From: Jordan Niethe <jniethe5@gmail.com>

Direct branch patching was disabled when using TCG_REG_TB in commit
736a1588c1 ("tcg/ppc: Fix race in goto_tb implementation").

The issue with direct branch patching with TCG_REG_TB is the lack of
synchronization between the new TCG_REG_TB being established and the
direct branch being patched in.

If each translation block is responsible for establishing its own
TCG_REG_TB then there can be no synchronization issue.

Make each translation block begin by setting up its own TCG_REG_TB.
Use the preferred 'bcl 20,31,$+4' sequence.

Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
[rth: Split out tcg_out_tb_start, power9 addpcis]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/ppc/tcg-target.c.inc | 48 ++++++++++++++--------------------------
 1 file changed, 17 insertions(+), 31 deletions(-)

diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 5cecc6ed95..9197cfd6c6 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -2509,9 +2509,6 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 
     tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
     tcg_out32(s, MTSPR | RS(tcg_target_call_iarg_regs[1]) | CTR);
-    if (USE_REG_TB) {
-        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_TB, tcg_target_call_iarg_regs[1]);
-    }
     tcg_out32(s, BCCTR | BO_ALWAYS);
 
     /* Epilogue */
@@ -2529,7 +2526,13 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 
 static void tcg_out_tb_start(TCGContext *s)
 {
-    /* nothing to do */
+    /* Load TCG_REG_TB. */
+    if (USE_REG_TB) {
+        /* bcl 20,31,$+4 (preferred form for getting nia) */
+        tcg_out32(s, BC | BO_ALWAYS | BI(7, CR_SO) | 0x4 | LK);
+        tcg_out32(s, MFSPR | RT(TCG_REG_TB) | LR);
+        tcg_out32(s, ADDI | TAI(TCG_REG_TB, TCG_REG_TB, -4));
+    }
 }
 
 static void tcg_out_exit_tb(TCGContext *s, uintptr_t arg)
@@ -2542,32 +2545,22 @@ static void tcg_out_goto_tb(TCGContext *s, int which)
 {
     uintptr_t ptr = get_jmp_target_addr(s, which);
 
+    /* Direct branch will be patched by tb_target_set_jmp_target. */
+    set_jmp_insn_offset(s, which);
+    tcg_out32(s, NOP);
+
+    /* When branch is out of range, fall through to indirect. */
     if (USE_REG_TB) {
         ptrdiff_t offset = tcg_tbrel_diff(s, (void *)ptr);
-        tcg_out_mem_long(s, LD, LDX, TCG_REG_TB, TCG_REG_TB, offset);
-    
-        /* TODO: Use direct branches when possible. */
-        set_jmp_insn_offset(s, which);
-        tcg_out32(s, MTSPR | RS(TCG_REG_TB) | CTR);
-
-        tcg_out32(s, BCCTR | BO_ALWAYS);
-
-        /* For the unlinked case, need to reset TCG_REG_TB.  */
-        set_jmp_reset_offset(s, which);
-        tcg_out_mem_long(s, ADDI, ADD, TCG_REG_TB, TCG_REG_TB,
-                         -tcg_current_code_size(s));
+        tcg_out_mem_long(s, LD, LDX, TCG_REG_TMP1, TCG_REG_TB, offset);
     } else {
-        /* Direct branch will be patched by tb_target_set_jmp_target. */
-        set_jmp_insn_offset(s, which);
-        tcg_out32(s, NOP);
-
-        /* When branch is out of range, fall through to indirect. */
         tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP1, ptr - (int16_t)ptr);
         tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_REG_TMP1, (int16_t)ptr);
-        tcg_out32(s, MTSPR | RS(TCG_REG_TMP1) | CTR);
-        tcg_out32(s, BCCTR | BO_ALWAYS);
-        set_jmp_reset_offset(s, which);
     }
+
+    tcg_out32(s, MTSPR | RS(TCG_REG_TMP1) | CTR);
+    tcg_out32(s, BCCTR | BO_ALWAYS);
+    set_jmp_reset_offset(s, which);
 }
 
 void tb_target_set_jmp_target(const TranslationBlock *tb, int n,
@@ -2577,10 +2570,6 @@ void tb_target_set_jmp_target(const TranslationBlock *tb, int n,
     intptr_t diff = addr - jmp_rx;
     tcg_insn_unit insn;
 
-    if (USE_REG_TB) {
-        return;
-    }
-
     if (in_range_b(diff)) {
         insn = B | (diff & 0x3fffffc);
     } else {
@@ -2600,9 +2589,6 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     switch (opc) {
     case INDEX_op_goto_ptr:
         tcg_out32(s, MTSPR | RS(args[0]) | CTR);
-        if (USE_REG_TB) {
-            tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_TB, args[0]);
-        }
         tcg_out32(s, ADDI | TAI(TCG_REG_R3, 0, 0));
         tcg_out32(s, BCCTR | BO_ALWAYS);
         break;
-- 
2.34.1