From: Naveen N. Rao Date: Thu, 27 Sep 2012 17:08:00 +0000 (-0700) Subject: x86/mce: Provide boot argument to honour bios-set CMCI threshold X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=450cc201038f3;p=linux-beck.git x86/mce: Provide boot argument to honour bios-set CMCI threshold The ACPI spec doesn't provide for a way for the bios to pass down recommended thresholds to the OS on a _per-bank_ basis. This patch adds a new boot option, which if passed, tells Linux to use CMCI thresholds set by the bios. As fail-safe, we initialize threshold to 1 if some banks have not been initialized by the bios and warn the user. Signed-off-by: Naveen N. Rao Signed-off-by: Tony Luck --- diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index c54b4f503e2a..de38429beb71 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -50,6 +50,13 @@ Machine check monarchtimeout: Sets the time in us to wait for other CPUs on machine checks. 0 to disable. + mce=bios_cmci_threshold + Don't overwrite the bios-set CMCI threshold. This boot option + prevents Linux from overwriting the CMCI threshold set by the + bios. Without this option, Linux always sets the CMCI + threshold to 1. Enabling this may make memory predictive failure + analysis less effective if the bios sets thresholds for memory + errors since we will not see details for all errors. nomce (for compatibility with i386): same as mce=off diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index ccaf7c581c8f..54d73b1f00a0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -161,6 +161,7 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL extern int mce_cmci_disabled; extern int mce_ignore_ce; +extern int mce_bios_cmci_threshold; 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 c311122ea838..29e87d3b2843 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -83,6 +83,7 @@ static int mce_dont_log_ce __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; +int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; @@ -1946,6 +1947,7 @@ static struct miscdevice mce_chrdev_device = { * check, or 0 to not wait * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. * mce=nobootlog Don't log MCEs from before booting. + * mce=bios_cmci_threshold Don't program the CMCI threshold */ static int __init mcheck_enable(char *str) { @@ -1965,6 +1967,8 @@ static int __init mcheck_enable(char *str) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) mce_bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &tolerant); if (*str == ',') { @@ -2205,6 +2209,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { &mce_cmci_disabled }; +static struct dev_ext_attribute dev_attr_bios_cmci_threshold = { + __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL), + &mce_bios_cmci_threshold +}; + static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, @@ -2213,6 +2222,7 @@ static struct device_attribute *mce_device_attrs[] = { &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, + &dev_attr_bios_cmci_threshold.attr, NULL }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 098386fed48e..5f88abf07e9c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -181,10 +181,12 @@ static void cmci_discover(int banks) unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); unsigned long flags; int i; + int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; + int bios_zero_thresh = 0; if (test_bit(i, owned)) continue; @@ -198,8 +200,20 @@ static void cmci_discover(int banks) continue; } - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; + if (!mce_bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); rdmsrl(MSR_IA32_MCx_CTL2(i), val); @@ -207,11 +221,26 @@ static void cmci_discover(int banks) if (val & MCI_CTL2_CMCI_EN) { set_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mce_bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; } else { WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); + if (mce_bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } } /* @@ -249,7 +278,7 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); + val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); }