Merge branch 'sk_filter-trim-limit'

Willem de Bruijn says:

====================
limit sk_filter trim to payload

Sockets can apply a filter to incoming packets to drop or trim them.
Fix two codepaths that call skb_pull/__skb_pull after sk_filter
without checking for packet length.

Reading beyond skb->tail after trimming happens in more codepaths, but
safety of reading in the linear segment is based on minimum allocation
size (MAX_HEADER, GRO_MAX_HEAD, ..).
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/linux/filter.h

@@ -467,7 +467,11 @@ 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);
+}
 
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
 void bpf_prog_free(struct bpf_prog *fp);

include/net/sock.h

@@ -1576,7 +1576,13 @@ static inline void sock_put(struct sock *sk)
  */
 void sock_gen_put(struct sock *sk);
 
-int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
+int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
+		     unsigned int trim_cap);
+static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
+				 const int nested)
+{
+	return __sk_receive_skb(sk, skb, nested, 1);
+}
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
 {

net/core/filter.c

@@ -53,9 +53,10 @@
 #include <net/sock_reuseport.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
@@ -64,7 +65,7 @@
  * 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;
@@ -85,14 +86,13 @@ 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)
 {

net/core/sock.c

@@ -452,11 +452,12 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_queue_rcv_skb);
 
-int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
+int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
+		     const int nested, unsigned int trim_cap)
 {
 	int rc = NET_RX_SUCCESS;
 
-	if (sk_filter(sk, skb))
+	if (sk_filter_trim_cap(sk, skb, trim_cap))
 		goto discard_and_relse;
 
 	skb->dev = NULL;
@@ -492,7 +493,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
 	kfree_skb(skb);
 	goto out;
 }
-EXPORT_SYMBOL(sk_receive_skb);
+EXPORT_SYMBOL(__sk_receive_skb);
 
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
 {

net/dccp/ipv4.c

@@ -868,7 +868,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 		goto discard_and_relse;
 	nf_reset(skb);
 
-	return sk_receive_skb(sk, skb, 1);
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4);
 
 no_dccp_socket:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))

net/dccp/ipv6.c

@@ -732,7 +732,7 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	return sk_receive_skb(sk, skb, 1) ? -1 : 0;
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0;
 
 no_dccp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))

net/rose/rose_in.c

@@ -164,7 +164,8 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety
 		rose_frames_acked(sk, nr);
 		if (ns == rose->vr) {
 			rose_start_idletimer(sk);
-			if (sock_queue_rcv_skb(sk, skb) == 0) {
+			if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 &&
+			    __sock_queue_rcv_skb(sk, skb) == 0) {
 				rose->vr = (rose->vr + 1) % ROSE_MODULUS;
 				queued = 1;
 			} else {