1 files changed, 107 insertions, 649 deletions

diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index d967e875ee8..c05f46e7348 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -1,11 +1,10 @@
 /*
  * linux/kernel/power/swsusp.c
  *
- * This file is to realize architecture-independent
- * machine suspend feature using pretty near only high-level routines
+ * This file provides code to write suspend image to swap and read it back.
  *
  * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
- * Copyright (C) 1998,2001-2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
  *
  * This file is released under the GPLv2.
  *
@@ -47,11 +46,7 @@
 #include <linux/utsname.h>
 #include <linux/version.h>
 #include <linux/delay.h>
-#include <linux/reboot.h>
 #include <linux/bitops.h>
-#include <linux/vt_kern.h>
-#include <linux/kbd_kern.h>
-#include <linux/keyboard.h>
 #include <linux/spinlock.h>
 #include <linux/genhd.h>
 #include <linux/kernel.h>
@@ -63,10 +58,8 @@
 #include <linux/swapops.h>
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
-#include <linux/console.h>
 #include <linux/highmem.h>
 #include <linux/bio.h>
-#include <linux/mount.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -80,36 +73,31 @@
 
 #include "power.h"
 
+#ifdef CONFIG_HIGHMEM
+int save_highmem(void);
+int restore_highmem(void);
+#else
+static int save_highmem(void) { return 0; }
+static int restore_highmem(void) { return 0; }
+#endif
+
 #define CIPHER "aes"
 #define MAXKEY 32
 #define MAXIV  32
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-/* Variables to be preserved over suspend */
-static int nr_copy_pages_check;
-
 extern char resume_file[];
 
 /* Local variables that should not be affected by save */
-static unsigned int nr_copy_pages __nosavedata = 0;
+unsigned int nr_copy_pages __nosavedata = 0;
 
 /* Suspend pagedir is allocated before final copy, therefore it
    must be freed after resume
 
-   Warning: this is evil. There are actually two pagedirs at time of
-   resume. One is "pagedir_save", which is empty frame allocated at
-   time of suspend, that must be freed. Second is "pagedir_nosave",
-   allocated at time of resume, that travels through memory not to
-   collide with anything.
-
    Warning: this is even more evil than it seems. Pagedirs this file
    talks about are completely different from page directories used by
    MMU hardware.
  */
 suspend_pagedir_t *pagedir_nosave __nosavedata = NULL;
-static suspend_pagedir_t *pagedir_save;
 
 #define SWSUSP_SIG	"S1SUSPEND"
 
@@ -124,12 +112,6 @@ static struct swsusp_header {
 static struct swsusp_info swsusp_info;
 
 /*
- * XXX: We try to keep some more pages free so that I/O operations succeed
- * without paging. Might this be more?
- */
-#define PAGES_FOR_IO	512
-
-/*
  * Saving part...
  */
 
@@ -141,8 +123,8 @@ static struct swsusp_info swsusp_info;
 static unsigned short swapfile_used[MAX_SWAPFILES];
 static unsigned short root_swap;
 
-static int write_page(unsigned long addr, swp_entry_t * loc);
-static int bio_read_page(pgoff_t page_off, void * page);
+static int write_page(unsigned long addr, swp_entry_t *loc);
+static int bio_read_page(pgoff_t page_off, void *page);
 
 static u8 key_iv[MAXKEY+MAXIV];
 
@@ -363,7 +345,7 @@ static void lock_swapdevices(void)
 }
 
 /**
- *	write_swap_page - Write one page to a fresh swap location.
+ *	write_page - Write one page to a fresh swap location.
  *	@addr:	Address we're writing.
  *	@loc:	Place to store the entry we used.
  *
@@ -374,7 +356,7 @@ static void lock_swapdevices(void)
  *	This is a partial improvement, since we will at least return other
  *	errors, though we need to eventually fix the damn code.
  */
-static int write_page(unsigned long addr, swp_entry_t * loc)
+static int write_page(unsigned long addr, swp_entry_t *loc)
 {
 	swp_entry_t entry;
 	int error = 0;
@@ -402,15 +384,14 @@ static int write_page(unsigned long addr, swp_entry_t * loc)
 static void data_free(void)
 {
 	swp_entry_t entry;
-	int i;
+	struct pbe *p;
 
-	for (i = 0; i < nr_copy_pages; i++) {
-		entry = (pagedir_nosave + i)->swap_address;
+	for_each_pbe (p, pagedir_nosave) {
+		entry = p->swap_address;
 		if (entry.val)
 			swap_free(entry);
 		else
 			break;
-		(pagedir_nosave + i)->swap_address = (swp_entry_t){0};
 	}
 }
 
@@ -512,8 +493,8 @@ static void free_pagedir_entries(void)
 static int write_pagedir(void)
 {
 	int error = 0;
-	unsigned n = 0;
-	struct pbe * pbe;
+	unsigned int n = 0;
+	struct pbe *pbe;
 
 	printk( "Writing pagedir...");
 	for_each_pb_page (pbe, pagedir_nosave) {
@@ -527,6 +508,26 @@ static int write_pagedir(void)
 }
 
 /**
+ *	enough_swap - Make sure we have enough swap to save the image.
+ *
+ *	Returns TRUE or FALSE after checking the total amount of swap
+ *	space avaiable.
+ *
+ *	FIXME: si_swapinfo(&i) returns all swap devices information.
+ *	We should only consider resume_device.
+ */
+
+static int enough_swap(unsigned int nr_pages)
+{
+	struct sysinfo i;
+
+	si_swapinfo(&i);
+	pr_debug("swsusp: available swap: %lu pages\n", i.freeswap);
+	return i.freeswap > (nr_pages + PAGES_FOR_IO +
+		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
+}
+
+/**
  *	write_suspend_image - Write entire image and metadata.
  *
  */
@@ -534,6 +535,11 @@ static int write_suspend_image(void)
 {
 	int error;
 
+	if (!enough_swap(nr_copy_pages)) {
+		printk(KERN_ERR "swsusp: Not enough free swap\n");
+		return -ENOSPC;
+	}
+
 	init_header();
 	if ((error = data_write()))
 		goto FreeData;
@@ -553,433 +559,6 @@ static int write_suspend_image(void)
 	goto Done;
 }
 
-
-#ifdef CONFIG_HIGHMEM
-struct highmem_page {
-	char *data;
-	struct page *page;
-	struct highmem_page *next;
-};
-
-static struct highmem_page *highmem_copy;
-
-static int save_highmem_zone(struct zone *zone)
-{
-	unsigned long zone_pfn;
-	mark_free_pages(zone);
-	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
-		struct page *page;
-		struct highmem_page *save;
-		void *kaddr;
-		unsigned long pfn = zone_pfn + zone->zone_start_pfn;
-
-		if (!(pfn%1000))
-			printk(".");
-		if (!pfn_valid(pfn))
-			continue;
-		page = pfn_to_page(pfn);
-		/*
-		 * This condition results from rvmalloc() sans vmalloc_32()
-		 * and architectural memory reservations. This should be
-		 * corrected eventually when the cases giving rise to this
-		 * are better understood.
-		 */
-		if (PageReserved(page)) {
-			printk("highmem reserved page?!\n");
-			continue;
-		}
-		BUG_ON(PageNosave(page));
-		if (PageNosaveFree(page))
-			continue;
-		save = kmalloc(sizeof(struct highmem_page), GFP_ATOMIC);
-		if (!save)
-			return -ENOMEM;
-		save->next = highmem_copy;
-		save->page = page;
-		save->data = (void *) get_zeroed_page(GFP_ATOMIC);
-		if (!save->data) {
-			kfree(save);
-			return -ENOMEM;
-		}
-		kaddr = kmap_atomic(page, KM_USER0);
-		memcpy(save->data, kaddr, PAGE_SIZE);
-		kunmap_atomic(kaddr, KM_USER0);
-		highmem_copy = save;
-	}
-	return 0;
-}
-#endif /* CONFIG_HIGHMEM */
-
-
-static int save_highmem(void)
-{
-#ifdef CONFIG_HIGHMEM
-	struct zone *zone;
-	int res = 0;
-
-	pr_debug("swsusp: Saving Highmem\n");
-	for_each_zone (zone) {
-		if (is_highmem(zone))
-			res = save_highmem_zone(zone);
-		if (res)
-			return res;
-	}
-#endif
-	return 0;
-}
-
-static int restore_highmem(void)
-{
-#ifdef CONFIG_HIGHMEM
-	printk("swsusp: Restoring Highmem\n");
-	while (highmem_copy) {
-		struct highmem_page *save = highmem_copy;
-		void *kaddr;
-		highmem_copy = save->next;
-
-		kaddr = kmap_atomic(save->page, KM_USER0);
-		memcpy(kaddr, save->data, PAGE_SIZE);
-		kunmap_atomic(kaddr, KM_USER0);
-		free_page((long) save->data);
-		kfree(save);
-	}
-#endif
-	return 0;
-}
-
-
-static int pfn_is_nosave(unsigned long pfn)
-{
-	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
-	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
-	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
-/**
- *	saveable - Determine whether a page should be cloned or not.
- *	@pfn:	The page
- *
- *	We save a page if it's Reserved, and not in the range of pages
- *	statically defined as 'unsaveable', or if it isn't reserved, and
- *	isn't part of a free chunk of pages.
- */
-
-static int saveable(struct zone * zone, unsigned long * zone_pfn)
-{
-	unsigned long pfn = *zone_pfn + zone->zone_start_pfn;
-	struct page * page;
-
-	if (!pfn_valid(pfn))
-		return 0;
-
-	page = pfn_to_page(pfn);
-	BUG_ON(PageReserved(page) && PageNosave(page));
-	if (PageNosave(page))
-		return 0;
-	if (PageReserved(page) && pfn_is_nosave(pfn)) {
-		pr_debug("[nosave pfn 0x%lx]", pfn);
-		return 0;
-	}
-	if (PageNosaveFree(page))
-		return 0;
-
-	return 1;
-}
-
-static void count_data_pages(void)
-{
-	struct zone *zone;
-	unsigned long zone_pfn;
-
-	nr_copy_pages = 0;
-
-	for_each_zone (zone) {
-		if (is_highmem(zone))
-			continue;
-		mark_free_pages(zone);
-		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
-			nr_copy_pages += saveable(zone, &zone_pfn);
-	}
-}
-
-
-static void copy_data_pages(void)
-{
-	struct zone *zone;
-	unsigned long zone_pfn;
-	struct pbe * pbe = pagedir_nosave;
-
-	pr_debug("copy_data_pages(): pages to copy: %d\n", nr_copy_pages);
-	for_each_zone (zone) {
-		if (is_highmem(zone))
-			continue;
-		mark_free_pages(zone);
-		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
-			if (saveable(zone, &zone_pfn)) {
-				struct page * page;
-				page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
-				BUG_ON(!pbe);
-				pbe->orig_address = (long) page_address(page);
-				/* copy_page is not usable for copying task structs. */
-				memcpy((void *)pbe->address, (void *)pbe->orig_address, PAGE_SIZE);
-				pbe = pbe->next;
-			}
-		}
-	}
-	BUG_ON(pbe);
-}
-
-
-/**
- *	calc_nr - Determine the number of pages needed for a pbe list.
- */
-
-static int calc_nr(int nr_copy)
-{
-	return nr_copy + (nr_copy+PBES_PER_PAGE-2)/(PBES_PER_PAGE-1);
-}
-
-/**
- *	free_pagedir - free pages allocated with alloc_pagedir()
- */
-
-static inline void free_pagedir(struct pbe *pblist)
-{
-	struct pbe *pbe;
-
-	while (pblist) {
-		pbe = (pblist + PB_PAGE_SKIP)->next;
-		free_page((unsigned long)pblist);
-		pblist = pbe;
-	}
-}
-
-/**
- *	fill_pb_page - Create a list of PBEs on a given memory page
- */
-
-static inline void fill_pb_page(struct pbe *pbpage)
-{
-	struct pbe *p;
-
-	p = pbpage;
-	pbpage += PB_PAGE_SKIP;
-	do
-		p->next = p + 1;
-	while (++p < pbpage);
-}
-
-/**
- *	create_pbe_list - Create a list of PBEs on top of a given chain
- *	of memory pages allocated with alloc_pagedir()
- */
-
-static void create_pbe_list(struct pbe *pblist, unsigned nr_pages)
-{
-	struct pbe *pbpage, *p;
-	unsigned num = PBES_PER_PAGE;
-
-	for_each_pb_page (pbpage, pblist) {
-		if (num >= nr_pages)
-			break;
-
-		fill_pb_page(pbpage);
-		num += PBES_PER_PAGE;
-	}
-	if (pbpage) {
-		for (num -= PBES_PER_PAGE - 1, p = pbpage; num < nr_pages; p++, num++)
-			p->next = p + 1;
-		p->next = NULL;
-	}
-	pr_debug("create_pbe_list(): initialized %d PBEs\n", num);
-}
-
-/**
- *	alloc_pagedir - Allocate the page directory.
- *
- *	First, determine exactly how many pages we need and
- *	allocate them.
- *
- *	We arrange the pages in a chain: each page is an array of PBES_PER_PAGE
- *	struct pbe elements (pbes) and the last element in the page points
- *	to the next page.
- *
- *	On each page we set up a list of struct_pbe elements.
- */
-
-static struct pbe * alloc_pagedir(unsigned nr_pages)
-{
-	unsigned num;
-	struct pbe *pblist, *pbe;
-
-	if (!nr_pages)
-		return NULL;
-
-	pr_debug("alloc_pagedir(): nr_pages = %d\n", nr_pages);
-	pblist = (struct pbe *)get_zeroed_page(GFP_ATOMIC | __GFP_COLD);
-	for (pbe = pblist, num = PBES_PER_PAGE; pbe && num < nr_pages;
-        		pbe = pbe->next, num += PBES_PER_PAGE) {
-		pbe += PB_PAGE_SKIP;
-		pbe->next = (struct pbe *)get_zeroed_page(GFP_ATOMIC | __GFP_COLD);
-	}
-	if (!pbe) { /* get_zeroed_page() failed */
-		free_pagedir(pblist);
-		pblist = NULL;
-        }
-	return pblist;
-}
-
-/**
- *	free_image_pages - Free pages allocated for snapshot
- */
-
-static void free_image_pages(void)
-{
-	struct pbe * p;
-
-	for_each_pbe (p, pagedir_save) {
-		if (p->address) {
-			ClearPageNosave(virt_to_page(p->address));
-			free_page(p->address);
-			p->address = 0;
-		}
-	}
-}
-
-/**
- *	alloc_image_pages - Allocate pages for the snapshot.
- */
-
-static int alloc_image_pages(void)
-{
-	struct pbe * p;
-
-	for_each_pbe (p, pagedir_save) {
-		p->address = get_zeroed_page(GFP_ATOMIC | __GFP_COLD);
-		if (!p->address)
-			return -ENOMEM;
-		SetPageNosave(virt_to_page(p->address));
-	}
-	return 0;
-}
-
-void swsusp_free(void)
-{
-	BUG_ON(PageNosave(virt_to_page(pagedir_save)));
-	BUG_ON(PageNosaveFree(virt_to_page(pagedir_save)));
-	free_image_pages();
-	free_pagedir(pagedir_save);
-}
-
-
-/**
- *	enough_free_mem - Make sure we enough free memory to snapshot.
- *
- *	Returns TRUE or FALSE after checking the number of available
- *	free pages.
- */
-
-static int enough_free_mem(void)
-{
-	if (nr_free_pages() < (nr_copy_pages + PAGES_FOR_IO)) {
-		pr_debug("swsusp: Not enough free pages: Have %d\n",
-			 nr_free_pages());
-		return 0;
-	}
-	return 1;
-}
-
-
-/**
- *	enough_swap - Make sure we have enough swap to save the image.
- *
- *	Returns TRUE or FALSE after checking the total amount of swap
- *	space avaiable.
- *
- *	FIXME: si_swapinfo(&i) returns all swap devices information.
- *	We should only consider resume_device.
- */
-
-static int enough_swap(void)
-{
-	struct sysinfo i;
-
-	si_swapinfo(&i);
-	if (i.freeswap < (nr_copy_pages + PAGES_FOR_IO))  {
-		pr_debug("swsusp: Not enough swap. Need %ld\n",i.freeswap);
-		return 0;
-	}
-	return 1;
-}
-
-static int swsusp_alloc(void)
-{
-	int error;
-
-	pagedir_nosave = NULL;
-	nr_copy_pages = calc_nr(nr_copy_pages);
-
-	pr_debug("suspend: (pages needed: %d + %d free: %d)\n",
-		 nr_copy_pages, PAGES_FOR_IO, nr_free_pages());
-
-	if (!enough_free_mem())
-		return -ENOMEM;
-
-	if (!enough_swap())
-		return -ENOSPC;
-
-	if (!(pagedir_save = alloc_pagedir(nr_copy_pages))) {
-		printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
-		return -ENOMEM;
-	}
-	create_pbe_list(pagedir_save, nr_copy_pages);
-	pagedir_nosave = pagedir_save;
-	if ((error = alloc_image_pages())) {
-		printk(KERN_ERR "suspend: Allocating image pages failed.\n");
-		swsusp_free();
-		return error;
-	}
-
-	nr_copy_pages_check = nr_copy_pages;
-	return 0;
-}
-
-static int suspend_prepare_image(void)
-{
-	int error;
-
-	pr_debug("swsusp: critical section: \n");
-	if (save_highmem()) {
-		printk(KERN_CRIT "Suspend machine: Not enough free pages for highmem\n");
-		restore_highmem();
-		return -ENOMEM;
-	}
-
-	drain_local_pages();
-	count_data_pages();
-	printk("swsusp: Need to copy %u pages\n", nr_copy_pages);
-
-	error = swsusp_alloc();
-	if (error)
-		return error;
-
-	/* During allocating of suspend pagedir, new cold pages may appear.
-	 * Kill them.
-	 */
-	drain_local_pages();
-	copy_data_pages();
-
-	/*
-	 * End of critical section. From now on, we can write to memory,
-	 * but we should not touch disk. This specially means we must _not_
-	 * touch swap space! Except we must write out our image of course.
-	 */
-
-	printk("swsusp: critical section/: done (%d pages copied)\n", nr_copy_pages );
-	return 0;
-}
-
-
 /* It is important _NOT_ to umount filesystems at this point. We want
  * them synced (in case something goes wrong) but we DO not want to mark
  * filesystem clean: it is not. (And it does not matter, if we resume
@@ -988,28 +567,24 @@ static int suspend_prepare_image(void)
 int swsusp_write(void)
 {
 	int error;
-	device_resume();
+
+	if ((error = swsusp_swap_check())) {
+		printk(KERN_ERR "swsusp: cannot find swap device, try swapon -a.\n");
+		return error;
+	}
 	lock_swapdevices();
 	error = write_suspend_image();
 	/* This will unlock ignored swap devices since writing is finished */
 	lock_swapdevices();
 	return error;
-
 }
 
 
-extern asmlinkage int swsusp_arch_suspend(void);
-extern asmlinkage int swsusp_arch_resume(void);
-
-
-asmlinkage int swsusp_save(void)
-{
-	return suspend_prepare_image();
-}
 
 int swsusp_suspend(void)
 {
 	int error;
+
 	if ((error = arch_prepare_suspend()))
 		return error;
 	local_irq_disable();
@@ -1021,15 +596,12 @@ int swsusp_suspend(void)
 	 */
 	if ((error = device_power_down(PMSG_FREEZE))) {
 		printk(KERN_ERR "Some devices failed to power down, aborting suspend\n");
-		local_irq_enable();
-		return error;
+		goto Enable_irqs;
 	}
 
-	if ((error = swsusp_swap_check())) {
-		printk(KERN_ERR "swsusp: cannot find swap device, try swapon -a.\n");
-		device_power_up();
-		local_irq_enable();
-		return error;
+	if ((error = save_highmem())) {
+		printk(KERN_ERR "swsusp: Not enough free pages for highmem\n");
+		goto Restore_highmem;
 	}
 
 	save_processor_state();
@@ -1037,9 +609,10 @@ int swsusp_suspend(void)
 		printk(KERN_ERR "Error %d suspending\n", error);
 	/* Restore control flow magically appears here */
 	restore_processor_state();
-	BUG_ON (nr_copy_pages_check != nr_copy_pages);
+Restore_highmem:
 	restore_highmem();
 	device_power_up();
+Enable_irqs:
 	local_irq_enable();
 	return error;
 }
@@ -1057,6 +630,11 @@ int swsusp_resume(void)
 	 * execution continues at place where swsusp_arch_suspend was called
          */
 	BUG_ON(!error);
+	/* The only reason why swsusp_arch_resume() can fail is memory being
+	 * very tight, so we have to free it as soon as we can to avoid
+	 * subsequent failures
+	 */
+	swsusp_free();
 	restore_processor_state();
 	restore_highmem();
 	touch_softlockup_watchdog();
@@ -1066,158 +644,43 @@ int swsusp_resume(void)
 }
 
 /**
- *	On resume, for storing the PBE list and the image,
- *	we can only use memory pages that do not conflict with the pages
- *	which had been used before suspend.
- *
- *	We don't know which pages are usable until we allocate them.
- *
- *	Allocated but unusable (ie eaten) memory pages are linked together
- *	to create a list, so that we can free them easily
- *
- *	We could have used a type other than (void *)
- *	for this purpose, but ...
+ *	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 void **eaten_memory = NULL;
-
-static inline void eat_page(void *page)
-{
-	void **c;
 
-	c = eaten_memory;
-	eaten_memory = page;
-	*eaten_memory = c;
-}
-
-static unsigned long get_usable_page(unsigned gfp_mask)
-{
-	unsigned long m;
-
-	m = get_zeroed_page(gfp_mask);
-	while (!PageNosaveFree(virt_to_page(m))) {
-		eat_page((void *)m);
-		m = get_zeroed_page(gfp_mask);
-		if (!m)
-			break;
-	}
-	return m;
-}
-
-static void free_eaten_memory(void)
-{
-	unsigned long m;
-	void **c;
-	int i = 0;
-
-	c = eaten_memory;
-	while (c) {
-		m = (unsigned long)c;
-		c = *c;
-		free_page(m);
-		i++;
-	}
-	eaten_memory = NULL;
-	pr_debug("swsusp: %d unused pages freed\n", i);
-}
-
-/**
- *	check_pagedir - We ensure here that pages that the PBEs point to
- *	won't collide with pages where we're going to restore from the loaded
- *	pages later
- */
-
-static int check_pagedir(struct pbe *pblist)
-{
-	struct pbe *p;
-
-	/* This is necessary, so that we can free allocated pages
-	 * in case of failure
-	 */
-	for_each_pbe (p, pblist)
-		p->address = 0UL;
-
-	for_each_pbe (p, pblist) {
-		p->address = get_usable_page(GFP_ATOMIC);
-		if (!p->address)
-			return -ENOMEM;
-	}
-	return 0;
-}
-
-/**
- *	swsusp_pagedir_relocate - It is possible, that some memory pages
- *	occupied by the list of PBEs collide with pages where we're going to
- *	restore from the loaded pages later.  We relocate them here.
- */
-
-static struct pbe * swsusp_pagedir_relocate(struct pbe *pblist)
+static void mark_unsafe_pages(struct pbe *pblist)
 {
 	struct zone *zone;
 	unsigned long zone_pfn;
-	struct pbe *pbpage, *tail, *p;
-	void *m;
-	int rel = 0, error = 0;
+	struct pbe *p;
 
 	if (!pblist) /* a sanity check */
-		return NULL;
-
-	pr_debug("swsusp: Relocating pagedir (%lu pages to check)\n",
-			swsusp_info.pagedir_pages);
-
-	/* Set page flags */
+		return;
 
+	/* Clear page flags */
 	for_each_zone (zone) {
-        	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
-                	SetPageNosaveFree(pfn_to_page(zone_pfn +
+		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+			if (pfn_valid(zone_pfn + zone->zone_start_pfn))
+				ClearPageNosaveFree(pfn_to_page(zone_pfn +
 					zone->zone_start_pfn));
 	}
 
-	/* Clear orig addresses */
-
+	/* Mark orig addresses */
 	for_each_pbe (p, pblist)
-		ClearPageNosaveFree(virt_to_page(p->orig_address));
-
-	tail = pblist + PB_PAGE_SKIP;
-
-	/* Relocate colliding pages */
-
-	for_each_pb_page (pbpage, pblist) {
-		if (!PageNosaveFree(virt_to_page((unsigned long)pbpage))) {
-			m = (void *)get_usable_page(GFP_ATOMIC | __GFP_COLD);
-			if (!m) {
-				error = -ENOMEM;
-				break;
-			}
-			memcpy(m, (void *)pbpage, PAGE_SIZE);
-			if (pbpage == pblist)
-				pblist = (struct pbe *)m;
-			else
-				tail->next = (struct pbe *)m;
-
-			eat_page((void *)pbpage);
-			pbpage = (struct pbe *)m;
-
-			/* We have to link the PBEs again */
+		SetPageNosaveFree(virt_to_page(p->orig_address));
 
-			for (p = pbpage; p < pbpage + PB_PAGE_SKIP; p++)
-				if (p->next) /* needed to save the end */
-					p->next = p + 1;
-
-			rel++;
-		}
-		tail = pbpage + PB_PAGE_SKIP;
-	}
+}
 
-	if (error) {
-		printk("\nswsusp: Out of memory\n\n");
-		free_pagedir(pblist);
-		free_eaten_memory();
-		pblist = NULL;
+static void copy_page_backup_list(struct pbe *dst, struct pbe *src)
+{
+	/* We assume both lists contain the same number of elements */
+	while (src) {
+		dst->orig_address = src->orig_address;
+		dst->swap_address = src->swap_address;
+		dst = dst->next;
+		src = src->next;
 	}
-	else
-		printk("swsusp: Relocated %d pages\n", rel);
-
-	return pblist;
 }
 
 /*
@@ -1231,7 +694,7 @@ static struct pbe * swsusp_pagedir_relocate(struct pbe *pblist)
 
 static atomic_t io_done = ATOMIC_INIT(0);
 
-static int end_io(struct bio * bio, unsigned int num, int err)
+static int end_io(struct bio *bio, unsigned int num, int err)
 {
 	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		panic("I/O error reading memory image");
@@ -1239,7 +702,7 @@ static int end_io(struct bio * bio, unsigned int num, int err)
 	return 0;
 }
 
-static struct block_device * resume_bdev;
+static struct block_device *resume_bdev;
 
 /**
  *	submit - submit BIO request.
@@ -1252,10 +715,10 @@ static struct block_device * resume_bdev;
  *	Then submit it and wait.
  */
 
-static int submit(int rw, pgoff_t page_off, void * page)
+static int submit(int rw, pgoff_t page_off, void *page)
 {
 	int error = 0;
-	struct bio * bio;
+	struct bio *bio;
 
 	bio = bio_alloc(GFP_ATOMIC, 1);
 	if (!bio)
@@ -1284,12 +747,12 @@ static int submit(int rw, pgoff_t page_off, void * page)
 	return error;
 }
 
-static int bio_read_page(pgoff_t page_off, void * page)
+static int bio_read_page(pgoff_t page_off, void *page)
 {
 	return submit(READ, page_off, page);
 }
 
-static int bio_write_page(pgoff_t page_off, void * page)
+static int bio_write_page(pgoff_t page_off, void *page)
 {
 	return submit(WRITE, page_off, page);
 }
@@ -1299,7 +762,7 @@ static int bio_write_page(pgoff_t page_off, void * page)
  * I really don't think that it's foolproof but more than nothing..
  */
 
-static const char * sanity_check(void)
+static const char *sanity_check(void)
 {
 	dump_info();
 	if (swsusp_info.version_code != LINUX_VERSION_CODE)
@@ -1325,7 +788,7 @@ static const char * sanity_check(void)
 
 static int check_header(void)
 {
-	const char * reason = NULL;
+	const char *reason = NULL;
 	int error;
 
 	if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info)))
@@ -1356,7 +819,7 @@ static int check_sig(void)
 		 * Reset swap signature now.
 		 */
 		error = bio_write_page(0, &swsusp_header);
-	} else { 
+	} else {
 		return -EINVAL;
 	}
 	if (!error)
@@ -1373,7 +836,7 @@ static int check_sig(void)
 
 static int data_read(struct pbe *pblist)
 {
-	struct pbe * p;
+	struct pbe *p;
 	int error = 0;
 	int i = 0;
 	int mod = swsusp_info.image_pages / 100;
@@ -1411,7 +874,7 @@ static int data_read(struct pbe *pblist)
 static int read_pagedir(struct pbe *pblist)
 {
 	struct pbe *pbpage, *p;
-	unsigned i = 0;
+	unsigned int i = 0;
 	int error;
 
 	if (!pblist)
@@ -1433,10 +896,8 @@ static int read_pagedir(struct pbe *pblist)
 			break;
 	}
 
-	if (error)
-		free_page((unsigned long)pblist);
-
-	BUG_ON(i != swsusp_info.pagedir_pages);
+	if (!error)
+		BUG_ON(i != swsusp_info.pagedir_pages);
 
 	return error;
 }
@@ -1460,32 +921,29 @@ static int read_suspend_image(void)
 	int error = 0;
 	struct pbe *p;
 
-	if (!(p = alloc_pagedir(nr_copy_pages)))
+	if (!(p = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 0)))
 		return -ENOMEM;
 
 	if ((error = read_pagedir(p)))
 		return error;
-
 	create_pbe_list(p, nr_copy_pages);
-
-	if (!(pagedir_nosave = swsusp_pagedir_relocate(p)))
+	mark_unsafe_pages(p);
+	pagedir_nosave = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 1);
+	if (pagedir_nosave) {
+		create_pbe_list(pagedir_nosave, nr_copy_pages);
+		copy_page_backup_list(pagedir_nosave, p);
+	}
+	free_pagedir(p);
+	if (!pagedir_nosave)
 		return -ENOMEM;
 
 	/* Allocate memory for the image and read the data from swap */
 
-	error = check_pagedir(pagedir_nosave);
-	free_eaten_memory();
+	error = alloc_data_pages(pagedir_nosave, GFP_ATOMIC, 1);
+
 	if (!error)
 		error = data_read(pagedir_nosave);
 
-	if (error) { /* We fail cleanly */
-		for_each_pbe (p, pagedir_nosave)
-			if (p->address) {
-				free_page(p->address);
-				p->address = 0UL;
-			}
-		free_pagedir(pagedir_nosave);
-	}
 	return error;
 }