20 files changed, 216 insertions, 231 deletions

diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 6ef688a1ef3e..7ff1b0c86a8e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1085,9 +1085,9 @@ static void aesni_free_simds(void)
 		    aesni_simd_skciphers[i]; i++)
 		simd_skcipher_free(aesni_simd_skciphers[i]);
 
-	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) &&
-		    aesni_simd_skciphers2[i].simd; i++)
-		simd_skcipher_free(aesni_simd_skciphers2[i].simd);
+	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++)
+		if (aesni_simd_skciphers2[i].simd)
+			simd_skcipher_free(aesni_simd_skciphers2[i].simd);
 }
 
 static int __init aesni_init(void)
@@ -1168,7 +1168,7 @@ static int __init aesni_init(void)
 		simd = simd_skcipher_create_compat(algname, drvname, basename);
 		err = PTR_ERR(simd);
 		if (IS_ERR(simd))
-			goto unregister_simds;
+			continue;
 
 		aesni_simd_skciphers2[i].simd = simd;
 	}
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 17c3564d087a..22ef4f72cf32 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;
@@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
+	if (!pmu) {
+		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+		if (!pmu)
+			return -ENOMEM;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
+
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
@@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
-	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-	if (!pmu)
-		return -ENOMEM;
-
-	raw_spin_lock_init(&pmu->lock);
-	INIT_LIST_HEAD(&pmu->active_list);
-	pmu->pmu = &rapl_pmus->pmu;
-	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
-	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void)
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -836,7 +829,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 8c4ccdc3a3f3..1ab45976474d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
 
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
-	return pmu->boxes[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 	pmu->registered = false;
 }
 
-static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
-{
-	struct intel_uncore_pmu *pmu = type->pmus;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	if (pmu) {
-		pkg = topology_physical_package_id(cpu);
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box)
-				uncore_box_exit(box);
-		}
-	}
-}
-
-static void uncore_exit_boxes(void *dummy)
-{
-	struct intel_uncore_type **types;
-
-	for (types = uncore_msr_uncores; *types; types++)
-		__uncore_exit_boxes(*types++, smp_processor_id());
-}
-
 static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
 	int pkg;
@@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void)
 	}
 }
 
-static int uncore_cpu_dying(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box && atomic_dec_return(&box->refcnt) == 0)
-				uncore_box_exit(box);
-		}
-	}
-	return 0;
-}
-
-static int first_init;
-
-static int uncore_cpu_starting(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg, ncpus = 1;
-
-	if (first_init) {
-		/*
-		 * On init we get the number of online cpus in the package
-		 * and set refcount for all of them.
-		 */
-		ncpus = cpumask_weight(topology_core_cpumask(cpu));
-	}
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (!box)
-				continue;
-			/* The first cpu on a package activates the box */
-			if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
-				uncore_box_init(box);
-		}
-	}
-
-	return 0;
-}
-
-static int uncore_cpu_prepare(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			if (pmu->boxes[pkg])
-				continue;
-			/* First cpu of a package allocates the box */
-			box = uncore_alloc_box(type, cpu_to_node(cpu));
-			if (!box)
-				return -ENOMEM;
-			box->pmu = pmu;
-			box->pkgid = pkg;
-			pmu->boxes[pkg] = box;
-		}
-	}
-	return 0;
-}
-
 static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 				   int new_cpu)
 {
@@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
 
 static int uncore_event_cpu_offline(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, pkg, target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
-		return 0;
-
+		goto unref;
 	/* Find a new cpu to collect uncore events */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
@@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu)
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
+
+unref:
+	/* Clear the references */
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (box && atomic_dec_return(&box->refcnt) == 0)
+				uncore_box_exit(box);
+		}
+	}
 	return 0;
 }
 
+static int allocate_boxes(struct intel_uncore_type **types,
+			 unsigned int pkg, unsigned int cpu)
+{
+	struct intel_uncore_box *box, *tmp;
+	struct intel_uncore_type *type;
+	struct intel_uncore_pmu *pmu;
+	LIST_HEAD(allocated);
+	int i;
+
+	/* Try to allocate all required boxes */
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			if (pmu->boxes[pkg])
+				continue;
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
+			if (!box)
+				goto cleanup;
+			box->pmu = pmu;
+			box->pkgid = pkg;
+			list_add(&box->active_list, &allocated);
+		}
+	}
+	/* Install them in the pmus */
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		box->pmu->boxes[pkg] = box;
+	}
+	return 0;
+
+cleanup:
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		kfree(box);
+	}
+	return -ENOMEM;
+}
+
 static int uncore_event_cpu_online(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, ret, pkg, target;
+
+	pkg = topology_logical_package_id(cpu);
+	ret = allocate_boxes(types, pkg, cpu);
+	if (ret)
+		return ret;
+
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (!box && atomic_inc_return(&box->refcnt) == 1)
+				uncore_box_init(box);
+		}
+	}
 
 	/*
 	 * Check if there is an online cpu in the package
@@ -1389,38 +1363,16 @@ static int __init intel_uncore_init(void)
 	if (cret && pret)
 		return -ENODEV;
 
-	/*
-	 * Install callbacks. Core will call them for each online cpu.
-	 *
-	 * The first online cpu of each package allocates and takes
-	 * the refcounts for all other online cpus in that package.
-	 * If msrs are not enabled no allocation is required and
-	 * uncore_cpu_prepare() is not called for each online cpu.
-	 */
-	if (!cret) {
-	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-				       "perf/x86/intel/uncore:prepare",
-				       uncore_cpu_prepare, NULL);
-		if (ret)
-			goto err;
-	} else {
-		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "perf/x86/intel/uncore:prepare",
-					  uncore_cpu_prepare, NULL);
-	}
-	first_init = 1;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "perf/x86/uncore:starting",
-			  uncore_cpu_starting, uncore_cpu_dying);
-	first_init = 0;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "perf/x86/uncore:online",
-			  uncore_event_cpu_online, uncore_event_cpu_offline);
+	/* Install hotplug callbacks to setup the targets for each package */
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+				"perf/x86/intel/uncore:online",
+				uncore_event_cpu_online,
+				uncore_event_cpu_offline);
+	if (ret)
+		goto err;
 	return 0;
 
 err:
-	/* Undo box->init_box() */
-	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 	return ret;
@@ -1429,9 +1381,7 @@ module_init(intel_uncore_init);
 
 static void __exit intel_uncore_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 }
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 38711df3bcb5..2266f864b747 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -140,6 +140,7 @@ extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 void reload_early_microcode(void);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
+extern bool initrd_gone;
 #else
 static inline int __init microcode_init(void)			{ return 0; };
 static inline void __init load_ucode_bsp(void)			{ }
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1be64da0384e..e6cfe7ba2d65 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1e35dd06b090..bd6b8c270c24 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1875,7 +1875,6 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1887,7 +1886,6 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2117,6 +2115,7 @@ static inline void __init check_timer(void)
 			if (idx != -1 && irq_trigger(idx))
 				unmask_ioapic_irq(irq_get_chip_data(0));
 		}
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
@@ -2138,6 +2137,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..2b4cf04239b6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-		node_id = cpuid_ecx(0x8000001e) & 7;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+		if (c->x86 == 0x15)
+			c->cu_id = ebx & 0xff;
+
+		if (c->x86 >= 0x17) {
+			c->cpu_core_id = ebx & 0xff;
+
+			if (smp_num_siblings > 1)
+				c->x86_max_cores /= smp_num_siblings;
+		}
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..ede03e849a8b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
 	c->x86_coreid_bits = 0;
+	c->cu_id = 0xff;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 00ef43233e03..537c6647d84c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1373,20 +1373,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 
 static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
 
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct timer_list *t, unsigned long interval)
 {
 	unsigned long when = jiffies + interval;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	if (timer_pending(t)) {
-		if (time_before(when, t->expires))
-			mod_timer(t, when);
-	} else {
-		t->expires = round_jiffies(when);
-		add_timer_on(t, smp_processor_id());
-	}
+	if (!timer_pending(t) || time_before(when, t->expires))
+		mod_timer(t, round_jiffies(when));
 
 	local_irq_restore(flags);
 }
@@ -1421,7 +1416,7 @@ static void mce_timer_fn(unsigned long data)
 
 done:
 	__this_cpu_write(mce_next_interval, iv);
-	__restart_timer(t, iv);
+	__start_timer(t, iv);
 }
 
 /*
@@ -1432,7 +1427,7 @@ void mce_timer_kick(unsigned long interval)
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
-	__restart_timer(t, interval);
+	__start_timer(t, interval);
 
 	if (interval < iv)
 		__this_cpu_write(mce_next_interval, interval);
@@ -1779,17 +1774,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
 
 	if (mca_cfg.ignore_ce || !iv)
 		return;
 
-	per_cpu(mce_next_interval, cpu) = iv;
-
-	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, cpu);
+	this_cpu_write(mce_next_interval, iv);
+	__start_timer(t, iv);
 }
 
 static void __mcheck_cpu_setup_timer(void)
@@ -1806,7 +1799,7 @@ static void __mcheck_cpu_init_timer(void)
 	unsigned int cpu = smp_processor_id();
 
 	setup_pinned_timer(t, mce_timer_fn, cpu);
-	mce_start_timer(cpu, t);
+	mce_start_timer(t);
 }
 
 /* Handle unconfigured int18 (should never happen) */
@@ -2566,7 +2559,7 @@ static int mce_cpu_dead(unsigned int cpu)
 
 static int mce_cpu_online(unsigned int cpu)
 {
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	int ret;
 
 	mce_device_create(cpu);
@@ -2577,13 +2570,13 @@ static int mce_cpu_online(unsigned int cpu)
 		return ret;
 	}
 	mce_reenable_cpu();
-	mce_start_timer(cpu, t);
+	mce_start_timer(t);
 	return 0;
 }
 
 static int mce_cpu_pre_down(unsigned int cpu)
 {
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 
 	mce_disable_cpu();
 	del_timer_sync(t);
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6a31e2691f3a..079e81733a58 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family)
 reget:
 		if (!get_builtin_microcode(&cp, family)) {
 #ifdef CONFIG_BLK_DEV_INITRD
-			cp = find_cpio_data(ucode_path, (void *)initrd_start,
-					    initrd_end - initrd_start, NULL);
+			if (!initrd_gone)
+				cp = find_cpio_data(ucode_path, (void *)initrd_start,
+						    initrd_end - initrd_start, NULL);
 #endif
 			if (!(cp.data && cp.size)) {
 				/*
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 2af69d27da62..73102d932760 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -46,6 +46,8 @@
 static struct microcode_ops	*microcode_ops;
 static bool dis_ucode_ldr = true;
 
+bool initrd_gone;
+
 LIST_HEAD(microcode_cache);
 
 /*
@@ -190,21 +192,24 @@ void load_ucode_ap(void)
 static int __init save_microcode_in_initrd(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	int ret = -EINVAL;
 
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		if (c->x86 >= 6)
-			return save_microcode_in_initrd_intel();
+			ret = save_microcode_in_initrd_intel();
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			return save_microcode_in_initrd_amd(c->x86);
+			ret = save_microcode_in_initrd_amd(c->x86);
 		break;
 	default:
 		break;
 	}
 
-	return -EINVAL;
+	initrd_gone = true;
+
+	return ret;
 }
 
 struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
@@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 	 * has the virtual address of the beginning of the initrd. It also
 	 * possibly relocates the ramdisk. In either case, initrd_start contains
 	 * the updated address so use that instead.
+	 *
+	 * initrd_gone is for the hotplug case where we've thrown out initrd
+	 * already.
 	 */
-	if (!use_pa && initrd_start)
-		start = initrd_start;
+	if (!use_pa) {
+		if (initrd_gone)
+			return (struct cpio_data){ NULL, 0, "" };
+		if (initrd_start)
+			start = initrd_start;
+	}
 
 	return find_cpio_data(path, (void *)start, size, NULL);
 #else /* !CONFIG_BLK_DEV_INITRD */
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 3f329b74e040..8325d8a09ab0 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -41,7 +41,7 @@
 
 static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
 
-/* Current microcode patch used in early patching */
+/* Current microcode patch used in early patching on the APs. */
 struct microcode_intel *intel_ucode_patch;
 
 static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
@@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void)
 	struct ucode_cpu_info uci;
 	struct cpio_data cp;
 
-	/*
-	 * AP loading didn't find any microcode patch, no need to save anything.
-	 */
-	if (!intel_ucode_patch || IS_ERR(intel_ucode_patch))
-		return 0;
-
 	if (!load_builtin_intel_microcode(&cp))
 		cp = find_microcode_in_initrd(ucode_path, false);
 
@@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void)
 	return 0;
 }
 
-
 /*
  * @res_patch, output: a pointer to the patch we found.
  */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e4e97a5355ce..de7234401275 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -9,6 +9,7 @@
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
+#include <asm/fpu/xstate.h>
 #include <asm/traps.h>
 
 #include <linux/hardirq.h>
@@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state)
 	 * it will #GP. Make sure it is replaced after the memset().
 	 */
 	if (static_cpu_has(X86_FEATURE_XSAVES))
-		state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
+		state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
+					       xfeatures_mask;
 
 	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 85e87b46c318..dc6ba5bda9fc 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 	} else {
 		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
 
+		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 		disable_irq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..99b920d0e516 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
-		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->cpu_core_id == o->cpu_core_id)
-			return topology_sane(c, o, "smt");
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+			if (c->cpu_core_id == o->cpu_core_id)
+				return topology_sane(c, o, "smt");
+
+			if ((c->cu_id != 0xff) &&
+			    (o->cu_id != 0xff) &&
+			    (c->cu_id == o->cu_id))
+				return topology_sane(c, o, "smt");
+		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..37e7cf544e51 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1356,6 +1356,9 @@ void __init tsc_init(void)
 		(unsigned long)cpu_khz / 1000,
 		(unsigned long)cpu_khz % 1000);
 
+	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+	tsc_store_and_check_tsc_adjust(true);
+
 	/*
 	 * Secondary CPUs do not run through tsc_init(), so set up
 	 * all the scale factors for all CPUs, assuming the same
@@ -1386,8 +1389,6 @@ void __init tsc_init(void)
 
 	if (unsynchronized_tsc())
 		mark_tsc_unstable("TSCs unsynchronized");
-	else
-		tsc_store_and_check_tsc_adjust(true);
 
 	check_system_tsc_reliable();
 
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011051a5..728f75378475 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu)
 	if (unsynchronized_tsc())
 		return;
 
-	if (tsc_clocksource_reliable) {
-		if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
-			pr_info(
-			"Skipped synchronization checks as TSC is reliable.\n");
-		return;
-	}
-
 	/*
 	 * Set the maximum number of test runs to
 	 *  1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@ void check_tsc_sync_target(void)
 	int cpus = 2;
 
 	/* Also aborts if there is no TSC. */
-	if (unsynchronized_tsc() || tsc_clocksource_reliable)
+	if (unsynchronized_tsc())
 		return;
 
 	/*
 	 * Store, verify and sanitize the TSC adjust register. If
 	 * successful skip the test.
+	 *
+	 * The test is also skipped when the TSC is marked reliable. This
+	 * is true for SoCs which have no fallback clocksource. On these
+	 * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+	 * register might have been wreckaged by the BIOS..
 	 */
-	if (tsc_store_and_check_tsc_adjust(false)) {
+	if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
 		atomic_inc(&skip_test);
 		return;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d153be8929a6..e52c9088660f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV */
+	xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
 	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
 
 	/*
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..8aa6bea1cd6c 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,6 +15,7 @@
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
@@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		} else
 			note_page(m, &st, __pgprot(0), 1);
 
+		cond_resched();
 		start++;
 	}
 
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 319148bd4b05..2f25a363068c 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	efi_scratch.use_pgd = true;
 
 	/*
+	 * Certain firmware versions are way too sentimential and still believe
+	 * they are exclusive and unquestionable owners of the first physical page,
+	 * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
+	 * (but then write-access it later during SetVirtualAddressMap()).
+	 *
+	 * Create a 1:1 mapping for this page, to avoid triple faults during early
+	 * boot with such firmware. We are free to hand this page to the BIOS,
+	 * as trim_bios_range() will reserve the first page and isolate it away
+	 * from memory allocators anyway.
+	 */
+	if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) {
+		pr_err("Failed to create 1:1 mapping for the first page!\n");
+		return 1;
+	}
+
+	/*
 	 * When making calls to the firmware everything needs to be 1:1
 	 * mapped and addressable with 32-bit pointers. Map the kernel
 	 * text and allocate a new stack because we can't rely on the