tcg/optimize: Split out fold_call

Calls are special in that they have a variable number
of arguments, and need to be able to clobber globals.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Luis Pires <luis.pires@eldorado.org.br>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2021-08-24 08:17:08 -07:00
parent 8774dded02
commit 5cf32be7d8
1 changed files with 41 additions and 22 deletions

View File

@ -624,10 +624,42 @@ static void copy_propagate(OptContext *ctx, TCGOp *op,
}
}
static bool fold_call(OptContext *ctx, TCGOp *op)
{
TCGContext *s = ctx->tcg;
int nb_oargs = TCGOP_CALLO(op);
int nb_iargs = TCGOP_CALLI(op);
int flags, i;
init_arguments(ctx, op, nb_oargs + nb_iargs);
copy_propagate(ctx, op, nb_oargs, nb_iargs);
/* If the function reads or writes globals, reset temp data. */
flags = tcg_call_flags(op);
if (!(flags & (TCG_CALL_NO_READ_GLOBALS | TCG_CALL_NO_WRITE_GLOBALS))) {
int nb_globals = s->nb_globals;
for (i = 0; i < nb_globals; i++) {
if (test_bit(i, ctx->temps_used.l)) {
reset_ts(&ctx->tcg->temps[i]);
}
}
}
/* Reset temp data for outputs. */
for (i = 0; i < nb_oargs; i++) {
reset_temp(op->args[i]);
}
/* Stop optimizing MB across calls. */
ctx->prev_mb = NULL;
return true;
}
/* Propagate constants and copies, fold constant expressions. */
void tcg_optimize(TCGContext *s)
{
int nb_temps, nb_globals, i;
int nb_temps, i;
TCGOp *op, *op_next;
OptContext ctx = { .tcg = s };
@ -637,8 +669,6 @@ void tcg_optimize(TCGContext *s)
available through the doubly linked circular list. */
nb_temps = s->nb_temps;
nb_globals = s->nb_globals;
for (i = 0; i < nb_temps; ++i) {
s->temps[i].state_ptr = NULL;
}
@ -647,17 +677,17 @@ void tcg_optimize(TCGContext *s)
uint64_t z_mask, partmask, affected, tmp;
int nb_oargs, nb_iargs;
TCGOpcode opc = op->opc;
const TCGOpDef *def = &tcg_op_defs[opc];
const TCGOpDef *def;
/* Count the arguments, and initialize the temps that are
going to be used */
/* Calls are special. */
if (opc == INDEX_op_call) {
nb_oargs = TCGOP_CALLO(op);
nb_iargs = TCGOP_CALLI(op);
} else {
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
fold_call(&ctx, op);
continue;
}
def = &tcg_op_defs[opc];
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
init_arguments(&ctx, op, nb_oargs + nb_iargs);
copy_propagate(&ctx, op, nb_oargs, nb_iargs);
@ -1549,16 +1579,6 @@ void tcg_optimize(TCGContext *s)
if (def->flags & TCG_OPF_BB_END) {
memset(&ctx.temps_used, 0, sizeof(ctx.temps_used));
} else {
if (opc == INDEX_op_call &&
!(tcg_call_flags(op)
& (TCG_CALL_NO_READ_GLOBALS | TCG_CALL_NO_WRITE_GLOBALS))) {
for (i = 0; i < nb_globals; i++) {
if (test_bit(i, ctx.temps_used.l)) {
reset_ts(&s->temps[i]);
}
}
}
for (i = 0; i < nb_oargs; i++) {
reset_temp(op->args[i]);
/* Save the corresponding known-zero bits mask for the
@ -1599,7 +1619,6 @@ void tcg_optimize(TCGContext *s)
case INDEX_op_qemu_st_i32:
case INDEX_op_qemu_st8_i32:
case INDEX_op_qemu_st_i64:
case INDEX_op_call:
/* Opcodes that touch guest memory stop the optimization. */
ctx.prev_mb = NULL;
break;