1 files changed, 142 insertions, 128 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 25e429152dd..ca406d91671 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/compat.h>
+#include <linux/kthread.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
 #include <linux/ptrace.h>
@@ -58,7 +59,6 @@
 #include <linux/taskstats_kern.h>
 #include <linux/random.h>
 #include <linux/tty.h>
-#include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
@@ -109,20 +109,25 @@ int nr_processes(void)
 }
 
 #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct()	kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
-# define free_task_struct(tsk)	kmem_cache_free(task_struct_cachep, (tsk))
+# define alloc_task_struct_node(node)		\
+		kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node)
+# define free_task_struct(tsk)			\
+		kmem_cache_free(task_struct_cachep, (tsk))
 static struct kmem_cache *task_struct_cachep;
 #endif
 
 #ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
+static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+						  int node)
 {
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	gfp_t mask = GFP_KERNEL | __GFP_ZERO;
 #else
 	gfp_t mask = GFP_KERNEL;
 #endif
-	return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
+	struct page *page = alloc_pages_node(node, mask, THREAD_SIZE_ORDER);
+
+	return page ? page_address(page) : NULL;
 }
 
 static inline void free_thread_info(struct thread_info *ti)
@@ -193,6 +198,7 @@ void __put_task_struct(struct task_struct *tsk)
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
 }
+EXPORT_SYMBOL_GPL(__put_task_struct);
 
 /*
  * macro override instead of weak attribute alias, to workaround
@@ -248,16 +254,16 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	struct task_struct *tsk;
 	struct thread_info *ti;
 	unsigned long *stackend;
-
+	int node = tsk_fork_get_node(orig);
 	int err;
 
 	prepare_to_copy(orig);
 
-	tsk = alloc_task_struct();
+	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info(tsk);
+	ti = alloc_thread_info_node(tsk, node);
 	if (!ti) {
 		free_task_struct(tsk);
 		return NULL;
@@ -376,15 +382,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
 				atomic_dec(&inode->i_writecount);
-			spin_lock(&mapping->i_mmap_lock);
+			mutex_lock(&mapping->i_mmap_mutex);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping->i_mmap_writable++;
-			tmp->vm_truncate_count = mpnt->vm_truncate_count;
 			flush_dcache_mmap_lock(mapping);
 			/* insert tmp into the share list, just after mpnt */
 			vma_prio_tree_add(tmp, mpnt);
 			flush_dcache_mmap_unlock(mapping);
-			spin_unlock(&mapping->i_mmap_lock);
+			mutex_unlock(&mapping->i_mmap_mutex);
 		}
 
 		/*
@@ -479,6 +484,20 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
+int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (oldmm)
+		cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
+	else
+		memset(mm_cpumask(mm), 0, cpumask_size());
+#endif
+	return 0;
+}
+
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
@@ -515,10 +534,20 @@ struct mm_struct * mm_alloc(void)
 	struct mm_struct * mm;
 
 	mm = allocate_mm();
-	if (mm) {
-		memset(mm, 0, sizeof(*mm));
-		mm = mm_init(mm, current);
+	if (!mm)
+		return NULL;
+
+	memset(mm, 0, sizeof(*mm));
+	mm = mm_init(mm, current);
+	if (!mm)
+		return NULL;
+
+	if (mm_init_cpumask(mm, NULL)) {
+		mm_free_pgd(mm);
+		free_mm(mm);
+		return NULL;
 	}
+
 	return mm;
 }
 
@@ -530,6 +559,7 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
+	free_cpumask_var(mm->cpu_vm_mask_var);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
@@ -566,6 +596,57 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
+/*
+ * We added or removed a vma mapping the executable. The vmas are only mapped
+ * during exec and are not mapped with the mmap system call.
+ * Callers must hold down_write() on the mm's mmap_sem for these
+ */
+void added_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas++;
+}
+
+void removed_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas--;
+	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+		fput(mm->exe_file);
+		mm->exe_file = NULL;
+	}
+
+}
+
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+	if (new_exe_file)
+		get_file(new_exe_file);
+	if (mm->exe_file)
+		fput(mm->exe_file);
+	mm->exe_file = new_exe_file;
+	mm->num_exe_file_vmas = 0;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+	struct file *exe_file;
+
+	/* We need mmap_sem to protect against races with removal of
+	 * VM_EXECUTABLE vmas */
+	down_read(&mm->mmap_sem);
+	exe_file = mm->exe_file;
+	if (exe_file)
+		get_file(exe_file);
+	up_read(&mm->mmap_sem);
+	return exe_file;
+}
+
+static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+	/* It's safe to write the exe_file pointer without exe_file_lock because
+	 * this is called during fork when the task is not yet in /proc */
+	newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
@@ -684,6 +765,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
+	if (mm_init_cpumask(mm, oldmm))
+		goto fail_nocpumask;
+
 	if (init_new_context(tsk, mm))
 		goto fail_nocontext;
 
@@ -710,6 +794,9 @@ fail_nomem:
 	return NULL;
 
 fail_nocontext:
+	free_cpumask_var(mm->cpu_vm_mask_var);
+
+fail_nocpumask:
 	/*
 	 * If init_new_context() failed, we cannot use mmput() to free the mm
 	 * because it calls destroy_context()
@@ -920,6 +1007,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->threadgroup_fork_lock);
+#endif
+
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
@@ -1096,12 +1187,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	posix_cpu_timers_init(p);
 
-	p->lock_depth = -1;		/* -1 = no lock */
 	do_posix_clock_monotonic_gettime(&p->start_time);
 	p->real_start_time = p->start_time;
 	monotonic_to_bootbased(&p->real_start_time);
 	p->io_context = NULL;
 	p->audit_context = NULL;
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_lock(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1146,7 +1238,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p, clone_flags);
+	sched_fork(p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1180,12 +1272,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		pid = alloc_pid(p->nsproxy->pid_ns);
 		if (!pid)
 			goto bad_fork_cleanup_io;
-
-		if (clone_flags & CLONE_NEWPID) {
-			retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
-			if (retval < 0)
-				goto bad_fork_free_pid;
-		}
 	}
 
 	p->pid = pid_nr(pid);
@@ -1193,17 +1279,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (clone_flags & CLONE_THREAD)
 		p->tgid = current->tgid;
 
-	if (current->nsproxy != p->nsproxy) {
-		retval = ns_cgroup_clone(p, pid);
-		if (retval)
-			goto bad_fork_free_pid;
-	}
-
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
 	/*
 	 * Clear TID on mm_release()?
 	 */
 	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
+#ifdef CONFIG_BLOCK
+	p->plug = NULL;
+#endif
 #ifdef CONFIG_FUTEX
 	p->robust_list = NULL;
 #ifdef CONFIG_COMPAT
@@ -1289,7 +1372,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		tracehook_finish_clone(p, clone_flags, trace);
 
 		if (thread_group_leader(p)) {
-			if (clone_flags & CLONE_NEWPID)
+			if (is_child_reaper(pid))
 				p->nsproxy->pid_ns->child_reaper = p;
 
 			p->signal->leader_pid = pid;
@@ -1309,6 +1392,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_unlock(current);
 	perf_event_fork(p);
 	return p;
 
@@ -1347,6 +1432,8 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_unlock(current);
 	cgroup_exit(p, cgroup_callbacks_done);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);
@@ -1460,7 +1547,7 @@ long do_fork(unsigned long clone_flags,
 		 */
 		p->flags &= ~PF_STARTING;
 
-		wake_up_new_task(p, clone_flags);
+		wake_up_new_task(p);
 
 		tracehook_report_clone_complete(trace, regs,
 						clone_flags, nr, p);
@@ -1512,38 +1599,24 @@ void __init proc_caches_init(void)
 }
 
 /*
- * Check constraints on flags passed to the unshare system call and
- * force unsharing of additional process context as appropriate.
+ * Check constraints on flags passed to the unshare system call.
  */
-static void check_unshare_flags(unsigned long *flags_ptr)
+static int check_unshare_flags(unsigned long unshare_flags)
 {
+	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
+				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
+				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
+		return -EINVAL;
 	/*
-	 * If unsharing a thread from a thread group, must also
-	 * unshare vm.
-	 */
-	if (*flags_ptr & CLONE_THREAD)
-		*flags_ptr |= CLONE_VM;
-
-	/*
-	 * If unsharing vm, must also unshare signal handlers.
-	 */
-	if (*flags_ptr & CLONE_VM)
-		*flags_ptr |= CLONE_SIGHAND;
-
-	/*
-	 * If unsharing namespace, must also unshare filesystem information.
+	 * Not implemented, but pretend it works if there is nothing to
+	 * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND
+	 * needs to unshare vm.
 	 */
-	if (*flags_ptr & CLONE_NEWNS)
-		*flags_ptr |= CLONE_FS;
-}
-
-/*
- * Unsharing of tasks created with CLONE_THREAD is not supported yet
- */
-static int unshare_thread(unsigned long unshare_flags)
-{
-	if (unshare_flags & CLONE_THREAD)
-		return -EINVAL;
+	if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
+		/* FIXME: get_task_mm() increments ->mm_users */
+		if (atomic_read(&current->mm->mm_users) > 1)
+			return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1570,34 +1643,6 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 }
 
 /*
- * Unsharing of sighand is not supported yet
- */
-static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
-{
-	struct sighand_struct *sigh = current->sighand;
-
-	if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1)
-		return -EINVAL;
-	else
-		return 0;
-}
-
-/*
- * Unshare vm if it is being shared
- */
-static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
-{
-	struct mm_struct *mm = current->mm;
-
-	if ((unshare_flags & CLONE_VM) &&
-	    (mm && atomic_read(&mm->mm_users) > 1)) {
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/*
  * Unshare file descriptor table if it is being shared
  */
 static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
@@ -1625,45 +1670,37 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
  */
 SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
-	int err = 0;
 	struct fs_struct *fs, *new_fs = NULL;
-	struct sighand_struct *new_sigh = NULL;
-	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
 	struct files_struct *fd, *new_fd = NULL;
 	struct nsproxy *new_nsproxy = NULL;
 	int do_sysvsem = 0;
+	int err;
 
-	check_unshare_flags(&unshare_flags);
-
-	/* Return -EINVAL for all unsupported flags */
-	err = -EINVAL;
-	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
-				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
-				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
+	err = check_unshare_flags(unshare_flags);
+	if (err)
 		goto bad_unshare_out;
 
 	/*
+	 * If unsharing namespace, must also unshare filesystem information.
+	 */
+	if (unshare_flags & CLONE_NEWNS)
+		unshare_flags |= CLONE_FS;
+	/*
 	 * CLONE_NEWIPC must also detach from the undolist: after switching
 	 * to a new ipc namespace, the semaphore arrays from the old
 	 * namespace are unreachable.
 	 */
 	if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
 		do_sysvsem = 1;
-	if ((err = unshare_thread(unshare_flags)))
-		goto bad_unshare_out;
 	if ((err = unshare_fs(unshare_flags, &new_fs)))
-		goto bad_unshare_cleanup_thread;
-	if ((err = unshare_sighand(unshare_flags, &new_sigh)))
-		goto bad_unshare_cleanup_fs;
-	if ((err = unshare_vm(unshare_flags, &new_mm)))
-		goto bad_unshare_cleanup_sigh;
+		goto bad_unshare_out;
 	if ((err = unshare_fd(unshare_flags, &new_fd)))
-		goto bad_unshare_cleanup_vm;
+		goto bad_unshare_cleanup_fs;
 	if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
 			new_fs)))
 		goto bad_unshare_cleanup_fd;
 
-	if (new_fs ||  new_mm || new_fd || do_sysvsem || new_nsproxy) {
+	if (new_fs || new_fd || do_sysvsem || new_nsproxy) {
 		if (do_sysvsem) {
 			/*
 			 * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1689,19 +1726,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 			spin_unlock(&fs->lock);
 		}
 
-		if (new_mm) {
-			mm = current->mm;
-			active_mm = current->active_mm;
-			current->mm = new_mm;
-			current->active_mm = new_mm;
-			if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
-				atomic_dec(&mm->oom_disable_count);
-				atomic_inc(&new_mm->oom_disable_count);
-			}
-			activate_mm(active_mm, new_mm);
-			new_mm = mm;
-		}
-
 		if (new_fd) {
 			fd = current->files;
 			current->files = new_fd;
@@ -1718,20 +1742,10 @@ bad_unshare_cleanup_fd:
 	if (new_fd)
 		put_files_struct(new_fd);
 
-bad_unshare_cleanup_vm:
-	if (new_mm)
-		mmput(new_mm);
-
-bad_unshare_cleanup_sigh:
-	if (new_sigh)
-		if (atomic_dec_and_test(&new_sigh->count))
-			kmem_cache_free(sighand_cachep, new_sigh);
-
 bad_unshare_cleanup_fs:
 	if (new_fs)
 		free_fs_struct(new_fs);
 
-bad_unshare_cleanup_thread:
 bad_unshare_out:
 	return err;
 }