From df023216c3f1f9a3384edeee46a73ae3f45b0f47 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Wed, 5 Nov 2025 23:14:06 +0800 Subject: [PATCH 1/2] bpf: Free special fields when update [lru_,]percpu_hash maps As [lru_,]percpu_hash maps support BPF_KPTR_{REF,PERCPU}, missing calls to 'bpf_obj_free_fields()' in 'pcpu_copy_value()' could cause the memory referenced by BPF_KPTR_{REF,PERCPU} fields to be held until the map gets freed. Fix this by calling 'bpf_obj_free_fields()' after 'copy_map_value[,_long]()' in 'pcpu_copy_value()'. Fixes: 65334e64a493 ("bpf: Support kptrs in percpu hashmap and percpu LRU hashmap") Signed-off-by: Leon Hwang Acked-by: Yonghong Song --- kernel/bpf/hashtab.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index f876f09355f0d..c8a9b27f8663b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -934,15 +934,21 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, void *value, bool onallcpus) { + void *ptr; + if (!onallcpus) { /* copy true value_size bytes */ - copy_map_value(&htab->map, this_cpu_ptr(pptr), value); + ptr = this_cpu_ptr(pptr); + copy_map_value(&htab->map, ptr, value); + bpf_obj_free_fields(htab->map.record, ptr); } else { u32 size = round_up(htab->map.value_size, 8); int off = 0, cpu; for_each_possible_cpu(cpu) { - copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off); + ptr = per_cpu_ptr(pptr, cpu); + copy_map_value_long(&htab->map, ptr, value + off); + bpf_obj_free_fields(htab->map.record, ptr); off += size; } } From 6a3651e876e2bcf9642b675bc85f89bed26a7be9 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Wed, 5 Nov 2025 23:14:07 +0800 Subject: [PATCH 2/2] selftests/bpf: Add test to verify freeing the special fields when update [lru_,]percpu_hash maps Add test to verify that updating [lru_,]percpu_hash maps decrements refcount when BPF_KPTR_REF objects are involved. The tests perform the following steps: 1. Call update_elem() to insert an initial value. 2. Use bpf_refcount_acquire() to increment the refcount. 3. Store the node pointer in the map value. 4. Add the node to a linked list. 5. Probe-read the refcount and verify it is *2*. 6. Call update_elem() again to trigger refcount decrement. 7. Probe-read the refcount and verify it is *1*. Signed-off-by: Leon Hwang Acked-by: Yonghong Song --- .../bpf/prog_tests/refcounted_kptr.c | 57 ++++++++++++++++++ .../selftests/bpf/progs/refcounted_kptr.c | 60 +++++++++++++++++++ 2 files changed, 117 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c index d6bd5e16e6372..086f679fa3f61 100644 --- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c @@ -44,3 +44,60 @@ void test_refcounted_kptr_wrong_owner(void) ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval"); refcounted_kptr__destroy(skel); } + +void test_percpu_hash_refcounted_kptr_refcount_leak(void) +{ + struct refcounted_kptr *skel; + int cpu_nr, fd, err, key = 0; + struct bpf_map *map; + size_t values_sz; + u64 *values; + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + + cpu_nr = libbpf_num_possible_cpus(); + if (!ASSERT_GT(cpu_nr, 0, "libbpf_num_possible_cpus")) + return; + + values = calloc(cpu_nr, sizeof(u64)); + if (!ASSERT_OK_PTR(values, "calloc values")) + return; + + skel = refcounted_kptr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load")) { + free(values); + return; + } + + values_sz = cpu_nr * sizeof(u64); + memset(values, 0, values_sz); + + map = skel->maps.percpu_hash; + err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0); + if (!ASSERT_OK(err, "bpf_map__update_elem")) + goto out; + + fd = bpf_program__fd(skel->progs.percpu_hash_refcount_leak); + err = bpf_prog_test_run_opts(fd, &opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + goto out; + if (!ASSERT_EQ(opts.retval, 2, "opts.retval")) + goto out; + + err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0); + if (!ASSERT_OK(err, "bpf_map__update_elem")) + goto out; + + fd = bpf_program__fd(skel->progs.check_percpu_hash_refcount); + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + ASSERT_EQ(opts.retval, 1, "opts.retval"); + +out: + refcounted_kptr__destroy(skel); + free(values); +} + diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index 893a4fdb4b6e9..1aca85d86aebc 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -568,4 +568,64 @@ int BPF_PROG(rbtree_sleepable_rcu_no_explicit_rcu_lock, return 0; } +private(kptr_ref) u64 ref; + +static int probe_read_refcount(void) +{ + u32 refcount; + + bpf_probe_read_kernel(&refcount, sizeof(refcount), (void *) ref); + return refcount; +} + +static int __insert_in_list(struct bpf_list_head *head, struct bpf_spin_lock *lock, + struct node_data __kptr **node) +{ + struct node_data *node_new, *node_ref, *node_old; + + node_new = bpf_obj_new(typeof(*node_new)); + if (!node_new) + return -1; + + node_ref = bpf_refcount_acquire(node_new); + node_old = bpf_kptr_xchg(node, node_new); + if (node_old) { + bpf_obj_drop(node_old); + bpf_obj_drop(node_ref); + return -2; + } + + bpf_spin_lock(lock); + bpf_list_push_front(head, &node_ref->l); + ref = (u64)(void *) &node_ref->ref; + bpf_spin_unlock(lock); + return probe_read_refcount(); +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} percpu_hash SEC(".maps"); + +SEC("tc") +int percpu_hash_refcount_leak(void *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&percpu_hash, &key); + if (!v) + return 0; + + return __insert_in_list(&head, &lock, &v->node); +} + +SEC("tc") +int check_percpu_hash_refcount(void *ctx) +{ + return probe_read_refcount(); +} + char _license[] SEC("license") = "GPL";