filter: add ANC_PAY_OFFSET instruction for loading payload start offset

It is very useful to do dynamic truncation of packets. In particular,
we're interested to push the necessary header bytes to the user space and
cut off user payload that should probably not be transferred for some reasons
(e.g. privacy, speed, or others). With the ancillary extension PAY_OFFSET,
we can load it into the accumulator, and return it. E.g. in bpfc syntax ...

        ld #poff        ; { 0x20, 0, 0, 0xfffff034 },
        ret a           ; { 0x16, 0, 0, 0x00000000 },

... as a filter will accomplish this without having to do a big hackery in
a BPF filter itself. Follow-up JIT implementations are welcome.

Thanks to Eric Dumazet for suggesting and discussing this during the
Netfilter Workshop in Copenhagen.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/filter.h

@@ -126,6 +126,7 @@ enum {
 	BPF_S_ANC_SECCOMP_LD_W,
 	BPF_S_ANC_VLAN_TAG,
 	BPF_S_ANC_VLAN_TAG_PRESENT,
+	BPF_S_ANC_PAY_OFFSET,
 };
 
 #endif /* __LINUX_FILTER_H__ */

include/uapi/linux/filter.h

@@ -129,7 +129,8 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define SKF_AD_ALU_XOR_X	40
 #define SKF_AD_VLAN_TAG	44
 #define SKF_AD_VLAN_TAG_PRESENT 48
-#define SKF_AD_MAX	52
+#define SKF_AD_PAY_OFFSET	52
+#define SKF_AD_MAX	56
 #define SKF_NET_OFF   (-0x100000)
 #define SKF_LL_OFF    (-0x200000)
 

net/core/filter.c

@@ -348,6 +348,9 @@ load_b:
 		case BPF_S_ANC_VLAN_TAG_PRESENT:
 			A = !!vlan_tx_tag_present(skb);
 			continue;
+		case BPF_S_ANC_PAY_OFFSET:
+			A = __skb_get_poff(skb);
+			continue;
 		case BPF_S_ANC_NLATTR: {
 			struct nlattr *nla;
 
@@ -612,6 +615,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 			ANCILLARY(ALU_XOR_X);
 			ANCILLARY(VLAN_TAG);
 			ANCILLARY(VLAN_TAG_PRESENT);
+			ANCILLARY(PAY_OFFSET);
 			}
 
 			/* ancillary operation unknown or unsupported */
@@ -814,6 +818,7 @@ static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
 		[BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
 		[BPF_S_ANC_VLAN_TAG]	= BPF_LD|BPF_B|BPF_ABS,
 		[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_PAY_OFFSET]	= BPF_LD|BPF_B|BPF_ABS,
 		[BPF_S_LD_W_LEN]	= BPF_LD|BPF_W|BPF_LEN,
 		[BPF_S_LD_W_IND]	= BPF_LD|BPF_W|BPF_IND,
 		[BPF_S_LD_H_IND]	= BPF_LD|BPF_H|BPF_IND,