bpf: verifier: Support eliding map lookup nullness

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.

Tests also have to be updated in sync with these changes, as the
verifier is more efficient with this change. Notable, iters.c tests had
to be changed to use a map type that still requires null checks, as it's
exercising verifier tracking logic w.r.t iterators.

Signed-off-by: Daniel Xu <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

kernel/bpf/verifier.c

···
 	u32 ret_btf_id;
 	u32 subprogno;
 	struct btf_field *kptr_field;
+	s64 const_map_key;
 };
 
 struct bpf_kfunc_call_arg_meta {
···
 	return 0;
 }
 
+/* Returns constant key value if possible, else negative error */
+static s64 get_constant_map_key(struct bpf_verifier_env *env,
+				struct bpf_reg_state *key,
+				u32 key_size)
+{
+	struct bpf_func_state *state = func(env, key);
+	struct bpf_reg_state *reg;
+	int slot, spi, off;
+	int spill_size = 0;
+	int zero_size = 0;
+	int stack_off;
+	int i, err;
+	u8 *stype;
+
+	if (!env->bpf_capable)
+		return -EOPNOTSUPP;
+	if (key->type != PTR_TO_STACK)
+		return -EOPNOTSUPP;
+	if (!tnum_is_const(key->var_off))
+		return -EOPNOTSUPP;
+
+	stack_off = key->off + key->var_off.value;
+	slot = -stack_off - 1;
+	spi = slot / BPF_REG_SIZE;
+	off = slot % BPF_REG_SIZE;
+	stype = state->stack[spi].slot_type;
+
+	/* First handle precisely tracked STACK_ZERO */
+	for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--)
+		zero_size++;
+	if (zero_size >= key_size)
+		return 0;
+
+	/* Check that stack contains a scalar spill of expected size */
+	if (!is_spilled_scalar_reg(&state->stack[spi]))
+		return -EOPNOTSUPP;
+	for (i = off; i >= 0 && stype[i] == STACK_SPILL; i--)
+		spill_size++;
+	if (spill_size != key_size)
+		return -EOPNOTSUPP;
+
+	reg = &state->stack[spi].spilled_ptr;
+	if (!tnum_is_const(reg->var_off))
+		/* Stack value not statically known */
+		return -EOPNOTSUPP;
+
+	/* We are relying on a constant value. So mark as precise
+	 * to prevent pruning on it.
+	 */
+	bt_set_frame_slot(&env->bt, key->frameno, spi);
+	err = mark_chain_precision_batch(env);
+	if (err < 0)
+		return err;
+
+	return reg->var_off.value;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn,
···
 	enum bpf_arg_type arg_type = fn->arg_type[arg];
 	enum bpf_reg_type type = reg->type;
 	u32 *arg_btf_id = NULL;
+	u32 key_size;
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
···
 			verbose(env, "invalid map_ptr to access map->key\n");
 			return -EACCES;
 		}
-		err = check_helper_mem_access(env, regno, meta->map_ptr->key_size,
-					      BPF_READ, false, NULL);
+		key_size = meta->map_ptr->key_size;
+		err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL);
+		if (err)
+			return err;
+		meta->const_map_key = get_constant_map_key(env, reg, key_size);
+		if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP)
+			return meta->const_map_key;
 		break;
 	case ARG_PTR_TO_MAP_VALUE:
 		if (type_may_be_null(arg_type) && register_is_null(reg))
···
 				 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;
+	}
+}
+
 static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
 			    const struct bpf_func_proto **ptr)
 {
···
 				"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;
-		if (!type_may_be_null(ret_type) &&
+		if (!type_may_be_null(ret_flag) &&
 		    btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) {
 			regs[BPF_REG_0].id = ++env->id_gen;
 		}

tools/testing/selftests/bpf/progs/iters.c

···
 }
 
 struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
 	__type(value, int);
 	__uint(max_entries, 1000);
-} arr_map SEC(".maps");
+} hash_map SEC(".maps");
 
 SEC("?raw_tp")
 __failure __msg("invalid mem access 'scalar'")
···
 
 	MY_PID_GUARD();
 
-	map_val = bpf_map_lookup_elem(&arr_map, &key);
+	map_val = bpf_map_lookup_elem(&hash_map, &key);
 	if (!map_val)
 		return 0;
 
···
 
 	MY_PID_GUARD();
 
-	map_val = bpf_map_lookup_elem(&arr_map, &key);
+	map_val = bpf_map_lookup_elem(&hash_map, &key);
 	if (!map_val)
 		return 0;
 
 	bpf_repeat(1000000) {
-		map_val = bpf_map_lookup_elem(&arr_map, &key);
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
 	}
 
 	*map_val = 123;
···
 	MY_PID_GUARD();
 
 	bpf_repeat(1000000) {
-		map_val = bpf_map_lookup_elem(&arr_map, &key);
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
 		found = true;
 	}
 
···
 	MY_PID_GUARD();
 
 	bpf_repeat(1000000) {
-		map_val = bpf_map_lookup_elem(&arr_map, &key);
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
 		if (map_val) {
 			found = true;
 			break;

tools/testing/selftests/bpf/progs/map_kptr_fail.c

···
 }
 
 SEC("?tc")
-__failure __msg("Unreleased reference id=5 alloc_insn=")
+__failure __msg("Unreleased reference id=4 alloc_insn=")
 int kptr_xchg_ref_state(struct __sk_buff *ctx)
 {
 	struct prog_test_ref_kfunc *p;

tools/testing/selftests/bpf/progs/verifier_map_in_map.c

···
 
 SEC("xdp")
 __description("map in map state pruning")
-__success __msg("processed 26 insns")
+__success __msg("processed 15 insns")
 __log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ)
 __naked void map_in_map_state_pruning(void)
 {

tools/testing/selftests/bpf/verifier/map_kptr.c

···
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
-	.errstr = "Unreleased reference id=5 alloc_insn=20",
+	.errstr = "Unreleased reference id=4 alloc_insn=20",
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_acquire", 15 },
 	}