free

fn free(ctx: *anyopaque, memory: []u8, alignment: Alignment, ra: usize) void {
    const s: *SafeAllocator = @ptrCast(@alignCast(ctx));
    const f: *AllocFooter = .of(memory);
    f.startModify(.freeing, s, .{ .memory = memory, .alignment = alignment });

    if (s.isLarge(memory.len, alignment)) {
        @branchHint(.unlikely);

        const t = s.acquireThread();
        freeAllocEntry(t, f.extended().container.large_entry);
        t.mutex.unlock();
        s.backing.rawFree(
            memory.ptr[0..AllocFooter.allocLenLarge(s, memory.len)],
            AllocFooter.allocAlign(alignment),
            ra,
        );
        return;
    }

    const b: *Bucket = .of(s, memory.ptr);
    s.overwriteFreed(memory);
    captureStackTrace(f.freeTrace(s), ra);

    // Fence the alloc count before setting `f.modify` to `.freed`.
    // This way, if another thread is waiting for the trace to become
    // available, it will not be racing with us to see this `.release`.
    //
    // The below alloc count update can not be moved up here instead
    // since that would allow another thread to see the `.freeing` state.
    b.alloc_count.fenceAcqRel();

    // If this result is different than .freeing, then some other thread
    // is in the process of panicing. So, just ignore it. (This is also
    // the reasoning for several other places.)
    _ = @atomicRmw(
        AllocFooter.Modify,
        &f.modify,
        .Xchg,
        .storedXor(.freed, &f.modify),
        .monotonic,
    );

    const prev_count = @atomicRmw(
        Bucket.AllocCount,
        &b.alloc_count,
        .Sub,
        .{ .filling = false, .n = 1 },
        .acq_rel,
    );

    if (prev_count.n - 1 == 0 and !prev_count.filling) {
        @branchHint(.unlikely);
        const t = s.acquireThread();
        freeAllocEntry(t, b.entry);
        t.mutex.unlock();
        b.check(s);
        s.backing.rawFree(b.bytes(s), @fromBackingInt(@intCast(s.bucket_size_log2)), ra);
    }
}