bpf: Added new helper bpf_get_ns_current_pid_tgid

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@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200304204157.58695-3-cneirabustos@gmail.com

Author: cneira

include/linux/bpf.h

@@ -1497,6 +1497,7 @@ 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_jiffies64_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);

include/uapi/linux/bpf.h

@@ -2914,6 +2914,19 @@ union bpf_attr {
  *		of sizeof(struct perf_branch_entry).
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ *	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 pidns does not exists for the current task.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3035,7 +3048,8 @@ union bpf_attr {
 	FN(tcp_send_ack),		\
 	FN(send_signal_thread),		\
 	FN(jiffies64),			\
-	FN(read_branch_records),
+	FN(read_branch_records),	\
+	FN(get_ns_current_pid_tgid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3829,4 +3843,8 @@ struct bpf_sockopt {
 	__s32	retval;
 };
 
+struct bpf_pidns_info {
+	__u32 pid;
+	__u32 tgid;
+};
 #endif /* _UAPI__LINUX_BPF_H__ */

kernel/bpf/core.c

@@ -2149,6 +2149,7 @@ 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)
 {

kernel/bpf/helpers.c

@@ -12,6 +12,8 @@
 #include <linux/filter.h>
 #include <linux/ctype.h>
 #include <linux/jiffies.h>
+#include <linux/pid_namespace.h>
+#include <linux/proc_ns.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -499,3 +501,46 @@ 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,
+};

kernel/trace/bpf_trace.c

@@ -843,6 +843,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_send_signal_thread_proto;
 	case BPF_FUNC_perf_event_read_value:
 		return &bpf_perf_event_read_value_proto;
+	case BPF_FUNC_get_ns_current_pid_tgid:
+		return &bpf_get_ns_current_pid_tgid_proto;
 	default:
 		return NULL;
 	}

scripts/bpf_helpers_doc.py

@@ -435,6 +435,7 @@ class PrinterHelpers(Printer):
             'struct bpf_fib_lookup',
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
+            'struct bpf_pidns_info',
             'struct bpf_sock',
             'struct bpf_sock_addr',
             'struct bpf_sock_ops',

tools/include/uapi/linux/bpf.h

@@ -2914,6 +2914,19 @@ union bpf_attr {
  *		of sizeof(struct perf_branch_entry).
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ *	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 pidns does not exists for the current task.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3035,7 +3048,8 @@ union bpf_attr {
 	FN(tcp_send_ack),		\
 	FN(send_signal_thread),		\
 	FN(jiffies64),			\
-	FN(read_branch_records),
+	FN(read_branch_records),	\
+	FN(get_ns_current_pid_tgid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3829,4 +3843,8 @@ struct bpf_sockopt {
 	__s32	retval;
 };
 
+struct bpf_pidns_info {
+	__u32 pid;
+	__u32 tgid;
+};
 #endif /* _UAPI__LINUX_BPF_H__ */