Merge with Linus' kernel.

15 files changed, 716 insertions, 609 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
new file mode 100644
index 00000000000..f2ab70073bd
--- /dev/null
+++ b/kernel/.gitignore
@@ -0,0 +1,5 @@
+#
+# Generated files
+#
+config_data.h
+config_data.gz
diff --git a/kernel/acct.c b/kernel/acct.c
index 6312d6bd43e..38d57fa6b78 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -427,6 +427,7 @@ static void do_acct_process(long exitcode, struct file *file)
 	u64 elapsed;
 	u64 run_time;
 	struct timespec uptime;
+	unsigned long jiffies;
 
 	/*
 	 * First check to see if there is enough free_space to continue
@@ -467,12 +468,12 @@ static void do_acct_process(long exitcode, struct file *file)
 #endif
 	do_div(elapsed, AHZ);
 	ac.ac_btime = xtime.tv_sec - elapsed;
-	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(
-					    current->signal->utime +
-					    current->group_leader->utime));
-	ac.ac_stime = encode_comp_t(jiffies_to_AHZ(
-					    current->signal->stime +
-					    current->group_leader->stime));
+	jiffies = cputime_to_jiffies(cputime_add(current->group_leader->utime,
+						 current->signal->utime));
+	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(jiffies));
+	jiffies = cputime_to_jiffies(cputime_add(current->group_leader->stime,
+						 current->signal->stime));
+	ac.ac_stime = encode_comp_t(jiffies_to_AHZ(jiffies));
 	/* we really need to bite the bullet and change layout */
 	ac.ac_uid = current->uid;
 	ac.ac_gid = current->gid;
@@ -580,7 +581,8 @@ void acct_process(long exitcode)
 void acct_update_integrals(struct task_struct *tsk)
 {
 	if (likely(tsk->mm)) {
-		long delta = tsk->stime - tsk->acct_stimexpd;
+		long delta =
+			cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd;
 
 		if (delta == 0)
 			return;
diff --git a/kernel/configs.c b/kernel/configs.c
index 986f7af31e0..009e1ebdcb8 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -3,7 +3,7 @@
  * Echo the kernel .config file used to build the kernel
  *
  * Copyright (C) 2002 Khalid Aziz <khalid_aziz@hp.com>
- * Copyright (C) 2002 Randy Dunlap <rddunlap@osdl.org>
+ * Copyright (C) 2002 Randy Dunlap <rdunlap@xenotime.net>
  * Copyright (C) 2002 Al Stone <ahs3@fc.hp.com>
  * Copyright (C) 2002 Hewlett-Packard Company
  *
diff --git a/kernel/futex.c b/kernel/futex.c
index 5e71a6bf6f6..5efa2f97803 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -356,6 +356,13 @@ retry:
 		if (bh1 != bh2)
 			spin_unlock(&bh2->lock);
 
+#ifndef CONFIG_MMU
+		/* we don't get EFAULT from MMU faults if we don't have an MMU,
+		 * but we might get them from range checking */
+		ret = op_ret;
+		goto out;
+#endif
+
 		if (unlikely(op_ret != -EFAULT)) {
 			ret = op_ret;
 			goto out;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 81c49a4d679..97d5559997d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -366,6 +366,8 @@ int request_irq(unsigned int irq,
 	action->next = NULL;
 	action->dev_id = dev_id;
 
+	select_smp_affinity(irq);
+
 	retval = setup_irq(irq, action);
 	if (retval)
 		kfree(action);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index f26e534c658..8a64a4844cd 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -68,7 +68,9 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 	 */
 	cpus_and(tmp, new_value, cpu_online_map);
 	if (cpus_empty(tmp))
-		return -EINVAL;
+		/* Special case for empty set - allow the architecture
+		   code to set default SMP affinity. */
+		return select_smp_affinity(irq) ? -EINVAL : full_count;
 
 	proc_set_irq_affinity(irq, new_value);
 
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 015fb69ad94..99af8b05eea 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -15,6 +15,9 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
+u64 uevent_seqnum;
+char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug";
+
 #define KERNEL_ATTR_RO(_name) \
 static struct subsys_attribute _name##_attr = __ATTR_RO(_name)
 
@@ -23,11 +26,29 @@ static struct subsys_attribute _name##_attr = \
 	__ATTR(_name, 0644, _name##_show, _name##_store)
 
 #ifdef CONFIG_HOTPLUG
-static ssize_t hotplug_seqnum_show(struct subsystem *subsys, char *page)
+/* current uevent sequence number */
+static ssize_t uevent_seqnum_show(struct subsystem *subsys, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)uevent_seqnum);
+}
+KERNEL_ATTR_RO(uevent_seqnum);
+
+/* uevent helper program, used during early boo */
+static ssize_t uevent_helper_show(struct subsystem *subsys, char *page)
+{
+	return sprintf(page, "%s\n", uevent_helper);
+}
+static ssize_t uevent_helper_store(struct subsystem *subsys, const char *page, size_t count)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)hotplug_seqnum);
+	if (count+1 > UEVENT_HELPER_PATH_LEN)
+		return -ENOENT;
+	memcpy(uevent_helper, page, count);
+	uevent_helper[count] = '\0';
+	if (count && uevent_helper[count-1] == '\n')
+		uevent_helper[count-1] = '\0';
+	return count;
 }
-KERNEL_ATTR_RO(hotplug_seqnum);
+KERNEL_ATTR_RW(uevent_helper);
 #endif
 
 #ifdef CONFIG_KEXEC
@@ -45,7 +66,8 @@ EXPORT_SYMBOL_GPL(kernel_subsys);
 
 static struct attribute * kernel_attrs[] = {
 #ifdef CONFIG_HOTPLUG
-	&hotplug_seqnum_attr.attr,
+	&uevent_seqnum_attr.attr,
+	&uevent_helper_attr.attr,
 #endif
 #ifdef CONFIG_KEXEC
 	&crash_notes_attr.attr,
diff --git a/kernel/module.c b/kernel/module.c
index 2ea929d51ad..4b06bbad49c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1854,8 +1854,7 @@ static struct module *load_module(void __user *umod,
 	kfree(args);
  free_hdr:
 	vfree(hdr);
-	if (err < 0) return ERR_PTR(err);
-	else return ptr;
+	return ERR_PTR(err);
 
  truncated:
 	printk(KERN_ERR "Module len %lu truncated\n", len);
diff --git a/kernel/panic.c b/kernel/panic.c
index aabc5f86fa3..c5c4ab25583 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -60,7 +60,7 @@ NORET_TYPE void panic(const char * fmt, ...)
 	long i;
 	static char buf[1024];
 	va_list args;
-#if defined(CONFIG_ARCH_S390)
+#if defined(CONFIG_S390)
         unsigned long caller = (unsigned long) __builtin_return_address(0);
 #endif
 
@@ -125,7 +125,7 @@ NORET_TYPE void panic(const char * fmt, ...)
 		printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
 	}
 #endif
-#if defined(CONFIG_ARCH_S390)
+#if defined(CONFIG_S390)
         disabled_wait(caller);
 #endif
 	local_irq_enable();
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index cae4f572899..4c68edff900 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -238,18 +238,7 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx,
 		while ((t = next_thread(t)) != p) {
 			cpu->sched += t->sched_time;
 		}
-		if (p->tgid == current->tgid) {
-			/*
-			 * We're sampling ourselves, so include the
-			 * cycles not yet banked.  We still omit
-			 * other threads running on other CPUs,
-			 * so the total can always be behind as
-			 * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ).
-			 */
-			cpu->sched += current_sched_time(current);
-		} else {
-			cpu->sched += p->sched_time;
-		}
+		cpu->sched += sched_ns(p);
 		break;
 	}
 	return 0;
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 027322a564f..e24446f8d8c 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -24,10 +24,11 @@
 
 extern suspend_disk_method_t pm_disk_mode;
 
+extern int swsusp_shrink_memory(void);
 extern int swsusp_suspend(void);
-extern int swsusp_write(void);
+extern int swsusp_write(struct pbe *pblist, unsigned int nr_pages);
 extern int swsusp_check(void);
-extern int swsusp_read(void);
+extern int swsusp_read(struct pbe **pblist_ptr);
 extern void swsusp_close(void);
 extern int swsusp_resume(void);
 
@@ -73,31 +74,6 @@ static void power_down(suspend_disk_method_t mode)
 static int in_suspend __nosavedata = 0;
 
 
-/**
- *	free_some_memory -  Try to free as much memory as possible
- *
- *	... but do not OOM-kill anyone
- *
- *	Notice: all userland should be stopped at this point, or
- *	livelock is possible.
- */
-
-static void free_some_memory(void)
-{
-	unsigned int i = 0;
-	unsigned int tmp;
-	unsigned long pages = 0;
-	char *p = "-\\|/";
-
-	printk("Freeing memory...  ");
-	while ((tmp = shrink_all_memory(10000))) {
-		pages += tmp;
-		printk("\b%c", p[i++ % 4]);
-	}
-	printk("\bdone (%li pages freed)\n", pages);
-}
-
-
 static inline void platform_finish(void)
 {
 	if (pm_disk_mode == PM_DISK_PLATFORM) {
@@ -127,8 +103,8 @@ static int prepare_processes(void)
 	}
 
 	/* Free memory before shutting down devices. */
-	free_some_memory();
-	return 0;
+	if (!(error = swsusp_shrink_memory()))
+		return 0;
 thaw:
 	thaw_processes();
 	enable_nonboot_cpus();
@@ -176,7 +152,7 @@ int pm_suspend_disk(void)
 	if (in_suspend) {
 		device_resume();
 		pr_debug("PM: writing image.\n");
-		error = swsusp_write();
+		error = swsusp_write(pagedir_nosave, nr_copy_pages);
 		if (!error)
 			power_down(pm_disk_mode);
 		else {
@@ -247,7 +223,7 @@ static int software_resume(void)
 
 	pr_debug("PM: Reading swsusp image.\n");
 
-	if ((error = swsusp_read())) {
+	if ((error = swsusp_read(&pagedir_nosave))) {
 		swsusp_free();
 		goto Thaw;
 	}
@@ -363,37 +339,55 @@ static ssize_t resume_show(struct subsystem * subsys, char *buf)
 		       MINOR(swsusp_resume_device));
 }
 
-static ssize_t resume_store(struct subsystem * subsys, const char * buf, size_t n)
+static ssize_t resume_store(struct subsystem *subsys, const char *buf, size_t n)
 {
-	int len;
-	char *p;
 	unsigned int maj, min;
-	int error = -EINVAL;
 	dev_t res;
+	int ret = -EINVAL;
 
-	p = memchr(buf, '\n', n);
-	len = p ? p - buf : n;
+	if (sscanf(buf, "%u:%u", &maj, &min) != 2)
+		goto out;
 
-	if (sscanf(buf, "%u:%u", &maj, &min) == 2) {
-		res = MKDEV(maj,min);
-		if (maj == MAJOR(res) && min == MINOR(res)) {
-			down(&pm_sem);
-			swsusp_resume_device = res;
-			up(&pm_sem);
-			printk("Attempting manual resume\n");
-			noresume = 0;
-			software_resume();
-		}
-	}
+	res = MKDEV(maj,min);
+	if (maj != MAJOR(res) || min != MINOR(res))
+		goto out;
 
-	return error >= 0 ? n : error;
+	down(&pm_sem);
+	swsusp_resume_device = res;
+	up(&pm_sem);
+	printk("Attempting manual resume\n");
+	noresume = 0;
+	software_resume();
+	ret = n;
+out:
+	return ret;
 }
 
 power_attr(resume);
 
+static ssize_t image_size_show(struct subsystem * subsys, char *buf)
+{
+	return sprintf(buf, "%u\n", image_size);
+}
+
+static ssize_t image_size_store(struct subsystem * subsys, const char * buf, size_t n)
+{
+	unsigned int size;
+
+	if (sscanf(buf, "%u", &size) == 1) {
+		image_size = size;
+		return n;
+	}
+
+	return -EINVAL;
+}
+
+power_attr(image_size);
+
 static struct attribute * g[] = {
 	&disk_attr.attr,
 	&resume_attr.attr,
+	&image_size_attr.attr,
 	NULL,
 };
 
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 6c042b5ee14..7e8492fd142 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -9,19 +9,13 @@
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
 #endif
 
-#define MAX_PBES	((PAGE_SIZE - sizeof(struct new_utsname) \
-			- 4 - 3*sizeof(unsigned long) - sizeof(int) \
-			- sizeof(void *)) / sizeof(swp_entry_t))
-
 struct swsusp_info {
 	struct new_utsname	uts;
 	u32			version_code;
 	unsigned long		num_physpages;
 	int			cpus;
 	unsigned long		image_pages;
-	unsigned long		pagedir_pages;
-	suspend_pagedir_t	* suspend_pagedir;
-	swp_entry_t		pagedir[MAX_PBES];
+	unsigned long		pages;
 } __attribute__((aligned(PAGE_SIZE)));
 
 
@@ -48,25 +42,27 @@ static struct subsys_attribute _name##_attr = {	\
 
 extern struct subsystem power_subsys;
 
-extern int freeze_processes(void);
-extern void thaw_processes(void);
-
 extern int pm_prepare_console(void);
 extern void pm_restore_console(void);
 
-
 /* References to section boundaries */
 extern const void __nosave_begin, __nosave_end;
 
 extern unsigned int nr_copy_pages;
-extern suspend_pagedir_t *pagedir_nosave;
-extern suspend_pagedir_t *pagedir_save;
+extern struct pbe *pagedir_nosave;
+
+/* Preferred image size in MB (default 500) */
+extern unsigned int image_size;
 
 extern asmlinkage int swsusp_arch_suspend(void);
 extern asmlinkage int swsusp_arch_resume(void);
 
+extern unsigned int count_data_pages(void);
 extern void free_pagedir(struct pbe *pblist);
+extern void release_eaten_pages(void);
 extern struct pbe *alloc_pagedir(unsigned nr_pages, gfp_t gfp_mask, int safe_needed);
-extern void create_pbe_list(struct pbe *pblist, unsigned nr_pages);
 extern void swsusp_free(void);
 extern int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed);
+extern unsigned int snapshot_nr_pages(void);
+extern struct pbe *snapshot_pblist(void);
+extern void snapshot_pblist_set(struct pbe *pblist);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 4a6dbcefd37..41f66365f0d 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -33,7 +33,35 @@
 
 #include "power.h"
 
+struct pbe *pagedir_nosave;
+unsigned int nr_copy_pages;
+
 #ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void)
+{
+	struct zone *zone;
+	unsigned long zone_pfn;
+	unsigned int n = 0;
+
+	for_each_zone (zone)
+		if (is_highmem(zone)) {
+			mark_free_pages(zone);
+			for (zone_pfn = 0; zone_pfn < zone->spanned_pages; zone_pfn++) {
+				struct page *page;
+				unsigned long pfn = zone_pfn + zone->zone_start_pfn;
+				if (!pfn_valid(pfn))
+					continue;
+				page = pfn_to_page(pfn);
+				if (PageReserved(page))
+					continue;
+				if (PageNosaveFree(page))
+					continue;
+				n++;
+			}
+		}
+	return n;
+}
+
 struct highmem_page {
 	char *data;
 	struct page *page;
@@ -149,17 +177,15 @@ static int saveable(struct zone *zone, unsigned long *zone_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);
+	if (PageReserved(page) && pfn_is_nosave(pfn))
 		return 0;
-	}
 	if (PageNosaveFree(page))
 		return 0;
 
 	return 1;
 }
 
-static unsigned count_data_pages(void)
+unsigned int count_data_pages(void)
 {
 	struct zone *zone;
 	unsigned long zone_pfn;
@@ -244,7 +270,7 @@ static inline void fill_pb_page(struct pbe *pbpage)
  *	of memory pages allocated with alloc_pagedir()
  */
 
-void create_pbe_list(struct pbe *pblist, unsigned int nr_pages)
+static inline void create_pbe_list(struct pbe *pblist, unsigned int nr_pages)
 {
 	struct pbe *pbpage, *p;
 	unsigned int num = PBES_PER_PAGE;
@@ -261,7 +287,35 @@ void create_pbe_list(struct pbe *pblist, unsigned int nr_pages)
 			p->next = p + 1;
 		p->next = NULL;
 	}
-	pr_debug("create_pbe_list(): initialized %d PBEs\n", num);
+}
+
+/**
+ *	On resume it is necessary to trace and eventually free the unsafe
+ *	pages that have been allocated, because they are needed for I/O
+ *	(on x86-64 we likely will "eat" these pages once again while
+ *	creating the temporary page translation tables)
+ */
+
+struct eaten_page {
+	struct eaten_page *next;
+	char padding[PAGE_SIZE - sizeof(void *)];
+};
+
+static struct eaten_page *eaten_pages = NULL;
+
+void release_eaten_pages(void)
+{
+	struct eaten_page *p, *q;
+
+	p = eaten_pages;
+	while (p) {
+		q = p->next;
+		/* We don't want swsusp_free() to free this page again */
+		ClearPageNosave(virt_to_page(p));
+		free_page((unsigned long)p);
+		p = q;
+	}
+	eaten_pages = NULL;
 }
 
 /**
@@ -282,9 +336,12 @@ static inline void *alloc_image_page(gfp_t gfp_mask, int safe_needed)
 	if (safe_needed)
 		do {
 			res = (void *)get_zeroed_page(gfp_mask);
-			if (res && PageNosaveFree(virt_to_page(res)))
+			if (res && PageNosaveFree(virt_to_page(res))) {
 				/* This is for swsusp_free() */
 				SetPageNosave(virt_to_page(res));
+				((struct eaten_page *)res)->next = eaten_pages;
+				eaten_pages = res;
+			}
 		} while (res && PageNosaveFree(virt_to_page(res)));
 	else
 		res = (void *)get_zeroed_page(gfp_mask);
@@ -332,7 +389,8 @@ struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed
 	if (!pbe) { /* get_zeroed_page() failed */
 		free_pagedir(pblist);
 		pblist = NULL;
-        }
+        } else
+        	create_pbe_list(pblist, nr_pages);
 	return pblist;
 }
 
@@ -370,8 +428,14 @@ void swsusp_free(void)
 
 static int enough_free_mem(unsigned int nr_pages)
 {
-	pr_debug("swsusp: available memory: %u pages\n", nr_free_pages());
-	return nr_free_pages() > (nr_pages + PAGES_FOR_IO +
+	struct zone *zone;
+	unsigned int n = 0;
+
+	for_each_zone (zone)
+		if (!is_highmem(zone))
+			n += zone->free_pages;
+	pr_debug("swsusp: available memory: %u pages\n", n);
+	return n > (nr_pages + PAGES_FOR_IO +
 		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
 }
 
@@ -395,7 +459,6 @@ static struct pbe *swsusp_alloc(unsigned int nr_pages)
 		printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
 		return NULL;
 	}
-	create_pbe_list(pblist, nr_pages);
 
 	if (alloc_data_pages(pblist, GFP_ATOMIC | __GFP_COLD, 0)) {
 		printk(KERN_ERR "suspend: Allocating image pages failed.\n");
@@ -421,10 +484,6 @@ asmlinkage int swsusp_save(void)
 		 (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE,
 		 PAGES_FOR_IO, nr_free_pages());
 
-	/* This is needed because of the fixed size of swsusp_info */
-	if (MAX_PBES < (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE)
-		return -ENOSPC;
-
 	if (!enough_free_mem(nr_pages)) {
 		printk(KERN_ERR "swsusp: Not enough free memory\n");
 		return -ENOMEM;
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index c05f46e7348..55a18d26abe 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -30,8 +30,8 @@
  * Alex Badea <vampire@go.ro>:
  * Fixed runaway init
  *
- * Andreas Steinmetz <ast@domdv.de>:
- * Added encrypted suspend option
+ * Rafael J. Wysocki <rjw@sisk.pl>
+ * Added the swap map data structure and reworked the handling of swap
  *
  * More state savers are welcome. Especially for the scsi layer...
  *
@@ -67,44 +67,33 @@
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
-#include <linux/random.h>
-#include <linux/crypto.h>
-#include <asm/scatterlist.h>
-
 #include "power.h"
 
+/*
+ * Preferred image size in MB (tunable via /sys/power/image_size).
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N MB, but if that is impossible, it will
+ * try to create the smallest image possible.
+ */
+unsigned int image_size = 500;
+
 #ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void);
 int save_highmem(void);
 int restore_highmem(void);
 #else
 static int save_highmem(void) { return 0; }
 static int restore_highmem(void) { return 0; }
+static unsigned int count_highmem_pages(void) { return 0; }
 #endif
 
-#define CIPHER "aes"
-#define MAXKEY 32
-#define MAXIV  32
-
 extern char resume_file[];
 
-/* Local variables that should not be affected by save */
-unsigned int nr_copy_pages __nosavedata = 0;
-
-/* Suspend pagedir is allocated before final copy, therefore it
-   must be freed after resume
-
-   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;
-
 #define SWSUSP_SIG	"S1SUSPEND"
 
 static struct swsusp_header {
-	char reserved[PAGE_SIZE - 20 - MAXKEY - MAXIV - sizeof(swp_entry_t)];
-	u8 key_iv[MAXKEY+MAXIV];
-	swp_entry_t swsusp_info;
+	char reserved[PAGE_SIZE - 20 - sizeof(swp_entry_t)];
+	swp_entry_t image;
 	char	orig_sig[10];
 	char	sig[10];
 } __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
@@ -115,140 +104,9 @@ static struct swsusp_info swsusp_info;
  * Saving part...
  */
 
-/* We memorize in swapfile_used what swap devices are used for suspension */
-#define SWAPFILE_UNUSED    0
-#define SWAPFILE_SUSPEND   1	/* This is the suspending device */
-#define SWAPFILE_IGNORED   2	/* Those are other swap devices ignored for suspension */
-
-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 u8 key_iv[MAXKEY+MAXIV];
-
-#ifdef CONFIG_SWSUSP_ENCRYPT
-
-static int crypto_init(int mode, void **mem)
-{
-	int error = 0;
-	int len;
-	char *modemsg;
-	struct crypto_tfm *tfm;
-
-	modemsg = mode ? "suspend not possible" : "resume not possible";
-
-	tfm = crypto_alloc_tfm(CIPHER, CRYPTO_TFM_MODE_CBC);
-	if(!tfm) {
-		printk(KERN_ERR "swsusp: no tfm, %s\n", modemsg);
-		error = -EINVAL;
-		goto out;
-	}
-
-	if(MAXKEY < crypto_tfm_alg_min_keysize(tfm)) {
-		printk(KERN_ERR "swsusp: key buffer too small, %s\n", modemsg);
-		error = -ENOKEY;
-		goto fail;
-	}
-
-	if (mode)
-		get_random_bytes(key_iv, MAXKEY+MAXIV);
-
-	len = crypto_tfm_alg_max_keysize(tfm);
-	if (len > MAXKEY)
-		len = MAXKEY;
-
-	if (crypto_cipher_setkey(tfm, key_iv, len)) {
-		printk(KERN_ERR "swsusp: key setup failure, %s\n", modemsg);
-		error = -EKEYREJECTED;
-		goto fail;
-	}
-
-	len = crypto_tfm_alg_ivsize(tfm);
-
-	if (MAXIV < len) {
-		printk(KERN_ERR "swsusp: iv buffer too small, %s\n", modemsg);
-		error = -EOVERFLOW;
-		goto fail;
-	}
-
-	crypto_cipher_set_iv(tfm, key_iv+MAXKEY, len);
-
-	*mem=(void *)tfm;
-
-	goto out;
-
-fail:	crypto_free_tfm(tfm);
-out:	return error;
-}
-
-static __inline__ void crypto_exit(void *mem)
-{
-	crypto_free_tfm((struct crypto_tfm *)mem);
-}
-
-static __inline__ int crypto_write(struct pbe *p, void *mem)
-{
-	int error = 0;
-	struct scatterlist src, dst;
-
-	src.page   = virt_to_page(p->address);
-	src.offset = 0;
-	src.length = PAGE_SIZE;
-	dst.page   = virt_to_page((void *)&swsusp_header);
-	dst.offset = 0;
-	dst.length = PAGE_SIZE;
-
-	error = crypto_cipher_encrypt((struct crypto_tfm *)mem, &dst, &src,
-					PAGE_SIZE);
-
-	if (!error)
-		error = write_page((unsigned long)&swsusp_header,
-				&(p->swap_address));
-	return error;
-}
-
-static __inline__ int crypto_read(struct pbe *p, void *mem)
-{
-	int error = 0;
-	struct scatterlist src, dst;
-
-	error = bio_read_page(swp_offset(p->swap_address), (void *)p->address);
-	if (!error) {
-		src.offset = 0;
-		src.length = PAGE_SIZE;
-		dst.offset = 0;
-		dst.length = PAGE_SIZE;
-		src.page = dst.page = virt_to_page((void *)p->address);
-
-		error = crypto_cipher_decrypt((struct crypto_tfm *)mem, &dst,
-						&src, PAGE_SIZE);
-	}
-	return error;
-}
-#else
-static __inline__ int crypto_init(int mode, void *mem)
-{
-	return 0;
-}
-
-static __inline__ void crypto_exit(void *mem)
-{
-}
-
-static __inline__ int crypto_write(struct pbe *p, void *mem)
-{
-	return write_page(p->address, &(p->swap_address));
-}
+static unsigned short root_swap = 0xffff;
 
-static __inline__ int crypto_read(struct pbe *p, void *mem)
-{
-	return bio_read_page(swp_offset(p->swap_address), (void *)p->address);
-}
-#endif
-
-static int mark_swapfiles(swp_entry_t prev)
+static int mark_swapfiles(swp_entry_t start)
 {
 	int error;
 
@@ -259,8 +117,7 @@ static int mark_swapfiles(swp_entry_t prev)
 	    !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
 		memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
 		memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
-		memcpy(swsusp_header.key_iv, key_iv, MAXKEY+MAXIV);
-		swsusp_header.swsusp_info = prev;
+		swsusp_header.image = start;
 		error = rw_swap_page_sync(WRITE,
 					  swp_entry(root_swap, 0),
 					  virt_to_page((unsigned long)
@@ -283,7 +140,7 @@ static int mark_swapfiles(swp_entry_t prev)
  * devfs, since the resume code can only recognize the form /dev/hda4,
  * but the suspend code would see the long name.)
  */
-static int is_resume_device(const struct swap_info_struct *swap_info)
+static inline int is_resume_device(const struct swap_info_struct *swap_info)
 {
 	struct file *file = swap_info->swap_file;
 	struct inode *inode = file->f_dentry->d_inode;
@@ -294,54 +151,22 @@ static int is_resume_device(const struct swap_info_struct *swap_info)
 
 static int swsusp_swap_check(void) /* This is called before saving image */
 {
-	int i, len;
-
-	len=strlen(resume_file);
-	root_swap = 0xFFFF;
-
-	spin_lock(&swap_lock);
-	for (i=0; i<MAX_SWAPFILES; i++) {
-		if (!(swap_info[i].flags & SWP_WRITEOK)) {
-			swapfile_used[i]=SWAPFILE_UNUSED;
-		} else {
-			if (!len) {
-	    			printk(KERN_WARNING "resume= option should be used to set suspend device" );
-				if (root_swap == 0xFFFF) {
-					swapfile_used[i] = SWAPFILE_SUSPEND;
-					root_swap = i;
-				} else
-					swapfile_used[i] = SWAPFILE_IGNORED;
-			} else {
-	  			/* we ignore all swap devices that are not the resume_file */
-				if (is_resume_device(&swap_info[i])) {
-					swapfile_used[i] = SWAPFILE_SUSPEND;
-					root_swap = i;
-				} else {
-				  	swapfile_used[i] = SWAPFILE_IGNORED;
-				}
-			}
-		}
-	}
-	spin_unlock(&swap_lock);
-	return (root_swap != 0xffff) ? 0 : -ENODEV;
-}
-
-/**
- * This is called after saving image so modification
- * will be lost after resume... and that's what we want.
- * we make the device unusable. A new call to
- * lock_swapdevices can unlock the devices.
- */
-static void lock_swapdevices(void)
-{
 	int i;
 
+	if (!swsusp_resume_device)
+		return -ENODEV;
 	spin_lock(&swap_lock);
-	for (i = 0; i< MAX_SWAPFILES; i++)
-		if (swapfile_used[i] == SWAPFILE_IGNORED) {
-			swap_info[i].flags ^= SWP_WRITEOK;
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		if (!(swap_info[i].flags & SWP_WRITEOK))
+			continue;
+		if (is_resume_device(swap_info + i)) {
+			spin_unlock(&swap_lock);
+			root_swap = i;
+			return 0;
 		}
+	}
 	spin_unlock(&swap_lock);
+	return -ENODEV;
 }
 
 /**
@@ -359,72 +184,217 @@ static void lock_swapdevices(void)
 static int write_page(unsigned long addr, swp_entry_t *loc)
 {
 	swp_entry_t entry;
-	int error = 0;
+	int error = -ENOSPC;
 
-	entry = get_swap_page();
-	if (swp_offset(entry) &&
-	    swapfile_used[swp_type(entry)] == SWAPFILE_SUSPEND) {
-		error = rw_swap_page_sync(WRITE, entry,
-					  virt_to_page(addr));
-		if (error == -EIO)
-			error = 0;
-		if (!error)
+	entry = get_swap_page_of_type(root_swap);
+	if (swp_offset(entry)) {
+		error = rw_swap_page_sync(WRITE, entry, virt_to_page(addr));
+		if (!error || error == -EIO)
 			*loc = entry;
-	} else
-		error = -ENOSPC;
+	}
 	return error;
 }
 
 /**
- *	data_free - Free the swap entries used by the saved image.
+ *	Swap map-handling functions
+ *
+ *	The swap map is a data structure used for keeping track of each page
+ *	written to the swap.  It consists of many swap_map_page structures
+ *	that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	These structures are linked together with the help of either the
+ *	.next (in memory) or the .next_swap (in swap) member.
  *
- *	Walk the list of used swap entries and free each one.
- *	This is only used for cleanup when suspend fails.
+ *	The swap map is created during suspend.  At that time we need to keep
+ *	it in memory, because we have to free all of the allocated swap
+ *	entries if an error occurs.  The memory needed is preallocated
+ *	so that we know in advance if there's enough of it.
+ *
+ *	The first swap_map_page structure is filled with the swap entries that
+ *	correspond to the first MAP_PAGE_SIZE data pages written to swap and
+ *	so on.  After the all of the data pages have been written, the order
+ *	of the swap_map_page structures in the map is reversed so that they
+ *	can be read from swap in the original order.  This causes the data
+ *	pages to be loaded in exactly the same order in which they have been
+ *	saved.
+ *
+ *	During resume we only need to use one swap_map_page structure
+ *	at a time, which means that we only need to use two memory pages for
+ *	reading the image - one for reading the swap_map_page structures
+ *	and the second for reading the data pages from swap.
  */
-static void data_free(void)
+
+#define MAP_PAGE_SIZE	((PAGE_SIZE - sizeof(swp_entry_t) - sizeof(void *)) \
+			/ sizeof(swp_entry_t))
+
+struct swap_map_page {
+	swp_entry_t		entries[MAP_PAGE_SIZE];
+	swp_entry_t		next_swap;
+	struct swap_map_page	*next;
+};
+
+static inline void free_swap_map(struct swap_map_page *swap_map)
 {
-	swp_entry_t entry;
-	struct pbe *p;
+	struct swap_map_page *swp;
 
-	for_each_pbe (p, pagedir_nosave) {
-		entry = p->swap_address;
-		if (entry.val)
-			swap_free(entry);
-		else
-			break;
+	while (swap_map) {
+		swp = swap_map->next;
+		free_page((unsigned long)swap_map);
+		swap_map = swp;
 	}
 }
 
+static struct swap_map_page *alloc_swap_map(unsigned int nr_pages)
+{
+	struct swap_map_page *swap_map, *swp;
+	unsigned n = 0;
+
+	if (!nr_pages)
+		return NULL;
+
+	pr_debug("alloc_swap_map(): nr_pages = %d\n", nr_pages);
+	swap_map = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+	swp = swap_map;
+	for (n = MAP_PAGE_SIZE; n < nr_pages; n += MAP_PAGE_SIZE) {
+		swp->next = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+		swp = swp->next;
+		if (!swp) {
+			free_swap_map(swap_map);
+			return NULL;
+		}
+	}
+	return swap_map;
+}
+
 /**
- *	data_write - Write saved image to swap.
- *
- *	Walk the list of pages in the image and sync each one to swap.
+ *	reverse_swap_map - reverse the order of pages in the swap map
+ *	@swap_map
  */
-static int data_write(void)
+
+static inline struct swap_map_page *reverse_swap_map(struct swap_map_page *swap_map)
 {
-	int error = 0, i = 0;
-	unsigned int mod = nr_copy_pages / 100;
-	struct pbe *p;
-	void *tfm;
+	struct swap_map_page *prev, *next;
+
+	prev = NULL;
+	while (swap_map) {
+		next = swap_map->next;
+		swap_map->next = prev;
+		prev = swap_map;
+		swap_map = next;
+	}
+	return prev;
+}
 
-	if ((error = crypto_init(1, &tfm)))
-		return error;
+/**
+ *	free_swap_map_entries - free the swap entries allocated to store
+ *	the swap map @swap_map (this is only called in case of an error)
+ */
+static inline void free_swap_map_entries(struct swap_map_page *swap_map)
+{
+	while (swap_map) {
+		if (swap_map->next_swap.val)
+			swap_free(swap_map->next_swap);
+		swap_map = swap_map->next;
+	}
+}
 
-	if (!mod)
-		mod = 1;
+/**
+ *	save_swap_map - save the swap map used for tracing the data pages
+ *	stored in the swap
+ */
 
-	printk( "Writing data to swap (%d pages)...     ", nr_copy_pages );
-	for_each_pbe (p, pagedir_nosave) {
-		if (!(i%mod))
-			printk( "\b\b\b\b%3d%%", i / mod );
-		if ((error = crypto_write(p, tfm))) {
-			crypto_exit(tfm);
+static int save_swap_map(struct swap_map_page *swap_map, swp_entry_t *start)
+{
+	swp_entry_t entry = (swp_entry_t){0};
+	int error;
+
+	while (swap_map) {
+		swap_map->next_swap = entry;
+		if ((error = write_page((unsigned long)swap_map, &entry)))
 			return error;
-		}
-		i++;
+		swap_map = swap_map->next;
 	}
-	printk("\b\b\b\bdone\n");
-	crypto_exit(tfm);
+	*start = entry;
+	return 0;
+}
+
+/**
+ *	free_image_entries - free the swap entries allocated to store
+ *	the image data pages (this is only called in case of an error)
+ */
+
+static inline void free_image_entries(struct swap_map_page *swp)
+{
+	unsigned k;
+
+	while (swp) {
+		for (k = 0; k < MAP_PAGE_SIZE; k++)
+			if (swp->entries[k].val)
+				swap_free(swp->entries[k]);
+		swp = swp->next;
+	}
+}
+
+/**
+ *	The swap_map_handle structure is used for handling the swap map in
+ *	a file-alike way
+ */
+
+struct swap_map_handle {
+	struct swap_map_page *cur;
+	unsigned int k;
+};
+
+static inline void init_swap_map_handle(struct swap_map_handle *handle,
+                                        struct swap_map_page *map)
+{
+	handle->cur = map;
+	handle->k = 0;
+}
+
+static inline int swap_map_write_page(struct swap_map_handle *handle,
+                                      unsigned long addr)
+{
+	int error;
+
+	error = write_page(addr, handle->cur->entries + handle->k);
+	if (error)
+		return error;
+	if (++handle->k >= MAP_PAGE_SIZE) {
+		handle->cur = handle->cur->next;
+		handle->k = 0;
+	}
+	return 0;
+}
+
+/**
+ *	save_image_data - save the data pages pointed to by the PBEs
+ *	from the list @pblist using the swap map handle @handle
+ *	(assume there are @nr_pages data pages to save)
+ */
+
+static int save_image_data(struct pbe *pblist,
+                           struct swap_map_handle *handle,
+                           unsigned int nr_pages)
+{
+	unsigned int m;
+	struct pbe *p;
+	int error = 0;
+
+	printk("Saving image data pages (%u pages) ...     ", nr_pages);
+	m = nr_pages / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	for_each_pbe (p, pblist) {
+		error = swap_map_write_page(handle, p->address);
+		if (error)
+			break;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
+	}
+	if (!error)
+		printk("\b\b\b\bdone\n");
 	return error;
 }
 
@@ -440,70 +410,70 @@ static void dump_info(void)
 	pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname);
 	pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus);
 	pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages);
-	pr_debug(" swsusp: Pagedir: %ld Pages\n",swsusp_info.pagedir_pages);
+	pr_debug(" swsusp: Total: %ld Pages\n", swsusp_info.pages);
 }
 
-static void init_header(void)
+static void init_header(unsigned int nr_pages)
 {
 	memset(&swsusp_info, 0, sizeof(swsusp_info));
 	swsusp_info.version_code = LINUX_VERSION_CODE;
 	swsusp_info.num_physpages = num_physpages;
 	memcpy(&swsusp_info.uts, &system_utsname, sizeof(system_utsname));
 
-	swsusp_info.suspend_pagedir = pagedir_nosave;
 	swsusp_info.cpus = num_online_cpus();
-	swsusp_info.image_pages = nr_copy_pages;
-}
-
-static int close_swap(void)
-{
-	swp_entry_t entry;
-	int error;
-
-	dump_info();
-	error = write_page((unsigned long)&swsusp_info, &entry);
-	if (!error) {
-		printk( "S" );
-		error = mark_swapfiles(entry);
-		printk( "|\n" );
-	}
-	return error;
+	swsusp_info.image_pages = nr_pages;
+	swsusp_info.pages = nr_pages +
+		((nr_pages * sizeof(long) + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
 }
 
 /**
- *	free_pagedir_entries - Free pages used by the page directory.
- *
- *	This is used during suspend for error recovery.
+ *	pack_orig_addresses - the .orig_address fields of the PBEs from the
+ *	list starting at @pbe are stored in the array @buf[] (1 page)
  */
 
-static void free_pagedir_entries(void)
+static inline struct pbe *pack_orig_addresses(unsigned long *buf,
+                                              struct pbe *pbe)
 {
-	int i;
+	int j;
 
-	for (i = 0; i < swsusp_info.pagedir_pages; i++)
-		swap_free(swsusp_info.pagedir[i]);
+	for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+		buf[j] = pbe->orig_address;
+		pbe = pbe->next;
+	}
+	if (!pbe)
+		for (; j < PAGE_SIZE / sizeof(long); j++)
+			buf[j] = 0;
+	return pbe;
 }
 
-
 /**
- *	write_pagedir - Write the array of pages holding the page directory.
- *	@last:	Last swap entry we write (needed for header).
+ *	save_image_metadata - save the .orig_address fields of the PBEs
+ *	from the list @pblist using the swap map handle @handle
  */
 
-static int write_pagedir(void)
+static int save_image_metadata(struct pbe *pblist,
+                               struct swap_map_handle *handle)
 {
-	int error = 0;
+	unsigned long *buf;
 	unsigned int n = 0;
-	struct pbe *pbe;
+	struct pbe *p;
+	int error = 0;
 
-	printk( "Writing pagedir...");
-	for_each_pb_page (pbe, pagedir_nosave) {
-		if ((error = write_page((unsigned long)pbe, &swsusp_info.pagedir[n++])))
-			return error;
+	printk("Saving image metadata ... ");
+	buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+	p = pblist;
+	while (p) {
+		p = pack_orig_addresses(buf, p);
+		error = swap_map_write_page(handle, (unsigned long)buf);
+		if (error)
+			break;
+		n++;
 	}
-
-	swsusp_info.pagedir_pages = n;
-	printk("done (%u pages)\n", n);
+	free_page((unsigned long)buf);
+	if (!error)
+		printk("done (%u pages saved)\n", n);
 	return error;
 }
 
@@ -511,75 +481,125 @@ 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.
+ *	space avaiable from the resume partition.
  */
 
 static int enough_swap(unsigned int nr_pages)
 {
-	struct sysinfo i;
+	unsigned int free_swap = swap_info[root_swap].pages -
+		swap_info[root_swap].inuse_pages;
 
-	si_swapinfo(&i);
-	pr_debug("swsusp: available swap: %lu pages\n", i.freeswap);
-	return i.freeswap > (nr_pages + PAGES_FOR_IO +
+	pr_debug("swsusp: free swap pages: %u\n", free_swap);
+	return free_swap > (nr_pages + PAGES_FOR_IO +
 		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
 }
 
 /**
- *	write_suspend_image - Write entire image and metadata.
+ *	swsusp_write - Write entire image and metadata.
  *
+ *	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
+ *	correctly, we'll mark system clean, anyway.)
  */
-static int write_suspend_image(void)
+
+int swsusp_write(struct pbe *pblist, unsigned int nr_pages)
 {
+	struct swap_map_page *swap_map;
+	struct swap_map_handle handle;
+	swp_entry_t start;
 	int error;
 
-	if (!enough_swap(nr_copy_pages)) {
+	if ((error = swsusp_swap_check())) {
+		printk(KERN_ERR "swsusp: Cannot find swap device, try swapon -a.\n");
+		return error;
+	}
+	if (!enough_swap(nr_pages)) {
 		printk(KERN_ERR "swsusp: Not enough free swap\n");
 		return -ENOSPC;
 	}
 
-	init_header();
-	if ((error = data_write()))
-		goto FreeData;
+	init_header(nr_pages);
+	swap_map = alloc_swap_map(swsusp_info.pages);
+	if (!swap_map)
+		return -ENOMEM;
+	init_swap_map_handle(&handle, swap_map);
+
+	error = swap_map_write_page(&handle, (unsigned long)&swsusp_info);
+	if (!error)
+		error = save_image_metadata(pblist, &handle);
+	if (!error)
+		error = save_image_data(pblist, &handle, nr_pages);
+	if (error)
+		goto Free_image_entries;
 
-	if ((error = write_pagedir()))
-		goto FreePagedir;
+	swap_map = reverse_swap_map(swap_map);
+	error = save_swap_map(swap_map, &start);
+	if (error)
+		goto Free_map_entries;
 
-	if ((error = close_swap()))
-		goto FreePagedir;
- Done:
-	memset(key_iv, 0, MAXKEY+MAXIV);
+	dump_info();
+	printk( "S" );
+	error = mark_swapfiles(start);
+	printk( "|\n" );
+	if (error)
+		goto Free_map_entries;
+
+Free_swap_map:
+	free_swap_map(swap_map);
 	return error;
- FreePagedir:
-	free_pagedir_entries();
- FreeData:
-	data_free();
-	goto Done;
+
+Free_map_entries:
+	free_swap_map_entries(swap_map);
+Free_image_entries:
+	free_image_entries(swap_map);
+	goto Free_swap_map;
 }
 
-/* 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
- * correctly, we'll mark system clean, anyway.)
+/**
+ *	swsusp_shrink_memory -  Try to free as much memory as needed
+ *
+ *	... but do not OOM-kill anyone
+ *
+ *	Notice: all userland should be stopped before it is called, or
+ *	livelock is possible.
  */
-int swsusp_write(void)
-{
-	int error;
 
-	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;
-}
+#define SHRINK_BITE	10000
 
+int swsusp_shrink_memory(void)
+{
+	long size, tmp;
+	struct zone *zone;
+	unsigned long pages = 0;
+	unsigned int i = 0;
+	char *p = "-\\|/";
+
+	printk("Shrinking memory...  ");
+	do {
+		size = 2 * count_highmem_pages();
+		size += size / 50 + count_data_pages();
+		size += (size + PBES_PER_PAGE - 1) / PBES_PER_PAGE +
+			PAGES_FOR_IO;
+		tmp = size;
+		for_each_zone (zone)
+			if (!is_highmem(zone))
+				tmp -= zone->free_pages;
+		if (tmp > 0) {
+			tmp = shrink_all_memory(SHRINK_BITE);
+			if (!tmp)
+				return -ENOMEM;
+			pages += tmp;
+		} else if (size > (image_size * 1024 * 1024) / PAGE_SIZE) {
+			tmp = shrink_all_memory(SHRINK_BITE);
+			pages += tmp;
+		}
+		printk("\b%c", p[i++%4]);
+	} while (tmp > 0);
+	printk("\bdone (%lu pages freed)\n", pages);
 
+	return 0;
+}
 
 int swsusp_suspend(void)
 {
@@ -677,7 +697,6 @@ 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;
 	}
@@ -757,198 +776,224 @@ static int bio_write_page(pgoff_t page_off, void *page)
 	return submit(WRITE, page_off, page);
 }
 
-/*
- * Sanity check if this image makes sense with this kernel/swap context
- * I really don't think that it's foolproof but more than nothing..
+/**
+ *	The following functions allow us to read data using a swap map
+ *	in a file-alike way
  */
 
-static const char *sanity_check(void)
+static inline void release_swap_map_reader(struct swap_map_handle *handle)
 {
-	dump_info();
-	if (swsusp_info.version_code != LINUX_VERSION_CODE)
-		return "kernel version";
-	if (swsusp_info.num_physpages != num_physpages)
-		return "memory size";
-	if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
-		return "system type";
-	if (strcmp(swsusp_info.uts.release,system_utsname.release))
-		return "kernel release";
-	if (strcmp(swsusp_info.uts.version,system_utsname.version))
-		return "version";
-	if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
-		return "machine";
-#if 0
-	/* We can't use number of online CPUs when we use hotplug to remove them ;-))) */
-	if (swsusp_info.cpus != num_possible_cpus())
-		return "number of cpus";
-#endif
-	return NULL;
+	if (handle->cur)
+		free_page((unsigned long)handle->cur);
+	handle->cur = NULL;
 }
 
-
-static int check_header(void)
+static inline int get_swap_map_reader(struct swap_map_handle *handle,
+                                      swp_entry_t start)
 {
-	const char *reason = NULL;
 	int error;
 
-	if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info)))
+	if (!swp_offset(start))
+		return -EINVAL;
+	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+	if (!handle->cur)
+		return -ENOMEM;
+	error = bio_read_page(swp_offset(start), handle->cur);
+	if (error) {
+		release_swap_map_reader(handle);
 		return error;
-
- 	/* Is this same machine? */
-	if ((reason = sanity_check())) {
-		printk(KERN_ERR "swsusp: Resume mismatch: %s\n",reason);
-		return -EPERM;
 	}
-	nr_copy_pages = swsusp_info.image_pages;
-	return error;
+	handle->k = 0;
+	return 0;
 }
 
-static int check_sig(void)
+static inline int swap_map_read_page(struct swap_map_handle *handle, void *buf)
 {
+	unsigned long offset;
 	int error;
 
-	memset(&swsusp_header, 0, sizeof(swsusp_header));
-	if ((error = bio_read_page(0, &swsusp_header)))
-		return error;
-	if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
-		memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
-		memcpy(key_iv, swsusp_header.key_iv, MAXKEY+MAXIV);
-		memset(swsusp_header.key_iv, 0, MAXKEY+MAXIV);
-
-		/*
-		 * Reset swap signature now.
-		 */
-		error = bio_write_page(0, &swsusp_header);
-	} else {
+	if (!handle->cur)
+		return -EINVAL;
+	offset = swp_offset(handle->cur->entries[handle->k]);
+	if (!offset)
 		return -EINVAL;
+	error = bio_read_page(offset, buf);
+	if (error)
+		return error;
+	if (++handle->k >= MAP_PAGE_SIZE) {
+		handle->k = 0;
+		offset = swp_offset(handle->cur->next_swap);
+		if (!offset)
+			release_swap_map_reader(handle);
+		else
+			error = bio_read_page(offset, handle->cur);
 	}
-	if (!error)
-		pr_debug("swsusp: Signature found, resuming\n");
 	return error;
 }
 
-/**
- *	data_read - Read image pages from swap.
- *
- *	You do not need to check for overlaps, check_pagedir()
- *	already did that.
- */
-
-static int data_read(struct pbe *pblist)
+static int check_header(void)
 {
-	struct pbe *p;
-	int error = 0;
-	int i = 0;
-	int mod = swsusp_info.image_pages / 100;
-	void *tfm;
-
-	if ((error = crypto_init(0, &tfm)))
-		return error;
-
-	if (!mod)
-		mod = 1;
-
-	printk("swsusp: Reading image data (%lu pages):     ",
-			swsusp_info.image_pages);
-
-	for_each_pbe (p, pblist) {
-		if (!(i % mod))
-			printk("\b\b\b\b%3d%%", i / mod);
+	char *reason = NULL;
 
-		if ((error = crypto_read(p, tfm))) {
-			crypto_exit(tfm);
-			return error;
-		}
-
-		i++;
+	dump_info();
+	if (swsusp_info.version_code != LINUX_VERSION_CODE)
+		reason = "kernel version";
+	if (swsusp_info.num_physpages != num_physpages)
+		reason = "memory size";
+	if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
+		reason = "system type";
+	if (strcmp(swsusp_info.uts.release,system_utsname.release))
+		reason = "kernel release";
+	if (strcmp(swsusp_info.uts.version,system_utsname.version))
+		reason = "version";
+	if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
+		reason = "machine";
+	if (reason) {
+		printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason);
+		return -EPERM;
 	}
-	printk("\b\b\b\bdone\n");
-	crypto_exit(tfm);
-	return error;
+	return 0;
 }
 
 /**
- *	read_pagedir - Read page backup list pages from swap
+ *	load_image_data - load the image data using the swap map handle
+ *	@handle and store them using the page backup list @pblist
+ *	(assume there are @nr_pages pages to load)
  */
 
-static int read_pagedir(struct pbe *pblist)
+static int load_image_data(struct pbe *pblist,
+                           struct swap_map_handle *handle,
+                           unsigned int nr_pages)
 {
-	struct pbe *pbpage, *p;
-	unsigned int i = 0;
 	int error;
+	unsigned int m;
+	struct pbe *p;
 
 	if (!pblist)
-		return -EFAULT;
-
-	printk("swsusp: Reading pagedir (%lu pages)\n",
-			swsusp_info.pagedir_pages);
-
-	for_each_pb_page (pbpage, pblist) {
-		unsigned long offset = swp_offset(swsusp_info.pagedir[i++]);
-
-		error = -EFAULT;
-		if (offset) {
-			p = (pbpage + PB_PAGE_SKIP)->next;
-			error = bio_read_page(offset, (void *)pbpage);
-			(pbpage + PB_PAGE_SKIP)->next = p;
-		}
+		return -EINVAL;
+	printk("Loading image data pages (%u pages) ...     ", nr_pages);
+	m = nr_pages / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	p = pblist;
+	while (p) {
+		error = swap_map_read_page(handle, (void *)p->address);
 		if (error)
 			break;
+		p = p->next;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
 	}
-
 	if (!error)
-		BUG_ON(i != swsusp_info.pagedir_pages);
-
+		printk("\b\b\b\bdone\n");
 	return error;
 }
 
+/**
+ *	unpack_orig_addresses - copy the elements of @buf[] (1 page) to
+ *	the PBEs in the list starting at @pbe
+ */
 
-static int check_suspend_image(void)
+static inline struct pbe *unpack_orig_addresses(unsigned long *buf,
+                                                struct pbe *pbe)
 {
-	int error = 0;
+	int j;
 
-	if ((error = check_sig()))
-		return error;
-
-	if ((error = check_header()))
-		return error;
-
-	return 0;
+	for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+		pbe->orig_address = buf[j];
+		pbe = pbe->next;
+	}
+	return pbe;
 }
 
-static int read_suspend_image(void)
+/**
+ *	load_image_metadata - load the image metadata using the swap map
+ *	handle @handle and put them into the PBEs in the list @pblist
+ */
+
+static int load_image_metadata(struct pbe *pblist, struct swap_map_handle *handle)
 {
-	int error = 0;
 	struct pbe *p;
+	unsigned long *buf;
+	unsigned int n = 0;
+	int error = 0;
 
-	if (!(p = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 0)))
+	printk("Loading image metadata ... ");
+	buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+	if (!buf)
 		return -ENOMEM;
-
-	if ((error = read_pagedir(p)))
-		return error;
-	create_pbe_list(p, nr_copy_pages);
-	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);
+	p = pblist;
+	while (p) {
+		error = swap_map_read_page(handle, buf);
+		if (error)
+			break;
+		p = unpack_orig_addresses(buf, p);
+		n++;
 	}
-	free_pagedir(p);
-	if (!pagedir_nosave)
-		return -ENOMEM;
+	free_page((unsigned long)buf);
+	if (!error)
+		printk("done (%u pages loaded)\n", n);
+	return error;
+}
 
-	/* Allocate memory for the image and read the data from swap */
+int swsusp_read(struct pbe **pblist_ptr)
+{
+	int error;
+	struct pbe *p, *pblist;
+	struct swap_map_handle handle;
+	unsigned int nr_pages;
 
-	error = alloc_data_pages(pagedir_nosave, GFP_ATOMIC, 1);
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("swsusp: block device not initialised\n");
+		return PTR_ERR(resume_bdev);
+	}
 
+	error = get_swap_map_reader(&handle, swsusp_header.image);
 	if (!error)
-		error = data_read(pagedir_nosave);
+		error = swap_map_read_page(&handle, &swsusp_info);
+	if (!error)
+		error = check_header();
+	if (error)
+		return error;
+	nr_pages = swsusp_info.image_pages;
+	p = alloc_pagedir(nr_pages, GFP_ATOMIC, 0);
+	if (!p)
+		return -ENOMEM;
+	error = load_image_metadata(p, &handle);
+	if (!error) {
+		mark_unsafe_pages(p);
+		pblist = alloc_pagedir(nr_pages, GFP_ATOMIC, 1);
+		if (pblist)
+			copy_page_backup_list(pblist, p);
+		free_pagedir(p);
+		if (!pblist)
+			error = -ENOMEM;
+
+		/* Allocate memory for the image and read the data from swap */
+		if (!error)
+			error = alloc_data_pages(pblist, GFP_ATOMIC, 1);
+		if (!error) {
+			release_eaten_pages();
+			error = load_image_data(pblist, &handle, nr_pages);
+		}
+		if (!error)
+			*pblist_ptr = pblist;
+	}
+	release_swap_map_reader(&handle);
 
+	blkdev_put(resume_bdev);
+
+	if (!error)
+		pr_debug("swsusp: Reading resume file was successful\n");
+	else
+		pr_debug("swsusp: Error %d resuming\n", error);
 	return error;
 }
 
 /**
- *      swsusp_check - Check for saved image in swap
+ *      swsusp_check - Check for swsusp signature in the resume device
  */
 
 int swsusp_check(void)
@@ -958,40 +1003,27 @@ int swsusp_check(void)
 	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
 	if (!IS_ERR(resume_bdev)) {
 		set_blocksize(resume_bdev, PAGE_SIZE);
-		error = check_suspend_image();
+		memset(&swsusp_header, 0, sizeof(swsusp_header));
+		if ((error = bio_read_page(0, &swsusp_header)))
+			return error;
+		if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
+			memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+			/* Reset swap signature now */
+			error = bio_write_page(0, &swsusp_header);
+		} else {
+			return -EINVAL;
+		}
 		if (error)
-		    blkdev_put(resume_bdev);
-	} else
+			blkdev_put(resume_bdev);
+		else
+			pr_debug("swsusp: Signature found, resuming\n");
+	} else {
 		error = PTR_ERR(resume_bdev);
-
-	if (!error)
-		pr_debug("swsusp: resume file found\n");
-	else
-		pr_debug("swsusp: Error %d check for resume file\n", error);
-	return error;
-}
-
-/**
- *	swsusp_read - Read saved image from swap.
- */
-
-int swsusp_read(void)
-{
-	int error;
-
-	if (IS_ERR(resume_bdev)) {
-		pr_debug("swsusp: block device not initialised\n");
-		return PTR_ERR(resume_bdev);
 	}
 
-	error = read_suspend_image();
-	blkdev_put(resume_bdev);
-	memset(key_iv, 0, MAXKEY+MAXIV);
+	if (error)
+		pr_debug("swsusp: Error %d check for resume file\n", error);
 
-	if (!error)
-		pr_debug("swsusp: Reading resume file was successful\n");
-	else
-		pr_debug("swsusp: Error %d resuming\n", error);
 	return error;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b53115b882e..a85047bb573 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -31,6 +31,7 @@
 #include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kobject.h>
 #include <linux/net.h>
 #include <linux/sysrq.h>
 #include <linux/highuid.h>
@@ -83,9 +84,6 @@ static int ngroups_max = NGROUPS_MAX;
 #ifdef CONFIG_KMOD
 extern char modprobe_path[];
 #endif
-#ifdef CONFIG_HOTPLUG
-extern char hotplug_path[];
-#endif
 #ifdef CONFIG_CHR_DEV_SG
 extern int sg_big_buff;
 #endif
@@ -110,7 +108,7 @@ extern int pwrsw_enabled;
 extern int unaligned_enabled;
 #endif
 
-#ifdef CONFIG_ARCH_S390
+#ifdef CONFIG_S390
 #ifdef CONFIG_MATHEMU
 extern int sysctl_ieee_emulation_warnings;
 #endif
@@ -397,8 +395,8 @@ static ctl_table kern_table[] = {
 	{
 		.ctl_name	= KERN_HOTPLUG,
 		.procname	= "hotplug",
-		.data		= &hotplug_path,
-		.maxlen		= HOTPLUG_PATH_LEN,
+		.data		= &uevent_helper,
+		.maxlen		= UEVENT_HELPER_PATH_LEN,
 		.mode		= 0644,
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,
@@ -544,7 +542,7 @@ static ctl_table kern_table[] = {
 		.extra1		= &minolduid,
 		.extra2		= &maxolduid,
 	},
-#ifdef CONFIG_ARCH_S390
+#ifdef CONFIG_S390
 #ifdef CONFIG_MATHEMU
 	{
 		.ctl_name	= KERN_IEEE_EMULATION_WARNINGS,
@@ -646,7 +644,7 @@ static ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
-#if defined(CONFIG_ARCH_S390)
+#if defined(CONFIG_S390)
 	{
 		.ctl_name	= KERN_SPIN_RETRY,
 		.procname	= "spin_retry",