Merge branch 'topic/error' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator into regulator-fixed

1 files changed, 215 insertions, 47 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 5c2c355aa97f..623259fc794d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,57 +148,113 @@ static inline void free_task_struct(struct task_struct *tsk)
 }
 #endif
 
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
 {
 }
 
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
 
 /*
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
  * kmemcache based allocator.
  */
-# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
-						  int node)
+# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
+
+#ifdef CONFIG_VMAP_STACK
+/*
+ * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
+ * flush.  Try to minimize the number of calls by caching stacks.
+ */
+#define NR_CACHED_STACKS 2
+static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+#endif
+
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 {
-	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
-						  THREAD_SIZE_ORDER);
+#ifdef CONFIG_VMAP_STACK
+	void *stack;
+	int i;
+
+	local_irq_disable();
+	for (i = 0; i < NR_CACHED_STACKS; i++) {
+		struct vm_struct *s = this_cpu_read(cached_stacks[i]);
+
+		if (!s)
+			continue;
+		this_cpu_write(cached_stacks[i], NULL);
 
-	if (page)
-		memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-					    1 << THREAD_SIZE_ORDER);
+		tsk->stack_vm_area = s;
+		local_irq_enable();
+		return s->addr;
+	}
+	local_irq_enable();
+
+	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
+				     VMALLOC_START, VMALLOC_END,
+				     THREADINFO_GFP | __GFP_HIGHMEM,
+				     PAGE_KERNEL,
+				     0, node, __builtin_return_address(0));
+
+	/*
+	 * We can't call find_vm_area() in interrupt context, and
+	 * free_thread_stack() can be called in interrupt context,
+	 * so cache the vm_struct.
+	 */
+	if (stack)
+		tsk->stack_vm_area = find_vm_area(stack);
+	return stack;
+#else
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
+#endif
 }
 
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(struct task_struct *tsk)
 {
-	struct page *page = virt_to_page(ti);
+#ifdef CONFIG_VMAP_STACK
+	if (task_stack_vm_area(tsk)) {
+		unsigned long flags;
+		int i;
+
+		local_irq_save(flags);
+		for (i = 0; i < NR_CACHED_STACKS; i++) {
+			if (this_cpu_read(cached_stacks[i]))
+				continue;
+
+			this_cpu_write(cached_stacks[i], tsk->stack_vm_area);
+			local_irq_restore(flags);
+			return;
+		}
+		local_irq_restore(flags);
 
-	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-				    -(1 << THREAD_SIZE_ORDER));
-	__free_kmem_pages(page, THREAD_SIZE_ORDER);
+		vfree(tsk->stack);
+		return;
+	}
+#endif
+
+	__free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
 }
 # else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
 
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
-	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
 }
 
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(struct task_struct *tsk)
 {
-	kmem_cache_free(thread_info_cache, ti);
+	kmem_cache_free(thread_stack_cache, tsk->stack);
 }
 
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
 {
-	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+	thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
 					      THREAD_SIZE, 0, NULL);
-	BUG_ON(thread_info_cache == NULL);
+	BUG_ON(thread_stack_cache == NULL);
 }
 # endif
 #endif
@@ -221,18 +277,76 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-static void account_kernel_stack(struct thread_info *ti, int account)
+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);
+		}
+
+		/* All stack pages belong to the same memcg. */
+		memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB,
+					    account * (THREAD_SIZE / 1024));
+	} 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);
+
+		memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB,
+					    account * (THREAD_SIZE / 1024));
+	}
+}
+
+static void release_task_stack(struct task_struct *tsk)
 {
-	struct zone *zone = page_zone(virt_to_page(ti));
+	account_kernel_stack(tsk, -1);
+	arch_release_thread_stack(tsk->stack);
+	free_thread_stack(tsk);
+	tsk->stack = NULL;
+#ifdef CONFIG_VMAP_STACK
+	tsk->stack_vm_area = NULL;
+#endif
+}
 
-	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+void put_task_stack(struct task_struct *tsk)
+{
+	if (atomic_dec_and_test(&tsk->stack_refcount))
+		release_task_stack(tsk);
 }
+#endif
 
 void free_task(struct task_struct *tsk)
 {
-	account_kernel_stack(tsk->stack, -1);
-	arch_release_thread_info(tsk->stack);
-	free_thread_info(tsk->stack);
+#ifndef CONFIG_THREAD_INFO_IN_TASK
+	/*
+	 * The task is finally done with both the stack and thread_info,
+	 * so free both.
+	 */
+	release_task_stack(tsk);
+#else
+	/*
+	 * If the task had a separate stack allocation, it should be gone
+	 * by now.
+	 */
+	WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0);
+#endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
 	put_seccomp_filter(tsk);
@@ -245,6 +359,12 @@ static inline void free_signal_struct(struct signal_struct *sig)
 {
 	taskstats_tgid_free(sig);
 	sched_autogroup_exit(sig);
+	/*
+	 * __mmdrop is not safe to call from softirq context on x86 due to
+	 * pgd_dtor so postpone it to the async context
+	 */
+	if (sig->oom_mm)
+		mmdrop_async(sig->oom_mm);
 	kmem_cache_free(signal_cachep, sig);
 }
 
@@ -304,6 +424,7 @@ int arch_task_struct_size __read_mostly;
 
 void __init fork_init(void)
 {
+	int i;
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
@@ -323,6 +444,10 @@ void __init fork_init(void)
 	init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
 	init_task.signal->rlim[RLIMIT_SIGPENDING] =
 		init_task.signal->rlim[RLIMIT_NPROC];
+
+	for (i = 0; i < UCOUNT_COUNTS; i++) {
+		init_user_ns.ucount_max[i] = max_threads/2;
+	}
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -343,7 +468,8 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
-	struct thread_info *ti;
+	unsigned long *stack;
+	struct vm_struct *stack_vm_area;
 	int err;
 
 	if (node == NUMA_NO_NODE)
@@ -352,15 +478,30 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info_node(tsk, node);
-	if (!ti)
+	stack = alloc_thread_stack_node(tsk, node);
+	if (!stack)
 		goto free_tsk;
 
+	stack_vm_area = task_stack_vm_area(tsk);
+
 	err = arch_dup_task_struct(tsk, orig);
+
+	/*
+	 * arch_dup_task_struct() clobbers the stack-related fields.  Make
+	 * sure they're properly initialized before using any stack-related
+	 * functions again.
+	 */
+	tsk->stack = stack;
+#ifdef CONFIG_VMAP_STACK
+	tsk->stack_vm_area = stack_vm_area;
+#endif
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	atomic_set(&tsk->stack_refcount, 1);
+#endif
+
 	if (err)
-		goto free_ti;
+		goto free_stack;
 
-	tsk->stack = ti;
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -392,21 +533,22 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
 
-	account_kernel_stack(ti, 1);
+	account_kernel_stack(tsk, 1);
 
 	kcov_task_init(tsk);
 
 	return tsk;
 
-free_ti:
-	free_thread_info(ti);
+free_stack:
+	free_thread_stack(tsk);
 free_tsk:
 	free_task_struct(tsk);
 	return NULL;
 }
 
 #ifdef CONFIG_MMU
-static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+static __latent_entropy int dup_mmap(struct mm_struct *mm,
+					struct mm_struct *oldmm)
 {
 	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
@@ -713,6 +855,7 @@ static inline void __mmput(struct mm_struct *mm)
 	ksm_exit(mm);
 	khugepaged_exit(mm); /* must run before exit_mmap */
 	exit_mmap(mm);
+	mm_put_huge_zero_page(mm);
 	set_mm_exe_file(mm, NULL);
 	if (!list_empty(&mm->mmlist)) {
 		spin_lock(&mmlist_lock);
@@ -721,6 +864,7 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
+	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
@@ -801,6 +945,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
 EXPORT_SYMBOL(get_mm_exe_file);
 
 /**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+	struct file *exe_file = NULL;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm) {
+		if (!(task->flags & PF_KTHREAD))
+			exe_file = get_mm_exe_file(mm);
+	}
+	task_unlock(task);
+	return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
+/**
  * get_task_mm - acquire a reference to the task's mm
  *
  * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
@@ -915,14 +1082,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * If we're exiting normally, clear a user-space tid field if
-	 * requested.  We leave this alone when dying by signal, to leave
-	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
@@ -1277,7 +1442,8 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
  * parts of the process environment (as per the clone
  * flags). The actual kick-off is left to the caller.
  */
-static struct task_struct *copy_process(unsigned long clone_flags,
+static __latent_entropy struct task_struct *copy_process(
+					unsigned long clone_flags,
 					unsigned long stack_start,
 					unsigned long stack_size,
 					int __user *child_tidptr,
@@ -1406,7 +1572,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1558,6 +1723,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1658,6 +1824,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_thread:
@@ -1690,12 +1857,12 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
 	exit_creds(p);
 bad_fork_free:
+	put_task_stack(p);
 	free_task(p);
 fork_out:
 	return ERR_PTR(retval);
@@ -1761,6 +1928,7 @@ long _do_fork(unsigned long clone_flags,
 
 	p = copy_process(clone_flags, stack_start, stack_size,
 			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
+	add_latent_entropy();
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.