x86/ras: RAS queue

index 53ab69704771..8bf766ef0e18 100644
@@ -110,6 +110,8 @@
 #define MSR_AMD64_SMCA_MC0_MISC0	0xc0002003
 #define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
 #define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
+#define MSR_AMD64_SMCA_MC0_DESTAT	0xc0002008
+#define MSR_AMD64_SMCA_MC0_DEADDR	0xc0002009
 #define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
 #define MSR_AMD64_SMCA_MCx_CTL(x)	(MSR_AMD64_SMCA_MC0_CTL + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_STATUS(x)	(MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x))

@@ -117,6 +119,8 @@
 #define MSR_AMD64_SMCA_MCx_MISC(x)	(MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_DESTAT(x)	(MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_DEADDR(x)	(MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
 
 /*

index c594680c36f2..d1b1e62f7cb9 100644
@@ -430,12 +430,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		deferred_error_interrupt_enable(c);
 }
 
-static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+static void
+__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 {
+	u32 msr_status = msr_ops.status(bank);
+	u32 msr_addr = msr_ops.addr(bank);
 	struct mce m;
 	u64 status;
 
-	rdmsrl(msr_ops.status(bank), status);
+	WARN_ON_ONCE(deferred_err && threshold_err);
+
+	if (deferred_err && mce_flags.smca) {
+		msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank);
+		msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank);
+	}
+
+	rdmsrl(msr_status, status);
+
 	if (!(status & MCI_STATUS_VAL))
 		return;
 

@@ -448,10 +459,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
 		m.misc = misc;
 
 	if (m.status & MCI_STATUS_ADDRV)
-		rdmsrl(msr_ops.addr(bank), m.addr);
+		rdmsrl(msr_addr, m.addr);
 
 	mce_log(&m);
-	wrmsrl(msr_ops.status(bank), 0);
+
+	wrmsrl(msr_status, 0);
 }
 
 static inline void __smp_deferred_error_interrupt(void)

@@ -479,17 +491,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
 /* APIC interrupt handler for deferred errors */
 static void amd_deferred_error_interrupt(void)
 {
-	u64 status;
 	unsigned int bank;
+	u32 msr_status;
+	u64 status;
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
-		rdmsrl(msr_ops.status(bank), status);
+		msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank)
+					      : msr_ops.status(bank);
+
+		rdmsrl(msr_status, status);
 
 		if (!(status & MCI_STATUS_VAL) ||
 		    !(status & MCI_STATUS_DEFERRED))
 			continue;
 
-		__log_error(bank, false, 0);
+		__log_error(bank, true, false, 0);
 		break;
 	}
 }

@@ -544,7 +560,7 @@ static void amd_threshold_interrupt(void)
 	return;
 
 log:
-	__log_error(bank, true, ((u64)high << 32) | low);
+	__log_error(bank, false, true, ((u64)high << 32) | low);
 }
 
 /*

index d1b1e62f7cb9..527ddae3017b 100644
@@ -54,14 +54,6 @@
 /* Threshold LVT offset is at MSR0xC0000410[15:12] */
 #define SMCA_THR_LVT_OFF	0xF000
 
-/*
- * OS is required to set the MCAX bit to acknowledge that it is now using the
- * new MSR ranges and new registers under each bank. It also means that the OS
- * will configure deferred errors in the new MCx_CONFIG register. If the bit is
- * not set, uncorrectable errors will cause a system panic.
- */
-#define SMCA_MCAX_EN_OFF	0x1
-
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",

@@ -374,7 +366,35 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 		u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
 
 		if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
-			smca_high |= SMCA_MCAX_EN_OFF;
+			/*
+			 * OS is required to set the MCAX bit to acknowledge
+			 * that it is now using the new MSR ranges and new
+			 * registers under each bank. It also means that the OS
+			 * will configure deferred errors in the new MCx_CONFIG
+			 * register. If the bit is not set, uncorrectable errors
+			 * will cause a system panic.
+			 *
+			 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of
+			 * the MSR.)
+			 */
+			smca_high |= BIT(0);
+
+			/*
+			 * SMCA logs Deferred Error information in
+			 * MCA_DE{STAT,ADDR} registers with the option of
+			 * additionally logging to MCA_{STATUS,ADDR} if
+			 * MCA_CONFIG[LogDeferredInMcaStat] is set.
+			 *
+			 * This bit is usually set by BIOS to retain the old
+			 * behavior for OSes that don't use the new registers.
+			 * Linux supports the new registers so let's disable
+			 * that additional logging here.
+			 *
+			 * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in
+			 * the high portion of the MSR).
+			 */
+			smca_high &= ~BIT(2);
+
 			wrmsr(smca_addr, smca_low, smca_high);
 		}
 

index 527ddae3017b..10b0661651e0 100644
@@ -343,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 			int offset, u32 misc_high)
 {
 	unsigned int cpu = smp_processor_id();
+	u32 smca_low, smca_high, smca_addr;
 	struct threshold_block b;
 	int new;
 

@@ -361,52 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 
 	b.interrupt_enable = 1;
 
-	if (mce_flags.smca) {
-		u32 smca_low, smca_high;
-		u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
-
-		if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
-			/*
-			 * OS is required to set the MCAX bit to acknowledge
-			 * that it is now using the new MSR ranges and new
-			 * registers under each bank. It also means that the OS
-			 * will configure deferred errors in the new MCx_CONFIG
-			 * register. If the bit is not set, uncorrectable errors
-			 * will cause a system panic.
-			 *
-			 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of
-			 * the MSR.)
-			 */
-			smca_high |= BIT(0);
+	if (!mce_flags.smca) {
+		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+		goto set_offset;
+	}
 
-			/*
-			 * SMCA logs Deferred Error information in
-			 * MCA_DE{STAT,ADDR} registers with the option of
-			 * additionally logging to MCA_{STATUS,ADDR} if
-			 * MCA_CONFIG[LogDeferredInMcaStat] is set.
-			 *
-			 * This bit is usually set by BIOS to retain the old
-			 * behavior for OSes that don't use the new registers.
-			 * Linux supports the new registers so let's disable
-			 * that additional logging here.
-			 *
-			 * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in
-			 * the high portion of the MSR).
-			 */
-			smca_high &= ~BIT(2);
+	smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
 
-			wrmsr(smca_addr, smca_low, smca_high);
-		}
+	if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
+		/*
+		 * OS is required to set the MCAX bit to acknowledge that it is
+		 * now using the new MSR ranges and new registers under each
+		 * bank. It also means that the OS will configure deferred
+		 * errors in the new MCx_CONFIG register. If the bit is not set,
+		 * uncorrectable errors will cause a system panic.
+		 *
+		 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.)
+		 */
+		smca_high |= BIT(0);
 
-		/* Gather LVT offset for thresholding: */
-		if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
-			goto out;
+		/*
+		 * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR}
+		 * registers with the option of additionally logging to
+		 * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set.
+		 *
+		 * This bit is usually set by BIOS to retain the old behavior
+		 * for OSes that don't use the new registers. Linux supports the
+		 * new registers so let's disable that additional logging here.
+		 *
+		 * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high
+		 * portion of the MSR).
+		 */
+		smca_high &= ~BIT(2);
 
-		new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
-	} else {
-		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+		wrmsr(smca_addr, smca_low, smca_high);
 	}
 
+	/* Gather LVT offset for thresholding: */
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
+		goto out;
+
+	new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
+
+set_offset:
 	offset = setup_APIC_mce_threshold(offset, new);
 
 	if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))

index 3636ec06c887..53ac9bbf2064 100644
@@ -27,6 +27,7 @@ enum cpuid_leafs
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
+	CPUID_8000_0007_EBX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES

index 8f9afefd2dc5..d4e5018e9a44 100644
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	17	/* N 32-bit words worth of info */
+#define NCAPINTS	18	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*

@@ -280,6 +280,11 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 
+/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+
 /*
  * BUG word(s)
  */

index 8394b3d1f94f..dbc6f066e231 100644
@@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		}
 	}
 
+	if (c->extended_cpuid_level >= 0x80000007) {
+		cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[CPUID_8000_0007_EBX] = ebx;
+		c->x86_power = edx;
+	}
+
 	if (c->extended_cpuid_level >= 0x80000008) {
 		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 

@@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_phys_bits = 36;
 #endif
 
-	if (c->extended_cpuid_level >= 0x80000007)
-		c->x86_power = cpuid_edx(0x80000007);
-
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 

index aeda44684758..92e5e37d97bf 100644
@@ -1683,11 +1683,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		break;
 
 	case X86_VENDOR_AMD: {
-		u32 ebx = cpuid_ebx(0x80000007);
-
-		mce_flags.overflow_recov = !!(ebx & BIT(0));
-		mce_flags.succor	 = !!(ebx & BIT(1));
-		mce_flags.smca		 = !!(ebx & BIT(3));
+		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);
 
 		/*
 		 * Install proper ops for Scalable MCA enabled processors

index 49768c08ac07..9b6800a79c7f 100644
@@ -1052,7 +1052,6 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	struct mce *m = (struct mce *)data;
 	struct cpuinfo_x86 *c = &cpu_data(m->extcpu);
 	int ecc;
-	u32 ebx = cpuid_ebx(0x80000007);
 
 	if (amd_filter_mce(m))
 		return NOTIFY_STOP;

@@ -1075,7 +1074,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 			((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"),
 			((m->status & MCI_STATUS_POISON)   ? "Poison"   : "-"));
 
-	if (!!(ebx & BIT(3))) {
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
 		u32 low, high;
 		u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
 

@@ -1094,7 +1093,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	if (m->status & MCI_STATUS_ADDRV)
 		pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr);
 
-	if (!!(ebx & BIT(3))) {
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
 		decode_smca_errors(m);
 		goto err_code;
 	}

@@ -1149,7 +1148,6 @@ static struct notifier_block amd_mce_dec_nb = {
 static int __init mce_amd_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
-	u32 ebx;
 
 	if (c->x86_vendor != X86_VENDOR_AMD)
 		return -ENODEV;

@@ -1205,9 +1203,8 @@ static int __init mce_amd_init(void)
 		break;
 
 	case 0x17:
-		ebx = cpuid_ebx(0x80000007);
 		xec_mask = 0x3f;
-		if (!(ebx & BIT(3))) {
+		if (!boot_cpu_has(X86_FEATURE_SMCA)) {
 			printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n");
 			goto err_out;
 		}

index 9e02dcaef683..e69f4701a076 100644
@@ -290,14 +290,33 @@ static void do_inject(void)
 	wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS,
 		     (u32)mcg_status, (u32)(mcg_status >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b),
-		     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
+		if (inj_type == DFR_INT_INJ) {
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b),
+				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b),
+				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		} else {
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b),
+				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
+
+			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b),
+				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		}
+
+		wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b),
+			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+	} else {
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b),
+			     (u32)i_mce.status, (u32)(i_mce.status >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b),
-		     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b),
+			     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b),
-		     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+		wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b),
+			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
+	}
 
 	toggle_hw_mce_inject(cpu, false);