#include <algorithm>

#include  <iterator>

#include  <iostream>

#include   <cstring>

#include   <iomanip>

#include   <cstdlib>

#include    <cstdio>

#include    <string>

#include    <vector>

#include    <bitset>

#include    <cctype>

#include     <queue>

#include     <cmath>

#include      <list>

#include       <map>

#include       <set>

using namespace std;

//#pragma GCC optimize(3)

//#pragma comment(linker, "/STACK:102400000,102400000")  //c++

#define lson (l , mid , rt << 1)

#define rson (mid + 1 , r , rt << 1 | 1)

#define debug(x) cerr << #x << " = " << x << "\n";

#define pb push_back

#define pq priority_queue

typedef long long ll;

typedef unsigned long long ull;

typedef pair<ll ,ll > pll;

typedef pair<int ,int > pii;

typedef pair<int ,pii> p3;

//priority_queue<int> q;//這是一個大根堆q

//priority_queue<int,vector<int>,greater<int> >q;//這是一個小根堆q

#define fi first

#define se second

//#define endl '\n'

#define OKC ios::sync_with_stdio(false);cin.tie(0)

#define FT(A,B,C) for(int A=B;A <= C;++A)  //用來壓行

#define REP(i , j , k)  for(int i = j ; i <  k ; ++i)

//priority_queue<int ,vector<int>, greater<int> >que;

const ll mos = 0x7FFFFFFFLL;  //

const ll nmos = 0x80000000LL;  //-2147483648

const int inf = 0x3f3f3f3f;

const ll inff = 0x3f3f3f3f3f3f3f3fLL; //

const double PI=acos(-1.0);

template<typename T>

inline T read(T&x){

    x=;int f=;char ch=getchar();

    while (ch<''||ch>'') f|=(ch=='-'),ch=getchar();

    while (ch>=''&&ch<='') x=x*+ch-'',ch=getchar();

    return x=f?-x:x;

}

// #define _DEBUG;         //*//

#ifdef _DEBUG

freopen("input", "r", stdin);

// freopen("output.txt", "w", stdout);

#endif

/*-----------------------show time----------------------*/

            const int maxn = ;

            ll dp[maxn][maxn],x[maxn],y[maxn];

            int m,n,mod;

            ll ksm (ll a,ll b){

                ll res = ;

                while(b>){

                    if(b&) res = (res * a)%mod;

                    a = (a * a)%mod;

                    b >>= ;

                }

                return res;

            }

            ll lagerange(int k){

                ll res = ;

                for(int i=; i<=*n; i++){

                    ll s1=,s2 = ;

                    for(int j=; j<=*n; j++){

                            if(i==j)continue;

                            s1 = 1ll*(s1 * (k - x[j] + mod)%mod)%mod;

                            s2 = 1ll*(s2 * ((x[i] - x[j] + mod)%mod))%mod;

                    }

                    res = (res + 1ll*s1 * ksm(s2,mod-) % mod * y[i] % mod+mod)%mod;

                }

                return res;

            }

int main(){

            scanf("%d%d%d", &m, &n, &mod);

            dp[][] = ;

            for(int i=; i<=*n; i++){

                dp[i][] = ;

                for(int j=; j<=n; j++){

                    dp[i][j] = 1ll*dp[i-][j-] * i % mod * j + dp[i-][j];

                    dp[i][j] = dp[i][j]%mod;

                }

            }

            if(m <=  * n){

                printf("%lld\n", dp[m][n]);

                return ;

            }

            for(int i=; i<=*n; i++) x[i] = i,y[i] = dp[i][n];

            printf("%lld\n",lagerange(m));

            return ;

}