Merge tag 'kvmarm-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm updates for Linux 5.7

- GICv4.1 support
- 32bit host removal

12 files changed, 135 insertions, 63 deletions

diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
index 748456c365f4..9557c5a15b91 100644
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ b/arch/x86/boot/compressed/kaslr_64.c
@@ -29,9 +29,6 @@
 #define __PAGE_OFFSET __PAGE_OFFSET_BASE
 #include "../../mm/ident_map.c"
 
-/* Used by pgtable.h asm code to force instruction serialization. */
-unsigned long __force_order;
-
 /* Used to track our page table allocation area. */
 struct alloc_pgt_data {
 	unsigned char *pgt_buf;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ebe1685e92dd..d5e517d1c3dd 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ac83a0fef628..1f875fbe1384 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -28,6 +28,7 @@
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
+static const int amd_erratum_1054[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 /*
@@ -972,6 +973,15 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+	/*
+	 * Turn on the Instructions Retired free counter on machines not
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (cpu_has(c, X86_FEATURE_IRPERF) &&
+	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 }
 
 #ifdef CONFIG_X86_32
@@ -1099,6 +1109,10 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
 	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index b3a50d962851..52de616a8065 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = {
 	.store			= store,
 };
 
+static void threshold_block_release(struct kobject *kobj);
+
 static struct kobj_type threshold_ktype = {
 	.sysfs_ops		= &threshold_ops,
 	.default_attrs		= default_attrs,
+	.release		= threshold_block_release,
 };
 
 static const char *get_name(unsigned int bank, struct threshold_block *b)
@@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 	return buf_mcatype;
 }
 
-static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
-				     unsigned int block, u32 address)
+static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb,
+				     unsigned int bank, unsigned int block,
+				     u32 address)
 {
 	struct threshold_block *b = NULL;
 	u32 low, high;
@@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 
 	INIT_LIST_HEAD(&b->miscj);
 
-	if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
-		list_add(&b->miscj,
-			 &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
-	} else {
-		per_cpu(threshold_banks, cpu)[bank]->blocks = b;
-	}
+	if (tb->blocks)
+		list_add(&b->miscj, &tb->blocks->miscj);
+	else
+		tb->blocks = b;
 
-	err = kobject_init_and_add(&b->kobj, &threshold_ktype,
-				   per_cpu(threshold_banks, cpu)[bank]->kobj,
-				   get_name(bank, b));
+	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
 	if (err)
 		goto out_free;
 recurse:
@@ -1260,7 +1260,7 @@ recurse:
 	if (!address)
 		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, block, address);
+	err = allocate_threshold_blocks(cpu, tb, bank, block, address);
 	if (err)
 		goto out_free;
 
@@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		goto out_free;
 	}
 
-	per_cpu(threshold_banks, cpu)[bank] = b;
-
 	if (is_shared_bank(bank)) {
 		refcount_set(&b->cpus, 1);
 
@@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		}
 	}
 
-	err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
-	if (!err)
-		goto out;
+	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+	if (err)
+		goto out_free;
+
+	per_cpu(threshold_banks, cpu)[bank] = b;
+
+	return 0;
 
  out_free:
 	kfree(b);
@@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	return err;
 }
 
-static void deallocate_threshold_block(unsigned int cpu,
-						 unsigned int bank)
+static void threshold_block_release(struct kobject *kobj)
+{
+	kfree(to_block(kobj));
+}
+
+static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
 {
 	struct threshold_block *pos = NULL;
 	struct threshold_block *tmp = NULL;
@@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu,
 		return;
 
 	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
-		kobject_put(&pos->kobj);
 		list_del(&pos->miscj);
-		kfree(pos);
+		kobject_put(&pos->kobj);
 	}
 
-	kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
-	per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
+	kobject_put(&head->blocks->kobj);
 }
 
 static void __threshold_remove_blocks(struct threshold_bank *b)
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index 4d4f5d9faac3..23054909c8dd 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -10,8 +10,6 @@ extern struct boot_params boot_params;
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;
@@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	/* Get variable contents into buffer */
-	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
 				  NULL, &size, &secboot);
 	if (status == EFI_NOT_FOUND) {
 		pr_info("ima: secureboot mode disabled\n");
@@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	size = sizeof(setupmode);
-	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
 				  NULL, &size, &setupmode);
 
 	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d817f255aed8..6efe0410fb72 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -425,7 +425,29 @@ static void __init sev_map_percpu_data(void)
 	}
 }
 
+static bool pv_tlb_flush_supported(void)
+{
+	return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
+
 #ifdef CONFIG_SMP
+
+static bool pv_ipi_supported(void)
+{
+	return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+}
+
+static bool pv_sched_yield_supported(void)
+{
+	return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
 #define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)
 
 static void __send_ipi_mask(const struct cpumask *mask, int vector)
@@ -490,12 +512,12 @@ static void kvm_send_ipi_mask(const struct cpumask *mask, int vector)
 static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
 {
 	unsigned int this_cpu = smp_processor_id();
-	struct cpumask new_mask;
+	struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
 	const struct cpumask *local_mask;
 
-	cpumask_copy(&new_mask, mask);
-	cpumask_clear_cpu(this_cpu, &new_mask);
-	local_mask = &new_mask;
+	cpumask_copy(new_mask, mask);
+	cpumask_clear_cpu(this_cpu, new_mask);
+	local_mask = new_mask;
 	__send_ipi_mask(local_mask, vector);
 }
 
@@ -575,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
 	update_intr_gate(X86_TRAP_PF, async_page_fault);
 }
 
-static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
 
 static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 			const struct flush_tlb_info *info)
@@ -583,7 +604,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 	u8 state;
 	int cpu;
 	struct kvm_steal_time *src;
-	struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+	struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
 
 	cpumask_copy(flushmask, cpumask);
 	/*
@@ -619,11 +640,10 @@ static void __init kvm_guest_init(void)
 		pv_ops.time.steal_clock = kvm_steal_clock;
 	}
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+	if (pv_tlb_flush_supported()) {
 		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
+		pr_info("KVM setup pv remote TLB flush\n");
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -632,9 +652,7 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
-	if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
-	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+	if (pv_sched_yield_supported()) {
 		smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
 		pr_info("KVM setup pv sched yield\n");
 	}
@@ -700,7 +718,7 @@ static uint32_t __init kvm_detect(void)
 static void __init kvm_apic_init(void)
 {
 #if defined(CONFIG_SMP)
-	if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI))
+	if (pv_ipi_supported())
 		kvm_setup_pv_ipi();
 #endif
 }
@@ -732,26 +750,31 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
-static __init int kvm_setup_pv_tlb_flush(void)
+static __init int kvm_alloc_cpumask(void)
 {
 	int cpu;
+	bool alloc = false;
 
 	if (!kvm_para_available() || nopv)
 		return 0;
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
-	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+	if (pv_tlb_flush_supported())
+		alloc = true;
+
+#if defined(CONFIG_SMP)
+	if (pv_ipi_supported())
+		alloc = true;
+#endif
+
+	if (alloc)
 		for_each_possible_cpu(cpu) {
-			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
 				GFP_KERNEL, cpu_to_node(cpu));
 		}
-		pr_info("KVM setup pv remote TLB flush\n");
-	}
 
 	return 0;
 }
-arch_initcall(kvm_setup_pv_tlb_flush);
+arch_initcall(kvm_alloc_cpumask);
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 991019d5eee1..1bb4927030af 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -59,6 +59,19 @@ config KVM
 
 	  If unsure, say N.
 
+config KVM_WERROR
+	bool "Compile KVM with -Werror"
+	# KASAN may cause the build to fail due to larger frames
+	default y if X86_64 && !KASAN
+	# We use the dependency on !COMPILE_TEST to not be enabled
+	# blindly in allmodconfig or allyesconfig configurations
+	depends on (X86_64 && !KASAN) || !COMPILE_TEST
+	depends on EXPERT
+	help
+	  Add -Werror to the build flags for (and only for) i915.ko.
+
+	  If in doubt, say "N".
+
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 4654e97a05cc..e553f0fdd87d 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 ccflags-y += -Iarch/x86/kvm
-ccflags-y += -Werror
+ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
 KVM := ../../../virt/kvm
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2125c6ae5951..05cb45bc0e08 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -57,11 +57,13 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+#ifdef MODULE
 static const struct x86_cpu_id svm_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_SVM),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
+#endif
 
 #define IOPM_ALLOC_ORDER 2
 #define MSRPM_ALLOC_ORDER 1
@@ -2230,8 +2232,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 static int avic_init_vcpu(struct vcpu_svm *svm)
 {
 	int ret;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
-	if (!kvm_vcpu_apicv_active(&svm->vcpu))
+	if (!avic || !irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
 	ret = avic_init_backing_page(&svm->vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3aba51d782e2..a7dd67859bd4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -64,11 +64,13 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+#ifdef MODULE
 static const struct x86_cpu_id vmx_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_VMX),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+#endif
 
 bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
@@ -7163,6 +7165,7 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
 	else
 		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
 
+	/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
 	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
 }
 
@@ -7192,6 +7195,20 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	case x86_intercept_outs:
 		return vmx_check_intercept_io(vcpu, info);
 
+	case x86_intercept_lgdt:
+	case x86_intercept_lidt:
+	case x86_intercept_lldt:
+	case x86_intercept_ltr:
+	case x86_intercept_sgdt:
+	case x86_intercept_sidt:
+	case x86_intercept_sldt:
+	case x86_intercept_str:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+			return X86EMUL_CONTINUE;
+
+		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+		break;
+
 	/* TODO: check more intercepts... */
 	default:
 		break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6fa014ccd253..1b6d9ac9533c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7195,15 +7195,15 @@ static void kvm_timer_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 #ifdef CONFIG_CPU_FREQ
-		struct cpufreq_policy policy;
+		struct cpufreq_policy *policy;
 		int cpu;
 
-		memset(&policy, 0, sizeof(policy));
 		cpu = get_cpu();
-		cpufreq_get_policy(&policy, cpu);
-		if (policy.cpuinfo.max_freq)
-			max_tsc_khz = policy.cpuinfo.max_freq;
+		policy = cpufreq_cpu_get(cpu);
+		if (policy && policy->cpuinfo.max_freq)
+			max_tsc_khz = policy->cpuinfo.max_freq;
 		put_cpu();
+		cpufreq_cpu_put(policy);
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
@@ -7313,12 +7313,12 @@ int kvm_arch_init(void *opaque)
 	}
 
 	if (!ops->cpu_has_kvm_support()) {
-		printk(KERN_ERR "kvm: no hardware support\n");
+		pr_err_ratelimited("kvm: no hardware support\n");
 		r = -EOPNOTSUPP;
 		goto out;
 	}
 	if (ops->disabled_by_bios()) {
-		printk(KERN_ERR "kvm: disabled by bios\n");
+		pr_err_ratelimited("kvm: disabled by bios\n");
 		r = -EOPNOTSUPP;
 		goto out;
 	}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 1f756ffffe8b..79409120a603 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -896,14 +896,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
+#ifdef CONFIG_X86_64
+	unsigned int which;
+	u64 base;
+#endif
 
 	ret = 0;
 
 	switch (msr) {
 #ifdef CONFIG_X86_64
-		unsigned which;
-		u64 base;
-
 	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
 	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
 	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;