tcp: take care of truncations done by sk_filter()

[ Upstream commit ac6e780070e30e4c35bd395acfe9191e6268bdd3 ]

With syzkaller help, Marco Grassi found a bug in TCP stack,
crashing in tcp_collapse()

Root cause is that sk_filter() can truncate the incoming skb,
but TCP stack was not really expecting this to happen.
It probably was expecting a simple DROP or ACCEPT behavior.

We first need to make sure no part of TCP header could be removed.
Then we need to adjust TCP_SKB_CB(skb)->end_seq

Many thanks to syzkaller team and Marco for giving us a reproducer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Marco Grassi <marco.gra@gmail.com>
Reported-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5110d42118665cdab0f3bb377298b40d7c48febb..ccb98b459c59fd18db0e61a258c502acfa2e92f1 100644 (file)
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -421,7 +421,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 }
 #endif /* CONFIG_DEBUG_SET_MODULE_RONX */
 
-int sk_filter(struct sock *sk, struct sk_buff *skb);
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
+static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
+{
+       return sk_filter_trim_cap(sk, skb, 1);
+}
 
 int bpf_prog_select_runtime(struct bpf_prog *fp);
 void bpf_prog_free(struct bpf_prog *fp);

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c3ab544d3a887cd12b4d524f046f2cfd5192359..e9d7a8ef9a6d6ee70da47892920d8db38dc9eaf5 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1156,6 +1156,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 }
 
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);
 
 #undef STATE_TRACE
 

diff --git a/net/core/filter.c b/net/core/filter.c
index 75e9b2b2336d552f217743b5c17866f4fba13257..e94355452166c8f9864a153c2f552ff37c9c756b 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -52,9 +52,10 @@
 #include <net/dst.h>
 
 /**
- *     sk_filter - run a packet through a socket filter
+ *     sk_filter_trim_cap - run a packet through a socket filter
  *     @sk: sock associated with &sk_buff
  *     @skb: buffer to filter
+ *     @cap: limit on how short the eBPF program may trim the packet
  *
  * Run the eBPF program and then cut skb->data to correct size returned by
  * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
@@ -63,7 +64,7 @@
  * be accepted or -EPERM if the packet should be tossed.
  *
  */
-int sk_filter(struct sock *sk, struct sk_buff *skb)
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 {
        int err;
        struct sk_filter *filter;
@@ -84,14 +85,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
        filter = rcu_dereference(sk->sk_filter);
        if (filter) {
                unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
-
-               err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
+               err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
        }
        rcu_read_unlock();
 
        return err;
 }
-EXPORT_SYMBOL(sk_filter);
+EXPORT_SYMBOL(sk_filter_trim_cap);
 
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b5853cac3269ab7ef8d2612a63accdb473cdebbc..b58a38eea0598bfa9cd874f980869c6868b01b2a 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1533,6 +1533,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_prequeue);
 
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+       struct tcphdr *th = (struct tcphdr *)skb->data;
+       unsigned int eaten = skb->len;
+       int err;
+
+       err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+       if (!err) {
+               eaten -= skb->len;
+               TCP_SKB_CB(skb)->end_seq -= eaten;
+       }
+       return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
 /*
  *     From tcp_input.c
  */
@@ -1638,8 +1653,10 @@ process:
 
        nf_reset(skb);
 
-       if (sk_filter(sk, skb))
+       if (tcp_filter(sk, skb))
                goto discard_and_relse;
+       th = (const struct tcphdr *)skb->data;
+       iph = ip_hdr(skb);
 
        skb->dev = NULL;
 

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fbd521fdae53606bb6db7dc729ed788b3abd82f0..5f581616bf6a068269587077879cf56b7e637cb5 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1214,7 +1214,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
        if (skb->protocol == htons(ETH_P_IP))
                return tcp_v4_do_rcv(sk, skb);
 
-       if (sk_filter(sk, skb))
+       if (tcp_filter(sk, skb))
                goto discard;
 
        /*
@@ -1438,8 +1438,10 @@ process:
        if (tcp_v6_inbound_md5_hash(sk, skb))
                goto discard_and_relse;
 
-       if (sk_filter(sk, skb))
+       if (tcp_filter(sk, skb))
                goto discard_and_relse;
+       th = (const struct tcphdr *)skb->data;
+       hdr = ipv6_hdr(skb);
 
        skb->dev = NULL;