|
Description
|
It's seen in snv_96, under X64 (not sure if other platforms have too), some classes of uncorrectable CPU error can't produce an immediate fault diagnosis. The ereport is normally
logged to errlog, but instead of producing a fault, it's fed to a serd engine, as a CE does.
This problem doesn't exist in snv_95.
The ereport payloads are:
Aug 18 2008 07:01:58.639978491 ereport.cpu.amd.bu.l2t_par
nvlist version: 0
class = ereport.cpu.amd.bu.l2t_par
ena = 0x9b62215e2000001
detector = (embedded nvlist)
nvlist version: 0
version = 0x0
scheme = hc
hc-list = (array of embedded nvlists)
(start hc-list[0])
nvlist version: 0
hc-name = motherboard
hc-id = 0
(end hc-list[0])
(start hc-list[1])
nvlist version: 0
hc-name = chip
hc-id = 0
(end hc-list[1])
(start hc-list[2])
nvlist version: 0
hc-name = cpu
hc-id = 0
(end hc-list[2])
(end detector)
compound_errorname = GCACHEL2_SNOOP_ERR
disp = processor_context_corrupt,unconstrained,forcefatal
IA32_MCG_STATUS = 0x7
machine_check_in_progress = 1
ip = 0xfffffffffb84b882
privileged = 0
bank_number = 0x2
bank_msr_offset = 0x408
IA32_MCi_STATUS = 0xb60000000002018a
overflow = 0
error_uncorrected = 1
error_enabled = 1
processor_context_corrupt = 1
error_code = 0x18a
model_specific_error_code = 0x2
IA32_MCi_ADDR = 0x1136e6000
__ttl = 0x1
__tod = 0x48a980d6 0x26254bfb
Serd engine bumps:
NAME >N T CNT DELTA STAT
serd.cpu.amd.l2t_sb@motherboard0/chip0/cpu0 >3 12h 1 6200848470392ns pend
|
