Adding upstream version 6.1.85.upstream/6.1.85

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 147 insertions, 54 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c3ef1fc60..62a44455c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -535,9 +535,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf)
 }
 
 static __always_inline
-void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask)
+void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask)
 {
-	/* Use kvm_cpu_cap_mask for non-scattered leafs. */
+	/* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */
 	BUILD_BUG_ON(leaf < NCAPINTS);
 
 	kvm_cpu_caps[leaf] = mask;
@@ -547,7 +547,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask)
 
 static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
 {
-	/* Use kvm_cpu_cap_init_scattered for scattered leafs. */
+	/* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */
 	BUILD_BUG_ON(leaf >= NCAPINTS);
 
 	kvm_cpu_caps[leaf] &= mask;
@@ -652,11 +652,16 @@ void kvm_set_cpu_caps(void)
 		F(AVX_VNNI) | F(AVX512_BF16)
 	);
 
+	kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
+		F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) |
+		F(BHI_CTRL) | F(MCDT_NO)
+	);
+
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
 	);
 
-	kvm_cpu_cap_init_scattered(CPUID_12_EAX,
+	kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX,
 		SF(SGX1) | SF(SGX2)
 	);
 
@@ -902,13 +907,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* function 7 has additional index. */
 	case 7:
-		entry->eax = min(entry->eax, 1u);
+		max_idx = entry->eax = min(entry->eax, 2u);
 		cpuid_entry_override(entry, CPUID_7_0_EBX);
 		cpuid_entry_override(entry, CPUID_7_ECX);
 		cpuid_entry_override(entry, CPUID_7_EDX);
 
-		/* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */
-		if (entry->eax == 1) {
+		/* KVM only supports up to 0x7.2, capped above via min(). */
+		if (max_idx >= 1) {
 			entry = do_host_cpuid(array, function, 1);
 			if (!entry)
 				goto out;
@@ -918,6 +923,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->ecx = 0;
 			entry->edx = 0;
 		}
+		if (max_idx >= 2) {
+			entry = do_host_cpuid(array, function, 2);
+			if (!entry)
+				goto out;
+
+			cpuid_entry_override(entry, CPUID_7_2_EDX);
+			entry->ecx = 0;
+			entry->ebx = 0;
+			entry->eax = 0;
+		}
 		break;
 	case 0xa: { /* Architectural Performance Monitoring */
 		union cpuid10_eax eax;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index edcf45e31..bfeafe485 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -40,6 +40,7 @@
 #include "ioapic.h"
 #include "trace.h"
 #include "x86.h"
+#include "xen.h"
 #include "cpuid.h"
 #include "hyperv.h"
 
@@ -338,8 +339,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 	}
 
 	/* Check if there are APF page ready requests pending */
-	if (enabled)
+	if (enabled) {
 		kvm_make_request(KVM_REQ_APF_READY, apic->vcpu);
+		kvm_xen_sw_enable_lapic(apic->vcpu);
+	}
 }
 
 static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 7eeade35a..e43909d65 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -7,23 +7,44 @@
 #include <asm/cpufeatures.h>
 
 /*
- * Hardware-defined CPUID leafs that are scattered in the kernel, but need to
- * be directly used by KVM.  Note, these word values conflict with the kernel's
- * "bug" caps, but KVM doesn't use those.
+ * Hardware-defined CPUID leafs that are either scattered by the kernel or are
+ * unknown to the kernel, but need to be directly used by KVM.  Note, these
+ * word values conflict with the kernel's "bug" caps, but KVM doesn't use those.
  */
 enum kvm_only_cpuid_leafs {
 	CPUID_12_EAX	 = NCAPINTS,
+	CPUID_7_2_EDX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
 };
 
+/*
+ * Define a KVM-only feature flag.
+ *
+ * For features that are scattered by cpufeatures.h, __feature_translate() also
+ * needs to be updated to translate the kernel-defined feature into the
+ * KVM-defined feature.
+ *
+ * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h,
+ * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so
+ * that X86_FEATURE_* can be used in KVM.  No __feature_translate() handling is
+ * needed in this case.
+ */
 #define KVM_X86_FEATURE(w, f)		((w)*32 + (f))
 
 /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */
 #define KVM_X86_FEATURE_SGX1		KVM_X86_FEATURE(CPUID_12_EAX, 0)
 #define KVM_X86_FEATURE_SGX2		KVM_X86_FEATURE(CPUID_12_EAX, 1)
 
+/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */
+#define X86_FEATURE_INTEL_PSFD		KVM_X86_FEATURE(CPUID_7_2_EDX, 0)
+#define X86_FEATURE_IPRED_CTRL		KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
+#define KVM_X86_FEATURE_RRSBA_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
+#define X86_FEATURE_DDPD_U		KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
+#define KVM_X86_FEATURE_BHI_CTRL	KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define X86_FEATURE_MCDT_NO		KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
+
 struct cpuid_reg {
 	u32 function;
 	u32 index;
@@ -49,6 +70,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_12_EAX]        = {0x00000012, 0, CPUID_EAX},
 	[CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX},
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
+	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 };
 
 /*
@@ -61,10 +83,12 @@ static const struct cpuid_reg reverse_cpuid[] = {
  */
 static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
 {
+	BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_5);
 	BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
 	BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
 }
@@ -75,12 +99,17 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
  */
 static __always_inline u32 __feature_translate(int x86_feature)
 {
-	if (x86_feature == X86_FEATURE_SGX1)
-		return KVM_X86_FEATURE_SGX1;
-	else if (x86_feature == X86_FEATURE_SGX2)
-		return KVM_X86_FEATURE_SGX2;
-
-	return x86_feature;
+#define KVM_X86_TRANSLATE_FEATURE(f)	\
+	case X86_FEATURE_##f: return KVM_X86_FEATURE_##f
+
+	switch (x86_feature) {
+	KVM_X86_TRANSLATE_FEATURE(SGX1);
+	KVM_X86_TRANSLATE_FEATURE(SGX2);
+	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+	KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+	default:
+		return x86_feature;
+	}
 }
 
 static __always_inline u32 __feature_leaf(int x86_feature)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 3060fe4e9..d8e192ad5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -76,9 +76,10 @@ struct enc_region {
 };
 
 /* Called with the sev_bitmap_lock held, or on shutdown  */
-static int sev_flush_asids(int min_asid, int max_asid)
+static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 {
-	int ret, asid, error = 0;
+	int ret, error = 0;
+	unsigned int asid;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
 	asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
@@ -108,7 +109,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
 }
 
 /* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(int min_asid, int max_asid)
+static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
 {
 	if (sev_flush_asids(min_asid, max_asid))
 		return false;
@@ -135,8 +136,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
 
 static int sev_asid_new(struct kvm_sev_info *sev)
 {
-	int asid, min_asid, max_asid, ret;
+	/*
+	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
+	 * Note: min ASID can end up larger than the max if basic SEV support is
+	 * effectively disabled by disallowing use of ASIDs for SEV guests.
+	 */
+	unsigned int min_asid = sev->es_active ? 1 : min_sev_asid;
+	unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
+	unsigned int asid;
 	bool retry = true;
+	int ret;
+
+	if (min_asid > max_asid)
+		return -ENOTTY;
 
 	WARN_ON(sev->misc_cg);
 	sev->misc_cg = get_current_misc_cg();
@@ -149,12 +162,6 @@ static int sev_asid_new(struct kvm_sev_info *sev)
 
 	mutex_lock(&sev_bitmap_lock);
 
-	/*
-	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
-	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
-	 */
-	min_asid = sev->es_active ? 1 : min_sev_asid;
-	max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
 again:
 	asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
 	if (asid > max_asid) {
@@ -179,7 +186,7 @@ e_uncharge:
 	return ret;
 }
 
-static int sev_get_asid(struct kvm *kvm)
+static unsigned int sev_get_asid(struct kvm *kvm)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
@@ -276,8 +283,8 @@ e_no_asid:
 
 static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 {
+	unsigned int asid = sev_get_asid(kvm);
 	struct sev_data_activate activate;
-	int asid = sev_get_asid(kvm);
 	int ret;
 
 	/* activate ASID on the given handle */
@@ -1958,20 +1965,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		goto e_free;
 	}
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
 	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
+	 * correct C-bit.  Note, this must be done before dropping kvm->lock,
+	 * as region and its array of pages can be freed by a different task
+	 * once kvm->lock is released.
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 
 e_free:
@@ -2211,11 +2220,10 @@ void __init sev_hardware_setup(void)
 		goto out;
 	}
 
-	sev_asid_count = max_sev_asid - min_sev_asid + 1;
-	if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count))
-		goto out;
-
-	pr_info("SEV supported: %u ASIDs\n", sev_asid_count);
+	if (min_sev_asid <= max_sev_asid) {
+		sev_asid_count = max_sev_asid - min_sev_asid + 1;
+		WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+	}
 	sev_supported = true;
 
 	/* SEV-ES support requested? */
@@ -2240,13 +2248,21 @@ void __init sev_hardware_setup(void)
 		goto out;
 
 	sev_es_asid_count = min_sev_asid - 1;
-	if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count))
-		goto out;
-
-	pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count);
+	WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count));
 	sev_es_supported = true;
 
 out:
+	if (boot_cpu_has(X86_FEATURE_SEV))
+		pr_info("SEV %s (ASIDs %u - %u)\n",
+			sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
+								       "unusable" :
+								       "disabled",
+			min_sev_asid, max_sev_asid);
+	if (boot_cpu_has(X86_FEATURE_SEV_ES))
+		pr_info("SEV-ES %s (ASIDs %u - %u)\n",
+			sev_es_supported ? "enabled" : "disabled",
+			min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
+
 	sev_enabled = sev_supported;
 	sev_es_enabled = sev_es_supported;
 #endif
@@ -2285,7 +2301,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
  */
 static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 {
-	int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+	unsigned int asid = sev_get_asid(vcpu->kvm);
 
 	/*
 	 * Note!  The address must be a kernel address, as regular page walk
@@ -2606,7 +2622,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-	int asid = sev_get_asid(svm->vcpu.kvm);
+	unsigned int asid = sev_get_asid(svm->vcpu.kvm);
 
 	/* Assign the asid allocated with this SEV guest */
 	svm->asid = asid;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index bc25589ad..6c1dcf44c 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -729,13 +729,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit,
  * Tracepoint for nested #vmexit because of interrupt pending
  */
 TRACE_EVENT(kvm_invlpga,
-	    TP_PROTO(__u64 rip, int asid, u64 address),
+	    TP_PROTO(__u64 rip, unsigned int asid, u64 address),
 	    TP_ARGS(rip, asid, address),
 
 	TP_STRUCT__entry(
-		__field(	__u64,	rip	)
-		__field(	int,	asid	)
-		__field(	__u64,	address	)
+		__field(	__u64,		rip	)
+		__field(	unsigned int,	asid	)
+		__field(	__u64,		address	)
 	),
 
 	TP_fast_assign(
@@ -744,7 +744,7 @@ TRACE_EVENT(kvm_invlpga,
 		__entry->address	=	address;
 	),
 
-	TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
+	TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx",
 		  __entry->rip, __entry->asid, __entry->address)
 );
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 0b2cad66d..b4f893722 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -242,6 +242,8 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
 
 	call vmx_spec_ctrl_restore_host
 
+	CLEAR_BRANCH_HISTORY_VMEXIT
+
 	/* Put return value in AX */
 	mov %_ASM_BX, %_ASM_AX
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 688bc7b72..f72476503 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1614,7 +1614,7 @@ static unsigned int num_msr_based_features;
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
 	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
-	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -7758,6 +7758,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
+
+	/*
+	 * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+	 * successful, as the old value is written back on failure.  Note, for
+	 * live migration, this is unnecessarily conservative as CMPXCHG writes
+	 * back the original value and the access is atomic, but KVM's ABI is
+	 * that all writes are dirty logged, regardless of the value written.
+	 */
+	kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index a58a426e6..684a39df6 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -314,7 +314,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
 }
 
-static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v)
+void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v)
 {
 	struct kvm_lapic_irq irq = { };
 	int r;
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index 532a535a9..500d9593a 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -16,6 +16,7 @@ extern struct static_key_false_deferred kvm_xen_enabled;
 
 int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu);
 void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu);
+void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu);
 int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data);
@@ -33,6 +34,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 struct kvm_kernel_irq_routing_entry *e,
 			 const struct kvm_irq_routing_entry *ue);
 
+static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * The local APIC is being enabled. If the per-vCPU upcall vector is
+	 * set and the vCPU's evtchn_upcall_pending flag is set, inject the
+	 * interrupt.
+	 */
+	if (static_branch_unlikely(&kvm_xen_enabled.key) &&
+	    vcpu->arch.xen.vcpu_info_cache.active &&
+	    vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu))
+		kvm_xen_inject_vcpu_vector(vcpu);
+}
+
 static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 {
 	return static_branch_unlikely(&kvm_xen_enabled.key) &&
@@ -98,6 +112,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
 {
 }
 
+static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu)
+{
+}
+
 static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 {
 	return false;