Introduce BPF_F_ALL_CPUS flag support for percpu_cgroup_storage maps to
allow updating values for all CPUs with a single value for update_elem
API.
Introduce BPF_F_CPU flag support for percpu_cgroup_storage maps to
allow:
* update value for specified CPU for update_elem API.
* lookup value for specified CPU for lookup_elem API.
The BPF_F_CPU flag is passed via map_flags along with embedded cpu info.
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
include/linux/bpf-cgroup.h | 4 ++--
include/linux/bpf.h | 1 +
kernel/bpf/local_storage.c | 23 ++++++++++++++++++-----
kernel/bpf/syscall.c | 2 +-
4 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index aedf573bdb42..013f4db9903f 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -172,7 +172,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map);
-int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value, u64 flags);
int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
void *value, u64 flags);
@@ -467,7 +467,7 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
static inline void bpf_cgroup_storage_free(
struct bpf_cgroup_storage *storage) {}
static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key,
- void *value) {
+ void *value, u64 flags) {
return 0;
}
static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f79d2ae27335..9e756db5e132 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3835,6 +3835,7 @@ static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
case BPF_MAP_TYPE_PERCPU_ARRAY:
case BPF_MAP_TYPE_PERCPU_HASH:
case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
return true;
default:
return false;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 2ab4b60ffe61..1ccbf28b2ad9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -180,7 +180,7 @@ static long cgroup_storage_update_elem(struct bpf_map *map, void *key,
}
int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
- void *value)
+ void *value, u64 map_flags)
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage *storage;
@@ -198,11 +198,17 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
* access 'value_size' of them, so copying rounded areas
* will not leak any kernel data
*/
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(_map, value, per_cpu_ptr(storage->percpu_buf, cpu));
+ goto unlock;
+ }
size = round_up(_map->value_size, 8);
for_each_possible_cpu(cpu) {
copy_map_value_long(_map, value + off, per_cpu_ptr(storage->percpu_buf, cpu));
off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
@@ -212,10 +218,11 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage *storage;
- int cpu, off = 0;
+ void *val;
u32 size;
+ int cpu;
- if (map_flags != BPF_ANY && map_flags != BPF_EXIST)
+ if ((u32)map_flags & ~(BPF_ANY | BPF_EXIST | BPF_F_CPU | BPF_F_ALL_CPUS))
return -EINVAL;
rcu_read_lock();
@@ -231,11 +238,17 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
* returned or zeros which were zero-filled by percpu_alloc,
* so no kernel data leaks possible
*/
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), value);
+ goto unlock;
+ }
size = round_up(_map->value_size, 8);
for_each_possible_cpu(cpu) {
- copy_map_value_long(_map, per_cpu_ptr(storage->percpu_buf, cpu), value + off);
- off += size;
+ val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu;
+ copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), val);
}
+unlock:
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 94ac63b1115f..d8c2336124b6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -320,7 +320,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_copy(map, key, value);
+ err = bpf_percpu_cgroup_storage_copy(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_extract(map, key, value, false);
} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
--
2.51.2> diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
> index aedf573bd..013f4db99 100644
> --- a/include/linux/bpf-cgroup.h
> +++ b/include/linux/bpf-cgroup.h
[ ... ]
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index f79d2ae27..9e756db5e 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
[ ... ]
> diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
> index 2ab4b60ff..1ccbf28b2 100644
> --- a/kernel/bpf/local_storage.c
> +++ b/kernel/bpf/local_storage.c
> @@ -180,7 +180,7 @@ static long cgroup_storage_update_elem(struct bpf_map *map, void *key,
> }
>
> int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
> - void *value)
> + void *value, u64 map_flags)
> {
> struct bpf_cgroup_storage_map *map = map_to_storage(_map);
> struct bpf_cgroup_storage *storage;
> @@ -198,11 +198,17 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
> * access 'value_size' of them, so copying rounded areas
> * will not leak any kernel data
> */
> + if (map_flags & BPF_F_CPU) {
> + cpu = map_flags >> 32;
> + copy_map_value(_map, value, per_cpu_ptr(storage->percpu_buf, cpu));
> + goto unlock;
> + }
Should check_and_init_map_value() be called here after copy_map_value()?
The similar implementations in bpf_percpu_array_copy() and
bpf_percpu_hash_copy() both call check_and_init_map_value() after
copying a single CPU's value when BPF_F_CPU is set:
bpf_percpu_array_copy():
if (map_flags & BPF_F_CPU) {
cpu = map_flags >> 32;
copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
check_and_init_map_value(map, value);
goto unlock;
}
bpf_percpu_hash_copy():
if (map_flags & BPF_F_CPU) {
cpu = map_flags >> 32;
copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
check_and_init_map_value(map, value);
goto out;
}
The check_and_init_map_value() call initializes special BTF fields
(timers, kptrs, etc.) when copying map values to userspace. Without it,
these fields might not be properly initialized if percpu_cgroup_storage
map values contain such fields.
> size = round_up(_map->value_size, 8);
> for_each_possible_cpu(cpu) {
> copy_map_value_long(_map, value + off, per_cpu_ptr(storage->percpu_buf, cpu));
> off += size;
> }
> +unlock:
> rcu_read_unlock();
> return 0;
> }
[ ... ]
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/19708012130
On 2025/11/26 23:11, bot+bpf-ci@kernel.org wrote:
>> diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
>> index aedf573bd..013f4db99 100644
>> --- a/include/linux/bpf-cgroup.h
>> +++ b/include/linux/bpf-cgroup.h
>
> [ ... ]
>
>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>> index f79d2ae27..9e756db5e 100644
>> --- a/include/linux/bpf.h
>> +++ b/include/linux/bpf.h
>
> [ ... ]
>
>> diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
>> index 2ab4b60ff..1ccbf28b2 100644
>> --- a/kernel/bpf/local_storage.c
>> +++ b/kernel/bpf/local_storage.c
>> @@ -180,7 +180,7 @@ static long cgroup_storage_update_elem(struct bpf_map *map, void *key,
>> }
>>
>> int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
>> - void *value)
>> + void *value, u64 map_flags)
>> {
>> struct bpf_cgroup_storage_map *map = map_to_storage(_map);
>> struct bpf_cgroup_storage *storage;
>> @@ -198,11 +198,17 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
>> * access 'value_size' of them, so copying rounded areas
>> * will not leak any kernel data
>> */
>> + if (map_flags & BPF_F_CPU) {
>> + cpu = map_flags >> 32;
>> + copy_map_value(_map, value, per_cpu_ptr(storage->percpu_buf, cpu));
>> + goto unlock;
>> + }
>
> Should check_and_init_map_value() be called here after copy_map_value()?
>
It should not be called, because percpu_cgroup_storage maps do not
support any special fields.
Thanks,
Leon
> The similar implementations in bpf_percpu_array_copy() and
> bpf_percpu_hash_copy() both call check_and_init_map_value() after
> copying a single CPU's value when BPF_F_CPU is set:
>
> bpf_percpu_array_copy():
> if (map_flags & BPF_F_CPU) {
> cpu = map_flags >> 32;
> copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
> check_and_init_map_value(map, value);
> goto unlock;
> }
>
> bpf_percpu_hash_copy():
> if (map_flags & BPF_F_CPU) {
> cpu = map_flags >> 32;
> copy_map_value(map, value, per_cpu_ptr(pptr, cpu));
> check_and_init_map_value(map, value);
> goto out;
> }
>
> The check_and_init_map_value() call initializes special BTF fields
> (timers, kptrs, etc.) when copying map values to userspace. Without it,> these fields might not be properly initialized if percpu_cgroup_storage
> map values contain such fields.
>
>> size = round_up(_map->value_size, 8);
>> for_each_possible_cpu(cpu) {
>> copy_map_value_long(_map, value + off, per_cpu_ptr(storage->percpu_buf, cpu));
>> off += size;
>> }
>> +unlock:
>> rcu_read_unlock();
>> return 0;
>> }
>
> [ ... ]
>
>
> ---
> AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
> See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
>
> CI run summary: https://github.com/kernel-patches/bpf/actions/runs/19708012130
© 2016 - 2025 Red Hat, Inc.