64-bit Intel Xeon Processor MP with 1 MB L2 Cache Specification Update

18 64-bit Intel
®
Xeon
®
Processor MP with up to 1 MB L2 Cache Specification Update
Errata
• If a memory access receives a machine check error on both 64 byte halves of a 128-byte L2
cache sector, the IA32_MC0_STATUS register records this event as multiple errors, i.e., the
valid error bit and the overflow error bit are both set indicating that a machine check error
occurred while the results of a previous error were in the error-reporting bank. The
IA32_MC1_STATUS register should also record this event as multiple errors but instead
records this event as only one correctable error.
• The overflow bit should be set to indicate when more than one error has occurred. The
overflow bit being set indicates that more than one error has occurred. Because of this erratum,
if any further errors occur, the MCA overflow bit will not be updated, thereby incorrectly
indicating only one error has been received.
• If an I/O instruction (IN, INS, REP INS, OUT, OUTS, or REP OUTS) is being executed, and if
the data for this instruction become corrupted, the processor will signal a Machine Check
Exception (MCE). If the instruction is directed at a device that is powered down, the processor
may also receive an assertion of SMI#. Since MCEs have higher priority, the processor will
call the MCE handler, and the SMI# assertion will remain pending. However, while attempting
to execute the first instruction of the MCE handler, the SMI# will be recognized and the
processor will attempt to execute the SMM handler. If the SMM handler is successfully
completed, it will attempt to restart the I/O instruction, but will not have the correct machine
state due to the call to the MCE handler. This can lead to failure of the restart and shutdown of
the processor.
• If PWRGOOD is de-asserted during a RESET# assertion causing internal glitches, the MCA
registers may latch invalid information.
• If RESET# is asserted, then de-asserted, and reasserted, before the processor has cleared the
MCA registers, then the information in the MCA registers may not be reliable, regardless of
the state or state transitions of PWRGOOD.
• If MCERR# is asserted by one processor and observed by another processor, the observing
processor does not log the assertion of MCERR#. The Machine Check Exception (MCE)
handler called upon assertion of MCERR# will not have any way to determine the cause of the
MCE.
• The Overflow Error bit (bit 62) in the IA32_MC0_STATUS register indicates, when set, that a
machine check error occurred while the results of a previous error were still in the error
reporting bank (i.e. The Valid bit was set when the new error occurred). If an uncorrectable
error is logged in the error-reporting bank and another error occurs, the overflow bit will not be
set.
• The MCA Error Code field of the IA32_MC0_STATUS register gets written by a different
mechanism than the rest of the register. For uncorrectable errors, the other fields in the
IA32_MC0_STATUS register are only updated by the first error. Any further errors that are
detected will update the MCA Error Code field without updating the rest of the register,
thereby leaving the IA32_MC0_STATUS register with stale information.
• When a speculative load operation hits the L2 cache and receives a correctable error, the
IA32_MC1_Status Register may be updated with incorrect information. The
IA32_MC1_Status Register should not be updated for speculative loads.
• The processor should only log the address for L1 parity errors in the IA32_MC1_Status
register if a valid address is available. If a valid address is not available, the Address Valid bit
in the IA32_MC1_Status register should not be set. In instances where an L1 parity error
occurs and the address is not available because the linear to physical address translation is not
complete or an internal resource conflict has occurred, the Address Valid bit is incorrectly set.
• The processor may hang when an instruction code fetch receives a hard failure response from
the Front Side Bus. This occurs because the bus control logic does not return data to the core,
leaving the processor empty. IA32_MC0_STATUS MSR does indicate that a hard fail
response occurred.