Merge branch 'kvm-updates/3.3' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/3.3' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (74 commits)
  KVM: PPC: Whitespace fix for kvm.h
  KVM: Fix whitespace in kvm_para.h
  KVM: PPC: annotate kvm_rma_init as __init
  KVM: x86 emulator: implement RDPMC (0F 33)
  KVM: x86 emulator: fix RDPMC privilege check
  KVM: Expose the architectural performance monitoring CPUID leaf
  KVM: VMX: Intercept RDPMC
  KVM: SVM: Intercept RDPMC
  KVM: Add generic RDPMC support
  KVM: Expose a version 2 architectural PMU to a guests
  KVM: Expose kvm_lapic_local_deliver()
  KVM: x86 emulator: Use opcode::execute for Group 9 instruction
  KVM: x86 emulator: Use opcode::execute for Group 4/5 instructions
  KVM: x86 emulator: Use opcode::execute for Group 1A instruction
  KVM: ensure that debugfs entries have been created
  KVM: drop bsp_vcpu pointer from kvm struct
  KVM: x86: Consolidate PIT legacy test
  KVM: x86: Do not rely on implicit inclusions
  KVM: Make KVM_INTEL depend on CPU_SUP_INTEL
  KVM: Use memdup_user instead of kmalloc/copy_from_user
  ...

27 files changed, 2146 insertions, 1649 deletions

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 43f4c92816e..40505200249 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -774,13 +774,13 @@ struct kvm *kvm_arch_alloc_vm(void)
 	return kvm;
 }
 
-struct kvm_io_range {
+struct kvm_ia64_io_range {
 	unsigned long start;
 	unsigned long size;
 	unsigned long type;
 };
 
-static const struct kvm_io_range io_ranges[] = {
+static const struct kvm_ia64_io_range io_ranges[] = {
 	{VGA_IO_START, VGA_IO_SIZE, GPFN_FRAME_BUFFER},
 	{MMIO_START, MMIO_SIZE, GPFN_LOW_MMIO},
 	{LEGACY_IO_START, LEGACY_IO_SIZE, GPFN_LEGACY_IO},
@@ -1366,14 +1366,12 @@ static void kvm_release_vm_pages(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
-	int i, j;
+	int j;
 	unsigned long base_gfn;
 
 	slots = kvm_memslots(kvm);
-	for (i = 0; i < slots->nmemslots; i++) {
-		memslot = &slots->memslots[i];
+	kvm_for_each_memslot(memslot, slots) {
 		base_gfn = memslot->base_gfn;
-
 		for (j = 0; j < memslot->npages; j++) {
 			if (memslot->rmap[j])
 				put_page((struct page *)memslot->rmap[j]);
@@ -1820,7 +1818,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots->memslots[log->slot];
+	memslot = id_to_memslot(kvm->memslots, log->slot);
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index 0ad432bc81d..f7727d91ac6 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -170,8 +170,8 @@ struct kvm_sregs {
 			} ppc64;
 			struct {
 				__u32 sr[16];
-				__u64 ibat[8]; 
-				__u64 dbat[8]; 
+				__u64 ibat[8];
+				__u64 dbat[8];
 			} ppc32;
 		} s;
 		struct {
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index a459479995c..e41ac6f7dcf 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -498,7 +498,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = &kvm->memslots->memslots[log->slot];
+		memslot = id_to_memslot(kvm->memslots, log->slot);
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 286f13d601c..a795a13f4a7 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -86,7 +86,7 @@ static inline int lpcr_rmls(unsigned long rma_size)
  * to allocate contiguous physical memory for the real memory
  * areas for guests.
  */
-void kvm_rma_init(void)
+void __init kvm_rma_init(void)
 {
 	unsigned long i;
 	unsigned long j, npages;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f3444f700f3..17c5d4bdee5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -197,7 +197,10 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_BMI1	(9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_AVX2	(9*32+ 5) /* AVX2 instructions */
 #define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	(9*32+ 8) /* 2nd group bit manipulation extensions */
 #define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index a026507893e..ab4092e3214 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -181,6 +181,7 @@ struct x86_emulate_ops {
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
 	int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
+	int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
@@ -364,6 +365,7 @@ enum x86_intercept {
 #endif
 
 int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b4973f4dab9..52d6640a5ca 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -16,10 +16,12 @@
 #include <linux/mmu_notifier.h>
 #include <linux/tracepoint.h>
 #include <linux/cpumask.h>
+#include <linux/irq_work.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
+#include <linux/perf_event.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -31,6 +33,8 @@
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+
 #define KVM_MMIO_SIZE 16
 
 #define KVM_PIO_PAGE_OFFSET 1
@@ -228,7 +232,7 @@ struct kvm_mmu_page {
 	 * One bit set per slot which has memory
 	 * in this shadow page.
 	 */
-	DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
+	DECLARE_BITMAP(slot_bitmap, KVM_MEM_SLOTS_NUM);
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
@@ -239,14 +243,9 @@ struct kvm_mmu_page {
 	int clear_spte_count;
 #endif
 
-	struct rcu_head rcu;
-};
+	int write_flooding_count;
 
-struct kvm_pv_mmu_op_buffer {
-	void *ptr;
-	unsigned len;
-	unsigned processed;
-	char buf[512] __aligned(sizeof(long));
+	struct rcu_head rcu;
 };
 
 struct kvm_pio_request {
@@ -294,6 +293,37 @@ struct kvm_mmu {
 	u64 pdptrs[4]; /* pae */
 };
 
+enum pmc_type {
+	KVM_PMC_GP = 0,
+	KVM_PMC_FIXED,
+};
+
+struct kvm_pmc {
+	enum pmc_type type;
+	u8 idx;
+	u64 counter;
+	u64 eventsel;
+	struct perf_event *perf_event;
+	struct kvm_vcpu *vcpu;
+};
+
+struct kvm_pmu {
+	unsigned nr_arch_gp_counters;
+	unsigned nr_arch_fixed_counters;
+	unsigned available_event_types;
+	u64 fixed_ctr_ctrl;
+	u64 global_ctrl;
+	u64 global_status;
+	u64 global_ovf_ctrl;
+	u64 counter_bitmask[2];
+	u64 global_ctrl_mask;
+	u8 version;
+	struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
+	struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+	struct irq_work irq_work;
+	u64 reprogram_pmi;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -345,19 +375,10 @@ struct kvm_vcpu_arch {
 	 */
 	struct kvm_mmu *walk_mmu;
 
-	/* only needed in kvm_pv_mmu_op() path, but it's hot so
-	 * put it here to avoid allocation */
-	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
-
 	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
-	gfn_t last_pt_write_gfn;
-	int   last_pt_write_count;
-	u64  *last_pte_updated;
-	gfn_t last_pte_gfn;
-
 	struct fpu guest_fpu;
 	u64 xcr0;
 
@@ -436,6 +457,8 @@ struct kvm_vcpu_arch {
 	unsigned access;
 	gfn_t mmio_gfn;
 
+	struct kvm_pmu pmu;
+
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
@@ -444,6 +467,9 @@ struct kvm_vcpu_arch {
 
 	cpumask_var_t wbinvd_dirty_mask;
 
+	unsigned long last_retry_eip;
+	unsigned long last_retry_addr;
+
 	struct {
 		bool halted;
 		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
@@ -459,7 +485,6 @@ struct kvm_arch {
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_max_mmu_pages;
 	unsigned int indirect_shadow_pages;
-	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
 	 * Hash table of struct kvm_mmu_page.
@@ -660,6 +685,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
+int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
+			       struct kvm_memory_slot *slot);
 void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
@@ -668,8 +695,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret);
 u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
@@ -692,6 +717,7 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
+#define EMULTYPE_RETRY		    (1 << 3)
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 			    int emulation_type, void *insn, int insn_len);
 
@@ -734,6 +760,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 
 unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
 void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+bool kvm_rdpmc(struct kvm_vcpu *vcpu);
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
@@ -754,13 +781,14 @@ int fx_init(struct kvm_vcpu *vcpu);
 
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes,
-		       bool guest_initiated);
+		       const u8 *new, int bytes);
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
 gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
 			      struct x86_exception *exception);
 gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
@@ -782,6 +810,11 @@ void kvm_disable_tdp(void);
 int complete_pio(struct kvm_vcpu *vcpu);
 bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
+static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+{
+	return gpa;
+}
+
 static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 {
 	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
@@ -894,4 +927,17 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
+int kvm_is_in_guest(void);
+
+void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+void kvm_pmu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
+bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
+void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
+void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a9c2116001d..f0c6fd6f176 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -39,8 +39,6 @@
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_QUEUE_SIZE 1024
-
 static int kvmapf = 1;
 
 static int parse_no_kvmapf(char *arg)
@@ -60,21 +58,10 @@ static int parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-struct kvm_para_state {
-	u8 mmu_queue[MMU_QUEUE_SIZE];
-	int mmu_queue_len;
-};
-
-static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
 
-static struct kvm_para_state *kvm_para_state(void)
-{
-	return &per_cpu(para_state, raw_smp_processor_id());
-}
-
 /*
  * No need for any "IO delay" on KVM
  */
@@ -271,151 +258,6 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 }
 
-static void kvm_mmu_op(void *buffer, unsigned len)
-{
-	int r;
-	unsigned long a1, a2;
-
-	do {
-		a1 = __pa(buffer);
-		a2 = 0;   /* on i386 __pa() always returns <4G */
-		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
-		buffer += r;
-		len -= r;
-	} while (len);
-}
-
-static void mmu_queue_flush(struct kvm_para_state *state)
-{
-	if (state->mmu_queue_len) {
-		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
-		state->mmu_queue_len = 0;
-	}
-}
-
-static void kvm_deferred_mmu_op(void *buffer, int len)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
-		kvm_mmu_op(buffer, len);
-		return;
-	}
-	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
-		mmu_queue_flush(state);
-	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
-	state->mmu_queue_len += len;
-}
-
-static void kvm_mmu_write(void *dest, u64 val)
-{
-	__u64 pte_phys;
-	struct kvm_mmu_op_write_pte wpte;
-
-#ifdef CONFIG_HIGHPTE
-	struct page *page;
-	unsigned long dst = (unsigned long) dest;
-
-	page = kmap_atomic_to_page(dest);
-	pte_phys = page_to_pfn(page);
-	pte_phys <<= PAGE_SHIFT;
-	pte_phys += (dst & ~(PAGE_MASK));
-#else
-	pte_phys = (unsigned long)__pa(dest);
-#endif
-	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
-	wpte.pte_val = val;
-	wpte.pte_phys = pte_phys;
-
-	kvm_deferred_mmu_op(&wpte, sizeof wpte);
-}
-
-/*
- * We only need to hook operations that are MMU writes.  We hook these so that
- * we can use lazy MMU mode to batch these operations.  We could probably
- * improve the performance of the host code if we used some of the information
- * here to simplify processing of batched writes.
- */
-static void kvm_set_pte(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	kvm_mmu_write(pmdp, pmd_val(pmd));
-}
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_pte_clear(struct mm_struct *mm,
-			  unsigned long addr, pte_t *ptep)
-{
-	kvm_mmu_write(ptep, 0);
-}
-
-static void kvm_pmd_clear(pmd_t *pmdp)
-{
-	kvm_mmu_write(pmdp, 0);
-}
-#endif
-
-static void kvm_set_pud(pud_t *pudp, pud_t pud)
-{
-	kvm_mmu_write(pudp, pud_val(pud));
-}
-
-#if PAGETABLE_LEVELS == 4
-static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	kvm_mmu_write(pgdp, pgd_val(pgd));
-}
-#endif
-#endif /* PAGETABLE_LEVELS >= 3 */
-
-static void kvm_flush_tlb(void)
-{
-	struct kvm_mmu_op_flush_tlb ftlb = {
-		.header.op = KVM_MMU_OP_FLUSH_TLB,
-	};
-
-	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
-}
-
-static void kvm_release_pt(unsigned long pfn)
-{
-	struct kvm_mmu_op_release_pt rpt = {
-		.header.op = KVM_MMU_OP_RELEASE_PT,
-		.pt_phys = (u64)pfn << PAGE_SHIFT,
-	};
-
-	kvm_mmu_op(&rpt, sizeof rpt);
-}
-
-static void kvm_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-}
-
-static void kvm_leave_lazy_mmu(void)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	mmu_queue_flush(state);
-	paravirt_leave_lazy_mmu();
-}
-
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
@@ -424,29 +266,6 @@ static void __init paravirt_ops_setup(void)
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 
-	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
-		pv_mmu_ops.set_pte = kvm_set_pte;
-		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
-		pv_mmu_ops.set_pmd = kvm_set_pmd;
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
-		pv_mmu_ops.pte_clear = kvm_pte_clear;
-		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
-#endif
-		pv_mmu_ops.set_pud = kvm_set_pud;
-#if PAGETABLE_LEVELS == 4
-		pv_mmu_ops.set_pgd = kvm_set_pgd;
-#endif
-#endif
-		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
-		pv_mmu_ops.release_pte = kvm_release_pt;
-		pv_mmu_ops.release_pmd = kvm_release_pt;
-		pv_mmu_ops.release_pud = kvm_release_pt;
-
-		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
-		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
-	}
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index ff5790d8e99..1a7fe868f37 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -35,6 +35,7 @@ config KVM
 	select KVM_MMIO
 	select TASKSTATS
 	select TASK_DELAY_ACCT
+	select PERF_EVENTS
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@@ -52,6 +53,8 @@ config KVM
 config KVM_INTEL
 	tristate "KVM for Intel processors support"
 	depends on KVM
+	# for perf_guest_get_msrs():
+	depends on CPU_SUP_INTEL
 	---help---
 	  Provides support for KVM on Intel processors equipped with the VT
 	  extensions.
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index f15501f431c..4f579e8dcac 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(addprefix ../../../virt/kvm/, async_pf.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o timer.o
+			   i8254.o timer.o cpuid.o pmu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
new file mode 100644
index 00000000000..89b02bfaaca
--- /dev/null
+++ b/arch/x86/kvm/cpuid.c
@@ -0,0 +1,670 @@
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ * cpuid support routines
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ * Copyright IBM Corporation, 2008
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/uaccess.h>
+#include <asm/user.h>
+#include <asm/xsave.h>
+#include "cpuid.h"
+#include "lapic.h"
+#include "mmu.h"
+#include "trace.h"
+
+void kvm_update_cpuid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	if (!best)
+		return;
+
+	/* Update OSXSAVE bit */
+	if (cpu_has_xsave && best->function == 0x1) {
+		best->ecx &= ~(bit(X86_FEATURE_OSXSAVE));
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
+			best->ecx |= bit(X86_FEATURE_OSXSAVE);
+	}
+
+	if (apic) {
+		if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
+			apic->lapic_timer.timer_mode_mask = 3 << 17;
+		else
+			apic->lapic_timer.timer_mode_mask = 1 << 17;
+	}
+
+	kvm_pmu_cpuid_update(vcpu);
+}
+
+static int is_efer_nx(void)
+{
+	unsigned long long efer = 0;
+
+	rdmsrl_safe(MSR_EFER, &efer);
+	return efer & EFER_NX;
+}
+
+static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_cpuid_entry2 *e, *entry;
+
+	entry = NULL;
+	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
+		e = &vcpu->arch.cpuid_entries[i];
+		if (e->function == 0x80000001) {
+			entry = e;
+			break;
+		}
+	}
+	if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
+		entry->edx &= ~(1 << 20);
+		printk(KERN_INFO "kvm: guest NX capability removed\n");
+	}
+}
+
+/* when an old userspace process fills a new kernel module */
+int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
+			     struct kvm_cpuid *cpuid,
+			     struct kvm_cpuid_entry __user *entries)
+{
+	int r, i;
+	struct kvm_cpuid_entry *cpuid_entries;
+
+	r = -E2BIG;
+	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
+		goto out;
+	r = -ENOMEM;
+	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
+	if (!cpuid_entries)
+		goto out;
+	r = -EFAULT;
+	if (copy_from_user(cpuid_entries, entries,
+			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+		goto out_free;
+	for (i = 0; i < cpuid->nent; i++) {
+		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
+		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
+		vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
+		vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
+		vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
+		vcpu->arch.cpuid_entries[i].index = 0;
+		vcpu->arch.cpuid_entries[i].flags = 0;
+		vcpu->arch.cpuid_entries[i].padding[0] = 0;
+		vcpu->arch.cpuid_entries[i].padding[1] = 0;
+		vcpu->arch.cpuid_entries[i].padding[2] = 0;
+	}
+	vcpu->arch.cpuid_nent = cpuid->nent;
+	cpuid_fix_nx_cap(vcpu);
+	r = 0;
+	kvm_apic_set_version(vcpu);
+	kvm_x86_ops->cpuid_update(vcpu);
+	kvm_update_cpuid(vcpu);
+
+out_free:
+	vfree(cpuid_entries);
+out:
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
+			      struct kvm_cpuid2 *cpuid,
+			      struct kvm_cpuid_entry2 __user *entries)
+{
+	int r;
+
+	r = -E2BIG;
+	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
+		goto out;
+	r = -EFAULT;
+	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
+			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
+		goto out;
+	vcpu->arch.cpuid_nent = cpuid->nent;
+	kvm_apic_set_version(vcpu);
+	kvm_x86_ops->cpuid_update(vcpu);
+	kvm_update_cpuid(vcpu);
+	return 0;
+
+out:
+	return r;
+}
+
+int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
+			      struct kvm_cpuid2 *cpuid,
+			      struct kvm_cpuid_entry2 __user *entries)
+{
+	int r;
+
+	r = -E2BIG;
+	if (cpuid->nent < vcpu->arch.cpuid_nent)
+		goto out;
+	r = -EFAULT;
+	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
+			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
+		goto out;
+	return 0;
+
+out:
+	cpuid->nent = vcpu->arch.cpuid_nent;
+	return r;
+}
+
+static void cpuid_mask(u32 *word, int wordnum)
+{
+	*word &= boot_cpu_data.x86_capability[wordnum];
+}
+
+static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+			   u32 index)
+{
+	entry->function = function;
+	entry->index = index;
+	cpuid_count(entry->function, entry->index,
+		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
+	entry->flags = 0;
+}
+
+static bool supported_xcr0_bit(unsigned bit)
+{
+	u64 mask = ((u64)1 << bit);
+
+	return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0;
+}
+
+#define F(x) bit(X86_FEATURE_##x)
+
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+			 u32 index, int *nent, int maxnent)
+{
+	int r;
+	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
+#ifdef CONFIG_X86_64
+	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
+				? F(GBPAGES) : 0;
+	unsigned f_lm = F(LM);
+#else
+	unsigned f_gbpages = 0;
+	unsigned f_lm = 0;
+#endif
+	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
+
+	/* cpuid 1.edx */
+	const u32 kvm_supported_word0_x86_features =
+		F(FPU) | F(VME) | F(DE) | F(PSE) |
+		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
+		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
+		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
+		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
+		0 /* Reserved, DS, ACPI */ | F(MMX) |
+		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
+		0 /* HTT, TM, Reserved, PBE */;
+	/* cpuid 0x80000001.edx */
+	const u32 kvm_supported_word1_x86_features =
+		F(FPU) | F(VME) | F(DE) | F(PSE) |
+		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
+		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
+		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
+		F(PAT) | F(PSE36) | 0 /* Reserved */ |
+		f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
+		F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp |
+		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
+	/* cpuid 1.ecx */
+	const u32 kvm_supported_word4_x86_features =
+		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
+		0 /* DS-CPL, VMX, SMX, EST */ |
+		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
+		F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ |
+		0 /* Reserved, DCA */ | F(XMM4_1) |
+		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
+		0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+		F(F16C) | F(RDRAND);
+	/* cpuid 0x80000001.ecx */
+	const u32 kvm_supported_word6_x86_features =
+		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
+		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
+		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
+
+	/* cpuid 0xC0000001.edx */
+	const u32 kvm_supported_word5_x86_features =
+		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
+		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
+		F(PMM) | F(PMM_EN);
+
+	/* cpuid 7.0.ebx */
+	const u32 kvm_supported_word9_x86_features =
+		F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS);
+
+	/* all calls to cpuid_count() should be made on the same cpu */
+	get_cpu();
+
+	r = -E2BIG;
+
+	if (*nent >= maxnent)
+		goto out;
+
+	do_cpuid_1_ent(entry, function, index);
+	++*nent;
+
+	switch (function) {
+	case 0:
+		entry->eax = min(entry->eax, (u32)0xd);
+		break;
+	case 1:
+		entry->edx &= kvm_supported_word0_x86_features;
+		cpuid_mask(&entry->edx, 0);