Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: add support for change_pte mmu notifiers
  KVM: MMU: add SPTE_HOST_WRITEABLE flag to the shadow ptes
  KVM: MMU: dont hold pagecount reference for mapped sptes pages
  KVM: Prevent overflow in KVM_GET_SUPPORTED_CPUID
  KVM: VMX: flush TLB with INVEPT on cpu migration
  KVM: fix LAPIC timer period overflow
  KVM: s390: fix memsize >= 4G
  KVM: SVM: Handle tsc in svm_get_msr/svm_set_msr correctly
  KVM: SVM: Fix tsc offset adjustment when running nested

9 files changed, 120 insertions, 30 deletions

diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index ec5eee7c25d8..06cce8285ba0 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -58,7 +58,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
-static inline int kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
+static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.sie_block->gmslm
 		- vcpu->arch.sie_block->gmsor
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3be000435fad..d83892226f73 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -796,6 +796,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 1ae5ceba7eb2..7024224f0fc8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -664,7 +664,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now = apic->lapic_timer.timer.base->get_time();
 
-	apic->lapic_timer.period = apic_get_reg(apic, APIC_TMICT) *
+	apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) *
 		    APIC_BUS_CYCLE_NS * apic->divide_count;
 	atomic_set(&apic->lapic_timer.pending, 0);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca41ae9f453..685a4ffac8e6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -156,6 +156,8 @@ module_param(oos_shadow, bool, 0644);
 #define CREATE_TRACE_POINTS
 #include "mmutrace.h"
 
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+
 #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 
 struct kvm_rmap_desc {
@@ -634,9 +636,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	if (*spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
 	if (is_writeble_pte(*spte))
-		kvm_release_pfn_dirty(pfn);
-	else
-		kvm_release_pfn_clean(pfn);
+		kvm_set_pfn_dirty(pfn);
 	rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level);
 	if (!*rmapp) {
 		printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
@@ -748,7 +748,7 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn)
 	return write_protected;
 }
 
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data)
 {
 	u64 *spte;
 	int need_tlb_flush = 0;
@@ -763,8 +763,45 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
 	return need_tlb_flush;
 }
 
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data)
+{
+	int need_flush = 0;
+	u64 *spte, new_spte;
+	pte_t *ptep = (pte_t *)data;
+	pfn_t new_pfn;
+
+	WARN_ON(pte_huge(*ptep));
+	new_pfn = pte_pfn(*ptep);
+	spte = rmap_next(kvm, rmapp, NULL);
+	while (spte) {
+		BUG_ON(!is_shadow_present_pte(*spte));
+		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+		need_flush = 1;
+		if (pte_write(*ptep)) {
+			rmap_remove(kvm, spte);
+			__set_spte(spte, shadow_trap_nonpresent_pte);
+			spte = rmap_next(kvm, rmapp, NULL);
+		} else {
+			new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+			new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+			new_spte &= ~PT_WRITABLE_MASK;
+			new_spte &= ~SPTE_HOST_WRITEABLE;
+			if (is_writeble_pte(*spte))
+				kvm_set_pfn_dirty(spte_to_pfn(*spte));
+			__set_spte(spte, new_spte);
+			spte = rmap_next(kvm, rmapp, spte);
+		}
+	}
+	if (need_flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, u64 data,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 u64 data))
 {
 	int i, j;
 	int retval = 0;
@@ -786,13 +823,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 		if (hva >= start && hva < end) {
 			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
 
-			retval |= handler(kvm, &memslot->rmap[gfn_offset]);
+			retval |= handler(kvm, &memslot->rmap[gfn_offset],
+					  data);
 
 			for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
 				int idx = gfn_offset;
 				idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j);
 				retval |= handler(kvm,
-					&memslot->lpage_info[j][idx].rmap_pde);
+					&memslot->lpage_info[j][idx].rmap_pde,
+					data);
 			}
 		}
 	}
@@ -802,10 +841,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
 }
 
-static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	kvm_handle_hva(kvm, hva, (u64)&pte, kvm_set_pte_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 data)
 {
 	u64 *spte;
 	int young = 0;
@@ -841,13 +885,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	gfn = unalias_gfn(vcpu->kvm, gfn);
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
 }
 
 #ifdef MMU_DEBUG
@@ -1756,7 +1800,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int user_fault,
 		    int write_fault, int dirty, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
-		    bool can_unsync)
+		    bool can_unsync, bool reset_host_protection)
 {
 	u64 spte;
 	int ret = 0;
@@ -1783,6 +1827,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
 			kvm_is_mmio_pfn(pfn));
 
+	if (reset_host_protection)
+		spte |= SPTE_HOST_WRITEABLE;
+
 	spte |= (u64)pfn << PAGE_SHIFT;
 
 	if ((pte_access & ACC_WRITE_MASK)
@@ -1828,7 +1875,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 unsigned pt_access, unsigned pte_access,
 			 int user_fault, int write_fault, int dirty,
 			 int *ptwrite, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative)
+			 pfn_t pfn, bool speculative,
+			 bool reset_host_protection)
 {
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*sptep);
@@ -1860,7 +1908,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 
 	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
-		      dirty, level, gfn, pfn, speculative, true)) {
+		      dirty, level, gfn, pfn, speculative, true,
+		      reset_host_protection)) {
 		if (write_fault)
 			*ptwrite = 1;
 		kvm_x86_ops->tlb_flush(vcpu);
@@ -1877,8 +1926,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	page_header_update_slot(vcpu->kvm, sptep, gfn);
 	if (!was_rmapped) {
 		rmap_count = rmap_add(vcpu, sptep, gfn);
-		if (!is_rmap_spte(*sptep))
-			kvm_release_pfn_clean(pfn);
+		kvm_release_pfn_clean(pfn);
 		if (rmap_count > RMAP_RECYCLE_THRESHOLD)
 			rmap_recycle(vcpu, sptep, gfn);
 	} else {
@@ -1909,7 +1957,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 		if (iterator.level == level) {
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
 				     0, write, 1, &pt_write,
-				     level, gfn, pfn, false);
+				     level, gfn, pfn, false, true);
 			++vcpu->stat.pf_fixed;
 			break;
 		}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index d2fec9c12d22..72558f8ff3f5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -273,9 +273,13 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 	if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq))
 		return;
 	kvm_get_pfn(pfn);
+	/*
+	 * we call mmu_set_spte() with reset_host_protection = true beacuse that
+	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
+	 */
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
 		     gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL,
-		     gpte_to_gfn(gpte), pfn, true);
+		     gpte_to_gfn(gpte), pfn, true, true);
 }
 
 /*
@@ -308,7 +312,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 				     user_fault, write_fault,
 				     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
 				     ptwrite, level,
-				     gw->gfn, pfn, false);
+				     gw->gfn, pfn, false, true);
 			break;
 		}
 
@@ -558,6 +562,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	int i, offset, nr_present;
+	bool reset_host_protection;
 
 	offset = nr_present = 0;
 
@@ -595,9 +600,16 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+		if (!(sp->spt[i] & SPTE_HOST_WRITEABLE)) {
+			pte_access &= ~ACC_WRITE_MASK;
+			reset_host_protection = 0;
+		} else {
+			reset_host_protection = 1;
+		}
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
 			 is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
-			 spte_to_pfn(sp->spt[i]), true, false);
+			 spte_to_pfn(sp->spt[i]), true, false,
+			 reset_host_protection);
 	}
 
 	return !nr_present;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 944cc9c04b3c..c17404add91f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -767,6 +767,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdtscll(tsc_this);
 		delta = vcpu->arch.host_tsc - tsc_this;
 		svm->vmcb->control.tsc_offset += delta;
+		if (is_nested(svm))
+			svm->nested.hsave->control.tsc_offset += delta;
 		vcpu->cpu = cpu;
 		kvm_migrate_timers(vcpu);
 		svm->asid_generation = 0;
@@ -2057,10 +2059,14 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset;
+
+		if (is_nested(svm))
+			tsc_offset = svm->nested.hsave->control.tsc_offset;
+		else
+			tsc_offset = svm->vmcb->control.tsc_offset;
 
-		rdtscll(tsc);
-		*data = svm->vmcb->control.tsc_offset + tsc;
+		*data = tsc_offset + native_read_tsc();
 		break;
 	}
 	case MSR_K6_STAR:
@@ -2146,10 +2152,17 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset = data - native_read_tsc();
+		u64 g_tsc_offset = 0;
+
+		if (is_nested(svm)) {
+			g_tsc_offset = svm->vmcb->control.tsc_offset -
+				       svm->nested.hsave->control.tsc_offset;
+			svm->nested.hsave->control.tsc_offset = tsc_offset;
+		}
+
+		svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset;
 
-		rdtscll(tsc);
-		svm->vmcb->control.tsc_offset = data - tsc;
 		break;
 	}
 	case MSR_K6_STAR:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f3812014bd0b..ed53b42caba1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -709,7 +709,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (vcpu->cpu != cpu) {
 		vcpu_clear(vmx);
 		kvm_migrate_timers(vcpu);
-		vpid_sync_vcpu_all(vmx);
+		set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
 		local_irq_disable();
 		list_add(&vmx->local_vcpus_link,
 			 &per_cpu(vcpus_on_cpu, cpu));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index be451ee44249..9b9695322f56 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1591,6 +1591,8 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 
 	if (cpuid->nent < 1)
 		goto out;
+	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
+		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
 	r = -ENOMEM;
 	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
 	if (!cpuid_entries)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e79c54034bcd..b7c78a403dc2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -850,6 +850,19 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
 
 }
 
+static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
+					struct mm_struct *mm,
+					unsigned long address,
+					pte_t pte)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+
+	spin_lock(&kvm->mmu_lock);
+	kvm->mmu_notifier_seq++;
+	kvm_set_spte_hva(kvm, address, pte);
+	spin_unlock(&kvm->mmu_lock);
+}
+
 static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 						    struct mm_struct *mm,
 						    unsigned long start,
@@ -929,6 +942,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
+	.change_pte		= kvm_mmu_notifier_change_pte,
 	.release		= kvm_mmu_notifier_release,
 };
 #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */