static int bpf_prog_load(union bpf_attr *attr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog;
int err;
char license[128];
bool is_gpl;
if (CHECK_ATTR(BPF_PROG_LOAD)) //check attr中不用的字段是否全零
return -EINVAL;
if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT) //只支持BPF_F_STRICT_ALIGNMENT
return -EINVAL;
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0; //从用户态内存copy license字符串
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license); //不是gpl 有些helper fn不能使用 verify时校验
if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS) //指令数校验
return -E2BIG;
if (type == BPF_PROG_TYPE_KPROBE &&
attr->kern_version != LINUX_VERSION_CODE) //kprobe类型的 要和内核版本一致
return -EINVAL;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB && //两种不查权限的类型
!capable(CAP_SYS_ADMIN))
return -EPERM;
bpf_prog_load_fixup_attach_type(attr); //加了expected_attach_type字段 向后兼容
if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type)) //check expected_attach_type
return -EINVAL;
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); //申请bpf_prog内存 用户空间内存 详解
if (!prog)
return -ENOMEM;
prog->expected_attach_type = attr->expected_attach_type;
prog->aux->offload_requested = !!attr->prog_ifindex;
err = security_bpf_prog_alloc(prog->aux); //LSM相关
if (err)
goto free_prog_nouncharge;
err = bpf_prog_charge_memlock(prog); //bpf_prog的内存锁定到当前用户
if (err)
goto free_prog_sec;
prog->len = attr->insn_cnt;
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
bpf_prog_insn_size(prog)) != 0) //copy指令 用户态内存到内核态内存
goto free_prog;
prog->orig_prog = NULL;
prog->jited = 0;
atomic_set(&prog->aux->refcnt, 1); //引用计数
prog->gpl_compatible = is_gpl ? 1 : 0;
if (bpf_prog_is_dev_bound(prog->aux)) {
err = bpf_prog_offload_init(prog, attr); //绑定接口的需要初始化offload
if (err)
goto free_prog;
}
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog); //按类型 绑定bpf_prog_ops
if (err < 0)
goto free_prog;
prog->aux->load_time = ktime_get_boot_ns();
err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
if (err)
goto free_prog;
/* run eBPF verifier */
err = bpf_check(&prog, attr);
if (err < 0)
goto free_used_maps;
prog = bpf_prog_select_runtime(prog, &err); //选择执行器
if (err < 0)
goto free_used_maps;
err = bpf_prog_alloc_id(prog); //分配id
if (err)
goto free_used_maps;
err = bpf_prog_new_fd(prog); //分配fd
if (err < 0) {
/* failed to allocate fd.
* bpf_prog_put() is needed because the above
* bpf_prog_alloc_id() has published the prog
* to the userspace and the userspace may
* have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
*/
bpf_prog_put(prog);
return err;
}
bpf_prog_kallsyms_add(prog);
return err;
free_used_maps:
bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
free_prog_sec:
security_bpf_prog_free(prog->aux);
free_prog_nouncharge:
bpf_prog_free(prog);
return err;
}
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
size = round_up(size, PAGE_SIZE);
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); //页粒度 存size个指令
if (fp == NULL)
return NULL;
aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); //其他信息
if (aux == NULL) {
vfree(fp);
return NULL;
}
fp->pages = size / PAGE_SIZE;
fp->aux = aux;
fp->aux->prog = fp;
fp->jit_requested = ebpf_jit_enabled();
INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
return fp;
}