On 06/04/2018 12:59 AM, Yonghong Song wrote:
> bpf has been used extensively for tracing. For example, bcc
> contains an almost full set of bpf-based tools to trace kernel
> and user functions/events. Most tracing tools are currently
> either filtered based on pid or system-wide.
>
> Containers have been used quite extensively in industry and
> cgroup is often used together to provide resource isolation
> and protection. Several processes may run inside the same
> container. It is often desirable to get container-level tracing
> results as well, e.g. syscall count, function count, I/O
> activity, etc.
>
> This patch implements a new helper, bpf_get_current_cgroup_id(),
> which will return cgroup id based on the cgroup within which
> the current task is running.
>
> The later patch will provide an example to show that
> userspace can get the same cgroup id so it could
> configure a filter or policy in the bpf program based on
> task cgroup id.
>
> The helper is currently implemented for tracing. It can
> be added to other program types as well when needed.
>
> Acked-by: Alexei Starovoitov <a...@kernel.org>
> Signed-off-by: Yonghong Song <y...@fb.com>
> ---
> include/linux/bpf.h | 1 +
> include/uapi/linux/bpf.h | 8 +++++++-
> kernel/bpf/core.c | 1 +
> kernel/bpf/helpers.c | 15 +++++++++++++++
> kernel/trace/bpf_trace.c | 2 ++
> 5 files changed, 26 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index bbe2974..995c3b1 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -746,6 +746,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto;
> extern const struct bpf_func_proto bpf_get_stack_proto;
> extern const struct bpf_func_proto bpf_sock_map_update_proto;
> extern const struct bpf_func_proto bpf_sock_hash_update_proto;
> +extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
>
> /* Shared helpers among cBPF and eBPF. */
> void bpf_user_rnd_init_once(void);
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index f0b6608..18712b0 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2070,6 +2070,11 @@ union bpf_attr {
> * **CONFIG_SOCK_CGROUP_DATA** configuration option.
> * Return
> * The id is returned or 0 in case the id could not be retrieved.
> + *
> + * u64 bpf_get_current_cgroup_id(void)
> + * Return
> + * A 64-bit integer containing the current cgroup id based
> + * on the cgroup within which the current task is running.
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -2151,7 +2156,8 @@ union bpf_attr {
> FN(lwt_seg6_action), \
> FN(rc_repeat), \
> FN(rc_keydown), \
> - FN(skb_cgroup_id),
> + FN(skb_cgroup_id), \
> + FN(get_current_cgroup_id),
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> * function eBPF program intends to call
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index 527587d..9f14937 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -1765,6 +1765,7 @@ const struct bpf_func_proto
> bpf_get_current_uid_gid_proto __weak;
> const struct bpf_func_proto bpf_get_current_comm_proto __weak;
> const struct bpf_func_proto bpf_sock_map_update_proto __weak;
> const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
> +const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
>
> const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
> {
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index 3d24e23..73065e2 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -179,3 +179,18 @@ const struct bpf_func_proto bpf_get_current_comm_proto =
> {
> .arg1_type = ARG_PTR_TO_UNINIT_MEM,
> .arg2_type = ARG_CONST_SIZE,
> };
> +
> +#ifdef CONFIG_CGROUPS
> +BPF_CALL_0(bpf_get_current_cgroup_id)
> +{
> + struct cgroup *cgrp = task_dfl_cgroup(current);
> +
> + return cgrp->kn->id.id;
> +}
> +
> +const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
> + .func = bpf_get_current_cgroup_id,
> + .gpl_only = false,
> + .ret_type = RET_INTEGER,
> +};
> +#endif
Nit: why not moving this function directly to bpf_trace.c?
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index 752992c..e2ab5b7 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -564,6 +564,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct
> bpf_prog *prog)
> return &bpf_get_prandom_u32_proto;
> case BPF_FUNC_probe_read_str:
> return &bpf_probe_read_str_proto;
> + case BPF_FUNC_get_current_cgroup_id:
> + return &bpf_get_current_cgroup_id_proto;
When you have !CONFIG_CGROUPS, then it relies on the weak definition of the
bpf_get_current_cgroup_id_proto, which I would think at latest in
fixup_bpf_calls()
bails out with 'kernel subsystem misconfigured func' due to func being NULL.
Can't we just do the #ifdef CONFIG_CGROUPS around BPF_FUNC_get_current_cgroup_id
case instead? Then we bail out normally with 'unknown func' when cgroups are
not configured?
> default:
> return NULL;
> }
>
