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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...

20 files changed, 568 insertions, 455 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 12ec402f4114..546d13e436aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2384,7 +2384,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(55, (unsigned long *)&status)) {
 		handled++;
-		intel_pt_interrupt();
+		if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() &&
+			perf_guest_cbs->handle_intel_pt_intr))
+			perf_guest_cbs->handle_intel_pt_intr();
+		else
+			intel_pt_interrupt();
 	}
 
 	/*
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index 62be73b23d5c..e8f58ddd06d9 100644
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -10,6 +10,7 @@ extern struct e820_table *e820_table_firmware;
 
 extern unsigned long pci_mem_start;
 
+extern bool e820__mapped_raw_any(u64 start, u64 end, enum e820_type type);
 extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type);
 extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c79abe7ca093..450d69a1e6fa 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -470,6 +470,7 @@ struct kvm_pmu {
 	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
+	u64 global_ovf_ctrl_mask;
 	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
@@ -781,6 +782,9 @@ struct kvm_vcpu_arch {
 
 	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
 	bool l1tf_flush_l1d;
+
+	/* AMD MSRC001_0015 Hardware Configuration */
+	u64 msr_hwcr;
 };
 
 struct kvm_lpage_info {
@@ -1168,7 +1172,8 @@ struct kvm_x86_ops {
 			      uint32_t guest_irq, bool set);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
 
-	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
+	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
+			    bool *expired);
 	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
 
 	void (*setup_mce)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 88dd202c8b00..979ef971cc78 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -789,6 +789,14 @@
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
 
+/* PERF_GLOBAL_OVF_CTL bits */
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT	55
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI		(1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF_BIT		62
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF			(1ULL <<  MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF_BIT)
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD_BIT		63
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD			(1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD_BIT)
+
 /* Geode defined MSRs */
 #define MSR_GEODE_BUSCONT_CONF0		0x00001900
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 2879e234e193..76dd605ee2a3 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -73,12 +73,13 @@ EXPORT_SYMBOL(pci_mem_start);
  * This function checks if any part of the range <start,end> is mapped
  * with type.
  */
-bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
+static bool _e820__mapped_any(struct e820_table *table,
+			      u64 start, u64 end, enum e820_type type)
 {
 	int i;
 
-	for (i = 0; i < e820_table->nr_entries; i++) {
-		struct e820_entry *entry = &e820_table->entries[i];
+	for (i = 0; i < table->nr_entries; i++) {
+		struct e820_entry *entry = &table->entries[i];
 
 		if (type && entry->type != type)
 			continue;
@@ -88,6 +89,17 @@ bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
 	}
 	return 0;
 }
+
+bool e820__mapped_raw_any(u64 start, u64 end, enum e820_type type)
+{
+	return _e820__mapped_any(e820_table_firmware, start, end, type);
+}
+EXPORT_SYMBOL_GPL(e820__mapped_raw_any);
+
+bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
+{
+	return _e820__mapped_any(e820_table, start, end, type);
+}
 EXPORT_SYMBOL_GPL(e820__mapped_any);
 
 /*
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bbbe611f0c49..80a642a0143d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -963,13 +963,13 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 	if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0))
 		return 1;
 
-	eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
+	eax = kvm_rax_read(vcpu);
+	ecx = kvm_rcx_read(vcpu);
 	kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, edx);
+	kvm_rax_write(vcpu, eax);
+	kvm_rbx_write(vcpu, ebx);
+	kvm_rcx_write(vcpu, ecx);
+	kvm_rdx_write(vcpu, edx);
 	return kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index cc24b3a32c44..8ca4b39918e0 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1535,10 +1535,10 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 
 	longmode = is_64_bit_mode(vcpu);
 	if (longmode)
-		kvm_register_write(vcpu, VCPU_REGS_RAX, result);
+		kvm_rax_write(vcpu, result);
 	else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff);
+		kvm_rdx_write(vcpu, result >> 32);
+		kvm_rax_write(vcpu, result & 0xffffffff);
 	}
 }
 
@@ -1611,18 +1611,18 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	longmode = is_64_bit_mode(vcpu);
 
 	if (!longmode) {
-		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
-		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
-		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
-			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+		param = ((u64)kvm_rdx_read(vcpu) << 32) |
+			(kvm_rax_read(vcpu) & 0xffffffff);
+		ingpa = ((u64)kvm_rbx_read(vcpu) << 32) |
+			(kvm_rcx_read(vcpu) & 0xffffffff);
+		outgpa = ((u64)kvm_rdi_read(vcpu) << 32) |
+			(kvm_rsi_read(vcpu) & 0xffffffff);
 	}
 #ifdef CONFIG_X86_64
 	else {
-		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
-		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+		param = kvm_rcx_read(vcpu);
+		ingpa = kvm_rdx_read(vcpu);
+		outgpa = kvm_r8_read(vcpu);
 	}
 #endif
 
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index f8f56a93358b..1cc6c47dc77e 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -9,6 +9,34 @@
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
 	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
 
+#define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
+static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
+{									      \
+	return vcpu->arch.regs[VCPU_REGS_##uname];			      \
+}									      \
+static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu,	      \
+						unsigned long val)	      \
+{									      \
+	vcpu->arch.regs[VCPU_REGS_##uname] = val;			      \
+}
+BUILD_KVM_GPR_ACCESSORS(rax, RAX)
+BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
+BUILD_KVM_GPR_ACCESSORS(rcx, RCX)
+BUILD_KVM_GPR_ACCESSORS(rdx, RDX)
+BUILD_KVM_GPR_ACCESSORS(rbp, RBP)
+BUILD_KVM_GPR_ACCESSORS(rsi, RSI)
+BUILD_KVM_GPR_ACCESSORS(rdi, RDI)
+#ifdef CONFIG_X86_64
+BUILD_KVM_GPR_ACCESSORS(r8,  R8)
+BUILD_KVM_GPR_ACCESSORS(r9,  R9)
+BUILD_KVM_GPR_ACCESSORS(r10, R10)
+BUILD_KVM_GPR_ACCESSORS(r11, R11)
+BUILD_KVM_GPR_ACCESSORS(r12, R12)
+BUILD_KVM_GPR_ACCESSORS(r13, R13)
+BUILD_KVM_GPR_ACCESSORS(r14, R14)
+BUILD_KVM_GPR_ACCESSORS(r15, R15)
+#endif
+
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
 					      enum kvm_reg reg)
 {
@@ -37,6 +65,16 @@ static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val)
 	kvm_register_write(vcpu, VCPU_REGS_RIP, val);
 }
 
+static inline unsigned long kvm_rsp_read(struct kvm_vcpu *vcpu)
+{
+	return kvm_register_read(vcpu, VCPU_REGS_RSP);
+}
+
+static inline void kvm_rsp_write(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	kvm_register_write(vcpu, VCPU_REGS_RSP, val);
+}
+
 static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 {
 	might_sleep();  /* on svm */
@@ -83,8 +121,8 @@ static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
 
 static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 {
-	return (kvm_register_read(vcpu, VCPU_REGS_RAX) & -1u)
-		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
+	return (kvm_rax_read(vcpu) & -1u)
+		| ((u64)(kvm_rdx_read(vcpu) & -1u) << 32);
 }
 
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bd13fdddbdc4..4924f83ed4f3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1454,7 +1454,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	if (swait_active(q))
 		swake_up_one(q);
 
-	if (apic_lvtt_tscdeadline(apic))
+	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 }
 
@@ -1696,37 +1696,42 @@ static void cancel_hv_timer(struct kvm_lapic *apic)
 static bool start_hv_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
-	int r;
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	bool expired;
 
 	WARN_ON(preemptible());
 	if (!kvm_x86_ops->set_hv_timer)
 		return false;
 
-	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
-		return false;
-
 	if (!ktimer->tscdeadline)
 		return false;
 
-	r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline);
-	if (r < 0)
+	if (kvm_x86_ops->set_hv_timer(vcpu, ktimer->tscdeadline, &expired))
 		return false;
 
 	ktimer->hv_timer_in_use = true;
 	hrtimer_cancel(&ktimer->timer);
 
 	/*
-	 * Also recheck ktimer->pending, in case the sw timer triggered in
-	 * the window.  For periodic timer, leave the hv timer running for
-	 * simplicity, and the deadline will be recomputed on the next vmexit.
+	 * To simplify handling the periodic timer, leave the hv timer running
+	 * even if the deadline timer has expired, i.e. rely on the resulting
+	 * VM-Exit to recompute the periodic timer's target expiration.
 	 */
-	if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) {
-		if (r)
+	if (!apic_lvtt_period(apic)) {
+		/*
+		 * Cancel the hv timer if the sw timer fired while the hv timer
+		 * was being programmed, or if the hv timer itself expired.
+		 */
+		if (atomic_read(&ktimer->pending)) {
+			cancel_hv_timer(apic);
+		} else if (expired) {
 			apic_timer_expired(apic);
-		return false;
+			cancel_hv_timer(apic);
+		}
 	}
 
-	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true);
+	trace_kvm_hv_timer_state(vcpu->vcpu_id, ktimer->hv_timer_in_use);
+
 	return true;
 }
 
@@ -1750,8 +1755,13 @@ static void start_sw_timer(struct kvm_lapic *apic)
 static void restart_apic_timer(struct kvm_lapic *apic)
 {
 	preempt_disable();
+
+	if (!apic_lvtt_period(apic) && atomic_read(&apic->lapic_timer.pending))
+		goto out;
+
 	if (!start_hv_timer(apic))
 		start_sw_timer(apic);
+out:
 	preempt_enable();
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d9c7b45d231f..1e9ba81accba 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -44,6 +44,7 @@
 #include <asm/page.h>
 #include <asm/pat.h>
 #include <asm/cmpxchg.h>
+#include <asm/e820/api.h>
 #include <asm/io.h>
 #include <asm/vmx.h>
 #include <asm/kvm_page_track.h>
@@ -487,16 +488,24 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	 * If the CPU has 46 or less physical address bits, then set an
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
+	 *
+	 * Some Intel CPUs address the L1 cache using more PA bits than are
+	 * reported by CPUID. Use the PA width of the L1 cache when possible
+	 * to achieve more effective mitigation, e.g. if system RAM overlaps
+	 * the most significant bits of legal physical address space.
 	 */
-	low_phys_bits = boot_cpu_data.x86_phys_bits;
-	if (boot_cpu_data.x86_phys_bits <
+	shadow_nonpresent_or_rsvd_mask = 0;
+	low_phys_bits = boot_cpu_data.x86_cache_bits;
+	if (boot_cpu_data.x86_cache_bits <
 	    52 - shadow_nonpresent_or_rsvd_mask_len) {
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_phys_bits -
+			rsvd_bits(boot_cpu_data.x86_cache_bits -
 				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_phys_bits - 1);
+				  boot_cpu_data.x86_cache_bits - 1);
 		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
-	}
+	} else
+		WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF));
+
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
@@ -2892,7 +2901,9 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 			 */
 			(!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));
 
-	return true;
+	return !e820__mapped_raw_any(pfn_to_hpa(pfn),
+				     pfn_to_hpa(pfn + 1) - 1,
+				     E820_TYPE_RAM);
 }
 
 /* Bits which may be returned by set_spte() */
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index e9ea2d45ae66..9f72cc427158 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -48,11 +48,6 @@ static bool msr_mtrr_valid(unsigned msr)
 	return false;
 }
 
-static bool valid_pat_type(unsigned t)
-{
-	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
-}
-
 static bool valid_mtrr_type(unsigned t)
 {
 	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
@@ -67,10 +62,7 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		return false;
 
 	if (msr == MSR_IA32_CR_PAT) {
-		for (i = 0; i < 8; i++)
-			if (!valid_pat_type((data >> (i * 8)) & 0xff))
-				return false;
-		return true;
+		return kvm_pat_valid(data);
 	} else if (msr == MSR_MTRRdefType) {
 		if (data & ~0xcff)
 			return false;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 08715034e315..367a47df4ba0 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -141,15 +141,35 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	struct page *page;
 
 	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
-	/* Check if the user is doing something meaningless. */
-	if (unlikely(npages != 1))
-		return -EFAULT;
-
-	table = kmap_atomic(page);
-	ret = CMPXCHG(&table[index], orig_pte, new_pte);
-	kunmap_atomic(table);
-
-	kvm_release_page_dirty(page);
+	if (likely(npages == 1)) {
+		table = kmap_atomic(page);
+		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+		kunmap_atomic(table);
+
+		kvm_release_page_dirty(page);
+	} else {
+		struct vm_area_struct *vma;
+		unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
+		unsigned long pfn;
+		unsigned long paddr;
+
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
+		if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
+			up_read(&current->mm->mmap_sem);
+			return -EFAULT;
+		}
+		pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+		paddr = pfn << PAGE_SHIFT;
+		table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
+		if (!table) {
+			up_read(&current->mm->mmap_sem);
+			return -EFAULT;
+		}
+		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+		memunmap(table);
+		up_read(&current->mm->mmap_sem);
+	}
 
 	return (ret != orig_pte);
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6b92eaf4a3b1..a849dcb7fbc5 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2091,7 +2091,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	init_vmcb(svm);
 
 	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
+	kvm_rdx_write(vcpu, eax);
 
 	if (kvm_vcpu_apicv_active(vcpu) && !init_event)
 		avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
@@ -3071,32 +3071,6 @@ static inline bool nested_svm_nmi(struct vcpu_svm *svm)
 	return false;
 }
 
-static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
-{
-	struct page *page;
-
-	might_sleep();
-
-	page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT);
-	if (is_error_page(page))
-		goto error;
-
-	*_page = page;
-
-	return kmap(page);
-
-error:
-	kvm_inject_gp(&svm->vcpu, 0);
-
-	return NULL;
-}
-
-static void nested_svm_unmap(struct page *page)
-{
-	kunmap(page);
-	kvm_release_page_dirty(page);
-}
-
 static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 {
 	unsigned port, size, iopm_len;
@@ -3299,10 +3273,11 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr
 
 static int nested_svm_vmexit(struct vcpu_svm *svm)
 {
+	int rc;
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 
 	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
 				       vmcb->control.exit_info_1,
@@ -3311,9 +3286,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 				       vmcb->control.exit_int_info_err,
 				       KVM_ISA_SVM);
 
-	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
-	if (!nested_vmcb)
+	rc = kvm_vcpu_map(&svm->vcpu, gfn_to_gpa(svm->nested.vmcb), &map);
+	if (rc) {
+		if (rc == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
+
+	nested_vmcb = map.hva;
 
 	/* Exit Guest-Mode */
 	leave_guest_mode(&svm->vcpu);
@@ -3408,16 +3388,16 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	} else {
 		(void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
 	}
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip);
+	kvm_rax_write(&svm->vcpu, hsave->save.rax);
+	kvm_rsp_write(&svm->vcpu, hsave->save.rsp);
+	kvm_rip_write(&svm->vcpu, hsave->save.rip);
 	svm->vmcb->save.dr7 = 0;
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
 	mark_all_dirty(svm->vmcb);
 
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	nested_svm_uninit_mmu_context(&svm->vcpu);
 	kvm_mmu_reset_context(&svm->vcpu);
@@ -3483,7 +3463,7 @@ static bool nested_vmcb_checks(struct vmcb *vmcb)
 }
 
 static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
-				 struct vmcb *nested_vmcb, struct page *page)
+				 struct vmcb *nested_vmcb, struct kvm_host_map *map)
 {
 	if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF)
 		svm->vcpu.arch.hflags |= HF_HIF_MASK;
@@ -3516,9 +3496,9 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	kvm_mmu_reset_context(&svm->vcpu);
 
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
-	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+	kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax);
+	kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp);
+	kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip);
 
 	/* In case we don't even reach vcpu_run, the fields are not updated */
 	svm->vmcb->save.rax = nested_vmcb->save.rax;
@@ -3567,7 +3547,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	svm->vmcb->control.pause_filter_thresh =
 		nested_vmcb->control.pause_filter_thresh;
 
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, map, true);
 
 	/* Enter Guest-Mode */
 	enter_guest_mode(&svm->vcpu);
@@ -3587,17 +3567,23 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 
 static bool nested_svm_vmrun(struct vcpu_svm *svm)
 {
+	int rc;
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	u64 vmcb_gpa;
 
 	vmcb_gpa = svm->vmcb->save.rax;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
+	rc = kvm_vcpu_map(&svm->vcpu, gfn_to_gpa(vmcb_gpa), &map);
+	if (rc) {
+		if (rc == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return false;
+	}
+
+	nested_vmcb = map.hva;
 
 	if (!nested_vmcb_checks(nested_vmcb)) {
 		nested_vmcb->control.exit_code    = SVM_EXIT_ERR;
@@ -3605,7 +3591,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 		nested_vmcb->control.exit_info_1  = 0;
 		nested_vmcb->control.exit_info_2  = 0;
 
-		nested_svm_unmap(page);
+		kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 		return false;
 	}
@@ -3649,7 +3635,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 
 	copy_vmcb_control_area(hsave, vmcb);
 
-	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, page);
+	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map);
 
 	return true;
 }
@@ -3673,21 +3659,26 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 static int vmload_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
+	if (ret) {
+		if (ret == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
+
+	nested_vmcb = map.hva;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	return ret;
 }
@@ -3695,21 +3686,26 @@ static int vmload_interception(struct vcpu_svm *svm)
 static int vmsave_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
-	if (!nested_vmcb)
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map);
+	if (ret) {
+		if (ret == -EINVAL)
+			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
+	}
+
+	nested_vmcb = map.hva;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
-	nested_svm_unmap(page);
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	return ret;
 }
@@ -3791,11 +3787,11 @@ static int invlpga_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
-	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX),
-			  kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_rcx_read(&svm->vcpu),
+			  kvm_rax_read(&svm->vcpu));
 
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
-	kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu));
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	return kvm_skip_emulated_instruction(&svm->vcpu);
@@ -3803,7 +3799,7 @@ static int invlpga_interception(struct vcpu_svm *svm)
 
 static int skinit_interception(struct vcpu_svm *svm)
 {
-	trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
+	trace_kvm_skinit(svm->vmcb->save.rip, kvm_rax_read(&svm->vcpu));
 
 	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
@@ -3817,7 +3813,7 @@ static int wbinvd_interception(struct vcpu_svm *svm)
 static int xsetbv_interception(struct vcpu_svm *svm)
 {
 	u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
-	u32 index = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+	u32 index = kvm_rcx_read(&svm->vcpu);
 
 	if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
@@ -4213,7 +4209,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 static int rdmsr_interception(struct vcpu_svm *svm)
 {
-	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+	u32 ecx = kvm_rcx_read(&svm->vcpu);
 	struct msr_data msr_info;
 
 	msr_info.index = ecx;
@@ -4225,10 +4221,8 @@ static int rdmsr_interception(struct vcpu_svm *svm)
 	} else {
 		trace_kvm_msr_read(ecx, msr_info.data);
 
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RAX,
-				   msr_info.data & 0xffffffff);
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
-				   msr_info.data >> 32);
+		kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff);
+		kvm_rdx_write(&svm->vcpu, msr_info.data >> 32);
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}
@@ -4422,7 +4416,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 static int wrmsr_interception(struct vcpu_svm *svm)
 {
 	struct msr_data msr;
-	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+	u32 ecx = kvm_rcx_read(&svm->vcpu);
 	u64 data = kvm_read_edx_eax(&svm->vcpu);
 
 	msr.data = data;
@@ -6236,7 +6230,7 @@ static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *nested_vmcb;
-	struct page *page;
+	struct kvm_host_map map;
 	u64 guest;
 	u64 vmcb;
 
@@ -6244,10 +6238,10 @@ static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
 	if (guest) {
-		nested_vmcb = nested_svm_map(svm, vmcb, &page);
-		if (!nested_vmcb)
+		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
 			return 1;
-		enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
+		nested_vmcb = map.hva;
+		enter_svm_guest_mode(svm, vmcb, nested_vmcb, &map);
 	}
 	return 0;
 }
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 854e144131c6..d6664ee3d127 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -2,6 +2,8 @@
 #ifndef __KVM_X86_VMX_CAPS_H
 #define __KVM_X86_VMX_CAPS_H
 
+#include <asm/vmx.h>
+
 #include "lapic.h"
 
 extern bool __read_mostly enable_vpid;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0c601d079cd2..f1a69117ac0f 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -193,10 +193,8 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.hv_evmcs)
 		return;
 
-	kunmap(vmx->nested.hv_evmcs_page);
-	kvm_release_page_dirty(vmx->nested.hv_evmcs_page);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
 	vmx->nested.hv_evmcs_vmptr = -1ull;
-	vmx->nested.hv_evmcs_page = NULL;
 	vmx->nested.hv_evmcs = NULL;
 }
 
@@ -229,16 +227,9 @@ static void free_nested(struct kvm_vcpu *vcpu)
 		kvm_release_page_dirty(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
-	if (vmx->nested.virtual_apic_page) {
-		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
-		vmx->nested.virtual_apic_page = NULL;
-	}
-	if (vmx->nested.pi_desc_page) {
-		kunmap(vmx->nested.pi_desc_page);
-		kvm_release_page_dirty(vmx->nested.pi_desc_page);
-		vmx->nested.pi_desc_page = NULL;
-		vmx->nested.pi_desc = NULL;
-	}
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
+	vmx->nested.pi_des