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

Pull KVM updates from Paolo Bonzini:

 - ARM: GICv3 ITS emulation and various fixes.  Removal of the
   old VGIC implementation.

 - s390: support for trapping software breakpoints, nested
   virtualization (vSIE), the STHYI opcode, initial extensions
   for CPU model support.

 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots
   of cleanups, preliminary to this and the upcoming support for
   hardware virtualization extensions.

 - x86: support for execute-only mappings in nested EPT; reduced
   vmexit latency for TSC deadline timer (by about 30%) on Intel
   hosts; support for more than 255 vCPUs.

 - PPC: bugfixes.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (302 commits)
  KVM: PPC: Introduce KVM_CAP_PPC_HTM
  MIPS: Select HAVE_KVM for MIPS64_R{2,6}
  MIPS: KVM: Reset CP0_PageMask during host TLB flush
  MIPS: KVM: Fix ptr->int cast via KVM_GUEST_KSEGX()
  MIPS: KVM: Sign extend MFC0/RDHWR results
  MIPS: KVM: Fix 64-bit big endian dynamic translation
  MIPS: KVM: Fail if ebase doesn't fit in CP0_EBase
  MIPS: KVM: Use 64-bit CP0_EBase when appropriate
  MIPS: KVM: Set CP0_Status.KX on MIPS64
  MIPS: KVM: Make entry code MIPS64 friendly
  MIPS: KVM: Use kmap instead of CKSEG0ADDR()
  MIPS: KVM: Use virt_to_phys() to get commpage PFN
  MIPS: Fix definition of KSEGX() for 64-bit
  KVM: VMX: Add VMCS to CPU's loaded VMCSs before VMPTRLD
  kvm: x86: nVMX: maintain internal copy of current VMCS
  KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE
  KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures
  KVM: arm64: vgic-its: Simplify MAPI error handling
  KVM: arm64: vgic-its: Make vgic_its_cmd_handle_mapi similar to other handlers
  KVM: arm64: vgic-its: Turn device_id validation into generic ID validation
  ...

14 files changed, 124 insertions, 194 deletions

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 3d5a5cd071bd..58faff5f1eb2 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -66,6 +66,8 @@ extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
+
+extern void __kvm_hyp_reset(unsigned long);
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 96387d477e91..de338d93d11b 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -241,8 +241,7 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
 
-static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
-				       phys_addr_t pgd_ptr,
+static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
@@ -251,18 +250,13 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	 * code. The init code doesn't need to preserve these
 	 * registers as r0-r3 are already callee saved according to
 	 * the AAPCS.
-	 * Note that we slightly misuse the prototype by casing the
+	 * Note that we slightly misuse the prototype by casting the
 	 * stack pointer to a void *.
-	 *
-	 * We don't have enough registers to perform the full init in
-	 * one go.  Install the boot PGD first, and then install the
-	 * runtime PGD, stack pointer and vectors. The PGDs are always
-	 * passed as the third argument, in order to be passed into
-	 * r2-r3 to the init code (yes, this is compliant with the
-	 * PCS!).
-	 */
 
-	kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+	 * The PGDs are always passed as the third argument, in order
+	 * to be passed into r2-r3 to the init code (yes, this is
+	 * compliant with the PCS!).
+	 */
 
 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
@@ -272,16 +266,13 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
-static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
 					phys_addr_t phys_idmap_start)
 {
-	/*
-	 * TODO
-	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
-	 */
+	kvm_call_hyp((void *)virt_to_idmap(__kvm_hyp_reset), vector_ptr);
 }
 
-static inline int kvm_arch_dev_ioctl_check_extension(long ext)
+static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;
 }
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index f0e860761380..6eaff28f2ff3 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -25,9 +25,6 @@
 
 #define __hyp_text __section(.hyp.text) notrace
 
-#define kern_hyp_va(v) (v)
-#define hyp_kern_va(v) (v)
-
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
 	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
 #define __ACCESS_CP15_64(Op1, CRm)		\
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index f9a65061130b..3bb803d6814b 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -26,16 +26,7 @@
  * We directly use the kernel VA for the HYP, as we can directly share
  * the mapping (HTTBR "covers" TTBR1).
  */
-#define HYP_PAGE_OFFSET_MASK	UL(~0)
-#define HYP_PAGE_OFFSET		PAGE_OFFSET
-#define KERN_TO_HYP(kva)	(kva)
-
-/*
- * Our virtual mapping for the boot-time MMU-enable code. Must be
- * shared across all the page-tables. Conveniently, we use the vectors
- * page, where no kernel data will ever be shared with HYP.
- */
-#define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
+#define kern_hyp_va(kva)	(kva)
 
 /*
  * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
@@ -49,9 +40,8 @@
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
-int create_hyp_mappings(void *from, void *to);
+int create_hyp_mappings(void *from, void *to, pgprot_t prot);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
-void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
@@ -65,7 +55,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
-phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index d62204060cbe..a8d656d9aec7 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -97,7 +97,9 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
 #define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
 #define PAGE_KERNEL_EXEC	pgprot_kernel
-#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
+#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN)
+#define PAGE_HYP_EXEC		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
+#define PAGE_HYP_RO		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index d4ceaf5f299b..a2e75b84e2ae 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -80,6 +80,10 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return false;
 }
 
+/* The section containing the hypervisor idmap text */
+extern char __hyp_idmap_text_start[];
+extern char __hyp_idmap_text_end[];
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 02abfff68ee5..95a000515e43 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -46,13 +46,6 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
-config KVM_NEW_VGIC
-	bool "New VGIC implementation"
-	depends on KVM
-	default y
-	---help---
-	  uses the new VGIC implementation
-
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index a596b58f6d37..5e28df80dca7 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -22,7 +22,6 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 
-ifeq ($(CONFIG_KVM_NEW_VGIC),y)
 obj-y += $(KVM)/arm/vgic/vgic.o
 obj-y += $(KVM)/arm/vgic/vgic-init.o
 obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
@@ -30,9 +29,4 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
-else
-obj-y += $(KVM)/arm/vgic.o
-obj-y += $(KVM)/arm/vgic-v2.o
-obj-y += $(KVM)/arm/vgic-v2-emul.o
-endif
 obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index f1bde7c4e736..d94bb9093ead 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -20,6 +20,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
@@ -122,7 +123,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_fail_alloc;
 
-	ret = create_hyp_mappings(kvm, kvm + 1);
+	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
 		goto out_free_stage2_pgd;
 
@@ -201,7 +202,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	default:
-		r = kvm_arch_dev_ioctl_check_extension(ext);
+		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
 		break;
 	}
 	return r;
@@ -239,7 +240,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
-	err = create_hyp_mappings(vcpu, vcpu + 1);
+	err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
 	if (err)
 		goto vcpu_uninit;
 
@@ -377,7 +378,7 @@ void force_vm_exit(const cpumask_t *mask)
 
 /**
  * need_new_vmid_gen - check that the VMID is still valid
- * @kvm: The VM's VMID to checkt
+ * @kvm: The VM's VMID to check
  *
  * return true if there is a new generation of VMIDs being used
  *
@@ -616,7 +617,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		__kvm_guest_enter();
+		guest_enter_irqoff();
 		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
@@ -642,14 +643,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();
 
 		/*
-		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * We do local_irq_enable() before calling guest_exit() so
 		 * that if a timer interrupt hits while running the guest we
 		 * account that tick as being spent in the guest.  We enable
-		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preemption after calling guest_exit() so that if we get
 		 * preempted we make sure ticks after that is not counted as
 		 * guest time.
 		 */
-		kvm_guest_exit();
+		guest_exit();
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/*
@@ -1039,7 +1040,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 static void cpu_init_hyp_mode(void *dummy)
 {
-	phys_addr_t boot_pgd_ptr;
 	phys_addr_t pgd_ptr;
 	unsigned long hyp_stack_ptr;
 	unsigned long stack_page;
@@ -1048,13 +1048,12 @@ static void cpu_init_hyp_mode(void *dummy)
 	/* Switch from the HYP stub to our own HYP init vector */
 	__hyp_set_vectors(kvm_get_idmap_vector());
 
-	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
 	pgd_ptr = kvm_mmu_get_httbr();
 	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
 	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
 
-	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
 
 	kvm_arm_init_debug();
@@ -1076,15 +1075,9 @@ static void cpu_hyp_reinit(void)
 
 static void cpu_hyp_reset(void)
 {
-	phys_addr_t boot_pgd_ptr;
-	phys_addr_t phys_idmap_start;
-
-	if (!is_kernel_in_hyp_mode()) {
-		boot_pgd_ptr = kvm_mmu_get_boot_httbr();
-		phys_idmap_start = kvm_get_idmap_start();
-
-		__cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);
-	}
+	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)
@@ -1294,14 +1287,14 @@ static int init_hyp_mode(void)
 	 * Map the Hyp-code called directly from the host
 	 */
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
-				  kvm_ksym_ref(__hyp_text_end));
+				  kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
 		goto out_err;
 	}
 
 	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
-				  kvm_ksym_ref(__end_rodata));
+				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
 		goto out_err;
@@ -1312,7 +1305,8 @@ static int init_hyp_mode(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);
+		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
+					  PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
@@ -1324,7 +1318,7 @@ static int init_hyp_mode(void)
 		kvm_cpu_context_t *cpu_ctxt;
 
 		cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
-		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1);
+		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
@@ -1332,10 +1326,6 @@ static int init_hyp_mode(void)
 		}
 	}
 
-#ifndef CONFIG_HOTPLUG_CPU
-	free_boot_hyp_pgd();
-#endif
-
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
 	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index a494def3f195..af93e3ffc9f3 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -210,7 +210,7 @@ bool kvm_condition_valid(struct kvm_vcpu *vcpu)
  * @vcpu:	The VCPU pointer
  *
  * When exceptions occur while instructions are executed in Thumb IF-THEN
- * blocks, the ITSTATE field of the CPSR is not advanved (updated), so we have
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
  * to do this little bit of work manually. The fields map like this:
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 9093ed0f8b2a..9aca92074f85 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -182,7 +182,7 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 /**
  * kvm_arm_copy_reg_indices - get indices of all registers.
  *
- * We do core registers right here, then we apppend coproc regs.
+ * We do core registers right here, then we append coproc regs.
  */
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1f9ae17476f9..bf89c919efc1 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -32,23 +32,13 @@
  *       r2,r3 = Hypervisor pgd pointer
  *
  * The init scenario is:
- * - We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd,
- *   runtime stack, runtime vectors
- * - Enable the MMU with the boot pgd
- * - Jump to a target into the trampoline page (remember, this is the same
- *   physical page!)
- * - Now switch to the runtime pgd (same VA, and still the same physical
- *   page!)
+ * - We jump in HYP with 3 parameters: runtime HYP pgd, runtime stack,
+ *   runtime vectors
  * - Invalidate TLBs
  * - Set stack and vectors
+ * - Setup the page tables
+ * - Enable the MMU
  * - Profit! (or eret, if you only care about the code).
- *
- * As we only have four registers available to pass parameters (and we
- * need six), we split the init in two phases:
- * - Phase 1: r0 = 0, r1 = 0, r2,r3 contain the boot PGD.
- *   Provides the basic HYP init, and enable the MMU.
- * - Phase 2: r0 = ToS, r1 = vectors, r2,r3 contain the runtime PGD.
- *   Switches to the runtime PGD, set stack and vectors.
  */
 
 	.text
@@ -68,8 +58,11 @@ __kvm_hyp_init:
 	W(b)	.
 
 __do_hyp_init:
-	cmp	r0, #0			@ We have a SP?
-	bne	phase2			@ Yes, second stage init
+	@ Set stack pointer
+	mov	sp, r0
+
+	@ Set HVBAR to point to the HYP vectors
+	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
 
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
 	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
@@ -114,34 +107,25 @@ __do_hyp_init:
  THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
-	isb
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
+	isb
 
-	@ End of init phase-1
 	eret
 
-phase2:
-	@ Set stack pointer
-	mov	sp, r0
-
-	@ Set HVBAR to point to the HYP vectors
-	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
-
-	@ Jump to the trampoline page
-	ldr	r0, =TRAMPOLINE_VA
-	adr	r1, target
-	bfi	r0, r1, #0, #PAGE_SHIFT
-	ret	r0
+	@ r0 : stub vectors address
+ENTRY(__kvm_hyp_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
+	mcr	p15, 4, r1, c1, c0, 0	@ HSCTLR
 
-target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
+	/* Install stub vectors */
+	mcr	p15, 4, r0, c12, c0, 0	@ HVBAR
 	isb
 
-	@ Invalidate the old TLBs
-	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
-	dsb	ish
-
 	eret
+ENDPROC(__kvm_hyp_reset)
 
 	.ltorg
 
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 45c43aecb8f2..bda27b6b1aa2 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -32,8 +32,6 @@
 
 #include "trace.h"
 
-extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
 static pgd_t *boot_hyp_pgd;
 static pgd_t *hyp_pgd;
 static pgd_t *merged_hyp_pgd;
@@ -484,28 +482,6 @@ static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
 }
 
 /**
- * free_boot_hyp_pgd - free HYP boot page tables
- *
- * Free the HYP boot page tables. The bounce page is also freed.
- */
-void free_boot_hyp_pgd(void)
-{
-	mutex_lock(&kvm_hyp_pgd_mutex);
-
-	if (boot_hyp_pgd) {
-		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_hyp_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
-		boot_hyp_pgd = NULL;
-	}
-
-	if (hyp_pgd)
-		unmap_hyp_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-
-	mutex_unlock(&kvm_hyp_pgd_mutex);
-}
-
-/**
  * free_hyp_pgds - free Hyp-mode page tables
  *
  * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
@@ -519,15 +495,20 @@ void free_hyp_pgds(void)
 {
 	unsigned long addr;
 
-	free_boot_hyp_pgd();
-
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
+	if (boot_hyp_pgd) {
+		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
+		boot_hyp_pgd = NULL;
+	}
+
 	if (hyp_pgd) {
+		unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
 
 		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
@@ -679,17 +660,18 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
  * @to:		The virtual kernel end address of the range (exclusive)
+ * @prot:	The protection to be applied to this range
  *
  * The same virtual address as the kernel virtual address is also used
  * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
  * physical pages.
  */
-int create_hyp_mappings(void *from, void *to)
+int create_hyp_mappings(void *from, void *to, pgprot_t prot)
 {
 	phys_addr_t phys_addr;
 	unsigned long virt_addr;
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
 
 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -704,7 +686,7 @@ int create_hyp_mappings(void *from, void *to)
 		err = __create_hyp_mappings(hyp_pgd, virt_addr,
 					    virt_addr + PAGE_SIZE,
 					    __phys_to_pfn(phys_addr),
-					    PAGE_HYP);
+					    prot);
 		if (err)
 			return err;
 	}
@@ -723,8 +705,8 @@ int create_hyp_mappings(void *from, void *to)
  */
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 {
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
 
 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -1687,14 +1669,6 @@ phys_addr_t kvm_mmu_get_httbr(void)
 		return virt_to_phys(hyp_pgd);
 }
 
-phys_addr_t kvm_mmu_get_boot_httbr(void)
-{
-	if (__kvm_cpu_uses_extended_idmap())
-		return virt_to_phys(merged_hyp_pgd);
-	else
-		return virt_to_phys(boot_hyp_pgd);
-}
-
 phys_addr_t kvm_get_idmap_vector(void)
 {
 	return hyp_idmap_vector;
@@ -1705,6 +1679,22 @@ phys_addr_t kvm_get_idmap_start(void)
 	return hyp_idmap_start;
 }
 
+static int kvm_map_idmap_text(pgd_t *pgd)
+{
+	int err;
+
+	/* Create the idmap in the boot page tables */
+	err = 	__create_hyp_mappings(pgd,
+				      hyp_idmap_start, hyp_idmap_end,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP_EXEC);
+	if (err)
+		kvm_err("Failed to idmap %lx-%lx\n",
+			hyp_idmap_start, hyp_idmap_end);
+
+	return err;
+}
+
 int kvm_mmu_init(void)
 {
 	int err;
@@ -1719,28 +1709,41 @@ int kvm_mmu_init(void)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
-	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
-	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	kvm_info("IDMAP page: %lx\n", hyp_idmap_start);
+	kvm_info("HYP VA range: %lx:%lx\n",
+		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
 
-	if (!hyp_pgd || !boot_hyp_pgd) {
-		kvm_err("Hyp mode PGD not allocated\n");
-		err = -ENOMEM;
+	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
+	    hyp_idmap_start <  kern_hyp_va(~0UL)) {
+		/*
+		 * The idmap page is intersecting with the VA space,
+		 * it is not safe to continue further.
+		 */
+		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
+		err = -EINVAL;
 		goto out;
 	}
 
-	/* Create the idmap in the boot page tables */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      hyp_idmap_start, hyp_idmap_end,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-
-	if (err) {
-		kvm_err("Failed to idmap %lx-%lx\n",
-			hyp_idmap_start, hyp_idmap_end);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	if (!hyp_pgd) {
+		kvm_err("Hyp mode PGD not allocated\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
 	if (__kvm_cpu_uses_extended_idmap()) {
+		boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+							 hyp_pgd_order);
+		if (!boot_hyp_pgd) {
+			kvm_err("Hyp boot PGD not allocated\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = kvm_map_idmap_text(boot_hyp_pgd);
+		if (err)
+			goto out;
+
 		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 		if (!merged_hyp_pgd) {
 			kvm_err("Failed to allocate extra HYP pgd\n");
@@ -1748,29 +1751,10 @@ int kvm_mmu_init(void)
 		}
 		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
 				    hyp_idmap_start);
-		return 0;
-	}
-
-	/* Map the very same page at the trampoline VA */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
-	}
-
-	/* Map the same page again into the runtime page tables */
-	err = 	__create_hyp_mappings(hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
+	} else {
+		err = kvm_map_idmap_text(hyp_pgd);
+		if (err)
+			goto out;
 	}
 
 	return 0;
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index 0048b5a62a50..4b5e802e57d1 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -52,7 +52,7 @@ static const struct kvm_irq_level cortexa_vtimer_irq = {
  * @vcpu: The VCPU pointer
  *
  * This function finds the right table above and sets the registers on the
- * virtual CPU struct to their architectually defined reset values.
+ * virtual CPU struct to their architecturally defined reset values.
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {