bpf: add bpf_ktime_get_boot_ns()

On a device like a cellphone which is constantly suspending
and resuming CLOCK_MONOTONIC is not particularly useful for
keeping track of or reacting to external network events.
Instead you want to use CLOCK_BOOTTIME.

Hence add bpf_ktime_get_boot_ns() as a mirror of bpf_ktime_get_ns()
based around CLOCK_BOOTTIME instead of CLOCK_MONOTONIC.

Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

drivers/media/rc/bpf-lirc.c

@@ -103,6 +103,8 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_prandom_u32:

include/linux/bpf.h

@@ -1509,6 +1509,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
 extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
 extern const struct bpf_func_proto bpf_tail_call_proto;
 extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
+extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto;
 extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
 extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;

include/uapi/linux/bpf.h

@@ -652,6 +652,8 @@ union bpf_attr {
  * u64 bpf_ktime_get_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does not include time the system was suspended.
+ * 		See: clock_gettime(CLOCK_MONOTONIC)
  * 	Return
  * 		Current *ktime*.
  *
@@ -3025,6 +3027,14 @@ union bpf_attr {
  *		* **-EOPNOTSUPP**	Unsupported operation, for example a
  *					call from outside of TC ingress.
  *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * 	Description
+ * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does include the time the system was suspended.
+ * 		See: clock_gettime(CLOCK_BOOTTIME)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3151,7 +3161,8 @@ union bpf_attr {
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
-	FN(sk_assign),
+	FN(sk_assign),			\
+	FN(ktime_get_boot_ns),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/core.c

@@ -2156,6 +2156,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
 
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;

kernel/bpf/helpers.c

@@ -155,6 +155,18 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_boot_ns)
+{
+	/* NMI safe access to clock boottime */
+	return ktime_get_boot_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
+	.func		= bpf_ktime_get_boot_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_get_current_pid_tgid)
 {
 	struct task_struct *task = current;
@@ -615,6 +627,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
 	default:
 		break;
 	}

kernel/trace/bpf_trace.c

@@ -797,6 +797,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:

tools/include/uapi/linux/bpf.h

@@ -652,6 +652,8 @@ union bpf_attr {
  * u64 bpf_ktime_get_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does not include time the system was suspended.
+ * 		See: clock_gettime(CLOCK_MONOTONIC)
  * 	Return
  * 		Current *ktime*.
  *
@@ -3025,6 +3027,14 @@ union bpf_attr {
  *		* **-EOPNOTSUPP**	Unsupported operation, for example a
  *					call from outside of TC ingress.
  *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * 	Description
+ * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does include the time the system was suspended.
+ * 		See: clock_gettime(CLOCK_BOOTTIME)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3151,7 +3161,8 @@ union bpf_attr {
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
-	FN(sk_assign),
+	FN(sk_assign),			\
+	FN(ktime_get_boot_ns),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call