1 files changed, 132 insertions, 183 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4da4eab56c81..460e90a1a0b1 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -423,7 +423,7 @@ noinstr u64 mce_rdmsrq(u32 msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static noinstr void mce_wrmsrq(u32 msr, u64 v)
+noinstr void mce_wrmsrq(u32 msr, u64 v)
 {
 	u32 low, high;
 
@@ -715,6 +715,60 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
+ * 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 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.
  *
@@ -765,51 +819,10 @@ 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);
 		/*
@@ -826,10 +839,7 @@ log_it:
 			mce_log(&err);
 
 clear_it:
-		/*
-		 * Clear state for this bank.
-		 */
-		mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
+		clear_bank(m);
 	}
 
 	/*
@@ -1810,9 +1820,10 @@ 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;
@@ -1840,69 +1851,34 @@ 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);
-
 	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;
-		wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrq(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];
@@ -1910,25 +1886,16 @@ static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
+		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;
 	}
 }
 
-static void apply_quirks_amd(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);
-
-	/* This should be disabled by the BIOS, but isn't always */
-	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 && mca_cfg.bootlog < 0) {
 		/*
 		 * Lots of broken BIOS around that don't clear them
@@ -1938,13 +1905,6 @@ static void apply_quirks_amd(struct cpuinfo_x86 *c)
 	}
 
 	/*
-	 * Various K7s with broken bank 0 around. Always disable
-	 * by default.
-	 */
-	if (c->x86 == 6 && this_cpu_read(mce_num_banks))
-		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.
 	 */
@@ -1955,26 +1915,13 @@ static void apply_quirks_amd(struct cpuinfo_x86 *c)
 		mce_flags.zen_ifu_quirk = 1;
 }
 
-static void apply_quirks_intel(struct cpuinfo_x86 *c)
+static void intel_apply_global_quirks(struct cpuinfo_x86 *c)
 {
-	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-
 	/* Older CPUs (prior to family 6) don't need quirks. */
 	if (c->x86_vfm < INTEL_PENTIUM_PRO)
 		return;
 
 	/*
-	 * 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_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks))
-		mce_banks[0].init = false;
-
-	/*
 	 * All newer Intel systems support MCE broadcasting. Enable
 	 * synchronization with a one second timeout.
 	 */
@@ -1999,7 +1946,7 @@ static void apply_quirks_intel(struct cpuinfo_x86 *c)
 		mce_flags.skx_repmov_quirk = 1;
 }
 
-static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
+static void zhaoxin_apply_global_quirks(struct cpuinfo_x86 *c)
 {
 	/*
 	 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
@@ -2011,34 +1958,6 @@ static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
 	}
 }
 
-/* Add per CPU specific workarounds here */
-static bool __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
-{
-	struct mca_config *cfg = &mca_cfg;
-
-	switch (c->x86_vendor) {
-	case X86_VENDOR_UNKNOWN:
-		pr_info("unknown CPU type - not enabling MCE support\n");
-		return false;
-	case X86_VENDOR_AMD:
-		apply_quirks_amd(c);
-		break;
-	case X86_VENDOR_INTEL:
-		apply_quirks_intel(c);
-		break;
-	case X86_VENDOR_ZHAOXIN:
-		apply_quirks_zhaoxin(c);
-		break;
-	}
-
-	if (cfg->monarch_timeout < 0)
-		cfg->monarch_timeout = 0;
-	if (cfg->bootlog != 0)
-		cfg->panic_timeout = 30;
-
-	return true;
-}
-
 static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 {
 	if (c->x86 != 5)
@@ -2060,19 +1979,6 @@ static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 	return false;
 }
 
-/*
- * 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;
-	}
-}
-
 static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
 {
 	struct mca_config *cfg = &mca_cfg;
@@ -2281,6 +2187,53 @@ 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:
@@ -2298,11 +2251,6 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	__mcheck_cpu_cap_init();
 
-	if (!__mcheck_cpu_apply_quirks(c)) {
-		mca_cfg.disabled = 1;
-		return;
-	}
-
 	if (!mce_gen_pool_init()) {
 		mca_cfg.disabled = 1;
 		pr_emerg("Couldn't allocate MCE records pool!\n");
@@ -2311,12 +2259,11 @@ 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);
 }
 
 /*
@@ -2483,7 +2430,8 @@ static void mce_syscore_resume(void)
 {
 	__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 = {
@@ -2501,8 +2449,9 @@ 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 */