Introduce support for the BPF_F_ALL_CPUS flag in percpu_array maps to
allow updating values for all CPUs with a single value for both
update_elem and update_batch APIs.
Introduce support for the BPF_F_CPU flag in percpu_array maps to allow:
* update value for specified CPU for both update_elem and update_batch
APIs.
* lookup value for specified CPU for both lookup_elem and lookup_batch
APIs.
The BPF_F_CPU flag is passed via:
* map_flags of lookup_elem and update_elem APIs along with embedded cpu
info.
* elem_flags of lookup_batch and update_batch APIs along with embedded
cpu info.
Signed-off-by: Leon Hwang <leon.hwang@xxxxxxxxx>
---
include/linux/bpf.h | 2 +-
kernel/bpf/arraymap.c | 36 +++++++++++++++++++++++++++++-------
kernel/bpf/syscall.c | 9 +++++++--
3 files changed, 37 insertions(+), 10 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 60c235836987d..b5143420ea947 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2697,7 +2697,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
struct bpf_func_state *callee);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
-int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3d080916faf97..aa5c17c707f1c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -295,14 +295,18 @@ static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key,
return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);
}
-int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
+ int err, cpu, off = 0;
void __percpu *pptr;
- int cpu, off = 0;
u32 size;
+ err = bpf_map_check_cpu_flags(map_flags, false);
+ if (unlikely(err))
+ return err;
+
if (unlikely(index >= array->map.max_entries))
return -ENOENT;
@@ -313,11 +317,18 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
size = array->elem_size;
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value_long(map, value, per_cpu_ptr(pptr, cpu));
+ check_and_init_map_value(map, value);
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
check_and_init_map_value(map, value + off);
off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
@@ -386,13 +397,13 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
+ int err, cpu, off = 0;
void __percpu *pptr;
- int cpu, off = 0;
u32 size;
- if (unlikely(map_flags > BPF_EXIST))
- /* unknown flags */
- return -EINVAL;
+ err = bpf_map_check_cpu_flags(map_flags, true);
+ if (unlikely(err))
+ return err;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
@@ -411,11 +422,22 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
size = array->elem_size;
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
+ if (map_flags & BPF_F_CPU) {
+ cpu = map_flags >> 32;
+ copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value);
+ bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
+ goto unlock;
+ }
for_each_possible_cpu(cpu) {
copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
- off += size;
+ /* same user-provided value is used if BPF_F_ALL_CPUS is
+ * specified, otherwise value is an array of per-CPU values.
+ */
+ if (!(map_flags & BPF_F_ALL_CPUS))
+ off += size;
}
+unlock:
rcu_read_unlock();
return 0;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index db841b38f0c22..6d0a08d63f175 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,7 +133,12 @@ bool bpf_map_write_active(const struct bpf_map *map)
static bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
{
- return false;
+ switch (map_type) {
+ case BPF_MAP_TYPE_PERCPU_ARRAY:
+ return true;
+ default:
+ return false;
+ }
}
static int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
@@ -338,7 +343,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
- err = bpf_percpu_array_copy(map, key, value);
+ 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);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
--
2.50.1
