Errata
Intel
®
Core™2 Extreme Quad-Core Processor QX6000
Δ
Sequence and
29
Intel
®
Core™2 Quad Processor Q6000
Δ
Sequence
Specification Update
Implication:
Due to this erratum, the processor may transfer control to an unintended
address. The result of fetching code at that address is unpredictable and may
include an unexpected trap or fault, or execution of the instructions found
there.
Workaround:
If the last page of the positive canonical address space is not allocated for
code (4K page at 00007ffffffff000 or 2M page at 00007fffffe00000) then the
problem cannot occur.
Status:
For the steppings affected, see the Summary Tables of Changes.
AK23.
VMCALL to Activate Dual-monitor Treatment of SMIs and SMM
Ignores Reserved Bit settings in VM-exit Control Field
Problem:
Processors supporting Intel
®
Virtualization Technology can execute VMCALL
from within the Virtual Machine Monitor (VMM) to activate dual-monitor
treatment of SMIs and SMM. Due to this erratum, if reserved bits are set to
values inconsistent with VMX Capability MSRs, VMCALL may not VMFail.
Implication:
VMCALL executed to activate dual-monitor treatment of SMIs and SMM may
not VMFail due to incorrect reserved bit settings in VM-Exit control field.
Workaround:
Software should ensure that all VMCS reserved bits are set to values
consistent with VMX Capability MSRs.
Status:
For the steppings affected, see the Summary Tables of Changes.
AK24.
The PECI Controller Resets to the Idle State
Problem:
After reset, the Platform Environment Control Interface (PECI) client
controller should first identify a PECI bus idle condition and only then search
for the first rising edge. Due to this erratum, the processor PECI controller
resets into the "Idle Detected" state upon processor reset. If another PECI
device on the platform is attempting to send a message as the processor
PECI controller comes out of reset, the processor PECI controller will typically
experience a Frame Check Sequence error and move to the idle state. Rarely,
the processor PECI controller may interpret that the message was intended
for it and try to reply. In this case a message may be corrupted but this
situation will be caught and handled by the PECI error handling protocol.
Implication:
The processor PECI controller resets to an incorrect state but the error handling
capability of PECI will resolve the situation so that the processor will be able to
respond to an incoming message immediately after reset and will not disregard
an incoming message that arrives before an idle bus is formally detected.
Workaround:
No workaround is necessary due to the PECI error handling protocol.
Status:
For the steppings affected, see the Summary Tables of Changes.