KVM: x86: do not execute halted vcpus

[safe/jmp/linux-2.6] / arch / x86 / kvm / x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5b3c882..bf98d40 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,6 +92,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
        { "fpu_reload", VCPU_STAT(fpu_reload) },
        { "insn_emulation", VCPU_STAT(insn_emulation) },
        { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
+       { "irq_injections", VCPU_STAT(irq_injections) },
        { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
        { "mmu_pte_write", VM_STAT(mmu_pte_write) },
        { "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -104,7 +105,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
        { NULL }
 };
 
-struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
                                                      int assigned_dev_id)
 {
        struct list_head *ptr;
@@ -991,6 +992,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
        case MSR_IA32_MC0_MISC+8:
        case MSR_IA32_MC0_MISC+12:
        case MSR_IA32_MC0_MISC+16:
+       case MSR_IA32_MC0_MISC+20:
        case MSR_IA32_UCODE_REV:
        case MSR_IA32_EBL_CR_POWERON:
        case MSR_IA32_DEBUGCTLMSR:
@@ -2796,11 +2798,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
        KVMTRACE_0D(HLT, vcpu, handler);
        if (irqchip_in_kernel(vcpu->kvm)) {
                vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
-               up_read(&vcpu->kvm->slots_lock);
-               kvm_vcpu_block(vcpu);
-               down_read(&vcpu->kvm->slots_lock);
-               if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
-                       return -EINTR;
                return 1;
        } else {
                vcpu->run->exit_reason = KVM_EXIT_HLT;
@@ -3095,24 +3092,10 @@ static void vapic_exit(struct kvm_vcpu *vcpu)
        up_read(&vcpu->kvm->slots_lock);
 }
 
-static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
        int r;
 
-       if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
-               pr_debug("vcpu %d received sipi with vector # %x\n",
-                      vcpu->vcpu_id, vcpu->arch.sipi_vector);
-               kvm_lapic_reset(vcpu);
-               r = kvm_x86_ops->vcpu_reset(vcpu);
-               if (r)
-                       return r;
-               vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-       }
-
-       down_read(&vcpu->kvm->slots_lock);
-       vapic_enter(vcpu);
-
-again:
        if (vcpu->requests)
                if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
                        kvm_mmu_unload(vcpu);
@@ -3149,22 +3132,13 @@ again:
 
        local_irq_disable();
 
-       if (vcpu->requests || need_resched()) {
+       if (vcpu->requests || need_resched() || signal_pending(current)) {
                local_irq_enable();
                preempt_enable();
                r = 1;
                goto out;
        }
 
-       if (signal_pending(current)) {
-               local_irq_enable();
-               preempt_enable();
-               r = -EINTR;
-               kvm_run->exit_reason = KVM_EXIT_INTR;
-               ++vcpu->stat.signal_exits;
-               goto out;
-       }
-
        if (vcpu->guest_debug.enabled)
                kvm_x86_ops->guest_debug_pre(vcpu);
 
@@ -3225,26 +3199,63 @@ again:
        kvm_lapic_sync_from_vapic(vcpu);
 
        r = kvm_x86_ops->handle_exit(kvm_run, vcpu);
+out:
+       return r;
+}
 
-       if (r > 0) {
-               if (dm_request_for_irq_injection(vcpu, kvm_run)) {
-                       r = -EINTR;
-                       kvm_run->exit_reason = KVM_EXIT_INTR;
-                       ++vcpu->stat.request_irq_exits;
-                       goto out;
-               }
-               if (!need_resched())
-                       goto again;
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+       int r;
+
+       if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
+               printk("vcpu %d received sipi with vector # %x\n",
+                      vcpu->vcpu_id, vcpu->arch.sipi_vector);
+               kvm_lapic_reset(vcpu);
+               r = kvm_x86_ops->vcpu_reset(vcpu);
+               if (r)
+                       return r;
+               vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
        }
 
-out:
-       up_read(&vcpu->kvm->slots_lock);
-       if (r > 0) {
-               kvm_resched(vcpu);
-               down_read(&vcpu->kvm->slots_lock);
-               goto again;
+       down_read(&vcpu->kvm->slots_lock);
+       vapic_enter(vcpu);
+
+       r = 1;
+       while (r > 0) {
+               if (kvm_arch_vcpu_runnable(vcpu))
+                       r = vcpu_enter_guest(vcpu, kvm_run);
+               else {
+                       up_read(&vcpu->kvm->slots_lock);
+                       kvm_vcpu_block(vcpu);
+                       down_read(&vcpu->kvm->slots_lock);
+                       if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
+                               if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
+                                       vcpu->arch.mp_state =
+                                                       KVM_MP_STATE_RUNNABLE;
+                       if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
+                               r = -EINTR;
+               }
+
+               if (r > 0) {
+                       if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+                               r = -EINTR;
+                               kvm_run->exit_reason = KVM_EXIT_INTR;
+                               ++vcpu->stat.request_irq_exits;
+                       }
+                       if (signal_pending(current)) {
+                               r = -EINTR;
+                               kvm_run->exit_reason = KVM_EXIT_INTR;
+                               ++vcpu->stat.signal_exits;
+                       }
+                       if (need_resched()) {
+                               up_read(&vcpu->kvm->slots_lock);
+                               kvm_resched(vcpu);
+                               down_read(&vcpu->kvm->slots_lock);
+                       }
+               }
        }
 
+       up_read(&vcpu->kvm->slots_lock);
        post_kvm_run_save(vcpu, kvm_run);
 
        vapic_exit(vcpu);
@@ -3264,6 +3275,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
        if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
                kvm_vcpu_block(vcpu);
+               clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
                r = -EAGAIN;
                goto out;
        }
@@ -3588,11 +3600,33 @@ static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu,
        return 0;
 }
 
+int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
+{
+       struct kvm_segment segvar = {
+               .base = selector << 4,
+               .limit = 0xffff,
+               .selector = selector,
+               .type = 3,
+               .present = 1,
+               .dpl = 3,
+               .db = 0,
+               .s = 1,
+               .l = 0,
+               .g = 0,
+               .avl = 0,
+               .unusable = 0,
+       };
+       kvm_x86_ops->set_segment(vcpu, &segvar, seg);
+       return 0;
+}
+
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
                                int type_bits, int seg)
 {
        struct kvm_segment kvm_seg;
 
+       if (!(vcpu->arch.cr0 & X86_CR0_PE))
+               return kvm_load_realmode_segment(vcpu, selector, seg);
        if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
                return 1;
        kvm_seg.type |= type_bits;
@@ -4274,7 +4308,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
                        userspace_addr = do_mmap(NULL, 0,
                                                 npages * PAGE_SIZE,
                                                 PROT_READ | PROT_WRITE,
-                                                MAP_SHARED | MAP_ANONYMOUS,
+                                                MAP_PRIVATE | MAP_ANONYMOUS,
                                                 0);
                        up_write(&current->mm->mmap_sem);