Merge tag 'kvmarm-for-v5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-next

KVM/arm updates for Linux v5.1

- A number of pre-nested code rework
- Direct physical timer assignment on VHE systems
- kvm_call_hyp type safety enforcement
- Set/Way cache sanitisation for 32bit guests
- Build system cleanups
- A bunch of janitorial fixes

23 files changed, 277 insertions, 115 deletions

diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 0bd530702118..bdc87700def2 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -54,7 +54,7 @@
 #define ICH_VTR				__ACCESS_CP15(c12, 4, c11, 1)
 #define ICH_MISR			__ACCESS_CP15(c12, 4, c11, 2)
 #define ICH_EISR			__ACCESS_CP15(c12, 4, c11, 3)
-#define ICH_ELSR			__ACCESS_CP15(c12, 4, c11, 5)
+#define ICH_ELRSR			__ACCESS_CP15(c12, 4, c11, 5)
 #define ICH_VMCR			__ACCESS_CP15(c12, 4, c11, 7)
 
 #define __LR0(x)			__ACCESS_CP15(c12, 4, c12, x)
@@ -151,7 +151,7 @@ CPUIF_MAP(ICH_HCR, ICH_HCR_EL2)
 CPUIF_MAP(ICH_VTR, ICH_VTR_EL2)
 CPUIF_MAP(ICH_MISR, ICH_MISR_EL2)
 CPUIF_MAP(ICH_EISR, ICH_EISR_EL2)
-CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2)
+CPUIF_MAP(ICH_ELRSR, ICH_ELRSR_EL2)
 CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2)
 CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2)
 CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2)
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 77121b713bef..8927cae7c966 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -265,6 +265,14 @@ static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index ca56537b61bc..8073267dc4a0 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -26,6 +26,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/fpstate.h>
+#include <asm/smp_plat.h>
 #include <kvm/arm_arch_timer.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -56,10 +57,13 @@ int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
-struct kvm_arch {
-	/* VTTBR value associated with below pgd and vmid */
-	u64    vttbr;
+struct kvm_vmid {
+	/* The VMID generation used for the virt. memory system */
+	u64    vmid_gen;
+	u32    vmid;
+};
 
+struct kvm_arch {
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
@@ -69,11 +73,11 @@ struct kvm_arch {
 	 */
 
 	/* The VMID generation used for the virt. memory system */
-	u64    vmid_gen;
-	u32    vmid;
+	struct kvm_vmid vmid;
 
 	/* Stage-2 page table */
 	pgd_t *pgd;
+	phys_addr_t pgd_phys;
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
@@ -147,6 +151,13 @@ struct kvm_cpu_context {
 
 typedef struct kvm_cpu_context kvm_cpu_context_t;
 
+static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
+					     int cpu)
+{
+	/* The host's MPIDR is immutable, so let's set it up at boot time */
+	cpu_ctxt->cp15[c0_MPIDR] = cpu_logical_map(cpu);
+}
+
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
 
@@ -214,7 +225,35 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-unsigned long kvm_call_hyp(void *hypfn, ...);
+
+unsigned long __kvm_call_hyp(void *hypfn, ...);
+
+/*
+ * The has_vhe() part doesn't get emitted, but is used for type-checking.
+ */
+#define kvm_call_hyp(f, ...)						\
+	do {								\
+		if (has_vhe()) {					\
+			f(__VA_ARGS__);					\
+		} else {						\
+			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+		}							\
+	} while(0)
+
+#define kvm_call_hyp_ret(f, ...)					\
+	({								\
+		typeof(f(__VA_ARGS__)) ret;				\
+									\
+		if (has_vhe()) {					\
+			ret = f(__VA_ARGS__);				\
+		} else {						\
+			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
+					     ##__VA_ARGS__);		\
+		}							\
+									\
+		ret;							\
+	})
+
 void force_vm_exit(const cpumask_t *mask);
 int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
@@ -265,7 +304,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 * compliant with the PCS!).
 	 */
 
-	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
+	__kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
 static inline void __cpu_init_stage2(void)
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index e93a0cac9add..87bcd18df8d5 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -40,6 +40,7 @@
 #define TTBR1		__ACCESS_CP15_64(1, c2)
 #define VTTBR		__ACCESS_CP15_64(6, c2)
 #define PAR		__ACCESS_CP15_64(0, c7)
+#define CNTP_CVAL	__ACCESS_CP15_64(2, c14)
 #define CNTV_CVAL	__ACCESS_CP15_64(3, c14)
 #define CNTVOFF		__ACCESS_CP15_64(4, c14)
 
@@ -85,6 +86,7 @@
 #define TID_PRIV	__ACCESS_CP15(c13, 0, c0, 4)
 #define HTPIDR		__ACCESS_CP15(c13, 4, c0, 2)
 #define CNTKCTL		__ACCESS_CP15(c14, 0, c1, 0)
+#define CNTP_CTL	__ACCESS_CP15(c14, 0, c2, 1)
 #define CNTV_CTL	__ACCESS_CP15(c14, 0, c3, 1)
 #define CNTHCTL		__ACCESS_CP15(c14, 4, c1, 0)
 
@@ -94,6 +96,8 @@
 #define read_sysreg_el0(r)		read_sysreg(r##_el0)
 #define write_sysreg_el0(v, r)		write_sysreg(v, r##_el0)
 
+#define cntp_ctl_el0			CNTP_CTL
+#define cntp_cval_el0			CNTP_CVAL
 #define cntv_ctl_el0			CNTV_CTL
 #define cntv_cval_el0			CNTV_CVAL
 #define cntvoff_el2			CNTVOFF
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 3a875fc1b63c..2de96a180166 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -421,9 +421,14 @@ static inline int hyp_map_aux_data(void)
 
 static inline void kvm_set_ipa_limit(void) {}
 
-static inline bool kvm_cpu_has_cnp(void)
+static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
 {
-	return false;
+	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	u64 vmid_field, baddr;
+
+	baddr = kvm->arch.pgd_phys;
+	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
+	return kvm_phys_to_vttbr(baddr) | vmid_field;
 }
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 48de846f2246..531e59f5be9c 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -8,9 +8,8 @@ ifeq ($(plus_virt),+virt)
 	plus_virt_def := -DREQUIRES_VIRT=1
 endif
 
-ccflags-y += -Iarch/arm/kvm -Ivirt/kvm/arm/vgic
-CFLAGS_arm.o := -I. $(plus_virt_def)
-CFLAGS_mmu.o := -I.
+ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic
+CFLAGS_arm.o := $(plus_virt_def)
 
 AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 222c1635bc7a..51863364f8d1 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -293,15 +293,16 @@ static bool access_cntp_tval(struct kvm_vcpu *vcpu,
 			     const struct coproc_params *p,
 			     const struct coproc_reg *r)
 {
-	u64 now = kvm_phys_timer_read();
-	u64 val;
+	u32 val;
 
 	if (p->is_write) {
 		val = *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val + now);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_TVAL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
-		*vcpu_reg(vcpu, p->Rt1) = val - now;
+		val = kvm_arm_timer_read_sysreg(vcpu,
+						TIMER_PTIMER, TIMER_REG_TVAL);
+		*vcpu_reg(vcpu, p->Rt1) = val;
 	}
 
 	return true;
@@ -315,9 +316,11 @@ static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
 
 	if (p->is_write) {
 		val = *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, val);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_CTL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
+		val = kvm_arm_timer_read_sysreg(vcpu,
+						TIMER_PTIMER, TIMER_REG_CTL);
 		*vcpu_reg(vcpu, p->Rt1) = val;
 	}
 
@@ -333,9 +336,11 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
 	if (p->is_write) {
 		val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32;
 		val |= *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_CVAL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		val = kvm_arm_timer_read_sysreg(vcpu,
+						TIMER_PTIMER, TIMER_REG_CVAL);
 		*vcpu_reg(vcpu, p->Rt1) = val;
 		*vcpu_reg(vcpu, p->Rt2) = val >> 32;
 	}
diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c
index c4782812714c..8bf895ec6e04 100644
--- a/arch/arm/kvm/hyp/cp15-sr.c
+++ b/arch/arm/kvm/hyp/cp15-sr.c
@@ -27,7 +27,6 @@ static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx)
 
 void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->cp15[c0_MPIDR]		= read_sysreg(VMPIDR);
 	ctxt->cp15[c0_CSSELR]		= read_sysreg(CSSELR);
 	ctxt->cp15[c1_SCTLR]		= read_sysreg(SCTLR);
 	ctxt->cp15[c1_CPACR]		= read_sysreg(CPACR);
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
index aa3f9a9837ac..6ed3cf23fe89 100644
--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -176,7 +176,7 @@ THUMB(	orr	lr, lr, #PSR_T_BIT	)
 	msr	spsr_cxsf, lr
 	ldr	lr, =panic
 	msr	ELR_hyp, lr
-	ldr	lr, =kvm_call_hyp
+	ldr	lr, =__kvm_call_hyp
 	clrex
 	eret
 ENDPROC(__hyp_do_panic)
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
index acf1c37fa49c..3b058a5d7c5f 100644
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -77,7 +77,7 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	write_sysreg(vcpu->arch.midr, VPIDR);
 }
 
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
index c0edd450e104..8e4afba73635 100644
--- a/arch/arm/kvm/hyp/tlb.c
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -41,7 +41,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	isb();
 
 	write_sysreg(0, TLBIALLIS);
@@ -61,7 +61,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	isb();
 
 	write_sysreg(0, TLBIALL);
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 80a1d6cd261c..a08e6419ebe9 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -42,7 +42,7 @@
  *   r12:     caller save
  *   rest:    callee save
  */
-ENTRY(kvm_call_hyp)
+ENTRY(__kvm_call_hyp)
 	hvc	#0
 	bx	lr
-ENDPROC(kvm_call_hyp)
+ENDPROC(__kvm_call_hyp)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 506386a3edde..d3842791e1c4 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -77,6 +77,10 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	 */
 	if (!vcpu_el1_is_32bit(vcpu))
 		vcpu->arch.hcr_el2 |= HCR_TID3;
+
+	if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
+	    vcpu_el1_is_32bit(vcpu))
+		vcpu->arch.hcr_el2 |= HCR_TID2;
 }
 
 static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
@@ -331,6 +335,14 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
+static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
 	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 7732d0ba4e60..444dd1cb1958 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,6 +30,7 @@
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/smp_plat.h>
 #include <asm/thread_info.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -56,16 +57,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
-struct kvm_arch {
+struct kvm_vmid {
 	/* The VMID generation used for the virt. memory system */
 	u64    vmid_gen;
 	u32    vmid;
+};
+
+struct kvm_arch {
+	struct kvm_vmid vmid;
 
 	/* stage2 entry level table */
 	pgd_t *pgd;
+	phys_addr_t pgd_phys;
 
-	/* VTTBR value associated with above pgd and vmid */
-	u64    vttbr;
 	/* VTCR_EL2 value for this VM */
 	u64    vtcr;
 
@@ -370,7 +374,36 @@ void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
 u64 __kvm_call_hyp(void *hypfn, ...);
-#define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__)
+
+/*
+ * The couple of isb() below are there to guarantee the same behaviour
+ * on VHE as on !VHE, where the eret to EL1 acts as a context
+ * synchronization event.
+ */
+#define kvm_call_hyp(f, ...)						\
+	do {								\
+		if (has_vhe()) {					\
+			f(__VA_ARGS__);					\
+			isb();						\
+		} else {						\
+			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+		}							\
+	} while(0)
+
+#define kvm_call_hyp_ret(f, ...)					\
+	({								\
+		typeof(f(__VA_ARGS__)) ret;				\
+									\
+		if (has_vhe()) {					\
+			ret = f(__VA_ARGS__);				\
+			isb();						\
+		} else {						\
+			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
+					     ##__VA_ARGS__);		\
+		}							\
+									\
+		ret;							\
+	})
 
 void force_vm_exit(const cpumask_t *mask);
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
@@ -389,6 +422,13 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
 DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
 
+static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
+					     int cpu)
+{
+	/* The host's MPIDR is immutable, so let's set it up at boot time */
+	cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu);
+}
+
 void __kvm_enable_ssbs(void);
 
 static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index a80a7ef57325..4da765f2cca5 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -21,6 +21,7 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/alternative.h>
+#include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
 #define __hyp_text __section(.hyp.text) notrace
@@ -163,7 +164,7 @@ void __noreturn __hyp_do_panic(unsigned long, ...);
 static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm)
 {
 	write_sysreg(kvm->arch.vtcr, vtcr_el2);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
 
 	/*
 	 * ARM erratum 1165522 requires the actual execution of the above
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8af4b1befa42..b0742a16c6c9 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -138,7 +138,8 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
 	})
 
 /*
- * We currently only support a 40bit IPA.
+ * We currently support using a VM-specified IPA size. For backward
+ * compatibility, the default IPA size is fixed to 40bits.
  */
 #define KVM_PHYS_SHIFT	(40)
 
@@ -591,9 +592,15 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
 	return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
 }
 
-static inline bool kvm_cpu_has_cnp(void)
+static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
 {
-	return system_supports_cnp();
+	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	u64 vmid_field, baddr;
+	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
+
+	baddr = kvm->arch.pgd_phys;
+	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
+	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 72dc4c011014..5b267dec6194 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -361,6 +361,7 @@
 
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
+#define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
 #define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
 
@@ -392,6 +393,10 @@
 #define SYS_CNTP_CTL_EL0		sys_reg(3, 3, 14, 2, 1)
 #define SYS_CNTP_CVAL_EL0		sys_reg(3, 3, 14, 2, 2)
 
+#define SYS_AARCH32_CNTP_TVAL		sys_reg(0, 0, 14, 2, 0)
+#define SYS_AARCH32_CNTP_CTL		sys_reg(0, 0, 14, 2, 1)
+#define SYS_AARCH32_CNTP_CVAL		sys_reg(0, 2, 0, 14, 0)
+
 #define __PMEV_op2(n)			((n) & 0x7)
 #define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))
 #define SYS_PMEVCNTRn_EL0(n)		sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
@@ -426,7 +431,7 @@
 #define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
 #define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
-#define SYS_ICH_ELSR_EL2		sys_reg(3, 4, 12, 11, 5)
+#define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
 #define SYS_ICH_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
 
 #define __SYS__LR0_EL2(x)		sys_reg(3, 4, 12, 12, x)
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 0f2a135ba15b..690e033a91c0 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -3,9 +3,7 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-ccflags-y += -Iarch/arm64/kvm -Ivirt/kvm/arm/vgic
-CFLAGS_arm.o := -I.
-CFLAGS_mmu.o := -I.
+ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic
 
 KVM=../../../virt/kvm
 
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index f39801e4136c..fd917d6d12af 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -76,7 +76,7 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
 
 void kvm_arm_init_debug(void)
 {
-	__this_cpu_write(mdcr_el2, kvm_call_hyp(__kvm_get_mdcr_el2));
+	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
 }
 
 /**
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 952f6cb9cf72..2845aa680841 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -40,9 +40,6 @@
  * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(__kvm_call_hyp)
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	hvc	#0
 	ret
-alternative_else_nop_endif
-	b	__vhe_hyp_call
 ENDPROC(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 73c1b483ec39..2b1e686772bf 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -43,18 +43,6 @@
 	ldr	lr, [sp], #16
 .endm
 
-ENTRY(__vhe_hyp_call)
-	do_el2_call
-	/*
-	 * We used to rely on having an exception return to get
-	 * an implicit isb. In the E2H case, we don't have it anymore.
-	 * rather than changing all the leaf functions, just do it here
-	 * before returning to the rest of the kernel.
-	 */
-	isb
-	ret
-ENDPROC(__vhe_hyp_call)
-
 el1_sync:				// Guest trapped into EL2
 
 	mrs	x0, esr_el2
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 68d6f7c3b237..2498f86defcb 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -52,7 +52,6 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 
 static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(sctlr);
 	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e3e37228ae4e..a398d04274b7 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -965,6 +965,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+#define reg_to_encoding(x)						\
+	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -986,44 +990,38 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
-static bool access_cntp_tval(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
+static bool access_arch_timer(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
 {
-	u64 now = kvm_phys_timer_read();
-	u64 cval;
+	enum kvm_arch_timers tmr;
+	enum kvm_arch_timer_regs treg;
+	u64 reg = reg_to_encoding(r);
 
-	if (p->is_write) {
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL,
-				      p->regval + now);
-	} else {
-		cval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
-		p->regval = cval - now;
+	switch (reg) {
+	case SYS_CNTP_TVAL_EL0:
+	case SYS_AARCH32_CNTP_TVAL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+	case SYS_CNTP_CTL_EL0:
+	case SYS_AARCH32_CNTP_CTL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+	case SYS_CNTP_CVAL_EL0:
+	case SYS_AARCH32_CNTP_CVAL:
+		tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+	default:
+		BUG();
 	}
 
-	return true;
-}
-
-static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
-{
-	if (p->is_write)
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, p->regval);
-	else
-		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
-
-	return true;
-}
-
-static bool access_cntp_cval(struct kvm_vcpu *vcpu,
-		struct sys_reg_params *p,
-		const struct sys_reg_desc *r)
-{
 	if (p->is_write)
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, p->regval);
+		kvm_arm_timer_write_sysreg(vcpu, tmr, treg, p->regval);
 	else
-		p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		p->regval = kvm_arm_timer_read_sysreg(vcpu, tmr, treg);
 
 	return true;
 }
@@ -1148,6 +1146,64 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	return __set_id_reg(rd, uaddr, true);
 }
 
+static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+		       const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_sanitised_ftr_reg(SYS_CTR_EL0);
+	return true;
+}
+
+static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = read_sysreg(clidr_el1);
+	return true;
+}
+
+static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+	else
+		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+	return true;
+}
+
+static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	u32 csselr;
+
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1);
+	p->regval = get_ccsidr(csselr);
+
+	/*
+	 * Guests should not be doing cache operations by set/way at all, and
+	 * for this reason, we trap them and attempt to infer the intent, so
+	 * that we can flush the entire guest's address space at the appropriate
+	 * time.
+	 * To prevent this trapping from causing performance problems, let's
+	 * expose the geometry of all data and unified caches (which are
+	 * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way.
+	 * [If guests should attempt to infer aliasing properties from the
+	 * geometry (which is not permitted by the architecture), they would
+	 * only do so for virtually indexed caches.]
+	 */
+	if (!(csselr & 1)) // data or unified cache
+		p->regval &= ~GENMASK(27, 3);
+	return true;
+}
+
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\
@@ -1365,7 +1421,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
 
-	{ SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },
+	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
+	{ SYS_DESC(SYS_CLIDR_EL1), access_clidr },
+	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
+	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 
 	{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, },
 	{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
@@ -1388,9 +1447,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 
-	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_cntp_tval },
-	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_cntp_ctl },
-	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_cntp_cval },
+	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
 
 	/* PMEVCNTRn_EL0 */
 	PMU_PMEVCNTR_EL0(0),
@@ -1464,7 +1523,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
-	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x70 },
+	{ SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 },
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
@@ -1665,6 +1724,7 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  * register).
  */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr },
 	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
@@ -1711,10 +1771,9 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
 
-	/* CNTP_TVAL */
-	{ Op1( 0), CRn(14), CRm( 2), Op2( 0), access_cntp_tval },
-	/* CNTP_CTL */
-	{ Op1( 0), CRn(14), CRm( 2), Op2( 1), access_cntp_ctl },
+	/* Arch Tmers */
+	{ SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer },
+	{ SYS_DESC(SYS_AARCH32_CNTP_CTL), access_arch_timer },
 
 	/* PMEVCNTRn */
 	PMU_PMEVCNTR(0),
@@ -1782,6 +1841,10 @@ static const struct sys_reg_desc cp15_regs[] = {
 	PMU_PMEVTYPER(30),
 	/* PMCCFILTR */
 	{ Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper },
+
+	{ Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr },
+	{ Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr },
+	{ Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, c0_CSSELR },
 };
 
 static const struct sys_reg_desc cp15_64_regs[] = {
@@ -1791,7 +1854,7 @@ static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 	{ Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */
 	{ Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */
-	{ Op1( 2), CRn( 0), CRm(14), Op2( 0), access_cntp_cval },
+	{ SYS_DESC(SYS_AARCH32_CNTP_CVAL),    access_arch_timer },
 };
 
 /* Target specific emulation tables */
@@ -1820,30 +1883,19 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 	}
 }
 
-#define reg_to_match_value(x)						\
-	({								\
-		unsigned long val;					\
-		val  = (x)->Op0 << 14;					\
-		val |= (x)->Op1 << 11;					\
-		val |= (x)->CRn << 7;					\
-		val |= (x)->CRm << 3;					\
-		val |= (x)->Op2;					\
-		val;							\
-	 })
-
 static int match_sys_reg(const void *key, const void *elt)
 {
 	const unsigned long pval = (unsigned long)key;
 	const struct sys_reg_desc *r = elt;
 
-	return pval - reg_to_match_value(r);
+	return pval - reg_to_encoding(r);
 }
 
 static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
 					 const struct sys_reg_desc table[],
 					 unsigned int num)
 {
-	unsigned long pval = reg_to_match_value(params);
+	unsigned long pval = reg_to_encoding(params);
 
 	return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
 }
@@ -2206,11 +2258,15 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	}
 
 FUNCTION_INVARIANT(midr_el1)
-FUNCTION_INVARIANT(ctr_el0)
 FUNCTION_INVARIANT(revidr_el1)
 FUNCTION_INVARIANT(clidr_el1)
 FUNCTION_INVARIANT(aidr_el1)
 
+static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
+{
+	((struct sys_reg_desc *)r)->val = read_sanitised_ftr_reg(SYS_CTR_EL0);
+}
+
 /* ->val is filled in by kvm_sys_reg_table_init() */
 static struct sys_reg_desc invariant_sys_regs[] = {
 	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },