#include <bits/stdc++.h>
#define lowbit(x) (x & -x)
#define eb emplace_back
#define pb push_back
#define mp make_pair
using namespace std;

typedef long long ll;
typedef vector<int> poly;
const int N = 4e4+5;

int n, Mod, ans = 1;
int f[N][2];
ll Bfac[N], Bifac[N], *fac = Bfac + 2, *ifac = Bifac + 2;

inline ll qpow(int a, int b) {
	ll base = a, ans = 1;
	while (b) {
		if (b & 1) ans = ans * base % Mod;
		base = base * base % Mod;
		b >>= 1;
	}
	return ans;
}

inline void Add(int &a, int b) { a += b; if (a >= Mod) a -= Mod; }
inline void Add(ll &a, int b) { a += b; if (a >= Mod) a -= Mod; }

ll A[N], B[N], C[N], r0[15][N], r1[15][N], r2[15][N], x[15][N], y[15][N];

inline int mul(int d, ll *a, ll *b, int n, ll *g) {
    if (!n) return 0;
    for (int i = 0; i < 2 * n - 1; i++) g[i] = 0;
    // if (1) {
    if (n <= 16) {
        for (int i = 0; i < n; i++)
            for (int j = 0; j < n; j++)
                Add(g[i + j], a[i] * b[j] % Mod);
        return 2 * n - 1;
    }
    int mid = (n + 1) / 2;
    int l0 = mul(d + 1, a, b, mid, r0[d]);
    int l1 = mul(d + 1, a + mid, b + mid, n - mid, r1[d]);
    for (int i = 0; i < l0; i++) Add(g[i + mid], Mod - r0[d][i]), Add(g[i], r0[d][i]);
    for (int i = 0; i < l1; i++) Add(g[i + mid], Mod - r1[d][i]), Add(g[i + 2 * mid], r1[d][i]);

    for (int i = 0; i < mid; i++) {
        x[d][i] = a[i], y[d][i] = b[i];
        if (mid + i < n) Add(x[d][i], a[mid + i]), Add(y[d][i], b[mid + i]);
    }
    int l2 = mul(d + 1, x[d], y[d], mid, r2[d]);

    for (int i = 0; i < l2; i++) Add(g[i + mid], r2[d][i]);

    return 2 * n - 1;
}

inline ll c0(int p, int q, ll j) { return (p * q * j * j + (p + q - p * q) * j) % Mod; }
inline ll c1(int p, int q, ll i) { return (p * q * i * i + (p * q - p - q) * i + (1 - p) * (1 - q) + Mod) % Mod; }

void solve(int l, int r) {
	if (l == r) return;
	int mid = (l + r) >> 1;
	solve(l, mid);
	for (int p = 0; p < 2; p++)
		for (int q = 0; q < 2; q++) {
			for (int i = 0; i < r - l; i++) B[i] = fac[mid - 2 + l - q + i - p], A[i] = 0;
			if (p * q || (p + q - p * q)) {
				for (int i = l; i <= mid; i++) A[mid - i] = f[i][p] * ifac[2 * i - 2 - p] % Mod;
				mul(0, A, B, r - l, C);
				for (int i = mid - l; i <= r - l - 1; i++) {
					int j = i + 1 + l - q;
					Add(f[j + q][q], c0(p, q, j) * C[i] % Mod);
				}
			}

			if (p * q || (p * q - p - q) || (1 - p) * (1 - q)) {
				for (int i = l; i <= mid; i++) A[mid - i] = f[i][p] * ifac[2 * i - 2 - p] % Mod * c1(p, q, i) % Mod;
				mul(0, A, B, r - l, C);
				for (int i = mid - l; i <= r - l - 1; i++) Add(f[i + 1 + l][q], C[i]);
			}

			if (p * q) {
				for (int i = l; i <= mid; i++) A[mid - i] = f[i][p] * ifac[2 * i - 2 - p] % Mod * i % Mod;
				mul(0, A, B, r - l, C);
				for (int i = mid - l; i <= r - l - 1; i++) {
					int j = i + 1 + l - q;
					Add(f[j + q][q], Mod - C[i] * 2 * j % Mod);
				}
			}
		}
	solve(mid + 1, r);
}

int main() {
	scanf("%d%d", &n, &Mod);

	fac[0] = 1;
	for (int i = 1; i <= 2 * n; i++) fac[i] = fac[i - 1] * i % Mod;
	ifac[2 * n] = qpow(fac[2 * n], Mod - 2);
	for (int i = 2 * n; i; i--) ifac[i - 1] = ifac[i] * i % Mod;

	f[1][0] = f[2][1] = 1;
	solve(1, n);

	for (int i = 3; i <= 2 * n; i += 2) ans = (ll) ans * i % Mod;
	for (int i = 1; i <= n; i++)
		for (int p = 0; p < 2; p++) {
			ll t = f[i][p];
			if (p) t = t * (n - i + 1) % Mod;
			Add(ans, Mod - t * fac[n + i - 3 + !p] % Mod * ifac[2 * i - 3 + !p] % Mod);
		}

	printf("%d", ans);
	return 0;
}