5 files changed, 41 insertions, 30 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 908ea5464a51..fb8b376bf28c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -720,7 +720,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
         }
 }
 
-static void set_spte_track_bits(u64 *sptep, u64 new_spte)
+static int set_spte_track_bits(u64 *sptep, u64 new_spte)
 {
         pfn_t pfn;
         u64 old_spte = *sptep;
@@ -731,19 +731,20 @@ static void set_spte_track_bits(u64 *sptep, u64 new_spte)
                 old_spte = __xchg_spte(sptep, new_spte);
 
         if (!is_rmap_spte(old_spte))
-                return;
+                return 0;
 
         pfn = spte_to_pfn(old_spte);
         if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
                 kvm_set_pfn_accessed(pfn);
         if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
                 kvm_set_pfn_dirty(pfn);
+        return 1;
 }
 
 static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte)
 {
-        set_spte_track_bits(sptep, new_spte);
-        rmap_remove(kvm, sptep);
+        if (set_spte_track_bits(sptep, new_spte))
+                rmap_remove(kvm, sptep);
 }
 
 static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 82e144a4e514..b81a9b7c2ca4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3395,6 +3395,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
         vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
         load_host_msrs(vcpu);
+        kvm_load_ldt(ldt_selector);
         loadsegment(fs, fs_selector);
 #ifdef CONFIG_X86_64
         load_gs_index(gs_selector);
@@ -3402,7 +3403,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #else
         loadsegment(gs, gs_selector);
 #endif
-        kvm_load_ldt(ldt_selector);
 
         reload_tss(vcpu);
 
@@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
         switch (func) {
+        case 0x00000001:
+                /* Mask out xsave bit as long as it is not supported by SVM */
+                entry->ecx &= ~(bit(X86_FEATURE_XSAVE));
+                break;
         case 0x80000001:
                 if (nested)
                         entry->ecx |= (1 << 2); /* Set SVM bit */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8da0e45ff7c9..81fcbe9515c5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -821,10 +821,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 #endif
 
 #ifdef CONFIG_X86_64
-        if (is_long_mode(&vmx->vcpu)) {
-                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+        rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+        if (is_long_mode(&vmx->vcpu))
                 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-        }
 #endif
         for (i = 0; i < vmx->save_nmsrs; ++i)
                 kvm_set_shared_msr(vmx->guest_msrs[i].index,
@@ -839,23 +838,23 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 
         ++vmx->vcpu.stat.host_state_reload;
         vmx->host_state.loaded = 0;
-        if (vmx->host_state.fs_reload_needed)
-                loadsegment(fs, vmx->host_state.fs_sel);
+#ifdef CONFIG_X86_64
+        if (is_long_mode(&vmx->vcpu))
+                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+#endif
         if (vmx->host_state.gs_ldt_reload_needed) {
                 kvm_load_ldt(vmx->host_state.ldt_sel);
 #ifdef CONFIG_X86_64
                 load_gs_index(vmx->host_state.gs_sel);
-                wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
 #else
                 loadsegment(gs, vmx->host_state.gs_sel);
 #endif
         }
+        if (vmx->host_state.fs_reload_needed)
+                loadsegment(fs, vmx->host_state.fs_sel);
         reload_tss();
 #ifdef CONFIG_X86_64
-        if (is_long_mode(&vmx->vcpu)) {
-                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-                wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
-        }
+        wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
         if (current_thread_info()->status & TS_USEDFPU)
                 clts();
@@ -4228,11 +4227,6 @@ static int vmx_get_lpage_level(void)
                 return PT_PDPE_LEVEL;
 }
 
-static inline u32 bit(int bitno)
-{
-        return 1 << (bitno & 31);
-}
-
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
         struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2288ad829b32..b989e1f1e5d3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 u64 __read_mostly host_xcr0;
 
-static inline u32 bit(int bitno)
-{
-        return 1 << (bitno & 31);
-}
-
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
         unsigned slot;
@@ -2560,6 +2555,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
                 !kvm_exception_is_soft(vcpu->arch.exception.nr);
         events->exception.nr = vcpu->arch.exception.nr;
         events->exception.has_error_code = vcpu->arch.exception.has_error_code;
+        events->exception.pad = 0;
         events->exception.error_code = vcpu->arch.exception.error_code;
 
         events->interrupt.injected =
@@ -2573,12 +2569,14 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
         events->nmi.injected = vcpu->arch.nmi_injected;
         events->nmi.pending = vcpu->arch.nmi_pending;
         events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+        events->nmi.pad = 0;
 
         events->sipi_vector = vcpu->arch.sipi_vector;
 
         events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
                          | KVM_VCPUEVENT_VALID_SIPI_VECTOR
                          | KVM_VCPUEVENT_VALID_SHADOW);
+        memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
@@ -2623,6 +2621,7 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
         dbgregs->dr6 = vcpu->arch.dr6;
         dbgregs->dr7 = vcpu->arch.dr7;
         dbgregs->flags = 0;
+        memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
 }
 
 static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
@@ -3106,6 +3105,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
                 sizeof(ps->channels));
         ps->flags = kvm->arch.vpit->pit_state.flags;
         mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+        memset(&ps->reserved, 0, sizeof(ps->reserved));
         return r;
 }
 
@@ -3169,10 +3169,6 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
                 struct kvm_memslots *slots, *old_slots;
                 unsigned long *dirty_bitmap;
 
-                spin_lock(&kvm->mmu_lock);
-                kvm_mmu_slot_remove_write_access(kvm, log->slot);
-                spin_unlock(&kvm->mmu_lock);
-
                 r = -ENOMEM;
                 dirty_bitmap = vmalloc(n);
                 if (!dirty_bitmap)
@@ -3194,6 +3190,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
                 dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap;
                 kfree(old_slots);
 
+                spin_lock(&kvm->mmu_lock);
+                kvm_mmu_slot_remove_write_access(kvm, log->slot);
+                spin_unlock(&kvm->mmu_lock);
+
                 r = -EFAULT;
                 if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) {
                         vfree(dirty_bitmap);
@@ -3486,6 +3486,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
                 user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
                 local_irq_enable();
                 user_ns.flags = 0;
+                memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
                 r = -EFAULT;
                 if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
@@ -3972,8 +3973,10 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
                 return X86EMUL_CONTINUE;
 
         if (kvm_x86_ops->has_wbinvd_exit()) {
+                preempt_disable();
                 smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
                                 wbinvd_ipi, NULL, 1);
+                preempt_enable();
                 cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
         }
         wbinvd();
@@ -4561,9 +4564,11 @@ static void kvm_timer_init(void)
 #ifdef CONFIG_CPU_FREQ
                 struct cpufreq_policy policy;
                 memset(&policy, 0, sizeof(policy));
-                cpufreq_get_policy(&policy, get_cpu());
+                cpu = get_cpu();
+                cpufreq_get_policy(&policy, cpu);
                 if (policy.cpuinfo.max_freq)
                         max_tsc_khz = policy.cpuinfo.max_freq;
+                put_cpu();
 #endif
                 cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
                                           CPUFREQ_TRANSITION_NOTIFIER);
@@ -5514,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
         mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
         kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
+        if (sregs->cr4 & X86_CR4_OSXSAVE)
+                update_cpuid(vcpu);
         if (!is_long_mode(vcpu) && is_pae(vcpu)) {
                 load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
                 mmu_reset_needed = 1;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2cea414489f3..c600da830ce0 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
         return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+static inline u32 bit(int bitno)
+{
+        return 1 << (bitno & 31);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq);