bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu maps

include/linux/bpf-cgroup.h

@@ -172,7 +172,8 @@ 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 +468,7 @@ 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,

include/linux/bpf.h

@@ -547,6 +547,56 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src
 	bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static inline void bpf_percpu_copy_to_user(struct bpf_map *map, void __percpu *pptr, void *value,
+					   u32 size, u64 flags)
+{
+	int current_cpu = raw_smp_processor_id();
+	int cpu, off = 0;
+
+	if (flags & BPF_F_CPU) {
+		cpu = flags >> 32;
+		copy_map_value_long(map, value, cpu != current_cpu ? per_cpu_ptr(pptr, cpu) :
+				    this_cpu_ptr(pptr));
+		check_and_init_map_value(map, value);
+	} else {
+		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;
+		}
+	}
+}
+
+void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
+
+static inline void bpf_percpu_copy_from_user(struct bpf_map *map, void __percpu *pptr, void *value,
+					     u32 size, u64 flags)
+{
+	int current_cpu = raw_smp_processor_id();
+	int cpu, off = 0;
+	void *ptr;
+
+	if (flags & BPF_F_CPU) {
+		cpu = flags >> 32;
+		ptr = cpu == current_cpu ? this_cpu_ptr(pptr) : per_cpu_ptr(pptr, cpu);
+		copy_map_value_long(map, ptr, value);
+		bpf_obj_free_fields(map->record, ptr);
+	} else {
+		for_each_possible_cpu(cpu) {
+			copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
+			/* same user-provided value is used if
+			 * BPF_F_ALL_CPUS is specified, otherwise value is
+			 * an array of per-cpu values.
+			 */
+			if (!(flags & BPF_F_ALL_CPUS))
+				off += size;
+			bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu));
+		}
+	}
+}
+#endif
+
 static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src)
 {
 	unsigned long *src_uptr, *dst_uptr;
@@ -2417,7 +2467,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec);
 bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
 void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
 void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
-void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
 void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
 
 struct bpf_map *bpf_map_get(u32 ufd);
@@ -2696,8 +2745,9 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
 				   struct bpf_func_state *caller,
 				   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_hash_copy(struct bpf_map *map, void *key, void *value, u64 flags);
+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,
@@ -3709,4 +3759,74 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
 			   const char **linep, int *nump);
 struct bpf_prog *bpf_prog_find_from_stack(void);
 
+static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type)
+{
+	switch (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;
+	}
+}
+
+static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 extra_flags_mask)
+{
+	if (extra_flags_mask && ((u32)flags & extra_flags_mask))
+		return -EINVAL;
+
+	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+		return -EINVAL;
+
+	if (!(flags & BPF_F_CPU) && flags >> 32)
+		return -EINVAL;
+
+	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) && !bpf_map_supports_cpu_flags(map->map_type))
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline int bpf_map_check_update_flags(struct bpf_map *map, u64 flags)
+{
+	return bpf_map_check_op_flags(map, flags, 0);
+}
+
+#define BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK (~(BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS))
+
+static inline int bpf_map_check_lookup_flags(struct bpf_map *map, u64 flags)
+{
+	return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
+}
+
+static inline int bpf_map_check_batch_flags(struct bpf_map *map, u64 flags)
+{
+	return bpf_map_check_op_flags(map, flags, BPF_MAP_LOOKUP_ELEM_EXTRA_FLAGS_MASK);
+}
+
+static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus_flag)
+{
+	const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
+	u32 cpu;
+
+	if (check_all_cpus_flag) {
+		if (unlikely((u32)flags > BPF_F_ALL_CPUS))
+			/* unknown flags */
+			return -EINVAL;
+		if (unlikely((flags & cpu_flags) == cpu_flags))
+			return -EINVAL;
+	} else {
+		if (unlikely((u32)flags & ~BPF_F_CPU))
+			return -EINVAL;
+	}
+
+	cpu = flags >> 32;
+	if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
+		return -ERANGE;
+
+	return 0;
+}
+
 #endif /* _LINUX_BPF_H */

include/uapi/linux/bpf.h

@@ -1372,6 +1372,8 @@ enum {
 	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
 	BPF_EXIST	= 2, /* update existing element */
 	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+	BPF_F_CPU	= 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+	BPF_F_ALL_CPUS	= 16, /* update value across all CPUs for percpu maps */
 };
 
 /* flags for BPF_MAP_CREATE command */

kernel/bpf/arraymap.c

@@ -295,29 +295,29 @@ 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 flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	u32 index = *(u32 *)key;
 	void __percpu *pptr;
-	int cpu, off = 0;
 	u32 size;
+	int err;
 
 	if (unlikely(index >= array->map.max_entries))
 		return -ENOENT;
 
+	err = bpf_map_check_cpu_flags(flags, false);
+	if (unlikely(err))
+		return err;
+
 	/* per_cpu areas are zero-filled and bpf programs can only
 	 * access 'value_size' of them, so copying rounded areas
 	 * will not leak any kernel data
 	 */
 	size = array->elem_size;
 	rcu_read_lock();
 	pptr = array->pptrs[index & array->index_mask];
-	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;
-	}
+	bpf_percpu_copy_to_user(map, pptr, value, size, flags);
 	rcu_read_unlock();
 	return 0;
 }
@@ -387,12 +387,12 @@ 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;
 	void __percpu *pptr;
-	int cpu, off = 0;
 	u32 size;
+	int err;
 
-	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 +411,7 @@ 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];
-	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;
-	}
+	bpf_percpu_copy_from_user(map, pptr, value, size, map_flags);
 	rcu_read_unlock();
 	return 0;
 }