x86/mce: Add mce=print_all option

Sometimes, when logs are getting lost, it's nice to just
have everything dumped to the serial console.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-7-tony.luck@intel.com

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index fc879b6..4efe6c1 100644 (file)
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -591,7 +591,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
        if (!m)
                return NOTIFY_DONE;
 
-       if (!m->kflags)
+       if (mca_cfg.print_all || !m->kflags)
                __print_mce(m);
 
        return NOTIFY_DONE;
@@ -1962,6 +1962,7 @@ void mce_disable_bank(int bank)
  * mce=no_cmci Disables CMCI
  * mce=no_lmce Disables LMCE
  * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
+ * mce=print_all Print all machine check logs to console
  * 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
@@ -1990,6 +1991,8 @@ static int __init mcheck_enable(char *str)
                cfg->lmce_disabled = 1;
        else if (!strcmp(str, "dont_log_ce"))
                cfg->dont_log_ce = true;
+       else if (!strcmp(str, "print_all"))
+               cfg->print_all = true;
        else if (!strcmp(str, "ignore_ce"))
                cfg->ignore_ce = true;
        else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
@@ -2256,6 +2259,7 @@ static ssize_t store_int_with_restart(struct device *s,
 static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
 static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
 static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
+static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all);
 
 static struct dev_ext_attribute dev_attr_check_interval = {
        __ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
@@ -2280,6 +2284,7 @@ static struct device_attribute *mce_device_attrs[] = {
 #endif
        &dev_attr_monarch_timeout.attr,
        &dev_attr_dont_log_ce.attr,
+       &dev_attr_print_all.attr,
        &dev_attr_ignore_ce.attr,
        &dev_attr_cmci_disabled.attr,
        NULL

diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 74a0182..55f5c7b 100644 (file)
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -119,6 +119,7 @@ struct mca_config {
        bool dont_log_ce;
        bool cmci_disabled;
        bool ignore_ce;
+       bool print_all;
 
        __u64 lmce_disabled             : 1,
              disabled                  : 1,