[PATCH bpf] bpf: Keep refcount_acquire nullable for borrowed RCU kptrs

[PATCH bpf] bpf: Keep refcount_acquire nullable for borrowed RCU kptrs

[Ning Ding]

bpf_refcount_acquire() can fail for a refcounted map kptr loaded
within RCU. Another execution can replace the map kptr and drop the
last owning reference after the pointer is loaded but before the
acquire, causing refcount_inc_not_zero() to fail.

check_kfunc_args() currently treats a refcounted pointer as owning
whenever it is not explicitly marked NON_OWN_REF. But an RCU-loaded
map kptr can lack NON_OWN_REF while still being borrowed and absent
from the verifier state's acquired-reference tracking. This sets
arg_owning_ref and causes is_kfunc_ret_null() to suppress KF_RET_NULL,
allowing an unchecked NULL return from bpf_refcount_acquire() to be
passed to bpf_obj_drop().

Require reg_is_referenced() before treating the input as owning. Add
tests for a genuine owning input, a checked borrowed RCU input, and
an unchecked borrowed RCU input.

Fixes: 7793fc3babe9 ("bpf: Make bpf_refcount_acquire fallible for non-owning refs")
Assisted-by: Codex:gpt-5.5
Assisted-by: ChatGPT:GPT-5.6-Thinking
Signed-off-by: Ning Ding <dingning04@gmail.com>
---
 kernel/bpf/verifier.c                         |  2 +-
 .../selftests/bpf/progs/refcounted_kptr.c     | 61 +++++++++++++++++++
 .../bpf/progs/refcounted_kptr_fail.c          | 47 ++++++++++++++
 3 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7aa47342dc65..1e7343b625de 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12419,7 +12419,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 					reg_arg_name(env, argno));
 				return -EINVAL;
 			}
-			if (!type_is_non_owning_ref(reg->type))
+			if (!type_is_non_owning_ref(reg->type) && reg_is_referenced(env, reg))
 				meta->arg_owning_ref = true;
 
 			rec = reg_btf_record(reg);
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
index 61906f48025c..fd35093285c0 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
@@ -23,6 +23,15 @@ struct map_value {
 	struct node_data __kptr *node;
 };
 
+struct node_refcount_only {
+	long key;
+	struct bpf_refcount refcount;
+};
+
+struct map_value_refcount_only {
+	struct node_refcount_only __kptr *node;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, int);
@@ -30,6 +39,13 @@ struct {
 	__uint(max_entries, 2);
 } stashed_nodes SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value_refcount_only);
+	__uint(max_entries, 1);
+} stashed_refcount_only SEC(".maps");
+
 struct node_acquire {
 	long key;
 	long data;
@@ -832,6 +848,51 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 	return 0;
 }
 
+SEC("tc")
+__success
+long refcount_acquire_owning_input_no_null_check(void *ctx)
+{
+	struct node_refcount_only *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	m = bpf_refcount_acquire(n);
+	bpf_obj_drop(m);
+	bpf_obj_drop(n);
+
+	return 0;
+}
+
+SEC("tc")
+__success
+long refcount_acquire_rcu_map_kptr_null_checked(void *ctx)
+{
+	struct map_value_refcount_only *mapval;
+	struct node_refcount_only *n, *m;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	n = mapval->node;
+	if (!n) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	m = bpf_refcount_acquire(n);
+	bpf_rcu_read_unlock();
+
+	if (!m)
+		return 3;
+	bpf_obj_drop(m);
+
+	return 0;
+}
+
 static long __stash_map_empty_xchg(struct node_data *n, int idx)
 {
 	struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index 024ef2aae200..acd3e81a3916 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -19,6 +19,15 @@ struct node_refcounted {
 	struct bpf_refcount refcount;
 };
 
+struct node_refcount_only {
+	long key;
+	struct bpf_refcount refcount;
+};
+
+struct map_value_refcount_only {
+	struct node_refcount_only __kptr *node;
+};
+
 extern void bpf_rcu_read_lock(void) __ksym;
 extern void bpf_rcu_read_unlock(void) __ksym;
 
@@ -28,6 +37,13 @@ private(A) struct bpf_rb_root groot __contains(node_acquire, node);
 private(B) struct bpf_spin_lock lock;
 private(B) struct bpf_list_head head __contains(node_refcounted, list);
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value_refcount_only);
+	__uint(max_entries, 1);
+} stashed_refcount_only SEC(".maps");
+
 static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 {
 	struct node_acquire *node_a;
@@ -80,6 +96,37 @@ long refcount_acquire_maybe_null(void *ctx)
 	return 0;
 }
 
+SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted R1")
+long refcount_acquire_rcu_map_kptr_unchecked_drop(void *ctx)
+{
+	struct map_value_refcount_only *mapval;
+	struct node_refcount_only *tmp, *n, *m;
+	int idx = 0;
+
+	tmp = bpf_obj_new(typeof(*tmp));
+	if (!tmp)
+		return 3;
+	bpf_obj_drop(tmp);
+
+	mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	n = mapval->node;
+	if (!n) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	m = bpf_refcount_acquire(n);
+	bpf_rcu_read_unlock();
+
+	bpf_obj_drop(m);
+
+	return 0;
+}
+
 SEC("?tc")
 __failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
 long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)

base-commit: 0ce37745d4bfbc493f718169c3974898ffec8ee7
-- 
2.43.0

Re: [PATCH bpf] bpf: Keep refcount_acquire nullable for borrowed RCU kptrs

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [Critical] bpf_refcount_acquire() permits untrusted pointers due to inadequate modifier checks, leading to Use-After-Free.
--

--- Patch [1]: [PATCH bpf] bpf: Keep refcount_acquire nullable for borrowed RCU kptrs ---
commit 5798e6cddf6ec01af2fa26e9f86dfc1bb3fd1681
Author: Ning Ding <dingning04@gmail.com>

bpf: Keep refcount_acquire nullable for borrowed RCU kptrs
    
bpf_refcount_acquire() can fail for a refcounted map kptr loaded
within RCU. Another execution can replace the map kptr and drop the
last owning reference after the pointer is loaded but before the
acquire, causing refcount_inc_not_zero() to fail.

> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 7aa47342dc659..1e7343b625de5 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -12419,7 +12419,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
>  					reg_arg_name(env, argno));
>  				return -EINVAL;
>  			}

[Severity: Critical]
This is a pre-existing issue, but does bpf_refcount_acquire() permit untrusted
pointers due to inadequate modifier checks, potentially leading to a
use-after-free?

In check_kfunc_args(), KF_ARG_PTR_TO_REFCOUNTED_KPTR skips the is_trusted_reg()
checks that are applied to other pointer types. The argument is subsequently
validated using type_is_ptr_alloc_obj():

include/linux/bpf_verifier.h:type_is_ptr_alloc_obj() {
    return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
}

Since type_is_ptr_alloc_obj() only requires MEM_ALLOC to be set and does not
restrict unsafe modifiers, it returns true for a pointer with the PTR_UNTRUSTED
flag.

If a BPF program loads a refcounted pointer from a map inside an RCU read-side
critical section, checks it for NULL, and then drops the RCU lock using
bpf_rcu_read_unlock(), the pointer's verifier type is updated to include the
PTR_UNTRUSTED flag.

The program can then pass this untrusted pointer to bpf_refcount_acquire(),
which bypasses trusted register checks and accepts it. At runtime, the
bpf_refcount_acquire_impl kfunc executes refcount_inc_not_zero() on the
provided untrusted address.

Since the address might have already been freed outside the RCU critical
section, could this result in memory corruption or a kernel panic? While this
patch sets meta->arg_owning_ref = false for untrusted inputs, does it fail to
prevent the unsafe input pointer from being dereferenced inside the kfunc
itself?

> -			if (!type_is_non_owning_ref(reg->type))
> +			if (!type_is_non_owning_ref(reg->type) && reg_is_referenced(env, reg))
>  				meta->arg_owning_ref = true;
>  
>  			rec = reg_btf_record(reg);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260726015330.705259-1-dingning04@gmail.com?part=1

[PATCH bpf] bpf: Reject writes through untrusted allocated pointers

[Ning Ding]

A kptr loaded under an RCU read lock has MEM_ALLOC set. After
bpf_rcu_read_unlock(), the verifier marks it PTR_UNTRUSTED, but
check_ptr_to_btf_access() still allows writes because
type_is_ptr_alloc_obj() ignores that flag.

Reject writes through MEM_ALLOC pointers that are PTR_UNTRUSTED. Reads
remain allowed and are converted to probe-memory accesses.

Also skip the owning-reference check for these pointers, since they no
longer have a live reference after leaving the RCU critical section.

Add verifier tests for the rejected write and permitted read cases.

Fixes: 503e4def5414 ("bpf: Replace open code with for allocated object check")
Closes: https://lore.kernel.org/all/20260726021304.97ED91F000E9@smtp.kernel.org/
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Ning Ding <dingning04@gmail.com>
---
 kernel/bpf/verifier.c                         |  6 +-
 .../bpf/progs/local_kptr_stash_fail.c         | 58 +++++++++++++++++++
 2 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7aa47342dc65..24c151ad2e62 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5804,13 +5804,15 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 		 * program allocated objects (which always have id > 0),
 		 * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC.
 		 */
-		if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) {
+		if (atype != BPF_READ &&
+		    (!type_is_ptr_alloc_obj(reg->type) || reg->type & PTR_UNTRUSTED)) {
 			verbose(env, "only read is supported\n");
 			return -EACCES;
 		}
 
 		if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) &&
-		    !(reg->type & MEM_RCU) && !reg_is_referenced(env, reg)) {
+		    !(reg->type & (MEM_RCU | PTR_UNTRUSTED)) &&
+		    !reg_is_referenced(env, reg)) {
 			verifier_bug(env, "allocated object must have a referenced id");
 			return -EFAULT;
 		}
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
index fcf7a7567da2..d7b8cd6458bb 100644
--- a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
@@ -8,14 +8,22 @@
 #include "../bpf_experimental.h"
 #include "bpf_misc.h"
 
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
 struct node_data {
 	long key;
 	long data;
 	struct bpf_rb_node node;
 };
 
+struct plain_data {
+	long key;
+};
+
 struct map_value {
 	struct node_data __kptr *node;
+	struct plain_data __kptr *plain;
 };
 
 struct node_data2 {
@@ -31,6 +39,7 @@ struct node_data2 {
  * [35] TYPE_TAG 'kptr_ref' type_id=34
  */
 struct node_data *just_here_because_btf_bug;
+struct plain_data *just_here_because_btf_bug2;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -82,4 +91,53 @@ long drop_rb_node_off(void *ctx)
 	return 0;
 }
 
+SEC("?tc")
+__failure __msg("only read is supported")
+long write_untrusted_alloc_obj(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	res = mapval->node;
+	if (!res) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	barrier_var(res);
+	bpf_rcu_read_unlock();
+
+	res->key = 42;
+	return 0;
+}
+
+SEC("?tc")
+__success
+long read_untrusted_alloc_obj(void *ctx)
+{
+	struct map_value *mapval;
+	struct plain_data *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	res = mapval->plain;
+	if (!res) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	barrier_var(res);
+	bpf_rcu_read_unlock();
+
+	return res->key;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
2.43.0