x86, mce: Add boot options for corrected errors

This patch introduces three boot options (no_cmci, dont_log_ce
and ignore_ce) to control handling for corrected errors.

The "mce=no_cmci" boot option disables the CMCI feature.

Since CMCI is a new feature so having boot controls to disable
it will be a help if the hardware is misbehaving.

The "mce=dont_log_ce" boot option disables logging for corrected
errors. All reported corrected errors will be cleared silently.
This option will be useful if you never care about corrected
errors.

The "mce=ignore_ce" boot option disables features for corrected
errors, i.e. polling timer and cmci.  All corrected events are
not cleared and kept in bank MSRs.

Usually this disablement is not recommended, however it will be
a help if there are some conflict with the BIOS or hardware
monitoring applications etc., that clears corrected events in
banks instead of OS.

[ And trivial cleanup (space -> tab) for doc is included. ]

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
LKML-Reference: <4A30ACDF.5030408@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 0ee5e3b212f3d43ec00216760bd4a55294c0e161..fa2bed07d21e1db2fb274747d6e75d6aaf5e469b 100644 (file)
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -7,12 +7,36 @@ Machine check
 
    Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables.
 
-   mce=off disable machine check
-   mce=bootlog Enable logging of machine checks left over from booting.
-               Disabled by default on AMD because some BIOS leave bogus ones.
-               If your BIOS doesn't do that it's a good idea to enable though
-               to make sure you log even machine check events that result
-               in a reboot. On Intel systems it is enabled by default.
+   mce=off
+               Disable machine check
+   mce=no_cmci
+               Disable CMCI(Corrected Machine Check Interrupt) that
+               Intel processor supports.  Usually this disablement is
+               not recommended, but it might be handy if your hardware
+               is misbehaving.
+               Note that you'll get more problems without CMCI than with
+               due to the shared banks, i.e. you might get duplicated
+               error logs.
+   mce=dont_log_ce
+               Don't make logs for corrected errors.  All events reported
+               as corrected are silently cleared by OS.
+               This option will be useful if you have no interest in any
+               of corrected errors.
+   mce=ignore_ce
+               Disable features for corrected errors, e.g. polling timer
+               and CMCI.  All events reported as corrected are not cleared
+               by OS and remained in its error banks.
+               Usually this disablement is not recommended, however if
+               there is an agent checking/clearing corrected errors
+               (e.g. BIOS or hardware monitoring applications), conflicting
+               with OS's error handling, and you cannot deactivate the agent,
+               then this option will be a help.
+   mce=bootlog
+               Enable logging of machine checks left over from booting.
+               Disabled by default on AMD because some BIOS leave bogus ones.
+               If your BIOS doesn't do that it's a good idea to enable though
+               to make sure you log even machine check events that result
+               in a reboot. On Intel systems it is enabled by default.
    mce=nobootlog
                Disable boot machine check logging.
    mce=tolerancelevel[,monarchtimeout] (number,number)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 82978ad120721f675a2c20632c02f32ad8ab5f8d..540a466e50f52860f410c831d293f57c63120a2d 100644 (file)
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -119,6 +119,8 @@ extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 #define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
 
 #ifdef CONFIG_X86_MCE_INTEL
+extern int mce_cmci_disabled;
+extern int mce_ignore_ce;
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6a3127ecb5cc61d4342ce0d1b4649475fd6c7e4b..fabba15e455864c6768eb958ac61fba3e2acf8a8 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -84,6 +84,9 @@ static int                    rip_msr;
 static int                     mce_bootlog = -1;
 static int                     monarch_timeout = -1;
 static int                     mce_panic_timeout;
+static int                     mce_dont_log_ce;
+int                            mce_cmci_disabled;
+int                            mce_ignore_ce;
 int                            mce_ser;
 
 static char                    trigger[128];
@@ -526,7 +529,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
                 * Don't get the IP here because it's unlikely to
                 * have anything to do with the actual error location.
                 */
-               if (!(flags & MCP_DONTLOG)) {
+               if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
                        mce_log(&m);
                        add_taint(TAINT_MACHINE_CHECK);
                }
@@ -1307,6 +1310,9 @@ static void mce_init_timer(void)
        struct timer_list *t = &__get_cpu_var(mce_timer);
        int *n = &__get_cpu_var(next_interval);
 
+       if (mce_ignore_ce)
+               return;
+
        *n = check_interval * HZ;
        if (!*n)
                return;
@@ -1517,7 +1523,10 @@ static struct miscdevice mce_log_device = {
 };
 
 /*
- * mce=off disables machine check
+ * mce=off Disables machine check
+ * mce=no_cmci Disables CMCI
+ * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
+ * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
  * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
  *     monarchtimeout is how long to wait for other CPUs on machine
  *     check, or 0 to not wait
@@ -1532,6 +1541,12 @@ static int __init mcheck_enable(char *str)
                str++;
        if (!strcmp(str, "off"))
                mce_disabled = 1;
+       else if (!strcmp(str, "no_cmci"))
+               mce_cmci_disabled = 1;
+       else if (!strcmp(str, "dont_log_ce"))
+               mce_dont_log_ce = 1;
+       else if (!strcmp(str, "ignore_ce"))
+               mce_ignore_ce = 1;
        else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
                mce_bootlog = (str[0] == 'b');
        else if (isdigit(str[0])) {

diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index b7c5a2470b404d4789599b09795898c567c5469d..046087e9808f1a88584b292db9bdf9c603bc723e 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -57,6 +57,9 @@ static int cmci_supported(int *banks)
 {
        u64 cap;
 
+       if (mce_cmci_disabled || mce_ignore_ce)
+               return 0;
+
        /*
         * Vendor check is not strictly needed, but the initial
         * initialization is vendor keyed and this