[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH 2/6] x86/xsaves: enable xsaves/xrstors in xen



This patch uses xsaves/xrstors instead of xsaveopt/xrstor
to perform the xsave_area switching so that xen itself
can benefit from them when available.

Please note that xsaves/xrstors only use compact format.

Signed-off-by: Shuai Ruan <shuai.ruan@xxxxxxxxx>
---
 xen/arch/x86/i387.c          |  5 ++++
 xen/arch/x86/xstate.c        | 70 +++++++++++++++++++++++++-------------------
 xen/include/asm-x86/xstate.h |  4 ++-
 3 files changed, 48 insertions(+), 31 deletions(-)

diff --git a/xen/arch/x86/i387.c b/xen/arch/x86/i387.c
index 14f2a79..9071374 100644
--- a/xen/arch/x86/i387.c
+++ b/xen/arch/x86/i387.c
@@ -309,7 +309,12 @@ int vcpu_init_fpu(struct vcpu *v)
         return rc;
 
     if ( v->arch.xsave_area )
+    {
         v->arch.fpu_ctxt = &v->arch.xsave_area->fpu_sse;
+
+        if ( cpu_has_xsaves )
+            v->arch.xsave_area->xsave_hdr.xcomp_bv |= 
XSTATE_COMPACTION_ENABLED;
+    }
     else
     {
         v->arch.fpu_ctxt = _xzalloc(sizeof(v->arch.xsave_area->fpu_sse), 16);
diff --git a/xen/arch/x86/xstate.c b/xen/arch/x86/xstate.c
index e34eda3..571ce13 100644
--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -102,7 +102,9 @@ void xsave(struct vcpu *v, uint64_t mask)
         typeof(ptr->fpu_sse.fip.sel) fcs = ptr->fpu_sse.fip.sel;
         typeof(ptr->fpu_sse.fdp.sel) fds = ptr->fpu_sse.fdp.sel;
 
-        if ( cpu_has_xsaveopt )
+        if ( cpu_has_xsaves )
+            xsaves(lmask, hmask, ptr);
+        else if ( cpu_has_xsaveopt )
         {
             /*
              * xsaveopt may not write the FPU portion even when the respective
@@ -155,7 +157,9 @@ void xsave(struct vcpu *v, uint64_t mask)
     }
     else
     {
-        if ( cpu_has_xsaveopt )
+        if ( cpu_has_xsaves )
+            xsaves(lmask, hmask, ptr);
+        else if ( cpu_has_xsaveopt )
             asm volatile ( ".byte 0x0f,0xae,0x37"
                            : "=m" (*ptr)
                            : "a" (lmask), "d" (hmask), "D" (ptr) );
@@ -198,36 +202,42 @@ void xrstor(struct vcpu *v, uint64_t mask)
     switch ( __builtin_expect(ptr->fpu_sse.x[FPU_WORD_SIZE_OFFSET], 8) )
     {
     default:
-        asm volatile ( "1: .byte 0x48,0x0f,0xae,0x2f\n"
-                       ".section .fixup,\"ax\"      \n"
-                       "2: mov %5,%%ecx             \n"
-                       "   xor %1,%1                \n"
-                       "   rep stosb                \n"
-                       "   lea %2,%0                \n"
-                       "   mov %3,%1                \n"
-                       "   jmp 1b                   \n"
-                       ".previous                   \n"
-                       _ASM_EXTABLE(1b, 2b)
-                       : "+&D" (ptr), "+&a" (lmask)
-                       : "m" (*ptr), "g" (lmask), "d" (hmask),
-                         "m" (xsave_cntxt_size)
-                       : "ecx" );
+        if ( cpu_has_xsaves )
+            xrstors(lmask, hmask, ptr);
+        else
+            asm volatile ( "1: .byte 0x48,0x0f,0xae,0x2f\n"
+                           ".section .fixup,\"ax\"      \n"
+                           "2: mov %5,%%ecx             \n"
+                           "   xor %1,%1                \n"
+                           "   rep stosb                \n"
+                           "   lea %2,%0                \n"
+                           "   mov %3,%1                \n"
+                           "   jmp 1b                   \n"
+                           ".previous                   \n"
+                           _ASM_EXTABLE(1b, 2b)
+                           : "+&D" (ptr), "+&a" (lmask)
+                           : "m" (*ptr), "g" (lmask), "d" (hmask),
+                             "m" (xsave_cntxt_size)
+                           : "ecx" );
         break;
     case 4: case 2:
-        asm volatile ( "1: .byte 0x0f,0xae,0x2f\n"
-                       ".section .fixup,\"ax\" \n"
-                       "2: mov %5,%%ecx        \n"
-                       "   xor %1,%1           \n"
-                       "   rep stosb           \n"
-                       "   lea %2,%0           \n"
-                       "   mov %3,%1           \n"
-                       "   jmp 1b              \n"
-                       ".previous              \n"
-                       _ASM_EXTABLE(1b, 2b)
-                       : "+&D" (ptr), "+&a" (lmask)
-                       : "m" (*ptr), "g" (lmask), "d" (hmask),
-                         "m" (xsave_cntxt_size)
-                       : "ecx" );
+        if ( cpu_has_xsaves )
+            xrstors(lmask, hmask, ptr);
+        else
+            asm volatile ( "1: .byte 0x48,0x0f,0xae,0x2f\n"
+                           ".section .fixup,\"ax\"      \n"
+                           "2: mov %5,%%ecx             \n"
+                           "   xor %1,%1                \n"
+                           "   rep stosb                \n"
+                           "   lea %2,%0                \n"
+                           "   mov %3,%1                \n"
+                           "   jmp 1b                   \n"
+                           ".previous                   \n"
+                           _ASM_EXTABLE(1b, 2b)
+                           : "+&D" (ptr), "+&a" (lmask)
+                           : "m" (*ptr), "g" (lmask), "d" (hmask),
+                             "m" (xsave_cntxt_size)
+                           : "ecx" );
         break;
     }
 }
diff --git a/xen/include/asm-x86/xstate.h b/xen/include/asm-x86/xstate.h
index 59c7156..47c2f59 100644
--- a/xen/include/asm-x86/xstate.h
+++ b/xen/include/asm-x86/xstate.h
@@ -41,6 +41,7 @@
 #define XSTATE_ALL     (~(1ULL << 63))
 #define XSTATE_NONLAZY (XSTATE_LWP | XSTATE_BNDREGS | XSTATE_BNDCSR)
 #define XSTATE_LAZY    (XSTATE_ALL & ~XSTATE_NONLAZY)
+#define XSTATE_COMPACTION_ENABLED  (1ULL << 63)
 
 extern u64 xfeature_mask;
 extern bool_t cpu_has_xsaves, cpu_has_xgetbv1;
@@ -72,7 +73,8 @@ struct __packed __attribute__((aligned (64))) xsave_struct
 
     struct {
         u64 xstate_bv;
-        u64 reserved[7];
+        u64 xcomp_bv;
+        u64 reserved[6];
     } xsave_hdr;                             /* The 64-byte header */
 
     struct { char x[XSTATE_YMM_SIZE]; } ymm; /* YMM */
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.