jzoj3717

#include<bits/stdc++.h>
using namespace std;
extern int main2(void) __asm__ ("main2");
typedef long long ll;
ll f[500010][21],dep[500010],n,m,a[400010];
ll ans=0,ec,v[1000010],nxt[1000010],h[500010],vis[500010],p[500010];
void add(ll x,ll y){v[++ec]=y;nxt[ec]=h[x];h[x]=ec;}
void dfs(ll x,ll g){
    for(ll i=1;i<=20;i++)
        f[x][i]=f[f[x][i-1]][i-1];
    for(ll i=h[x];i;i=nxt[i])
        if(v[i]!=g){
            dep[v[i]]=dep[x]+1;
            p[v[i]]=x;
            f[v[i]][0]=x;
            dfs(v[i],x);
        }
}
ll lca(ll x,ll y){
    if(dep[x]<dep[y])swap(x,y);
    for(int i=20;i>=0;i--)
        if(dep[f[x][i]]>=dep[y])
            x=f[x][i];
    if(x==y)return x;
    for(int i=20;i>=0;i--)
        if(f[x][i]!=f[y][i])
            x=f[x][i],y=f[y][i];
    return f[x][0];
}
ll find(ll x){return p[x]==x?x:p[x]=find(p[x]);}
void jump(ll x,ll y){
    if(dep[x]<dep[y])return;
    p[x]=f[x][0];
    vis[x]=1;
    jump(find(x),y);
}
int main2(){
    freopen("train.in","r",stdin);
    freopen("train.out","w",stdout);
    ll las;
    scanf("%lld%lld%lld",&n,&m,&las);
    for(ll i=1;i<n;i++){
        ll x,y;
        scanf("%lld%lld",&x,&y);
        add(x,y);add(y,x);
    }
    dep[1]=1;
    dfs(1,0);
    for(ll i=1;i<=m;i++)scanf("%lld",&a[i]),p[a[i]]=a[i];
    for(ll i=1;i<=m;i++){
        if(vis[a[i]])continue;
        ll lc=lca(las,a[i]);
        ans+=dep[las]+dep[a[i]]-2*dep[lc];
        jump(las,lc);
        jump(a[i],lc);
        las=a[i];
    }
    printf("%lld\n",ans);exit(0);
}
int main(){
    int size=32<<20; char *p=(char*)malloc(size)+size;
    __asm__ __volatile__("movq  %0, %%rsp\n"  "pushq $exit\n"   "jmp main2\n"  :: "r"(p));
}

占坑