X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fexit.c;h=549c0558ba68273c7586b26f6579d12c27d0f79d;hb=74feb6e84e189707ca1324a92f7206617efbd735;hp=179ac74bf9115c4f6889b1b03b4ee3fdfc96482a;hpb=d4c5e41f3f1b0c19448fcf2d259bdab1ede75e2e;p=linux-2.6

diff --git a/kernel/exit.c b/kernel/exit.c
index 179ac74bf9..549c0558ba 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -148,6 +148,7 @@ void release_task(struct task_struct * p)
 	int zap_leader;
 repeat:
 	atomic_dec(&p->user->processes);
+	proc_flush_task(p);
 	write_lock_irq(&tasklist_lock);
 	ptrace_unlink(p);
 	BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
@@ -175,7 +176,6 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	proc_flush_task(p);
 	release_thread(p);
 	call_rcu(&p->rcu, delayed_put_task_struct);
 
@@ -306,7 +306,7 @@ void __set_special_pids(pid_t session, pid_t pgrp)
 	}
 	if (task_pgrp_nr(curr) != pgrp) {
 		detach_pid(curr, PIDTYPE_PGID);
-		curr->signal->pgrp = pgrp;
+		set_task_pgrp(curr, pgrp);
 		attach_pid(curr, PIDTYPE_PGID, find_pid(pgrp));
 	}
 }
@@ -493,7 +493,7 @@ void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
 }
 EXPORT_SYMBOL(reset_files_struct);
 
-static inline void __exit_files(struct task_struct *tsk)
+static void __exit_files(struct task_struct *tsk)
 {
 	struct files_struct * files = tsk->files;
 
@@ -510,7 +510,7 @@ void exit_files(struct task_struct *tsk)
 	__exit_files(tsk);
 }
 
-static inline void __put_fs_struct(struct fs_struct *fs)
+static void __put_fs_struct(struct fs_struct *fs)
 {
 	/* No need to hold fs->lock if we are killing it */
 	if (atomic_dec_and_test(&fs->count)) {
@@ -531,7 +531,7 @@ void put_fs_struct(struct fs_struct *fs)
 	__put_fs_struct(fs);
 }
 
-static inline void __exit_fs(struct task_struct *tsk)
+static void __exit_fs(struct task_struct *tsk)
 {
 	struct fs_struct * fs = tsk->fs;
 
@@ -666,10 +666,14 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
  * the child reaper process (ie "init") in our pid
  * space.
  */
-static void
-forget_original_parent(struct task_struct *father, struct list_head *to_release)
+static void forget_original_parent(struct task_struct *father)
 {
 	struct task_struct *p, *n, *reaper = father;
+	struct list_head ptrace_dead;
+
+	INIT_LIST_HEAD(&ptrace_dead);
+
+	write_lock_irq(&tasklist_lock);
 
 	do {
 		reaper = next_thread(reaper);
@@ -677,7 +681,7 @@ forget_original_parent(struct task_struct *father, struct list_head *to_release)
 			reaper = task_child_reaper(father);
 			break;
 		}
-	} while (reaper->exit_state);
+	} while (reaper->flags & PF_EXITING);
 
 	/*
 	 * There are only two places where our children can be:
@@ -714,12 +718,23 @@ forget_original_parent(struct task_struct *father, struct list_head *to_release)
 		 * while it was being traced by us, to be able to see it in wait4.
 		 */
 		if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1))
-			list_add(&p->ptrace_list, to_release);
+			list_add(&p->ptrace_list, &ptrace_dead);
 	}
+
 	list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) {
 		p->real_parent = reaper;
 		reparent_thread(p, father, 1);
 	}
+
+	write_unlock_irq(&tasklist_lock);
+	BUG_ON(!list_empty(&father->children));
+	BUG_ON(!list_empty(&father->ptrace_children));
+
+	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_list) {
+		list_del_init(&p->ptrace_list);
+		release_task(p);
+	}
+
 }
 
 /*
@@ -730,7 +745,6 @@ static void exit_notify(struct task_struct *tsk)
 {
 	int state;
 	struct task_struct *t;
-	struct list_head ptrace_dead, *_p, *_n;
 	struct pid *pgrp;
 
 	if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT)
@@ -751,8 +765,6 @@ static void exit_notify(struct task_struct *tsk)
 		spin_unlock_irq(&tsk->sighand->siglock);
 	}
 
-	write_lock_irq(&tasklist_lock);
-
 	/*
 	 * This does two things:
 	 *
@@ -761,12 +773,10 @@ static void exit_notify(struct task_struct *tsk)
 	 *	as a result of our exiting, and if they have any stopped
 	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
 	 */
+	forget_original_parent(tsk);
+	exit_task_namespaces(tsk);
 
-	INIT_LIST_HEAD(&ptrace_dead);
-	forget_original_parent(tsk, &ptrace_dead);
-	BUG_ON(!list_empty(&tsk->children));
-	BUG_ON(!list_empty(&tsk->ptrace_children));
-
+	write_lock_irq(&tasklist_lock);
 	/*
 	 * Check to see if any process groups have become orphaned
 	 * as a result of our exiting, and if they have any stopped
@@ -831,12 +841,6 @@ static void exit_notify(struct task_struct *tsk)
 
 	write_unlock_irq(&tasklist_lock);
 
-	list_for_each_safe(_p, _n, &ptrace_dead) {
-		list_del_init(_p);
-		t = list_entry(_p, struct task_struct, ptrace_list);
-		release_task(t);
-	}
-
 	/* If the process is dead, release it - nobody will wait for it */
 	if (state == EXIT_DEAD)
 		release_task(tsk);
@@ -875,7 +879,32 @@ static inline void exit_child_reaper(struct task_struct *tsk)
 	if (likely(tsk->group_leader != task_child_reaper(tsk)))
 		return;
 
-	panic("Attempted to kill init!");
+	if (tsk->nsproxy->pid_ns == &init_pid_ns)
+		panic("Attempted to kill init!");
+
+	/*
+	 * @tsk is the last thread in the 'cgroup-init' and is exiting.
+	 * Terminate all remaining processes in the namespace and reap them
+	 * before exiting @tsk.
+	 *
+	 * Note that @tsk (last thread of cgroup-init) may not necessarily
+	 * be the child-reaper (i.e main thread of cgroup-init) of the
+	 * namespace i.e the child_reaper may have already exited.
+	 *
+	 * Even after a child_reaper exits, we let it inherit orphaned children,
+	 * because, pid_ns->child_reaper remains valid as long as there is
+	 * at least one living sub-thread in the cgroup init.
+
+	 * This living sub-thread of the cgroup-init will be notified when
+	 * a child inherited by the 'child-reaper' exits (do_notify_parent()
+	 * uses __group_send_sig_info()). Further, when reaping child processes,
+	 * do_wait() iterates over children of all living sub threads.
+
+	 * i.e even though 'child_reaper' thread is listed as the parent of the
+	 * orphaned children, any living sub-thread in the cgroup-init can
+	 * perform the role of the child_reaper.
+	 */
+	zap_pid_ns_processes(tsk->nsproxy->pid_ns);
 }
 
 fastcall NORET_TYPE void do_exit(long code)
@@ -930,7 +959,7 @@ fastcall NORET_TYPE void do_exit(long code)
 
 	if (unlikely(in_atomic()))
 		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
-				current->comm, current->pid,
+				current->comm, task_pid_nr(current),
 				preempt_count());
 
 	acct_update_integrals(tsk);
@@ -981,7 +1010,6 @@ fastcall NORET_TYPE void do_exit(long code)
 		module_put(tsk->binfmt->module);
 
 	proc_exit_connector(tsk);
-	exit_task_namespaces(tsk);
 	exit_notify(tsk);
 #ifdef CONFIG_NUMA
 	mpol_free(tsk->mempolicy);
@@ -1084,15 +1112,17 @@ asmlinkage void sys_exit_group(int error_code)
 static int eligible_child(pid_t pid, int options, struct task_struct *p)
 {
 	int err;
+	struct pid_namespace *ns;
 
+	ns = current->nsproxy->pid_ns;
 	if (pid > 0) {
-		if (p->pid != pid)
+		if (task_pid_nr_ns(p, ns) != pid)
 			return 0;
 	} else if (!pid) {
-		if (task_pgrp_nr(p) != task_pgrp_nr(current))
+		if (task_pgrp_nr_ns(p, ns) != task_pgrp_vnr(current))
 			return 0;
 	} else if (pid != -1) {
-		if (task_pgrp_nr(p) != -pid)
+		if (task_pgrp_nr_ns(p, ns) != -pid)
 			return 0;
 	}
 
@@ -1162,9 +1192,12 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
 {
 	unsigned long state;
 	int retval, status, traced;
+	struct pid_namespace *ns;
+
+	ns = current->nsproxy->pid_ns;
 
 	if (unlikely(noreap)) {
-		pid_t pid = p->pid;
+		pid_t pid = task_pid_nr_ns(p, ns);
 		uid_t uid = p->uid;
 		int exit_code = p->exit_code;
 		int why, status;
@@ -1283,11 +1316,11 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
 			retval = put_user(status, &infop->si_status);
 	}
 	if (!retval && infop)
-		retval = put_user(p->pid, &infop->si_pid);
+		retval = put_user(task_pid_nr_ns(p, ns), &infop->si_pid);
 	if (!retval && infop)
 		retval = put_user(p->uid, &infop->si_uid);
 	if (!retval)
-		retval = p->pid;
+		retval = task_pid_nr_ns(p, ns);
 
 	if (traced) {
 		write_lock_irq(&tasklist_lock);
@@ -1324,6 +1357,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader,
 			     int __user *stat_addr, struct rusage __user *ru)
 {
 	int retval, exit_code;
+	pid_t pid;
 
 	if (!p->exit_code)
 		return 0;
@@ -1342,20 +1376,19 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader,
 	 * keep holding onto the tasklist_lock while we call getrusage and
 	 * possibly take page faults for user memory.
 	 */
+	pid = task_pid_nr_ns(p, current->nsproxy->pid_ns);
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
 
 	if (unlikely(noreap)) {
-		pid_t pid = p->pid;
 		uid_t uid = p->uid;
 		int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED;
 
 		exit_code = p->exit_code;
-		if (unlikely(!exit_code) ||
-		    unlikely(p->state & TASK_TRACED))
+		if (unlikely(!exit_code) || unlikely(p->exit_state))
 			goto bail_ref;
 		return wait_noreap_copyout(p, pid, uid,
-					   why, (exit_code << 8) | 0x7f,
+					   why, exit_code,
 					   infop, ru);
 	}
 
@@ -1417,11 +1450,11 @@ bail_ref:
 	if (!retval && infop)
 		retval = put_user(exit_code, &infop->si_status);
 	if (!retval && infop)
-		retval = put_user(p->pid, &infop->si_pid);
+		retval = put_user(pid, &infop->si_pid);
 	if (!retval && infop)
 		retval = put_user(p->uid, &infop->si_uid);
 	if (!retval)
-		retval = p->pid;
+		retval = pid;
 	put_task_struct(p);
 
 	BUG_ON(!retval);
@@ -1441,6 +1474,7 @@ static int wait_task_continued(struct task_struct *p, int noreap,
 	int retval;
 	pid_t pid;
 	uid_t uid;
+	struct pid_namespace *ns;
 
 	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
 		return 0;
@@ -1455,7 +1489,8 @@ static int wait_task_continued(struct task_struct *p, int noreap,
 		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
 	spin_unlock_irq(&p->sighand->siglock);
 
-	pid = p->pid;
+	ns = current->nsproxy->pid_ns;
+	pid = task_pid_nr_ns(p, ns);
 	uid = p->uid;
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
@@ -1466,7 +1501,7 @@ static int wait_task_continued(struct task_struct *p, int noreap,
 		if (!retval && stat_addr)
 			retval = put_user(0xffff, stat_addr);
 		if (!retval)
-			retval = p->pid;
+			retval = task_pid_nr_ns(p, ns);
 	} else {
 		retval = wait_noreap_copyout(p, pid, uid,
 					     CLD_CONTINUED, SIGCONT,