ebpf, filter: do not convert skb->protocol to host endianess during runtime

Commit c24973957975 ("bpf: allow BPF programs access 'protocol' and 'vlan_tci'
fields") has added support for accessing protocol, vlan_present and vlan_tci
into the skb offset map.

As referenced in the below discussion, accessing skb->protocol from an eBPF
program should be converted without handling endianess.

The reason for this is that an eBPF program could simply do a check more
naturally, by f.e. testing skb->protocol == htons(ETH_P_IP), where the LLVM
compiler resolves htons() against a constant automatically during compilation
time, as opposed to an otherwise needed run time conversion.

After all, the way of programming both from a user perspective differs quite
a lot, i.e. bpf_asm ["ld proto"] versus a C subset/LLVM.

Reference: https://patchwork.ozlabs.org/patch/450819/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/filter.c b/net/core/filter.c
index b95ae7f..bdaac58 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -178,16 +178,6 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
                                      offsetof(struct sk_buff, queue_mapping));
                break;
 
-       case SKF_AD_PROTOCOL:
-               BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
-
-               /* dst_reg = *(u16 *) (src_reg + offsetof(protocol)) */
-               *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
-                                     offsetof(struct sk_buff, protocol));
-               /* dst_reg = ntohs(dst_reg) [emitting a nop or swap16] */
-               *insn++ = BPF_ENDIAN(BPF_FROM_BE, dst_reg, 16);
-               break;
-
        case SKF_AD_VLAN_TAG:
        case SKF_AD_VLAN_TAG_PRESENT:
                BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
@@ -219,8 +209,13 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 
        switch (fp->k) {
        case SKF_AD_OFF + SKF_AD_PROTOCOL:
-               cnt = convert_skb_access(SKF_AD_PROTOCOL, BPF_REG_A, BPF_REG_CTX, insn);
-               insn += cnt - 1;
+               BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+               /* A = *(u16 *) (CTX + offsetof(protocol)) */
+               *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+                                     offsetof(struct sk_buff, protocol));
+               /* A = ntohs(A) [emitting a nop or swap16] */
+               *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
                break;
 
        case SKF_AD_OFF + SKF_AD_PKTTYPE:
@@ -1224,6 +1219,13 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
                                      offsetof(struct sk_buff, len));
                break;
 
+       case offsetof(struct __sk_buff, protocol):
+               BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+               *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+                                     offsetof(struct sk_buff, protocol));
+               break;
+
        case offsetof(struct __sk_buff, mark):
                return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn);
 
@@ -1233,9 +1235,6 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
        case offsetof(struct __sk_buff, queue_mapping):
                return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn);
 
-       case offsetof(struct __sk_buff, protocol):
-               return convert_skb_access(SKF_AD_PROTOCOL, dst_reg, src_reg, insn);
-
        case offsetof(struct __sk_buff, vlan_present):
                return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
                                          dst_reg, src_reg, insn);