[PATCH bpf-next v2] bpf, seccomp: fix false positive preemption splat for cbpf->ebpf progs

[Daniel Borkmann]

In 568f196756ad ("bpf: check that BPF programs run with preemption disabled")
a check was added for BPF_PROG_RUN() that for every invocation preemption is
disabled to not break eBPF assumptions (e.g. per-cpu map). Of course this does
not count for seccomp because only cBPF -> eBPF is loaded here and it does
not make use of any functionality that would require this assertion. Fix this
false positive by adding and using SECCOMP_RUN() variant that does not have
the cant_sleep(); check.

Fixes: 568f196756ad ("bpf: check that BPF programs run with preemption 
disabled")
Reported-by: syzbot+8bf19ee2aa580de7a...@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <dan...@iogearbox.net>
Acked-by: Kees Cook <keesc...@chromium.org>
---
 v1 -> v2:
  - More elaborate comment and added SECCOMP_RUN
  - Added Kees' ACK from earlier v1 patch

 include/linux/filter.h | 22 +++++++++++++++++++++-
 kernel/seccomp.c       |  2 +-
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index f32b3ec..cd7f957 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -533,7 +533,27 @@ struct sk_filter {
        struct bpf_prog *prog;
 };
 
-#define BPF_PROG_RUN(filter, ctx)  ({ cant_sleep(); (*(filter)->bpf_func)(ctx, 
(filter)->insnsi); })
+#define __bpf_prog_run(prog, ctx)              \
+       (*(prog)->bpf_func)(ctx, (prog)->insnsi)
+#define __bpf_prog_run__may_preempt(prog, ctx) \
+       ({ __bpf_prog_run(prog, ctx); })
+#define __bpf_prog_run__non_preempt(prog, ctx) \
+       ({ cant_sleep(); __bpf_prog_run(prog, ctx); })
+
+/* Preemption must be disabled when native eBPF programs are run in
+ * order to not break per CPU data structures, for example; make
+ * sure to throw a stack trace under CONFIG_DEBUG_ATOMIC_SLEEP when
+ * we find that preemption is still enabled.
+ *
+ * Only exception today is seccomp, where progs have transitioned
+ * from cBPF to eBPF, and native eBPF is _not_ supported. They can
+ * safely run with preemption enabled.
+ */
+#define BPF_PROG_RUN(prog, ctx)                        \
+       __bpf_prog_run__non_preempt(prog, ctx)
+
+#define SECCOMP_RUN(prog, ctx)                 \
+       __bpf_prog_run__may_preempt(prog, ctx)
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e815781..701a3cf 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -268,7 +268,7 @@ static u32 seccomp_run_filters(const struct seccomp_data 
*sd,
         * value always takes priority (ignoring the DATA).
         */
        for (; f; f = f->prev) {
-               u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
+               u32 cur_ret = SECCOMP_RUN(f->prog, sd);
 
                if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
                        ret = cur_ret;
-- 
2.9.5