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

#include <bits/stdc++.h>
using namespace std;

#define rep(i,n) for(int i = 0; i < (int)n; i++)
#define FOR(n) for(int i = 0; i < (int)n; i++)
#define repi(i,a,b) for(int i = (int)a; i < (int)b; i++)
#define all(x) x.begin(),x.end()
//#define mp make_pair
#define vi vector<int>
#define vvi vector<vi>
#define vvvi vector<vvi>
#define vvvvi vector<vvvi>
#define pii pair<int,int>
#define vpii vector<pair<int,int>>

template<typename T>
bool chmax(T &a, const T b) {if(a<b) {a=b; return true;} else {return false;}}
template<typename T>
bool chmin(T &a, const T b) {if(a>b) {a=b; return true;} else {return false;}}

using ll = long long;
using ld = long double;
using ull = unsigned long long;

const ll INF = numeric_limits<long long>::max() / 2;
const ld pi = 3.1415926535897932384626433832795028;
const ll mod = 998244353;
int dx[] = {1, 0, -1, 0, -1, -1, 1, 1};
int dy[] = {0, 1, 0, -1, -1, 1, -1, 1};

void solve() {
    const int MX = (5*1e6-1)*2-1;
    int n, m;
    cin >> n >> m;
    vector<vector<int>> dp(MX+1, vector<int>(3, 0));
    dp[1][0] = 1, dp[1][1] = 1, dp[1][2] = 1;
    repi(i, 1, MX) {
        dp[i+1][0] = ((ll)dp[i][0] + (ll)dp[i][1]*(ll)(i+1)) % m;
        dp[i+1][1] = ((ll)dp[i][0] + (ll)dp[i][1] + (ll)dp[i][2]*(ll)(i+1)) % m;
        dp[i+1][2] = ((ll)dp[i][0] + (ll)dp[i][1] + (ll)dp[i][2]) % m;
    }
    ll ans = 1;
    repi(i, 1, 2*n) (ans *= (ll)i) %= m;
    repi(i, 1, n) (ans *= (ll)dp[i*2-1][2]) %= m;
    cout << (ans%mod+mod)%mod << endl;
}

signed main() {
    cin.tie(nullptr);
    ios::sync_with_stdio(false);
    solve();
    return 0;
}