Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-tcg-20210113' into staging

Improvements to tcg constant handling.
Force utf8 for decodetree.

# gpg: Signature made Thu 14 Jan 2021 02:15:42 GMT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-tcg-20210113: (24 commits)
  decodetree: Open files with encoding='utf-8'
  tcg/aarch64: Use tcg_constant_vec with tcg vec expanders
  tcg/ppc: Use tcg_constant_vec with tcg vec expanders
  tcg: Remove tcg_gen_dup{8,16,32,64}i_vec
  tcg/i386: Use tcg_constant_vec with tcg vec expanders
  tcg: Add tcg_reg_alloc_dup2
  tcg: Remove movi and dupi opcodes
  tcg/tci: Add special tci_movi_{i32,i64} opcodes
  tcg: Use tcg_constant_{i32,i64,vec} with gvec expanders
  tcg: Use tcg_constant_{i32,i64} with tcg plugins
  tcg: Use tcg_constant_{i32,i64} with tcg int expanders
  tcg: Use tcg_constant_i32 with icount expander
  tcg: Convert tcg_gen_dupi_vec to TCG_CONST
  tcg/optimize: Use tcg_constant_internal with constant folding
  tcg/optimize: Adjust TempOptInfo allocation
  tcg/optimize: Improve find_better_copy
  tcg: Introduce TYPE_CONST temporaries
  tcg: Expand TempOptInfo to 64-bits
  tcg: Rename struct tcg_temp_info to TempOptInfo
  tcg: Expand TCGTemp.val to 64-bits
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 64 insertions, 39 deletions

diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h
index aa4b443..298e01e 100644
--- a/include/exec/gen-icount.h
+++ b/include/exec/gen-icount.h
@@ -34,7 +34,7 @@ static inline void gen_io_end(void)
 
 static inline void gen_tb_start(const TranslationBlock *tb)
 {
-    TCGv_i32 count, imm;
+    TCGv_i32 count;
 
     tcg_ctx->exitreq_label = gen_new_label();
     if (tb_cflags(tb) & CF_USE_ICOUNT) {
@@ -48,15 +48,13 @@ static inline void gen_tb_start(const TranslationBlock *tb)
                    offsetof(ArchCPU, env));
 
     if (tb_cflags(tb) & CF_USE_ICOUNT) {
-        imm = tcg_temp_new_i32();
-        /* We emit a movi with a dummy immediate argument. Keep the insn index
-         * of the movi so that we later (when we know the actual insn count)
-         * can update the immediate argument with the actual insn count.  */
-        tcg_gen_movi_i32(imm, 0xdeadbeef);
+        /*
+         * We emit a sub with a dummy immediate argument. Keep the insn index
+         * of the sub so that we later (when we know the actual insn count)
+         * can update the argument with the actual insn count.
+         */
+        tcg_gen_sub_i32(count, count, tcg_constant_i32(0));
         icount_start_insn = tcg_last_op();
-
-        tcg_gen_sub_i32(count, count, imm);
-        tcg_temp_free_i32(imm);
     }
 
     tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, tcg_ctx->exitreq_label);
@@ -74,9 +72,12 @@ static inline void gen_tb_start(const TranslationBlock *tb)
 static inline void gen_tb_end(const TranslationBlock *tb, int num_insns)
 {
     if (tb_cflags(tb) & CF_USE_ICOUNT) {
-        /* Update the num_insn immediate parameter now that we know
-         * the actual insn count.  */
-        tcg_set_insn_param(icount_start_insn, 1, num_insns);
+        /*
+         * Update the num_insn immediate parameter now that we know
+         * the actual insn count.
+         */
+        tcg_set_insn_param(icount_start_insn, 2,
+                           tcgv_i32_arg(tcg_constant_i32(num_insns)));
     }
 
     gen_set_label(tcg_ctx->exitreq_label);
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index 901b19f..2cd1faf 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -271,6 +271,7 @@ void tcg_gen_mb(TCGBar);
 
 /* 32 bit ops */
 
+void tcg_gen_movi_i32(TCGv_i32 ret, int32_t arg);
 void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
 void tcg_gen_subfi_i32(TCGv_i32 ret, int32_t arg1, TCGv_i32 arg2);
 void tcg_gen_subi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
@@ -349,11 +350,6 @@ static inline void tcg_gen_mov_i32(TCGv_i32 ret, TCGv_i32 arg)
     }
 }
 
-static inline void tcg_gen_movi_i32(TCGv_i32 ret, int32_t arg)
-{
-    tcg_gen_op2i_i32(INDEX_op_movi_i32, ret, arg);
-}
-
 static inline void tcg_gen_ld8u_i32(TCGv_i32 ret, TCGv_ptr arg2,
                                     tcg_target_long offset)
 {
@@ -467,6 +463,7 @@ static inline void tcg_gen_not_i32(TCGv_i32 ret, TCGv_i32 arg)
 
 /* 64 bit ops */
 
+void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg);
 void tcg_gen_addi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
 void tcg_gen_subfi_i64(TCGv_i64 ret, int64_t arg1, TCGv_i64 arg2);
 void tcg_gen_subi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
@@ -550,11 +547,6 @@ static inline void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg)
     }
 }
 
-static inline void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg)
-{
-    tcg_gen_op2i_i64(INDEX_op_movi_i64, ret, arg);
-}
-
 static inline void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2,
                                     tcg_target_long offset)
 {
@@ -698,7 +690,6 @@ static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 
 void tcg_gen_discard_i64(TCGv_i64 arg);
 void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg);
-void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg);
 void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
 void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
 void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
@@ -968,10 +959,6 @@ void tcg_gen_mov_vec(TCGv_vec, TCGv_vec);
 void tcg_gen_dup_i32_vec(unsigned vece, TCGv_vec, TCGv_i32);
 void tcg_gen_dup_i64_vec(unsigned vece, TCGv_vec, TCGv_i64);
 void tcg_gen_dup_mem_vec(unsigned vece, TCGv_vec, TCGv_ptr, tcg_target_long);
-void tcg_gen_dup8i_vec(TCGv_vec, uint32_t);
-void tcg_gen_dup16i_vec(TCGv_vec, uint32_t);
-void tcg_gen_dup32i_vec(TCGv_vec, uint32_t);
-void tcg_gen_dup64i_vec(TCGv_vec, uint64_t);
 void tcg_gen_dupi_vec(unsigned vece, TCGv_vec, uint64_t);
 void tcg_gen_add_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b);
 void tcg_gen_sub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b);
diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h
index 70a7664..900984c 100644
--- a/include/tcg/tcg-opc.h
+++ b/include/tcg/tcg-opc.h
@@ -45,7 +45,6 @@ DEF(br, 0, 0, 1, TCG_OPF_BB_END)
 DEF(mb, 0, 0, 1, 0)
 
 DEF(mov_i32, 1, 1, 0, TCG_OPF_NOT_PRESENT)
-DEF(movi_i32, 1, 0, 1, TCG_OPF_NOT_PRESENT)
 DEF(setcond_i32, 1, 2, 1, 0)
 DEF(movcond_i32, 1, 4, 1, IMPL(TCG_TARGET_HAS_movcond_i32))
 /* load/store */
@@ -111,7 +110,6 @@ DEF(ctz_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_ctz_i32))
 DEF(ctpop_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ctpop_i32))
 
 DEF(mov_i64, 1, 1, 0, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT)
-DEF(movi_i64, 1, 0, 1, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT)
 DEF(setcond_i64, 1, 2, 1, IMPL64)
 DEF(movcond_i64, 1, 4, 1, IMPL64 | IMPL(TCG_TARGET_HAS_movcond_i64))
 /* load/store */
@@ -221,7 +219,6 @@ DEF(qemu_st8_i32, 0, TLADDR_ARGS + 1, 1,
 #define IMPLVEC  TCG_OPF_VECTOR | IMPL(TCG_TARGET_MAYBE_vec)
 
 DEF(mov_vec, 1, 1, 0, TCG_OPF_VECTOR | TCG_OPF_NOT_PRESENT)
-DEF(dupi_vec, 1, 0, 1, TCG_OPF_VECTOR | TCG_OPF_NOT_PRESENT)
 
 DEF(dup_vec, 1, 1, 0, IMPLVEC)
 DEF(dup2_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_REG_BITS == 32))
@@ -278,6 +275,14 @@ DEF(last_generic, 0, 0, 0, TCG_OPF_NOT_PRESENT)
 #include "tcg-target.opc.h"
 #endif
 
+#ifdef TCG_TARGET_INTERPRETER
+/* These opcodes are only for use between the tci generator and interpreter. */
+DEF(tci_movi_i32, 1, 0, 1, TCG_OPF_NOT_PRESENT)
+#if TCG_TARGET_REG_BITS == 64
+DEF(tci_movi_i64, 1, 0, 1, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT)
+#endif
+#endif
+
 #undef TLADDR_ARGS
 #undef DATA64_ARGS
 #undef IMPL
diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h
index 95fe560..504c5e9 100644
--- a/include/tcg/tcg.h
+++ b/include/tcg/tcg.h
@@ -483,26 +483,32 @@ typedef enum TCGTempVal {
     TEMP_VAL_CONST,
 } TCGTempVal;
 
+typedef enum TCGTempKind {
+    /* Temp is dead at the end of all basic blocks. */
+    TEMP_NORMAL,
+    /* Temp is saved across basic blocks but dead at the end of TBs. */
+    TEMP_LOCAL,
+    /* Temp is saved across both basic blocks and translation blocks. */
+    TEMP_GLOBAL,
+    /* Temp is in a fixed register. */
+    TEMP_FIXED,
+    /* Temp is a fixed constant. */
+    TEMP_CONST,
+} TCGTempKind;
+
 typedef struct TCGTemp {
     TCGReg reg:8;
     TCGTempVal val_type:8;
     TCGType base_type:8;
     TCGType type:8;
-    unsigned int fixed_reg:1;
+    TCGTempKind kind:3;
     unsigned int indirect_reg:1;
     unsigned int indirect_base:1;
     unsigned int mem_coherent:1;
     unsigned int mem_allocated:1;
-    /* If true, the temp is saved across both basic blocks and
-       translation blocks.  */
-    unsigned int temp_global:1;
-    /* If true, the temp is saved across basic blocks but dead
-       at the end of translation blocks.  If false, the temp is
-       dead at the end of basic blocks.  */
-    unsigned int temp_local:1;
     unsigned int temp_allocated:1;
 
-    tcg_target_long val;
+    int64_t val;
     struct TCGTemp *mem_base;
     intptr_t mem_offset;
     const char *name;
@@ -661,6 +667,7 @@ struct TCGContext {
     QSIMPLEQ_HEAD(, TCGOp) plugin_ops;
 #endif
 
+    GHashTable *const_table[TCG_TYPE_COUNT];
     TCGTempSet free_temps[TCG_TYPE_COUNT * 2];
     TCGTemp temps[TCG_MAX_TEMPS]; /* globals first, temps after */
 
@@ -675,6 +682,11 @@ struct TCGContext {
     target_ulong gen_insn_data[TCG_MAX_INSNS][TARGET_INSN_START_WORDS];
 };
 
+static inline bool temp_readonly(TCGTemp *ts)
+{
+    return ts->kind >= TEMP_FIXED;
+}
+
 extern TCGContext tcg_init_ctx;
 extern __thread TCGContext *tcg_ctx;
 extern const void *tcg_code_gen_epilogue;
@@ -1070,6 +1082,7 @@ TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *op, TCGOpcode opc);
 
 void tcg_optimize(TCGContext *s);
 
+/* Allocate a new temporary and initialize it with a constant. */
 TCGv_i32 tcg_const_i32(int32_t val);
 TCGv_i64 tcg_const_i64(int64_t val);
 TCGv_i32 tcg_const_local_i32(int32_t val);
@@ -1079,6 +1092,25 @@ TCGv_vec tcg_const_ones_vec(TCGType);
 TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec);
 TCGv_vec tcg_const_ones_vec_matching(TCGv_vec);
 
+/*
+ * Locate or create a read-only temporary that is a constant.
+ * This kind of temporary need not and should not be freed.
+ */
+TCGTemp *tcg_constant_internal(TCGType type, int64_t val);
+
+static inline TCGv_i32 tcg_constant_i32(int32_t val)
+{
+    return temp_tcgv_i32(tcg_constant_internal(TCG_TYPE_I32, val));
+}
+
+static inline TCGv_i64 tcg_constant_i64(int64_t val)
+{
+    return temp_tcgv_i64(tcg_constant_internal(TCG_TYPE_I64, val));
+}
+
+TCGv_vec tcg_constant_vec(TCGType type, unsigned vece, int64_t val);
+TCGv_vec tcg_constant_vec_matching(TCGv_vec match, unsigned vece, int64_t val);
+
 #if UINTPTR_MAX == UINT32_MAX
 # define tcg_const_ptr(x)        ((TCGv_ptr)tcg_const_i32((intptr_t)(x)))
 # define tcg_const_local_ptr(x)  ((TCGv_ptr)tcg_const_local_i32((intptr_t)(x)))