Re: [PATCH v2] x86/mce: Include the PPIN in machine check records when it is available

From: Borislav Petkov
Date: Wed Nov 23 2016 - 06:49:04 EST


On Fri, Nov 18, 2016 at 09:48:36AM -0800, Luck, Tony wrote:
> From: Tony Luck <tony.luck@xxxxxxxxx>
>
> Intel Xeons from Ivy Bridge onwards support a processor identification
> number set in the factory. To the user this is a handy unique number to
> identify a particular cpu. Intel can decode this to the fab/production
> run to track errors. On systems that have it, include it in the machine
> check record. I'm told that this would be helpful for users that run
> large data centers with multi-socket servers to keep track of which
> CPUs are seeing errors.
>
> Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
> ---
>
> Boris:
> Moved feature detection to mce_intel.c
> Use feature bit.
> Don't spam console if feature is disabled
> Program defensively against future bits in MSR_PPIN_CTL
> Updated commit comment to note the PPIN is set in factory
>
> Andi:
> Dynamic feature bits don't impact tiny kernels (well we
> are using one *bit* so this could contribute to NCAPINTS
> someday needing to be increased).
>
> arch/x86/include/asm/cpufeatures.h | 1 +
> arch/x86/include/asm/msr-index.h | 4 ++++
> arch/x86/include/uapi/asm/mce.h | 1 +
> arch/x86/kernel/cpu/mcheck/mce.c | 3 +++
> arch/x86/kernel/cpu/mcheck/mce_intel.c | 29 +++++++++++++++++++++++++++++
> 5 files changed, 38 insertions(+)

Applied with some minor fixups:

---
From: Tony Luck <tony.luck@xxxxxxxxx>
Date: Fri, 18 Nov 2016 09:48:36 -0800
Subject: [PATCH] x86/mce: Include the PPIN in MCE records when available

Intel Xeons from Ivy Bridge onwards support a processor identification
number set in the factory. To the user this is a handy unique number to
identify a particular CPU. Intel can decode this to the fab/production
run to track errors. On systems that have it, include it in the machine
check record. I'm told that this would be helpful for users that run
large data centers with multi-socket servers to keep track of which CPUs
are seeing errors.

Boris:
* Add some clarifying comments and spacing.
* Mask out [63:2] in the disabled-but-not-locked case
* Call the MSR variable "val" for more readability.

Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Ashok Raj <ashok.raj@xxxxxxxxx>
Cc: linux-edac <linux-edac@xxxxxxxxxxxxxxx>
Cc: x86-ml <x86@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/1479491316-11716-1-git-send-email-tony.luck@xxxxxxxxx
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
---
arch/x86/include/asm/cpufeatures.h | 1 +
arch/x86/include/asm/msr-index.h | 4 ++++
arch/x86/include/uapi/asm/mce.h | 1 +
arch/x86/kernel/cpu/mcheck/mce.c | 4 ++++
arch/x86/kernel/cpu/mcheck/mce_intel.c | 37 ++++++++++++++++++++++++++++++++++
5 files changed, 47 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a39629206864..d625b651e526 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -193,6 +193,7 @@
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */

+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 78f3760ca1f2..710273c617b8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -37,6 +37,10 @@
#define EFER_FFXSR (1<<_EFER_FFXSR)

/* Intel MSRs. Some also available on other CPUs */
+
+#define MSR_PPIN_CTL 0x0000004e
+#define MSR_PPIN 0x0000004f
+
#define MSR_IA32_PERFCTR0 0x000000c1
#define MSR_IA32_PERFCTR1 0x000000c2
#define MSR_FSB_FREQ 0x000000cd
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 69a6e07e3149..eb6247a7009b 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -28,6 +28,7 @@ struct mce {
__u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
__u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */
__u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
+ __u64 ppin; /* Protected Processor Inventory Number */
};

#define MCE_GET_RECORD_LEN _IOR('M', 1, int)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index aab96f8d52b0..a3cb27af4f9b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -43,6 +43,7 @@
#include <linux/export.h>
#include <linux/jump_label.h>

+#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
@@ -135,6 +136,9 @@ void mce_setup(struct mce *m)
m->socketid = cpu_data(m->extcpu).phys_proc_id;
m->apicid = cpu_data(m->extcpu).initial_apicid;
rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
+
+ if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
+ rdmsrl(MSR_PPIN, m->ppin);
}

DEFINE_PER_CPU(struct mce, injectm);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index be0b2fad47c5..1faefb696af8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -11,6 +11,8 @@
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <asm/apic.h>
+#include <asm/cpufeature.h>
+#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/mce.h>
@@ -464,11 +466,46 @@ static void intel_clear_lmce(void)
wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
}

+static void intel_ppin_init(struct cpuinfo_x86 *c)
+{
+ unsigned long long val;
+
+ /*
+ * Even if testing the presence of the MSR would be enough, we don't
+ * want to risk the situation where other models reuse this MSR for
+ * other purposes.
+ */
+ switch (c->x86_model) {
+ case INTEL_FAM6_IVYBRIDGE_X:
+ case INTEL_FAM6_HASWELL_X:
+ case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_X:
+ case INTEL_FAM6_SKYLAKE_X:
+ if (rdmsrl_safe(MSR_PPIN_CTL, &val))
+ return;
+
+ if ((val & 3ul) == 1ul) {
+ /* PPIN available but disabled: */
+ return;
+ }
+
+ /* if PPIN is disabled, but not locked, try to enable: */
+ if (!(val & 3ul)) {
+ wrmsrl_safe(MSR_PPIN_CTL, val | 2ul);
+ rdmsrl_safe(MSR_PPIN_CTL, &val);
+ }
+
+ if ((val & 3ul) == 2ul)
+ set_cpu_cap(c, X86_FEATURE_INTEL_PPIN);
+ }
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
intel_init_lmce();
+ intel_ppin_init(c);
}

void mce_intel_feature_clear(struct cpuinfo_x86 *c)
--
2.10.0

SUSE Linux GmbH, GF: Felix ImendÃrffer, Jane Smithard, Graham Norton, HRB 21284 (AG NÃrnberg)
--