[Qemu-devel] [PATCH 09/14] tcg-sparc: Clean up cruft stemming from attempts to use global registers.

[Richard Henderson]

Don't use -ffixed-gN.  Don't link statically.  Don't save/restore
AREG0 around calls.  Don't allocate space on the stack for AREG0 save.

Signed-off-by: Richard Henderson <address@hidden>
---
 configure              | 12 -----------
 tcg/sparc/tcg-target.c | 55 +++++++++++++++++---------------------------------
 tcg/sparc/tcg-target.h | 18 +++++++----------
 3 files changed, 26 insertions(+), 59 deletions(-)

diff --git a/configure b/configure
index 0dc4170..1b86517 100755
--- a/configure
+++ b/configure
@@ -866,19 +866,11 @@ case "$cpu" in
     sparc)
            LDFLAGS="-m32 $LDFLAGS"
            QEMU_CFLAGS="-m32 -mcpu=ultrasparc $QEMU_CFLAGS"
-           QEMU_CFLAGS="-ffixed-g2 -ffixed-g3 $QEMU_CFLAGS"
-           if test "$solaris" = "no" ; then
-             QEMU_CFLAGS="-ffixed-g1 -ffixed-g6 $QEMU_CFLAGS"
-           fi
            host_guest_base="yes"
            ;;
     sparc64)
            LDFLAGS="-m64 $LDFLAGS"
            QEMU_CFLAGS="-m64 -mcpu=ultrasparc $QEMU_CFLAGS"
-           QEMU_CFLAGS="-ffixed-g5 -ffixed-g6 -ffixed-g7 $QEMU_CFLAGS"
-           if test "$solaris" != "no" ; then
-             QEMU_CFLAGS="-ffixed-g1 $QEMU_CFLAGS"
-           fi
            host_guest_base="yes"
            ;;
     s390)
@@ -4101,10 +4093,6 @@ fi
 
 if test "$target_linux_user" = "yes" -o "$target_bsd_user" = "yes" ; then
   case "$ARCH" in
-  sparc)
-    # -static is used to avoid g1/g3 usage by the dynamic linker
-    ldflags="$linker_script -static $ldflags"
-    ;;
   alpha | s390x)
     # The default placement of the application is fine.
     ;;
diff --git a/tcg/sparc/tcg-target.c b/tcg/sparc/tcg-target.c
index 9ab5746..e625aa3 100644
--- a/tcg/sparc/tcg-target.c
+++ b/tcg/sparc/tcg-target.c
@@ -161,7 +161,6 @@ static int target_parse_constraint(TCGArgConstraint *ct, 
const char **pct_str)
         tcg_regset_reset_reg(ct->u.regs, TCG_REG_O0);
         tcg_regset_reset_reg(ct->u.regs, TCG_REG_O1);
         tcg_regset_reset_reg(ct->u.regs, TCG_REG_O2);
-        tcg_regset_reset_reg(ct->u.regs, TCG_REG_O3);
         break;
     case 'I':
         ct->ct |= TCG_CT_CONST_S11;
@@ -681,11 +680,22 @@ static void tcg_out_setcond2_i32(TCGContext *s, TCGCond 
cond, TCGArg ret,
 /* Generate global QEMU prologue and epilogue code */
 static void tcg_target_qemu_prologue(TCGContext *s)
 {
-    tcg_set_frame(s, TCG_REG_I6, TCG_TARGET_CALL_STACK_OFFSET,
-                  CPU_TEMP_BUF_NLONGS * (int)sizeof(long));
+    int tmp_buf_size, frame_size;
+
+    /* The TCG temp buffer is at the top of the frame, immediately
+       below the frame pointer.  */
+    tmp_buf_size = CPU_TEMP_BUF_NLONGS * (int)sizeof(long);
+    tcg_set_frame(s, TCG_REG_I6, TCG_TARGET_STACK_BIAS - tmp_buf_size,
+                  tmp_buf_size);
+
+    /* TCG_TARGET_CALL_STACK_OFFSET includes the stack bias, but is
+       otherwise the minimal frame usable by callees.  */
+    frame_size = TCG_TARGET_CALL_STACK_OFFSET - TCG_TARGET_STACK_BIAS;
+    frame_size += TCG_STATIC_CALL_ARGS_SIZE + tmp_buf_size;
+    frame_size += TCG_TARGET_STACK_ALIGN - 1;
+    frame_size &= -TCG_TARGET_STACK_ALIGN;
     tcg_out32(s, SAVE | INSN_RD(TCG_REG_O6) | INSN_RS1(TCG_REG_O6) |
-              INSN_IMM13(-(TCG_TARGET_STACK_MINFRAME +
-                           CPU_TEMP_BUF_NLONGS * (int)sizeof(long))));
+              INSN_IMM13(-frame_size));
 
 #ifdef CONFIG_USE_GUEST_BASE
     if (GUEST_BASE != 0) {
@@ -698,6 +708,8 @@ static void tcg_target_qemu_prologue(TCGContext *s)
               INSN_RS2(TCG_REG_G0));
     /* delay slot */
     tcg_out_nop(s);
+
+    /* No epilogue required.  We issue ret + restore directly in the TB.  */
 }
 
 #if defined(CONFIG_SOFTMMU)
@@ -880,12 +892,6 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg 
*args, int sizeop)
     tcg_out_mov(s, TCG_TYPE_REG, tcg_target_call_iarg_regs[n++],
                 args[addrlo_idx]);
 
-    /* Store AREG0 in stack to avoid ugly glibc bugs that mangle
-       global registers */
-    tcg_out_st(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-               TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-               sizeof(long));
-
     /* qemu_ld_helper[s_bits](arg0, arg1) */
     tcg_out32(s, CALL | ((((tcg_target_ulong)qemu_ld_helpers[s_bits]
                            - (tcg_target_ulong)s->code_ptr) >> 2)
@@ -893,11 +899,6 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg 
*args, int sizeop)
     /* delay slot */
     tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[n], memi);
 
-    /* Reload AREG0.  */
-    tcg_out_ld(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-               TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-               sizeof(long));
-
     n = tcg_target_call_oarg_regs[0];
     /* datalo = sign_extend(arg0) */
     switch (sizeop) {
@@ -1011,12 +1012,6 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg 
*args, int sizeop)
     }
     tcg_out_mov(s, TCG_TYPE_REG, tcg_target_call_iarg_regs[n++], datalo);
 
-    /* Store AREG0 in stack to avoid ugly glibc bugs that mangle
-       global registers */
-    tcg_out_st(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-               TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-               sizeof(long));
-
     /* qemu_st_helper[s_bits](arg0, arg1, arg2) */
     tcg_out32(s, CALL | ((((tcg_target_ulong)qemu_st_helpers[sizeop]
                            - (tcg_target_ulong)s->code_ptr) >> 2)
@@ -1024,11 +1019,6 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg 
*args, int sizeop)
     /* delay slot */
     tcg_out_movi(s, TCG_TYPE_REG, tcg_target_call_iarg_regs[n], memi);
 
-    /* Reload AREG0.  */
-    tcg_out_ld(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-               TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-               sizeof(long));
-
     *label_ptr |= INSN_OFF19((unsigned long)s->code_ptr -
                              (unsigned long)label_ptr);
 #else
@@ -1091,15 +1081,8 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode 
opc, const TCGArg *args,
             tcg_out32(s, JMPL | INSN_RD(TCG_REG_O7) | INSN_RS1(TCG_REG_I5) |
                       INSN_RS2(TCG_REG_G0));
         }
-        /* Store AREG0 in stack to avoid ugly glibc bugs that mangle
-           global registers */
-        // delay slot
-        tcg_out_st(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-                   TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-                   sizeof(long));
-        tcg_out_ld(s, TCG_TYPE_REG, TCG_AREG0, TCG_REG_CALL_STACK,
-                   TCG_TARGET_CALL_STACK_OFFSET - TCG_STATIC_CALL_ARGS_SIZE -
-                   sizeof(long));
+        /* delay slot */
+        tcg_out_nop(s);
         break;
     case INDEX_op_jmp:
     case INDEX_op_br:
diff --git a/tcg/sparc/tcg-target.h b/tcg/sparc/tcg-target.h
index ee154d0..6314ffb 100644
--- a/tcg/sparc/tcg-target.h
+++ b/tcg/sparc/tcg-target.h
@@ -66,20 +66,16 @@ typedef enum {
 #define TCG_CT_CONST_S13 0x200
 
 /* used for function call generation */
-#define TCG_REG_CALL_STACK TCG_REG_I6
+#define TCG_REG_CALL_STACK TCG_REG_O6
 
 #if TCG_TARGET_REG_BITS == 64
-// Reserve space for AREG0
-#define TCG_TARGET_STACK_MINFRAME (176 + 4 * (int)sizeof(long) + \
-                                   TCG_STATIC_CALL_ARGS_SIZE)
-#define TCG_TARGET_CALL_STACK_OFFSET (2047 - 16)
-#define TCG_TARGET_STACK_ALIGN 16
+#define TCG_TARGET_STACK_BIAS           2047
+#define TCG_TARGET_STACK_ALIGN          16
+#define TCG_TARGET_CALL_STACK_OFFSET    (128 + 6*8 + TCG_TARGET_STACK_BIAS)
 #else
-// AREG0 + one word for alignment
-#define TCG_TARGET_STACK_MINFRAME (92 + (2 + 1) * (int)sizeof(long) + \
-                                   TCG_STATIC_CALL_ARGS_SIZE)
-#define TCG_TARGET_CALL_STACK_OFFSET TCG_TARGET_STACK_MINFRAME
-#define TCG_TARGET_STACK_ALIGN 8
+#define TCG_TARGET_STACK_BIAS           0
+#define TCG_TARGET_STACK_ALIGN          8
+#define TCG_TARGET_CALL_STACK_OFFSET    (64 + 4 + 6*4)
 #endif
 
 #if TCG_TARGET_REG_BITS == 64
-- 
1.7.11.4