1 files changed, 298 insertions, 299 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7fb5556a0b53..34440021e8cf 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -45,6 +45,7 @@
 #include <linux/task_work.h>
 #include <linux/hardirq.h>
 #include <linux/kexec.h>
+#include <linux/vmcore_info.h>
 
 #include <asm/fred.h>
 #include <asm/cpu_device_id.h>
@@ -121,7 +122,7 @@ void mce_prep_record_common(struct mce *m)
 {
 	m->cpuid	= cpuid_eax(1);
 	m->cpuvendor	= boot_cpu_data.x86_vendor;
-	m->mcgcap	= __rdmsr(MSR_IA32_MCG_CAP);
+	m->mcgcap	= native_rdmsrq(MSR_IA32_MCG_CAP);
 	/* need the internal __ version to avoid deadlocks */
 	m->time		= __ktime_get_real_seconds();
 }
@@ -151,7 +152,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm);
 
 void mce_log(struct mce_hw_err *err)
 {
-	if (!mce_gen_pool_add(err))
+	if (mce_gen_pool_add(err))
 		irq_work_queue(&mce_irq_work);
 }
 EXPORT_SYMBOL_GPL(mce_log);
@@ -388,9 +389,9 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 }
 
 /* MSR access wrappers used for error injection */
-noinstr u64 mce_rdmsrl(u32 msr)
+noinstr u64 mce_rdmsrq(u32 msr)
 {
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	if (__this_cpu_read(injectm.finished)) {
 		int offset;
@@ -423,7 +424,7 @@ noinstr u64 mce_rdmsrl(u32 msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static noinstr void mce_wrmsrl(u32 msr, u64 v)
+noinstr void mce_wrmsrq(u32 msr, u64 v)
 {
 	u32 low, high;
 
@@ -444,7 +445,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
 	low  = (u32)v;
 	high = (u32)(v >> 32);
 
-	/* See comment in mce_rdmsrl() */
+	/* See comment in mce_rdmsrq() */
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
@@ -468,7 +469,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 	instrumentation_end();
 
 	m = &err->m;
-	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+	m->mcgstatus = mce_rdmsrq(MSR_IA32_MCG_STATUS);
 	if (regs) {
 		/*
 		 * Get the address of the instruction at the time of
@@ -488,14 +489,14 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 		}
 		/* Use accurate RIP reporting if available. */
 		if (mca_cfg.rip_msr)
-			m->ip = mce_rdmsrl(mca_cfg.rip_msr);
+			m->ip = mce_rdmsrq(mca_cfg.rip_msr);
 	}
 }
 
-int mce_available(struct cpuinfo_x86 *c)
+bool mce_available(struct cpuinfo_x86 *c)
 {
 	if (mca_cfg.disabled)
-		return 0;
+		return false;
 	return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA);
 }
 
@@ -584,6 +585,28 @@ bool mce_is_correctable(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_correctable);
 
+/*
+ * Notify the user(s) about new machine check events.
+ * Can be called from interrupt context, but not from machine check/NMI
+ * context.
+ */
+static bool 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 true;
+	}
+
+	return false;
+}
+
 static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
@@ -662,10 +685,13 @@ 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));
+		m->misc = mce_rdmsrq(mca_msr_reg(i, MCA_MISC));
 
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR));
+		if (m->kflags & MCE_CHECK_DFR_REGS)
+			m->addr = mce_rdmsrq(MSR_AMD64_SMCA_MCx_DEADDR(i));
+		else
+			m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -680,12 +706,12 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 	}
 
 	if (mce_flags.smca) {
-		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+		m->ipid = mce_rdmsrq(MSR_AMD64_SMCA_MCx_IPID(i));
 
 		if (m->status & MCI_STATUS_SYNDV) {
-			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
-			err->vendor.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i));
-			err->vendor.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i));
+			m->synd = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND(i));
+			err->vendor.amd.synd1 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(i));
+			err->vendor.amd.synd2 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(i));
 		}
 	}
 }
@@ -693,6 +719,86 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
+ * We have three scenarios for checking for Deferred errors:
+ *
+ * 1) Non-SMCA systems check MCA_STATUS and log error if found.
+ * 2) SMCA systems check MCA_STATUS. If error is found then log it and also
+ *    clear MCA_DESTAT.
+ * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and
+ *    log it.
+ */
+static bool smca_should_log_poll_error(struct mce *m)
+{
+	if (m->status & MCI_STATUS_VAL)
+		return true;
+
+	m->status = mce_rdmsrq(MSR_AMD64_SMCA_MCx_DESTAT(m->bank));
+	if ((m->status & MCI_STATUS_VAL) && (m->status & MCI_STATUS_DEFERRED)) {
+		m->kflags |= MCE_CHECK_DFR_REGS;
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Newer Intel systems that support software error
+ * recovery need to make additional checks. Other
+ * CPUs should skip over uncorrected errors, but log
+ * everything else.
+ */
+static bool ser_should_log_poll_error(struct mce *m)
+{
+	/* Log "not enabled" (speculative) errors */
+	if (!(m->status & MCI_STATUS_EN))
+		return true;
+
+	/*
+	 * 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))
+		return true;
+
+	return false;
+}
+
+static bool should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
+{
+	struct mce *m = &err->m;
+
+	if (mce_flags.smca)
+		return smca_should_log_poll_error(m);
+
+	/* If this entry is not valid, ignore it. */
+	if (!(m->status & MCI_STATUS_VAL))
+		return false;
+
+	/*
+	 * 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))
+		return true;
+
+	if (mca_cfg.ser)
+		return ser_should_log_poll_error(m);
+
+	if (m->status & MCI_STATUS_UC)
+		return false;
+
+	return true;
+}
+
+static void clear_bank(struct mce *m)
+{
+	if (m->cpuvendor == X86_VENDOR_AMD)
+		return amd_clear_bank(m);
+
+	mce_wrmsrq(mca_msr_reg(m->bank, MCA_STATUS), 0);
+}
+
+/*
  * Poll for corrected events or events that happened before reset.
  * Those are just logged through /dev/mcelog.
  *
@@ -731,7 +837,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m->bank = i;
 
 		barrier();
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 
 		/*
 		 * Update storm tracking here, before checking for the
@@ -743,51 +849,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!mca_cfg.cmci_disabled)
 			mce_track_storm(m);
 
-		/* If this entry is not valid, ignore it */
-		if (!(m->status & MCI_STATUS_VAL))
+		/* Verify that the error should be logged based on hardware conditions. */
+		if (!should_log_poll_error(flags, &err))
 			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))
-			goto log_it;
-
-		/*
-		 * Newer Intel systems that support software error
-		 * recovery need to make additional checks. Other
-		 * CPUs should skip over uncorrected errors, but log
-		 * everything else.
-		 */
-		if (!mca_cfg.ser) {
-			if (m->status & MCI_STATUS_UC)
-				continue;
-			goto log_it;
-		}
-
-		/* Log "not enabled" (speculative) errors */
-		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))
-			goto log_it;
-
-		/*
-		 * Skip anything else. Presumption is that our read of this
-		 * bank is racing with a machine check. Leave the log alone
-		 * for do_machine_check() to deal with it.
-		 */
-		continue;
-
-log_it:
-		if (flags & MCP_DONTLOG)
-			goto clear_it;
-
 		mce_read_aux(&err, i);
 		m->severity = mce_severity(m, NULL, NULL, false);
 		/*
@@ -804,10 +869,7 @@ log_it:
 			mce_log(&err);
 
 clear_it:
-		/*
-		 * Clear state for this bank.
-		 */
-		mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		clear_bank(m);
 	}
 
 	/*
@@ -865,8 +927,8 @@ quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
  */
 static noinstr bool quirk_skylake_repmov(void)
 {
-	u64 mcgstatus   = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-	u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE);
+	u64 mcgstatus   = mce_rdmsrq(MSR_IA32_MCG_STATUS);
+	u64 misc_enable = mce_rdmsrq(MSR_IA32_MISC_ENABLE);
 	u64 mc1_status;
 
 	/*
@@ -877,7 +939,7 @@ static noinstr bool quirk_skylake_repmov(void)
 	    !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING))
 		return false;
 
-	mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1));
+	mc1_status = mce_rdmsrq(MSR_IA32_MCx_STATUS(1));
 
 	/* Check for a software-recoverable data fetch error. */
 	if ((mc1_status &
@@ -888,8 +950,8 @@ static noinstr bool quirk_skylake_repmov(void)
 	      MCI_STATUS_ADDRV | MCI_STATUS_MISCV |
 	      MCI_STATUS_AR | MCI_STATUS_S)) {
 		misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-		mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0);
+		mce_wrmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
+		mce_wrmsrq(MSR_IA32_MCx_STATUS(1), 0);
 
 		instrumentation_begin();
 		pr_err_once("Erratum detected, disable fast string copy instructions.\n");
@@ -933,7 +995,7 @@ static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, un
 	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1252,7 +1314,7 @@ static __always_inline void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (arch_test_bit(i, toclear))
-			mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+			mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1276,7 +1338,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
-		mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS);
+		mcgstatus = native_rdmsrq(MSR_IA32_MCG_STATUS);
 
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
 			if (mcgstatus & MCG_STATUS_LMCES)
@@ -1284,7 +1346,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 		}
 
 		if (mcgstatus & MCG_STATUS_RIPV) {
-			__wrmsr(MSR_IA32_MCG_STATUS, 0, 0);
+			native_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 			return true;
 		}
 	}
@@ -1313,7 +1375,7 @@ __mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs,
 		m->addr = 0;
 		m->bank = i;
 
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1668,10 +1730,13 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	}
 
 out:
+	/* Given it didn't panic, mark it as recoverable */
+	hwerr_log_error_type(HWERR_RECOV_OTHERS);
+
 	instrumentation_end();
 
 clear:
-	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+	mce_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1718,6 +1783,11 @@ static void mc_poll_banks_default(void)
 
 void (*mc_poll_banks)(void) = mc_poll_banks_default;
 
+static bool should_enable_timer(unsigned long iv)
+{
+	return !mca_cfg.ignore_ce && iv;
+}
+
 static void mce_timer_fn(struct timer_list *t)
 {
 	struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1741,7 +1811,7 @@ static void mce_timer_fn(struct timer_list *t)
 
 	if (mce_get_storm_mode()) {
 		__start_timer(t, HZ);
-	} else {
+	} else if (should_enable_timer(iv)) {
 		__this_cpu_write(mce_next_interval, iv);
 		__start_timer(t, iv);
 	}
@@ -1764,36 +1834,14 @@ void mce_timer_kick(bool storm)
 		__this_cpu_write(mce_next_interval, check_interval * HZ);
 }
 
-/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+/* Must not be called in IRQ context where timer_delete_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;
+		timer_delete_sync(&per_cpu(mce_timer, cpu));
 }
-EXPORT_SYMBOL_GPL(mce_notify_irq);
 
 static void __mcheck_cpu_mce_banks_init(void)
 {
@@ -1805,9 +1853,10 @@ static void __mcheck_cpu_mce_banks_init(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		/*
-		 * Init them all, __mcheck_cpu_apply_quirks() is going to apply
-		 * the required vendor quirks before
-		 * __mcheck_cpu_init_clear_banks() does the final bank setup.
+		 * Init them all by default.
+		 *
+		 * The required vendor quirks will be applied before
+		 * __mcheck_cpu_init_prepare_banks() does the final bank setup.
 		 */
 		b->ctl = -1ULL;
 		b->init = true;
@@ -1822,7 +1871,7 @@ static void __mcheck_cpu_cap_init(void)
 	u64 cap;
 	u8 b;
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
 
@@ -1835,69 +1884,34 @@ static void __mcheck_cpu_cap_init(void)
 	this_cpu_write(mce_num_banks, b);
 
 	__mcheck_cpu_mce_banks_init();
-
-	/* 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 = 1;
 }
 
 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. Log them
-	 * only, do not start processing them. That will happen in mcheck_late_init()
-	 * when all consumers have been registered on the notifier chain.
-	 */
-	bitmap_fill(all_banks, MAX_NR_BANKS);
-	machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
-
-	cr4_set_bits(X86_CR4_MCE);
-
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(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)
+static void __mcheck_cpu_init_prepare_banks(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	u64 msrval;
 	int i;
 
-	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		struct mce_bank *b = &mce_banks[i];
+	/*
+	 * Log the machine checks left over from the previous reset. Log them
+	 * only, do not start processing them. That will happen in mcheck_late_init()
+	 * when all consumers have been registered on the notifier chain.
+	 */
+	if (mca_cfg.bootlog) {
+		mce_banks_t all_banks;
 
-		if (!b->init)
-			continue;
-		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		bitmap_fill(all_banks, MAX_NR_BANKS);
+		machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
 	}
-}
-
-/*
- * Do a final check to see if there are any unused/RAZ banks.
- *
- * This must be done after the banks have been initialized and any quirks have
- * been applied.
- *
- * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
- * Otherwise, a user who disables a bank will not be able to re-enable it
- * without a system reboot.
- */
-static void __mcheck_cpu_check_banks(void)
-{
-	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-	u64 msrval;
-	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -1905,148 +1919,97 @@ static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
-		rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
+		wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+		wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+
+		rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
 		b->init = !!msrval;
 	}
 }
 
-/* Add per CPU specific workarounds here */
-static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
+static void amd_apply_global_quirks(struct cpuinfo_x86 *c)
 {
-	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-	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 && this_cpu_read(mce_num_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 && this_cpu_read(mce_num_banks) > 0)
-			mce_banks[0].ctl = 0;
-
+	if (c->x86 < 0x11 && mca_cfg.bootlog < 0) {
 		/*
-		 * overflow_recov is supported for F15h Models 00h-0fh
-		 * even though we don't have a CPUID bit for it.
+		 * Lots of broken BIOS around that don't clear them
+		 * by default and leave crap in there. Don't log:
 		 */
-		if (c->x86 == 0x15 && c->x86_model <= 0xf)
-			mce_flags.overflow_recov = 1;
-
-		if (c->x86 >= 0x17 && c->x86 <= 0x1A)
-			mce_flags.zen_ifu_quirk = 1;
-
+		mca_cfg.bootlog = 0;
 	}
 
-	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 && this_cpu_read(mce_num_banks) > 0)
-			mce_banks[0].init = false;
+	/*
+	 * 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;
 
-		/*
-		 * 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;
+	if (c->x86 >= 0x17 && c->x86 <= 0x1A)
+		mce_flags.zen_ifu_quirk = 1;
+}
 
-		/*
-		 * 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;
+static void intel_apply_global_quirks(struct cpuinfo_x86 *c)
+{
+	/* Older CPUs (prior to family 6) don't need quirks. */
+	if (c->x86_vfm < INTEL_PENTIUM_PRO)
+		return;
 
-		if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
-			mce_flags.snb_ifu_quirk = 1;
+	/*
+	 * All newer Intel systems support MCE broadcasting. Enable
+	 * synchronization with a one second timeout.
+	 */
+	if (c->x86_vfm >= INTEL_CORE_YONAH && mca_cfg.monarch_timeout < 0)
+		mca_cfg.monarch_timeout = USEC_PER_SEC;
 
-		/*
-		 * Skylake, Cascacde Lake and Cooper Lake require a quirk on
-		 * rep movs.
-		 */
-		if (c->x86_vfm == INTEL_SKYLAKE_X)
-			mce_flags.skx_repmov_quirk = 1;
-	}
+	/*
+	 * There are also broken BIOSes on some Pentium M and
+	 * earlier systems:
+	 */
+	if (c->x86_vfm < INTEL_CORE_YONAH && mca_cfg.bootlog < 0)
+		mca_cfg.bootlog = 0;
 
-	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
-		/*
-		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
-		 * synchronization with a one second timeout.
-		 */
-		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
-			if (cfg->monarch_timeout < 0)
-				cfg->monarch_timeout = USEC_PER_SEC;
-		}
-	}
+	if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
+		mce_flags.snb_ifu_quirk = 1;
 
-	if (cfg->monarch_timeout < 0)
-		cfg->monarch_timeout = 0;
-	if (cfg->bootlog != 0)
-		cfg->panic_timeout = 30;
+	/*
+	 * Skylake, Cascacde Lake and Cooper Lake require a quirk on
+	 * rep movs.
+	 */
+	if (c->x86_vfm == INTEL_SKYLAKE_X)
+		mce_flags.skx_repmov_quirk = 1;
+}
 
-	return 0;
+static void zhaoxin_apply_global_quirks(struct cpuinfo_x86 *c)
+{
+	/*
+	 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+	 * synchronization with a one second timeout.
+	 */
+	if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (mca_cfg.monarch_timeout < 0)
+			mca_cfg.monarch_timeout = USEC_PER_SEC;
+	}
 }
 
-static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
+static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 {
 	if (c->x86 != 5)
-		return 0;
+		return false;
 
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		intel_p5_mcheck_init(c);
 		mce_flags.p5 = 1;
-		return 1;
+		return true;
 	case X86_VENDOR_CENTAUR:
 		winchip_mcheck_init(c);
 		mce_flags.winchip = 1;
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 
-	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 || c->x86_vendor == X86_VENDOR_HYGON) {
-		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);
-		mce_flags.amd_threshold	 = 1;
-	}
+	return false;
 }
 
 static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
@@ -2099,13 +2062,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_intel_feature_init(c);
 		break;
 
-	case X86_VENDOR_AMD: {
-		mce_amd_feature_init(c);
-		break;
-		}
-
+	case X86_VENDOR_AMD:
 	case X86_VENDOR_HYGON:
-		mce_hygon_feature_init(c);
+		mce_amd_feature_init(c);
 		break;
 
 	case X86_VENDOR_CENTAUR:
@@ -2141,11 +2100,10 @@ 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);
+	if (should_enable_timer(iv)) {
+		this_cpu_write(mce_next_interval, iv);
+		__start_timer(t, iv);
+	}
 }
 
 static void __mcheck_cpu_setup_timer(void)
@@ -2262,6 +2220,53 @@ DEFINE_IDTENTRY_RAW(exc_machine_check)
 }
 #endif
 
+void mca_bsp_init(struct cpuinfo_x86 *c)
+{
+	u64 cap;
+
+	if (!mce_available(c))
+		return;
+
+	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
+		mca_cfg.disabled = 1;
+		pr_info("unknown CPU type - not enabling MCE support\n");
+		return;
+	}
+
+	mce_flags.overflow_recov = cpu_feature_enabled(X86_FEATURE_OVERFLOW_RECOV);
+	mce_flags.succor	 = cpu_feature_enabled(X86_FEATURE_SUCCOR);
+	mce_flags.smca		 = cpu_feature_enabled(X86_FEATURE_SMCA);
+
+	if (mce_flags.smca)
+		smca_bsp_init();
+
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
+
+	/* 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 = 1;
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		amd_apply_global_quirks(c);
+		break;
+	case X86_VENDOR_INTEL:
+		intel_apply_global_quirks(c);
+		break;
+	case X86_VENDOR_ZHAOXIN:
+		zhaoxin_apply_global_quirks(c);
+		break;
+	}
+
+	if (mca_cfg.monarch_timeout < 0)
+		mca_cfg.monarch_timeout = 0;
+	if (mca_cfg.bootlog != 0)
+		mca_cfg.panic_timeout = 30;
+}
+
 /*
  * Called for each booted CPU to set up machine checks.
  * Must be called with preempt off:
@@ -2279,12 +2284,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	__mcheck_cpu_cap_init();
 
-	if (__mcheck_cpu_apply_quirks(c) < 0) {
-		mca_cfg.disabled = 1;
-		return;
-	}
-
-	if (mce_gen_pool_init()) {
+	if (!mce_gen_pool_init()) {
 		mca_cfg.disabled = 1;
 		pr_emerg("Couldn't allocate MCE records pool!\n");
 		return;
@@ -2292,12 +2292,11 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	mca_cfg.initialized = 1;
 
-	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
-	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_check_banks();
+	__mcheck_cpu_init_prepare_banks();
 	__mcheck_cpu_setup_timer();
+	cr4_set_bits(X86_CR4_MCE);
 }
 
 /*
@@ -2421,7 +2420,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), 0);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), 0);
 	}
 	return;
 }
@@ -2444,13 +2443,13 @@ static void vendor_disable_error_reporting(void)
 	mce_disable_error_reporting();
 }
 
-static int mce_syscore_suspend(void)
+static int mce_syscore_suspend(void *data)
 {
 	vendor_disable_error_reporting();
 	return 0;
 }
 
-static void mce_syscore_shutdown(void)
+static void mce_syscore_shutdown(void *data)
 {
 	vendor_disable_error_reporting();
 }
@@ -2460,19 +2459,24 @@ static void mce_syscore_shutdown(void)
  * Only one CPU is active at this time, the others get re-added later using
  * CPU hotplug:
  */
-static void mce_syscore_resume(void)
+static void mce_syscore_resume(void *data)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
-	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_init_prepare_banks();
+	cr4_set_bits(X86_CR4_MCE);
 }
 
-static struct syscore_ops mce_syscore_ops = {
+static const struct syscore_ops mce_syscore_ops = {
 	.suspend	= mce_syscore_suspend,
 	.shutdown	= mce_syscore_shutdown,
 	.resume		= mce_syscore_resume,
 };
 
+static struct syscore mce_syscore = {
+	.ops = &mce_syscore_ops,
+};
+
 /*
  * mce_device: Sysfs support
  */
@@ -2482,8 +2486,9 @@ 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_prepare_banks();
 	__mcheck_cpu_init_timer();
+	cr4_set_bits(X86_CR4_MCE);
 }
 
 /* Reinit MCEs after user configuration changes */
@@ -2771,7 +2776,7 @@ static void mce_reenable_cpu(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
 	}
 }
 
@@ -2786,15 +2791,9 @@ static int mce_cpu_dead(unsigned int cpu)
 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_threshold_create_device(cpu);
 	mce_reenable_cpu();
 	mce_start_timer(t);
 	return 0;
@@ -2805,7 +2804,7 @@ 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);
+	timer_delete_sync(t);
 	mce_threshold_remove_device(cpu);
 	mce_device_remove(cpu);
 	return 0;
@@ -2878,7 +2877,7 @@ static __init int mcheck_init_device(void)
 	if (err < 0)
 		goto err_out_online;
 
-	register_syscore_ops(&mce_syscore_ops);
+	register_syscore(&mce_syscore);
 
 	return 0;