#include <iostream>
#include <vector>
#include <algorithm>
#include <cmath>
#include <string>
#include <queue>
#include <stack>
#include <set>
#include <map>
#include <iomanip>
#include <utility>
#include <tuple>
#include <functional>
#include <bitset>
#include <cassert>
#include <complex>
#include <stdio.h>
#include <time.h>
#include <numeric>
#include <random>
#include <unordered_map>
#include <unordered_set>
#define all(a) a.begin(),a.end()
#define rep(i, n) for (ll i = 0; i < (n); i++)
#define pb push_back
#pragma GCC optimize("O3")
#pragma GCC optimize("unroll-loops")
using namespace std;
typedef long long ll;
typedef unsigned long long ull;
typedef long double ld;
typedef pair<ll, ll> P;
typedef complex<ld> com;
constexpr int inf = 1000000010;
constexpr ll INF = 1000000000000000010;
constexpr ld eps = 1e-12;
constexpr ld pi = 3.141592653589793238;
template<class T, class U> inline bool chmax(T &a, const U &b) { if (a < b) { a = b; return true; } return false; }
template<class T, class U> inline bool chmin(T &a, const U &b) { if (a > b) { a = b; return true; } return false; }

vector<vector<int>> graph(1000010, vector<int>());
vector<ll> cnt(1000010), sz(1000010, 1);

void dfs(int n) {
	for (int i : graph[n]) {
		dfs(i);
		cnt[n] += cnt[i];
		sz[n] += sz[i];
	}
	cnt[n] += sz[n] - 1;
}

int main() {
	cin.tie(0);
	ios::sync_with_stdio(false);
	cout << fixed << setprecision(20);

	int n;
	cin >> n;
	vector<bool> a(n);
	rep(i, n - 1) {
		int u, v;
		//cin >> u >> v;
		u = i + 1, v = i + 2;
		u--; v--;
		graph[u].pb(v);
		a[v] = true;
	}
	int root = -1;
	rep(i, n) if (!a[i]) root = i;
	dfs(root);
	ll ans = 0;
	rep(i, n) {
		ans += cnt[i];
		ans %= 1000000007;
	}
	cout << ans << '\n';
}