KVM: VMX: Prepare an identity page table for EPT in real mode

[aliguory: plug leak]

Signed-off-by: Sheng Yang <sheng.yang@intel.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

4 files changed, 84 insertions, 3 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 98e4f2b036de..de5f6150f2f7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -87,7 +87,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
         return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
-static int init_rmode_tss(struct kvm *kvm);
+static int init_rmode(struct kvm *kvm);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -1304,7 +1304,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
         fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs);
 
         kvm_mmu_reset_context(vcpu);
-        init_rmode_tss(vcpu->kvm);
+        init_rmode(vcpu->kvm);
 }
 
 #ifdef CONFIG_X86_64
@@ -1578,6 +1578,41 @@ out:
         return ret;
 }
 
+static int init_rmode_identity_map(struct kvm *kvm)
+{
+        int i, r, ret;
+        pfn_t identity_map_pfn;
+        u32 tmp;
+
+        if (!vm_need_ept())
+                return 1;
+        if (unlikely(!kvm->arch.ept_identity_pagetable)) {
+                printk(KERN_ERR "EPT: identity-mapping pagetable "
+                        "haven't been allocated!\n");
+                return 0;
+        }
+        if (likely(kvm->arch.ept_identity_pagetable_done))
+                return 1;
+        ret = 0;
+        identity_map_pfn = VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT;
+        r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
+        if (r < 0)
+                goto out;
+        /* Set up identity-mapping pagetable for EPT in real mode */
+        for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
+                tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
+                        _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
+                r = kvm_write_guest_page(kvm, identity_map_pfn,
+                                &tmp, i * sizeof(tmp), sizeof(tmp));
+                if (r < 0)
+                        goto out;
+        }
+        kvm->arch.ept_identity_pagetable_done = true;
+        ret = 1;
+out:
+        return ret;
+}
+
 static void seg_setup(int seg)
 {
         struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1612,6 +1647,31 @@ out:
         return r;
 }
 
+static int alloc_identity_pagetable(struct kvm *kvm)
+{
+        struct kvm_userspace_memory_region kvm_userspace_mem;
+        int r = 0;
+
+        down_write(&kvm->slots_lock);
+        if (kvm->arch.ept_identity_pagetable)
+                goto out;
+        kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
+        kvm_userspace_mem.flags = 0;
+        kvm_userspace_mem.guest_phys_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
+        kvm_userspace_mem.memory_size = PAGE_SIZE;
+        r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
+        if (r)
+                goto out;
+
+        down_read(&current->mm->mmap_sem);
+        kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
+                        VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT);
+        up_read(&current->mm->mmap_sem);
+out:
+        up_write(&kvm->slots_lock);
+        return r;
+}
+
 static void allocate_vpid(struct vcpu_vmx *vmx)
 {
         int vpid;
@@ -1775,6 +1835,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
         return 0;
 }
 
+static int init_rmode(struct kvm *kvm)
+{
+        if (!init_rmode_tss(kvm))
+                return 0;
+        if (!init_rmode_identity_map(kvm))
+                return 0;
+        return 1;
+}
+
 static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 {
         struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -1782,7 +1851,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
         int ret;
 
         down_read(&vcpu->kvm->slots_lock);
-        if (!init_rmode_tss(vmx->vcpu.kvm)) {
+        if (!init_rmode(vmx->vcpu.kvm)) {
                 ret = -ENOMEM;
                 goto out;
         }
@@ -2759,6 +2828,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
                 if (alloc_apic_access_page(kvm) != 0)
                         goto free_vmcs;
 
+        if (vm_need_ept())
+                if (alloc_identity_pagetable(kvm) != 0)
+                        goto free_vmcs;
+
         return &vmx->vcpu;
 
 free_vmcs:
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 093b085daf6a..f97eccc754e8 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -340,6 +340,7 @@ enum vmcs_field {
 #define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED  0x4
 
 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT        9
+#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT      10
 
 #define VMX_NR_VPIDS                            (1 << 16)
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT          1
@@ -353,4 +354,6 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_GLOBAL_BIT               (1ull << 26)
 #define VMX_EPT_DEFAULT_GAW                     3
 
+#define VMX_EPT_IDENTITY_PAGETABLE_ADDR         0xfffbc000ul
+
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0735efbfa712..1842a86f7c33 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3909,6 +3909,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
         kvm_free_physmem(kvm);
         if (kvm->arch.apic_access_page)
                 put_page(kvm->arch.apic_access_page);
+        if (kvm->arch.ept_identity_pagetable)
+                put_page(kvm->arch.ept_identity_pagetable);
         kfree(kvm);
 }
 
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index d1dedda958ff..e24afaa64a4d 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -314,6 +314,9 @@ struct kvm_arch{
         struct page *apic_access_page;
 
         gpa_t wall_clock;
+
+        struct page *ept_identity_pagetable;
+        bool ept_identity_pagetable_done;
 };
 
 struct kvm_vm_stat {