#include <algorithm>
#include <array>
#include <bitset>
#include <cassert>
#include <chrono>
#include <cmath>
#include <complex>
#include <deque>
#include <forward_list>
#include <fstream>
#include <functional>
#include <iomanip>
#include <ios>
#include <iostream>
#include <limits>
#include <list>
#include <map>
#include <memory>
#include <numeric>
#include <optional>
#include <queue>
#include <random>
#include <set>
#include <sstream>
#include <stack>
#include <string>
#include <tuple>
#include <type_traits>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
using namespace std;
using lint = long long;
using pint = pair<int, int>;
using plint = pair<lint, lint>;
struct fast_ios { fast_ios(){ cin.tie(nullptr), ios::sync_with_stdio(false), cout << fixed << setprecision(20); }; } fast_ios_;
#define ALL(x) (x).begin(), (x).end()
#define FOR(i, begin, end) for(int i=(begin),i##_end_=(end);i<i##_end_;i++)
#define IFOR(i, begin, end) for(int i=(end)-1,i##_begin_=(begin);i>=i##_begin_;i--)
#define REP(i, n) FOR(i,0,n)
#define IREP(i, n) IFOR(i,0,n)
template <typename T> bool chmax(T &m, const T q) { return m < q ? (m = q, true) : false; }
template <typename T> bool chmin(T &m, const T q) { return m > q ? (m = q, true) : false; }
const std::vector<std::pair<int, int>> grid_dxs{{1, 0}, {-1, 0}, {0, 1}, {0, -1}};
int floor_lg(long long x) { return x <= 0 ? -1 : 63 - __builtin_clzll(x); }
template <class T1, class T2> T1 floor_div(T1 num, T2 den) { return (num > 0 ? num / den : -((-num + den - 1) / den)); }
template <class T1, class T2> std::pair<T1, T2> operator+(const std::pair<T1, T2> &l, const std::pair<T1, T2> &r) { return std::make_pair(l.first + r.first, l.second + r.second); }
template <class T1, class T2> std::pair<T1, T2> operator-(const std::pair<T1, T2> &l, const std::pair<T1, T2> &r) { return std::make_pair(l.first - r.first, l.second - r.second); }
template <class T> std::vector<T> sort_unique(std::vector<T> vec) { sort(vec.begin(), vec.end()), vec.erase(unique(vec.begin(), vec.end()), vec.end()); return vec; }
template <class T> int arglb(const std::vector<T> &v, const T &x) { return std::distance(v.begin(), std::lower_bound(v.begin(), v.end(), x)); }
template <class T> int argub(const std::vector<T> &v, const T &x) { return std::distance(v.begin(), std::upper_bound(v.begin(), v.end(), x)); }
template <class IStream, class T> IStream &operator>>(IStream &is, std::vector<T> &vec) { for (auto &v : vec) is >> v; return is; }

template <class OStream, class T> OStream &operator<<(OStream &os, const std::vector<T> &vec);
template <class OStream, class T, size_t sz> OStream &operator<<(OStream &os, const std::array<T, sz> &arr);
template <class OStream, class T, class TH> OStream &operator<<(OStream &os, const std::unordered_set<T, TH> &vec);
template <class OStream, class T, class U> OStream &operator<<(OStream &os, const pair<T, U> &pa);
template <class OStream, class T> OStream &operator<<(OStream &os, const std::deque<T> &vec);
template <class OStream, class T> OStream &operator<<(OStream &os, const std::set<T> &vec);
template <class OStream, class T> OStream &operator<<(OStream &os, const std::multiset<T> &vec);
template <class OStream, class T> OStream &operator<<(OStream &os, const std::unordered_multiset<T> &vec);
template <class OStream, class T, class U> OStream &operator<<(OStream &os, const std::pair<T, U> &pa);
template <class OStream, class TK, class TV> OStream &operator<<(OStream &os, const std::map<TK, TV> &mp);
template <class OStream, class TK, class TV, class TH> OStream &operator<<(OStream &os, const std::unordered_map<TK, TV, TH> &mp);
template <class OStream, class... T> OStream &operator<<(OStream &os, const std::tuple<T...> &tpl);

template <class OStream, class T> OStream &operator<<(OStream &os, const std::vector<T> &vec) { os << '['; for (auto v : vec) os << v << ','; os << ']'; return os; }
template <class OStream, class T, size_t sz> OStream &operator<<(OStream &os, const std::array<T, sz> &arr) { os << '['; for (auto v : arr) os << v << ','; os << ']'; return os; }
template <class... T> std::istream &operator>>(std::istream &is, std::tuple<T...> &tpl) { std::apply([&is](auto &&... args) { ((is >> args), ...);}, tpl); return is; }
template <class OStream, class... T> OStream &operator<<(OStream &os, const std::tuple<T...> &tpl) { os << '('; std::apply([&os](auto &&... args) { ((os << args << ','), ...);}, tpl); return os << ')'; }
template <class OStream, class T, class TH> OStream &operator<<(OStream &os, const std::unordered_set<T, TH> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <class OStream, class T> OStream &operator<<(OStream &os, const std::deque<T> &vec) { os << "deq["; for (auto v : vec) os << v << ','; os << ']'; return os; }
template <class OStream, class T> OStream &operator<<(OStream &os, const std::set<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <class OStream, class T> OStream &operator<<(OStream &os, const std::multiset<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <class OStream, class T> OStream &operator<<(OStream &os, const std::unordered_multiset<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <class OStream, class T, class U> OStream &operator<<(OStream &os, const std::pair<T, U> &pa) { return os << '(' << pa.first << ',' << pa.second << ')'; }
template <class OStream, class TK, class TV> OStream &operator<<(OStream &os, const std::map<TK, TV> &mp) { os << '{'; for (auto v : mp) os << v.first << "=>" << v.second << ','; os << '}'; return os; }
template <class OStream, class TK, class TV, class TH> OStream &operator<<(OStream &os, const std::unordered_map<TK, TV, TH> &mp) { os << '{'; for (auto v : mp) os << v.first << "=>" << v.second << ','; os << '}'; return os; }
#ifdef HITONANODE_LOCAL
const string COLOR_RESET = "\033[0m", BRIGHT_CYAN = "\033[1;36m", NORMAL_FAINT = "\033[0;2m";
#define dbg(x) std::cerr << BRIGHT_CYAN << #x << COLOR_RESET << " = " << (x) << NORMAL_FAINT << " (L" << __LINE__ << ") " << __FILE__ << COLOR_RESET << std::endl
#define dbgif(cond, x) ((cond) ? std::cerr << BRIGHT_CYAN << #x << COLOR_RESET << " = " << (x) << NORMAL_FAINT << " (L" << __LINE__ << ") " << __FILE__ << COLOR_RESET << std::endl : std::cerr)
#else
#define dbg(x) ((void)0)
#define dbgif(cond, x) ((void)0)
#endif


vector<int> Solve(int p, vector<int> A) {
    const int N = A.size();

    // if (N == 2) return {0, 1};

    vector<int> ret(N, -1);
    vector<int> used(N);

    map<int, vector<vector<int>>> mp;
    REP(i, N) {
        if (used.at(i)) continue;

        vector<int> st;
        for (int now = i;; now = A.at(now)) {
            if (!chmax(used.at(now), 1)) break;
            st.push_back(now);
        }
        // dbg(st);
        mp[st.size()].push_back(st);


        // if (st.size() == 2) {
        //     if (pairs.size()) {
        //         const auto a = pairs.back().first, b = pairs.back().second;
        //         pairs.pop_back();
        //         const int c = st.at(0), d = st.at(1);
        //         ret[a] = c;
        //         ret[c] = b;
        //         ret[b] = d;
        //         ret[d] = a;
        //     } else {
        //         pairs.emplace_back(st.at(0), st.at(1));
        //     }
        // } else if (st.size() == 1) {
        //     ret.at(st.at(0)) = st.at(0);
        // } else if (st.size() == 4) {
        //     const int 
        // } else {
        //     const int stride = p * 2 % st.size();
        //     vector<int> permute(st.size(), -1);
        //     for (int i = 0; i < (int)st.size(); ++i) {
        //         // permute.push_back(st.at(lint(i) * stride % st.size()));
        //         permute.at(lint(i) * stride % st.size()) = st.at(i);
        //     }
        //     REP(i, permute.size()) {
        //         ret.at(permute.at(i)) = permute.at((i + 1) % permute.size());
        //     }
        // }
    }
    dbg(mp);

    for (auto [len, sts] : mp) {
        if (len % 2) {
            const int stride = p * 2 % len;
            for (auto st : sts) {
                vector<int> permute(st.size(), -1);
                for (int i = 0; i < (int)st.size(); ++i) {
                    permute.at(lint(i) * stride % st.size()) = st.at(i);
                }
                REP(i, permute.size()) {
                    ret.at(permute.at(i)) = permute.at((i + 1) % permute.size());
                }
            }
        } else {
            while (sts.size() > 1) {
                const auto a = sts.back();
                sts.pop_back();
                const auto b = sts.back();
                sts.pop_back();

                const int stride = p % len;

                vector<int> pa(a.size(), -1), pb(b.size(), -1);
                for (int i = 0; i < (int)a.size(); ++i) {
                    pa.at(lint(i) * stride % a.size()) = a.at(i);
                }

                for (int i = 0; i < (int)b.size(); ++i) {
                    pb.at(lint(i) * stride % b.size()) = b.at(i);
                }

                vector<int> permute;
                REP(i, a.size()) permute.push_back(pa.at(i)), permute.push_back(pb.at(i));

                REP(i, permute.size()) {
                    ret.at(permute.at(i)) = permute.at((i + 1) % permute.size());
                }
            }

            if (sts.size()) {
                assert(sts.size() == 1);
                const auto st = sts.back();

                const int stride = p * 2 % (len - 1);

                vector<int> permute(st.size() - 1, -1);
                REP(i, st.size() - 1) {
                    permute.at(lint(i) * stride % (st.size() - 1)) = st.at(i);
                }

                REP(i, permute.size()) {
                    ret.at(permute.at(i)) = permute.at((i + 1) % permute.size());
                }

                const int r = (p * 2 - 1) % permute.size();
                ret.at(st.back()) = permute.at((permute.size() - r) % permute.size());
            }
        }
    }

    return ret;
}


int main() {
    int T;
    cin >> T;
    while (T--) {
        int N, p;
        cin >> N >> p;
        vector<int> A(N);
        for (auto &a : A) cin >> a, --a;
        dbg(make_tuple(p, A));

        const auto ret = Solve(p, A);
        for (auto e : ret) cout << e + 1 << ' ';
        cout << '\n';
    }
}