Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - A couple of fixes when handling an exception while a SError has
     been delivered

   - Workaround for Cortex-A510's single-step erratum

  RISC-V:

   - Make CY, TM, and IR counters accessible in VU mode

   - Fix SBI implementation version

  x86:

   - Report deprecation of x87 features in supported CPUID

   - Preparation for fixing an interrupt delivery race on AMD hardware

   - Sparse fix

  All except POWER and s390:

   - Rework guest entry code to correctly mark noinstr areas and fix
     vtime' accounting (for x86, this was already mostly correct but not
     entirely; for ARM, MIPS and RISC-V it wasn't)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Use ERR_PTR_USR() to return -EFAULT as a __user pointer
  KVM: x86: Report deprecated x87 features in supported CPUID
  KVM: arm64: Workaround Cortex-A510's single-step and PAC trap errata
  KVM: arm64: Stop handle_exit() from handling HVC twice when an SError occurs
  KVM: arm64: Avoid consuming a stale esr value when SError occur
  RISC-V: KVM: Fix SBI implementation version
  RISC-V: KVM: make CY, TM, and IR counters accessible in VU mode
  kvm/riscv: rework guest entry logic
  kvm/arm64: rework guest entry logic
  kvm/x86: rework guest entry logic
  kvm/mips: rework guest entry logic
  kvm: add guest_state_{enter,exit}_irqoff()
  KVM: x86: Move delivery of non-APICv interrupt into vendor code
  kvm: Move KVM_GET_XSAVE2 IOCTL definition at the end of kvm.h

8 files changed, 54 insertions, 71 deletions

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 631d5040b31e..d39e0de06be2 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -82,7 +82,7 @@ KVM_X86_OP_NULL(guest_apic_has_interrupt)
 KVM_X86_OP(load_eoi_exitmap)
 KVM_X86_OP(set_virtual_apic_mode)
 KVM_X86_OP_NULL(set_apic_access_page_addr)
-KVM_X86_OP(deliver_posted_interrupt)
+KVM_X86_OP(deliver_interrupt)
 KVM_X86_OP_NULL(sync_pir_to_irr)
 KVM_X86_OP(set_tss_addr)
 KVM_X86_OP(set_identity_map_addr)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6e7c545bc7ee..6dcccb304775 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1410,7 +1410,8 @@ struct kvm_x86_ops {
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
-	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode,
+				  int trig_mode, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 28be02adc669..494d4d351859 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -554,12 +554,13 @@ void kvm_set_cpu_caps(void)
 	);
 
 	kvm_cpu_cap_mask(CPUID_7_0_EBX,
-		F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
-		F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
-		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
-		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
-		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/
-	);
+		F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) |
+		F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) |
+		F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) |
+		F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) |
+		F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) |
+		F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) |
+		F(AVX512VL));
 
 	kvm_cpu_cap_mask(CPUID_7_ECX,
 		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4662469240bc..d7e6fde82d25 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1096,14 +1096,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 						       apic->regs + APIC_TMR);
 		}
 
-		if (static_call(kvm_x86_deliver_posted_interrupt)(vcpu, vector)) {
-			kvm_lapic_set_irr(vector, apic);
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
-			kvm_vcpu_kick(vcpu);
-		} else {
-			trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode,
-						   trig_mode, vector);
-		}
+		static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode,
+						       trig_mode, vector);
 		break;
 
 	case APIC_DM_REMRD:
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 6d97629655e3..a290efb272ad 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3291,6 +3291,21 @@ static void svm_set_irq(struct kvm_vcpu *vcpu)
 		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
 }
 
+static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+				  int trig_mode, int vector)
+{
+	struct kvm_vcpu *vcpu = apic->vcpu;
+
+	if (svm_deliver_avic_intr(vcpu, vector)) {
+		kvm_lapic_set_irr(vector, apic);
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
+	} else {
+		trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode,
+					   trig_mode, vector);
+	}
+}
+
 static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3615,7 +3630,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	unsigned long vmcb_pa = svm->current_vmcb->pa;
 
-	kvm_guest_enter_irqoff();
+	guest_state_enter_irqoff();
 
 	if (sev_es_guest(vcpu->kvm)) {
 		__svm_sev_es_vcpu_run(vmcb_pa);
@@ -3635,7 +3650,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 		vmload(__sme_page_pa(sd->save_area));
 	}
 
-	kvm_guest_exit_irqoff();
+	guest_state_exit_irqoff();
 }
 
 static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
@@ -4545,7 +4560,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.pmu_ops = &amd_pmu_ops,
 	.nested_ops = &svm_nested_ops,
 
-	.deliver_posted_interrupt = svm_deliver_avic_intr,
+	.deliver_interrupt = svm_deliver_interrupt,
 	.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
 	.update_pi_irte = svm_update_pi_irte,
 	.setup_mce = svm_setup_mce,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index aca3ae2a02f3..6c27bd0c89e1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4041,6 +4041,21 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	return 0;
 }
 
+static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+				  int trig_mode, int vector)
+{
+	struct kvm_vcpu *vcpu = apic->vcpu;
+
+	if (vmx_deliver_posted_interrupt(vcpu, vector)) {
+		kvm_lapic_set_irr(vector, apic);
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
+	} else {
+		trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode,
+					   trig_mode, vector);
+	}
+}
+
 /*
  * Set up the vmcs's constant host-state fields, i.e., host-state fields that
  * will not change in the lifetime of the guest.
@@ -6754,7 +6769,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 					struct vcpu_vmx *vmx)
 {
-	kvm_guest_enter_irqoff();
+	guest_state_enter_irqoff();
 
 	/* L1D Flush includes CPU buffer clear to mitigate MDS */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
@@ -6770,7 +6785,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.cr2 = native_read_cr2();
 
-	kvm_guest_exit_irqoff();
+	guest_state_exit_irqoff();
 }
 
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -7768,7 +7783,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hwapic_isr_update = vmx_hwapic_isr_update,
 	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
 	.sync_pir_to_irr = vmx_sync_pir_to_irr,
-	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+	.deliver_interrupt = vmx_deliver_interrupt,
 	.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
 
 	.set_tss_addr = vmx_set_tss_addr,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 74b53a16f38a..7131d735b1ef 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,6 +90,8 @@
 u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
 EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);
 
+#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
+
 #define emul_to_vcpu(ctxt) \
 	((struct kvm_vcpu *)(ctxt)->vcpu)
 
@@ -4340,7 +4342,7 @@ static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr)
 	void __user *uaddr = (void __user*)(unsigned long)attr->addr;
 
 	if ((u64)(unsigned long)uaddr != attr->addr)
-		return ERR_PTR(-EFAULT);
+		return ERR_PTR_USR(-EFAULT);
 	return uaddr;
 }
 
@@ -10041,6 +10043,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	guest_timing_enter_irqoff();
+
 	for (;;) {
 		/*
 		 * Assert that vCPU vs. VM APICv state is consistent.  An APICv
@@ -10125,7 +10129,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * of accounting via context tracking, but the loss of accuracy is
 	 * acceptable for all known use cases.
 	 */
-	vtime_account_guest_exit();
+	guest_timing_exit_irqoff();
 
 	if (lapic_in_kernel(vcpu)) {
 		s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
@@ -11639,8 +11643,6 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
-
 /**
  * __x86_set_memory_region: Setup KVM internal memory slot
  *
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 635b75f9e145..767ec7f99516 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -10,51 +10,6 @@
 
 void kvm_spurious_fault(void);
 
-static __always_inline void kvm_guest_enter_irqoff(void)
-{
-	/*
-	 * VMENTER enables interrupts (host state), but the kernel state is
-	 * interrupts disabled when this is invoked. Also tell RCU about
-	 * it. This is the same logic as for exit_to_user_mode().
-	 *
-	 * This ensures that e.g. latency analysis on the host observes
-	 * guest mode as interrupt enabled.
-	 *
-	 * guest_enter_irqoff() informs context tracking about the
-	 * transition to guest mode and if enabled adjusts RCU state
-	 * accordingly.
-	 */
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
-	instrumentation_end();
-
-	guest_enter_irqoff();
-	lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-static __always_inline void kvm_guest_exit_irqoff(void)
-{
-	/*
-	 * VMEXIT disables interrupts (host state), but tracing and lockdep
-	 * have them in state 'on' as recorded before entering guest mode.
-	 * Same as enter_from_user_mode().
-	 *
-	 * context_tracking_guest_exit() restores host context and reinstates
-	 * RCU if enabled and required.
-	 *
-	 * This needs to be done immediately after VM-Exit, before any code
-	 * that might contain tracepoints or call out to the greater world,
-	 * e.g. before x86_spec_ctrl_restore_host().
-	 */
-	lockdep_hardirqs_off(CALLER_ADDR0);
-	context_tracking_guest_exit();
-
-	instrumentation_begin();
-	trace_hardirqs_off_finish();
-	instrumentation_end();
-}
-
 #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check)		\
 ({									\
 	bool failed = (consistency_check);				\