# HG changeset patch
# User Wei Huang <wei.huang2@xxxxxxx>
# Date 1304697215 18000
# Node ID e58b1d06aabe5c0aa26f2bd29b607a1c337d6c80
# Parent  ab7d2191421fbf95313e1109de3ced5e2a094424
FPU: create lazy and non-lazy FPU restore functions

Currently Xen relies on #NM (via CR0.TS) to trigger FPU context restore. But not all FPU state is tracked by TS bit. This function creates two FPU restore functions: vcpu_restore_fpu_lazy() and vcpu_restore_fpu_eager(). vcpu_restore_fpu_lazy() is still used when #NM is triggered. vcpu_restore_fpu_eager(), as a comparision, is called for vcpu which is being scheduled in on every context switch. To minimize restore overhead, it creates a flag, nonlazy_xstate_used, to control non-lazy restore.

Signed-off-by: Wei Huang <wei.huang2@xxxxxxx>

diff -r ab7d2191421f -r e58b1d06aabe xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c	Fri May 06 10:40:22 2011 -0500
+++ b/xen/arch/x86/domain.c	Fri May 06 10:53:35 2011 -0500
@@ -1578,6 +1578,7 @@
         memcpy(stack_regs, &n->arch.user_regs, CTXT_SWITCH_STACK_BYTES);
         if ( xsave_enabled(n) && n->arch.xcr0 != get_xcr0() )
             set_xcr0(n->arch.xcr0);
+        vcpu_restore_fpu_eager(n);
         n->arch.ctxt_switch_to(n);
     }
 
diff -r ab7d2191421f -r e58b1d06aabe xen/arch/x86/hvm/svm/svm.c
--- a/xen/arch/x86/hvm/svm/svm.c	Fri May 06 10:40:22 2011 -0500
+++ b/xen/arch/x86/hvm/svm/svm.c	Fri May 06 10:53:35 2011 -0500
@@ -348,7 +348,7 @@
 {
     struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb;
 
-    vcpu_restore_fpu(v);
+    vcpu_restore_fpu_lazy(v);
     vmcb_set_exception_intercepts(
         vmcb, vmcb_get_exception_intercepts(vmcb) & ~(1U << TRAP_no_device));
 }
diff -r ab7d2191421f -r e58b1d06aabe xen/arch/x86/hvm/vmx/vmx.c
--- a/xen/arch/x86/hvm/vmx/vmx.c	Fri May 06 10:40:22 2011 -0500
+++ b/xen/arch/x86/hvm/vmx/vmx.c	Fri May 06 10:53:35 2011 -0500
@@ -612,7 +612,7 @@
 
 static void vmx_fpu_enter(struct vcpu *v)
 {
-    vcpu_restore_fpu(v);
+    vcpu_restore_fpu_lazy(v);
     v->arch.hvm_vmx.exception_bitmap &= ~(1u << TRAP_no_device);
     vmx_update_exception_bitmap(v);
     v->arch.hvm_vmx.host_cr0 &= ~X86_CR0_TS;
diff -r ab7d2191421f -r e58b1d06aabe xen/arch/x86/i387.c
--- a/xen/arch/x86/i387.c	Fri May 06 10:40:22 2011 -0500
+++ b/xen/arch/x86/i387.c	Fri May 06 10:53:35 2011 -0500
@@ -98,13 +98,13 @@
 /*      FPU Save Functions     */
 /*******************************/
 /* Save x87 extended state */
-static inline void fpu_xsave(struct vcpu *v, uint64_t mask)
+static inline void fpu_xsave(struct vcpu *v)
 {
     /* XCR0 normally represents what guest OS set. In case of Xen itself,
      * we set all accumulated feature mask before doing save/restore.
      */
     set_xcr0(v->arch.xcr0_accum);
-    xsave(v, mask);
+    xsave(v, v->arch.nonlazy_xstate_used ? XSTATE_ALL : XSTATE_LAZY);
     set_xcr0(v->arch.xcr0);    
 }
 
@@ -160,10 +160,25 @@
 /*******************************/
 /*       VCPU FPU Functions    */
 /*******************************/
+/* Restore FPU state whenever VCPU is schduled in. */
+void vcpu_restore_fpu_eager(struct vcpu *v)
+{
+    ASSERT(!is_idle_vcpu(v));
+    
+    /* save the nonlazy extended state which is not tracked by CR0.TS bit */
+    if ( v->arch.nonlazy_xstate_used )
+    {
+        /* Avoid recursion */
+        clts();        
+        fpu_xrstor(v, XSTATE_NONLAZY);
+        stts();
+    }
+}
+
 /* 
  * Restore FPU state when #NM is triggered.
  */
-void vcpu_restore_fpu(struct vcpu *v)
+void vcpu_restore_fpu_lazy(struct vcpu *v)
 {
     ASSERT(!is_idle_vcpu(v));
 
@@ -174,7 +189,7 @@
         return;
 
     if ( xsave_enabled(v) )
-        fpu_xrstor(v, XSTATE_ALL);
+        fpu_xrstor(v, XSTATE_LAZY);
     else if ( v->fpu_initialised )
     {
         if ( cpu_has_fxsr )
@@ -204,7 +219,7 @@
     clts();
 
     if ( xsave_enabled(v) )
-        fpu_xsave(v, XSTATE_ALL);
+        fpu_xsave(v);
     else if ( cpu_has_fxsr )
         fpu_fxsave(v);
     else
diff -r ab7d2191421f -r e58b1d06aabe xen/arch/x86/traps.c
--- a/xen/arch/x86/traps.c	Fri May 06 10:40:22 2011 -0500
+++ b/xen/arch/x86/traps.c	Fri May 06 10:53:35 2011 -0500
@@ -3198,7 +3198,7 @@
 
     BUG_ON(!guest_mode(regs));
 
-    vcpu_restore_fpu(curr);
+    vcpu_restore_fpu_lazy(curr);
 
     if ( curr->arch.pv_vcpu.ctrlreg[0] & X86_CR0_TS )
     {
diff -r ab7d2191421f -r e58b1d06aabe xen/include/asm-x86/domain.h
--- a/xen/include/asm-x86/domain.h	Fri May 06 10:40:22 2011 -0500
+++ b/xen/include/asm-x86/domain.h	Fri May 06 10:53:35 2011 -0500
@@ -492,7 +492,10 @@
      * it explicitly enables it via xcr0.
      */
     uint64_t xcr0_accum;
-
+    /* This variable determines whether nonlazy extended state has been used,
+     * and thus should be saved/restored. */
+    bool_t nonlazy_xstate_used;
+    
     struct paging_vcpu paging;
 
 #ifdef CONFIG_X86_32
diff -r ab7d2191421f -r e58b1d06aabe xen/include/asm-x86/i387.h
--- a/xen/include/asm-x86/i387.h	Fri May 06 10:40:22 2011 -0500
+++ b/xen/include/asm-x86/i387.h	Fri May 06 10:53:35 2011 -0500
@@ -14,7 +14,8 @@
 #include <xen/types.h>
 #include <xen/percpu.h>
 
-void vcpu_restore_fpu(struct vcpu *v);
+void vcpu_restore_fpu_eager(struct vcpu *v);
+void vcpu_restore_fpu_lazy(struct vcpu *v);
 void vcpu_save_fpu(struct vcpu *v);
 
 int vcpu_init_fpu(struct vcpu *v);