[PATCH RFC bpf-next v1 11/32] bpf: Support constant scalar arguments for kfuncs

[Kumar Kartikeya Dwivedi <memxor@gmail.com>]

Allow passing known constant scalars as arguments to kfuncs that do not
represent a size parameter. This makes the search pruning optimization
of verifier more conservative for such kfunc calls, and each
non-distinct argument is considered unequivalent.

We will use this support to then expose a global bpf_kptr_alloc function
where it takes the local type ID in program BTF, and returns a
PTR_TO_BTF_ID to the local type. These will be called local kptrs, and
allows programs to allocate their own objects.

However, this is still not completely safe, as mark_chain_precision
logic is buggy without more work when the constant argument is not a
size, but still needs precise marker propagation for pruning checks.
Next patch will fix this problem.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 Documentation/bpf/kfuncs.rst | 30 ++++++++++++++++
 kernel/bpf/verifier.c        | 67 +++++++++++++++++++++++++++---------
 2 files changed, 80 insertions(+), 17 deletions(-)

diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 781731749e55..31625393204a 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -72,6 +72,36 @@ argument as its size. By default, without __sz annotation, the size of the type
 of the pointer is used. Without __sz annotation, a kfunc cannot accept a void
 pointer.
 
+2.2.1 __k Annotation
+--------------------
+
+This annotation is only understood for scalar arguments, where it indicates that
+the verifier must check the scalar argument to be a known constant, which does
+not indicate a size parameter. This distinction is important, as when the scalar
+argument does not represent a size parameter, verifier is more conservative in
+state search pruning and does not consider two arguments equivalent for safety
+purposes if the already verified value was within range of the new one.
+
+This assumption holds well for sizes (as memory accessed within smaller bounds
+in old verified state will also work for bigger bounds in current to be explored
+state), but not for other constant arguments where each carries a distinct
+semantic effect.
+
+An example is given below::
+
+        void *bpf_mem_alloc(u32 local_type_id__k)
+        {
+        ...
+        }
+
+Here, bpf_mem_alloc uses local_type_id argument to find out the size of that
+type ID in program's BTF and return a sized pointer to it. Each type ID will
+have a distinct size, hence it is crucial to treat each such call as distinct
+when values don't match.
+
+Hence, whenever a constant scalar argument is accepted by a kfunc which is not a
+size parameter, __k suffix must be used.
+
 .. _BPF_kfunc_nodef:
 
 2.3 Using an existing kernel function
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 96fab14eb94e..b28e88d6fabd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7588,6 +7588,10 @@ struct bpf_kfunc_arg_meta {
 	/* Out parameters */
 	u32 ref_obj_id;
 	u8 release_regno;
+	struct {
+		u64 value;
+		bool found;
+	} arg_constant;
 };
 
 static bool is_kfunc_acquire(struct bpf_kfunc_arg_meta *meta)
@@ -7625,30 +7629,40 @@ static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_arg_meta *meta, int arg)
 	return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET);
 }
 
-static bool is_kfunc_arg_mem_size(const struct btf *btf,
-				  const struct btf_param *arg,
-				  const struct bpf_reg_state *reg)
+static bool __kfunc_param_match_suffix(const struct btf *btf,
+				       const struct btf_param *arg,
+				       const char *suffix)
 {
-	int len, sfx_len = sizeof("__sz") - 1;
-	const struct btf_type *t;
+	int suffix_len = strlen(suffix), len;
 	const char *param_name;
 
-	t = btf_type_skip_modifiers(btf, arg->type, NULL);
-	if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE)
-		return false;
-
 	/* In the future, this can be ported to use BTF tagging */
 	param_name = btf_name_by_offset(btf, arg->name_off);
 	if (str_is_empty(param_name))
 		return false;
 	len = strlen(param_name);
-	if (len < sfx_len)
+	if (len < suffix_len)
 		return false;
-	param_name += len - sfx_len;
-	if (strncmp(param_name, "__sz", sfx_len))
+	param_name += len - suffix_len;
+	return !strncmp(param_name, suffix, suffix_len);
+}
+
+static bool is_kfunc_arg_mem_size(const struct btf *btf,
+				  const struct btf_param *arg,
+				  const struct bpf_reg_state *reg)
+{
+	const struct btf_type *t;
+
+	t = btf_type_skip_modifiers(btf, arg->type, NULL);
+	if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE)
 		return false;
 
-	return true;
+	return __kfunc_param_match_suffix(btf, arg, "__sz");
+}
+
+static bool is_kfunc_arg_sfx_constant(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__k");
 }
 
 /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */
@@ -7873,10 +7887,29 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_arg_m
 
 		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
 		if (btf_type_is_scalar(t)) {
-			if (reg->type == SCALAR_VALUE)
-				continue;
-			verbose(env, "R%d is not a scalar\n", regno);
-			return -EINVAL;
+			if (reg->type != SCALAR_VALUE) {
+				verbose(env, "R%d is not a scalar\n", regno);
+				return -EINVAL;
+			}
+			if (is_kfunc_arg_sfx_constant(meta->btf, &args[i])) {
+				/* kfunc is already bpf_capable() only, no need
+				 * to check it here.
+				 */
+				if (meta->arg_constant.found) {
+					verbose(env, "verifier internal error: only one constant argument permitted\n");
+					return -EFAULT;
+				}
+				if (!tnum_is_const(reg->var_off)) {
+					verbose(env, "R%d must be a known constant\n", regno);
+					return -EINVAL;
+				}
+				ret = mark_chain_precision(env, regno);
+				if (ret < 0)
+					return ret;
+				meta->arg_constant.found = true;
+				meta->arg_constant.value = reg->var_off.value;
+			}
+			continue;
 		}
 
 		if (!btf_type_is_ptr(t)) {
-- 
2.34.1