sx/src/backend/llvm/abi.zig

const std = @import("std");
const llvm = @import("../../llvm_api.zig");
const c = llvm.c;
const ir_types = @import("../../ir/types.zig");
const emit = @import("../../ir/emit_llvm.zig");

const TypeId = ir_types.TypeId;
const LLVMEmitter = emit.LLVMEmitter;

/// C-ABI parameter coercion (architecture phase A7.1), extracted from
/// `LLVMEmitter`. A backend `*LLVMEmitter` facade: it borrows the emitter for
/// the cached LLVM handles, the IR type table, the module data layout, and the
/// IR builder. `LLVMEmitter.{abiCoerceParamType, abiCoerceParamTypeEx,
/// needsByval, materializeByvalArg}` are thin wrappers delegating here.
///
/// On ARM64 (and x86_64), the C calling convention coerces small struct
/// arguments to integers for register passing:
///   - String/slice {ptr, i64} → ptr (extract raw pointer)
///   - Small integer struct (≤ 8 bytes, non-HFA) → i64
///   - HFA (homogeneous float aggregate) → leave as-is (LLVM handles it)
pub const AbiLowering = struct {
    e: *LLVMEmitter,

    pub fn abiCoerceParamType(self: AbiLowering, ir_ty: TypeId, llvm_ty: c.LLVMTypeRef) c.LLVMTypeRef {
        return self.abiCoerceParamTypeEx(ir_ty, llvm_ty, true);
    }

    /// Same as `abiCoerceParamType` but with an explicit
    /// `is_foreign_c_api` knob. When true, sx `string` / `[]T` slices
    /// collapse to `ptr` — the libc convention where the user writes
    /// `string` to mean `char *` and the length is dropped. When
    /// false (sx-internal `callconv(.c)` like block trampolines), the
    /// full slice shape is preserved and goes through the general
    /// struct-coerce path (16-byte slice → `[2 x i64]`, lands in two
    /// registers on AArch64 — the true C ABI for a 16-byte
    /// aggregate). Without the split, sx-to-sx calls through a
    /// `(*Block, string) -> void callconv(.c)` fn-pointer mismatched
    /// the caller's `{ptr, i64}` value against the trampoline's
    /// collapsed `ptr` param.
    pub fn abiCoerceParamTypeEx(self: AbiLowering, ir_ty: TypeId, llvm_ty: c.LLVMTypeRef, is_foreign_c_api: bool) c.LLVMTypeRef {
        if (is_foreign_c_api) {
            if (ir_ty == .string) return self.e.cached_ptr;
            if (!ir_ty.isBuiltin()) {
                const info = self.e.ir_mod.types.get(ir_ty);
                if (info == .slice) return self.e.cached_ptr;
            }
        }

        // WASM32: usize/isize are pointer-sized (i32 on wasm32).
        // Other integer types (s64, u64) keep their declared size — they represent
        // genuinely 64-bit values (SDL_WindowFlags, timestamps, etc.).
        if (self.e.target_config.isWasm32()) {
            if (ir_ty == .usize or ir_ty == .isize) return self.e.cached_i32;
            return llvm_ty;
        }

        // Only coerce struct types
        if (c.LLVMGetTypeKind(llvm_ty) != c.LLVMStructTypeKind) return llvm_ty;

        // Check if it's an HFA (all float or all double fields) — leave as-is
        const n_fields = c.LLVMCountStructElementTypes(llvm_ty);
        if (n_fields >= 1 and n_fields <= 4) {
            var all_float = true;
            var all_double = true;
            var fi: c_uint = 0;
            while (fi < n_fields) : (fi += 1) {
                const ft = c.LLVMStructGetTypeAtIndex(llvm_ty, fi);
                const fk = c.LLVMGetTypeKind(ft);
                if (fk != c.LLVMFloatTypeKind) all_float = false;
                if (fk != c.LLVMDoubleTypeKind) all_double = false;
            }
            if (all_float or all_double) return llvm_ty;
        }

        // Small struct (≤ 8 bytes) → coerce to i64
        const size = c.LLVMABISizeOfType(
            c.LLVMGetModuleDataLayout(self.e.llvm_module),
            llvm_ty,
        );
        if (size <= 8) return self.e.cached_i64;

        // Medium struct (9-16 bytes) → coerce to [2 x i64]
        if (size <= 16) {
            return c.LLVMArrayType2(self.e.cached_i64, 2);
        }

        // Large composite (> 16 bytes) → pass by reference: ptr + byval(<T>) at
        // the call/sig sites. LLVM's AArch64/x86_64 backend lowers byval to
        // the right ABI sequence (caller copy + indirect arg).
        return self.e.cached_ptr;
    }

    pub fn needsByval(self: AbiLowering, ir_ty: TypeId, raw_llvm_ty: c.LLVMTypeRef) bool {
        if (self.e.target_config.isWasm32()) return false;
        if (ir_ty == .string) return false;
        if (!ir_ty.isBuiltin()) {
            const info = self.e.ir_mod.types.get(ir_ty);
            if (info == .slice) return false;
        }
        if (c.LLVMGetTypeKind(raw_llvm_ty) != c.LLVMStructTypeKind) return false;
        const n = c.LLVMCountStructElementTypes(raw_llvm_ty);
        if (n >= 1 and n <= 4) {
            var all_f = true;
            var all_d = true;
            var i: c_uint = 0;
            while (i < n) : (i += 1) {
                const ft = c.LLVMStructGetTypeAtIndex(raw_llvm_ty, i);
                const fk = c.LLVMGetTypeKind(ft);
                if (fk != c.LLVMFloatTypeKind) all_f = false;
                if (fk != c.LLVMDoubleTypeKind) all_d = false;
            }
            if (all_f or all_d) return false;
        }
        const size = c.LLVMABISizeOfType(c.LLVMGetModuleDataLayout(self.e.llvm_module), raw_llvm_ty);
        return size > 16;
    }

    pub fn materializeByvalArg(self: AbiLowering, val: c.LLVMValueRef, struct_ty: c.LLVMTypeRef) c.LLVMValueRef {
        const tmp = c.LLVMBuildAlloca(self.e.builder, struct_ty, "byval.tmp");
        _ = c.LLVMBuildStore(self.e.builder, val, tmp);
        return tmp;
    }
};