Merging upstream version 6.7.12.

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

8 files changed, 94 insertions, 29 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index dda6fc4cfa..1811a9ddfe 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -679,6 +679,11 @@ void kvm_set_cpu_caps(void)
 		F(AMX_COMPLEX)
 	);
 
+	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
 	);
@@ -960,13 +965,13 @@ 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;
@@ -976,6 +981,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->ebx = 0;
 			entry->ecx = 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/hyperv.c b/arch/x86/kvm/hyperv.c
index 238afd7335..4943f6b2bb 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 
-	eventfd_signal(eventfd, 1);
+	eventfd_signal(eventfd);
 	return HV_STATUS_SUCCESS;
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 245b20973c..23fab75993 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -41,6 +41,7 @@
 #include "ioapic.h"
 #include "trace.h"
 #include "x86.h"
+#include "xen.h"
 #include "cpuid.h"
 #include "hyperv.h"
 #include "smm.h"
@@ -499,8 +500,10 @@ 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 b816506783..aadefcaa95 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_7_1_EDX,
 	CPUID_8000_0007_EDX,
 	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs {
 #define X86_FEATURE_AMX_COMPLEX         KVM_X86_FEATURE(CPUID_7_1_EDX, 8)
 #define X86_FEATURE_PREFETCHITI         KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
 
+/* 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 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)
+
 /* CPUID level 0x80000007 (EDX). */
 #define KVM_X86_FEATURE_CONSTANT_TSC	KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8)
 
@@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX},
 	[CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
+	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 };
 
 /*
@@ -106,18 +116,19 @@ 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;
-	else if (x86_feature == X86_FEATURE_SGX_EDECCSSA)
-		return KVM_X86_FEATURE_SGX_EDECCSSA;
-	else if (x86_feature == X86_FEATURE_CONSTANT_TSC)
-		return KVM_X86_FEATURE_CONSTANT_TSC;
-	else if (x86_feature == X86_FEATURE_PERFMON_V2)
-		return KVM_X86_FEATURE_PERFMON_V2;
-
-	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(SGX_EDECCSSA);
+	KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
+	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
+	KVM_X86_TRANSLATE_FEATURE(RRSBA_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 6ee925d666..1226bb2151 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -57,7 +57,7 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = true;
+static bool sev_es_debug_swap_enabled = false;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
@@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
-	if (sev_es_debug_swap_enabled)
+	if (sev_es_debug_swap_enabled) {
 		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+		pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
+			     "This will not work starting with Linux 6.10\n");
+	}
 
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
@@ -1975,20 +1978,22 @@ 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:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 468870450b..365caf7328 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1620,7 +1620,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
 	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
 	 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_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1652,6 +1653,8 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_SSB_NO;
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
+	if (!boot_cpu_has_bug(X86_BUG_RFDS))
+		data |= ARCH_CAP_RFDS_NO;
 
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
@@ -7948,6 +7951,16 @@ 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 e53fad915a..c069521f24 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -493,7 +493,7 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state)
 		kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable);
 }
 
-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;
@@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r)
 		if (ret < 0 && ret != -ENOTCONN)
 			return false;
 	} else {
-		eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1);
+		eventfd_signal(evtchnfd->deliver.eventfd.ctx);
 	}
 
 	*r = 0;
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index f8f1fe22d0..f5841d9000 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -18,6 +18,7 @@ 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);
@@ -36,6 +37,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 const struct kvm_irq_routing_entry *ue);
 void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu);
 
+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) &&
@@ -101,6 +115,10 @@ 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;