9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4198,9 +4198,6 @@ union bpf_attr {
* **-EOPNOTSUPP** if the operation is not supported, for example
* a call from outside of TC ingress.
*
- * **-ESOCKTNOSUPPORT** if the socket type is not supported
- * (reuseport).
- *
* long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
* Description
* Helper is overloaded depending on BPF program type. This
diff --git a/net/core/filter.c b/net/core/filter.c
index b5b51ef48c5f..7c37f4646c20 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7351,8 +7351,6 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
return -EOPNOTSUPP;
if (unlikely(dev_net(skb->dev) != sock_net(sk)))
return -ENETUNREACH;
- if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
- return -ESOCKTNOSUPPORT;
if (sk_unhashed(sk))
return -EOPNOTSUPP;
if (sk_is_refcounted(sk) &&
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 456fb6ee6ee8..d89c4a39cf27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2388,7 +2388,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
- sk = skb_steal_sock(skb, &refcounted);
+ sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+ &refcounted, udp_ehashfn);
+ if (IS_ERR(sk))
+ goto no_sk;
+
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -2409,7 +2413,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk)
return udp_unicast_rcv_skb(sk, skb, uh);
-
+no_sk:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
nf_reset_ct(skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4b8974a8c7a3..00996f0f7cfe 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -964,7 +964,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto csum_error;
/* Check if the socket is already available, e.g. due to early demux */
- sk = skb_steal_sock(skb, &refcounted);
+ sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
+ &refcounted, udp6_ehashfn);
+ if (IS_ERR(sk))
+ goto no_sk;
+
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
@@ -998,7 +1002,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
-
+no_sk:
reason = SKB_DROP_REASON_NO_SOCKET;
if (!uh->check)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 739c15906a65..7fc98f4b63e9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4198,9 +4198,6 @@ union bpf_attr {
* **-EOPNOTSUPP** if the operation is not supported, for example
* a call from outside of TC ingress.
*
- * **-ESOCKTNOSUPPORT** if the socket type is not supported
- * (reuseport).
- *
* long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
* Description
* Helper is overloaded depending on BPF program type. This
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-17 16:46:25 +0000