Merge tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael  Wysocki:
 "Again, the majority of changes go into the cpufreq subsystem, but
  there are no big features this time.  The cpufreq changes that stand
  out somewhat are the governor interface rework and improvements
  related to the handling of frequency tables.  Apart from those, there
  are fixes and new device/CPU IDs in drivers, cleanups and an
  improvement of the new schedutil governor.

  Next, there are some changes in the hibernation core, including a fix
  for a nasty problem related to the MONITOR/MWAIT usage by CPU offline
  during resume from hibernation, a few core improvements related to
  memory management during resume, a couple of additional debug features
  and cleanups.

  Finally, we have some fixes and cleanups in the devfreq subsystem,
  generic power domains framework improvements related to system
  suspend/resume, support for some new chips in intel_idle and in the
  power capping RAPL driver, a new version of the AnalyzeSuspend utility
  and some assorted fixes and cleanups.

  Specifics:

   - Rework the cpufreq governor interface to make it more
     straightforward and modify the conservative governor to avoid using
     transition notifications (Rafael Wysocki).

   - Rework the handling of frequency tables by the cpufreq core to make
     it more efficient (Viresh Kumar).

   - Modify the schedutil governor to reduce the number of wakeups it
     causes to occur in cases when the CPU frequency doesn't need to be
     changed (Steve Muckle, Viresh Kumar).

   - Fix some minor issues and clean up code in the cpufreq core and
     governors (Rafael Wysocki, Viresh Kumar).

   - Add Intel Broxton support to the intel_pstate driver (Srinivas
     Pandruvada).

   - Fix problems related to the config TDP feature and to the validity
     of the MSR_HWP_INTERRUPT register in intel_pstate (Jan Kiszka,
     Srinivas Pandruvada).

   - Make intel_pstate update the cpu_frequency tracepoint even if the
     frequency doesn't change to avoid confusing powertop (Rafael
     Wysocki).

   - Clean up the usage of __init/__initdata in intel_pstate, mark some
     of its internal variables as __read_mostly and drop an unused
     structure element from it (Jisheng Zhang, Carsten Emde).

   - Clean up the usage of some duplicate MSR symbols in intel_pstate
     and turbostat (Srinivas Pandruvada).

   - Update/fix the powernv, s3c24xx and mvebu cpufreq drivers (Akshay
     Adiga, Viresh Kumar, Ben Dooks).

   - Fix a regression (introduced during the 4.5 cycle) in the
     pcc-cpufreq driver by reverting the problematic commit (Andreas
     Herrmann).

   - Add support for Intel Denverton to intel_idle, clean up Broxton
     support in it and make it explicitly non-modular (Jacob Pan, Jan
     Beulich, Paul Gortmaker).

   - Add support for Denverton and Ivy Bridge server to the Intel RAPL
     power capping driver and make it more careful about the handing of
     MSRs that may not be present (Jacob Pan, Xiaolong Wang).

   - Fix resume from hibernation on x86-64 by making the CPU offline
     during resume avoid using MONITOR/MWAIT in the "play dead" loop
     which may lead to an inadvertent "revival" of a "dead" CPU and a
     page fault leading to a kernel crash from it (Rafael Wysocki).

   - Make memory management during resume from hibernation more
     straightforward (Rafael Wysocki).

   - Add debug features that should help to detect problems related to
     hibernation and resume from it (Rafael Wysocki, Chen Yu).

   - Clean up hibernation core somewhat (Rafael Wysocki).

   - Prevent KASAN from instrumenting the hibernation core which leads
     to large numbers of false-positives from it (James Morse).

   - Prevent PM (hibernate and suspend) notifiers from being called
     during the cleanup phase if they have not been called during the
     corresponding preparation phase which is possible if one of the
     other notifiers returns an error at that time (Lianwei Wang).

   - Improve suspend-related debug printout in the tasks freezer and
     clean up suspend-related console handling (Roger Lu, Borislav
     Petkov).

   - Update the AnalyzeSuspend script in the kernel sources to version
     4.2 (Todd Brandt).

   - Modify the generic power domains framework to make it handle system
     suspend/resume better (Ulf Hansson).

   - Make the runtime PM framework avoid resuming devices synchronously
     when user space changes the runtime PM settings for them and
     improve its error reporting (Rafael Wysocki, Linus Walleij).

   - Fix error paths in devfreq drivers (exynos, exynos-ppmu,
     exynos-bus) and in the core, make some devfreq code explicitly
     non-modular and change some of it into tristate (Bartlomiej
     Zolnierkiewicz, Peter Chen, Paul Gortmaker).

   - Add DT support to the generic PM clocks management code and make it
     export some more symbols (Jon Hunter, Paul Gortmaker).

   - Make the PCI PM core code slightly more robust against possible
     driver errors (Andy Shevchenko).

   - Make it possible to change DESTDIR and PREFIX in turbostat (Andy
     Shevchenko)"

* tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (89 commits)
  Revert "cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency"
  PM / hibernate: Introduce test_resume mode for hibernation
  cpufreq: export cpufreq_driver_resolve_freq()
  cpufreq: Disallow ->resolve_freq() for drivers providing ->target_index()
  PCI / PM: check all fields in pci_set_platform_pm()
  cpufreq: acpi-cpufreq: use cached frequency mapping when possible
  cpufreq: schedutil: map raw required frequency to driver frequency
  cpufreq: add cpufreq_driver_resolve_freq()
  cpufreq: intel_pstate: Check cpuid for MSR_HWP_INTERRUPT
  intel_pstate: Update cpu_frequency tracepoint every time
  cpufreq: intel_pstate: clean remnant struct element
  PM / tools: scripts: AnalyzeSuspend v4.2
  x86 / hibernate: Use hlt_play_dead() when resuming from hibernation
  cpufreq: powernv: Replacing pstate_id with frequency table index
  intel_pstate: Fix MSR_CONFIG_TDP_x addressing in core_get_max_pstate()
  PM / hibernate: Image data protection during restoration
  PM / hibernate: Add missing braces in __register_nosave_region()
  PM / hibernate: Clean up comments in snapshot.c
  PM / hibernate: Clean up function headers in snapshot.c
  PM / hibernate: Add missing braces in hibernate_setup()
  ...

10 files changed, 632 insertions, 474 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 9021387c6ff4..a881c6a7ba74 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -52,6 +52,7 @@ enum {
 #ifdef CONFIG_SUSPEND
 	HIBERNATION_SUSPEND,
 #endif
+	HIBERNATION_TEST_RESUME,
 	/* keep last */
 	__HIBERNATION_AFTER_LAST
 };
@@ -409,6 +410,11 @@ int hibernation_snapshot(int platform_mode)
 	goto Close;
 }
 
+int __weak hibernate_resume_nonboot_cpu_disable(void)
+{
+	return disable_nonboot_cpus();
+}
+
 /**
  * resume_target_kernel - Restore system state from a hibernation image.
  * @platform_mode: Whether or not to use the platform driver.
@@ -433,7 +439,7 @@ static int resume_target_kernel(bool platform_mode)
 	if (error)
 		goto Cleanup;
 
-	error = disable_nonboot_cpus();
+	error = hibernate_resume_nonboot_cpu_disable();
 	if (error)
 		goto Enable_cpus;
 
@@ -642,12 +648,39 @@ static void power_down(void)
 		cpu_relax();
 }
 
+static int load_image_and_restore(void)
+{
+	int error;
+	unsigned int flags;
+
+	pr_debug("PM: Loading hibernation image.\n");
+
+	lock_device_hotplug();
+	error = create_basic_memory_bitmaps();
+	if (error)
+		goto Unlock;
+
+	error = swsusp_read(&flags);
+	swsusp_close(FMODE_READ);
+	if (!error)
+		hibernation_restore(flags & SF_PLATFORM_MODE);
+
+	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
+	swsusp_free();
+	free_basic_memory_bitmaps();
+ Unlock:
+	unlock_device_hotplug();
+
+	return error;
+}
+
 /**
  * hibernate - Carry out system hibernation, including saving the image.
  */
 int hibernate(void)
 {
-	int error;
+	int error, nr_calls = 0;
+	bool snapshot_test = false;
 
 	if (!hibernation_available()) {
 		pr_debug("PM: Hibernation not available.\n");
@@ -662,9 +695,11 @@ 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();
@@ -697,8 +732,12 @@ int hibernate(void)
 		pr_debug("PM: writing image.\n");
 		error = swsusp_write(flags);
 		swsusp_free();
-		if (!error)
-			power_down();
+		if (!error) {
+			if (hibernation_mode == HIBERNATION_TEST_RESUME)
+				snapshot_test = true;
+			else
+				power_down();
+		}
 		in_suspend = 0;
 		pm_restore_gfp_mask();
 	} else {
@@ -709,12 +748,18 @@ int hibernate(void)
 	free_basic_memory_bitmaps();
  Thaw:
 	unlock_device_hotplug();
+	if (snapshot_test) {
+		pr_debug("PM: Checking hibernation image\n");
+		error = swsusp_check();
+		if (!error)
+			error = load_image_and_restore();
+	}
 	thaw_processes();
 
 	/* 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:
@@ -740,8 +785,7 @@ int hibernate(void)
  */
 static int software_resume(void)
 {
-	int error;
-	unsigned int flags;
+	int error, nr_calls = 0;
 
 	/*
 	 * If the user said "noresume".. bail out early.
@@ -827,35 +871,20 @@ 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();
 	if (error)
 		goto Close_Finish;
-
-	pr_debug("PM: Loading hibernation image.\n");
-
-	lock_device_hotplug();
-	error = create_basic_memory_bitmaps();
-	if (error)
-		goto Thaw;
-
-	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ);
-	if (!error)
-		hibernation_restore(flags & SF_PLATFORM_MODE);
-
-	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
-	swsusp_free();
-	free_basic_memory_bitmaps();
- Thaw:
-	unlock_device_hotplug();
+	error = load_image_and_restore();
 	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 */
@@ -878,6 +907,7 @@ static const char * const hibernation_modes[] = {
 #ifdef CONFIG_SUSPEND
 	[HIBERNATION_SUSPEND]	= "suspend",
 #endif
+	[HIBERNATION_TEST_RESUME]	= "test_resume",
 };
 
 /*
@@ -924,6 +954,7 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 #ifdef CONFIG_SUSPEND
 		case HIBERNATION_SUSPEND:
 #endif
+		case HIBERNATION_TEST_RESUME:
 			break;
 		case HIBERNATION_PLATFORM:
 			if (hibernation_ops)
@@ -970,6 +1001,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 #ifdef CONFIG_SUSPEND
 		case HIBERNATION_SUSPEND:
 #endif
+		case HIBERNATION_TEST_RESUME:
 			hibernation_mode = mode;
 			break;
 		case HIBERNATION_PLATFORM:
@@ -1115,13 +1147,16 @@ static int __init resume_offset_setup(char *str)
 
 static int __init hibernate_setup(char *str)
 {
-	if (!strncmp(str, "noresume", 8))
+	if (!strncmp(str, "noresume", 8)) {
 		noresume = 1;
-	else if (!strncmp(str, "nocompress", 10))
+	} else if (!strncmp(str, "nocompress", 10)) {
 		nocompress = 1;
-	else if (!strncmp(str, "no", 2)) {
+	} else if (!strncmp(str, "no", 2)) {
 		noresume = 1;
 		nohibernate = 1;
+	} else if (IS_ENABLED(CONFIG_DEBUG_RODATA)
+		   && !strncmp(str, "protect_image", 13)) {
+		enable_restore_image_protection();
 	}
 	return 1;
 }
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..242d8b827dd5 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -38,6 +38,8 @@ static inline char *check_image_kernel(struct swsusp_info *info)
 }
 #endif /* CONFIG_ARCH_HIBERNATION_HEADER */
 
+extern int hibernate_resume_nonboot_cpu_disable(void);
+
 /*
  * Keep some memory free so that I/O operations can succeed without paging
  * [Might this be more than 4 MB?]
@@ -59,6 +61,13 @@ extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);
 extern int hibernation_platform_enter(void);
 
+#ifdef CONFIG_DEBUG_RODATA
+/* kernel/power/snapshot.c */
+extern void enable_restore_image_protection(void);
+#else
+static inline void enable_restore_image_protection(void) {}
+#endif /* CONFIG_DEBUG_RODATA */
+
 #else /* !CONFIG_HIBERNATION */
 
 static inline void hibernate_reserved_size_init(void) {}
@@ -200,6 +209,8 @@ 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..d90df926b59f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -38,6 +38,43 @@
 
 #include "power.h"
 
+#ifdef CONFIG_DEBUG_RODATA
+static bool hibernate_restore_protection;
+static bool hibernate_restore_protection_active;
+
+void enable_restore_image_protection(void)
+{
+	hibernate_restore_protection = true;
+}
+
+static inline void hibernate_restore_protection_begin(void)
+{
+	hibernate_restore_protection_active = hibernate_restore_protection;
+}
+
+static inline void hibernate_restore_protection_end(void)
+{
+	hibernate_restore_protection_active = false;
+}
+
+static inline void hibernate_restore_protect_page(void *page_address)
+{
+	if (hibernate_restore_protection_active)
+		set_memory_ro((unsigned long)page_address, 1);
+}
+
+static inline void hibernate_restore_unprotect_page(void *page_address)
+{
+	if (hibernate_restore_protection_active)
+		set_memory_rw((unsigned long)page_address, 1);
+}
+#else
+static inline void hibernate_restore_protection_begin(void) {}
+static inline void hibernate_restore_protection_end(void) {}
+static inline void hibernate_restore_protect_page(void *page_address) {}
+static inline void hibernate_restore_unprotect_page(void *page_address) {}
+#endif /* CONFIG_DEBUG_RODATA */
+
 static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
@@ -67,25 +104,32 @@ void __init hibernate_image_size_init(void)
 	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
 }
 
-/* List of PBEs needed for restoring the pages that were allocated before
+/*
+ * List of PBEs needed for restoring the pages that were allocated before
  * the suspend and included in the suspend image, but have also been
  * allocated by the "resume" kernel, so their contents cannot be written
  * directly to their "original" page frames.
  */
 struct pbe *restore_pblist;
 
-/* Pointer to an auxiliary buffer (1 page) */
-static void *buffer;
+/* struct linked_page is used to build chains of pages */
 
-/**
- *	@safe_needed - on resume, for storing the PBE list and the image,
- *	we can only use memory pages that do not conflict with the pages
- *	used before suspend.  The unsafe pages have PageNosaveFree set
- *	and we count them using unsafe_pages.
- *
- *	Each allocated image page is marked as PageNosave and PageNosaveFree
- *	so that swsusp_free() can release it.
+#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;
 
 #define PG_ANY		0
 #define PG_SAFE		1
@@ -94,6 +138,19 @@ static void *buffer;
 
 static unsigned int allocated_unsafe_pages;
 
+/**
+ * get_image_page - Allocate a page for a hibernation image.
+ * @gfp_mask: GFP mask for the allocation.
+ * @safe_needed: Get pages that were not used before hibernation (restore only)
+ *
+ * During image restoration, for storing the PBE list and the image data, we can
+ * only use memory pages that do not conflict with the pages used before
+ * hibernation.  The "unsafe" pages have PageNosaveFree set and we count them
+ * using allocated_unsafe_pages.
+ *
+ * Each allocated image page is marked as PageNosave and PageNosaveFree so that
+ * swsusp_free() can release it.
+ */
 static void *get_image_page(gfp_t gfp_mask, int safe_needed)
 {
 	void *res;
@@ -113,9 +170,21 @@ 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)
@@ -130,11 +199,22 @@ 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)
+ * free_image_page - Free a page allocated for hibernation image.
+ * @addr: Address of the page to free.
+ * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page.
+ *
+ * The page to free should have been allocated by get_image_page() (page flags
+ * set by it are affected).
  */
-
 static inline void free_image_page(void *addr, int clear_nosave_free)
 {
 	struct page *page;
@@ -150,17 +230,8 @@ 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)
+static inline void free_list_of_pages(struct linked_page *list,
+				      int clear_page_nosave)
 {
 	while (list) {
 		struct linked_page *lp = list->next;
@@ -170,30 +241,28 @@ free_list_of_pages(struct linked_page *list, int clear_page_nosave)
 	}
 }
 
-/**
-  *	struct chain_allocator is used for allocating small objects out of
-  *	a linked list of pages called 'the chain'.
-  *
-  *	The chain grows each time when there is no room for a new object in
-  *	the current page.  The allocated objects cannot be freed individually.
-  *	It is only possible to free them all at once, by freeing the entire
-  *	chain.
-  *
-  *	NOTE: The chain allocator may be inefficient if the allocated objects
-  *	are not much smaller than PAGE_SIZE.
-  */
-
+/*
+ * struct chain_allocator is used for allocating small objects out of
+ * a linked list of pages called 'the chain'.
+ *
+ * The chain grows each time when there is no room for a new object in
+ * the current page.  The allocated objects cannot be freed individually.
+ * It is only possible to free them all at once, by freeing the entire
+ * chain.
+ *
+ * NOTE: The chain allocator may be inefficient if the allocated objects
+ * are not much smaller than PAGE_SIZE.
+ */
 struct chain_allocator {
 	struct linked_page *chain;	/* the chain */
 	unsigned int used_space;	/* total size of objects allocated out
-					 * of the current page
-					 */
+					   of the current page */
 	gfp_t gfp_mask;		/* mask for allocating pages */
 	int safe_needed;	/* if set, only "safe" pages are allocated */
 };
 
-static void
-chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed)
+static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask,
+		       int safe_needed)
 {
 	ca->chain = NULL;
 	ca->used_space = LINKED_PAGE_DATA_SIZE;
@@ -208,7 +277,8 @@ 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;
 
@@ -222,44 +292,44 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 }
 
 /**
- *	Data types related to memory bitmaps.
+ * Data types related to memory bitmaps.
  *
- *	Memory bitmap is a structure consiting of many linked lists of
- *	objects.  The main list's elements are of type struct zone_bitmap
- *	and each of them corresonds to one zone.  For each zone bitmap
- *	object there is a list of objects of type struct bm_block that
- *	represent each blocks of bitmap in which information is stored.
+ * Memory bitmap is a structure consiting of many linked lists of
+ * objects.  The main list's elements are of type struct zone_bitmap
+ * and each of them corresonds to one zone.  For each zone bitmap
+ * object there is a list of objects of type struct bm_block that
+ * represent each blocks of bitmap in which information is stored.
  *
- *	struct memory_bitmap contains a pointer to the main list of zone
- *	bitmap objects, a struct bm_position used for browsing the bitmap,
- *	and a pointer to the list of pages used for allocating all of the
- *	zone bitmap objects and bitmap block objects.
+ * struct memory_bitmap contains a pointer to the main list of zone
+ * bitmap objects, a struct bm_position used for browsing the bitmap,
+ * and a pointer to the list of pages used for allocating all of the
+ * zone bitmap objects and bitmap block objects.
  *
- *	NOTE: It has to be possible to lay out the bitmap in memory
- *	using only allocations of order 0.  Additionally, the bitmap is
- *	designed to work with arbitrary number of zones (this is over the
- *	top for now, but let's avoid making unnecessary assumptions ;-).
+ * NOTE: It has to be possible to lay out the bitmap in memory
+ * using only allocations of order 0.  Additionally, the bitmap is
+ * designed to work with arbitrary number of zones (this is over the
+ * top for now, but let's avoid making unnecessary assumptions ;-).
  *
- *	struct zone_bitmap contains a pointer to a list of bitmap block
- *	objects and a pointer to the bitmap block object that has been
- *	most recently used for setting bits.  Additionally, it contains the
- *	pfns that correspond to the start and end of the represented zone.
+ * struct zone_bitmap contains a pointer to a list of bitmap block
+ * objects and a pointer to the bitmap block object that has been
+ * most recently used for setting bits.  Additionally, it contains the
+ * PFNs that correspond to the start and end of the represented zone.
  *
- *	struct bm_block contains a pointer to the memory page in which
- *	information is stored (in the form of a block of bitmap)
- *	It also contains the pfns that correspond to the start and end of
- *	the represented memory area.
+ * struct bm_block contains a pointer to the memory page in which
+ * information is stored (in the form of a block of bitmap)
+ * It also contains the pfns that correspond to the start and end of
+ * the represented memory area.
  *
- *	The memory bitmap is organized as a radix tree to guarantee fast random
- *	access to the bits. There is one radix tree for each zone (as returned
- *	from create_mem_extents).
+ * The memory bitmap is organized as a radix tree to guarantee fast random
+ * access to the bits. There is one radix tree for each zone (as returned
+ * from create_mem_extents).
  *
- *	One radix tree is represented by one struct mem_zone_bm_rtree. There are
- *	two linked lists for the nodes of the tree, one for the inner nodes and
- *	one for the leave nodes. The linked leave nodes are used for fast linear
- *	access of the memory bitmap.
+ * One radix tree is represented by one struct mem_zone_bm_rtree. There are
+ * two linked lists for the nodes of the tree, one for the inner nodes and
+ * one for the leave nodes. The linked leave nodes are used for fast linear
+ * access of the memory bitmap.
  *
- *	The struct rtree_node represents one node of the radix tree.
+ * The struct rtree_node represents one node of the radix tree.
  */
 
 #define BM_END_OF_MAP	(~0UL)
@@ -305,9 +375,8 @@ struct bm_position {
 struct memory_bitmap {
 	struct list_head zones;
 	struct linked_page *p_list;	/* list of pages used to store zone
-					 * bitmap objects and bitmap block
-					 * objects
-					 */
+					   bitmap objects and bitmap block
+					   objects */
 	struct bm_position cur;	/* most recently used bit position */
 };
 
@@ -321,12 +390,12 @@ struct memory_bitmap {
 #endif
 #define BM_RTREE_LEVEL_MASK	((1UL << BM_RTREE_LEVEL_SHIFT) - 1)
 
-/*
- *	alloc_rtree_node - Allocate a new node and add it to the radix tree.
+/**
+ * alloc_rtree_node - Allocate a new node and add it to the radix tree.
  *
- *	This function is used to allocate inner nodes as well as the
- *	leave nodes of the radix tree. It also adds the node to the
- *	corresponding linked list passed in by the *list parameter.
+ * This function is used to allocate inner nodes as well as the
+ * leave nodes of the radix tree. It also adds the node to the
+ * corresponding linked list passed in by the *list parameter.
  */
 static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed,
 					   struct chain_allocator *ca,
@@ -347,12 +416,12 @@ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed,
 	return node;
 }
 
-/*
- *	add_rtree_block - Add a new leave node to the radix tree
+/**
+ * add_rtree_block - Add a new leave node to the radix tree.
  *
- *	The leave nodes need to be allocated in order to keep the leaves
- *	linked list in order. This is guaranteed by the zone->blocks
- *	counter.
+ * The leave nodes need to be allocated in order to keep the leaves
+ * linked list in order. This is guaranteed by the zone->blocks
+ * counter.
  */
 static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask,
 			   int safe_needed, struct chain_allocator *ca)
@@ -417,17 +486,18 @@ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask,
 static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone,
 			       int clear_nosave_free);
 
-/*
- *	create_zone_bm_rtree - create a radix tree for one zone
+/**
+ * create_zone_bm_rtree - Create a radix tree for one zone.
  *
- *	Allocated the mem_zone_bm_rtree structure and initializes it.
- *	This function also allocated and builds the radix tree for the
- *	zone.
+ * Allocated the mem_zone_bm_rtree structure and initializes it.
+ * This function also allocated and builds the radix tree for the
+ * zone.
  */
-static struct mem_zone_bm_rtree *
-create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed,
-		     struct chain_allocator *ca,
-		     unsigned long start, unsigned long end)
+static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask,
+						      int safe_needed,
+						      struct chain_allocator *ca,
+						      unsigned long start,
+						      unsigned long end)
 {
 	struct mem_zone_bm_rtree *zone;
 	unsigned int i, nr_blocks;
@@ -454,12 +524,12 @@ create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed,
 	return zone;
 }
 
-/*
- *	free_zone_bm_rtree - Free the memory of the radix tree
+/**
+ * free_zone_bm_rtree - Free the memory of the radix tree.
  *
- *	Free all node pages of the radix tree. The mem_zone_bm_rtree
- *	structure itself is not freed here nor are the rtree_node
- *	structs.
+ * Free all node pages of the radix tree. The mem_zone_bm_rtree
+ * structure itself is not freed here nor are the rtree_node
+ * structs.
  */
 static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone,
 			       int clear_nosave_free)
@@ -492,8 +562,8 @@ struct mem_extent {
 };
 
 /**
- *	free_mem_extents - free a list of memory extents
- *	@list - list of extents to empty
+ * free_mem_extents - Free a list of memory extents.
+ * @list: List of extents to free.
  */
 static void free_mem_extents(struct list_head *list)
 {
@@ -506,10 +576,11 @@ static void free_mem_extents(struct list_head *list)
 }
 
 /**
- *	create_mem_extents - create a list of memory extents representing
- *	                     contiguous ranges of PFNs
- *	@list - list to put the extents into
- *	@gfp_mask - mask to use for memory allocations
+ * create_mem_extents - Create a list of memory extents.
+ * @list: List to put the extents into.
+ * @gfp_mask: Mask to use for memory allocations.
+ *
+ * The extents represent contiguous ranges of PFNs.
  */
 static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 {
@@ -565,10 +636,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 }
 
 /**
-  *	memory_bm_create - allocate memory for a memory bitmap
-  */
-static int
-memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
+ * memory_bm_create - Allocate memory for a memory bitmap.
+ */
+static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask,
+			    int safe_needed)
 {
 	struct chain_allocator ca;
 	struct list_head mem_extents;
@@ -607,8 +678,9 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 }
 
 /**
-  *	memory_bm_free - free memory occupied by the memory bitmap @bm
-  */
+ * memory_bm_free - Free memory occupied by the memory bitmap.
+ * @bm: Memory bitmap.
+ */
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 {
 	struct mem_zone_bm_rtree *zone;
@@ -622,14 +694,13 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 }
 
 /**
- *	memory_bm_find_bit - Find the bit for pfn in the memory
- *			     bitmap
+ * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap.
  *
- *	Find the bit in the bitmap @bm that corresponds to given pfn.
- *	The cur.zone, cur.block and cur.node_pfn member of @bm are
- *	updated.
- *	It walks the radix tree to find the page which contains the bit for
- *	pfn and returns the bit position in **addr and *bit_nr.
+ * Find the bit in memory bitmap @bm that corresponds to the given PFN.
+ * The cur.zone, cur.block and cur.node_pfn members of @bm are updated.
+ *
+ * Walk the radix tree to find the page containing the bit that represents @pfn
+ * and return the position of the bit in @addr and @bit_nr.
  */
 static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 			      void **addr, unsigned int *bit_nr)
@@ -658,10 +729,9 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 
 zone_found:
 	/*
-	 * We have a zone. Now walk the radix tree to find the leave
-	 * node for our pfn.
+	 * We have found the zone. Now walk the radix tree to find the leaf node
+	 * for our PFN.
 	 */
-
 	node = bm->cur.node;
 	if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
 		goto node_found;
@@ -754,14 +824,14 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
 }
 
 /*
- *	rtree_next_node - Jumps to the next leave node