mirrors/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tcg: Vary the allocation size for TCGOp

Browse Source 
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>
This commit is contained in:
Richard Henderson 2022-12-18 22:18:32 +01:00
parent d44789434b
commit cb10bc63b7
4 changed files with 47 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
accel/tcg/plugin-gen.c
View File

@ -258,12 +258,12 @@ static TCGOp *rm_ops(TCGOp *op)
static TCGOp *copy_op_nocheck(TCGOp **begin_op, TCGOp *op)
{
unsigned nargs = ARRAY_SIZE(op->args);
TCGOp *old_op = QTAILQ_NEXT(*begin_op, link);
unsigned nargs = old_op->nargs;
*begin_op = QTAILQ_NEXT(*begin_op, link);
tcg_debug_assert(*begin_op);
op = tcg_op_insert_after(tcg_ctx, op, (*begin_op)->opc, nargs);
memcpy(op->args, (*begin_op)->args, sizeof(op->args));
*begin_op = old_op;
op = tcg_op_insert_after(tcg_ctx, op, old_op->opc, nargs);
memcpy(op->args, old_op->args, sizeof(op->args[0]) * nargs);
return op;
}

2
include/exec/helper-head.h
View File

@ -133,6 +133,4 @@
#define DEF_HELPER_7(name, ret, t1, t2, t3, t4, t5, t6, t7) \
DEF_HELPER_FLAGS_7(name, 0, ret, t1, t2, t3, t4, t5, t6, t7)
/* MAX_OPC_PARAM_IARGS must be set to n if last entry is DEF_HELPER_FLAGS_n. */
#endif /* EXEC_HELPER_HEAD_H */

46
include/tcg/tcg.h
View File

@ -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

35
tcg/tcg.c
View File

@ -1513,7 +1513,12 @@ void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args)
}
}
max_args = ARRAY_SIZE(op->args);
/*
* 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).
*/
max_args = (64 / TCG_TARGET_REG_BITS) * nargs + 4;
op = tcg_emit_op(INDEX_op_call, max_args);
pi = 0;
@ -2298,19 +2303,31 @@ void tcg_remove_ops_after(TCGOp *op)
static TCGOp *tcg_op_alloc(TCGOpcode opc, unsigned nargs)
{
TCGContext *s = tcg_ctx;
TCGOp *op;
TCGOp *op = NULL;
assert(nargs < ARRAY_SIZE(op->args));
if (likely(QTAILQ_EMPTY(&s->free_ops))) {
op = tcg_malloc(sizeof(TCGOp));
} else {
op = QTAILQ_FIRST(&s->free_ops);
QTAILQ_REMOVE(&s->free_ops, op, link);
if (unlikely(!QTAILQ_EMPTY(&s->free_ops))) {
QTAILQ_FOREACH(op, &s->free_ops, link) {
if (nargs <= op->nargs) {
QTAILQ_REMOVE(&s->free_ops, op, link);
nargs = op->nargs;
goto found;
}
}
}
/* Most opcodes have 3 or 4 operands: reduce fragmentation. */
nargs = MAX(4, nargs);
op = tcg_malloc(sizeof(TCGOp) + sizeof(TCGArg) * nargs);
found:
memset(op, 0, offsetof(TCGOp, link));
op->opc = opc;
s->nb_ops++;
op->nargs = nargs;
/* Check for bitfield overflow. */
tcg_debug_assert(op->nargs == nargs);
s->nb_ops++;
return op;
}