1 |
On Saturday 28 Mar 2015 22:48:48 Sebas Pedersen wrote: |
2 |
> On 28-03-2015 07:37 PM, Volker Armin Hemmann wrote: |
3 |
> > Am 28.03.2015 um 23:00 schrieb Sebas Pedersen: |
4 |
> >> On 28-03-2015 06:45 PM, Volker Armin Hemmann wrote: |
5 |
> >>> Am 28.03.2015 um 14:58 schrieb Sebas Pedersen: |
6 |
> >>>> Hi guys, |
7 |
> >>>> |
8 |
> >>>> From a few days ago I am experimenting an MCE error. |
9 |
> >>>> Sometimes I turn on the computer and at some point while booting the |
10 |
> >>>> kernel (after the grub menu) just freezes and puts this: |
11 |
> >>>> |
12 |
> >>>> CPU 0: Machine Check Exception: 4 Bank 4: b200000000070f0f |
13 |
> >>>> TSC f5acc9180 |
14 |
> >>>> PROCESSOR 2:20fc2 TIME 1427486735 SOCKET 0 APIC 0 microcode 0 |
15 |
> >>>> |
16 |
> >>>> the number for TSC may vary, but the b200000000070f0f it's always |
17 |
> >>>> the |
18 |
> >>>> same (at least for now). The error message suggest to parse the |
19 |
> >>>> above |
20 |
> >>>> error with mcelog. I did that and the result was: |
21 |
> >>>> |
22 |
> >>>> Hardware event. This is not a software error. |
23 |
> >>>> CPU 0 4 northbridge TSC f5acc9180 |
24 |
> >>>> TIME 1427486735 Fri Mar 27 17:05:35 2015 |
25 |
> >>>> |
26 |
> >>>> Northbridge Watchdog error |
27 |
> >>>> |
28 |
> >>>> bit57 = processor context corrupt |
29 |
> >>>> bit61 = error uncorrected |
30 |
> >>>> |
31 |
> >>>> bus error 'generic participation, request timed out |
32 |
> >>>> |
33 |
> >>>> generic error mem transaction |
34 |
> >>>> generic access, level generic' |
35 |
> >>>> |
36 |
> >>>> STATUS b200000000070f0f MCGSTATUS 4 |
37 |
> >>>> CPUID Vendor AMD Family 15 Model 44 |
38 |
> >>>> SOCKET 0 APIC 0 microcode 0 |
39 |
> >>>> |
40 |
> >>>> The error suggest it's a hardware problem. I replace de RAM with no |
41 |
> >>>> luck. Same error keeps happening. |
42 |
> >>>> |
43 |
> >>>> Any suggestion for identifying the problem or how to procede? |
44 |
> >>>> |
45 |
> >>>> Many thanks in advance! |
46 |
> >>>> |
47 |
> >>>> Sebas |
48 |
> >>> |
49 |
> >>> bios update/microcode update. A google search suggests that you have |
50 |
> >>> run |
51 |
> >>> into an errata. |
52 |
> >> |
53 |
> >> Oh OK, thank you. Must have miss that in the search. So you are saying |
54 |
> >> that the error comes from a bios errata (and don't know what microdode |
55 |
> >> is), and the fix is to update bios? |
56 |
> > |
57 |
> > no, possibly from a CPU errata and a bios update might bring in the |
58 |
> > microcode update that works around that. |
59 |
> |
60 |
> I see, thanks for clarifying that. So looks like not too many options, |
61 |
> either try to update the bios and/or replace the CPU. |
62 |
> |
63 |
> I really appreciated you replys and time. |
64 |
> |
65 |
> Thanks!, |
66 |
> Sebas |
67 |
|
68 |
There's 'CONFIG_MICROCODE=y' and friends in the kernel which along with sys- |
69 |
apps/microcode-ctl will load what ever is the latest Intel/AMD CPU code |
70 |
(firmware) to patch any bugs with instructions that the CPU manufacturers have |
71 |
discovered. |
72 |
|
73 |
-- |
74 |
Regards, |
75 |
Mick |