vmx: add VMX RDTSC(P) scaling support

Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>

xen/arch/x86/hvm/hvm.c

@@ -2124,6 +2124,9 @@ static int hvm_load_cpu_ctxt(struct domain *d, hvm_domain_context_t *h)
     if ( hvm_funcs.load_cpu_ctxt(v, &ctxt) < 0 )
         return -EINVAL;
 
+    if ( hvm_funcs.tsc_scaling.setup )
+        hvm_funcs.tsc_scaling.setup(v);
+
     v->arch.hvm_vcpu.msr_tsc_aux = ctxt.msr_tsc_aux;
 
     hvm_set_guest_tsc_fixed(v, ctxt.tsc, d->arch.hvm_domain.sync_tsc);
@@ -5639,6 +5642,9 @@ void hvm_vcpu_reset_state(struct vcpu *v, uint16_t cs, uint16_t ip)
     hvm_set_segment_register(v, x86_seg_gdtr, &reg);
     hvm_set_segment_register(v, x86_seg_idtr, &reg);
 
+    if ( hvm_funcs.tsc_scaling.setup )
+        hvm_funcs.tsc_scaling.setup(v);
+
     /* Sync AP's TSC with BSP's. */
     v->arch.hvm_vcpu.cache_tsc_offset =
         v->domain->vcpu[0]->arch.hvm_vcpu.cache_tsc_offset;

xen/arch/x86/hvm/vmx/vmcs.c

@@ -149,6 +149,7 @@ static void __init vmx_display_features(void)
     P(cpu_has_vmx_vmfunc, "VM Functions");
     P(cpu_has_vmx_virt_exceptions, "Virtualisation Exceptions");
     P(cpu_has_vmx_pml, "Page Modification Logging");
+    P(cpu_has_vmx_tsc_scaling, "TSC Scaling");
 #undef P
 
     if ( !printed )
@@ -243,7 +244,8 @@ static int vmx_init_vmcs_config(void)
                SECONDARY_EXEC_ENABLE_VM_FUNCTIONS |
                SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS |
                SECONDARY_EXEC_XSAVES |
-               SECONDARY_EXEC_PCOMMIT);
+               SECONDARY_EXEC_PCOMMIT |
+               SECONDARY_EXEC_TSC_SCALING);
         rdmsrl(MSR_IA32_VMX_MISC, _vmx_misc_cap);
         if ( _vmx_misc_cap & VMX_MISC_VMWRITE_ALL )
             opt |= SECONDARY_EXEC_ENABLE_VMCS_SHADOWING;
@@ -999,7 +1001,7 @@ static int construct_vmcs(struct vcpu *v)
     __vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_control);
 
     v->arch.hvm_vmx.exec_control = vmx_cpu_based_exec_control;
-    if ( d->arch.vtsc )
+    if ( d->arch.vtsc && !cpu_has_vmx_tsc_scaling )
         v->arch.hvm_vmx.exec_control |= CPU_BASED_RDTSC_EXITING;
 
     v->arch.hvm_vmx.secondary_exec_control = vmx_secondary_exec_control;
@@ -1287,6 +1289,9 @@ static int construct_vmcs(struct vcpu *v)
     if ( cpu_has_vmx_xsaves )
         __vmwrite(XSS_EXIT_BITMAP, 0);
 
+    if ( cpu_has_vmx_tsc_scaling )
+        __vmwrite(TSC_MULTIPLIER, d->arch.hvm_domain.tsc_scaling_ratio);
+
     vmx_vmcs_exit(v);
 
     /* PVH: paging mode is updated by arch_set_info_guest(). */
@@ -1869,7 +1874,8 @@ void vmcs_dump_vcpu(struct vcpu *v)
            vmr32(VM_EXIT_REASON), vmr(EXIT_QUALIFICATION));
     printk("IDTVectoring: info=%08x errcode=%08x\n",
            vmr32(IDT_VECTORING_INFO), vmr32(IDT_VECTORING_ERROR_CODE));
-    printk("TSC Offset = 0x%016lx\n", vmr(TSC_OFFSET));
+    printk("TSC Offset = 0x%016lx  TSC Multiplier = 0x%016lx\n",
+           vmr(TSC_OFFSET), vmr(TSC_MULTIPLIER));
     if ( (v->arch.hvm_vmx.exec_control & CPU_BASED_TPR_SHADOW) ||
          (vmx_pin_based_exec_control & PIN_BASED_POSTED_INTERRUPT) )
         printk("TPR Threshold = 0x%02x  PostedIntrVec = 0x%02x\n",

xen/arch/x86/hvm/vmx/vmx.c

@@ -1122,6 +1122,16 @@ static void vmx_handle_cd(struct vcpu *v, unsigned long value)
     }
 }
 
+static void vmx_setup_tsc_scaling(struct vcpu *v)
+{
+    if ( !hvm_tsc_scaling_supported || v->domain->arch.vtsc )
+        return;
+
+    vmx_vmcs_enter(v);
+    __vmwrite(TSC_MULTIPLIER, hvm_tsc_scaling_ratio(v->domain));
+    vmx_vmcs_exit(v);
+}
+
 static void vmx_set_tsc_offset(struct vcpu *v, u64 offset, u64 at_tsc)
 {
     vmx_vmcs_enter(v);
@@ -2014,6 +2024,10 @@ static struct hvm_function_table __initdata vmx_function_table = {
     .altp2m_vcpu_update_vmfunc_ve = vmx_vcpu_update_vmfunc_ve,
     .altp2m_vcpu_emulate_ve = vmx_vcpu_emulate_ve,
     .altp2m_vcpu_emulate_vmfunc = vmx_vcpu_emulate_vmfunc,
+    .tsc_scaling = {
+        .max_ratio = VMX_TSC_MULTIPLIER_MAX,
+        .setup     = vmx_setup_tsc_scaling,
+    },
 };
 
 /* Handle VT-d posted-interrupt when VCPU is running. */
@@ -2118,6 +2132,9 @@ const struct hvm_function_table * __init start_vmx(void)
          && cpu_has_vmx_secondary_exec_control )
         vmx_function_table.pvh_supported = 1;
 
+    if ( cpu_has_vmx_tsc_scaling )
+        vmx_function_table.tsc_scaling.ratio_frac_bits = 48;
+
     setup_vmcs_dump();
 
     return &vmx_function_table;

xen/include/asm-x86/hvm/hvm.h

@@ -231,6 +231,9 @@ struct hvm_function_table {
         uint8_t  ratio_frac_bits;
         /* maximum-allowed TSC scaling ratio */
         uint64_t max_ratio;
+
+        /* Architecture function to setup TSC scaling ratio */
+        void (*setup)(struct vcpu *v);
     } tsc_scaling;
 };
 

xen/include/asm-x86/hvm/vmx/vmcs.h

@@ -237,6 +237,7 @@ extern u32 vmx_vmentry_control;
 #define SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS   0x00040000
 #define SECONDARY_EXEC_XSAVES                   0x00100000
 #define SECONDARY_EXEC_PCOMMIT                  0x00200000
+#define SECONDARY_EXEC_TSC_SCALING              0x02000000
 extern u32 vmx_secondary_exec_control;
 
 #define VMX_EPT_EXEC_ONLY_SUPPORTED                         0x00000001
@@ -259,6 +260,8 @@ extern u64 vmx_ept_vpid_cap;
 #define VMX_MISC_CR3_TARGET                     0x01ff0000
 #define VMX_MISC_VMWRITE_ALL                    0x20000000
 
+#define VMX_TSC_MULTIPLIER_MAX                  0xffffffffffffffffULL
+
 #define cpu_has_wbinvd_exiting \
     (vmx_secondary_exec_control & SECONDARY_EXEC_WBINVD_EXITING)
 #define cpu_has_vmx_virtualize_apic_accesses \
@@ -306,6 +309,9 @@ extern u64 vmx_ept_vpid_cap;
     (vmx_secondary_exec_control & SECONDARY_EXEC_XSAVES)
 #define cpu_has_vmx_pcommit \
     (vmx_secondary_exec_control & SECONDARY_EXEC_PCOMMIT)
+#define cpu_has_vmx_tsc_scaling \
+    (vmx_secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
+
 #define VMCS_RID_TYPE_MASK              0x80000000
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
@@ -380,6 +386,7 @@ enum vmcs_field {
     VMWRITE_BITMAP                  = 0x00002028,
     VIRT_EXCEPTION_INFO             = 0x0000202a,
     XSS_EXIT_BITMAP                 = 0x0000202c,
+    TSC_MULTIPLIER                  = 0x00002032,
     GUEST_PHYSICAL_ADDRESS          = 0x00002400,
     VMCS_LINK_POINTER               = 0x00002800,
     GUEST_IA32_DEBUGCTL             = 0x00002802,