bpf: Add bpf_ktime_get_coarse_ns helper

The helper uses CLOCK_MONOTONIC_COARSE source of time that is less
accurate but more performant.

We have a BPF CGROUP_SKB firewall that supports event logging through
bpf_perf_event_output(). Each event has a timestamp and currently we use
bpf_ktime_get_ns() for it. Use of bpf_ktime_get_coarse_ns() saves ~15-20
ns in time required for event logging.

bpf_ktime_get_ns():
EgressLogByRemoteEndpoint                              113.82ns    8.79M

bpf_ktime_get_coarse_ns():
EgressLogByRemoteEndpoint                               95.40ns   10.48M

Signed-off-by: Dmitrii Banshchikov <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Acked-by: Martin KaFai Lau <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: ubique

include/linux/bpf.h

@@ -1842,6 +1842,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);

include/uapi/linux/bpf.h

@@ -3797,6 +3797,16 @@ union bpf_attr {
  *		is cleared if the flag is not specified.
  *	Return
  *		**-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * 	Description
+ * 		Return a coarse-grained version of the time elapsed since
+ * 		system boot, in nanoseconds. Does not include time the system
+ * 		was suspended.
+ *
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3959,6 +3969,7 @@ union bpf_attr {
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
 	FN(bprm_opts_set),		\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/core.c

@@ -2211,6 +2211,7 @@ 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_ktime_get_coarse_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

@@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_coarse_ns)
+{
+	return ktime_get_coarse_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
+	.func		= bpf_ktime_get_coarse_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_get_current_pid_tgid)
 {
 	struct task_struct *task = current;
@@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:

kernel/trace/bpf_trace.c

@@ -1280,6 +1280,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_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

@@ -3797,6 +3797,16 @@ union bpf_attr {
  *		is cleared if the flag is not specified.
  *	Return
  *		**-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * 	Description
+ * 		Return a coarse-grained version of the time elapsed since
+ * 		system boot, in nanoseconds. Does not include time the system
+ * 		was suspended.
+ *
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3959,6 +3969,7 @@ union bpf_attr {
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
 	FN(bprm_opts_set),		\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper