tcg/sparc: Add tcg_out_jmpl_const for better tail calls

Due to mapping changes, we now rarely place the code_gen_buffer
near the main executable.  Which means that direct calls will
now rarely be in range.

So, always use indirect calls for tail calls, which allows us to
avoid clobbering %o7, and therefore we need not save and restore it.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 23 insertions, 14 deletions

diff --git a/tcg/sparc/tcg-target.c.inc b/tcg/sparc/tcg-target.c.inc
index e78945d..646bb46 100644
--- a/tcg/sparc/tcg-target.c.inc
+++ b/tcg/sparc/tcg-target.c.inc
@@ -858,6 +858,19 @@ static void tcg_out_addsub2_i64(TCGContext *s, TCGReg rl, TCGReg rh,
     tcg_out_mov(s, TCG_TYPE_I64, rl, tmp);
 }
 
+static void tcg_out_jmpl_const(TCGContext *s, const tcg_insn_unit *dest,
+                               bool in_prologue, bool tail_call)
+{
+    uintptr_t desti = (uintptr_t)dest;
+
+    /* Be careful not to clobber %o7 for a tail call. */
+    tcg_out_movi_int(s, TCG_TYPE_PTR, TCG_REG_T1,
+                     desti & ~0xfff, in_prologue,
+                     tail_call ? TCG_REG_G2 : TCG_REG_O7);
+    tcg_out_arithi(s, tail_call ? TCG_REG_G0 : TCG_REG_O7,
+                   TCG_REG_T1, desti & 0xfff, JMPL);
+}
+
 static void tcg_out_call_nodelay(TCGContext *s, const tcg_insn_unit *dest,
                                  bool in_prologue)
 {
@@ -866,10 +879,7 @@ static void tcg_out_call_nodelay(TCGContext *s, const tcg_insn_unit *dest,
     if (disp == (int32_t)disp) {
         tcg_out32(s, CALL | (uint32_t)disp >> 2);
     } else {
-        uintptr_t desti = (uintptr_t)dest;
-        tcg_out_movi_int(s, TCG_TYPE_PTR, TCG_REG_T1,
-                         desti & ~0xfff, in_prologue, TCG_REG_O7);
-        tcg_out_arithi(s, TCG_REG_O7, TCG_REG_T1, desti & 0xfff, JMPL);
+        tcg_out_jmpl_const(s, dest, in_prologue, false);
     }
 }
 
@@ -960,11 +970,10 @@ static void build_trampolines(TCGContext *s)
 
         /* Set the retaddr operand.  */
         tcg_out_mov(s, TCG_TYPE_PTR, ra, TCG_REG_O7);
-        /* Set the env operand.  */
-        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O0, TCG_AREG0);
         /* Tail call.  */
-        tcg_out_call_nodelay(s, qemu_ld_helpers[i], true);
-        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O7, ra);
+        tcg_out_jmpl_const(s, qemu_ld_helpers[i], true, true);
+        /* delay slot -- set the env argument */
+        tcg_out_mov_delay(s, TCG_REG_O0, TCG_AREG0);
     }
 
     for (i = 0; i < ARRAY_SIZE(qemu_st_helpers); ++i) {
@@ -1006,14 +1015,14 @@ static void build_trampolines(TCGContext *s)
         if (ra >= TCG_REG_O6) {
             tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_O7, TCG_REG_CALL_STACK,
                        TCG_TARGET_CALL_STACK_OFFSET);
-            ra = TCG_REG_G1;
+        } else {
+            tcg_out_mov(s, TCG_TYPE_PTR, ra, TCG_REG_O7);
         }
-        tcg_out_mov(s, TCG_TYPE_PTR, ra, TCG_REG_O7);
-        /* Set the env operand.  */
-        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O0, TCG_AREG0);
+
         /* Tail call.  */
-        tcg_out_call_nodelay(s, qemu_st_helpers[i], true);
-        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O7, ra);
+        tcg_out_jmpl_const(s, qemu_st_helpers[i], true, true);
+        /* delay slot -- set the env argument */
+        tcg_out_mov_delay(s, TCG_REG_O0, TCG_AREG0);
     }
 }
 #endif