diff mbox

[04/17] ACPI, APEI, GHES, Do not ratelimit fatal error printk before panic

Message ID 1310534068-30547-5-git-send-email-ying.huang@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Huang, Ying July 13, 2011, 5:14 a.m. UTC
printk is used by GHES to report hardware errors.  Normally, the
printk will be ratelimited to avoid too many hardware error reports in
kernel log.  Because there may be thousands or even millions of
corrected hardware errors during system running.

That is different for fatal hardware error, because system will go
panic as soon as possible, there will be no more than several error
records.  And these error records are valuable for system fault
diagnosis, so they should not be ratelimited.

Signed-off-by: Huang Ying <ying.huang@intel.com>
---
 drivers/acpi/apei/ghes.c |   25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Len Brown July 14, 2011, 3:33 a.m. UTC | #1
applied

thanks,
Len Brown, Intel Open Source Technology Center

--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -360,11 +360,8 @@  static void ghes_do_proc(struct ghes *gh
 	}
 }
 
-static void ghes_print_estatus(const char *pfx, struct ghes *ghes)
+static void __ghes_print_estatus(const char *pfx, struct ghes *ghes)
 {
-	/* Not more than 2 messages every 5 seconds */
-	static DEFINE_RATELIMIT_STATE(ratelimit, 5*HZ, 2);
-
 	if (pfx == NULL) {
 		if (ghes_severity(ghes->estatus->error_severity) <=
 		    GHES_SEV_CORRECTED)
@@ -372,12 +369,18 @@  static void ghes_print_estatus(const cha
 		else
 			pfx = KERN_ERR HW_ERR;
 	}
-	if (__ratelimit(&ratelimit)) {
-		printk(
-	"%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
-	pfx, ghes->generic->header.source_id);
-		apei_estatus_print(pfx, ghes->estatus);
-	}
+	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
+	       pfx, ghes->generic->header.source_id);
+	apei_estatus_print(pfx, ghes->estatus);
+}
+
+static void ghes_print_estatus(const char *pfx, struct ghes *ghes)
+{
+	/* Not more than 2 messages every 5 seconds */
+	static DEFINE_RATELIMIT_STATE(ratelimit, 5*HZ, 2);
+
+	if (__ratelimit(&ratelimit))
+		__ghes_print_estatus(pfx, ghes);
 }
 
 static int ghes_proc(struct ghes *ghes)
@@ -476,7 +479,7 @@  static int ghes_notify_nmi(struct notifi
 
 	if (sev_global >= GHES_SEV_PANIC) {
 		oops_begin();
-		ghes_print_estatus(KERN_EMERG HW_ERR, ghes_global);
+		__ghes_print_estatus(KERN_EMERG HW_ERR, ghes_global);
 		/* reboot to log the error! */
 		if (panic_timeout == 0)
 			panic_timeout = ghes_panic_timeout;