diff mbox series

[bpf-next] bpf: Add bpf_ktime_get_coarse_ns helper

Message ID 20201117184549.257280-1-me@ubique.spb.ru (mailing list archive)
State Accepted
Delegated to: BPF
Headers show
Series [bpf-next] bpf: Add bpf_ktime_get_coarse_ns helper | expand

Checks

Context Check Description
netdev/apply fail Patch does not apply to bpf-next
netdev/tree_selection success Clearly marked for bpf-next

Commit Message

Dmitrii Banshchikov Nov. 17, 2020, 6:45 p.m. UTC 
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 <me@ubique.spb.ru>
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/helpers.c           | 13 +++++++++++++
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 6 files changed, 35 insertions(+)

Comments

Martin KaFai Lau Nov. 17, 2020, 8:56 p.m. UTC | #1 
On Tue, Nov 17, 2020 at 06:45:49PM +0000, Dmitrii Banshchikov wrote:
> 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
Acked-by: Martin KaFai Lau <kafai@fb.com>
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 581b2a2e78eb..e1bcb6d7345c 100644
--- a/include/linux/bpf.h
+++ b/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);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 162999b12790..b637b68b10a9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3787,6 +3787,14 @@  union bpf_attr {
  *		*ARG_PTR_TO_BTF_ID* of type *task_struct*.
  *	Return
  *		Pointer to the current task.
+ *
+ * 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),			\
@@ -3948,6 +3956,7 @@  union bpf_attr {
 	FN(task_storage_get),		\
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 55454d2278b1..ff55cbcfbab4 100644
--- a/kernel/bpf/core.c
+++ b/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;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 25520f5eeaf6..78e9bb968482 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -651,6 +651,17 @@  const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 };
 
+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,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -695,6 +706,8 @@  bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_discard_proto;
 	case BPF_FUNC_ringbuf_query:
 		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		break;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 02986c7b90eb..c3b2222ab573 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1354,6 +1354,8 @@  bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_per_cpu_ptr_proto;
 	case BPF_FUNC_bpf_this_cpu_ptr:
 		return &bpf_this_cpu_ptr_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 162999b12790..b637b68b10a9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3787,6 +3787,14 @@  union bpf_attr {
  *		*ARG_PTR_TO_BTF_ID* of type *task_struct*.
  *	Return
  *		Pointer to the current task.
+ *
+ * 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),			\
@@ -3948,6 +3956,7 @@  union bpf_attr {
 	FN(task_storage_get),		\
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper