[Qemu-devel] [PATCH v3 9/9] tcg: Lower indirect registers in a separate pass

[Richard Henderson]

Rather than rely on recursion during the middle of register allocation,
lower indirect registers to loads and stores off the indirect base into
plain temps.

For an x86_64 host, with sufficient registers, this results in identical
code, modulo the actual register assignments.

For an i686 host, with insufficient registers, this means that temps can
be (temporarily) spilled to the stack in order to satisfy an allocation.
This as opposed to the possibility of not being able to spill, to allocate
a register for the indirect base, in order to perform a spill.

Signed-off-by: Richard Henderson <address@hidden>
---
 include/qemu/log.h |   1 +
 tcg/optimize.c     |  31 +-----
 tcg/tcg.c          | 306 +++++++++++++++++++++++++++++++++++++++++++----------
 tcg/tcg.h          |   4 +
 util/log.c         |   5 +-
 5 files changed, 263 insertions(+), 84 deletions(-)

diff --git a/include/qemu/log.h b/include/qemu/log.h
index 8bec6b4..9c1cc38 100644
--- a/include/qemu/log.h
+++ b/include/qemu/log.h
@@ -42,6 +42,7 @@ static inline bool qemu_log_separate(void)
 #define CPU_LOG_TB_NOCHAIN (1 << 13)
 #define CPU_LOG_PAGE       (1 << 14)
 #define LOG_TRACE          (1 << 15)
+#define CPU_LOG_TB_OP_IND  (1 << 16)
 
 /* Returns true if a bit is set in the current loglevel mask
  */
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 8df7fc7..cffe89b 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -82,33 +82,6 @@ static void init_temp_info(TCGArg temp)
     }
 }
 
-static TCGOp *insert_op_before(TCGContext *s, TCGOp *old_op,
-                                TCGOpcode opc, int nargs)
-{
-    int oi = s->gen_next_op_idx;
-    int pi = s->gen_next_parm_idx;
-    int prev = old_op->prev;
-    int next = old_op - s->gen_op_buf;
-    TCGOp *new_op;
-
-    tcg_debug_assert(oi < OPC_BUF_SIZE);
-    tcg_debug_assert(pi + nargs <= OPPARAM_BUF_SIZE);
-    s->gen_next_op_idx = oi + 1;
-    s->gen_next_parm_idx = pi + nargs;
-
-    new_op = &s->gen_op_buf[oi];
-    *new_op = (TCGOp){
-        .opc = opc,
-        .args = pi,
-        .prev = prev,
-        .next = next
-    };
-    s->gen_op_buf[prev].next = oi;
-    old_op->prev = oi;
-
-    return new_op;
-}
-
 static int op_bits(TCGOpcode op)
 {
     const TCGOpDef *def = &tcg_op_defs[op];
@@ -1116,7 +1089,7 @@ void tcg_optimize(TCGContext *s)
                 uint64_t a = ((uint64_t)ah << 32) | al;
                 uint64_t b = ((uint64_t)bh << 32) | bl;
                 TCGArg rl, rh;
-                TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
+                TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32, 2);
                 TCGArg *args2 = &s->gen_opparam_buf[op2->args];
 
                 if (opc == INDEX_op_add2_i32) {
@@ -1142,7 +1115,7 @@ void tcg_optimize(TCGContext *s)
                 uint32_t b = temps[args[3]].val;
                 uint64_t r = (uint64_t)a * b;
                 TCGArg rl, rh;
-                TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
+                TCGOp *op2 = tcg_op_insert_before(s, op, INDEX_op_movi_i32, 2);
                 TCGArg *args2 = &s->gen_opparam_buf[op2->args];
 
                 rl = args[0];
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 3e4bc99..f00500e 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -531,8 +531,12 @@ int tcg_global_mem_new_internal(TCGType type, TCGv_ptr 
base,
 #endif
 
     if (!base_ts->fixed_reg) {
-        indirect_reg = 1;
+        /* We do not support double-indirect registers.  */
+        tcg_debug_assert(!base_ts->indirect_reg);
         base_ts->indirect_base = 1;
+        s->nb_indirects += (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64
+                            ? 2 : 1);
+        indirect_reg = 1;
     }
 
     if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
@@ -1323,9 +1327,66 @@ void tcg_op_remove(TCGContext *s, TCGOp *op)
 #endif
 }
 
+TCGOp *tcg_op_insert_before(TCGContext *s, TCGOp *old_op,
+                            TCGOpcode opc, int nargs)
+{
+    int oi = s->gen_next_op_idx;
+    int pi = s->gen_next_parm_idx;
+    int prev = old_op->prev;
+    int next = old_op - s->gen_op_buf;
+    TCGOp *new_op;
+
+    tcg_debug_assert(oi < OPC_BUF_SIZE);
+    tcg_debug_assert(pi + nargs <= OPPARAM_BUF_SIZE);
+    s->gen_next_op_idx = oi + 1;
+    s->gen_next_parm_idx = pi + nargs;
+
+    new_op = &s->gen_op_buf[oi];
+    *new_op = (TCGOp){
+        .opc = opc,
+        .args = pi,
+        .prev = prev,
+        .next = next
+    };
+    s->gen_op_buf[prev].next = oi;
+    old_op->prev = oi;
+
+    return new_op;
+}
+
+TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *old_op,
+                           TCGOpcode opc, int nargs)
+{
+    int oi = s->gen_next_op_idx;
+    int pi = s->gen_next_parm_idx;
+    int prev = old_op - s->gen_op_buf;
+    int next = old_op->next;
+    TCGOp *new_op;
+
+    tcg_debug_assert(oi < OPC_BUF_SIZE);
+    tcg_debug_assert(pi + nargs <= OPPARAM_BUF_SIZE);
+    s->gen_next_op_idx = oi + 1;
+    s->gen_next_parm_idx = pi + nargs;
+
+    new_op = &s->gen_op_buf[oi];
+    *new_op = (TCGOp){
+        .opc = opc,
+        .args = pi,
+        .prev = prev,
+        .next = next
+    };
+    s->gen_op_buf[next].prev = oi;
+    old_op->next = oi;
+
+    return new_op;
+}
+
 #define TS_DEAD  1
 #define TS_SYNC  2
 
+#define IS_DEAD_ARG(n)   (arg_life & (DEAD_ARG << (n)))
+#define NEED_SYNC_ARG(n) (arg_life & (SYNC_ARG << (n)))
+
 /* liveness analysis: end of function: all temps are dead, and globals
    should be in memory. */
 static inline void tcg_la_func_end(TCGContext *s, uint8_t *temp_state)
@@ -1351,13 +1412,11 @@ static inline void tcg_la_bb_end(TCGContext *s, uint8_t 
*temp_state)
 /* Liveness analysis : update the opc_arg_life array to tell if a
    given input arguments is dead. Instructions updating dead
    temporaries are removed. */
-static void tcg_liveness_analysis(TCGContext *s)
+static void liveness_pass_1(TCGContext *s, uint8_t *temp_state)
 {
-    uint8_t *temp_state;
-    int oi, oi_prev;
     int nb_globals = s->nb_globals;
+    int oi, oi_prev;
 
-    temp_state = tcg_malloc(s->nb_temps);
     tcg_la_func_end(s, temp_state);
 
     for (oi = s->gen_op_buf[0].prev; oi != 0; oi = oi_prev) {
@@ -1580,6 +1639,165 @@ static void tcg_liveness_analysis(TCGContext *s)
     }
 }
 
+/* Liveness analysis: Convert indirect regs to direct temporaries.  */
+static bool liveness_pass_2(TCGContext *s, uint8_t *temp_state)
+{
+    int nb_globals = s->nb_globals;
+    int16_t *dir_temps;
+    int i, oi, oi_next;
+    bool changes = false;
+
+    dir_temps = tcg_malloc(nb_globals * sizeof(int16_t));
+    memset(dir_temps, 0, nb_globals * sizeof(int16_t));
+
+    /* Create a temporary for each indirect global.  */
+    for (i = 0; i < nb_globals; ++i) {
+        TCGTemp *its = &s->temps[i];
+        if (its->indirect_reg) {
+            TCGTemp *dts = tcg_temp_alloc(s);
+            dts->type = its->type;
+            dts->base_type = its->base_type;
+            dir_temps[i] = temp_idx(s, dts);
+        }
+    }
+
+    memset(temp_state, TS_DEAD, nb_globals);
+
+    for (oi = s->gen_op_buf[0].next; oi != 0; oi = oi_next) {
+        TCGOp *op = &s->gen_op_buf[oi];
+        TCGArg *args = &s->gen_opparam_buf[op->args];
+        TCGOpcode opc = op->opc;
+        const TCGOpDef *def = &tcg_op_defs[opc];
+        TCGLifeData arg_life = op->life;
+        int nb_iargs, nb_oargs, call_flags;
+        TCGArg arg, dir;
+
+        oi_next = op->next;
+
+        if (opc == INDEX_op_call) {
+            nb_oargs = op->callo;
+            nb_iargs = op->calli;
+            call_flags = args[nb_oargs + nb_iargs + 1];
+        } else {
+            nb_iargs = def->nb_iargs;
+            nb_oargs = def->nb_oargs;
+
+            /* Set flags similar to how calls require.  */
+            if (def->flags & TCG_OPF_BB_END) {
+                /* Like writing globals: save_globals */
+                call_flags = 0;
+            } else if (def->flags & TCG_OPF_SIDE_EFFECTS) {
+                /* Like reading globals: sync_globals */
+                call_flags = TCG_CALL_NO_WRITE_GLOBALS;
+            } else {
+                /* No effect on globals.  */
+                call_flags = (TCG_CALL_NO_READ_GLOBALS |
+                              TCG_CALL_NO_WRITE_GLOBALS);
+            }
+        }
+
+        /* Make sure that input arguments are available.  */
+        for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
+            arg = args[i];
+            /* Note this unsigned test catches TCG_CALL_ARG_DUMMY too.  */
+            if (arg < nb_globals) {
+                dir = dir_temps[arg];
+                if (dir != 0 && temp_state[arg] == TS_DEAD) {
+                    TCGTemp *its = &s->temps[arg];
+                    TCGOpcode lopc = (its->type == TCG_TYPE_I32
+                                      ? INDEX_op_ld_i32
+                                      : INDEX_op_ld_i64);
+                    TCGOp *lop = tcg_op_insert_before(s, op, lopc, 3);
+                    TCGArg *largs = &s->gen_opparam_buf[lop->args];
+
+                    largs[0] = dir;
+                    largs[1] = temp_idx(s, its->mem_base);
+                    largs[2] = its->mem_offset;
+
+                    /* Loaded, but synced with memory.  */
+                    temp_state[arg] = TS_SYNC;
+                }
+            }
+        }
+
+        /* Perform input replacement, and mark inputs that became dead.
+           No action is required except keeping temp_state up to date
+           so that we reload when needed.  */
+        for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
+            arg = args[i];
+            if (arg < nb_globals) {
+                dir = dir_temps[arg];
+                if (dir != 0) {
+                    args[i] = dir;
+                    changes = true;
+                    if (IS_DEAD_ARG(i)) {
+                        temp_state[arg] = TS_DEAD;
+                    }
+                }
+            }
+        }
+
+        /* Liveness analysis should ensure that the following are
+           all correct, for call sites and basic block end points.  */
+        if (call_flags & TCG_CALL_NO_READ_GLOBALS) {
+            /* Nothing to do */
+        } else if (call_flags & TCG_CALL_NO_WRITE_GLOBALS) {
+            for (i = 0; i < nb_globals; ++i) {
+                /* Liveness should see that globals are synced back,
+                   that is, either TS_DEAD or TS_SYNC.  */
+                tcg_debug_assert(dir_temps[i] == 0
+                                 || temp_state[i] != 0);
+            }
+        } else {
+            for (i = 0; i < nb_globals; ++i) {
+                /* Liveness should see that globals are saved back,
+                   that is, TS_DEAD, waiting to be reloaded.  */
+                tcg_debug_assert(dir_temps[i] == 0
+                                 || temp_state[i] == TS_DEAD);
+            }
+        }
+
+        /* Outputs become available.  */
+        for (i = 0; i < nb_oargs; i++) {
+            arg = args[i];
+            if (arg >= nb_globals) {
+                continue;
+            }
+            dir = dir_temps[arg];
+            if (dir == 0) {
+                continue;
+            }
+            args[i] = dir;
+            changes = true;
+
+            /* The output is now live and modified.  */
+            temp_state[arg] = 0;
+
+            /* Sync outputs upon their last write.  */
+            if (NEED_SYNC_ARG(i)) {
+                TCGTemp *its = &s->temps[arg];
+                TCGOpcode sopc = (its->type == TCG_TYPE_I32
+                                  ? INDEX_op_st_i32
+                                  : INDEX_op_st_i64);
+                TCGOp *sop = tcg_op_insert_after(s, op, sopc, 3);
+                TCGArg *sargs = &s->gen_opparam_buf[sop->args];
+
+                sargs[0] = dir;
+                sargs[1] = temp_idx(s, its->mem_base);
+                sargs[2] = its->mem_offset;
+
+                temp_state[arg] = TS_SYNC;
+            }
+            /* Drop outputs that are dead.  */
+            if (IS_DEAD_ARG(i)) {
+                temp_state[arg] = TS_DEAD;
+            }
+        }
+    }
+
+    return changes;
+}
+
 #ifdef CONFIG_DEBUG_TCG
 static void dump_regs(TCGContext *s)
 {
@@ -1710,14 +1928,6 @@ static void temp_sync(TCGContext *s, TCGTemp *ts,
         if (!ts->mem_allocated) {
             temp_allocate_frame(s, temp_idx(s, ts));
         }
-        if (ts->indirect_reg) {
-            if (ts->val_type == TEMP_VAL_REG) {
-                tcg_regset_set_reg(allocated_regs, ts->reg);
-            }
-            temp_load(s, ts->mem_base,
-                      tcg_target_available_regs[TCG_TYPE_PTR],
-                      allocated_regs);
-        }
         switch (ts->val_type) {
         case TEMP_VAL_CONST:
             /* If we're going to free the temp immediately, then we won't
@@ -1807,12 +2017,6 @@ static void temp_load(TCGContext *s, TCGTemp *ts, 
TCGRegSet desired_regs,
         break;
     case TEMP_VAL_MEM:
         reg = tcg_reg_alloc(s, desired_regs, allocated_regs, 
ts->indirect_base);
-        if (ts->indirect_reg) {
-            tcg_regset_set_reg(allocated_regs, reg);
-            temp_load(s, ts->mem_base,
-                      tcg_target_available_regs[TCG_TYPE_PTR],
-                      allocated_regs);
-        }
         tcg_out_ld(s, ts->type, reg, ts->mem_base->reg, ts->mem_offset);
         ts->mem_coherent = 1;
         break;
@@ -1830,14 +2034,9 @@ static void temp_load(TCGContext *s, TCGTemp *ts, 
TCGRegSet desired_regs,
 static inline void temp_save(TCGContext *s, TCGTemp *ts,
                              TCGRegSet allocated_regs)
 {
-    /* ??? Liveness does not yet incorporate indirect bases.  */
-    if (!ts->indirect_base) {
-        /* The liveness analysis already ensures that globals are back
-           in memory. Keep an tcg_debug_assert for safety. */
-        tcg_debug_assert(ts->val_type == TEMP_VAL_MEM || ts->fixed_reg);
-        return;
-    }
-    temp_sync(s, ts, allocated_regs, 1);
+    /* The liveness analysis already ensures that globals are back
+       in memory. Keep an tcg_debug_assert for safety. */
+    tcg_debug_assert(ts->val_type == TEMP_VAL_MEM || ts->fixed_reg);
 }
 
 /* save globals to their canonical location and assume they can be
@@ -1861,14 +2060,9 @@ static void sync_globals(TCGContext *s, TCGRegSet 
allocated_regs)
 
     for (i = 0; i < s->nb_globals; i++) {
         TCGTemp *ts = &s->temps[i];
-        /* ??? Liveness does not yet incorporate indirect bases.  */
-        if (!ts->indirect_base) {
-            tcg_debug_assert(ts->val_type != TEMP_VAL_REG
-                             || ts->fixed_reg
-                             || ts->mem_coherent);
-            continue;
-        }
-        temp_sync(s, ts, allocated_regs, 0);
+        tcg_debug_assert(ts->val_type != TEMP_VAL_REG
+                         || ts->fixed_reg
+                         || ts->mem_coherent);
     }
 }
 
@@ -1883,23 +2077,15 @@ static void tcg_reg_alloc_bb_end(TCGContext *s, 
TCGRegSet allocated_regs)
         if (ts->temp_local) {
             temp_save(s, ts, allocated_regs);
         } else {
-            /* ??? Liveness does not yet incorporate indirect bases.  */
-            if (!ts->indirect_base) {
-                /* The liveness analysis already ensures that temps are dead.
-                   Keep an tcg_debug_assert for safety. */
-                tcg_debug_assert(ts->val_type == TEMP_VAL_DEAD);
-                continue;
-            }
-            temp_dead(s, ts);
+            /* The liveness analysis already ensures that temps are dead.
+               Keep an tcg_debug_assert for safety. */
+            tcg_debug_assert(ts->val_type == TEMP_VAL_DEAD);
         }
     }
 
     save_globals(s, allocated_regs);
 }
 
-#define IS_DEAD_ARG(n)   (arg_life & (DEAD_ARG << (n)))
-#define NEED_SYNC_ARG(n) (arg_life & (SYNC_ARG << (n)))
-
 static void tcg_reg_alloc_movi(TCGContext *s, const TCGArg *args,
                                TCGLifeData arg_life)
 {
@@ -1962,12 +2148,6 @@ 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, otype, ts->reg, ots->mem_base->reg, ots->mem_offset);
         if (IS_DEAD_ARG(1)) {
             temp_dead(s, ts);
@@ -2372,7 +2552,27 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)
     s->la_time -= profile_getclock();
 #endif
 
-    tcg_liveness_analysis(s);
+    {
+        uint8_t *temp_state = tcg_malloc(s->nb_temps + s->nb_indirects);
+
+        liveness_pass_1(s, temp_state);
+
+        if (s->nb_indirects > 0) {
+#ifdef DEBUG_DISAS
+            if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND)
+                         && qemu_log_in_addr_range(tb->pc))) {
+                qemu_log("OP before indirect lowering:\n");
+                tcg_dump_ops(s);
+                qemu_log("\n");
+            }
+#endif
+            /* Replace indirect temps with direct temps.  */
+            if (liveness_pass_2(s, temp_state)) {
+                /* If changes were made, re-run liveness.  */
+                liveness_pass_1(s, temp_state);
+            }
+        }
+    }
 
 #ifdef CONFIG_PROFILER
     s->la_time += profile_getclock();
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 2ff3ad2..c726355 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -547,6 +547,7 @@ struct TCGContext {
     int nb_labels;
     int nb_globals;
     int nb_temps;
+    int nb_indirects;
 
     /* goto_tb support */
     tcg_insn_unit *code_buf;
@@ -839,6 +840,9 @@ void tcg_gen_callN(TCGContext *s, void *func,
                    TCGArg ret, int nargs, TCGArg *args);
 
 void tcg_op_remove(TCGContext *s, TCGOp *op);
+TCGOp *tcg_op_insert_before(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
+TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
+
 void tcg_optimize(TCGContext *s);
 
 /* only used for debugging purposes */
diff --git a/util/log.c b/util/log.c
index 32e4160..7760d2a 100644
--- a/util/log.c
+++ b/util/log.c
@@ -239,8 +239,9 @@ const QEMULogItem qemu_log_items[] = {
     { CPU_LOG_TB_OP, "op",
       "show micro ops for each compiled TB" },
     { CPU_LOG_TB_OP_OPT, "op_opt",
-      "show micro ops (x86 only: before eflags optimization) and\n"
-      "after liveness analysis" },
+      "show micro ops after optimization" },
+    { CPU_LOG_TB_OP_IND, "op_ind",
+      "show micro ops before indirect lowering" },
     { CPU_LOG_INT, "int",
       "show interrupts/exceptions in short format" },
     { CPU_LOG_EXEC, "exec",
-- 
2.5.5