2007-02-17 16:08:54

by Stephane Eranian

Subject: [PATCH] x86_64 make NMI use PERFCTR1 for architectural perfmon

Hello,

This patch against 2.6.20 makes the NMI watchdog use PERFSEL1/PERFCTR1
instead of PERFSEL0/PERFCTR0 on processors supporting Intel architectural
perfmon, such as Intel Core 2. Although all PMU events can work on
both counters, the Precise Event-Based Sampling (PEBS) requires that the
event be in PERFCTR0 to work correctly (see section 18.14.4.1 in the
IA32 SDM Vol 3b).

Changelog:
- make the x86_64 NMI watchdog use PERFSEL1/PERFCTR1 instead of PERFSEL0/PERFCTR0
on processors supporting the Intel architectural perfmon (e.g. Core 2 Duo).
This allows PEBS to work when the NMI watchdog is active.

signed-off-by: stephane eranian <[email protected]>

diff -urNp --exclude=.git linux-2.6.20.orig/arch/x86_64/kernel/nmi.c linux-2.6.20.base/arch/x86_64/kernel/nmi.c
--- linux-2.6.20.orig/arch/x86_64/kernel/nmi.c 2007-02-04 10:44:54.000000000 -0800
+++ linux-2.6.20.base/arch/x86_64/kernel/nmi.c 2007-02-17 08:04:19.000000000 -0800
@@ -275,7 +275,7 @@ int __init check_nmi_watchdog (void)
* 32nd bit should be 1, for 33.. to be 1.
* Find the appropriate nmi_hz
*/
- if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 &&
+ if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1 &&
((u64)cpu_khz * 1000) > 0x7fffffffULL) {
nmi_hz = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1;
}
@@ -615,8 +615,8 @@ static int setup_intel_arch_watchdog(voi
(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
goto fail;

- perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
- evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
+ perfctr_msr = MSR_ARCH_PERFMON_PERFCTR1;
+ evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL1;

if (!reserve_perfctr_nmi(perfctr_msr))
goto fail;
@@ -855,7 +855,7 @@ int __kprobes nmi_watchdog_tick(struct p
dummy &= ~P4_CCCR_OVF;
wrmsrl(wd->cccr_msr, dummy);
apic_write(APIC_LVTPC, APIC_DM_NMI);
- } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+ } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) {
/*
* ArchPerfom/Core Duo needs to re-unmask
* the apic vector

2007-02-19 22:34:13

by Stephane Eranian

Subject: Re: [PATCH] x86_64 make NMI use PERFCTR1 for architectural perfmon (take 2)

Hello,

This patch against 2.6.20-git14 makes the NMI watchdog use PERFSEL1/PERFCTR1
instead of PERFSEL0/PERFCTR0 on processors supporting Intel architectural
perfmon, such as Intel Core 2. Although all PMU events can work on
both counters, the Precise Event-Based Sampling (PEBS) requires that the
event be in PERFCTR0 to work correctly (see section 18.14.4.1 in the
IA32 SDM Vol 3b). This versions has 3 chunks compared to previous where
we had missed on check.

Changelog:
- make the x86-64 NMI watchdog use PERFSEL1/PERFCTR1 instead of PERFSEL0/PERFCTR0
on processors supporting the Intel architectural perfmon (e.g. Core 2 Duo).
This allows PEBS to work when the NMI watchdog is active.

signed-off-by: stephane eranian <[email protected]>


diff -urNp --exclude=.git linux-2.6.20.orig/arch/x86_64/kernel/nmi.c linux-2.6.20.base/arch/x86_64/kernel/nmi.c
--- linux-2.6.20.orig/arch/x86_64/kernel/nmi.c 2007-02-19 13:37:27.000000000 -0800
+++ linux-2.6.20.base/arch/x86_64/kernel/nmi.c 2007-02-19 14:27:45.000000000 -0800
@@ -285,7 +285,7 @@ int __init check_nmi_watchdog (void)
struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

nmi_hz = 1;
- if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0)
+ if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1)
nmi_hz = adjust_for_32bit_ctr(nmi_hz);
}

@@ -650,8 +650,8 @@ static int setup_intel_arch_watchdog(voi
(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
goto fail;

- perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
- evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
+ perfctr_msr = MSR_ARCH_PERFMON_PERFCTR1;
+ evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL1;

if (!reserve_perfctr_nmi(perfctr_msr))
goto fail;
@@ -895,7 +895,7 @@ int __kprobes nmi_watchdog_tick(struct p
/* start the cycle over again */
wrmsrl(wd->perfctr_msr,
-((u64)cpu_khz * 1000 / nmi_hz));
- } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+ } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) {
/*
* ArchPerfom/Core Duo needs to re-unmask
* the apic vector