KVM: VMX: Add PAT support for EPT

GUEST_PAT support is a new feature introduced by Intel Core i7 architecture.
With this, cpu would save/load guest and host PAT automatically, for EPT memory
type in guest depends on MSR_IA32_CR_PAT.

Also add save/restore for MSR_IA32_CR_PAT.

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

3 files changed, 34 insertions, 4 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2180109d794c..b4c95a501cca 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -962,6 +962,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
                 pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
 
                 break;
+        case MSR_IA32_CR_PAT:
+                if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+                        vmcs_write64(GUEST_IA32_PAT, data);
+                        vcpu->arch.pat = data;
+                        break;
+                }
+                /* Otherwise falls through to kvm_set_msr_common */
         default:
                 vmx_load_host_state(vmx);
                 msr = find_msr_entry(vmx, msr_index);
@@ -1181,12 +1188,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 #ifdef CONFIG_X86_64
         min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
-        opt = 0;
+        opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT;
         if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
                                 &_vmexit_control) < 0)
                 return -EIO;
 
-        min = opt = 0;
+        min = 0;
+        opt = VM_ENTRY_LOAD_IA32_PAT;
         if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
                                 &_vmentry_control) < 0)
                 return -EIO;
@@ -2092,8 +2100,9 @@ static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
  */
 static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 {
-        u32 host_sysenter_cs;
+        u32 host_sysenter_cs, msr_low, msr_high;
         u32 junk;
+        u64 host_pat;
         unsigned long a;
         struct descriptor_table dt;
         int i;
@@ -2181,6 +2190,20 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
         rdmsrl(MSR_IA32_SYSENTER_EIP, a);
         vmcs_writel(HOST_IA32_SYSENTER_EIP, a);   /* 22.2.3 */
 
+        if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
+                rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+                host_pat = msr_low | ((u64) msr_high << 32);
+                vmcs_write64(HOST_IA32_PAT, host_pat);
+        }
+        if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+                rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+                host_pat = msr_low | ((u64) msr_high << 32);
+                /* Write the default value follow host pat */
+                vmcs_write64(GUEST_IA32_PAT, host_pat);
+                /* Keep arch.pat sync with GUEST_IA32_PAT */
+                vmx->vcpu.arch.pat = host_pat;
+        }
+
         for (i = 0; i < NR_VMX_MSR; ++i) {
                 u32 index = vmx_msr_index[i];
                 u32 data_low, data_high;
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index ec5edc339da6..18598afe52eb 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -63,10 +63,13 @@
 
 #define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
 #define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
+#define VM_EXIT_SAVE_IA32_PAT                   0x00040000
+#define VM_EXIT_LOAD_IA32_PAT                   0x00080000
 
 #define VM_ENTRY_IA32E_MODE                     0x00000200
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
+#define VM_ENTRY_LOAD_IA32_PAT                  0x00004000
 
 /* VMCS Encodings */
 enum vmcs_field {
@@ -112,6 +115,8 @@ enum vmcs_field {
         VMCS_LINK_POINTER_HIGH          = 0x00002801,
         GUEST_IA32_DEBUGCTL             = 0x00002802,
         GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
+        GUEST_IA32_PAT                  = 0x00002804,
+        GUEST_IA32_PAT_HIGH             = 0x00002805,
         GUEST_PDPTR0                    = 0x0000280a,
         GUEST_PDPTR0_HIGH               = 0x0000280b,
         GUEST_PDPTR1                    = 0x0000280c,
@@ -120,6 +125,8 @@ enum vmcs_field {
         GUEST_PDPTR2_HIGH               = 0x0000280f,
         GUEST_PDPTR3                    = 0x00002810,
         GUEST_PDPTR3_HIGH               = 0x00002811,
+        HOST_IA32_PAT                   = 0x00002c00,
+        HOST_IA32_PAT_HIGH              = 0x00002c01,
         PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
         CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
         EXCEPTION_BITMAP                = 0x00004004,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f5b2334c6bda..0edf75339f3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -452,7 +452,7 @@ static u32 msrs_to_save[] = {
         MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
         MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-        MSR_IA32_PERF_STATUS,
+        MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT
 };
 
 static unsigned num_msrs_to_save;