gcpu_amd.esc revision b7d3956b92a285d8dac2c7f5f7e28d2ef5347ef8
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2008 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#pragma ident "%Z%%M% %I% %E% SMI"
/*
* Eversholt rules for generic AMD with on-chip memory-controller(s), as seen
* in AMD family 0xf and 0x10.
*
* In the absence of any model-specific support, any memory errors that
* are observed via MCA (typically through an on-chip memory-controller)
* will surface as ereport.cpu.generic-x86.bus_interconnect_memory[_uc]
* ereports and are diagnosed via generic rules in gcpu.esc.
*
* If full model-specific support is available, including full NorthBridge
* support, then memory ereports will surface in a more-specific subclass
* such as ereport.cpu.amd.mem_ce; these are diagnosed in amd64.esc.
*
* In the case where some "vendor generic" support is present, memory errors
* are reported as ereport.cpu.generic-x86.mem_{ce,ue} and include a
* syndrome and syndrome-type, and usually also a resource FMRI to identify
* the affected resource. In the AMD case a resource FMRI is included for
* those chip versions that include an Online Spare Control register; this
* register provides counts of ECC errors seen per channel and chip-select
* on a NorthBridge node. The resource FMRI has form
* hc:///motherboard/chip/memory-controller/dram-channel/chip-select
* in these cases.
*/
#pragma dictionary "GMCA"
/*
* The number of pages that must be faulted on a chip-select for repeated
* correctable errors before we will consider one of the component dimms
* faulty.
*/
#define CS_DIMMSB_THRESH 64
/*
* The maximum number of pages we will diagnose as faulty on any one
* chip-select (must be at least CS_PAGEFLT_THRESH). If a chip-select
* has a fault that will affect zillions of pages this limit stops us
* diagnosing excessive numbers of page faults.
*/
#define CS_PAGEFLT_MAX (2 * CS_DIMMSB_THRESH)
/*
* SERD paramters for individual page faults. When more than PAGE_SB_COUNT
* correctable ereports are experienced on a single chip-select within
* PAGE_SB_TIME the engine will fire and we will fault the most recent
* page.
*/
#define PAGE_SB_COUNT 3
#define PAGE_SB_TIME 24h
#define CSPATH chip/memory-controller/dram-channel/chip-select
/*
* ADDR_VALID is true if the ereport payload includes IA32_MCi_ADDR.
*/
#define ADDR_VALID (payloadprop_defined("IA32_MCi_ADDR"))
/*
* CONTAINS_CS is true if the resource nvlist array exists and one of its
* members matches the chip-select path. This is used to constrain
* propogations to those for which a resource element matches the
* chip-select path of the propogation. This is necessary because the
* detector element of memory ereports is a cpu and not the chip-select itself.
*/
#define CONTAINS_CS (payloadprop_contains("resource", asru(CSPATH)))
#define SET_ADDR (setpayloadprop("asru-physaddr", payloadprop("IA32_MCi_ADDR")))
/* Generic memory ereports. */
event ereport.cpu.generic-x86.mem_ce@chip/cpu { within(1s) };
event ereport.cpu.generic-x86.mem_ue@chip/cpu { within(1s) };
/*
* ========= Propogations for correctable memory faults ==========
* | |
* | Discard mem_ce with no resource in the ereport payload. |
* | Discard mem_ce with no address info - we can't fault the |
* | corresponding page without it. |
* | |
* | For a mem_ce ereport detected by a given chip/cpu (as per |
* | the payload detector info) whose resource payload member |
* | includes a chip/memory-controller/dram-channel/chip-select |
* | (CSPATH) for the same chip number, diagnose to an fault event |
* | associated with a per-CSPATH SERD engine as long as we are |
* | below the page fault limit for this CSPATH (defined below); |
* | if we are over that limit then discard the event since we |
* | will already have faulted a dimm and there is no point in |
* | continuing to diagnose endless page faults from a dimm with |
* | something like a pin failure. |
* | |
* | When the per-CSPATH SERD engine fires we fault the page |
* | containing the address included in the ereport that caused |
* | the trip, and increment a per-CSPATH counter to count page |
* | faults on that chip-select from repeated correctable errors. |
* | |
* | A dimm_ce fault is diagnosed when we have faulted an |
* | excessive number of page_ce faults on a chip-select - more |
* | than CE_DIMMSB_THRESH. |
* |===============================================================|
*/
#define CS_PGFLT_LIMIT_REACHED (count(stat.cepgflt@CSPATH) > CS_PAGEFLT_MAX)
#define CS_DIMMSB_THRESH_REACHED \
(count(stat.cepgflt@CSPATH) >= CS_DIMMSB_THRESH)
engine stat.cepgflt@CSPATH;
engine serd.memory.generic-x86.page_ce@CSPATH, N=PAGE_SB_COUNT, T=PAGE_SB_TIME;
event fault.memory.generic-x86.page_ce@CSPATH,
message=0, response=0, /* do not message individual pageflts */
count=stat.cepgflt@CSPATH, /* increment on pageflt diagnosis */
engine=serd.memory.generic-x86.page_ce@CSPATH;
engine serd.memory.generic-x86.dimm_ce@CSPATH, N=PAGE_SB_COUNT, T=PAGE_SB_TIME;
event fault.memory.generic-x86.dimm_ce@CSPATH,
engine=serd.memory.generic-x86.dimm_ce@CSPATH;
prop fault.memory.generic-x86.page_ce@CSPATH
{ ADDR_VALID && CONTAINS_CS && !CS_PGFLT_LIMIT_REACHED && SET_ADDR } (1)->
ereport.cpu.generic-x86.mem_ce@chip/cpu;
prop fault.memory.generic-x86.dimm_ce@CSPATH
{ ADDR_VALID && CONTAINS_CS && CS_DIMMSB_THRESH_REACHED } (1)->
ereport.cpu.generic-x86.mem_ce@chip/cpu;
event upset.memory.generic-x86.discard@chip/cpu;
prop upset.memory.generic-x86.discard@chip/cpu
{ !payloadprop_defined("resource") || !ADDR_VALID } (1)->
ereport.cpu.generic-x86.mem_ce@chip/cpu;
/*
* ========= Propogations for uncorrectable page faults ==========
* | |
* | A UE produces an immediate page fault.
* |===============================================================|
*/
event fault.memory.generic-x86.page_ue@CSPATH,
message=0, response=0, /* do not message individual pageflts */
count=stat.cepgflt@CSPATH; /* increment on pageflt diagnosis */
event fault.memory.generic-x86.dimm_ue@CSPATH;
prop fault.memory.generic-x86.page_ue@CSPATH
{ ADDR_VALID && CONTAINS_CS && SET_ADDR } (1)->
ereport.cpu.generic-x86.mem_ue@chip/cpu;
prop fault.memory.generic-x86.dimm_ue@CSPATH
{ ADDR_VALID && CONTAINS_CS } (1)->
ereport.cpu.generic-x86.mem_ue@chip/cpu;
event upset.memory.generic-x86.discard3@CSPATH;
prop upset.memory.generic-x86.discard3@CSPATH
{ !payloadprop_defined("resource") || !ADDR_VALID } (1)->
ereport.cpu.generic-x86.mem_ue@chip/cpu;
/*
* ========= Propogations for GART Table Walk Errors =============
* | |
* | These are usually due to software mis-programming of the GART |
* | TLB rather than from hardware errors. It would be incorrect |
* | to fault and potentially offline a cpu in response to these |
* | so they have their own fault class to facilitate us ignoring |
* | them. |
* |===============================================================|
*/
event ereport.cpu.generic-x86.gart_tbl_walk@chip/cpu { within(1s) };
event upset.cpu.generic-x86.gart_tbl_walk@chip/cpu;
prop upset.cpu.generic-x86.gart_tbl_walk@chip/cpu (1)->
ereport.cpu.generic-x86.gart_tbl_walk@chip/cpu;