linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>,
	LKML <linux-kernel@vger.kernel.org>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <peterz@infradead.org>,
	John Stultz <john.stultz@linaro.org>,
	Douglas Anderson <dianders@chromium.org>,
	Nicolas Pitre <nico@linaro.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Jonathan Austin <jonathan.austin@arm.com>,
	Arnd Bergmann <arnd@arndb.de>, Kevin Hilman <khilman@kernel.org>,
	Russell King <linux@arm.linux.org.uk>,
	Michael Turquette <mturquette@baylibre.com>,
	Stephen Boyd <sboyd@codeaurora.org>,
	Boris Brezillon <boris.brezillon@free-electrons.com>,
	Thibaud Cornic <thibaud_cornic@sigmadesigns.com>,
	Mason <slash.tmp@free.fr>
Subject: Re: [RFC] Improving udelay/ndelay on platforms where that is possible
Date: Wed, 15 Nov 2017 13:51:54 +0100	[thread overview]
Message-ID: <11393e07-b042-180c-3bcd-484bf51eada6@sigmadesigns.com> (raw)
In-Reply-To: <e03436d1-b140-3f29-59a6-3b1eb6bf9da4@free.fr>

On 01/11/2017 20:38, Marc Gonzalez wrote:

> OK, I'll just send my patch, and then crawl back under my rock.

Linus,

As promised, the patch is provided below. And as promised, I will
no longer bring this up on LKML.

FWIW, I have checked that the computed value matches the expected
value for all HZ and delay_us, and for a few clock frequencies,
using the following program:

$ cat delays.c
#include <stdio.h>
#define MEGA 1000000u
typedef unsigned int uint;
typedef unsigned long long u64;
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))

static const uint HZ_tab[] = { 100, 250, 300, 1000 };

static void check_cycle_count(uint freq, uint HZ, uint delay_us)
{
	uint UDELAY_MULT = (2147 * HZ) + (483648 * HZ / MEGA);
	uint lpj = DIV_ROUND_UP(freq, HZ);
	uint computed = ((u64)lpj * delay_us * UDELAY_MULT >> 31) + 1;
	uint expected = DIV_ROUND_UP((u64)delay_us * freq, MEGA);

	if (computed != expected)
		printf("freq=%u HZ=%u delay_us=%u comp=%u exp=%u\n", freq, HZ, delay_us, computed, expected);
}

int main(void)
{
	uint idx, delay_us, freq;

	for (freq = 3*MEGA; freq <= 100*MEGA; freq += 3*MEGA)
		for (idx = 0; idx < sizeof HZ_tab / sizeof *HZ_tab; ++idx)
			for (delay_us = 1; delay_us <= 2000; ++delay_us)
				check_cycle_count(freq, HZ_tab[idx], delay_us);

	return 0;
}



-- >8 --
Subject: [PATCH] ARM: Tweak clock-based udelay implementation

In 9f8197980d87a ("delay: Add explanation of udelay() inaccuracy")
Russell pointed out that loop-based delays may return early.

On the arm platform, delays may be either loop-based or clock-based.

This patch tweaks the clock-based implementation so that udelay(N)
is guaranteed to spin at least N microseconds.

Signed-off-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
---
 arch/arm/lib/delay.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 2cef11884857..0a25712077ec 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -58,15 +58,15 @@ static void __timer_delay(unsigned long cycles)
 {
 	cycles_t start = get_cycles();
 
-	while ((get_cycles() - start) < cycles)
+	while ((get_cycles() - start) <= cycles)
 		cpu_relax();
 }
 
 static void __timer_const_udelay(unsigned long xloops)
 {
-	unsigned long long loops = xloops;
-	loops *= arm_delay_ops.ticks_per_jiffy;
-	__timer_delay(loops >> UDELAY_SHIFT);
+	u64 tmp = (u64)xloops * arm_delay_ops.ticks_per_jiffy;
+	unsigned long cycles = tmp >> UDELAY_SHIFT;
+	__timer_delay(cycles + 1); /* Round up in 1 instruction */
 }
 
 static void __timer_udelay(unsigned long usecs)
@@ -92,7 +92,7 @@ void __init register_current_timer_delay(const struct delay_timer *timer)
 	if (!delay_calibrated && (!delay_res || (res < delay_res))) {
 		pr_info("Switching to timer-based delay loop, resolution %lluns\n", res);
 		delay_timer			= timer;
-		lpj_fine			= timer->freq / HZ;
+		lpj_fine			= DIV_ROUND_UP(timer->freq, HZ);
 		delay_res			= res;
 
 		/* cpufreq may scale loops_per_jiffy, so keep a private copy */
-- 
2.15.0

  reply	other threads:[~2017-11-15 12:53 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-31 16:15 [RFC] Improving udelay/ndelay on platforms where that is possible Marc Gonzalez
2017-10-31 16:44 ` Linus Torvalds
2017-10-31 16:56   ` Russell King - ARM Linux
2017-10-31 17:45     ` Linus Torvalds
2017-10-31 17:58       ` Linus Torvalds
2017-11-01  0:23       ` Doug Anderson
2017-11-01  9:26         ` Russell King - ARM Linux
2017-11-01 15:53           ` Doug Anderson
2017-12-07 12:31             ` Pavel Machek
2017-11-01 19:28           ` Marc Gonzalez
2017-11-01 20:30             ` Russell King - ARM Linux
2017-10-31 16:46 ` Russell King - ARM Linux
2017-11-01 17:53 ` Alan Cox
2017-11-01 19:03   ` Marc Gonzalez
2017-11-01 19:09     ` Linus Torvalds
2017-11-01 19:17       ` Linus Torvalds
2017-11-01 19:38       ` Marc Gonzalez
2017-11-15 12:51         ` Marc Gonzalez [this message]
2017-11-15 13:13           ` Russell King - ARM Linux
2017-11-16 15:26             ` Marc Gonzalez
2017-11-16 15:36               ` Russell King - ARM Linux
2017-11-16 15:47                 ` Marc Gonzalez
2017-11-16 16:08                   ` Nicolas Pitre
2017-11-16 16:26                     ` Marc Gonzalez
2017-11-16 16:32                       ` Russell King - ARM Linux
2017-11-16 16:42                         ` Marc Gonzalez
2017-11-16 17:05                           ` Russell King - ARM Linux
2017-11-16 21:05                             ` Marc Gonzalez
2017-11-16 22:15                               ` Doug Anderson
2017-11-16 23:22                                 ` Russell King - ARM Linux
2017-11-20 17:38                                   ` Doug Anderson
2017-11-20 18:31                                     ` Russell King - ARM Linux
2017-11-16 16:47                       ` Nicolas Pitre
2017-11-16 16:51                         ` Marc Gonzalez
2017-11-16 17:00                           ` Nicolas Pitre
2017-12-07 12:43             ` Pavel Machek
2017-11-15 18:45           ` Doug Anderson
2017-11-01 19:36     ` Alan Cox
2017-11-01 19:39     ` Thomas Gleixner
2017-11-01 19:48     ` Baruch Siach
2017-11-02 16:12       ` Boris Brezillon

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=11393e07-b042-180c-3bcd-484bf51eada6@sigmadesigns.com \
    --to=marc_gonzalez@sigmadesigns.com \
    --cc=arnd@arndb.de \
    --cc=boris.brezillon@free-electrons.com \
    --cc=dianders@chromium.org \
    --cc=gnomes@lxorguk.ukuu.org.uk \
    --cc=john.stultz@linaro.org \
    --cc=jonathan.austin@arm.com \
    --cc=khilman@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@arm.linux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=mingo@kernel.org \
    --cc=mturquette@baylibre.com \
    --cc=nico@linaro.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sboyd@codeaurora.org \
    --cc=slash.tmp@free.fr \
    --cc=tglx@linutronix.de \
    --cc=thibaud_cornic@sigmadesigns.com \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    /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;
as well as URLs for NNTP newsgroup(s).