// rt/malloc.ww — bump allocator over 2MiB chunks. Archived into
// libwwrt.a, compiled standalone with bare symbols, like rt/ensure.ww.
// Under strict-package (#24a) it declares `package rt;` (matching its
// directory); the export's link name stays bare via its own
// @symbol("rt_malloc").
//
// WHY bump, replacing the page-per-call mmap (rt_segmalloc, ex-rt_malloc):
// the old rt_malloc page-rounded every request, so a 32-72B node cost a
// whole 4KiB page. w6a/w6c emit ~4 such nodes per .s line; a 145K-line
// assembly burned ~625K pages (~2.5GB) vs C w6a's 24MB. Packing nodes
// into shared chunks collapses that to the live set. (task #8)
//
// Mirrors Hare rt::malloc's chunk-bump (ref/hare/rt/malloc.ha:52-66,
// CHUNKSZ :24, ALIGN :14), minus the bin/freelist machinery — that
// exists only to support free, which ww does not have.
//
// Zero-init is preserved: every byte handed out is fresh from
// MAP_ANONYMOUS (kernel-zeroed) and never reused, so alloc(T{})'s
// zero-fill still holds. Lazy first chunk falls out of cur=rem=0.
package rt;

def CHUNKSZ: u64 = 2097152u64;	// 1<<21, ref/hare/rt/malloc.ha:24
def ALIGN:   u64 = 16u64;	// ref/hare/rt/malloc.ha:14

@symbol("rt_segmalloc") fn segmalloc(n: u64) *void;

let cur: u64 = 0u64;
let rem: u64 = 0u64;

@symbol("rt_malloc") export fn rt_malloc(n: u64) *void = {
	let need: u64 = (n + (ALIGN - 1u64)) & ~(ALIGN - 1u64);
	// Oversized requests bypass the chunk so one huge alloc can't
	// strand most of a chunk (ref/hare/rt/malloc.ha:38).
	if (need > CHUNKSZ) { return segmalloc(need); };
	if (rem < need) {
		let c: *void = segmalloc(CHUNKSZ);
		// mmap failure: keep the nomem null contract that the
		// alloc-builtin `!`/`?` lowering checks.
		if (c == nil) { return nil; };
		cur = c: u64;
		rem = CHUNKSZ;
	};
	let p: u64 = cur;
	cur += need;
	rem -= need;
	return p: *void;
};