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

36 files changed, 316 insertions, 252 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);
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3f9b22c4983a..34eed5f85ed6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -315,7 +315,10 @@ struct kvm_vcpu {
 	int cpu;
 	int vcpu_id; /* id given by userspace at creation */
 	int vcpu_idx; /* index in kvm->vcpus array */
-	int srcu_idx;
+	int ____srcu_idx; /* Don't use this directly.  You've been warned. */
+#ifdef CONFIG_PROVE_RCU
+	int srcu_depth;
+#endif
 	int mode;
 	u64 requests;
 	unsigned long guest_debug;
@@ -840,6 +843,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm)
 	unlikely(__ret);					\
 })
 
+static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PROVE_RCU
+	WARN_ONCE(vcpu->srcu_depth++,
+		  "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1);
+#endif
+	vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+}
+
+static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu)
+{
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx);
+
+#ifdef CONFIG_PROVE_RCU
+	WARN_ONCE(--vcpu->srcu_depth,
+		  "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth);
+#endif
+}
+
 static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
 {
 	return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
@@ -2197,6 +2219,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 					    unsigned long start, unsigned long end);
 
+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
+
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
 int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
 #else
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 37db341d4cc5..d0d51adec76e 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -60,6 +60,23 @@
 /* CPUID.0x8000_0001.EDX */
 #define CPUID_GBPAGES		(1ul << 26)
 
+/* Page table bitfield declarations */
+#define PTE_PRESENT_MASK        BIT_ULL(0)
+#define PTE_WRITABLE_MASK       BIT_ULL(1)
+#define PTE_USER_MASK           BIT_ULL(2)
+#define PTE_ACCESSED_MASK       BIT_ULL(5)
+#define PTE_DIRTY_MASK          BIT_ULL(6)
+#define PTE_LARGE_MASK          BIT_ULL(7)
+#define PTE_GLOBAL_MASK         BIT_ULL(8)
+#define PTE_NX_MASK             BIT_ULL(63)
+
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(1ULL << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
+
+#define PHYSICAL_PAGE_MASK      GENMASK_ULL(51, 12)
+#define PTE_GET_PFN(pte)        (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index ba1fdc3dcf4a..2c4a7563a4f8 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 	else
 		guest_test_phys_mem = p->phys_offset;
 #ifdef __s390x__
-	alignment = max(0x100000, alignment);
+	alignment = max(0x100000UL, alignment);
 #endif
 	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 9f000dfb5594..33ea5e9955d9 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -19,38 +19,6 @@
 
 vm_vaddr_t exception_handlers;
 
-/* Virtual translation table structure declarations */
-struct pageUpperEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t pfn:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageTableEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t dirty:1;
-	uint64_t reserved_07:1;
-	uint64_t global:1;
-	uint64_t ignored_11_09:3;
-	uint64_t pfn:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
 void regs_dump(FILE *stream, struct kvm_regs *regs,
 	       uint8_t indent)
 {
@@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
 	return &page_table[index];
 }
 
-static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
-						    uint64_t pt_pfn,
-						    uint64_t vaddr,
-						    uint64_t paddr,
-						    int level,
-						    enum x86_page_size page_size)
+static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
+				       uint64_t pt_pfn,
+				       uint64_t vaddr,
+				       uint64_t paddr,
+				       int level,
+				       enum x86_page_size page_size)
 {
-	struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
-
-	if (!pte->present) {
-		pte->writable = true;
-		pte->present = true;
-		pte->page_size = (level == page_size);
-		if (pte->page_size)
-			pte->pfn = paddr >> vm->page_shift;
+	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+
+	if (!(*pte & PTE_PRESENT_MASK)) {
+		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
+		if (level == page_size)
+			*pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 		else
-			pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift;
+			*pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
 	} else {
 		/*
 		 * Entry already present.  Assert that the caller doesn't want
@@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
 		TEST_ASSERT(level != page_size,
 			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
 			    page_size, vaddr);
-		TEST_ASSERT(!pte->page_size,
+		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
 			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
 			    level, vaddr);
 	}
@@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		   enum x86_page_size page_size)
 {
 	const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
 		    "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	 */
 	pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
 				      vaddr, paddr, 3, page_size);
-	if (pml4e->page_size)
+	if (*pml4e & PTE_LARGE_MASK)
 		return;
 
-	pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
-	if (pdpe->page_size)
+	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+	if (*pdpe & PTE_LARGE_MASK)
 		return;
 
-	pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
-	if (pde->page_size)
+	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+	if (*pde & PTE_LARGE_MASK)
 		return;
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
-	TEST_ASSERT(!pte->present,
+	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
-	pte->pfn = paddr >> vm->page_shift;
-	pte->writable = true;
-	pte->present = 1;
+	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 }
 
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
 }
 
-static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
+static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
 						       uint64_t vaddr)
 {
 	uint16_t index[4];
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 	struct kvm_cpuid_entry2 *entry;
 	struct kvm_sregs sregs;
 	int max_phy_addr;
-	/* Set the bottom 52 bits. */
-	uint64_t rsvd_mask = 0x000fffffffffffff;
+	uint64_t rsvd_mask = 0;
 
 	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
 	max_phy_addr = entry->eax & 0x000000ff;
-	/* Clear the bottom bits of the reserved mask. */
-	rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr;
+	/* Set the high bits in the reserved mask. */
+	if (max_phy_addr < 52)
+		rsvd_mask = GENMASK_ULL(51, max_phy_addr);
 
 	/*
 	 * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries
@@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 	 */
 	vcpu_sregs_get(vm, vcpuid, &sregs);
 	if ((sregs.efer & EFER_NX) == 0) {
-		rsvd_mask |= (1ull << 63);
+		rsvd_mask |= PTE_NX_MASK;
 	}
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
@@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 	index[3] = (vaddr >> 39) & 0x1ffu;
 
 	pml4e = addr_gpa2hva(vm, vm->pgd);
-	TEST_ASSERT(pml4e[index[3]].present,
+	TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK,
 		"Expected pml4e to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) &
-		(rsvd_mask | (1ull << 7))) == 0,
+	TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0,
 		"Unexpected reserved bits set.");
 
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
-	TEST_ASSERT(pdpe[index[2]].present,
+	pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+	TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK,
 		"Expected pdpe to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT(pdpe[index[2]].page_size == 0,
+	TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK),
 		"Expected pdpe to map a pde not a 1-GByte page.");
-	TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0,
+	TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0,
 		"Unexpected reserved bits set.");
 
-	pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
-	TEST_ASSERT(pde[index[1]].present,
+	pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+	TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK,
 		"Expected pde to be present for gva: 0x%08lx", vaddr);
-	TEST_ASSERT(pde[index[1]].page_size == 0,
+	TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK),
 		"Expected pde to map a pte not a 2-MByte page.");
-	TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0,
+	TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0,
 		"Unexpected reserved bits set.");
 
-	pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
-	TEST_ASSERT(pte[index[0]].present,
+	pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+	TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK,
 		"Expected pte to be present for gva: 0x%08lx", vaddr);
 
 	return &pte[index[0]];
@@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
 
 uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
 {
-	struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
+	uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
 
 	return *(uint64_t *)pte;
 }
@@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
 void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
 			     uint64_t pte)
 {
-	struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid,
-								  vaddr);
+	uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
 
 	*(uint64_t *)new_pte = pte;
 }
 
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
-	struct pageUpperEntry *pml4e, *pml4e_start;
-	struct pageUpperEntry *pdpe, *pdpe_start;
-	struct pageUpperEntry *pde, *pde_start;
-	struct pageTableEntry *pte, *pte_start;
+	uint64_t *pml4e, *pml4e_start;
+	uint64_t *pdpe, *pdpe_start;
+	uint64_t *pde, *pde_start;
+	uint64_t *pte, *pte_start;
 
 	if (!vm->pgd_created)
 		return;
@@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	fprintf(stream, "%*s      index hvaddr         gpaddr         "
 		"addr         w exec dirty\n",
 		indent, "");
-	pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd);
+	pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd);
 	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
 		pml4e = &pml4e_start[n1];
-		if (!pml4e->present)
+		if (!(*pml4e & PTE_PRESENT_MASK))
 			continue;
-		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u "
 			" %u\n",
 			indent, "",
 			pml4e - pml4e_start, pml4e,
-			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn,
-			pml4e->writable, pml4e->execute_disable);
+			addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e),
+			!!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK));
 
-		pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size);
+		pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK);
 		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
 			pdpe = &pdpe_start[n2];
-			if (!pdpe->present)
+			if (!(*pdpe & PTE_PRESENT_MASK))
 				continue;
-			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
+			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10llx "
 				"%u  %u\n",
 				indent, "",
 				pdpe - pdpe_start, pdpe,
 				addr_hva2gpa(vm, pdpe),
-				(uint64_t) pdpe->pfn, pdpe->writable,
-				pdpe->execute_disable);
+				PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK),
+				!!(*pdpe & PTE_NX_MASK));
 
-			pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size);
+			pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK);
 			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
 				pde = &pde_start[n3];
-				if (!pde->present)
+				if (!(*pde & PTE_PRESENT_MASK))
 					continue;
 				fprintf(stream, "%*spde   0x%-3zx %p "
-					"0x%-12lx 0x%-10lx %u  %u\n",
+					"0x%-12lx 0x%-10llx %u  %u\n",
 					indent, "", pde - pde_start, pde,
 					addr_hva2gpa(vm, pde),
-					(uint64_t) pde->pfn, pde->writable,
-					pde->execute_disable);
+					PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK),
+					!!(*pde & PTE_NX_MASK));
 
-				pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size);
+				pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK);
 				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
 					pte = &pte_start[n4];
-					if (!pte->present)
+					if (!(*pte & PTE_PRESENT_MASK))
 						continue;
 					fprintf(stream, "%*spte   0x%-3zx %p "
-						"0x%-12lx 0x%-10lx %u  %u "
+						"0x%-12lx 0x%-10llx %u  %u "
 						"    %u    0x%-10lx\n",
 						indent, "",
 						pte - pte_start, pte,
 						addr_hva2gpa(vm, pte),
-						(uint64_t) pte->pfn,
-						pte->writable,
-						pte->execute_disable,
-						pte->dirty,
+						PTE_GET_PFN(*pte),
+						!!(*pte & PTE_WRITABLE_MASK),
+						!!(*pte & PTE_NX_MASK),
+						!!(*pte & PTE_DIRTY_MASK),
 						((uint64_t) n1 << 27)
 							| ((uint64_t) n2 << 18)
 							| ((uint64_t) n3 << 9)
@@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
 vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	uint16_t index[4];
-	struct pageUpperEntry *pml4e, *pdpe, *pde;
-	struct pageTableEntry *pte;
+	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	if (!vm->pgd_created)
 		goto unmapped_gva;
 	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present)
+	if (!(pml4e[index[3]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
-	if (!pdpe[index[2]].present)
+	pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+	if (!(pdpe[index[2]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
-	if (!pde[index[1]].present)
+	pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+	if (!(pde[index[1]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
-	if (!pte[index[0]].present)
+	pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+	if (!(pte[index[0]] & PTE_PRESENT_MASK))
 		goto unmapped_gva;
 
-	return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu);
+	return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK);
 
 unmapped_gva:
 	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 52a3ef6629e8..76f65c22796f 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -29,7 +29,6 @@
 #define X86_FEATURE_XSAVE		(1 << 26)
 #define X86_FEATURE_OSXSAVE		(1 << 27)
 
-#define PAGE_SIZE			(1 << 12)
 #define NUM_TILES			8
 #define TILE_SIZE			1024
 #define XSAVE_SIZE			((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
index f070ff0224fa..aeb3850f81bd 100644
--- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
+++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
@@ -12,7 +12,6 @@
 #include "vmx.h"
 
 #define VCPU_ID	   1
-#define PAGE_SIZE  4096
 #define MAXPHYADDR 36
 
 #define MEM_REGION_GVA	0x0000123456789000
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index a626d40fdb48..b4e0c860769e 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -21,8 +21,6 @@
 
 #define VCPU_ID	      1
 
-#define PAGE_SIZE  4096
-
 #define SMRAM_SIZE 65536
 #define SMRAM_MEMSLOT ((1 << 16) | 1)
 #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index e683d0ac3e45..19b35c607dc6 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -32,7 +32,6 @@
 #define MSR_IA32_TSC_ADJUST 0x3b
 #endif
 
-#define PAGE_SIZE	4096
 #define VCPU_ID		5
 
 #define TSC_ADJUST_VALUE (1ll << 32)
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 865e17146815..bcd370827859 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -23,7 +23,6 @@
 #define SHINFO_REGION_GVA	0xc0000000ULL
 #define SHINFO_REGION_GPA	0xc0000000ULL
 #define SHINFO_REGION_SLOT	10
-#define PAGE_SIZE		4096
 
 #define DUMMY_REGION_GPA	(SHINFO_REGION_GPA + (2 * PAGE_SIZE))
 #define DUMMY_REGION_SLOT	11
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
index adc94452b57c..b30fe9de1d4f 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
@@ -15,7 +15,6 @@
 
 #define HCALL_REGION_GPA	0xc0000000ULL
 #define HCALL_REGION_SLOT	10
-#define PAGE_SIZE		4096
 
 static struct kvm_vm *vm;
 
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index 222ecc81d7df..f4c2a6eb1666 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * KVM dirty ring implementation
  *
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dfb7dabdbc63..f30bb8c16f26 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -164,6 +164,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 {
 }
 
+__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+}
+
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
 {
 	/*
@@ -357,6 +361,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 #endif
 
+static void kvm_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_arch_flush_shadow_all(kvm);
+	kvm_arch_guest_memory_reclaimed(kvm);
+}
+
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 					       gfp_t gfp_flags)
@@ -485,12 +495,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
 			     unsigned long end);
 
+typedef void (*on_unlock_fn_t)(struct kvm *kvm);
+
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
 	pte_t pte;
 	hva_handler_t handler;
 	on_lock_fn_t on_lock;
+	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
 };
@@ -578,8 +591,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked)
+	if (locked) {
 		KVM_MMU_UNLOCK(kvm);
+		if (!IS_KVM_NULL_FN(range->on_unlock))
+			range->on_unlock(kvm);
+	}
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
@@ -600,6 +616,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.pte		= pte,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
@@ -619,6 +636,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.pte		= __pte(0),
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
@@ -662,7 +680,7 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
 		kvm->mmu_notifier_range_end = end;
 	} else {
 		/*
-		 * Fully tracking multiple concurrent ranges has dimishing
+		 * Fully tracking multiple concurrent ranges has diminishing
 		 * returns. Keep things simple and just find the minimal range
 		 * which includes the current and new ranges. As there won't be
 		 * enough information to subtract a range after its invalidate
@@ -687,6 +705,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
 		.on_lock	= kvm_inc_notifier_count,
+		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -741,6 +760,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_dec_notifier_count,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -813,7 +833,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -955,12 +975,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	/*
-	 * Force subsequent debugfs file creations to fail if the VM directory
-	 * is not created.
-	 */
-	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
-
 	if (!debugfs_initialized())
 		return 0;
 
@@ -1081,6 +1095,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
+	/*
+	 * Force subsequent debugfs file creations to fail if the VM directory
+	 * is not created (by kvm_create_vm_debugfs()).
+	 */
+	kvm->debugfs_dentry = ERR_PTR(-ENOENT);
+
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
 	if (init_srcu_struct(&kvm->irq_srcu))
@@ -1225,7 +1245,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
 	kvm->mn_active_invalidate_count = 0;
 #else
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
@@ -1652,6 +1672,7 @@ static void kvm_invalidate_memslot(struct kvm *kvm,
 	 *	- kvm_is_visible_gfn (mmu_check_root)
 	 */
 	kvm_arch_flush_shadow_memslot(kvm, old);
+	kvm_arch_guest_memory_reclaimed(kvm);
 
 	/* Was released by kvm_swap_active_memslots, reacquire. */
 	mutex_lock(&kvm->slots_arch_lock);
@@ -1799,7 +1820,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 
 	/*
 	 * No need to refresh new->arch, changes after dropping slots_arch_lock
-	 * will directly hit the final, active memsot.  Architectures are
+	 * will directly hit the final, active memslot.  Architectures are
 	 * responsible for knowing that new->arch may be stale.
 	 */
 	kvm_commit_memory_region(kvm, old, new, change);
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 34ca40823260..41da467d99c9 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+/* SPDX-License-Identifier: GPL-2.0-only */
 
 #ifndef __KVM_MM_H__
 #define __KVM_MM_H__ 1