Merge tag 'kvm-arm-for-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/ARM Changes for v4.12.

Changes include:
 - Using the common sysreg definitions between KVM and arm64
 - Improved hyp-stub implementation with support for kexec and kdump on the 32-bit side
 - Proper PMU exception handling
 - Performance improvements of our GIC handling
 - Support for irqchip in userspace with in-kernel arch-timers and PMU support
 - A fix for a race condition in our PSCI code

Conflicts:
	Documentation/virtual/kvm/api.txt
	include/uapi/linux/kvm.h

Documentation/virtual/kvm/api.txt

@@ -4120,3 +4120,44 @@ This capability indicates that guest using memory monotoring instructions
 (MWAIT/MWAITX) to stop the virtual CPU will not cause a VM exit.  As such time
 spent while virtual CPU is halted in this way will then be accounted for as
 guest running time on the host (as opposed to e.g. HLT).
+
+8.9 KVM_CAP_ARM_USER_IRQ
+
+Architectures: arm, arm64
+This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
+that if userspace creates a VM without an in-kernel interrupt controller, it
+will be notified of changes to the output level of in-kernel emulated devices,
+which can generate virtual interrupts, presented to the VM.
+For such VMs, on every return to userspace, the kernel
+updates the vcpu's run->s.regs.device_irq_level field to represent the actual
+output level of the device.
+
+Whenever kvm detects a change in the device output level, kvm guarantees at
+least one return to userspace before running the VM.  This exit could either
+be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
+userspace can always sample the device output level and re-compute the state of
+the userspace interrupt controller.  Userspace should always check the state
+of run->s.regs.device_irq_level on every kvm exit.
+The value in run->s.regs.device_irq_level can represent both level and edge
+triggered interrupt signals, depending on the device.  Edge triggered interrupt
+signals will exit to userspace with the bit in run->s.regs.device_irq_level
+set exactly once per edge signal.
+
+The field run->s.regs.device_irq_level is available independent of
+run->kvm_valid_regs or run->kvm_dirty_regs bits.
+
+If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
+number larger than 0 indicating the version of this capability is implemented
+and thereby which bits in in run->s.regs.device_irq_level can signal values.
+
+Currently the following bits are defined for the device_irq_level bitmap:
+
+  KVM_CAP_ARM_USER_IRQ >= 1:
+
+    KVM_ARM_DEV_EL1_VTIMER -  EL1 virtual timer
+    KVM_ARM_DEV_EL1_PTIMER -  EL1 physical timer
+    KVM_ARM_DEV_PMU        -  ARM PMU overflow interrupt signal
+
+Future versions of kvm may implement additional events. These will get
+indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
+listed above.

Documentation/virtual/kvm/arm/hyp-abi.txt

@@ -0,0 +1,53 @@
+* Internal ABI between the kernel and HYP
+
+This file documents the interaction between the Linux kernel and the
+hypervisor layer when running Linux as a hypervisor (for example
+KVM). It doesn't cover the interaction of the kernel with the
+hypervisor when running as a guest (under Xen, KVM or any other
+hypervisor), or any hypervisor-specific interaction when the kernel is
+used as a host.
+
+On arm and arm64 (without VHE), the kernel doesn't run in hypervisor
+mode, but still needs to interact with it, allowing a built-in
+hypervisor to be either installed or torn down.
+
+In order to achieve this, the kernel must be booted at HYP (arm) or
+EL2 (arm64), allowing it to install a set of stubs before dropping to
+SVC/EL1. These stubs are accessible by using a 'hvc #0' instruction,
+and only act on individual CPUs.
+
+Unless specified otherwise, any built-in hypervisor must implement
+these functions (see arch/arm{,64}/include/asm/virt.h):
+
+* r0/x0 = HVC_SET_VECTORS
+  r1/x1 = vectors
+
+  Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors'
+  must be a physical address, and respect the alignment requirements
+  of the architecture. Only implemented by the initial stubs, not by
+  Linux hypervisors.
+
+* r0/x0 = HVC_RESET_VECTORS
+
+  Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials
+  stubs' exception vector value. This effectively disables an existing
+  hypervisor.
+
+* r0/x0 = HVC_SOFT_RESTART
+  r1/x1 = restart address
+  x2 = x0's value when entering the next payload (arm64)
+  x3 = x1's value when entering the next payload (arm64)
+  x4 = x2's value when entering the next payload (arm64)
+
+  Mask all exceptions, disable the MMU, move the arguments into place
+  (arm64 only), and jump to the restart address while at HYP/EL2. This
+  hypercall is not expected to return to its caller.
+
+Any other value of r0/x0 triggers a hypervisor-specific handling,
+which is not documented here.
+
+The return value of a stub hypercall is held by r0/x0, and is 0 on
+success, and HVC_STUB_ERR on error. A stub hypercall is allowed to
+clobber any of the caller-saved registers (x0-x18 on arm64, r0-r3 and
+ip on arm). It is thus recommended to use a function call to perform
+the hypercall.

arch/arm/boot/compressed/head.S

@@ -422,7 +422,17 @@ dtb_check_done:
 		cmp	r0, #HYP_MODE
 		bne	1f
 
-		bl	__hyp_get_vectors
+		/*
+		 * Compute the address of the hyp vectors after relocation.
+		 * This requires some arithmetic since we cannot directly
+		 * reference __hyp_stub_vectors in a PC-relative way.
+		 * Call __hyp_set_vectors with the new address so that we
+		 * can HVC again after the copy.
+		 */
+0:		adr	r0, 0b
+		movw	r1, #:lower16:__hyp_stub_vectors - 0b
+		movt	r1, #:upper16:__hyp_stub_vectors - 0b
+		add	r0, r0, r1
 		sub	r0, r0, r5
 		add	r0, r0, r10
 		bl	__hyp_set_vectors

arch/arm/include/asm/kvm_asm.h

@@ -33,7 +33,7 @@
 #define ARM_EXCEPTION_IRQ	  5
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
-
+#define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
 /*
  * The rr_lo_hi macro swaps a pair of registers depending on
  * current endianness. It is used in conjunction with ldrd and strd
@@ -72,10 +72,11 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
 
-extern void __kvm_hyp_reset(unsigned long);
-
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */

arch/arm/include/asm/kvm_host.h

@@ -269,12 +269,6 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
-static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
-					phys_addr_t phys_idmap_start)
-{
-	kvm_call_hyp((void *)virt_to_idmap(__kvm_hyp_reset), vector_ptr);
-}
-
 static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;

arch/arm/include/asm/kvm_mmu.h

@@ -56,7 +56,6 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
-phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

arch/arm/include/asm/proc-fns.h

@@ -43,7 +43,7 @@ extern struct processor {
 	/*
 	 * Special stuff for a reset
 	 */
-	void (*reset)(unsigned long addr) __attribute__((noreturn));
+	void (*reset)(unsigned long addr, bool hvc) __attribute__((noreturn));
 	/*
 	 * Idle the processor
 	 */
@@ -88,7 +88,7 @@ extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
 #else
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 #endif
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+extern void cpu_reset(unsigned long addr, bool hvc) __attribute__((noreturn));
 
 /* These three are private to arch/arm/kernel/suspend.c */
 extern void cpu_do_suspend(void *);

arch/arm/include/asm/virt.h

@@ -53,7 +53,7 @@ static inline void sync_boot_mode(void)
 }
 
 void __hyp_set_vectors(unsigned long phys_vector_base);
-unsigned long __hyp_get_vectors(void);
+void __hyp_reset_vectors(void);
 #else
 #define __boot_cpu_mode	(SVC_MODE)
 #define sync_boot_mode()
@@ -94,6 +94,18 @@ extern char __hyp_text_start[];
 extern char __hyp_text_end[];
 #endif
 
+#else
+
+/* Only assembly code should need those */
+
+#define HVC_SET_VECTORS 0
+#define HVC_SOFT_RESTART 1
+#define HVC_RESET_VECTORS 2
+
+#define HVC_STUB_HCALL_NR 3
+
 #endif /* __ASSEMBLY__ */
 
+#define HVC_STUB_ERR	0xbadca11
+
 #endif /* ! VIRT_H */

arch/arm/include/uapi/asm/kvm.h

@@ -116,6 +116,8 @@ struct kvm_debug_exit_arch {
 };
 
 struct kvm_sync_regs {
+	/* Used with KVM_CAP_ARM_USER_IRQ */
+	__u64 device_irq_level;
 };
 
 struct kvm_arch_memory_slot {

arch/arm/kernel/hyp-stub.S

@@ -125,7 +125,7 @@ ENTRY(__hyp_stub_install_secondary)
  * (see safe_svcmode_maskall).
  */
 	@ Now install the hypervisor stub:
-	adr	r7, __hyp_stub_vectors
+	W(adr)	r7, __hyp_stub_vectors
 	mcr	p15, 4, r7, c12, c0, 0	@ set hypervisor vector base (HVBAR)
 
 	@ Disable all traps, so we don't get any nasty surprise
@@ -202,9 +202,23 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 ENDPROC(__hyp_stub_install_secondary)
 
 __hyp_stub_do_trap:
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	mcrne	p15, 4, r0, c12, c0, 0	@ set HVBAR
+	teq	r0, #HVC_SET_VECTORS
+	bne	1f
+	mcr	p15, 4, r1, c12, c0, 0	@ set HVBAR
+	b	__hyp_stub_exit
+
+1:	teq	r0, #HVC_SOFT_RESTART
+	bne	1f
+	bx	r1
+
+1:	teq	r0, #HVC_RESET_VECTORS
+	beq	__hyp_stub_exit
+
+	ldr	r0, =HVC_STUB_ERR
+	__ERET
+
+__hyp_stub_exit:
+	mov	r0, #0
 	__ERET
 ENDPROC(__hyp_stub_do_trap)
 
@@ -230,15 +244,26 @@ ENDPROC(__hyp_stub_do_trap)
  * so you will need to set that to something sensible at the new hypervisor's
  * initialisation entry point.
  */
-ENTRY(__hyp_get_vectors)
-	mov	r0, #-1
-ENDPROC(__hyp_get_vectors)
-	@ fall through
 ENTRY(__hyp_set_vectors)
+	mov	r1, r0
+	mov	r0, #HVC_SET_VECTORS
 	__HVC(0)
 	ret	lr
 ENDPROC(__hyp_set_vectors)
 
+ENTRY(__hyp_soft_restart)
+	mov	r1, r0
+	mov	r0, #HVC_SOFT_RESTART
+	__HVC(0)
+	ret	lr
+ENDPROC(__hyp_soft_restart)
+
+ENTRY(__hyp_reset_vectors)
+	mov	r0, #HVC_RESET_VECTORS
+	__HVC(0)
+	ret	lr
+ENDPROC(__hyp_reset_vectors)
+
 #ifndef ZIMAGE
 .align 2
 .L__boot_cpu_mode_offset:
@@ -246,7 +271,7 @@ ENDPROC(__hyp_set_vectors)
 #endif
 
 .align 5
-__hyp_stub_vectors:
+ENTRY(__hyp_stub_vectors)
 __hyp_stub_reset:	W(b)	.
 __hyp_stub_und:		W(b)	.
 __hyp_stub_svc:		W(b)	.

arch/arm/kernel/reboot.c

@@ -12,10 +12,11 @@
 
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
+#include <asm/virt.h>
 
 #include "reboot.h"
 
-typedef void (*phys_reset_t)(unsigned long);
+typedef void (*phys_reset_t)(unsigned long, bool);
 
 /*
  * Function pointers to optional machine specific functions
@@ -51,7 +52,9 @@ static void __soft_restart(void *addr)
 
 	/* Switch to the identity mapping. */
 	phys_reset = (phys_reset_t)virt_to_idmap(cpu_reset);
-	phys_reset((unsigned long)addr);
+
+	/* original stub should be restored by kvm */
+	phys_reset((unsigned long)addr, is_hyp_mode_available());
 
 	/* Should never get here. */
 	BUG();

arch/arm/kvm/arm.c

@@ -53,7 +53,6 @@ __asm__(".arch_extension	virt");
 
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 static kvm_cpu_context_t __percpu *kvm_host_cpu_state;
-static unsigned long hyp_default_vectors;
 
 /* Per-CPU variable containing the currently running vcpu. */
 static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
@@ -227,6 +226,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		else
 			r = kvm->arch.vgic.msis_require_devid;
 		break;
+	case KVM_CAP_ARM_USER_IRQ:
+		/*
+		 * 1: EL1_VTIMER, EL1_PTIMER, and PMU.
+		 * (bump this number if adding more devices)
+		 */
+		r = 1;
+		break;
 	default:
 		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
 		break;
@@ -348,15 +354,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
 
 	kvm_arm_set_running_vcpu(vcpu);
+
+	kvm_vgic_load(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * The arch-generic KVM code expects the cpu field of a vcpu to be -1
-	 * if the vcpu is no longer assigned to a cpu.  This is used for the
-	 * optimized make_all_cpus_request path.
-	 */
+	kvm_vgic_put(vcpu);
+
 	vcpu->cpu = -1;
 
 	kvm_arm_set_running_vcpu(NULL);
@@ -514,13 +519,7 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	/*
-	 * Enable the arch timers only if we have an in-kernel VGIC
-	 * and it has been properly initialized, since we cannot handle
-	 * interrupts from the virtual timer with a userspace gic.
-	 */
-	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
-		ret = kvm_timer_enable(vcpu);
+	ret = kvm_timer_enable(vcpu);
 
 	return ret;
 }
@@ -630,16 +629,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+
 		kvm_pmu_flush_hwstate(vcpu);
+
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
 		local_irq_disable();
 
 		/*
-		 * Re-check atomic conditions
+		 * If we have a singal pending, or need to notify a userspace
+		 * irqchip about timer or PMU level changes, then we exit (and
+		 * update the timer level state in kvm_timer_update_run
+		 * below).
 		 */
-		if (signal_pending(current)) {
+		if (signal_pending(current) ||
+		    kvm_timer_should_notify_user(vcpu) ||
+		    kvm_pmu_should_notify_user(vcpu)) {
 			ret = -EINTR;
 			run->exit_reason = KVM_EXIT_INTR;
 		}
@@ -711,6 +717,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		ret = handle_exit(vcpu, run, ret);
 	}
 
+	/* Tell userspace about in-kernel device output levels */
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
+		kvm_timer_update_run(vcpu);
+		kvm_pmu_update_run(vcpu);
+	}
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	return ret;
@@ -1109,8 +1121,16 @@ static void cpu_init_hyp_mode(void *dummy)
 	kvm_arm_init_debug();
 }
 
+static void cpu_hyp_reset(void)
+{
+	if (!is_kernel_in_hyp_mode())
+		__hyp_reset_vectors();
+}
+
 static void cpu_hyp_reinit(void)
 {
+	cpu_hyp_reset();
+
 	if (is_kernel_in_hyp_mode()) {
 		/*
 		 * __cpu_init_stage2() is safe to call even if the PM
@@ -1118,18 +1138,10 @@ static void cpu_hyp_reinit(void)
 		 */
 		__cpu_init_stage2();
 	} else {
-		if (__hyp_get_vectors() == hyp_default_vectors)
-			cpu_init_hyp_mode(NULL);
+		cpu_init_hyp_mode(NULL);
 	}
 }
 
-static void cpu_hyp_reset(void)
-{
-	if (!is_kernel_in_hyp_mode())
-		__cpu_reset_hyp_mode(hyp_default_vectors,
-				     kvm_get_idmap_start());
-}
-
 static void _kvm_arch_hardware_enable(void *discard)
 {
 	if (!__this_cpu_read(kvm_arm_hardware_enabled)) {
@@ -1312,12 +1324,6 @@ static int init_hyp_mode(void)
 	if (err)
 		goto out_err;
 
-	/*
-	 * It is probably enough to obtain the default on one
-	 * CPU. It's unlikely to be different on the others.
-	 */
-	hyp_default_vectors = __hyp_get_vectors();
-
 	/*
 	 * Allocate stack pages for Hypervisor-mode
 	 */

arch/arm/kvm/coproc.c

@@ -40,6 +40,24 @@
  * Co-processor emulation
  *****************************************************************************/
 
+static bool write_to_read_only(struct kvm_vcpu *vcpu,
+			       const struct coproc_params *params)
+{
+	WARN_ONCE(1, "CP15 write to read-only register\n");
+	print_cp_instr(params);
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+				 const struct coproc_params *params)
+{
+	WARN_ONCE(1, "CP15 read to write-only register\n");
+	print_cp_instr(params);
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
 static u32 cache_levels;
 
@@ -502,15 +520,15 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			return 1;
 		}
-		/* If access function fails, it should complain. */
 	} else {
+		/* If access function fails, it should complain. */
 		kvm_err("Unsupported guest CP15 access at: %08lx\n",
 			*vcpu_pc(vcpu));
 		print_cp_instr(params);
+		kvm_inject_undefined(vcpu);
 	}
-	kvm_inject_undefined(vcpu);
+
 	return 1;
 }
 

arch/arm/kvm/coproc.h

@@ -81,24 +81,6 @@ static inline bool read_zero(struct kvm_vcpu *vcpu,
 	return true;
 }
 
-static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
-				      const struct coproc_params *params)
-{
-	kvm_debug("CP15 write to read-only register at: %08lx\n",
-		  *vcpu_pc(vcpu));
-	print_cp_instr(params);
-	return false;
-}
-
-static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
-					const struct coproc_params *params)
-{
-	kvm_debug("CP15 read to write-only register at: %08lx\n",
-		  *vcpu_pc(vcpu));
-	print_cp_instr(params);
-	return false;
-}
-
 /* Reset functions */
 static inline void reset_unknown(struct kvm_vcpu *vcpu,
 				 const struct coproc_reg *r)

arch/arm/kvm/handle_exit.c

@@ -160,6 +160,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_DATA_ABORT:
 		kvm_inject_vabt(vcpu);
 		return 1;
+	case ARM_EXCEPTION_HYP_GONE:
+		/*
+		 * HYP has been reset to the hyp-stub. This happens
+		 * when a guest is pre-empted by kvm_reboot()'s
+		 * shutdown call.
+		 */
+		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		return 0;
 	default:
 		kvm_pr_unimpl("Unsupported exception type: %d",
 			      exception_index);

arch/arm/kvm/hyp/hyp-entry.S

@@ -126,11 +126,29 @@ hyp_hvc:
 	 */
 	pop	{r0, r1, r2}
 
-	/* Check for __hyp_get_vectors */
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	beq	1f
+	/*
+	 * Check if we have a kernel function, which is guaranteed to be
+	 * bigger than the maximum hyp stub hypercall
+	 */
+	cmp	r0, #HVC_STUB_HCALL_NR
+	bhs	1f
 
+	/*
+	 * Not a kernel function, treat it as a stub hypercall.
+	 * Compute the physical address for __kvm_handle_stub_hvc
+	 * (as the code lives in the idmaped page) and branch there.
+	 * We hijack ip (r12) as a tmp register.
+	 */
+	push	{r1}
+	ldr	r1, =kimage_voffset
+	ldr	r1, [r1]
+	ldr	ip, =__kvm_handle_stub_hvc
+	sub	ip, ip, r1
+	pop	{r1}
+
+	bx	ip
+
+1:
 	push	{lr}
 
 	mov	lr, r0
@@ -142,7 +160,7 @@ THUMB(	orr	lr, #1)
 	blx	lr			@ Call the HYP function
 
 	pop	{lr}
-1:	eret
+	eret
 
 guest_trap:
 	load_vcpu r0			@ Load VCPU pointer to r0

arch/arm/kvm/init.S

@@ -23,6 +23,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/virt.h>
 
 /********************************************************************
  * Hypervisor initialization
@@ -39,6 +40,10 @@
  * - Setup the page tables
  * - Enable the MMU
  * - Profit! (or eret, if you only care about the code).
+ *
+ * Another possibility is to get a HYP stub hypercall.
+ * We discriminate between the two by checking if r0 contains a value
+ * that is less than HVC_STUB_HCALL_NR.
  */
 
 	.text
@@ -58,6 +63,10 @@ __kvm_hyp_init:
 	W(b)	.
 
 __do_hyp_init:
+	@ Check for a stub hypercall
+	cmp	r0, #HVC_STUB_HCALL_NR
+	blo	__kvm_handle_stub_hvc
+
 	@ Set stack pointer
 	mov	sp, r0
 
@@ -112,20 +121,46 @@ __do_hyp_init:
 
 	eret
 
-	@ r0 : stub vectors address
-ENTRY(__kvm_hyp_reset)
+ENTRY(__kvm_handle_stub_hvc)
+	cmp	r0, #HVC_SOFT_RESTART
+	bne	1f
+
+	/* The target is expected in r1 */
+	msr	ELR_hyp, r1
+	mrs	r0, cpsr
+	bic	r0, r0, #MODE_MASK
+	orr	r0, r0, #HYP_MODE
+THUMB(	orr	r0, r0, #PSR_T_BIT	)
+	msr	spsr_cxsf, r0
+	b	reset
+
+1:	cmp	r0, #HVC_RESET_VECTORS
+	bne	1f
+
+reset:
 	/* We're now in idmap, disable MMU */
 	mrc	p15, 4, r1, c1, c0, 0	@ HSCTLR
-	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I)
-	bic	r1, r1, r2
+	ldr	r0, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I)
+	bic	r1, r1, r0
 	mcr	p15, 4, r1, c1, c0, 0	@ HSCTLR
 
-	/* Install stub vectors */
-	mcr	p15, 4, r0, c12, c0, 0	@ HVBAR
-	isb
+	/*
+	 * Install stub vectors, using ardb's VA->PA trick.
+	 */
+0:	adr	r0, 0b					@ PA(0)
+	movw	r1, #:lower16:__hyp_stub_vectors - 0b   @ VA(stub) - VA(0)
+	movt	r1, #:upper16:__hyp_stub_vectors - 0b
+	add	r1, r1, r0				@ PA(stub)
+	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
+	b	exit
+
+1:	ldr	r0, =HVC_STUB_ERR
+	eret
 
+exit:
+	mov	r0, #0
 	eret
-ENDPROC(__kvm_hyp_reset)
+ENDPROC(__kvm_handle_stub_hvc)
 
 	.ltorg
 

arch/arm/kvm/interrupts.S

@@ -37,10 +37,6 @@
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 (strictly 32bit).
  *
- * A function pointer with a value of 0xffffffff has a special meaning,
- * and is used to implement __hyp_get_vectors in the same way as in
- * arch/arm/kernel/hyp_stub.S.
- *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save

arch/arm/kvm/mmu.c

@@ -1512,7 +1512,8 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 			     unsigned long start,
 			     unsigned long end,
 			     int (*handler)(struct kvm *kvm,
-					    gpa_t gpa, void *data),
+					    gpa_t gpa, u64 size,
+					    void *data),
 			     void *data)
 {
 	struct kvm_memslots *slots;
@@ -1524,7 +1525,7 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 	/* we only care about the pages that the guest sees */
 	kvm_for_each_memslot(memslot, slots) {
 		unsigned long hva_start, hva_end;
-		gfn_t gfn, gfn_end;
+		gfn_t gpa;
 
 		hva_start = max(start, memslot->userspace_addr);
 		hva_end = min(end, memslot->userspace_addr +
@@ -1532,25 +1533,16 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 		if (hva_start >= hva_end)
 			continue;
 
-		/*
-		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
-		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
-		 */
-		gfn = hva_to_gfn_memslot(hva_start, memslot);
-		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
-
-		for (; gfn < gfn_end; ++gfn) {
-			gpa_t gpa = gfn << PAGE_SHIFT;
-			ret |= handler(kvm, gpa, data);
-		}
+		gpa = hva_to_gfn_memslot(hva_start, memslot) << PAGE_SHIFT;
+		ret |= handler(kvm, gpa, (u64)(hva_end - hva_start), data);
 	}
 
 	return ret;
 }
 
-static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
+	unmap_stage2_range(kvm, gpa, size);
 	return 0;
 }
 
@@ -1577,10 +1569,11 @@ int kvm_unmap_hva_range(struct kvm *kvm,
 	return 0;
 }
 
-static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
 	pte_t *pte = (pte_t *)data;
 
+	WARN_ON(size != PAGE_SIZE);
 	/*
 	 * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE
 	 * flag clear because MMU notifiers will have unmapped a huge PMD before
@@ -1606,11 +1599,12 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
 }
 
-static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
 	pmd_t *pmd;
 	pte_t *pte;
 
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
 	pmd = stage2_get_pmd(kvm, NULL, gpa);
 	if (!pmd || pmd_none(*pmd))	/* Nothing there */
 		return 0;
@@ -1625,11 +1619,12 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 	return stage2_ptep_test_and_clear_young(pte);
 }
 
-static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
 	pmd_t *pmd;
 	pte_t *pte;
 
+	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
 	pmd = stage2_get_pmd(kvm, NULL, gpa);
 	if (!pmd || pmd_none(*pmd))	/* Nothing there */
 		return 0;
@@ -1674,11 +1669,6 @@ phys_addr_t kvm_get_idmap_vector(void)
 	return hyp_idmap_vector;
 }
 
-phys_addr_t kvm_get_idmap_start(void)
-{
-	return hyp_idmap_start;
-}
-
 static int kvm_map_idmap_text(pgd_t *pgd)
 {
 	int err;

arch/arm/kvm/psci.c

@@ -208,9 +208,10 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
-	int ret = 1;
+	struct kvm *kvm = vcpu->kvm;
 	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
+	int ret = 1;
 
 	switch (psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
@@ -230,7 +231,9 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	case PSCI_0_2_FN_CPU_ON:
 	case PSCI_0_2_FN64_CPU_ON:
+		mutex_lock(&kvm->lock);
 		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
 		break;
 	case PSCI_0_2_FN_AFFINITY_INFO:
 	case PSCI_0_2_FN64_AFFINITY_INFO:
@@ -279,6 +282,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
@@ -288,7 +292,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:
+		mutex_lock(&kvm->lock);
 		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
 		break;
 	default:
 		val = PSCI_RET_NOT_SUPPORTED;

arch/arm/mm/mmu.c

@@ -87,6 +87,8 @@ struct cachepolicy {
 #define s2_policy(policy)	0
 #endif
 
+unsigned long kimage_voffset __ro_after_init;
+
 static struct cachepolicy cache_policies[] __initdata = {
 	{
 		.policy		= "uncached",
@@ -1635,4 +1637,7 @@ void __init paging_init(const struct machine_desc *mdesc)
 
 	empty_zero_page = virt_to_page(zero_page);
 	__flush_dcache_page(NULL, empty_zero_page);
+
+	/* Compute the virt/idmap offset, mostly for the sake of KVM */
+	kimage_voffset = (unsigned long)&kimage_voffset - virt_to_idmap(&kimage_voffset);
 }

arch/arm/mm/proc-v7.S

@@ -39,13 +39,14 @@ ENTRY(cpu_v7_proc_fin)
 ENDPROC(cpu_v7_proc_fin)
 
 /*
- *	cpu_v7_reset(loc)
+ *	cpu_v7_reset(loc, hyp)
  *
  *	Perform a soft reset of the system.  Put the CPU into the
  *	same state as it would be if it had been reset, and branch
  *	to what would be the reset vector.
  *
  *	- loc   - location to jump to for soft reset
+ *	- hyp   - indicate if restart occurs in HYP mode
  *
  *	This code must be executed using a flat identity mapping with
  *      caches disabled.
@@ -53,11 +54,15 @@ ENDPROC(cpu_v7_proc_fin)
 	.align	5
 	.pushsection	.idmap.text, "ax"
 ENTRY(cpu_v7_reset)
-	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
-	bic	r1, r1, #0x1			@ ...............m
- THUMB(	bic	r1, r1, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
-	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
+	mrc	p15, 0, r2, c1, c0, 0		@ ctrl register
+	bic	r2, r2, #0x1			@ ...............m
+ THUMB(	bic	r2, r2, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
+	mcr	p15, 0, r2, c1, c0, 0		@ disable MMU
 	isb
+#ifdef CONFIG_ARM_VIRT_EXT
+	teq	r1, #0
+	bne	__hyp_soft_restart
+#endif
 	bx	r0
 ENDPROC(cpu_v7_reset)
 	.popsection

arch/arm64/include/asm/arch_gicv3.h

@@ -20,69 +20,14 @@
 
 #include <asm/sysreg.h>
 
-#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
-#define ICC_DIR_EL1			sys_reg(3, 0, 12, 11, 1)
-#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
-#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
-#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
-#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
-#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
-#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
-#define ICC_BPR1_EL1			sys_reg(3, 0, 12, 12, 3)
-
-#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-
-/*
- * System register definitions
- */
-#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
-#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
-#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
-#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
-#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
-#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
-#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
-
-#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
-#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
-
-#define ICH_LR0_EL2			__LR0_EL2(0)
-#define ICH_LR1_EL2			__LR0_EL2(1)
-#define ICH_LR2_EL2			__LR0_EL2(2)
-#define ICH_LR3_EL2			__LR0_EL2(3)
-#define ICH_LR4_EL2			__LR0_EL2(4)
-#define ICH_LR5_EL2			__LR0_EL2(5)
-#define ICH_LR6_EL2			__LR0_EL2(6)
-#define ICH_LR7_EL2			__LR0_EL2(7)
-#define ICH_LR8_EL2			__LR8_EL2(0)
-#define ICH_LR9_EL2			__LR8_EL2(1)
-#define ICH_LR10_EL2			__LR8_EL2(2)
-#define ICH_LR11_EL2			__LR8_EL2(3)
-#define ICH_LR12_EL2			__LR8_EL2(4)
-#define ICH_LR13_EL2			__LR8_EL2(5)
-#define ICH_LR14_EL2			__LR8_EL2(6)
-#define ICH_LR15_EL2			__LR8_EL2(7)
-
-#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
-#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
-#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
-#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
-#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
-
-#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
-#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
-#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
-#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
-#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
-
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
 
-#define read_gicreg			read_sysreg_s
-#define write_gicreg			write_sysreg_s
+#define read_gicreg(r)			read_sysreg_s(SYS_ ## r)
+#define write_gicreg(v, r)		write_sysreg_s(v, SYS_ ## r)
 
 /*
  * Low-level accessors
@@ -93,13 +38,13 @@
 
 static inline void gic_write_eoir(u32 irq)
 {
-	write_sysreg_s(irq, ICC_EOIR1_EL1);
+	write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
 	isb();
 }
 
 static inline void gic_write_dir(u32 irq)
 {
-	write_sysreg_s(irq, ICC_DIR_EL1);
+	write_sysreg_s(irq, SYS_ICC_DIR_EL1);
 	isb();
 }
 
@@ -107,7 +52,7 @@ static inline u64 gic_read_iar_common(void)
 {
 	u64 irqstat;
 
-	irqstat = read_sysreg_s(ICC_IAR1_EL1);
+	irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
 	dsb(sy);
 	return irqstat;
 }
@@ -124,7 +69,7 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 	u64 irqstat;
 
 	nops(8);
-	irqstat = read_sysreg_s(ICC_IAR1_EL1);
+	irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
 	nops(4);
 	mb();
 
@@ -133,40 +78,40 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 
 static inline void gic_write_pmr(u32 val)
 {
-	write_sysreg_s(val, ICC_PMR_EL1);
+	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }
 
 static inline void gic_write_ctlr(u32 val)
 {
-	write_sysreg_s(val, ICC_CTLR_EL1);
+	write_sysreg_s(val, SYS_ICC_CTLR_EL1);
 	isb();
 }
 
 static inline void gic_write_grpen1(u32 val)
 {
-	write_sysreg_s(val, ICC_GRPEN1_EL1);
+	write_sysreg_s(val, SYS_ICC_GRPEN1_EL1);
 	isb();
 }
 
 static inline void gic_write_sgi1r(u64 val)
 {
-	write_sysreg_s(val, ICC_SGI1R_EL1);
+	write_sysreg_s(val, SYS_ICC_SGI1R_EL1);
 }
 
 static inline u32 gic_read_sre(void)
 {
-	return read_sysreg_s(ICC_SRE_EL1);
+	return read_sysreg_s(SYS_ICC_SRE_EL1);
 }
 
 static inline void gic_write_sre(u32 val)
 {
-	write_sysreg_s(val, ICC_SRE_EL1);
+	write_sysreg_s(val, SYS_ICC_SRE_EL1);
 	isb();
 }
 
 static inline void gic_write_bpr1(u32 val)
 {
-	asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val));
+	write_sysreg_s(val, SYS_ICC_BPR1_EL1);
 }
 
 #define gic_read_typer(c)		readq_relaxed(c)

arch/arm64/include/asm/kvm_asm.h

@@ -28,7 +28,7 @@
 #define ARM_EXCEPTION_EL1_SERROR  1
 #define ARM_EXCEPTION_TRAP	  2
 /* The hyp-stub will return this for any kvm_call_hyp() call */
-#define ARM_EXCEPTION_HYP_GONE	  3
+#define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
 
 #define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
 #define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
@@ -47,7 +47,6 @@ struct kvm_vcpu;
 
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
-extern char __kvm_hyp_reset[];
 
 extern char __kvm_hyp_vector[];
 
@@ -59,6 +58,8 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);

arch/arm64/include/asm/kvm_host.h

@@ -361,13 +361,6 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
 }
 
-void __kvm_hyp_teardown(void);
-static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
-					phys_addr_t phys_idmap_start)
-{
-	kvm_call_hyp(__kvm_hyp_teardown, phys_idmap_start);
-}
-
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

arch/arm64/include/asm/kvm_mmu.h

@@ -155,7 +155,6 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
-phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

arch/arm64/include/asm/sysreg.h

@@ -48,6 +48,8 @@
 	 ((crn) << CRn_shift) | ((crm) << CRm_shift) | \
 	 ((op2) << Op2_shift))
 
+#define sys_insn	sys_reg
+
 #define sys_reg_Op0(id)	(((id) >> Op0_shift) & Op0_mask)
 #define sys_reg_Op1(id)	(((id) >> Op1_shift) & Op1_mask)
 #define sys_reg_CRn(id)	(((id) >> CRn_shift) & CRn_mask)
@@ -81,6 +83,41 @@
 
 #endif	/* CONFIG_BROKEN_GAS_INST */
 
+#define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
+#define REG_PSTATE_UAO_IMM		sys_reg(0, 0, 4, 0, 3)
+
+#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM |	\
+				      (!!x)<<8 | 0x1f)
+#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM |	\
+				      (!!x)<<8 | 0x1f)
+
+#define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
+#define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
+#define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
+
+#define SYS_OSDTRRX_EL1			sys_reg(2, 0, 0, 0, 2)
+#define SYS_MDCCINT_EL1			sys_reg(2, 0, 0, 2, 0)
+#define SYS_MDSCR_EL1			sys_reg(2, 0, 0, 2, 2)
+#define SYS_OSDTRTX_EL1			sys_reg(2, 0, 0, 3, 2)
+#define SYS_OSECCR_EL1			sys_reg(2, 0, 0, 6, 2)
+#define SYS_DBGBVRn_EL1(n)		sys_reg(2, 0, 0, n, 4)
+#define SYS_DBGBCRn_EL1(n)		sys_reg(2, 0, 0, n, 5)
+#define SYS_DBGWVRn_EL1(n)		sys_reg(2, 0, 0, n, 6)
+#define SYS_DBGWCRn_EL1(n)		sys_reg(2, 0, 0, n, 7)
+#define SYS_MDRAR_EL1			sys_reg(2, 0, 1, 0, 0)
+#define SYS_OSLAR_EL1			sys_reg(2, 0, 1, 0, 4)
+#define SYS_OSLSR_EL1			sys_reg(2, 0, 1, 1, 4)
+#define SYS_OSDLR_EL1			sys_reg(2, 0, 1, 3, 4)
+#define SYS_DBGPRCR_EL1			sys_reg(2, 0, 1, 4, 4)
+#define SYS_DBGCLAIMSET_EL1		sys_reg(2, 0, 7, 8, 6)
+#define SYS_DBGCLAIMCLR_EL1		sys_reg(2, 0, 7, 9, 6)
+#define SYS_DBGAUTHSTATUS_EL1		sys_reg(2, 0, 7, 14, 6)
+#define SYS_MDCCSR_EL0			sys_reg(2, 3, 0, 1, 0)
+#define SYS_DBGDTR_EL0			sys_reg(2, 3, 0, 4, 0)
+#define SYS_DBGDTRRX_EL0		sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGDTRTX_EL0		sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGVCR32_EL2		sys_reg(2, 4, 0, 7, 0)
+
 #define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
@@ -88,6 +125,7 @@
 #define SYS_ID_PFR0_EL1			sys_reg(3, 0, 0, 1, 0)
 #define SYS_ID_PFR1_EL1			sys_reg(3, 0, 0, 1, 1)
 #define SYS_ID_DFR0_EL1			sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_AFR0_EL1			sys_reg(3, 0, 0, 1, 3)
 #define SYS_ID_MMFR0_EL1		sys_reg(3, 0, 0, 1, 4)
 #define SYS_ID_MMFR1_EL1		sys_reg(3, 0, 0, 1, 5)
 #define SYS_ID_MMFR2_EL1		sys_reg(3, 0, 0, 1, 6)
@@ -118,17 +156,127 @@
 #define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
 #define SYS_ID_AA64MMFR2_EL1		sys_reg(3, 0, 0, 7, 2)
 
-#define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
+#define SYS_SCTLR_EL1			sys_reg(3, 0, 1, 0, 0)
+#define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
+#define SYS_CPACR_EL1			sys_reg(3, 0, 1, 0, 2)
+
+#define SYS_TTBR0_EL1			sys_reg(3, 0, 2, 0, 0)
+#define SYS_TTBR1_EL1			sys_reg(3, 0, 2, 0, 1)
+#define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
+
+#define SYS_ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+
+#define SYS_AFSR0_EL1			sys_reg(3, 0, 5, 1, 0)
+#define SYS_AFSR1_EL1			sys_reg(3, 0, 5, 1, 1)
+#define SYS_ESR_EL1			sys_reg(3, 0, 5, 2, 0)
+#define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
+#define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
+
+#define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
+#define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
+
+#define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
+#define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
+
+#define SYS_VBAR_EL1			sys_reg(3, 0, 12, 0, 0)
+
+#define SYS_ICC_DIR_EL1			sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_SGI1R_EL1		sys_reg(3, 0, 12, 11, 5)
+#define SYS_ICC_IAR1_EL1		sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1		sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_BPR1_EL1		sys_reg(3, 0, 12, 12, 3)
+#define SYS_ICC_CTLR_EL1		sys_reg(3, 0, 12, 12, 4)
+#define SYS_ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_GRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
+
+#define SYS_CONTEXTIDR_EL1		sys_reg(3, 0, 13, 0, 1)
+#define SYS_TPIDR_EL1			sys_reg(3, 0, 13, 0, 4)
+
+#define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
+
+#define SYS_CLIDR_EL1			sys_reg(3, 1, 0, 0, 1)
+#define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
+
+#define SYS_CSSELR_EL1			sys_reg(3, 2, 0, 0, 0)
+
 #define SYS_CTR_EL0			sys_reg(3, 3, 0, 0, 1)
 #define SYS_DCZID_EL0			sys_reg(3, 3, 0, 0, 7)
 
-#define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
-#define REG_PSTATE_UAO_IMM		sys_reg(0, 0, 4, 0, 3)
+#define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
+#define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
+#define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
+#define SYS_PMOVSCLR_EL0		sys_reg(3, 3, 9, 12, 3)
+#define SYS_PMSWINC_EL0			sys_reg(3, 3, 9, 12, 4)
+#define SYS_PMSELR_EL0			sys_reg(3, 3, 9, 12, 5)
+#define SYS_PMCEID0_EL0			sys_reg(3, 3, 9, 12, 6)
+#define SYS_PMCEID1_EL0			sys_reg(3, 3, 9, 12, 7)
+#define SYS_PMCCNTR_EL0			sys_reg(3, 3, 9, 13, 0)
+#define SYS_PMXEVTYPER_EL0		sys_reg(3, 3, 9, 13, 1)
+#define SYS_PMXEVCNTR_EL0		sys_reg(3, 3, 9, 13, 2)
+#define SYS_PMUSERENR_EL0		sys_reg(3, 3, 9, 14, 0)
+#define SYS_PMOVSSET_EL0		sys_reg(3, 3, 9, 14, 3)
+
+#define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
+#define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
 
-#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM |	\
-				      (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM |	\
-				      (!!x)<<8 | 0x1f)
+#define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
+
+#define SYS_CNTP_TVAL_EL0		sys_reg(3, 3, 14, 2, 0)
+#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 __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))
+#define __TYPER_CRm(n)			(0xc | (((n) >> 3) & 0x3))
+#define SYS_PMEVTYPERn_EL0(n)		sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
+
+#define SYS_PMCCFILTR_EL0		sys_reg (3, 3, 14, 15, 7)
+
+#define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
+#define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
+#define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
+
+#define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
+#define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
+#define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)
+#define SYS_ICH_AP0R2_EL2		__SYS__AP0Rx_EL2(2)
+#define SYS_ICH_AP0R3_EL2		__SYS__AP0Rx_EL2(3)
+
+#define __SYS__AP1Rx_EL2(x)		sys_reg(3, 4, 12, 9, x)
+#define SYS_ICH_AP1R0_EL2		__SYS__AP1Rx_EL2(0)
+#define SYS_ICH_AP1R1_EL2		__SYS__AP1Rx_EL2(1)
+#define SYS_ICH_AP1R2_EL2		__SYS__AP1Rx_EL2(2)
+#define SYS_ICH_AP1R3_EL2		__SYS__AP1Rx_EL2(3)
+
+#define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
+#define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+#define SYS_ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#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_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
+
+#define __SYS__LR0_EL2(x)		sys_reg(3, 4, 12, 12, x)
+#define SYS_ICH_LR0_EL2			__SYS__LR0_EL2(0)
+#define SYS_ICH_LR1_EL2			__SYS__LR0_EL2(1)
+#define SYS_ICH_LR2_EL2			__SYS__LR0_EL2(2)
+#define SYS_ICH_LR3_EL2			__SYS__LR0_EL2(3)
+#define SYS_ICH_LR4_EL2			__SYS__LR0_EL2(4)
+#define SYS_ICH_LR5_EL2			__SYS__LR0_EL2(5)
+#define SYS_ICH_LR6_EL2			__SYS__LR0_EL2(6)
+#define SYS_ICH_LR7_EL2			__SYS__LR0_EL2(7)
+
+#define __SYS__LR8_EL2(x)		sys_reg(3, 4, 12, 13, x)
+#define SYS_ICH_LR8_EL2			__SYS__LR8_EL2(0)
+#define SYS_ICH_LR9_EL2			__SYS__LR8_EL2(1)
+#define SYS_ICH_LR10_EL2		__SYS__LR8_EL2(2)
+#define SYS_ICH_LR11_EL2		__SYS__LR8_EL2(3)
+#define SYS_ICH_LR12_EL2		__SYS__LR8_EL2(4)
+#define SYS_ICH_LR13_EL2		__SYS__LR8_EL2(5)
+#define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
+#define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_EE    (1 << 25)

arch/arm64/include/asm/virt.h

@@ -19,25 +19,38 @@
 #define __ASM__VIRT_H
 
 /*
- * The arm64 hcall implementation uses x0 to specify the hcall type. A value
- * less than 0xfff indicates a special hcall, such as get/set vector.
- * Any other value is used as a pointer to the function to call.
+ * The arm64 hcall implementation uses x0 to specify the hcall
+ * number. A value less than HVC_STUB_HCALL_NR indicates a special
+ * hcall, such as set vector. Any other value is handled in a
+ * hypervisor specific way.
+ *
+ * The hypercall is allowed to clobber any of the caller-saved
+ * registers (x0-x18), so it is advisable to use it through the
+ * indirection of a function call (as implemented in hyp-stub.S).
  */
 
-/* HVC_GET_VECTORS - Return the value of the vbar_el2 register. */
-#define HVC_GET_VECTORS 0
-
 /*
  * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
  *
  * @x1: Physical address of the new vector table.
  */
-#define HVC_SET_VECTORS 1
+#define HVC_SET_VECTORS 0
 
 /*
  * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
  */
-#define HVC_SOFT_RESTART 2
+#define HVC_SOFT_RESTART 1
+
+/*
+ * HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs
+ */
+#define HVC_RESET_VECTORS 2
+
+/* Max number of HYP stub hypercalls */
+#define HVC_STUB_HCALL_NR 3
+
+/* Error returned when an invalid stub number is passed into x0 */
+#define HVC_STUB_ERR	0xbadca11
 
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
@@ -61,7 +74,7 @@
 extern u32 __boot_cpu_mode[2];
 
 void __hyp_set_vectors(phys_addr_t phys_vector_base);
-phys_addr_t __hyp_get_vectors(void);
+void __hyp_reset_vectors(void);
 
 /* Reports the availability of HYP mode */
 static inline bool is_hyp_mode_available(void)

arch/arm64/include/uapi/asm/kvm.h

@@ -145,6 +145,8 @@ struct kvm_debug_exit_arch {
 #define KVM_GUESTDBG_USE_HW		(1 << 17)
 
 struct kvm_sync_regs {
+	/* Used with KVM_CAP_ARM_USER_IRQ */
+	__u64 device_irq_level;
 };
 
 struct kvm_arch_memory_slot {

arch/arm64/kernel/head.S

@@ -594,14 +594,14 @@ set_hcr:
 	cmp	x0, #1
 	b.ne	3f
 
-	mrs_s	x0, ICC_SRE_EL2
+	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
 	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
-	msr_s	ICC_SRE_EL2, x0
+	msr_s	SYS_ICC_SRE_EL2, x0
 	isb					// Make sure SRE is now set
-	mrs_s	x0, ICC_SRE_EL2			// Read SRE back,
+	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
 	tbz	x0, #0, 3f			// and check that it sticks
-	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
 
 3:
 #endif

arch/arm64/kernel/hyp-stub.S

@@ -55,18 +55,7 @@ ENDPROC(__hyp_stub_vectors)
 	.align 11
 
 el1_sync:
-	mrs	x30, esr_el2
-	lsr	x30, x30, #ESR_ELx_EC_SHIFT
-
-	cmp	x30, #ESR_ELx_EC_HVC64
-	b.ne	9f				// Not an HVC trap
-
-	cmp	x0, #HVC_GET_VECTORS
-	b.ne	1f
-	mrs	x0, vbar_el2
-	b	9f
-
-1:	cmp	x0, #HVC_SET_VECTORS
+	cmp	x0, #HVC_SET_VECTORS
 	b.ne	2f
 	msr	vbar_el2, x1
 	b	9f
@@ -79,10 +68,15 @@ el1_sync:
 	mov	x1, x3
 	br	x4				// no return
 
+3:	cmp	x0, #HVC_RESET_VECTORS
+	beq	9f				// Nothing to reset!
+
 	/* Someone called kvm_call_hyp() against the hyp-stub... */
-3:	mov	x0, #ARM_EXCEPTION_HYP_GONE
+	ldr	x0, =HVC_STUB_ERR
+	eret
 
-9:	eret
+9:	mov	x0, xzr
+	eret
 ENDPROC(el1_sync)
 
 .macro invalid_vector	label
@@ -121,19 +115,15 @@ ENDPROC(\label)
  * initialisation entry point.
  */
 
-ENTRY(__hyp_get_vectors)
-	str	lr, [sp, #-16]!
-	mov	x0, #HVC_GET_VECTORS
-	hvc	#0
-	ldr	lr, [sp], #16
-	ret
-ENDPROC(__hyp_get_vectors)
-
 ENTRY(__hyp_set_vectors)
-	str	lr, [sp, #-16]!
 	mov	x1, x0
 	mov	x0, #HVC_SET_VECTORS
 	hvc	#0
-	ldr	lr, [sp], #16
 	ret
 ENDPROC(__hyp_set_vectors)
+
+ENTRY(__hyp_reset_vectors)
+	mov	x0, #HVC_RESET_VECTORS
+	hvc	#0
+	ret
+ENDPROC(__hyp_reset_vectors)

arch/arm64/kvm/hyp-init.S

@@ -22,6 +22,7 @@
 #include <asm/kvm_mmu.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sysreg.h>
+#include <asm/virt.h>
 
 	.text
 	.pushsection	.hyp.idmap.text, "ax"
@@ -58,6 +59,9 @@ __invalid:
 	 * x2: HYP vectors
 	 */
 __do_hyp_init:
+	/* Check for a stub HVC call */
+	cmp	x0, #HVC_STUB_HCALL_NR
+	b.lo	__kvm_handle_stub_hvc
 
 	msr	ttbr0_el2, x0
 
@@ -119,23 +123,45 @@ __do_hyp_init:
 	eret
 ENDPROC(__kvm_hyp_init)
 
+ENTRY(__kvm_handle_stub_hvc)
+	cmp	x0, #HVC_SOFT_RESTART
+	b.ne	1f
+
+	/* This is where we're about to jump, staying at EL2 */
+	msr	elr_el2, x1
+	mov	x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h)
+	msr	spsr_el2, x0
+
+	/* Shuffle the arguments, and don't come back */
+	mov	x0, x2
+	mov	x1, x3
+	mov	x2, x4
+	b	reset
+
+1:	cmp	x0, #HVC_RESET_VECTORS
+	b.ne	1f
+reset:
 	/*
-	 * Reset kvm back to the hyp stub.
+	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
+	 * case we coming via HVC_SOFT_RESTART.
 	 */
-ENTRY(__kvm_hyp_reset)
-	/* We're now in idmap, disable MMU */
-	mrs	x0, sctlr_el2
-	ldr	x1, =SCTLR_ELx_FLAGS
-	bic	x0, x0, x1		// Clear SCTL_M and etc
-	msr	sctlr_el2, x0
+	mrs	x5, sctlr_el2
+	ldr	x6, =SCTLR_ELx_FLAGS
+	bic	x5, x5, x6		// Clear SCTL_M and etc
+	msr	sctlr_el2, x5
 	isb
 
 	/* Install stub vectors */
-	adr_l	x0, __hyp_stub_vectors
-	msr	vbar_el2, x0
+	adr_l	x5, __hyp_stub_vectors
+	msr	vbar_el2, x5
+	mov	x0, xzr
+	eret
 
+1:	/* Bad stub call */
+	ldr	x0, =HVC_STUB_ERR
 	eret
-ENDPROC(__kvm_hyp_reset)
+
+ENDPROC(__kvm_handle_stub_hvc)
 
 	.ltorg
 

arch/arm64/kvm/hyp.S

@@ -36,15 +36,12 @@
  * passed in x0.
  *
  * A function pointer with a value less than 0xfff has a special meaning,
- * and is used to implement __hyp_get_vectors in the same way as in
+ * and is used to implement hyp stubs in the same way as in
  * arch/arm64/kernel/hyp_stub.S.
- * HVC behaves as a 'bl' call and will clobber lr.
  */
 ENTRY(__kvm_call_hyp)
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	str     lr, [sp, #-16]!
 	hvc	#0
-	ldr     lr, [sp], #16
 	ret
 alternative_else_nop_endif
 	b	__vhe_hyp_call

arch/arm64/kvm/hyp/hyp-entry.S

@@ -32,17 +32,17 @@
 	 * Shuffle the parameters before calling the function
 	 * pointed to in x0. Assumes parameters in x[1,2,3].
 	 */
+	str	lr, [sp, #-16]!
 	mov	lr, x0
 	mov	x0, x1
 	mov	x1, x2
 	mov	x2, x3
 	blr	lr
+	ldr	lr, [sp], #16
 .endm
 
 ENTRY(__vhe_hyp_call)
-	str	lr, [sp, #-16]!
 	do_el2_call
-	ldr	lr, [sp], #16
 	/*
 	 * We used to rely on having an exception return to get
 	 * an implicit isb. In the E2H case, we don't have it anymore.
@@ -53,21 +53,6 @@ ENTRY(__vhe_hyp_call)
 	ret
 ENDPROC(__vhe_hyp_call)
 
-/*
- * Compute the idmap address of __kvm_hyp_reset based on the idmap
- * start passed as a parameter, and jump there.
- *
- * x0: HYP phys_idmap_start
- */
-ENTRY(__kvm_hyp_teardown)
-	mov	x4, x0
-	adr_l	x3, __kvm_hyp_reset
-
-	/* insert __kvm_hyp_reset()s offset into phys_idmap_start */
-	bfi	x4, x3, #0, #PAGE_SHIFT
-	br	x4
-ENDPROC(__kvm_hyp_teardown)
-	
 el1_sync:				// Guest trapped into EL2
 	stp	x0, x1, [sp, #-16]!
 
@@ -87,10 +72,24 @@ alternative_endif
 	/* Here, we're pretty sure the host called HVC. */
 	ldp	x0, x1, [sp], #16
 
-	cmp	x0, #HVC_GET_VECTORS
-	b.ne	1f
-	mrs	x0, vbar_el2
-	b	2f
+	/* Check for a stub HVC call */
+	cmp	x0, #HVC_STUB_HCALL_NR
+	b.hs	1f
+
+	/*
+	 * Compute the idmap address of __kvm_handle_stub_hvc and
+	 * jump there. Since we use kimage_voffset, do not use the
+	 * HYP VA for __kvm_handle_stub_hvc, but the kernel VA instead
+	 * (by loading it from the constant pool).
+	 *
+	 * Preserve x0-x4, which may contain stub parameters.
+	 */
+	ldr	x5, =__kvm_handle_stub_hvc
+	ldr_l	x6, kimage_voffset
+
+	/* x5 = __pa(x5) */
+	sub	x5, x5, x6
+	br	x5
 
 1:
 	/*
@@ -99,7 +98,7 @@ alternative_endif
 	kern_hyp_va	x0
 	do_el2_call
 
-2:	eret
+	eret
 
 el1_trap:
 	/*

arch/arm64/kvm/sys_regs.c

@@ -55,6 +55,15 @@
  * 64bit interface.
  */
 
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+				 const struct sys_reg_params *params)
+{
+	WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
+	print_sys_reg_instr(params);
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
 static u32 cache_levels;
 
@@ -460,35 +469,35 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 }
 
-static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
+static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
 {
 	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+	bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
 
-	return !((reg & ARMV8_PMU_USERENR_EN) || vcpu_mode_priv(vcpu));
+	if (!enabled)
+		kvm_inject_undefined(vcpu);
+
+	return !enabled;
 }
 
-static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
 {
-	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+	return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_EN);
+}
 
-	return !((reg & (ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN))
-		 || vcpu_mode_priv(vcpu));
+static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN);
 }
 
 static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu)
 {
-	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-
-	return !((reg & (ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN))
-		 || vcpu_mode_priv(vcpu));
+	return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN);
 }
 
 static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu)
 {
-	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-
-	return !((reg & (ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN))
-		 || vcpu_mode_priv(vcpu));
+	return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN);
 }
 
 static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -567,8 +576,10 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 
 	pmcr = vcpu_sys_reg(vcpu, PMCR_EL0);
 	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
-	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX)
+	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
+		kvm_inject_undefined(vcpu);
 		return false;
+	}
 
 	return true;
 }
@@ -707,8 +718,10 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (!kvm_arm_pmu_v3_ready(vcpu))
 		return trap_raz_wi(vcpu, p, r);
 
-	if (!vcpu_mode_priv(vcpu))
+	if (!vcpu_mode_priv(vcpu)) {
+		kvm_inject_undefined(vcpu);
 		return false;
+	}
 
 	if (p->is_write) {
 		u64 val = p->regval & mask;
@@ -759,16 +772,15 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (!kvm_arm_pmu_v3_ready(vcpu))
 		return trap_raz_wi(vcpu, p, r);
 
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p);
+
 	if (pmu_write_swinc_el0_disabled(vcpu))
 		return false;
 
-	if (p->is_write) {
-		mask = kvm_pmu_valid_counter_mask(vcpu);
-		kvm_pmu_software_increment(vcpu, p->regval & mask);
-		return true;
-	}
-
-	return false;
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	kvm_pmu_software_increment(vcpu, p->regval & mask);
+	return true;
 }
 
 static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -778,8 +790,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return trap_raz_wi(vcpu, p, r);
 
 	if (p->is_write) {
-		if (!vcpu_mode_priv(vcpu))
+		if (!vcpu_mode_priv(vcpu)) {
+			kvm_inject_undefined(vcpu);
 			return false;
+		}
 
 		vcpu_sys_reg(vcpu, PMUSERENR_EL0) = p->regval
 						    & ARMV8_PMU_USERENR_MASK;
@@ -793,31 +807,23 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
-	/* DBGBVRn_EL1 */						\
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100),	\
+	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
 	  trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr },		\
-	/* DBGBCRn_EL1 */						\
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101),	\
+	{ SYS_DESC(SYS_DBGBCRn_EL1(n)),					\
 	  trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr },		\
-	/* DBGWVRn_EL1 */						\
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110),	\
+	{ SYS_DESC(SYS_DBGWVRn_EL1(n)),					\
 	  trap_wvr, reset_wvr, n, 0,  get_wvr, set_wvr },		\
-	/* DBGWCRn_EL1 */						\
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
+	{ SYS_DESC(SYS_DBGWCRn_EL1(n)),					\
 	  trap_wcr, reset_wcr, n, 0,  get_wcr, set_wcr }
 
 /* Macro to expand the PMEVCNTRn_EL0 register */
 #define PMU_PMEVCNTR_EL0(n)						\
-	/* PMEVCNTRn_EL0 */						\
-	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
-	  CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	{ SYS_DESC(SYS_PMEVCNTRn_EL0(n)),					\
 	  access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
 #define PMU_PMEVTYPER_EL0(n)						\
-	/* PMEVTYPERn_EL0 */						\
-	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
-	  CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
 static bool access_cntp_tval(struct kvm_vcpu *vcpu,
@@ -887,24 +893,14 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
  * more demanding guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
-	/* DC ISW */
-	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010),
-	  access_dcsw },
-	/* DC CSW */
-	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010),
-	  access_dcsw },
-	/* DC CISW */
-	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
-	  access_dcsw },
+	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
 
 	DBG_BCR_BVR_WCR_WVR_EL1(0),
 	DBG_BCR_BVR_WCR_WVR_EL1(1),
-	/* MDCCINT_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
-	  trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
-	/* MDSCR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
-	  trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+	{ SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+	{ SYS_DESC(SYS_MDSCR_EL1), trap_debug_regs, reset_val, MDSCR_EL1, 0 },
 	DBG_BCR_BVR_WCR_WVR_EL1(2),
 	DBG_BCR_BVR_WCR_WVR_EL1(3),
 	DBG_BCR_BVR_WCR_WVR_EL1(4),
@@ -920,179 +916,77 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	DBG_BCR_BVR_WCR_WVR_EL1(14),
 	DBG_BCR_BVR_WCR_WVR_EL1(15),
 
-	/* MDRAR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  trap_raz_wi },
-	/* OSLAR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
-	  trap_raz_wi },
-	/* OSLSR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
-	  trap_oslsr_el1 },
-	/* OSDLR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
-	  trap_raz_wi },
-	/* DBGPRCR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
-	  trap_raz_wi },
-	/* DBGCLAIMSET_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
-	  trap_raz_wi },
-	/* DBGCLAIMCLR_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
-	  trap_raz_wi },
-	/* DBGAUTHSTATUS_EL1 */
-	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
-	  trap_dbgauthstatus_el1 },
-
-	/* MDCCSR_EL1 */
-	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
-	  trap_raz_wi },
-	/* DBGDTR_EL0 */
-	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
-	  trap_raz_wi },
-	/* DBGDTR[TR]X_EL0 */
-	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
-	  trap_raz_wi },
-
-	/* DBGVCR32_EL2 */
-	{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
-	  NULL, reset_val, DBGVCR32_EL2, 0 },
-
-	/* MPIDR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101),
-	  NULL, reset_mpidr, MPIDR_EL1 },
-	/* SCTLR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
-	/* CPACR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
-	  NULL, reset_val, CPACR_EL1, 0 },
-	/* TTBR0_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
-	  access_vm_reg, reset_unknown, TTBR0_EL1 },
-	/* TTBR1_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
-	  access_vm_reg, reset_unknown, TTBR1_EL1 },
-	/* TCR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
-	  access_vm_reg, reset_val, TCR_EL1, 0 },
-
-	/* AFSR0_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
-	  access_vm_reg, reset_unknown, AFSR0_EL1 },
-	/* AFSR1_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
-	  access_vm_reg, reset_unknown, AFSR1_EL1 },
-	/* ESR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
-	  access_vm_reg, reset_unknown, ESR_EL1 },
-	/* FAR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
-	  access_vm_reg, reset_unknown, FAR_EL1 },
-	/* PAR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
-	  NULL, reset_unknown, PAR_EL1 },
-
-	/* PMINTENSET_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
-	  access_pminten, reset_unknown, PMINTENSET_EL1 },
-	/* PMINTENCLR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
-	  access_pminten, NULL, PMINTENSET_EL1 },
-
-	/* MAIR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
-	  access_vm_reg, reset_unknown, MAIR_EL1 },
-	/* AMAIR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
-	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
-
-	/* VBAR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, VBAR_EL1, 0 },
-
-	/* ICC_SGI1R_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
-	  access_gic_sgi },
-	/* ICC_SRE_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
-	  access_gic_sre },
-
-	/* CONTEXTIDR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
-	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
-	/* TPIDR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
-	  NULL, reset_unknown, TPIDR_EL1 },
-
-	/* CNTKCTL_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000),
-	  NULL, reset_val, CNTKCTL_EL1, 0},
-
-	/* CSSELR_EL1 */
-	{ Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, CSSELR_EL1 },
-
-	/* PMCR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
-	  access_pmcr, reset_pmcr, },
-	/* PMCNTENSET_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
-	  access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
-	/* PMCNTENCLR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
-	  access_pmcnten, NULL, PMCNTENSET_EL0 },
-	/* PMOVSCLR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
-	  access_pmovs, NULL, PMOVSSET_EL0 },
-	/* PMSWINC_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
-	  access_pmswinc, reset_unknown, PMSWINC_EL0 },
-	/* PMSELR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
-	  access_pmselr, reset_unknown, PMSELR_EL0 },
-	/* PMCEID0_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
-	  access_pmceid },
-	/* PMCEID1_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
-	  access_pmceid },
-	/* PMCCNTR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
-	  access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
-	/* PMXEVTYPER_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
-	  access_pmu_evtyper },
-	/* PMXEVCNTR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
-	  access_pmu_evcntr },
-	/* PMUSERENR_EL0
-	 * This register resets as unknown in 64bit mode while it resets as zero
+	{ SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_OSLAR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1 },
+	{ SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_DBGCLAIMCLR_EL1), trap_raz_wi },
+	{ SYS_DESC(SYS_DBGAUTHSTATUS_EL1), trap_dbgauthstatus_el1 },
+
+	{ SYS_DESC(SYS_MDCCSR_EL0), trap_raz_wi },
+	{ SYS_DESC(SYS_DBGDTR_EL0), trap_raz_wi },
+	// DBGDTR[TR]X_EL0 share the same encoding
+	{ SYS_DESC(SYS_DBGDTRTX_EL0), trap_raz_wi },
+
+	{ SYS_DESC(SYS_DBGVCR32_EL2), NULL, reset_val, DBGVCR32_EL2, 0 },
+
+	{ SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 },
+	{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
+	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
+	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
+	{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
+
+	{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
+	{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
+	{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
+	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
+	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
+
+	{ SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
+	{ SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, NULL, PMINTENSET_EL1 },
+
+	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
+	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
+
+	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+
+	{ SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi },
+	{ SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre },
+
+	{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
+	{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
+
+	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
+
+	{ SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },
+
+	{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, },
+	{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
+	{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 },
+	{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 },
+	{ SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 },
+	{ SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 },
+	{ SYS_DESC(SYS_PMCEID0_EL0), access_pmceid },
+	{ SYS_DESC(SYS_PMCEID1_EL0), access_pmceid },
+	{ SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
+	{ SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper },
+	{ SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr },
+	/*
+	 * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
-	  access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
-	/* PMOVSSET_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
-	  access_pmovs, reset_unknown, PMOVSSET_EL0 },
-
-	/* TPIDR_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
-	  NULL, reset_unknown, TPIDR_EL0 },
-	/* TPIDRRO_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
-	  NULL, reset_unknown, TPIDRRO_EL0 },
-
-	/* CNTP_TVAL_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b000),
-	  access_cntp_tval },
-	/* CNTP_CTL_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b001),
-	  access_cntp_ctl },
-	/* CNTP_CVAL_EL0 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b010),
-	  access_cntp_cval },
+	{ SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
+	{ SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
+
+	{ 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 },
 
 	/* PMEVCNTRn_EL0 */
 	PMU_PMEVCNTR_EL0(0),
@@ -1158,22 +1052,15 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	PMU_PMEVTYPER_EL0(28),
 	PMU_PMEVTYPER_EL0(29),
 	PMU_PMEVTYPER_EL0(30),
-	/* PMCCFILTR_EL0
-	 * This register resets as unknown in 64bit mode while it resets as zero
+	/*
+	 * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b1111), Op2(0b111),
-	  access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
-
-	/* DACR32_EL2 */
-	{ Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, DACR32_EL2 },
-	/* IFSR32_EL2 */
-	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0000), Op2(0b001),
-	  NULL, reset_unknown, IFSR32_EL2 },
-	/* FPEXC32_EL2 */
-	{ Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0011), Op2(0b000),
-	  NULL, reset_val, FPEXC32_EL2, 0x70 },
+	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+
+	{ 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 },
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
@@ -1557,6 +1444,22 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static void perform_access(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *params,
+			   const struct sys_reg_desc *r)
+{
+	/*
+	 * Not having an accessor means that we have configured a trap
+	 * that we don't know how to handle. This certainly qualifies
+	 * as a gross bug that should be fixed right away.
+	 */
+	BUG_ON(!r->access);
+
+	/* Skip instruction if instructed so */
+	if (likely(r->access(vcpu, params, r)))
+		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+}
+
 /*
  * emulate_cp --  tries to match a sys_reg access in a handling table, and
  *                call the corresponding trap handler.
@@ -1580,20 +1483,8 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 	r = find_reg(params, table, num);
 
 	if (r) {
-		/*
-		 * Not having an accessor means that we have
-		 * configured a trap that we don't know how to
-		 * handle. This certainly qualifies as a gross bug
-		 * that should be fixed right away.
-		 */
-		BUG_ON(!r->access);
-
-		if (likely(r->access(vcpu, params, r))) {
-			/* Skip instruction, since it was emulated */
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			/* Handled */
-			return 0;
-		}
+		perform_access(vcpu, params, r);
+		return 0;
 	}
 
 	/* Not handled */
@@ -1660,20 +1551,25 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
 	}
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
-		goto out;
-	if (!emulate_cp(vcpu, &params, global, nr_global))
-		goto out;
-
-	unhandled_cp_access(vcpu, &params);
+	/*
+	 * Try to emulate the coprocessor access using the target
+	 * specific table first, and using the global table afterwards.
+	 * If either of the tables contains a handler, handle the
+	 * potential register operation in the case of a read and return
+	 * with success.
+	 */
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+	    !emulate_cp(vcpu, &params, global, nr_global)) {
+		/* Split up the value between registers for the read side */
+		if (!params.is_write) {
+			vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+			vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
+		}
 
-out:
-	/* Split up the value between registers for the read side */
-	if (!params.is_write) {
-		vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
-		vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
+		return 1;
 	}
 
+	unhandled_cp_access(vcpu, &params);
 	return 1;
 }
 
@@ -1763,26 +1659,13 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 		r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 
 	if (likely(r)) {
-		/*
-		 * Not having an accessor means that we have
-		 * configured a trap that we don't know how to
-		 * handle. This certainly qualifies as a gross bug
-		 * that should be fixed right away.
-		 */
-		BUG_ON(!r->access);
-
-		if (likely(r->access(vcpu, params, r))) {
-			/* Skip instruction, since it was emulated */
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			return 1;
-		}
-		/* If access function fails, it should complain. */
+		perform_access(vcpu, params, r);
 	} else {
 		kvm_err("Unsupported guest sys_reg access at: %lx\n",
 			*vcpu_pc(vcpu));
 		print_sys_reg_instr(params);
+		kvm_inject_undefined(vcpu);
 	}
-	kvm_inject_undefined(vcpu);
 	return 1;
 }
 
@@ -1932,44 +1815,25 @@ FUNCTION_INVARIANT(aidr_el1)
 
 /* ->val is filled in by kvm_sys_reg_table_init() */
 static struct sys_reg_desc invariant_sys_regs[] = {
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000),
-	  NULL, get_midr_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110),
-	  NULL, get_revidr_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000),
-	  NULL, get_id_pfr0_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001),
-	  NULL, get_id_pfr1_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010),
-	  NULL, get_id_dfr0_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011),
-	  NULL, get_id_afr0_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100),
-	  NULL, get_id_mmfr0_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101),
-	  NULL, get_id_mmfr1_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110),
-	  NULL, get_id_mmfr2_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111),
-	  NULL, get_id_mmfr3_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
-	  NULL, get_id_isar0_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001),
-	  NULL, get_id_isar1_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
-	  NULL, get_id_isar2_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011),
-	  NULL, get_id_isar3_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100),
-	  NULL, get_id_isar4_el1 },
-	{ Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101),
-	  NULL, get_id_isar5_el1 },
-	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001),
-	  NULL, get_clidr_el1 },
-	{ Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111),
-	  NULL, get_aidr_el1 },
-	{ Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001),
-	  NULL, get_ctr_el0 },
+	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
+	{ SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
+	{ SYS_DESC(SYS_ID_PFR0_EL1), NULL, get_id_pfr0_el1 },
+	{ SYS_DESC(SYS_ID_PFR1_EL1), NULL, get_id_pfr1_el1 },
+	{ SYS_DESC(SYS_ID_DFR0_EL1), NULL, get_id_dfr0_el1 },
+	{ SYS_DESC(SYS_ID_AFR0_EL1), NULL, get_id_afr0_el1 },
+	{ SYS_DESC(SYS_ID_MMFR0_EL1), NULL, get_id_mmfr0_el1 },
+	{ SYS_DESC(SYS_ID_MMFR1_EL1), NULL, get_id_mmfr1_el1 },
+	{ SYS_DESC(SYS_ID_MMFR2_EL1), NULL, get_id_mmfr2_el1 },
+	{ SYS_DESC(SYS_ID_MMFR3_EL1), NULL, get_id_mmfr3_el1 },
+	{ SYS_DESC(SYS_ID_ISAR0_EL1), NULL, get_id_isar0_el1 },
+	{ SYS_DESC(SYS_ID_ISAR1_EL1), NULL, get_id_isar1_el1 },
+	{ SYS_DESC(SYS_ID_ISAR2_EL1), NULL, get_id_isar2_el1 },
+	{ SYS_DESC(SYS_ID_ISAR3_EL1), NULL, get_id_isar3_el1 },
+	{ SYS_DESC(SYS_ID_ISAR4_EL1), NULL, get_id_isar4_el1 },
+	{ SYS_DESC(SYS_ID_ISAR5_EL1), NULL, get_id_isar5_el1 },
+	{ SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 },
+	{ SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 },
+	{ SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 },
 };
 
 static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)

arch/arm64/kvm/sys_regs.h

@@ -83,24 +83,6 @@ static inline bool read_zero(struct kvm_vcpu *vcpu,
 	return true;
 }
 
-static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
-				      const struct sys_reg_params *params)
-{
-	kvm_debug("sys_reg write to read-only register at: %lx\n",
-		  *vcpu_pc(vcpu));
-	print_sys_reg_instr(params);
-	return false;
-}
-
-static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
-					const struct sys_reg_params *params)
-{
-	kvm_debug("sys_reg read to write-only register at: %lx\n",
-		  *vcpu_pc(vcpu));
-	print_sys_reg_instr(params);
-	return false;
-}
-
 /* Reset functions */
 static inline void reset_unknown(struct kvm_vcpu *vcpu,
 				 const struct sys_reg_desc *r)
@@ -147,4 +129,9 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 #define CRm(_x) 	.CRm = _x
 #define Op2(_x) 	.Op2 = _x
 
+#define SYS_DESC(reg)					\
+	Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)),	\
+	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
+	Op2(sys_reg_Op2(reg))
+
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */

arch/arm64/kvm/sys_regs_generic_v8.c

@@ -52,9 +52,7 @@ static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
  */
 static const struct sys_reg_desc genericv8_sys_regs[] = {
-	/* ACTLR_EL1 */
-	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
-	  access_actlr, reset_actlr, ACTLR_EL1 },
+	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 };
 
 static const struct sys_reg_desc genericv8_cp15_regs[] = {

include/kvm/arm_arch_timer.h

@@ -63,6 +63,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
+bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
+void kvm_timer_update_run(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
 
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);

include/kvm/arm_pmu.h

@@ -50,6 +50,8 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
+bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
+void kvm_pmu_update_run(struct kvm_vcpu *vcpu);
 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,
@@ -85,6 +87,11 @@ static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void kvm_pmu_update_run(struct kvm_vcpu *vcpu) {}
 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,

include/kvm/arm_vgic.h

@@ -225,8 +225,6 @@ struct vgic_dist {
 struct vgic_v2_cpu_if {
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
-	u32		vgic_misr;	/* Saved only */
-	u64		vgic_eisr;	/* Saved only */
 	u64		vgic_elrsr;	/* Saved only */
 	u32		vgic_apr;
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
@@ -236,8 +234,6 @@ struct vgic_v3_cpu_if {
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
 	u32		vgic_sre;	/* Restored only, change ignored */
-	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr;	/* Saved only */
 	u32		vgic_elrsr;	/* Saved only */
 	u32		vgic_ap0r[4];
 	u32		vgic_ap1r[4];
@@ -264,8 +260,6 @@ struct vgic_cpu {
 	 */
 	struct list_head ap_list_head;
 
-	u64 live_lrs;
-
 	/*
 	 * Members below are used with GICv3 emulation only and represent
 	 * parts of the redistributor.
@@ -306,6 +300,9 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 
+void kvm_vgic_load(struct kvm_vcpu *vcpu);
+void kvm_vgic_put(struct kvm_vcpu *vcpu);
+
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	((k)->arch.vgic.initialized)
 #define vgic_ready(k)		((k)->arch.vgic.ready)

include/uapi/linux/kvm.h

@@ -894,6 +894,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_AIS 141
 #define KVM_CAP_SPAPR_TCE_VFIO 142
 #define KVM_CAP_X86_GUEST_MWAIT 143
+#define KVM_CAP_ARM_USER_IRQ 144
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1371,4 +1372,11 @@ struct kvm_assigned_msix_entry {
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
+/* Available with KVM_CAP_ARM_USER_IRQ */
+
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER		(1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER		(1 << 1)
+#define KVM_ARM_DEV_PMU			(1 << 2)
+
 #endif /* __LINUX_KVM_H */

virt/kvm/arm/arch_timer.c

@@ -184,28 +184,47 @@ bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
 	return cval <= now;
 }
 
+/*
+ * Reflect the timer output level into the kvm_run structure
+ */
+void kvm_timer_update_run(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Populate the device bitmap with the timer states */
+	regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
+				    KVM_ARM_DEV_EL1_PTIMER);
+	if (vtimer->irq.level)
+		regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER;
+	if (ptimer->irq.level)
+		regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
+}
+
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx)
 {
 	int ret;
 
-	BUG_ON(!vgic_initialized(vcpu->kvm));
-
 	timer_ctx->active_cleared_last = false;
 	timer_ctx->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq,
 				   timer_ctx->irq.level);
 
-	ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq,
-				  timer_ctx->irq.level);
-	WARN_ON(ret);
+	if (likely(irqchip_in_kernel(vcpu->kvm))) {
+		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+					  timer_ctx->irq.irq,
+					  timer_ctx->irq.level);
+		WARN_ON(ret);
+	}
 }
 
 /*
  * Check if there was a change in the timer state (should we raise or lower
  * the line level to the GIC).
  */
-static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
+static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
@@ -217,16 +236,14 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 	 * because the guest would never see the interrupt.  Instead wait
 	 * until we call this function from kvm_timer_flush_hwstate.
 	 */
-	if (!vgic_initialized(vcpu->kvm) || !timer->enabled)
-		return -ENODEV;
+	if (unlikely(!timer->enabled))
+		return;
 
 	if (kvm_timer_should_fire(vtimer) != vtimer->irq.level)
 		kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer);
 
 	if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
 		kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
-
-	return 0;
 }
 
 /* Schedule the background timer for the emulated timer. */
@@ -286,25 +303,12 @@ void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
 	timer_disarm(timer);
 }
 
-/**
- * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
- * @vcpu: The vcpu pointer
- *
- * Check if the virtual timer has expired while we were running in the host,
- * and inject an interrupt if that was the case.
- */
-void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+static void kvm_timer_flush_hwstate_vgic(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	bool phys_active;
 	int ret;
 
-	if (kvm_timer_update_state(vcpu))
-		return;
-
-	/* Set the background timer for the physical timer emulation. */
-	kvm_timer_emulate(vcpu, vcpu_ptimer(vcpu));
-
 	/*
 	* If we enter the guest with the virtual input level to the VGIC
 	* asserted, then we have already told the VGIC what we need to, and
@@ -356,11 +360,72 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	vtimer->active_cleared_last = !phys_active;
 }
 
+bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
+	bool vlevel, plevel;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm)))
+		return false;
+
+	vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER;
+	plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER;
+
+	return vtimer->irq.level != vlevel ||
+	       ptimer->irq.level != plevel;
+}
+
+static void kvm_timer_flush_hwstate_user(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
+
+	/*
+	 * To prevent continuously exiting from the guest, we mask the
+	 * physical interrupt such that the guest can make forward progress.
+	 * Once we detect the output level being deasserted, we unmask the
+	 * interrupt again so that we exit from the guest when the timer
+	 * fires.
+	*/
+	if (vtimer->irq.level)
+		disable_percpu_irq(host_vtimer_irq);
+	else
+		enable_percpu_irq(host_vtimer_irq, 0);
+}
+
+/**
+ * kvm_timer_flush_hwstate - prepare timers before running the vcpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the virtual timer has expired while we were running in the host,
+ * and inject an interrupt if that was the case, making sure the timer is
+ * masked or disabled on the host so that we keep executing.  Also schedule a
+ * software timer for the physical timer if it is enabled.
+ */
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+	if (unlikely(!timer->enabled))
+		return;
+
+	kvm_timer_update_state(vcpu);
+
+	/* Set the background timer for the physical timer emulation. */
+	kvm_timer_emulate(vcpu, vcpu_ptimer(vcpu));
+
+	if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+		kvm_timer_flush_hwstate_user(vcpu);
+	else
+		kvm_timer_flush_hwstate_vgic(vcpu);
+}
+
 /**
  * kvm_timer_sync_hwstate - sync timer state from cpu
  * @vcpu: The vcpu pointer
  *
- * Check if the virtual timer has expired while we were running in the guest,
+ * Check if any of the timers have expired while we were running in the guest,
  * and inject an interrupt if that was the case.
  */
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
@@ -560,6 +625,13 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (timer->enabled)
 		return 0;
 
+	/* Without a VGIC we do not map virtual IRQs to physical IRQs */
+	if (!irqchip_in_kernel(vcpu->kvm))
+		goto no_vgic;
+
+	if (!vgic_initialized(vcpu->kvm))
+		return -ENODEV;
+
 	/*
 	 * Find the physical IRQ number corresponding to the host_vtimer_irq
 	 */
@@ -583,8 +655,8 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+no_vgic:
 	timer->enabled = 1;
-
 	return 0;
 }
 

virt/kvm/arm/hyp/vgic-v2-sr.c

@@ -22,49 +22,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
-static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
-					    void __iomem *base)
-{
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
-	u32 eisr0, eisr1;
-	int i;
-	bool expect_mi;
-
-	expect_mi = !!(cpu_if->vgic_hcr & GICH_HCR_UIE);
-
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
-		expect_mi |= (!(cpu_if->vgic_lr[i] & GICH_LR_HW) &&
-			      (cpu_if->vgic_lr[i] & GICH_LR_EOI));
-	}
-
-	if (expect_mi) {
-		cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
-
-		if (cpu_if->vgic_misr & GICH_MISR_EOI) {
-			eisr0  = readl_relaxed(base + GICH_EISR0);
-			if (unlikely(nr_lr > 32))
-				eisr1  = readl_relaxed(base + GICH_EISR1);
-			else
-				eisr1 = 0;
-		} else {
-			eisr0 = eisr1 = 0;
-		}
-	} else {
-		cpu_if->vgic_misr = 0;
-		eisr0 = eisr1 = 0;
-	}
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1;
-#else
-	cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0;
-#endif
-}
-
 static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -87,13 +44,10 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-			continue;
-
+	for (i = 0; i < used_lrs; i++) {
 		if (cpu_if->vgic_elrsr & (1UL << i))
 			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
 		else
@@ -110,26 +64,20 @@ void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
 	if (!base)
 		return;
 
-	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
-
-	if (vcpu->arch.vgic_cpu.live_lrs) {
+	if (used_lrs) {
 		cpu_if->vgic_apr = readl_relaxed(base + GICH_APR);
 
-		save_maint_int_state(vcpu, base);
 		save_elrsr(vcpu, base);
 		save_lrs(vcpu, base);
 
 		writel_relaxed(0, base + GICH_HCR);
-
-		vcpu->arch.vgic_cpu.live_lrs = 0;
 	} else {
-		cpu_if->vgic_eisr = 0;
 		cpu_if->vgic_elrsr = ~0UL;
-		cpu_if->vgic_misr = 0;
 		cpu_if->vgic_apr = 0;
 	}
 }
@@ -141,32 +89,20 @@ void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
-	u64 live_lrs = 0;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 
 	if (!base)
 		return;
 
-
-	for (i = 0; i < nr_lr; i++)
-		if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
-			live_lrs |= 1UL << i;
-
-	if (live_lrs) {
+	if (used_lrs) {
 		writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
 		writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
-		for (i = 0; i < nr_lr; i++) {
-			if (!(live_lrs & (1UL << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++) {
 			writel_relaxed(cpu_if->vgic_lr[i],
 				       base + GICH_LR0 + (i * 4));
 		}
 	}
-
-	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
-	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 }
 
 #ifdef CONFIG_ARM64

virt/kvm/arm/hyp/vgic-v3-sr.c

@@ -118,66 +118,32 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
 	}
 }
 
-static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr)
-{
-	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
-	int i;
-	bool expect_mi;
-
-	expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE);
-
-	for (i = 0; i < nr_lr; i++) {
-		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
-		expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) &&
-			      (cpu_if->vgic_lr[i] & ICH_LR_EOI));
-	}
-
-	if (expect_mi) {
-		cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
-
-		if (cpu_if->vgic_misr & ICH_MISR_EOI)
-			cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2);
-		else
-			cpu_if->vgic_eisr = 0;
-	} else {
-		cpu_if->vgic_misr = 0;
-		cpu_if->vgic_eisr = 0;
-	}
-}
-
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	u64 val;
 
 	/*
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	if (!cpu_if->vgic_sre)
+	if (!cpu_if->vgic_sre) {
 		dsb(st);
+		cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);
+	}
 
-	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
-
-	if (vcpu->arch.vgic_cpu.live_lrs) {
+	if (used_lrs) {
 		int i;
-		u32 max_lr_idx, nr_pri_bits;
+		u32 nr_pri_bits;
 
 		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
 		write_gicreg(0, ICH_HCR_EL2);
 		val = read_gicreg(ICH_VTR_EL2);
-		max_lr_idx = vtr_to_max_lr_idx(val);
 		nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-		save_maint_int_state(vcpu, max_lr_idx + 1);
-
-		for (i = 0; i <= max_lr_idx; i++) {
-			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++) {
 			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
 			else
@@ -205,11 +171,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 		default:
 			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
 		}
-
-		vcpu->arch.vgic_cpu.live_lrs = 0;
 	} else {
-		cpu_if->vgic_misr  = 0;
-		cpu_if->vgic_eisr  = 0;
 		cpu_if->vgic_elrsr = 0xffff;
 		cpu_if->vgic_ap0r[0] = 0;
 		cpu_if->vgic_ap0r[1] = 0;
@@ -234,9 +196,9 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	u64 val;
-	u32 max_lr_idx, nr_pri_bits;
-	u16 live_lrs = 0;
+	u32 nr_pri_bits;
 	int i;
 
 	/*
@@ -245,25 +207,19 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * delivered as a FIQ to the guest, with potentially fatal
 	 * consequences. So we must make sure that ICC_SRE_EL1 has
 	 * been actually programmed with the value we want before
-	 * starting to mess with the rest of the GIC.
+	 * starting to mess with the rest of the GIC, and VMCR_EL2 in
+	 * particular.
 	 */
 	if (!cpu_if->vgic_sre) {
 		write_gicreg(0, ICC_SRE_EL1);
 		isb();
+		write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
 	}
 
 	val = read_gicreg(ICH_VTR_EL2);
-	max_lr_idx = vtr_to_max_lr_idx(val);
 	nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	for (i = 0; i <= max_lr_idx; i++) {
-		if (cpu_if->vgic_lr[i] & ICH_LR_STATE)
-			live_lrs |= (1 << i);
-	}
-
-	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
-
-	if (live_lrs) {
+	if (used_lrs) {
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 
 		switch (nr_pri_bits) {
@@ -286,12 +242,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
 		}
 
-		for (i = 0; i <= max_lr_idx; i++) {
-			if (!(live_lrs & (1 << i)))
-				continue;
-
+		for (i = 0; i < used_lrs; i++)
 			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
-		}
 	}
 
 	/*
@@ -303,7 +255,6 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 		isb();
 		dsb(sy);
 	}
-	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
@@ -326,3 +277,13 @@ u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
 }
+
+u64 __hyp_text __vgic_v3_read_vmcr(void)
+{
+	return read_gicreg(ICH_VMCR_EL2);
+}
+
+void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
+{
+	write_gicreg(vmcr, ICH_VMCR_EL2);
+}

virt/kvm/arm/pmu.c

@@ -230,13 +230,44 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 		return;
 
 	overflow = !!kvm_pmu_overflow_status(vcpu);
-	if (pmu->irq_level != overflow) {
-		pmu->irq_level = overflow;
-		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-				    pmu->irq_num, overflow);
+	if (pmu->irq_level == overflow)
+		return;
+
+	pmu->irq_level = overflow;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm))) {
+		int ret;
+		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+					  pmu->irq_num, overflow);
+		WARN_ON(ret);
 	}
 }
 
+bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
+	bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU;
+
+	if (likely(irqchip_in_kernel(vcpu->kvm)))
+		return false;
+
+	return pmu->irq_level != run_level;
+}
+
+/*
+ * Reflect the PMU overflow interrupt output level into the kvm_run structure
+ */
+void kvm_pmu_update_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Populate the timer bitmap for user space */
+	regs->device_irq_level &= ~KVM_ARM_DEV_PMU;
+	if (vcpu->arch.pmu.irq_level)
+		regs->device_irq_level |= KVM_ARM_DEV_PMU;
+}
+
 /**
  * kvm_pmu_flush_hwstate - flush pmu state to cpu
  * @vcpu: The vcpu pointer

virt/kvm/arm/vgic/vgic-init.c

@@ -24,7 +24,12 @@
 
 /*
  * Initialization rules: there are multiple stages to the vgic
- * initialization, both for the distributor and the CPU interfaces.
+ * initialization, both for the distributor and the CPU interfaces.  The basic
+ * idea is that even though the VGIC is not functional or not requested from
+ * user space, the critical path of the run loop can still call VGIC functions
+ * that just won't do anything, without them having to check additional
+ * initialization flags to ensure they don't look at uninitialized data
+ * structures.
  *
  * Distributor:
  *
@@ -39,23 +44,67 @@
  *
  * CPU Interface:
  *
- * - kvm_vgic_cpu_early_init(): initialization of static data that
+ * - kvm_vgic_vcpu_early_init(): initialization of static data that
  *   doesn't depend on any sizing information or emulation type. No
  *   allocation is allowed there.
  */
 
 /* EARLY INIT */
 
-/*
- * Those 2 functions should not be needed anymore but they
- * still are called from arm.c
+/**
+ * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures
+ * @kvm: The VM whose VGIC districutor should be initialized
+ *
+ * Only do initialization of static structures that don't require any
+ * allocation or sizing information from userspace.  vgic_init() called
+ * kvm_vgic_dist_init() which takes care of the rest.
  */
 void kvm_vgic_early_init(struct kvm *kvm)
 {
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	INIT_LIST_HEAD(&dist->lpi_list_head);
+	spin_lock_init(&dist->lpi_list_lock);
 }
 
+/**
+ * kvm_vgic_vcpu_early_init() - Initialize static VGIC VCPU data structures
+ * @vcpu: The VCPU whose VGIC data structures whould be initialized
+ *
+ * Only do initialization, but do not actually enable the VGIC CPU interface
+ * yet.
+ */
 void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
 {
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	int i;
+
+	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+	spin_lock_init(&vgic_cpu->ap_list_lock);
+
+	/*
+	 * Enable and configure all SGIs to be edge-triggered and
+	 * configure all PPIs as level-triggered.
+	 */
+	for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+
+		INIT_LIST_HEAD(&irq->ap_list);
+		spin_lock_init(&irq->irq_lock);
+		irq->intid = i;
+		irq->vcpu = NULL;
+		irq->target_vcpu = vcpu;
+		irq->targets = 1U << vcpu->vcpu_id;
+		kref_init(&irq->refcount);
+		if (vgic_irq_is_sgi(i)) {
+			/* SGIs */
+			irq->enabled = 1;
+			irq->config = VGIC_CONFIG_EDGE;
+		} else {
+			/* PPIs */
+			irq->config = VGIC_CONFIG_LEVEL;
+		}
+	}
 }
 
 /* CREATION */
@@ -148,9 +197,6 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
 	int i;
 
-	INIT_LIST_HEAD(&dist->lpi_list_head);
-	spin_lock_init(&dist->lpi_list_lock);
-
 	dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
 	if (!dist->spis)
 		return  -ENOMEM;
@@ -181,41 +227,11 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 }
 
 /**
- * kvm_vgic_vcpu_init: initialize the vcpu data structures and
- * enable the VCPU interface
- * @vcpu: the VCPU which's VGIC should be initialized
+ * kvm_vgic_vcpu_init() - Enable the VCPU interface
+ * @vcpu: the VCPU which's VGIC should be enabled
  */
 static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	int i;
-
-	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	spin_lock_init(&vgic_cpu->ap_list_lock);
-
-	/*
-	 * Enable and configure all SGIs to be edge-triggered and
-	 * configure all PPIs as level-triggered.
-	 */
-	for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
-
-		INIT_LIST_HEAD(&irq->ap_list);
-		spin_lock_init(&irq->irq_lock);
-		irq->intid = i;
-		irq->vcpu = NULL;
-		irq->target_vcpu = vcpu;
-		irq->targets = 1U << vcpu->vcpu_id;
-		kref_init(&irq->refcount);
-		if (vgic_irq_is_sgi(i)) {
-			/* SGIs */
-			irq->enabled = 1;
-			irq->config = VGIC_CONFIG_EDGE;
-		} else {
-			/* PPIs */
-			irq->config = VGIC_CONFIG_LEVEL;
-		}
-	}
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_enable(vcpu);
 	else
@@ -262,6 +278,18 @@ int vgic_init(struct kvm *kvm)
 	vgic_debug_init(kvm);
 
 	dist->initialized = true;
+
+	/*
+	 * If we're initializing GICv2 on-demand when first running the VCPU
+	 * then we need to load the VGIC state onto the CPU.  We can detect
+	 * this easily by checking if we are in between vcpu_load and vcpu_put
+	 * when we just initialized the VGIC.
+	 */
+	preempt_disable();
+	vcpu = kvm_arm_get_running_vcpu();
+	if (vcpu)
+		kvm_vgic_load(vcpu);
+	preempt_enable();
 out:
 	return ret;
 }

virt/kvm/arm/vgic/vgic-v2.c

@@ -22,59 +22,17 @@
 
 #include "vgic.h"
 
-/*
- * Call this function to convert a u64 value to an unsigned long * bitmask
- * in a way that works on both 32-bit and 64-bit LE and BE platforms.
- *
- * Warning: Calling this function may modify *val.
- */
-static unsigned long *u64_to_bitmask(u64 *val)
-{
-#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
-	*val = (*val >> 32) | (*val << 32);
-#endif
-	return (unsigned long *)val;
-}
-
-void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
+void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
 
-	if (cpuif->vgic_misr & GICH_MISR_EOI) {
-		u64 eisr = cpuif->vgic_eisr;
-		unsigned long *eisr_bmap = u64_to_bitmask(&eisr);
-		int lr;
-
-		for_each_set_bit(lr, eisr_bmap, kvm_vgic_global_state.nr_lr) {
-			u32 intid = cpuif->vgic_lr[lr] & GICH_LR_VIRTUALID;
-
-			WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE);
-
-			/* Only SPIs require notification */
-			if (vgic_valid_spi(vcpu->kvm, intid))
-				kvm_notify_acked_irq(vcpu->kvm, 0,
-						     intid - VGIC_NR_PRIVATE_IRQS);
-		}
-	}
-
-	/* check and disable underflow maintenance IRQ */
-	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
-
-	/*
-	 * In the next iterations of the vcpu loop, if we sync the
-	 * vgic state after flushing it, but before entering the guest
-	 * (this happens for pending signals and vmid rollovers), then
-	 * make sure we don't pick up any old maintenance interrupts
-	 * here.
-	 */
-	cpuif->vgic_eisr = 0;
+	cpuif->vgic_hcr |= GICH_HCR_UIE;
 }
 
-void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
+static bool lr_signals_eoi_mi(u32 lr_val)
 {
-	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
-	cpuif->vgic_hcr |= GICH_HCR_UIE;
+	return !(lr_val & GICH_LR_STATE) && (lr_val & GICH_LR_EOI) &&
+	       !(lr_val & GICH_LR_HW);
 }
 
 /*
@@ -86,14 +44,22 @@ void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
  */
 void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2;
 	int lr;
 
-	for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
+
+	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u32 val = cpuif->vgic_lr[lr];
 		u32 intid = val & GICH_LR_VIRTUALID;
 		struct vgic_irq *irq;
 
+		/* Notify fds when the guest EOI'ed a level-triggered SPI */
+		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
+			kvm_notify_acked_irq(vcpu->kvm, 0,
+					     intid - VGIC_NR_PRIVATE_IRQS);
+
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
 
 		spin_lock(&irq->irq_lock);
@@ -126,6 +92,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
+
+	vgic_cpu->used_lrs = 0;
 }
 
 /*
@@ -184,6 +152,7 @@ void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr)
 
 void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	u32 vmcr;
 
 	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
@@ -194,12 +163,15 @@ void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
 		GICH_VMCR_PRIMASK_MASK;
 
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+	cpu_if->vgic_vmcr = vmcr;
 }
 
 void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	u32 vmcr;
+
+	vmcr = cpu_if->vgic_vmcr;
 
 	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
 			GICH_VMCR_CTRL_SHIFT;
@@ -375,3 +347,19 @@ out:
 
 	return ret;
 }
+
+void vgic_v2_load(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &vcpu->kvm->arch.vgic;
+
+	writel_relaxed(cpu_if->vgic_vmcr, vgic->vctrl_base + GICH_VMCR);
+}
+
+void vgic_v2_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &vcpu->kvm->arch.vgic;
+
+	cpu_if->vgic_vmcr = readl_relaxed(vgic->vctrl_base + GICH_VMCR);
+}

virt/kvm/arm/vgic/vgic-v3.c

@@ -21,59 +21,29 @@
 
 #include "vgic.h"
 
-void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu)
+void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-	u32 model = vcpu->kvm->arch.vgic.vgic_model;
-
-	if (cpuif->vgic_misr & ICH_MISR_EOI) {
-		unsigned long eisr_bmap = cpuif->vgic_eisr;
-		int lr;
-
-		for_each_set_bit(lr, &eisr_bmap, kvm_vgic_global_state.nr_lr) {
-			u32 intid;
-			u64 val = cpuif->vgic_lr[lr];
-
-			if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
-				intid = val & ICH_LR_VIRTUAL_ID_MASK;
-			else
-				intid = val & GICH_LR_VIRTUALID;
-
-			WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE);
-
-			/* Only SPIs require notification */
-			if (vgic_valid_spi(vcpu->kvm, intid))
-				kvm_notify_acked_irq(vcpu->kvm, 0,
-						     intid - VGIC_NR_PRIVATE_IRQS);
-		}
-
-		/*
-		 * In the next iterations of the vcpu loop, if we sync
-		 * the vgic state after flushing it, but before
-		 * entering the guest (this happens for pending
-		 * signals and vmid rollovers), then make sure we
-		 * don't pick up any old maintenance interrupts here.
-		 */
-		cpuif->vgic_eisr = 0;
-	}
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	cpuif->vgic_hcr |= ICH_HCR_UIE;
 }
 
-void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
+static bool lr_signals_eoi_mi(u64 lr_val)
 {
-	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
-	cpuif->vgic_hcr |= ICH_HCR_UIE;
+	return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) &&
+	       !(lr_val & ICH_LR_HW);
 }
 
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 {
-	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
 	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	int lr;
 
-	for (lr = 0; lr < vcpu->arch.vgic_cpu.used_lrs; lr++) {
+	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+
+	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];
 		u32 intid;
 		struct vgic_irq *irq;
@@ -82,6 +52,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 			intid = val & ICH_LR_VIRTUAL_ID_MASK;
 		else
 			intid = val & GICH_LR_VIRTUALID;
+
+		/* Notify fds when the guest EOI'ed a level-triggered IRQ */
+		if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
+			kvm_notify_acked_irq(vcpu->kvm, 0,
+					     intid - VGIC_NR_PRIVATE_IRQS);
+
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
 		if (!irq)	/* An LPI could have been unmapped. */
 			continue;
@@ -117,6 +93,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
+
+	vgic_cpu->used_lrs = 0;
 }
 
 /* Requires the irq to be locked already */
@@ -173,6 +151,7 @@ void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr)
 
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u32 vmcr;
 
 	/*
@@ -188,12 +167,15 @@ void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK;
 	vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK;
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+	cpu_if->vgic_vmcr = vmcr;
 }
 
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 vmcr;
+
+	vmcr = cpu_if->vgic_vmcr;
 
 	/*
 	 * Ignore the FIQen bit, because GIC emulation always implies
@@ -386,3 +368,24 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 
 	return 0;
 }
+
+void vgic_v3_load(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	/*
+	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
+	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
+	 * VMCR_EL2 save/restore in the world switch.
+	 */
+	if (likely(cpu_if->vgic_sre))
+		kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr);
+}
+
+void vgic_v3_put(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	if (likely(cpu_if->vgic_sre))
+		cpu_if->vgic_vmcr = kvm_call_hyp(__vgic_v3_read_vmcr);
+}

virt/kvm/arm/vgic/vgic.c

@@ -527,14 +527,6 @@ retry:
 	spin_unlock(&vgic_cpu->ap_list_lock);
 }
 
-static inline void vgic_process_maintenance_interrupt(struct kvm_vcpu *vcpu)
-{
-	if (kvm_vgic_global_state.type == VGIC_V2)
-		vgic_v2_process_maintenance(vcpu);
-	else
-		vgic_v3_process_maintenance(vcpu);
-}
-
 static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vgic_global_state.type == VGIC_V2)
@@ -601,10 +593,8 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 
 	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
 
-	if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr) {
-		vgic_set_underflow(vcpu);
+	if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr)
 		vgic_sort_ap_list(vcpu);
-	}
 
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		spin_lock(&irq->irq_lock);
@@ -623,8 +613,12 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 next:
 		spin_unlock(&irq->irq_lock);
 
-		if (count == kvm_vgic_global_state.nr_lr)
+		if (count == kvm_vgic_global_state.nr_lr) {
+			if (!list_is_last(&irq->ap_list,
+					  &vgic_cpu->ap_list_head))
+				vgic_set_underflow(vcpu);
 			break;
+		}
 	}
 
 	vcpu->arch.vgic_cpu.used_lrs = count;
@@ -637,18 +631,30 @@ next:
 /* Sync back the hardware VGIC state into our emulation after a guest's run. */
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(!vgic_initialized(vcpu->kvm)))
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	/* An empty ap_list_head implies used_lrs == 0 */
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
 
-	vgic_process_maintenance_interrupt(vcpu);
-	vgic_fold_lr_state(vcpu);
+	if (vgic_cpu->used_lrs)
+		vgic_fold_lr_state(vcpu);
 	vgic_prune_ap_list(vcpu);
 }
 
 /* Flush our emulation state into the GIC hardware before entering the guest. */
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(!vgic_initialized(vcpu->kvm)))
+	/*
+	 * If there are no virtual interrupts active or pending for this
+	 * VCPU, then there is no work to do and we can bail out without
+	 * taking any lock.  There is a potential race with someone injecting
+	 * interrupts to the VCPU, but it is a benign race as the VCPU will
+	 * either observe the new interrupt before or after doing this check,
+	 * and introducing additional synchronization mechanism doesn't change
+	 * this.
+	 */
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
 
 	spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
@@ -656,6 +662,28 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
 }
 
+void kvm_vgic_load(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!vgic_initialized(vcpu->kvm)))
+		return;
+
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_load(vcpu);
+	else
+		vgic_v3_load(vcpu);
+}
+
+void kvm_vgic_put(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(!vgic_initialized(vcpu->kvm)))
+		return;
+
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_put(vcpu);
+	else
+		vgic_v3_put(vcpu);
+}
+
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

virt/kvm/arm/vgic/vgic.h

@@ -112,7 +112,6 @@ void vgic_kick_vcpus(struct kvm *kvm);
 int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
 		      phys_addr_t addr, phys_addr_t alignment);
 
-void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr);
@@ -130,6 +129,9 @@ int vgic_v2_map_resources(struct kvm *kvm);
 int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 			     enum vgic_type);
 
+void vgic_v2_load(struct kvm_vcpu *vcpu);
+void vgic_v2_put(struct kvm_vcpu *vcpu);
+
 static inline void vgic_get_irq_kref(struct vgic_irq *irq)
 {
 	if (irq->intid < VGIC_MIN_LPI)
@@ -138,7 +140,6 @@ static inline void vgic_get_irq_kref(struct vgic_irq *irq)
 	kref_get(&irq->refcount);
 }
 
-void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr);
@@ -150,6 +151,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
 
+void vgic_v3_load(struct kvm_vcpu *vcpu);
+void vgic_v3_put(struct kvm_vcpu *vcpu);
+
 int vgic_register_its_iodevs(struct kvm *kvm);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);