1 files changed, 52 insertions, 112 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index fc72f09a61b2..4d32190861bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -261,7 +261,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 					     THREAD_SIZE_ORDER);
 
 	if (likely(page)) {
-		tsk->stack = page_address(page);
+		tsk->stack = kasan_reset_tag(page_address(page));
 		return tsk->stack;
 	}
 	return NULL;
@@ -276,13 +276,8 @@ static inline void free_thread_stack(struct task_struct *tsk)
 	if (vm) {
 		int i;
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     -(int)(PAGE_SIZE / 1024));
-
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
 			memcg_kmem_uncharge_page(vm->pages[i], 0);
-		}
 
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
 			if (this_cpu_cmpxchg(cached_stacks[i],
@@ -307,6 +302,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 {
 	unsigned long *stack;
 	stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+	stack = kasan_reset_tag(stack);
 	tsk->stack = stack;
 	return stack;
 }
@@ -359,7 +355,13 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 
 	if (new) {
-		*new = *orig;
+		ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
+		ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
+		/*
+		 * orig->shared.rb may be modified concurrently, but the clone
+		 * will be reinitialized.
+		 */
+		*new = data_race(*orig);
 		INIT_LIST_HEAD(&new->anon_vma_chain);
 		new->vm_next = new->vm_prev = NULL;
 	}
@@ -376,31 +378,14 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
-
-	if (vm) {
-		int i;
-
-		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
-
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_zone_page_state(page_zone(vm->pages[i]),
-					    NR_KERNEL_STACK_KB,
-					    PAGE_SIZE / 1024 * account);
-		}
-	} else {
-		/*
-		 * All stack pages are in the same zone and belong to the
-		 * same memcg.
-		 */
-		struct page *first_page = virt_to_page(stack);
-
-		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
-				    THREAD_SIZE / 1024 * account);
 
-		mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
-				    account * (THREAD_SIZE / 1024));
-	}
+	/* All stack pages are in the same node. */
+	if (vm)
+		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
+	else
+		mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
@@ -409,24 +394,23 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 	int ret;
 
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
 	if (vm) {
 		int i;
 
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
 			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
-			 * pointer is NULL, and both memcg_kmem_uncharge_page()
-			 * and mod_memcg_page_state() in free_thread_stack()
-			 * will ignore this page. So it's safe.
+			 * pointer is NULL, and memcg_kmem_uncharge_page() in
+			 * free_thread_stack() will ignore this page.
 			 */
 			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
 						     0);
 			if (ret)
 				return ret;
-
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     PAGE_SIZE / 1024);
 		}
 	}
 #endif
@@ -473,7 +457,6 @@ void free_task(struct task_struct *tsk)
 #endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
-	put_seccomp_filter(tsk);
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
@@ -1474,7 +1457,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 		goto out;
 	}
 
-	newf = dup_fd(oldf, &error);
+	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
 	if (!newf)
 		goto out;
 
@@ -1787,22 +1770,18 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
  */
 static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 {
-	struct task_struct *task;
 	struct pid *pid = file->private_data;
 	__poll_t poll_flags = 0;
 
 	poll_wait(file, &pid->wait_pidfd, pts);
 
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
 	/*
 	 * Inform pollers only when the whole thread group exits.
 	 * If the thread group leader exits before all other threads in the
 	 * group, then poll(2) should block, similar to the wait(2) family.
 	 */
-	if (!task || (task->exit_state && thread_group_empty(task)))
+	if (thread_group_exited(pid))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
-	rcu_read_unlock();
 
 	return poll_flags;
 }
@@ -2035,17 +2014,11 @@ static __latent_entropy struct task_struct *copy_process(
 	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
-	p->irq_events = 0;
-	p->hardirq_enable_ip = 0;
-	p->hardirq_enable_event = 0;
-	p->hardirq_disable_ip = _THIS_IP_;
-	p->hardirq_disable_event = 0;
-	p->softirqs_enabled = 1;
-	p->softirq_enable_ip = _THIS_IP_;
-	p->softirq_enable_event = 0;
-	p->softirq_disable_ip = 0;
-	p->softirq_disable_event = 0;
-	p->softirq_context = 0;
+	memset(&p->irqtrace, 0, sizeof(p->irqtrace));
+	p->irqtrace.hardirq_disable_ip	= _THIS_IP_;
+	p->irqtrace.softirq_enable_ip	= _THIS_IP_;
+	p->softirqs_enabled		= 1;
+	p->softirq_context		= 0;
 #endif
 
 	p->pagefault_disabled = 0;
@@ -2102,8 +2075,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread_tls(clone_flags, args->stack, args->stack_size, p,
-				 args->tls);
+	retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -2302,6 +2274,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
+	sched_post_fork(p);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
@@ -2421,6 +2394,20 @@ long _do_fork(struct kernel_clone_args *args)
 	long nr;
 
 	/*
+	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
+	 * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are
+	 * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate
+	 * field in struct clone_args and it still doesn't make sense to have
+	 * them both point at the same memory location. Performing this check
+	 * here has the advantage that we don't need to have a separate helper
+	 * to check for legacy clone().
+	 */
+	if ((args->flags & CLONE_PIDFD) &&
+	    (args->flags & CLONE_PARENT_SETTID) &&
+	    (args->pidfd == args->parent_tid))
+		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
@@ -2477,42 +2464,6 @@ long _do_fork(struct kernel_clone_args *args)
 	return nr;
 }
 
-bool legacy_clone_args_valid(const struct kernel_clone_args *kargs)
-{
-	/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
-	if ((kargs->flags & CLONE_PIDFD) &&
-	    (kargs->flags & CLONE_PARENT_SETTID))
-		return false;
-
-	return true;
-}
-
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-/* For compatibility with architectures that call do_fork directly rather than
- * using the syscall entry points below. */
-long do_fork(unsigned long clone_flags,
-	      unsigned long stack_start,
-	      unsigned long stack_size,
-	      int __user *parent_tidptr,
-	      int __user *child_tidptr)
-{
-	struct kernel_clone_args args = {
-		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
-		.pidfd		= parent_tidptr,
-		.child_tid	= child_tidptr,
-		.parent_tid	= parent_tidptr,
-		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
-		.stack		= stack_start,
-		.stack_size	= stack_size,
-	};
-
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
-	return _do_fork(&args);
-}
-#endif
-
 /*
  * Create a kernel thread.
  */
@@ -2591,24 +2542,12 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 #endif
 
 #ifdef __ARCH_WANT_SYS_CLONE3
 
-/*
- * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
- * the registers containing the syscall arguments for clone. This doesn't work
- * with clone3 since the TLS value is passed in clone_args instead.
- */
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-#error clone3 requires copy_thread_tls support in arch
-#endif
-
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)
@@ -2905,14 +2844,15 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
+int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+	       struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
 	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, &error);
+		*new_fdp = dup_fd(fd, max_fds, &error);
 		if (!*new_fdp)
 			return error;
 	}
@@ -2923,7 +2863,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by do_fork() cannot be used here directly
+ * functions used by _do_fork() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.
@@ -2972,7 +2912,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, &new_fd);
+	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3061,7 +3001,7 @@ int unshare_files(struct files_struct **displaced)
 	struct files_struct *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, &copy);
+	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
 	if (error || !copy) {
 		*displaced = NULL;
 		return error;