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
-ENDPROC(__kvm_hyp_reset)
+
+exit:
+	mov	r0, #0
+	eret
+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;