2009-06-25 23:45:04

by Pallipadi, Venkatesh

[permalink] [raw]
Subject: [PATCH] x86: tsc based udelay should have rdtsc_barrier


delay_tsc needs rdtsc_barrier to provide proper delay.

Output from a test driver using hpet to cross check delay
provided by udelay().

Before:
[ 86.794363] Expected delay 5us actual 4679ns
[ 87.154362] Expected delay 5us actual 698ns
[ 87.514162] Expected delay 5us actual 4539ns
[ 88.653716] Expected delay 5us actual 4539ns
[ 94.664106] Expected delay 10us actual 9638ns
[ 95.049351] Expected delay 10us actual 10126ns
[ 95.416110] Expected delay 10us actual 9568ns
[ 95.799216] Expected delay 10us actual 9638ns
[ 103.624104] Expected delay 10us actual 9707ns
[ 104.020619] Expected delay 10us actual 768ns
[ 104.419951] Expected delay 10us actual 9707ns

After:
[ 50.983320] Expected delay 5us actual 5587ns
[ 51.261807] Expected delay 5us actual 5587ns
[ 51.565715] Expected delay 5us actual 5657ns
[ 51.861171] Expected delay 5us actual 5587ns
[ 52.164704] Expected delay 5us actual 5726ns
[ 52.487457] Expected delay 5us actual 5657ns
[ 52.789338] Expected delay 5us actual 5726ns
[ 57.119680] Expected delay 10us actual 10755ns
[ 57.893997] Expected delay 10us actual 10615ns
[ 58.261287] Expected delay 10us actual 10755ns
[ 58.620505] Expected delay 10us actual 10825ns
[ 58.941035] Expected delay 10us actual 10755ns
[ 59.320903] Expected delay 10us actual 10615ns
[ 61.306311] Expected delay 10us actual 10755ns
[ 61.520542] Expected delay 10us actual 10615ns


Signed-off-by: Venkatesh Pallipadi <[email protected]>
---
arch/x86/lib/delay.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index f456860..ff485d3 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -55,8 +55,10 @@ static void delay_tsc(unsigned long loops)

preempt_disable();
cpu = smp_processor_id();
+ rdtsc_barrier();
rdtscl(bclock);
for (;;) {
+ rdtsc_barrier();
rdtscl(now);
if ((now - bclock) >= loops)
break;
@@ -78,6 +80,7 @@ static void delay_tsc(unsigned long loops)
if (unlikely(cpu != smp_processor_id())) {
loops -= (now - bclock);
cpu = smp_processor_id();
+ rdtsc_barrier();
rdtscl(bclock);
}
}
--
1.6.0.6


2009-06-26 07:25:22

by Ingo Molnar

[permalink] [raw]
Subject: Re: [PATCH] x86: tsc based udelay should have rdtsc_barrier


* Pallipadi, Venkatesh <[email protected]> wrote:

>
> delay_tsc needs rdtsc_barrier to provide proper delay.
>
> Output from a test driver using hpet to cross check delay
> provided by udelay().
>
> Before:
> [ 86.794363] Expected delay 5us actual 4679ns
> [ 87.154362] Expected delay 5us actual 698ns
> [ 87.514162] Expected delay 5us actual 4539ns
> [ 88.653716] Expected delay 5us actual 4539ns
> [ 94.664106] Expected delay 10us actual 9638ns
> [ 95.049351] Expected delay 10us actual 10126ns
> [ 95.416110] Expected delay 10us actual 9568ns
> [ 95.799216] Expected delay 10us actual 9638ns
> [ 103.624104] Expected delay 10us actual 9707ns
> [ 104.020619] Expected delay 10us actual 768ns
> [ 104.419951] Expected delay 10us actual 9707ns
>
> After:
> [ 50.983320] Expected delay 5us actual 5587ns
> [ 51.261807] Expected delay 5us actual 5587ns
> [ 51.565715] Expected delay 5us actual 5657ns
> [ 51.861171] Expected delay 5us actual 5587ns
> [ 52.164704] Expected delay 5us actual 5726ns
> [ 52.487457] Expected delay 5us actual 5657ns
> [ 52.789338] Expected delay 5us actual 5726ns
> [ 57.119680] Expected delay 10us actual 10755ns
> [ 57.893997] Expected delay 10us actual 10615ns
> [ 58.261287] Expected delay 10us actual 10755ns
> [ 58.620505] Expected delay 10us actual 10825ns
> [ 58.941035] Expected delay 10us actual 10755ns
> [ 59.320903] Expected delay 10us actual 10615ns
> [ 61.306311] Expected delay 10us actual 10755ns
> [ 61.520542] Expected delay 10us actual 10615ns

Nice fix!

Ingo