bpf: Allow narrow loads of bpf_sysctl fields with offset > 0

"ctx:file_pos sysctl:read read ok narrow" works on s390 by accident: it
reads the wrong byte, which happens to have the expected value of 0.
Improve the test by seeking to the 4th byte and expecting 4 instead of
0.

This makes the latent problem apparent: the test attempts to read the
first byte of bpf_sysctl.file_pos, assuming this is the least-significant
byte, which is not the case on big-endian machines: a non-zero offset is
needed.

The point of the test is to verify narrow loads, so we cannot cheat our
way out by simply using BPF_W. The existence of the test means that such
loads have to be supported, most likely because llvm can generate them.
Fix the test by adding a big-endian variant, which uses an offset to
access the least-significant byte of bpf_sysctl.file_pos.

This reveals the final problem: verifier rejects accesses to bpf_sysctl
fields with offset > 0. Such accesses are already allowed for a wide
range of structs: __sk_buff, bpf_sock_addr and sk_msg_md to name a few.
Extend this support to bpf_sysctl by using bpf_ctx_range instead of
offsetof when matching field offsets.

Fixes: 7b146cebe30c ("bpf: Sysctl hook")
Fixes: e1550bfe0de4 ("bpf: Add file_pos field to bpf_sysctl ctx")
Fixes: 9a1027e52535 ("selftests/bpf: Test file_pos field in bpf_sysctl ctx")
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191028122902.9763-1-iii@linux.ibm.com

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ddd8add..a3eaf08 100644 (file)
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1311,12 +1311,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
                return false;
 
        switch (off) {
-       case offsetof(struct bpf_sysctl, write):
+       case bpf_ctx_range(struct bpf_sysctl, write):
                if (type != BPF_READ)
                        return false;
                bpf_ctx_record_field_size(info, size_default);
                return bpf_ctx_narrow_access_ok(off, size, size_default);
-       case offsetof(struct bpf_sysctl, file_pos):
+       case bpf_ctx_range(struct bpf_sysctl, file_pos):
                if (type == BPF_READ) {
                        bpf_ctx_record_field_size(info, size_default);
                        return bpf_ctx_narrow_access_ok(off, size, size_default);

diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index a320e38..7c6e5b1 100644 (file)
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -161,9 +161,14 @@ static struct sysctl_test tests[] = {
                .descr = "ctx:file_pos sysctl:read read ok narrow",
                .insns = {
                        /* If (file_pos == X) */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                        BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
                                    offsetof(struct bpf_sysctl, file_pos)),
-                       BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
+#else
+                       BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+                                   offsetof(struct bpf_sysctl, file_pos) + 3),
+#endif
+                       BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2),
 
                        /* return ALLOW; */
                        BPF_MOV64_IMM(BPF_REG_0, 1),
@@ -176,6 +181,7 @@ static struct sysctl_test tests[] = {
                .attach_type = BPF_CGROUP_SYSCTL,
                .sysctl = "kernel/ostype",
                .open_flags = O_RDONLY,
+               .seek = 4,
                .result = SUCCESS,
        },
        {