KVM: Enable MTRR for EPT

The effective memory type of EPT is the mixture of MSR_IA32_CR_PAT and memory
type field of EPT entry.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

5 files changed, 27 insertions, 5 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8082e87f628d..93040b5eed96 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -483,6 +483,7 @@ struct kvm_x86_ops {
 
         int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
         int (*get_tdp_level)(void);
+        int (*get_mt_mask_shift)(void);
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -496,7 +497,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
 void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-                u64 dirty_mask, u64 nx_mask, u64 x_mask);
+                u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ac2304fd173e..09d05f57bf66 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -168,6 +168,7 @@ static u64 __read_mostly shadow_x_mask;	/* mutual exclusive with nx_mask */
 static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
+static u64 __read_mostly shadow_mt_mask;
 
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 {
@@ -183,13 +184,14 @@ void kvm_mmu_set_base_ptes(u64 base_pte)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-                u64 dirty_mask, u64 nx_mask, u64 x_mask)
+                u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask)
 {
         shadow_user_mask = user_mask;
         shadow_accessed_mask = accessed_mask;
         shadow_dirty_mask = dirty_mask;
         shadow_nx_mask = nx_mask;
         shadow_x_mask = x_mask;
+        shadow_mt_mask = mt_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -1546,6 +1548,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 {
         u64 spte;
         int ret = 0;
+        u64 mt_mask = shadow_mt_mask;
+
         /*
          * We don't set the accessed bit, since we sometimes want to see
          * whether the guest actually used the pte (in order to detect
@@ -1564,6 +1568,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                 spte |= shadow_user_mask;
         if (largepage)
                 spte |= PT_PAGE_SIZE_MASK;
+        if (mt_mask) {
+                mt_mask = get_memory_type(vcpu, gfn) <<
+                          kvm_x86_ops->get_mt_mask_shift();
+                spte |= mt_mask;
+        }
 
         spte |= (u64)pfn << PAGE_SHIFT;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9c4ce657d963..05efc4ef75a6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1912,6 +1912,11 @@ static int get_npt_level(void)
 #endif
 }
 
+static int svm_get_mt_mask_shift(void)
+{
+        return 0;
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
         .cpu_has_kvm_support = has_svm,
         .disabled_by_bios = is_disabled,
@@ -1967,6 +1972,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 
         .set_tss_addr = svm_set_tss_addr,
         .get_tdp_level = get_npt_level,
+        .get_mt_mask_shift = svm_get_mt_mask_shift,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b4c95a501cca..dae134fa09e7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3574,6 +3574,11 @@ static int get_ept_level(void)
         return VMX_EPT_DEFAULT_GAW + 1;
 }
 
+static int vmx_get_mt_mask_shift(void)
+{
+        return VMX_EPT_MT_EPTE_SHIFT;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
         .cpu_has_kvm_support = cpu_has_kvm_support,
         .disabled_by_bios = vmx_disabled_by_bios,
@@ -3629,6 +3634,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
         .set_tss_addr = vmx_set_tss_addr,
         .get_tdp_level = get_ept_level,
+        .get_mt_mask_shift = vmx_get_mt_mask_shift,
 };
 
 static int __init vmx_init(void)
@@ -3685,10 +3691,10 @@ static int __init vmx_init(void)
                 bypass_guest_pf = 0;
                 kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
                         VMX_EPT_WRITABLE_MASK |
-                        VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT |
                         VMX_EPT_IGMT_BIT);
                 kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
-                                VMX_EPT_EXECUTABLE_MASK);
+                                VMX_EPT_EXECUTABLE_MASK,
+                                VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
                 kvm_enable_tdp();
         } else
                 kvm_disable_tdp();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0edf75339f3a..f175b796c2a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2615,7 +2615,7 @@ int kvm_arch_init(void *opaque)
         kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
         kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
         kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-                        PT_DIRTY_MASK, PT64_NX_MASK, 0);
+                        PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
         return 0;
 
 out: