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

Documentation/arm64/silicon-errata.rst

@@ -100,6 +100,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2051678        | ARM64_ERRATUM_2051678       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2077057        | ARM64_ERRATUM_2077057       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2054223        | ARM64_ERRATUM_2054223       |

arch/arm64/Kconfig

@@ -680,6 +680,22 @@ config ARM64_ERRATUM_2051678
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2077057
+	bool "Cortex-A510: 2077057: workaround software-step corrupting SPSR_EL2"
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2077057.
+	  Affected Cortex-A510 may corrupt SPSR_EL2 when the a step exception is
+	  expected, but a Pointer Authentication trap is taken instead. The
+	  erratum causes SPSR_EL1 to be copied to SPSR_EL2, which could allow
+	  EL1 to cause a return to EL2 with a guest controlled ELR_EL2.
+
+	  This can only happen when EL2 is stepping EL1.
+
+	  When these conditions occur, the SPSR_EL2 value is unchanged from the
+	  previous guest entry, and can be restored from the in-memory copy.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_2119858
 	bool "Cortex-A710/X2: 2119858: workaround TRBE overwriting trace data in FILL mode"
 	default y

arch/arm64/kernel/cpu_errata.c

@@ -600,6 +600,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2077057
+	{
+		.desc = "ARM erratum 2077057",
+		.capability = ARM64_WORKAROUND_2077057,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2064142
 	{
 		.desc = "ARM erratum 2064142",

arch/arm64/kvm/arm.c

@@ -797,6 +797,24 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
 			xfer_to_guest_mode_work_pending();
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_enter_irqoff();
+	ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+	guest_state_exit_irqoff();
+
+	return ret;
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -881,9 +899,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		guest_enter_irqoff();
+		guest_timing_enter_irqoff();
 
-		ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+		ret = kvm_arm_vcpu_enter_exit(vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -918,26 +936,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
 		/*
-		 * We may have taken a host interrupt in HYP mode (ie
-		 * while executing the guest). This interrupt is still
-		 * pending, as we haven't serviced it yet!
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
 		 *
-		 * We're now back in SVC mode, with interrupts
-		 * disabled.  Enabling the interrupts now will have
-		 * the effect of taking the interrupt again, in SVC
-		 * mode this time.
+		 * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other
+		 * context synchronization event) is necessary to ensure that
+		 * pending interrupts are taken.
 		 */
 		local_irq_enable();
+		isb();
+		local_irq_disable();
+
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
 
-		/*
-		 * We do local_irq_enable() before calling guest_exit() so
-		 * that if a timer interrupt hits while running the guest we
-		 * account that tick as being spent in the guest.  We enable
-		 * preemption after calling guest_exit() so that if we get
-		 * preempted we make sure ticks after that is not counted as
-		 * guest time.
-		 */
-		guest_exit();
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/* Exit types that need handling before we can be preempted */

arch/arm64/kvm/handle_exit.c

@@ -228,6 +228,14 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 {
 	struct kvm_run *run = vcpu->run;
 
+	if (ARM_SERROR_PENDING(exception_index)) {
+		/*
+		 * The SError is handled by handle_exit_early(). If the guest
+		 * survives it will re-execute the original instruction.
+		 */
+		return 1;
+	}
+
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	switch (exception_index) {

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -402,6 +402,24 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
+static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/*
+	 * Check for the conditions of Cortex-A510's #2077057. When these occur
+	 * SPSR_EL2 can't be trusted, but isn't needed either as it is
+	 * unchanged from the value in vcpu_gp_regs(vcpu)->pstate.
+	 * Are we single-stepping the guest, and took a PAC exception from the
+	 * active-not-pending state?
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_2077057)		&&
+	    vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP			&&
+	    *vcpu_cpsr(vcpu) & DBG_SPSR_SS				&&
+	    ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC)
+		write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -413,7 +431,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	 * Save PSTATE early so that we can evaluate the vcpu mode
 	 * early on.
 	 */
-	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+	synchronize_vcpu_pstate(vcpu, exit_code);
 
 	/*
 	 * Check whether we want to repaint the state one way or
@@ -424,7 +442,8 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
-	if (ARM_SERROR_PENDING(*exit_code)) {
+	if (ARM_SERROR_PENDING(*exit_code) &&
+	    ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) {
 		u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
 
 		/*

arch/arm64/tools/cpucaps

@@ -55,9 +55,10 @@ WORKAROUND_1418040
 WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
-WORKAROUND_2064142
-WORKAROUND_2038923
 WORKAROUND_1902691
+WORKAROUND_2038923
+WORKAROUND_2064142
+WORKAROUND_2077057
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_TRBE_WRITE_OUT_OF_RANGE

arch/mips/kvm/mips.c

@@ -414,6 +414,24 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -ENOIOCTLCMD;
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static int noinstr kvm_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_enter_irqoff();
+	ret = kvm_mips_callbacks->vcpu_run(vcpu);
+	guest_state_exit_irqoff();
+
+	return ret;
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	int r = -EINTR;
@@ -434,7 +452,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	lose_fpu(1);
 
 	local_irq_disable();
-	guest_enter_irqoff();
+	guest_timing_enter_irqoff();
 	trace_kvm_enter(vcpu);
 
 	/*
@@ -445,10 +463,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	 */
 	smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 
-	r = kvm_mips_callbacks->vcpu_run(vcpu);
+	r = kvm_mips_vcpu_enter_exit(vcpu);
+
+	/*
+	 * We must ensure that any pending interrupts are taken before
+	 * we exit guest timing so that timer ticks are accounted as
+	 * guest time. Transiently unmask interrupts so that any
+	 * pending interrupts are taken.
+	 *
+	 * TODO: is there a barrier which ensures that pending interrupts are
+	 * recognised? Currently this just hopes that the CPU takes any pending
+	 * interrupts between the enable and disable.
+	 */
+	local_irq_enable();
+	local_irq_disable();
 
 	trace_kvm_out(vcpu);
-	guest_exit_irqoff();
+	guest_timing_exit_irqoff();
 	local_irq_enable();
 
 out:
@@ -1168,7 +1199,7 @@ static void kvm_mips_set_c0_status(void)
 /*
  * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
  */
-int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+static int __kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 cause = vcpu->arch.host_cp0_cause;
@@ -1357,6 +1388,17 @@ int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+int noinstr kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guest_state_exit_irqoff();
+	ret = __kvm_mips_handle_exit(vcpu);
+	guest_state_enter_irqoff();
+
+	return ret;
+}
+
 /* Enable FPU for guest and restore context */
 void kvm_own_fpu(struct kvm_vcpu *vcpu)
 {

arch/riscv/kvm/vcpu.c

@@ -90,6 +90,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *cntx;
+	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 
 	/* Mark this VCPU never ran */
 	vcpu->arch.ran_atleast_once = false;
@@ -106,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SPVP;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	/* By default, make CY, TM, and IR counters accessible in VU mode */
+	reset_csr->scounteren = 0x7;
+
 	/* Setup VCPU timer */
 	kvm_riscv_vcpu_timer_init(vcpu);
 
@@ -699,6 +703,20 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
 	csr_write(CSR_HVIP, csr->hvip);
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	guest_state_enter_irqoff();
+	__kvm_riscv_switch_to(&vcpu->arch);
+	guest_state_exit_irqoff();
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -790,9 +808,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		guest_enter_irqoff();
+		guest_timing_enter_irqoff();
 
-		__kvm_riscv_switch_to(&vcpu->arch);
+		kvm_riscv_vcpu_enter_exit(vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -812,25 +830,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_riscv_vcpu_sync_interrupts(vcpu);
 
 		/*
-		 * We may have taken a host interrupt in VS/VU-mode (i.e.
-		 * while executing the guest). This interrupt is still
-		 * pending, as we haven't serviced it yet!
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
 		 *
-		 * We're now back in HS-mode with interrupts disabled
-		 * so enabling the interrupts now will have the effect
-		 * of taking the interrupt again, in HS-mode this time.
+		 * There's no barrier which ensures that pending interrupts are
+		 * recognised, so we just hope that the CPU takes any pending
+		 * interrupts between the enable and disable.
 		 */
 		local_irq_enable();
+		local_irq_disable();
 
-		/*
-		 * We do local_irq_enable() before calling guest_exit() so
-		 * that if a timer interrupt hits while running the guest
-		 * we account that tick as being spent in the guest. We
-		 * enable preemption after calling guest_exit() so that if
-		 * we get preempted we make sure ticks after that is not
-		 * counted as guest time.
-		 */
-		guest_exit();
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
 
 		preempt_enable();
 

arch/riscv/kvm/vcpu_sbi_base.c

@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/version.h>
 #include <asm/csr.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_timer.h>
@@ -32,7 +33,7 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		*out_val = KVM_SBI_IMPID;
 		break;
 	case SBI_EXT_BASE_GET_IMP_VERSION:
-		*out_val = 0;
+		*out_val = LINUX_VERSION_CODE;
 		break;
 	case SBI_EXT_BASE_PROBE_EXT:
 		if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START &&

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)

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);

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) |

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:

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,

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,

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
  *

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);				\

include/linux/kvm_host.h

@@ -29,7 +29,9 @@
 #include <linux/refcount.h>
 #include <linux/nospec.h>
 #include <linux/notifier.h>
+#include <linux/ftrace.h>
 #include <linux/hashtable.h>
+#include <linux/instrumentation.h>
 #include <linux/interval_tree.h>
 #include <linux/rbtree.h>
 #include <linux/xarray.h>
@@ -368,8 +370,11 @@ struct kvm_vcpu {
 	u64 last_used_slot_gen;
 };
 
-/* must be called with irqs disabled */
-static __always_inline void guest_enter_irqoff(void)
+/*
+ * Start accounting time towards a guest.
+ * Must be called before entering guest context.
+ */
+static __always_inline void guest_timing_enter_irqoff(void)
 {
 	/*
 	 * This is running in ioctl context so its safe to assume that it's the
@@ -378,7 +383,18 @@ static __always_inline void guest_enter_irqoff(void)
 	instrumentation_begin();
 	vtime_account_guest_enter();
 	instrumentation_end();
+}
 
+/*
+ * Enter guest context and enter an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_enter_irqoff(void)
+{
 	/*
 	 * KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
@@ -394,16 +410,79 @@ static __always_inline void guest_enter_irqoff(void)
 	}
 }
 
-static __always_inline void guest_exit_irqoff(void)
+/*
+ * Deprecated. Architectures should move to guest_timing_enter_irqoff() and
+ * guest_state_enter_irqoff().
+ */
+static __always_inline void guest_enter_irqoff(void)
+{
+	guest_timing_enter_irqoff();
+	guest_context_enter_irqoff();
+}
+
+/**
+ * guest_state_enter_irqoff - Fixup state when entering a guest
+ *
+ * Entry to a guest will enable interrupts, but the kernel state is interrupts
+ * disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code before entering a guest.
+ * Must be called with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_enter_irqoff() before this.
+ *
+ * Note: this is analogous to exit_to_user_mode().
+ */
+static __always_inline void guest_state_enter_irqoff(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instrumentation_end();
+
+	guest_context_enter_irqoff();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/*
+ * Exit guest context and exit an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_exit_irqoff(void)
 {
 	context_tracking_guest_exit();
+}
 
+/*
+ * Stop accounting time towards a guest.
+ * Must be called after exiting guest context.
+ */
+static __always_inline void guest_timing_exit_irqoff(void)
+{
 	instrumentation_begin();
 	/* Flush the guest cputime we spent on the guest */
 	vtime_account_guest_exit();
 	instrumentation_end();
 }
 
+/*
+ * Deprecated. Architectures should move to guest_state_exit_irqoff() and
+ * guest_timing_exit_irqoff().
+ */
+static __always_inline void guest_exit_irqoff(void)
+{
+	guest_context_exit_irqoff();
+	guest_timing_exit_irqoff();
+}
+
 static inline void guest_exit(void)
 {
 	unsigned long flags;
@@ -413,6 +492,33 @@ static inline void guest_exit(void)
 	local_irq_restore(flags);
 }
 
+/**
+ * guest_state_exit_irqoff - Establish state when returning from guest mode
+ *
+ * Entry from a guest disables interrupts, but guest mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific code after exiting a guest.
+ * Must be invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_exit_irqoff() after this.
+ *
+ * Note: this is analogous to enter_from_user_mode().
+ */
+static __always_inline void guest_state_exit_irqoff(void)
+{
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	guest_context_exit_irqoff();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
 {
 	/*

include/uapi/linux/kvm.h

@@ -1624,9 +1624,6 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
-
 struct kvm_s390_pv_sec_parm {
 	__u64 origin;
 	__u64 length;
@@ -2048,4 +2045,7 @@ struct kvm_stats_desc {
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
 
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
+
 #endif /* __LINUX_KVM_H */