#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
-int mce_disabled __read_mostly;
-
#define SPINUNIT 100 /* 100ns */
atomic_t mce_entry;
DEFINE_PER_CPU(unsigned, mce_exception_count);
-/*
- * Tolerant levels:
- * 0: always panic on uncorrected errors, log corrected errors
- * 1: panic or SIGBUS on uncorrected errors, log corrected errors
- * 2: SIGBUS or log uncorrected errors (if possible), log corrected errors
- * 3: never panic or SIGBUS, log all errors (for testing only)
- */
-static int tolerant __read_mostly = 1;
-static int banks __read_mostly;
-static int rip_msr __read_mostly;
-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;
-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;
+struct mce_bank *mce_banks __read_mostly;
+
+struct mca_config mca_cfg __read_mostly = {
+ .bootlog = -1,
+ /*
+ * Tolerant levels:
+ * 0: always panic on uncorrected errors, log corrected errors
+ * 1: panic or SIGBUS on uncorrected errors, log corrected errors
+ * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors
+ * 3: never panic or SIGBUS, log all errors (for testing only)
+ */
+ .tolerant = 1,
+ .monarch_timeout = -1
+};
/* User mode helper program triggered by machine check event */
static unsigned long mce_need_notify;
while (timeout-- > 0)
udelay(1);
if (panic_timeout == 0)
- panic_timeout = mce_panic_timeout;
+ panic_timeout = mca_cfg.panic_timeout;
panic("Panicing machine check CPU died");
}
pr_emerg(HW_ERR "Machine check: %s\n", exp);
if (!fake_panic) {
if (panic_timeout == 0)
- panic_timeout = mce_panic_timeout;
+ panic_timeout = mca_cfg.panic_timeout;
panic(msg);
} else
pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
{
unsigned bank = __this_cpu_read(injectm.bank);
- if (msr == rip_msr)
+ if (msr == mca_cfg.rip_msr)
return offsetof(struct mce, ip);
if (msr == MSR_IA32_MCx_STATUS(bank))
return offsetof(struct mce, status);
m->cs |= 3;
}
/* Use accurate RIP reporting if available. */
- if (rip_msr)
- m->ip = mce_rdmsrl(rip_msr);
+ if (mca_cfg.rip_msr)
+ m->ip = mce_rdmsrl(mca_cfg.rip_msr);
}
}
int mce_available(struct cpuinfo_x86 *c)
{
- if (mce_disabled)
+ if (mca_cfg.disabled)
return 0;
return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA);
}
/*
* Mask the reported address by the reported granularity.
*/
- if (mce_ser && (m->status & MCI_STATUS_MISCV)) {
+ if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) {
u8 shift = MCI_MISC_ADDR_LSB(m->misc);
m->addr >>= shift;
m->addr <<= shift;
mce_gather_info(&m, NULL);
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
continue;
* TBD do the same check for MCI_STATUS_EN here?
*/
if (!(flags & MCP_UC) &&
- (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)))
+ (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
continue;
mce_read_aux(&m, i);
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
*/
- if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce)
+ if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
mce_log(&m);
/*
{
int i, ret = 0;
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
if (m->status & MCI_STATUS_VAL) {
__set_bit(i, validp);
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
+ if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY)
ret = 1;
}
return ret;
rmb();
if (atomic_read(&mce_paniced))
wait_for_panic();
- if (!monarch_timeout)
+ if (!mca_cfg.monarch_timeout)
goto out;
if ((s64)*t < SPINUNIT) {
/* CHECKME: Make panic default for 1 too? */
- if (tolerant < 1)
+ if (mca_cfg.tolerant < 1)
mce_panic("Timeout synchronizing machine check over CPUs",
NULL, NULL);
cpu_missing = 1;
* Grade the severity of the errors of all the CPUs.
*/
for_each_possible_cpu(cpu) {
- int severity = mce_severity(&per_cpu(mces_seen, cpu), tolerant,
+ int severity = mce_severity(&per_cpu(mces_seen, cpu),
+ mca_cfg.tolerant,
&nmsg);
if (severity > global_worst) {
msg = nmsg;
* This dumps all the mces in the log buffer and stops the
* other CPUs.
*/
- if (m && global_worst >= MCE_PANIC_SEVERITY && tolerant < 3)
+ if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
mce_panic("Fatal Machine check", m, msg);
/*
* No machine check event found. Must be some external
* source or one CPU is hung. Panic.
*/
- if (global_worst <= MCE_KEEP_SEVERITY && tolerant < 3)
+ if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3)
mce_panic("Machine check from unknown source", NULL, NULL);
/*
{
int order;
int cpus = num_online_cpus();
- u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC;
+ u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;
if (!timeout)
return -1;
static int mce_end(int order)
{
int ret = -1;
- u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC;
+ u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;
if (!timeout)
goto reset;
{
int i;
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
if (test_bit(i, toclear))
mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0);
}
*/
void do_machine_check(struct pt_regs *regs, long error_code)
{
+ struct mca_config *cfg = &mca_cfg;
struct mce m, *final;
int i;
int worst = 0;
int order;
/*
* If no_way_out gets set, there is no safe way to recover from this
- * MCE. If tolerant is cranked up, we'll try anyway.
+ * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway.
*/
int no_way_out = 0;
/*
this_cpu_inc(mce_exception_count);
- if (!banks)
+ if (!cfg->banks)
goto out;
mce_gather_info(&m, regs);
* because the first one to see it will clear it.
*/
order = mce_start(&no_way_out);
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
if (!test_bit(i, valid_banks))
continue;
* Non uncorrected or non signaled errors are handled by
* machine_check_poll. Leave them alone, unless this panics.
*/
- if (!(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+ if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
!no_way_out)
continue;
*/
add_taint(TAINT_MACHINE_CHECK);
- severity = mce_severity(&m, tolerant, NULL);
+ severity = mce_severity(&m, cfg->tolerant, NULL);
/*
* When machine check was for corrected handler don't touch,
* When the ring overflows we just ignore the AO error.
* RED-PEN add some logging mechanism when
* usable_address or mce_add_ring fails.
- * RED-PEN don't ignore overflow for tolerant == 0
+ * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0
*/
if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
mce_ring_add(m.addr >> PAGE_SHIFT);
* issues we try to recover, or limit damage to the current
* process.
*/
- if (tolerant < 3) {
+ if (cfg->tolerant < 3) {
if (no_way_out)
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst == MCE_AR_SEVERITY) {
static int __cpuinit __mcheck_cpu_mce_banks_init(void)
{
int i;
+ u8 num_banks = mca_cfg.banks;
- mce_banks = kzalloc(banks * sizeof(struct mce_bank), GFP_KERNEL);
+ mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL);
if (!mce_banks)
return -ENOMEM;
- for (i = 0; i < banks; i++) {
+
+ for (i = 0; i < num_banks; i++) {
struct mce_bank *b = &mce_banks[i];
b->ctl = -1ULL;
rdmsrl(MSR_IA32_MCG_CAP, cap);
b = cap & MCG_BANKCNT_MASK;
- if (!banks)
+ if (!mca_cfg.banks)
pr_info("CPU supports %d MCE banks\n", b);
if (b > MAX_NR_BANKS) {
}
/* Don't support asymmetric configurations today */
- WARN_ON(banks != 0 && b != banks);
- banks = b;
+ WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
+ mca_cfg.banks = b;
+
if (!mce_banks) {
int err = __mcheck_cpu_mce_banks_init();
/* Use accurate RIP reporting if available. */
if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
- rip_msr = MSR_IA32_MCG_EIP;
+ mca_cfg.rip_msr = MSR_IA32_MCG_EIP;
if (cap & MCG_SER_P)
- mce_ser = 1;
+ mca_cfg.ser = true;
return 0;
}
static void __mcheck_cpu_init_generic(void)
{
+ enum mcp_flags m_fl = 0;
mce_banks_t all_banks;
u64 cap;
int i;
+ if (!mca_cfg.bootlog)
+ m_fl = MCP_DONTLOG;
+
/*
* Log the machine checks left over from the previous reset.
*/
bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);
+ machine_check_poll(MCP_UC | m_fl, &all_banks);
set_in_cr4(X86_CR4_MCE);
if (cap & MCG_CTL_P)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
if (!b->init)
/* Add per CPU specific workarounds here */
static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
{
+ struct mca_config *cfg = &mca_cfg;
+
if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
pr_info("unknown CPU type - not enabling MCE support\n");
return -EOPNOTSUPP;
/* This should be disabled by the BIOS, but isn't always */
if (c->x86_vendor == X86_VENDOR_AMD) {
- if (c->x86 == 15 && banks > 4) {
+ if (c->x86 == 15 && cfg->banks > 4) {
/*
* disable GART TBL walk error reporting, which
* trips off incorrectly with the IOMMU & 3ware
*/
clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
}
- if (c->x86 <= 17 && mce_bootlog < 0) {
+ if (c->x86 <= 17 && cfg->bootlog < 0) {
/*
* Lots of broken BIOS around that don't clear them
* by default and leave crap in there. Don't log:
*/
- mce_bootlog = 0;
+ cfg->bootlog = 0;
}
/*
* Various K7s with broken bank 0 around. Always disable
* by default.
*/
- if (c->x86 == 6 && banks > 0)
+ if (c->x86 == 6 && cfg->banks > 0)
mce_banks[0].ctl = 0;
/*
* valid event later, merely don't write CTL0.
*/
- if (c->x86 == 6 && c->x86_model < 0x1A && banks > 0)
+ if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0)
mce_banks[0].init = 0;
/*
* synchronization with a one second timeout.
*/
if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
- monarch_timeout < 0)
- monarch_timeout = USEC_PER_SEC;
+ cfg->monarch_timeout < 0)
+ cfg->monarch_timeout = USEC_PER_SEC;
/*
* There are also broken BIOSes on some Pentium M and
* earlier systems:
*/
- if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
- mce_bootlog = 0;
+ if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
+ cfg->bootlog = 0;
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
}
- if (monarch_timeout < 0)
- monarch_timeout = 0;
- if (mce_bootlog != 0)
- mce_panic_timeout = 30;
+ if (cfg->monarch_timeout < 0)
+ cfg->monarch_timeout = 0;
+ if (cfg->bootlog != 0)
+ cfg->panic_timeout = 30;
return 0;
}
__this_cpu_write(mce_next_interval, iv);
- if (mce_ignore_ce || !iv)
+ if (mca_cfg.ignore_ce || !iv)
return;
t->expires = round_jiffies(jiffies + iv);
*/
void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c)
{
- if (mce_disabled)
+ if (mca_cfg.disabled)
return;
if (__mcheck_cpu_ancient_init(c))
return;
if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
- mce_disabled = 1;
+ mca_cfg.disabled = true;
return;
}
*/
static int __init mcheck_enable(char *str)
{
+ struct mca_config *cfg = &mca_cfg;
+
if (*str == 0) {
enable_p5_mce();
return 1;
if (*str == '=')
str++;
if (!strcmp(str, "off"))
- mce_disabled = 1;
+ cfg->disabled = true;
else if (!strcmp(str, "no_cmci"))
- mce_cmci_disabled = 1;
+ cfg->cmci_disabled = true;
else if (!strcmp(str, "dont_log_ce"))
- mce_dont_log_ce = 1;
+ cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
- mce_ignore_ce = 1;
+ cfg->ignore_ce = true;
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
- mce_bootlog = (str[0] == 'b');
+ cfg->bootlog = (str[0] == 'b');
else if (!strcmp(str, "bios_cmci_threshold"))
- mce_bios_cmci_threshold = 1;
+ cfg->bios_cmci_threshold = true;
else if (isdigit(str[0])) {
- get_option(&str, &tolerant);
+ get_option(&str, &(cfg->tolerant));
if (*str == ',') {
++str;
- get_option(&str, &monarch_timeout);
+ get_option(&str, &(cfg->monarch_timeout));
}
} else {
pr_info("mce argument %s ignored. Please use /sys\n", str);
{
int i;
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
if (b->init)
if (strict_strtoull(buf, 0, &new) < 0)
return -EINVAL;
- if (mce_ignore_ce ^ !!new) {
+ if (mca_cfg.ignore_ce ^ !!new) {
if (new) {
/* disable ce features */
mce_timer_delete_all();
on_each_cpu(mce_disable_cmci, NULL, 1);
- mce_ignore_ce = 1;
+ mca_cfg.ignore_ce = true;
} else {
/* enable ce features */
- mce_ignore_ce = 0;
+ mca_cfg.ignore_ce = false;
on_each_cpu(mce_enable_ce, (void *)1, 1);
}
}
if (strict_strtoull(buf, 0, &new) < 0)
return -EINVAL;
- if (mce_cmci_disabled ^ !!new) {
+ if (mca_cfg.cmci_disabled ^ !!new) {
if (new) {
/* disable cmci */
on_each_cpu(mce_disable_cmci, NULL, 1);
- mce_cmci_disabled = 1;
+ mca_cfg.cmci_disabled = true;
} else {
/* enable cmci */
- mce_cmci_disabled = 0;
+ mca_cfg.cmci_disabled = false;
on_each_cpu(mce_enable_ce, NULL, 1);
}
}
}
static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
-static DEVICE_INT_ATTR(tolerant, 0644, tolerant);
-static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
-static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
+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 struct dev_ext_attribute dev_attr_check_interval = {
__ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
};
static struct dev_ext_attribute dev_attr_ignore_ce = {
- __ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce),
- &mce_ignore_ce
+ __ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce),
+ &mca_cfg.ignore_ce
};
static struct dev_ext_attribute dev_attr_cmci_disabled = {
- __ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled),
- &mce_cmci_disabled
+ __ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled),
+ &mca_cfg.cmci_disabled
};
static struct device_attribute *mce_device_attrs[] = {
if (err)
goto error;
}
- for (j = 0; j < banks; j++) {
+ for (j = 0; j < mca_cfg.banks; j++) {
err = device_create_file(dev, &mce_banks[j].attr);
if (err)
goto error2;
for (i = 0; mce_device_attrs[i]; i++)
device_remove_file(dev, mce_device_attrs[i]);
- for (i = 0; i < banks; i++)
+ for (i = 0; i < mca_cfg.banks; i++)
device_remove_file(dev, &mce_banks[i].attr);
device_unregister(dev);
if (!(action & CPU_TASKS_FROZEN))
cmci_clear();
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
if (b->init)
if (!(action & CPU_TASKS_FROZEN))
cmci_reenable();
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
if (b->init)
{
int i;
- for (i = 0; i < banks; i++) {
+ for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
struct device_attribute *a = &b->attr;
*/
static int __init mcheck_disable(char *str)
{
- mce_disabled = 1;
+ mca_cfg.disabled = true;
return 1;
}
__setup("nomce", mcheck_disable);
projects / firefly-linux-kernel-4.4.55.git / commitdiff