|
|
Please find attached a patch which filters the panic message from the __print_mce function in mce.c.
The patch is for Centos kernel 3.10.0-1062.9.1.el7.
I would appreciate if something like this could somehow make its way into the mainline kernel - BSD seems to have it for years, why not Linux? I did not encounter any discussions regarding HSD131 or HSW131 in Linux developer areas when searching for this.
Intel_HSD131_etc.patch (2,216 bytes)
--- a/arch/x86/kernel/cpu/mcheck/mce.c.orig 2020-01-31 14:10:36.421882426 +0100
+++ b/arch/x86/kernel/cpu/mcheck/mce.c 2020-01-31 14:13:16.584315314 +0100
@@ -116,6 +116,9 @@
static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
+/* filter false positives from panic pr_emerg */
+static int (*quirk_noprint)(struct mce *m);
+
/*
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
@@ -281,6 +284,9 @@
static void __print_mce(struct mce *m)
{
+ if (quirk_noprint && quirk_noprint(m))
+ return;
+
pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
m->extcpu,
(m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
@@ -321,8 +327,8 @@
static void print_mce(struct mce *m)
{
- __print_mce(m);
- pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
+ __print_mce(m);
+ pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -1570,6 +1576,22 @@
m->cs = regs->cs;
}
+/* detect if mcd should be filtered from printk */
+static int quirk_haswell_hsd131_noprint(struct mce *m)
+{
+ if ( // Intel Haswell notice HSD131
+ m->cpuvendor == X86_VENDOR_INTEL
+ && m->cpuid == 0x306c3
+ && m->bank == 0
+ && (m->status & 0xa0000000ffffffff) == 0x80000000000f0005
+ )
+ {
+ return 1;
+ } else {
+ return 0;
+ }
+}
+
/* Add per CPU specific workarounds here */
static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
{
@@ -1673,6 +1696,16 @@
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
+
+ /* similar to https://svnweb.freebsd.org/changeset/base/281751 */
+ if (c->x86 == 6 && ( c->x86_model == 0x3c /* HSD131, HSM142, HSW131 */
+ || c->x86_model == 0x3d /* BDM48 */
+ || c->x86_model == 0x45
+ || c->x86_model == 0x46 ) /* HSM142 */
+ {
+ pr_info("Detected Haswell CPU. MCE quirk HSD131, HSM142, HSW131, BDM48, or HSM142 enabled.\n");
+ quirk_noprint = quirk_haswell_hsd131_noprint;
+ }
}
if (cfg->monarch_timeout < 0)
cfg->monarch_timeout = 0;
|
|
|
|
Additional information about the erratum is here:
https://trick77.com/qemu-on-haswell-causes-spurious-mce-events/
QEMU on Haswell causes spurious MCE events
Posted on November 4, 2014 by Jan
https://www.linuxquestions.org/questions/linux-hardware-18/hardware-error-this-is-%2Anot%2A-a-software-problem-4175535727/page2.html |
|
|
|
You need to report this on bugzilla.redhat.com. CenTOS is a rebuild of RHEL and aims for bug for bug compatibility with it. To get this fixed in CentOS, first you have to get it fixed in RHEL. |
|
|
|
Reported as https://bugzilla.redhat.com/show_bug.cgi?id=1797205 |
|
|
|
Fix seems to be scheduled for 7.9 |
|
|
|
Fix is in 7.9
The following was logged last in the RHEL bug tracker:
---
errata-xmlrpc 2020-09-29 21:07:02 UTC
Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.
For information on the advisory (Important: kernel security, bug fix, and enhancement update), and where to find the updated
files, follow the link below.
If the solution does not work for you, open a new bug report.
https://access.redhat.com/errata/RHSA-2020:4060 |
|
