mce.c

/*
 * Machine check handler.
 *
 * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
 * Rest from unknown author(s).
 * 2004 Andi Kleen. Rewrote most of it.
 * Copyright 2008 Intel Corporation
 * Author: Andi Kleen
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/thread_info.h>
#include <linux/capability.h>
#include <linux/miscdevice.h>
#include <linux/ratelimit.h>
#include <linux/rcupdate.h>
#include <linux/kobject.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/device.h>
#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/cpu.h>
#include <linux/ras.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/debugfs.h>
#include <linux/irq_work.h>
#include <linux/export.h>
#include <linux/jump_label.h>

#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/reboot.h>
#include <asm/set_memory.h>

#include "mce-internal.h"

static DEFINE_MUTEX(mce_log_mutex);

#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>

#define SPINUNIT		100	/* 100ns */

DEFINE_PER_CPU(unsigned, mce_exception_count);

struct mce_bank *mce_banks __read_mostly;
struct mce_vendor_flags mce_flags __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
};

static DEFINE_PER_CPU(struct mce, mces_seen);
static unsigned long mce_need_notify;
static int cpu_missing;

/*
 * MCA banks polled by the period polling timer for corrected events.
 * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
 */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
};

/*
 * MCA banks controlled through firmware first for corrected errors.
 * This is a global list of banks for which we won't enable CMCI and we
 * won't poll. Firmware controls these banks and is responsible for
 * reporting corrected errors through GHES. Uncorrected/recoverable
 * errors are still notified through a machine check.
 */
mce_banks_t mce_banks_ce_disabled;

static struct work_struct mce_work;
static struct irq_work mce_irq_work;

static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);

#ifndef mce_unmap_kpfn
static void mce_unmap_kpfn(unsigned long pfn);
#endif

/*
 * CPU/chipset specific EDAC code can register a notifier call here to print
 * MCE errors in a human-readable form.
 */
BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);

/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
{
	memset(m, 0, sizeof(struct mce));
	m->cpu = m->extcpu = smp_processor_id();
	/* We hope get_seconds stays lockless */
	m->time = get_seconds();
	m->cpuvendor = boot_cpu_data.x86_vendor;
	m->cpuid = cpuid_eax(1);
	m->socketid = cpu_data(m->extcpu).phys_proc_id;
	m->apicid = cpu_data(m->extcpu).initial_apicid;
	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);

	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
		rdmsrl(MSR_PPIN, m->ppin);
}

DEFINE_PER_CPU(struct mce, injectm);
EXPORT_PER_CPU_SYMBOL_GPL(injectm);

void mce_log(struct mce *m)
{
	if (!mce_gen_pool_add(m))
		irq_work_queue(&mce_irq_work);
}

void mce_inject_log(struct mce *m)
{
	mutex_lock(&mce_log_mutex);
	mce_log(m);
	mutex_unlock(&mce_log_mutex);
}
EXPORT_SYMBOL_GPL(mce_inject_log);

static struct notifier_block mce_srao_nb;

/*
 * We run the default notifier if we have only the SRAO, the first and the
 * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
 * notifiers registered on the chain.
 */
#define NUM_DEFAULT_NOTIFIERS	3
static atomic_t num_notifiers;

void mce_register_decode_chain(struct notifier_block *nb)
{
	if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
		return;

	atomic_inc(&num_notifiers);

	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_register_decode_chain);

void mce_unregister_decode_chain(struct notifier_block *nb)
{
	atomic_dec(&num_notifiers);

	blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);

static inline u32 ctl_reg(int bank)
{
	return MSR_IA32_MCx_CTL(bank);
}

static inline u32 status_reg(int bank)
{
	return MSR_IA32_MCx_STATUS(bank);
}

static inline u32 addr_reg(int bank)
{
	return MSR_IA32_MCx_ADDR(bank);
}

static inline u32 misc_reg(int bank)
{
	return MSR_IA32_MCx_MISC(bank);
}

static inline u32 smca_ctl_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_CTL(bank);
}

static inline u32 smca_status_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_STATUS(bank);
}

static inline u32 smca_addr_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_ADDR(bank);
}

static inline u32 smca_misc_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_MISC(bank);
}

struct mca_msr_regs msr_ops = {
	.ctl	= ctl_reg,
	.status	= status_reg,
	.addr	= addr_reg,
	.misc	= misc_reg
};

static void __print_mce(struct mce *m)
{
	pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
		 m->extcpu,
		 (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
		 m->mcgstatus, m->bank, m->status);

	if (m->ip) {
		pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
			!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
			m->cs, m->ip);

		if (m->cs == __KERNEL_CS)
			pr_cont("{%pS}", (void *)(unsigned long)m->ip);
		pr_cont("\n");
	}

	pr_emerg(HW_ERR "TSC %llx ", m->tsc);
	if (m->addr)
		pr_cont("ADDR %llx ", m->addr);
	if (m->misc)
		pr_cont("MISC %llx ", m->misc);

	if (mce_flags.smca) {
		if (m->synd)
			pr_cont("SYND %llx ", m->synd);
		if (m->ipid)
			pr_cont("IPID %llx ", m->ipid);
	}

	pr_cont("\n");
	/*
	 * Note this output is parsed by external tools and old fields
	 * should not be changed.
	 */
	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
		cpu_data(m->extcpu).microcode);
}

static void print_mce(struct mce *m)
{
	__print_mce(m);
	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}

#define PANIC_TIMEOUT 5 /* 5 seconds */

static atomic_t mce_panicked;

static int fake_panic;
static atomic_t mce_fake_panicked;

/* Panic in progress. Enable interrupts and wait for final IPI */
static void wait_for_panic(void)
{
	long timeout = PANIC_TIMEOUT*USEC_PER_SEC;

	preempt_disable();
	local_irq_enable();
	while (timeout-- > 0)
		udelay(1);
	if (panic_timeout == 0)
		panic_timeout = mca_cfg.panic_timeout;
	panic("Panicing machine check CPU died");
}

static void mce_panic(const char *msg, struct mce *final, char *exp)
{
	int apei_err = 0;
	struct llist_node *pending;
	struct mce_evt_llist *l;

	if (!fake_panic) {
		/*
		 * Make sure only one CPU runs in machine check panic
		 */
		if (atomic_inc_return(&mce_panicked) > 1)
			wait_for_panic();
		barrier();

		bust_spinlocks(1);
		console_verbose();
	} else {
		/* Don't log too much for fake panic */
		if (atomic_inc_return(&mce_fake_panicked) > 1)
			return;
	}
	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;
		if (!(m->status & MCI_STATUS_UC)) {
			print_mce(m);
			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;
		if (!(m->status & MCI_STATUS_UC))
			continue;
		if (!final || mce_cmp(m, final)) {
			print_mce(m);
			if (!apei_err)
				apei_err = apei_write_mce(m);
		}
	}
	if (final) {
		print_mce(final);
		if (!apei_err)
			apei_err = apei_write_mce(final);
	}
	if (cpu_missing)
		pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n");
	if (exp)
		pr_emerg(HW_ERR "Machine check: %s\n", exp);
	if (!fake_panic) {
		if (panic_timeout == 0)
			panic_timeout = mca_cfg.panic_timeout;
		panic(msg);
	} else
		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
}

/* Support code for software error injection */

static int msr_to_offset(u32 msr)
{
	unsigned bank = __this_cpu_read(injectm.bank);

	if (msr == mca_cfg.rip_msr)
		return offsetof(struct mce, ip);
	if (msr == msr_ops.status(bank))
		return offsetof(struct mce, status);
	if (msr == msr_ops.addr(bank))
		return offsetof(struct mce, addr);
	if (msr == msr_ops.misc(bank))
		return offsetof(struct mce, misc);
	if (msr == MSR_IA32_MCG_STATUS)
		return offsetof(struct mce, mcgstatus);
	return -1;
}

/* MSR access wrappers used for error injection */
static u64 mce_rdmsrl(u32 msr)
{
	u64 v;

	if (__this_cpu_read(injectm.finished)) {
		int offset = msr_to_offset(msr);

		if (offset < 0)
			return 0;
		return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
	}

	if (rdmsrl_safe(msr, &v)) {
		WARN_ONCE(1, "mce: Unable to read MSR 0x%x!\n", msr);
		/*
		 * Return zero in case the access faulted. This should
		 * not happen normally but can happen if the CPU does
		 * something weird, or if the code is buggy.
		 */
		v = 0;
	}

	return v;
}

static void mce_wrmsrl(u32 msr, u64 v)
{
	if (__this_cpu_read(injectm.finished)) {
		int offset = msr_to_offset(msr);

		if (offset >= 0)
			*(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
		return;
	}
	wrmsrl(msr, v);
}

/*
 * Collect all global (w.r.t. this processor) status about this machine
 * 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 inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
{
	mce_setup(m);

	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
	if (regs) {
		/*
		 * Get the address of the instruction at the time of
		 * the machine check error.
		 */
		if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) {
			m->ip = regs->ip;
			m->cs = regs->cs;

			/*
			 * When in VM86 mode make the cs look like ring 3
			 * always. This is a lie, but it's better than passing
			 * the additional vm86 bit around everywhere.
			 */
			if (v8086_mode(regs))
				m->cs |= 3;
		}
		/* Use accurate RIP reporting if available. */
		if (mca_cfg.rip_msr)
			m->ip = mce_rdmsrl(mca_cfg.rip_msr);
	}
}

int mce_available(struct cpuinfo_x86 *c)
{
	if (mca_cfg.disabled)
		return 0;
	return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA);
}

static void mce_schedule_work(void)
{
	if (!mce_gen_pool_empty())
		schedule_work(&mce_work);
}

static void mce_irq_work_cb(struct irq_work *entry)
{
	mce_schedule_work();
}

static void mce_report_event(struct pt_regs *regs)
{
	if (regs->flags & (X86_VM_MASK|X86_EFLAGS_IF)) {
		mce_notify_irq();
		/*
		 * Triggering the work queue here is just an insurance
		 * policy in case the syscall exit notify handler
		 * doesn't run soon enough or ends up running on the
		 * wrong CPU (can happen when audit sleeps)
		 */
		mce_schedule_work();
		return;
	}

	irq_work_queue(&mce_irq_work);
}

/*
 * Check if the address reported by the CPU is in a format we can parse.
 * It would be possible to add code for most other cases, but all would
 * be somewhat complicated (e.g. segment offset would require an instruction
 * parser). So only support physical addresses up to page granuality for now.
 */
static int mce_usable_address(struct mce *m)
{
	if (!(m->status & MCI_STATUS_ADDRV))
		return 0;

	/* Checks after this one are Intel-specific: */
	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
		return 1;

	if (!(m->status & MCI_STATUS_MISCV))
		return 0;

	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
		return 0;

	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
		return 0;

	return 1;
}

bool mce_is_memory_error(struct mce *m)
{
	if (m->cpuvendor == X86_VENDOR_AMD) {
		return amd_mce_is_memory_error(m);

	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
		/*
		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
		 *
		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
		 * indicating a memory error. Bit 8 is used for indicating a
		 * cache hierarchy error. The combination of bit 2 and bit 3
		 * is used for indicating a `generic' cache hierarchy error
		 * But we can't just blindly check the above bits, because if
		 * bit 11 is set, then it is a bus/interconnect error - and
		 * either way the above bits just gives more detail on what
		 * bus/interconnect error happened. Note that bit 12 can be
		 * ignored, as it's the "filter" bit.
		 */
		return (m->status & 0xef80) == BIT(7) ||
		       (m->status & 0xef00) == BIT(8) ||
		       (m->status & 0xeffc) == 0xc;
	}

	return false;
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);

static bool mce_is_correctable(struct mce *m)
{
	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
		return false;

	if (m->status & MCI_STATUS_UC)
		return false;

	return true;
}

static bool cec_add_mce(struct mce *m)
{
	if (!m)
		return false;

	/* We eat only correctable DRAM errors with usable addresses. */
	if (mce_is_memory_error(m) &&
	    mce_is_correctable(m)  &&
	    mce_usable_address(m))
		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
			return true;

	return false;
}

static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
			      void *data)
{
	struct mce *m = (struct mce *)data;

	if (!m)
		return NOTIFY_DONE;

	if (cec_add_mce(m))
		return NOTIFY_STOP;

	/* Emit the trace record: */
	trace_mce_record(m);

	set_bit(0, &mce_need_notify);

	mce_notify_irq();

	return NOTIFY_DONE;
}

static struct notifier_block first_nb = {
	.notifier_call	= mce_first_notifier,
	.priority	= MCE_PRIO_FIRST,
};

static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
				void *data)
{
	struct mce *mce = (struct mce *)data;
	unsigned long pfn;

	if (!mce)
		return NOTIFY_DONE;

	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
		pfn = mce->addr >> PAGE_SHIFT;
		if (!memory_failure(pfn, 0))
			mce_unmap_kpfn(pfn);
	}

	return NOTIFY_OK;
}
static struct notifier_block mce_srao_nb = {
	.notifier_call	= srao_decode_notifier,
	.priority	= MCE_PRIO_SRAO,
};

static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
				void *data)
{
	struct mce *m = (struct mce *)data;

	if (!m)
		return NOTIFY_DONE;

	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
		return NOTIFY_DONE;

	__print_mce(m);

	return NOTIFY_DONE;
}

static struct notifier_block mce_default_nb = {
	.notifier_call	= mce_default_notifier,
	/* lowest prio, we want it to run last. */
	.priority	= MCE_PRIO_LOWEST,
};

/*
 * Read ADDR and MISC registers.
 */
static void mce_read_aux(struct mce *m, int i)
{
	if (m->status & MCI_STATUS_MISCV)
		m->misc = mce_rdmsrl(msr_ops.misc(i));

	if (m->status & MCI_STATUS_ADDRV) {
		m->addr = mce_rdmsrl(msr_ops.addr(i));

		/*
		 * Mask the reported address by the reported granularity.
		 */
		if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) {
			u8 shift = MCI_MISC_ADDR_LSB(m->misc);
			m->addr >>= shift;
			m->addr <<= shift;
		}

		/*
		 * Extract [55:<lsb>] where lsb is the least significant
		 * *valid* bit of the address bits.
		 */
		if (mce_flags.smca) {
			u8 lsb = (m->addr >> 56) & 0x3f;

			m->addr &= GENMASK_ULL(55, lsb);
		}
	}

	if (mce_flags.smca) {
		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));

		if (m->status & MCI_STATUS_SYNDV)
			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
	}
}

DEFINE_PER_CPU(unsigned, mce_poll_count);

/*
 * Poll for corrected events or events that happened before reset.
 * Those are just logged through /dev/mcelog.
 *
 * This is executed in standard interrupt context.
 *
 * Note: spec recommends to panic for fatal unsignalled
 * errors here. However this would be quite problematic --
 * we would need to reimplement the Monarch handling and
 * it would mess up the exclusion between exception handler
 * and poll hander -- * so we skip this for now.
 * These cases should not happen anyways, or only when the CPU
 * is already totally * confused. In this case it's likely it will
 * not fully execute the machine check handler either.
 */
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
	bool error_seen = false;
	struct mce m;
	int i;

	this_cpu_inc(mce_poll_count);

	mce_gather_info(&m, NULL);

	if (flags & MCP_TIMESTAMP)
		m.tsc = rdtsc();

	for (i = 0; i < mca_cfg.banks; i++) {
		if (!mce_banks[i].ctl || !test_bit(i, *b))
			continue;

		m.misc = 0;
		m.addr = 0;
		m.bank = i;

		barrier();
		m.status = mce_rdmsrl(msr_ops.status(i));
		if (!(m.status & MCI_STATUS_VAL))
			continue;

		/*
		 * Uncorrected or signalled events are handled by the exception
		 * handler when it is enabled, so don't process those here.
		 *
		 * TBD do the same check for MCI_STATUS_EN here?
		 */
		if (!(flags & MCP_UC) &&
		    (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
			continue;

		error_seen = true;

		mce_read_aux(&m, i);

		m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);

		/*
		 * Don't get the IP here because it's unlikely to
		 * have anything to do with the actual error location.
		 */
		if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
			mce_log(&m);
		else if (mce_usable_address(&m)) {
			/*
			 * Although we skipped logging this, we still want
			 * to take action. Add to the pool so the registered
			 * notifiers will see it.
			 */
			if (!mce_gen_pool_add(&m))
				mce_schedule_work();
		}

		/*
		 * Clear state for this bank.
		 */
		mce_wrmsrl(msr_ops.status(i), 0);
	}

	/*
	 * Don't clear MCG_STATUS here because it's only defined for
	 * exceptions.
	 */

	sync_core();

	return error_seen;
}
EXPORT_SYMBOL_GPL(machine_check_poll);

/*
 * Do a quick check if any of the events requires a panic.
 * This decides if we keep the events around or clear them.
 */
static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
			  struct pt_regs *regs)
{
	int i, ret = 0;
	char *tmp;

	for (i = 0; i < mca_cfg.banks; i++) {
		m->status = mce_rdmsrl(msr_ops.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, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
			*msg = tmp;
			ret = 1;
		}
	}
	return ret;
}

/*
 * Variable to establish order between CPUs while scanning.
 * Each CPU spins initially until executing is equal its number.
 */
static atomic_t mce_executing;

/*
 * Defines order of CPUs on entry. First CPU becomes Monarch.
 */
static atomic_t mce_callin;

/*
 * Check if a timeout waiting for other CPUs happened.
 */
static int mce_timed_out(u64 *t, const char *msg)
{
	/*
	 * The others already did panic for some reason.
	 * Bail out like in a timeout.
	 * rmb() to tell the compiler that system_state
	 * might have been modified by someone else.
	 */
	rmb();
	if (atomic_read(&mce_panicked))
		wait_for_panic();
	if (!mca_cfg.monarch_timeout)
		goto out;
	if ((s64)*t < SPINUNIT) {
		if (mca_cfg.tolerant <= 1)
			mce_panic(msg, NULL, NULL);
		cpu_missing = 1;
		return 1;
	}
	*t -= SPINUNIT;
out:
	touch_nmi_watchdog();
	return 0;
}

/*
 * The Monarch's reign.  The Monarch is the CPU who entered
 * the machine check handler first. It waits for the others to
 * raise the exception too and then grades them. When any
 * error is fatal panic. Only then let the others continue.
 *
 * The other CPUs entering the MCE handler will be controlled by the
 * Monarch. They are called Subjects.
 *
 * This way we prevent any potential data corruption in a unrecoverable case
 * and also makes sure always all CPU's errors are examined.
 *
 * Also this detects the case of a machine check event coming from outer
 * space (not detected by any CPUs) In this case some external agent wants
 * us to shut down, so panic too.
 *
 * The other CPUs might still decide to panic if the handler happens
 * in a unrecoverable place, but in this case the system is in a semi-stable
 * state and won't corrupt anything by itself. It's ok to let the others
 * continue for a bit first.
 *
 * All the spin loops have timeouts; when a timeout happens a CPU
 * typically elects itself to be Monarch.
 */
static void mce_reign(void)
{
	int cpu;
	struct mce *m = NULL;
	int global_worst = 0;
	char *msg = NULL;
	char *nmsg = NULL;

	/*
	 * This CPU is the Monarch and the other CPUs have run
	 * through their handlers.
	 * Grade the severity of the errors of all the CPUs.
	 */
	for_each_possible_cpu(cpu) {
		int severity = mce_severity(&per_cpu(mces_seen, cpu),
					    mca_cfg.tolerant,
					    &nmsg, true);
		if (severity > global_worst) {
			msg = nmsg;
			global_worst = severity;
			m = &per_cpu(mces_seen, cpu);
		}
	}

	/*
	 * Cannot recover? Panic here then.
	 * This dumps all the mces in the log buffer and stops the
	 * other CPUs.
	 */
	if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
		mce_panic("Fatal machine check", m, msg);

	/*
	 * For UC somewhere we let the CPU who detects it handle it.
	 * Also must let continue the others, otherwise the handling
	 * CPU could deadlock on a lock.
	 */

	/*
	 * No machine check event found. Must be some external
	 * source or one CPU is hung. Panic.
	 */
	if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3)
		mce_panic("Fatal machine check from unknown source", NULL, NULL);

	/*
	 * Now clear all the mces_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));
}

static atomic_t global_nwo;

/*
 * Start of Monarch synchronization. This waits until all CPUs have
 * entered the exception handler and then determines if any of them
 * saw a fatal event that requires panic. Then it executes them
 * in the entry order.
 * TBD double check parallel CPU hotunplug
 */
static int mce_start(int *no_way_out)
{
	int order;
	int cpus = num_online_cpus();
	u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;

	if (!timeout)
		return -1;

	atomic_add(*no_way_out, &global_nwo);
	/*
	 * Rely on the implied barrier below, such that global_nwo
	 * is updated before mce_callin.
	 */
	order = atomic_inc_return(&mce_callin);

	/*
	 * Wait for everyone.
	 */
	while (atomic_read(&mce_callin) != cpus) {
		if (mce_timed_out(&timeout,
				  "Timeout: Not all CPUs entered broadcast exception handler")) {
			atomic_set(&global_nwo, 0);
			return -1;
		}
		ndelay(SPINUNIT);
	}

	/*
	 * mce_callin should be read before global_nwo
	 */
	smp_rmb();

	if (order == 1) {
		/*
		 * Monarch: Starts executing now, the others wait.
		 */
		atomic_set(&mce_executing, 1);
	} else {
		/*
		 * Subject: Now start the scanning loop one by one in
		 * the original callin order.
		 * This way when there are any shared banks it will be
		 * only seen by one CPU before cleared, avoiding duplicates.
		 */
		while (atomic_read(&mce_executing) < order) {
			if (mce_timed_out(&timeout,
					  "Timeout: Subject CPUs unable to finish machine check processing")) {
				atomic_set(&global_nwo, 0);
				return -1;
			}
			ndelay(SPINUNIT);
		}
	}

	/*
	 * Cache the global no_way_out state.
	 */
	*no_way_out = atomic_read(&global_nwo);

	return order;
}

/*
 * Synchronize between CPUs after main scanning loop.
 * This invokes the bulk of the Monarch processing.
 */
static int mce_end(int order)
{
	int ret = -1;
	u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC;

	if (!timeout)
		goto reset;
	if (order < 0)
		goto reset;

	/*
	 * Allow others to run.
	 */
	atomic_inc(&mce_executing);

	if (order == 1) {
		/* CHECKME: Can this race with a parallel hotplug? */
		int cpus = num_online_cpus();

		/*
		 * Monarch: Wait for everyone to go through their scanning
		 * loops.
		 */
		while (atomic_read(&mce_executing) <= cpus) {
			if (mce_timed_out(&timeout,
					  "Timeout: Monarch CPU unable to finish machine check processing"))
				goto reset;
			ndelay(SPINUNIT);
		}

		mce_reign();
		barrier();
		ret = 0;
	} else {
		/*
		 * Subject: Wait for Monarch to finish.
		 */
		while (atomic_read(&mce_executing) != 0) {
			if (mce_timed_out(&timeout,
					  "Timeout: Monarch CPU did not finish machine check processing"))
				goto reset;
			ndelay(SPINUNIT);
		}

		/*
		 * Don't reset anything. That's done by the Monarch.
		 */
		return 0;
	}

	/*
	 * Reset all global state.
	 */
reset:
	atomic_set(&global_nwo, 0);
	atomic_set(&mce_callin, 0);
	barrier();

	/*
	 * Let others run again.
	 */
	atomic_set(&mce_executing, 0);
	return ret;
}

static void mce_clear_state(unsigned long *toclear)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		if (test_bit(i, toclear))
			mce_wrmsrl(msr_ops.status(i), 0);
	}
}

static int do_memory_failure(struct mce *m)
{
	int flags = MF_ACTION_REQUIRED;
	int ret;

	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
	if (!(m->mcgstatus & MCG_STATUS_RIPV))
		flags |= MF_MUST_KILL;
	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
	if (ret)
		pr_err("Memory error not recovered");
	else
		mce_unmap_kpfn(m->addr >> PAGE_SHIFT);
	return ret;
}

#ifndef mce_unmap_kpfn
static void mce_unmap_kpfn(unsigned long pfn)
{
	unsigned long decoy_addr;

	/*
	 * Unmap this page from the kernel 1:1 mappings to make sure
	 * we don't log more errors because of speculative access to
	 * the page.
	 * We would like to just call:
	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
	 * but doing that would radically increase the odds of a
	 * speculative access to the poison page because we'd have
	 * the virtual address of the kernel 1:1 mapping sitting
	 * around in registers.
	 * Instead we get tricky.  We create a non-canonical address
	 * that looks just like the one we want, but has bit 63 flipped.
	 * This relies on set_memory_np() not checking whether we passed
	 * a legal address.
	 */

/*
 * Build time check to see if we have a spare virtual bit. Don't want
 * to leave this until run time because most developers don't have a
 * system that can exercise this code path. This will only become a
 * problem if/when we move beyond 5-level page tables.
 *
 * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD)
 */
#if PGDIR_SHIFT + 9 < 63
	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
#else
#error "no unused virtual bit available"
#endif

	if (set_memory_np(decoy_addr, 1))
		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
}
#endif

/*
 * The actual machine check handler. This only handles real
 * exceptions when something got corrupted coming in through int 18.
 *
 * This is executed in NMI context not subject to normal locking rules. This
 * implies that most kernel services cannot be safely used. Don't even
 * think about putting a printk in there!
 *
 * On Intel systems this is entered on all CPUs in parallel through
 * MCE broadcast. However some CPUs might be broken beyond repair,
 * so be always careful when synchronizing with others.
 */
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 severity;

	/*
	 * Establish sequential order between the CPUs entering the machine
	 * check handler.
	 */
	int order = -1;
	/*
	 * If no_way_out gets set, there is no safe way to recover from this
	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
	 */
	int no_way_out = 0;
	/*
	 * If kill_it gets set, there might be a way to recover from this
	 * error.
	 */
	int kill_it = 0;
	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
	char *msg = "Unknown";

	/*
	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
	 * on Intel.
	 */
	int lmce = 1;
	int cpu = smp_processor_id();

	/*
	 * Cases where we avoid rendezvous handler timeout:
	 * 1) If this CPU is offline.
	 *
	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
	 *  skip those CPUs which remain looping in the 1st kernel - see
	 *  crash_nmi_callback().
	 *
	 * Note: there still is a small window between kexec-ing and the new,
	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
	 * might not get handled properly.
	 */
	if (cpu_is_offline(cpu) ||
	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
		u64 mcgstatus;

		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
		if (mcgstatus & MCG_STATUS_RIPV) {
			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
			return;
		}
	}

	ist_enter(regs);

	this_cpu_inc(mce_exception_count);

	if (!cfg->banks)
		goto out;

	mce_gather_info(&m, regs);
	m.tsc = rdtsc();

	final = this_cpu_ptr(&mces_seen);
	*final = m;

	memset(valid_banks, 0, sizeof(valid_banks));
	no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);

	barrier();

	/*
	 * When no restart IP might need to kill or panic.
	 * 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))
		kill_it = 1;

	/*
	 * Check if this MCE is signaled to only this logical processor,
	 * on Intel only.
	 */
	if (m.cpuvendor == X86_VENDOR_INTEL)
		lmce = m.mcgstatus & MCG_STATUS_LMCES;

	/*
	 * Go through all banks in exclusion of the other CPUs. This way we
	 * don't report duplicated events on shared banks because the first one
	 * to see it will clear it. If this is a Local MCE, then no need to
	 * perform rendezvous.
	 */
	if (!lmce)
		order = mce_start(&no_way_out);

	for (i = 0; i < cfg->banks; i++) {
		__clear_bit(i, toclear);
		if (!test_bit(i, valid_banks))
			continue;
		if (!mce_banks[i].ctl)
			continue;

		m.misc = 0;
		m.addr = 0;
		m.bank = i;

		m.status = mce_rdmsrl(msr_ops.status(i));
		if ((m.status & MCI_STATUS_VAL) == 0)
			continue;

		/*
		 * Non uncorrected or non signaled errors are handled by
		 * machine_check_poll. Leave them alone, unless this panics.
		 */
		if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
			!no_way_out)
			continue;

		/*
		 * Set taint even when machine check was not enabled.
		 */
		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);

		severity = mce_severity(&m, cfg->tolerant, NULL, true);

		/*
		 * When machine check was for corrected/deferred handler don't
		 * touch, unless we're panicing.
		 */
		if ((severity == MCE_KEEP_SEVERITY ||
		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
			continue;
		__set_bit(i, toclear);
		if (severity == MCE_NO_SEVERITY) {
			/*
			 * Machine check event was not enabled. Clear, but
			 * ignore.
			 */
			continue;
		}

		mce_read_aux(&m, i);

		/* assuming valid severity level != 0 */
		m.severity = severity;

		mce_log(&m);

		if (severity > worst) {
			*final = m;
			worst = severity;
		}
	}

	/* mce_clear_state will clear *final, save locally for use later */
	m = *final;

	if (!no_way_out)
		mce_clear_state(toclear);

	/*
	 * Do most of the synchronization with other CPUs.
	 * When there's any problem use only local no_way_out state.
	 */
	if (!lmce) {
		if (mce_end(order) < 0)
			no_way_out = worst >= MCE_PANIC_SEVERITY;
	} else {
		/*
		 * Local MCE skipped calling mce_reign()
		 * If we found a fatal error, we need to panic here.
		 */
		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
			mce_panic("Machine check from unknown source",
				NULL, NULL);
	}

	/*
	 * If tolerant is at an insane level we drop requests to kill
	 * processes and continue even when there is no way out.
	 */
	if (cfg->tolerant == 3)
		kill_it = 0;
	else if (no_way_out)
		mce_panic("Fatal machine check on current CPU", &m, msg);

	if (worst > 0)
		mce_report_event(regs);
	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
out:
	sync_core();

	if (worst != MCE_AR_SEVERITY && !kill_it)
		goto out_ist;

	/* Fault was in user mode and we need to take some action */
	if ((m.cs & 3) == 3) {
		ist_begin_non_atomic(regs);
		local_irq_enable();

		if (kill_it || do_memory_failure(&m))
			force_sig(SIGBUS, current);
		local_irq_disable();
		ist_end_non_atomic();
	} else {
		if (!fixup_exception(regs, X86_TRAP_MC))
			mce_panic("Failed kernel mode recovery", &m, NULL);
	}

out_ist:
	ist_exit(regs);
}
EXPORT_SYMBOL_GPL(do_machine_check);

#ifndef CONFIG_MEMORY_FAILURE
int memory_failure(unsigned long pfn, int flags)
{
	/* mce_severity() should not hand us an ACTION_REQUIRED error */
	BUG_ON(flags & MF_ACTION_REQUIRED);
	pr_err("Uncorrected memory error in page 0x%lx ignored\n"
	       "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n",
	       pfn);

	return 0;
}
#endif

/*
 * Periodic polling timer for "silent" machine check errors.  If the
 * poller finds an MCE, poll 2x faster.  When the poller finds no more
 * errors, poll 2x slower (up to check_interval seconds).
 */
static unsigned long check_interval = INITIAL_CHECK_INTERVAL;

static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);

static unsigned long mce_adjust_timer_default(unsigned long interval)
{
	return interval;
}

static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;

static void __start_timer(struct timer_list *t, unsigned long interval)
{
	unsigned long when = jiffies + interval;
	unsigned long flags;

	local_irq_save(flags);

	if (!timer_pending(t) || time_before(when, t->expires))
		mod_timer(t, round_jiffies(when));

	local_irq_restore(flags);
}

static void mce_timer_fn(struct timer_list *t)
{
	struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
	unsigned long iv;

	WARN_ON(cpu_t != t);

	iv = __this_cpu_read(mce_next_interval);

	if (mce_available(this_cpu_ptr(&cpu_info))) {
		machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));

		if (mce_intel_cmci_poll()) {
			iv = mce_adjust_timer(iv);
			goto done;
		}
	}

	/*
	 * Alert userspace if needed. If we logged an MCE, reduce the polling
	 * interval, otherwise increase the polling interval.
	 */
	if (mce_notify_irq())
		iv = max(iv / 2, (unsigned long) HZ/100);
	else
		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));

done:
	__this_cpu_write(mce_next_interval, iv);
	__start_timer(t, iv);
}

/*
 * Ensure that the timer is firing in @interval from now.
 */
void mce_timer_kick(unsigned long interval)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	unsigned long iv = __this_cpu_read(mce_next_interval);

	__start_timer(t, interval);

	if (interval < iv)
		__this_cpu_write(mce_next_interval, interval);
}

/* Must not be called in IRQ context where del_timer_sync() can deadlock */
static void mce_timer_delete_all(void)
{
	int cpu;

	for_each_online_cpu(cpu)
		del_timer_sync(&per_cpu(mce_timer, cpu));
}

/*
 * Notify the user(s) about new machine check events.
 * Can be called from interrupt context, but not from machine check/NMI
 * context.
 */
int mce_notify_irq(void)
{
	/* Not more than two messages every minute */
	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);

	if (test_and_clear_bit(0, &mce_need_notify)) {
		mce_work_trigger();

		if (__ratelimit(&ratelimit))
			pr_info(HW_ERR "Machine check events logged\n");

		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(mce_notify_irq);

static int __mcheck_cpu_mce_banks_init(void)
{
	int i;
	u8 num_banks = mca_cfg.banks;

	mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL);
	if (!mce_banks)
		return -ENOMEM;

	for (i = 0; i < num_banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		b->ctl = -1ULL;
		b->init = 1;
	}
	return 0;
}

/*
 * Initialize Machine Checks for a CPU.
 */
static int __mcheck_cpu_cap_init(void)
{
	unsigned b;
	u64 cap;

	rdmsrl(MSR_IA32_MCG_CAP, cap);

	b = cap & MCG_BANKCNT_MASK;
	if (!mca_cfg.banks)
		pr_info("CPU supports %d MCE banks\n", b);

	if (b > MAX_NR_BANKS) {
		pr_warn("Using only %u machine check banks out of %u\n",
			MAX_NR_BANKS, b);
		b = MAX_NR_BANKS;
	}

	/* Don't support asymmetric configurations today */
	WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
	mca_cfg.banks = b;

	if (!mce_banks) {
		int err = __mcheck_cpu_mce_banks_init();

		if (err)
			return err;
	}

	/* Use accurate RIP reporting if available. */
	if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
		mca_cfg.rip_msr = MSR_IA32_MCG_EIP;

	if (cap & MCG_SER_P)
		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;

	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 | m_fl, &all_banks);

	cr4_set_bits(X86_CR4_MCE);

	rdmsrl(MSR_IA32_MCG_CAP, cap);
	if (cap & MCG_CTL_P)
		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
}

static void __mcheck_cpu_init_clear_banks(void)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (!b->init)
			continue;
		wrmsrl(msr_ops.ctl(i), b->ctl);
		wrmsrl(msr_ops.status(i), 0);
	}
}

/*
 * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
 * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
 * Vol 3B Table 15-20). But this confuses both the code that determines
 * whether the machine check occurred in kernel or user mode, and also
 * the severity assessment code. Pretend that EIPV was set, and take the
 * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
 */
static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
{
	if (bank != 0)
		return;
	if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
		return;
	if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
		          MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
			  MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
			  MCACOD)) !=
			 (MCI_STATUS_UC|MCI_STATUS_EN|
			  MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
			  MCI_STATUS_AR|MCACOD_INSTR))
		return;

	m->mcgstatus |= MCG_STATUS_EIPV;
	m->ip = regs->ip;
	m->cs = regs->cs;
}

/* Add per CPU specific workarounds here */
static int __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 && cfg->banks > 4) {
			/*
			 * disable GART TBL walk error reporting, which
			 * trips off incorrectly with the IOMMU & 3ware
			 * & Cerberus:
			 */
			clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
		}
		if (c->x86 < 0x11 && cfg->bootlog < 0) {
			/*
			 * Lots of broken BIOS around that don't clear them
			 * by default and leave crap in there. Don't log:
			 */
			cfg->bootlog = 0;
		}
		/*
		 * Various K7s with broken bank 0 around. Always disable
		 * by default.
		 */
		if (c->x86 == 6 && cfg->banks > 0)
			mce_banks[0].ctl = 0;

		/*
		 * overflow_recov is supported for F15h Models 00h-0fh
		 * even though we don't have a CPUID bit for it.
		 */
		if (c->x86 == 0x15 && c->x86_model <= 0xf)
			mce_flags.overflow_recov = 1;

		/*
		 * Turn off MC4_MISC thresholding banks on those models since
		 * they're not supported there.
		 */
		if (c->x86 == 0x15 &&
		    (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
			int i;
			u64 hwcr;
			bool need_toggle;
			u32 msrs[] = {
				0x00000413, /* MC4_MISC0 */
				0xc0000408, /* MC4_MISC1 */
			};

			rdmsrl(MSR_K7_HWCR, hwcr);

			/* McStatusWrEn has to be set */
			need_toggle = !(hwcr & BIT(18));

			if (need_toggle)
				wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));

			/* Clear CntP bit safely */
			for (i = 0; i < ARRAY_SIZE(msrs); i++)
				msr_clear_bit(msrs[i], 62);

			/* restore old settings */
			if (need_toggle)
				wrmsrl(MSR_K7_HWCR, hwcr);
		}
	}

	if (c->x86_vendor == X86_VENDOR_INTEL) {
		/*
		 * SDM documents that on family 6 bank 0 should not be written
		 * because it aliases to another special BIOS controlled
		 * register.
		 * But it's not aliased anymore on model 0x1a+
		 * Don't ignore bank 0 completely because there could be a
		 * valid event later, merely don't write CTL0.
		 */

		if (c->x86 == 6 && c->x86_model < 0x1A && cfg->banks > 0)
			mce_banks[0].init = 0;

		/*
		 * All newer Intel systems support MCE broadcasting. Enable
		 * synchronization with a one second timeout.
		 */
		if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
			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 && cfg->bootlog < 0)
			cfg->bootlog = 0;

		if (c->x86 == 6 && c->x86_model == 45)
			quirk_no_way_out = quirk_sandybridge_ifu;
	}
	if (cfg->monarch_timeout < 0)
		cfg->monarch_timeout = 0;
	if (cfg->bootlog != 0)
		cfg->panic_timeout = 30;

	return 0;
}

static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
{
	if (c->x86 != 5)
		return 0;

	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		intel_p5_mcheck_init(c);
		return 1;
		break;
	case X86_VENDOR_CENTAUR:
		winchip_mcheck_init(c);
		return 1;
		break;
	default:
		return 0;
	}

	return 0;
}

/*
 * Init basic CPU features needed for early decoding of MCEs.
 */
static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
{
	if (c->x86_vendor == X86_VENDOR_AMD) {
		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);

		if (mce_flags.smca) {
			msr_ops.ctl	= smca_ctl_reg;
			msr_ops.status	= smca_status_reg;
			msr_ops.addr	= smca_addr_reg;
			msr_ops.misc	= smca_misc_reg;
		}
	}
}

static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
{
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		mce_intel_feature_init(c);
		mce_adjust_timer = cmci_intel_adjust_timer;
		break;

	case X86_VENDOR_AMD: {
		mce_amd_feature_init(c);
		break;
		}

	default:
		break;
	}
}

static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
{
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		mce_intel_feature_clear(c);
		break;
	default:
		break;
	}
}

static void mce_start_timer(struct timer_list *t)
{
	unsigned long iv = check_interval * HZ;

	if (mca_cfg.ignore_ce || !iv)
		return;

	this_cpu_write(mce_next_interval, iv);
	__start_timer(t, iv);
}

static void __mcheck_cpu_setup_timer(void)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);

	timer_setup(t, mce_timer_fn, TIMER_PINNED);
}

static void __mcheck_cpu_init_timer(void)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);

	timer_setup(t, mce_timer_fn, TIMER_PINNED);
	mce_start_timer(t);
}

/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
	pr_err("CPU#%d: Unexpected int18 (Machine Check)\n",
	       smp_processor_id());
}

/* Call the installed machine check handler for this CPU setup. */
void (*machine_check_vector)(struct pt_regs *, long error_code) =
						unexpected_machine_check;

dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
{
	machine_check_vector(regs, error_code);
}

/*
 * Called for each booted CPU to set up machine checks.
 * Must be called with preempt off:
 */
void mcheck_cpu_init(struct cpuinfo_x86 *c)
{
	if (mca_cfg.disabled)
		return;

	if (__mcheck_cpu_ancient_init(c))
		return;

	if (!mce_available(c))
		return;

	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
		mca_cfg.disabled = true;
		return;
	}

	if (mce_gen_pool_init()) {
		mca_cfg.disabled = true;
		pr_emerg("Couldn't allocate MCE records pool!\n");
		return;
	}

	machine_check_vector = do_machine_check;

	__mcheck_cpu_init_early(c);
	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_vendor(c);
	__mcheck_cpu_init_clear_banks();
	__mcheck_cpu_setup_timer();
}

/*
 * Called for each booted CPU to clear some machine checks opt-ins
 */
void mcheck_cpu_clear(struct cpuinfo_x86 *c)
{
	if (mca_cfg.disabled)
		return;

	if (!mce_available(c))
		return;

	/*
	 * Possibly to clear general settings generic to x86
	 * __mcheck_cpu_clear_generic(c);
	 */
	__mcheck_cpu_clear_vendor(c);

}

static void __mce_disable_bank(void *arg)
{
	int bank = *((int *)arg);
	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
	cmci_disable_bank(bank);
}

void mce_disable_bank(int bank)
{
	if (bank >= mca_cfg.banks) {
		pr_warn(FW_BUG
			"Ignoring request to disable invalid MCA bank %d.\n",
			bank);
		return;
	}
	set_bit(bank, mce_banks_ce_disabled);
	on_each_cpu(__mce_disable_bank, &bank, 1);
}

/*
 * mce=off Disables machine check
 * mce=no_cmci Disables CMCI
 * mce=no_lmce Disables LMCE
 * 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
 * mce=bootlog Log MCEs from before booting. Disabled by default on AMD Fam10h
	and older.
 * mce=nobootlog Don't log MCEs from before booting.
 * mce=bios_cmci_threshold Don't program the CMCI threshold
 * mce=recovery force enable memcpy_mcsafe()
 */
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"))
		cfg->disabled = true;
	else if (!strcmp(str, "no_cmci"))
		cfg->cmci_disabled = true;
	else if (!strcmp(str, "no_lmce"))
		cfg->lmce_disabled = true;
	else if (!strcmp(str, "dont_log_ce"))
		cfg->dont_log_ce = true;
	else if (!strcmp(str, "ignore_ce"))
		cfg->ignore_ce = true;
	else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
		cfg->bootlog = (str[0] == 'b');
	else if (!strcmp(str, "bios_cmci_threshold"))
		cfg->bios_cmci_threshold = true;
	else if (!strcmp(str, "recovery"))
		cfg->recovery = true;
	else if (isdigit(str[0])) {
		if (get_option(&str, &cfg->tolerant) == 2)
			get_option(&str, &(cfg->monarch_timeout));
	} else {
		pr_info("mce argument %s ignored. Please use /sys\n", str);
		return 0;
	}
	return 1;
}
__setup("mce", mcheck_enable);

int __init mcheck_init(void)
{
	mcheck_intel_therm_init();
	mce_register_decode_chain(&first_nb);
	mce_register_decode_chain(&mce_srao_nb);
	mce_register_decode_chain(&mce_default_nb);
	mcheck_vendor_init_severity();

	INIT_WORK(&mce_work, mce_gen_pool_process);
	init_irq_work(&mce_irq_work, mce_irq_work_cb);

	return 0;
}

/*
 * mce_syscore: PM support
 */

/*
 * Disable machine checks on suspend and shutdown. We can't really handle
 * them later.
 */
static void mce_disable_error_reporting(void)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (b->init)
			wrmsrl(msr_ops.ctl(i), 0);
	}
	return;
}

static void vendor_disable_error_reporting(void)
{
	/*
	 * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide.
	 * Disabling them for just a single offlined CPU is bad, since it will
	 * inhibit reporting for all shared resources on the socket like the
	 * last level cache (LLC), the integrated memory controller (iMC), etc.
	 */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
		return;

	mce_disable_error_reporting();
}

static int mce_syscore_suspend(void)
{
	vendor_disable_error_reporting();
	return 0;
}

static void mce_syscore_shutdown(void)
{
	vendor_disable_error_reporting();
}

/*
 * On resume clear all MCE state. Don't want to see leftovers from the BIOS.
 * Only one CPU is active at this time, the others get re-added later using
 * CPU hotplug:
 */
static void mce_syscore_resume(void)
{
	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
	__mcheck_cpu_init_clear_banks();
}

static struct syscore_ops mce_syscore_ops = {
	.suspend	= mce_syscore_suspend,
	.shutdown	= mce_syscore_shutdown,
	.resume		= mce_syscore_resume,
};

/*
 * mce_device: Sysfs support
 */

static void mce_cpu_restart(void *data)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_clear_banks();
	__mcheck_cpu_init_timer();
}

/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
	mce_timer_delete_all();
	on_each_cpu(mce_cpu_restart, NULL, 1);
}

/* Toggle features for corrected errors */
static void mce_disable_cmci(void *data)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	cmci_clear();
}

static void mce_enable_ce(void *all)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	cmci_reenable();
	cmci_recheck();
	if (all)
		__mcheck_cpu_init_timer();
}

static struct bus_type mce_subsys = {
	.name		= "machinecheck",
	.dev_name	= "machinecheck",
};

DEFINE_PER_CPU(struct device *, mce_device);

static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
{
	return container_of(attr, struct mce_bank, attr);
}

static ssize_t show_bank(struct device *s, struct device_attribute *attr,
			 char *buf)
{
	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
}

static ssize_t set_bank(struct device *s, struct device_attribute *attr,
			const char *buf, size_t size)
{
	u64 new;

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	attr_to_bank(attr)->ctl = new;
	mce_restart();

	return size;
}

static ssize_t set_ignore_ce(struct device *s,
			     struct device_attribute *attr,
			     const char *buf, size_t size)
{
	u64 new;

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	if (mca_cfg.ignore_ce ^ !!new) {
		if (new) {
			/* disable ce features */
			mce_timer_delete_all();
			on_each_cpu(mce_disable_cmci, NULL, 1);
			mca_cfg.ignore_ce = true;
		} else {
			/* enable ce features */
			mca_cfg.ignore_ce = false;
			on_each_cpu(mce_enable_ce, (void *)1, 1);
		}
	}
	return size;
}

static ssize_t set_cmci_disabled(struct device *s,
				 struct device_attribute *attr,
				 const char *buf, size_t size)
{
	u64 new;

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	if (mca_cfg.cmci_disabled ^ !!new) {
		if (new) {
			/* disable cmci */
			on_each_cpu(mce_disable_cmci, NULL, 1);
			mca_cfg.cmci_disabled = true;
		} else {
			/* enable cmci */
			mca_cfg.cmci_disabled = false;
			on_each_cpu(mce_enable_ce, NULL, 1);
		}
	}
	return size;
}

static ssize_t store_int_with_restart(struct device *s,
				      struct device_attribute *attr,
				      const char *buf, size_t size)
{
	ssize_t ret = device_store_int(s, attr, buf, size);
	mce_restart();
	return ret;
}

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),
	&check_interval
};

static struct dev_ext_attribute dev_attr_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_bool, set_cmci_disabled),
	&mca_cfg.cmci_disabled
};

static struct device_attribute *mce_device_attrs[] = {
	&dev_attr_tolerant.attr,
	&dev_attr_check_interval.attr,
#ifdef CONFIG_X86_MCELOG_LEGACY
	&dev_attr_trigger,
#endif
	&dev_attr_monarch_timeout.attr,
	&dev_attr_dont_log_ce.attr,
	&dev_attr_ignore_ce.attr,
	&dev_attr_cmci_disabled.attr,
	NULL
};

static cpumask_var_t mce_device_initialized;

static void mce_device_release(struct device *dev)
{
	kfree(dev);
}

/* Per cpu device init. All of the cpus still share the same ctrl bank: */
static int mce_device_create(unsigned int cpu)
{
	struct device *dev;
	int err;
	int i, j;

	if (!mce_available(&boot_cpu_data))
		return -EIO;

	dev = per_cpu(mce_device, cpu);
	if (dev)
		return 0;

	dev = kzalloc(sizeof *dev, GFP_KERNEL);
	if (!dev)
		return -ENOMEM;
	dev->id  = cpu;
	dev->bus = &mce_subsys;
	dev->release = &mce_device_release;

	err = device_register(dev);
	if (err) {
		put_device(dev);
		return err;
	}

	for (i = 0; mce_device_attrs[i]; i++) {
		err = device_create_file(dev, mce_device_attrs[i]);
		if (err)
			goto error;
	}
	for (j = 0; j < mca_cfg.banks; j++) {
		err = device_create_file(dev, &mce_banks[j].attr);
		if (err)
			goto error2;
	}
	cpumask_set_cpu(cpu, mce_device_initialized);
	per_cpu(mce_device, cpu) = dev;

	return 0;
error2:
	while (--j >= 0)
		device_remove_file(dev, &mce_banks[j].attr);
error:
	while (--i >= 0)
		device_remove_file(dev, mce_device_attrs[i]);

	device_unregister(dev);

	return err;
}

static void mce_device_remove(unsigned int cpu)
{
	struct device *dev = per_cpu(mce_device, cpu);
	int i;

	if (!cpumask_test_cpu(cpu, mce_device_initialized))
		return;

	for (i = 0; mce_device_attrs[i]; i++)
		device_remove_file(dev, mce_device_attrs[i]);

	for (i = 0; i < mca_cfg.banks; i++)
		device_remove_file(dev, &mce_banks[i].attr);

	device_unregister(dev);
	cpumask_clear_cpu(cpu, mce_device_initialized);
	per_cpu(mce_device, cpu) = NULL;
}

/* Make sure there are no machine checks on offlined CPUs. */
static void mce_disable_cpu(void)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;

	if (!cpuhp_tasks_frozen)
		cmci_clear();

	vendor_disable_error_reporting();
}

static void mce_reenable_cpu(void)
{
	int i;

	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;

	if (!cpuhp_tasks_frozen)
		cmci_reenable();
	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (b->init)
			wrmsrl(msr_ops.ctl(i), b->ctl);
	}
}

static int mce_cpu_dead(unsigned int cpu)
{
	mce_intel_hcpu_update(cpu);

	/* intentionally ignoring frozen here */
	if (!cpuhp_tasks_frozen)
		cmci_rediscover();
	return 0;
}

static int mce_cpu_online(unsigned int cpu)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	int ret;

	mce_device_create(cpu);

	ret = mce_threshold_create_device(cpu);
	if (ret) {
		mce_device_remove(cpu);
		return ret;
	}
	mce_reenable_cpu();
	mce_start_timer(t);
	return 0;
}

static int mce_cpu_pre_down(unsigned int cpu)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);

	mce_disable_cpu();
	del_timer_sync(t);
	mce_threshold_remove_device(cpu);
	mce_device_remove(cpu);
	return 0;
}

static __init void mce_init_banks(void)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];
		struct device_attribute *a = &b->attr;

		sysfs_attr_init(&a->attr);
		a->attr.name	= b->attrname;
		snprintf(b->attrname, ATTR_LEN, "bank%d", i);

		a->attr.mode	= 0644;
		a->show		= show_bank;
		a->store	= set_bank;
	}
}

static __init int mcheck_init_device(void)
{
	int err;

	if (!mce_available(&boot_cpu_data)) {
		err = -EIO;
		goto err_out;
	}

	if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) {
		err = -ENOMEM;
		goto err_out;
	}

	mce_init_banks();

	err = subsys_system_register(&mce_subsys, NULL);
	if (err)
		goto err_out_mem;

	err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL,
				mce_cpu_dead);
	if (err)
		goto err_out_mem;

	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
				mce_cpu_online, mce_cpu_pre_down);
	if (err < 0)
		goto err_out_online;

	register_syscore_ops(&mce_syscore_ops);

	return 0;

err_out_online:
	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);

err_out_mem:
	free_cpumask_var(mce_device_initialized);

err_out:
	pr_err("Unable to init MCE device (rc: %d)\n", err);

	return err;
}
device_initcall_sync(mcheck_init_device);

/*
 * Old style boot options parsing. Only for compatibility.
 */
static int __init mcheck_disable(char *str)
{
	mca_cfg.disabled = true;
	return 1;
}
__setup("nomce", mcheck_disable);

#ifdef CONFIG_DEBUG_FS
struct dentry *mce_get_debugfs_dir(void)
{
	static struct dentry *dmce;

	if (!dmce)
		dmce = debugfs_create_dir("mce", NULL);

	return dmce;
}

static void mce_reset(void)
{
	cpu_missing = 0;
	atomic_set(&mce_fake_panicked, 0);
	atomic_set(&mce_executing, 0);
	atomic_set(&mce_callin, 0);
	atomic_set(&global_nwo, 0);
}

static int fake_panic_get(void *data, u64 *val)
{
	*val = fake_panic;
	return 0;
}

static int fake_panic_set(void *data, u64 val)
{
	mce_reset();
	fake_panic = val;
	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
			fake_panic_set, "%llu\n");

static int __init mcheck_debugfs_init(void)
{
	struct dentry *dmce, *ffake_panic;

	dmce = mce_get_debugfs_dir();
	if (!dmce)
		return -ENOMEM;
	ffake_panic = debugfs_create_file("fake_panic", 0444, dmce, NULL,
					  &fake_panic_fops);
	if (!ffake_panic)
		return -ENOMEM;

	return 0;
}
#else
static int __init mcheck_debugfs_init(void) { return -EINVAL; }
#endif

DEFINE_STATIC_KEY_FALSE(mcsafe_key);
EXPORT_SYMBOL_GPL(mcsafe_key);

static int __init mcheck_late_init(void)
{
	if (mca_cfg.recovery)
		static_branch_inc(&mcsafe_key);

	mcheck_debugfs_init();
	cec_init();

	/*
	 * Flush out everything that has been logged during early boot, now that
	 * everything has been initialized (workqueues, decoders, ...).
	 */
	mce_schedule_work();

	return 0;
}
late_initcall(mcheck_late_init);