[bpf,v2,3/8] bpf: track changes_pkt_data property for global functions

Commit Message

Eduard Zingerman Dec. 10, 2024, 4:10 a.m. UTC

When processing calls to certain helpers, verifier invalidates all
packet pointers in a current state. For example, consider the
following program:

    __attribute__((__noinline__))
    long skb_pull_data(struct __sk_buff *sk, __u32 len)
    {
        return bpf_skb_pull_data(sk, len);
    }

    SEC("tc")
    int test_invalidate_checks(struct __sk_buff *sk)
    {
        int *p = (void *)(long)sk->data;
        if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP;
        skb_pull_data(sk, 0);
        *p = 42;
        return TCX_PASS;
    }

After a call to bpf_skb_pull_data() the pointer 'p' can't be used
safely. See function filter.c:bpf_helper_changes_pkt_data() for a list
of such helpers.

At the moment verifier invalidates packet pointers when processing
helper function calls, and does not traverse global sub-programs when
processing calls to global sub-programs. This means that calls to
helpers done from global sub-programs do not invalidate pointers in
the caller state. E.g. the program above is unsafe, but is not
rejected by verifier.

This commit fixes the omission by computing field
bpf_subprog_info->changes_pkt_data for each sub-program before main
verification pass.
changes_pkt_data should be set if:
- subprogram calls helper for which bpf_helper_changes_pkt_data
  returns true;
- subprogram calls a global function,
  for which bpf_subprog_info->changes_pkt_data should be set.

The verifier.c:check_cfg() pass is modified to compute this
information. The commit relies on depth first instruction traversal
done by check_cfg() and absence of recursive function calls:
- check_cfg() would eventually visit every call to subprogram S in a
  state when S is fully explored;
- when S is fully explored:
  - every direct helper call within S is explored
    (and thus changes_pkt_data is set if needed);
  - every call to subprogram S1 called by S was visited with S1 fully
    explored (and thus S inherits changes_pkt_data from S1).

The downside of such approach is that dead code elimination is not
taken into account: if a helper call inside global function is dead
because of current configuration, verifier would conservatively assume
that the call occurs for the purpose of the changes_pkt_data
computation.

Reported-by: Nick Zavaritsky <[e-mail]>
Closes: https://lore.kernel.org/bpf/[e-mail]/
Signed-off-by: Eduard Zingerman <[e-mail]>
---
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/verifier.c        | 32 +++++++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

Patch

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f4290c179bee..48b7b2eeb7e2 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -659,6 +659,7 @@  struct bpf_subprog_info {
 	bool args_cached: 1;
 	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
 	bool keep_fastcall_stack: 1;
+	bool changes_pkt_data: 1;
 
 	enum priv_stack_mode priv_stack_mode;
 	u8 arg_cnt;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ad3f6d28e8e4..6a29b68cebd6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10042,6 +10042,8 @@  static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 
 		verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
 			subprog, sub_name);
+		if (env->subprog_info[subprog].changes_pkt_data)
+			clear_all_pkt_pointers(env);
 		/* mark global subprog for verifying after main prog */
 		subprog_aux(env, subprog)->called = true;
 		clear_caller_saved_regs(env, caller->regs);
@@ -16246,6 +16248,29 @@  static int check_return_code(struct bpf_verifier_env *env, int regno, const char
 	return 0;
 }
 
+static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off)
+{
+	struct bpf_subprog_info *subprog;
+
+	subprog = find_containing_subprog(env, off);
+	subprog->changes_pkt_data = true;
+}
+
+/* 't' is an index of a call-site.
+ * 'w' is a callee entry point.
+ * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED.
+ * Rely on DFS traversal order and absence of recursive calls to guarantee that
+ * callee's change_pkt_data marks would be correct at that moment.
+ */
+static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w)
+{
+	struct bpf_subprog_info *caller, *callee;
+
+	caller = find_containing_subprog(env, t);
+	callee = find_containing_subprog(env, w);
+	caller->changes_pkt_data |= callee->changes_pkt_data;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered
@@ -16379,6 +16404,7 @@  static int visit_func_call_insn(int t, struct bpf_insn *insns,
 				bool visit_callee)
 {
 	int ret, insn_sz;
+	int w;
 
 	insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
 	ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
@@ -16390,8 +16416,10 @@  static int visit_func_call_insn(int t, struct bpf_insn *insns,
 	mark_jmp_point(env, t + insn_sz);
 
 	if (visit_callee) {
+		w = t + insns[t].imm + 1;
 		mark_prune_point(env, t);
-		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
+		merge_callee_effects(env, t, w);
+		ret = push_insn(t, w, BRANCH, env);
 	}
 	return ret;
 }
@@ -16708,6 +16736,8 @@  static int visit_insn(int t, struct bpf_verifier_env *env)
 			mark_prune_point(env, t);
 			mark_jmp_point(env, t);
 		}
+		if (bpf_helper_call(insn) && bpf_helper_changes_pkt_data(insn->imm))
+			mark_subprog_changes_pkt_data(env, t);
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 			struct bpf_kfunc_call_arg_meta meta;