Merge branch 'linus' into irq/core to pick up dependencies.

38 files changed, 489 insertions, 199 deletions

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6db28f17ff28..c88e0b127810 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -235,7 +235,7 @@ int amd_cache_northbridges(void)
 	if (boot_cpu_data.x86 == 0x10 &&
 	    boot_cpu_data.x86_model >= 0x8 &&
 	    (boot_cpu_data.x86_model > 0x9 ||
-	     boot_cpu_data.x86_mask >= 0x1))
+	     boot_cpu_data.x86_stepping >= 0x1))
 		amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
 
 	if (boot_cpu_data.x86 == 0x15)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 25ddf02598d2..b203af0855b5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
 static u32 hsx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x3a; /* EP */
 	case 0x04: return 0x0f; /* EX */
 	}
@@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void)
 
 static u32 bdx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x00000011;
 	case 0x03: return 0x0700000e;
 	case 0x04: return 0x0f00000c;
@@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void)
 
 static u32 skx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x03: return 0x01000136;
 	case 0x04: return 0x02000014;
 	}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ad2e410974f..7c5538769f7e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void)
 	do {
 		rep_nop();
 		now = rdtsc();
-	} while ((now - start) < 40000000000UL / HZ &&
+	} while ((now - start) < 40000000000ULL / HZ &&
 		time_before_eq(jiffies, end));
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 3cc471beb50b..bb6f7a2148d7 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -134,21 +134,40 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec,
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	struct irq_desc *desc = irq_data_to_desc(irqd);
+	bool managed = irqd_affinity_is_managed(irqd);
 
 	lockdep_assert_held(&vector_lock);
 
 	trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector,
 			    apicd->cpu);
 
-	/* Setup the vector move, if required  */
-	if (apicd->vector && cpu_online(apicd->cpu)) {
+	/*
+	 * If there is no vector associated or if the associated vector is
+	 * the shutdown vector, which is associated to make PCI/MSI
+	 * shutdown mode work, then there is nothing to release. Clear out
+	 * prev_vector for this and the offlined target case.
+	 */
+	apicd->prev_vector = 0;
+	if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR)
+		goto setnew;
+	/*
+	 * If the target CPU of the previous vector is online, then mark
+	 * the vector as move in progress and store it for cleanup when the
+	 * first interrupt on the new vector arrives. If the target CPU is
+	 * offline then the regular release mechanism via the cleanup
+	 * vector is not possible and the vector can be immediately freed
+	 * in the underlying matrix allocator.
+	 */
+	if (cpu_online(apicd->cpu)) {
 		apicd->move_in_progress = true;
 		apicd->prev_vector = apicd->vector;
 		apicd->prev_cpu = apicd->cpu;
 	} else {
-		apicd->prev_vector = 0;
+		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
+				managed);
 	}
 
+setnew:
 	apicd->vector = newvec;
 	apicd->cpu = newcpu;
 	BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec]));
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 46b675aaf20b..f11910b44638 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 
 	uv_gre_table = gre;
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		unsigned long size = ((unsigned long)(gre->limit - lgre)
+					<< UV_GAM_RANGE_SHFT);
+		int order = 0;
+		char suffix[] = " KMGTPE";
+
+		while (size > 9999 && order < sizeof(suffix)) {
+			size /= 1024;
+			order++;
+		}
+
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
 			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
 		}
-		pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
+		pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
-			((unsigned long)(gre->limit - lgre)) >>
-				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
+			size, suffix[order],
 			gre->type, gre->nasid, gre->sockid, gre->pnode);
 
 		lgre = gre->limit;
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index fa1261eefa16..f91ba53e06c8 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -18,7 +18,7 @@ void foo(void)
 	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
 	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
 	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
-	OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask);
+	OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
 	OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
 	OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
 	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5bddbdcbc4a3..f0e6456ca7d3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	if (c->x86_model == 6 && c->x86_mask == 1) {
+	if (c->x86_model == 6 && c->x86_stepping == 1) {
 		const int K6_BUG_LOOP = 1000000;
 		int n;
 		void (*f_vide)(void);
@@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 
 	/* K6 with old style WHCR */
 	if (c->x86_model < 8 ||
-	   (c->x86_model == 8 && c->x86_mask < 8)) {
+	   (c->x86_model == 8 && c->x86_stepping < 8)) {
 		/* We can only write allocate on the low 508Mb */
 		if (mbytes > 508)
 			mbytes = 508;
@@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	if ((c->x86_model == 8 && c->x86_mask > 7) ||
+	if ((c->x86_model == 8 && c->x86_stepping > 7) ||
 	     c->x86_model == 9 || c->x86_model == 13) {
 		/* The more serious chips .. */
 
@@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
 	 * As per AMD technical note 27212 0.2
 	 */
-	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+	if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) {
 		rdmsr(MSR_K7_CLK_CTL, l, h);
 		if ((l & 0xfff00000) != 0x20000000) {
 			pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
@@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	 * but they are not certified as MP capable.
 	 */
 	/* Athlon 660/661 is valid. */
-	if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
-	    (c->x86_mask == 1)))
+	if ((c->x86_model == 6) && ((c->x86_stepping == 0) ||
+	    (c->x86_stepping == 1)))
 		return;
 
 	/* Duron 670 is valid */
-	if ((c->x86_model == 7) && (c->x86_mask == 0))
+	if ((c->x86_model == 7) && (c->x86_stepping == 0))
 		return;
 
 	/*
@@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	 * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for
 	 * more.
 	 */
-	if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
-	    ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
+	if (((c->x86_model == 6) && (c->x86_stepping >= 2)) ||
+	    ((c->x86_model == 7) && (c->x86_stepping >= 1)) ||
 	     (c->x86_model > 7))
 		if (cpu_has(c, X86_FEATURE_MP))
 			return;
@@ -628,7 +628,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	/*  Set MTRR capability flag if appropriate */
 	if (c->x86 == 5)
 		if (c->x86_model == 13 || c->x86_model == 9 ||
-		    (c->x86_model == 8 && c->x86_mask >= 8))
+		    (c->x86_model == 8 && c->x86_stepping >= 8))
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
@@ -795,7 +795,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
 	 * all up to and including B1.
 	 */
-	if (c->x86_model <= 1 && c->x86_mask <= 1)
+	if (c->x86_model <= 1 && c->x86_stepping <= 1)
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
@@ -906,11 +906,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	/* AMD errata T13 (order #21922) */
 	if ((c->x86 == 6)) {
 		/* Duron Rev A0 */
-		if (c->x86_model == 3 && c->x86_mask == 0)
+		if (c->x86_model == 3 && c->x86_stepping == 0)
 			size = 64;
 		/* Tbird rev A1/A2 */
 		if (c->x86_model == 4 &&
-			(c->x86_mask == 0 || c->x86_mask == 1))
+			(c->x86_stepping == 0 || c->x86_stepping == 1))
 			size = 256;
 	}
 	return size;
@@ -1047,7 +1047,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 	}
 
 	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 4) | cpu->x86_mask;
+	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
 	while ((range = *erratum++))
 		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
 		    (ms >= AMD_MODEL_RANGE_START(range)) &&
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 71949bf2de5a..bfca937bdcc3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;
 	else {
-		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
-					  sizeof(arg));
+		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
 		if (ret < 0)
 			return SPECTRE_V2_CMD_AUTO;
 
@@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		}
 
 		if (i >= ARRAY_SIZE(mitigation_options)) {
-			pr_err("unknown option (%s). Switching to AUTO select\n",
-			       mitigation_options[i].option);
+			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
 			return SPECTRE_V2_CMD_AUTO;
 		}
 	}
@@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
 	    !IS_ENABLED(CONFIG_RETPOLINE)) {
-		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
-		       mitigation_options[i].option);
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
@@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void)
 			goto retpoline_auto;
 		break;
 	}
-	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!");
 	return;
 
 retpoline_auto:
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
-			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
 			goto retpoline_generic;
 		}
 		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
@@ -281,7 +278,7 @@ retpoline_auto:
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP or KPTI are available, there is a risk of
+	 * If neither SMEP nor PTI are available, there is a risk of
 	 * hitting userspace addresses in the RSB after a context switch
 	 * from a shallow call stack to a deeper one. To prevent this fill
 	 * the entire RSB, even when using IBRS.
@@ -295,21 +292,29 @@ retpoline_auto:
 	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
 	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
 		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Filling RSB on context switch\n");
+		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
+	}
+
+	/*
+	 * Retpoline means the kernel is safe because it has no indirect
+	 * branches. But firmware isn't, so use IBRS to protect that.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
 }
 
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
 		return sprintf(buf, "Not affected\n");
@@ -318,28 +323,21 @@ ssize_t cpu_show_meltdown(struct device *dev,
 	return sprintf(buf, "Vulnerable\n");
 }
 
-ssize_t cpu_show_spectre_v1(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
 	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
-ssize_t cpu_show_spectre_v2(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       spectre_v2_module_string());
 }
 #endif
-
-void __ibp_barrier(void)
-{
-	__wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
-}
-EXPORT_SYMBOL_GPL(__ibp_barrier);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index c578cd29c2d2..e5ec0f11c0de 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -140,7 +140,7 @@ static void init_centaur(struct cpuinfo_x86 *c)
 			clear_cpu_cap(c, X86_FEATURE_TSC);
 			break;
 		case 8:
-			switch (c->x86_mask) {
+			switch (c->x86_stepping) {
 			default:
 			name = "2";
 				break;
@@ -215,7 +215,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 *  - Note, it seems this may only be in engineering samples.
 	 */
 	if ((c->x86 == 6) && (c->x86_model == 9) &&
-				(c->x86_mask == 1) && (size == 65))
+				(c->x86_stepping == 1) && (size == 65))
 		size -= 1;
 	return size;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d63f4b5706e4..348cf4821240 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c)
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
 		c->x86		= x86_family(tfms);
 		c->x86_model	= x86_model(tfms);
-		c->x86_mask	= x86_stepping(tfms);
+		c->x86_stepping	= x86_stepping(tfms);
 
 		if (cap0 & (1<<19)) {
 			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
@@ -1184,9 +1184,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	int i;
 
 	c->loops_per_jiffy = loops_per_jiffy;
-	c->x86_cache_size = -1;
+	c->x86_cache_size = 0;
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
-	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
+	c->x86_model = c->x86_stepping = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
@@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 
 	pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
 
-	if (c->x86_mask || c->cpuid_level >= 0)
-		pr_cont(", stepping: 0x%x)\n", c->x86_mask);
+	if (c->x86_stepping || c->cpuid_level >= 0)
+		pr_cont(", stepping: 0x%x)\n", c->x86_stepping);
 	else
 		pr_cont(")\n");
 }
@@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void)
 	return 0;
 }
 core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+	struct cpuinfo_x86 info;
+
+	perf_check_microcode();
+
+	/* Reload CPUID max function as it might've changed. */
+	info.cpuid_level = cpuid_eax(0);
+
+	/*
+	 * Copy all capability leafs to pick up the synthetic ones so that
+	 * memcmp() below doesn't fail on that. The ones coming from CPUID will
+	 * get overwritten in get_cpu_cap().
+	 */
+	memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+	get_cpu_cap(&info);
+
+	if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+		return;
+
+	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 6b4bb335641f..8949b7ae6d92 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 
 	/* common case step number/rev -- exceptions handled below */
 	c->x86_model = (dir1 >> 4) + 1;
-	c->x86_mask = dir1 & 0xf;
+	c->x86_stepping = dir1 & 0xf;
 
 	/* Now cook; the original recipe is by Channing Corn, from Cyrix.
 	 * We do the same thing for each generation: we work out
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 319bf989fad1..4aa9fd379390 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -116,14 +116,13 @@ struct sku_microcode {
 	u32 microcode;
 };
 static const struct sku_microcode spectre_bad_microcodes[] = {
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
 	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
@@ -136,8 +135,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
 	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
 	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
-	/* Updated in the 20180108 release; blacklist until we know otherwise */
-	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
 	/* Observed in the wild */
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },
@@ -147,9 +144,16 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 {
 	int i;
 
+	/*
+	 * We know that the hypervisor lie to us on the microcode version so
+	 * we may as well hope that it is running the correct version.
+	 */
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
-		    c->x86_mask == spectre_bad_microcodes[i].stepping)
+		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
 			return (c->microcode <= spectre_bad_microcodes[i].microcode);
 	}
 	return false;
@@ -196,7 +200,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 * need the microcode to have already been loaded... so if it is
 	 * not, recommend a BIOS update and disable large pages.
 	 */
-	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
+	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 &&
 	    c->microcode < 0x20e) {
 		pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n");
 		clear_cpu_cap(c, X86_FEATURE_PSE);
@@ -212,7 +216,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 
 	/* CPUID workaround for 0F33/0F34 CPU */
 	if (c->x86 == 0xF && c->x86_model == 0x3
-	    && (c->x86_mask == 0x3 || c->x86_mask == 0x4))
+	    && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
 		c->x86_phys_bits = 36;
 
 	/*
@@ -310,7 +314,7 @@ int ppro_with_ram_bug(void)
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
 	    boot_cpu_data.x86 == 6 &&
 	    boot_cpu_data.x86_model == 1 &&
-	    boot_cpu_data.x86_mask < 8) {
+	    boot_cpu_data.x86_stepping < 8) {
 		pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n");
 		return 1;
 	}
@@ -327,7 +331,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
 	 * Mask B, Pentium, but not Pentium MMX
 	 */
 	if (c->x86 == 5 &&
-	    c->x86_mask >= 1 && c->x86_mask <= 4 &&
+	    c->x86_stepping >= 1 && c->x86_stepping <= 4 &&
 	    c->x86_model <= 3) {
 		/*
 		 * Remember we have B step Pentia with bugs
@@ -370,7 +374,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
 	 * model 3 mask 3
 	 */
-	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
+	if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633)
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
@@ -388,7 +392,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * P4 Xeon erratum 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
-	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
+	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) {
 		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
 				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) {
 			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
@@ -403,7 +407,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * Specification Update").
 	 */
 	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
-	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
+	    (c->x86_stepping < 0x6 || c->x86_stepping == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
 
@@ -650,7 +654,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 		case 6:
 			if (l2 == 128)
 				p = "Celeron (Mendocino)";
-			else if (c->x86_mask == 0 || c->x86_mask == 5)
+			else if (c->x86_stepping == 0 || c->x86_stepping == 5)
 				p = "Celeron-A";
 			break;
 
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 410629f10ad3..589b948e6e01 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -819,7 +819,7 @@ static __init void rdt_quirks(void)
 			cache_alloc_hsw_probe();
 		break;
 	case INTEL_FAM6_SKYLAKE_X:
-		if (boot_cpu_data.x86_mask <= 4)
+		if (boot_cpu_data.x86_stepping <= 4)
 			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
 	}
 }
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index bdab7d2f51af..fca759d272a1 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1804,6 +1804,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		goto out_common_fail;
 	}
 	closid = ret;
+	ret = 0;
 
 	rdtgrp->closid = closid;
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index aa0d5df9dc60..e956eb267061 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb)	{ }
 
 extern struct mca_config mca_cfg;
 
+#ifndef CONFIG_X86_64
+/*
+ * On 32-bit systems it would be difficult to safely unmap a poison page
+ * from the kernel 1:1 map because there are no non-canonical addresses that
+ * we can use to refer to the address without risking a speculative access.
+ * However, this isn't much of an issue because:
+ * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which
+ *    are only mapped into the kernel as needed
+ * 2) Few people would run a 32-bit kernel on a machine that supports
+ *    recoverable errors because they have too much memory to boot 32-bit.
+ */
+static inline void mce_unmap_kpfn(unsigned long pfn) {}
+#define mce_unmap_kpfn mce_unmap_kpfn
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3a8e88a611eb..466f47301334 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -56,6 +56,9 @@
 
 static DEFINE_MUTEX(mce_log_mutex);
 
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -105,6 +108,10 @@ 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.
@@ -126,6 +133,8 @@ void mce_setup(struct mce *m)
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
 		rdmsrl(MSR_PPIN, m->ppin);
+
+	m->microcode = boot_cpu_data.microcode;
 }
 
 DEFINE_PER_CPU(struct mce, injectm);
@@ -234,7 +243,7 @@ static void __print_mce(struct mce *m)
 			m->cs, m->ip);
 
 		if (m->cs == __KERNEL_CS)
-			pr_cont("{%pS}", (void *)m->ip);
+			pr_cont("{%pS}", (void *)(unsigned long)m->ip);
 		pr_cont("\n");
 	}
 
@@ -258,7 +267,7 @@ static void __print_mce(struct mce *m)
 	 */
 	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);
+		m->microcode);
 }
 
 static void print_mce(struct mce *m)
@@ -590,7 +599,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
-		memory_failure(pfn, 0);
+		if (!memory_failure(pfn, 0))
+			mce_unmap_kpfn(pfn);
 	}
 
 	return NOTIFY_OK;
@@ -1057,12 +1067,13 @@ static int do_memory_failure(struct mce *m)
 	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;
 }
 
-#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE)
-
-void arch_unmap_kpfn(unsigned long pfn)
+#ifndef mce_unmap_kpfn
+static void mce_unmap_kpfn(unsigned long pfn)
 {
 	unsigned long decoy_addr;
 
@@ -1073,7 +1084,7 @@ void arch_unmap_kpfn(unsigned long pfn)
 	 * 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 posion page because we'd have
+	 * 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
@@ -1098,7 +1109,6 @@ void arch_unmap_kpfn(unsigned long pfn)
 
 	if (set_memory_np(decoy_addr, 1))
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-
 }
 #endif
 
@@ -2081,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
@@ -2093,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s,
 			on_each_cpu(mce_enable_ce, (void *)1, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2105,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
@@ -2116,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s,
 			on_each_cpu(mce_enable_ce, NULL, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2123,8 +2139,19 @@ 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);
+	unsigned long old_check_interval = check_interval;
+	ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+	if (check_interval == old_check_interval)
+		return ret;
+
+	if (check_interval < 1)
+		check_interval = 1;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b8462d426..a998e1a7d46f 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	return patch_size;
 }
 
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu)
 
 	p = find_patch(cpu);
 	if (!p)
-		return 0;
+		return UCODE_NFOUND;
 
 	mc_amd  = p->data;
 	uci->mc = p->data;
@@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu)
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
 		uci->cpu_sig.rev = rev;
-		return 0;
+		return UCODE_OK;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-		return -1;
+		return UCODE_ERROR;
 	}
 	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
 		mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu)
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 319dd65f98a2..70ecbc8099c9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
 #define pr_fmt(fmt) "microcode: " fmt
 
 #include <linux/platform_device.h>
+#include <linux/stop_machine.h>
 #include <linux/syscore_ops.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
 	return ret;
 }
 
-struct apply_microcode_ctx {
-	int err;
-};
-
 static void apply_microcode_local(void *arg)
 {
-	struct apply_microcode_ctx *ctx = arg;
+	enum ucode_state *err = arg;
 
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+	*err = microcode_ops->apply_microcode(smp_processor_id());
 }
 
 static int apply_microcode_on_target(int cpu)
 {
-	struct apply_microcode_ctx ctx = { .err = 0 };
+	enum ucode_state err;
 	int ret;
 
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
+	ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+	if (!ret) {
+		if (err == UCODE_ERROR)
+			ret = 1;
+	}
 	return ret;
 }
 
@@ -489,31 +494,110 @@ static void __exit microcode_dev_exit(void)
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static int reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ *   is loading microcode in order to avoid any negative interactions caused by
+ *   the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ *   requirement can be relaxed in the future. Right now, this is conservative
+ *   and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
-	int err = 0;
+	if (num_online_cpus() == num_present_cpus())
+		return 0;
 
-	if (!uci->valid)
-		return err;
+	pr_err("Not all CPUs online, aborting microcode update.\n");
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
+	return -EINVAL;
+}
+
+static atomic_t late_cpus;
+
+/*
+ * Returns:
+ * < 0 - on error
+ *   0 - no update done
+ *   1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+	unsigned int timeout = NSEC_PER_SEC;
+	int all_cpus = num_online_cpus();
+	int cpu = smp_processor_id();
+	enum ucode_state err;
+	int ret = 0;
+
+	atomic_dec(&late_cpus);
+
+	/*
+	 * Wait for all CPUs to arrive. A load will not be attempted unless all
+	 * CPUs show up.
+	 * */
+	while (atomic_read(&late_cpus)) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				atomic_read(&late_cpus));
+			return -1;
+		}
+
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+
+	spin_lock(&update_lock);
+	apply_microcode_local(&err);
+	spin_unlock(&update_lock);
+
+	if (err > UCODE_NFOUND) {
+		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+		ret = -1;
+	} else if (err == UCODE_UPDATED) {
+		ret = 1;
+	}
+
+	atomic_inc(&late_cpus);
+
+	while (atomic_read(&late_cpus) != all_cpus)
+		cpu_relax();
+
+	return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+	int ret;
+
+	atomic_set(&late_cpus, num_online_cpus());
+
+	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+	if (ret < 0)
+		return ret;
+	else if (ret > 0)
+		microcode_check();
+
+	return ret;
 }
 
 static ssize_t reload_store(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t size)
 {
+	enum ucode_state tmp_ret = UCODE_OK;
+	int bsp = boot_cpu_data.cpu_index;
 	unsigned long val;
-	int cpu;
-	ssize_t ret = 0, tmp_ret;
+	ssize_t ret = 0;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -522,23 +606,24 @@ static ssize_t reload_store(struct device *dev,
 	if (val != 1)
 		return size;
 
+	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+	if (tmp_ret != UCODE_OK)
+		return size;
+
 	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
 
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
-	}
-	if (!ret)
-		perf_check_microcode();
+	ret = check_online_cpus();
+	if (ret)
+		goto put;
+
+	mutex_lock(&microcode_mutex);
+	ret = microcode_reload_late();
 	mutex_unlock(&microcode_mutex);
+
+put:
 	put_online_cpus();
 
-	if (!ret)
+	if (ret >= 0)
 		ret = size;
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index f7c55b0e753a..2aded9db1d42 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (!mc)
 		return 0;
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	return 0;
 }
 
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
 {
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
-	struct ucode_cpu_info *uci;
-	struct cpuinfo_x86 *c;
 	static int prev_rev;
 	u32 rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
-		return -1;
+		return UCODE_ERROR;
 
-	uci = ucode_cpu_info + cpu;
-	mc = uci->mc;
+	/* Look for a newer patch in our cache: */
+	mc = find_patch(uci);
 	if (!mc) {
-		/* Look for a newer patch in our cache: */
-		mc = find_patch(uci);
+		mc = uci->mc;
 		if (!mc)
-			return 0;
+			return UCODE_NFOUND;
 	}
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		c->microcode = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu)
 	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
-		return -1;
+		return UCODE_ERROR;
 	}
 
 	if (rev != prev_rev) {
@@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	c = &cpu_data(cpu);
-
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
@@ -921,7 +953,7 @@ static bool is_blacklisted(unsigned int cpu)
 	 */
 	if (c->x86 == 6 &&
 	    c->x86_model == INTEL_FAM6_BROADWELL_X &&
-	    c->x86_mask == 0x01 &&
+	    c->x86_stepping == 0x01 &&
 	    llc_size_per_core > 2621440 &&
 	    c->microcode < 0x0b000021) {
 		pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
@@ -944,7 +976,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 		return UCODE_NFOUND;
 
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
-		c->x86, c->x86_model, c->x86_mask);
+		c->x86, c->x86_model, c->x86_stepping);
 
 	if (request_firmware_direct(&firmware, name, device)) {
 		pr_debug("data file %s load failed\n", name);
@@ -982,7 +1014,7 @@ static struct microcode_ops microcode_intel_ops = {
 
 static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
 {
-	u64 llc_size = c->x86_cache_size * 1024;
+	u64 llc_size = c->x86_cache_size * 1024ULL;
 
 	do_div(llc_size, c->x86_max_cores);
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index fdc55215d44d..e12ee86906c6 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size,
 	 */
 	if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 &&
 	    boot_cpu_data.x86_model == 1 &&
-	    boot_cpu_data.x86_mask <= 7) {
+	    boot_cpu_data.x86_stepping <= 7) {
 		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
 			pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
 			return -EINVAL;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 40d5a8a75212..7468de429087 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -711,8 +711,8 @@ void __init mtrr_bp_init(void)
 			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
 			    boot_cpu_data.x86 == 0xF &&
 			    boot_cpu_data.x86_model == 0x3 &&
-			    (boot_cpu_data.x86_mask == 0x3 ||
-			     boot_cpu_data.x86_mask == 0x4))
+			    (boot_cpu_data.x86_stepping == 0x3 ||
+			     boot_cpu_data.x86_stepping == 0x4))
 				phys_addr = 36;
 
 			size_or_mask = SIZE_OR_MASK_BITS(phys_addr);
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7ecedafa1c8..2c8522a39ed5 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		   c->x86_model,
 		   c->x86_model_id[0] ? c->x86_model_id : "unknown");
 
-	if (c->x86_mask || c->cpuid_level >= 0)
-		seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+	if (c->x86_stepping || c->cpuid_level >= 0)
+		seq_printf(m, "stepping\t: %d\n", c->x86_stepping);
 	else
 		seq_puts(m, "stepping\t: unknown\n");
 	if (c->microcode)
@@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	}
 
 	/* Cache size */
-	if (c->x86_cache_size >= 0)
-		seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+	if (c->x86_cache_size)
+		seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size);
 
 	show_cpuinfo_core(m, c, cpu);
 	show_cpuinfo_misc(m, c);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c29020907886..b59e4fb40fd9 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -37,7 +37,7 @@
 #define X86		new_cpu_data+CPUINFO_x86
 #define X86_VENDOR	new_cpu_data+CPUINFO_x86_vendor
 #define X86_MODEL	new_cpu_data+CPUINFO_x86_model
-#define X86_MASK	new_cpu_data+CPUINFO_x86_mask
+#define X86_STEPPING	new_cpu_data+CPUINFO_x86_stepping
 #define X86_HARD_MATH	new_cpu_data+CPUINFO_hard_math
 #define X86_CPUID	new_cpu_data+CPUINFO_cpuid_level
 #define X86_CAPABILITY	new_cpu_data+CPUINFO_x86_capability
@@ -332,7 +332,7 @@ ENTRY(startup_32_smp)
 	shrb $4,%al
 	movb %al,X86_MODEL
 	andb $0x0f,%cl		# mask mask revision
-	movb %cl,X86_MASK
+	movb %cl,X86_STEPPING
 	movl %edx,X86_CAPABILITY
 
 .Lis486:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 04a625f0fcda..0f545b3cf926 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -23,6 +23,7 @@
 #include <asm/nops.h>
 #include "../entry/calling.h"
 #include <asm/export.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -134,6 +135,7 @@ ENTRY(secondary_startup_64)
 
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 1:
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 2f723301eb58..38deafebb21b 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
 /*
  * this changes the io permissions bitmap in the current task.
  */
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 {
 	struct thread_struct *t = &current->thread;
 	struct tss_struct *tss;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd36f3c33cd0..0715f827607c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);
 
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
+	bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+	is_in_entry_trampoline_section =
+		(addr >= (unsigned long)__entry_trampoline_start &&
+		 addr < (unsigned long)__entry_trampoline_end);
+#endif
 	return  (addr >= (unsigned long)__kprobes_text_start &&
 		 addr < (unsigned long)__kprobes_text_end) ||
 		(addr >= (unsigned long)__entry_text_start &&
-		 addr < (unsigned long)__entry_text_end);
+		 addr < (unsigned long)__entry_text_end) ||
+		is_in_entry_trampoline_section;
 }
 
 int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4e37d1a851a6..bc1a27280c4b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -49,7 +49,7 @@
 
 static int kvmapf = 1;
 
-static int parse_no_kvmapf(char *arg)
+static int __init parse_no_kvmapf(char *arg)
 {
         kvmapf = 0;
         return 0;
@@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg)
 early_param("no-kvmapf", parse_no_kvmapf);
 
 static int steal_acc = 1;
-static int parse_no_stealacc(char *arg)
+static int __init parse_no_stealacc(char *arg)
 {
         steal_acc = 0;
         return 0;
@@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 static int kvmclock_vsyscall = 1;
-static int parse_no_kvmclock_vsyscall(char *arg)
+static int __init parse_no_kvmclock_vsyscall(char *arg)
 {
         kvmclock_vsyscall = 0;
         return 0;
@@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void)
 #endif
 		pa |= KVM_ASYNC_PF_ENABLED;
 
-		/* Async page fault support for L1 hypervisor is optional */
-		if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
-			(pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
-			wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
+			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+
+		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
@@ -545,7 +545,8 @@ static void __init kvm_guest_init(void)
 		pv_time_ops.steal_clock = kvm_steal_clock;
 	}
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void)
 {
 	int cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
 				GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 1f790cf9d38f..3b7427aa7d85 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -542,6 +542,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			value -= (u64)address;
 			*(u32 *)location = value;
 			break;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index da0c160e5589..f58336af095c 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -191,6 +191,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 27d0a1712663..f1c5eb99d445 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -410,7 +410,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01;
 	processor.cpuflag = CPU_ENABLED;
 	processor.cpufeature = (boot_cpu_data.x86 << 8) |
-	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
+	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping;
 	processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX];
 	processor.reserved[0] = 0;
 	processor.reserved[1] = 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 041096bdef86..99dc79e76bdc 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -200,9 +200,9 @@ static void native_flush_tlb_global(void)
 	__native_flush_tlb_global();
 }
 
-static void native_flush_tlb_single(unsigned long addr)
+static void native_flush_tlb_one_user(unsigned long addr)
 {
-	__native_flush_tlb_single(addr);
+	__native_flush_tlb_one_user(addr);
 }
 
 struct static_key paravirt_steal_enabled;
@@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 
 	.flush_tlb_user = native_flush_tlb,
 	.flush_tlb_kernel = native_flush_tlb_global,
-	.flush_tlb_single = native_flush_tlb_single,
+	.flush_tlb_one_user = native_flush_tlb_one_user,
 	.flush_tlb_others = native_flush_tlb_others,
 
 	.pgd_alloc = __paravirt_pgd_alloc,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1ae67e982af7..4c616be28506 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-#ifdef CONFIG_X86_32
-	/* sync back kernel address range */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
 	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
+	 * Sync back kernel address range.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 
 	tboot_probe();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa766fab3..ea554f812ee1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void)
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
 
-#ifdef CONFIG_X86_32
 	/*
 	 * Sync back kernel address range again.  We already did this in
 	 * setup_arch(), but percpu data also needs to be available in
 	 * the smpboot asm.  We can't reliably pick up percpu mappings
 	 * using vmalloc_fault(), because exception dispatch needs
 	 * percpu data.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
-	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
-	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 }
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ac057f9b0763..0d930d8987cc 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
 #define CHECK_CSI_OFFSET(name)	  BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_code)  != 8);
+
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code)  != 8);
 	 /*
 	 * Ensure that the size of each si_field never changes.
 	 * If it does, it is a sign that the
@@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void)
 	CHECK_CSI_SIZE  (_kill, 2*sizeof(int));
 	CHECK_SI_SIZE   (_kill, 2*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+
 	CHECK_CSI_OFFSET(_timer);
 	CHECK_CSI_SIZE  (_timer, 3*sizeof(int));
 	CHECK_SI_SIZE   (_timer, 6*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_tid)     != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value)   != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid)     != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value)   != 0x14);
+
 	CHECK_CSI_OFFSET(_rt);
 	CHECK_CSI_SIZE  (_rt, 3*sizeof(int));
 	CHECK_SI_SIZE   (_rt, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)   != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)   != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigchld);
 	CHECK_CSI_SIZE  (_sigchld, 5*sizeof(int));
 	CHECK_SI_SIZE   (_sigchld, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)    != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)    != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_utime)  != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_stime)  != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)    != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)    != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime)  != 0x1C);
+
 #ifdef CONFIG_X86_X32_ABI
 	CHECK_CSI_OFFSET(_sigchld_x32);
 	CHECK_CSI_SIZE  (_sigchld_x32, 7*sizeof(int));
 	/* no _sigchld_x32 in the generic siginfo_t */
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime)  != 0x20);
 #endif
 
 	CHECK_CSI_OFFSET(_sigfault);
 	CHECK_CSI_SIZE  (_sigfault, 4*sizeof(int));
 	CHECK_SI_SIZE   (_sigfault, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
 	CHECK_SI_SIZE   (_sigpoll, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_fd)     != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd)   != 0x10);
+
 	CHECK_CSI_OFFSET(_sigsys);
 	CHECK_CSI_SIZE  (_sigsys, 3*sizeof(int));
 	CHECK_SI_SIZE   (_sigsys, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_syscall)   != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_arch)      != 0x1C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch)      != 0x14);
+
 	/* any new si_fields should be added here */
 }
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6f27facbaa9b..ff99e2b6fc54 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void)
 	cpu_set_state_online(me);
 }
 
-void __init native_smp_cpus_done(unsigned int max_cpus)
+void __init calculate_max_logical_packages(void)
 {
 	int ncpus;
 
-	pr_debug("Boot done\n");
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
@@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
+}
+
+void __init native_smp_cpus_done(unsigned int max_cpus)
+{
+	pr_debug("Boot done\n");
+
+	calculate_max_logical_packages();
 
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);
@@ -1430,8 +1436,8 @@ static void remove_siblinginfo(int cpu)
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
 	cpumask_clear(topology_core_cpumask(cpu));
-	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
+	c->booted_cores = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
 	recompute_smt_state();
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 446c9ef8cfc3..3d9b2308e7fa 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr)
 		break;
 
 	case BUG_TRAP_TYPE_WARN:
-		regs->ip += LEN_UD0;
+		regs->ip += LEN_UD2;
 		return 1;
 	}
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1f9188f5357c..feb28fee6cea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -5,7 +5,6 @@
 #include <asm/unwind.h>
 #include <asm/orc_types.h>
 #include <asm/orc_lookup.h>
-#include <asm/sections.h>
 
 #define orc_warn(fmt, ...) \
 	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
@@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip)
 	}
 
 	/* vmlinux .init slow lookup: */
-	if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+	if (init_kernel_text(ip))
 		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9b138a06c1a4..b854ebf5851b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_start) = .;
 		_entry_trampoline = .;
 		*(.entry_trampoline)
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_end) = .;
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif