Merge branch 'master' into queue

* master: (15791 commits)
  Linux 3.9-rc1
  btrfs/raid56: Add missing #include <linux/vmalloc.h>
  fix compat_sys_rt_sigprocmask()
  SUNRPC: One line comment fix
  ext4: enable quotas before orphan cleanup
  ext4: don't allow quota mount options when quota feature enabled
  ext4: fix a warning from sparse check for ext4_dir_llseek
  ext4: convert number of blocks to clusters properly
  ext4: fix possible memory leak in ext4_remount()
  jbd2: fix ERR_PTR dereference in jbd2__journal_start
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  ...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	arch/x86/kernel/kvmclock.c

1 files changed, 73 insertions, 34 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3c31e874afad..8d932b1c9056 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti)
 static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 						  int node)
 {
-	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED,
 					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
@@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 
 static inline void free_thread_info(struct thread_info *ti)
 {
-	free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+	free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_info_cache;
@@ -413,7 +413,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
-			struct inode *inode = file->f_path.dentry->d_inode;
+			struct inode *inode = file_inode(file);
 			struct address_space *mapping = file->f_mapping;
 
 			get_file(file);
@@ -823,6 +823,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	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;
 
@@ -1041,8 +1044,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
-	if (clone_flags & CLONE_NEWPID)
-		sig->flags |= SIGNAL_UNKILLABLE;
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
@@ -1165,6 +1166,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 				current->signal->flags & SIGNAL_UNKILLABLE)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * If the new process will be in a different pid namespace
+	 * don't allow the creation of threads.
+	 */
+	if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
+	    (task_active_pid_ns(current) != current->nsproxy->pid_ns))
+		return ERR_PTR(-EINVAL);
+
 	retval = security_task_create(clone_flags);
 	if (retval)
 		goto fork_out;
@@ -1224,6 +1233,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+	seqlock_init(&p->vtime_seqlock);
+	p->vtime_snap = 0;
+	p->vtime_snap_whence = VTIME_SLEEPING;
+#endif
+
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
@@ -1435,8 +1450,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
 		if (thread_group_leader(p)) {
-			if (is_child_reaper(pid))
-				p->nsproxy->pid_ns->child_reaper = p;
+			if (is_child_reaper(pid)) {
+				ns_of_pid(pid)->child_reaper = p;
+				p->signal->flags |= SIGNAL_UNKILLABLE;
+			}
 
 			p->signal->leader_pid = pid;
 			p->signal->tty = tty_kref_get(current->signal->tty);
@@ -1470,8 +1487,6 @@ bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
 bad_fork_cleanup_namespaces:
-	if (unlikely(clone_flags & CLONE_NEWPID))
-		pid_ns_release_proc(p->nsproxy->pid_ns);
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm)
@@ -1551,15 +1566,9 @@ long do_fork(unsigned long clone_flags,
 	 * Do some preliminary argument and permissions checking before we
 	 * actually start allocating stuff
 	 */
-	if (clone_flags & CLONE_NEWUSER) {
-		if (clone_flags & CLONE_THREAD)
+	if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
+		if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
 			return -EINVAL;
-		/* hopefully this check will go away when userns support is
-		 * complete
-		 */
-		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
-				!capable(CAP_SETGID))
-			return -EPERM;
 	}
 
 	/*
@@ -1618,7 +1627,6 @@ long do_fork(unsigned long clone_flags,
 	return nr;
 }
 
-#ifdef CONFIG_GENERIC_KERNEL_THREAD
 /*
  * Create a kernel thread.
  */
@@ -1627,7 +1635,6 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
 		(unsigned long)arg, NULL, NULL);
 }
-#endif
 
 #ifdef __ARCH_WANT_SYS_FORK
 SYSCALL_DEFINE0(fork)
@@ -1667,8 +1674,10 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int, tls_val)
 #endif
 {
-	return do_fork(clone_flags, newsp, 0,
-		parent_tidptr, child_tidptr);
+	long ret = do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr);
+	asmlinkage_protect(5, ret, clone_flags, newsp,
+			parent_tidptr, child_tidptr, tls_val);
+	return ret;
 }
 #endif
 
@@ -1721,7 +1730,8 @@ 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))
+				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
+				CLONE_NEWUSER|CLONE_NEWPID))
 		return -EINVAL;
 	/*
 	 * Not implemented, but pretend it works if there is nothing to
@@ -1788,19 +1798,40 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
 	struct fs_struct *fs, *new_fs = NULL;
 	struct files_struct *fd, *new_fd = NULL;
+	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
 	int do_sysvsem = 0;
 	int err;
 
-	err = check_unshare_flags(unshare_flags);
-	if (err)
-		goto bad_unshare_out;
-
+	/*
+	 * If unsharing a user namespace must also unshare the thread.
+	 */
+	if (unshare_flags & CLONE_NEWUSER)
+		unshare_flags |= CLONE_THREAD;
+	/*
+	 * 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)
+		unshare_flags |= CLONE_VM;
+	/*
+	 * If unsharing vm, must also unshare signal handlers.
+	 */
+	if (unshare_flags & CLONE_VM)
+		unshare_flags |= CLONE_SIGHAND;
 	/*
 	 * If unsharing namespace, must also unshare filesystem information.
 	 */
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
+
+	err = check_unshare_flags(unshare_flags);
+	if (err)
+		goto bad_unshare_out;
 	/*
 	 * CLONE_NEWIPC must also detach from the undolist: after switching
 	 * to a new ipc namespace, the semaphore arrays from the old
@@ -1814,11 +1845,15 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
-	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs);
+	err = unshare_userns(unshare_flags, &new_cred);
 	if (err)
 		goto bad_unshare_cleanup_fd;
+	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
+					 new_cred, new_fs);
+	if (err)
+		goto bad_unshare_cleanup_cred;
 
-	if (new_fs || new_fd || do_sysvsem || new_nsproxy) {
+	if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
 		if (do_sysvsem) {
 			/*
 			 * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1826,10 +1861,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 			exit_sem(current);
 		}
 
-		if (new_nsproxy) {
+		if (new_nsproxy)
 			switch_task_namespaces(current, new_nsproxy);
-			new_nsproxy = NULL;
-		}
 
 		task_lock(current);
 
@@ -1851,11 +1884,17 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 
 		task_unlock(current);
-	}
 
-	if (new_nsproxy)
-		put_nsproxy(new_nsproxy);
+		if (new_cred) {
+			/* Install the new user namespace */
+			commit_creds(new_cred);
+			new_cred = NULL;
+		}
+	}
 
+bad_unshare_cleanup_cred:
+	if (new_cred)
+		put_cred(new_cred);
 bad_unshare_cleanup_fd:
 	if (new_fd)
 		put_files_struct(new_fd);