view release on metacpan or  search on metacpan

infix/src/arch/aarch64/abi_arm64.c  view on Meta::CPAN

/**
 * Copyright (c) 2025 Sanko Robinson
 *
 * This source code is dual-licensed under the Artistic License 2.0 or the MIT License.
 * You may choose to use this code under the terms of either license.
 *
 * SPDX-License-Identifier: (Artistic-2.0 OR MIT)
 *
 * The documentation blocks within this file are licensed under the
 * Creative Commons Attribution 4.0 International License (CC BY 4.0).
 *
 * SPDX-License-Identifier: CC-BY-4.0
 */
/**
 * @file abi_arm64.c
 * @brief Implements the FFI logic for the AArch64 (ARM64) architecture.
 * @ingroup internal_abi_aarch64
 *
 * @internal
 * This file provides the concrete implementation of the `infix_forward_abi_spec`
 * and `infix_reverse_abi_spec` for the ARM64 architecture. It primarily follows
 * the standard "Procedure Call Standard for the ARM 64-bit Architecture" (AAPCS64),
 * but also contains critical conditional logic to handle deviations for specific
 * platforms like Apple macOS and Windows on ARM.
 *
 * @section aapcs64_rules Key AAPCS64 Rules Implemented
 *
 * - **Register Usage:**
 *   - The first 8 integer/pointer arguments are passed in GPRs (X0-X7).
 *   - The first 8 floating-point/vector arguments are passed in VPRs (V0-V7).
 *
 * - **Homogeneous Floating-point Aggregates (HFAs):** Structs or arrays composed
 *   entirely of 1 to 4 identical floating-point types (`float` or `double`) are
 *   passed in consecutive VPRs.
 *
 * - **Return Values:**
 *   - Aggregates up to 16 bytes are returned in registers (GPRs and/or VPRs).
 *   - Larger aggregates are returned via a hidden pointer passed by the caller
 *     in the dedicated "indirect result location register", `X8`.
 *
 * @section platform_deviations Platform-Specific Deviations
 *
 * - **Variadic Calls (Apple macOS):** All variadic arguments are passed on the
 *   stack. Arguments smaller than 8 bytes are promoted to fill 8-byte stack slots.
 *
 * - **Variadic Calls (Windows on ARM):** The HFA rule is disabled for variadic
 *   arguments. Floating-point scalars are passed in GPRs, not VPRs.
 *
 * - **16-Byte Argument Alignment:**
 *   - **Standard/macOS:** 16-byte aggregates passed in GPRs must start in an
 *     even-numbered register (X0, X2, X4, X6).
 *   - **macOS Exception:** `__int128_t` does NOT require even-GPR alignment.
 *   - **Windows Exception:** Variadic 16-byte aggregates do NOT require even-GPR alignment.
 * @endinternal
 */
#include "arch/aarch64/abi_arm64_common.h"
#include "arch/aarch64/abi_arm64_emitters.h"
#include "common/infix_internals.h"
#include "common/utility.h"
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
/** @internal The General-Purpose Registers used for the first 8 integer/pointer arguments. */
static const arm64_gpr GPR_ARGS[] = {X0_REG, X1_REG, X2_REG, X3_REG, X4_REG, X5_REG, X6_REG, X7_REG};
/** @internal The SIMD/Floating-Point Registers used for the first 8 float/double/vector arguments. */
static const arm64_vpr VPR_ARGS[] = {V0_REG, V1_REG, V2_REG, V3_REG, V4_REG, V5_REG, V6_REG, V7_REG};
/** @internal The total number of GPRs available for argument passing. */
#define NUM_GPR_ARGS 8
/** @internal The total number of VPRs available for argument passing. */
#define NUM_VPR_ARGS 8
/** @internal A safe limit on the number of fields to classify to prevent DoS from exponential complexity. */
#define MAX_AGGREGATE_FIELDS_TO_CLASSIFY 32

//
static bool is_hfa(const infix_type * type, const infix_type ** base_type);

/** @internal The v-table of AArch64 functions for generating forward trampolines. */
static infix_status prepare_forward_call_frame_arm64(infix_arena_t * arena,
                                                     infix_call_frame_layout ** out_layout,
                                                     infix_type * ret_type,
                                                     infix_type ** arg_types,
                                                     size_t num_args,
                                                     size_t num_fixed_args,
                                                     void * target_fn);
static infix_status generate_forward_prologue_arm64(code_buffer * buf, infix_call_frame_layout * layout);
static infix_status generate_forward_argument_moves_arm64(code_buffer * buf,
                                                          infix_call_frame_layout * layout,
                                                          infix_type ** arg_types,
                                                          size_t num_args,
                                                          c23_maybe_unused size_t num_fixed_args);
static infix_status generate_forward_call_instruction_arm64(code_buffer *, infix_call_frame_layout *);
static infix_status generate_forward_epilogue_arm64(code_buffer * buf,
                                                    infix_call_frame_layout * layout,
                                                    infix_type * ret_type);
const infix_forward_abi_spec g_arm64_forward_spec = {
    .prepare_forward_call_frame = prepare_forward_call_frame_arm64,
    .generate_forward_prologue = generate_forward_prologue_arm64,
    .generate_forward_argument_moves = generate_forward_argument_moves_arm64,
    .generate_forward_call_instruction = generate_forward_call_instruction_arm64,
    .generate_forward_epilogue = generate_forward_epilogue_arm64};