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

Pull KVM fixes from Paolo Bonzini:
 "More fixes for ARM and x86"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: LAPIC: Advancing the timer expiration on guest initiated write
  KVM: x86/mmu: Skip !MMU-present SPTEs when removing SP in exclusive mode
  KVM: kvmclock: Fix vCPUs > 64 can't be online/hotpluged
  kvm: x86: annotate RCU pointers
  KVM: arm64: Fix exclusive limit for IPA size
  KVM: arm64: Reject VM creation when the default IPA size is unsupported
  KVM: arm64: Ensure I-cache isolation between vcpus of a same VM
  KVM: arm64: Don't use cbz/adr with external symbols
  KVM: arm64: Fix range alignment when walking page tables
  KVM: arm64: Workaround firmware wrongly advertising GICv2-on-v3 compatibility
  KVM: arm64: Rename __vgic_v3_get_ich_vtr_el2() to __vgic_v3_get_gic_config()
  KVM: arm64: Don't access PMSELR_EL0/PMUSERENR_EL0 when no PMU is available
  KVM: arm64: Turn kvm_arm_support_pmu_v3() into a static key
  KVM: arm64: Fix nVHE hyp panic host context restore
  KVM: arm64: Avoid corrupting vCPU context register in guest exit
  KVM: arm64: nvhe: Save the SPE context early
  kvm: x86: use NULL instead of using plain integer as pointer
  KVM: SVM: Connect 'npt' module param to KVM's internal 'npt_enabled'
  KVM: x86: Ensure deadline timer has truly expired before posting its IRQ

27 files changed, 194 insertions, 81 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1a2b5210cdbf58..38e327d4b47903 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -182,6 +182,9 @@ is dependent on the CPU capability and the kernel configuration. The limit can
 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
 ioctl() at run-time.
 
+Creation of the VM will fail if the requested IPA size (whether it is
+implicit or explicit) is unsupported on the host.
+
 Please note that configuring the IPA size does not affect the capability
 exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
 size of the address translated by the stage2 level (guest physical to
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 22d933e9b59e52..a7ab84f781f73d 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -47,10 +47,10 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context		2
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa		3
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid		4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context		5
 #define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
 #define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2		8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config		8
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr		9
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr		10
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs		11
@@ -183,16 +183,16 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
 
 extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
-extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_get_gic_config(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c0450828378b52..32ae676236b6b4 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -83,6 +83,11 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
@@ -97,7 +102,8 @@ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
 
 void __noreturn hyp_panic(void);
 #ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+			       u64 elr, u64 par);
 #endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 23f1a557bd9f04..5aa9ed1e9ec618 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -101,6 +101,9 @@ KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 /* Array containing bases of nVHE per-CPU memory regions. */
 KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
 
+/* PMU available static key */
+KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index fc4c95dd2d2617..7f06ba76698d84 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -385,11 +385,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * We guarantee that both TLBs and I-cache are private to each
+	 * vcpu. If detecting that a vcpu from the same VM has
+	 * previously run on the same physical CPU, call into the
+	 * hypervisor code to nuke the relevant contexts.
+	 *
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index b0afad7a99c6e8..e831d3dfd50d7c 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -85,8 +85,10 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 
 	// If the hyp context is loaded, go straight to hyp_panic
 	get_loaded_vcpu x0, x1
-	cbz	x0, hyp_panic
+	cbnz	x0, 1f
+	b	hyp_panic
 
+1:
 	// The hyp context is saved so make sure it is restored to allow
 	// hyp_panic to run at hyp and, subsequently, panic to run in the host.
 	// This makes use of __guest_exit to avoid duplication but sets the
@@ -94,7 +96,7 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// current state is saved to the guest context but it will only be
 	// accurate if the guest had been completely restored.
 	adr_this_cpu x0, kvm_hyp_ctxt, x1
-	adr	x1, hyp_panic
+	adr_l	x1, hyp_panic
 	str	x1, [x0, #CPU_XREG_OFFSET(30)]
 
 	get_vcpu_ptr	x1, x0
@@ -146,7 +148,7 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Now restore the hyp regs
 	restore_callee_saved_regs x2
 
-	set_loaded_vcpu xzr, x1, x2
+	set_loaded_vcpu xzr, x2, x3
 
 alternative_if ARM64_HAS_RAS_EXTN
 	// If we have the RAS extensions we can consume a pending error
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 54f4860cd87c06..6c1f51f25eb340 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -90,15 +90,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
 	 * EL1 instead of being trapped to EL2.
 	 */
-	write_sysreg(0, pmselr_el0);
-	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3()) {
+		write_sysreg(0, pmselr_el0);
+		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	}
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
 static inline void __deactivate_traps_common(void)
 {
 	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3())
+		write_sysreg(0, pmuserenr_el0);
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 91a711aa8382e1..f401724f12ef75 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -58,16 +58,24 @@ static void __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
 	__debug_switch_to_guest_common(vcpu);
 }
 
-void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
 	__debug_switch_to_host_common(vcpu);
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 6585a7cbbc5662..5d94584840ccfe 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -71,7 +71,8 @@ SYM_FUNC_START(__host_enter)
 SYM_FUNC_END(__host_enter)
 
 /*
- * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ * 				  u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
 	/* Prepare and exit to the host's panic funciton. */
@@ -82,9 +83,11 @@ SYM_FUNC_START(__hyp_do_panic)
 	hyp_kimg_va lr, x6
 	msr	elr_el2, lr
 
-	/* Set the panic format string. Use the, now free, LR as scratch. */
-	ldr	lr, =__hyp_panic_string
-	hyp_kimg_va lr, x6
+	mov	x29, x0
+
+	/* Load the format string into x0 and arguments into x1-7 */
+	ldr	x0, =__hyp_panic_string
+	hyp_kimg_va x0, x6
 
 	/* Load the format arguments into x1-7. */
 	mov	x6, x3
@@ -94,9 +97,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	mrs	x5, hpfar_el2
 
 	/* Enter the host, conditionally restoring the host context. */
-	cmp	x0, xzr
-	mov	x0, lr
-	b.eq	__host_enter_without_restoring
+	cbz	x29, __host_enter_without_restoring
 	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index f012f8665ecc1c..936328207bde02 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -46,11 +46,11 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-	__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+	__kvm_flush_cpu_context(kern_hyp_va(mmu));
 }
 
 static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
@@ -67,9 +67,9 @@ static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
 	write_sysreg_el2(tmp, SYS_SCTLR);
 }
 
-static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
 {
-	cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
 }
 
 static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
@@ -115,10 +115,10 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
-	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__kvm_enable_ssbs),
-	HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+	HANDLE_FUNC(__vgic_v3_get_gic_config),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),
 	HANDLE_FUNC(__vgic_v3_write_vmcr),
 	HANDLE_FUNC(__vgic_v3_init_lrs),
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f3d0e9eca56cd2..68ab6b4d514140 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -192,6 +192,14 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
 
 	__sysreg_save_state_nvhe(host_ctxt);
+	/*
+	 * We must flush and disable the SPE buffer for nVHE, as
+	 * the translation regime(EL1&0) is going to be loaded with
+	 * that of the guest. And we must do this before we change the
+	 * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and
+	 * before we load guest Stage1.
+	 */
+	__debug_save_host_buffers_nvhe(vcpu);
 
 	__adjust_pc(vcpu);
 
@@ -234,11 +242,12 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
 		__fpsimd_save_fpexc32(vcpu);
 
+	__debug_switch_to_host(vcpu);
 	/*
 	 * This must come after restoring the host sysregs, since a non-VHE
 	 * system may enable SPE here and make use of the TTBRs.
 	 */
-	__debug_switch_to_host(vcpu);
+	__debug_restore_host_buffers_nvhe(vcpu);
 
 	if (pmu_switch_needed)
 		__pmu_switch_to_host(host_ctxt);
@@ -257,7 +266,6 @@ void __noreturn hyp_panic(void)
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
 	u64 par = read_sysreg_par();
-	bool restore_host = true;
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
@@ -271,7 +279,7 @@ void __noreturn hyp_panic(void)
 		__sysreg_restore_state_nvhe(host_ctxt);
 	}
 
-	__hyp_do_panic(restore_host, spsr, elr, par);
+	__hyp_do_panic(host_ctxt, spsr, elr, par);
 	unreachable();
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index fbde89a2c6e838..229b06748c2084 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -123,7 +123,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -131,6 +131,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 4d177ce1d536f3..926fc07074f57b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -223,6 +223,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		goto out;
 
 	if (!table) {
+		data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
 		data->addr += kvm_granule_size(level);
 		goto out;
 	}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 80406f463c28fd..ee3682b9873c44 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -405,9 +405,45 @@ void __vgic_v3_init_lrs(void)
 		__gic_v3_set_lr(0, i);
 }
 
-u64 __vgic_v3_get_ich_vtr_el2(void)
+/*
+ * Return the GIC CPU configuration:
+ * - [31:0]  ICH_VTR_EL2
+ * - [62:32] RES0
+ * - [63]    MMIO (GICv2) capable
+ */
+u64 __vgic_v3_get_gic_config(void)
 {
-	return read_gicreg(ICH_VTR_EL2);
+	u64 val, sre = read_gicreg(ICC_SRE_EL1);
+	unsigned long flags = 0;
+
+	/*
+	 * To check whether we have a MMIO-based (GICv2 compatible)
+	 * CPU interface, we need to disable the system register
+	 * view. To do that safely, we have to prevent any interrupt
+	 * from firing (which would be deadly).
+	 *
+	 * Note that this only makes sense on VHE, as interrupts are
+	 * already masked for nVHE as part of the exception entry to
+	 * EL2.
+	 */
+	if (has_vhe())
+		flags = local_daif_save();
+
+	write_gicreg(0, ICC_SRE_EL1);
+	isb();
+
+	val = read_gicreg(ICC_SRE_EL1);
+
+	write_gicreg(sre, ICC_SRE_EL1);
+	isb();
+
+	if (has_vhe())
+		local_daif_restore(flags);
+
+	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
+	val |= read_gicreg(ICH_VTR_EL2);
+
+	return val;
 }
 
 u64 __vgic_v3_read_vmcr(void)
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index fd7895945bbc6f..66f17349f0c369 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -127,7 +127,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -135,6 +135,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 77cb2d28f2a43a..8711894db8c224 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1312,8 +1312,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the IPA
 	 * space addressable by the KVM guest IPA space.
 	 */
-	if (memslot->base_gfn + memslot->npages >=
-	    (kvm_phys_size(kvm) >> PAGE_SHIFT))
+	if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
 		return -EFAULT;
 
 	mmap_read_lock(current->mm);
diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c
index d45b8b9a441518..739164324afedb 100644
--- a/arch/arm64/kvm/perf.c
+++ b/arch/arm64/kvm/perf.c
@@ -11,6 +11,8 @@
 
 #include <asm/kvm_emulate.h>
 
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
 static int kvm_is_in_guest(void)
 {
         return kvm_get_running_vcpu() != NULL;
@@ -48,6 +50,14 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0)
+		static_branch_enable(&kvm_arm_pmu_available);
+
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
 }
 
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index e9ec08b0b07033..e32c6e139a09d3 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -823,16 +823,6 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return val & mask;
 }
 
-bool kvm_arm_support_pmu_v3(void)
-{
-	/*
-	 * Check if HW_PERF_EVENTS are supported by checking the number of
-	 * hardware performance counters. This could ensure the presence of
-	 * a physical PMU and CONFIG_PERF_EVENT is selected.
-	 */
-	return (perf_num_counters() > 0);
-}
-
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_vcpu_has_pmu(vcpu))
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index e81c7ec9e10202..bd354cd45d2860 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -326,10 +326,9 @@ int kvm_set_ipa_limit(void)
 	}
 
 	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
-	WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
-	     "KVM IPA Size Limit (%d bits) is smaller than default size\n",
-	     kvm_ipa_limit);
-	kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);
+	kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
+		 ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
+		  " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
 
 	return 0;
 }
@@ -358,6 +357,11 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 			return -EINVAL;
 	} else {
 		phys_shift = KVM_PHYS_SHIFT;
+		if (phys_shift > kvm_ipa_limit) {
+			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+				     current->comm);
+			return -EINVAL;
+		}
 	}
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 52915b34235143..6f530925a23144 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -574,9 +574,13 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
  */
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
-	u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	bool has_v2;
 	int ret;
 
+	has_v2 = ich_vtr_el2 >> 63;
+	ich_vtr_el2 = (u32)ich_vtr_el2;
+
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
 	 * maximum of 16 list registers. Just ignore bit 4...
@@ -594,13 +598,15 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 			 gicv4_enable ? "en" : "dis");
 	}
 
+	kvm_vgic_global_state.vcpu_base = 0;
+
 	if (!info->vcpu.start) {
 		kvm_info("GICv3: no GICV resource entry\n");
-		kvm_vgic_global_state.vcpu_base = 0;
+	} else if (!has_v2) {
+		pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
 	} else if (!PAGE_ALIGNED(info->vcpu.start)) {
 		pr_warn("GICV physical address 0x%llx not page aligned\n",
 			(unsigned long long)info->vcpu.start);
-		kvm_vgic_global_state.vcpu_base = 0;
 	} else {
 		kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 		kvm_vgic_global_state.can_emulate_gicv2 = true;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 877a4025d8da08..9bc091ecaaeb97 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -963,7 +963,7 @@ struct kvm_arch {
 	struct kvm_pit *vpit;
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
-	struct kvm_apic_map *apic_map;
+	struct kvm_apic_map __rcu *apic_map;
 	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
@@ -1036,7 +1036,7 @@ struct kvm_arch {
 
 	bool bus_lock_detection_enabled;
 
-	struct kvm_pmu_event_filter *pmu_event_filter;
+	struct kvm_pmu_event_filter __rcu *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa593743acf679..1fc0962c89c082 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void)
 
 static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-#ifdef CONFIG_X86_64
-	u8 flags;
+	kvmclock_init_mem();
 
-	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
-		return 0;
+#ifdef CONFIG_X86_64
+	if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
+		u8 flags;
 
-	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 0;
+		flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+		if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+			return 0;
 
-	kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+		kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+	}
 #endif
 
-	kvmclock_init_mem();
-
 	return 0;
 }
 early_initcall(kvm_setup_vsyscall_timeinfo);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 45d40bfacb7cbe..cc369b9ad8f11c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
-		kvm_wait_lapic_expire(vcpu);
+		/*
+		 * Ensure the guest's timer has truly expired before posting an
+		 * interrupt.  Open code the relevant checks to avoid querying
+		 * lapic_timer_int_injected(), which will be false since the
+		 * interrupt isn't yet injected.  Waiting until after injecting
+		 * is not an option since that won't help a posted interrupt.
+		 */
+		if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+		    vcpu->arch.apic->lapic_timer.timer_advance_ns)
+			__kvm_wait_lapic_expire(vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
 	}
@@ -2595,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c926c6b899a106..d78915019b082f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 				cpu_relax();
 			}
 		} else {
+			/*
+			 * If the SPTE is not MMU-present, there is no backing
+			 * page associated with the SPTE and so no side effects
+			 * that need to be recorded, and exclusive ownership of
+			 * mmu_lock ensures the SPTE can't be made present.
+			 * Note, zapping MMIO SPTEs is also unnecessary as they
+			 * are guarded by the memslots generation, not by being
+			 * unreachable.
+			 */
 			old_child_spte = READ_ONCE(*sptep);
+			if (!is_shadow_present_pte(old_child_spte))
+				continue;
 
 			/*
 			 * Marking the SPTE as a removed SPTE is not
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index baee91c1e93643..58a45bb139f88a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_INVALID,				.always = false },
 };
 
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * pause_filter_count: On processors that support Pause filtering(indicated
@@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444);
 static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
 module_param(pause_filter_count_max, ushort, 0444);
 
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default.  Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
 
 /* allow nested virtualization in KVM/SVM */
 static int nested = true;
@@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_NPT))
+	/*
+	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
+	 * NPT isn't supported if the host is using 2-level paging since host
+	 * CR4 is unchanged on VMRUN.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
 		npt_enabled = false;
 
-	if (npt_enabled && !npt)
+	if (!boot_cpu_has(X86_FEATURE_NPT))
 		npt_enabled = false;
 
 	kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2a20ce60152ea9..47e021bdcc94ab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10601,7 +10601,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
-			return 0;
+			return NULL;
 
 		old_npages = slot->npages;
 		hva = slot->userspace_addr;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 8dcb3e1477bc98..6fd3cda608e4a6 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -13,6 +13,13 @@
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 #define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
+DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
+static __always_inline bool kvm_arm_support_pmu_v3(void)
+{
+	return static_branch_likely(&kvm_arm_pmu_available);
+}
+
 #ifdef CONFIG_HW_PERF_EVENTS
 
 struct kvm_pmc {
@@ -47,7 +54,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx);
-bool kvm_arm_support_pmu_v3(void);
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
@@ -87,7 +93,6 @@ static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,
 						  u64 data, u64 select_idx) {}
-static inline bool kvm_arm_support_pmu_v3(void) { return false; }
 static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 					  struct kvm_device_attr *attr)
 {