Merge back earlier suspend/hibernation changes for v4.8.

10 files changed, 149 insertions, 95 deletions

diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index cb880a14cc39..eb4f717705ba 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,6 +1,8 @@
 
 ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
 
+KASAN_SANITIZE_snapshot.o	:= n
+
 obj-y				+= qos.o
 obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index aba9c545a0e3..0e781798b0b3 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -126,17 +126,17 @@ out:
 	return ret;
 }
 
-int pm_prepare_console(void)
+void pm_prepare_console(void)
 {
 	if (!pm_vt_switch())
-		return 0;
+		return;
 
 	orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1);
 	if (orig_fgconsole < 0)
-		return 1;
+		return;
 
 	orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
-	return 0;
+	return;
 }
 
 void pm_restore_console(void)
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index fca9254280ee..126e24caa82e 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -647,7 +647,7 @@ static void power_down(void)
  */
 int hibernate(void)
 {
-	int error;
+	int error, nr_calls = 0;
 
 	if (!hibernation_available()) {
 		pr_debug("PM: Hibernation not available.\n");
@@ -662,9 +662,11 @@ int hibernate(void)
 	}
 
 	pm_prepare_console();
-	error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Exit;
+	}
 
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
@@ -714,7 +716,7 @@ int hibernate(void)
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
-	pm_notifier_call_chain(PM_POST_HIBERNATION);
+	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
 	pm_restore_console();
 	atomic_inc(&snapshot_device_available);
  Unlock:
@@ -740,7 +742,7 @@ int hibernate(void)
  */
 static int software_resume(void)
 {
-	int error;
+	int error, nr_calls = 0;
 	unsigned int flags;
 
 	/*
@@ -827,9 +829,11 @@ static int software_resume(void)
 	}
 
 	pm_prepare_console();
-	error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Close_Finish;
+	}
 
 	pr_debug("PM: Preparing processes for restore.\n");
 	error = freeze_processes();
@@ -855,7 +859,7 @@ static int software_resume(void)
 	unlock_device_hotplug();
 	thaw_processes();
  Finish:
-	pm_notifier_call_chain(PM_POST_RESTORE);
+	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	pm_restore_console();
 	atomic_inc(&snapshot_device_available);
 	/* For success case, the suspend path will release the lock */
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 27946975eff0..5ea50b1b7595 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_pm_notifier);
 
-int pm_notifier_call_chain(unsigned long val)
+int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
 {
-	int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL);
+	int ret;
+
+	ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
+						nr_to_call, nr_calls);
 
 	return notifier_to_errno(ret);
 }
+int pm_notifier_call_chain(unsigned long val)
+{
+	return __pm_notifier_call_chain(val, -1, NULL);
+}
 
 /* If set, devices may be suspended and resumed asynchronously. */
 int pm_async_enabled = 1;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index efe1b3b17c88..51f02ecaf125 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -200,6 +200,8 @@ static inline void suspend_test_finish(const char *label) {}
 
 #ifdef CONFIG_PM_SLEEP
 /* kernel/power/main.c */
+extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call,
+				    int *nr_calls);
 extern int pm_notifier_call_chain(unsigned long val);
 #endif
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0c2ee9761d57..8f27d5a8adf6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -89,6 +89,9 @@ static int try_to_freeze_tasks(bool user_only)
 		       elapsed_msecs / 1000, elapsed_msecs % 1000,
 		       todo - wq_busy, wq_busy);
 
+		if (wq_busy)
+			show_workqueue_state();
+
 		if (!wakeup) {
 			read_lock(&tasklist_lock);
 			for_each_process_thread(g, p) {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 3a970604308f..94b6fe6c9ae3 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -74,6 +74,22 @@ void __init hibernate_image_size_init(void)
  */
 struct pbe *restore_pblist;
 
+/* struct linked_page is used to build chains of pages */
+
+#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))
+
+struct linked_page {
+	struct linked_page *next;
+	char data[LINKED_PAGE_DATA_SIZE];
+} __packed;
+
+/*
+ * List of "safe" pages (ie. pages that were not used by the image kernel
+ * before hibernation) that may be used as temporary storage for image kernel
+ * memory contents.
+ */
+static struct linked_page *safe_pages_list;
+
 /* Pointer to an auxiliary buffer (1 page) */
 static void *buffer;
 
@@ -113,9 +129,21 @@ static void *get_image_page(gfp_t gfp_mask, int safe_needed)
 	return res;
 }
 
+static void *__get_safe_page(gfp_t gfp_mask)
+{
+	if (safe_pages_list) {
+		void *ret = safe_pages_list;
+
+		safe_pages_list = safe_pages_list->next;
+		memset(ret, 0, PAGE_SIZE);
+		return ret;
+	}
+	return get_image_page(gfp_mask, PG_SAFE);
+}
+
 unsigned long get_safe_page(gfp_t gfp_mask)
 {
-	return (unsigned long)get_image_page(gfp_mask, PG_SAFE);
+	return (unsigned long)__get_safe_page(gfp_mask);
 }
 
 static struct page *alloc_image_page(gfp_t gfp_mask)
@@ -130,6 +158,14 @@ static struct page *alloc_image_page(gfp_t gfp_mask)
 	return page;
 }
 
+static void recycle_safe_page(void *page_address)
+{
+	struct linked_page *lp = page_address;
+
+	lp->next = safe_pages_list;
+	safe_pages_list = lp;
+}
+
 /**
  *	free_image_page - free page represented by @addr, allocated with
  *	get_image_page (page flags set by it must be cleared)
@@ -150,15 +186,6 @@ static inline void free_image_page(void *addr, int clear_nosave_free)
 	__free_page(page);
 }
 
-/* struct linked_page is used to build chains of pages */
-
-#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))
-
-struct linked_page {
-	struct linked_page *next;
-	char data[LINKED_PAGE_DATA_SIZE];
-} __packed;
-
 static inline void
 free_list_of_pages(struct linked_page *list, int clear_page_nosave)
 {
@@ -208,7 +235,8 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) {
 		struct linked_page *lp;
 
-		lp = get_image_page(ca->gfp_mask, ca->safe_needed);
+		lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) :
+					get_image_page(ca->gfp_mask, PG_ANY);
 		if (!lp)
 			return NULL;
 
@@ -832,6 +860,34 @@ struct nosave_region {
 
 static LIST_HEAD(nosave_regions);
 
+static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone)
+{
+	struct rtree_node *node;
+
+	list_for_each_entry(node, &zone->nodes, list)
+		recycle_safe_page(node->data);
+
+	list_for_each_entry(node, &zone->leaves, list)
+		recycle_safe_page(node->data);
+}
+
+static void memory_bm_recycle(struct memory_bitmap *bm)
+{
+	struct mem_zone_bm_rtree *zone;
+	struct linked_page *p_list;
+
+	list_for_each_entry(zone, &bm->zones, list)
+		recycle_zone_bm_rtree(zone);
+
+	p_list = bm->p_list;
+	while (p_list) {
+		struct linked_page *lp = p_list;
+
+		p_list = lp->next;
+		recycle_safe_page(lp);
+	}
+}
+
 /**
  *	register_nosave_region - register a range of page frames the contents
  *	of which should not be saved during the suspend (to be used in the early
@@ -1999,53 +2055,41 @@ int snapshot_read_next(struct snapshot_handle *handle)
 	return PAGE_SIZE;
 }
 
+static void duplicate_memory_bitmap(struct memory_bitmap *dst,
+				    struct memory_bitmap *src)
+{
+	unsigned long pfn;
+
+	memory_bm_position_reset(src);
+	pfn = memory_bm_next_pfn(src);
+	while (pfn != BM_END_OF_MAP) {
+		memory_bm_set_bit(dst, pfn);
+		pfn = memory_bm_next_pfn(src);
+	}
+}
+
 /**
  *	mark_unsafe_pages - mark the pages that cannot be used for storing
  *	the image during resume, because they conflict with the pages that
  *	had been used before suspend
  */
 
-static int mark_unsafe_pages(struct memory_bitmap *bm)
+static void mark_unsafe_pages(struct memory_bitmap *bm)
 {
-	struct zone *zone;
-	unsigned long pfn, max_zone_pfn;
+	unsigned long pfn;
 
-	/* Clear page flags */
-	for_each_populated_zone(zone) {
-		max_zone_pfn = zone_end_pfn(zone);
-		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (pfn_valid(pfn))
-				swsusp_unset_page_free(pfn_to_page(pfn));
+	/* Clear the "free"/"unsafe" bit for all PFNs */
+	memory_bm_position_reset(free_pages_map);
+	pfn = memory_bm_next_pfn(free_pages_map);
+	while (pfn != BM_END_OF_MAP) {
+		memory_bm_clear_current(free_pages_map);
+		pfn = memory_bm_next_pfn(free_pages_map);
 	}
 
-	/* Mark pages that correspond to the "original" pfns as "unsafe" */
-	memory_bm_position_reset(bm);
-	do {
-		pfn = memory_bm_next_pfn(bm);
-		if (likely(pfn != BM_END_OF_MAP)) {
-			if (likely(pfn_valid(pfn)))
-				swsusp_set_page_free(pfn_to_page(pfn));
-			else
-				return -EFAULT;
-		}
-	} while (pfn != BM_END_OF_MAP);
+	/* Mark pages that correspond to the "original" PFNs as "unsafe" */
+	duplicate_memory_bitmap(free_pages_map, bm);
 
 	allocated_unsafe_pages = 0;
-
-	return 0;
-}
-
-static void
-duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src)
-{
-	unsigned long pfn;
-
-	memory_bm_position_reset(src);
-	pfn = memory_bm_next_pfn(src);
-	while (pfn != BM_END_OF_MAP) {
-		memory_bm_set_bit(dst, pfn);
-		pfn = memory_bm_next_pfn(src);
-	}
 }
 
 static int check_header(struct swsusp_info *info)
@@ -2095,7 +2139,7 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		/* Extract and buffer page key for data page (s390 only). */
 		page_key_memorize(buf + j);
 
-		if (memory_bm_pfn_present(bm, buf[j]))
+		if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j]))
 			memory_bm_set_bit(bm, buf[j]);
 		else
 			return -EFAULT;
@@ -2104,11 +2148,6 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 	return 0;
 }
 
-/* List of "safe" pages that may be used to store data loaded from the suspend
- * image
- */
-static struct linked_page *safe_pages_list;
-
 #ifdef CONFIG_HIGHMEM
 /* struct highmem_pbe is used for creating the list of highmem pages that
  * should be restored atomically during the resume from disk, because the page
@@ -2334,7 +2373,7 @@ static int
 prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 {
 	unsigned int nr_pages, nr_highmem;
-	struct linked_page *sp_list, *lp;
+	struct linked_page *lp;
 	int error;
 
 	/* If there is no highmem, the buffer will not be necessary */
@@ -2342,9 +2381,7 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 	buffer = NULL;
 
 	nr_highmem = count_highmem_image_pages(bm);
-	error = mark_unsafe_pages(bm);
-	if (error)
-		goto Free;
+	mark_unsafe_pages(bm);
 
 	error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE);
 	if (error)
@@ -2362,9 +2399,9 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 	 * NOTE: This way we make sure there will be enough safe pages for the
 	 * chain_alloc() in get_buffer().  It is a bit wasteful, but
 	 * nr_copy_pages cannot be greater than 50% of the memory anyway.
+	 *
+	 * nr_copy_pages cannot be less than allocated_unsafe_pages too.
 	 */
-	sp_list = NULL;
-	/* nr_copy_pages cannot be lesser than allocated_unsafe_pages */
 	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
 	nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE);
 	while (nr_pages > 0) {
@@ -2373,12 +2410,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 			error = -ENOMEM;
 			goto Free;
 		}
-		lp->next = sp_list;
-		sp_list = lp;
+		lp->next = safe_pages_list;
+		safe_pages_list = lp;
 		nr_pages--;
 	}
 	/* Preallocate memory for the image */
-	safe_pages_list = NULL;
 	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
 	while (nr_pages > 0) {
 		lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC);
@@ -2396,12 +2432,6 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 		swsusp_set_page_free(virt_to_page(lp));
 		nr_pages--;
 	}
-	/* Free the reserved safe pages so that chain_alloc() can use them */
-	while (sp_list) {
-		lp = sp_list->next;
-		free_image_page(sp_list, PG_UNSAFE_CLEAR);
-		sp_list = lp;
-	}
 	return 0;
 
  Free:
@@ -2491,6 +2521,8 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		if (error)
 			return error;
 
+		safe_pages_list = NULL;
+
 		error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
 		if (error)
 			return error;
@@ -2546,9 +2578,9 @@ void snapshot_write_finalize(struct snapshot_handle *handle)
 	/* Restore page key for data page (s390 only). */
 	page_key_write(handle->buffer);
 	page_key_free();
-	/* Free only if we have loaded the image entirely */
+	/* Do that only if we have loaded the image entirely */
 	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
-		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
+		memory_bm_recycle(&orig_bm);
 		free_highmem_data();
 	}
 }
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 5b70d64b871e..0acab9d7f96f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -266,16 +266,18 @@ static int suspend_test(int level)
  */
 static int suspend_prepare(suspend_state_t state)
 {
-	int error;
+	int error, nr_calls = 0;
 
 	if (!sleep_state_supported(state))
 		return -EPERM;
 
 	pm_prepare_console();
 
-	error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
-	if (error)
+	error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
 		goto Finish;
+	}
 
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
@@ -286,7 +288,7 @@ static int suspend_prepare(suspend_state_t state)
 	suspend_stats.failed_freeze++;
 	dpm_save_failed_step(SUSPEND_FREEZE);
  Finish:
-	pm_notifier_call_chain(PM_POST_SUSPEND);
+	__pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
 	pm_restore_console();
 	return error;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 526e8911460a..35310b627388 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1);
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
-	int error;
+	int error, nr_calls = 0;
 
 	if (!hibernation_available())
 		return -EPERM;
@@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
-		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
 		if (error)
-			pm_notifier_call_chain(PM_POST_HIBERNATION);
+			__pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
 	} else {
 		/*
 		 * Resuming.  We may need to wait for the image device to
@@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
 		if (!error) {
 			error = create_basic_memory_bitmaps();
 			data->free_bitmaps = !error;
-		}
+		} else
+			nr_calls--;
+
 		if (error)
-			pm_notifier_call_chain(PM_POST_RESTORE);
+			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	}
 	if (error)
 		atomic_inc(&snapshot_device_available);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e1c0e996b5ae..619e80ce4a59 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4369,8 +4369,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 /**
  * show_workqueue_state - dump workqueue state
  *
- * Called from a sysrq handler and prints out all busy workqueues and
- * pools.
+ * Called from a sysrq handler or try_to_freeze_tasks() and prints out
+ * all busy workqueues and pools.
  */
 void show_workqueue_state(void)
 {