如题，我用的是倍增LCA，卡常卡疯了也没能卡过去#8和#9，求大佬们帮忙卡常，感激不尽！

%:pragma GCC optimize("Ofast")
%:pragma GCC optimize("unroll-loops")
%:pragma GCC target("sse,sse2,sse3,ssse3,sse4,popcnt,abm,mmx,avx,tune=native")
#include <cstdio>
#include <cmath>
#include <algorithm>
#include <cctype>
#define rint register int
inline void read(int &x){x=0;
	char ch=getchar();
	while(!isdigit(ch)) ch=getchar();
	while(isdigit(ch)){
		x=x*10+ch-'0';
		ch=getchar();
	}
}
const int N=5e5;
const int LOG=std::log(N+0.0)/std::log(2.0);
int n,m;
namespace edge
{
	int head[N],cnt=0;
	struct Edge{
		int to,nxt;
	}e[N<<1];
	inline void add_edge(int u,int v){
		e[++cnt]=Edge{v,head[u]};
		head[u]=cnt;
	}
}
using namespace edge;
namespace LCA
{
	int anc[N][LOG+5],depth[N];
	int Log;
	void dfs(int u,int father){
		depth[u]=depth[father]+1;
		anc[u][0]=father;
		for(int i=head[u];i;i=e[i].nxt){
			if(e[i].to!=father)
				dfs(e[i].to,u);
		}
	}
	inline void pre(){
		Log=std::log(n+0.0)/std::log(2.0);
		dfs(1,0);
		for(int j=1;j<=Log;++j){
			for(int i=1;i<=n;++i){
				anc[i][j]=anc[anc[i][j-1]][j-1];
			}
		}
	}
	inline int LCA(int x,int y){
		if(depth[x]<depth[y]) std::swap(x,y);
		int k=depth[x]-depth[y];
		for(int i=0;k;++i,k>>=1){
			if(k&1) x=anc[x][i];
		}
		if(y==x) return y;
		for(int i=Log;i>=0;--i){
			if(anc[x][i]!=anc[y][i]){
				x=anc[x][i],y=anc[y][i];
			}
		}
		return anc[x][0];
	}
}
int main()
{
	read(n);read(m);
	int x,y;
	for(rint i=1;i<n;++i){
		read(x);read(y);
		add_edge(x,y);
		add_edge(y,x);
	}
	rint z,ans,ansl,l1,l2,l3;
	LCA::pre();
	using LCA::depth;
	while(m--){
		read(x);read(y);read(z);
		l1=LCA::LCA(x,y),l2=LCA::LCA(y,z),l3=LCA::LCA(x,z);
		if(l1==l2) ansl=l3;
		else if(l2==l3) ansl=l1;
		else if(l1==l3) ansl=l2;
		std::printf("%d %d\n",ansl,depth[x]+depth[y]+depth[z]-depth[l1]-depth[l2]-depth[l3]);
	}
	return 0;
}