#pragma GCC target("avx2")
#pragma GCC optimize("O3")
#pragma GCC optimize("unroll-loops")
#include <atcoder/all>
#include <iostream> // cout, endl, cin
#include <string> // string, to_string, stoi
#include <vector> // vector
#include <algorithm> // min, max, swap, sort, reverse, lower_bound, upper_bound
#include <utility> // pair, make_pair
#include <tuple> // tuple, make_tuple
#include <cstdint> // int64_t, int*_t
#include <cstdio> // printf
#include <map> // map
#include <queue> // queue, priority_queue
#include <set> // set
#include <stack> // stack
#include <deque> // deque
#include <unordered_map> // unordered_map
#include <unordered_set> // unordered_set
#include <bitset> // bitset
#include <cctype> // isupper, islower, isdigit, toupper, tolower
#include <math.h>
#include <iomanip>
#include <functional>
using namespace std;  
using namespace atcoder;
#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define repi(i, a, b) for (int i = (int)(a); i < (int)(b); i++)
typedef long long ll;
typedef unsigned long long ull;
const ll inf=1e18;  
using graph = vector<vector<int> > ;
using P= pair<ll,ll>;  
using vi=vector<int>;
using vvi=vector<vi>;
using vll=vector<ll>; 
using vvll=vector<vll>;
using vp=vector<P>;
using vvp=vector<vp>;
using vd=vector<double>;
using vvd =vector<vd>;
//string T="ABCDEFGHIJKLMNOPQRSTUVWXYZ";
//string S="abcdefghijklmnopqrstuvwxyz";
//g++ main.cpp -std=c++17 -I .  
//cout <<setprecision(20);
//cout << fixed << setprecision(10);
//cin.tie(0); ios::sync_with_stdio(false);
const double PI = acos(-1);
int vx[]={0,1,0,-1,-1,1,1,-1},vy[]={1,0,-1,0,1,1,-1,-1};
void putsYes(bool f){cout << (f?"Yes":"No") << endl;}
void putsYES(bool f){cout << (f?"YES":"NO") << endl;}
void putsFirst(bool f){cout << (f?"First":"Second") << endl;}
void debug(int test){cout << "TEST" << " " << test << endl;}
ll pow_pow(ll x,ll n,ll mod){
    if(n==0) return 1; 
    x%=mod;
    ll res=pow_pow(x*x%mod,n/2,mod);
    if(n&1)res=res*x%mod;
    return res;
}
ll gcd(ll x,ll y){
    if(y==0)return x;
    return gcd(y,x%y);
}
 
ll lcm(ll x,ll y){
    return ll(x/gcd(x,y))*y;
}
template<class T> bool chmin(T& a, T b) {
    if (a > b) {
        a = b;
        return true;
    }
    else return false;
}
template<class T> bool chmax(T& a, T b) {
    if (a < b) {
        a = b;
        return true;
    }
    else return false;
}
// https://youtu.be/L8grWxBlIZ4?t=9858
// https://youtu.be/ERZuLAxZffQ?t=4807 : optimize
// https://youtu.be/8uowVvQ_-Mo?t=1329 : division
ll mod =998244353;
//ll mod =1e9+7;
struct mint {
  ll x; // typedef long long ll;
  mint(ll x=0):x((x%mod+mod)%mod){}
  mint operator-() const { return mint(-x);}
  mint& operator+=(const mint a) {
    if ((x += a.x) >= mod) x -= mod;
    return *this;
  }
  mint& operator-=(const mint a) {
    if ((x += mod-a.x) >= mod) x -= mod;
    return *this;
  }
  mint& operator*=(const mint a) { (x *= a.x) %= mod; return *this;}
  mint operator+(const mint a) const { return mint(*this) += a;}
  mint operator-(const mint a) const { return mint(*this) -= a;}
  mint operator*(const mint a) const { return mint(*this) *= a;}
  mint pow(ll t) const {
    if (!t) return 1;
    mint a = pow(t>>1);
    a *= a;
    if (t&1) a *= *this;
    return a;
  }
 
  // for prime mod
  mint inv() const { return pow(mod-2);}
  mint& operator/=(const mint a) { return *this *= a.inv();}
  mint operator/(const mint a) const { return mint(*this) /= a;}
};
istream& operator>>(istream& is, const mint& a) { return is >> a.x;}
ostream& operator<<(ostream& os, const mint& a) { return os << a.x;}
// combination mod prime
// https://www.youtube.com/watch?v=8uowVvQ_-Mo&feature=youtu.be&t=1619
struct combination {
  vector<mint> fact, ifact;
  combination(int n):fact(n+1),ifact(n+1) {
    //assert(n < mod);
    fact[0] = 1;
    for (int i = 1; i <= n; ++i) fact[i] = fact[i-1]*i;
    ifact[n] = fact[n].inv();
    for (int i = n; i >= 1; --i) ifact[i-1] = ifact[i]*i;
  }
  mint operator()(int n, int k) {
    if (k < 0 || k > n) return 0;
    if (n<0) return 0;
    return fact[n]*ifact[k]*ifact[n-k];
  } mint p(int n, int k) { return fact[n]*ifact[n-k]; } } c(2000000); 
using vm=vector<mint> ;
using vvm=vector<vm> ;
struct edge{
  int to; ll cost;
  edge(int to,ll cost) : to(to),cost(cost){}
};
using ve=vector<edge>;
using vve=vector<ve>;
struct Compress{
   vll a;
   map<ll,ll> d,d2;
   int cnt;
   Compress() :cnt(0) {}
   void add(ll x){a.push_back(x);}
   void init(){
     set<ll>s(a.begin(),a.end());
     for(auto y:s)d[y]=cnt++;
     for(auto&y:a)y=d[y];
     for(auto u:d)d2[u.second]=u.first;
   }
   ll to(ll x){return d[x];} //変換先
   ll from(ll x){return d2[x];}//逆引き
   int size(){return cnt;}
};
//vll anss;
vll anss;
struct UnionFind { vector<int> par, siz; UnionFind(int n) : par(n, -1) , siz(n, 1) { } int root(int x) { if (par[x] == -1) return x;
        else return par[x] = root(par[x]);
    }
    bool issame(int x, int y) {
        return root(x) == root(y);
    }
    bool unite(int x, int y) {
        x = root(x), y = root(y);
        if (x == y) return false; 
        if (siz[x] < siz[y]) swap(x, y);
        par[y] = x;
        siz[x] += siz[y];
        return true;
    }
    int size(int x) {
        return siz[root(x)];
    }
};
const int N=5005;
//mint dp[N][N][2];
void solve(int test){
  int n,m; cin >> n >> m;
  UnionFind uf(n);
  vi p(n);rep(i,n)cin >> p[i],p[i]--;
  rep(i,n)uf.unite(i,p[i]);
  int tot=0;
  vvm dp;
  rep(x,n)if(x==uf.root(x)){
    int si=uf.size(x);
   // rep(i,si+1)rep(j,si+1)rep(k,2)dp[i][j][k]=0;
    if(tot==0){
      dp.resize(2,vm(2));
      dp[1][1]=1;
    }
    else {
      vvm next(dp.size()+1,vm(2));
      rep(i,dp.size())rep(j,2){
        next[i][1]+=dp[i][j]*i;
        next[i+1][1]+=dp[i][j];
      }
      swap(next,dp);
    }
    repi(i,1,si){
      vvm next(dp.size()+1,vm(2));
        rep(j,dp.size())rep(k,2){
          mint now=dp[j][k];
          if(!now.x)continue;
          {
            next[j+1][0]+=now;
          }
          {
            if(k){
              next[j][0]+=now*(j-1);
            }
            else {
              next[j][0]+=now*(j-2);
              if(i!=si-1)next[j][1]+=now;
            }
          }
        }
        swap(next,dp);
    }
    tot+=si;
  }
  cout << dp[m][0]+dp[m][1] << endl;
}
//g++ main.cpp -std=c++17 -I .
int main(){cin.tie(0);ios::sync_with_stdio(false);
  int t=1;//cin >> t;
  rep(test,t)solve(test);
 for(auto u:anss)cout << u << endl;
}