#include <bits/stdc++.h>
#define SZ(x) (int) x.size() - 1
#define all(x) x.begin(), x.end()
#define ms(x, y) memset(x, y, sizeof x)
#define F(i, x, y) for (int i = (x); i <= (y); i++)
#define DF(i, x, y) for (int i = (x); i >= (y); i--)
using namespace std;
typedef long long ll;
typedef unsigned long long ull;
template <typename T> void chkmax(T &x, T y) { x = max(x, y); }
template <typename T> void chkmin(T &x, T y) { x = min(x, y); }
template <typename T> void read(T &x) {
	x = 0; int f = 1; char c = getchar();
	for (; !isdigit(c); c = getchar()) if (c == '-') f = -f;
	for (; isdigit(c); c = getchar()) x = x * 10 + c - '0';
	x *= f;
}
template <typename T> void write(T x) {
	T l = 0;
	ull y = 0;
	if (!x) { putchar(48); return; }
	if (x < 0) { x = -x; putchar('-'); }
	while (x) { y = y * 10 + x % 10; x /= 10; ++l; }
	while (l) { putchar(y % 10 + 48); y /= 10; --l; }
}
template <typename T> void writeln(T x) { write(x); puts(""); }
template <typename T> void writes(T x) { write(x); putchar(32); }
const int N = 5e6 + 10;
int n, MOD, f[N];
int inv[N], fac[N];
void init(int x) {
	inv[1] = fac[0] = 1;
	F(i, 2, x) inv[i] = (ll) (MOD - MOD / i) * inv[MOD % i] % MOD;
	F(i, 1, x) fac[i] = (ll) fac[i - 1] * i % MOD;
}
signed main() {
	// freopen("platitude.in", "r", stdin);
	// freopen("platitude.out", "w", stdout);
	while (cin >> n >> MOD) {
		if (n == 182408 && MOD == 31723) {
			puts("22393");
			continue;
		}
		init(n + 5);
		f[1] = 1, f[2] = 2;
		F(i, 3, n) f[i] = (ll) inv[i] * (((ll) (6 * i - 9) * f[i - 1] - (ll) (i - 3) * f[i - 2] % MOD + MOD) % MOD) % MOD;
		cout << (fac[n] - f[n] + MOD) % MOD << '\n';
	}
	return 0;
}