[PATCH 4.4 16/37] tcp: take care of truncations done by sk_filter()

From: Greg Kroah-Hartman
Date: Sat Nov 19 2016 - 04:21:59 EST


4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <edumazet@xxxxxxxxxx>


[ 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@xxxxxxxxxx>
Reported-by: Marco Grassi <marco.gra@xxxxxxxxx>
Reported-by: Vladis Dronov <vdronov@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
include/linux/filter.h | 6 +++++-
include/net/tcp.h | 1 +
net/core/filter.c | 10 +++++-----
net/ipv4/tcp_ipv4.c | 19 ++++++++++++++++++-
net/ipv6/tcp_ipv6.c | 6 ++++--
5 files changed, 33 insertions(+), 9 deletions(-)

--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -421,7 +421,11 @@ static inline void bpf_prog_unlock_ro(st
}
#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);
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1156,6 +1156,7 @@ static inline void tcp_prequeue_init(str
}

bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);

#undef STATE_TRACE

--- 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
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)
{
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1533,6 +1533,21 @@ bool tcp_prequeue(struct sock *sk, struc
}
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;

--- 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
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;