[Qemu-devel] [RFC 14/16] tcg: Implement indirect memory registers

[Richard Henderson <rth@twiddle.net>]

That is, global_mem registers whose base is another global_mem
register, rather than a fixed register.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/tcg.c | 104 ++++++++++++++++++++++++++++++++++++++++++--------------------
 tcg/tcg.h |   2 ++
 2 files changed, 73 insertions(+), 33 deletions(-)

diff --git a/tcg/tcg.c b/tcg/tcg.c
index 3591491..eb4ed0d 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -412,17 +412,23 @@ int tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
     TCGContext *s = &tcg_ctx;
     TCGTemp *base_ts = &s->temps[GET_TCGV_PTR(base)];
     TCGTemp *ts = tcg_global_alloc(s);
-    int bigendian = 0;
+    int indirect_reg = 0, bigendian = 0;
 #ifdef TCG_TARGET_WORDS_BIGENDIAN
     bigendian = 1;
 #endif
 
+    if (!base_ts->fixed_reg) {
+        indirect_reg = 1;
+        base_ts->indirect_base = 1;
+    }
+
     if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
         TCGTemp *ts2 = tcg_global_alloc(s);
         char buf[64];
 
         ts->base_type = TCG_TYPE_I64;
         ts->type = TCG_TYPE_I32;
+        ts->indirect_reg = indirect_reg;
         ts->mem_allocated = 1;
         ts->mem_base = base_ts;
         ts->mem_offset = offset + bigendian * 4;
@@ -433,6 +439,7 @@ int tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
         assert(ts2 == ts + 1);
         ts2->base_type = TCG_TYPE_I64;
         ts2->type = TCG_TYPE_I32;
+        ts2->indirect_reg = indirect_reg;
         ts2->mem_allocated = 1;
         ts2->mem_base = base_ts;
         ts2->mem_offset = offset + (1 - bigendian) * 4;
@@ -442,6 +449,7 @@ int tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
     } else {
         ts->base_type = type;
         ts->type = type;
+        ts->indirect_reg = indirect_reg;
         ts->mem_allocated = 1;
         ts->mem_base = base_ts;
         ts->mem_offset = offset;
@@ -1585,8 +1593,10 @@ static void temp_allocate_frame(TCGContext *s, int temp)
     s->current_frame_offset += sizeof(tcg_target_long);
 }
 
+static void temp_load(TCGContext *, TCGTemp *, TCGRegSet, TCGRegSet);
+
 /* sync register 'reg' by saving it to the corresponding temporary */
-static inline void tcg_reg_sync(TCGContext *s, TCGReg reg)
+static void tcg_reg_sync(TCGContext *s, TCGReg reg, TCGRegSet allocated_regs)
 {
     TCGTemp *ts = s->reg_to_temp[reg];
 
@@ -1594,6 +1604,11 @@ static inline void tcg_reg_sync(TCGContext *s, TCGReg reg)
     if (!ts->mem_coherent && !ts->fixed_reg) {
         if (!ts->mem_allocated) {
             temp_allocate_frame(s, temp_idx(s, ts));
+        } else if (ts->indirect_reg) {
+            tcg_regset_set_reg(allocated_regs, ts->reg);
+            temp_load(s, ts->mem_base,
+                      tcg_target_available_regs[TCG_TYPE_PTR],
+                      allocated_regs);
         }
         tcg_out_st(s, ts->type, reg, ts->mem_base->reg, ts->mem_offset);
     }
@@ -1601,25 +1616,26 @@ static inline void tcg_reg_sync(TCGContext *s, TCGReg reg)
 }
 
 /* free register 'reg' by spilling the corresponding temporary if necessary */
-static void tcg_reg_free(TCGContext *s, TCGReg reg)
+static void tcg_reg_free(TCGContext *s, TCGReg reg, TCGRegSet allocated_regs)
 {
     TCGTemp *ts = s->reg_to_temp[reg];
 
     if (ts != NULL) {
-        tcg_reg_sync(s, reg);
+        tcg_reg_sync(s, reg, allocated_regs);
         ts->val_type = TEMP_VAL_MEM;
         s->reg_to_temp[reg] = NULL;
     }
 }
 
 /* Allocate a register belonging to reg1 & ~reg2 */
-static TCGReg tcg_reg_alloc(TCGContext *s, TCGRegSet reg1, TCGRegSet reg2)
+static TCGReg tcg_reg_alloc(TCGContext *s, TCGRegSet desired_regs,
+                            TCGRegSet allocated_regs)
 {
     int i;
     TCGReg reg;
     TCGRegSet reg_ct;
 
-    tcg_regset_andnot(reg_ct, reg1, reg2);
+    tcg_regset_andnot(reg_ct, desired_regs, allocated_regs);
 
     /* first try free registers */
     for(i = 0; i < ARRAY_SIZE(tcg_target_reg_alloc_order); i++) {
@@ -1632,7 +1648,7 @@ static TCGReg tcg_reg_alloc(TCGContext *s, TCGRegSet reg1, TCGRegSet reg2)
     for(i = 0; i < ARRAY_SIZE(tcg_target_reg_alloc_order); i++) {
         reg = tcg_target_reg_alloc_order[i];
         if (tcg_regset_test_reg(reg_ct, reg)) {
-            tcg_reg_free(s, reg);
+            tcg_reg_free(s, reg, allocated_regs);
             return reg;
         }
     }
@@ -1652,22 +1668,28 @@ static void temp_load(TCGContext *s, TCGTemp *ts, TCGRegSet desired_regs,
     }
 
     ts->reg = tcg_reg_alloc(s, desired_regs, allocated_regs);
-    ts->val_type = TEMP_VAL_REG;
-    s->reg_to_temp[ts->reg] = ts;
 
     switch (val_type) {
     case TEMP_VAL_CONST:
-        ts->mem_coherent = 0;
         tcg_out_movi(s, ts->type, ts->reg, ts->val);
+        ts->mem_coherent = 0;
         break;
     case TEMP_VAL_MEM:
-        ts->mem_coherent = 1;
+        if (ts->indirect_reg) {
+            tcg_regset_set_reg(allocated_regs, ts->reg);
+            temp_load(s, ts->mem_base,
+                      tcg_target_available_regs[TCG_TYPE_PTR],
+                      allocated_regs);
+        }
         tcg_out_ld(s, ts->type, ts->reg, ts->mem_base->reg, ts->mem_offset);
+        ts->mem_coherent = 1;
         break;
     case TEMP_VAL_DEAD:
     default:
         tcg_abort();
     }
+    ts->val_type = TEMP_VAL_REG;
+    s->reg_to_temp[ts->reg] = ts;
 }
 
 /* mark a temporary as dead. */
@@ -1696,7 +1718,7 @@ static void temp_sync(TCGContext *s, TCGTemp *ts, TCGRegSet allocated_regs)
         temp_load(s, ts, tcg_target_available_regs[ts->type], allocated_regs);
         /* fallthrough*/
     case TEMP_VAL_REG:
-        tcg_reg_sync(s, ts->reg);
+        tcg_reg_sync(s, ts->reg, allocated_regs);
         break;
     case TEMP_VAL_DEAD:
     case TEMP_VAL_MEM:
@@ -1712,13 +1734,16 @@ static inline void temp_save(TCGContext *s, TCGTemp *ts,
                              TCGRegSet allocated_regs)
 {
 #ifdef USE_LIVENESS_ANALYSIS
-    /* The liveness analysis already ensures that globals are back
-       in memory. Keep an assert for safety. */
-    assert(ts->val_type == TEMP_VAL_MEM || ts->fixed_reg);
-#else
+    /* ??? Liveness does not yet incorporate indirect bases.  */
+    if (!ts->indirect_base) {
+        /* The liveness analysis already ensures that globals are back
+           in memory. Keep an assert for safety. */
+        assert(ts->val_type == TEMP_VAL_MEM || ts->fixed_reg);
+        return;
+    }
+#endif
     temp_sync(s, ts, allocated_regs);
     temp_dead(s, ts);
-#endif
 }
 
 /* save globals to their canonical location and assume they can be
@@ -1742,13 +1767,17 @@ static void sync_globals(TCGContext *s, TCGRegSet allocated_regs)
 
     for (i = 0; i < s->nb_globals; i++) {
         TCGTemp *ts = &s->temps[i];
+
 #ifdef USE_LIVENESS_ANALYSIS
-        assert(ts->val_type != TEMP_VAL_REG
-               || ts->fixed_reg
-               || ts->mem_coherent);
-#else
-        temp_sync(s, ts, allocated_regs);
+        /* ??? Liveness does not yet incorporate indirect bases.  */
+        if (!ts->indirect_base) {
+            assert(ts->val_type != TEMP_VAL_REG
+                   || ts->fixed_reg
+                   || ts->mem_coherent);
+            continue;
+        }
 #endif
+        temp_sync(s, ts, allocated_regs);
     }
 }
 
@@ -1764,12 +1793,15 @@ static void tcg_reg_alloc_bb_end(TCGContext *s, TCGRegSet allocated_regs)
             temp_save(s, ts, allocated_regs);
         } else {
 #ifdef USE_LIVENESS_ANALYSIS
-            /* The liveness analysis already ensures that temps are dead.
-               Keep an assert for safety. */
-            assert(ts->val_type == TEMP_VAL_DEAD);
-#else
-            temp_dead(s, ts);
+            /* ??? Liveness does not yet incorporate indirect bases.  */
+            if (!ts->indirect_base) {
+                /* The liveness analysis already ensures that temps are dead.
+                   Keep an assert for safety. */
+                assert(ts->val_type == TEMP_VAL_DEAD);
+                continue;
+            }
 #endif
+            temp_dead(s, ts);
         }
     }
 
@@ -1840,6 +1872,12 @@ static void tcg_reg_alloc_mov(TCGContext *s, const TCGOpDef *def,
         if (!ots->mem_allocated) {
             temp_allocate_frame(s, args[0]);
         }
+        if (ots->indirect_reg) {
+            tcg_regset_set_reg(allocated_regs, ts->reg);
+            temp_load(s, ots->mem_base,
+                      tcg_target_available_regs[TCG_TYPE_PTR],
+                      allocated_regs);
+        }
         tcg_out_st(s, ots->type, ts->reg, ots->mem_base->reg, ots->mem_offset);
         if (IS_DEAD_ARG(1)) {
             temp_dead(s, ts);
@@ -1876,7 +1914,7 @@ static void tcg_reg_alloc_mov(TCGContext *s, const TCGOpDef *def,
         ots->mem_coherent = 0;
         s->reg_to_temp[ots->reg] = ots;
         if (NEED_SYNC_ARG(0)) {
-            tcg_reg_sync(s, ots->reg);
+            tcg_reg_sync(s, ots->reg, allocated_regs);
         }
     }
 }
@@ -1966,7 +2004,7 @@ static void tcg_reg_alloc_op(TCGContext *s,
             /* XXX: permit generic clobber register list ? */ 
             for(reg = 0; reg < TCG_TARGET_NB_REGS; reg++) {
                 if (tcg_regset_test_reg(tcg_target_call_clobber_regs, reg)) {
-                    tcg_reg_free(s, reg);
+                    tcg_reg_free(s, reg, allocated_regs);
                 }
             }
         }
@@ -2023,7 +2061,7 @@ static void tcg_reg_alloc_op(TCGContext *s,
             tcg_out_mov(s, ts->type, ts->reg, reg);
         }
         if (NEED_SYNC_ARG(i)) {
-            tcg_reg_sync(s, reg);
+            tcg_reg_sync(s, reg, allocated_regs);
         }
         if (IS_DEAD_ARG(i)) {
             temp_dead(s, ts);
@@ -2099,7 +2137,7 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
         if (arg != TCG_CALL_DUMMY_ARG) {
             ts = &s->temps[arg];
             reg = tcg_target_call_iarg_regs[i];
-            tcg_reg_free(s, reg);
+            tcg_reg_free(s, reg, allocated_regs);
 
             if (ts->val_type == TEMP_VAL_REG) {
                 if (ts->reg != reg) {
@@ -2158,7 +2196,7 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
     /* clobber call registers */
     for(reg = 0; reg < TCG_TARGET_NB_REGS; reg++) {
         if (tcg_regset_test_reg(tcg_target_call_clobber_regs, reg)) {
-            tcg_reg_free(s, reg);
+            tcg_reg_free(s, reg, allocated_regs);
         }
     }
 
@@ -2193,7 +2231,7 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
             ts->mem_coherent = 0;
             s->reg_to_temp[reg] = ts;
             if (NEED_SYNC_ARG(i)) {
-                tcg_reg_sync(s, reg);
+                tcg_reg_sync(s, reg, allocated_regs);
             }
             if (IS_DEAD_ARG(i)) {
                 temp_dead(s, ts);
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 74649fa..cff86dc 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -399,6 +399,8 @@ typedef struct TCGTemp {
     struct TCGTemp *mem_base;
     intptr_t mem_offset;
     unsigned int fixed_reg:1;
+    unsigned int indirect_reg:1;
+    unsigned int indirect_base:1;
     unsigned int mem_coherent:1;
     unsigned int mem_allocated:1;
     unsigned int temp_local:1; /* If true, the temp is saved across
-- 
1.8.1.4