//#pragma GCC optimize("Ofast,no-stack-protector")
//#pragma GCC target("se,se2,se3,se3,se4,popcnt,abm,mmx,avx")
//#pragma GCC optimize("Ofast,fast-math")
//#pragma GCC target("avx,avx2")
//#pragma GCC optimize(2)
//#pragma GCC optimize(3)
//#pragma GCC optimize("Ofast")
#include <bits/stdc++.h>
using namespace std;
// #define int long long
typedef pair<int, int> pii;
typedef vector<int> vi;
typedef double db;
#define F(i, a, b) for(int i = a; i <= (b); ++i)
#define F2(i, a, b) for(int i = a; i < (b); ++i)
#define dF(i, a, b) for(int i = a; i >= (b); --i)
template<typename T> void debug(string s, T x) {
    cerr << "[" << s << "] = [" << x << "]\n";
}
template<typename T, typename... Args> void debug(string s, T x, Args... args) {
    for (int i = 0, b = 0; i < (int)s.size(); i++) if (s[i] == '(' || s[i] == '{') b++;
    else if (s[i] == ')' || s[i] == '}') b--;
    else if (s[i] == ',' && b == 0) {
        cerr << "[" << s.substr(0, i) << "] = [" << x << "] | ";
        debug(s.substr(s.find_first_not_of(' ', i + 1)), args...);
        break;
    }
}
#ifdef orzz
#define Debug(...) debug(#__VA_ARGS__, __VA_ARGS__)
#else
#define Debug(...)
#endif
#define pb push_back
#define fi first
#define se second
#define Mry fprintf(stderr, "%.3lf MB\n", (&Med - &Mbe) / 1048576.0)
#define Try cerr << 1e3 * clock() / CLOCKs_PER_sEC << " ms\n";
typedef long long ll;
// namespace Fread {const int sIZE = 1 << 17; char buf[sIZE], *s, *T; inline char getchar() {if (s == T) {T = (s = buf) + fread(buf, 1, sIZE, stdin); if (s == T) return '\n';} return *s++;}}
// namespace Fwrite {const int sIZE = 1 << 17; char buf[sIZE], *s = buf, *T = buf + sIZE; inline void flush() {fwrite(buf, 1, s - buf, stdout), s = buf;} inline void putchar(char c) {*s++ = c;if (s == T) flush();} struct NTR {~NTR() {flush();}} ztr;}
// #ifdef ONLINE_JUDGE
// #define getchar Fread::getchar
// #define putchar Fwrite::putchar
// #endif
inline int ri() {
    int x = 0;
    bool t = 0;
    char c = getchar();
    while (c < '0' || c > '9') t |= c == '-', c = getchar();
    while (c >= '0' && c <= '9') x = (x << 3) + (x << 1) + (c ^ 48), c = getchar();
    return t ? -x : x;
}
inline void wi(int x) {
    if (x < 0) {
        putchar('-'), x = -x;
    }
    if (x > 9) wi(x / 10);
    putchar(x % 10 + 48);
}
inline void wi(int x, char s) {
    wi(x), putchar(s);
}
bool Mbe;
// mt19937 rnd(chrono::steady_clock::now().time_since_epoch().count());
const int mod = 998244353;
const int inf = 0x3f3f3f3f;
const ll infll = 0x3f3f3f3f3f3f3f3f;
const int _ = 2e5 + 5, M = 1e6 + 5;

int n, m, fa[_], rt, hson[_], dfn[_], cnt, top[_], mxd[_], dep[_];

vi d[_];

void dfs(int u, int fa) {
	dep[u] = dep[fa] + 1;
	mxd[u] = 1;
	for(int v : d[u]) if(v != fa) {
		dfs(v, u);
		if(mxd[u] < mxd[v] + 1) mxd[u] = mxd[v] + 1, hson[u] = v;
	}
}

vector<pii> mgs[_];

vi cg[_];

array<int, 4> chg[M << 3]; int zkw;

int ans[M];

void dfs2(int u, int tf) {
	top[u] = tf;
	dfn[u] = ++cnt;
	if(hson[u]) dfs2(hson[u], tf);
	for(int v : d[u]) if(!dfn[v]) {
		dfs2(v, v);
		F(j, 1, mxd[v]) {
			// merge dfn[v]+j-1 -> dfn[u]+j, k = j
			// Debug(u, v, j);
			mgs[j].pb(make_pair(dfn[v] + j - 1, dfn[u] + j));
		}
	}
}

set<int> st[_];

int pre[_];

struct Bit {
	int C[_];
	void add(int x, int v) {
		if(!x) {
			C[0] += v;
			return;
		}
		for(; x <= n; x += x & -x) C[x] += v;
	}
	int qry(int x) {
		int res = C[0];
		for(; x; x -= x & -x) res += C[x];
		return res;
	}
} tr;

void cdq(int l, int r) {
	if(l >= r) return;
	int mid = (l + r) >> 1;
	cdq(l, mid), cdq(mid + 1, r);
	// 左边time < 右边
	// 内部按照pos排好序
	// I will use 4进制bit
	int p = l - 1;
	F(i, mid + 1, r) if(chg[i][3] > 0) {
		while(p + 1 <= mid && chg[p + 1][1] <= chg[i][1]) {
			p++;
			if(chg[p][3] <= 0) {
				tr.add(chg[p][2], chg[p][3] == 0 ? 1 : -1);
			}
		}
		ans[chg[i][3] >m ? chg[i][3] - m : chg[i][3]] += tr.qry(chg[i][2] - 1) * (chg[i][3] > m ? -1 : 1);
	}
	while(p >= l) {
		if(chg[p][3] <= 0) 
			tr.add(chg[p][2], chg[p][3] == 0 ? -1 : 1);
		p--;
	}
	assert(tr.qry(n) == 0);
	sort(chg + l, chg + r + 1, [&](array<int, 4> a, array<int, 4> b) { return a[1] < b[1]; });
}

bool Med;
signed main() {
    // Mry;
	n = ri(), m = ri();
	F(i, 1, n) {
		fa[i] = ri();
		if(!fa[i]) rt = i;
		else d[fa[i]].pb(i);
	}
	dfs(rt, 0);
	dfs2(rt, rt);
	F(i, 1, n) st[dfn[i]].insert(i), chg[++zkw] = {0, i, 0, 0}, cg[dep[i]].pb(i);
	// static vector<array<int, 3>> qr[_];
	F(i, 1, m) {
		int l = ri(), r = ri(), x = ri();
		chg[++zkw] = {x, r, l, i};
		chg[++zkw] = {x, l - 1, l, m+i};
		// ans[i] -= (l - 1);
		// qr[x].pb({l, r, i});
	}
	F(k, 1, n) {
		for(pii &v : mgs[k]) {
			// v.fi->v.se
			if(st[v.fi].size() > st[v.se].size()) st[v.fi].swap(st[v.se]);
			for(auto w : st[v.fi]) {
				auto p = st[v.se].upper_bound(w);
				if(p != st[v.se].end()) {
					chg[++zkw] = {k, *p, pre[*p], -1};
					chg[++zkw] = {k, *p, w, 0};
					pre[*p] = w;
				}
				if(p != st[v.se].begin()) {
					p--;
					chg[++zkw] = {k, w, pre[w], -1};
					chg[++zkw] = {k, w, *p, 0};
					pre[w] = *p;
				} else {
					chg[++zkw] = {k, w, pre[w], -1};
					chg[++zkw] = {k, w, 0, 0};
					pre[w] = 0;
				}
				st[v.se].insert(w);
			}
			st[v.fi].clear();
		}
		for(int &v :cg[k]) {
			chg[++zkw] = {k, v, pre[v], -1};
			chg[++zkw] = {k, v, n, 0};
			pre[v] = n;
		}
		// for(auto &v :qr[k]) {
		// 	chg[++zkw] = {k, v[1], v[0], v[2]};
		// }
		// for(int &v : chg[k]) pre[v] = n;
		// for(auto &v : qr[k]) {
		// 	int res = 0;
		// 	F(i, v[0], v[1]) if(pre[i] < v[0]) res++;
		// 	ans[v[2]] = res;
		// }
	}
	sort(chg + 1, chg + zkw + 1, [&](array<int, 4> a, array<int, 4> b) { return (a[0] ^ b[0]) ? a[0] < b[0] : (a[3] <= 0 ? 1 : 0); });
	// F(i, 1, zkw) {
		// Debug(i, chg[i][0], chg[i][1], chg[i][2], chg[i][3]);
	// }
	// F(i, 1, zkw) if(chg[i][3] > 0) {
		// F(j, 1, i - 1) if(chg[j][3] <= 0 && chg[j][1] <= chg[i][1]) {
			// ans[chg[i][3] > m ? chg[i][3] - m :chg[i][3]] += (chg[j][2] < chg[i][2]) * (chg[j][3] == 0 ? 1 : -1) * (chg[i][3] > m ? -1 : 1);
		// }
	// }
	cdq(1, zkw);
	F(i,1 , m) printf("%d\n", ans[i]);
 	// Try;
    return 0;
}