Merge branch 'for-3.5' of ../cgroup into block/for-3.5/core-merged

cgroup/for-3.5 contains the following changes which blk-cgroup needs
to proceed with the on-going cleanup.

* Dynamic addition and removal of cftypes to make config/stat file
  handling modular for policies.

* cgroup removal update to not wait for css references to drain to fix
  blkcg removal hang caused by cfq caching cfqgs.

Pull in cgroup/for-3.5 into block/for-3.5/core.  This causes the
following conflicts in block/blk-cgroup.c.

* 761b3ef50e "cgroup: remove cgroup_subsys argument from callbacks"
  conflicts with blkiocg_pre_destroy() addition and blkiocg_attach()
  removal.  Resolved by removing @subsys from all subsys methods.

* 676f7c8f84 "cgroup: relocate cftype and cgroup_subsys definitions in
  controllers" conflicts with ->pre_destroy() and ->attach() updates
  and removal of modular config.  Resolved by dropping forward
  declarations of the methods and applying updates to the relocated
  blkio_subsys.

* 4baf6e3325 "cgroup: convert all non-memcg controllers to the new
  cftype interface" builds upon the previous item.  Resolved by adding
  ->base_cftypes to the relocated blkio_subsys.

Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/fork.c

@@ -66,6 +66,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/oom.h>
 #include <linux/khugepaged.h>
+#include <linux/signalfd.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -192,6 +193,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	security_task_free(tsk);
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
 	put_signal_struct(tsk->signal);
@@ -354,7 +356,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		charge = 0;
 		if (mpnt->vm_flags & VM_ACCOUNT) {
 			unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
-			if (security_vm_enough_memory(len))
+			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
 				goto fail_nomem;
 			charge = len;
 		}
@@ -510,6 +512,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	return NULL;
 }
 
+static void check_mm(struct mm_struct *mm)
+{
+	int i;
+
+	for (i = 0; i < NR_MM_COUNTERS; i++) {
+		long x = atomic_long_read(&mm->rss_stat.count[i]);
+
+		if (unlikely(x))
+			printk(KERN_ALERT "BUG: Bad rss-counter state "
+					  "mm:%p idx:%d val:%ld\n", mm, i, x);
+	}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
+}
+
 /*
  * Allocate and initialize an mm_struct.
  */
@@ -537,9 +556,7 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON(mm->pmd_huge_pte);
-#endif
+	check_mm(mm);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -667,6 +684,38 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	return mm;
 }
 
+static void complete_vfork_done(struct task_struct *tsk)
+{
+	struct completion *vfork;
+
+	task_lock(tsk);
+	vfork = tsk->vfork_done;
+	if (likely(vfork)) {
+		tsk->vfork_done = NULL;
+		complete(vfork);
+	}
+	task_unlock(tsk);
+}
+
+static int wait_for_vfork_done(struct task_struct *child,
+				struct completion *vfork)
+{
+	int killed;
+
+	freezer_do_not_count();
+	killed = wait_for_completion_killable(vfork);
+	freezer_count();
+
+	if (killed) {
+		task_lock(child);
+		child->vfork_done = NULL;
+		task_unlock(child);
+	}
+
+	put_task_struct(child);
+	return killed;
+}
+
 /* Please note the differences between mmput and mm_release.
  * mmput is called whenever we stop holding onto a mm_struct,
  * error success whatever.
@@ -682,8 +731,6 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
  */
 void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 {
-	struct completion *vfork_done = tsk->vfork_done;
-
 	/* Get rid of any futexes when releasing the mm */
 #ifdef CONFIG_FUTEX
 	if (unlikely(tsk->robust_list)) {
@@ -703,17 +750,15 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	/* Get rid of any cached register state */
 	deactivate_mm(tsk, mm);
 
-	/* notify parent sleeping on vfork() */
-	if (vfork_done) {
-		tsk->vfork_done = NULL;
-		complete(vfork_done);
-	}
+	if (tsk->vfork_done)
+		complete_vfork_done(tsk);
 
 	/*
 	 * If we're exiting normally, clear a user-space tid field if
 	 * requested.  We leave this alone when dying by signal, to leave
 	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble otherwise.  Userland only wants this done for a sys_exit.
+	 * trouble, say, a killed vfork parent shouldn't touch this mm.
+	 * Userland only wants this done for a sys_exit.
 	 */
 	if (tsk->clear_child_tid) {
 		if (!(tsk->flags & PF_SIGNALED) &&
@@ -934,8 +979,10 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_sighand(struct sighand_struct *sighand)
 {
-	if (atomic_dec_and_test(&sighand->count))
+	if (atomic_dec_and_test(&sighand->count)) {
+		signalfd_cleanup(sighand);
 		kmem_cache_free(sighand_cachep, sighand);
+	}
 }
 
 
@@ -1003,6 +1050,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
+	sig->has_child_subreaper = current->signal->has_child_subreaper ||
+				   current->signal->is_child_subreaper;
+
 	mutex_init(&sig->cred_guard_mutex);
 
 	return 0;
@@ -1014,7 +1064,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
 	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	new_flags |= PF_FORKNOEXEC;
-	new_flags |= PF_STARTING;
 	p->flags = new_flags;
 }
 
@@ -1191,6 +1240,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
 	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
+	seqcount_init(&p->mems_allowed_seq);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
@@ -1309,7 +1359,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	clear_all_latency_tracing(p);
 
 	/* ok, now we should be set up.. */
-	p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
+	if (clone_flags & CLONE_THREAD)
+		p->exit_signal = -1;
+	else if (clone_flags & CLONE_PARENT)
+		p->exit_signal = current->group_leader->exit_signal;
+	else
+		p->exit_signal = (clone_flags & CSIGNAL);
+
 	p->pdeath_signal = 0;
 	p->exit_state = 0;
 
@@ -1544,16 +1600,9 @@ long do_fork(unsigned long clone_flags,
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
 			init_completion(&vfork);
+			get_task_struct(p);
 		}
 
-		/*
-		 * We set PF_STARTING at creation in case tracing wants to
-		 * use this to distinguish a fully live task from one that
-		 * hasn't finished SIGSTOP raising yet.  Now we clear it
-		 * and set the child going.
-		 */
-		p->flags &= ~PF_STARTING;
-
 		wake_up_new_task(p);
 
 		/* forking complete and child started to run, tell ptracer */
@@ -1561,10 +1610,8 @@ long do_fork(unsigned long clone_flags,
 			ptrace_event(trace, nr);
 
 		if (clone_flags & CLONE_VFORK) {
-			freezer_do_not_count();
-			wait_for_completion(&vfork);
-			freezer_count();
-			ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+			if (!wait_for_vfork_done(p, &vfork))
+				ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
 		}
 	} else {
 		nr = PTR_ERR(p);