Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1264813 > unrolled thread

Re: [PATCH v2 03/19] clocksource: Add NPS400 timers driver

Started byThomas Gleixner <tglx@linutronix.de>
First post2015-11-07 12:30 +0100
Last post2015-11-07 12:30 +0100
Articles 1 — 1 participant

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH v2 03/19] clocksource: Add NPS400 timers driver Thomas Gleixner <tglx@linutronix.de> - 2015-11-07 12:30 +0100

#1264813 — Re: [PATCH v2 03/19] clocksource: Add NPS400 timers driver

FromThomas Gleixner <tglx@linutronix.de>
Date2015-11-07 12:30 +0100
SubjectRe: [PATCH v2 03/19] clocksource: Add NPS400 timers driver
Message-ID<qs9QZ-1CF-17@gated-at.bofh.it>
On Sat, 7 Nov 2015, Noam Camus wrote:
> +/*
> + * To get the value from the Global Timer Counter register proceed as follows:
> + * 1. Read the upper 32-bit timer counter register
> + * 2. Read the lower 32-bit timer counter register
> + * 3. Read the upper 32-bit timer counter register again. If the value is
> + *  different to the 32-bit upper value read previously, go back to step 2.
> + *  Otherwise the 64-bit timer counter value is correct.
> + */
> +static cycle_t nps_clksrc_read(struct clocksource *clksrc)
> +{
> +	u64 counter;
> +	u32 lower, upper, old_upper;
> +	void *lower_p, *upper_p;
> +	int cluster = (smp_processor_id() >> NPS_CLUSTER_OFFSET);
> +
> +	lower_p = nps_msu_reg_low_addr[cluster];
> +	upper_p = lower_p + 4;
> +
> +	upper = ioread32be(upper_p);
> +	do {
> +		old_upper = upper;
> +		lower = ioread32be(lower_p);
> +		upper = ioread32be(upper_p);
> +	} while (upper != old_upper);
> +
> +	counter = (upper << 32) | lower;
> +	return (cycle_t)counter;

So that clocksource goes up to 1GHz. That means u32 fits ~4.29
seconds. Unless you are striving for NOHZ idle sleep times above that
there is no point in doing that 64bit dance.

The timekeeping code is perfectly fine with a 32bit value. You just
have to set the proper mask.

Thanks,

	tglx


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [standalone]


Back to top | Article view | linux.kernel


csiph-web