1 files changed, 63 insertions, 69 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 987b28a..728d5be 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -351,7 +351,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge;
-	struct mempolicy *pol;
 
 	uprobe_start_dup_mmap();
 	down_write(&oldmm->mmap_sem);
@@ -365,8 +364,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
 	mm->mmap_cache = NULL;
-	mm->free_area_cache = oldmm->mmap_base;
-	mm->cached_hole_size = ~0UL;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -402,11 +399,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 			goto fail_nomem;
 		*tmp = *mpnt;
 		INIT_LIST_HEAD(&tmp->anon_vma_chain);
-		pol = mpol_dup(vma_policy(mpnt));
-		retval = PTR_ERR(pol);
-		if (IS_ERR(pol))
+		retval = vma_dup_policy(mpnt, tmp);
+		if (retval)
 			goto fail_nomem_policy;
-		vma_set_policy(tmp, pol);
 		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
@@ -474,7 +469,7 @@ out:
 	uprobe_end_dup_mmap();
 	return retval;
 fail_nomem_anon_vma_fork:
-	mpol_put(pol);
+	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
 	kmem_cache_free(vm_area_cachep, tmp);
 fail_nomem:
@@ -524,7 +519,7 @@ static void mm_init_aio(struct mm_struct *mm)
 {
 #ifdef CONFIG_AIO
 	spin_lock_init(&mm->ioctx_lock);
-	INIT_HLIST_HEAD(&mm->ioctx_list);
+	mm->ioctx_table = NULL;
 #endif
 }
 
@@ -537,11 +532,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm->flags = (current->mm) ?
 		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
-	mm->nr_ptes = 0;
+	atomic_long_set(&mm->nr_ptes, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
-	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
 
@@ -567,7 +560,7 @@ static void check_mm(struct mm_struct *mm)
 					  "mm:%p idx:%d val:%ld\n", mm, i, x);
 	}
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	VM_BUG_ON(mm->pmd_huge_pte);
 #endif
 }
@@ -821,12 +814,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	memcpy(mm, oldmm, sizeof(*mm));
 	mm_init_cpumask(mm);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
 #endif
-#ifdef CONFIG_NUMA_BALANCING
-	mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
@@ -1121,6 +1111,12 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
 	INIT_LIST_HEAD(&tsk->cpu_timers[2]);
 }
 
+static inline void
+init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
+{
+	 task->pids[type].pid = pid;
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1171,12 +1167,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		return ERR_PTR(-EINVAL);
 
 	/*
-	 * If the new process will be in a different pid namespace
-	 * don't allow the creation of threads.
+	 * If the new process will be in a different pid or user namespace
+	 * do not allow it to share a thread group or signal handlers or
+	 * parent with the forking task.
 	 */
-	if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
-	    (task_active_pid_ns(current) != current->nsproxy->pid_ns))
-		return ERR_PTR(-EINVAL);
+	if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
+		    (task_active_pid_ns(current) !=
+				current->nsproxy->pid_ns_for_children))
+			return ERR_PTR(-EINVAL);
+	}
 
 	retval = security_task_create(clone_flags);
 	if (retval)
@@ -1199,8 +1199,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	retval = -EAGAIN;
 	if (atomic_read(&p->real_cred->user->processes) >=
 			task_rlimit(p, RLIMIT_NPROC)) {
-		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
-		    p->real_cred->user != INIT_USER)
+		if (p->real_cred->user != INIT_USER &&
+		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
 			goto bad_fork_free;
 	}
 	current->flags &= ~PF_NPROC_EXCEEDED;
@@ -1310,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p);
+	sched_fork(clone_flags, p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1349,16 +1349,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (pid != &init_struct_pid) {
 		retval = -ENOMEM;
-		pid = alloc_pid(p->nsproxy->pid_ns);
+		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
 		if (!pid)
 			goto bad_fork_cleanup_io;
 	}
 
-	p->pid = pid_nr(pid);
-	p->tgid = p->pid;
-	if (clone_flags & CLONE_THREAD)
-		p->tgid = current->tgid;
-
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
 	/*
 	 * Clear TID on mm_release()?
@@ -1375,7 +1370,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->pi_state_list);
 	p->pi_state_cache = NULL;
 #endif
-	uprobe_copy_process(p);
 	/*
 	 * sigaltstack should be cleared when sharing the same VM
 	 */
@@ -1394,12 +1388,19 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	clear_all_latency_tracing(p);
 
 	/* ok, now we should be set up.. */
-	if (clone_flags & CLONE_THREAD)
+	p->pid = pid_nr(pid);
+	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->group_leader = current->group_leader;
+		p->tgid = current->tgid;
+	} else {
+		if (clone_flags & CLONE_PARENT)
+			p->exit_signal = current->group_leader->exit_signal;
+		else
+			p->exit_signal = (clone_flags & CSIGNAL);
+		p->group_leader = p;
+		p->tgid = p->pid;
+	}
 
 	p->pdeath_signal = 0;
 	p->exit_state = 0;
@@ -1408,15 +1409,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
 	p->dirty_paused_when = 0;
 
-	/*
-	 * Ok, make it visible to the rest of the system.
-	 * We dont wake it up yet.
-	 */
-	p->group_leader = p;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	/* Need tasklist lock for parent etc handling! */
+	/*
+	 * Make it visible to the rest of the system, but dont wake it up yet.
+	 * Need tasklist lock for parent etc handling!
+	 */
 	write_lock_irq(&tasklist_lock);
 
 	/* CLONE_PARENT re-uses the old parent */
@@ -1446,18 +1445,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_free_pid;
 	}
 
-	if (clone_flags & CLONE_THREAD) {
-		current->signal->nr_threads++;
-		atomic_inc(&current->signal->live);
-		atomic_inc(&current->signal->sigcnt);
-		p->group_leader = current->group_leader;
-		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-	}
-
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
+		init_task_pid(p, PIDTYPE_PID, pid);
 		if (thread_group_leader(p)) {
+			init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
+			init_task_pid(p, PIDTYPE_SID, task_session(current));
+
 			if (is_child_reaper(pid)) {
 				ns_of_pid(pid)->child_reaper = p;
 				p->signal->flags |= SIGNAL_UNKILLABLE;
@@ -1465,13 +1460,19 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 			p->signal->leader_pid = pid;
 			p->signal->tty = tty_kref_get(current->signal->tty);
-			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
-			attach_pid(p, PIDTYPE_SID, task_session(current));
 			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
+			attach_pid(p, PIDTYPE_PGID);
+			attach_pid(p, PIDTYPE_SID);
 			__this_cpu_inc(process_counts);
+		} else {
+			current->signal->nr_threads++;
+			atomic_inc(&current->signal->live);
+			atomic_inc(&current->signal->sigcnt);
+			list_add_tail_rcu(&p->thread_group,
+					  &p->group_leader->thread_group);
 		}
-		attach_pid(p, PIDTYPE_PID, pid);
+		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;
 	}
 
@@ -1485,6 +1486,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
+	uprobe_copy_process(p, clone_flags);
 
 	return p;
 
@@ -1542,7 +1544,7 @@ static inline void init_idle_pids(struct pid_link *links)
 	}
 }
 
-struct task_struct * __cpuinit fork_idle(int cpu)
+struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
 	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
@@ -1571,15 +1573,6 @@ long do_fork(unsigned long clone_flags,
 	long nr;
 
 	/*
-	 * Do some preliminary argument and permissions checking before we
-	 * actually start allocating stuff
-	 */
-	if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
-		if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
-			return -EINVAL;
-	}
-
-	/*
 	 * Determine whether and which event to report to ptracer.  When
 	 * called from kernel_thread or CLONE_UNTRACED is explicitly
 	 * requested, no event is reported; otherwise, report if the event
@@ -1675,6 +1668,12 @@ SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
 		 int __user *, parent_tidptr,
 		 int __user *, child_tidptr,
 		 int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+		int, stack_size,
+		int __user *, parent_tidptr,
+		int __user *, child_tidptr,
+		int, tls_val)
 #else
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int __user *, parent_tidptr,
@@ -1814,11 +1813,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	if (unshare_flags & CLONE_NEWUSER)
 		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
-	 * If unsharing a pid namespace must also unshare the thread.
-	 */
-	if (unshare_flags & CLONE_NEWPID)
-		unshare_flags |= CLONE_THREAD;
-	/*
 	 * If unsharing a thread from a thread group, must also unshare vm.
 	 */
 	if (unshare_flags & CLONE_THREAD)