Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi...

[deliverable/linux.git] / arch / x86 / kvm / vmx.c

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2e2685424fdc53f14537c089d68cd675ce6aaa2b..df07a0a4611ffa81b059229aaa08d04a2981bc56 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
        unsigned int dest;
 
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-               !irq_remapping_cap(IRQ_POSTING_CAP))
+               !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+               !kvm_vcpu_apicv_active(vcpu))
                return;
 
        do {
@@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
        struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-               !irq_remapping_cap(IRQ_POSTING_CAP))
+               !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+               !kvm_vcpu_apicv_active(vcpu))
                return;
 
        /* Set SN when the vCPU is preempted */
@@ -4973,6 +4975,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
        if (vmx_xsaves_supported())
                vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
+       if (enable_pml) {
+               ASSERT(vmx->pml_pg);
+               vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+               vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+       }
+
        return 0;
 }
 
@@ -6665,7 +6673,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
        /* Checks for #GP/#SS exceptions. */
        exn = false;
-       if (is_protmode(vcpu)) {
+       if (is_long_mode(vcpu)) {
+               /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+                * non-canonical form. This is the only check on the memory
+                * destination for long mode!
+                */
+               exn = is_noncanonical_address(*ret);
+       } else if (is_protmode(vcpu)) {
                /* Protected mode: apply checks for segment validity in the
                 * following order:
                 * - segment type check (#GP(0) may be thrown)
@@ -6682,17 +6696,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
                         * execute-only code segment
                         */
                        exn = ((s.type & 0xa) == 8);
-       }
-       if (exn) {
-               kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-               return 1;
-       }
-       if (is_long_mode(vcpu)) {
-               /* Long mode: #GP(0)/#SS(0) if the memory address is in a
-                * non-canonical form. This is an only check for long mode.
-                */
-               exn = is_noncanonical_address(*ret);
-       } else if (is_protmode(vcpu)) {
+               if (exn) {
+                       kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+                       return 1;
+               }
                /* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
                 */
                exn = (s.unusable != 0);
@@ -7922,22 +7929,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
        *info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
-       struct page *pml_pg;
-
-       pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-       if (!pml_pg)
-               return -ENOMEM;
-
-       vmx->pml_pg = pml_pg;
-
-       vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-       vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
-       return 0;
-}
-
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
        if (vmx->pml_pg) {
@@ -8209,6 +8200,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
        if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
                        (exit_reason != EXIT_REASON_EXCEPTION_NMI &&
                        exit_reason != EXIT_REASON_EPT_VIOLATION &&
+                       exit_reason != EXIT_REASON_PML_FULL &&
                        exit_reason != EXIT_REASON_TASK_SWITCH)) {
                vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
                vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8839,6 +8831,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
        put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
        struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8847,8 +8855,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
                vmx_destroy_pml_buffer(vmx);
        free_vpid(vmx->vpid);
        leave_guest_mode(vcpu);
-       vmx_load_vmcs01(vcpu);
-       free_nested(vmx);
+       vmx_free_vcpu_nested(vcpu);
        free_loaded_vmcs(vmx->loaded_vmcs);
        kfree(vmx->guest_msrs);
        kvm_vcpu_uninit(vcpu);
@@ -8870,14 +8877,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
        if (err)
                goto free_vcpu;
 
+       err = -ENOMEM;
+
+       /*
+        * If PML is turned on, failure on enabling PML just results in failure
+        * of creating the vcpu, therefore we can simplify PML logic (by
+        * avoiding dealing with cases, such as enabling PML partially on vcpus
+        * for the guest, etc.
+        */
+       if (enable_pml) {
+               vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+               if (!vmx->pml_pg)
+                       goto uninit_vcpu;
+       }
+
        vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
        BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
                     > PAGE_SIZE);
 
-       err = -ENOMEM;
-       if (!vmx->guest_msrs) {
-               goto uninit_vcpu;
-       }
+       if (!vmx->guest_msrs)
+               goto free_pml;
 
        vmx->loaded_vmcs = &vmx->vmcs01;
        vmx->loaded_vmcs->vmcs = alloc_vmcs();
@@ -8921,18 +8940,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
        vmx->nested.current_vmptr = -1ull;
        vmx->nested.current_vmcs12 = NULL;
 
-       /*
-        * If PML is turned on, failure on enabling PML just results in failure
-        * of creating the vcpu, therefore we can simplify PML logic (by
-        * avoiding dealing with cases, such as enabling PML partially on vcpus
-        * for the guest, etc.
-        */
-       if (enable_pml) {
-               err = vmx_create_pml_buffer(vmx);
-               if (err)
-                       goto free_vmcs;
-       }
-
        return &vmx->vcpu;
 
 free_vmcs:
@@ -8940,6 +8947,8 @@ free_vmcs:
        free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
        kfree(vmx->guest_msrs);
+free_pml:
+       vmx_destroy_pml_buffer(vmx);
 uninit_vcpu:
        kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:
@@ -10690,7 +10699,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
        struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-               !irq_remapping_cap(IRQ_POSTING_CAP))
+               !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+               !kvm_vcpu_apicv_active(vcpu))
                return 0;
 
        vcpu->pre_pcpu = vcpu->cpu;
@@ -10756,7 +10766,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
        unsigned long flags;
 
        if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-               !irq_remapping_cap(IRQ_POSTING_CAP))
+               !irq_remapping_cap(IRQ_POSTING_CAP)  ||
+               !kvm_vcpu_apicv_active(vcpu))
                return;
 
        do {
@@ -10809,7 +10820,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
        int idx, ret = -EINVAL;
 
        if (!kvm_arch_has_assigned_device(kvm) ||
-               !irq_remapping_cap(IRQ_POSTING_CAP))
+               !irq_remapping_cap(IRQ_POSTING_CAP) ||
+               !kvm_vcpu_apicv_active(kvm->vcpus[0]))
                return 0;
 
        idx = srcu_read_lock(&kvm->irq_srcu);