Skip to content

L
linux
Commit 15c14a3d authored by Brian Vazquez's avatar Brian Vazquez Committed by Alexei Starovoitov
Browse files
Options

bpf: Add bpf_map_{value_size, update_value, map_copy_value} functions 

This commit moves reusable code from map_lookup_elem and map_update_elem
to avoid code duplication in kernel/bpf/syscall.c.
Signed-off-by: default avatarBrian Vazquez <brianvv@google.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Acked-by: default avatarYonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200115184308.162644-2-brianvv@google.com
parent 83e4b88b
Show whitespace changes
Inline Side-by-side
Showing with 152 additions and 128 deletions
kernel/bpf/syscall.c
View file @ 15c14a3d
......@@ -129,6 +129,154 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
static u32 bpf_map_value_size(struct bpf_map *map)
{
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_CGROUP_STORAGE)
return round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
return sizeof(u32);
else
return map->value_size;
}
static void maybe_wait_bpf_programs(struct bpf_map *map)
{
/* Wait for any running BPF programs to complete so that
* userspace, when we return to it, knows that all programs
* that could be running use the new map value.
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
synchronize_rcu();
}
static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
void *value, __u64 flags)
{
int err;
/* Need to create a kthread, thus must support schedule */
if (bpf_map_is_dev_bound(map)) {
return bpf_map_offload_update_elem(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
map->map_type == BPF_MAP_TYPE_SOCKHASH ||
map->map_type == BPF_MAP_TYPE_SOCKMAP ||
map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
return map->ops->map_update_elem(map, key, value, flags);
} else if (IS_FD_PROG_ARRAY(map)) {
return bpf_fd_array_map_update_elem(map, f.file, key, value,
flags);
}
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
preempt_disable();
__this_cpu_inc(bpf_prog_active);
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_update(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_update(map, key, value,
flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
/* rcu_read_lock() is not needed */
err = bpf_fd_reuseport_array_update_elem(map, key, value,
flags);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_push_elem(map, value, flags);
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, flags);
rcu_read_unlock();
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
maybe_wait_bpf_programs(map);
return err;
}
static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
__u64 flags)
{
void *ptr;
int err;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_lookup_elem(map, key, value);
return err;
}
preempt_disable();
this_cpu_inc(bpf_prog_active);
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
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);
} 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) || IS_FD_PROG_ARRAY(map)) {
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
err = bpf_fd_htab_map_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_peek_elem(map, value);
} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
/* struct_ops map requires directly updating "value" */
err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
} else {
rcu_read_lock();
if (map->ops->map_lookup_elem_sys_only)
ptr = map->ops->map_lookup_elem_sys_only(map, key);
else
ptr = map->ops->map_lookup_elem(map, key);
if (IS_ERR(ptr)) {
err = PTR_ERR(ptr);
} else if (!ptr) {
err = -ENOENT;
} else {
err = 0;
if (flags & BPF_F_LOCK)
/* lock 'ptr' and copy everything but lock */
copy_map_value_locked(map, value, ptr, true);
else
copy_map_value(map, value, ptr);
/* mask lock, since value wasn't zero inited */
check_and_init_map_lock(map, value);
}
rcu_read_unlock();
}
this_cpu_dec(bpf_prog_active);
preempt_enable();
maybe_wait_bpf_programs(map);
return err;
}
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
{
/* We really just want to fail instead of triggering OOM killer
......@@ -827,7 +975,7 @@ static int map_lookup_elem(union bpf_attr *attr)
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
void *key, *value;
u32 value_size;
struct fd f;
int err;
......@@ -859,75 +1007,14 @@ static int map_lookup_elem(union bpf_attr *attr)
goto err_put;
}
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_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
value_size = sizeof(u32);
else
value_size = map->value_size;
value_size = bpf_map_value_size(map);
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_lookup_elem(map, key, value);
goto done;
}
preempt_disable();
this_cpu_inc(bpf_prog_active);
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
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);
} 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) || IS_FD_PROG_ARRAY(map)) {
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
err = bpf_fd_htab_map_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_peek_elem(map, value);
} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
/* struct_ops map requires directly updating "value" */
err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
} else {
rcu_read_lock();
if (map->ops->map_lookup_elem_sys_only)
ptr = map->ops->map_lookup_elem_sys_only(map, key);
else
ptr = map->ops->map_lookup_elem(map, key);
if (IS_ERR(ptr)) {
err = PTR_ERR(ptr);
} else if (!ptr) {
err = -ENOENT;
} else {
err = 0;
if (attr->flags & BPF_F_LOCK)
/* lock 'ptr' and copy everything but lock */
copy_map_value_locked(map, value, ptr, true);
else
copy_map_value(map, value, ptr);
/* mask lock, since value wasn't zero inited */
check_and_init_map_lock(map, value);
}
rcu_read_unlock();
}
this_cpu_dec(bpf_prog_active);
preempt_enable();
done:
err = bpf_map_copy_value(map, key, value, attr->flags);
if (err)
goto free_value;
......@@ -946,16 +1033,6 @@ static int map_lookup_elem(union bpf_attr *attr)
return err;
}
static void maybe_wait_bpf_programs(struct bpf_map *map)
{
/* Wait for any running BPF programs to complete so that
* userspace, when we return to it, knows that all programs
* that could be running use the new map value.
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
synchronize_rcu();
}
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
......@@ -1011,61 +1088,8 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
/* Need to create a kthread, thus must support schedule */
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
map->map_type == BPF_MAP_TYPE_SOCKHASH ||
map->map_type == BPF_MAP_TYPE_SOCKMAP ||
map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
} else if (IS_FD_PROG_ARRAY(map)) {
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
attr->flags);
goto out;
}
err = bpf_map_update_value(map, f, key, value, attr->flags);
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
preempt_disable();
__this_cpu_inc(bpf_prog_active);
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
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,
attr->flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
/* rcu_read_lock() is not needed */
err = bpf_fd_reuseport_array_update_elem(map, key, value,
attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_push_elem(map, value, attr->flags);
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
rcu_read_unlock();
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
maybe_wait_bpf_programs(map);
out:
free_value:
kfree(value);
free_key:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7