[net-next v1] bpf: add bpf_ktime_get_real_ns helper

* [net-next v1] bpf: add bpf_ktime_get_real_ns helper
@ 2022-04-20 12:23 xiangxia.m.yue
  2022-04-20 12:53 ` Toke Høiland-Jørgensen
  0 siblings, 1 reply; 6+ messages in thread
From: xiangxia.m.yue @ 2022-04-20 12:23 UTC (permalink / raw)
  To: netdev, bpf
  Cc: Tonghao Zhang, Alexei Starovoitov, Daniel Borkmann,
	Andrii Nakryiko, Martin KaFai Lau, Song Liu, Yonghong Song,
	John Fastabend, KP Singh, Jiri Olsa, Dave Marchevsky,
	Kuniyuki Iwashima, Joanne Koong, Geliang Tang, David S. Miller,
	Jakub Kicinski, Eric Dumazet

From: Tonghao Zhang <xiangxia.m.yue@gmail.com>

This patch introduce a new bpf_ktime_get_real_ns helper, which may
help us to measure the skb latency in the ingress/forwarding path:

HW/SW[1] -> ip_rcv/tcp_rcv_established -> tcp_recvmsg_locked/tcp_update_recv_tstamps

* Insert BPF kprobe into ip_rcv/tcp_rcv_established invoking this helper.
  Then we can inspect how long time elapsed since HW/SW.
* If inserting BPF kprobe tcp_update_recv_tstamps invoked by tcp_recvmsg,
  we can measure how much latency skb in tcp receive queue. The reason for
  this can be application fetch the TCP messages too late.

[1]:
- HW drivers may set skb_hwtstamps(skb)->hwtstamp
- SW __netif_receive_skb_core set skb->tstamp with ktime_get_real()

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Dave Marchevsky <davemarchevsky@fb.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Cc: Joanne Koong <joannekoong@fb.com>
Cc: Geliang Tang <geliang.tang@suse.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
---
 include/uapi/linux/bpf.h       | 13 +++++++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/helpers.c           | 14 ++++++++++++++
 tools/include/uapi/linux/bpf.h | 13 +++++++++++++
 4 files changed, 41 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d14b10b85e51..2565c587fe1b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5143,6 +5143,18 @@ union bpf_attr {
  *		The **hash_algo** is returned on success,
  *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
+ *
+ * u64 bpf_ktime_get_real_ns(void)
+ * 	Description
+ * 		Return a fine-grained version of the real (i.e., wall-clock) time,
+ * 		in nanoseconds. This clock is affected by discontinuous jumps in
+ * 		the system time (e.g., if the system administrator manually changes
+ * 		the clock), and by the incremental adjustments performed by adjtime(3)
+ * 		and NTP.
+ * 		See: **clock_gettime**\ (**CLOCK_REALTIME**)
+ * 	Return
+ * 		Current *ktime*.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5339,6 +5351,7 @@ union bpf_attr {
 	FN(copy_from_user_task),	\
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
+	FN(ktime_get_real_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 13e9dbeeedf3..acdf538b1dcd 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2627,6 +2627,7 @@ 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_real_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;
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 315053ef6a75..d38548ed292f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -159,6 +159,18 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_real_ns)
+{
+	/* NMI safe access to clock realtime. */
+	return ktime_get_real_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_real_ns_proto = {
+	.func		= bpf_ktime_get_real_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_ktime_get_boot_ns)
 {
 	/* NMI safe access to clock boottime */
@@ -1410,6 +1422,8 @@ 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_real_ns:
+		return &bpf_ktime_get_real_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d14b10b85e51..2565c587fe1b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5143,6 +5143,18 @@ union bpf_attr {
  *		The **hash_algo** is returned on success,
  *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
+ *
+ * u64 bpf_ktime_get_real_ns(void)
+ * 	Description
+ * 		Return a fine-grained version of the real (i.e., wall-clock) time,
+ * 		in nanoseconds. This clock is affected by discontinuous jumps in
+ * 		the system time (e.g., if the system administrator manually changes
+ * 		the clock), and by the incremental adjustments performed by adjtime(3)
+ * 		and NTP.
+ * 		See: **clock_gettime**\ (**CLOCK_REALTIME**)
+ * 	Return
+ * 		Current *ktime*.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5339,6 +5351,7 @@ union bpf_attr {
 	FN(copy_from_user_task),	\
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
+	FN(ktime_get_real_ns),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.27.0


^ permalink raw reply related	[flat|nested] 6+ messages in thread