bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide

remote_port is another case of a BPF context field documented as a 32-bit
value in network byte order for which the BPF context access converter
generates a load of a zero-padded 16-bit integer in network byte order.

First such case was dst_port in bpf_sock which got addressed in commit
4421a582718a ("bpf: Make dst_port field in struct bpf_sock 16-bit wide").

Loading 4-bytes from the remote_port offset and converting the value with
bpf_ntohl() leads to surprising results, as the expected value is shifted
by 16 bits.

Reduce the confusion by splitting the field in two - a 16-bit field holding
a big-endian integer, and a 16-bit zero-padding anonymous field that
follows it.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220209184333.654927-2-jakub@cloudflare.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a7f0ddedac1fafa1ec0a84345b1d1cb05b098b04..afe3d0d7f5f259499059c8162710f0bb007bd715 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6453,7 +6453,8 @@ struct bpf_sk_lookup {
        __u32 protocol;         /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
        __u32 remote_ip4;       /* Network byte order */
        __u32 remote_ip6[4];    /* Network byte order */
-       __u32 remote_port;      /* Network byte order */
+       __be16 remote_port;     /* Network byte order */
+       __u16 :16;              /* Zero padding */
        __u32 local_ip4;        /* Network byte order */
        __u32 local_ip6[4];     /* Network byte order */
        __u32 local_port;       /* Host byte order */

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index cb150f756f3db812b75af012e334746ec094b1db..f08034500813f5a3b3f66c3c7293cc925743a7b2 100644 (file)
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1147,7 +1147,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
        if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
                goto out;
 
-       if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+       if (user_ctx->local_port > U16_MAX) {
                ret = -ERANGE;
                goto out;
        }
@@ -1155,7 +1155,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
        ctx.family = (u16)user_ctx->family;
        ctx.protocol = (u16)user_ctx->protocol;
        ctx.dport = (u16)user_ctx->local_port;
-       ctx.sport = (__force __be16)user_ctx->remote_port;
+       ctx.sport = user_ctx->remote_port;
 
        switch (ctx.family) {
        case AF_INET:

diff --git a/net/core/filter.c b/net/core/filter.c
index 99a05199a806d409f32a450d3ed69383cd828834..83f06d3b2c529eeeb69c1bad7de275e0352ad350 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10843,7 +10843,8 @@ static bool sk_lookup_is_valid_access(int off, int size,
        case bpf_ctx_range(struct bpf_sk_lookup, local_ip4):
        case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]):
        case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
-       case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
+       case offsetof(struct bpf_sk_lookup, remote_port) ...
+            offsetof(struct bpf_sk_lookup, local_ip4) - 1:
        case bpf_ctx_range(struct bpf_sk_lookup, local_port):
        case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex):
                bpf_ctx_record_field_size(info, sizeof(__u32));