.monarch_timeout = -1
};
-static DEFINE_PER_CPU(struct mce, mces_seen);
+static DEFINE_PER_CPU(struct mce_hw_err, hw_errs_seen);
static unsigned long mce_need_notify;
/*
void mce_prep_record_common(struct mce *m)
{
- memset(m, 0, sizeof(struct mce));
-
m->cpuid = cpuid_eax(1);
m->cpuvendor = boot_cpu_data.x86_vendor;
m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
m->socketid = topology_physical_package_id(cpu);
}
-/* Do initial initialization of a struct mce */
-void mce_prep_record(struct mce *m)
+/* Do initial initialization of struct mce_hw_err */
+void mce_prep_record(struct mce_hw_err *err)
{
+ struct mce *m = &err->m;
+
+ memset(err, 0, sizeof(struct mce_hw_err));
mce_prep_record_common(m);
mce_prep_record_per_cpu(smp_processor_id(), m);
}
DEFINE_PER_CPU(struct mce, injectm);
EXPORT_PER_CPU_SYMBOL_GPL(injectm);
-void mce_log(struct mce *m)
+void mce_log(struct mce_hw_err *err)
{
- if (!mce_gen_pool_add(m))
+ if (!mce_gen_pool_add(err))
irq_work_queue(&mce_irq_work);
}
EXPORT_SYMBOL_GPL(mce_log);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
-static void __print_mce(struct mce *m)
+static void __print_mce(struct mce_hw_err *err)
{
+ struct mce *m = &err->m;
+
pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
m->extcpu,
(m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
m->microcode);
}
-static void print_mce(struct mce *m)
+static void print_mce(struct mce_hw_err *err)
{
- __print_mce(m);
+ struct mce *m = &err->m;
+
+ __print_mce(err);
if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON)
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
return NULL;
}
-static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
+static noinstr void mce_panic(const char *msg, struct mce_hw_err *final, char *exp)
{
struct llist_node *pending;
struct mce_evt_llist *l;
pending = mce_gen_pool_prepare_records();
/* First print corrected ones that are still unlogged */
llist_for_each_entry(l, pending, llnode) {
- struct mce *m = &l->mce;
+ struct mce_hw_err *err = &l->err;
+ struct mce *m = &err->m;
if (!(m->status & MCI_STATUS_UC)) {
- print_mce(m);
+ print_mce(err);
if (!apei_err)
apei_err = apei_write_mce(m);
}
}
/* Now print uncorrected but with the final one last */
llist_for_each_entry(l, pending, llnode) {
- struct mce *m = &l->mce;
+ struct mce_hw_err *err = &l->err;
+ struct mce *m = &err->m;
if (!(m->status & MCI_STATUS_UC))
continue;
- if (!final || mce_cmp(m, final)) {
- print_mce(m);
+ if (!final || mce_cmp(m, &final->m)) {
+ print_mce(err);
if (!apei_err)
apei_err = apei_write_mce(m);
}
if (final) {
print_mce(final);
if (!apei_err)
- apei_err = apei_write_mce(final);
+ apei_err = apei_write_mce(&final->m);
}
if (exp)
pr_emerg(HW_ERR "Machine check: %s\n", exp);
- memmsg = mce_dump_aux_info(final);
+ memmsg = mce_dump_aux_info(&final->m);
if (memmsg)
pr_emerg(HW_ERR "Machine check: %s\n", memmsg);
* panic.
*/
if (kexec_crash_loaded()) {
- if (final && (final->status & MCI_STATUS_ADDRV)) {
+ if (final && (final->m.status & MCI_STATUS_ADDRV)) {
struct page *p;
- p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+ p = pfn_to_online_page(final->m.addr >> PAGE_SHIFT);
if (p)
SetPageHWPoison(p);
}
* check into our "mce" struct so that we can use it later to assess
* the severity of the problem as we read per-bank specific details.
*/
-static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs)
+static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs)
{
+ struct mce *m;
/*
* Enable instrumentation around mce_prep_record() which calls external
* facilities.
*/
instrumentation_begin();
- mce_prep_record(m);
+ mce_prep_record(err);
instrumentation_end();
+ m = &err->m;
m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
if (regs) {
/*
static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
- struct mce *m = (struct mce *)data;
+ struct mce_hw_err *err = to_mce_hw_err(data);
- if (!m)
+ if (!err)
return NOTIFY_DONE;
/* Emit the trace record: */
- trace_mce_record(m);
+ trace_mce_record(err);
set_bit(0, &mce_need_notify);
static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
- struct mce *m = (struct mce *)data;
+ struct mce_hw_err *err = to_mce_hw_err(data);
- if (!m)
+ if (!err)
return NOTIFY_DONE;
- if (mca_cfg.print_all || !m->kflags)
- __print_mce(m);
+ if (mca_cfg.print_all || !(err->m.kflags))
+ __print_mce(err);
return NOTIFY_DONE;
}
/*
* Read ADDR and MISC registers.
*/
-static noinstr void mce_read_aux(struct mce *m, int i)
+static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
{
+ struct mce *m = &err->m;
+
if (m->status & MCI_STATUS_MISCV)
m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- struct mce m;
+ struct mce_hw_err err;
+ struct mce *m;
int i;
this_cpu_inc(mce_poll_count);
- mce_gather_info(&m, NULL);
+ mce_gather_info(&err, NULL);
+ m = &err.m;
if (flags & MCP_TIMESTAMP)
- m.tsc = rdtsc();
+ m->tsc = rdtsc();
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
continue;
- m.misc = 0;
- m.addr = 0;
- m.bank = i;
+ m->misc = 0;
+ m->addr = 0;
+ m->bank = i;
barrier();
- m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+ m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
/*
* Update storm tracking here, before checking for the
* storm status.
*/
if (!mca_cfg.cmci_disabled)
- mce_track_storm(&m);
+ mce_track_storm(m);
/* If this entry is not valid, ignore it */
- if (!(m.status & MCI_STATUS_VAL))
+ if (!(m->status & MCI_STATUS_VAL))
continue;
/*
* If we are logging everything (at CPU online) or this
* is a corrected error, then we must log it.
*/
- if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+ if ((flags & MCP_UC) || !(m->status & MCI_STATUS_UC))
goto log_it;
/*
* everything else.
*/
if (!mca_cfg.ser) {
- if (m.status & MCI_STATUS_UC)
+ if (m->status & MCI_STATUS_UC)
continue;
goto log_it;
}
/* Log "not enabled" (speculative) errors */
- if (!(m.status & MCI_STATUS_EN))
+ if (!(m->status & MCI_STATUS_EN))
goto log_it;
/*
* Log UCNA (SDM: 15.6.3 "UCR Error Classification")
* UC == 1 && PCC == 0 && S == 0
*/
- if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+ if (!(m->status & MCI_STATUS_PCC) && !(m->status & MCI_STATUS_S))
goto log_it;
/*
if (flags & MCP_DONTLOG)
goto clear_it;
- mce_read_aux(&m, i);
- m.severity = mce_severity(&m, NULL, NULL, false);
+ mce_read_aux(&err, i);
+ m->severity = mce_severity(m, NULL, NULL, false);
/*
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
*/
- if (mca_cfg.dont_log_ce && !mce_usable_address(&m))
+ if (mca_cfg.dont_log_ce && !mce_usable_address(m))
goto clear_it;
if (flags & MCP_QUEUE_LOG)
- mce_gen_pool_add(&m);
+ mce_gen_pool_add(&err);
else
- mce_log(&m);
+ mce_log(&err);
clear_it:
/*
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
+static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
+ struct mce *m = &err->m;
char *tmp = *msg;
int i;
m->bank = i;
if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) {
- mce_read_aux(m, i);
+ mce_read_aux(err, i);
*msg = tmp;
return 1;
}
*/
static void mce_reign(void)
{
- int cpu;
+ struct mce_hw_err *err = NULL;
struct mce *m = NULL;
int global_worst = 0;
char *msg = NULL;
+ int cpu;
/*
* This CPU is the Monarch and the other CPUs have run
* Grade the severity of the errors of all the CPUs.
*/
for_each_possible_cpu(cpu) {
- struct mce *mtmp = &per_cpu(mces_seen, cpu);
+ struct mce_hw_err *etmp = &per_cpu(hw_errs_seen, cpu);
+ struct mce *mtmp = &etmp->m;
if (mtmp->severity > global_worst) {
global_worst = mtmp->severity;
- m = &per_cpu(mces_seen, cpu);
+ err = &per_cpu(hw_errs_seen, cpu);
+ m = &err->m;
}
}
if (m && global_worst >= MCE_PANIC_SEVERITY) {
/* call mce_severity() to get "msg" for panic */
mce_severity(m, NULL, &msg, true);
- mce_panic("Fatal machine check", m, msg);
+ mce_panic("Fatal machine check", err, msg);
}
/*
mce_panic("Fatal machine check from unknown source", NULL, NULL);
/*
- * Now clear all the mces_seen so that they don't reappear on
+ * Now clear all the hw_errs_seen so that they don't reappear on
* the next mce.
*/
for_each_possible_cpu(cpu)
- memset(&per_cpu(mces_seen, cpu), 0, sizeof(struct mce));
+ memset(&per_cpu(hw_errs_seen, cpu), 0, sizeof(struct mce_hw_err));
}
static atomic_t global_nwo;
}
static __always_inline int
-__mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final,
- unsigned long *toclear, unsigned long *valid_banks, int no_way_out,
- int *worst)
+__mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs,
+ struct mce_hw_err *final, unsigned long *toclear,
+ unsigned long *valid_banks, int no_way_out, int *worst)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
struct mca_config *cfg = &mca_cfg;
int severity, i, taint = 0;
+ struct mce *m = &err->m;
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
arch___clear_bit(i, toclear);
if (severity == MCE_NO_SEVERITY)
continue;
- mce_read_aux(m, i);
+ mce_read_aux(err, i);
/* assuming valid severity level != 0 */
m->severity = severity;
* done in #MC context, where instrumentation is disabled.
*/
instrumentation_begin();
- mce_log(m);
+ mce_log(err);
instrumentation_end();
if (severity > *worst) {
- *final = *m;
+ *final = *err;
*worst = severity;
}
}
/* mce_clear_state will clear *final, save locally for use later */
- *m = *final;
+ *err = *final;
return taint;
}
set_mce_nospec(pfn);
}
-static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *))
+static void queue_task_work(struct mce_hw_err *err, char *msg, void (*func)(struct callback_head *))
{
int count = ++current->mce_count;
+ struct mce *m = &err->m;
/* First call, save all the details */
if (count == 1) {
/* Ten is likely overkill. Don't expect more than two faults before task_work() */
if (count > 10)
- mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+ mce_panic("Too many consecutive machine checks while accessing user data",
+ err, msg);
/* Second or later call, make sure page address matches the one from first call */
if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
- mce_panic("Consecutive machine checks to different user pages", m, msg);
+ mce_panic("Consecutive machine checks to different user pages", err, msg);
/* Do not call task_work_add() more than once */
if (count > 1)
int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0;
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 };
DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 };
- struct mce m, *final;
+ struct mce_hw_err *final;
+ struct mce_hw_err err;
char *msg = NULL;
+ struct mce *m;
if (unlikely(mce_flags.p5))
return pentium_machine_check(regs);
this_cpu_inc(mce_exception_count);
- mce_gather_info(&m, regs);
- m.tsc = rdtsc();
+ mce_gather_info(&err, regs);
+ m = &err.m;
+ m->tsc = rdtsc();
- final = this_cpu_ptr(&mces_seen);
- *final = m;
+ final = this_cpu_ptr(&hw_errs_seen);
+ *final = err;
- no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);
+ no_way_out = mce_no_way_out(&err, &msg, valid_banks, regs);
barrier();
* Assume the worst for now, but if we find the
* severity is MCE_AR_SEVERITY we have other options.
*/
- if (!(m.mcgstatus & MCG_STATUS_RIPV))
+ if (!(m->mcgstatus & MCG_STATUS_RIPV))
kill_current_task = 1;
/*
* Check if this MCE is signaled to only this logical processor,
* on Intel, Zhaoxin only.
*/
- if (m.cpuvendor == X86_VENDOR_INTEL ||
- m.cpuvendor == X86_VENDOR_ZHAOXIN)
- lmce = m.mcgstatus & MCG_STATUS_LMCES;
+ if (m->cpuvendor == X86_VENDOR_INTEL ||
+ m->cpuvendor == X86_VENDOR_ZHAOXIN)
+ lmce = m->mcgstatus & MCG_STATUS_LMCES;
/*
* Local machine check may already know that we have to panic.
*/
if (lmce) {
if (no_way_out)
- mce_panic("Fatal local machine check", &m, msg);
+ mce_panic("Fatal local machine check", &err, msg);
} else {
order = mce_start(&no_way_out);
}
- taint = __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst);
+ taint = __mc_scan_banks(&err, regs, final, toclear, valid_banks, no_way_out, &worst);
if (!no_way_out)
mce_clear_state(toclear);
no_way_out = worst >= MCE_PANIC_SEVERITY;
if (no_way_out)
- mce_panic("Fatal machine check on current CPU", &m, msg);
+ mce_panic("Fatal machine check on current CPU", &err, msg);
}
} else {
/*
* make sure we have the right "msg".
*/
if (worst >= MCE_PANIC_SEVERITY) {
- mce_severity(&m, regs, &msg, true);
- mce_panic("Local fatal machine check!", &m, msg);
+ mce_severity(m, regs, &msg, true);
+ mce_panic("Local fatal machine check!", &err, msg);
}
}
goto out;
/* Fault was in user mode and we need to take some action */
- if ((m.cs & 3) == 3) {
+ if ((m->cs & 3) == 3) {
/* If this triggers there is no way to recover. Die hard. */
BUG_ON(!on_thread_stack() || !user_mode(regs));
- if (!mce_usable_address(&m))
- queue_task_work(&m, msg, kill_me_now);
+ if (!mce_usable_address(m))
+ queue_task_work(&err, msg, kill_me_now);
else
- queue_task_work(&m, msg, kill_me_maybe);
+ queue_task_work(&err, msg, kill_me_maybe);
- } else if (m.mcgstatus & MCG_STATUS_SEAM_NR) {
+ } else if (m->mcgstatus & MCG_STATUS_SEAM_NR) {
/*
* Saved RIP on stack makes it look like the machine check
* was taken in the kernel on the instruction following
* not occur there. Mark the page as poisoned so it won't
* be added to free list when the guest is terminated.
*/
- if (mce_usable_address(&m)) {
- struct page *p = pfn_to_online_page(m.addr >> PAGE_SHIFT);
+ if (mce_usable_address(m)) {
+ struct page *p = pfn_to_online_page(m->addr >> PAGE_SHIFT);
if (p)
SetPageHWPoison(p);
* corresponding exception handler which would do that is the
* proper one.
*/
- if (m.kflags & MCE_IN_KERNEL_RECOV) {
+ if (m->kflags & MCE_IN_KERNEL_RECOV) {
if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
- mce_panic("Failed kernel mode recovery", &m, msg);
+ mce_panic("Failed kernel mode recovery", &err, msg);
}
- if (m.kflags & MCE_IN_KERNEL_COPYIN)
- queue_task_work(&m, msg, kill_me_never);
+ if (m->kflags & MCE_IN_KERNEL_COPYIN)
+ queue_task_work(&err, msg, kill_me_never);
}
out:
projects / users / jedix / linux-maple.git / commitdiff