mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Wen Gu <guwen@linux.alibaba.com>
To: "David Woodhouse" <dwmw2@infradead.org>,
	"Richard Cochran" <richardcochran@gmail.com>,
	"Andrew Lunn" <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Paolo Abeni" <pabeni@redhat.com>,
	"John Stultz" <jstultz@google.com>,
	"Thomas Gleixner" <tglx@kernel.org>,
	"Stephen Boyd" <sboyd@kernel.org>,
	"Anna-Maria Behnsen" <anna-maria@linutronix.de>,
	"Frederic Weisbecker" <frederic@kernel.org>,
	"Shuah Khan" <shuah@kernel.org>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Thomas Weißschuh" <thomas.weissschuh@linutronix.de>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Miroslav Lichvar" <mlichvar@redhat.com>,
	"Julien Ridoux" <ridouxj@amazon.com>,
	"Ryan Luu" <rluu@amazon.com>,
	linux-kernel@vger.kernel.org
Cc: David Woodhouse <dwmw@amazon.co.uk>
Subject: Re: [RFC PATCH v3 10/10] kernel/time: Add /dev/vmclock_host miscdev
Date: Thu, 21 May 2026 14:29:46 +0800	[thread overview]
Message-ID: <d923d603-b500-4b99-a23a-de76f285f487@linux.alibaba.com> (raw)
In-Reply-To: <20260520135207.37826-11-dwmw2@infradead.org>



On 2026/5/20 21:33, David Woodhouse wrote:

> +/*
> + * Called from pvclock_gtod_notify on every timekeeping update.
> + * Only does real work when ntp_tick or skew_delta changes.
> + */
> +static int vmclock_host_notify(struct notifier_block *nb,
> +			       unsigned long was_set, void *data)
> +{

<...>

> +
> +	/* Compute time tuple: C = A + ntp_error + time_offset */
> +	ns = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
> +	sec = tk->xtime_sec + tk->tai_offset;
> +	ns += tk->ntp_error >> (tk->tkr_mono.shift + tk->ntp_error_shift);
> +	ns += ntp_get_time_offset_ns(tk->id);
> +
> +	while (ns < 0) {
> +		ns += NSEC_PER_SEC;
> +		sec--;
> +	}
> +	while (ns >= NSEC_PER_SEC) {
> +		ns -= NSEC_PER_SEC;
> +		sec++;
> +	}
> +
> +	counter_value = tk->tkr_mono.cycle_last;
> +	hi = div64_u64_rem((u64)ns << 32, 1000000000ULL, &rem);
> +	time_frac = (hi << 32) | div64_u64(rem << 32, 1000000000ULL);
> +
> +	clock_status = !(ntp_get_status() & STA_UNSYNC) ?
> +		VMCLOCK_STATUS_SYNCHRONIZED : VMCLOCK_STATUS_FREERUNNING;
> +
> +	/* Prepare le values */
> +	le_counter_value = cpu_to_le64(counter_value);
> +	le_time_sec = cpu_to_le64(sec);
> +	le_time_frac = cpu_to_le64(time_frac);
> +	le_period_frac = cpu_to_le64(cached_period_frac);
> +	period_shift = cached_period_shift;
> +
> +	/* Update page under seqcount */
> +	WRITE_ONCE(clk->seq_count, cpu_to_le32(
> +		le32_to_cpu(READ_ONCE(clk->seq_count)) + 1));
> +	smp_wmb();
> +
> +	clk->counter_id = counter_id;
> +	clk->counter_value = le_counter_value;
> +	clk->time_sec = le_time_sec;
> +	clk->time_frac_sec = le_time_frac;
> +	if (period_changed) {
> +		clk->counter_period_frac_sec = le_period_frac;
> +		clk->counter_period_shift = period_shift;
> +	}
> +	clk->clock_status = clock_status;
> +
> +	/* Set leap second indicator from NTP time_state */
> +	switch (ntp_get_time_state()) {
> +	case TIME_INS:
> +		clk->leap_indicator = VMCLOCK_LEAP_PRE_POS;
> +		break;
> +	case TIME_DEL:
> +		clk->leap_indicator = VMCLOCK_LEAP_PRE_NEG;
> +		break;
> +	case TIME_OOP:
> +		clk->leap_indicator = VMCLOCK_LEAP_POS;
> +		break;
> +	case TIME_WAIT:
> +		clk->leap_indicator = (ntp_get_status() & STA_DEL) ?
> +			VMCLOCK_LEAP_POST_NEG : VMCLOCK_LEAP_POST_POS;
> +		break;
> +	default:
> +		clk->leap_indicator = VMCLOCK_LEAP_NONE;
> +		break;
> +	}
> +
> +	/* Export as TAI if tai_offset is known, otherwise UTC */
> +	if (tk->tai_offset) {
> +		clk->time_type = VMCLOCK_TIME_TAI;
> +		clk->tai_offset_sec = cpu_to_le16((s16)tk->tai_offset);

I think this should be cpu_to_le16(-(s16)tk->tai_offset)?

vmclock_set_tk_reference() in Patch 9 treats clk->tai_offset_sec as
a (UTC - TAI) offset, so the sign here probably needs to be inverted.

> +		clk->flags = cpu_to_le64(VMCLOCK_FLAG_TAI_OFFSET_VALID |
> +					 VMCLOCK_FLAG_TIME_MONOTONIC |
> +					 VMCLOCK_FLAG_NOTIFICATION_PRESENT);
> +	} else {
> +		clk->time_type = VMCLOCK_TIME_UTC;
> +		clk->tai_offset_sec = 0;
> +		clk->flags = cpu_to_le64(VMCLOCK_FLAG_TIME_MONOTONIC |
> +					 VMCLOCK_FLAG_NOTIFICATION_PRESENT);
> +	}
> +
> +	smp_wmb();
> +	WRITE_ONCE(clk->seq_count, cpu_to_le32(
> +		le32_to_cpu(READ_ONCE(clk->seq_count)) + 1));
> +
> +	wake_up_interruptible(&vmclock_wait);
> +	return NOTIFY_DONE;
> +}

  reply	other threads:[~2026-05-21  6:30 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-20 13:33 [RFC PATCH v3 00/10] timekeeping: Fix drift tracking precision and add feed-forward discipline via vmclock David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 01/10] MAINTAINERS: Add Miroslav as timekeeping reviewer David Woodhouse
2026-05-20 23:28   ` John Stultz
2026-05-20 13:33 ` [RFC PATCH v3 02/10] timekeeping: Remove xtime_remainder from ntp_error accumulation David Woodhouse
2026-05-22 11:41   ` David Woodhouse
2026-05-29 23:21     ` John Stultz
2026-05-30 10:51       ` David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 03/10] timekeeping: Account for monotonicity adjustment in ntp_error David Woodhouse
2026-05-20 23:27   ` John Stultz
2026-05-20 23:36     ` David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 04/10] timekeeping: Guard against divide-by-zero in timekeeping_adjust David Woodhouse
2026-05-20 23:29   ` John Stultz
2026-05-20 13:33 ` [RFC PATCH v3 05/10] timekeeping: Drive time_offset skew via per-tick ntp_error transfer David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 06/10] ntp: Convert adjtime() to use time_offset instead of tick_length inflation David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 07/10] ntp: Remove tick_length_base, use tick_length directly David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 08/10] timekeeping: Add absolute reference for feed-forward clock discipline David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 09/10] ptp_vmclock: Feed reference to timekeeping for feed-forward discipline David Woodhouse
2026-05-20 13:33 ` [RFC PATCH v3 10/10] kernel/time: Add /dev/vmclock_host miscdev David Woodhouse
2026-05-21  6:29   ` Wen Gu [this message]
2026-05-28 16:18     ` David Woodhouse
2026-05-23 11:49 ` [RFC PATCH v3 00/10] timekeeping: Fix drift tracking precision and add feed-forward discipline via vmclock David Woodhouse

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=d923d603-b500-4b99-a23a-de76f285f487@linux.alibaba.com \
    --to=guwen@linux.alibaba.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=anna-maria@linutronix.de \
    --cc=arnd@arndb.de \
    --cc=davem@davemloft.net \
    --cc=dwmw2@infradead.org \
    --cc=dwmw@amazon.co.uk \
    --cc=edumazet@google.com \
    --cc=frederic@kernel.org \
    --cc=jstultz@google.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mlichvar@redhat.com \
    --cc=pabeni@redhat.com \
    --cc=peterz@infradead.org \
    --cc=richardcochran@gmail.com \
    --cc=ridouxj@amazon.com \
    --cc=rluu@amazon.com \
    --cc=sboyd@kernel.org \
    --cc=shuah@kernel.org \
    --cc=tglx@kernel.org \
    --cc=thomas.weissschuh@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®