From: Daniel Walker <dwalker@mvista.com>
To: kus Kusche Klaus <kus@keba.com>
Cc: Ingo Molnar <mingo@elte.hu>, Lee Revell <rlrevell@joe-job.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: RE: Latency traces I cannot interpret (sa1100, 2.6.15-rc7-rt1)
Date: Mon, 02 Jan 2006 08:07:18 -0800 [thread overview]
Message-ID: <1136218038.22548.19.camel@localhost.localdomain> (raw)
In-Reply-To: <AAD6DA242BC63C488511C611BD51F367323310@MAILIT.keba.co.at>
[-- Attachment #1: Type: text/plain, Size: 763 bytes --]
Here's a more updated patch, the should replace the other patch I sent.
I think the tracing error is the result of a missed interrupt enable in
the ARM assembly code. I've only compile tested this.
Daniel
On Mon, 2006-01-02 at 15:55 +0100, kus Kusche Klaus wrote:
> > From: Daniel Walker
> > Right .. I'm still looking into it. ARM is just missing some vital
> > tracing bits I think .
>
> As I wrote in some earlier mail, I'm probably the first one ever
> who tried it on ARM: When I tried first, tracing didn't work at all,
> because the trace timing macro's were not defined (at least for
> sa1100). I quick-hacked the three missing macros (this caused the
> tracer to produce at least some output) without checking if
> anything else is missing.
>
>
[-- Attachment #2: fix_tracing_arm_idle_loop.patch --]
[-- Type: text/x-patch, Size: 1523 bytes --]
Index: linux-2.6.14/arch/arm/kernel/process.c
===================================================================
--- linux-2.6.14.orig/arch/arm/kernel/process.c
+++ linux-2.6.14/arch/arm/kernel/process.c
@@ -89,12 +89,12 @@ void default_idle(void)
if (hlt_counter)
cpu_relax();
else {
- raw_local_irq_disable();
+ __raw_local_irq_disable();
if (!need_resched()) {
timer_dyn_reprogram();
arch_idle();
}
- raw_local_irq_enable();
+ __raw_local_irq_enable();
}
}
@@ -121,8 +121,10 @@ void cpu_idle(void)
if (!idle)
idle = default_idle;
leds_event(led_idle_start);
+ __preempt_enable_no_resched();
while (!need_resched())
idle();
+ preempt_disable();
leds_event(led_idle_end);
__preempt_enable_no_resched();
__schedule();
Index: linux-2.6.14/arch/arm/kernel/entry-header.S
===================================================================
--- linux-2.6.14.orig/arch/arm/kernel/entry-header.S
+++ linux-2.6.14/arch/arm/kernel/entry-header.S
@@ -38,18 +38,30 @@
#if __LINUX_ARM_ARCH__ >= 6
.macro disable_irq
+#ifdef CONFIG_CRITICAL_IRQSOFF_TIMING
+ b trace_irqs_off
+#endif
cpsid i
.endm
.macro enable_irq
+#ifdef CONFIG_CRITICAL_IRQSOFF_TIMING
+ b trace_irqs_on
+#endif
cpsie i
.endm
#else
.macro disable_irq
+#ifdef CONFIG_CRITICAL_IRQSOFF_TIMING
+ b trace_irqs_off
+#endif
msr cpsr_c, #PSR_I_BIT | SVC_MODE
.endm
.macro enable_irq
+#ifdef CONFIG_CRITICAL_IRQSOFF_TIMING
+ b trace_irqs_on
+#endif
msr cpsr_c, #SVC_MODE
.endm
#endif
next prev parent reply other threads:[~2006-01-02 16:07 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-02 14:55 Latency traces I cannot interpret (sa1100, 2.6.15-rc7-rt1) kus Kusche Klaus
2006-01-02 15:36 ` Daniel Walker
2006-01-02 16:07 ` Daniel Walker [this message]
-- strict thread matches above, loose matches on Subject: below --
2006-01-05 15:32 kus Kusche Klaus
2006-01-04 9:28 kus Kusche Klaus
2006-01-05 14:30 ` Daniel Walker
2006-01-03 15:40 kus Kusche Klaus
2006-01-03 14:57 kus Kusche Klaus
2006-01-03 15:01 ` Daniel Walker
2006-01-03 8:00 kus Kusche Klaus
2006-01-03 14:16 ` Daniel Walker
2006-01-03 7:27 kus Kusche Klaus
2006-01-02 14:39 kus Kusche Klaus
2006-01-02 14:44 ` Daniel Walker
2006-01-02 7:57 kus Kusche Klaus
2006-01-02 14:14 ` Daniel Walker
2005-12-30 12:40 kus Kusche Klaus
2005-12-30 13:35 ` Daniel Walker
2005-12-30 11:18 kus Kusche Klaus
2005-12-30 10:59 kus Kusche Klaus
2005-12-30 10:35 kus Kusche Klaus
2005-12-30 8:02 kus Kusche Klaus
2005-12-30 7:42 Kai Geek
2005-12-30 18:46 ` Lee Revell
2005-12-30 6:35 kus Kusche Klaus
2005-12-29 15:08 kus Kusche Klaus
2005-12-29 18:25 ` Daniel Walker
2005-12-30 7:29 ` Lee Revell
2005-12-30 7:36 ` Ingo Molnar
2005-12-30 7:44 ` Ingo Molnar
2005-12-30 13:07 ` Daniel Walker
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=1136218038.22548.19.camel@localhost.localdomain \
--to=dwalker@mvista.com \
--cc=kus@keba.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rlrevell@joe-job.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.