lkml.org 
[lkml]   [2004]   [Aug]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: nmi_watchdog=2 and oprofile - Oops with 2.6.8
On Thu, 26 Aug 2004 at 22:59 +0000, Zarakin wrote:

> Oprofile oops'd this time at p4_setup_ctrs - there seems to be one more loop
> that tries to
> access MSR_IQ_ESCR0/1. I did a small change myself and it seems to work
> fine, on both
> SMP&HT and UP kernels. I was able to start oprofile and get profile sample
> data.

Thanks, I missed this one.

I redo the diff, mangled space in last patch, I added the
nmi.c:clear_msr_range() fix. It must go in 2.6.9 imho, please
Andrew apply.

-- phe

--- linux-2.5/arch/i386/kernel/nmi.c~ 2004-06-15 10:52:00.000000000 +0200
+++ linux-2.5/arch/i386/kernel/nmi.c 2004-08-25 17:33:45.000000000 +0200
@@ -376,7 +376,13 @@
clear_msr_range(0x3F1, 2);
/* MSR 0x3F0 seems to have a default value of 0xFC00, but current
docs doesn't fully define it, so leave it alone for now. */
- clear_msr_range(0x3A0, 31);
+ if (boot_cpu_data.x86_model >= 0x3) {
+ /* MSR_P4_IQ_ESCR0/1 (0x3ba/0x3bb) removed */
+ clear_msr_range(0x3A0, 26);
+ clear_msr_range(0x3BC, 3);
+ } else {
+ clear_msr_range(0x3A0, 31);
+ }
clear_msr_range(0x3C0, 6);
clear_msr_range(0x3C8, 6);
clear_msr_range(0x3E0, 2);
--- linux-2.5/arch/i386/oprofile/op_model_p4.c.old 2004-08-25 20:00:56.000000000 +0200
+++ linux-2.5/arch/i386/oprofile/op_model_p4.c 2004-08-27 18:35:16.000000000 +0200
@@ -419,9 +419,28 @@
msrs->controls[i].addr = addr;
}

- /* 43 ESCR registers in three discontiguous group */
+ /* 43 ESCR registers in three or four discontiguous group */
for (addr = MSR_P4_BSU_ESCR0 + stag;
- addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) {
+ addr < MSR_P4_IQ_ESCR0; ++i, addr += addr_increment()) {
+ msrs->controls[i].addr = addr;
+ }
+
+ /* no IQ_ESCR0/1 on some models, we save a seconde time BSU_ESCR0/1
+ * to avoid special case in nmi_{save|restore}_registers() */
+ if (boot_cpu_data.x86_model >= 0x3) {
+ for (addr = MSR_P4_BSU_ESCR0 + stag;
+ addr <= MSR_P4_BSU_ESCR1; ++i, addr += addr_increment()) {
+ msrs->controls[i].addr = addr;
+ }
+ } else {
+ for (addr = MSR_P4_IQ_ESCR0 + stag;
+ addr <= MSR_P4_IQ_ESCR1; ++i, addr += addr_increment()) {
+ msrs->controls[i].addr = addr;
+ }
+ }
+
+ for (addr = MSR_P4_RAT_ESCR0 + stag;
+ addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) {
msrs->controls[i].addr = addr;
}

@@ -553,7 +572,18 @@

/* clear all escrs (including those outside our concern) */
for (addr = MSR_P4_BSU_ESCR0 + stag;
- addr <= MSR_P4_SSU_ESCR0; addr += addr_increment()) {
+ addr < MSR_P4_IQ_ESCR0; addr += addr_increment()) {
+ wrmsr(addr, 0, 0);
+ }
+
+ /* On older models clear also MSR_P4_IQ_ESCR0/1 */
+ if (boot_cpu_data.x86_model < 0x3) {
+ wrmsr(MSR_P4_IQ_ESCR0, 0, 0);
+ wrmsr(MSR_P4_IQ_ESCR1, 0, 0);
+ }
+
+ for (addr = MSR_P4_RAT_ESCR0 + stag;
+ addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) {
wrmsr(addr, 0, 0);
}

-
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/
\
 
 \ /
  Last update: 2005-03-22 14:05    [W:0.462 / U:0.044 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site