This commit allows progs to elide a null check on statically known map
lookup keys. In other words, if the verifier can statically prove that
the lookup will be in-bounds, allow the prog to drop the null check.

This is useful for two reasons:

1. Large numbers of nullness checks (especially when they cannot fail)
   unnecessarily pushes prog towards BPF_COMPLEXITY_LIMIT_JMP_SEQ.
2. It forms a tighter contract between programmer and verifier.

For (1), bpftrace is starting to make heavier use of percpu scratch
maps. As a result, for user scripts with large number of unrolled loops,
we are starting to hit jump complexity verification errors.  These
percpu lookups cannot fail anyways, as we only use static key values.
Eliding nullness probably results in less work for verifier as well.

For (2), percpu scratch maps are often used as a larger stack, as the
currrent stack is limited to 512 bytes. In these situations, it is
desirable for the programmer to express: "this lookup should never fail,
and if it does, it means I messed up the code". By omitting the null
check, the programmer can "ask" the verifier to double check the logic.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
---
 kernel/bpf/verifier.c | 56 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7df5c29293a4..5b5ae3c1a456 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -282,6 +282,7 @@ struct bpf_call_arg_meta {
 	u32 ret_btf_id;
 	u32 subprogno;
 	struct btf_field *kptr_field;
+	long const_map_key;
 };
 
 struct bpf_kfunc_call_arg_meta {
@@ -10414,6 +10415,45 @@ static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno
 				 state->callback_subprogno == subprogno);
 }
 
+/* Returns whether or not the given map type can potentially elide
+ * lookup return value nullness check. This is possible if the key
+ * is statically known.
+ */
+static bool can_elide_value_nullness(enum bpf_map_type type)
+{
+	switch (type) {
+	case BPF_MAP_TYPE_ARRAY:
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/* Returns constant key value if possible, else -1 */
+static long get_constant_map_key(struct bpf_verifier_env *env,
+				 struct bpf_reg_state *key)
+{
+	struct bpf_func_state *state = func(env, key);
+	struct bpf_reg_state *reg;
+	int stack_off;
+	int slot;
+	int spi;
+
+	if (!tnum_is_const(key->var_off))
+		return -1;
+
+	stack_off = key->off + key->var_off.value;
+	slot = -stack_off - 1;
+	spi = slot / BPF_REG_SIZE;
+	reg = &state->stack[spi].spilled_ptr;
+
+	if (!tnum_is_const(reg->var_off))
+		return -1;
+
+	return reg->var_off.value;
+}
+
 static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
 			    const struct bpf_func_proto **ptr)
 {
@@ -10511,6 +10551,15 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			env->insn_aux_data[insn_idx].storage_get_func_atomic = true;
 	}
 
+	/* Logically we are trying to check on key register state before
+	 * the helper is called, so process here. Otherwise argument processing
+	 * may clobber the spilled key values.
+	 */
+	regs = cur_regs(env);
+	if (func_id == BPF_FUNC_map_lookup_elem)
+		meta.const_map_key = get_constant_map_key(env, &regs[BPF_REG_2]);
+
+
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
@@ -10771,6 +10820,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 				"kernel subsystem misconfigured verifier\n");
 			return -EINVAL;
 		}
+
+		if (func_id == BPF_FUNC_map_lookup_elem &&
+		    can_elide_value_nullness(meta.map_ptr->map_type) &&
+		    meta.const_map_key >= 0 &&
+		    meta.const_map_key < meta.map_ptr->max_entries)
+			ret_flag &= ~PTR_MAYBE_NULL;
+
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
 		regs[BPF_REG_0].map_uid = meta.map_uid;
 		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag;
-- 
2.46.0