Merge branch 'kvm-updates/2.6.30' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.30' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (113 commits)
  KVM: VMX: Don't allow uninhibited access to EFER on i386
  KVM: Correct deassign device ioctl to IOW
  KVM: ppc: e500: Fix the bug that KVM is unstable in SMP
  KVM: ppc: e500: Fix the bug that mas0 update to wrong value when read TLB entry
  KVM: Fix missing smp tlb flush in invlpg
  KVM: Get support IRQ routing entry counts
  KVM: fix sparse warnings: Should it be static?
  KVM: fix sparse warnings: context imbalance
  KVM: is_long_mode() should check for EFER.LMA
  KVM: VMX: Update necessary state when guest enters long mode
  KVM: ia64: Fix the build errors due to lack of macros related to MSI.
  ia64: Move the macro definitions related to MSI to one header file.
  KVM: fix kvm_vm_ioctl_deassign_device
  KVM: define KVM_CAP_DEVICE_DEASSIGNMENT
  KVM: ppc: Add emulation of E500 register mmucsr0
  KVM: Report IRQ injection status for MSI delivered interrupts
  KVM: MMU: Fix another largepage memory leak
  KVM: SVM: set accessed bit for VMCB segment selectors
  KVM: Report IRQ injection status to userspace.
  KVM: MMU: remove assertion in kvm_mmu_alloc_page
  ...

19 files changed, 1744 insertions, 686 deletions

diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 886c9402ec4..dc3f6cf1170 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -15,6 +15,7 @@
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -212,7 +213,30 @@ struct kvm_pit_channel_state {
 	__s64 count_load_time;
 };
 
+struct kvm_debug_exit_arch {
+	__u32 exception;
+	__u32 pad;
+	__u64 pc;
+	__u64 dr6;
+	__u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+#define KVM_GUESTDBG_INJECT_DB		0x00040000
+#define KVM_GUESTDBG_INJECT_BP		0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u64 debugreg[8];
+};
+
 struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
+
+struct kvm_reinject_control {
+	__u8 pit_reinject;
+	__u8 reserved[31];
+};
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 730843d1d2f..f0faf58044f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -22,6 +22,7 @@
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
+#include <asm/msr-index.h>
 
 #define KVM_MAX_VCPUS 16
 #define KVM_MEMORY_SLOTS 32
@@ -134,11 +135,18 @@ enum {
 
 #define KVM_NR_MEM_OBJS 40
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
+#define KVM_NR_DB_REGS	4
+
+#define DR6_BD		(1 << 13)
+#define DR6_BS		(1 << 14)
+#define DR6_FIXED_1	0xffff0ff0
+#define DR6_VOLATILE	0x0000e00f
+
+#define DR7_BP_EN_MASK	0x000000ff
+#define DR7_GE		(1 << 9)
+#define DR7_GD		(1 << 13)
+#define DR7_FIXED_1	0x00000400
+#define DR7_VOLATILE	0xffff23ff
 
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
@@ -162,7 +170,8 @@ struct kvm_pte_chain {
  *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
  *   bits 4:7 - page table level for this shadow (1-4)
  *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ *   bit   16 - direct mapping of virtual to physical mapping at gfn
+ *              used for real mode and two-dimensional paging
  *   bits 17:19 - common access permissions for all ptes in this shadow page
  */
 union kvm_mmu_page_role {
@@ -172,9 +181,10 @@ union kvm_mmu_page_role {
 		unsigned level:4;
 		unsigned quadrant:2;
 		unsigned pad_for_nice_hex_output:6;
-		unsigned metaphysical:1;
+		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
+		unsigned cr4_pge:1;
 	};
 };
 
@@ -218,6 +228,18 @@ struct kvm_pv_mmu_op_buffer {
 	char buf[512] __aligned(sizeof(long));
 };
 
+struct kvm_pio_request {
+	unsigned long count;
+	int cur_count;
+	gva_t guest_gva;
+	int in;
+	int port;
+	int size;
+	int string;
+	int down;
+	int rep;
+};
+
 /*
  * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
  * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
@@ -236,6 +258,7 @@ struct kvm_mmu {
 	hpa_t root_hpa;
 	int root_level;
 	int shadow_root_level;
+	union kvm_mmu_page_role base_role;
 
 	u64 *pae_root;
 };
@@ -258,6 +281,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr3;
 	unsigned long cr4;
 	unsigned long cr8;
+	u32 hflags;
 	u64 pdptrs[4]; /* pae */
 	u64 shadow_efer;
 	u64 apic_base;
@@ -338,6 +362,15 @@ struct kvm_vcpu_arch {
 
 	struct mtrr_state_type mtrr_state;
 	u32 pat;
+
+	int switch_db_regs;
+	unsigned long host_db[KVM_NR_DB_REGS];
+	unsigned long host_dr6;
+	unsigned long host_dr7;
+	unsigned long db[KVM_NR_DB_REGS];
+	unsigned long dr6;
+	unsigned long dr7;
+	unsigned long eff_db[KVM_NR_DB_REGS];
 };
 
 struct kvm_mem_alias {
@@ -378,6 +411,7 @@ struct kvm_arch{
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
+	u64 vm_init_tsc;
 };
 
 struct kvm_vm_stat {
@@ -446,8 +480,7 @@ struct kvm_x86_ops {
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-			       struct kvm_debug_guest *dbg);
-	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+			       struct kvm_guest_debug *dbg);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -583,16 +616,12 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
 			   u32 error_code);
 
-void kvm_pic_set_irq(void *opaque, int irq, int level);
+int kvm_pic_set_irq(void *opaque, int irq, int level);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
 void fx_init(struct kvm_vcpu *vcpu);
 
-int emulator_read_std(unsigned long addr,
-		      void *val,
-		      unsigned int bytes,
-		      struct kvm_vcpu *vcpu);
 int emulator_write_emulated(unsigned long addr,
 			    const void *val,
 			    unsigned int bytes,
@@ -737,6 +766,10 @@ enum {
 	TASK_SWITCH_GATE = 3,
 };
 
+#define HF_GIF_MASK		(1 << 0)
+#define HF_HIF_MASK		(1 << 1)
+#define HF_VINTR_MASK		(1 << 2)
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 358acc59ae0..f4e505f286b 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -18,11 +18,15 @@
 #define _EFER_LME		8  /* Long mode enable */
 #define _EFER_LMA		10 /* Long mode active (read-only) */
 #define _EFER_NX		11 /* No execute enable */
+#define _EFER_SVME		12 /* Enable virtualization */
+#define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
 
 #define EFER_SCE		(1<<_EFER_SCE)
 #define EFER_LME		(1<<_EFER_LME)
 #define EFER_LMA		(1<<_EFER_LMA)
 #define EFER_NX			(1<<_EFER_NX)
+#define EFER_SVME		(1<<_EFER_SVME)
+#define EFER_FFXSR		(1<<_EFER_FFXSR)
 
 /* Intel MSRs. Some also available on other CPUs */
 #define MSR_IA32_PERFCTR0		0x000000c1
@@ -360,4 +364,9 @@
 #define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
 #define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
 
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
 #endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1b8afa78e86..82ada75f3eb 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_CPUID_FEATURE_SHIFT 2
 #define SVM_CPUID_FUNC 0x8000000a
 
-#define MSR_EFER_SVME_MASK (1ULL << 12)
-#define MSR_VM_CR       0xc0010114
-#define MSR_VM_HSAVE_PA 0xc0010117ULL
-
 #define SVM_VM_CR_SVM_DISABLE 4
 
 #define SVM_SELECTOR_S_SHIFT 4
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 59363627523..e0f9aa16358 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void)
 
 	wrmsrl(MSR_VM_HSAVE_PA, 0);
 	rdmsrl(MSR_EFER, efer);
-	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+	wrmsrl(MSR_EFER, efer & ~EFER_SVME);
 }
 
 /** Makes sure SVM is disabled, if it is supported on the CPU
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index d0238e6151d..498f944010b 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -270,8 +270,9 @@ enum vmcs_field {
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
 #define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
-#define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
+#define INTR_TYPE_HARD_EXCEPTION	(3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+#define INTR_TYPE_SOFT_EXCEPTION	(6 << 8) /* software exception */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
 #define GUEST_INTR_STATE_STI		0x00000001
@@ -311,7 +312,7 @@ enum vmcs_field {
 #define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
 #define TYPE_MOV_TO_DR                  (0 << 4)
 #define TYPE_MOV_FROM_DR                (1 << 4)
-#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
+#define DEBUG_REG_ACCESS_REG(eq)        (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */
 
 
 /* segment AR */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b81125f0bde..0a303c3ed11 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -4,6 +4,10 @@
 config HAVE_KVM
        bool
 
+config HAVE_KVM_IRQCHIP
+       bool
+       default y
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
 	depends on HAVE_KVM || X86
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 72bd275a9b5..c13bb92d315 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -201,6 +201,9 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps)
 	if (!atomic_inc_and_test(&pt->pending))
 		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
 
+	if (!pt->reinject)
+		atomic_set(&pt->pending, 1);
+
 	if (vcpu0 && waitqueue_active(&vcpu0->wq))
 		wake_up_interruptible(&vcpu0->wq);
 
@@ -536,6 +539,16 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	pit->pit_state.irq_ack = 1;
 }
 
+static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+{
+	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
+
+	if (!mask) {
+		atomic_set(&pit->pit_state.pit_timer.pending, 0);
+		pit->pit_state.irq_ack = 1;
+	}
+}
+
 struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 {
 	struct kvm_pit *pit;
@@ -545,9 +558,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	if (!pit)
 		return NULL;
 
-	mutex_lock(&kvm->lock);
 	pit->irq_source_id = kvm_request_irq_source_id(kvm);
-	mutex_unlock(&kvm->lock);
 	if (pit->irq_source_id < 0) {
 		kfree(pit);
 		return NULL;
@@ -580,10 +591,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
 	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
+	pit_state->pit_timer.reinject = true;
 	mutex_unlock(&pit->pit_state.lock);
 
 	kvm_pit_reset(pit);
 
+	pit->mask_notifier.func = pit_mask_notifer;
+	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+
 	return pit;
 }
 
@@ -592,6 +607,8 @@ void kvm_free_pit(struct kvm *kvm)
 	struct hrtimer *timer;
 
 	if (kvm->arch.vpit) {
+		kvm_unregister_irq_mask_notifier(kvm, 0,
+					       &kvm->arch.vpit->mask_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
 		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
 		hrtimer_cancel(timer);
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 4178022b97a..6acbe4b505d 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -9,6 +9,7 @@ struct kvm_kpit_timer {
 	s64 period; /* unit: ns */
 	s64 scheduled;
 	atomic_t pending;
+	bool reinject;
 };
 
 struct kvm_kpit_channel_state {
@@ -45,6 +46,7 @@ struct kvm_pit {
 	struct kvm *kvm;
 	struct kvm_kpit_state pit_state;
 	int irq_source_id;
+	struct kvm_irq_mask_notifier mask_notifier;
 };
 
 #define KVM_PIT_BASE_ADDRESS	    0x40
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 179dcb0103f..1ccb50c74f1 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -32,11 +32,13 @@
 #include <linux/kvm_host.h>
 
 static void pic_lock(struct kvm_pic *s)
+	__acquires(&s->lock)
 {
 	spin_lock(&s->lock);
 }
 
 static void pic_unlock(struct kvm_pic *s)
+	__releases(&s->lock)
 {
 	struct kvm *kvm = s->kvm;
 	unsigned acks = s->pending_acks;
@@ -49,7 +51,8 @@ static void pic_unlock(struct kvm_pic *s)
 	spin_unlock(&s->lock);
 
 	while (acks) {
-		kvm_notify_acked_irq(kvm, __ffs(acks));
+		kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)),
+				     __ffs(acks));
 		acks &= acks - 1;
 	}
 
@@ -76,12 +79,13 @@ void kvm_pic_clear_isr_ack(struct kvm *kvm)
 /*
  * set irq level. If an edge is detected, then the IRR is set to 1
  */
-static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
+static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
 {
-	int mask;
+	int mask, ret = 1;
 	mask = 1 << irq;
 	if (s->elcr & mask)	/* level triggered */
 		if (level) {
+			ret = !(s->irr & mask);
 			s->irr |= mask;
 			s->last_irr |= mask;
 		} else {
@@ -90,11 +94,15 @@ static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
 		}
 	else	/* edge triggered */
 		if (level) {
-			if ((s->last_irr & mask) == 0)
+			if ((s->last_irr & mask) == 0) {
+				ret = !(s->irr & mask);
 				s->irr |= mask;
+			}
 			s->last_irr |= mask;
 		} else
 			s->last_irr &= ~mask;
+
+	return (s->imr & mask) ? -1 : ret;
 }
 
 /*
@@ -171,16 +179,19 @@ void kvm_pic_update_irq(struct kvm_pic *s)
 	pic_unlock(s);
 }
 
-void kvm_pic_set_irq(void *opaque, int irq, int level)
+int kvm_pic_set_irq(void *opaque, int irq, int level)
 {
 	struct kvm_pic *s = opaque;
+	int ret = -1;
 
 	pic_lock(s);
 	if (irq >= 0 && irq < PIC_NUM_PINS) {
-		pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
+		ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
 		pic_update_irq(s);
 	}
 	pic_unlock(s);
+
+	return ret;
 }
 
 /*
@@ -232,7 +243,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	}
 	pic_update_irq(s);
 	pic_unlock(s);
-	kvm_notify_acked_irq(kvm, irq);
+	kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq);
 
 	return intno;
 }
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 82579ee538d..9f593188129 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -32,6 +32,8 @@
 #include "lapic.h"
 
 #define PIC_NUM_PINS 16
+#define SELECT_PIC(irq) \
+	((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE)
 
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index 8e5ee99551f..ed66e4c078d 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = {
 };
 
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-#define NUM_DB_REGS 4
 
 struct kvm_vcpu;
 
@@ -29,18 +28,23 @@ struct vcpu_svm {
 	struct svm_cpu_data *svm_data;
 	uint64_t asid_generation;
 
-	unsigned long db_regs[NUM_DB_REGS];
-
 	u64 next_rip;
 
 	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
 	u64 host_gs_base;
 	unsigned long host_cr2;
-	unsigned long host_db_regs[NUM_DB_REGS];
-	unsigned long host_dr6;
-	unsigned long host_dr7;
 
 	u32 *msrpm;
+	struct vmcb *hsave;
+	u64 hsave_msr;
+
+	u64 nested_vmcb;
+
+	/* These are the merged vectors */
+	u32 *nested_msrpm;
+
+	/* gpa pointers to the real vectors */
+	u64 nested_vmcb_msrpm;
 };
 
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2d4477c7147..2a36f7f7c4c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -145,11 +145,20 @@ struct kvm_rmap_desc {
 	struct kvm_rmap_desc *more;
 };
 
-struct kvm_shadow_walk {
-	int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu,
-		     u64 addr, u64 *spte, int level);
+struct kvm_shadow_walk_iterator {
+	u64 addr;
+	hpa_t shadow_addr;
+	int level;
+	u64 *sptep;
+	unsigned index;
 };
 
+#define for_each_shadow_entry(_vcpu, _addr, _walker)    \
+	for (shadow_walk_init(&(_walker), _vcpu, _addr);	\
+	     shadow_walk_okay(&(_walker));			\
+	     shadow_walk_next(&(_walker)))
+
+
 struct kvm_unsync_walk {
 	int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
 };
@@ -343,7 +352,6 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc,
 
 	BUG_ON(!mc->nobjs);
 	p = mc->objects[--mc->nobjs];
-	memset(p, 0, size);
 	return p;
 }
 
@@ -794,10 +802,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&sp->oos_link);
-	ASSERT(is_empty_shadow_page(sp->spt));
 	bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
 	sp->multimapped = 0;
-	sp->global = 1;
 	sp->parent_pte = parent_pte;
 	--vcpu->kvm->arch.n_free_mmu_pages;
 	return sp;
@@ -983,8 +989,8 @@ struct kvm_mmu_pages {
 	     idx < 512;					\
 	     idx = find_next_bit(bitmap, 512, idx+1))
 
-int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
-		   int idx)
+static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
+			 int idx)
 {
 	int i;
 
@@ -1059,7 +1065,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry(sp, node, bucket, hash_link)
-		if (sp->gfn == gfn && !sp->role.metaphysical
+		if (sp->gfn == gfn && !sp->role.direct
 		    && !sp->role.invalid) {
 			pgprintk("%s: found role %x\n",
 				 __func__, sp->role.word);
@@ -1115,8 +1121,9 @@ struct mmu_page_path {
 			i < pvec.nr && ({ sp = pvec.page[i].sp; 1;});	\
 			i = mmu_pages_next(&pvec, &parents, i))
 
-int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
-		   int i)
+static int mmu_pages_next(struct kvm_mmu_pages *pvec,
+			  struct mmu_page_path *parents,
+			  int i)
 {
 	int n;
 
@@ -1135,7 +1142,7 @@ int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
 	return n;
 }
 
-void mmu_pages_clear_parents(struct mmu_page_path *parents)
+static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 {
 	struct kvm_mmu_page *sp;
 	unsigned int level = 0;
@@ -1193,7 +1200,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 					     gfn_t gfn,
 					     gva_t gaddr,
 					     unsigned level,
-					     int metaphysical,
+					     int direct,
 					     unsigned access,
 					     u64 *parent_pte)
 {
@@ -1204,10 +1211,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node, *tmp;
 
-	role.word = 0;
-	role.glevels = vcpu->arch.mmu.root_level;
+	role = vcpu->arch.mmu.base_role;
 	role.level = level;
-	role.metaphysical = metaphysical;
+	role.direct = direct;
 	role.access = access;
 	if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
@@ -1242,8 +1248,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
 	sp->gfn = gfn;
 	sp->role = role;
+	sp->global = role.cr4_pge;
 	hlist_add_head(&sp->hash_link, bucket);
-	if (!metaphysical) {
+	if (!direct) {
 		if (rmap_write_protect(vcpu->kvm, gfn))
 			kvm_flush_remote_tlbs(vcpu->kvm);
 		account_shadowed(vcpu->kvm, gfn);
@@ -1255,35 +1262,35 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	return sp;
 }
 
-static int walk_shadow(struct kvm_shadow_walk *walker,
-		       struct kvm_vcpu *vcpu, u64 addr)
+static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
+			     struct kvm_vcpu *vcpu, u64 addr)
 {
-	hpa_t shadow_addr;
-	int level;
-	int r;
-	u64 *sptep;
-	unsigned index;
-
-	shadow_addr = vcpu->arch.mmu.root_hpa;
-	level = vcpu->arch.mmu.shadow_root_level;
-	if (level == PT32E_ROOT_LEVEL) {
-		shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
-		shadow_addr &= PT64_BASE_ADDR_MASK;
-		if (!shadow_addr)
-			return 1;
-		--level;
+	iterator->addr = addr;
+	iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
+	iterator->level = vcpu->arch.mmu.shadow_root_level;
+	if (iterator->level == PT32E_ROOT_LEVEL) {
+		iterator->shadow_addr
+			= vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+		iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
+		--iterator->level;
+		if (!iterator->shadow_addr)
+			iterator->level = 0;
 	}
+}
 
-	while (level >= PT_PAGE_TABLE_LEVEL) {
-		index = SHADOW_PT_INDEX(addr, level);
-		sptep = ((u64 *)__va(shadow_addr)) + index;
-		r = walker->entry(walker, vcpu, addr, sptep, level);
-		if (r)
-			return r;
-		shadow_addr = *sptep & PT64_BASE_ADDR_MASK;
-		--level;
-	}
-	return 0;
+static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
+{
+	if (iterator->level < PT_PAGE_TABLE_LEVEL)
+		return false;
+	iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
+	iterator->sptep	= ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
+	return true;
+}
+
+static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
+{
+	iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK;
+	--iterator->level;
 }
 
 static void kvm_mmu_page_unlink_children(struct kvm *kvm,
@@ -1388,7 +1395,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_page_unlink_children(kvm, sp);
 	kvm_mmu_unlink_parents(kvm, sp);
 	kvm_flush_remote_tlbs(kvm);
-	if (!sp->role.invalid && !sp->role.metaphysical)
+	if (!sp->role.invalid && !sp->role.direct)
 		unaccount_shadowed(kvm, sp->gfn);
 	if (sp->unsync)
 		kvm_unlink_unsync_page(kvm, sp);
@@ -1451,7 +1458,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
-		if (sp->gfn == gfn && !sp->role.metaphysical) {
+		if (sp->gfn == gfn && !sp->role.direct) {
 			pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
 				 sp->role.word);
 			r = 1;
@@ -1463,11 +1470,20 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
 static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 {
+	unsigned index;
+	struct hlist_head *bucket;
 	struct kvm_mmu_page *sp;
+	struct hlist_node *node, *nn;
 
-	while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
-		pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
-		kvm_mmu_zap_page(kvm, sp);
+	index = kvm_page_table_hashfn(gfn);
+	bucket = &kvm->arch.mmu_page_hash[index];
+	hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
+		if (sp->gfn == gfn && !sp->role.direct
+		    && !sp->role.invalid) {
+			pgprintk("%s: zap %lx %x\n",
+				 __func__, gfn, sp->role.word);
+			kvm_mmu_zap_page(kvm, sp);
+		}
 	}
 }
 
@@ -1622,7 +1638,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	/* don't unsync if pagetable is shadowed with multiple roles */
 	hlist_for_each_entry_safe(s, node, n, bucket, hash_link) {
-		if (s->gfn != sp->gfn || s->role.metaphysical)
+		if (s->gfn != sp->gfn || s->role.direct)
 			continue;
 		if (s->role.word != sp->role.word)
 			return 1;
@@ -1669,8 +1685,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	u64 mt_mask = shadow_mt_mask;
 	struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
 
-	if (!(vcpu->arch.cr4 & X86_CR4_PGE))
-		global = 0;
 	if (!global && sp->global) {
 		sp->global = 0;
 		if (sp->unsync) {
@@ -1777,12 +1791,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			pgprintk("hfn old %lx new %lx\n",
 				 spte_to_pfn(*shadow_pte), pfn);
 			rmap_remove(vcpu->kvm, shadow_pte);
-		} else {
-			if (largepage)
-				was_rmapped = is_large_pte(*shadow_pte);
-			else
-				was_rmapped = 1;
-		}
+		} else
+			was_rmapped = 1;
 	}
 	if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
 		      dirty, largepage, global, gfn, pfn, speculative, true)) {
@@ -1820,67 +1830,42 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 {
 }
 
-struct direct_shadow_walk {
-	struct kvm_shadow_walk walker;
-	pfn_t pfn;
-	int write;
-	int largepage;
-	int pt_write;
-};
-
-static int direct_map_entry(struct kvm_shadow_walk *_walk,
-			    struct kvm_vcpu *vcpu,
-			    u64 addr, u64 *sptep, int level)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
+			int largepage, gfn_t gfn, pfn_t pfn)
 {
-	struct direct_shadow_walk *walk =
-		container_of(_walk, struct direct_shadow_walk, walker);
+	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
+	int pt_write = 0;
 	gfn_t pseudo_gfn;
-	gfn_t gfn = addr >> PAGE_SHIFT;
-
-	if (level == PT_PAGE_TABLE_LEVEL
-	    || (walk->largepage && level == PT_DIRECTORY_LEVEL)) {
-		mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL,
-			     0, walk->write, 1, &walk->pt_write,
-			     walk->largepage, 0, gfn, walk->pfn, false);
-		++vcpu->stat.pf_fixed;
-		return 1;
-	}
 
-	if (*sptep == shadow_trap_nonpresent_pte) {
-		pseudo_gfn = (addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
-		sp = kvm_mmu_get_page(vcpu, pseudo_gfn, (gva_t)addr, level - 1,
-				      1, ACC_ALL, sptep);
-		if (!sp) {
-			pgprintk("nonpaging_map: ENOMEM\n");
-			kvm_release_pfn_clean(walk->pfn);
-			return -ENOMEM;
+	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
+		if (iterator.level == PT_PAGE_TABLE_LEVEL
+		    || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
+			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
+				     0, write, 1, &pt_write,
+				     largepage, 0, gfn, pfn, false);
+			++vcpu->stat.pf_fixed;
+			break;
 		}
 
-		set_shadow_pte(sptep,
-			       __pa(sp->spt)
-			       | PT_PRESENT_MASK | PT_WRITABLE_MASK
-			       | shadow_user_mask | shadow_x_mask);
-	}
-	return 0;
-}
+		if (*iterator.sptep == shadow_trap_nonpresent_pte) {
+			pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
+					      iterator.level - 1,
+					      1, ACC_ALL, iterator.sptep);
+			if (!sp) {
+				pgprintk("nonpaging_map: ENOMEM\n");
+				kvm_release_pfn_clean(pfn);
+				return -ENOMEM;
+			}
 
-static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
-			int largepage, gfn_t gfn, pfn_t pfn)
-{
-	int r;
-	struct direct_shadow_walk walker = {
-		.walker = { .entry = direct_map_entry, },
-		.pfn = pfn,
-		.largepage = largepage,
-		.write = write,
-		.pt_write = 0,
-	};
-
-	r = walk_shadow(&walker.walker, vcpu, gfn << PAGE_SHIFT);
-	if (r < 0)
-		return r;
-	return walker.pt_write;
+			set_shadow_pte(iterator.sptep,
+				       __pa(sp->spt)
+				       | PT_PRESENT_MASK | PT_WRITABLE_MASK
+				       | shadow_user_mask | shadow_x_mask);
+		}
+	}
+	return pt_write;
 }
 
 static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
@@ -1962,7 +1947,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 	int i;
 	gfn_t root_gfn;
 	struct kvm_mmu_page *sp;
-	int metaphysical = 0;
+	int direct = 0;
 
 	root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
 
@@ -1971,18 +1956,18 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 
 		ASSERT(!VALID_PAGE(root));
 		if (tdp_enabled)
-			metaphysical = 1;
+			direct = 1;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
-				      PT64_ROOT_LEVEL, metaphysical,
+				      PT64_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		vcpu->arch.mmu.root_hpa = root;
 		return;
 	}