#include <bits/stdc++.h>
#include <bits/extc++.h>
using namespace __gnu_pbds;
using namespace std;
#pragma GCC optimize("Ofast")
#pragma GCC optimize ("unroll-loops")
#pragma GCC target("sse,sse2,sse3,ssse3,sse4,popcnt,abm,mmx,avx,tune=native")
#define ff first
#define sc second
#define pb push_back
#define ll long long
#define pll pair<ll, ll>
#define pii pair<int, int>
#define ull unsigned long long
#define all(x) (x).begin(),(x).end()
#define rall(x) (x).rbegin(),(x).rend()
mt19937 rng(chrono::steady_clock::now().time_since_epoch().count());
mt19937_64 rngl(chrono::steady_clock::now().time_since_epoch().count());
#define int long long
// #define int unsigned long long
// #define ordered_set(T) tree<T, null_type, less<T>, rb_tree_tag, tree_order_statistics_node_update>
// #define ordered_multiset(T) tree<T, null_type, less_equal<T>, rb_tree_tag, tree_order_statistics_node_update>
const ll mod = 1e9 + 7;
// const ll mod = 998244353;
const ll inf = 1e9;
const ll biginf = 1e18;
const int maxN = 3 * 1e5 + 15;
int n, fnw[maxN];
void add(int x, int d) {
for ( ; x <= n; x += x & -x) fnw[x] += d;
}
int get(int x) {
int ans = 0;
for ( ; x; x -= x & -x) ans += fnw[x];
return ans;
}
void solve() {
cin >> n;
int arr[n + 1], fact[n + 1]; fact[0] = 1;
for (int i = 1; i <= n; i++) {
cin >> arr[i]; fact[i] = (fact[i - 1] * i) % mod;
}
vector<int> x;
for (int i = 1; i <= n; i++) x.pb(arr[i]);
sort(all(x)); x.resize(unique(all(x)) - x.begin());
for (int i = 1; i <= n; i++)
arr[i] = lower_bound(all(x), arr[i]) - x.begin() + 1;
for (int i = 1; i <= n; i++) add(i, 1);
ll ans = 1;
for (int i = 1; i <= n; i++) {
(ans += get(arr[i] - 1) * fact[n - i] % mod) %= mod;
add(arr[i], -1);
}
cout << ans;
}
int32_t main() {
// #ifndef ONLINE_JUDGE
// freopen("input.txt", "r", stdin);
// freopen("output.txt", "w", stdout);
// #endif
ios_base::sync_with_stdio(false);
cin.tie(nullptr); cout.tie(nullptr);
int t = 1;
// cin >> t;
while (t--) {
solve();
cout << '\n';
}
return 0;
}
