Message-Id: <20170117152719.23618-3-vkuznets@redhat.com>
Date:   Tue, 17 Jan 2017 16:27:19 +0100
From:   Vitaly Kuznetsov <vkuznets@...hat.com>
To:     devel@...uxdriverproject.org
Cc:     Thomas Gleixner <tglx@...utronix.de>, linux-kernel@...r.kernel.org,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        "K. Y. Srinivasan" <kys@...rosoft.com>,
        John Stultz <john.stultz@...aro.org>,
        Alex Ng <alexng@...rosoft.com>,
        Stephen Hemminger <stephen@...workplumber.org>,
        Olaf Hering <olaf@...fle.de>,
        Richard Cochran <richardcochran@...il.com>
Subject: [PATCH v3 2/2] hv_utils: implement Hyper-V PTP source

With TimeSync version 4 protocol support we started updating system time
continuously through the whole lifetime of Hyper-V guests. Every 5 seconds
there is a time sample from the host which triggers do_settimeofday[64]().
While the time from the host is very accurate such adjustments may cause
issues:
- Time is jumping forward and backward, some applications may misbehave.
- In case an NTP server runs in parallel and uses something else for time
  sync (network, PTP,...) system time will never converge.
- Systemd starts annoying you by printing "Time has been changed" every 5
  seconds to the system log.

Instead of doing in-kernel time adjustments offload the work to an
NTP client by exposing TimeSync messages as a PTP device. Users may now
decide what they want to use as a source.

I tested the solution with chrony, the config was:

 refclock PHC /dev/ptp0 poll 3 precision 1e-9

The result I'm seeing is accurate enough, the time delta between the guest
and the host is almost always within [-10us, +10us], the in-kernel solution
was giving us comparable results.

I also tried implementing PPS device instead of PTP by using not currently
used Hyper-V synthetic timers (we use only one of four for clockevent) but
with PPS source only chrony wasn't able to give me the required accuracy,
the delta often more that 100us.

Signed-off-by: Vitaly Kuznetsov <vkuznets@...hat.com>
---
 drivers/hv/hv_util.c | 140 ++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 115 insertions(+), 25 deletions(-)

diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 94719eb..e49c5f3 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -27,6 +27,7 @@
 #include <linux/sysctl.h>
 #include <linux/reboot.h>
 #include <linux/hyperv.h>
+#include <linux/ptp_clock_kernel.h>
 
 #include "hyperv_vmbus.h"
 
@@ -179,31 +180,35 @@ struct adj_time_work {
 	u8	flags;
 };
 
+static inline u64 get_timeadj_latency(u64 ref_time)
+{
+	u64 current_tick;
+
+	if (ts_srv_version <= TS_VERSION_3)
+		return 0;
+
+	/*
+	 * Some latency has been introduced since Hyper-V generated
+	 * its time sample. Take that latency into account before
+	 * using TSC reference time sample from Hyper-V.
+	 *
+	 * This sample is given by TimeSync v4 and above hosts.
+	 */
+
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	return current_tick - ref_time;
+}
+
 static void hv_set_host_time(struct work_struct *work)
 {
 	struct adj_time_work	*wrk;
-	s64 host_tns;
-	u64 newtime;
 	struct timespec64 host_ts;
+	u64 newtime;
 
 	wrk = container_of(work, struct adj_time_work, work);
 
-	newtime = wrk->host_time;
-	if (ts_srv_version > TS_VERSION_3) {
-		/*
-		 * Some latency has been introduced since Hyper-V generated
-		 * its time sample. Take that latency into account before
-		 * using TSC reference time sample from Hyper-V.
-		 *
-		 * This sample is given by TimeSync v4 and above hosts.
-		 */
-		u64 current_tick;
-
-		rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-		newtime += (current_tick - wrk->ref_time);
-	}
-	host_tns = (newtime - WLTIMEDELTA) * 100;
-	host_ts = ns_to_timespec64(host_tns);
+	newtime = wrk->host_time + get_timeadj_latency(wrk->ref_time);
+	host_ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
 
 	do_settimeofday64(&host_ts);
 }
@@ -222,22 +227,52 @@ static void hv_set_host_time(struct work_struct *work)
  * to discipline the clock.
  */
 static struct adj_time_work  wrk;
-static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 flags)
+
+/*
+ * The last time sample, received from the host. PTP device responds to
+ * requests by using this data and the current partition-wide time reference
+ * count.
+ */
+static struct {
+	u64		host_time;
+	u64		ref_time;
+	spinlock_t	lock;
+} host_ts;
+
+static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
 {
+	unsigned long flags;
 
 	/*
 	 * This check is safe since we are executing in the
 	 * interrupt context and time synch messages arre always
 	 * delivered on the same CPU.
 	 */
-	if (work_pending(&wrk.work))
-		return;
+	if (adj_flags & ICTIMESYNCFLAG_SYNC) {
+		if (work_pending(&wrk.work))
+			return;
 
-	wrk.host_time = hosttime;
-	wrk.ref_time = reftime;
-	wrk.flags = flags;
-	if ((flags & (ICTIMESYNCFLAG_SYNC | ICTIMESYNCFLAG_SAMPLE)) != 0) {
+		wrk.host_time = hosttime;
+		wrk.ref_time = reftime;
+		wrk.flags = adj_flags;
 		schedule_work(&wrk.work);
+	} else {
+		spin_lock_irqsave(&host_ts.lock, flags);
+		host_ts.host_time = hosttime;
+
+		/*
+		 * Prior to version 4 TimeSync messages from the host don't
+		 * contain any reference time (the time when the time sample
+		 * was generated), save the current time reference count
+		 * instead. This adds a small delta between the time sample
+		 * generation and the reception of the sample here to the result
+		 * but it's the best thing we can do.
+		 */
+		if (ts_srv_version <= TS_VERSION_3)
+			rdmsrl(HV_X64_MSR_TIME_REF_COUNT, host_ts.ref_time);
+		else
+			host_ts.ref_time = reftime;
+		spin_unlock_irqrestore(&host_ts.lock, flags);
 	}
 }
 
@@ -470,14 +505,69 @@ static  struct hv_driver util_drv = {
 	.remove =  util_remove,
 };
 
+static int hv_ptp_enable(struct ptp_clock_info *info,
+			 struct ptp_clock_request *request, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_settime(struct ptp_clock_info *p, const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+	return -EOPNOTSUPP;
+}
+static int hv_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
+{
+	u64 newtime;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host_ts.lock, flags);
+	newtime = host_ts.host_time + get_timeadj_latency(host_ts.ref_time);
+	*ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
+	spin_unlock_irqrestore(&host_ts.lock, flags);
+
+	return 0;
+}
+
+struct ptp_clock_info ptp_hyperv_info = {
+	.name		= "hyperv",
+	.enable         = hv_ptp_enable,
+	.adjtime        = hv_ptp_adjtime,
+	.adjfreq        = hv_ptp_adjfreq,
+	.gettime64      = hv_ptp_gettime,
+	.settime64      = hv_ptp_settime,
+	.owner		= THIS_MODULE,
+};
+
+static struct ptp_clock *hv_ptp_clock;
+
 static int hv_timesync_init(struct hv_util_service *srv)
 {
 	INIT_WORK(&wrk.work, hv_set_host_time);
+
+	hv_ptp_clock = ptp_clock_register(&ptp_hyperv_info, NULL);
+	if (IS_ERR_OR_NULL(hv_ptp_clock)) {
+		pr_err("cannot register PTP clock: %ld\n",
+		       PTR_ERR(hv_ptp_clock));
+		hv_ptp_clock = NULL;
+	}
+
 	return 0;
 }
 
 static void hv_timesync_deinit(void)
 {
+	if (hv_ptp_clock)
+		ptp_clock_unregister(hv_ptp_clock);
 	cancel_work_sync(&wrk.work);
 }
 
-- 
2.9.3

Powered by blists - more mailing lists