The patch titled
edac i5000: fix error messages
has been added to the -mm tree. Its filename is
edac-i5000-fix-error-messages.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: edac i5000: fix error messages
From: Aristeu Rozanski <aris@xxxxxxxxxx>
Update the i5000_edac messages, making everything pass through the EDAC
(so the log controls will work) and being more specific about the errors.
Also, it makes the miscellaneous errors optional and disabled by default.
As I didn't found anywhere information about M23ERR-M26ERR
(FERR_NF_THERMAL) on FERR_NF_FBD, I'm removing them.
Signed-off-by: Aristeu Rozanski <aris@xxxxxxxxxx>
Signed-off-by: Doug Thompson <dougthompson@xxxxxxxxxxxx>
Cc: Alan Cox <alan@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/edac/i5000_edac.c | 181 +++++++++++++++++++++++-------------
1 file changed, 119 insertions(+), 62 deletions(-)
diff -puN drivers/edac/i5000_edac.c~edac-i5000-fix-error-messages drivers/edac/i5000_edac.c
--- a/drivers/edac/i5000_edac.c~edac-i5000-fix-error-messages
+++ a/drivers/edac/i5000_edac.c
@@ -119,6 +119,7 @@
#define FERR_NF_UNCORRECTABLE (FERR_NF_M12ERR | \
FERR_NF_M11ERR | \
FERR_NF_M10ERR | \
+ FERR_NF_M9ERR | \
FERR_NF_M8ERR | \
FERR_NF_M7ERR | \
FERR_NF_M6ERR | \
@@ -301,6 +302,9 @@ static char *numcol_toString[] = {
};
#endif
+/* enables the report of miscellaneous messages as CE errors - default off */
+static int misc_messages;
+
/* Enumeration of supported devices */
enum i5000_chips {
I5000P = 0,
@@ -466,7 +470,8 @@ static void i5000_process_fatal_error_in
struct i5000_error_info *info,
int handle_errors)
{
- char msg[EDAC_MC_LABEL_LEN + 1 + 90];
+ char msg[EDAC_MC_LABEL_LEN + 1 + 160];
+ char *specific = NULL;
u32 allErrors;
int branch;
int channel;
@@ -480,11 +485,6 @@ static void i5000_process_fatal_error_in
if (!allErrors)
return; /* if no error, return now */
- /* ONLY ONE of the possible error bits will be set, as per the docs */
- i5000_mc_printk(mci, KERN_ERR,
- "FATAL ERRORS Found!!! 1st FATAL Err Reg= 0x%x\n",
- allErrors);
-
branch = EXTRACT_FBDCHAN_INDX(info->ferr_fat_fbd);
channel = branch;
@@ -501,28 +501,27 @@ static void i5000_process_fatal_error_in
rdwr ? "Write" : "Read", ras, cas);
/* Only 1 bit will be on */
- if (allErrors & FERR_FAT_M1ERR) {
- i5000_mc_printk(mci, KERN_ERR,
- "Alert on non-redundant retry or fast "
- "reset timeout\n");
-
- } else if (allErrors & FERR_FAT_M2ERR) {
- i5000_mc_printk(mci, KERN_ERR,
- "Northbound CRC error on non-redundant "
- "retry\n");
-
- } else if (allErrors & FERR_FAT_M3ERR) {
- i5000_mc_printk(mci, KERN_ERR,
- ">Tmid Thermal event with intelligent "
- "throttling disabled\n");
+ switch (allErrors) {
+ case FERR_FAT_M1ERR:
+ specific = "Alert on non-redundant retry or fast "
+ "reset timeout";
+ break;
+ case FERR_FAT_M2ERR:
+ specific = "Northbound CRC error on non-redundant "
+ "retry";
+ break;
+ case FERR_FAT_M3ERR:
+ specific = ">Tmid Thermal event with intelligent "
+ "throttling disabled";
+ break;
}
/* Form out message */
snprintf(msg, sizeof(msg),
"(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d CAS=%d "
- "FATAL Err=0x%x)",
+ "FATAL Err=0x%x (%s))",
branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas,
- allErrors);
+ allErrors, specific);
/* Call the helper to output message */
edac_mc_handle_fbd_ue(mci, rank, channel, channel + 1, msg);
@@ -539,7 +538,8 @@ static void i5000_process_nonfatal_error
struct i5000_error_info *info,
int handle_errors)
{
- char msg[EDAC_MC_LABEL_LEN + 1 + 90];
+ char msg[EDAC_MC_LABEL_LEN + 1 + 170];
+ char *specific = NULL;
u32 allErrors;
u32 ue_errors;
u32 ce_errors;
@@ -557,10 +557,6 @@ static void i5000_process_nonfatal_error
return; /* if no error, return now */
/* ONLY ONE of the possible error bits will be set, as per the docs */
- i5000_mc_printk(mci, KERN_WARNING,
- "NON-FATAL ERRORS Found!!! 1st NON-FATAL Err "
- "Reg= 0x%x\n", allErrors);
-
ue_errors = allErrors & FERR_NF_UNCORRECTABLE;
if (ue_errors) {
debugf0("\tUncorrected bits= 0x%x\n", ue_errors);
@@ -579,12 +575,47 @@ static void i5000_process_nonfatal_error
rank, channel, channel + 1, branch >> 1, bank,
rdwr ? "Write" : "Read", ras, cas);
+ switch (ue_errors) {
+ case FERR_NF_M12ERR:
+ specific = "Non-Aliased Uncorrectable Patrol Data ECC";
+ break;
+ case FERR_NF_M11ERR:
+ specific = "Non-Aliased Uncorrectable Spare-Copy "
+ "Data ECC";
+ break;
+ case FERR_NF_M10ERR:
+ specific = "Non-Aliased Uncorrectable Mirrored Demand "
+ "Data ECC";
+ break;
+ case FERR_NF_M9ERR:
+ specific = "Non-Aliased Uncorrectable Non-Mirrored "
+ "Demand Data ECC";
+ break;
+ case FERR_NF_M8ERR:
+ specific = "Aliased Uncorrectable Patrol Data ECC";
+ break;
+ case FERR_NF_M7ERR:
+ specific = "Aliased Uncorrectable Spare-Copy Data ECC";
+ break;
+ case FERR_NF_M6ERR:
+ specific = "Aliased Uncorrectable Mirrored Demand "
+ "Data ECC";
+ break;
+ case FERR_NF_M5ERR:
+ specific = "Aliased Uncorrectable Non-Mirrored Demand "
+ "Data ECC";
+ break;
+ case FERR_NF_M4ERR:
+ specific = "Uncorrectable Data ECC on Replay";
+ break;
+ }
+
/* Form out message */
snprintf(msg, sizeof(msg),
"(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d "
- "CAS=%d, UE Err=0x%x)",
+ "CAS=%d, UE Err=0x%x (%s))",
branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas,
- ue_errors);
+ ue_errors, specific);
/* Call the helper to output message */
edac_mc_handle_fbd_ue(mci, rank, channel, channel + 1, msg);
@@ -616,51 +647,74 @@ static void i5000_process_nonfatal_error
rank, channel, branch >> 1, bank,
rdwr ? "Write" : "Read", ras, cas);
+ switch (ce_errors) {
+ case FERR_NF_M17ERR:
+ specific = "Correctable Non-Mirrored Demand Data ECC";
+ break;
+ case FERR_NF_M18ERR:
+ specific = "Correctable Mirrored Demand Data ECC";
+ break;
+ case FERR_NF_M19ERR:
+ specific = "Correctable Spare-Copy Data ECC";
+ break;
+ case FERR_NF_M20ERR:
+ specific = "Correctable Patrol Data ECC";
+ break;
+ }
+
/* Form out message */
snprintf(msg, sizeof(msg),
"(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d "
- "CAS=%d, CE Err=0x%x)", branch >> 1, bank,
- rdwr ? "Write" : "Read", ras, cas, ce_errors);
+ "CAS=%d, CE Err=0x%x (%s))", branch >> 1, bank,
+ rdwr ? "Write" : "Read", ras, cas, ce_errors,
+ specific);
/* Call the helper to output message */
edac_mc_handle_fbd_ce(mci, rank, channel, msg);
}
- /* See if any of the thermal errors have fired */
- misc_errors = allErrors & FERR_NF_THERMAL;
- if (misc_errors) {
- i5000_printk(KERN_WARNING, "\tTHERMAL Error, bits= 0x%x\n",
- misc_errors);
- }
-
- /* See if any of the thermal errors have fired */
- misc_errors = allErrors & FERR_NF_NON_RETRY;
- if (misc_errors) {
- i5000_printk(KERN_WARNING, "\tNON-Retry Errors, bits= 0x%x\n",
- misc_errors);
- }
+ if (!misc_messages)
+ return;
- /* See if any of the thermal errors have fired */
- misc_errors = allErrors & FERR_NF_NORTH_CRC;
+ misc_errors = allErrors & (FERR_NF_NON_RETRY | FERR_NF_NORTH_CRC |
+ FERR_NF_SPD_PROTOCOL | FERR_NF_DIMM_SPARE);
if (misc_errors) {
- i5000_printk(KERN_WARNING,
- "\tNORTHBOUND CRC Error, bits= 0x%x\n",
- misc_errors);
- }
+ switch (misc_errors) {
+ case FERR_NF_M13ERR:
+ specific = "Non-Retry or Redundant Retry FBD Memory "
+ "Alert or Redundant Fast Reset Timeout";
+ break;
+ case FERR_NF_M14ERR:
+ specific = "Non-Retry or Redundant Retry FBD "
+ "Configuration Alert";
+ break;
+ case FERR_NF_M15ERR:
+ specific = "Non-Retry or Redundant Retry FBD "
+ "Northbound CRC error on read data";
+ break;
+ case FERR_NF_M21ERR:
+ specific = "FBD Northbound CRC error on "
+ "FBD Sync Status";
+ break;
+ case FERR_NF_M22ERR:
+ specific = "SPD protocol error";
+ break;
+ case FERR_NF_M27ERR:
+ specific = "DIMM-spare copy started";
+ break;
+ case FERR_NF_M28ERR:
+ specific = "DIMM-spare copy completed";
+ break;
+ }
+ branch = EXTRACT_FBDCHAN_INDX(info->ferr_nf_fbd);
- /* See if any of the thermal errors have fired */
- misc_errors = allErrors & FERR_NF_SPD_PROTOCOL;
- if (misc_errors) {
- i5000_printk(KERN_WARNING,
- "\tSPD Protocol Error, bits= 0x%x\n",
- misc_errors);
- }
+ /* Form out message */
+ snprintf(msg, sizeof(msg),
+ "(Branch=%d Err=%#x (%s))", branch >> 1,
+ misc_errors, specific);
- /* See if any of the thermal errors have fired */
- misc_errors = allErrors & FERR_NF_DIMM_SPARE;
- if (misc_errors) {
- i5000_printk(KERN_WARNING, "\tDIMM-Spare Error, bits= 0x%x\n",
- misc_errors);
+ /* Call the helper to output message */
+ edac_mc_handle_fbd_ce(mci, 0, 0, msg);
}
}
@@ -1497,3 +1551,6 @@ MODULE_DESCRIPTION("MC Driver for Intel
module_param(edac_op_state, int, 0444);
MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+module_param(misc_messages, int, 0444);
+MODULE_PARM_DESC(misc_messages, "Log miscellaneous non fatal messages");
+
_
Patches currently in -mm which might be from aris@xxxxxxxxxx are
git-tip.patch
git-security-testing.patch
edac-i5000-fix-error-messages.patch
edac-i5000-fix-thermal-issues.patch
tpm-include-moderated-for-non-subscribers-notation-in-maintainers.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
