On 10/17/19 8:00 AM, Carlos Neira wrote:
> New bpf helper bpf_get_ns_current_pid_tgid,
> This helper will return pid and tgid from current task
> which namespace matches dev_t and inode number provided,
> this will allows us to instrument a process inside a container.
>
> Signed-off-by: Carlos Neira <cneirabustos@xxxxxxxxx>
You need to rebase the whole series, a new helper skb_output
is just added.
> ---
> include/linux/bpf.h | 1 +
> include/uapi/linux/bpf.h | 20 +++++++++++++++++-
> kernel/bpf/core.c | 1 +
> kernel/bpf/helpers.c | 45 ++++++++++++++++++++++++++++++++++++++++
> kernel/trace/bpf_trace.c | 2 ++
> 5 files changed, 68 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 5b9d22338606..231001475504 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1055,6 +1055,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto;
> extern const struct bpf_func_proto bpf_strtol_proto;
> extern const struct bpf_func_proto bpf_strtoul_proto;
> extern const struct bpf_func_proto bpf_tcp_sock_proto;
> +extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_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 a65c3b0c6935..a17583ae9aa3 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2750,6 +2750,19 @@ union bpf_attr {
> * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies
> *
> * **-EPROTONOSUPPORT** IP packet version is not 4 or 6
> + *
> + * u64 bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
-EINVAL/-ENOENT may be returned, so let us have return type "int" instead.
> + * Description
> + * Returns 0 on success, values for *pid* and *tgid* as seen from the current
> + * *namespace* will be returned in *nsdata*.
> + *
> + * On failure, the returned value is one of the following:
> + *
> + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number
> + * with nsfs of current task, or if dev conversion to dev_t lost high bits.
> + *
> + * **-ENOENT** if /proc/self/ns does not exists.
Let us do not hard code the /proc/self/ns path. Just mention that the
pidns does not exist for the current task.
> + *
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -2862,7 +2875,8 @@ union bpf_attr {
> FN(sk_storage_get), \
> FN(sk_storage_delete), \
> FN(send_signal), \
> - FN(tcp_gen_syncookie),
> + FN(tcp_gen_syncookie), \
> + FN(get_ns_current_pid_tgid),
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> * function eBPF program intends to call
> @@ -3613,4 +3627,8 @@ struct bpf_sockopt {
> __s32 retval;
> };
>
> +struct bpf_pidns_info {
> + __u32 pid;
> + __u32 tgid;
> +};
> #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index 66088a9e9b9e..b2fd5358f472 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -2042,6 +2042,7 @@ 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_get_current_cgroup_id_proto __weak;
> const struct bpf_func_proto bpf_get_local_storage_proto __weak;
> +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_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 5e28718928ca..5477ad984d7c 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -11,6 +11,8 @@
> #include <linux/uidgid.h>
> #include <linux/filter.h>
> #include <linux/ctype.h>
> +#include <linux/pid_namespace.h>
> +#include <linux/proc_ns.h>
>
> #include "../../lib/kstrtox.h"
>
> @@ -487,3 +489,46 @@ const struct bpf_func_proto bpf_strtoul_proto = {
> .arg4_type = ARG_PTR_TO_LONG,
> };
> #endif
> +
> +BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
> + struct bpf_pidns_info *, nsdata, u32, size)
> +{
> + struct task_struct *task = current;
> + struct pid_namespace *pidns;
> + int err = -EINVAL;
> +
> + if (unlikely(size != sizeof(struct bpf_pidns_info)))
> + goto clear;
> +
> + if (unlikely((u64)(dev_t)dev != dev))
> + goto clear;
> +
> + if (unlikely(!task))
> + goto clear;
> +
> + pidns = task_active_pid_ns(task);
> + if (unlikely(!pidns)) {
> + err = -ENOENT;
> + goto clear;
> + }
> +
> + if (!ns_match(&pidns->ns, (dev_t)dev, ino))
> + goto clear;
> +
> + nsdata->pid = task_pid_nr_ns(task, pidns);
> + nsdata->tgid = task_tgid_nr_ns(task, pidns);
> + return 0;
> +clear:
> + memset((void *)nsdata, 0, (size_t) size);
> + return err;
> +}
> +
> +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = {
> + .func = bpf_get_ns_current_pid_tgid,
> + .gpl_only = false,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_ANYTHING,
> + .arg2_type = ARG_ANYTHING,
> + .arg3_type = ARG_PTR_TO_UNINIT_MEM,
> + .arg4_type = ARG_CONST_SIZE,
> +};
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index 44bd08f2443b..32331a1dcb6d 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -735,6 +735,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> #endif
> case BPF_FUNC_send_signal:
> return &bpf_send_signal_proto;
> + case BPF_FUNC_get_ns_current_pid_tgid:
> + return &bpf_get_ns_current_pid_tgid_proto;
> default:
> return NULL;
> }
>
