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

Pull kvm fixes from Paolo Bonzini:
 "The main and larger change here is a workaround for AMD's lack of
  cache coherency for encrypted-memory guests.

  I have another patch pending, but it's waiting for review from the
  architecture maintainers.

  RISC-V:

   - Remove 's' & 'u' as valid ISA extension

   - Do not allow disabling the base extensions 'i'/'m'/'a'/'c'

  x86:

   - Fix NMI watchdog in guests on AMD

   - Fix for SEV cache incoherency issues

   - Don't re-acquire SRCU lock in complete_emulated_io()

   - Avoid NULL pointer deref if VM creation fails

   - Fix race conditions between APICv disabling and vCPU creation

   - Bugfixes for disabling of APICv

   - Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume

  selftests:

   - Do not use bitfields larger than 32-bits, they differ between GCC
     and clang"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: selftests: introduce and use more page size-related constants
  kvm: selftests: do not use bitfields larger than 32-bits for PTEs
  KVM: SEV: add cache flush to solve SEV cache incoherency issues
  KVM: SVM: Flush when freeing encrypted pages even on SME_COHERENT CPUs
  KVM: SVM: Simplify and harden helper to flush SEV guest page(s)
  KVM: selftests: Silence compiler warning in the kvm_page_table_test
  KVM: x86/pmu: Update AMD PMC sample period to fix guest NMI-watchdog
  x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume
  KVM: SPDX style and spelling fixes
  KVM: x86: Skip KVM_GUESTDBG_BLOCKIRQ APICv update if APICv is disabled
  KVM: x86: Pend KVM_REQ_APICV_UPDATE during vCPU creation to fix a race
  KVM: nVMX: Defer APICv updates while L2 is active until L1 is active
  KVM: x86: Tag APICv DISABLE inhibit, not ABSENT, if APICv is disabled
  KVM: Initialize debugfs_dentry when a VM is created to avoid NULL deref
  KVM: Add helpers to wrap vcpu->srcu_idx and yell if it's abused
  KVM: RISC-V: Use kvm_vcpu.srcu_idx, drop RISC-V's unnecessary copy
  KVM: x86: Don't re-acquire SRCU lock in complete_emulated_io()
  RISC-V: KVM: Restrict the extensions that can be disabled
  RISC-V: KVM: Remove 's' & 'u' as valid ISA extension

23 files changed, 157 insertions, 110 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index e4ce2a35483f..42851c32ff3b 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -168,9 +168,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			return -EINVAL;
 		/* Read the entry from guest memory */
 		addr = base + (index * sizeof(rpte));
-		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+
+		kvm_vcpu_srcu_read_lock(vcpu);
 		ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		if (ret) {
 			if (pte_ret_p)
 				*pte_ret_p = addr;
@@ -246,9 +247,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	/* Read the table to find the root of the radix tree */
 	ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
-	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
-	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (ret)
 		return ret;
 
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 9d373f8963ee..c943a051c6e7 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -306,10 +306,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	/* copy parameters in */
 	hv_ptr = kvmppc_get_gpr(vcpu, 4);
 	regs_ptr = kvmppc_get_gpr(vcpu, 5);
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
 					      hv_ptr, regs_ptr);
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (err)
 		return H_PARAMETER;
 
@@ -410,10 +410,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 		byteswap_hv_regs(&l2_hv);
 		byteswap_pt_regs(&l2_regs);
 	}
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
 					       hv_ptr, regs_ptr);
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (err)
 		return H_AUTHORITY;
 
@@ -600,16 +600,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu)
 			goto not_found;
 
 		/* Write what was loaded into our buffer back to the L1 guest */
-		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 		rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n);
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		if (rc)
 			goto not_found;
 	} else {
 		/* Load the data to be stored from the L1 guest into our buf */
-		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 		rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n);
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		if (rc)
 			goto not_found;
 
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 0f847f1e5ddd..6808bda0dbc1 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -229,9 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 */
 	args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM;
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args));
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (rc)
 		goto fail;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 875c30c12db0..533c4232e5ab 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -425,9 +425,9 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		return EMULATE_DONE;
 	}
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size);
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	if (rc)
 		return EMULATE_DO_MMIO;
 
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 78da839657e5..cd4bbcecb0fb 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -193,9 +193,6 @@ struct kvm_vcpu_arch {
 
 	/* Don't run the VCPU (blocked) */
 	bool pause;
-
-	/* SRCU lock index for in-kernel run loop */
-	int srcu_idx;
 };
 
 static inline void kvm_arch_hardware_unsetup(void) {}
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 6785aef4cbd4..7461f964d20a 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -38,14 +38,16 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
 		       sizeof(kvm_vcpu_stats_desc),
 };
 
-#define KVM_RISCV_ISA_ALLOWED	(riscv_isa_extension_mask(a) | \
-				 riscv_isa_extension_mask(c) | \
-				 riscv_isa_extension_mask(d) | \
-				 riscv_isa_extension_mask(f) | \
-				 riscv_isa_extension_mask(i) | \
-				 riscv_isa_extension_mask(m) | \
-				 riscv_isa_extension_mask(s) | \
-				 riscv_isa_extension_mask(u))
+#define KVM_RISCV_ISA_DISABLE_ALLOWED	(riscv_isa_extension_mask(d) | \
+					riscv_isa_extension_mask(f))
+
+#define KVM_RISCV_ISA_DISABLE_NOT_ALLOWED	(riscv_isa_extension_mask(a) | \
+						riscv_isa_extension_mask(c) | \
+						riscv_isa_extension_mask(i) | \
+						riscv_isa_extension_mask(m))
+
+#define KVM_RISCV_ISA_ALLOWED (KVM_RISCV_ISA_DISABLE_ALLOWED | \
+			       KVM_RISCV_ISA_DISABLE_NOT_ALLOWED)
 
 static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 {
@@ -219,7 +221,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
 	switch (reg_num) {
 	case KVM_REG_RISCV_CONFIG_REG(isa):
 		if (!vcpu->arch.ran_atleast_once) {
-			vcpu->arch.isa = reg_val;
+			/* Ignore the disable request for these extensions */
+			vcpu->arch.isa = reg_val | KVM_RISCV_ISA_DISABLE_NOT_ALLOWED;
 			vcpu->arch.isa &= riscv_isa_extension_base(NULL);
 			vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED;
 			kvm_riscv_vcpu_fp_reset(vcpu);
@@ -724,13 +727,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	/* Mark this VCPU ran at least once */
 	vcpu->arch.ran_atleast_once = true;
 
-	vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	/* Process MMIO value returned from user-space */
 	if (run->exit_reason == KVM_EXIT_MMIO) {
 		ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run);
 		if (ret) {
-			srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+			kvm_vcpu_srcu_read_unlock(vcpu);
 			return ret;
 		}
 	}
@@ -739,13 +742,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	if (run->exit_reason == KVM_EXIT_RISCV_SBI) {
 		ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run);
 		if (ret) {
-			srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+			kvm_vcpu_srcu_read_unlock(vcpu);
 			return ret;
 		}
 	}
 
 	if (run->immediate_exit) {
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		return -EINTR;
 	}
 
@@ -784,7 +787,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		vcpu->mode = IN_GUEST_MODE;
 
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		smp_mb__after_srcu_read_unlock();
 
 		/*
@@ -802,7 +805,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
 			preempt_enable();
-			vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+			kvm_vcpu_srcu_read_lock(vcpu);
 			continue;
 		}
 
@@ -846,7 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 		preempt_enable();
 
-		vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 
 		ret = kvm_riscv_vcpu_exit(vcpu, run, &trap);
 	}
@@ -855,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	vcpu_put(vcpu);
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 
 	return ret;
 }
diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c
index aa8af129e4bb..a72c15d4b42a 100644
--- a/arch/riscv/kvm/vcpu_exit.c
+++ b/arch/riscv/kvm/vcpu_exit.c
@@ -456,9 +456,9 @@ static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run,
 void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_arch_vcpu_runnable(vcpu)) {
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		kvm_vcpu_halt(vcpu);
-		vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 		kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 	}
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9b30beac904d..af96dc0549a4 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1334,11 +1334,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 	hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL);
 	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
 no_timer:
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	kvm_vcpu_halt(vcpu);
 	vcpu->valid_wakeup = false;
 	__unset_cpu_idle(vcpu);
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	hrtimer_cancel(&vcpu->arch.ckc_timer);
 	return 0;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 156d1c25a3c1..da3dabda1a12 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4237,14 +4237,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	 * We try to hold kvm->srcu during most of vcpu_run (except when run-
 	 * ning the guest), so that memslots (and other stuff) are protected
 	 */
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	do {
 		rc = vcpu_pre_run(vcpu);
 		if (rc)
 			break;
 
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		/*
 		 * As PF_VCPU will be used in fault handler, between
 		 * guest_enter and guest_exit should be no uaccess.
@@ -4281,12 +4281,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		__enable_cpu_timer_accounting(vcpu);
 		guest_exit_irqoff();
 		local_irq_enable();
-		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 
 		rc = vcpu_post_run(vcpu, exit_reason);
 	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 	return rc;
 }
 
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index acda4b6fc851..dada78b92691 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1091,7 +1091,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 
 	handle_last_fault(vcpu, vsie_page);
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 
 	/* save current guest state of bp isolation override */
 	guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST);
@@ -1133,7 +1133,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	if (!guest_bp_isolation)
 		clear_thread_flag(TIF_ISOLATE_BP_GUEST);
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	if (rc == -EINTR) {
 		VCPU_EVENT(vcpu, 3, "%s", "machine check");
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 3c368b639c04..1a6d7e3f6c32 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -118,6 +118,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_register_region)
 KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
 KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from)
 KVM_X86_OP_OPTIONAL(vm_move_enc_context_from)
+KVM_X86_OP_OPTIONAL(guest_memory_reclaimed)
 KVM_X86_OP(get_msr_feature)
 KVM_X86_OP(can_emulate_instruction)
 KVM_X86_OP(apic_init_signal_blocked)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0c0f0e1f754..4ff36610af6a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1484,6 +1484,7 @@ struct kvm_x86_ops {
 	int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
 	int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
+	void (*guest_memory_reclaimed)(struct kvm *kvm);
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a22deb58f86d..8b1c45c9cda8 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
 /*
  * No need for any "IO delay" on KVM
  */
@@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
+	u64 val = 0;
+
 	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
 	return 0;
 }
 
 static void kvm_resume(void)
 {
 	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
 }
 
 static struct syscore_ops kvm_syscore_ops = {
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 9e66fba1d6a3..22992b049d38 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -138,6 +138,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
 	return sample_period;
 }
 
+static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event || pmc->is_paused)
+		return;
+
+	perf_event_period(pmc->perf_event,
+			  get_sample_period(pmc, pmc->counter));
+}
+
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
 void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
 void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 24eb935b6f85..b14860863c39 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -257,6 +257,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
 		pmc->counter += data - pmc_read_counter(pmc);
+		pmc_update_sample_period(pmc);
 		return 0;
 	}
 	/* MSR_EVNTSELn */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 537aaddc852f..0ad70c12c7c3 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2226,51 +2226,47 @@ int sev_cpu_init(struct svm_cpu_data *sd)
  * Pages used by hardware to hold guest encrypted state must be flushed before
  * returning them to the system.
  */
-static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
-				   unsigned long len)
+static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 {
+	int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+
 	/*
-	 * If hardware enforced cache coherency for encrypted mappings of the
-	 * same physical page is supported, nothing to do.
+	 * Note!  The address must be a kernel address, as regular page walk
+	 * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user
+	 * address is non-deterministic and unsafe.  This function deliberately
+	 * takes a pointer to deter passing in a user address.
 	 */
-	if (boot_cpu_has(X86_FEATURE_SME_COHERENT))
-		return;
+	unsigned long addr = (unsigned long)va;
 
 	/*
-	 * If the VM Page Flush MSR is supported, use it to flush the page
-	 * (using the page virtual address and the guest ASID).
+	 * If CPU enforced cache coherency for encrypted mappings of the
+	 * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache
+	 * flush is still needed in order to work properly with DMA devices.
 	 */
-	if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) {
-		struct kvm_sev_info *sev;
-		unsigned long va_start;
-		u64 start, stop;
-
-		/* Align start and stop to page boundaries. */
-		va_start = (unsigned long)va;
-		start = (u64)va_start & PAGE_MASK;
-		stop = PAGE_ALIGN((u64)va_start + len);
-
-		if (start < stop) {
-			sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+	if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) {
+		clflush_cache_range(va, PAGE_SIZE);
+		return;
+	}
 
-			while (start < stop) {
-				wrmsrl(MSR_AMD64_VM_PAGE_FLUSH,
-				       start | sev->asid);
+	/*
+	 * VM Page Flush takes a host virtual address and a guest ASID.  Fall
+	 * back to WBINVD if this faults so as not to make any problems worse
+	 * by leaving stale encrypted data in the cache.
+	 */
+	if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
+		goto do_wbinvd;
 
-				start += PAGE_SIZE;
-			}
+	return;
 
-			return;
-		}
+do_wbinvd:
+	wbinvd_on_all_cpus();
+}
 
-		WARN(1, "Address overflow, using WBINVD\n");
-	}
+void sev_guest_memory_reclaimed(struct kvm *kvm)
+{
+	if (!sev_guest(kvm))
+		return;
 
-	/*
-	 * Hardware should always have one of the above features,
-	 * but if not, use WBINVD and issue a warning.
-	 */
-	WARN_ONCE(1, "Using WBINVD to flush guest memory\n");
 	wbinvd_on_all_cpus();
 }
 
@@ -2284,7 +2280,8 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	svm = to_svm(vcpu);
 
 	if (vcpu->arch.guest_state_protected)
-		sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE);
+		sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa);
+
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
 	if (svm->sev_es.ghcb_sa_free)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index bd4c64b362d2..7e45d03cd018 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4620,6 +4620,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.mem_enc_ioctl = sev_mem_enc_ioctl,
 	.mem_enc_register_region = sev_mem_enc_register_region,
 	.mem_enc_unregister_region = sev_mem_enc_unregister_region,
+	.guest_memory_reclaimed = sev_guest_memory_reclaimed,
 
 	.vm_copy_enc_context_from = sev_vm_copy_enc_context_from,
 	.vm_move_enc_context_from = sev_vm_move_enc_context_from,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f77a7d2d39dd..f76deff71002 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -609,6 +609,8 @@ int sev_mem_enc_unregister_region(struct kvm *kvm,
 				  struct kvm_enc_region *range);
 int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd);
 int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd);
+void sev_guest_memory_reclaimed(struct kvm *kvm);
+
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 void __init sev_set_cpu_caps(void);
 void __init sev_hardware_setup(void);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f18744f7ff82..856c87563883 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4618,6 +4618,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 	}
 
+	if (vmx->nested.update_vmcs01_apicv_status) {
+		vmx->nested.update_vmcs01_apicv_status = false;
+		kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
+	}
+
 	if ((vm_exit_reason != -1) &&
 	    (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)))
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index bc3f8512bb64..b82b6709d7a8 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
 				data = (s64)(s32)data;
 			pmc->counter += data - pmc_read_counter(pmc);
-			if (pmc->perf_event && !pmc->is_paused)
-				perf_event_period(pmc->perf_event,
-						  get_sample_period(pmc, data));
+			pmc_update_sample_period(pmc);
 			return 0;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
 			pmc->counter += data - pmc_read_counter(pmc);
-			if (pmc->perf_event && !pmc->is_paused)
-				perf_event_period(pmc->perf_event,
-						  get_sample_period(pmc, data));
+			pmc_update_sample_period(pmc);
 			return 0;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04d170c4b61e..d58b763df855 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4174,6 +4174,11 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (is_guest_mode(vcpu)) {
+		vmx->nested.update_vmcs01_apicv_status = true;
+		return;
+	}
+
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
 	if (cpu_has_secondary_exec_ctrls()) {
 		if (kvm_vcpu_apicv_active(vcpu))
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 9c6bfcd84008..b98c7e96697a 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -183,6 +183,7 @@ struct nested_vmx {
 	bool change_vmcs01_virtual_apic_mode;
 	bool reload_vmcs01_apic_access_page;
 	bool update_vmcs01_cpu_dirty_logging;
+	bool update_vmcs01_apicv_status;
 
 	/*
 	 * Enlightened VMCS has been enabled. It does not mean that L1 has to
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 547ba00ef64f..a6ab19afc638 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9111,7 +9111,7 @@ static void kvm_apicv_init(struct kvm *kvm)
 
 	if (!enable_apicv)
 		set_or_clear_apicv_inhibit(inhibits,
-					   APICV_INHIBIT_REASON_ABSENT, true);
+					   APICV_INHIBIT_REASON_DISABLE, true);
 }
 
 static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
@@ -9889,6 +9889,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
 }
 
+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+	static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm);
+}
+
 static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	if (!lapic_in_kernel(vcpu))
@@ -10097,7 +10102,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	/* Store vcpu->apicv_active before vcpu->mode.  */
 	smp_store_release(&vcpu->mode, IN_GUEST_MODE);
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 
 	/*
 	 * 1) We should set ->mode before checking ->requests.  Please see
@@ -10128,7 +10133,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
-		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 		r = 1;
 		goto cancel_injection;
 	}
@@ -10254,7 +10259,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	preempt_enable();
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 
 	/*
 	 * Profile KVM exit RIPs:
@@ -10284,7 +10289,7 @@ out:
 }
 
 /* Called within kvm->srcu read side.  */
-static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
+static inline int vcpu_block(struct kvm_vcpu *vcpu)
 {
 	bool hv_timer;
 
@@ -10300,12 +10305,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 		if (hv_timer)
 			kvm_lapic_switch_to_sw_timer(vcpu);
 
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
 			kvm_vcpu_halt(vcpu);
 		else
 			kvm_vcpu_block(vcpu);
-		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 
 		if (hv_timer)
 			kvm_lapic_switch_to_hv_timer(vcpu);
@@ -10347,7 +10352,6 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 static int vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
-	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->arch.l1tf_flush_l1d = true;
 
@@ -10355,7 +10359,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
 		} else {
-			r = vcpu_block(kvm, vcpu);
+			r = vcpu_block(vcpu);
 		}
 
 		if (r <= 0)
@@ -10374,9 +10378,9 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		}
 
 		if (__xfer_to_guest_mode_work_pending()) {
-			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+			kvm_vcpu_srcu_read_unlock(vcpu);
 			r = xfer_to_guest_mode_handle_work(vcpu);
-			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+			kvm_vcpu_srcu_read_lock(vcpu);
 			if (r)
 				return r;
 		}
@@ -10387,12 +10391,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 
 static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
 {
-	int r;
-
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-	return r;
+	return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 }
 
 static int complete_emulated_pio(struct kvm_vcpu *vcpu)
@@ -10484,7 +10483,6 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
-	struct kvm *kvm = vcpu->kvm;
 	int r;
 
 	vcpu_load(vcpu);
@@ -10492,7 +10490,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	kvm_run->flags = 0;
 	kvm_load_guest_fpu(vcpu);
 
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_vcpu_srcu_read_lock(vcpu);
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
 		if (kvm_run->immediate_exit) {
 			r = -EINTR;
@@ -10504,9 +10502,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));
 
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		kvm_vcpu_block(vcpu);
-		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+		kvm_vcpu_srcu_read_lock(vcpu);
 
 		if (kvm_apic_accept_events(vcpu) < 0) {
 			r = 0;
@@ -10567,7 +10565,7 @@ out:
 	if (kvm_run->kvm_valid_regs)
 		store_regs(vcpu);
 	post_kvm_run_save(vcpu);
-	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+	kvm_vcpu_srcu_read_unlock(vcpu);
 
 	kvm_sigset_deactivate(vcpu);
 	vcpu_put(vcpu);
@@ -10985,6 +10983,9 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
+	if (!enable_apicv)
+		return;
+
 	down_write(&kvm->arch.apicv_update_lock);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -11196,8 +11197,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
-		if (kvm_apicv_activated(vcpu->kvm))
+
+		/*
+		 * Defer evaluating inhibits until the vCPU is first run, as
+		 * this vCPU will not get notified of any changes until this
+		 * vCPU is visible to other vCPUs (marked online and added to
+		 * the set of vCPUs).  Opportunistically mark APICv active as
+		 * VMX in particularly is highly unlikely to have inhibits.
+		 * Ignore the current per-VM APICv state so that vCPU creation
+		 * is guaranteed to run with a deterministic value, the request
+		 * will ensure the vCPU gets the correct state before VM-Entry.
+		 */
+		if (enable_apicv) {
 			vcpu->arch.apicv_active = true;
+			kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
+		}
 	} else
 		static_branch_inc(&kvm_has_noapic_vcpu);