#include<bits/stdc++.h>
using namespace std;
int f[405][405],g[405][405][3];
int n,m,mod,pw[405][405],pwinv[405][405],a[405],inv[405];
typedef unsigned long long ull;
typedef __uint128_t L;
struct FastMod {
    ull b, m;
    FastMod(ull b) : b(b), m(ull((L(1) << 64) / b)) {}
    ull reduce(ull a) {
        ull q = (ull)((L(m) * a) >> 64);
        ull r = a - q * b; // can be proven that 0 <= r < 2*b
        return r >= b ? r - b : r;
    }
}F(2);
int Interpolate(int n) {
	int sum=0;
	for(int i=1; i<=n; i++) {
		int s=a[i];
		for(int j=1; j<i; j++)s=1ll*s*inv[i-j]%mod*(m-j+mod)%mod;
		for(int j=i+1; j<=n; j++)s=1ll*s*inv[j-i]%mod*(m-j+mod)%mod*(mod-1)%mod;
		sum=(sum+s)%mod;
	}
	return sum;
}
void del(int &x,int y){
	x-=y,(x<0&&(x+=mod));
}
int main() {
	scanf("%d%d%d",&n,&m,&mod),F=FastMod(mod),f[0][0]=mod-1,inv[1]=1;
	for(int i=2;i<=n+1;i++)inv[i]=1ll*inv[mod%i]*(mod-mod/i)%mod;
	for(int i=0;i<=n+1;i++){
		pw[i][0]=pwinv[i][0]=1;
		for(int j=1;j<=n;j++){
			pw[i][j]=1ll*i*pw[i][j-1]%mod;
			pwinv[i][j]=1ll*inv[i]*pwinv[i][j-1]%mod;
		}
	}
	for(int i=1;i<=n;i++){
		for(int j=1;j<=n+1;j++){
			f[i][j]=(pw[j][i]-pw[j-1][i]+mod)%mod;
			for(int k=1; k<=j; k++){
				del(f[i][j],F.reduce(1ll*g[k][j][0]*pw[j-k+1][i]));
				f[i][j]=F.reduce(f[i][j]+1ll*g[k][j][1]*pw[j-k][i]);
				if(k<j)del(f[i][j],F.reduce(1ll*g[k][j][2]*pw[j-k-1][i]));
			}
		}
		for(int j=1;j<=n+1;j++){
			for(int k=j;k<=n+1;k++) {
				g[j][k][0]=F.reduce(g[j][k][0]+1ll*f[i][j]*pwinv[k-j+1][i]);
				g[j][k][1]=F.reduce(g[j][k][1]+2ll*f[i][j]%mod*pwinv[k-j][i]);
				if(j<k)g[j][k][2]=F.reduce(g[j][k][2]+1ll*f[i][j]*pwinv[k-j-1][i]);
			}
		}
	}
	for(int i=1; i<=n+1; i++)a[i]=(a[i-1]+f[n][i])%mod;
	cout<<Interpolate(n+1);
}