#pragma GCC target("avx2")
#pragma GCC optimize("O3")
#pragma GCC optimize("unroll-loops")

#include <algorithm>
#include <atcoder/all>
#include <bitset>
#include <cassert>
#include <cmath>
#include <ctime>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <random>
#include <set>
#include <stack>
#include <string>
#include <tuple>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
using namespace std;
using namespace atcoder;
typedef long long ll;
#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define repr(i, n) for (int i = (int)(n)-1; i >= 0; i--)
#define repk(i, k, n) for (int i = k; i < (int)(n); i++)
#define all(v) v.begin(), v.end()
#define mod1 1000000007
#define mod2 998244353
#define mod3 100000007
#define vi vector<int>
#define vs vector<string>
#define vc vector<char>
#define vl vector<ll>
#define vb vector<bool>
#define vvi vector<vector<int>>
#define vvc vector<vector<char>>
#define vvl vector<vector<ll>>
#define vvb vector<vector<bool>>
#define vvvi vector<vector<vector<int>>>
#define vvvl vector<vector<vector<ll>>>
#define pii pair<int, int>
#define pil pair<int, ll>
#define pli pair<ll, int>
#define pll pair<ll, ll>
#define vpii vector<pair<int, int>>
#define vpll vector<pair<ll, ll>>
#define vvpii vector<vector<pair<int, int>>>
#define vvpll vector<vector<pair<ll, ll>>>

using mint = modint998244353;

template <typename T>
void debug(T e) {
    cerr << e << endl;
}

template <typename T>
void debug(vector<T> &v) {
    rep(i, v.size()) { cerr << v[i] << " "; }
    cerr << endl;
}

template <typename T>
void debug(vector<vector<T>> &v) {
    rep(i, v.size()) {
        rep(j, v[i].size()) { cerr << v[i][j] << " "; }
        cerr << endl;
    }
}

template <typename T>
void debug(vector<pair<T, T>> &v) {
    rep(i, v.size()) { cerr << v[i].first << " " << v[i].second << endl; }
}

template <typename T>
void debug(set<T> &st) {
    for (auto itr = st.begin(); itr != st.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(multiset<T> &ms) {
    for (auto itr = ms.begin(); itr != ms.end(); itr++) {
        cerr << *itr << " ";
    }
    cerr << endl;
}

template <typename T>
void debug(map<T, T> &mp) {
    for (auto itr = mp.begin(); itr != mp.end(); itr++) {
        cerr << itr->first << " " << itr->second << endl;
    }
}

void debug_out() { cerr << endl; }

template <typename Head, typename... Tail>
void debug_out(Head H, Tail... T) {
    cerr << H << " ";
    debug_out(T...);
}

ll my_pow(ll x, ll n, ll mod) {
    // 　繰り返し二乗法．x^nをmodで割った余り．
    ll ret;
    if (n == 0) {
        ret = 1;
    } else if (n % 2 == 1) {
        ret = (x * my_pow((x * x) % mod, n / 2, mod)) % mod;
    } else {
        ret = my_pow((x * x) % mod, n / 2, mod);
    }
    return ret;
}

int main() {
    ll N, P;
    cin >> N >> P;
    vector<ll> fact(500005);
    fact[0] = 1;
    for (ll i = 0; i < 500004; i++) {
        fact[i + 1] = (fact[i] * (i + 1)) % mod2;
    }
    if (N < P) {
        cout << (fact[N] + mod2 - 1) % mod2 << endl;
    } else {
        ll fail = 0;
        /*ll perfecto = fact[P];
        ll p_sub = 0;
        for (ll k = 2; k <= P; k++) {
            if (k % 2 == 0) {
                p_sub = (p_sub + my_pow(fact[k], mod2 - 2, mod2)) % mod2;
            } else {
                p_sub = (p_sub + mod2 - my_pow(fact[k], mod2 - 2, mod2)) % mod2;
            }
        }
        perfecto = (perfecto * p_sub) % mod2;*/
        ll sub = fact[N];
        for (ll i = 0; i <= N; i += P) {
            // debug_out(i / P, N - i);
            ll subsub = sub;
            subsub = (subsub * my_pow(fact[i / P], mod2 - 2, mod2)) % mod2;
            subsub = (subsub * my_pow(fact[N - i], mod2 - 2, mod2)) % mod2;
            subsub = (subsub * my_pow(fact[P - 1], i / P, mod2)) % mod2;
            fail = (fail + subsub) % mod2;

            sub = (sub * my_pow(fact[P], mod2 - 2, mod2)) % mod2;
        }
        cout << (fact[N] + mod2 - fail) % mod2 << endl;
    }
}