| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1294700597-24239-1-git-send-email-mikew@google.com>
Date: Mon, 10 Jan 2011 15:03:17 -0800
From: Mike Waychison <mikew@...gle.com>
To: mingo@...e.hu, borislav.petkov@....com, rdunlap@...otime.net
Cc: linux-kernel@...r.kernel.org, linux-edac@...r.kernel.org,
mikew@...gle.com
Subject: [PATCH] x86: Add an option to disable decoding of MCE
This patch applies to v2.6.37.
Updated with documentation of the new option.
---
On our systems, we do not want to have any "decoders" called on machine
check events. These decoders can easily spam our logs and cause space
problems on machines that have a lot of correctable error events. We
_do_ however want to get the messages delivered via /dev/mcelog for
userland processing.
Introduce an interface "dont_decode" that allows us to skip the
decoders. We always call the decoders by default.
Google-Bug-Id: 3289142
Signed-off-by: Mike Waychison <mikew@...gle.com>
---
Documentation/x86/x86_64/boot-options.txt | 5 +++++
Documentation/x86/x86_64/machinecheck | 6 ++++++
arch/x86/kernel/cpu/mcheck/mce.c | 24 ++++++++++++++++++------
3 files changed, 29 insertions(+), 6 deletions(-)
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 7fbbaf8..dd7145a 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -22,6 +22,11 @@ Machine check
as corrected are silently cleared by OS.
This option will be useful if you have no interest in any
of corrected errors.
+ mce=dont_decode
+ Disable in-kernel decoding of errors. Setting this boot
+ option will cause EDAC to be skipped (if enabled) and no
+ messages to be printed into the logs. Events will still
+ be available via /dev/mcelog however.
mce=ignore_ce
Disable features for corrected errors, e.g. polling timer
and CMCI. All events reported as corrected are not cleared
diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index b1fb302..7ef7003 100644
--- a/Documentation/x86/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
@@ -65,6 +65,12 @@ tolerant
Note this only makes a difference if the CPU allows recovery
from a machine check exception. Current x86 CPUs generally do not.
+dont_decode
+ Disable in-kernel decoding of any errors. Setting this boot
+ option will cause EDAC to be skipped (if enabled) and no
+ messages to be printed into the logs. Events will still be
+ available via /dev/mcelog however.
+
trigger
Program to run when a machine check event is detected.
This is an alternative to running mcelog regularly from cron
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a35b72..3c30057 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -82,6 +82,7 @@ static int mce_bootlog __read_mostly = -1;
static int monarch_timeout __read_mostly = -1;
static int mce_panic_timeout __read_mostly;
static int mce_dont_log_ce __read_mostly;
+static int mce_dont_decode __read_mostly;
int mce_cmci_disabled __read_mostly;
int mce_ignore_ce __read_mostly;
int mce_ser __read_mostly;
@@ -209,6 +210,17 @@ void mce_log(struct mce *mce)
set_bit(0, &mce_need_notify);
}
+static void call_decoders(struct mce *m)
+{
+ if (mce_dont_decode)
+ return;
+ /*
+ * Print out human-readable details about the MCE error,
+ * (if the CPU has an implementation for that)
+ */
+ atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+}
+
static void print_mce(struct mce *m)
{
pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
@@ -234,11 +246,7 @@ static void print_mce(struct mce *m)
pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
- /*
- * Print out human-readable details about the MCE error,
- * (if the CPU has an implementation for that)
- */
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ call_decoders(m);
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -588,7 +596,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
*/
if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
mce_log(&m);
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
+ call_decoders(&m);
add_taint(TAINT_MACHINE_CHECK);
}
@@ -1700,6 +1708,8 @@ static int __init mcheck_enable(char *str)
mce_cmci_disabled = 1;
else if (!strcmp(str, "dont_log_ce"))
mce_dont_log_ce = 1;
+ else if (!strcmp(str, "dont_decode"))
+ mce_dont_decode = 1;
else if (!strcmp(str, "ignore_ce"))
mce_ignore_ce = 1;
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
@@ -1926,6 +1936,7 @@ static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
static SYSDEV_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
static SYSDEV_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
+static SYSDEV_INT_ATTR(dont_decode, 0644, mce_dont_decode);
static struct sysdev_ext_attribute attr_check_interval = {
_SYSDEV_ATTR(check_interval, 0644, sysdev_show_int,
@@ -1949,6 +1960,7 @@ static struct sysdev_attribute *mce_attrs[] = {
&attr_trigger,
&attr_monarch_timeout.attr,
&attr_dont_log_ce.attr,
+ &attr_dont_decode.attr,
&attr_ignore_ce.attr,
&attr_cmci_disabled.attr,
NULL
--
1.7.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists