tcg: Vary the allocation size for TCGOp

We have been allocating a worst case number of arguments
to support calls.  Instead, allow the size to vary.
By default leave space for 4 args, to maximize reuse,
but allow calls to increase the number of args to 32.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
[PMD: Split patch in two]
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221218211832.73312-3-philmd@linaro.org>

1 files changed, 16 insertions, 30 deletions

diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h
index c55fa21a89..d430ea10c8 100644
--- a/include/tcg/tcg.h
+++ b/include/tcg/tcg.h
@@ -38,20 +38,6 @@
 /* XXX: make safe guess about sizes */
 #define MAX_OP_PER_INSTR 266
 
-#if HOST_LONG_BITS == 32
-#define MAX_OPC_PARAM_PER_ARG 2
-#else
-#define MAX_OPC_PARAM_PER_ARG 1
-#endif
-#define MAX_OPC_PARAM_IARGS 7
-#define MAX_OPC_PARAM_OARGS 1
-#define MAX_OPC_PARAM_ARGS (MAX_OPC_PARAM_IARGS + MAX_OPC_PARAM_OARGS)
-
-/* A Call op needs up to 4 + 2N parameters on 32-bit archs,
- * and up to 4 + N parameters on 64-bit archs
- * (N = number of input arguments + output arguments).  */
-#define MAX_OPC_PARAM (4 + (MAX_OPC_PARAM_PER_ARG * MAX_OPC_PARAM_ARGS))
-
 #define CPU_TEMP_BUF_NLONGS 128
 #define TCG_STATIC_FRAME_SIZE  (CPU_TEMP_BUF_NLONGS * sizeof(long))
 
@@ -493,34 +479,34 @@ typedef struct TCGTempSet {
     unsigned long l[BITS_TO_LONGS(TCG_MAX_TEMPS)];
 } TCGTempSet;
 
-/* While we limit helpers to 6 arguments, for 32-bit hosts, with padding,
-   this imples a max of 6*2 (64-bit in) + 2 (64-bit out) = 14 operands.
-   There are never more than 2 outputs, which means that we can store all
-   dead + sync data within 16 bits.  */
-#define DEAD_ARG  4
-#define SYNC_ARG  1
-typedef uint16_t TCGLifeData;
+/*
+ * With 1 128-bit output, a 32-bit host requires 4 output parameters,
+ * which leaves a maximum of 28 other slots.  Which is enough for 7
+ * 128-bit operands.
+ */
+#define DEAD_ARG  (1 << 4)
+#define SYNC_ARG  (1 << 0)
+typedef uint32_t TCGLifeData;
 
-/* The layout here is designed to avoid a bitfield crossing of
-   a 32-bit boundary, which would cause GCC to add extra padding.  */
 typedef struct TCGOp {
-    TCGOpcode opc   : 8;        /*  8 */
+    TCGOpcode opc   : 8;
+    unsigned nargs  : 8;
 
     /* Parameters for this opcode.  See below.  */
-    unsigned param1 : 4;        /* 12 */
-    unsigned param2 : 4;        /* 16 */
+    unsigned param1 : 8;
+    unsigned param2 : 8;
 
     /* Lifetime data of the operands.  */
-    unsigned life   : 16;       /* 32 */
+    TCGLifeData life;
 
     /* Next and previous opcodes.  */
     QTAILQ_ENTRY(TCGOp) link;
 
-    /* Arguments for the opcode.  */
-    TCGArg args[MAX_OPC_PARAM];
-
     /* Register preferences for the output(s).  */
     TCGRegSet output_pref[2];
+
+    /* Arguments for the opcode.  */
+    TCGArg args[];
 } TCGOp;
 
 #define TCGOP_CALLI(X)    (X)->param1