Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few random little subsystems

 - almost all of the MM patches which are staged ahead of linux-next
   material. I'll trickle to post-linux-next work in as the dependents
   get merged up.

Subsystems affected by this patch series: kthread, kbuild, ide, ntfs,
ocfs2, arch, and mm (slab-generic, slab, slub, dax, debug, pagecache,
gup, swap, shmem, memcg, pagemap, mremap, hmm, vmalloc, documentation,
kasan, pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
oom-kill, migration, cma, page-poison, userfaultfd, zswap, zsmalloc,
uaccess, zram, and cleanups).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (200 commits)
  mm: cleanup kstrto*() usage
  mm: fix fall-through warnings for Clang
  mm: slub: convert sysfs sprintf family to sysfs_emit/sysfs_emit_at
  mm: shmem: convert shmem_enabled_show to use sysfs_emit_at
  mm:backing-dev: use sysfs_emit in macro defining functions
  mm: huge_memory: convert remaining use of sprintf to sysfs_emit and neatening
  mm: use sysfs_emit for struct kobject * uses
  mm: fix kernel-doc markups
  zram: break the strict dependency from lzo
  zram: add stat to gather incompressible pages since zram set up
  zram: support page writeback
  mm/process_vm_access: remove redundant initialization of iov_r
  mm/zsmalloc.c: rework the list_add code in insert_zspage()
  mm/zswap: move to use crypto_acomp API for hardware acceleration
  mm/zswap: fix passing zero to 'PTR_ERR' warning
  mm/zswap: make struct kernel_param_ops definitions const
  userfaultfd/selftests: hint the test runner on required privilege
  userfaultfd/selftests: fix retval check for userfaultfd_open()
  userfaultfd/selftests: always dump something in modes
  userfaultfd: selftests: make __{s,u}64 format specifiers portable
  ...

8 files changed, 83 insertions, 22 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f2eeff74d713..fefa21981027 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -281,9 +281,6 @@ bool cgroup_ssid_enabled(int ssid)
  * - cpuset: a task can be moved into an empty cpuset, and again it takes
  *   masks of ancestors.
  *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
  * - blkcg: blk-throttle becomes properly hierarchical.
  *
  * - debug: disallowed on the default hierarchy.
@@ -5152,15 +5149,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 	if (err)
 		goto err_list_del;
 
-	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
-	    cgroup_parent(parent)) {
-		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
-			current->comm, current->pid, ss->name);
-		if (!strcmp(ss->name, "memory"))
-			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
-		ss->warned_broken_hierarchy = true;
-	}
-
 	return css;
 
 err_list_del:
diff --git a/kernel/fork.c b/kernel/fork.c
index 99c76dab31c1..d61fa86eaaad 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -385,7 +385,7 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		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,
+		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
 				      account * (THREAD_SIZE / 1024));
 }
 
@@ -1009,6 +1009,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm->vmacache_seqnum = 0;
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
+	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index e6aa66551241..a5eceecd4513 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -704,8 +704,15 @@ repeat:
 	raw_spin_unlock_irq(&worker->lock);
 
 	if (work) {
+		kthread_work_func_t func = work->func;
 		__set_current_state(TASK_RUNNING);
+		trace_sched_kthread_work_execute_start(work);
 		work->func(work);
+		/*
+		 * Avoid dereferencing work after this point.  The trace
+		 * event only cares about the address.
+		 */
+		trace_sched_kthread_work_execute_end(work, func);
 	} else if (!freezing(current))
 		schedule();
 
@@ -786,7 +793,25 @@ EXPORT_SYMBOL(kthread_create_worker);
  * A good practice is to add the cpu number also into the worker name.
  * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu).
  *
- * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
+ * CPU hotplug:
+ * The kthread worker API is simple and generic. It just provides a way
+ * to create, use, and destroy workers.
+ *
+ * It is up to the API user how to handle CPU hotplug. They have to decide
+ * how to handle pending work items, prevent queuing new ones, and
+ * restore the functionality when the CPU goes off and on. There are a
+ * few catches:
+ *
+ *    - CPU affinity gets lost when it is scheduled on an offline CPU.
+ *
+ *    - The worker might not exist when the CPU was off when the user
+ *      created the workers.
+ *
+ * Good practice is to implement two CPU hotplug callbacks and to
+ * destroy/create the worker when the CPU goes down/up.
+ *
+ * Return:
+ * The pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
  * when the needed structures could not get allocated, and ERR_PTR(-EINTR)
  * when the worker was SIGKILLed.
  */
@@ -834,6 +859,8 @@ static void kthread_insert_work(struct kthread_worker *worker,
 {
 	kthread_insert_work_sanity_check(worker, work);
 
+	trace_sched_kthread_work_queue_work(worker, work);
+
 	list_add_tail(&work->node, pos);
 	work->worker = worker;
 	if (!worker->current_work && likely(worker->task))
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2fc7d509a34f..da0b41914177 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -326,7 +326,7 @@ static int create_image(int platform_mode)
 
 	if (!in_suspend) {
 		events_check_enabled = false;
-		clear_free_pages();
+		clear_or_poison_free_pages();
 	}
 
 	platform_leave(platform_mode);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 24f12d534515..778bf431ec02 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -106,7 +106,7 @@ extern int create_basic_memory_bitmaps(void);
 extern void free_basic_memory_bitmaps(void);
 extern int hibernate_preallocate_memory(void);
 
-extern void clear_free_pages(void);
+extern void clear_or_poison_free_pages(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 46b1804c1ddf..d63560e1cf87 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -76,6 +76,40 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
 static inline void hibernate_restore_unprotect_page(void *page_address) {}
 #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
 
+
+/*
+ * The calls to set_direct_map_*() should not fail because remapping a page
+ * here means that we only update protection bits in an existing PTE.
+ * It is still worth to have a warning here if something changes and this
+ * will no longer be the case.
+ */
+static inline void hibernate_map_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		int ret = set_direct_map_default_noflush(page);
+
+		if (ret)
+			pr_warn_once("Failed to remap page\n");
+	} else {
+		debug_pagealloc_map_pages(page, 1);
+	}
+}
+
+static inline void hibernate_unmap_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		unsigned long addr = (unsigned long)page_address(page);
+		int ret  = set_direct_map_invalid_noflush(page);
+
+		if (ret)
+			pr_warn_once("Failed to remap page\n");
+
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	} else {
+		debug_pagealloc_unmap_pages(page, 1);
+	}
+}
+
 static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
@@ -1144,7 +1178,15 @@ void free_basic_memory_bitmaps(void)
 	pr_debug("Basic memory bitmaps freed\n");
 }
 
-void clear_free_pages(void)
+static void clear_or_poison_free_page(struct page *page)
+{
+	if (page_poisoning_enabled_static())
+		__kernel_poison_pages(page, 1);
+	else if (want_init_on_free())
+		clear_highpage(page);
+}
+
+void clear_or_poison_free_pages(void)
 {
 	struct memory_bitmap *bm = free_pages_map;
 	unsigned long pfn;
@@ -1152,12 +1194,12 @@ void clear_free_pages(void)
 	if (WARN_ON(!(free_pages_map)))
 		return;
 
-	if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) {
+	if (page_poisoning_enabled() || want_init_on_free()) {
 		memory_bm_position_reset(bm);
 		pfn = memory_bm_next_pfn(bm);
 		while (pfn != BM_END_OF_MAP) {
 			if (pfn_valid(pfn))
-				clear_highpage(pfn_to_page(pfn));
+				clear_or_poison_free_page(pfn_to_page(pfn));
 
 			pfn = memory_bm_next_pfn(bm);
 		}
@@ -1355,9 +1397,9 @@ static void safe_copy_page(void *dst, struct page *s_page)
 	if (kernel_page_present(s_page)) {
 		do_copy_page(dst, page_address(s_page));
 	} else {
-		kernel_map_pages(s_page, 1, 1);
+		hibernate_map_page(s_page);
 		do_copy_page(dst, page_address(s_page));
-		kernel_map_pages(s_page, 1, 0);
+		hibernate_unmap_page(s_page);
 	}
 }
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index add677d79fcf..61db50f7ca86 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -57,7 +57,7 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 		return 0;
 	}
 
-	ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+	ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
 	mmput(mm);
 
 	return ret;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c71da2a59e12..b5295a0b0536 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1327,6 +1327,9 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 {
 	struct worker_pool *pool = pwq->pool;
 
+	/* record the work call stack in order to print it in KASAN reports */
+	kasan_record_aux_stack(work);
+
 	/* we own @work, set data and link */
 	set_work_pwq(work, pwq, extra_flags);
 	list_add_tail(&work->entry, head);