sparc64: Convert U1copy_{from,to}_user to accurate exception reporting.

Report the exact number of bytes which have not been successfully
copied when an exception occurs, using the running remaining length.

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 237 insertions, 124 deletions

diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index 1ad59fbac7a7..bb6ff73229e3 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_LD(x)                \
+#define EX_LD(x,y)              \
 98:     x;                      \
         .section __ex_table,"a";\
         .align 4;               \
-        .word 98b, __retl_mone; \
+        .word 98b, y;           \
         .text;                  \
         .align 4;
 
-#define EX_LD_FP(x)             \
+#define EX_LD_FP(x,y)           \
 98:     x;                      \
         .section __ex_table,"a";\
         .align 4;               \
-        .word 98b, __retl_mone_fp;\
+        .word 98b, y;           \
         .text;                  \
         .align 4;
 
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index adcc3a510185..ed92ce739558 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_ST(x)                \
+#define EX_ST(x,y)              \
 98:     x;                      \
         .section __ex_table,"a";\
         .align 4;               \
-        .word 98b, __retl_mone; \
+        .word 98b, y;           \
         .text;                  \
         .align 4;
 
-#define EX_ST_FP(x)             \
+#define EX_ST_FP(x,y)           \
 98:     x;                      \
         .section __ex_table,"a";\
         .align 4;               \
-        .word 98b, __retl_mone_fp;\
+        .word 98b, y;           \
         .text;                  \
         .align 4;
 
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index 97e1b211090c..4f0d50b33a72 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -5,6 +5,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #include <asm/export.h>
@@ -24,21 +25,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)        x
+#define EX_LD(x,y)      x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)     x
+#define EX_LD_FP(x,y)   x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)        x
+#define EX_ST(x,y)      x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)     x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)    x
+#define EX_ST_FP(x,y)   x
 #endif
 
 #ifndef LOAD
@@ -79,53 +76,169 @@
         faligndata              %f7, %f8, %f60;                 \
         faligndata              %f8, %f9, %f62;
 
-#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt)    \
-        EX_LD_FP(LOAD_BLK(%src, %fdest));                               \
-        EX_ST_FP(STORE_BLK(%fsrc, %dest));                              \
-        add                     %src, 0x40, %src;               \
-        subcc                   %len, 0x40, %len;               \
-        be,pn                   %xcc, jmptgt;                   \
-         add                    %dest, 0x40, %dest;             \
-
-#define LOOP_CHUNK1(src, dest, len, branch_dest)                \
-        MAIN_LOOP_CHUNK(src, dest, f0,  f48, len, branch_dest)
-#define LOOP_CHUNK2(src, dest, len, branch_dest)                \
-        MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
-#define LOOP_CHUNK3(src, dest, len, branch_dest)                \
-        MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
+#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt)                 \
+        EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp);                  \
+        EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp);                 \
+        add                     %src, 0x40, %src;                       \
+        subcc                   %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE;     \
+        be,pn                   %xcc, jmptgt;                           \
+         add                    %dest, 0x40, %dest;                     \
+
+#define LOOP_CHUNK1(src, dest, branch_dest)             \
+        MAIN_LOOP_CHUNK(src, dest, f0,  f48, branch_dest)
+#define LOOP_CHUNK2(src, dest, branch_dest)             \
+        MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest)
+#define LOOP_CHUNK3(src, dest, branch_dest)             \
+        MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest)
 
 #define DO_SYNC                 membar  #Sync;
 #define STORE_SYNC(dest, fsrc)                          \
-        EX_ST_FP(STORE_BLK(%fsrc, %dest));                      \
+        EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \
         add                     %dest, 0x40, %dest;     \
         DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)                  \
-        EX_ST_FP(STORE_BLK(%fsrc, %dest));                      \
+        EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp); \
         add                     %dest, 0x40, %dest;     \
         ba,pt                   %xcc, target;           \
          nop;
 
-#define FINISH_VISCHUNK(dest, f0, f1, left)     \
-        subcc                   %left, 8, %left;\
-        bl,pn                   %xcc, 95f;      \
-         faligndata             %f0, %f1, %f48; \
-        EX_ST_FP(STORE(std, %f48, %dest));              \
+#define FINISH_VISCHUNK(dest, f0, f1)                   \
+        subcc                   %g3, 8, %g3;            \
+        bl,pn                   %xcc, 95f;              \
+         faligndata             %f0, %f1, %f48;         \
+        EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp);  \
         add                     %dest, 8, %dest;
 
-#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)        \
-        subcc                   %left, 8, %left;        \
-        bl,pn                   %xcc, 95f;              \
+#define UNEVEN_VISCHUNK_LAST(dest, f0, f1)      \
+        subcc                   %g3, 8, %g3;    \
+        bl,pn                   %xcc, 95f;      \
          fsrc2                  %f0, %f1;
 
-#define UNEVEN_VISCHUNK(dest, f0, f1, left)             \
-        UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)        \
+#define UNEVEN_VISCHUNK(dest, f0, f1)           \
+        UNEVEN_VISCHUNK_LAST(dest, f0, f1)      \
         ba,a,pt                 %xcc, 93f;
 
         .register       %g2,#scratch
         .register       %g3,#scratch
 
         .text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)    x
+ENTRY(U1_g1_1_fp)
+        VISExitHalf
+        add             %g1, 1, %g1
+        add             %g1, %g2, %g1
+        retl
+         add            %g1, %o2, %o0
+ENDPROC(U1_g1_1_fp)
+ENTRY(U1_g2_0_fp)
+        VISExitHalf
+        retl
+         add            %g2, %o2, %o0
+ENDPROC(U1_g2_0_fp)
+ENTRY(U1_g2_8_fp)
+        VISExitHalf
+        add             %g2, 8, %g2
+        retl
+         add            %g2, %o2, %o0
+ENDPROC(U1_g2_8_fp)
+ENTRY(U1_gs_0_fp)
+        VISExitHalf
+        add             %GLOBAL_SPARE, %g3, %o0
+        retl
+         add            %o0, %o2, %o0
+ENDPROC(U1_gs_0_fp)
+ENTRY(U1_gs_80_fp)
+        VISExitHalf
+        add             %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
+        add             %GLOBAL_SPARE, %g3, %o0
+        retl
+         add            %o0, %o2, %o0
+ENDPROC(U1_gs_80_fp)
+ENTRY(U1_gs_40_fp)
+        VISExitHalf
+        add             %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE
+        add             %GLOBAL_SPARE, %g3, %o0
+        retl
+         add            %o0, %o2, %o0
+ENDPROC(U1_gs_40_fp)
+ENTRY(U1_g3_0_fp)
+        VISExitHalf
+        retl
+         add            %g3, %o2, %o0
+ENDPROC(U1_g3_0_fp)
+ENTRY(U1_g3_8_fp)
+        VISExitHalf
+        add             %g3, 8, %g3
+        retl
+         add            %g3, %o2, %o0
+ENDPROC(U1_g3_8_fp)
+ENTRY(U1_o2_0_fp)
+        VISExitHalf
+        retl
+         mov            %o2, %o0
+ENDPROC(U1_o2_0_fp)
+ENTRY(U1_o2_1_fp)
+        VISExitHalf
+        retl
+         add            %o2, 1, %o0
+ENDPROC(U1_o2_1_fp)
+ENTRY(U1_gs_0)
+        VISExitHalf
+        retl
+         add            %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0)
+ENTRY(U1_gs_8)
+        VISExitHalf
+        add             %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+        retl
+         add            %GLOBAL_SPARE, 0x8, %o0
+ENDPROC(U1_gs_8)
+ENTRY(U1_gs_10)
+        VISExitHalf
+        add             %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+        retl
+         add            %GLOBAL_SPARE, 0x10, %o0
+ENDPROC(U1_gs_10)
+ENTRY(U1_o2_0)
+        retl
+         mov            %o2, %o0
+ENDPROC(U1_o2_0)
+ENTRY(U1_o2_8)
+        retl
+         add            %o2, 8, %o0
+ENDPROC(U1_o2_8)
+ENTRY(U1_o2_4)
+        retl
+         add            %o2, 4, %o0
+ENDPROC(U1_o2_4)
+ENTRY(U1_o2_1)
+        retl
+         add            %o2, 1, %o0
+ENDPROC(U1_o2_1)
+ENTRY(U1_g1_0)
+        retl
+         add            %g1, %o2, %o0
+ENDPROC(U1_g1_0)
+ENTRY(U1_g1_1)
+        add             %g1, 1, %g1
+        retl
+         add            %g1, %o2, %o0
+ENDPROC(U1_g1_1)
+ENTRY(U1_gs_0_o2_adj)
+        and             %o2, 7, %o2
+        retl
+         add            %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0_o2_adj)
+ENTRY(U1_gs_8_o2_adj)
+        and             %o2, 7, %o2
+        add             %GLOBAL_SPARE, 8, %GLOBAL_SPARE
+        retl
+         add            %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_8_o2_adj)
+#endif
+
         .align          64
 
         .globl          FUNC_NAME
@@ -167,8 +280,8 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          and            %g2, 0x38, %g2
 
 1:      subcc           %g1, 0x1, %g1
-        EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
-        EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+        EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp)
+        EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp)
         bgu,pt          %XCC, 1b
          add            %o1, 0x1, %o1
 
@@ -179,20 +292,20 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         be,pt           %icc, 3f
          alignaddr      %o1, %g0, %o1
 
-        EX_LD_FP(LOAD(ldd, %o1, %f4))
-1:      EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+        EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp)
+1:      EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp)
         add             %o1, 0x8, %o1
         subcc           %g2, 0x8, %g2
         faligndata      %f4, %f6, %f0
-        EX_ST_FP(STORE(std, %f0, %o0))
+        EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
         be,pn           %icc, 3f
          add            %o0, 0x8, %o0
 
-        EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+        EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp)
         add             %o1, 0x8, %o1
         subcc           %g2, 0x8, %g2
         faligndata      %f6, %f4, %f0
-        EX_ST_FP(STORE(std, %f0, %o0))
+        EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
         bne,pt          %icc, 1b
          add            %o0, 0x8, %o0
 
@@ -215,13 +328,13 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         add             %g1, %GLOBAL_SPARE, %g1
         subcc           %o2, %g3, %o2
 
-        EX_LD_FP(LOAD_BLK(%o1, %f0))
+        EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp)
         add             %o1, 0x40, %o1
         add             %g1, %g3, %g1
-        EX_LD_FP(LOAD_BLK(%o1, %f16))
+        EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp)
         add             %o1, 0x40, %o1
         sub             %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
-        EX_LD_FP(LOAD_BLK(%o1, %f32))
+        EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp)
         add             %o1, 0x40, %o1
 
         /* There are 8 instances of the unrolled loop,
@@ -241,11 +354,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
         .align          64
 1:      FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f0, %f2, %f48
 1:      FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
@@ -262,11 +375,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 56f)
 
 1:      FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f2, %f4, %f48
 1:      FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
@@ -283,11 +396,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 57f)
 
 1:      FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f4, %f6, %f48
 1:      FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
@@ -304,11 +417,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 58f)
 
 1:      FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) 
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f6, %f8, %f48
 1:      FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
@@ -325,11 +438,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 59f)
 
 1:      FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f8, %f10, %f48
 1:      FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
@@ -346,11 +459,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 60f)
 
 1:      FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f10, %f12, %f48
 1:      FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
@@ -367,11 +480,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 61f)
 
 1:      FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f12, %f14, %f48
 1:      FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
@@ -388,11 +501,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         STORE_JUMP(o0, f48, 62f)
 
 1:      FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
-        LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+        LOOP_CHUNK1(o1, o0, 1f)
         FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
-        LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+        LOOP_CHUNK2(o1, o0, 2f)
         FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
-        LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+        LOOP_CHUNK3(o1, o0, 3f)
         ba,pt           %xcc, 1b+4
          faligndata     %f14, %f16, %f48
 1:      FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
@@ -408,53 +521,53 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
         STORE_JUMP(o0, f48, 63f)
 
-40:     FINISH_VISCHUNK(o0, f0,  f2,  g3)
-41:     FINISH_VISCHUNK(o0, f2,  f4,  g3)
-42:     FINISH_VISCHUNK(o0, f4,  f6,  g3)
-43:     FINISH_VISCHUNK(o0, f6,  f8,  g3)
-44:     FINISH_VISCHUNK(o0, f8,  f10, g3)
-45:     FINISH_VISCHUNK(o0, f10, f12, g3)
-46:     FINISH_VISCHUNK(o0, f12, f14, g3)
-47:     UNEVEN_VISCHUNK(o0, f14, f0,  g3)
-48:     FINISH_VISCHUNK(o0, f16, f18, g3)
-49:     FINISH_VISCHUNK(o0, f18, f20, g3)
-50:     FINISH_VISCHUNK(o0, f20, f22, g3)
-51:     FINISH_VISCHUNK(o0, f22, f24, g3)
-52:     FINISH_VISCHUNK(o0, f24, f26, g3)
-53:     FINISH_VISCHUNK(o0, f26, f28, g3)
-54:     FINISH_VISCHUNK(o0, f28, f30, g3)
-55:     UNEVEN_VISCHUNK(o0, f30, f0,  g3)
-56:     FINISH_VISCHUNK(o0, f32, f34, g3)
-57:     FINISH_VISCHUNK(o0, f34, f36, g3)
-58:     FINISH_VISCHUNK(o0, f36, f38, g3)
-59:     FINISH_VISCHUNK(o0, f38, f40, g3)
-60:     FINISH_VISCHUNK(o0, f40, f42, g3)
-61:     FINISH_VISCHUNK(o0, f42, f44, g3)
-62:     FINISH_VISCHUNK(o0, f44, f46, g3)
-63:     UNEVEN_VISCHUNK_LAST(o0, f46, f0,  g3)
-
-93:     EX_LD_FP(LOAD(ldd, %o1, %f2))
+40:     FINISH_VISCHUNK(o0, f0,  f2)
+41:     FINISH_VISCHUNK(o0, f2,  f4)
+42:     FINISH_VISCHUNK(o0, f4,  f6)
+43:     FINISH_VISCHUNK(o0, f6,  f8)
+44:     FINISH_VISCHUNK(o0, f8,  f10)
+45:     FINISH_VISCHUNK(o0, f10, f12)
+46:     FINISH_VISCHUNK(o0, f12, f14)
+47:     UNEVEN_VISCHUNK(o0, f14, f0)
+48:     FINISH_VISCHUNK(o0, f16, f18)
+49:     FINISH_VISCHUNK(o0, f18, f20)
+50:     FINISH_VISCHUNK(o0, f20, f22)
+51:     FINISH_VISCHUNK(o0, f22, f24)
+52:     FINISH_VISCHUNK(o0, f24, f26)
+53:     FINISH_VISCHUNK(o0, f26, f28)
+54:     FINISH_VISCHUNK(o0, f28, f30)
+55:     UNEVEN_VISCHUNK(o0, f30, f0)
+56:     FINISH_VISCHUNK(o0, f32, f34)
+57:     FINISH_VISCHUNK(o0, f34, f36)
+58:     FINISH_VISCHUNK(o0, f36, f38)
+59:     FINISH_VISCHUNK(o0, f38, f40)
+60:     FINISH_VISCHUNK(o0, f40, f42)
+61:     FINISH_VISCHUNK(o0, f42, f44)
+62:     FINISH_VISCHUNK(o0, f44, f46)
+63:     UNEVEN_VISCHUNK_LAST(o0, f46, f0)
+
+93:     EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
         add             %o1, 8, %o1
         subcc           %g3, 8, %g3
         faligndata      %f0, %f2, %f8
-        EX_ST_FP(STORE(std, %f8, %o0))
+        EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
         bl,pn           %xcc, 95f
          add            %o0, 8, %o0
-        EX_LD_FP(LOAD(ldd, %o1, %f0))
+        EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
         add             %o1, 8, %o1
         subcc           %g3, 8, %g3
         faligndata      %f2, %f0, %f8
-        EX_ST_FP(STORE(std, %f8, %o0))
+        EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
         bge,pt          %xcc, 93b
          add            %o0, 8, %o0
 
 95:     brz,pt          %o2, 2f
          mov            %g1, %o1
 
-1:      EX_LD_FP(LOAD(ldub, %o1, %o3))
+1:      EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp)
         add             %o1, 1, %o1
         subcc           %o2, 1, %o2
-        EX_ST_FP(STORE(stb, %o3, %o0))
+        EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp)
         bne,pt          %xcc, 1b
          add            %o0, 1, %o0
 
@@ -470,27 +583,27 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 72:     andn            %o2, 0xf, %GLOBAL_SPARE
         and             %o2, 0xf, %o2
-1:      EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
-        EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
+1:      EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0)
+        EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0)
         subcc           %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
-        EX_ST(STORE(stx, %o5, %o1 + %o3))
+        EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10)
         add             %o1, 0x8, %o1
-        EX_ST(STORE(stx, %g1, %o1 + %o3))
+        EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8)
         bgu,pt          %XCC, 1b
          add            %o1, 0x8, %o1
 73:     andcc           %o2, 0x8, %g0
         be,pt           %XCC, 1f
          nop
-        EX_LD(LOAD(ldx, %o1, %o5))
+        EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0)
         sub             %o2, 0x8, %o2
-        EX_ST(STORE(stx, %o5, %o1 + %o3))
+        EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8)
         add             %o1, 0x8, %o1
 1:      andcc           %o2, 0x4, %g0
         be,pt           %XCC, 1f
          nop
-        EX_LD(LOAD(lduw, %o1, %o5))
+        EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0)
         sub             %o2, 0x4, %o2
-        EX_ST(STORE(stw, %o5, %o1 + %o3))
+        EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4)
         add             %o1, 0x4, %o1
 1:      cmp             %o2, 0
         be,pt           %XCC, 85f
@@ -504,9 +617,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          sub            %g0, %g1, %g1
         sub             %o2, %g1, %o2
 
-1:      EX_LD(LOAD(ldub, %o1, %o5))
+1:      EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0)
         subcc           %g1, 1, %g1
-        EX_ST(STORE(stb, %o5, %o1 + %o3))
+        EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1)
         bgu,pt          %icc, 1b
          add            %o1, 1, %o1
 
@@ -522,16 +635,16 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 8:      mov             64, %o3
         andn            %o1, 0x7, %o1
-        EX_LD(LOAD(ldx, %o1, %g2))
+        EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0)
         sub             %o3, %g1, %o3
         andn            %o2, 0x7, %GLOBAL_SPARE
         sllx            %g2, %g1, %g2
-1:      EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1:      EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj)
         subcc           %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
         add             %o1, 0x8, %o1
         srlx            %g3, %o3, %o5
         or              %o5, %g2, %o5
-        EX_ST(STORE(stx, %o5, %o0))
+        EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj)
         add             %o0, 0x8, %o0
         bgu,pt          %icc, 1b
          sllx           %g3, %g1, %g2
@@ -549,9 +662,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         bne,pn          %XCC, 90f
          sub            %o0, %o1, %o3
 
-1:      EX_LD(LOAD(lduw, %o1, %g1))
+1:      EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0)
         subcc           %o2, 4, %o2
-        EX_ST(STORE(stw, %g1, %o1 + %o3))
+        EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4)
         bgu,pt          %XCC, 1b
          add            %o1, 4, %o1
 
@@ -559,9 +672,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          mov            EX_RETVAL(%o4), %o0
 
         .align          32
-90:     EX_LD(LOAD(ldub, %o1, %g1))
+90:     EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0)
         subcc           %o2, 1, %o2
-        EX_ST(STORE(stb, %g1, %o1 + %o3))
+        EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1)
         bgu,pt          %XCC, 90b
          add            %o1, 1, %o1
         retl