# HG changeset patch
# User Wei Huang <wei.huang2@xxxxxxx>
# Date 1304937563 -3600
# Node ID 103f89fef2942fc44887a777064532aaa9a1f90d
# Parent 631bdf00a81f2099233ca3146c8c7383511aba0f
x86/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 631bdf00a81f -r 103f89fef294 xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c Mon May 09 11:38:55 2011 +0100
+++ b/xen/arch/x86/domain.c Mon May 09 11:39:23 2011 +0100
@@ -1566,6 +1566,7 @@
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 631bdf00a81f -r 103f89fef294 xen/arch/x86/hvm/svm/svm.c
--- a/xen/arch/x86/hvm/svm/svm.c Mon May 09 11:38:55 2011 +0100
+++ b/xen/arch/x86/hvm/svm/svm.c Mon May 09 11:39:23 2011 +0100
@@ -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 631bdf00a81f -r 103f89fef294 xen/arch/x86/hvm/vmx/vmx.c
--- a/xen/arch/x86/hvm/vmx/vmx.c Mon May 09 11:38:55 2011 +0100
+++ b/xen/arch/x86/hvm/vmx/vmx.c Mon May 09 11:39:23 2011 +0100
@@ -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 631bdf00a81f -r 103f89fef294 xen/arch/x86/i387.c
--- a/xen/arch/x86/i387.c Mon May 09 11:38:55 2011 +0100
+++ b/xen/arch/x86/i387.c Mon May 09 11:39:23 2011 +0100
@@ -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 631bdf00a81f -r 103f89fef294 xen/arch/x86/traps.c
--- a/xen/arch/x86/traps.c Mon May 09 11:38:55 2011 +0100
+++ b/xen/arch/x86/traps.c Mon May 09 11:39:23 2011 +0100
@@ -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 631bdf00a81f -r 103f89fef294 xen/include/asm-x86/domain.h
--- a/xen/include/asm-x86/domain.h Mon May 09 11:38:55 2011 +0100
+++ b/xen/include/asm-x86/domain.h Mon May 09 11:39:23 2011 +0100
@@ -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 631bdf00a81f -r 103f89fef294 xen/include/asm-x86/i387.h
--- a/xen/include/asm-x86/i387.h Mon May 09 11:38:55 2011 +0100
+++ b/xen/include/asm-x86/i387.h Mon May 09 11:39:23 2011 +0100
@@ -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);
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home