Prevent the system from becoming unusable due to a flood of memory error
messages with DECstation and DECsystem models using ECC, that is KN02,
KN03 and KN05 systems. It seems common for gradual oxidation of memory
module contacts to cause memory errors to eventually develop and while
ECC takes care of correcting them and the system affected can continue
operating normally until the contacts have been cleaned, the unlimited
messages make the system spend all its time on producing them, therefore
preventing it from being used.
Rate-limiting removes the load from the system and enables its normal
operation, e.g.:
Bus error interrupt: CPU memory read ECC error at 0x139cfb04
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU partial memory write ECC error at 0x138c1f5c
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU partial memory write ECC error at 0x138c1f6c
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x139cff64
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af00c
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af044
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af0cc
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af0cc
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af0e4
ECC syndrome 0x54 -- corrected single bit error at data bit D3
Bus error interrupt: CPU memory read ECC error at 0x136af104
ECC syndrome 0x54 -- corrected single bit error at data bit D3
dec_ecc_be_backend: 34455 callbacks suppressed
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
---
arch/mips/dec/ecc-berr.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
linux-mips-dec-berr-ratelimit-ecc.diff
Index: linux-macro/arch/mips/dec/ecc-berr.c
===================================================================
--- linux-macro.orig/arch/mips/dec/ecc-berr.c
+++ linux-macro/arch/mips/dec/ecc-berr.c
@@ -5,12 +5,13 @@
* 5000/240 (KN03), 5000/260 (KN05) and DECsystem 5900 (KN03),
* 5900/260 (KN05) systems.
*
- * Copyright (c) 2003, 2005 Maciej W. Rozycki
+ * Copyright (c) 2003, 2005, 2026 Maciej W. Rozycki
*/
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
+#include <linux/ratelimit.h>
#include <linux/sched.h>
#include <linux/types.h>
@@ -51,6 +52,10 @@ static int dec_ecc_be_backend(struct pt_
static const char overstr[] = "overrun";
static const char eccstr[] = "ECC error";
+ static DEFINE_RATELIMIT_STATE(rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
const char *kind, *agent, *cycle, *event;
const char *status = "", *xbit = "", *fmt = "";
unsigned long address;
@@ -70,7 +75,7 @@ static int dec_ecc_be_backend(struct pt_
if (!(erraddr & KN0X_EAR_VALID)) {
/* No idea what happened. */
- printk(KERN_ALERT "Unidentified bus error %s\n", kind);
+ pr_alert_ratelimited("Unidentified bus error %s\n", kind);
return action;
}
@@ -180,12 +185,13 @@ static int dec_ecc_be_backend(struct pt_
}
}
- if (action != MIPS_BE_FIXUP)
+ if (action != MIPS_BE_FIXUP && __ratelimit(&rs)) {
printk(KERN_ALERT "Bus error %s: %s %s %s at %#010lx\n",
kind, agent, cycle, event, address);
- if (action != MIPS_BE_FIXUP && erraddr & KN0X_EAR_ECCERR)
- printk(fmt, " ECC syndrome ", syn, status, xbit, i);
+ if (erraddr & KN0X_EAR_ECCERR)
+ printk(fmt, " ECC syndrome ", syn, status, xbit, i);
+ }
return action;
}
© 2016 - 2026 Red Hat, Inc.