tcg: Add TCG_CALL_{RET,ARG}_BY_REF

These will be used by some hosts, both 32 and 64-bit, to pass and
return i128.  Not yet used, because allocation is not yet enabled.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2022-10-31 09:22:59 +11:00
parent 6a6d772e30
commit 313bdea84d
2 changed files with 135 additions and 3 deletions

View File

@ -36,6 +36,7 @@
*/
typedef enum {
TCG_CALL_RET_NORMAL, /* by registers */
TCG_CALL_RET_BY_REF, /* for i128, by reference */
} TCGCallReturnKind;
typedef enum {
@ -44,6 +45,8 @@ typedef enum {
TCG_CALL_ARG_EXTEND, /* for i32, as a sign/zero-extended i64 */
TCG_CALL_ARG_EXTEND_U, /* ... as a zero-extended i64 */
TCG_CALL_ARG_EXTEND_S, /* ... as a sign-extended i64 */
TCG_CALL_ARG_BY_REF, /* for i128, by reference, first */
TCG_CALL_ARG_BY_REF_N, /* ... by reference, subsequent */
} TCGCallArgumentKind;
typedef struct TCGCallArgumentLoc {

135
tcg/tcg.c
View File

@ -104,8 +104,7 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg1,
static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg);
static void tcg_out_movi(TCGContext *s, TCGType type,
TCGReg ret, tcg_target_long arg);
static void tcg_out_addi_ptr(TCGContext *s, TCGReg, TCGReg, tcg_target_long)
__attribute__((unused));
static void tcg_out_addi_ptr(TCGContext *s, TCGReg, TCGReg, tcg_target_long);
static void tcg_out_exit_tb(TCGContext *s, uintptr_t arg);
static void tcg_out_goto_tb(TCGContext *s, int which);
static void tcg_out_op(TCGContext *s, TCGOpcode opc,
@ -683,6 +682,38 @@ static void layout_arg_normal_n(TCGCumulativeArgs *cum,
cum->arg_slot += n;
}
static void layout_arg_by_ref(TCGCumulativeArgs *cum, TCGHelperInfo *info)
{
TCGCallArgumentLoc *loc = &info->in[cum->info_in_idx];
int n = 128 / TCG_TARGET_REG_BITS;
/* The first subindex carries the pointer. */
layout_arg_1(cum, info, TCG_CALL_ARG_BY_REF);
/*
* The callee is allowed to clobber memory associated with
* structure pass by-reference. Therefore we must make copies.
* Allocate space from "ref_slot", which will be adjusted to
* follow the parameters on the stack.
*/
loc[0].ref_slot = cum->ref_slot;
/*
* Subsequent words also go into the reference slot, but
* do not accumulate into the regular arguments.
*/
for (int i = 1; i < n; ++i) {
loc[i] = (TCGCallArgumentLoc){
.kind = TCG_CALL_ARG_BY_REF_N,
.arg_idx = cum->arg_idx,
.tmp_subindex = i,
.ref_slot = cum->ref_slot + i,
};
}
cum->info_in_idx += n;
cum->ref_slot += n;
}
static void init_call_layout(TCGHelperInfo *info)
{
int max_reg_slots = ARRAY_SIZE(tcg_target_call_iarg_regs);
@ -718,6 +749,14 @@ static void init_call_layout(TCGHelperInfo *info)
case TCG_CALL_RET_NORMAL:
assert(info->nr_out <= ARRAY_SIZE(tcg_target_call_oarg_regs));
break;
case TCG_CALL_RET_BY_REF:
/*
* Allocate the first argument to the output.
* We don't need to store this anywhere, just make it
* unavailable for use in the input loop below.
*/
cum.arg_slot = 1;
break;
default:
qemu_build_not_reached();
}
@ -796,6 +835,9 @@ static void init_call_layout(TCGHelperInfo *info)
case TCG_CALL_ARG_NORMAL:
layout_arg_normal_n(&cum, info, 128 / TCG_TARGET_REG_BITS);
break;
case TCG_CALL_ARG_BY_REF:
layout_arg_by_ref(&cum, info);
break;
default:
qemu_build_not_reached();
}
@ -811,7 +853,39 @@ static void init_call_layout(TCGHelperInfo *info)
assert(cum.info_in_idx <= ARRAY_SIZE(info->in));
/* Validate the backend has enough argument space. */
assert(cum.arg_slot <= max_reg_slots + max_stk_slots);
assert(cum.ref_slot <= max_stk_slots);
/*
* Relocate the "ref_slot" area to the end of the parameters.
* Minimizing this stack offset helps code size for x86,
* which has a signed 8-bit offset encoding.
*/
if (cum.ref_slot != 0) {
int ref_base = 0;
if (cum.arg_slot > max_reg_slots) {
int align = __alignof(Int128) / sizeof(tcg_target_long);
ref_base = cum.arg_slot - max_reg_slots;
if (align > 1) {
ref_base = ROUND_UP(ref_base, align);
}
}
assert(ref_base + cum.ref_slot <= max_stk_slots);
if (ref_base != 0) {
for (int i = cum.info_in_idx - 1; i >= 0; --i) {
TCGCallArgumentLoc *loc = &info->in[i];
switch (loc->kind) {
case TCG_CALL_ARG_BY_REF:
case TCG_CALL_ARG_BY_REF_N:
loc->ref_slot += ref_base;
break;
default:
break;
}
}
}
}
}
static int indirect_reg_alloc_order[ARRAY_SIZE(tcg_target_reg_alloc_order)];
@ -1740,6 +1814,8 @@ void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args)
switch (loc->kind) {
case TCG_CALL_ARG_NORMAL:
case TCG_CALL_ARG_BY_REF:
case TCG_CALL_ARG_BY_REF_N:
op->args[pi++] = temp_arg(ts);
break;
@ -4411,6 +4487,27 @@ static void load_arg_normal(TCGContext *s, const TCGCallArgumentLoc *l,
}
}
static void load_arg_ref(TCGContext *s, int arg_slot, TCGReg ref_base,
intptr_t ref_off, TCGRegSet *allocated_regs)
{
TCGReg reg;
int stk_slot = arg_slot - ARRAY_SIZE(tcg_target_call_iarg_regs);
if (stk_slot < 0) {
reg = tcg_target_call_iarg_regs[arg_slot];
tcg_reg_free(s, reg, *allocated_regs);
tcg_out_addi_ptr(s, reg, ref_base, ref_off);
tcg_regset_set_reg(*allocated_regs, reg);
} else {
reg = tcg_reg_alloc(s, tcg_target_available_regs[TCG_TYPE_PTR],
*allocated_regs, 0, false);
tcg_out_addi_ptr(s, reg, ref_base, ref_off);
tcg_out_st(s, TCG_TYPE_PTR, reg, TCG_REG_CALL_STACK,
TCG_TARGET_CALL_STACK_OFFSET
+ stk_slot * sizeof(tcg_target_long));
}
}
static void tcg_reg_alloc_call(TCGContext *s, TCGOp *op)
{
const int nb_oargs = TCGOP_CALLO(op);
@ -4434,6 +4531,16 @@ static void tcg_reg_alloc_call(TCGContext *s, TCGOp *op)
case TCG_CALL_ARG_EXTEND_S:
load_arg_normal(s, loc, ts, &allocated_regs);
break;
case TCG_CALL_ARG_BY_REF:
load_arg_stk(s, loc->ref_slot, ts, allocated_regs);
load_arg_ref(s, loc->arg_slot, TCG_REG_CALL_STACK,
TCG_TARGET_CALL_STACK_OFFSET
+ loc->ref_slot * sizeof(tcg_target_long),
&allocated_regs);
break;
case TCG_CALL_ARG_BY_REF_N:
load_arg_stk(s, loc->ref_slot, ts, allocated_regs);
break;
default:
g_assert_not_reached();
}
@ -4465,6 +4572,19 @@ static void tcg_reg_alloc_call(TCGContext *s, TCGOp *op)
save_globals(s, allocated_regs);
}
/*
* If the ABI passes a pointer to the returned struct as the first
* argument, load that now. Pass a pointer to the output home slot.
*/
if (info->out_kind == TCG_CALL_RET_BY_REF) {
TCGTemp *ts = arg_temp(op->args[0]);
if (!ts->mem_allocated) {
temp_allocate_frame(s, ts);
}
load_arg_ref(s, 0, ts->mem_base->reg, ts->mem_offset, &allocated_regs);
}
tcg_out_call(s, tcg_call_func(op), info);
/* Assign output registers and emit moves if needed. */
@ -4481,6 +4601,15 @@ static void tcg_reg_alloc_call(TCGContext *s, TCGOp *op)
ts->mem_coherent = 0;
}
break;
case TCG_CALL_RET_BY_REF:
/* The callee has performed a write through the reference. */
for (i = 0; i < nb_oargs; i++) {
TCGTemp *ts = arg_temp(op->args[i]);
ts->val_type = TEMP_VAL_MEM;
}
break;
default:
g_assert_not_reached();
}