Merge bk://linux.bkbits.net/linux-2.5

into kernel.bkbits.net:/home/mochel/linux-2.5-power

arch/i386/Makefile

@@ -96,6 +96,7 @@ drivers-$(CONFIG_MATH_EMULATION)	+= arch/i386/math-emu/
 drivers-$(CONFIG_PCI)			+= arch/i386/pci/
 # must be linked after kernel/
 drivers-$(CONFIG_OPROFILE)		+= arch/i386/oprofile/
+drivers-$(CONFIG_PM)			+= arch/i386/power/
 
 CFLAGS += $(mflags-y)
 AFLAGS += $(mflags-y)

arch/i386/kernel/Makefile

@@ -17,9 +17,7 @@ obj-$(CONFIG_MCA)		+= mca.o
 obj-$(CONFIG_X86_MSR)		+= msr.o
 obj-$(CONFIG_X86_CPUID)		+= cpuid.o
 obj-$(CONFIG_MICROCODE)		+= microcode.o
-obj-$(CONFIG_PM)		+= suspend.o
 obj-$(CONFIG_APM)		+= apm.o
-obj-$(CONFIG_SOFTWARE_SUSPEND)	+= suspend_asm.o
 obj-$(CONFIG_X86_SMP)		+= smp.o smpboot.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o

arch/i386/power/Makefile

+obj-$(CONFIG_PM)		+= cpu.o
+obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o

arch/i386/kernel/suspend_asm.S → arch/i386/power/swsusp.S

@@ -8,11 +8,10 @@
 
 	.text
 
-ENTRY(do_magic)
+ENTRY(swsusp_arch_suspend)
 	pushl %ebx
 	cmpl $0,8(%esp)
 	jne .L1450
-	call do_magic_suspend_1
 	call save_processor_state
 
 	movl %esp, saved_context_esp
@@ -25,14 +24,13 @@ ENTRY(do_magic)
 	movl %edi, saved_context_edi
 	pushfl ; popl saved_context_eflags
 
-	call do_magic_suspend_2
+	call swsusp_suspend
 	jmp .L1449
 	.p2align 4,,7
 .L1450:
 	movl $swapper_pg_dir-__PAGE_OFFSET,%ecx
 	movl %ecx,%cr3
 
-	call do_magic_resume_1
 	movl $0,loop
 	cmpl $0,nr_copy_pages
 	je .L1453
@@ -80,7 +78,7 @@ ENTRY(do_magic)
 	movl saved_context_edi, %edi
 	call restore_processor_state
 	pushl saved_context_eflags ; popfl
-	call do_magic_resume_2
+	call swsusp_resume
 .L1449:
 	popl %ebx
 	ret
@@ -91,4 +89,4 @@ loop:
 loop2:
        .quad 0
        .previous
-	
\ No newline at end of file
+

drivers/acpi/sleep/main.c

@@ -41,7 +41,6 @@ static u32 acpi_suspend_states[] = {
 
 static int acpi_pm_prepare(u32 state)
 {
-	int error = 0;
 	u32 acpi_state = acpi_suspend_states[state];
 
 	if (!sleep_states[acpi_state])
@@ -56,21 +55,9 @@ static int acpi_pm_prepare(u32 state)
 		acpi_set_firmware_waking_vector(
 			(acpi_physical_address) acpi_wakeup_address);
 	}
-
 	ACPI_FLUSH_CPU_CACHE();
-
-	/* Do arch specific saving of state. */
-	if (state > PM_SUSPEND_STANDBY) {
-		if ((error = acpi_save_state_mem()))
-			goto Err;
-	}
-
 	acpi_enter_sleep_state_prep(acpi_state);
-
 	return 0;
- Err:
-	acpi_set_firmware_waking_vector(0);
-	return error;
 }
 
 
@@ -90,6 +77,15 @@ static int acpi_pm_enter(u32 state)
 	u32 acpi_state = acpi_suspend_states[state];
 
 	ACPI_FLUSH_CPU_CACHE();
+
+	/* Do arch specific saving of state. */
+	if (state > PM_SUSPEND_STANDBY) {
+		int error = acpi_save_state_mem();
+		if (error)
+			return error;
+	}
+
+
 	local_irq_save(flags);
 	switch (state)
 	{
@@ -114,6 +110,15 @@ static int acpi_pm_enter(u32 state)
 	local_irq_restore(flags);
 	printk(KERN_DEBUG "Back to C!\n");
 
+	/* restore processor state
+	 * We should only be here if we're coming back from STR or STD.
+	 * And, in the case of the latter, the memory image should have already
+	 * been loaded from disk.
+	 */
+	if (state > PM_SUSPEND_STANDBY)
+		acpi_restore_state_mem();
+
+
 	return ACPI_SUCCESS(status) ? 0 : -EFAULT;
 }
 
@@ -130,14 +135,6 @@ static int acpi_pm_finish(u32 state)
 {
 	acpi_leave_sleep_state(state);
 
-	/* restore processor state
-	 * We should only be here if we're coming back from STR or STD.
-	 * And, in the case of the latter, the memory image should have already
-	 * been loaded from disk.
-	 */
-	if (state > ACPI_STATE_S1)
-		acpi_restore_state_mem();
-
 	/* reset firmware waking vector */
 	acpi_set_firmware_waking_vector((acpi_physical_address) 0);
 
@@ -149,6 +146,20 @@ static int acpi_pm_finish(u32 state)
 }
 
 
+int acpi_suspend(u32 acpi_state)
+{
+	u32 states[] = {
+		[1]	= PM_SUSPEND_STANDBY,
+		[3]	= PM_SUSPEND_MEM,
+		[4]	= PM_SUSPEND_DISK,
+	};
+
+	if (acpi_state <= 4 && states[acpi_state])
+		return pm_suspend(states[acpi_state]);
+	return -EINVAL;
+}
+
+
 static struct pm_ops acpi_pm_ops = {
 	.prepare	= acpi_pm_prepare,
 	.enter		= acpi_pm_enter,

drivers/acpi/sleep/proc.c

@@ -13,12 +13,71 @@
 
 #include "sleep.h"
 
+#define ACPI_SYSTEM_FILE_SLEEP		"sleep"
 #define ACPI_SYSTEM_FILE_ALARM		"alarm"
 
 #define _COMPONENT		ACPI_SYSTEM_COMPONENT
 ACPI_MODULE_NAME		("sleep")
 
 
+static int acpi_system_sleep_seq_show(struct seq_file *seq, void *offset)
+{
+	int			i;
+
+	ACPI_FUNCTION_TRACE("acpi_system_sleep_seq_show");
+
+	for (i = 0; i <= ACPI_STATE_S5; i++) {
+		if (sleep_states[i]) {
+			seq_printf(seq,"S%d ", i);
+			if (i == ACPI_STATE_S4 && acpi_gbl_FACS->S4bios_f)
+				seq_printf(seq, "S4bios ");
+		}
+	}
+
+	seq_puts(seq, "\n");
+
+	return 0;
+}
+
+static int acpi_system_sleep_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, acpi_system_sleep_seq_show, PDE(inode)->data);
+}
+
+static int
+acpi_system_write_sleep (
+	struct file		*file,
+	const char		*buffer,
+	size_t			count,
+	loff_t			*ppos)
+{
+	char	str[12];
+	u32	state = 0;
+	int	error = 0;
+
+	if (count > sizeof(str) - 1)
+		goto Done;
+	memset(str,0,sizeof(str));
+	if (copy_from_user(str, buffer, count))
+		return -EFAULT;
+
+	/* Check for S4 bios request */
+	if (!strcmp(str,"4b")) {
+		error = acpi_suspend(4);
+		goto Done;
+	}
+	state = simple_strtoul(str, NULL, 0);
+#ifdef CONFIG_SOFTWARE_SUSPEND
+	if (state == 4) {
+		error = software_suspend();
+		goto Done;
+	}
+#endif
+	error = acpi_suspend(state);
+ Done:
+	return error ? error : count;
+}
+
 static int acpi_system_alarm_seq_show(struct seq_file *seq, void *offset)
 {
 	u32			sec, min, hr;
@@ -294,6 +353,14 @@ acpi_system_write_alarm (
 }
 
 
+static struct file_operations acpi_system_sleep_fops = {
+	.open		= acpi_system_sleep_open_fs,
+	.read		= seq_read,
+	.write		= acpi_system_write_sleep,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct file_operations acpi_system_alarm_fops = {
 	.open		= acpi_system_alarm_open_fs,
 	.read		= seq_read,
@@ -307,6 +374,12 @@ static int acpi_sleep_proc_init(void)
 {
 	struct proc_dir_entry	*entry = NULL;
 
+	/* 'sleep' [R/W]*/
+	entry = create_proc_entry(ACPI_SYSTEM_FILE_SLEEP,
+				  S_IFREG|S_IRUGO|S_IWUSR, acpi_root_dir);
+	if (entry)
+		entry->proc_fops = &acpi_system_sleep_fops;
+
 	/* 'alarm' [R/W] */
 	entry = create_proc_entry(ACPI_SYSTEM_FILE_ALARM,
 		S_IFREG|S_IRUGO|S_IWUSR, acpi_root_dir);

drivers/acpi/sleep/sleep.h

 
 extern u8 sleep_states[];
-
-extern acpi_status acpi_suspend (u32 state);
+extern int acpi_suspend (u32 state);
 

drivers/base/core.c

@@ -225,28 +225,30 @@ int device_add(struct device *dev)
 		dev->kobj.parent = &parent->kobj;
 
 	if ((error = kobject_add(&dev->kobj)))
-		goto register_done;
-
-	/* now take care of our own registration */
-
+		goto Error;
+	if ((error = device_pm_add(dev)))
+		goto PMError;
+	if ((error = bus_add_device(dev)))
+		goto BusError;
 	down_write(&devices_subsys.rwsem);
 	if (parent)
 		list_add_tail(&dev->node,&parent->children);
 	up_write(&devices_subsys.rwsem);
 
-	bus_add_device(dev);
-
-	device_pm_add(dev);
-
 	/* notify platform of device entry */
 	if (platform_notify)
 		platform_notify(dev);
-
- register_done:
-	if (error && parent)
-		put_device(parent);
+ Done:
 	put_device(dev);
 	return error;
+ BusError:
+	device_pm_remove(dev);
+ PMError:
+	kobject_unregister(&dev->kobj);
+ Error:
+	if (parent)
+		put_device(parent);
+	goto Done;
 }
 
 
@@ -312,8 +314,6 @@ void device_del(struct device * dev)
 {
 	struct device * parent = dev->parent;
 
-	device_pm_remove(dev);
-
 	down_write(&devices_subsys.rwsem);
 	if (parent)
 		list_del_init(&dev->node);
@@ -324,14 +324,11 @@ void device_del(struct device * dev)
 	 */
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
-
 	bus_remove_device(dev);
-
+	device_pm_remove(dev);
 	kobject_del(&dev->kobj);
-
 	if (parent)
 		put_device(parent);
-
 }
 
 /**

drivers/base/power/main.c

@@ -36,12 +36,14 @@ DECLARE_MUTEX(dpm_sem);
 
 static inline void device_pm_hold(struct device * dev)
 {
-	atomic_inc(&dev->power.pm_users);
+	if (dev)
+		atomic_inc(&dev->power.pm_users);
 }
 
 static inline void device_pm_release(struct device * dev)
 {
-	atomic_inc(&dev->power.pm_users);
+	if (dev)
+		atomic_dec(&dev->power.pm_users);
 }
 
 
@@ -61,11 +63,9 @@ static inline void device_pm_release(struct device * dev)
 void device_pm_set_parent(struct device * dev, struct device * parent)
 {
 	struct device * old_parent = dev->power.pm_parent;
-	if (old_parent)
-		device_pm_release(old_parent);
+	device_pm_release(old_parent);
 	dev->power.pm_parent = parent;
-	if (parent)
-		device_pm_hold(parent);
+	device_pm_hold(parent);
 }
 EXPORT_SYMBOL(device_pm_set_parent);
 
@@ -91,6 +91,7 @@ void device_pm_remove(struct device * dev)
 		 dev->bus ? dev->bus->name : "No Bus", dev->kobj.name);
 	down(&dpm_sem);
 	dpm_sysfs_remove(dev);
+	device_pm_release(dev->power.pm_parent);
 	list_del(&dev->power.entry);
 	up(&dpm_sem);
 }

drivers/base/power/power.h

@@ -58,7 +58,8 @@ extern void dpm_sysfs_remove(struct device *);
 /*
  * resume.c 
  */
-extern int dpm_resume(void);
+
+extern void dpm_resume(void);
 extern void dpm_power_up(void);
 extern int resume_device(struct device *);
 

drivers/base/power/resume.c

@@ -28,6 +28,19 @@ int resume_device(struct device * dev)
 }
 
 
+
+void dpm_resume(void)
+{
+	while(!list_empty(&dpm_off)) {
+		struct list_head * entry = dpm_off.next;
+		struct device * dev = to_device(entry);
+		list_del_init(entry);
+		resume_device(dev);
+		list_add_tail(entry,&dpm_active);
+	}
+}
+
+
 /**
  *	device_resume - Restore state of each device in system.
  *
@@ -38,13 +51,7 @@ int resume_device(struct device * dev)
 void device_resume(void)
 {
 	down(&dpm_sem);
-	while(!list_empty(&dpm_off)) {
-		struct list_head * entry = dpm_off.next;
-		struct device * dev = to_device(entry);
-		list_del_init(entry);
-		resume_device(dev);
-		list_add_tail(entry,&dpm_active);
-	}
+	dpm_resume();
 	up(&dpm_sem);
 }
 

drivers/base/power/suspend.c

@@ -81,14 +81,18 @@ int device_suspend(u32 state)
 	while(!list_empty(&dpm_active)) {
 		struct list_head * entry = dpm_active.prev;
 		struct device * dev = to_device(entry);
-		if ((error = suspend_device(dev,state)))
-			goto Error;
+		if ((error = suspend_device(dev,state))) {
+			if (error != -EAGAIN)
+				goto Error;
+			else
+				error = 0;
+		}
 	}
  Done:
 	up(&dpm_sem);
 	return error;
  Error:
-	device_resume();
+	dpm_resume();
 	goto Done;
 }
 

include/asm-i386/suspend.h

@@ -6,11 +6,12 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 
-static inline void
+static inline int
 arch_prepare_suspend(void)
 {
 	if (!cpu_has_pse)
-		panic("pse required");
+		return -EPERM;
+	return 0;
 }
 
 /* image of the saved processor state */
@@ -38,8 +39,6 @@ struct saved_context {
 extern void save_processor_state(void);
 extern void restore_processor_state(void);
 
-extern int do_magic(int resume);
-
 #ifdef CONFIG_ACPI_SLEEP
 extern unsigned long saved_eip;
 extern unsigned long saved_esp;

include/linux/suspend.h

@@ -53,6 +53,7 @@ extern suspend_pagedir_t *pagedir_nosave __nosavedata;
 extern void do_suspend_lowlevel(int resume);
 extern void do_suspend_lowlevel_s4bios(int resume);
 
+extern int software_suspend(void);
 #else	/* CONFIG_SOFTWARE_SUSPEND */
 static inline int software_suspend(void)
 {

kernel/power/Makefile

 obj-y				:= main.o process.o console.o pm.o
-obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o
+obj-$(CONFIG_SOFTWARE_SUSPEND)	+= disk.o swsusp.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o

kernel/power/console.c

@@ -8,7 +8,7 @@
 #include <linux/kbd_kern.h>
 #include "power.h"
 
-static int new_loglevel = 7;
+static int new_loglevel = 10;
 static int orig_loglevel;
 static int orig_fgconsole, orig_kmsg;
 

kernel/power/disk.c

+/*
+ * kernel/power/disk.c - Suspend-to-disk support.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ *
+ * This file is release under the GPLv2
+ *
+ */
+
+#define DEBUG
+
+
+#include <linux/suspend.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include "power.h"
+
+
+extern u32 pm_disk_mode;
+extern struct pm_ops * pm_ops;
+
+extern int swsusp_save(void);
+extern int swsusp_write(void);
+extern int swsusp_read(void);
+extern int swsusp_restore(void);
+extern int swsusp_free(void);
+
+extern long sys_sync(void);
+
+
+/**
+ *	power_down - Shut machine down for hibernate.
+ *	@mode:		Suspend-to-disk mode
+ *
+ *	Use the platform driver, if configured so, and return gracefully if it
+ *	fails.
+ *	Otherwise, try to power off and reboot. If they fail, halt the machine,
+ *	there ain't no turning back.
+ */
+
+static int power_down(u32 mode)
+{
+	unsigned long flags;
+	int error = 0;
+
+	local_irq_save(flags);
+	device_power_down(PM_SUSPEND_DISK);
+	switch(mode) {
+	case PM_DISK_PLATFORM:
+		error = pm_ops->enter(PM_SUSPEND_DISK);
+		break;
+	case PM_DISK_SHUTDOWN:
+		printk("Powering off system\n");
+		machine_power_off();
+		break;
+	case PM_DISK_REBOOT:
+		machine_restart(NULL);
+		break;
+	}
+	machine_halt();
+	device_power_up();
+	local_irq_restore(flags);
+	return 0;
+}
+
+
+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)
+{
+	printk("Freeing memory: ");
+	while (shrink_all_memory(10000))
+		printk(".");
+	printk("|\n");
+	blk_run_queues();
+}
+
+
+static inline void platform_finish(void)
+{
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->finish)
+			pm_ops->finish(PM_SUSPEND_DISK);
+	}
+}
+
+static void finish(void)
+{
+	device_resume();
+	platform_finish();
+	thaw_processes();
+	pm_restore_console();
+}
+
+
+static int prepare(void)
+{
+	int error;
+
+	pm_prepare_console();
+
+	sys_sync();
+	if (freeze_processes()) {
+		error = -EBUSY;
+		goto Thaw;
+	}
+
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->prepare) {
+			if ((error = pm_ops->prepare(PM_SUSPEND_DISK)))
+				goto Thaw;
+		}
+	}
+
+	/* Free memory before shutting down devices. */
+	free_some_memory();
+
+	if ((error = device_suspend(PM_SUSPEND_DISK)))
+		goto Finish;
+
+	return 0;
+ Finish:
+	platform_finish();
+ Thaw:
+	thaw_processes();
+	pm_restore_console();
+	return error;
+}
+
+
+/**
+ *	pm_suspend_disk - The granpappy of power management.
+ *
+ *	If we're going through the firmware, then get it over with quickly.
+ *
+ *	If not, then call swsusp to do it's thing, then figure out how
+ *	to power down the system.
+ */
+
+int pm_suspend_disk(void)
+{
+	int error;
+
+	if ((error = prepare()))
+		return error;
+
+	pr_debug("PM: Attempting to suspend to disk.\n");
+	if (pm_disk_mode == PM_DISK_FIRMWARE)
+		return pm_ops->enter(PM_SUSPEND_DISK);
+
+	pr_debug("PM: snapshotting memory.\n");
+	in_suspend = 1;
+	local_irq_disable();
+	if ((error = swsusp_save()))
+		goto Done;
+
+	pr_debug("PM: writing image.\n");
+
+	/*
+	 * FIXME: Leftover from swsusp. Are they necessary?
+	 */
+	mb();
+	barrier();
+
+	error = swsusp_write();
+	if (!error && in_suspend) {
+		error = power_down(pm_disk_mode);
+		pr_debug("PM: Power down failed.\n");
+	} else
+		pr_debug("PM: Image restored successfully.\n");
+	swsusp_free();
+ Done:
+	local_irq_enable();
+	finish();
+	return error;
+}
+
+
+/**
+ *	pm_resume - Resume from a saved image.
+ *
+ *	Called as a late_initcall (so all devices are discovered and
+ *	initialized), we call swsusp to see if we have a saved image or not.
+ *	If so, we quiesce devices, the restore the saved image. We will
+ *	return above (in pm_suspend_disk() ) if everything goes well.
+ *	Otherwise, we fail gracefully and return to the normally
+ *	scheduled program.
+ *
+ */
+
+static int pm_resume(void)
+{
+	int error;
+
+	pr_debug("PM: Reading swsusp image.\n");
+
+	if ((error = swsusp_read()))
+		goto Done;
+
+	pr_debug("PM: Preparing system for restore.\n");
+
+	if ((error = prepare()))
+		goto Free;
+
+	barrier();
+	mb();
+	local_irq_disable();
+
+	/* FIXME: The following (comment and mdelay()) are from swsusp.
+	 * Are they really necessary?
+	 *
+	 * We do not want some readahead with DMA to corrupt our memory, right?
+	 * Do it with disabled interrupts for best effect. That way, if some
+	 * driver scheduled DMA, we have good chance for DMA to finish ;-).
+	 */
+	pr_debug("PM: Waiting for DMAs to settle down.\n");
+	mdelay(1000);
+
+	pr_debug("PM: Restoring saved image.\n");
+	swsusp_restore();
+	local_irq_enable();
+	pr_debug("PM: Restore failed, recovering.n");
+	finish();
+ Free:
+	swsusp_free();
+ Done:
+	pr_debug("PM: Resume from disk failed.\n");
+	return 0;
+}
+
+late_initcall(pm_resume);
+
+
+static char * pm_disk_modes[] = {
+	[PM_DISK_FIRMWARE]	= "firmware",
+	[PM_DISK_PLATFORM]	= "platform",
+	[PM_DISK_SHUTDOWN]	= "shutdown",
+	[PM_DISK_REBOOT]	= "reboot",
+};
+
+/**
+ *	disk - Control suspend-to-disk mode
+ *
+ *	Suspend-to-disk can be handled in several ways. The greatest
+ *	distinction is who writes memory to disk - the firmware or the OS.
+ *	If the firmware does it, we assume that it also handles suspending
+ *	the system.
+ *	If the OS does it, then we have three options for putting the system
+ *	to sleep - using the platform driver (e.g. ACPI or other PM registers),
+ *	powering off the system or rebooting the system (for testing).
+ *
+ *	The system will support either 'firmware' or 'platform', and that is
+ *	known a priori (and encoded in pm_ops). But, the user may choose
+ *	'shutdown' or 'reboot' as alternatives.
+ *
+ *	show() will display what the mode is currently set to.
+ *	store() will accept one of
+ *
+ *	'firmware'
+ *	'platform'
+ *	'shutdown'
+ *	'reboot'
+ *
+ *	It will only change to 'firmware' or 'platform' if the system
+ *	supports it (as determined from pm_ops->pm_disk_mode).
+ */
+
+static ssize_t disk_show(struct subsystem * subsys, char * buf)
+{
+	return sprintf(buf,"%s\n",pm_disk_modes[pm_disk_mode]);
+}
+
+
+static ssize_t disk_store(struct subsystem * s, const char * buf, size_t n)
+{
+	int error = 0;
+	int i;
+	u32 mode = 0;
+
+	down(&pm_sem);
+	for (i = PM_DISK_FIRMWARE; i < PM_DISK_MAX; i++) {
+		if (!strcmp(buf,pm_disk_modes[i])) {
+			mode = i;
+			break;
+		}
+	}
+	if (mode) {
+		if (mode == PM_DISK_SHUTDOWN || mode == PM_DISK_REBOOT)
+			pm_disk_mode = mode;
+		else {
+			if (pm_ops && pm_ops->enter &&
+			    (mode == pm_ops->pm_disk_mode))
+				pm_disk_mode = mode;
+			else
+				error = -EINVAL;
+		}
+	} else
+		error = -EINVAL;
+
+	pr_debug("PM: suspend-to-disk mode set to '%s'\n",
+		 pm_disk_modes[mode]);
+	up(&pm_sem);
+	return error ? error : n;
+}
+
+power_attr(disk);
+
+static struct attribute * g[] = {
+	&disk_attr.attr,
+	NULL,
+};
+
+
+static struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+
+static int __init pm_disk_init(void)
+{
+	return sysfs_create_group(&power_subsys.kset.kobj,&attr_group);
+}
+
+core_initcall(pm_disk_init);

kernel/power/main.c

@@ -8,32 +8,23 @@
  *
  */
 
+#define DEBUG
+
 #include <linux/suspend.h>
 #include <linux/kobject.h>
-#include <linux/reboot.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/pm.h>
-#include <linux/fs.h>
 
 
 #include "power.h"
 
-static DECLARE_MUTEX(pm_sem);
-
-static struct pm_ops * pm_ops = NULL;
-
-static u32 pm_disk_mode = PM_DISK_SHUTDOWN;
-
-#ifdef CONFIG_SOFTWARE_SUSPEND
-static int have_swsusp = 1;
-#else
-static int have_swsusp = 0;
-#endif
-
-extern long sys_sync(void);
+DECLARE_MUTEX(pm_sem);
 
+struct pm_ops * pm_ops = NULL;
+u32 pm_disk_mode = PM_DISK_SHUTDOWN;
 
 /**
  *	pm_set_ops - Set the global power method table. 
@@ -50,171 +41,6 @@ void pm_set_ops(struct pm_ops * ops)
 }
 
 
-/**
- *	pm_suspend_standby - Enter 'standby' state.
- *	
- *	'standby' is also known as 'Power-On Suspend'. Here, we power down
- *	devices, disable interrupts, and enter the state.
- */
-
-static int pm_suspend_standby(void)
-{
-	int error = 0;
-	unsigned long flags;
-
-	if (!pm_ops || !pm_ops->enter)
-		return -EPERM;
-
-	local_irq_save(flags);
-	if ((error = device_power_down(PM_SUSPEND_STANDBY)))
-		goto Done;
-	error = pm_ops->enter(PM_SUSPEND_STANDBY);
-	local_irq_restore(flags);
-	device_power_up();
- Done:
-	return error;
-}
-
-
-/**
- *	pm_suspend_mem - Enter suspend-to-RAM state.
- *
- *	Identical to pm_suspend_standby() - we power down devices, disable 
- *	interrupts, and enter the low-power state.
- */
-
-static int pm_suspend_mem(void)
-{
-	int error = 0;
-	unsigned long flags;
-
-	if (!pm_ops || !pm_ops->enter)
-		return -EPERM;
-
-	local_irq_save(flags);
-	if ((error = device_power_down(PM_SUSPEND_STANDBY)))
-		goto Done;
-	error = pm_ops->enter(PM_SUSPEND_STANDBY);
-	local_irq_restore(flags);
-	device_power_up();
- Done:
-	return error;
-}
-
-
-/**
- *	power_down - Shut machine down for hibernate.
- *	@mode:		Suspend-to-disk mode
- *
- *	Use the platform driver, if configured so, and return gracefully if it
- *	fails. 
- *	Otherwise, try to power off and reboot. If they fail, halt the machine,
- *	there ain't no turning back.
- */
-
-static int power_down(u32 mode)
-{
-	unsigned long flags;
-	int error = 0;
-
-	local_irq_save(flags);
-	device_power_down(PM_SUSPEND_DISK);
-	switch(mode) {
-	case PM_DISK_PLATFORM:
-		error = pm_ops->enter(PM_SUSPEND_DISK);
-		if (error) {
-			device_power_up();
-			local_irq_restore(flags);
-			return error;
-		}
-	case PM_DISK_SHUTDOWN:
-		machine_power_off();
-		break;
-	case PM_DISK_REBOOT:
-		machine_restart(NULL);
-		break;
-	}
-	machine_halt();
-	return 0;
-}
-
-
-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)
-{
-	printk("Freeing memory: ");
-	while (shrink_all_memory(10000))
-		printk(".");
-	printk("|\n");
-	blk_run_queues();
-}
-
-
-/**
- *	pm_suspend_disk - The granpappy of power management.
- *	
- *	If we're going through the firmware, then get it over with quickly.
- *
- *	If not, then call swsusp to do it's thing, then figure out how
- *	to power down the system.
- */
-
-static int pm_suspend_disk(void)
-{
-	int error;
-
-	pr_debug("PM: Attempting to suspend to disk.\n");
-	if (pm_disk_mode == PM_DISK_FIRMWARE)
-		return pm_ops->enter(PM_SUSPEND_DISK);
-
-	if (!have_swsusp)
-		return -EPERM;
-
-	pr_debug("PM: snapshotting memory.\n");
-	in_suspend = 1;
-	if ((error = swsusp_save()))
-		goto Done;
-
-	if (in_suspend) {
-		pr_debug("PM: writing image.\n");
-		error = swsusp_write();
-		if (!error)
-			error = power_down(pm_disk_mode);
-		pr_debug("PM: Power down failed.\n");
-	} else
-		pr_debug("PM: Image restored successfully.\n");
-	swsusp_free();
- Done:
-	return error;
-}
-
-
-
-#define decl_state(_name) \
-	{ .name = __stringify(_name), .fn = pm_suspend_##_name }
-
-struct pm_state {
-	char * name;
-	int (*fn)(void);
-} pm_states[] = {
-	[PM_SUSPEND_STANDBY]	= decl_state(standby),
-	[PM_SUSPEND_MEM]	= decl_state(mem),
-	[PM_SUSPEND_DISK]	= decl_state(disk),
-	{ NULL },
-};
-
-
 /**
  *	suspend_prepare - Do prep work before entering low-power state.
  *	@state:		State we're entering.
@@ -228,23 +54,21 @@ static int suspend_prepare(u32 state)
 {
 	int error = 0;
 
+	if (!pm_ops || !pm_ops->enter)
+		return -EPERM;
+
 	pm_prepare_console();
 
-	sys_sync();
 	if (freeze_processes()) {
 		error = -EAGAIN;
 		goto Thaw;
 	}
 
-	if (pm_ops && pm_ops->prepare) {
+	if (pm_ops->prepare) {
 		if ((error = pm_ops->prepare(state)))
 			goto Thaw;
 	}
 
-	/* Free memory before shutting down devices. */
-	if (state == PM_SUSPEND_DISK)
-		free_some_memory();
-
 	if ((error = device_suspend(state)))
 		goto Finish;
 
@@ -253,7 +77,7 @@ static int suspend_prepare(u32 state)
 	pm_restore_console();
 	return error;
  Finish:
-	if (pm_ops && pm_ops->finish)
+	if (pm_ops->finish)
 		pm_ops->finish(state);
  Thaw:
 	thaw_processes();
@@ -261,6 +85,22 @@ static int suspend_prepare(u32 state)
 }
 
 
+static int suspend_enter(u32 state)
+{
+	int error = 0;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if ((error = device_power_down(state)))
+		goto Done;
+	error = pm_ops->enter(state);
+	local_irq_restore(flags);
+	device_power_up();
+ Done:
+	return error;
+}
+
+
 /**
  *	suspend_finish - Do final work before exiting suspend sequence.
  *	@state:		State we're coming out of.
@@ -279,6 +119,16 @@ static void suspend_finish(u32 state)
 }
 
 
+
+
+char * pm_states[] = {
+	[PM_SUSPEND_STANDBY]	= "standby",
+	[PM_SUSPEND_MEM]	= "mem",
+	[PM_SUSPEND_DISK]	= "disk",
+	NULL,
+};
+
+
 /**
  *	enter_state - Do common work of entering low-power state.
  *	@state:		pm_state structure for state we're entering.
@@ -293,7 +143,6 @@ static void suspend_finish(u32 state)
 static int enter_state(u32 state)
 {
 	int error;
-	struct pm_state * s = &pm_states[state];
 
 	if (down_trylock(&pm_sem))
 		return -EBUSY;
@@ -304,12 +153,17 @@ static int enter_state(u32 state)
 		goto Unlock;
 	}
 
-	pr_debug("PM: Preparing system for suspend.\n");
+	if (state == PM_SUSPEND_DISK) {
+		error = pm_suspend_disk();
+		goto Unlock;
+	}
+
+	pr_debug("PM: Preparing system for suspend\n");
 	if ((error = suspend_prepare(state)))
 		goto Unlock;
 
 	pr_debug("PM: Entering state.\n");
-	error = s->fn();
+	error = suspend_enter(state);
 
 	pr_debug("PM: Finishing up.\n");
 	suspend_finish(state);
@@ -335,138 +189,10 @@ int pm_suspend(u32 state)
 }
 
 
-/**
- *	pm_resume - Resume from a saved image.
- *
- *	Called as a late_initcall (so all devices are discovered and 
- *	initialized), we call swsusp to see if we have a saved image or not.
- *	If so, we quiesce devices, the restore the saved image. We will 
- *	return above (in pm_suspend_disk() ) if everything goes well. 
- *	Otherwise, we fail gracefully and return to the normally 
- *	scheduled program.
- *
- */
-
-static int pm_resume(void)
-{
-	int error;
-
-	if (!have_swsusp)
-		return 0;
-
-	pr_debug("PM: Reading swsusp image.\n");
-
-	if ((error = swsusp_read()))
-		goto Done;
-
-	pr_debug("PM: Preparing system for restore.\n");
-
-	if ((error = suspend_prepare(PM_SUSPEND_DISK)))
-		goto Free;
-
-	pr_debug("PM: Restoring saved image.\n");
-	swsusp_restore();
-
-	pr_debug("PM: Restore failed, recovering.n");
-	suspend_finish(PM_SUSPEND_DISK);
- Free:
-	swsusp_free();
- Done:
-	pr_debug("PM: Resume from disk failed.\n");
-	return 0;
-}
-
-late_initcall(pm_resume);
-
 
 decl_subsys(power,NULL,NULL);
 
 
-#define power_attr(_name) \
-static struct subsys_attribute _name##_attr = {	\
-	.attr	= {				\
-		.name = __stringify(_name),	\
-		.mode = 0644,			\
-	},					\
-	.show	= _name##_show,			\
-	.store	= _name##_store,		\
-}
-
-
-static char * pm_disk_modes[] = {
-	[PM_DISK_FIRMWARE]	= "firmware",
-	[PM_DISK_PLATFORM]	= "platform",
-	[PM_DISK_SHUTDOWN]	= "shutdown",
-	[PM_DISK_REBOOT]	= "reboot",
-};
-
-/**
- *	disk - Control suspend-to-disk mode
- *
- *	Suspend-to-disk can be handled in several ways. The greatest 
- *	distinction is who writes memory to disk - the firmware or the OS.
- *	If the firmware does it, we assume that it also handles suspending 
- *	the system.
- *	If the OS does it, then we have three options for putting the system
- *	to sleep - using the platform driver (e.g. ACPI or other PM registers),
- *	powering off the system or rebooting the system (for testing). 
- *
- *	The system will support either 'firmware' or 'platform', and that is
- *	known a priori (and encoded in pm_ops). But, the user may choose
- *	'shutdown' or 'reboot' as alternatives.
- *
- *	show() will display what the mode is currently set to. 
- *	store() will accept one of
- *
- *	'firmware'
- *	'platform'
- *	'shutdown'
- *	'reboot'
- *
- *	It will only change to 'firmware' or 'platform' if the system
- *	supports it (as determined from pm_ops->pm_disk_mode).
- */
-
-static ssize_t disk_show(struct subsystem * subsys, char * buf)
-{
-	return sprintf(buf,"%s\n",pm_disk_modes[pm_disk_mode]);
-}
-
-
-static ssize_t disk_store(struct subsystem * s, const char * buf, size_t n)
-{
-	int error = 0;
-	int i;
-	u32 mode = 0;
-
-	down(&pm_sem);
-	for (i = PM_DISK_FIRMWARE; i < PM_DISK_MAX; i++) {
-		if (!strcmp(buf,pm_disk_modes[i])) {
-			mode = i;
-			break;
-		}
-	}
-	if (mode) {
-		if (mode == PM_DISK_SHUTDOWN || mode == PM_DISK_REBOOT)
-			pm_disk_mode = mode;
-		else {
-			if (pm_ops && pm_ops->enter && 
-			    (mode == pm_ops->pm_disk_mode))
-				pm_disk_mode = mode;
-			else
-				error = -EINVAL;
-		}
-	} else
-		error = -EINVAL;
-
-	pr_debug("PM: suspend-to-disk mode set to '%s'\n",
-		 pm_disk_modes[mode]);
-	up(&pm_sem);
-	return error ? error : n;
-}
-
-power_attr(disk);
-
 /**
  *	state - control system power state.
  *
@@ -480,27 +206,28 @@ power_attr(disk);
 
 static ssize_t state_show(struct subsystem * subsys, char * buf)
 {
-	struct pm_state * state;
+	int i;
 	char * s = buf;
 
-	for (state = &pm_states[0]; state->name; state++)
-		s += sprintf(s,"%s ",state->name);
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (pm_states[i])
+			s += sprintf(s,"%s ",pm_states[i]);
+	}
 	s += sprintf(s,"\n");
 	return (s - buf);
 }
 
 static ssize_t state_store(struct subsystem * subsys, const char * buf, size_t n)
 {
-	u32 state;
-	struct pm_state * s;
+	u32 state = PM_SUSPEND_STANDBY;
+	char ** s;
 	int error;
 
-	for (state = 0; state < PM_SUSPEND_MAX; state++) {
-		s = &pm_states[state];
-		if (s->name && !strcmp(buf,s->name))
+	for (s = &pm_states[state]; *s; s++, state++) {
+		if (!strcmp(buf,*s))
 			break;
 	}
-	if (s)
+	if (*s)
 		error = enter_state(state);
 	else
 		error = -EINVAL;
@@ -511,7 +238,6 @@ power_attr(state);
 
 static struct attribute * g[] = {
 	&state_attr.attr,
-	&disk_attr.attr,
 	NULL,
 };
 
@@ -520,7 +246,7 @@ static struct attribute_group attr_group = {
 };
 
 
-static int pm_init(void)
+static int __init pm_init(void)
 {
 	int error = subsystem_register(&power_subsys);
 	if (!error)

kernel/power/power.h

@@ -10,34 +10,27 @@
 
 
 #ifdef CONFIG_SOFTWARE_SUSPEND
-extern int swsusp_save(void);
-extern int swsusp_write(void);
-extern int swsusp_read(void);
-extern int swsusp_restore(void);
-extern int swsusp_free(void);
+extern int pm_suspend_disk(void);
+
 #else
-static inline int swsusp_save(void) 
-{
-	return 0;
-}
-static inline int swsusp_write(void)
+static inline int pm_suspend_disk(void)
 {
-	return 0;
-}
-static inline int swsusp_read(void)
-{
-	return 0;
-}
-static inline int swsusp_restore(void)
-{
-	return 0;
-}
-static inline int swsusp_free(void)
-{
-	return 0;
+	return -EPERM;
 }
 #endif
 
+extern struct semaphore pm_sem;
+#define power_attr(_name) \
+static struct subsys_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = 0644,			\
+	},					\
+	.show	= _name##_show,			\
+	.store	= _name##_store,		\
+}
+
+extern struct subsystem power_subsys;
 
 extern int freeze_processes(void);
 extern void thaw_processes(void);

kernel/power/swsusp.c

@@ -34,38 +34,21 @@
  * For TODOs,FIXMEs also look in Documentation/swsusp.txt
  */
 
-#include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/bio.h>
 #include <linux/suspend.h>
-#include <linux/smp_lock.h>
-#include <linux/file.h>
-#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>
-#include <linux/major.h>
-#include <linux/swap.h>
-#include <linux/pm.h>
 #include <linux/device.h>
-#include <linux/buffer_head.h>
 #include <linux/swapops.h>
 #include <linux/bootmem.h>
 
-#include <asm/uaccess.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
-#include <asm/io.h>
 
 #include "power.h"
 
-unsigned char software_suspend_enabled = 1;
+
+extern int swsusp_arch_suspend(int resume);
 
 #define __ADDRESS(x)  ((unsigned long) phys_to_virt(x))
 #define ADDRESS(x) __ADDRESS((x) << PAGE_SHIFT)
@@ -76,9 +59,6 @@ extern char __nosave_begin, __nosave_end;
 
 extern int is_head_of_free_region(struct page *);
 
-/* Locks */
-spinlock_t suspend_pagedir_lock __nosavedata = SPIN_LOCK_UNLOCKED;
-
 /* Variables to be preserved over suspend */
 static int pagedir_order_check;
 static int nr_copy_pages_check;
@@ -488,21 +468,30 @@ static int suspend_prepare_image(void)
 	return 0;
 }
 
+
+/**
+ *	suspend_save_image - Prepare and write saved image to swap.
+ *
+ *	IRQs are re-enabled here so we can resume devices and safely write
+ *	to the swap devices. We disable them again before we leave.
+ *
+ *	The second lock_swapdevices() will unlock ignored swap devices since
+ *	writing is finished.
+ *	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 suspend_save_image(void)
 {
 	int error;
-
+	local_irq_enable();
 	device_resume();
-
 	lock_swapdevices();
 	error = write_suspend_image();
-	lock_swapdevices();	/* This will unlock ignored swap devices since writing is finished */
-
-	/* 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.)
-	 */
+	lock_swapdevices();
+	local_irq_disable();
 	return error;
 }
 
@@ -510,66 +499,49 @@ static int suspend_save_image(void)
  * Magic happens here
  */
 
-void do_magic_resume_1(void)
-{
-	barrier();
-	mb();
-	spin_lock_irq(&suspend_pagedir_lock);	/* Done to disable interrupts */ 
-	PRINTK( "Waiting for DMAs to settle down...\n");
-	/* We do not want some readahead with DMA to corrupt our memory, right?
-	   Do it with disabled interrupts for best effect. That way, if some
-	   driver scheduled DMA, we have good chance for DMA to finish ;-). */
-	mdelay(1000);
-}
-
-void do_magic_resume_2(void)
+int swsusp_resume(void)
 {
 	BUG_ON (nr_copy_pages_check != nr_copy_pages);
 	BUG_ON (pagedir_order_check != pagedir_order);
 	
 	/* Even mappings of "global" things (vmalloc) need to be fixed */
 	__flush_tlb_global();
-	spin_unlock_irq(&suspend_pagedir_lock);
+	return 0;
 }
 
-/* do_magic() is implemented in arch/?/kernel/suspend_asm.S, and basically does:
+/* swsusp_arch_suspend() is implemented in arch/?/power/swsusp.S,
+   and basically does:
 
 	if (!resume) {
-		do_magic_suspend_1();
 		save_processor_state();
 		SAVE_REGISTERS
-		do_magic_suspend_2();
+		swsusp_suspend();
 		return;
 	}
 	GO_TO_SWAPPER_PAGE_TABLES
-	do_magic_resume_1();
 	COPY_PAGES_BACK
 	RESTORE_REGISTERS
 	restore_processor_state();
-	do_magic_resume_2();
+	swsusp_resume();
 
  */
 
-void do_magic_suspend_1(void)
-{
-	mb();
-	barrier();
-	spin_lock_irq(&suspend_pagedir_lock);
-}
 
-int do_magic_suspend_2(void)
+int swsusp_suspend(void)
 {
-	int is_problem;
+	int error;
 	read_swapfiles();
-	is_problem = suspend_prepare_image();
-	spin_unlock_irq(&suspend_pagedir_lock);
-	if (!is_problem)
-		return suspend_save_image();
-	printk(KERN_EMERG "%sSuspend failed, trying to recover...\n", name_suspend);
-	barrier();
-	mb();
-	mdelay(1000);
-	return -EFAULT;
+	error = suspend_prepare_image();
+	if (!error)
+		error = suspend_save_image();
+	if (error) {
+		printk(KERN_EMERG "%sSuspend failed, trying to recover...\n",
+		       name_suspend);
+		barrier();
+		mb();
+		mdelay(1000);
+	}
+	return error;
 }
 
 /* More restore stuff */
@@ -701,61 +673,146 @@ static int __init sanity_check(struct suspend_header *sh)
 	return 0;
 }
 
-static int __init bdev_read_page(struct block_device *bdev, 
-				 long pos, void *buf)
+static struct block_device * resume_bdev;
+
+
+/**
+ *	Using bio to read from swap.
+ *	This code requires a bit more work than just using buffer heads
+ *	but, it is the recommended way for 2.5/2.6.
+ *	The following are to signal the beginning and end of I/O. Bios
+ *	finish asynchronously, while we want them to happen synchronously.
+ *	A simple atomic_t, and a wait loop take care of this problem.
+ */
+
+static atomic_t io_done = ATOMIC_INIT(0);
+
+static void start_io(void)
 {
-	struct buffer_head *bh;
-	BUG_ON (pos%PAGE_SIZE);
-	bh = __bread(bdev, pos/PAGE_SIZE, PAGE_SIZE);
-	if (!bh || (!bh->b_data)) {
-		return -1;
-	}
-	memcpy(buf, bh->b_data, PAGE_SIZE);	/* FIXME: may need kmap() */
-	BUG_ON(!buffer_uptodate(bh));
-	brelse(bh);
+	atomic_set(&io_done,1);
+}
+
+static int end_io(struct bio * bio, unsigned int num, int err)
+{
+	atomic_set(&io_done,0);
 	return 0;
-} 
+}
+
+static void wait_io(void)
+{
+	blk_run_queues();
+	while(atomic_read(&io_done))
+		io_schedule();
+}
+
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@off	physical offset of page.
+ *	@page:	page we're reading or writing.
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're writing, make sure the page is marked as dirty.
+ *	Then submit it and wait.
+ */
+
+static int submit(int rw, pgoff_t page_off, void * page)
+{
+	int error = 0;
+	struct bio * bio;
+
+	bio = bio_alloc(GFP_ATOMIC,1);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio_get(bio);
+	bio->bi_bdev = resume_bdev;
+	bio->bi_end_io = end_io;
+
+	if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk("ERROR: adding page to bio at %ld\n",page_off);
+		error = -EFAULT;
+		goto Done;
+	}
+
+	if (rw == WRITE)
+		bio_set_pages_dirty(bio);
+	start_io();
+	submit_bio(rw,bio);
+	wait_io();
+ Done:
+	bio_put(bio);
+	return error;
+}
+
+static int
+read_page(pgoff_t page_off, void * page)
+{
+	return submit(READ,page_off,page);
+}
+
+static int
+write_page(pgoff_t page_off, void * page)
+{
+	return submit(WRITE,page_off,page);
+}
+
 
 extern dev_t __init name_to_dev_t(const char *line);
 
-static int __init read_suspend_image(struct block_device *bdev, 
-				     union diskpage *cur)
+
+#define next_entry(diskpage)	diskpage->link.next
+
+static int __init read_suspend_image(void)
 {
 	swp_entry_t next;
 	int i, nr_pgdir_pages;
+	union diskpage *cur;
+	int error = 0;
 
-#define PREPARENEXT \
-	{	next = cur->link.next; \
-		next.val = swp_offset(next) * PAGE_SIZE; \
-        }
-
-	if (bdev_read_page(bdev, 0, cur)) return -EIO;
+	cur = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
+	if (!cur)
+		return -ENOMEM;
 
-	if ((!memcmp("SWAP-SPACE",cur->swh.magic.magic,10)) ||
-	    (!memcmp("SWAPSPACE2",cur->swh.magic.magic,10))) {
-		printk(KERN_ERR "%sThis is normal swap space\n", name_resume );
-		return -EINVAL;
-	}
+	if ((error = read_page(0, cur)))
+		goto Done;
 
-	PREPARENEXT; /* We have to read next position before we overwrite it */
+	/*
+	 * We have to read next position before we overwrite it
+	 */
+	next = next_entry(cur);
 
 	if (!memcmp("S1",cur->swh.magic.magic,2))
 		memcpy(cur->swh.magic.magic,"SWAP-SPACE",10);
 	else if (!memcmp("S2",cur->swh.magic.magic,2))
 		memcpy(cur->swh.magic.magic,"SWAPSPACE2",10);
-	else {
-		printk("swsusp: %s: Unable to find suspended-data signature (%.10s - misspelled?\n", 
-			name_resume, cur->swh.magic.magic);
-		return -EFAULT;
+	else if ((!memcmp("SWAP-SPACE",cur->swh.magic.magic,10)) ||
+		 (!memcmp("SWAPSPACE2",cur->swh.magic.magic,10))) {
+		printk(KERN_ERR "swsusp: Partition is normal swap space\n");
+		error = -EINVAL;
+		goto Done;
+	} else {
+		printk(KERN_ERR "swsusp: Invalid partition type.\n");
+		error = -EINVAL;
+		goto Done;
 	}
 
+	/*
+	 * Reset swap signature now.
+	 */
+	if ((error = write_page(0,cur)))
+		goto Done;
+
 	printk( "%sSignature found, resuming\n", name_resume );
 	MDELAY(1000);
 
-	if (bdev_read_page(bdev, next.val, cur)) return -EIO;
-	if (sanity_check(&cur->sh)) 	/* Is this same machine? */	
-		return -EPERM;
-	PREPARENEXT;
+	if ((error = read_page(swp_offset(next), cur)))
+		goto Done;
+ 	/* Is this same machine? */
+	if ((error = sanity_check(&cur->sh)))
+		goto Done;
+	next = next_entry(cur);
 
 	pagedir_save = cur->sh.suspend_pagedir;
 	nr_copy_pages = cur->sh.num_pbes;
@@ -763,8 +820,10 @@ static int __init read_suspend_image(struct block_device *bdev,
 	pagedir_order = get_bitmask_order(nr_pgdir_pages);
 
 	pagedir_nosave = (suspend_pagedir_t *)__get_free_pages(GFP_ATOMIC, pagedir_order);
-	if (!pagedir_nosave)
-		return -ENOMEM;
+	if (!pagedir_nosave) {
+		error = -ENOMEM;
+		goto Done;
+	}
 
 	PRINTK( "%sReading pagedir, ", name_resume );
 
@@ -772,15 +831,17 @@ static int __init read_suspend_image(struct block_device *bdev,
 	for (i=nr_pgdir_pages-1; i>=0; i--) {
 		BUG_ON (!next.val);
 		cur = (union diskpage *)((char *) pagedir_nosave)+i;
-		if (bdev_read_page(bdev, next.val, cur)) return -EIO;
-		PREPARENEXT;
+		error = read_page(swp_offset(next), cur);
+		if (error)
+			goto FreePagedir;
+		next = next_entry(cur);
 	}
 	BUG_ON (next.val);
 
-	if (relocate_pagedir())
-		return -ENOMEM;
-	if (check_pagedir())
-		return -ENOMEM;
+	if ((error = relocate_pagedir()))
+		goto FreePagedir;
+	if ((error = check_pagedir()))
+		goto FreePagedir;
 
 	printk( "Reading image data (%d pages): ", nr_copy_pages );
 	for(i=0; i < nr_copy_pages; i++) {
@@ -789,11 +850,18 @@ static int __init read_suspend_image(struct block_device *bdev,
 			printk( "." );
 		/* You do not need to check for overlaps...
 		   ... check_pagedir already did this work */
-		if (bdev_read_page(bdev, swp_offset(swap_address) * PAGE_SIZE, (char *)((pagedir_nosave+i)->address)))
-			return -EIO;
+		error = read_page(swp_offset(swap_address),
+				  (char *)((pagedir_nosave+i)->address));
+		if (error)
+			goto FreePagedir;
 	}
 	printk( "|\n" );
-	return 0;
+ Done:
+	free_page((unsigned long)cur);
+	return error;
+ FreePagedir:
+	free_pages((unsigned long)pagedir_nosave,pagedir_order);
+	goto Done;
 }
 
 /**
@@ -806,24 +874,23 @@ int swsusp_save(void)
 	printk("swsusp is not supported with high- or discontig-mem.\n");
 	return -EPERM;
 #endif
-	return 0;
+	return arch_prepare_suspend();
 }
 
 
 /**
  *	swsusp_write - Write saved memory image to swap.
  *
- *	do_magic(0) returns after system is resumed.
+ *	swsusp_arch_suspend(0) returns after system is resumed.
  *
- *	do_magic() copies all "used" memory to "free" memory, then
- *	unsuspends all device drivers, and writes memory to disk
+ *	swsusp_arch_suspend() copies all "used" memory to "free" memory,
+ *	then unsuspends all device drivers, and writes memory to disk
  *	using normal kernel mechanism.
  */
 
 int swsusp_write(void)
 {
-	arch_prepare_suspend();
-	return do_magic(0);
+	return swsusp_arch_suspend(0);
 }
 
 
@@ -833,7 +900,6 @@ int swsusp_write(void)
 
 int __init swsusp_read(void)
 {
-	union diskpage *cur;
 	int error;
 	char b[BDEVNAME_SIZE];
 
@@ -844,19 +910,13 @@ int __init swsusp_read(void)
 	printk("swsusp: Resume From Partition: %s, Device: %s\n", 
 	       resume_file, __bdevname(resume_device, b));
 
-	cur = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
-	if (cur) {
-		struct block_device *bdev;
-		bdev = open_by_devnum(resume_device, FMODE_READ, BDEV_RAW);
-		if (!IS_ERR(bdev)) {
-			set_blocksize(bdev, PAGE_SIZE);
-			error = read_suspend_image(bdev, cur);
-			blkdev_put(bdev, BDEV_RAW);
-		} else
-			error = PTR_ERR(bdev);
-		free_page((unsigned long)cur);
+	resume_bdev = open_by_devnum(resume_device, FMODE_READ, BDEV_RAW);
+	if (!IS_ERR(resume_bdev)) {
+		set_blocksize(resume_bdev, PAGE_SIZE);
+		error = read_suspend_image();
+		blkdev_put(resume_bdev, BDEV_RAW);
 	} else
-		error = -ENOMEM;
+		error = PTR_ERR(resume_bdev);
 
 	if (!error)
 		PRINTK("Reading resume file was successful\n");
@@ -873,7 +933,7 @@ int __init swsusp_read(void)
 
 int __init swsusp_restore(void)
 {
-	return do_magic(1);
+	return swsusp_arch_suspend(1);
 }
 
 
@@ -885,13 +945,20 @@ int swsusp_free(void)
 {
 	PRINTK( "Freeing prev allocated pagedir\n" );
 	free_suspend_pagedir((unsigned long) pagedir_save);
-
-	PRINTK( "Fixing swap signatures... " );
-	mark_swapfiles(((swp_entry_t) {0}), MARK_SWAP_RESUME);
-	PRINTK( "ok\n" );
 	return 0;
 }
 
+
+int software_suspend(void)
+{
+	struct pm_ops swsusp_ops = {
+		.pm_disk_mode	= PM_DISK_SHUTDOWN,
+	};
+
+	pm_set_ops(&swsusp_ops);
+	return pm_suspend(PM_SUSPEND_DISK);
+}
+
 static int __init resume_setup(char *str)
 {
 	if (strlen(str))

kernel/sys.c

@@ -456,7 +456,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
 
 #ifdef CONFIG_SOFTWARE_SUSPEND
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
-		if (!pm_suspend(PM_SUSPEND_DISK))
+		if (!software_suspend())
 			break;
 		do_exit(0);
 		break;