summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2018-09-28 17:45:43 +0300
committerDaniel Borkmann <daniel@iogearbox.net>2018-10-01 17:18:32 +0300
commitb741f1630346defcbc8cc60f1a2bdae8b3b0036f (patch)
treec5698184b5398cea8e288276844232d0101b64da /kernel
parentf294b37ec7b24a574884cd157497a3748081c0f0 (diff)
downloadlinux-b741f1630346defcbc8cc60f1a2bdae8b3b0036f.tar.xz
bpf: introduce per-cpu cgroup local storage
This commit introduced per-cpu cgroup local storage. Per-cpu cgroup local storage is very similar to simple cgroup storage (let's call it shared), except all the data is per-cpu. The main goal of per-cpu variant is to implement super fast counters (e.g. packet counters), which don't require neither lookups, neither atomic operations. >From userspace's point of view, accessing a per-cpu cgroup storage is similar to other per-cpu map types (e.g. per-cpu hashmaps and arrays). Writing to a per-cpu cgroup storage is not atomic, but is performed by copying longs, so some minimal atomicity is here, exactly as with other per-cpu maps. Signed-off-by: Roman Gushchin <guro@fb.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/helpers.c8
-rw-r--r--kernel/bpf/local_storage.c150
-rw-r--r--kernel/bpf/syscall.c11
-rw-r--r--kernel/bpf/verifier.c15
4 files changed, 157 insertions, 27 deletions
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e42f8789b7ea..6502115e8f55 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -206,10 +206,16 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
*/
enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
struct bpf_cgroup_storage *storage;
+ void *ptr;
storage = this_cpu_read(bpf_cgroup_storage[stype]);
- return (unsigned long)&READ_ONCE(storage->buf)->data[0];
+ if (stype == BPF_CGROUP_STORAGE_SHARED)
+ ptr = &READ_ONCE(storage->buf)->data[0];
+ else
+ ptr = this_cpu_ptr(storage->percpu_buf);
+
+ return (unsigned long)ptr;
}
const struct bpf_func_proto bpf_get_local_storage_proto = {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 6742292fb39e..944eb297465f 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -152,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return 0;
}
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
+ void *value)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ int cpu, off = 0;
+ u32 size;
+
+ rcu_read_lock();
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
+
+ /* 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 = round_up(_map->value_size, 8);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off,
+ per_cpu_ptr(storage->percpu_buf, cpu), size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
+ void *value, u64 map_flags)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ int cpu, off = 0;
+ u32 size;
+
+ if (map_flags != BPF_ANY && map_flags != BPF_EXIST)
+ return -EINVAL;
+
+ rcu_read_lock();
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
+
+ /* the user space will provide round_up(value_size, 8) bytes that
+ * will be copied into per-cpu area. bpf programs can only access
+ * value_size of it. During lookup the same extra bytes will be
+ * returned or zeros which were zero-filled by percpu_alloc,
+ * so no kernel data leaks possible
+ */
+ size = round_up(_map->value_size, 8);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
+ value + off, size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
void *_next_key)
{
@@ -287,60 +352,105 @@ void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
spin_unlock_bh(&map->lock);
}
+static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages)
+{
+ size_t size;
+
+ if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) {
+ size = sizeof(struct bpf_storage_buffer) + map->value_size;
+ *pages = round_up(sizeof(struct bpf_cgroup_storage) + size,
+ PAGE_SIZE) >> PAGE_SHIFT;
+ } else {
+ size = map->value_size;
+ *pages = round_up(round_up(size, 8) * num_possible_cpus(),
+ PAGE_SIZE) >> PAGE_SHIFT;
+ }
+
+ return size;
+}
+
struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
enum bpf_cgroup_storage_type stype)
{
struct bpf_cgroup_storage *storage;
struct bpf_map *map;
+ gfp_t flags;
+ size_t size;
u32 pages;
map = prog->aux->cgroup_storage[stype];
if (!map)
return NULL;
- pages = round_up(sizeof(struct bpf_cgroup_storage) +
- sizeof(struct bpf_storage_buffer) +
- map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ size = bpf_cgroup_storage_calculate_size(map, &pages);
+
if (bpf_map_charge_memlock(map, pages))
return ERR_PTR(-EPERM);
storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
__GFP_ZERO | GFP_USER, map->numa_node);
- if (!storage) {
- bpf_map_uncharge_memlock(map, pages);
- return ERR_PTR(-ENOMEM);
- }
+ if (!storage)
+ goto enomem;
- storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size, __GFP_ZERO | GFP_USER,
- map->numa_node);
- if (!storage->buf) {
- bpf_map_uncharge_memlock(map, pages);
- kfree(storage);
- return ERR_PTR(-ENOMEM);
+ flags = __GFP_ZERO | GFP_USER;
+
+ if (stype == BPF_CGROUP_STORAGE_SHARED) {
+ storage->buf = kmalloc_node(size, flags, map->numa_node);
+ if (!storage->buf)
+ goto enomem;
+ } else {
+ storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
+ if (!storage->percpu_buf)
+ goto enomem;
}
storage->map = (struct bpf_cgroup_storage_map *)map;
return storage;
+
+enomem:
+ bpf_map_uncharge_memlock(map, pages);
+ kfree(storage);
+ return ERR_PTR(-ENOMEM);
+}
+
+static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu)
+{
+ struct bpf_cgroup_storage *storage =
+ container_of(rcu, struct bpf_cgroup_storage, rcu);
+
+ kfree(storage->buf);
+ kfree(storage);
+}
+
+static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu)
+{
+ struct bpf_cgroup_storage *storage =
+ container_of(rcu, struct bpf_cgroup_storage, rcu);
+
+ free_percpu(storage->percpu_buf);
+ kfree(storage);
}
void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
{
- u32 pages;
+ enum bpf_cgroup_storage_type stype;
struct bpf_map *map;
+ u32 pages;
if (!storage)
return;
map = &storage->map->map;
- pages = round_up(sizeof(struct bpf_cgroup_storage) +
- sizeof(struct bpf_storage_buffer) +
- map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+
+ bpf_cgroup_storage_calculate_size(map, &pages);
bpf_map_uncharge_memlock(map, pages);
- kfree_rcu(storage->buf, rcu);
- kfree_rcu(storage, rcu);
+ stype = cgroup_storage_type(map);
+ if (stype == BPF_CGROUP_STORAGE_SHARED)
+ call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu);
+ else
+ call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu);
}
void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8c91d2b41b1e..5742df21598c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
value_size = sizeof(u32);
@@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr)
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);
+ } 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) {
err = bpf_stackmap_copy(map, key, value);
} else if (IS_FD_ARRAY(map)) {
@@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
value_size = map->value_size;
@@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_percpu_hash_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_update(map, key, value,
+ attr->flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e90899df585d..a8cc83a970d1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2074,6 +2074,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
goto error;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
if (func_id != BPF_FUNC_get_local_storage)
goto error;
break;
@@ -2164,7 +2165,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
goto error;
break;
case BPF_FUNC_get_local_storage:
- if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
goto error;
break;
case BPF_FUNC_sk_select_reuseport:
@@ -5049,6 +5051,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
return 0;
}
+static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
+{
+ return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+}
+
/* look for pseudo eBPF instructions that access map FDs and
* replace them with actual map pointers
*/
@@ -5139,10 +5147,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
}
env->used_maps[env->used_map_cnt++] = map;
- if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+ if (bpf_map_is_cgroup_storage(map) &&
bpf_cgroup_storage_assign(env->prog, map)) {
- verbose(env,
- "only one cgroup storage is allowed\n");
+ verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
}