x86/xsaves: enable xsaves/xrstors for hvm guest

This patch enables xsaves for hvm guest, includes:
1.handle xsaves vmcs init and vmexit.
2.add logic to write/read the XSS msr.

Add IA32_XSS_MSR save/rstore support.

Signed-off-by: Shuai Ruan <shuai.ruan@linux.intel.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/hvm/hvm.c

@@ -4606,6 +4606,20 @@ void hvm_cpuid(unsigned int input, unsigned int *eax, unsigned int *ebx,
                     *ebx = _eax + _ebx;
             }
         }
+        if ( count == 1 )
+        {
+            if ( cpu_has_xsaves && cpu_has_vmx_xsaves )
+            {
+                *ebx = XSTATE_AREA_MIN_SIZE;
+                if ( v->arch.xcr0 | v->arch.hvm_vcpu.msr_xss )
+                    for ( sub_leaf = 2; sub_leaf < 63; sub_leaf++ )
+                        if ( (v->arch.xcr0 | v->arch.hvm_vcpu.msr_xss) &
+                             (1ULL << sub_leaf) )
+                            *ebx += xstate_sizes[sub_leaf];
+            }
+            else
+                *ebx = *ecx = *edx = 0;
+        }
         break;
 
     case 0x80000001:
@@ -4705,6 +4719,12 @@ int hvm_msr_read_intercept(unsigned int msr, uint64_t *msr_content)
         *msr_content = v->arch.hvm_vcpu.guest_efer;
         break;
 
+    case MSR_IA32_XSS:
+        if ( !cpu_has_xsaves )
+            goto gp_fault;
+        *msr_content = v->arch.hvm_vcpu.msr_xss;
+        break;
+
     case MSR_IA32_TSC:
         *msr_content = _hvm_rdtsc_intercept();
         break;
@@ -4837,6 +4857,13 @@ int hvm_msr_write_intercept(unsigned int msr, uint64_t msr_content,
            return X86EMUL_EXCEPTION;
         break;
 
+    case MSR_IA32_XSS:
+        /* No XSS features currently supported for guests. */
+        if ( !cpu_has_xsaves || msr_content != 0 )
+            goto gp_fault;
+        v->arch.hvm_vcpu.msr_xss = msr_content;
+        break;
+
     case MSR_IA32_TSC:
         hvm_set_guest_tsc(v, msr_content);
         break;

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

@@ -241,7 +241,8 @@ static int vmx_init_vmcs_config(void)
                SECONDARY_EXEC_PAUSE_LOOP_EXITING |
                SECONDARY_EXEC_ENABLE_INVPCID |
                SECONDARY_EXEC_ENABLE_VM_FUNCTIONS |
-               SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS);
+               SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS |
+               SECONDARY_EXEC_XSAVES);
         rdmsrl(MSR_IA32_VMX_MISC, _vmx_misc_cap);
         if ( _vmx_misc_cap & VMX_MISC_VMWRITE_ALL )
             opt |= SECONDARY_EXEC_ENABLE_VMCS_SHADOWING;
@@ -1273,6 +1274,8 @@ static int construct_vmcs(struct vcpu *v)
         __vmwrite(HOST_PAT, host_pat);
         __vmwrite(GUEST_PAT, guest_pat);
     }
+    if ( cpu_has_vmx_xsaves )
+        __vmwrite(XSS_EXIT_BITMAP, 0);
 
     vmx_vmcs_exit(v);
 

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

@@ -625,7 +625,7 @@ static int vmx_load_vmcs_ctxt(struct vcpu *v, struct hvm_hw_cpu *ctxt)
 
 static unsigned int __init vmx_init_msr(void)
 {
-    return !!cpu_has_mpx;
+    return !!cpu_has_mpx + !!cpu_has_xsaves;
 }
 
 static void vmx_save_msr(struct vcpu *v, struct hvm_msr *ctxt)
@@ -640,6 +640,13 @@ static void vmx_save_msr(struct vcpu *v, struct hvm_msr *ctxt)
     }
 
     vmx_vmcs_exit(v);
+
+    if ( cpu_has_xsaves )
+    {
+        ctxt->msr[ctxt->count].val = v->arch.hvm_vcpu.msr_xss;
+        if ( ctxt->msr[ctxt->count].val )
+            ctxt->msr[ctxt->count++].index = MSR_IA32_XSS;
+    }
 }
 
 static int vmx_load_msr(struct vcpu *v, struct hvm_msr *ctxt)
@@ -659,6 +666,12 @@ static int vmx_load_msr(struct vcpu *v, struct hvm_msr *ctxt)
             else
                 err = -ENXIO;
             break;
+        case MSR_IA32_XSS:
+            if ( cpu_has_xsaves )
+                v->arch.hvm_vcpu.msr_xss = ctxt->msr[i].val;
+            else
+                err = -ENXIO;
+            break;
         default:
             continue;
         }
@@ -2819,6 +2832,18 @@ static void vmx_idtv_reinject(unsigned long idtv_info)
     }
 }
 
+static void vmx_handle_xsaves(void)
+{
+    gdprintk(XENLOG_ERR, "xsaves should not cause vmexit\n");
+    domain_crash(current->domain);
+}
+
+static void vmx_handle_xrstors(void)
+{
+    gdprintk(XENLOG_ERR, "xrstors should not cause vmexit\n");
+    domain_crash(current->domain);
+}
+
 static int vmx_handle_apic_write(void)
 {
     unsigned long exit_qualification;
@@ -3396,6 +3421,14 @@ void vmx_vmexit_handler(struct cpu_user_regs *regs)
         vmx_vcpu_flush_pml_buffer(v);
         break;
 
+    case EXIT_REASON_XSAVES:
+        vmx_handle_xsaves();
+        break;
+
+    case EXIT_REASON_XRSTORS:
+        vmx_handle_xrstors();
+        break;
+
     case EXIT_REASON_ACCESS_GDTR_OR_IDTR:
     case EXIT_REASON_ACCESS_LDTR_OR_TR:
     case EXIT_REASON_VMX_PREEMPTION_TIMER_EXPIRED:

xen/arch/x86/xstate.c

@@ -25,7 +25,7 @@ static u32 __read_mostly xsave_cntxt_size;
 u64 __read_mostly xfeature_mask;
 
 static unsigned int *__read_mostly xstate_offsets;
-static unsigned int *__read_mostly xstate_sizes;
+unsigned int *__read_mostly xstate_sizes;
 static unsigned int __read_mostly xstate_features;
 static unsigned int __read_mostly xstate_comp_offsets[sizeof(xfeature_mask)*8];
 

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

@@ -235,6 +235,7 @@ extern u32 vmx_vmentry_control;
 #define SECONDARY_EXEC_ENABLE_VMCS_SHADOWING    0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS   0x00040000
+#define SECONDARY_EXEC_XSAVES                   0x00100000
 extern u32 vmx_secondary_exec_control;
 
 #define VMX_EPT_EXEC_ONLY_SUPPORTED                         0x00000001
@@ -300,6 +301,8 @@ extern u64 vmx_ept_vpid_cap;
     (vmx_secondary_exec_control & SECONDARY_EXEC_ENABLE_VIRT_EXCEPTIONS)
 #define cpu_has_vmx_pml \
     (vmx_secondary_exec_control & SECONDARY_EXEC_ENABLE_PML)
+#define cpu_has_vmx_xsaves \
+    (vmx_secondary_exec_control & SECONDARY_EXEC_XSAVES)
 
 #define VMCS_RID_TYPE_MASK              0x80000000
 
@@ -374,6 +377,7 @@ enum vmcs_field {
     VMREAD_BITMAP                   = 0x00002026,
     VMWRITE_BITMAP                  = 0x00002028,
     VIRT_EXCEPTION_INFO             = 0x0000202a,
+    XSS_EXIT_BITMAP                 = 0x0000202c,
     GUEST_PHYSICAL_ADDRESS          = 0x00002400,
     VMCS_LINK_POINTER               = 0x00002800,
     GUEST_IA32_DEBUGCTL             = 0x00002802,

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

@@ -211,6 +211,8 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc)
 #define EXIT_REASON_INVPCID             58
 #define EXIT_REASON_VMFUNC              59
 #define EXIT_REASON_PML_FULL            62
+#define EXIT_REASON_XSAVES              63
+#define EXIT_REASON_XRSTORS             64
 
 /*
  * Interruption-information format

xen/include/asm-x86/xstate.h

@@ -45,6 +45,7 @@
 #define XSTATE_COMPACTION_ENABLED  (1ULL << 63)
 
 extern u64 xfeature_mask;
+extern unsigned int *xstate_sizes;
 
 /* extended state save area */
 struct __packed __attribute__((aligned (64))) xsave_struct