#include "bits/stdc++.h"
#include <unordered_map>
#include <unordered_set>

#include <stdio.h>
#include <math.h>
#include <cassert>

#pragma warning(push)
#pragma warning(disable:26498 26450 26451 26812)
#include "atcoder/all"
#pragma warning(pop)

//#include <boost/multiprecision/cpp_int.hpp>
//using namespace boost::multiprecision;
// std::fixed << std::setprecision(10) <<

using namespace std;
using namespace atcoder;

using ll = long long;
using ull = unsigned long long;
using mint = modint998244353;
using mint2 = modint1000000007;

const double eps = 1e-9;

#define REP(i, n) for (ll i = 0; i < ll(n); ++i)
#define REPI(i, init, n) for (ll i = init; i < ll(n); ++i)
#define REPD(i, init) for (ll i = init; i >=0; --i)
#define REPDI(i, init, n) for (ll i = init; i >=n; --i)
#define REPE(i, c) for (const auto& i : c)

using vl = vector<ll>;
#define VL(a, n) vector<ll> a; a.assign(n, 0);
#define VLI(a, n) vector<ll> a; a.assign(n, 0); for(auto& x : a) cin >> x;
#define VSI(a, n) vector<string> a; a.assign(n, ""); for(auto& x : a) cin >> x;
using vvl = vector<vector<ll>>;
#define VVLI(a, n, m, init) vector<vector<ll>> a(n); for(auto& x : a) x.assign(m, init);
using pl = pair<ll, ll>;

struct uv { ll u; ll v; ll c; };
#define VUVI(a, n) vector<uv> a; a.assign(n, {0, 0, 1}); for(auto& x : a) {cin >> x.u >> x.v; x.u--; x.v--;}
#define VUVCI(a, n) vector<uv> a; a.assign(n, {0, 0, 0}); for(auto& x : a) {cin >> x.u >> x.v >> x.c; x.u--; x.v--;}
vvl to_edge(const ll n, const vector<uv>& v) { vvl ret(n); for (auto& x : v) ret[x.u].push_back(x.v); return ret; }
vvl to_edge_d(const ll n, const vector<uv>& v) { vvl ret(n); for (auto& x : v) { ret[x.u].push_back(x.v); ret[x.v].push_back(x.u); } return ret; }

template <class T = long long> using pql = priority_queue<T>;
template <class T = long long> using pqg = priority_queue<T, vector<T>, greater<T>>;

const char* YES = "Yes";
const char* NO = "No";
void yn(bool f) { std::cout << (f ? YES : NO) << endl; };
template<class T> void ov(const T& v) { for (auto it = v.begin(); it != v.end(); it++) { if (it != v.begin()) cout << " "; cout << *it; } };

const ll llhuge = 1LL << 60; //十分でかいが多少足しても溢れない数値
template<class T, class U> bool chmin(T& a, const U& b) { a = min(a, b); return b == a; }
template<class T, class U> bool chmax(T& a, const U& b) { a = max(a, b); return b == a; }
template<class T> void mysort(T& v) { std::sort(begin(v), end(v)); };
template<class T, class U> void mysort(T& v, U pr) { std::sort(begin(v), end(v), pr); };
template<class T> void myrev(T& v) { std::reverse(begin(v), end(v)); };
using vm = vector<mint>;
using vvm = vector<vm>;

using _mint = atcoder::modint998244353;

_mint fac[3000001], finv[3000001], inv[3000001];

void setup() {
	const int MOD = _mint::mod();
	fac[0] = fac[1] = 1;
	finv[0] = finv[1] = 1;
	inv[1] = 1;
	for (int i = 2; i <= 3000000; i++) {
		fac[i] = fac[i - 1] * i;
		inv[i] = (_mint)MOD - inv[MOD % i] * (MOD / i);
		finv[i] = finv[i - 1] * inv[i];
	}
}

_mint binom(int n, int r) {
	if (n < r or n < 0 or r < 0) return _mint::raw(0);
	return fac[n] * finv[r] * finv[n - r];
}
int main() {
	cin.tie(nullptr);
	ios::sync_with_stdio(false);

	ll n, p;
	cin >> n >> p;

	setup();

	mint all = 1; //全組み合わせ
	REP(i, n) {
		all *= (i + 1);
	}

	mint ngp = 1; //(p-1)!
	REP(i, p-1) {
		ngp *= (i + 1);
	}

	mint ng = 0;
	REP(i, n / p + 1) {
		ng += binom(n, p*i) * fac[p*i] * finv[p].pow(i) * finv[i] * ngp.pow(i);
	}

	//n個のものからp*i個を選ぶ  binom(n, p*i);
	//p*i個をp個ずつi種類に分ける (p*i)! / (p!)^i = fac[p*i] * finv[p]^i
	//p個の並び替え = p!

	cout << (all - ng).val() << endl;
}