1 files changed, 31 insertions, 48 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3244cc56b697..a024bf6254df 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -42,6 +42,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
@@ -365,12 +366,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 		*new = data_race(*orig);
 		INIT_LIST_HEAD(&new->anon_vma_chain);
 		new->vm_next = new->vm_prev = NULL;
+		dup_vma_anon_name(orig, new);
 	}
 	return new;
 }
 
 void vm_area_free(struct vm_area_struct *vma)
 {
+	free_vma_anon_name(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 }
 
@@ -754,9 +757,7 @@ void __put_task_struct(struct task_struct *tsk)
 	delayacct_tsk_free(tsk);
 	put_signal_struct(tsk->signal);
 	sched_core_free(tsk);
-
-	if (!profile_handoff_task(tsk))
-		free_task(tsk);
+	free_task(tsk);
 }
 EXPORT_SYMBOL_GPL(__put_task_struct);
 
@@ -950,7 +951,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->splice_pipe = NULL;
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
-	tsk->pf_io_worker = NULL;
+	tsk->worker_private = NULL;
 
 	account_kernel_stack(tsk, 1);
 
@@ -1556,32 +1557,6 @@ out:
 	return error;
 }
 
-static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
-{
-#ifdef CONFIG_BLOCK
-	struct io_context *ioc = current->io_context;
-	struct io_context *new_ioc;
-
-	if (!ioc)
-		return 0;
-	/*
-	 * Share io context with parent, if CLONE_IO is set
-	 */
-	if (clone_flags & CLONE_IO) {
-		ioc_task_link(ioc);
-		tsk->io_context = ioc;
-	} else if (ioprio_valid(ioc->ioprio)) {
-		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
-		if (unlikely(!new_ioc))
-			return -ENOMEM;
-
-		new_ioc->ioprio = ioc->ioprio;
-		put_io_context(new_ioc);
-	}
-#endif
-	return 0;
-}
-
 static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct sighand_struct *sig;
@@ -2032,12 +2007,6 @@ static __latent_entropy struct task_struct *copy_process(
 		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
 	}
 
-	/*
-	 * This _must_ happen before we call free_task(), i.e. before we jump
-	 * to any of the bad_fork_* labels. This is to avoid freeing
-	 * p->set_child_tid which is (ab)used as a kthread's data pointer for
-	 * kernel threads (PF_KTHREAD).
-	 */
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
 	/*
 	 * Clear TID on mm_release()?
@@ -2052,18 +2021,18 @@ static __latent_entropy struct task_struct *copy_process(
 #ifdef CONFIG_PROVE_LOCKING
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
+	retval = copy_creds(p, clone_flags);
+	if (retval < 0)
+		goto bad_fork_free;
+
 	retval = -EAGAIN;
 	if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		if (p->real_cred->user != INIT_USER &&
 		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
-			goto bad_fork_free;
+			goto bad_fork_cleanup_count;
 	}
 	current->flags &= ~PF_NPROC_EXCEEDED;
 
-	retval = copy_creds(p, clone_flags);
-	if (retval < 0)
-		goto bad_fork_free;
-
 	/*
 	 * If multiple threads are within copy_process(), then this check
 	 * triggers too late. This doesn't hurt, the check is only there
@@ -2118,12 +2087,16 @@ static __latent_entropy struct task_struct *copy_process(
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
 	cgroup_fork(p);
+	if (p->flags & PF_KTHREAD) {
+		if (!set_kthread_struct(p))
+			goto bad_fork_cleanup_delayacct;
+	}
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
 	if (IS_ERR(p->mempolicy)) {
 		retval = PTR_ERR(p->mempolicy);
 		p->mempolicy = NULL;
-		goto bad_fork_cleanup_threadgroup_lock;
+		goto bad_fork_cleanup_delayacct;
 	}
 #endif
 #ifdef CONFIG_CPUSETS
@@ -2294,6 +2267,17 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_put_pidfd;
 
 	/*
+	 * Now that the cgroups are pinned, re-clone the parent cgroup and put
+	 * the new task on the correct runqueue. All this *before* the task
+	 * becomes visible.
+	 *
+	 * This isn't part of ->can_fork() because while the re-cloning is
+	 * cgroup specific, it unconditionally needs to place the task on a
+	 * runqueue.
+	 */
+	sched_cgroup_fork(p, args);
+
+	/*
 	 * From this point on we must avoid any synchronous user-space
 	 * communication until we take the tasklist-lock. In particular, we do
 	 * not want user-space to be able to predict the process start-time by
@@ -2350,10 +2334,6 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cancel_cgroup;
 	}
 
-	/* past the last point of failure */
-	if (pidfile)
-		fd_install(pidfd, pidfile);
-
 	init_task_pid_links(p);
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -2402,8 +2382,11 @@ static __latent_entropy struct task_struct *copy_process(
 	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
 
+	if (pidfile)
+		fd_install(pidfd, pidfile);
+
 	proc_fork_connector(p);
-	sched_post_fork(p, args);
+	sched_post_fork(p);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
@@ -2460,8 +2443,8 @@ bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
-bad_fork_cleanup_threadgroup_lock:
 #endif
+bad_fork_cleanup_delayacct:
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);